{ "best_metric": 1.0423674583435059, "best_model_checkpoint": "ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v7/checkpoint-60155", "epoch": 30.0, "global_step": 360930, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 3.2e-07, "loss": 0.8841, "step": 10 }, { "epoch": 0.0, "learning_rate": 7.2e-07, "loss": 0.8432, "step": 20 }, { "epoch": 0.0, "learning_rate": 1.12e-06, "loss": 0.8834, "step": 30 }, { "epoch": 0.0, "learning_rate": 1.5199999999999998e-06, "loss": 0.8489, "step": 40 }, { "epoch": 0.0, "learning_rate": 1.8799999999999998e-06, "loss": 0.839, "step": 50 }, { "epoch": 0.0, "learning_rate": 2.2799999999999998e-06, "loss": 0.9517, "step": 60 }, { "epoch": 0.01, "learning_rate": 2.64e-06, "loss": 0.9002, "step": 70 }, { "epoch": 0.01, "learning_rate": 3.0399999999999997e-06, "loss": 0.8492, "step": 80 }, { "epoch": 0.01, "learning_rate": 3.4399999999999997e-06, "loss": 0.8241, "step": 90 }, { "epoch": 0.01, "learning_rate": 3.84e-06, "loss": 0.8406, "step": 100 }, { "epoch": 0.01, "learning_rate": 3.9999334866834795e-06, "loss": 0.9167, "step": 110 }, { "epoch": 0.01, "learning_rate": 3.999822631155946e-06, "loss": 0.8127, "step": 120 }, { "epoch": 0.01, "learning_rate": 3.999711775628412e-06, "loss": 0.8258, "step": 130 }, { "epoch": 0.01, "learning_rate": 3.999600920100879e-06, "loss": 0.7762, "step": 140 }, { "epoch": 0.01, "learning_rate": 3.999490064573345e-06, "loss": 0.8977, "step": 150 }, { "epoch": 0.01, "learning_rate": 3.9993792090458106e-06, "loss": 0.8884, "step": 160 }, { "epoch": 0.01, "learning_rate": 3.999268353518277e-06, "loss": 0.8073, "step": 170 }, { "epoch": 0.01, "learning_rate": 3.999157497990743e-06, "loss": 0.8521, "step": 180 }, { "epoch": 0.02, "learning_rate": 3.999046642463209e-06, "loss": 0.7494, "step": 190 }, { "epoch": 0.02, "learning_rate": 3.998935786935676e-06, "loss": 0.8579, "step": 200 }, { "epoch": 0.02, "learning_rate": 3.9988249314081425e-06, "loss": 0.948, "step": 210 }, { "epoch": 0.02, "learning_rate": 3.998714075880608e-06, "loss": 0.8574, "step": 220 }, { "epoch": 0.02, "learning_rate": 3.998603220353075e-06, "loss": 0.8869, "step": 230 }, { "epoch": 0.02, "learning_rate": 3.998492364825541e-06, "loss": 0.87, "step": 240 }, { "epoch": 0.02, "learning_rate": 3.998381509298008e-06, "loss": 0.854, "step": 250 }, { "epoch": 0.02, "learning_rate": 3.9982706537704735e-06, "loss": 0.8824, "step": 260 }, { "epoch": 0.02, "learning_rate": 3.998159798242939e-06, "loss": 0.8575, "step": 270 }, { "epoch": 0.02, "learning_rate": 3.998048942715406e-06, "loss": 0.8267, "step": 280 }, { "epoch": 0.02, "learning_rate": 3.997938087187872e-06, "loss": 0.8458, "step": 290 }, { "epoch": 0.02, "learning_rate": 3.997827231660339e-06, "loss": 0.8428, "step": 300 }, { "epoch": 0.03, "learning_rate": 3.9977163761328046e-06, "loss": 0.8988, "step": 310 }, { "epoch": 0.03, "learning_rate": 3.9976055206052704e-06, "loss": 0.9388, "step": 320 }, { "epoch": 0.03, "learning_rate": 3.997494665077737e-06, "loss": 0.8441, "step": 330 }, { "epoch": 0.03, "learning_rate": 3.997383809550204e-06, "loss": 0.8614, "step": 340 }, { "epoch": 0.03, "learning_rate": 3.99727295402267e-06, "loss": 0.8557, "step": 350 }, { "epoch": 0.03, "learning_rate": 3.9971620984951365e-06, "loss": 0.9156, "step": 360 }, { "epoch": 0.03, "learning_rate": 3.997051242967602e-06, "loss": 0.8262, "step": 370 }, { "epoch": 0.03, "learning_rate": 3.996940387440069e-06, "loss": 0.8898, "step": 380 }, { "epoch": 0.03, "learning_rate": 3.996829531912535e-06, "loss": 0.88, "step": 390 }, { "epoch": 0.03, "learning_rate": 3.996718676385001e-06, "loss": 0.8159, "step": 400 }, { "epoch": 0.03, "learning_rate": 3.9966078208574675e-06, "loss": 0.895, "step": 410 }, { "epoch": 0.03, "learning_rate": 3.996496965329933e-06, "loss": 0.8162, "step": 420 }, { "epoch": 0.04, "learning_rate": 3.996386109802399e-06, "loss": 0.9011, "step": 430 }, { "epoch": 0.04, "learning_rate": 3.996275254274866e-06, "loss": 0.8777, "step": 440 }, { "epoch": 0.04, "learning_rate": 3.996164398747333e-06, "loss": 0.7995, "step": 450 }, { "epoch": 0.04, "learning_rate": 3.996053543219799e-06, "loss": 0.8607, "step": 460 }, { "epoch": 0.04, "learning_rate": 3.995942687692265e-06, "loss": 0.8919, "step": 470 }, { "epoch": 0.04, "learning_rate": 3.995831832164731e-06, "loss": 0.8256, "step": 480 }, { "epoch": 0.04, "learning_rate": 3.995720976637198e-06, "loss": 0.8305, "step": 490 }, { "epoch": 0.04, "learning_rate": 3.995610121109664e-06, "loss": 0.7989, "step": 500 }, { "epoch": 0.04, "learning_rate": 3.99549926558213e-06, "loss": 0.864, "step": 510 }, { "epoch": 0.04, "learning_rate": 3.995388410054596e-06, "loss": 0.8453, "step": 520 }, { "epoch": 0.04, "learning_rate": 3.995277554527062e-06, "loss": 0.8659, "step": 530 }, { "epoch": 0.04, "learning_rate": 3.995166698999529e-06, "loss": 0.7478, "step": 540 }, { "epoch": 0.05, "learning_rate": 3.995055843471995e-06, "loss": 0.8098, "step": 550 }, { "epoch": 0.05, "learning_rate": 3.994944987944461e-06, "loss": 0.8636, "step": 560 }, { "epoch": 0.05, "learning_rate": 3.994834132416927e-06, "loss": 0.8288, "step": 570 }, { "epoch": 0.05, "learning_rate": 3.994723276889394e-06, "loss": 0.9288, "step": 580 }, { "epoch": 0.05, "learning_rate": 3.99461242136186e-06, "loss": 0.8789, "step": 590 }, { "epoch": 0.05, "learning_rate": 3.994501565834327e-06, "loss": 0.7641, "step": 600 }, { "epoch": 0.05, "learning_rate": 3.994390710306793e-06, "loss": 0.8073, "step": 610 }, { "epoch": 0.05, "learning_rate": 3.994279854779259e-06, "loss": 0.8683, "step": 620 }, { "epoch": 0.05, "learning_rate": 3.994168999251725e-06, "loss": 0.8435, "step": 630 }, { "epoch": 0.05, "learning_rate": 3.994058143724191e-06, "loss": 0.859, "step": 640 }, { "epoch": 0.05, "learning_rate": 3.993947288196658e-06, "loss": 0.8215, "step": 650 }, { "epoch": 0.05, "learning_rate": 3.993836432669124e-06, "loss": 0.9012, "step": 660 }, { "epoch": 0.06, "learning_rate": 3.9937255771415895e-06, "loss": 0.8184, "step": 670 }, { "epoch": 0.06, "learning_rate": 3.993614721614056e-06, "loss": 0.728, "step": 680 }, { "epoch": 0.06, "learning_rate": 3.993503866086522e-06, "loss": 0.907, "step": 690 }, { "epoch": 0.06, "learning_rate": 3.993393010558989e-06, "loss": 0.8221, "step": 700 }, { "epoch": 0.06, "learning_rate": 3.9932821550314555e-06, "loss": 0.8552, "step": 710 }, { "epoch": 0.06, "learning_rate": 3.993171299503921e-06, "loss": 0.7937, "step": 720 }, { "epoch": 0.06, "learning_rate": 3.993060443976388e-06, "loss": 0.8798, "step": 730 }, { "epoch": 0.06, "learning_rate": 3.992949588448854e-06, "loss": 0.8349, "step": 740 }, { "epoch": 0.06, "learning_rate": 3.99283873292132e-06, "loss": 0.8245, "step": 750 }, { "epoch": 0.06, "learning_rate": 3.992727877393787e-06, "loss": 0.9399, "step": 760 }, { "epoch": 0.06, "learning_rate": 3.9926170218662525e-06, "loss": 0.8533, "step": 770 }, { "epoch": 0.06, "learning_rate": 3.992506166338718e-06, "loss": 0.8281, "step": 780 }, { "epoch": 0.07, "learning_rate": 3.992395310811185e-06, "loss": 0.8484, "step": 790 }, { "epoch": 0.07, "learning_rate": 3.992284455283651e-06, "loss": 0.9329, "step": 800 }, { "epoch": 0.07, "learning_rate": 3.992173599756118e-06, "loss": 0.8094, "step": 810 }, { "epoch": 0.07, "learning_rate": 3.992062744228584e-06, "loss": 0.8483, "step": 820 }, { "epoch": 0.07, "learning_rate": 3.99195188870105e-06, "loss": 0.8191, "step": 830 }, { "epoch": 0.07, "learning_rate": 3.991841033173517e-06, "loss": 0.8224, "step": 840 }, { "epoch": 0.07, "learning_rate": 3.991730177645983e-06, "loss": 0.8584, "step": 850 }, { "epoch": 0.07, "learning_rate": 3.991619322118449e-06, "loss": 0.8338, "step": 860 }, { "epoch": 0.07, "learning_rate": 3.991508466590915e-06, "loss": 0.8362, "step": 870 }, { "epoch": 0.07, "learning_rate": 3.991397611063381e-06, "loss": 0.7893, "step": 880 }, { "epoch": 0.07, "learning_rate": 3.991286755535848e-06, "loss": 0.782, "step": 890 }, { "epoch": 0.07, "learning_rate": 3.991175900008314e-06, "loss": 0.8551, "step": 900 }, { "epoch": 0.08, "learning_rate": 3.99106504448078e-06, "loss": 0.9164, "step": 910 }, { "epoch": 0.08, "learning_rate": 3.9909541889532465e-06, "loss": 0.8145, "step": 920 }, { "epoch": 0.08, "learning_rate": 3.990843333425712e-06, "loss": 0.9329, "step": 930 }, { "epoch": 0.08, "learning_rate": 3.990732477898179e-06, "loss": 0.8256, "step": 940 }, { "epoch": 0.08, "learning_rate": 3.990621622370646e-06, "loss": 0.8934, "step": 950 }, { "epoch": 0.08, "learning_rate": 3.990510766843112e-06, "loss": 0.9546, "step": 960 }, { "epoch": 0.08, "learning_rate": 3.990399911315578e-06, "loss": 0.8546, "step": 970 }, { "epoch": 0.08, "learning_rate": 3.990289055788044e-06, "loss": 0.8761, "step": 980 }, { "epoch": 0.08, "learning_rate": 3.99017820026051e-06, "loss": 0.8264, "step": 990 }, { "epoch": 0.08, "learning_rate": 3.990067344732977e-06, "loss": 0.8757, "step": 1000 }, { "epoch": 0.08, "learning_rate": 3.989956489205443e-06, "loss": 0.9084, "step": 1010 }, { "epoch": 0.08, "learning_rate": 3.9898456336779086e-06, "loss": 0.874, "step": 1020 }, { "epoch": 0.09, "learning_rate": 3.989734778150375e-06, "loss": 0.8852, "step": 1030 }, { "epoch": 0.09, "learning_rate": 3.989623922622841e-06, "loss": 0.8989, "step": 1040 }, { "epoch": 0.09, "learning_rate": 3.989513067095308e-06, "loss": 0.8606, "step": 1050 }, { "epoch": 0.09, "learning_rate": 3.989402211567774e-06, "loss": 0.9582, "step": 1060 }, { "epoch": 0.09, "learning_rate": 3.9892913560402405e-06, "loss": 0.8604, "step": 1070 }, { "epoch": 0.09, "learning_rate": 3.989180500512707e-06, "loss": 0.8468, "step": 1080 }, { "epoch": 0.09, "learning_rate": 3.989069644985173e-06, "loss": 0.8397, "step": 1090 }, { "epoch": 0.09, "learning_rate": 3.988958789457639e-06, "loss": 0.8, "step": 1100 }, { "epoch": 0.09, "learning_rate": 3.988847933930106e-06, "loss": 0.8341, "step": 1110 }, { "epoch": 0.09, "learning_rate": 3.9887370784025715e-06, "loss": 0.8398, "step": 1120 }, { "epoch": 0.09, "learning_rate": 3.988626222875037e-06, "loss": 0.8519, "step": 1130 }, { "epoch": 0.09, "learning_rate": 3.988515367347504e-06, "loss": 0.8056, "step": 1140 }, { "epoch": 0.1, "learning_rate": 3.98840451181997e-06, "loss": 0.828, "step": 1150 }, { "epoch": 0.1, "learning_rate": 3.988293656292437e-06, "loss": 0.8812, "step": 1160 }, { "epoch": 0.1, "learning_rate": 3.988182800764903e-06, "loss": 0.8536, "step": 1170 }, { "epoch": 0.1, "learning_rate": 3.988071945237369e-06, "loss": 0.8694, "step": 1180 }, { "epoch": 0.1, "learning_rate": 3.987961089709836e-06, "loss": 0.8437, "step": 1190 }, { "epoch": 0.1, "learning_rate": 3.987850234182302e-06, "loss": 0.842, "step": 1200 }, { "epoch": 0.1, "learning_rate": 3.987739378654768e-06, "loss": 0.8992, "step": 1210 }, { "epoch": 0.1, "learning_rate": 3.9876285231272345e-06, "loss": 0.8638, "step": 1220 }, { "epoch": 0.1, "learning_rate": 3.9875176675997e-06, "loss": 0.7511, "step": 1230 }, { "epoch": 0.1, "learning_rate": 3.987406812072167e-06, "loss": 0.7798, "step": 1240 }, { "epoch": 0.1, "learning_rate": 3.987295956544633e-06, "loss": 0.8571, "step": 1250 }, { "epoch": 0.1, "learning_rate": 3.987185101017099e-06, "loss": 0.9169, "step": 1260 }, { "epoch": 0.11, "learning_rate": 3.9870742454895655e-06, "loss": 0.9203, "step": 1270 }, { "epoch": 0.11, "learning_rate": 3.986963389962031e-06, "loss": 0.9162, "step": 1280 }, { "epoch": 0.11, "learning_rate": 3.986852534434498e-06, "loss": 0.8079, "step": 1290 }, { "epoch": 0.11, "learning_rate": 3.986741678906964e-06, "loss": 0.8533, "step": 1300 }, { "epoch": 0.11, "learning_rate": 3.986630823379431e-06, "loss": 0.8087, "step": 1310 }, { "epoch": 0.11, "learning_rate": 3.9865199678518974e-06, "loss": 0.8552, "step": 1320 }, { "epoch": 0.11, "learning_rate": 3.986409112324363e-06, "loss": 0.8456, "step": 1330 }, { "epoch": 0.11, "learning_rate": 3.986298256796829e-06, "loss": 0.8164, "step": 1340 }, { "epoch": 0.11, "learning_rate": 3.986187401269296e-06, "loss": 0.9147, "step": 1350 }, { "epoch": 0.11, "learning_rate": 3.986076545741762e-06, "loss": 0.9632, "step": 1360 }, { "epoch": 0.11, "learning_rate": 3.985965690214228e-06, "loss": 0.8699, "step": 1370 }, { "epoch": 0.11, "learning_rate": 3.985854834686694e-06, "loss": 0.8636, "step": 1380 }, { "epoch": 0.12, "learning_rate": 3.98574397915916e-06, "loss": 0.89, "step": 1390 }, { "epoch": 0.12, "learning_rate": 3.985633123631627e-06, "loss": 0.8773, "step": 1400 }, { "epoch": 0.12, "learning_rate": 3.985522268104093e-06, "loss": 0.9109, "step": 1410 }, { "epoch": 0.12, "learning_rate": 3.9854114125765595e-06, "loss": 0.9137, "step": 1420 }, { "epoch": 0.12, "learning_rate": 3.985300557049025e-06, "loss": 0.877, "step": 1430 }, { "epoch": 0.12, "learning_rate": 3.985189701521492e-06, "loss": 0.8599, "step": 1440 }, { "epoch": 0.12, "learning_rate": 3.985078845993958e-06, "loss": 0.8594, "step": 1450 }, { "epoch": 0.12, "learning_rate": 3.984967990466425e-06, "loss": 0.8484, "step": 1460 }, { "epoch": 0.12, "learning_rate": 3.984857134938891e-06, "loss": 0.7797, "step": 1470 }, { "epoch": 0.12, "learning_rate": 3.9847462794113565e-06, "loss": 0.8012, "step": 1480 }, { "epoch": 0.12, "learning_rate": 3.984635423883823e-06, "loss": 0.8094, "step": 1490 }, { "epoch": 0.12, "learning_rate": 3.984524568356289e-06, "loss": 0.773, "step": 1500 }, { "epoch": 0.13, "learning_rate": 3.984413712828756e-06, "loss": 0.8408, "step": 1510 }, { "epoch": 0.13, "learning_rate": 3.984302857301222e-06, "loss": 0.8561, "step": 1520 }, { "epoch": 0.13, "learning_rate": 3.984192001773688e-06, "loss": 0.8044, "step": 1530 }, { "epoch": 0.13, "learning_rate": 3.984081146246154e-06, "loss": 0.8411, "step": 1540 }, { "epoch": 0.13, "learning_rate": 3.983970290718621e-06, "loss": 0.8872, "step": 1550 }, { "epoch": 0.13, "learning_rate": 3.983859435191087e-06, "loss": 0.8819, "step": 1560 }, { "epoch": 0.13, "learning_rate": 3.9837485796635535e-06, "loss": 0.8275, "step": 1570 }, { "epoch": 0.13, "learning_rate": 3.983637724136019e-06, "loss": 0.8235, "step": 1580 }, { "epoch": 0.13, "learning_rate": 3.983526868608486e-06, "loss": 0.8066, "step": 1590 }, { "epoch": 0.13, "learning_rate": 3.983416013080952e-06, "loss": 0.7707, "step": 1600 }, { "epoch": 0.13, "learning_rate": 3.983305157553418e-06, "loss": 0.869, "step": 1610 }, { "epoch": 0.13, "learning_rate": 3.983194302025885e-06, "loss": 0.7858, "step": 1620 }, { "epoch": 0.14, "learning_rate": 3.9830834464983505e-06, "loss": 0.8307, "step": 1630 }, { "epoch": 0.14, "learning_rate": 3.982972590970817e-06, "loss": 0.9118, "step": 1640 }, { "epoch": 0.14, "learning_rate": 3.982861735443283e-06, "loss": 0.8602, "step": 1650 }, { "epoch": 0.14, "learning_rate": 3.98275087991575e-06, "loss": 0.8875, "step": 1660 }, { "epoch": 0.14, "learning_rate": 3.982640024388216e-06, "loss": 0.8585, "step": 1670 }, { "epoch": 0.14, "learning_rate": 3.982529168860682e-06, "loss": 0.8771, "step": 1680 }, { "epoch": 0.14, "learning_rate": 3.982418313333148e-06, "loss": 0.7834, "step": 1690 }, { "epoch": 0.14, "learning_rate": 3.982307457805615e-06, "loss": 0.8329, "step": 1700 }, { "epoch": 0.14, "learning_rate": 3.982196602278081e-06, "loss": 0.8853, "step": 1710 }, { "epoch": 0.14, "learning_rate": 3.982085746750547e-06, "loss": 0.8251, "step": 1720 }, { "epoch": 0.14, "learning_rate": 3.9819748912230134e-06, "loss": 0.7985, "step": 1730 }, { "epoch": 0.14, "learning_rate": 3.981864035695479e-06, "loss": 0.8369, "step": 1740 }, { "epoch": 0.15, "learning_rate": 3.981753180167946e-06, "loss": 0.8654, "step": 1750 }, { "epoch": 0.15, "learning_rate": 3.981642324640412e-06, "loss": 0.9027, "step": 1760 }, { "epoch": 0.15, "learning_rate": 3.981531469112879e-06, "loss": 0.8781, "step": 1770 }, { "epoch": 0.15, "learning_rate": 3.9814206135853445e-06, "loss": 0.8436, "step": 1780 }, { "epoch": 0.15, "learning_rate": 3.981309758057811e-06, "loss": 0.8875, "step": 1790 }, { "epoch": 0.15, "learning_rate": 3.981198902530277e-06, "loss": 0.8365, "step": 1800 }, { "epoch": 0.15, "learning_rate": 3.981088047002744e-06, "loss": 0.8455, "step": 1810 }, { "epoch": 0.15, "learning_rate": 3.98097719147521e-06, "loss": 0.8343, "step": 1820 }, { "epoch": 0.15, "learning_rate": 3.980866335947676e-06, "loss": 0.8329, "step": 1830 }, { "epoch": 0.15, "learning_rate": 3.980755480420142e-06, "loss": 0.8222, "step": 1840 }, { "epoch": 0.15, "learning_rate": 3.980644624892608e-06, "loss": 0.8344, "step": 1850 }, { "epoch": 0.15, "learning_rate": 3.980533769365075e-06, "loss": 0.9569, "step": 1860 }, { "epoch": 0.16, "learning_rate": 3.980422913837541e-06, "loss": 0.8655, "step": 1870 }, { "epoch": 0.16, "learning_rate": 3.9803120583100074e-06, "loss": 0.8112, "step": 1880 }, { "epoch": 0.16, "learning_rate": 3.980201202782473e-06, "loss": 0.9265, "step": 1890 }, { "epoch": 0.16, "learning_rate": 3.98009034725494e-06, "loss": 0.84, "step": 1900 }, { "epoch": 0.16, "learning_rate": 3.979979491727406e-06, "loss": 0.867, "step": 1910 }, { "epoch": 0.16, "learning_rate": 3.979868636199873e-06, "loss": 0.8814, "step": 1920 }, { "epoch": 0.16, "learning_rate": 3.9797577806723385e-06, "loss": 0.8443, "step": 1930 }, { "epoch": 0.16, "learning_rate": 3.979646925144805e-06, "loss": 0.8518, "step": 1940 }, { "epoch": 0.16, "learning_rate": 3.979536069617271e-06, "loss": 0.8317, "step": 1950 }, { "epoch": 0.16, "learning_rate": 3.979425214089737e-06, "loss": 0.9085, "step": 1960 }, { "epoch": 0.16, "learning_rate": 3.979314358562204e-06, "loss": 0.8028, "step": 1970 }, { "epoch": 0.16, "learning_rate": 3.9792035030346695e-06, "loss": 0.7891, "step": 1980 }, { "epoch": 0.17, "learning_rate": 3.979092647507136e-06, "loss": 0.8749, "step": 1990 }, { "epoch": 0.17, "learning_rate": 3.978981791979602e-06, "loss": 0.8428, "step": 2000 }, { "epoch": 0.17, "learning_rate": 3.978870936452069e-06, "loss": 0.913, "step": 2010 }, { "epoch": 0.17, "learning_rate": 3.978760080924535e-06, "loss": 0.8512, "step": 2020 }, { "epoch": 0.17, "learning_rate": 3.9786492253970014e-06, "loss": 0.8795, "step": 2030 }, { "epoch": 0.17, "learning_rate": 3.978538369869467e-06, "loss": 0.8, "step": 2040 }, { "epoch": 0.17, "learning_rate": 3.978427514341934e-06, "loss": 0.9163, "step": 2050 }, { "epoch": 0.17, "learning_rate": 3.9783166588144e-06, "loss": 0.8933, "step": 2060 }, { "epoch": 0.17, "learning_rate": 3.978205803286866e-06, "loss": 0.8731, "step": 2070 }, { "epoch": 0.17, "learning_rate": 3.9780949477593325e-06, "loss": 0.9079, "step": 2080 }, { "epoch": 0.17, "learning_rate": 3.977984092231798e-06, "loss": 0.8495, "step": 2090 }, { "epoch": 0.17, "learning_rate": 3.977873236704265e-06, "loss": 0.8825, "step": 2100 }, { "epoch": 0.18, "learning_rate": 3.977762381176731e-06, "loss": 0.8883, "step": 2110 }, { "epoch": 0.18, "learning_rate": 3.977651525649198e-06, "loss": 0.8081, "step": 2120 }, { "epoch": 0.18, "learning_rate": 3.9775406701216635e-06, "loss": 0.7996, "step": 2130 }, { "epoch": 0.18, "learning_rate": 3.97742981459413e-06, "loss": 0.8239, "step": 2140 }, { "epoch": 0.18, "learning_rate": 3.977318959066596e-06, "loss": 0.7479, "step": 2150 }, { "epoch": 0.18, "learning_rate": 3.977208103539063e-06, "loss": 0.8367, "step": 2160 }, { "epoch": 0.18, "learning_rate": 3.977097248011529e-06, "loss": 0.7758, "step": 2170 }, { "epoch": 0.18, "learning_rate": 3.9769863924839954e-06, "loss": 0.8394, "step": 2180 }, { "epoch": 0.18, "learning_rate": 3.976875536956461e-06, "loss": 0.7761, "step": 2190 }, { "epoch": 0.18, "learning_rate": 3.976764681428927e-06, "loss": 0.8264, "step": 2200 }, { "epoch": 0.18, "learning_rate": 3.976653825901394e-06, "loss": 0.8648, "step": 2210 }, { "epoch": 0.18, "learning_rate": 3.97654297037386e-06, "loss": 0.8166, "step": 2220 }, { "epoch": 0.19, "learning_rate": 3.9764321148463265e-06, "loss": 0.8365, "step": 2230 }, { "epoch": 0.19, "learning_rate": 3.976321259318792e-06, "loss": 0.8431, "step": 2240 }, { "epoch": 0.19, "learning_rate": 3.976210403791259e-06, "loss": 0.8347, "step": 2250 }, { "epoch": 0.19, "learning_rate": 3.976099548263725e-06, "loss": 0.8732, "step": 2260 }, { "epoch": 0.19, "learning_rate": 3.975988692736192e-06, "loss": 0.8028, "step": 2270 }, { "epoch": 0.19, "learning_rate": 3.9758778372086576e-06, "loss": 0.8532, "step": 2280 }, { "epoch": 0.19, "learning_rate": 3.975766981681124e-06, "loss": 0.8774, "step": 2290 }, { "epoch": 0.19, "learning_rate": 3.97565612615359e-06, "loss": 0.8674, "step": 2300 }, { "epoch": 0.19, "learning_rate": 3.975545270626056e-06, "loss": 0.8336, "step": 2310 }, { "epoch": 0.19, "learning_rate": 3.975434415098523e-06, "loss": 0.8214, "step": 2320 }, { "epoch": 0.19, "learning_rate": 3.975323559570989e-06, "loss": 0.7922, "step": 2330 }, { "epoch": 0.19, "learning_rate": 3.975212704043455e-06, "loss": 0.8092, "step": 2340 }, { "epoch": 0.2, "learning_rate": 3.975101848515921e-06, "loss": 0.9117, "step": 2350 }, { "epoch": 0.2, "learning_rate": 3.975002078541141e-06, "loss": 0.9587, "step": 2360 }, { "epoch": 0.2, "learning_rate": 3.9748912230136075e-06, "loss": 0.7686, "step": 2370 }, { "epoch": 0.2, "learning_rate": 3.974780367486074e-06, "loss": 0.8586, "step": 2380 }, { "epoch": 0.2, "learning_rate": 3.97466951195854e-06, "loss": 0.8301, "step": 2390 }, { "epoch": 0.2, "learning_rate": 3.974558656431006e-06, "loss": 0.8572, "step": 2400 }, { "epoch": 0.2, "learning_rate": 3.974447800903473e-06, "loss": 0.8982, "step": 2410 }, { "epoch": 0.2, "learning_rate": 3.9743369453759385e-06, "loss": 0.8559, "step": 2420 }, { "epoch": 0.2, "learning_rate": 3.974226089848404e-06, "loss": 0.8997, "step": 2430 }, { "epoch": 0.2, "learning_rate": 3.974115234320871e-06, "loss": 0.8517, "step": 2440 }, { "epoch": 0.2, "learning_rate": 3.974004378793337e-06, "loss": 0.8525, "step": 2450 }, { "epoch": 0.2, "learning_rate": 3.973893523265804e-06, "loss": 0.9159, "step": 2460 }, { "epoch": 0.21, "learning_rate": 3.9737826677382696e-06, "loss": 0.8211, "step": 2470 }, { "epoch": 0.21, "learning_rate": 3.973671812210736e-06, "loss": 0.8457, "step": 2480 }, { "epoch": 0.21, "learning_rate": 3.973560956683202e-06, "loss": 0.8223, "step": 2490 }, { "epoch": 0.21, "learning_rate": 3.973450101155669e-06, "loss": 0.8166, "step": 2500 }, { "epoch": 0.21, "learning_rate": 3.973339245628135e-06, "loss": 0.8654, "step": 2510 }, { "epoch": 0.21, "learning_rate": 3.9732283901006015e-06, "loss": 0.823, "step": 2520 }, { "epoch": 0.21, "learning_rate": 3.973117534573067e-06, "loss": 0.7875, "step": 2530 }, { "epoch": 0.21, "learning_rate": 3.973006679045534e-06, "loss": 0.9064, "step": 2540 }, { "epoch": 0.21, "learning_rate": 3.972895823518e-06, "loss": 0.8536, "step": 2550 }, { "epoch": 0.21, "learning_rate": 3.972784967990466e-06, "loss": 0.8858, "step": 2560 }, { "epoch": 0.21, "learning_rate": 3.9726741124629325e-06, "loss": 0.8392, "step": 2570 }, { "epoch": 0.21, "learning_rate": 3.972563256935398e-06, "loss": 0.8669, "step": 2580 }, { "epoch": 0.22, "learning_rate": 3.972452401407865e-06, "loss": 0.8366, "step": 2590 }, { "epoch": 0.22, "learning_rate": 3.972341545880331e-06, "loss": 0.7952, "step": 2600 }, { "epoch": 0.22, "learning_rate": 3.972230690352798e-06, "loss": 0.8433, "step": 2610 }, { "epoch": 0.22, "learning_rate": 3.9721198348252636e-06, "loss": 0.7849, "step": 2620 }, { "epoch": 0.22, "learning_rate": 3.97200897929773e-06, "loss": 0.9062, "step": 2630 }, { "epoch": 0.22, "learning_rate": 3.971898123770196e-06, "loss": 0.8656, "step": 2640 }, { "epoch": 0.22, "learning_rate": 3.971787268242663e-06, "loss": 0.8109, "step": 2650 }, { "epoch": 0.22, "learning_rate": 3.971676412715129e-06, "loss": 0.8916, "step": 2660 }, { "epoch": 0.22, "learning_rate": 3.971565557187595e-06, "loss": 0.845, "step": 2670 }, { "epoch": 0.22, "learning_rate": 3.971454701660061e-06, "loss": 0.7932, "step": 2680 }, { "epoch": 0.22, "learning_rate": 3.971343846132527e-06, "loss": 0.8172, "step": 2690 }, { "epoch": 0.22, "learning_rate": 3.971244076157747e-06, "loss": 0.8942, "step": 2700 }, { "epoch": 0.23, "learning_rate": 3.9711332206302135e-06, "loss": 0.8713, "step": 2710 }, { "epoch": 0.23, "learning_rate": 3.97102236510268e-06, "loss": 0.86, "step": 2720 }, { "epoch": 0.23, "learning_rate": 3.970911509575146e-06, "loss": 0.8365, "step": 2730 }, { "epoch": 0.23, "learning_rate": 3.970800654047613e-06, "loss": 0.8427, "step": 2740 }, { "epoch": 0.23, "learning_rate": 3.970689798520079e-06, "loss": 0.7927, "step": 2750 }, { "epoch": 0.23, "learning_rate": 3.9705789429925445e-06, "loss": 0.8227, "step": 2760 }, { "epoch": 0.23, "learning_rate": 3.970468087465011e-06, "loss": 0.814, "step": 2770 }, { "epoch": 0.23, "learning_rate": 3.970357231937477e-06, "loss": 0.8459, "step": 2780 }, { "epoch": 0.23, "learning_rate": 3.970246376409944e-06, "loss": 0.7854, "step": 2790 }, { "epoch": 0.23, "learning_rate": 3.97013552088241e-06, "loss": 0.8624, "step": 2800 }, { "epoch": 0.23, "learning_rate": 3.9700246653548756e-06, "loss": 0.7989, "step": 2810 }, { "epoch": 0.23, "learning_rate": 3.969913809827342e-06, "loss": 0.8324, "step": 2820 }, { "epoch": 0.24, "learning_rate": 3.969802954299808e-06, "loss": 0.8442, "step": 2830 }, { "epoch": 0.24, "learning_rate": 3.969692098772275e-06, "loss": 0.8168, "step": 2840 }, { "epoch": 0.24, "learning_rate": 3.969581243244742e-06, "loss": 0.7884, "step": 2850 }, { "epoch": 0.24, "learning_rate": 3.9694703877172075e-06, "loss": 0.9066, "step": 2860 }, { "epoch": 0.24, "learning_rate": 3.969359532189674e-06, "loss": 0.848, "step": 2870 }, { "epoch": 0.24, "learning_rate": 3.96924867666214e-06, "loss": 0.8699, "step": 2880 }, { "epoch": 0.24, "learning_rate": 3.969137821134606e-06, "loss": 0.8092, "step": 2890 }, { "epoch": 0.24, "learning_rate": 3.969026965607073e-06, "loss": 0.8708, "step": 2900 }, { "epoch": 0.24, "learning_rate": 3.9689161100795385e-06, "loss": 0.9082, "step": 2910 }, { "epoch": 0.24, "learning_rate": 3.968805254552004e-06, "loss": 0.7711, "step": 2920 }, { "epoch": 0.24, "learning_rate": 3.968694399024471e-06, "loss": 0.8832, "step": 2930 }, { "epoch": 0.24, "learning_rate": 3.968583543496937e-06, "loss": 0.7737, "step": 2940 }, { "epoch": 0.25, "learning_rate": 3.968472687969404e-06, "loss": 0.8381, "step": 2950 }, { "epoch": 0.25, "learning_rate": 3.9683618324418704e-06, "loss": 0.8625, "step": 2960 }, { "epoch": 0.25, "learning_rate": 3.968250976914336e-06, "loss": 0.7862, "step": 2970 }, { "epoch": 0.25, "learning_rate": 3.968140121386803e-06, "loss": 0.8438, "step": 2980 }, { "epoch": 0.25, "learning_rate": 3.968029265859269e-06, "loss": 0.8287, "step": 2990 }, { "epoch": 0.25, "learning_rate": 3.967918410331735e-06, "loss": 0.8349, "step": 3000 }, { "epoch": 0.25, "learning_rate": 3.9678075548042015e-06, "loss": 0.8585, "step": 3010 }, { "epoch": 0.25, "learning_rate": 3.967696699276667e-06, "loss": 0.8291, "step": 3020 }, { "epoch": 0.25, "learning_rate": 3.967585843749133e-06, "loss": 0.7761, "step": 3030 }, { "epoch": 0.25, "learning_rate": 3.9674749882216e-06, "loss": 0.8458, "step": 3040 }, { "epoch": 0.25, "learning_rate": 3.967364132694066e-06, "loss": 0.8625, "step": 3050 }, { "epoch": 0.25, "learning_rate": 3.9672532771665325e-06, "loss": 0.9256, "step": 3060 }, { "epoch": 0.26, "learning_rate": 3.967142421638998e-06, "loss": 0.8721, "step": 3070 }, { "epoch": 0.26, "learning_rate": 3.967031566111465e-06, "loss": 0.8013, "step": 3080 }, { "epoch": 0.26, "learning_rate": 3.966920710583932e-06, "loss": 0.839, "step": 3090 }, { "epoch": 0.26, "learning_rate": 3.966809855056398e-06, "loss": 0.8775, "step": 3100 }, { "epoch": 0.26, "learning_rate": 3.966698999528864e-06, "loss": 0.9315, "step": 3110 }, { "epoch": 0.26, "learning_rate": 3.96658814400133e-06, "loss": 0.8564, "step": 3120 }, { "epoch": 0.26, "learning_rate": 3.966477288473796e-06, "loss": 0.8466, "step": 3130 }, { "epoch": 0.26, "learning_rate": 3.966366432946263e-06, "loss": 0.8279, "step": 3140 }, { "epoch": 0.26, "learning_rate": 3.966255577418729e-06, "loss": 0.8594, "step": 3150 }, { "epoch": 0.26, "learning_rate": 3.966144721891195e-06, "loss": 0.9081, "step": 3160 }, { "epoch": 0.26, "learning_rate": 3.966033866363661e-06, "loss": 0.8877, "step": 3170 }, { "epoch": 0.26, "learning_rate": 3.965923010836127e-06, "loss": 0.9488, "step": 3180 }, { "epoch": 0.27, "learning_rate": 3.965812155308594e-06, "loss": 0.8822, "step": 3190 }, { "epoch": 0.27, "learning_rate": 3.96570129978106e-06, "loss": 0.8506, "step": 3200 }, { "epoch": 0.27, "learning_rate": 3.9655904442535265e-06, "loss": 0.9329, "step": 3210 }, { "epoch": 0.27, "learning_rate": 3.965479588725993e-06, "loss": 0.8067, "step": 3220 }, { "epoch": 0.27, "learning_rate": 3.965368733198459e-06, "loss": 0.8787, "step": 3230 }, { "epoch": 0.27, "learning_rate": 3.965257877670925e-06, "loss": 0.9503, "step": 3240 }, { "epoch": 0.27, "learning_rate": 3.965147022143392e-06, "loss": 0.8433, "step": 3250 }, { "epoch": 0.27, "learning_rate": 3.965036166615858e-06, "loss": 0.9133, "step": 3260 }, { "epoch": 0.27, "learning_rate": 3.9649253110883235e-06, "loss": 0.8973, "step": 3270 }, { "epoch": 0.27, "learning_rate": 3.96481445556079e-06, "loss": 0.8479, "step": 3280 }, { "epoch": 0.27, "learning_rate": 3.964703600033256e-06, "loss": 0.9209, "step": 3290 }, { "epoch": 0.27, "learning_rate": 3.964592744505723e-06, "loss": 0.7972, "step": 3300 }, { "epoch": 0.28, "learning_rate": 3.964481888978189e-06, "loss": 0.8633, "step": 3310 }, { "epoch": 0.28, "learning_rate": 3.964371033450655e-06, "loss": 0.7997, "step": 3320 }, { "epoch": 0.28, "learning_rate": 3.964260177923122e-06, "loss": 0.8709, "step": 3330 }, { "epoch": 0.28, "learning_rate": 3.964149322395588e-06, "loss": 0.8595, "step": 3340 }, { "epoch": 0.28, "learning_rate": 3.964038466868054e-06, "loss": 0.8816, "step": 3350 }, { "epoch": 0.28, "learning_rate": 3.9639276113405205e-06, "loss": 0.8536, "step": 3360 }, { "epoch": 0.28, "learning_rate": 3.963816755812986e-06, "loss": 0.8143, "step": 3370 }, { "epoch": 0.28, "learning_rate": 3.963705900285452e-06, "loss": 0.839, "step": 3380 }, { "epoch": 0.28, "learning_rate": 3.963595044757919e-06, "loss": 0.8161, "step": 3390 }, { "epoch": 0.28, "learning_rate": 3.963484189230385e-06, "loss": 0.8622, "step": 3400 }, { "epoch": 0.28, "learning_rate": 3.963373333702852e-06, "loss": 0.911, "step": 3410 }, { "epoch": 0.28, "learning_rate": 3.9632624781753175e-06, "loss": 0.8395, "step": 3420 }, { "epoch": 0.29, "learning_rate": 3.963151622647784e-06, "loss": 0.8352, "step": 3430 }, { "epoch": 0.29, "learning_rate": 3.96304076712025e-06, "loss": 0.8368, "step": 3440 }, { "epoch": 0.29, "learning_rate": 3.962929911592717e-06, "loss": 0.8194, "step": 3450 }, { "epoch": 0.29, "learning_rate": 3.962819056065183e-06, "loss": 0.9279, "step": 3460 }, { "epoch": 0.29, "learning_rate": 3.962708200537649e-06, "loss": 0.8673, "step": 3470 }, { "epoch": 0.29, "learning_rate": 3.962597345010115e-06, "loss": 0.8388, "step": 3480 }, { "epoch": 0.29, "learning_rate": 3.962486489482582e-06, "loss": 0.8734, "step": 3490 }, { "epoch": 0.29, "learning_rate": 3.962375633955048e-06, "loss": 0.8828, "step": 3500 }, { "epoch": 0.29, "learning_rate": 3.962264778427514e-06, "loss": 0.9045, "step": 3510 }, { "epoch": 0.29, "learning_rate": 3.9621539228999804e-06, "loss": 0.7816, "step": 3520 }, { "epoch": 0.29, "learning_rate": 3.962043067372446e-06, "loss": 0.8939, "step": 3530 }, { "epoch": 0.29, "learning_rate": 3.961932211844913e-06, "loss": 0.8258, "step": 3540 }, { "epoch": 0.3, "learning_rate": 3.961821356317379e-06, "loss": 0.8639, "step": 3550 }, { "epoch": 0.3, "learning_rate": 3.961710500789846e-06, "loss": 0.901, "step": 3560 }, { "epoch": 0.3, "learning_rate": 3.9615996452623115e-06, "loss": 0.924, "step": 3570 }, { "epoch": 0.3, "learning_rate": 3.961488789734778e-06, "loss": 0.8395, "step": 3580 }, { "epoch": 0.3, "learning_rate": 3.961377934207244e-06, "loss": 0.8594, "step": 3590 }, { "epoch": 0.3, "learning_rate": 3.961267078679711e-06, "loss": 0.8223, "step": 3600 }, { "epoch": 0.3, "learning_rate": 3.961156223152177e-06, "loss": 0.8745, "step": 3610 }, { "epoch": 0.3, "learning_rate": 3.9610453676246425e-06, "loss": 0.805, "step": 3620 }, { "epoch": 0.3, "learning_rate": 3.960934512097109e-06, "loss": 0.7806, "step": 3630 }, { "epoch": 0.3, "learning_rate": 3.960823656569575e-06, "loss": 0.8571, "step": 3640 }, { "epoch": 0.3, "learning_rate": 3.960712801042042e-06, "loss": 0.8141, "step": 3650 }, { "epoch": 0.3, "learning_rate": 3.960601945514508e-06, "loss": 0.8735, "step": 3660 }, { "epoch": 0.31, "learning_rate": 3.9604910899869744e-06, "loss": 0.8151, "step": 3670 }, { "epoch": 0.31, "learning_rate": 3.96038023445944e-06, "loss": 0.8773, "step": 3680 }, { "epoch": 0.31, "learning_rate": 3.960269378931907e-06, "loss": 0.8487, "step": 3690 }, { "epoch": 0.31, "learning_rate": 3.960158523404373e-06, "loss": 0.8942, "step": 3700 }, { "epoch": 0.31, "learning_rate": 3.96004766787684e-06, "loss": 0.8492, "step": 3710 }, { "epoch": 0.31, "learning_rate": 3.9599368123493055e-06, "loss": 0.7659, "step": 3720 }, { "epoch": 0.31, "learning_rate": 3.959825956821772e-06, "loss": 0.7705, "step": 3730 }, { "epoch": 0.31, "learning_rate": 3.959715101294238e-06, "loss": 0.8849, "step": 3740 }, { "epoch": 0.31, "learning_rate": 3.959604245766704e-06, "loss": 0.8532, "step": 3750 }, { "epoch": 0.31, "learning_rate": 3.959493390239171e-06, "loss": 0.9054, "step": 3760 }, { "epoch": 0.31, "learning_rate": 3.9593825347116365e-06, "loss": 0.8997, "step": 3770 }, { "epoch": 0.31, "learning_rate": 3.959271679184103e-06, "loss": 0.8056, "step": 3780 }, { "epoch": 0.32, "learning_rate": 3.959160823656569e-06, "loss": 0.8644, "step": 3790 }, { "epoch": 0.32, "learning_rate": 3.959049968129036e-06, "loss": 0.8463, "step": 3800 }, { "epoch": 0.32, "learning_rate": 3.958939112601502e-06, "loss": 0.8437, "step": 3810 }, { "epoch": 0.32, "learning_rate": 3.9588282570739684e-06, "loss": 0.8087, "step": 3820 }, { "epoch": 0.32, "learning_rate": 3.958717401546434e-06, "loss": 0.9043, "step": 3830 }, { "epoch": 0.32, "learning_rate": 3.958606546018901e-06, "loss": 0.8639, "step": 3840 }, { "epoch": 0.32, "learning_rate": 3.958495690491367e-06, "loss": 0.831, "step": 3850 }, { "epoch": 0.32, "learning_rate": 3.958384834963833e-06, "loss": 0.907, "step": 3860 }, { "epoch": 0.32, "learning_rate": 3.9582739794362995e-06, "loss": 0.9104, "step": 3870 }, { "epoch": 0.32, "learning_rate": 3.958163123908765e-06, "loss": 0.9, "step": 3880 }, { "epoch": 0.32, "learning_rate": 3.958052268381232e-06, "loss": 0.8406, "step": 3890 }, { "epoch": 0.32, "learning_rate": 3.957941412853698e-06, "loss": 0.7863, "step": 3900 }, { "epoch": 0.32, "learning_rate": 3.957830557326165e-06, "loss": 0.9221, "step": 3910 }, { "epoch": 0.33, "learning_rate": 3.9577197017986305e-06, "loss": 0.8781, "step": 3920 }, { "epoch": 0.33, "learning_rate": 3.957608846271097e-06, "loss": 0.7841, "step": 3930 }, { "epoch": 0.33, "learning_rate": 3.957497990743563e-06, "loss": 0.8389, "step": 3940 }, { "epoch": 0.33, "learning_rate": 3.95738713521603e-06, "loss": 0.8437, "step": 3950 }, { "epoch": 0.33, "learning_rate": 3.957276279688496e-06, "loss": 0.8508, "step": 3960 }, { "epoch": 0.33, "learning_rate": 3.957165424160962e-06, "loss": 0.8649, "step": 3970 }, { "epoch": 0.33, "learning_rate": 3.957054568633428e-06, "loss": 0.795, "step": 3980 }, { "epoch": 0.33, "learning_rate": 3.956943713105894e-06, "loss": 0.8792, "step": 3990 }, { "epoch": 0.33, "learning_rate": 3.956832857578361e-06, "loss": 0.8327, "step": 4000 }, { "epoch": 0.33, "learning_rate": 3.956722002050827e-06, "loss": 0.8767, "step": 4010 }, { "epoch": 0.33, "learning_rate": 3.9566111465232935e-06, "loss": 0.8265, "step": 4020 }, { "epoch": 0.33, "learning_rate": 3.956500290995759e-06, "loss": 0.8336, "step": 4030 }, { "epoch": 0.34, "learning_rate": 3.956389435468226e-06, "loss": 0.8138, "step": 4040 }, { "epoch": 0.34, "learning_rate": 3.956278579940692e-06, "loss": 0.8466, "step": 4050 }, { "epoch": 0.34, "learning_rate": 3.956167724413159e-06, "loss": 0.9733, "step": 4060 }, { "epoch": 0.34, "learning_rate": 3.9560568688856246e-06, "loss": 0.8852, "step": 4070 }, { "epoch": 0.34, "learning_rate": 3.955946013358091e-06, "loss": 0.7796, "step": 4080 }, { "epoch": 0.34, "learning_rate": 3.955835157830557e-06, "loss": 0.8244, "step": 4090 }, { "epoch": 0.34, "learning_rate": 3.955724302303023e-06, "loss": 0.8977, "step": 4100 }, { "epoch": 0.34, "learning_rate": 3.95561344677549e-06, "loss": 0.9264, "step": 4110 }, { "epoch": 0.34, "learning_rate": 3.955502591247956e-06, "loss": 0.8884, "step": 4120 }, { "epoch": 0.34, "learning_rate": 3.955391735720422e-06, "loss": 0.7891, "step": 4130 }, { "epoch": 0.34, "learning_rate": 3.955280880192888e-06, "loss": 0.9049, "step": 4140 }, { "epoch": 0.34, "learning_rate": 3.955170024665355e-06, "loss": 0.8426, "step": 4150 }, { "epoch": 0.35, "learning_rate": 3.955059169137821e-06, "loss": 0.8838, "step": 4160 }, { "epoch": 0.35, "learning_rate": 3.9549483136102875e-06, "loss": 0.8515, "step": 4170 }, { "epoch": 0.35, "learning_rate": 3.954837458082753e-06, "loss": 0.8499, "step": 4180 }, { "epoch": 0.35, "learning_rate": 3.95472660255522e-06, "loss": 0.7983, "step": 4190 }, { "epoch": 0.35, "learning_rate": 3.954615747027686e-06, "loss": 0.9014, "step": 4200 }, { "epoch": 0.35, "learning_rate": 3.954504891500152e-06, "loss": 0.9461, "step": 4210 }, { "epoch": 0.35, "learning_rate": 3.9543940359726186e-06, "loss": 0.9095, "step": 4220 }, { "epoch": 0.35, "learning_rate": 3.9542831804450844e-06, "loss": 0.8239, "step": 4230 }, { "epoch": 0.35, "learning_rate": 3.954172324917551e-06, "loss": 0.8406, "step": 4240 }, { "epoch": 0.35, "learning_rate": 3.954061469390017e-06, "loss": 0.8088, "step": 4250 }, { "epoch": 0.35, "learning_rate": 3.953950613862484e-06, "loss": 0.8943, "step": 4260 }, { "epoch": 0.35, "learning_rate": 3.95383975833495e-06, "loss": 0.8734, "step": 4270 }, { "epoch": 0.36, "learning_rate": 3.953728902807416e-06, "loss": 0.7907, "step": 4280 }, { "epoch": 0.36, "learning_rate": 3.953618047279882e-06, "loss": 0.8726, "step": 4290 }, { "epoch": 0.36, "learning_rate": 3.953507191752349e-06, "loss": 0.8905, "step": 4300 }, { "epoch": 0.36, "learning_rate": 3.953396336224815e-06, "loss": 0.9673, "step": 4310 }, { "epoch": 0.36, "learning_rate": 3.953285480697281e-06, "loss": 0.8016, "step": 4320 }, { "epoch": 0.36, "learning_rate": 3.953174625169747e-06, "loss": 0.88, "step": 4330 }, { "epoch": 0.36, "learning_rate": 3.953063769642213e-06, "loss": 0.8621, "step": 4340 }, { "epoch": 0.36, "learning_rate": 3.95295291411468e-06, "loss": 0.7821, "step": 4350 }, { "epoch": 0.36, "learning_rate": 3.952842058587146e-06, "loss": 0.9324, "step": 4360 }, { "epoch": 0.36, "learning_rate": 3.9527312030596126e-06, "loss": 0.8485, "step": 4370 }, { "epoch": 0.36, "learning_rate": 3.9526203475320784e-06, "loss": 0.82, "step": 4380 }, { "epoch": 0.36, "learning_rate": 3.952509492004545e-06, "loss": 0.7619, "step": 4390 }, { "epoch": 0.37, "learning_rate": 3.952398636477011e-06, "loss": 0.8741, "step": 4400 }, { "epoch": 0.37, "learning_rate": 3.952287780949478e-06, "loss": 0.9318, "step": 4410 }, { "epoch": 0.37, "learning_rate": 3.952176925421944e-06, "loss": 0.834, "step": 4420 }, { "epoch": 0.37, "learning_rate": 3.95206606989441e-06, "loss": 0.8938, "step": 4430 }, { "epoch": 0.37, "learning_rate": 3.951955214366876e-06, "loss": 0.8273, "step": 4440 }, { "epoch": 0.37, "learning_rate": 3.951844358839342e-06, "loss": 0.847, "step": 4450 }, { "epoch": 0.37, "learning_rate": 3.951733503311809e-06, "loss": 0.8834, "step": 4460 }, { "epoch": 0.37, "learning_rate": 3.951622647784275e-06, "loss": 0.8144, "step": 4470 }, { "epoch": 0.37, "learning_rate": 3.951511792256741e-06, "loss": 0.8363, "step": 4480 }, { "epoch": 0.37, "learning_rate": 3.951400936729207e-06, "loss": 0.8676, "step": 4490 }, { "epoch": 0.37, "learning_rate": 3.951290081201674e-06, "loss": 0.759, "step": 4500 }, { "epoch": 0.37, "learning_rate": 3.95117922567414e-06, "loss": 0.8539, "step": 4510 }, { "epoch": 0.38, "learning_rate": 3.9510683701466066e-06, "loss": 0.8677, "step": 4520 }, { "epoch": 0.38, "learning_rate": 3.9509575146190724e-06, "loss": 0.8727, "step": 4530 }, { "epoch": 0.38, "learning_rate": 3.950846659091539e-06, "loss": 0.8586, "step": 4540 }, { "epoch": 0.38, "learning_rate": 3.950735803564005e-06, "loss": 0.8663, "step": 4550 }, { "epoch": 0.38, "learning_rate": 3.950624948036471e-06, "loss": 0.8946, "step": 4560 }, { "epoch": 0.38, "learning_rate": 3.950514092508938e-06, "loss": 0.8792, "step": 4570 }, { "epoch": 0.38, "learning_rate": 3.9504032369814035e-06, "loss": 0.7365, "step": 4580 }, { "epoch": 0.38, "learning_rate": 3.95029238145387e-06, "loss": 0.8184, "step": 4590 }, { "epoch": 0.38, "learning_rate": 3.950181525926336e-06, "loss": 0.8057, "step": 4600 }, { "epoch": 0.38, "learning_rate": 3.950070670398803e-06, "loss": 0.8755, "step": 4610 }, { "epoch": 0.38, "learning_rate": 3.949959814871269e-06, "loss": 0.8927, "step": 4620 }, { "epoch": 0.38, "learning_rate": 3.949848959343735e-06, "loss": 0.776, "step": 4630 }, { "epoch": 0.39, "learning_rate": 3.949738103816201e-06, "loss": 0.7994, "step": 4640 }, { "epoch": 0.39, "learning_rate": 3.949627248288668e-06, "loss": 0.8322, "step": 4650 }, { "epoch": 0.39, "learning_rate": 3.949516392761134e-06, "loss": 0.8645, "step": 4660 }, { "epoch": 0.39, "learning_rate": 3.9494055372336e-06, "loss": 0.887, "step": 4670 }, { "epoch": 0.39, "learning_rate": 3.9492946817060665e-06, "loss": 0.8241, "step": 4680 }, { "epoch": 0.39, "learning_rate": 3.949183826178532e-06, "loss": 0.8974, "step": 4690 }, { "epoch": 0.39, "learning_rate": 3.949072970650999e-06, "loss": 0.9293, "step": 4700 }, { "epoch": 0.39, "learning_rate": 3.948962115123465e-06, "loss": 0.8914, "step": 4710 }, { "epoch": 0.39, "learning_rate": 3.948851259595932e-06, "loss": 0.797, "step": 4720 }, { "epoch": 0.39, "learning_rate": 3.9487404040683975e-06, "loss": 0.8071, "step": 4730 }, { "epoch": 0.39, "learning_rate": 3.948629548540864e-06, "loss": 0.8474, "step": 4740 }, { "epoch": 0.39, "learning_rate": 3.94851869301333e-06, "loss": 0.8831, "step": 4750 }, { "epoch": 0.4, "learning_rate": 3.948407837485797e-06, "loss": 0.9092, "step": 4760 }, { "epoch": 0.4, "learning_rate": 3.948296981958263e-06, "loss": 0.8839, "step": 4770 }, { "epoch": 0.4, "learning_rate": 3.948186126430729e-06, "loss": 0.7846, "step": 4780 }, { "epoch": 0.4, "learning_rate": 3.948075270903195e-06, "loss": 0.8647, "step": 4790 }, { "epoch": 0.4, "learning_rate": 3.947964415375661e-06, "loss": 0.8138, "step": 4800 }, { "epoch": 0.4, "learning_rate": 3.947853559848128e-06, "loss": 0.9247, "step": 4810 }, { "epoch": 0.4, "learning_rate": 3.947742704320594e-06, "loss": 0.8521, "step": 4820 }, { "epoch": 0.4, "learning_rate": 3.9476318487930605e-06, "loss": 0.8798, "step": 4830 }, { "epoch": 0.4, "learning_rate": 3.947520993265526e-06, "loss": 0.8354, "step": 4840 }, { "epoch": 0.4, "learning_rate": 3.947410137737993e-06, "loss": 0.8381, "step": 4850 }, { "epoch": 0.4, "learning_rate": 3.947299282210459e-06, "loss": 0.8721, "step": 4860 }, { "epoch": 0.4, "learning_rate": 3.947188426682926e-06, "loss": 0.8154, "step": 4870 }, { "epoch": 0.41, "learning_rate": 3.9470775711553915e-06, "loss": 0.8355, "step": 4880 }, { "epoch": 0.41, "learning_rate": 3.946966715627858e-06, "loss": 0.8389, "step": 4890 }, { "epoch": 0.41, "learning_rate": 3.946855860100324e-06, "loss": 0.8357, "step": 4900 }, { "epoch": 0.41, "learning_rate": 3.94674500457279e-06, "loss": 0.9093, "step": 4910 }, { "epoch": 0.41, "learning_rate": 3.946634149045257e-06, "loss": 0.8402, "step": 4920 }, { "epoch": 0.41, "learning_rate": 3.9465232935177226e-06, "loss": 0.8847, "step": 4930 }, { "epoch": 0.41, "learning_rate": 3.946412437990189e-06, "loss": 0.8231, "step": 4940 }, { "epoch": 0.41, "learning_rate": 3.946301582462655e-06, "loss": 0.7609, "step": 4950 }, { "epoch": 0.41, "learning_rate": 3.946190726935122e-06, "loss": 0.9179, "step": 4960 }, { "epoch": 0.41, "learning_rate": 3.946079871407588e-06, "loss": 0.8412, "step": 4970 }, { "epoch": 0.41, "learning_rate": 3.9459690158800545e-06, "loss": 0.8839, "step": 4980 }, { "epoch": 0.41, "learning_rate": 3.94585816035252e-06, "loss": 0.7767, "step": 4990 }, { "epoch": 0.42, "learning_rate": 3.945747304824987e-06, "loss": 0.8538, "step": 5000 }, { "epoch": 0.42, "learning_rate": 3.945636449297453e-06, "loss": 0.8655, "step": 5010 }, { "epoch": 0.42, "learning_rate": 3.94552559376992e-06, "loss": 0.8407, "step": 5020 }, { "epoch": 0.42, "learning_rate": 3.9454147382423855e-06, "loss": 0.7939, "step": 5030 }, { "epoch": 0.42, "learning_rate": 3.945303882714851e-06, "loss": 0.7661, "step": 5040 }, { "epoch": 0.42, "learning_rate": 3.945193027187318e-06, "loss": 0.8303, "step": 5050 }, { "epoch": 0.42, "learning_rate": 3.945082171659784e-06, "loss": 0.8996, "step": 5060 }, { "epoch": 0.42, "learning_rate": 3.944971316132251e-06, "loss": 0.8066, "step": 5070 }, { "epoch": 0.42, "learning_rate": 3.9448604606047166e-06, "loss": 0.8999, "step": 5080 }, { "epoch": 0.42, "learning_rate": 3.944749605077183e-06, "loss": 0.8077, "step": 5090 }, { "epoch": 0.42, "learning_rate": 3.944638749549649e-06, "loss": 0.8363, "step": 5100 }, { "epoch": 0.42, "learning_rate": 3.944527894022116e-06, "loss": 0.8964, "step": 5110 }, { "epoch": 0.43, "learning_rate": 3.944417038494582e-06, "loss": 0.8188, "step": 5120 }, { "epoch": 0.43, "learning_rate": 3.9443061829670485e-06, "loss": 0.8892, "step": 5130 }, { "epoch": 0.43, "learning_rate": 3.944195327439514e-06, "loss": 0.8247, "step": 5140 }, { "epoch": 0.43, "learning_rate": 3.94408447191198e-06, "loss": 0.8919, "step": 5150 }, { "epoch": 0.43, "learning_rate": 3.943973616384447e-06, "loss": 0.8261, "step": 5160 }, { "epoch": 0.43, "learning_rate": 3.943862760856913e-06, "loss": 0.8749, "step": 5170 }, { "epoch": 0.43, "learning_rate": 3.9437519053293795e-06, "loss": 0.8797, "step": 5180 }, { "epoch": 0.43, "learning_rate": 3.943641049801845e-06, "loss": 0.8513, "step": 5190 }, { "epoch": 0.43, "learning_rate": 3.943530194274312e-06, "loss": 0.8177, "step": 5200 }, { "epoch": 0.43, "learning_rate": 3.943419338746778e-06, "loss": 0.8758, "step": 5210 }, { "epoch": 0.43, "learning_rate": 3.943308483219245e-06, "loss": 0.8531, "step": 5220 }, { "epoch": 0.43, "learning_rate": 3.943197627691711e-06, "loss": 0.8067, "step": 5230 }, { "epoch": 0.44, "learning_rate": 3.943086772164177e-06, "loss": 0.7827, "step": 5240 }, { "epoch": 0.44, "learning_rate": 3.942975916636643e-06, "loss": 0.9085, "step": 5250 }, { "epoch": 0.44, "learning_rate": 3.942865061109109e-06, "loss": 0.8695, "step": 5260 }, { "epoch": 0.44, "learning_rate": 3.942754205581576e-06, "loss": 0.7734, "step": 5270 }, { "epoch": 0.44, "learning_rate": 3.942643350054042e-06, "loss": 0.8318, "step": 5280 }, { "epoch": 0.44, "learning_rate": 3.942532494526508e-06, "loss": 0.7826, "step": 5290 }, { "epoch": 0.44, "learning_rate": 3.942421638998974e-06, "loss": 0.8787, "step": 5300 }, { "epoch": 0.44, "learning_rate": 3.942310783471441e-06, "loss": 0.9133, "step": 5310 }, { "epoch": 0.44, "learning_rate": 3.942199927943907e-06, "loss": 0.7922, "step": 5320 }, { "epoch": 0.44, "learning_rate": 3.9420890724163735e-06, "loss": 0.8045, "step": 5330 }, { "epoch": 0.44, "learning_rate": 3.941978216888839e-06, "loss": 0.8303, "step": 5340 }, { "epoch": 0.44, "learning_rate": 3.941867361361306e-06, "loss": 0.8582, "step": 5350 }, { "epoch": 0.45, "learning_rate": 3.941756505833772e-06, "loss": 0.9574, "step": 5360 }, { "epoch": 0.45, "learning_rate": 3.941645650306239e-06, "loss": 0.7705, "step": 5370 }, { "epoch": 0.45, "learning_rate": 3.941534794778705e-06, "loss": 0.8841, "step": 5380 }, { "epoch": 0.45, "learning_rate": 3.9414239392511705e-06, "loss": 0.8347, "step": 5390 }, { "epoch": 0.45, "learning_rate": 3.941313083723637e-06, "loss": 0.8493, "step": 5400 }, { "epoch": 0.45, "learning_rate": 3.941202228196103e-06, "loss": 0.8924, "step": 5410 }, { "epoch": 0.45, "learning_rate": 3.94109137266857e-06, "loss": 0.805, "step": 5420 }, { "epoch": 0.45, "learning_rate": 3.940980517141036e-06, "loss": 0.8546, "step": 5430 }, { "epoch": 0.45, "learning_rate": 3.940869661613502e-06, "loss": 0.8377, "step": 5440 }, { "epoch": 0.45, "learning_rate": 3.940758806085968e-06, "loss": 0.9206, "step": 5450 }, { "epoch": 0.45, "learning_rate": 3.940647950558435e-06, "loss": 0.9069, "step": 5460 }, { "epoch": 0.45, "learning_rate": 3.940537095030901e-06, "loss": 0.8214, "step": 5470 }, { "epoch": 0.46, "learning_rate": 3.9404262395033675e-06, "loss": 0.8517, "step": 5480 }, { "epoch": 0.46, "learning_rate": 3.940315383975833e-06, "loss": 0.8565, "step": 5490 }, { "epoch": 0.46, "learning_rate": 3.940204528448299e-06, "loss": 0.9084, "step": 5500 }, { "epoch": 0.46, "learning_rate": 3.940093672920766e-06, "loss": 0.9084, "step": 5510 }, { "epoch": 0.46, "learning_rate": 3.939982817393232e-06, "loss": 0.8316, "step": 5520 }, { "epoch": 0.46, "learning_rate": 3.939871961865698e-06, "loss": 0.8626, "step": 5530 }, { "epoch": 0.46, "learning_rate": 3.9397611063381645e-06, "loss": 0.8203, "step": 5540 }, { "epoch": 0.46, "learning_rate": 3.939650250810631e-06, "loss": 0.8155, "step": 5550 }, { "epoch": 0.46, "learning_rate": 3.939539395283097e-06, "loss": 0.8848, "step": 5560 }, { "epoch": 0.46, "learning_rate": 3.939428539755564e-06, "loss": 0.9025, "step": 5570 }, { "epoch": 0.46, "learning_rate": 3.93931768422803e-06, "loss": 0.8515, "step": 5580 }, { "epoch": 0.46, "learning_rate": 3.939206828700496e-06, "loss": 0.819, "step": 5590 }, { "epoch": 0.47, "learning_rate": 3.939095973172962e-06, "loss": 0.9216, "step": 5600 }, { "epoch": 0.47, "learning_rate": 3.938985117645428e-06, "loss": 0.8479, "step": 5610 }, { "epoch": 0.47, "learning_rate": 3.938874262117895e-06, "loss": 0.8333, "step": 5620 }, { "epoch": 0.47, "learning_rate": 3.938763406590361e-06, "loss": 0.78, "step": 5630 }, { "epoch": 0.47, "learning_rate": 3.938652551062827e-06, "loss": 0.8669, "step": 5640 }, { "epoch": 0.47, "learning_rate": 3.938541695535293e-06, "loss": 0.8541, "step": 5650 }, { "epoch": 0.47, "learning_rate": 3.938430840007759e-06, "loss": 0.8897, "step": 5660 }, { "epoch": 0.47, "learning_rate": 3.938319984480226e-06, "loss": 0.7897, "step": 5670 }, { "epoch": 0.47, "learning_rate": 3.938209128952693e-06, "loss": 0.8339, "step": 5680 }, { "epoch": 0.47, "learning_rate": 3.9380982734251585e-06, "loss": 0.8382, "step": 5690 }, { "epoch": 0.47, "learning_rate": 3.937987417897625e-06, "loss": 0.8561, "step": 5700 }, { "epoch": 0.47, "learning_rate": 3.937876562370091e-06, "loss": 0.8638, "step": 5710 }, { "epoch": 0.48, "learning_rate": 3.937765706842558e-06, "loss": 0.786, "step": 5720 }, { "epoch": 0.48, "learning_rate": 3.937654851315024e-06, "loss": 0.8577, "step": 5730 }, { "epoch": 0.48, "learning_rate": 3.9375439957874895e-06, "loss": 0.8143, "step": 5740 }, { "epoch": 0.48, "learning_rate": 3.937433140259956e-06, "loss": 0.8913, "step": 5750 }, { "epoch": 0.48, "learning_rate": 3.937322284732422e-06, "loss": 0.8738, "step": 5760 }, { "epoch": 0.48, "learning_rate": 3.937211429204888e-06, "loss": 0.8688, "step": 5770 }, { "epoch": 0.48, "learning_rate": 3.937100573677355e-06, "loss": 0.8422, "step": 5780 }, { "epoch": 0.48, "learning_rate": 3.936989718149821e-06, "loss": 0.8344, "step": 5790 }, { "epoch": 0.48, "learning_rate": 3.936878862622287e-06, "loss": 0.8539, "step": 5800 }, { "epoch": 0.48, "learning_rate": 3.936768007094754e-06, "loss": 0.9109, "step": 5810 }, { "epoch": 0.48, "learning_rate": 3.93665715156722e-06, "loss": 0.8836, "step": 5820 }, { "epoch": 0.48, "learning_rate": 3.936546296039687e-06, "loss": 0.7334, "step": 5830 }, { "epoch": 0.49, "learning_rate": 3.9364354405121525e-06, "loss": 0.8263, "step": 5840 }, { "epoch": 0.49, "learning_rate": 3.936324584984618e-06, "loss": 0.7893, "step": 5850 }, { "epoch": 0.49, "learning_rate": 3.936213729457085e-06, "loss": 0.9129, "step": 5860 }, { "epoch": 0.49, "learning_rate": 3.936102873929551e-06, "loss": 0.8067, "step": 5870 }, { "epoch": 0.49, "learning_rate": 3.935992018402017e-06, "loss": 0.9105, "step": 5880 }, { "epoch": 0.49, "learning_rate": 3.9358811628744835e-06, "loss": 0.8227, "step": 5890 }, { "epoch": 0.49, "learning_rate": 3.935770307346949e-06, "loss": 0.8536, "step": 5900 }, { "epoch": 0.49, "learning_rate": 3.935659451819416e-06, "loss": 0.8694, "step": 5910 }, { "epoch": 0.49, "learning_rate": 3.935548596291883e-06, "loss": 0.858, "step": 5920 }, { "epoch": 0.49, "learning_rate": 3.935437740764349e-06, "loss": 0.8322, "step": 5930 }, { "epoch": 0.49, "learning_rate": 3.9353268852368154e-06, "loss": 0.8479, "step": 5940 }, { "epoch": 0.49, "learning_rate": 3.935216029709281e-06, "loss": 0.8924, "step": 5950 }, { "epoch": 0.5, "learning_rate": 3.935105174181747e-06, "loss": 0.9339, "step": 5960 }, { "epoch": 0.5, "learning_rate": 3.934994318654214e-06, "loss": 0.8504, "step": 5970 }, { "epoch": 0.5, "learning_rate": 3.93488346312668e-06, "loss": 0.866, "step": 5980 }, { "epoch": 0.5, "learning_rate": 3.9347726075991465e-06, "loss": 0.8209, "step": 5990 }, { "epoch": 0.5, "learning_rate": 3.934661752071612e-06, "loss": 0.8344, "step": 6000 }, { "epoch": 0.5, "learning_rate": 3.934550896544078e-06, "loss": 0.9244, "step": 6010 }, { "epoch": 0.5, "learning_rate": 3.934440041016545e-06, "loss": 0.8689, "step": 6020 }, { "epoch": 0.5, "learning_rate": 3.934329185489011e-06, "loss": 0.8079, "step": 6030 }, { "epoch": 0.5, "learning_rate": 3.9342183299614775e-06, "loss": 0.7996, "step": 6040 }, { "epoch": 0.5, "learning_rate": 3.934107474433944e-06, "loss": 0.824, "step": 6050 }, { "epoch": 0.5, "learning_rate": 3.93399661890641e-06, "loss": 0.8455, "step": 6060 }, { "epoch": 0.5, "learning_rate": 3.933885763378877e-06, "loss": 0.8634, "step": 6070 }, { "epoch": 0.51, "learning_rate": 3.933774907851343e-06, "loss": 0.8913, "step": 6080 }, { "epoch": 0.51, "learning_rate": 3.933664052323809e-06, "loss": 0.872, "step": 6090 }, { "epoch": 0.51, "learning_rate": 3.933553196796275e-06, "loss": 0.8226, "step": 6100 }, { "epoch": 0.51, "learning_rate": 3.933442341268741e-06, "loss": 0.8386, "step": 6110 }, { "epoch": 0.51, "learning_rate": 3.933331485741207e-06, "loss": 0.8528, "step": 6120 }, { "epoch": 0.51, "learning_rate": 3.933220630213674e-06, "loss": 0.8752, "step": 6130 }, { "epoch": 0.51, "learning_rate": 3.93310977468614e-06, "loss": 0.8061, "step": 6140 }, { "epoch": 0.51, "learning_rate": 3.932998919158606e-06, "loss": 0.7827, "step": 6150 }, { "epoch": 0.51, "learning_rate": 3.932888063631073e-06, "loss": 0.905, "step": 6160 }, { "epoch": 0.51, "learning_rate": 3.932777208103539e-06, "loss": 0.8239, "step": 6170 }, { "epoch": 0.51, "learning_rate": 3.932666352576006e-06, "loss": 0.8183, "step": 6180 }, { "epoch": 0.51, "learning_rate": 3.9325554970484715e-06, "loss": 0.8824, "step": 6190 }, { "epoch": 0.52, "learning_rate": 3.932444641520937e-06, "loss": 0.829, "step": 6200 }, { "epoch": 0.52, "learning_rate": 3.932333785993404e-06, "loss": 0.8925, "step": 6210 }, { "epoch": 0.52, "learning_rate": 3.93222293046587e-06, "loss": 0.8551, "step": 6220 }, { "epoch": 0.52, "learning_rate": 3.932112074938337e-06, "loss": 0.8272, "step": 6230 }, { "epoch": 0.52, "learning_rate": 3.932001219410803e-06, "loss": 0.8315, "step": 6240 }, { "epoch": 0.52, "learning_rate": 3.9318903638832685e-06, "loss": 0.8401, "step": 6250 }, { "epoch": 0.52, "learning_rate": 3.931779508355735e-06, "loss": 0.8857, "step": 6260 }, { "epoch": 0.52, "learning_rate": 3.931668652828201e-06, "loss": 0.8264, "step": 6270 }, { "epoch": 0.52, "learning_rate": 3.931557797300668e-06, "loss": 0.8456, "step": 6280 }, { "epoch": 0.52, "learning_rate": 3.9314469417731345e-06, "loss": 0.8624, "step": 6290 }, { "epoch": 0.52, "learning_rate": 3.9313360862456e-06, "loss": 0.8466, "step": 6300 }, { "epoch": 0.52, "learning_rate": 3.931225230718067e-06, "loss": 0.9436, "step": 6310 }, { "epoch": 0.53, "learning_rate": 3.931114375190533e-06, "loss": 0.8291, "step": 6320 }, { "epoch": 0.53, "learning_rate": 3.931003519662999e-06, "loss": 0.8508, "step": 6330 }, { "epoch": 0.53, "learning_rate": 3.9308926641354655e-06, "loss": 0.8713, "step": 6340 }, { "epoch": 0.53, "learning_rate": 3.930781808607931e-06, "loss": 0.9009, "step": 6350 }, { "epoch": 0.53, "learning_rate": 3.930670953080397e-06, "loss": 0.8914, "step": 6360 }, { "epoch": 0.53, "learning_rate": 3.930560097552864e-06, "loss": 0.8162, "step": 6370 }, { "epoch": 0.53, "learning_rate": 3.93044924202533e-06, "loss": 0.8373, "step": 6380 }, { "epoch": 0.53, "learning_rate": 3.930338386497797e-06, "loss": 0.7772, "step": 6390 }, { "epoch": 0.53, "learning_rate": 3.9302275309702625e-06, "loss": 0.8295, "step": 6400 }, { "epoch": 0.53, "learning_rate": 3.930116675442729e-06, "loss": 0.9155, "step": 6410 }, { "epoch": 0.53, "learning_rate": 3.930005819915196e-06, "loss": 0.8369, "step": 6420 }, { "epoch": 0.53, "learning_rate": 3.929894964387662e-06, "loss": 0.8929, "step": 6430 }, { "epoch": 0.54, "learning_rate": 3.929784108860128e-06, "loss": 0.8239, "step": 6440 }, { "epoch": 0.54, "learning_rate": 3.929673253332594e-06, "loss": 0.8824, "step": 6450 }, { "epoch": 0.54, "learning_rate": 3.92956239780506e-06, "loss": 0.8564, "step": 6460 }, { "epoch": 0.54, "learning_rate": 3.929451542277526e-06, "loss": 0.8188, "step": 6470 }, { "epoch": 0.54, "learning_rate": 3.929340686749993e-06, "loss": 0.8225, "step": 6480 }, { "epoch": 0.54, "learning_rate": 3.929229831222459e-06, "loss": 0.8632, "step": 6490 }, { "epoch": 0.54, "learning_rate": 3.9291189756949254e-06, "loss": 0.8056, "step": 6500 }, { "epoch": 0.54, "learning_rate": 3.929008120167391e-06, "loss": 0.9495, "step": 6510 }, { "epoch": 0.54, "learning_rate": 3.928897264639858e-06, "loss": 0.8789, "step": 6520 }, { "epoch": 0.54, "learning_rate": 3.928786409112325e-06, "loss": 0.834, "step": 6530 }, { "epoch": 0.54, "learning_rate": 3.928675553584791e-06, "loss": 0.8323, "step": 6540 }, { "epoch": 0.54, "learning_rate": 3.9285646980572565e-06, "loss": 0.8093, "step": 6550 }, { "epoch": 0.55, "learning_rate": 3.928453842529723e-06, "loss": 0.909, "step": 6560 }, { "epoch": 0.55, "learning_rate": 3.928342987002189e-06, "loss": 0.774, "step": 6570 }, { "epoch": 0.55, "learning_rate": 3.928232131474656e-06, "loss": 0.8976, "step": 6580 }, { "epoch": 0.55, "learning_rate": 3.928121275947122e-06, "loss": 0.8763, "step": 6590 }, { "epoch": 0.55, "learning_rate": 3.9280104204195875e-06, "loss": 0.8084, "step": 6600 }, { "epoch": 0.55, "learning_rate": 3.927899564892054e-06, "loss": 0.8354, "step": 6610 }, { "epoch": 0.55, "learning_rate": 3.92778870936452e-06, "loss": 0.8205, "step": 6620 }, { "epoch": 0.55, "learning_rate": 3.927677853836987e-06, "loss": 0.8551, "step": 6630 }, { "epoch": 0.55, "learning_rate": 3.927566998309453e-06, "loss": 0.8865, "step": 6640 }, { "epoch": 0.55, "learning_rate": 3.9274561427819194e-06, "loss": 0.857, "step": 6650 }, { "epoch": 0.55, "learning_rate": 3.927345287254386e-06, "loss": 0.8581, "step": 6660 }, { "epoch": 0.55, "learning_rate": 3.927234431726852e-06, "loss": 0.8492, "step": 6670 }, { "epoch": 0.56, "learning_rate": 3.927123576199318e-06, "loss": 0.814, "step": 6680 }, { "epoch": 0.56, "learning_rate": 3.927012720671785e-06, "loss": 0.8073, "step": 6690 }, { "epoch": 0.56, "learning_rate": 3.9269018651442505e-06, "loss": 0.9037, "step": 6700 }, { "epoch": 0.56, "learning_rate": 3.926791009616716e-06, "loss": 0.8779, "step": 6710 }, { "epoch": 0.56, "learning_rate": 3.926680154089183e-06, "loss": 0.9183, "step": 6720 }, { "epoch": 0.56, "learning_rate": 3.926569298561649e-06, "loss": 0.836, "step": 6730 }, { "epoch": 0.56, "learning_rate": 3.926458443034116e-06, "loss": 0.8379, "step": 6740 }, { "epoch": 0.56, "learning_rate": 3.9263475875065815e-06, "loss": 0.8372, "step": 6750 }, { "epoch": 0.56, "learning_rate": 3.926236731979048e-06, "loss": 0.8744, "step": 6760 }, { "epoch": 0.56, "learning_rate": 3.926125876451515e-06, "loss": 0.7607, "step": 6770 }, { "epoch": 0.56, "learning_rate": 3.926015020923981e-06, "loss": 0.8055, "step": 6780 }, { "epoch": 0.56, "learning_rate": 3.925904165396447e-06, "loss": 0.8212, "step": 6790 }, { "epoch": 0.57, "learning_rate": 3.9257933098689134e-06, "loss": 0.8831, "step": 6800 }, { "epoch": 0.57, "learning_rate": 3.925682454341379e-06, "loss": 0.8689, "step": 6810 }, { "epoch": 0.57, "learning_rate": 3.925571598813845e-06, "loss": 0.8024, "step": 6820 }, { "epoch": 0.57, "learning_rate": 3.925460743286312e-06, "loss": 0.8028, "step": 6830 }, { "epoch": 0.57, "learning_rate": 3.925349887758778e-06, "loss": 0.9009, "step": 6840 }, { "epoch": 0.57, "learning_rate": 3.9252390322312445e-06, "loss": 0.9073, "step": 6850 }, { "epoch": 0.57, "learning_rate": 3.92512817670371e-06, "loss": 0.9126, "step": 6860 }, { "epoch": 0.57, "learning_rate": 3.925017321176177e-06, "loss": 0.7769, "step": 6870 }, { "epoch": 0.57, "learning_rate": 3.924906465648643e-06, "loss": 0.889, "step": 6880 }, { "epoch": 0.57, "learning_rate": 3.92479561012111e-06, "loss": 0.8424, "step": 6890 }, { "epoch": 0.57, "learning_rate": 3.9246847545935755e-06, "loss": 0.9098, "step": 6900 }, { "epoch": 0.57, "learning_rate": 3.924573899066042e-06, "loss": 0.9325, "step": 6910 }, { "epoch": 0.58, "learning_rate": 3.924463043538508e-06, "loss": 0.9284, "step": 6920 }, { "epoch": 0.58, "learning_rate": 3.924352188010975e-06, "loss": 0.8083, "step": 6930 }, { "epoch": 0.58, "learning_rate": 3.924241332483441e-06, "loss": 0.827, "step": 6940 }, { "epoch": 0.58, "learning_rate": 3.924130476955907e-06, "loss": 0.8465, "step": 6950 }, { "epoch": 0.58, "learning_rate": 3.924019621428373e-06, "loss": 0.9106, "step": 6960 }, { "epoch": 0.58, "learning_rate": 3.923908765900839e-06, "loss": 0.8931, "step": 6970 }, { "epoch": 0.58, "learning_rate": 3.923797910373306e-06, "loss": 0.8402, "step": 6980 }, { "epoch": 0.58, "learning_rate": 3.923687054845772e-06, "loss": 0.9307, "step": 6990 }, { "epoch": 0.58, "learning_rate": 3.9235761993182385e-06, "loss": 0.795, "step": 7000 }, { "epoch": 0.58, "learning_rate": 3.923465343790704e-06, "loss": 0.8973, "step": 7010 }, { "epoch": 0.58, "learning_rate": 3.923354488263171e-06, "loss": 0.8704, "step": 7020 }, { "epoch": 0.58, "learning_rate": 3.923243632735637e-06, "loss": 0.8865, "step": 7030 }, { "epoch": 0.59, "learning_rate": 3.923132777208104e-06, "loss": 0.8443, "step": 7040 }, { "epoch": 0.59, "learning_rate": 3.9230219216805696e-06, "loss": 0.8556, "step": 7050 }, { "epoch": 0.59, "learning_rate": 3.9229110661530354e-06, "loss": 0.9171, "step": 7060 }, { "epoch": 0.59, "learning_rate": 3.922800210625502e-06, "loss": 0.8082, "step": 7070 }, { "epoch": 0.59, "learning_rate": 3.922689355097968e-06, "loss": 0.8145, "step": 7080 }, { "epoch": 0.59, "learning_rate": 3.922578499570435e-06, "loss": 0.861, "step": 7090 }, { "epoch": 0.59, "learning_rate": 3.922467644042901e-06, "loss": 0.8334, "step": 7100 }, { "epoch": 0.59, "learning_rate": 3.922356788515367e-06, "loss": 0.9668, "step": 7110 }, { "epoch": 0.59, "learning_rate": 3.922245932987833e-06, "loss": 0.832, "step": 7120 }, { "epoch": 0.59, "learning_rate": 3.9221350774603e-06, "loss": 0.8332, "step": 7130 }, { "epoch": 0.59, "learning_rate": 3.922024221932766e-06, "loss": 0.8948, "step": 7140 }, { "epoch": 0.59, "learning_rate": 3.9219133664052325e-06, "loss": 0.8747, "step": 7150 }, { "epoch": 0.6, "learning_rate": 3.921802510877698e-06, "loss": 0.8813, "step": 7160 }, { "epoch": 0.6, "learning_rate": 3.921691655350164e-06, "loss": 0.8662, "step": 7170 }, { "epoch": 0.6, "learning_rate": 3.921580799822631e-06, "loss": 0.8437, "step": 7180 }, { "epoch": 0.6, "learning_rate": 3.921469944295097e-06, "loss": 0.8995, "step": 7190 }, { "epoch": 0.6, "learning_rate": 3.9213590887675636e-06, "loss": 0.8781, "step": 7200 }, { "epoch": 0.6, "learning_rate": 3.9212482332400294e-06, "loss": 0.8991, "step": 7210 }, { "epoch": 0.6, "learning_rate": 3.921137377712496e-06, "loss": 0.8561, "step": 7220 }, { "epoch": 0.6, "learning_rate": 3.921026522184962e-06, "loss": 0.8588, "step": 7230 }, { "epoch": 0.6, "learning_rate": 3.920915666657429e-06, "loss": 0.8761, "step": 7240 }, { "epoch": 0.6, "learning_rate": 3.920804811129895e-06, "loss": 0.795, "step": 7250 }, { "epoch": 0.6, "learning_rate": 3.920693955602361e-06, "loss": 0.8561, "step": 7260 }, { "epoch": 0.6, "learning_rate": 3.920583100074827e-06, "loss": 0.8276, "step": 7270 }, { "epoch": 0.61, "learning_rate": 3.920472244547294e-06, "loss": 0.8319, "step": 7280 }, { "epoch": 0.61, "learning_rate": 3.92036138901976e-06, "loss": 0.7814, "step": 7290 }, { "epoch": 0.61, "learning_rate": 3.920250533492226e-06, "loss": 0.8567, "step": 7300 }, { "epoch": 0.61, "learning_rate": 3.920139677964692e-06, "loss": 0.8538, "step": 7310 }, { "epoch": 0.61, "learning_rate": 3.920028822437158e-06, "loss": 0.8799, "step": 7320 }, { "epoch": 0.61, "learning_rate": 3.919917966909625e-06, "loss": 0.803, "step": 7330 }, { "epoch": 0.61, "learning_rate": 3.919807111382091e-06, "loss": 0.7964, "step": 7340 }, { "epoch": 0.61, "learning_rate": 3.9196962558545576e-06, "loss": 0.7929, "step": 7350 }, { "epoch": 0.61, "learning_rate": 3.9195854003270234e-06, "loss": 0.8838, "step": 7360 }, { "epoch": 0.61, "learning_rate": 3.919485630352244e-06, "loss": 0.8354, "step": 7370 }, { "epoch": 0.61, "learning_rate": 3.91937477482471e-06, "loss": 0.7753, "step": 7380 }, { "epoch": 0.61, "learning_rate": 3.9192639192971756e-06, "loss": 0.8776, "step": 7390 }, { "epoch": 0.62, "learning_rate": 3.919153063769642e-06, "loss": 0.8312, "step": 7400 }, { "epoch": 0.62, "learning_rate": 3.919042208242108e-06, "loss": 0.8485, "step": 7410 }, { "epoch": 0.62, "learning_rate": 3.918931352714574e-06, "loss": 0.8582, "step": 7420 }, { "epoch": 0.62, "learning_rate": 3.918820497187041e-06, "loss": 0.8744, "step": 7430 }, { "epoch": 0.62, "learning_rate": 3.918709641659507e-06, "loss": 0.7992, "step": 7440 }, { "epoch": 0.62, "learning_rate": 3.918598786131973e-06, "loss": 0.8461, "step": 7450 }, { "epoch": 0.62, "learning_rate": 3.918487930604439e-06, "loss": 0.9383, "step": 7460 }, { "epoch": 0.62, "learning_rate": 3.918377075076906e-06, "loss": 0.8018, "step": 7470 }, { "epoch": 0.62, "learning_rate": 3.918266219549373e-06, "loss": 0.9203, "step": 7480 }, { "epoch": 0.62, "learning_rate": 3.9181553640218385e-06, "loss": 0.8157, "step": 7490 }, { "epoch": 0.62, "learning_rate": 3.918044508494304e-06, "loss": 0.8543, "step": 7500 }, { "epoch": 0.62, "learning_rate": 3.917933652966771e-06, "loss": 0.8643, "step": 7510 }, { "epoch": 0.63, "learning_rate": 3.917822797439237e-06, "loss": 0.7956, "step": 7520 }, { "epoch": 0.63, "learning_rate": 3.917711941911704e-06, "loss": 0.7948, "step": 7530 }, { "epoch": 0.63, "learning_rate": 3.9176010863841696e-06, "loss": 0.7959, "step": 7540 }, { "epoch": 0.63, "learning_rate": 3.9174902308566354e-06, "loss": 0.8141, "step": 7550 }, { "epoch": 0.63, "learning_rate": 3.917379375329102e-06, "loss": 0.9113, "step": 7560 }, { "epoch": 0.63, "learning_rate": 3.917268519801568e-06, "loss": 0.7441, "step": 7570 }, { "epoch": 0.63, "learning_rate": 3.917157664274035e-06, "loss": 0.8588, "step": 7580 }, { "epoch": 0.63, "learning_rate": 3.917046808746501e-06, "loss": 0.8225, "step": 7590 }, { "epoch": 0.63, "learning_rate": 3.916935953218967e-06, "loss": 0.8068, "step": 7600 }, { "epoch": 0.63, "learning_rate": 3.916825097691434e-06, "loss": 0.994, "step": 7610 }, { "epoch": 0.63, "learning_rate": 3.9167142421639e-06, "loss": 0.7775, "step": 7620 }, { "epoch": 0.63, "learning_rate": 3.916603386636366e-06, "loss": 0.8431, "step": 7630 }, { "epoch": 0.64, "learning_rate": 3.9164925311088325e-06, "loss": 0.768, "step": 7640 }, { "epoch": 0.64, "learning_rate": 3.916381675581298e-06, "loss": 0.8759, "step": 7650 }, { "epoch": 0.64, "learning_rate": 3.916270820053764e-06, "loss": 0.8907, "step": 7660 }, { "epoch": 0.64, "learning_rate": 3.916159964526231e-06, "loss": 0.8718, "step": 7670 }, { "epoch": 0.64, "learning_rate": 3.916049108998697e-06, "loss": 0.7575, "step": 7680 }, { "epoch": 0.64, "learning_rate": 3.915938253471164e-06, "loss": 0.832, "step": 7690 }, { "epoch": 0.64, "learning_rate": 3.9158273979436295e-06, "loss": 0.8621, "step": 7700 }, { "epoch": 0.64, "learning_rate": 3.915716542416096e-06, "loss": 0.8746, "step": 7710 }, { "epoch": 0.64, "learning_rate": 3.915605686888563e-06, "loss": 0.9495, "step": 7720 }, { "epoch": 0.64, "learning_rate": 3.915494831361029e-06, "loss": 0.8815, "step": 7730 }, { "epoch": 0.64, "learning_rate": 3.915383975833495e-06, "loss": 0.8082, "step": 7740 }, { "epoch": 0.64, "learning_rate": 3.915273120305961e-06, "loss": 0.8045, "step": 7750 }, { "epoch": 0.65, "learning_rate": 3.915162264778427e-06, "loss": 0.9111, "step": 7760 }, { "epoch": 0.65, "learning_rate": 3.915051409250893e-06, "loss": 0.8108, "step": 7770 }, { "epoch": 0.65, "learning_rate": 3.91494055372336e-06, "loss": 0.8002, "step": 7780 }, { "epoch": 0.65, "learning_rate": 3.914829698195826e-06, "loss": 0.9104, "step": 7790 }, { "epoch": 0.65, "learning_rate": 3.914718842668292e-06, "loss": 0.833, "step": 7800 }, { "epoch": 0.65, "learning_rate": 3.914607987140758e-06, "loss": 0.8817, "step": 7810 }, { "epoch": 0.65, "learning_rate": 3.914497131613225e-06, "loss": 0.8135, "step": 7820 }, { "epoch": 0.65, "learning_rate": 3.914386276085691e-06, "loss": 0.754, "step": 7830 }, { "epoch": 0.65, "learning_rate": 3.914275420558158e-06, "loss": 0.8235, "step": 7840 }, { "epoch": 0.65, "learning_rate": 3.9141645650306235e-06, "loss": 0.8353, "step": 7850 }, { "epoch": 0.65, "learning_rate": 3.91405370950309e-06, "loss": 0.8558, "step": 7860 }, { "epoch": 0.65, "learning_rate": 3.913942853975556e-06, "loss": 0.8351, "step": 7870 }, { "epoch": 0.65, "learning_rate": 3.913831998448023e-06, "loss": 0.8681, "step": 7880 }, { "epoch": 0.66, "learning_rate": 3.913721142920489e-06, "loss": 0.7907, "step": 7890 }, { "epoch": 0.66, "learning_rate": 3.9136102873929545e-06, "loss": 0.788, "step": 7900 }, { "epoch": 0.66, "learning_rate": 3.913499431865421e-06, "loss": 0.9116, "step": 7910 }, { "epoch": 0.66, "learning_rate": 3.913388576337887e-06, "loss": 0.8619, "step": 7920 }, { "epoch": 0.66, "learning_rate": 3.913277720810354e-06, "loss": 0.8352, "step": 7930 }, { "epoch": 0.66, "learning_rate": 3.91316686528282e-06, "loss": 0.7917, "step": 7940 }, { "epoch": 0.66, "learning_rate": 3.913056009755286e-06, "loss": 0.8498, "step": 7950 }, { "epoch": 0.66, "learning_rate": 3.912945154227752e-06, "loss": 0.9391, "step": 7960 }, { "epoch": 0.66, "learning_rate": 3.912834298700219e-06, "loss": 0.9218, "step": 7970 }, { "epoch": 0.66, "learning_rate": 3.912723443172685e-06, "loss": 0.8311, "step": 7980 }, { "epoch": 0.66, "learning_rate": 3.912612587645152e-06, "loss": 0.9902, "step": 7990 }, { "epoch": 0.66, "learning_rate": 3.9125017321176175e-06, "loss": 0.806, "step": 8000 }, { "epoch": 0.67, "learning_rate": 3.912390876590083e-06, "loss": 0.9757, "step": 8010 }, { "epoch": 0.67, "learning_rate": 3.91228002106255e-06, "loss": 0.8217, "step": 8020 }, { "epoch": 0.67, "learning_rate": 3.912169165535016e-06, "loss": 0.8541, "step": 8030 }, { "epoch": 0.67, "learning_rate": 3.912058310007483e-06, "loss": 0.7893, "step": 8040 }, { "epoch": 0.67, "learning_rate": 3.9119474544799485e-06, "loss": 0.8058, "step": 8050 }, { "epoch": 0.67, "learning_rate": 3.911836598952415e-06, "loss": 0.8566, "step": 8060 }, { "epoch": 0.67, "learning_rate": 3.911725743424881e-06, "loss": 0.8491, "step": 8070 }, { "epoch": 0.67, "learning_rate": 3.911614887897348e-06, "loss": 0.8394, "step": 8080 }, { "epoch": 0.67, "learning_rate": 3.911504032369814e-06, "loss": 0.8653, "step": 8090 }, { "epoch": 0.67, "learning_rate": 3.91139317684228e-06, "loss": 0.8461, "step": 8100 }, { "epoch": 0.67, "learning_rate": 3.911282321314746e-06, "loss": 0.8648, "step": 8110 }, { "epoch": 0.67, "learning_rate": 3.911171465787212e-06, "loss": 0.8381, "step": 8120 }, { "epoch": 0.68, "learning_rate": 3.911060610259679e-06, "loss": 0.8132, "step": 8130 }, { "epoch": 0.68, "learning_rate": 3.910949754732145e-06, "loss": 0.864, "step": 8140 }, { "epoch": 0.68, "learning_rate": 3.9108388992046115e-06, "loss": 0.7988, "step": 8150 }, { "epoch": 0.68, "learning_rate": 3.910728043677077e-06, "loss": 0.8496, "step": 8160 }, { "epoch": 0.68, "learning_rate": 3.910617188149544e-06, "loss": 0.9266, "step": 8170 }, { "epoch": 0.68, "learning_rate": 3.91050633262201e-06, "loss": 0.8173, "step": 8180 }, { "epoch": 0.68, "learning_rate": 3.910395477094477e-06, "loss": 0.7925, "step": 8190 }, { "epoch": 0.68, "learning_rate": 3.9102846215669425e-06, "loss": 0.8059, "step": 8200 }, { "epoch": 0.68, "learning_rate": 3.910173766039409e-06, "loss": 0.949, "step": 8210 }, { "epoch": 0.68, "learning_rate": 3.910062910511875e-06, "loss": 0.8643, "step": 8220 }, { "epoch": 0.68, "learning_rate": 3.909952054984342e-06, "loss": 0.7679, "step": 8230 }, { "epoch": 0.68, "learning_rate": 3.909841199456808e-06, "loss": 0.8428, "step": 8240 }, { "epoch": 0.69, "learning_rate": 3.909730343929274e-06, "loss": 0.8178, "step": 8250 }, { "epoch": 0.69, "learning_rate": 3.90961948840174e-06, "loss": 0.8913, "step": 8260 }, { "epoch": 0.69, "learning_rate": 3.909508632874206e-06, "loss": 0.9222, "step": 8270 }, { "epoch": 0.69, "learning_rate": 3.909397777346673e-06, "loss": 0.8969, "step": 8280 }, { "epoch": 0.69, "learning_rate": 3.909286921819139e-06, "loss": 0.8123, "step": 8290 }, { "epoch": 0.69, "learning_rate": 3.9091760662916055e-06, "loss": 0.8612, "step": 8300 }, { "epoch": 0.69, "learning_rate": 3.909065210764071e-06, "loss": 0.8584, "step": 8310 }, { "epoch": 0.69, "learning_rate": 3.908954355236538e-06, "loss": 0.8551, "step": 8320 }, { "epoch": 0.69, "learning_rate": 3.908843499709004e-06, "loss": 0.8673, "step": 8330 }, { "epoch": 0.69, "learning_rate": 3.908732644181471e-06, "loss": 0.8274, "step": 8340 }, { "epoch": 0.69, "learning_rate": 3.9086217886539365e-06, "loss": 0.8072, "step": 8350 }, { "epoch": 0.69, "learning_rate": 3.908510933126402e-06, "loss": 0.9027, "step": 8360 }, { "epoch": 0.7, "learning_rate": 3.908400077598869e-06, "loss": 0.8266, "step": 8370 }, { "epoch": 0.7, "learning_rate": 3.908289222071335e-06, "loss": 0.7795, "step": 8380 }, { "epoch": 0.7, "learning_rate": 3.908178366543802e-06, "loss": 0.8264, "step": 8390 }, { "epoch": 0.7, "learning_rate": 3.908067511016268e-06, "loss": 0.8214, "step": 8400 }, { "epoch": 0.7, "learning_rate": 3.907956655488734e-06, "loss": 0.8957, "step": 8410 }, { "epoch": 0.7, "learning_rate": 3.9078457999612e-06, "loss": 0.9951, "step": 8420 }, { "epoch": 0.7, "learning_rate": 3.907734944433667e-06, "loss": 0.8911, "step": 8430 }, { "epoch": 0.7, "learning_rate": 3.907624088906133e-06, "loss": 0.7979, "step": 8440 }, { "epoch": 0.7, "learning_rate": 3.9075132333785995e-06, "loss": 0.8465, "step": 8450 }, { "epoch": 0.7, "learning_rate": 3.907402377851065e-06, "loss": 0.8622, "step": 8460 }, { "epoch": 0.7, "learning_rate": 3.907291522323532e-06, "loss": 0.9071, "step": 8470 }, { "epoch": 0.7, "learning_rate": 3.907180666795998e-06, "loss": 0.7743, "step": 8480 }, { "epoch": 0.71, "learning_rate": 3.907069811268464e-06, "loss": 0.8076, "step": 8490 }, { "epoch": 0.71, "learning_rate": 3.9069589557409305e-06, "loss": 0.8513, "step": 8500 }, { "epoch": 0.71, "learning_rate": 3.906848100213396e-06, "loss": 0.8518, "step": 8510 }, { "epoch": 0.71, "learning_rate": 3.906737244685863e-06, "loss": 0.8423, "step": 8520 }, { "epoch": 0.71, "learning_rate": 3.906626389158329e-06, "loss": 0.8071, "step": 8530 }, { "epoch": 0.71, "learning_rate": 3.906515533630796e-06, "loss": 0.8478, "step": 8540 }, { "epoch": 0.71, "learning_rate": 3.906404678103262e-06, "loss": 0.7902, "step": 8550 }, { "epoch": 0.71, "learning_rate": 3.906293822575728e-06, "loss": 0.9553, "step": 8560 }, { "epoch": 0.71, "learning_rate": 3.906182967048194e-06, "loss": 0.7733, "step": 8570 }, { "epoch": 0.71, "learning_rate": 3.906072111520661e-06, "loss": 0.8204, "step": 8580 }, { "epoch": 0.71, "learning_rate": 3.905961255993127e-06, "loss": 0.8612, "step": 8590 }, { "epoch": 0.71, "learning_rate": 3.905850400465593e-06, "loss": 0.8474, "step": 8600 }, { "epoch": 0.72, "learning_rate": 3.905739544938059e-06, "loss": 0.9044, "step": 8610 }, { "epoch": 0.72, "learning_rate": 3.905628689410525e-06, "loss": 0.8233, "step": 8620 }, { "epoch": 0.72, "learning_rate": 3.905517833882992e-06, "loss": 0.8429, "step": 8630 }, { "epoch": 0.72, "learning_rate": 3.905406978355458e-06, "loss": 0.8902, "step": 8640 }, { "epoch": 0.72, "learning_rate": 3.9052961228279245e-06, "loss": 0.8087, "step": 8650 }, { "epoch": 0.72, "learning_rate": 3.90518526730039e-06, "loss": 0.9594, "step": 8660 }, { "epoch": 0.72, "learning_rate": 3.905074411772857e-06, "loss": 0.8268, "step": 8670 }, { "epoch": 0.72, "learning_rate": 3.904963556245323e-06, "loss": 0.7972, "step": 8680 }, { "epoch": 0.72, "learning_rate": 3.90485270071779e-06, "loss": 0.8822, "step": 8690 }, { "epoch": 0.72, "learning_rate": 3.904741845190256e-06, "loss": 0.8178, "step": 8700 }, { "epoch": 0.72, "learning_rate": 3.9046309896627215e-06, "loss": 0.8958, "step": 8710 }, { "epoch": 0.72, "learning_rate": 3.904520134135188e-06, "loss": 0.863, "step": 8720 }, { "epoch": 0.73, "learning_rate": 3.904409278607654e-06, "loss": 0.7795, "step": 8730 }, { "epoch": 0.73, "learning_rate": 3.904298423080121e-06, "loss": 0.8116, "step": 8740 }, { "epoch": 0.73, "learning_rate": 3.904187567552587e-06, "loss": 0.8079, "step": 8750 }, { "epoch": 0.73, "learning_rate": 3.904076712025053e-06, "loss": 0.8915, "step": 8760 }, { "epoch": 0.73, "learning_rate": 3.903965856497519e-06, "loss": 0.8799, "step": 8770 }, { "epoch": 0.73, "learning_rate": 3.903855000969986e-06, "loss": 0.8454, "step": 8780 }, { "epoch": 0.73, "learning_rate": 3.903744145442452e-06, "loss": 0.8422, "step": 8790 }, { "epoch": 0.73, "learning_rate": 3.9036332899149186e-06, "loss": 0.7997, "step": 8800 }, { "epoch": 0.73, "learning_rate": 3.903522434387384e-06, "loss": 0.8974, "step": 8810 }, { "epoch": 0.73, "learning_rate": 3.903411578859851e-06, "loss": 0.9052, "step": 8820 }, { "epoch": 0.73, "learning_rate": 3.903300723332317e-06, "loss": 0.8024, "step": 8830 }, { "epoch": 0.73, "learning_rate": 3.903189867804783e-06, "loss": 0.7675, "step": 8840 }, { "epoch": 0.74, "learning_rate": 3.90307901227725e-06, "loss": 0.8486, "step": 8850 }, { "epoch": 0.74, "learning_rate": 3.9029681567497155e-06, "loss": 0.9069, "step": 8860 }, { "epoch": 0.74, "learning_rate": 3.902857301222182e-06, "loss": 0.8487, "step": 8870 }, { "epoch": 0.74, "learning_rate": 3.902746445694648e-06, "loss": 0.7794, "step": 8880 }, { "epoch": 0.74, "learning_rate": 3.902635590167115e-06, "loss": 0.903, "step": 8890 }, { "epoch": 0.74, "learning_rate": 3.902524734639581e-06, "loss": 0.8978, "step": 8900 }, { "epoch": 0.74, "learning_rate": 3.902413879112047e-06, "loss": 0.843, "step": 8910 }, { "epoch": 0.74, "learning_rate": 3.902303023584513e-06, "loss": 0.908, "step": 8920 }, { "epoch": 0.74, "learning_rate": 3.90219216805698e-06, "loss": 0.8415, "step": 8930 }, { "epoch": 0.74, "learning_rate": 3.902081312529446e-06, "loss": 0.8238, "step": 8940 }, { "epoch": 0.74, "learning_rate": 3.901970457001912e-06, "loss": 0.8079, "step": 8950 }, { "epoch": 0.74, "learning_rate": 3.9018596014743784e-06, "loss": 0.8426, "step": 8960 }, { "epoch": 0.75, "learning_rate": 3.901748745946844e-06, "loss": 0.8942, "step": 8970 }, { "epoch": 0.75, "learning_rate": 3.901637890419311e-06, "loss": 0.7866, "step": 8980 }, { "epoch": 0.75, "learning_rate": 3.901527034891777e-06, "loss": 0.8017, "step": 8990 }, { "epoch": 0.75, "learning_rate": 3.901416179364244e-06, "loss": 0.8713, "step": 9000 }, { "epoch": 0.75, "learning_rate": 3.9013053238367095e-06, "loss": 0.8881, "step": 9010 }, { "epoch": 0.75, "learning_rate": 3.901194468309176e-06, "loss": 0.8235, "step": 9020 }, { "epoch": 0.75, "learning_rate": 3.901083612781642e-06, "loss": 0.8246, "step": 9030 }, { "epoch": 0.75, "learning_rate": 3.900972757254109e-06, "loss": 0.8331, "step": 9040 }, { "epoch": 0.75, "learning_rate": 3.900861901726575e-06, "loss": 0.9347, "step": 9050 }, { "epoch": 0.75, "learning_rate": 3.9007510461990405e-06, "loss": 0.9152, "step": 9060 }, { "epoch": 0.75, "learning_rate": 3.900640190671507e-06, "loss": 0.8498, "step": 9070 }, { "epoch": 0.75, "learning_rate": 3.900529335143973e-06, "loss": 0.7443, "step": 9080 }, { "epoch": 0.76, "learning_rate": 3.90041847961644e-06, "loss": 0.7721, "step": 9090 }, { "epoch": 0.76, "learning_rate": 3.900307624088906e-06, "loss": 0.9, "step": 9100 }, { "epoch": 0.76, "learning_rate": 3.9001967685613724e-06, "loss": 0.9034, "step": 9110 }, { "epoch": 0.76, "learning_rate": 3.900085913033838e-06, "loss": 0.8069, "step": 9120 }, { "epoch": 0.76, "learning_rate": 3.899975057506305e-06, "loss": 0.8162, "step": 9130 }, { "epoch": 0.76, "learning_rate": 3.899864201978771e-06, "loss": 0.8035, "step": 9140 }, { "epoch": 0.76, "learning_rate": 3.899753346451238e-06, "loss": 0.7888, "step": 9150 }, { "epoch": 0.76, "learning_rate": 3.8996424909237035e-06, "loss": 0.8952, "step": 9160 }, { "epoch": 0.76, "learning_rate": 3.89953163539617e-06, "loss": 0.8002, "step": 9170 }, { "epoch": 0.76, "learning_rate": 3.899420779868636e-06, "loss": 0.8197, "step": 9180 }, { "epoch": 0.76, "learning_rate": 3.899309924341102e-06, "loss": 0.9299, "step": 9190 }, { "epoch": 0.76, "learning_rate": 3.899199068813569e-06, "loss": 0.8231, "step": 9200 }, { "epoch": 0.77, "learning_rate": 3.8990882132860345e-06, "loss": 0.8899, "step": 9210 }, { "epoch": 0.77, "learning_rate": 3.898977357758501e-06, "loss": 0.8739, "step": 9220 }, { "epoch": 0.77, "learning_rate": 3.898866502230967e-06, "loss": 0.8435, "step": 9230 }, { "epoch": 0.77, "learning_rate": 3.898755646703434e-06, "loss": 0.8378, "step": 9240 }, { "epoch": 0.77, "learning_rate": 3.8986447911759e-06, "loss": 0.8502, "step": 9250 }, { "epoch": 0.77, "learning_rate": 3.8985339356483664e-06, "loss": 0.9335, "step": 9260 }, { "epoch": 0.77, "learning_rate": 3.898423080120832e-06, "loss": 0.832, "step": 9270 }, { "epoch": 0.77, "learning_rate": 3.898312224593299e-06, "loss": 0.8367, "step": 9280 }, { "epoch": 0.77, "learning_rate": 3.898201369065765e-06, "loss": 0.8052, "step": 9290 }, { "epoch": 0.77, "learning_rate": 3.898090513538231e-06, "loss": 0.8269, "step": 9300 }, { "epoch": 0.77, "learning_rate": 3.8979796580106975e-06, "loss": 0.9043, "step": 9310 }, { "epoch": 0.77, "learning_rate": 3.897868802483163e-06, "loss": 0.8596, "step": 9320 }, { "epoch": 0.78, "learning_rate": 3.89775794695563e-06, "loss": 0.8311, "step": 9330 }, { "epoch": 0.78, "learning_rate": 3.897647091428096e-06, "loss": 0.811, "step": 9340 }, { "epoch": 0.78, "learning_rate": 3.897536235900563e-06, "loss": 0.8839, "step": 9350 }, { "epoch": 0.78, "learning_rate": 3.8974253803730285e-06, "loss": 0.8695, "step": 9360 }, { "epoch": 0.78, "learning_rate": 3.897314524845495e-06, "loss": 0.8194, "step": 9370 }, { "epoch": 0.78, "learning_rate": 3.897214754870715e-06, "loss": 0.7957, "step": 9380 }, { "epoch": 0.78, "learning_rate": 3.897103899343181e-06, "loss": 0.8179, "step": 9390 }, { "epoch": 0.78, "learning_rate": 3.896993043815647e-06, "loss": 0.886, "step": 9400 }, { "epoch": 0.78, "learning_rate": 3.896882188288113e-06, "loss": 0.8708, "step": 9410 }, { "epoch": 0.78, "learning_rate": 3.89677133276058e-06, "loss": 0.7699, "step": 9420 }, { "epoch": 0.78, "learning_rate": 3.896660477233046e-06, "loss": 0.8696, "step": 9430 }, { "epoch": 0.78, "learning_rate": 3.896549621705512e-06, "loss": 0.8134, "step": 9440 }, { "epoch": 0.79, "learning_rate": 3.8964387661779784e-06, "loss": 0.8479, "step": 9450 }, { "epoch": 0.79, "learning_rate": 3.896327910650444e-06, "loss": 0.9304, "step": 9460 }, { "epoch": 0.79, "learning_rate": 3.896217055122911e-06, "loss": 0.8289, "step": 9470 }, { "epoch": 0.79, "learning_rate": 3.896106199595377e-06, "loss": 0.8761, "step": 9480 }, { "epoch": 0.79, "learning_rate": 3.895995344067844e-06, "loss": 0.8631, "step": 9490 }, { "epoch": 0.79, "learning_rate": 3.8958844885403095e-06, "loss": 0.8209, "step": 9500 }, { "epoch": 0.79, "learning_rate": 3.895773633012776e-06, "loss": 0.8359, "step": 9510 }, { "epoch": 0.79, "learning_rate": 3.895662777485242e-06, "loss": 0.8448, "step": 9520 }, { "epoch": 0.79, "learning_rate": 3.895551921957709e-06, "loss": 0.8659, "step": 9530 }, { "epoch": 0.79, "learning_rate": 3.895441066430175e-06, "loss": 0.8483, "step": 9540 }, { "epoch": 0.79, "learning_rate": 3.8953302109026406e-06, "loss": 0.9025, "step": 9550 }, { "epoch": 0.79, "learning_rate": 3.895219355375107e-06, "loss": 0.8592, "step": 9560 }, { "epoch": 0.8, "learning_rate": 3.895108499847573e-06, "loss": 0.7897, "step": 9570 }, { "epoch": 0.8, "learning_rate": 3.89499764432004e-06, "loss": 0.8075, "step": 9580 }, { "epoch": 0.8, "learning_rate": 3.894886788792506e-06, "loss": 0.8255, "step": 9590 }, { "epoch": 0.8, "learning_rate": 3.8947759332649725e-06, "loss": 0.8879, "step": 9600 }, { "epoch": 0.8, "learning_rate": 3.894665077737438e-06, "loss": 0.9994, "step": 9610 }, { "epoch": 0.8, "learning_rate": 3.894554222209905e-06, "loss": 0.8684, "step": 9620 }, { "epoch": 0.8, "learning_rate": 3.894443366682371e-06, "loss": 0.8729, "step": 9630 }, { "epoch": 0.8, "learning_rate": 3.894332511154838e-06, "loss": 0.8389, "step": 9640 }, { "epoch": 0.8, "learning_rate": 3.8942216556273035e-06, "loss": 0.8026, "step": 9650 }, { "epoch": 0.8, "learning_rate": 3.894110800099769e-06, "loss": 0.8815, "step": 9660 }, { "epoch": 0.8, "learning_rate": 3.893999944572236e-06, "loss": 0.8537, "step": 9670 }, { "epoch": 0.8, "learning_rate": 3.893889089044702e-06, "loss": 0.8364, "step": 9680 }, { "epoch": 0.81, "learning_rate": 3.893778233517169e-06, "loss": 0.8394, "step": 9690 }, { "epoch": 0.81, "learning_rate": 3.8936673779896346e-06, "loss": 0.8168, "step": 9700 }, { "epoch": 0.81, "learning_rate": 3.893556522462101e-06, "loss": 0.8397, "step": 9710 }, { "epoch": 0.81, "learning_rate": 3.893445666934567e-06, "loss": 0.7895, "step": 9720 }, { "epoch": 0.81, "learning_rate": 3.893334811407034e-06, "loss": 0.9142, "step": 9730 }, { "epoch": 0.81, "learning_rate": 3.8932239558795e-06, "loss": 0.9099, "step": 9740 }, { "epoch": 0.81, "learning_rate": 3.8931131003519665e-06, "loss": 0.8175, "step": 9750 }, { "epoch": 0.81, "learning_rate": 3.893002244824432e-06, "loss": 0.8567, "step": 9760 }, { "epoch": 0.81, "learning_rate": 3.892891389296899e-06, "loss": 0.8111, "step": 9770 }, { "epoch": 0.81, "learning_rate": 3.892780533769365e-06, "loss": 0.8067, "step": 9780 }, { "epoch": 0.81, "learning_rate": 3.892669678241831e-06, "loss": 0.8253, "step": 9790 }, { "epoch": 0.81, "learning_rate": 3.8925588227142975e-06, "loss": 0.8227, "step": 9800 }, { "epoch": 0.82, "learning_rate": 3.892447967186763e-06, "loss": 0.93, "step": 9810 }, { "epoch": 0.82, "learning_rate": 3.89233711165923e-06, "loss": 0.8563, "step": 9820 }, { "epoch": 0.82, "learning_rate": 3.892226256131696e-06, "loss": 0.8768, "step": 9830 }, { "epoch": 0.82, "learning_rate": 3.892115400604163e-06, "loss": 0.8233, "step": 9840 }, { "epoch": 0.82, "learning_rate": 3.8920045450766286e-06, "loss": 0.8268, "step": 9850 }, { "epoch": 0.82, "learning_rate": 3.891893689549095e-06, "loss": 0.8644, "step": 9860 }, { "epoch": 0.82, "learning_rate": 3.891782834021561e-06, "loss": 0.804, "step": 9870 }, { "epoch": 0.82, "learning_rate": 3.891671978494028e-06, "loss": 0.8404, "step": 9880 }, { "epoch": 0.82, "learning_rate": 3.891561122966494e-06, "loss": 0.8408, "step": 9890 }, { "epoch": 0.82, "learning_rate": 3.89145026743896e-06, "loss": 0.8467, "step": 9900 }, { "epoch": 0.82, "learning_rate": 3.891339411911426e-06, "loss": 0.9414, "step": 9910 }, { "epoch": 0.82, "learning_rate": 3.891228556383892e-06, "loss": 0.8265, "step": 9920 }, { "epoch": 0.83, "learning_rate": 3.891117700856359e-06, "loss": 0.7993, "step": 9930 }, { "epoch": 0.83, "learning_rate": 3.891006845328825e-06, "loss": 0.8951, "step": 9940 }, { "epoch": 0.83, "learning_rate": 3.8908959898012915e-06, "loss": 0.8383, "step": 9950 }, { "epoch": 0.83, "learning_rate": 3.890785134273757e-06, "loss": 0.8246, "step": 9960 }, { "epoch": 0.83, "learning_rate": 3.890674278746224e-06, "loss": 0.8695, "step": 9970 }, { "epoch": 0.83, "learning_rate": 3.89056342321869e-06, "loss": 0.7833, "step": 9980 }, { "epoch": 0.83, "learning_rate": 3.890452567691157e-06, "loss": 0.8105, "step": 9990 }, { "epoch": 0.83, "learning_rate": 3.8903417121636226e-06, "loss": 0.833, "step": 10000 }, { "epoch": 0.83, "learning_rate": 3.8902308566360884e-06, "loss": 0.8229, "step": 10010 }, { "epoch": 0.83, "learning_rate": 3.890120001108555e-06, "loss": 0.8162, "step": 10020 }, { "epoch": 0.83, "learning_rate": 3.890009145581021e-06, "loss": 0.844, "step": 10030 }, { "epoch": 0.83, "learning_rate": 3.889898290053488e-06, "loss": 0.867, "step": 10040 }, { "epoch": 0.84, "learning_rate": 3.889787434525954e-06, "loss": 0.8027, "step": 10050 }, { "epoch": 0.84, "learning_rate": 3.88967657899842e-06, "loss": 0.8452, "step": 10060 }, { "epoch": 0.84, "learning_rate": 3.889565723470886e-06, "loss": 0.812, "step": 10070 }, { "epoch": 0.84, "learning_rate": 3.889454867943353e-06, "loss": 0.7894, "step": 10080 }, { "epoch": 0.84, "learning_rate": 3.889344012415819e-06, "loss": 0.7947, "step": 10090 }, { "epoch": 0.84, "learning_rate": 3.8892331568882855e-06, "loss": 0.8538, "step": 10100 }, { "epoch": 0.84, "learning_rate": 3.889122301360751e-06, "loss": 0.8725, "step": 10110 }, { "epoch": 0.84, "learning_rate": 3.889011445833218e-06, "loss": 0.812, "step": 10120 }, { "epoch": 0.84, "learning_rate": 3.888900590305684e-06, "loss": 0.8796, "step": 10130 }, { "epoch": 0.84, "learning_rate": 3.88878973477815e-06, "loss": 0.8541, "step": 10140 }, { "epoch": 0.84, "learning_rate": 3.888678879250617e-06, "loss": 0.8534, "step": 10150 }, { "epoch": 0.84, "learning_rate": 3.8885680237230825e-06, "loss": 0.8915, "step": 10160 }, { "epoch": 0.85, "learning_rate": 3.888457168195549e-06, "loss": 0.8846, "step": 10170 }, { "epoch": 0.85, "learning_rate": 3.888346312668015e-06, "loss": 0.8757, "step": 10180 }, { "epoch": 0.85, "learning_rate": 3.888235457140482e-06, "loss": 0.8438, "step": 10190 }, { "epoch": 0.85, "learning_rate": 3.888124601612948e-06, "loss": 0.8335, "step": 10200 }, { "epoch": 0.85, "learning_rate": 3.888013746085414e-06, "loss": 0.9133, "step": 10210 }, { "epoch": 0.85, "learning_rate": 3.88790289055788e-06, "loss": 0.8112, "step": 10220 }, { "epoch": 0.85, "learning_rate": 3.887792035030347e-06, "loss": 0.8027, "step": 10230 }, { "epoch": 0.85, "learning_rate": 3.887681179502813e-06, "loss": 0.8556, "step": 10240 }, { "epoch": 0.85, "learning_rate": 3.887570323975279e-06, "loss": 0.786, "step": 10250 }, { "epoch": 0.85, "learning_rate": 3.887459468447745e-06, "loss": 0.8894, "step": 10260 }, { "epoch": 0.85, "learning_rate": 3.887348612920211e-06, "loss": 0.8474, "step": 10270 }, { "epoch": 0.85, "learning_rate": 3.887237757392678e-06, "loss": 0.8289, "step": 10280 }, { "epoch": 0.86, "learning_rate": 3.887126901865144e-06, "loss": 0.8168, "step": 10290 }, { "epoch": 0.86, "learning_rate": 3.887016046337611e-06, "loss": 0.813, "step": 10300 }, { "epoch": 0.86, "learning_rate": 3.8869051908100765e-06, "loss": 0.8459, "step": 10310 }, { "epoch": 0.86, "learning_rate": 3.886794335282543e-06, "loss": 0.8485, "step": 10320 }, { "epoch": 0.86, "learning_rate": 3.886683479755009e-06, "loss": 0.8409, "step": 10330 }, { "epoch": 0.86, "learning_rate": 3.886572624227476e-06, "loss": 0.8069, "step": 10340 }, { "epoch": 0.86, "learning_rate": 3.886461768699942e-06, "loss": 0.8305, "step": 10350 }, { "epoch": 0.86, "learning_rate": 3.8863509131724075e-06, "loss": 0.9366, "step": 10360 }, { "epoch": 0.86, "learning_rate": 3.886240057644874e-06, "loss": 0.8435, "step": 10370 }, { "epoch": 0.86, "learning_rate": 3.88612920211734e-06, "loss": 0.7872, "step": 10380 }, { "epoch": 0.86, "learning_rate": 3.886018346589807e-06, "loss": 0.9109, "step": 10390 }, { "epoch": 0.86, "learning_rate": 3.885907491062273e-06, "loss": 0.8504, "step": 10400 }, { "epoch": 0.87, "learning_rate": 3.885796635534739e-06, "loss": 0.8555, "step": 10410 }, { "epoch": 0.87, "learning_rate": 3.885685780007205e-06, "loss": 0.8686, "step": 10420 }, { "epoch": 0.87, "learning_rate": 3.885574924479672e-06, "loss": 0.859, "step": 10430 }, { "epoch": 0.87, "learning_rate": 3.885464068952138e-06, "loss": 0.877, "step": 10440 }, { "epoch": 0.87, "learning_rate": 3.885353213424605e-06, "loss": 0.8827, "step": 10450 }, { "epoch": 0.87, "learning_rate": 3.8852423578970705e-06, "loss": 0.8911, "step": 10460 }, { "epoch": 0.87, "learning_rate": 3.885131502369537e-06, "loss": 0.8837, "step": 10470 }, { "epoch": 0.87, "learning_rate": 3.885020646842003e-06, "loss": 0.8932, "step": 10480 }, { "epoch": 0.87, "learning_rate": 3.884909791314469e-06, "loss": 0.7994, "step": 10490 }, { "epoch": 0.87, "learning_rate": 3.884798935786936e-06, "loss": 0.8639, "step": 10500 }, { "epoch": 0.87, "learning_rate": 3.8846880802594015e-06, "loss": 0.8507, "step": 10510 }, { "epoch": 0.87, "learning_rate": 3.884577224731868e-06, "loss": 0.8763, "step": 10520 }, { "epoch": 0.88, "learning_rate": 3.884466369204334e-06, "loss": 0.8208, "step": 10530 }, { "epoch": 0.88, "learning_rate": 3.884355513676801e-06, "loss": 0.8578, "step": 10540 }, { "epoch": 0.88, "learning_rate": 3.88425574370202e-06, "loss": 0.7879, "step": 10550 }, { "epoch": 0.88, "learning_rate": 3.884144888174486e-06, "loss": 0.841, "step": 10560 }, { "epoch": 0.88, "learning_rate": 3.884034032646953e-06, "loss": 0.9156, "step": 10570 }, { "epoch": 0.88, "learning_rate": 3.883923177119419e-06, "loss": 0.8156, "step": 10580 }, { "epoch": 0.88, "learning_rate": 3.8838123215918855e-06, "loss": 0.8191, "step": 10590 }, { "epoch": 0.88, "learning_rate": 3.883701466064351e-06, "loss": 0.846, "step": 10600 }, { "epoch": 0.88, "learning_rate": 3.883590610536817e-06, "loss": 0.9179, "step": 10610 }, { "epoch": 0.88, "learning_rate": 3.883479755009284e-06, "loss": 0.813, "step": 10620 }, { "epoch": 0.88, "learning_rate": 3.88336889948175e-06, "loss": 0.8187, "step": 10630 }, { "epoch": 0.88, "learning_rate": 3.883258043954217e-06, "loss": 0.8387, "step": 10640 }, { "epoch": 0.89, "learning_rate": 3.8831471884266825e-06, "loss": 0.8011, "step": 10650 }, { "epoch": 0.89, "learning_rate": 3.883036332899149e-06, "loss": 0.8865, "step": 10660 }, { "epoch": 0.89, "learning_rate": 3.882925477371615e-06, "loss": 0.8461, "step": 10670 }, { "epoch": 0.89, "learning_rate": 3.882814621844082e-06, "loss": 0.8384, "step": 10680 }, { "epoch": 0.89, "learning_rate": 3.882703766316548e-06, "loss": 0.777, "step": 10690 }, { "epoch": 0.89, "learning_rate": 3.882592910789014e-06, "loss": 0.8444, "step": 10700 }, { "epoch": 0.89, "learning_rate": 3.88248205526148e-06, "loss": 0.9189, "step": 10710 }, { "epoch": 0.89, "learning_rate": 3.882371199733947e-06, "loss": 0.8614, "step": 10720 }, { "epoch": 0.89, "learning_rate": 3.882260344206413e-06, "loss": 0.8681, "step": 10730 }, { "epoch": 0.89, "learning_rate": 3.882149488678879e-06, "loss": 0.8325, "step": 10740 }, { "epoch": 0.89, "learning_rate": 3.8820386331513454e-06, "loss": 0.7982, "step": 10750 }, { "epoch": 0.89, "learning_rate": 3.881927777623811e-06, "loss": 0.8077, "step": 10760 }, { "epoch": 0.9, "learning_rate": 3.881816922096278e-06, "loss": 0.8746, "step": 10770 }, { "epoch": 0.9, "learning_rate": 3.881706066568744e-06, "loss": 0.8303, "step": 10780 }, { "epoch": 0.9, "learning_rate": 3.881595211041211e-06, "loss": 0.8355, "step": 10790 }, { "epoch": 0.9, "learning_rate": 3.8814843555136765e-06, "loss": 0.8343, "step": 10800 }, { "epoch": 0.9, "learning_rate": 3.881373499986143e-06, "loss": 0.8623, "step": 10810 }, { "epoch": 0.9, "learning_rate": 3.881262644458609e-06, "loss": 0.8195, "step": 10820 }, { "epoch": 0.9, "learning_rate": 3.881151788931076e-06, "loss": 0.8442, "step": 10830 }, { "epoch": 0.9, "learning_rate": 3.881040933403542e-06, "loss": 0.8098, "step": 10840 }, { "epoch": 0.9, "learning_rate": 3.8809300778760075e-06, "loss": 0.8319, "step": 10850 }, { "epoch": 0.9, "learning_rate": 3.880819222348474e-06, "loss": 0.8634, "step": 10860 }, { "epoch": 0.9, "learning_rate": 3.88070836682094e-06, "loss": 0.8344, "step": 10870 }, { "epoch": 0.9, "learning_rate": 3.880597511293407e-06, "loss": 0.7867, "step": 10880 }, { "epoch": 0.91, "learning_rate": 3.880486655765873e-06, "loss": 0.8458, "step": 10890 }, { "epoch": 0.91, "learning_rate": 3.8803758002383394e-06, "loss": 0.8079, "step": 10900 }, { "epoch": 0.91, "learning_rate": 3.880264944710805e-06, "loss": 0.9344, "step": 10910 }, { "epoch": 0.91, "learning_rate": 3.880154089183272e-06, "loss": 0.8917, "step": 10920 }, { "epoch": 0.91, "learning_rate": 3.880043233655738e-06, "loss": 0.7999, "step": 10930 }, { "epoch": 0.91, "learning_rate": 3.879932378128205e-06, "loss": 0.7663, "step": 10940 }, { "epoch": 0.91, "learning_rate": 3.8798215226006705e-06, "loss": 0.8657, "step": 10950 }, { "epoch": 0.91, "learning_rate": 3.879710667073136e-06, "loss": 0.8825, "step": 10960 }, { "epoch": 0.91, "learning_rate": 3.879599811545603e-06, "loss": 0.8822, "step": 10970 }, { "epoch": 0.91, "learning_rate": 3.879488956018069e-06, "loss": 0.8352, "step": 10980 }, { "epoch": 0.91, "learning_rate": 3.879378100490536e-06, "loss": 0.835, "step": 10990 }, { "epoch": 0.91, "learning_rate": 3.8792672449630015e-06, "loss": 0.8268, "step": 11000 }, { "epoch": 0.92, "learning_rate": 3.879156389435468e-06, "loss": 0.8822, "step": 11010 }, { "epoch": 0.92, "learning_rate": 3.879045533907934e-06, "loss": 0.876, "step": 11020 }, { "epoch": 0.92, "learning_rate": 3.878934678380401e-06, "loss": 0.8559, "step": 11030 }, { "epoch": 0.92, "learning_rate": 3.878823822852867e-06, "loss": 0.8168, "step": 11040 }, { "epoch": 0.92, "learning_rate": 3.8787129673253334e-06, "loss": 0.8488, "step": 11050 }, { "epoch": 0.92, "learning_rate": 3.878602111797799e-06, "loss": 0.9622, "step": 11060 }, { "epoch": 0.92, "learning_rate": 3.878491256270266e-06, "loss": 0.8884, "step": 11070 }, { "epoch": 0.92, "learning_rate": 3.878380400742732e-06, "loss": 0.7893, "step": 11080 }, { "epoch": 0.92, "learning_rate": 3.878269545215198e-06, "loss": 0.8374, "step": 11090 }, { "epoch": 0.92, "learning_rate": 3.8781586896876645e-06, "loss": 0.8732, "step": 11100 }, { "epoch": 0.92, "learning_rate": 3.87804783416013e-06, "loss": 0.8829, "step": 11110 }, { "epoch": 0.92, "learning_rate": 3.877936978632597e-06, "loss": 0.7935, "step": 11120 }, { "epoch": 0.93, "learning_rate": 3.877826123105063e-06, "loss": 0.8837, "step": 11130 }, { "epoch": 0.93, "learning_rate": 3.87771526757753e-06, "loss": 0.791, "step": 11140 }, { "epoch": 0.93, "learning_rate": 3.8776044120499955e-06, "loss": 0.7927, "step": 11150 }, { "epoch": 0.93, "learning_rate": 3.877493556522462e-06, "loss": 0.8666, "step": 11160 }, { "epoch": 0.93, "learning_rate": 3.877382700994928e-06, "loss": 0.9139, "step": 11170 }, { "epoch": 0.93, "learning_rate": 3.877271845467395e-06, "loss": 0.8167, "step": 11180 }, { "epoch": 0.93, "learning_rate": 3.877160989939861e-06, "loss": 0.7962, "step": 11190 }, { "epoch": 0.93, "learning_rate": 3.877050134412327e-06, "loss": 0.8939, "step": 11200 }, { "epoch": 0.93, "learning_rate": 3.876939278884793e-06, "loss": 0.9406, "step": 11210 }, { "epoch": 0.93, "learning_rate": 3.876828423357259e-06, "loss": 0.8071, "step": 11220 }, { "epoch": 0.93, "learning_rate": 3.876717567829726e-06, "loss": 0.8005, "step": 11230 }, { "epoch": 0.93, "learning_rate": 3.876606712302192e-06, "loss": 0.8116, "step": 11240 }, { "epoch": 0.94, "learning_rate": 3.8764958567746585e-06, "loss": 0.8404, "step": 11250 }, { "epoch": 0.94, "learning_rate": 3.876385001247124e-06, "loss": 0.8664, "step": 11260 }, { "epoch": 0.94, "learning_rate": 3.876274145719591e-06, "loss": 0.8084, "step": 11270 }, { "epoch": 0.94, "learning_rate": 3.876163290192057e-06, "loss": 0.7927, "step": 11280 }, { "epoch": 0.94, "learning_rate": 3.876052434664524e-06, "loss": 0.8349, "step": 11290 }, { "epoch": 0.94, "learning_rate": 3.8759415791369896e-06, "loss": 0.8381, "step": 11300 }, { "epoch": 0.94, "learning_rate": 3.8758307236094554e-06, "loss": 0.8938, "step": 11310 }, { "epoch": 0.94, "learning_rate": 3.875719868081922e-06, "loss": 0.8422, "step": 11320 }, { "epoch": 0.94, "learning_rate": 3.875609012554388e-06, "loss": 0.8679, "step": 11330 }, { "epoch": 0.94, "learning_rate": 3.875498157026855e-06, "loss": 0.8754, "step": 11340 }, { "epoch": 0.94, "learning_rate": 3.875387301499321e-06, "loss": 0.7942, "step": 11350 }, { "epoch": 0.94, "learning_rate": 3.875276445971787e-06, "loss": 0.8617, "step": 11360 }, { "epoch": 0.95, "learning_rate": 3.875165590444253e-06, "loss": 0.7803, "step": 11370 }, { "epoch": 0.95, "learning_rate": 3.87505473491672e-06, "loss": 0.818, "step": 11380 }, { "epoch": 0.95, "learning_rate": 3.874943879389186e-06, "loss": 0.7765, "step": 11390 }, { "epoch": 0.95, "learning_rate": 3.8748330238616525e-06, "loss": 0.7853, "step": 11400 }, { "epoch": 0.95, "learning_rate": 3.874722168334118e-06, "loss": 0.9046, "step": 11410 }, { "epoch": 0.95, "learning_rate": 3.874611312806585e-06, "loss": 0.8566, "step": 11420 }, { "epoch": 0.95, "learning_rate": 3.874500457279051e-06, "loss": 0.8441, "step": 11430 }, { "epoch": 0.95, "learning_rate": 3.874389601751517e-06, "loss": 0.7818, "step": 11440 }, { "epoch": 0.95, "learning_rate": 3.8742787462239836e-06, "loss": 0.93, "step": 11450 }, { "epoch": 0.95, "learning_rate": 3.8741678906964494e-06, "loss": 0.8582, "step": 11460 }, { "epoch": 0.95, "learning_rate": 3.874057035168916e-06, "loss": 0.8262, "step": 11470 }, { "epoch": 0.95, "learning_rate": 3.873946179641382e-06, "loss": 0.7822, "step": 11480 }, { "epoch": 0.96, "learning_rate": 3.873835324113849e-06, "loss": 0.8749, "step": 11490 }, { "epoch": 0.96, "learning_rate": 3.873724468586315e-06, "loss": 0.799, "step": 11500 }, { "epoch": 0.96, "learning_rate": 3.873613613058781e-06, "loss": 0.8604, "step": 11510 }, { "epoch": 0.96, "learning_rate": 3.873502757531247e-06, "loss": 0.8092, "step": 11520 }, { "epoch": 0.96, "learning_rate": 3.873391902003714e-06, "loss": 0.807, "step": 11530 }, { "epoch": 0.96, "learning_rate": 3.87328104647618e-06, "loss": 0.7678, "step": 11540 }, { "epoch": 0.96, "learning_rate": 3.873170190948646e-06, "loss": 0.8601, "step": 11550 }, { "epoch": 0.96, "learning_rate": 3.873059335421112e-06, "loss": 0.9308, "step": 11560 }, { "epoch": 0.96, "learning_rate": 3.872948479893578e-06, "loss": 0.8628, "step": 11570 }, { "epoch": 0.96, "learning_rate": 3.872837624366045e-06, "loss": 0.8278, "step": 11580 }, { "epoch": 0.96, "learning_rate": 3.872726768838511e-06, "loss": 0.8601, "step": 11590 }, { "epoch": 0.96, "learning_rate": 3.8726159133109776e-06, "loss": 0.8845, "step": 11600 }, { "epoch": 0.97, "learning_rate": 3.8725050577834434e-06, "loss": 0.8927, "step": 11610 }, { "epoch": 0.97, "learning_rate": 3.87239420225591e-06, "loss": 0.7779, "step": 11620 }, { "epoch": 0.97, "learning_rate": 3.872283346728376e-06, "loss": 0.8668, "step": 11630 }, { "epoch": 0.97, "learning_rate": 3.872172491200843e-06, "loss": 0.8623, "step": 11640 }, { "epoch": 0.97, "learning_rate": 3.872061635673309e-06, "loss": 0.7813, "step": 11650 }, { "epoch": 0.97, "learning_rate": 3.871950780145775e-06, "loss": 0.9395, "step": 11660 }, { "epoch": 0.97, "learning_rate": 3.871839924618241e-06, "loss": 0.7617, "step": 11670 }, { "epoch": 0.97, "learning_rate": 3.871729069090707e-06, "loss": 0.8644, "step": 11680 }, { "epoch": 0.97, "learning_rate": 3.871629299115927e-06, "loss": 0.8187, "step": 11690 }, { "epoch": 0.97, "learning_rate": 3.871518443588393e-06, "loss": 0.8506, "step": 11700 }, { "epoch": 0.97, "learning_rate": 3.871407588060859e-06, "loss": 0.8712, "step": 11710 }, { "epoch": 0.97, "learning_rate": 3.871296732533326e-06, "loss": 0.8576, "step": 11720 }, { "epoch": 0.97, "learning_rate": 3.871185877005792e-06, "loss": 0.8717, "step": 11730 }, { "epoch": 0.98, "learning_rate": 3.8710750214782585e-06, "loss": 0.8732, "step": 11740 }, { "epoch": 0.98, "learning_rate": 3.870964165950724e-06, "loss": 0.7677, "step": 11750 }, { "epoch": 0.98, "learning_rate": 3.870853310423191e-06, "loss": 0.9521, "step": 11760 }, { "epoch": 0.98, "learning_rate": 3.870742454895657e-06, "loss": 0.8174, "step": 11770 }, { "epoch": 0.98, "learning_rate": 3.870631599368124e-06, "loss": 0.89, "step": 11780 }, { "epoch": 0.98, "learning_rate": 3.8705207438405896e-06, "loss": 0.8057, "step": 11790 }, { "epoch": 0.98, "learning_rate": 3.8704098883130554e-06, "loss": 0.8216, "step": 11800 }, { "epoch": 0.98, "learning_rate": 3.870299032785522e-06, "loss": 0.9601, "step": 11810 }, { "epoch": 0.98, "learning_rate": 3.870188177257988e-06, "loss": 0.8016, "step": 11820 }, { "epoch": 0.98, "learning_rate": 3.870077321730455e-06, "loss": 0.8317, "step": 11830 }, { "epoch": 0.98, "learning_rate": 3.869966466202921e-06, "loss": 0.7903, "step": 11840 }, { "epoch": 0.98, "learning_rate": 3.869855610675387e-06, "loss": 0.8399, "step": 11850 }, { "epoch": 0.99, "learning_rate": 3.869744755147853e-06, "loss": 0.8844, "step": 11860 }, { "epoch": 0.99, "learning_rate": 3.86963389962032e-06, "loss": 0.8293, "step": 11870 }, { "epoch": 0.99, "learning_rate": 3.869523044092786e-06, "loss": 0.9198, "step": 11880 }, { "epoch": 0.99, "learning_rate": 3.8694121885652525e-06, "loss": 0.801, "step": 11890 }, { "epoch": 0.99, "learning_rate": 3.869301333037718e-06, "loss": 0.8281, "step": 11900 }, { "epoch": 0.99, "learning_rate": 3.869190477510184e-06, "loss": 0.9058, "step": 11910 }, { "epoch": 0.99, "learning_rate": 3.869079621982651e-06, "loss": 0.8396, "step": 11920 }, { "epoch": 0.99, "learning_rate": 3.868968766455117e-06, "loss": 0.9046, "step": 11930 }, { "epoch": 0.99, "learning_rate": 3.868857910927584e-06, "loss": 0.7773, "step": 11940 }, { "epoch": 0.99, "learning_rate": 3.8687470554000495e-06, "loss": 0.8501, "step": 11950 }, { "epoch": 0.99, "learning_rate": 3.868636199872516e-06, "loss": 0.8795, "step": 11960 }, { "epoch": 0.99, "learning_rate": 3.868525344344982e-06, "loss": 0.8331, "step": 11970 }, { "epoch": 1.0, "learning_rate": 3.868414488817449e-06, "loss": 0.8284, "step": 11980 }, { "epoch": 1.0, "learning_rate": 3.868303633289915e-06, "loss": 0.8731, "step": 11990 }, { "epoch": 1.0, "learning_rate": 3.868192777762381e-06, "loss": 0.8259, "step": 12000 }, { "epoch": 1.0, "learning_rate": 3.868081922234847e-06, "loss": 0.8421, "step": 12010 }, { "epoch": 1.0, "learning_rate": 3.867971066707314e-06, "loss": 0.8529, "step": 12020 }, { "epoch": 1.0, "learning_rate": 3.86786021117978e-06, "loss": 0.9303, "step": 12030 }, { "epoch": 1.0, "eval_loss": 1.1160094738006592, "eval_runtime": 342.8507, "eval_samples_per_second": 7.799, "eval_steps_per_second": 3.9, "eval_wer": 0.6711587631196057, "step": 12031 }, { "epoch": 1.0, "learning_rate": 3.867749355652246e-06, "loss": 0.8189, "step": 12040 }, { "epoch": 1.0, "learning_rate": 3.867638500124712e-06, "loss": 0.8668, "step": 12050 }, { "epoch": 1.0, "learning_rate": 3.867527644597178e-06, "loss": 0.8518, "step": 12060 }, { "epoch": 1.0, "learning_rate": 3.867416789069645e-06, "loss": 0.8048, "step": 12070 }, { "epoch": 1.0, "learning_rate": 3.867305933542111e-06, "loss": 0.8275, "step": 12080 }, { "epoch": 1.0, "learning_rate": 3.867195078014578e-06, "loss": 0.9305, "step": 12090 }, { "epoch": 1.01, "learning_rate": 3.8670842224870435e-06, "loss": 0.8896, "step": 12100 }, { "epoch": 1.01, "learning_rate": 3.86697336695951e-06, "loss": 0.8082, "step": 12110 }, { "epoch": 1.01, "learning_rate": 3.866862511431976e-06, "loss": 0.8458, "step": 12120 }, { "epoch": 1.01, "learning_rate": 3.866751655904443e-06, "loss": 0.8593, "step": 12130 }, { "epoch": 1.01, "learning_rate": 3.866640800376909e-06, "loss": 0.8699, "step": 12140 }, { "epoch": 1.01, "learning_rate": 3.8665299448493745e-06, "loss": 0.859, "step": 12150 }, { "epoch": 1.01, "learning_rate": 3.866419089321841e-06, "loss": 0.8184, "step": 12160 }, { "epoch": 1.01, "learning_rate": 3.866308233794307e-06, "loss": 0.8437, "step": 12170 }, { "epoch": 1.01, "learning_rate": 3.866197378266774e-06, "loss": 0.8117, "step": 12180 }, { "epoch": 1.01, "learning_rate": 3.86608652273924e-06, "loss": 0.7969, "step": 12190 }, { "epoch": 1.01, "learning_rate": 3.865975667211706e-06, "loss": 0.8216, "step": 12200 }, { "epoch": 1.01, "learning_rate": 3.865864811684172e-06, "loss": 0.8113, "step": 12210 }, { "epoch": 1.02, "learning_rate": 3.865753956156639e-06, "loss": 0.7829, "step": 12220 }, { "epoch": 1.02, "learning_rate": 3.865643100629105e-06, "loss": 0.8312, "step": 12230 }, { "epoch": 1.02, "learning_rate": 3.865532245101572e-06, "loss": 0.9013, "step": 12240 }, { "epoch": 1.02, "learning_rate": 3.8654213895740375e-06, "loss": 0.745, "step": 12250 }, { "epoch": 1.02, "learning_rate": 3.865310534046503e-06, "loss": 0.7924, "step": 12260 }, { "epoch": 1.02, "learning_rate": 3.86519967851897e-06, "loss": 0.8695, "step": 12270 }, { "epoch": 1.02, "learning_rate": 3.865088822991436e-06, "loss": 0.8021, "step": 12280 }, { "epoch": 1.02, "learning_rate": 3.864977967463903e-06, "loss": 0.9151, "step": 12290 }, { "epoch": 1.02, "learning_rate": 3.8648671119363685e-06, "loss": 0.8236, "step": 12300 }, { "epoch": 1.02, "learning_rate": 3.864756256408835e-06, "loss": 0.851, "step": 12310 }, { "epoch": 1.02, "learning_rate": 3.864645400881301e-06, "loss": 0.843, "step": 12320 }, { "epoch": 1.02, "learning_rate": 3.864534545353768e-06, "loss": 0.9019, "step": 12330 }, { "epoch": 1.03, "learning_rate": 3.864423689826234e-06, "loss": 0.8913, "step": 12340 }, { "epoch": 1.03, "learning_rate": 3.8643128342987e-06, "loss": 0.7819, "step": 12350 }, { "epoch": 1.03, "learning_rate": 3.864201978771166e-06, "loss": 0.7761, "step": 12360 }, { "epoch": 1.03, "learning_rate": 3.864091123243633e-06, "loss": 0.7728, "step": 12370 }, { "epoch": 1.03, "learning_rate": 3.863980267716099e-06, "loss": 0.8508, "step": 12380 }, { "epoch": 1.03, "learning_rate": 3.863869412188565e-06, "loss": 0.8867, "step": 12390 }, { "epoch": 1.03, "learning_rate": 3.8637585566610315e-06, "loss": 0.8307, "step": 12400 }, { "epoch": 1.03, "learning_rate": 3.863647701133497e-06, "loss": 0.8292, "step": 12410 }, { "epoch": 1.03, "learning_rate": 3.863536845605964e-06, "loss": 0.8259, "step": 12420 }, { "epoch": 1.03, "learning_rate": 3.86342599007843e-06, "loss": 0.8685, "step": 12430 }, { "epoch": 1.03, "learning_rate": 3.863315134550897e-06, "loss": 0.918, "step": 12440 }, { "epoch": 1.03, "learning_rate": 3.8632042790233625e-06, "loss": 0.8928, "step": 12450 }, { "epoch": 1.04, "learning_rate": 3.863093423495829e-06, "loss": 0.8481, "step": 12460 }, { "epoch": 1.04, "learning_rate": 3.862982567968295e-06, "loss": 0.8475, "step": 12470 }, { "epoch": 1.04, "learning_rate": 3.862871712440762e-06, "loss": 0.8482, "step": 12480 }, { "epoch": 1.04, "learning_rate": 3.862760856913228e-06, "loss": 0.8016, "step": 12490 }, { "epoch": 1.04, "learning_rate": 3.862650001385694e-06, "loss": 0.8098, "step": 12500 }, { "epoch": 1.04, "learning_rate": 3.86253914585816e-06, "loss": 0.7845, "step": 12510 }, { "epoch": 1.04, "learning_rate": 3.862428290330626e-06, "loss": 0.8313, "step": 12520 }, { "epoch": 1.04, "learning_rate": 3.862317434803093e-06, "loss": 0.8226, "step": 12530 }, { "epoch": 1.04, "learning_rate": 3.862206579275559e-06, "loss": 0.8764, "step": 12540 }, { "epoch": 1.04, "learning_rate": 3.8620957237480255e-06, "loss": 0.805, "step": 12550 }, { "epoch": 1.04, "learning_rate": 3.861984868220491e-06, "loss": 0.8576, "step": 12560 }, { "epoch": 1.04, "learning_rate": 3.861874012692958e-06, "loss": 0.7841, "step": 12570 }, { "epoch": 1.05, "learning_rate": 3.861763157165424e-06, "loss": 0.8793, "step": 12580 }, { "epoch": 1.05, "learning_rate": 3.861652301637891e-06, "loss": 0.8824, "step": 12590 }, { "epoch": 1.05, "learning_rate": 3.8615414461103565e-06, "loss": 0.8956, "step": 12600 }, { "epoch": 1.05, "learning_rate": 3.861430590582823e-06, "loss": 0.8899, "step": 12610 }, { "epoch": 1.05, "learning_rate": 3.861319735055289e-06, "loss": 0.8386, "step": 12620 }, { "epoch": 1.05, "learning_rate": 3.861208879527755e-06, "loss": 0.8808, "step": 12630 }, { "epoch": 1.05, "learning_rate": 3.861098024000222e-06, "loss": 0.9227, "step": 12640 }, { "epoch": 1.05, "learning_rate": 3.860987168472688e-06, "loss": 0.7782, "step": 12650 }, { "epoch": 1.05, "learning_rate": 3.860876312945154e-06, "loss": 0.8652, "step": 12660 }, { "epoch": 1.05, "learning_rate": 3.86076545741762e-06, "loss": 0.8783, "step": 12670 }, { "epoch": 1.05, "learning_rate": 3.860654601890087e-06, "loss": 0.8557, "step": 12680 }, { "epoch": 1.05, "learning_rate": 3.860543746362553e-06, "loss": 0.8714, "step": 12690 }, { "epoch": 1.06, "learning_rate": 3.8604328908350195e-06, "loss": 0.8784, "step": 12700 }, { "epoch": 1.06, "learning_rate": 3.860322035307485e-06, "loss": 0.7944, "step": 12710 }, { "epoch": 1.06, "learning_rate": 3.860211179779952e-06, "loss": 0.8572, "step": 12720 }, { "epoch": 1.06, "learning_rate": 3.860100324252418e-06, "loss": 0.8714, "step": 12730 }, { "epoch": 1.06, "learning_rate": 3.859989468724884e-06, "loss": 0.8842, "step": 12740 }, { "epoch": 1.06, "learning_rate": 3.8598786131973505e-06, "loss": 0.8898, "step": 12750 }, { "epoch": 1.06, "learning_rate": 3.859767757669816e-06, "loss": 0.8213, "step": 12760 }, { "epoch": 1.06, "learning_rate": 3.859656902142282e-06, "loss": 0.8584, "step": 12770 }, { "epoch": 1.06, "learning_rate": 3.859546046614749e-06, "loss": 0.8003, "step": 12780 }, { "epoch": 1.06, "learning_rate": 3.859435191087216e-06, "loss": 0.9192, "step": 12790 }, { "epoch": 1.06, "learning_rate": 3.859324335559682e-06, "loss": 0.9172, "step": 12800 }, { "epoch": 1.06, "learning_rate": 3.859213480032148e-06, "loss": 0.8719, "step": 12810 }, { "epoch": 1.07, "learning_rate": 3.859102624504614e-06, "loss": 0.8525, "step": 12820 }, { "epoch": 1.07, "learning_rate": 3.858991768977081e-06, "loss": 0.7619, "step": 12830 }, { "epoch": 1.07, "learning_rate": 3.858880913449547e-06, "loss": 0.7785, "step": 12840 }, { "epoch": 1.07, "learning_rate": 3.858770057922013e-06, "loss": 0.9167, "step": 12850 }, { "epoch": 1.07, "learning_rate": 3.858659202394479e-06, "loss": 0.8121, "step": 12860 }, { "epoch": 1.07, "learning_rate": 3.858548346866945e-06, "loss": 0.8976, "step": 12870 }, { "epoch": 1.07, "learning_rate": 3.858437491339412e-06, "loss": 0.8137, "step": 12880 }, { "epoch": 1.07, "learning_rate": 3.858326635811878e-06, "loss": 0.7933, "step": 12890 }, { "epoch": 1.07, "learning_rate": 3.8582157802843445e-06, "loss": 0.8537, "step": 12900 }, { "epoch": 1.07, "learning_rate": 3.85810492475681e-06, "loss": 0.8557, "step": 12910 }, { "epoch": 1.07, "learning_rate": 3.857994069229277e-06, "loss": 0.7798, "step": 12920 }, { "epoch": 1.07, "learning_rate": 3.857883213701743e-06, "loss": 0.8113, "step": 12930 }, { "epoch": 1.08, "learning_rate": 3.85777235817421e-06, "loss": 0.8732, "step": 12940 }, { "epoch": 1.08, "learning_rate": 3.857661502646676e-06, "loss": 0.8245, "step": 12950 }, { "epoch": 1.08, "learning_rate": 3.857550647119142e-06, "loss": 0.8167, "step": 12960 }, { "epoch": 1.08, "learning_rate": 3.857439791591608e-06, "loss": 0.8756, "step": 12970 }, { "epoch": 1.08, "learning_rate": 3.857328936064074e-06, "loss": 0.778, "step": 12980 }, { "epoch": 1.08, "learning_rate": 3.857218080536541e-06, "loss": 0.8331, "step": 12990 }, { "epoch": 1.08, "learning_rate": 3.857107225009007e-06, "loss": 0.8093, "step": 13000 }, { "epoch": 1.08, "learning_rate": 3.8569963694814725e-06, "loss": 0.8034, "step": 13010 }, { "epoch": 1.08, "learning_rate": 3.856885513953939e-06, "loss": 0.7881, "step": 13020 }, { "epoch": 1.08, "learning_rate": 3.856774658426406e-06, "loss": 0.8112, "step": 13030 }, { "epoch": 1.08, "learning_rate": 3.856663802898872e-06, "loss": 0.8962, "step": 13040 }, { "epoch": 1.08, "learning_rate": 3.8565529473713386e-06, "loss": 0.825, "step": 13050 }, { "epoch": 1.09, "learning_rate": 3.8564420918438044e-06, "loss": 0.8705, "step": 13060 }, { "epoch": 1.09, "learning_rate": 3.856331236316271e-06, "loss": 0.8112, "step": 13070 }, { "epoch": 1.09, "learning_rate": 3.856220380788737e-06, "loss": 0.9388, "step": 13080 }, { "epoch": 1.09, "learning_rate": 3.856109525261203e-06, "loss": 0.9308, "step": 13090 }, { "epoch": 1.09, "learning_rate": 3.85599866973367e-06, "loss": 0.8863, "step": 13100 }, { "epoch": 1.09, "learning_rate": 3.8558878142061355e-06, "loss": 0.8394, "step": 13110 }, { "epoch": 1.09, "learning_rate": 3.855776958678601e-06, "loss": 0.9027, "step": 13120 }, { "epoch": 1.09, "learning_rate": 3.855666103151068e-06, "loss": 0.8471, "step": 13130 }, { "epoch": 1.09, "learning_rate": 3.855555247623534e-06, "loss": 0.9267, "step": 13140 }, { "epoch": 1.09, "learning_rate": 3.855444392096001e-06, "loss": 0.8671, "step": 13150 }, { "epoch": 1.09, "learning_rate": 3.855333536568467e-06, "loss": 0.8022, "step": 13160 }, { "epoch": 1.09, "learning_rate": 3.855222681040933e-06, "loss": 0.8301, "step": 13170 }, { "epoch": 1.1, "learning_rate": 3.8551118255134e-06, "loss": 0.8786, "step": 13180 }, { "epoch": 1.1, "learning_rate": 3.855000969985866e-06, "loss": 0.9343, "step": 13190 }, { "epoch": 1.1, "learning_rate": 3.854890114458332e-06, "loss": 0.863, "step": 13200 }, { "epoch": 1.1, "learning_rate": 3.8547792589307984e-06, "loss": 0.8142, "step": 13210 }, { "epoch": 1.1, "learning_rate": 3.854668403403264e-06, "loss": 0.7449, "step": 13220 }, { "epoch": 1.1, "learning_rate": 3.854557547875731e-06, "loss": 0.7722, "step": 13230 }, { "epoch": 1.1, "learning_rate": 3.854446692348197e-06, "loss": 0.8211, "step": 13240 }, { "epoch": 1.1, "learning_rate": 3.854335836820663e-06, "loss": 0.828, "step": 13250 }, { "epoch": 1.1, "learning_rate": 3.8542249812931295e-06, "loss": 0.8702, "step": 13260 }, { "epoch": 1.1, "learning_rate": 3.854114125765596e-06, "loss": 0.8876, "step": 13270 }, { "epoch": 1.1, "learning_rate": 3.854003270238062e-06, "loss": 0.8997, "step": 13280 }, { "epoch": 1.1, "learning_rate": 3.853892414710529e-06, "loss": 0.902, "step": 13290 }, { "epoch": 1.11, "learning_rate": 3.853781559182995e-06, "loss": 0.9102, "step": 13300 }, { "epoch": 1.11, "learning_rate": 3.853670703655461e-06, "loss": 0.848, "step": 13310 }, { "epoch": 1.11, "learning_rate": 3.853559848127927e-06, "loss": 0.8377, "step": 13320 }, { "epoch": 1.11, "learning_rate": 3.853448992600393e-06, "loss": 0.8834, "step": 13330 }, { "epoch": 1.11, "learning_rate": 3.85333813707286e-06, "loss": 0.9372, "step": 13340 }, { "epoch": 1.11, "learning_rate": 3.853227281545326e-06, "loss": 0.8443, "step": 13350 }, { "epoch": 1.11, "learning_rate": 3.853116426017792e-06, "loss": 0.763, "step": 13360 }, { "epoch": 1.11, "learning_rate": 3.853005570490258e-06, "loss": 0.8031, "step": 13370 }, { "epoch": 1.11, "learning_rate": 3.852894714962724e-06, "loss": 0.8709, "step": 13380 }, { "epoch": 1.11, "learning_rate": 3.852783859435191e-06, "loss": 0.876, "step": 13390 }, { "epoch": 1.11, "learning_rate": 3.852673003907658e-06, "loss": 0.8029, "step": 13400 }, { "epoch": 1.11, "learning_rate": 3.8525621483801235e-06, "loss": 0.824, "step": 13410 }, { "epoch": 1.12, "learning_rate": 3.85245129285259e-06, "loss": 0.7516, "step": 13420 }, { "epoch": 1.12, "learning_rate": 3.852340437325056e-06, "loss": 0.775, "step": 13430 }, { "epoch": 1.12, "learning_rate": 3.852229581797522e-06, "loss": 0.89, "step": 13440 }, { "epoch": 1.12, "learning_rate": 3.852118726269989e-06, "loss": 0.8679, "step": 13450 }, { "epoch": 1.12, "learning_rate": 3.8520078707424545e-06, "loss": 0.8179, "step": 13460 }, { "epoch": 1.12, "learning_rate": 3.85189701521492e-06, "loss": 0.8005, "step": 13470 }, { "epoch": 1.12, "learning_rate": 3.851786159687387e-06, "loss": 0.853, "step": 13480 }, { "epoch": 1.12, "learning_rate": 3.851675304159853e-06, "loss": 0.8826, "step": 13490 }, { "epoch": 1.12, "learning_rate": 3.85156444863232e-06, "loss": 0.8943, "step": 13500 }, { "epoch": 1.12, "learning_rate": 3.851453593104786e-06, "loss": 0.8661, "step": 13510 }, { "epoch": 1.12, "learning_rate": 3.851342737577252e-06, "loss": 0.8214, "step": 13520 }, { "epoch": 1.12, "learning_rate": 3.851231882049719e-06, "loss": 0.8073, "step": 13530 }, { "epoch": 1.13, "learning_rate": 3.851121026522185e-06, "loss": 0.8135, "step": 13540 }, { "epoch": 1.13, "learning_rate": 3.851010170994651e-06, "loss": 0.8536, "step": 13550 }, { "epoch": 1.13, "learning_rate": 3.8508993154671175e-06, "loss": 0.8828, "step": 13560 }, { "epoch": 1.13, "learning_rate": 3.850788459939583e-06, "loss": 0.8866, "step": 13570 }, { "epoch": 1.13, "learning_rate": 3.85067760441205e-06, "loss": 0.851, "step": 13580 }, { "epoch": 1.13, "learning_rate": 3.850566748884516e-06, "loss": 0.8805, "step": 13590 }, { "epoch": 1.13, "learning_rate": 3.850455893356982e-06, "loss": 0.8275, "step": 13600 }, { "epoch": 1.13, "learning_rate": 3.8503450378294486e-06, "loss": 0.8358, "step": 13610 }, { "epoch": 1.13, "learning_rate": 3.850234182301914e-06, "loss": 0.8151, "step": 13620 }, { "epoch": 1.13, "learning_rate": 3.850123326774381e-06, "loss": 0.7986, "step": 13630 }, { "epoch": 1.13, "learning_rate": 3.850012471246848e-06, "loss": 0.8914, "step": 13640 }, { "epoch": 1.13, "learning_rate": 3.849901615719314e-06, "loss": 0.8255, "step": 13650 }, { "epoch": 1.14, "learning_rate": 3.8497907601917805e-06, "loss": 0.8707, "step": 13660 }, { "epoch": 1.14, "learning_rate": 3.849679904664246e-06, "loss": 0.9258, "step": 13670 }, { "epoch": 1.14, "learning_rate": 3.849569049136712e-06, "loss": 0.8869, "step": 13680 }, { "epoch": 1.14, "learning_rate": 3.849458193609179e-06, "loss": 0.9051, "step": 13690 }, { "epoch": 1.14, "learning_rate": 3.849347338081645e-06, "loss": 0.8399, "step": 13700 }, { "epoch": 1.14, "learning_rate": 3.849236482554111e-06, "loss": 0.858, "step": 13710 }, { "epoch": 1.14, "learning_rate": 3.849125627026577e-06, "loss": 0.8067, "step": 13720 }, { "epoch": 1.14, "learning_rate": 3.849014771499043e-06, "loss": 0.82, "step": 13730 }, { "epoch": 1.14, "learning_rate": 3.84890391597151e-06, "loss": 0.8863, "step": 13740 }, { "epoch": 1.14, "learning_rate": 3.848793060443976e-06, "loss": 0.8162, "step": 13750 }, { "epoch": 1.14, "learning_rate": 3.8486822049164426e-06, "loss": 0.8964, "step": 13760 }, { "epoch": 1.14, "learning_rate": 3.848571349388909e-06, "loss": 0.8825, "step": 13770 }, { "epoch": 1.15, "learning_rate": 3.848460493861375e-06, "loss": 0.7313, "step": 13780 }, { "epoch": 1.15, "learning_rate": 3.848349638333841e-06, "loss": 0.8928, "step": 13790 }, { "epoch": 1.15, "learning_rate": 3.848238782806308e-06, "loss": 0.7983, "step": 13800 }, { "epoch": 1.15, "learning_rate": 3.848127927278774e-06, "loss": 0.8613, "step": 13810 }, { "epoch": 1.15, "learning_rate": 3.84801707175124e-06, "loss": 0.8406, "step": 13820 }, { "epoch": 1.15, "learning_rate": 3.847906216223706e-06, "loss": 0.79, "step": 13830 }, { "epoch": 1.15, "learning_rate": 3.847795360696172e-06, "loss": 0.8938, "step": 13840 }, { "epoch": 1.15, "learning_rate": 3.847684505168639e-06, "loss": 0.907, "step": 13850 }, { "epoch": 1.15, "learning_rate": 3.847573649641105e-06, "loss": 0.7934, "step": 13860 }, { "epoch": 1.15, "learning_rate": 3.847462794113571e-06, "loss": 0.9302, "step": 13870 }, { "epoch": 1.15, "learning_rate": 3.847351938586038e-06, "loss": 0.8043, "step": 13880 }, { "epoch": 1.15, "learning_rate": 3.847241083058504e-06, "loss": 0.8848, "step": 13890 }, { "epoch": 1.16, "learning_rate": 3.847130227530971e-06, "loss": 0.8063, "step": 13900 }, { "epoch": 1.16, "learning_rate": 3.8470193720034366e-06, "loss": 0.8381, "step": 13910 }, { "epoch": 1.16, "learning_rate": 3.8469085164759024e-06, "loss": 0.8126, "step": 13920 }, { "epoch": 1.16, "learning_rate": 3.846797660948369e-06, "loss": 0.8792, "step": 13930 }, { "epoch": 1.16, "learning_rate": 3.846686805420835e-06, "loss": 0.8369, "step": 13940 }, { "epoch": 1.16, "learning_rate": 3.846575949893301e-06, "loss": 0.7746, "step": 13950 }, { "epoch": 1.16, "learning_rate": 3.846465094365768e-06, "loss": 0.7769, "step": 13960 }, { "epoch": 1.16, "learning_rate": 3.8463542388382335e-06, "loss": 0.7907, "step": 13970 }, { "epoch": 1.16, "learning_rate": 3.8462433833107e-06, "loss": 0.9256, "step": 13980 }, { "epoch": 1.16, "learning_rate": 3.846132527783166e-06, "loss": 0.8652, "step": 13990 }, { "epoch": 1.16, "learning_rate": 3.846021672255633e-06, "loss": 0.8234, "step": 14000 }, { "epoch": 1.16, "learning_rate": 3.8459108167280995e-06, "loss": 0.8296, "step": 14010 }, { "epoch": 1.17, "learning_rate": 3.845799961200565e-06, "loss": 0.7672, "step": 14020 }, { "epoch": 1.17, "learning_rate": 3.845689105673031e-06, "loss": 0.8778, "step": 14030 }, { "epoch": 1.17, "learning_rate": 3.845578250145498e-06, "loss": 0.8775, "step": 14040 }, { "epoch": 1.17, "learning_rate": 3.845467394617964e-06, "loss": 0.9085, "step": 14050 }, { "epoch": 1.17, "learning_rate": 3.84535653909043e-06, "loss": 0.8609, "step": 14060 }, { "epoch": 1.17, "learning_rate": 3.8452456835628964e-06, "loss": 0.8475, "step": 14070 }, { "epoch": 1.17, "learning_rate": 3.845134828035362e-06, "loss": 0.8679, "step": 14080 }, { "epoch": 1.17, "learning_rate": 3.845023972507829e-06, "loss": 0.905, "step": 14090 }, { "epoch": 1.17, "learning_rate": 3.844913116980295e-06, "loss": 0.8669, "step": 14100 }, { "epoch": 1.17, "learning_rate": 3.844802261452762e-06, "loss": 0.8095, "step": 14110 }, { "epoch": 1.17, "learning_rate": 3.8446914059252275e-06, "loss": 0.7809, "step": 14120 }, { "epoch": 1.17, "learning_rate": 3.844580550397694e-06, "loss": 0.8844, "step": 14130 }, { "epoch": 1.18, "learning_rate": 3.84446969487016e-06, "loss": 0.8722, "step": 14140 }, { "epoch": 1.18, "learning_rate": 3.844358839342627e-06, "loss": 0.7899, "step": 14150 }, { "epoch": 1.18, "learning_rate": 3.844247983815093e-06, "loss": 0.8375, "step": 14160 }, { "epoch": 1.18, "learning_rate": 3.844137128287559e-06, "loss": 0.8595, "step": 14170 }, { "epoch": 1.18, "learning_rate": 3.844026272760025e-06, "loss": 0.8232, "step": 14180 }, { "epoch": 1.18, "learning_rate": 3.843915417232491e-06, "loss": 0.9984, "step": 14190 }, { "epoch": 1.18, "learning_rate": 3.843804561704958e-06, "loss": 0.9479, "step": 14200 }, { "epoch": 1.18, "learning_rate": 3.843693706177424e-06, "loss": 0.8222, "step": 14210 }, { "epoch": 1.18, "learning_rate": 3.8435828506498904e-06, "loss": 0.7673, "step": 14220 }, { "epoch": 1.18, "learning_rate": 3.843471995122356e-06, "loss": 0.8322, "step": 14230 }, { "epoch": 1.18, "learning_rate": 3.843361139594823e-06, "loss": 0.8988, "step": 14240 }, { "epoch": 1.18, "learning_rate": 3.84325028406729e-06, "loss": 0.822, "step": 14250 }, { "epoch": 1.19, "learning_rate": 3.843139428539756e-06, "loss": 0.8572, "step": 14260 }, { "epoch": 1.19, "learning_rate": 3.8430285730122215e-06, "loss": 0.8282, "step": 14270 }, { "epoch": 1.19, "learning_rate": 3.842917717484688e-06, "loss": 0.8092, "step": 14280 }, { "epoch": 1.19, "learning_rate": 3.842806861957154e-06, "loss": 0.8848, "step": 14290 }, { "epoch": 1.19, "learning_rate": 3.84269600642962e-06, "loss": 0.8664, "step": 14300 }, { "epoch": 1.19, "learning_rate": 3.842585150902087e-06, "loss": 0.7658, "step": 14310 }, { "epoch": 1.19, "learning_rate": 3.8424742953745526e-06, "loss": 0.869, "step": 14320 }, { "epoch": 1.19, "learning_rate": 3.842363439847019e-06, "loss": 0.8655, "step": 14330 }, { "epoch": 1.19, "learning_rate": 3.842252584319485e-06, "loss": 0.9049, "step": 14340 }, { "epoch": 1.19, "learning_rate": 3.842141728791952e-06, "loss": 0.8729, "step": 14350 }, { "epoch": 1.19, "learning_rate": 3.842030873264418e-06, "loss": 0.9013, "step": 14360 }, { "epoch": 1.19, "learning_rate": 3.8419200177368845e-06, "loss": 0.7563, "step": 14370 }, { "epoch": 1.2, "learning_rate": 3.84180916220935e-06, "loss": 0.8177, "step": 14380 }, { "epoch": 1.2, "learning_rate": 3.841698306681817e-06, "loss": 0.9097, "step": 14390 }, { "epoch": 1.2, "learning_rate": 3.841587451154283e-06, "loss": 0.903, "step": 14400 }, { "epoch": 1.2, "learning_rate": 3.841476595626749e-06, "loss": 0.8771, "step": 14410 }, { "epoch": 1.2, "learning_rate": 3.8413657400992155e-06, "loss": 0.837, "step": 14420 }, { "epoch": 1.2, "learning_rate": 3.841254884571681e-06, "loss": 0.8183, "step": 14430 }, { "epoch": 1.2, "learning_rate": 3.841144029044148e-06, "loss": 0.8121, "step": 14440 }, { "epoch": 1.2, "learning_rate": 3.841033173516614e-06, "loss": 0.8774, "step": 14450 }, { "epoch": 1.2, "learning_rate": 3.840922317989081e-06, "loss": 0.8424, "step": 14460 }, { "epoch": 1.2, "learning_rate": 3.8408114624615466e-06, "loss": 0.7865, "step": 14470 }, { "epoch": 1.2, "learning_rate": 3.840700606934013e-06, "loss": 0.8632, "step": 14480 }, { "epoch": 1.2, "learning_rate": 3.840589751406479e-06, "loss": 0.9012, "step": 14490 }, { "epoch": 1.21, "learning_rate": 3.840478895878946e-06, "loss": 0.7749, "step": 14500 }, { "epoch": 1.21, "learning_rate": 3.840368040351412e-06, "loss": 0.8542, "step": 14510 }, { "epoch": 1.21, "learning_rate": 3.8402571848238785e-06, "loss": 0.8935, "step": 14520 }, { "epoch": 1.21, "learning_rate": 3.840146329296344e-06, "loss": 0.8558, "step": 14530 }, { "epoch": 1.21, "learning_rate": 3.84003547376881e-06, "loss": 0.8581, "step": 14540 }, { "epoch": 1.21, "learning_rate": 3.839924618241277e-06, "loss": 0.7606, "step": 14550 }, { "epoch": 1.21, "learning_rate": 3.839813762713743e-06, "loss": 0.8096, "step": 14560 }, { "epoch": 1.21, "learning_rate": 3.8397029071862095e-06, "loss": 0.8043, "step": 14570 }, { "epoch": 1.21, "learning_rate": 3.839592051658675e-06, "loss": 0.7908, "step": 14580 }, { "epoch": 1.21, "learning_rate": 3.839481196131142e-06, "loss": 0.9462, "step": 14590 }, { "epoch": 1.21, "learning_rate": 3.839370340603608e-06, "loss": 0.8358, "step": 14600 }, { "epoch": 1.21, "learning_rate": 3.839259485076075e-06, "loss": 0.8069, "step": 14610 }, { "epoch": 1.22, "learning_rate": 3.8391486295485406e-06, "loss": 0.8029, "step": 14620 }, { "epoch": 1.22, "learning_rate": 3.839037774021007e-06, "loss": 0.8743, "step": 14630 }, { "epoch": 1.22, "learning_rate": 3.838926918493473e-06, "loss": 0.892, "step": 14640 }, { "epoch": 1.22, "learning_rate": 3.838816062965939e-06, "loss": 0.8018, "step": 14650 }, { "epoch": 1.22, "learning_rate": 3.838705207438406e-06, "loss": 0.8297, "step": 14660 }, { "epoch": 1.22, "learning_rate": 3.838594351910872e-06, "loss": 0.8597, "step": 14670 }, { "epoch": 1.22, "learning_rate": 3.838483496383338e-06, "loss": 0.8975, "step": 14680 }, { "epoch": 1.22, "learning_rate": 3.838372640855804e-06, "loss": 0.8741, "step": 14690 }, { "epoch": 1.22, "learning_rate": 3.838261785328271e-06, "loss": 0.9149, "step": 14700 }, { "epoch": 1.22, "learning_rate": 3.838150929800737e-06, "loss": 0.7957, "step": 14710 }, { "epoch": 1.22, "learning_rate": 3.8380400742732035e-06, "loss": 0.7681, "step": 14720 }, { "epoch": 1.22, "learning_rate": 3.837929218745669e-06, "loss": 0.8803, "step": 14730 }, { "epoch": 1.23, "learning_rate": 3.837818363218136e-06, "loss": 0.8636, "step": 14740 }, { "epoch": 1.23, "learning_rate": 3.837707507690602e-06, "loss": 0.8819, "step": 14750 }, { "epoch": 1.23, "learning_rate": 3.837596652163068e-06, "loss": 0.7988, "step": 14760 }, { "epoch": 1.23, "learning_rate": 3.8374857966355346e-06, "loss": 0.8611, "step": 14770 }, { "epoch": 1.23, "learning_rate": 3.8373749411080004e-06, "loss": 0.8163, "step": 14780 }, { "epoch": 1.23, "learning_rate": 3.837264085580467e-06, "loss": 0.859, "step": 14790 }, { "epoch": 1.23, "learning_rate": 3.837153230052933e-06, "loss": 0.8217, "step": 14800 }, { "epoch": 1.23, "learning_rate": 3.8370423745254e-06, "loss": 0.826, "step": 14810 }, { "epoch": 1.23, "learning_rate": 3.836931518997866e-06, "loss": 0.7797, "step": 14820 }, { "epoch": 1.23, "learning_rate": 3.836820663470332e-06, "loss": 0.8463, "step": 14830 }, { "epoch": 1.23, "learning_rate": 3.836709807942798e-06, "loss": 0.8958, "step": 14840 }, { "epoch": 1.23, "learning_rate": 3.836598952415265e-06, "loss": 0.8467, "step": 14850 }, { "epoch": 1.24, "learning_rate": 3.836488096887731e-06, "loss": 0.8303, "step": 14860 }, { "epoch": 1.24, "learning_rate": 3.8363772413601975e-06, "loss": 0.7723, "step": 14870 }, { "epoch": 1.24, "learning_rate": 3.836266385832663e-06, "loss": 0.8561, "step": 14880 }, { "epoch": 1.24, "learning_rate": 3.836155530305129e-06, "loss": 0.9235, "step": 14890 }, { "epoch": 1.24, "learning_rate": 3.836044674777596e-06, "loss": 0.8635, "step": 14900 }, { "epoch": 1.24, "learning_rate": 3.835933819250062e-06, "loss": 0.8496, "step": 14910 }, { "epoch": 1.24, "learning_rate": 3.835822963722529e-06, "loss": 0.7801, "step": 14920 }, { "epoch": 1.24, "learning_rate": 3.8357121081949945e-06, "loss": 0.809, "step": 14930 }, { "epoch": 1.24, "learning_rate": 3.835601252667461e-06, "loss": 0.9309, "step": 14940 }, { "epoch": 1.24, "learning_rate": 3.835490397139927e-06, "loss": 0.8571, "step": 14950 }, { "epoch": 1.24, "learning_rate": 3.835379541612394e-06, "loss": 0.8345, "step": 14960 }, { "epoch": 1.24, "learning_rate": 3.83526868608486e-06, "loss": 0.878, "step": 14970 }, { "epoch": 1.25, "learning_rate": 3.835157830557326e-06, "loss": 0.7699, "step": 14980 }, { "epoch": 1.25, "learning_rate": 3.835046975029792e-06, "loss": 0.8806, "step": 14990 }, { "epoch": 1.25, "learning_rate": 3.834936119502258e-06, "loss": 0.8641, "step": 15000 }, { "epoch": 1.25, "learning_rate": 3.834825263974725e-06, "loss": 0.8589, "step": 15010 }, { "epoch": 1.25, "learning_rate": 3.834714408447191e-06, "loss": 0.8495, "step": 15020 }, { "epoch": 1.25, "learning_rate": 3.834603552919657e-06, "loss": 0.8007, "step": 15030 }, { "epoch": 1.25, "learning_rate": 3.834492697392123e-06, "loss": 0.8914, "step": 15040 }, { "epoch": 1.25, "learning_rate": 3.83438184186459e-06, "loss": 0.9079, "step": 15050 }, { "epoch": 1.25, "learning_rate": 3.834270986337056e-06, "loss": 0.8576, "step": 15060 }, { "epoch": 1.25, "learning_rate": 3.834160130809523e-06, "loss": 0.9474, "step": 15070 }, { "epoch": 1.25, "learning_rate": 3.8340492752819885e-06, "loss": 0.7886, "step": 15080 }, { "epoch": 1.25, "learning_rate": 3.833938419754455e-06, "loss": 0.9156, "step": 15090 }, { "epoch": 1.26, "learning_rate": 3.833827564226921e-06, "loss": 0.8672, "step": 15100 }, { "epoch": 1.26, "learning_rate": 3.833716708699388e-06, "loss": 0.7742, "step": 15110 }, { "epoch": 1.26, "learning_rate": 3.833605853171854e-06, "loss": 0.8307, "step": 15120 }, { "epoch": 1.26, "learning_rate": 3.8334949976443195e-06, "loss": 0.8144, "step": 15130 }, { "epoch": 1.26, "learning_rate": 3.833384142116786e-06, "loss": 0.8519, "step": 15140 }, { "epoch": 1.26, "learning_rate": 3.833273286589252e-06, "loss": 0.8663, "step": 15150 }, { "epoch": 1.26, "learning_rate": 3.833162431061719e-06, "loss": 0.7777, "step": 15160 }, { "epoch": 1.26, "learning_rate": 3.833051575534185e-06, "loss": 0.7917, "step": 15170 }, { "epoch": 1.26, "learning_rate": 3.832940720006651e-06, "loss": 0.8399, "step": 15180 }, { "epoch": 1.26, "learning_rate": 3.832829864479117e-06, "loss": 0.9383, "step": 15190 }, { "epoch": 1.26, "learning_rate": 3.832719008951584e-06, "loss": 0.8301, "step": 15200 }, { "epoch": 1.26, "learning_rate": 3.83260815342405e-06, "loss": 0.8126, "step": 15210 }, { "epoch": 1.27, "learning_rate": 3.832497297896517e-06, "loss": 0.8416, "step": 15220 }, { "epoch": 1.27, "learning_rate": 3.8323864423689825e-06, "loss": 0.8499, "step": 15230 }, { "epoch": 1.27, "learning_rate": 3.832275586841448e-06, "loss": 0.8842, "step": 15240 }, { "epoch": 1.27, "learning_rate": 3.832164731313915e-06, "loss": 0.8522, "step": 15250 }, { "epoch": 1.27, "learning_rate": 3.832053875786381e-06, "loss": 0.8134, "step": 15260 }, { "epoch": 1.27, "learning_rate": 3.831943020258848e-06, "loss": 0.8327, "step": 15270 }, { "epoch": 1.27, "learning_rate": 3.8318321647313135e-06, "loss": 0.7981, "step": 15280 }, { "epoch": 1.27, "learning_rate": 3.83172130920378e-06, "loss": 0.8629, "step": 15290 }, { "epoch": 1.27, "learning_rate": 3.831610453676246e-06, "loss": 0.852, "step": 15300 }, { "epoch": 1.27, "learning_rate": 3.831499598148713e-06, "loss": 0.8693, "step": 15310 }, { "epoch": 1.27, "learning_rate": 3.831388742621179e-06, "loss": 0.8458, "step": 15320 }, { "epoch": 1.27, "learning_rate": 3.831277887093645e-06, "loss": 0.8967, "step": 15330 }, { "epoch": 1.28, "learning_rate": 3.831167031566111e-06, "loss": 0.8951, "step": 15340 }, { "epoch": 1.28, "learning_rate": 3.831056176038577e-06, "loss": 0.8068, "step": 15350 }, { "epoch": 1.28, "learning_rate": 3.830945320511044e-06, "loss": 0.8481, "step": 15360 }, { "epoch": 1.28, "learning_rate": 3.83083446498351e-06, "loss": 0.7911, "step": 15370 }, { "epoch": 1.28, "learning_rate": 3.8307236094559765e-06, "loss": 0.8085, "step": 15380 }, { "epoch": 1.28, "learning_rate": 3.830612753928442e-06, "loss": 0.9204, "step": 15390 }, { "epoch": 1.28, "learning_rate": 3.830501898400909e-06, "loss": 0.7842, "step": 15400 }, { "epoch": 1.28, "learning_rate": 3.830391042873375e-06, "loss": 0.8366, "step": 15410 }, { "epoch": 1.28, "learning_rate": 3.830280187345842e-06, "loss": 0.7936, "step": 15420 }, { "epoch": 1.28, "learning_rate": 3.8301693318183075e-06, "loss": 0.8948, "step": 15430 }, { "epoch": 1.28, "learning_rate": 3.830058476290774e-06, "loss": 0.8901, "step": 15440 }, { "epoch": 1.28, "learning_rate": 3.82994762076324e-06, "loss": 0.8359, "step": 15450 }, { "epoch": 1.29, "learning_rate": 3.829836765235707e-06, "loss": 0.8418, "step": 15460 }, { "epoch": 1.29, "learning_rate": 3.829725909708173e-06, "loss": 0.838, "step": 15470 }, { "epoch": 1.29, "learning_rate": 3.829615054180639e-06, "loss": 0.9352, "step": 15480 }, { "epoch": 1.29, "learning_rate": 3.829504198653105e-06, "loss": 0.9267, "step": 15490 }, { "epoch": 1.29, "learning_rate": 3.829393343125571e-06, "loss": 0.8588, "step": 15500 }, { "epoch": 1.29, "learning_rate": 3.829282487598038e-06, "loss": 0.8587, "step": 15510 }, { "epoch": 1.29, "learning_rate": 3.829171632070504e-06, "loss": 0.8351, "step": 15520 }, { "epoch": 1.29, "learning_rate": 3.8290607765429705e-06, "loss": 0.8892, "step": 15530 }, { "epoch": 1.29, "learning_rate": 3.828949921015436e-06, "loss": 0.8985, "step": 15540 }, { "epoch": 1.29, "learning_rate": 3.828839065487903e-06, "loss": 0.7975, "step": 15550 }, { "epoch": 1.29, "learning_rate": 3.828728209960369e-06, "loss": 0.8153, "step": 15560 }, { "epoch": 1.29, "learning_rate": 3.828617354432836e-06, "loss": 0.8448, "step": 15570 }, { "epoch": 1.29, "learning_rate": 3.8285064989053015e-06, "loss": 0.7535, "step": 15580 }, { "epoch": 1.3, "learning_rate": 3.828395643377767e-06, "loss": 0.9126, "step": 15590 }, { "epoch": 1.3, "learning_rate": 3.828284787850234e-06, "loss": 0.8232, "step": 15600 }, { "epoch": 1.3, "learning_rate": 3.8281739323227e-06, "loss": 0.855, "step": 15610 }, { "epoch": 1.3, "learning_rate": 3.828063076795167e-06, "loss": 0.8243, "step": 15620 }, { "epoch": 1.3, "learning_rate": 3.827952221267633e-06, "loss": 0.8416, "step": 15630 }, { "epoch": 1.3, "learning_rate": 3.827841365740099e-06, "loss": 0.9101, "step": 15640 }, { "epoch": 1.3, "learning_rate": 3.827730510212565e-06, "loss": 0.8155, "step": 15650 }, { "epoch": 1.3, "learning_rate": 3.827619654685032e-06, "loss": 0.8187, "step": 15660 }, { "epoch": 1.3, "learning_rate": 3.827508799157498e-06, "loss": 0.8507, "step": 15670 }, { "epoch": 1.3, "learning_rate": 3.8273979436299645e-06, "loss": 0.777, "step": 15680 }, { "epoch": 1.3, "learning_rate": 3.82728708810243e-06, "loss": 0.8932, "step": 15690 }, { "epoch": 1.3, "learning_rate": 3.827176232574896e-06, "loss": 0.79, "step": 15700 }, { "epoch": 1.31, "learning_rate": 3.827065377047363e-06, "loss": 0.876, "step": 15710 }, { "epoch": 1.31, "learning_rate": 3.826954521519829e-06, "loss": 0.8742, "step": 15720 }, { "epoch": 1.31, "learning_rate": 3.8268436659922955e-06, "loss": 0.8659, "step": 15730 }, { "epoch": 1.31, "learning_rate": 3.826732810464761e-06, "loss": 0.8674, "step": 15740 }, { "epoch": 1.31, "learning_rate": 3.826621954937228e-06, "loss": 0.8408, "step": 15750 }, { "epoch": 1.31, "learning_rate": 3.826511099409694e-06, "loss": 0.8023, "step": 15760 }, { "epoch": 1.31, "learning_rate": 3.826400243882161e-06, "loss": 0.8146, "step": 15770 }, { "epoch": 1.31, "learning_rate": 3.826289388354627e-06, "loss": 0.8659, "step": 15780 }, { "epoch": 1.31, "learning_rate": 3.826178532827093e-06, "loss": 0.851, "step": 15790 }, { "epoch": 1.31, "learning_rate": 3.826067677299559e-06, "loss": 0.8423, "step": 15800 }, { "epoch": 1.31, "learning_rate": 3.825956821772026e-06, "loss": 0.8476, "step": 15810 }, { "epoch": 1.31, "learning_rate": 3.825845966244492e-06, "loss": 0.7375, "step": 15820 }, { "epoch": 1.32, "learning_rate": 3.825735110716958e-06, "loss": 0.8694, "step": 15830 }, { "epoch": 1.32, "learning_rate": 3.825624255189424e-06, "loss": 0.879, "step": 15840 }, { "epoch": 1.32, "learning_rate": 3.82551339966189e-06, "loss": 0.8245, "step": 15850 }, { "epoch": 1.32, "learning_rate": 3.825402544134357e-06, "loss": 0.8009, "step": 15860 }, { "epoch": 1.32, "learning_rate": 3.825291688606823e-06, "loss": 0.7965, "step": 15870 }, { "epoch": 1.32, "learning_rate": 3.8251808330792895e-06, "loss": 0.7713, "step": 15880 }, { "epoch": 1.32, "learning_rate": 3.825069977551755e-06, "loss": 0.9542, "step": 15890 }, { "epoch": 1.32, "learning_rate": 3.824959122024222e-06, "loss": 0.8159, "step": 15900 }, { "epoch": 1.32, "learning_rate": 3.824848266496688e-06, "loss": 0.8065, "step": 15910 }, { "epoch": 1.32, "learning_rate": 3.824737410969155e-06, "loss": 0.7912, "step": 15920 }, { "epoch": 1.32, "learning_rate": 3.824626555441621e-06, "loss": 0.83, "step": 15930 }, { "epoch": 1.32, "learning_rate": 3.8245156999140865e-06, "loss": 0.9341, "step": 15940 }, { "epoch": 1.33, "learning_rate": 3.824404844386553e-06, "loss": 0.924, "step": 15950 }, { "epoch": 1.33, "learning_rate": 3.824293988859019e-06, "loss": 0.8725, "step": 15960 }, { "epoch": 1.33, "learning_rate": 3.824183133331486e-06, "loss": 0.8436, "step": 15970 }, { "epoch": 1.33, "learning_rate": 3.824072277803952e-06, "loss": 0.8116, "step": 15980 }, { "epoch": 1.33, "learning_rate": 3.823961422276418e-06, "loss": 0.8747, "step": 15990 }, { "epoch": 1.33, "learning_rate": 3.823850566748884e-06, "loss": 0.8465, "step": 16000 }, { "epoch": 1.33, "learning_rate": 3.823739711221351e-06, "loss": 0.8261, "step": 16010 }, { "epoch": 1.33, "learning_rate": 3.823628855693817e-06, "loss": 0.7267, "step": 16020 }, { "epoch": 1.33, "learning_rate": 3.8235180001662836e-06, "loss": 0.8025, "step": 16030 }, { "epoch": 1.33, "learning_rate": 3.8234071446387494e-06, "loss": 0.8884, "step": 16040 }, { "epoch": 1.33, "learning_rate": 3.823296289111215e-06, "loss": 0.8882, "step": 16050 }, { "epoch": 1.33, "learning_rate": 3.823185433583682e-06, "loss": 0.8593, "step": 16060 }, { "epoch": 1.34, "learning_rate": 3.823074578056148e-06, "loss": 0.7729, "step": 16070 }, { "epoch": 1.34, "learning_rate": 3.822963722528615e-06, "loss": 0.7738, "step": 16080 }, { "epoch": 1.34, "learning_rate": 3.8228528670010805e-06, "loss": 0.9102, "step": 16090 }, { "epoch": 1.34, "learning_rate": 3.822742011473547e-06, "loss": 0.7596, "step": 16100 }, { "epoch": 1.34, "learning_rate": 3.822631155946013e-06, "loss": 0.8009, "step": 16110 }, { "epoch": 1.34, "learning_rate": 3.82252030041848e-06, "loss": 0.7789, "step": 16120 }, { "epoch": 1.34, "learning_rate": 3.822409444890946e-06, "loss": 0.8132, "step": 16130 }, { "epoch": 1.34, "learning_rate": 3.822298589363412e-06, "loss": 0.923, "step": 16140 }, { "epoch": 1.34, "learning_rate": 3.822187733835878e-06, "loss": 0.8048, "step": 16150 }, { "epoch": 1.34, "learning_rate": 3.822076878308345e-06, "loss": 0.8246, "step": 16160 }, { "epoch": 1.34, "learning_rate": 3.821966022780811e-06, "loss": 0.8649, "step": 16170 }, { "epoch": 1.34, "learning_rate": 3.821855167253277e-06, "loss": 0.833, "step": 16180 }, { "epoch": 1.35, "learning_rate": 3.8217443117257434e-06, "loss": 0.8798, "step": 16190 }, { "epoch": 1.35, "learning_rate": 3.821633456198209e-06, "loss": 0.8654, "step": 16200 }, { "epoch": 1.35, "learning_rate": 3.821522600670675e-06, "loss": 0.7831, "step": 16210 }, { "epoch": 1.35, "learning_rate": 3.821411745143142e-06, "loss": 0.8071, "step": 16220 }, { "epoch": 1.35, "learning_rate": 3.821300889615609e-06, "loss": 0.8566, "step": 16230 }, { "epoch": 1.35, "learning_rate": 3.8211900340880745e-06, "loss": 0.9032, "step": 16240 }, { "epoch": 1.35, "learning_rate": 3.821079178560541e-06, "loss": 0.8072, "step": 16250 }, { "epoch": 1.35, "learning_rate": 3.820968323033007e-06, "loss": 0.9087, "step": 16260 }, { "epoch": 1.35, "learning_rate": 3.820857467505474e-06, "loss": 0.821, "step": 16270 }, { "epoch": 1.35, "learning_rate": 3.82074661197794e-06, "loss": 0.795, "step": 16280 }, { "epoch": 1.35, "learning_rate": 3.8206357564504055e-06, "loss": 0.8507, "step": 16290 }, { "epoch": 1.35, "learning_rate": 3.820524900922872e-06, "loss": 0.7837, "step": 16300 }, { "epoch": 1.36, "learning_rate": 3.820414045395338e-06, "loss": 0.869, "step": 16310 }, { "epoch": 1.36, "learning_rate": 3.820303189867804e-06, "loss": 0.8062, "step": 16320 }, { "epoch": 1.36, "learning_rate": 3.820192334340271e-06, "loss": 0.7964, "step": 16330 }, { "epoch": 1.36, "learning_rate": 3.8200814788127374e-06, "loss": 0.892, "step": 16340 }, { "epoch": 1.36, "learning_rate": 3.819970623285203e-06, "loss": 0.8758, "step": 16350 }, { "epoch": 1.36, "learning_rate": 3.81985976775767e-06, "loss": 0.8373, "step": 16360 }, { "epoch": 1.36, "learning_rate": 3.819748912230136e-06, "loss": 0.8148, "step": 16370 }, { "epoch": 1.36, "learning_rate": 3.819638056702603e-06, "loss": 0.8244, "step": 16380 }, { "epoch": 1.36, "learning_rate": 3.8195272011750685e-06, "loss": 0.9101, "step": 16390 }, { "epoch": 1.36, "learning_rate": 3.819416345647535e-06, "loss": 0.8403, "step": 16400 }, { "epoch": 1.36, "learning_rate": 3.819305490120001e-06, "loss": 0.7759, "step": 16410 }, { "epoch": 1.36, "learning_rate": 3.819194634592467e-06, "loss": 0.8632, "step": 16420 }, { "epoch": 1.37, "learning_rate": 3.819083779064934e-06, "loss": 0.7544, "step": 16430 }, { "epoch": 1.37, "learning_rate": 3.8189729235373995e-06, "loss": 0.9094, "step": 16440 }, { "epoch": 1.37, "learning_rate": 3.818862068009865e-06, "loss": 0.7764, "step": 16450 }, { "epoch": 1.37, "learning_rate": 3.818751212482332e-06, "loss": 0.7985, "step": 16460 }, { "epoch": 1.37, "learning_rate": 3.818640356954799e-06, "loss": 0.8569, "step": 16470 }, { "epoch": 1.37, "learning_rate": 3.818529501427265e-06, "loss": 0.8072, "step": 16480 }, { "epoch": 1.37, "learning_rate": 3.8184186458997314e-06, "loss": 0.8086, "step": 16490 }, { "epoch": 1.37, "learning_rate": 3.818307790372197e-06, "loss": 0.8412, "step": 16500 }, { "epoch": 1.37, "learning_rate": 3.818196934844664e-06, "loss": 0.853, "step": 16510 }, { "epoch": 1.37, "learning_rate": 3.81808607931713e-06, "loss": 0.8012, "step": 16520 }, { "epoch": 1.37, "learning_rate": 3.817975223789596e-06, "loss": 0.8592, "step": 16530 }, { "epoch": 1.37, "learning_rate": 3.8178643682620625e-06, "loss": 0.9343, "step": 16540 }, { "epoch": 1.38, "learning_rate": 3.817753512734528e-06, "loss": 0.8728, "step": 16550 }, { "epoch": 1.38, "learning_rate": 3.817642657206994e-06, "loss": 0.7994, "step": 16560 }, { "epoch": 1.38, "learning_rate": 3.817531801679461e-06, "loss": 0.788, "step": 16570 }, { "epoch": 1.38, "learning_rate": 3.817420946151927e-06, "loss": 0.8307, "step": 16580 }, { "epoch": 1.38, "learning_rate": 3.8173100906243935e-06, "loss": 0.8214, "step": 16590 }, { "epoch": 1.38, "learning_rate": 3.81719923509686e-06, "loss": 0.7963, "step": 16600 }, { "epoch": 1.38, "learning_rate": 3.817088379569326e-06, "loss": 0.872, "step": 16610 }, { "epoch": 1.38, "learning_rate": 3.816977524041793e-06, "loss": 0.8508, "step": 16620 }, { "epoch": 1.38, "learning_rate": 3.816866668514259e-06, "loss": 0.8224, "step": 16630 }, { "epoch": 1.38, "learning_rate": 3.816755812986725e-06, "loss": 0.8988, "step": 16640 }, { "epoch": 1.38, "learning_rate": 3.816644957459191e-06, "loss": 0.7654, "step": 16650 }, { "epoch": 1.38, "learning_rate": 3.816534101931657e-06, "loss": 0.8487, "step": 16660 }, { "epoch": 1.39, "learning_rate": 3.816423246404124e-06, "loss": 0.8839, "step": 16670 }, { "epoch": 1.39, "learning_rate": 3.81631239087659e-06, "loss": 0.8369, "step": 16680 }, { "epoch": 1.39, "learning_rate": 3.816201535349056e-06, "loss": 0.9018, "step": 16690 }, { "epoch": 1.39, "learning_rate": 3.816090679821522e-06, "loss": 0.8737, "step": 16700 }, { "epoch": 1.39, "learning_rate": 3.815979824293989e-06, "loss": 0.8236, "step": 16710 }, { "epoch": 1.39, "learning_rate": 3.815868968766455e-06, "loss": 0.7791, "step": 16720 }, { "epoch": 1.39, "learning_rate": 3.815758113238922e-06, "loss": 0.7983, "step": 16730 }, { "epoch": 1.39, "learning_rate": 3.8156472577113876e-06, "loss": 0.9035, "step": 16740 }, { "epoch": 1.39, "learning_rate": 3.815536402183854e-06, "loss": 0.8385, "step": 16750 }, { "epoch": 1.39, "learning_rate": 3.81542554665632e-06, "loss": 0.8334, "step": 16760 }, { "epoch": 1.39, "learning_rate": 3.815314691128786e-06, "loss": 0.7885, "step": 16770 }, { "epoch": 1.39, "learning_rate": 3.815203835601253e-06, "loss": 0.8138, "step": 16780 }, { "epoch": 1.4, "learning_rate": 3.815092980073719e-06, "loss": 0.9067, "step": 16790 }, { "epoch": 1.4, "learning_rate": 3.8149821245461845e-06, "loss": 0.8607, "step": 16800 }, { "epoch": 1.4, "learning_rate": 3.814871269018651e-06, "loss": 0.8583, "step": 16810 }, { "epoch": 1.4, "learning_rate": 3.814760413491117e-06, "loss": 0.7702, "step": 16820 }, { "epoch": 1.4, "learning_rate": 3.814649557963584e-06, "loss": 0.7817, "step": 16830 }, { "epoch": 1.4, "learning_rate": 3.81453870243605e-06, "loss": 0.7974, "step": 16840 }, { "epoch": 1.4, "learning_rate": 3.8144278469085164e-06, "loss": 0.7575, "step": 16850 }, { "epoch": 1.4, "learning_rate": 3.8143169913809827e-06, "loss": 0.8364, "step": 16860 }, { "epoch": 1.4, "learning_rate": 3.8142061358534485e-06, "loss": 0.8449, "step": 16870 }, { "epoch": 1.4, "learning_rate": 3.8140952803259153e-06, "loss": 0.826, "step": 16880 }, { "epoch": 1.4, "learning_rate": 3.813984424798381e-06, "loss": 0.8876, "step": 16890 }, { "epoch": 1.4, "learning_rate": 3.813873569270848e-06, "loss": 0.8301, "step": 16900 }, { "epoch": 1.41, "learning_rate": 3.8137627137433137e-06, "loss": 0.8056, "step": 16910 }, { "epoch": 1.41, "learning_rate": 3.81365185821578e-06, "loss": 0.7612, "step": 16920 }, { "epoch": 1.41, "learning_rate": 3.8135410026882463e-06, "loss": 0.8674, "step": 16930 }, { "epoch": 1.41, "learning_rate": 3.8134301471607126e-06, "loss": 0.912, "step": 16940 }, { "epoch": 1.41, "learning_rate": 3.8133192916331785e-06, "loss": 0.8425, "step": 16950 }, { "epoch": 1.41, "learning_rate": 3.813208436105645e-06, "loss": 0.8702, "step": 16960 }, { "epoch": 1.41, "learning_rate": 3.8130975805781115e-06, "loss": 0.8248, "step": 16970 }, { "epoch": 1.41, "learning_rate": 3.812986725050578e-06, "loss": 0.8556, "step": 16980 }, { "epoch": 1.41, "learning_rate": 3.812875869523044e-06, "loss": 0.8892, "step": 16990 }, { "epoch": 1.41, "learning_rate": 3.81276501399551e-06, "loss": 0.8594, "step": 17000 }, { "epoch": 1.41, "learning_rate": 3.8126541584679767e-06, "loss": 0.8351, "step": 17010 }, { "epoch": 1.41, "learning_rate": 3.8125433029404426e-06, "loss": 0.8279, "step": 17020 }, { "epoch": 1.42, "learning_rate": 3.812432447412909e-06, "loss": 0.8604, "step": 17030 }, { "epoch": 1.42, "learning_rate": 3.812321591885375e-06, "loss": 0.9047, "step": 17040 }, { "epoch": 1.42, "learning_rate": 3.8122107363578414e-06, "loss": 0.8315, "step": 17050 }, { "epoch": 1.42, "learning_rate": 3.8120998808303077e-06, "loss": 0.7942, "step": 17060 }, { "epoch": 1.42, "learning_rate": 3.811989025302774e-06, "loss": 0.7921, "step": 17070 }, { "epoch": 1.42, "learning_rate": 3.8118781697752403e-06, "loss": 0.7787, "step": 17080 }, { "epoch": 1.42, "learning_rate": 3.8117673142477066e-06, "loss": 0.8807, "step": 17090 }, { "epoch": 1.42, "learning_rate": 3.811656458720173e-06, "loss": 0.8528, "step": 17100 }, { "epoch": 1.42, "learning_rate": 3.811545603192639e-06, "loss": 0.8393, "step": 17110 }, { "epoch": 1.42, "learning_rate": 3.8114347476651055e-06, "loss": 0.7975, "step": 17120 }, { "epoch": 1.42, "learning_rate": 3.8113238921375714e-06, "loss": 0.8388, "step": 17130 }, { "epoch": 1.42, "learning_rate": 3.811213036610038e-06, "loss": 0.8828, "step": 17140 }, { "epoch": 1.43, "learning_rate": 3.811102181082504e-06, "loss": 0.8485, "step": 17150 }, { "epoch": 1.43, "learning_rate": 3.8109913255549703e-06, "loss": 0.8182, "step": 17160 }, { "epoch": 1.43, "learning_rate": 3.8108804700274366e-06, "loss": 0.8686, "step": 17170 }, { "epoch": 1.43, "learning_rate": 3.810769614499903e-06, "loss": 0.7983, "step": 17180 }, { "epoch": 1.43, "learning_rate": 3.8106587589723687e-06, "loss": 0.9062, "step": 17190 }, { "epoch": 1.43, "learning_rate": 3.8105479034448354e-06, "loss": 0.8472, "step": 17200 }, { "epoch": 1.43, "learning_rate": 3.8104370479173017e-06, "loss": 0.8953, "step": 17210 }, { "epoch": 1.43, "learning_rate": 3.8103261923897676e-06, "loss": 0.8656, "step": 17220 }, { "epoch": 1.43, "learning_rate": 3.8102153368622343e-06, "loss": 0.8392, "step": 17230 }, { "epoch": 1.43, "learning_rate": 3.8101044813347e-06, "loss": 0.8886, "step": 17240 }, { "epoch": 1.43, "learning_rate": 3.809993625807167e-06, "loss": 0.8672, "step": 17250 }, { "epoch": 1.43, "learning_rate": 3.809882770279633e-06, "loss": 0.8116, "step": 17260 }, { "epoch": 1.44, "learning_rate": 3.809771914752099e-06, "loss": 0.8296, "step": 17270 }, { "epoch": 1.44, "learning_rate": 3.8096610592245654e-06, "loss": 0.8758, "step": 17280 }, { "epoch": 1.44, "learning_rate": 3.8095502036970317e-06, "loss": 0.8595, "step": 17290 }, { "epoch": 1.44, "learning_rate": 3.8094393481694976e-06, "loss": 0.8102, "step": 17300 }, { "epoch": 1.44, "learning_rate": 3.8093284926419643e-06, "loss": 0.8659, "step": 17310 }, { "epoch": 1.44, "learning_rate": 3.80921763711443e-06, "loss": 0.8758, "step": 17320 }, { "epoch": 1.44, "learning_rate": 3.809106781586897e-06, "loss": 0.8116, "step": 17330 }, { "epoch": 1.44, "learning_rate": 3.808995926059363e-06, "loss": 0.8651, "step": 17340 }, { "epoch": 1.44, "learning_rate": 3.808885070531829e-06, "loss": 0.811, "step": 17350 }, { "epoch": 1.44, "learning_rate": 3.8087742150042957e-06, "loss": 0.8096, "step": 17360 }, { "epoch": 1.44, "learning_rate": 3.8086633594767616e-06, "loss": 0.8508, "step": 17370 }, { "epoch": 1.44, "learning_rate": 3.808552503949228e-06, "loss": 0.796, "step": 17380 }, { "epoch": 1.45, "learning_rate": 3.8084416484216942e-06, "loss": 0.8233, "step": 17390 }, { "epoch": 1.45, "learning_rate": 3.8083307928941605e-06, "loss": 0.8266, "step": 17400 }, { "epoch": 1.45, "learning_rate": 3.808219937366627e-06, "loss": 0.8413, "step": 17410 }, { "epoch": 1.45, "learning_rate": 3.808109081839093e-06, "loss": 0.7907, "step": 17420 }, { "epoch": 1.45, "learning_rate": 3.807998226311559e-06, "loss": 0.833, "step": 17430 }, { "epoch": 1.45, "learning_rate": 3.8078873707840257e-06, "loss": 0.9061, "step": 17440 }, { "epoch": 1.45, "learning_rate": 3.807776515256492e-06, "loss": 0.8663, "step": 17450 }, { "epoch": 1.45, "learning_rate": 3.807665659728958e-06, "loss": 0.7682, "step": 17460 }, { "epoch": 1.45, "learning_rate": 3.8075548042014246e-06, "loss": 0.8332, "step": 17470 }, { "epoch": 1.45, "learning_rate": 3.8074439486738904e-06, "loss": 0.8536, "step": 17480 }, { "epoch": 1.45, "learning_rate": 3.807333093146357e-06, "loss": 0.883, "step": 17490 }, { "epoch": 1.45, "learning_rate": 3.807222237618823e-06, "loss": 0.8556, "step": 17500 }, { "epoch": 1.46, "learning_rate": 3.8071113820912893e-06, "loss": 0.7855, "step": 17510 }, { "epoch": 1.46, "learning_rate": 3.8070005265637556e-06, "loss": 0.751, "step": 17520 }, { "epoch": 1.46, "learning_rate": 3.806889671036222e-06, "loss": 0.7768, "step": 17530 }, { "epoch": 1.46, "learning_rate": 3.806778815508688e-06, "loss": 0.9548, "step": 17540 }, { "epoch": 1.46, "learning_rate": 3.8066679599811545e-06, "loss": 0.8038, "step": 17550 }, { "epoch": 1.46, "learning_rate": 3.8065571044536204e-06, "loss": 0.8296, "step": 17560 }, { "epoch": 1.46, "learning_rate": 3.806446248926087e-06, "loss": 0.838, "step": 17570 }, { "epoch": 1.46, "learning_rate": 3.8063353933985534e-06, "loss": 0.7577, "step": 17580 }, { "epoch": 1.46, "learning_rate": 3.8062245378710193e-06, "loss": 0.8379, "step": 17590 }, { "epoch": 1.46, "learning_rate": 3.806113682343486e-06, "loss": 0.846, "step": 17600 }, { "epoch": 1.46, "learning_rate": 3.806002826815952e-06, "loss": 0.7966, "step": 17610 }, { "epoch": 1.46, "learning_rate": 3.805891971288418e-06, "loss": 0.7857, "step": 17620 }, { "epoch": 1.47, "learning_rate": 3.8057811157608845e-06, "loss": 0.8256, "step": 17630 }, { "epoch": 1.47, "learning_rate": 3.8056702602333507e-06, "loss": 0.9089, "step": 17640 }, { "epoch": 1.47, "learning_rate": 3.8055594047058166e-06, "loss": 0.8485, "step": 17650 }, { "epoch": 1.47, "learning_rate": 3.8054485491782833e-06, "loss": 0.8417, "step": 17660 }, { "epoch": 1.47, "learning_rate": 3.805337693650749e-06, "loss": 0.8567, "step": 17670 }, { "epoch": 1.47, "learning_rate": 3.805226838123216e-06, "loss": 0.8802, "step": 17680 }, { "epoch": 1.47, "learning_rate": 3.805115982595682e-06, "loss": 0.8904, "step": 17690 }, { "epoch": 1.47, "learning_rate": 3.805005127068148e-06, "loss": 0.8437, "step": 17700 }, { "epoch": 1.47, "learning_rate": 3.804894271540615e-06, "loss": 0.8027, "step": 17710 }, { "epoch": 1.47, "learning_rate": 3.8047834160130807e-06, "loss": 0.8187, "step": 17720 }, { "epoch": 1.47, "learning_rate": 3.804672560485547e-06, "loss": 0.8132, "step": 17730 }, { "epoch": 1.47, "learning_rate": 3.8045617049580133e-06, "loss": 0.8603, "step": 17740 }, { "epoch": 1.48, "learning_rate": 3.8044508494304796e-06, "loss": 0.8029, "step": 17750 }, { "epoch": 1.48, "learning_rate": 3.804339993902946e-06, "loss": 0.8155, "step": 17760 }, { "epoch": 1.48, "learning_rate": 3.804229138375412e-06, "loss": 0.8142, "step": 17770 }, { "epoch": 1.48, "learning_rate": 3.804118282847878e-06, "loss": 0.8593, "step": 17780 }, { "epoch": 1.48, "learning_rate": 3.8040074273203448e-06, "loss": 0.9166, "step": 17790 }, { "epoch": 1.48, "learning_rate": 3.8038965717928106e-06, "loss": 0.9041, "step": 17800 }, { "epoch": 1.48, "learning_rate": 3.803785716265277e-06, "loss": 0.8064, "step": 17810 }, { "epoch": 1.48, "learning_rate": 3.8036748607377436e-06, "loss": 0.8091, "step": 17820 }, { "epoch": 1.48, "learning_rate": 3.8035640052102095e-06, "loss": 0.8436, "step": 17830 }, { "epoch": 1.48, "learning_rate": 3.8034531496826762e-06, "loss": 0.9105, "step": 17840 }, { "epoch": 1.48, "learning_rate": 3.803342294155142e-06, "loss": 0.8708, "step": 17850 }, { "epoch": 1.48, "learning_rate": 3.8032314386276084e-06, "loss": 0.8002, "step": 17860 }, { "epoch": 1.49, "learning_rate": 3.8031205831000747e-06, "loss": 0.8603, "step": 17870 }, { "epoch": 1.49, "learning_rate": 3.803009727572541e-06, "loss": 0.8144, "step": 17880 }, { "epoch": 1.49, "learning_rate": 3.802898872045007e-06, "loss": 0.8493, "step": 17890 }, { "epoch": 1.49, "learning_rate": 3.8027880165174736e-06, "loss": 0.8037, "step": 17900 }, { "epoch": 1.49, "learning_rate": 3.8026771609899395e-06, "loss": 0.8127, "step": 17910 }, { "epoch": 1.49, "learning_rate": 3.802566305462406e-06, "loss": 0.8183, "step": 17920 }, { "epoch": 1.49, "learning_rate": 3.802455449934872e-06, "loss": 0.8286, "step": 17930 }, { "epoch": 1.49, "learning_rate": 3.8023445944073383e-06, "loss": 0.9209, "step": 17940 }, { "epoch": 1.49, "learning_rate": 3.802233738879805e-06, "loss": 0.8619, "step": 17950 }, { "epoch": 1.49, "learning_rate": 3.802122883352271e-06, "loss": 0.7734, "step": 17960 }, { "epoch": 1.49, "learning_rate": 3.8020120278247372e-06, "loss": 0.7532, "step": 17970 }, { "epoch": 1.49, "learning_rate": 3.8019011722972035e-06, "loss": 0.7928, "step": 17980 }, { "epoch": 1.5, "learning_rate": 3.80179031676967e-06, "loss": 0.8465, "step": 17990 }, { "epoch": 1.5, "learning_rate": 3.801679461242136e-06, "loss": 0.878, "step": 18000 }, { "epoch": 1.5, "learning_rate": 3.8015686057146024e-06, "loss": 0.8255, "step": 18010 }, { "epoch": 1.5, "learning_rate": 3.8014577501870683e-06, "loss": 0.8125, "step": 18020 }, { "epoch": 1.5, "learning_rate": 3.801346894659535e-06, "loss": 0.8142, "step": 18030 }, { "epoch": 1.5, "learning_rate": 3.801236039132001e-06, "loss": 0.8823, "step": 18040 }, { "epoch": 1.5, "learning_rate": 3.801125183604467e-06, "loss": 0.8498, "step": 18050 }, { "epoch": 1.5, "learning_rate": 3.801014328076934e-06, "loss": 0.8596, "step": 18060 }, { "epoch": 1.5, "learning_rate": 3.8009145581021534e-06, "loss": 0.8196, "step": 18070 }, { "epoch": 1.5, "learning_rate": 3.8008037025746193e-06, "loss": 0.8904, "step": 18080 }, { "epoch": 1.5, "learning_rate": 3.800692847047086e-06, "loss": 0.8366, "step": 18090 }, { "epoch": 1.5, "learning_rate": 3.800581991519552e-06, "loss": 0.8131, "step": 18100 }, { "epoch": 1.51, "learning_rate": 3.800471135992018e-06, "loss": 0.8305, "step": 18110 }, { "epoch": 1.51, "learning_rate": 3.8003602804644845e-06, "loss": 0.8082, "step": 18120 }, { "epoch": 1.51, "learning_rate": 3.8002494249369508e-06, "loss": 0.8646, "step": 18130 }, { "epoch": 1.51, "learning_rate": 3.8001385694094166e-06, "loss": 0.9604, "step": 18140 }, { "epoch": 1.51, "learning_rate": 3.8000277138818834e-06, "loss": 0.8318, "step": 18150 }, { "epoch": 1.51, "learning_rate": 3.7999168583543497e-06, "loss": 0.7651, "step": 18160 }, { "epoch": 1.51, "learning_rate": 3.7998060028268155e-06, "loss": 0.9012, "step": 18170 }, { "epoch": 1.51, "learning_rate": 3.7996951472992822e-06, "loss": 0.7859, "step": 18180 }, { "epoch": 1.51, "learning_rate": 3.799584291771748e-06, "loss": 0.9373, "step": 18190 }, { "epoch": 1.51, "learning_rate": 3.799473436244215e-06, "loss": 0.8049, "step": 18200 }, { "epoch": 1.51, "learning_rate": 3.7993625807166807e-06, "loss": 0.8416, "step": 18210 }, { "epoch": 1.51, "learning_rate": 3.799251725189147e-06, "loss": 0.8198, "step": 18220 }, { "epoch": 1.52, "learning_rate": 3.7991408696616133e-06, "loss": 0.8534, "step": 18230 }, { "epoch": 1.52, "learning_rate": 3.7990300141340796e-06, "loss": 0.8715, "step": 18240 }, { "epoch": 1.52, "learning_rate": 3.7989191586065455e-06, "loss": 0.799, "step": 18250 }, { "epoch": 1.52, "learning_rate": 3.798808303079012e-06, "loss": 0.8567, "step": 18260 }, { "epoch": 1.52, "learning_rate": 3.7986974475514785e-06, "loss": 0.8221, "step": 18270 }, { "epoch": 1.52, "learning_rate": 3.7985865920239448e-06, "loss": 0.8474, "step": 18280 }, { "epoch": 1.52, "learning_rate": 3.798475736496411e-06, "loss": 0.9112, "step": 18290 }, { "epoch": 1.52, "learning_rate": 3.798364880968877e-06, "loss": 0.8182, "step": 18300 }, { "epoch": 1.52, "learning_rate": 3.7982540254413437e-06, "loss": 0.834, "step": 18310 }, { "epoch": 1.52, "learning_rate": 3.7981431699138095e-06, "loss": 0.86, "step": 18320 }, { "epoch": 1.52, "learning_rate": 3.798032314386276e-06, "loss": 0.8958, "step": 18330 }, { "epoch": 1.52, "learning_rate": 3.797921458858742e-06, "loss": 0.9344, "step": 18340 }, { "epoch": 1.53, "learning_rate": 3.7978106033312084e-06, "loss": 0.8275, "step": 18350 }, { "epoch": 1.53, "learning_rate": 3.7976997478036747e-06, "loss": 0.7501, "step": 18360 }, { "epoch": 1.53, "learning_rate": 3.797588892276141e-06, "loss": 0.8014, "step": 18370 }, { "epoch": 1.53, "learning_rate": 3.797478036748607e-06, "loss": 0.8325, "step": 18380 }, { "epoch": 1.53, "learning_rate": 3.7973671812210736e-06, "loss": 0.873, "step": 18390 }, { "epoch": 1.53, "learning_rate": 3.79725632569354e-06, "loss": 0.8423, "step": 18400 }, { "epoch": 1.53, "learning_rate": 3.7971454701660058e-06, "loss": 0.8666, "step": 18410 }, { "epoch": 1.53, "learning_rate": 3.7970346146384725e-06, "loss": 0.8488, "step": 18420 }, { "epoch": 1.53, "learning_rate": 3.7969237591109384e-06, "loss": 0.8214, "step": 18430 }, { "epoch": 1.53, "learning_rate": 3.796812903583405e-06, "loss": 0.8825, "step": 18440 }, { "epoch": 1.53, "learning_rate": 3.796702048055871e-06, "loss": 0.8994, "step": 18450 }, { "epoch": 1.53, "learning_rate": 3.7965911925283372e-06, "loss": 0.793, "step": 18460 }, { "epoch": 1.54, "learning_rate": 3.7964803370008035e-06, "loss": 0.8111, "step": 18470 }, { "epoch": 1.54, "learning_rate": 3.79636948147327e-06, "loss": 0.9259, "step": 18480 }, { "epoch": 1.54, "learning_rate": 3.7962586259457357e-06, "loss": 0.872, "step": 18490 }, { "epoch": 1.54, "learning_rate": 3.7961477704182024e-06, "loss": 0.7896, "step": 18500 }, { "epoch": 1.54, "learning_rate": 3.7960369148906683e-06, "loss": 0.8436, "step": 18510 }, { "epoch": 1.54, "learning_rate": 3.795926059363135e-06, "loss": 0.7509, "step": 18520 }, { "epoch": 1.54, "learning_rate": 3.7958152038356013e-06, "loss": 0.7948, "step": 18530 }, { "epoch": 1.54, "learning_rate": 3.795704348308067e-06, "loss": 0.8672, "step": 18540 }, { "epoch": 1.54, "learning_rate": 3.795593492780534e-06, "loss": 0.8623, "step": 18550 }, { "epoch": 1.54, "learning_rate": 3.7954826372529998e-06, "loss": 0.8234, "step": 18560 }, { "epoch": 1.54, "learning_rate": 3.795371781725466e-06, "loss": 0.8723, "step": 18570 }, { "epoch": 1.54, "learning_rate": 3.7952609261979324e-06, "loss": 0.9117, "step": 18580 }, { "epoch": 1.55, "learning_rate": 3.7951500706703987e-06, "loss": 0.8953, "step": 18590 }, { "epoch": 1.55, "learning_rate": 3.7950392151428645e-06, "loss": 0.7905, "step": 18600 }, { "epoch": 1.55, "learning_rate": 3.7949283596153313e-06, "loss": 0.8385, "step": 18610 }, { "epoch": 1.55, "learning_rate": 3.794817504087797e-06, "loss": 0.7995, "step": 18620 }, { "epoch": 1.55, "learning_rate": 3.794706648560264e-06, "loss": 0.8178, "step": 18630 }, { "epoch": 1.55, "learning_rate": 3.79459579303273e-06, "loss": 0.8866, "step": 18640 }, { "epoch": 1.55, "learning_rate": 3.794484937505196e-06, "loss": 0.8092, "step": 18650 }, { "epoch": 1.55, "learning_rate": 3.7943740819776627e-06, "loss": 0.8299, "step": 18660 }, { "epoch": 1.55, "learning_rate": 3.7942632264501286e-06, "loss": 0.8651, "step": 18670 }, { "epoch": 1.55, "learning_rate": 3.794152370922595e-06, "loss": 0.8236, "step": 18680 }, { "epoch": 1.55, "learning_rate": 3.794041515395061e-06, "loss": 0.8512, "step": 18690 }, { "epoch": 1.55, "learning_rate": 3.7939306598675275e-06, "loss": 0.8231, "step": 18700 }, { "epoch": 1.56, "learning_rate": 3.7938198043399938e-06, "loss": 0.8423, "step": 18710 }, { "epoch": 1.56, "learning_rate": 3.79370894881246e-06, "loss": 0.7913, "step": 18720 }, { "epoch": 1.56, "learning_rate": 3.793598093284926e-06, "loss": 0.8504, "step": 18730 }, { "epoch": 1.56, "learning_rate": 3.7934872377573927e-06, "loss": 0.815, "step": 18740 }, { "epoch": 1.56, "learning_rate": 3.7933763822298585e-06, "loss": 0.8444, "step": 18750 }, { "epoch": 1.56, "learning_rate": 3.793265526702325e-06, "loss": 0.8142, "step": 18760 }, { "epoch": 1.56, "learning_rate": 3.7931546711747916e-06, "loss": 0.7968, "step": 18770 }, { "epoch": 1.56, "learning_rate": 3.7930438156472574e-06, "loss": 0.8657, "step": 18780 }, { "epoch": 1.56, "learning_rate": 3.792932960119724e-06, "loss": 0.8066, "step": 18790 }, { "epoch": 1.56, "learning_rate": 3.79282210459219e-06, "loss": 0.8079, "step": 18800 }, { "epoch": 1.56, "learning_rate": 3.7927112490646563e-06, "loss": 0.839, "step": 18810 }, { "epoch": 1.56, "learning_rate": 3.7926003935371226e-06, "loss": 0.8207, "step": 18820 }, { "epoch": 1.57, "learning_rate": 3.792489538009589e-06, "loss": 0.7815, "step": 18830 }, { "epoch": 1.57, "learning_rate": 3.7923786824820548e-06, "loss": 0.9054, "step": 18840 }, { "epoch": 1.57, "learning_rate": 3.7922678269545215e-06, "loss": 0.8343, "step": 18850 }, { "epoch": 1.57, "learning_rate": 3.7921569714269874e-06, "loss": 0.8836, "step": 18860 }, { "epoch": 1.57, "learning_rate": 3.792046115899454e-06, "loss": 0.8553, "step": 18870 }, { "epoch": 1.57, "learning_rate": 3.79193526037192e-06, "loss": 0.832, "step": 18880 }, { "epoch": 1.57, "learning_rate": 3.7918244048443863e-06, "loss": 0.8265, "step": 18890 }, { "epoch": 1.57, "learning_rate": 3.791713549316853e-06, "loss": 0.8216, "step": 18900 }, { "epoch": 1.57, "learning_rate": 3.791602693789319e-06, "loss": 0.8426, "step": 18910 }, { "epoch": 1.57, "learning_rate": 3.791491838261785e-06, "loss": 0.7764, "step": 18920 }, { "epoch": 1.57, "learning_rate": 3.7913809827342514e-06, "loss": 0.8543, "step": 18930 }, { "epoch": 1.57, "learning_rate": 3.7912701272067177e-06, "loss": 0.9069, "step": 18940 }, { "epoch": 1.58, "learning_rate": 3.791159271679184e-06, "loss": 0.7805, "step": 18950 }, { "epoch": 1.58, "learning_rate": 3.7910484161516503e-06, "loss": 0.797, "step": 18960 }, { "epoch": 1.58, "learning_rate": 3.790937560624116e-06, "loss": 0.8418, "step": 18970 }, { "epoch": 1.58, "learning_rate": 3.790826705096583e-06, "loss": 0.757, "step": 18980 }, { "epoch": 1.58, "learning_rate": 3.7907158495690488e-06, "loss": 0.9225, "step": 18990 }, { "epoch": 1.58, "learning_rate": 3.790604994041515e-06, "loss": 0.7778, "step": 19000 }, { "epoch": 1.58, "learning_rate": 3.790494138513982e-06, "loss": 0.7959, "step": 19010 }, { "epoch": 1.58, "learning_rate": 3.7903832829864477e-06, "loss": 0.8465, "step": 19020 }, { "epoch": 1.58, "learning_rate": 3.7902724274589144e-06, "loss": 0.8379, "step": 19030 }, { "epoch": 1.58, "learning_rate": 3.7901615719313803e-06, "loss": 0.9038, "step": 19040 }, { "epoch": 1.58, "learning_rate": 3.7900507164038466e-06, "loss": 0.8087, "step": 19050 }, { "epoch": 1.58, "learning_rate": 3.789939860876313e-06, "loss": 0.826, "step": 19060 }, { "epoch": 1.59, "learning_rate": 3.789829005348779e-06, "loss": 0.8148, "step": 19070 }, { "epoch": 1.59, "learning_rate": 3.789718149821245e-06, "loss": 0.8587, "step": 19080 }, { "epoch": 1.59, "learning_rate": 3.7896072942937117e-06, "loss": 0.9387, "step": 19090 }, { "epoch": 1.59, "learning_rate": 3.7894964387661776e-06, "loss": 0.8633, "step": 19100 }, { "epoch": 1.59, "learning_rate": 3.789385583238644e-06, "loss": 0.7888, "step": 19110 }, { "epoch": 1.59, "learning_rate": 3.78927472771111e-06, "loss": 0.8096, "step": 19120 }, { "epoch": 1.59, "learning_rate": 3.7891638721835765e-06, "loss": 0.8273, "step": 19130 }, { "epoch": 1.59, "learning_rate": 3.789053016656043e-06, "loss": 0.8717, "step": 19140 }, { "epoch": 1.59, "learning_rate": 3.788942161128509e-06, "loss": 0.8358, "step": 19150 }, { "epoch": 1.59, "learning_rate": 3.7888313056009754e-06, "loss": 0.9134, "step": 19160 }, { "epoch": 1.59, "learning_rate": 3.7887204500734417e-06, "loss": 0.8168, "step": 19170 }, { "epoch": 1.59, "learning_rate": 3.788609594545908e-06, "loss": 0.851, "step": 19180 }, { "epoch": 1.6, "learning_rate": 3.788498739018374e-06, "loss": 0.888, "step": 19190 }, { "epoch": 1.6, "learning_rate": 3.7883878834908406e-06, "loss": 0.8752, "step": 19200 }, { "epoch": 1.6, "learning_rate": 3.7882770279633064e-06, "loss": 0.8935, "step": 19210 }, { "epoch": 1.6, "learning_rate": 3.788166172435773e-06, "loss": 0.8089, "step": 19220 }, { "epoch": 1.6, "learning_rate": 3.788055316908239e-06, "loss": 0.7644, "step": 19230 }, { "epoch": 1.6, "learning_rate": 3.7879444613807053e-06, "loss": 0.8918, "step": 19240 }, { "epoch": 1.6, "learning_rate": 3.7878336058531716e-06, "loss": 0.8629, "step": 19250 }, { "epoch": 1.6, "learning_rate": 3.787722750325638e-06, "loss": 0.7868, "step": 19260 }, { "epoch": 1.6, "learning_rate": 3.787611894798104e-06, "loss": 0.8267, "step": 19270 }, { "epoch": 1.6, "learning_rate": 3.7875010392705705e-06, "loss": 0.8116, "step": 19280 }, { "epoch": 1.6, "learning_rate": 3.787390183743037e-06, "loss": 0.889, "step": 19290 }, { "epoch": 1.6, "learning_rate": 3.787279328215503e-06, "loss": 0.8473, "step": 19300 }, { "epoch": 1.61, "learning_rate": 3.7871684726879694e-06, "loss": 0.8295, "step": 19310 }, { "epoch": 1.61, "learning_rate": 3.7870576171604353e-06, "loss": 0.8438, "step": 19320 }, { "epoch": 1.61, "learning_rate": 3.786946761632902e-06, "loss": 0.8129, "step": 19330 }, { "epoch": 1.61, "learning_rate": 3.786835906105368e-06, "loss": 0.8771, "step": 19340 }, { "epoch": 1.61, "learning_rate": 3.786725050577834e-06, "loss": 0.8907, "step": 19350 }, { "epoch": 1.61, "learning_rate": 3.7866141950503004e-06, "loss": 0.9193, "step": 19360 }, { "epoch": 1.61, "learning_rate": 3.7865033395227667e-06, "loss": 0.833, "step": 19370 }, { "epoch": 1.61, "learning_rate": 3.7863924839952335e-06, "loss": 0.9338, "step": 19380 }, { "epoch": 1.61, "learning_rate": 3.7862816284676993e-06, "loss": 0.9403, "step": 19390 }, { "epoch": 1.61, "learning_rate": 3.7861707729401656e-06, "loss": 0.806, "step": 19400 }, { "epoch": 1.61, "learning_rate": 3.786059917412632e-06, "loss": 0.8205, "step": 19410 }, { "epoch": 1.61, "learning_rate": 3.785949061885098e-06, "loss": 0.788, "step": 19420 }, { "epoch": 1.61, "learning_rate": 3.785838206357564e-06, "loss": 0.7753, "step": 19430 }, { "epoch": 1.62, "learning_rate": 3.785727350830031e-06, "loss": 0.8151, "step": 19440 }, { "epoch": 1.62, "learning_rate": 3.7856164953024967e-06, "loss": 0.9176, "step": 19450 }, { "epoch": 1.62, "learning_rate": 3.785505639774963e-06, "loss": 0.8766, "step": 19460 }, { "epoch": 1.62, "learning_rate": 3.7853947842474293e-06, "loss": 0.7888, "step": 19470 }, { "epoch": 1.62, "learning_rate": 3.7852839287198956e-06, "loss": 0.8837, "step": 19480 }, { "epoch": 1.62, "learning_rate": 3.785173073192362e-06, "loss": 0.8598, "step": 19490 }, { "epoch": 1.62, "learning_rate": 3.785062217664828e-06, "loss": 0.8302, "step": 19500 }, { "epoch": 1.62, "learning_rate": 3.7849513621372944e-06, "loss": 0.7797, "step": 19510 }, { "epoch": 1.62, "learning_rate": 3.7848405066097607e-06, "loss": 0.8582, "step": 19520 }, { "epoch": 1.62, "learning_rate": 3.784729651082227e-06, "loss": 0.7538, "step": 19530 }, { "epoch": 1.62, "learning_rate": 3.784618795554693e-06, "loss": 0.8536, "step": 19540 }, { "epoch": 1.62, "learning_rate": 3.7845079400271596e-06, "loss": 0.8864, "step": 19550 }, { "epoch": 1.63, "learning_rate": 3.7843970844996255e-06, "loss": 0.8049, "step": 19560 }, { "epoch": 1.63, "learning_rate": 3.7842862289720922e-06, "loss": 0.8434, "step": 19570 }, { "epoch": 1.63, "learning_rate": 3.784175373444558e-06, "loss": 0.8913, "step": 19580 }, { "epoch": 1.63, "learning_rate": 3.7840645179170244e-06, "loss": 0.9215, "step": 19590 }, { "epoch": 1.63, "learning_rate": 3.7839536623894907e-06, "loss": 0.9061, "step": 19600 }, { "epoch": 1.63, "learning_rate": 3.783842806861957e-06, "loss": 0.7922, "step": 19610 }, { "epoch": 1.63, "learning_rate": 3.783731951334423e-06, "loss": 0.8047, "step": 19620 }, { "epoch": 1.63, "learning_rate": 3.7836210958068896e-06, "loss": 0.8597, "step": 19630 }, { "epoch": 1.63, "learning_rate": 3.783510240279356e-06, "loss": 0.8551, "step": 19640 }, { "epoch": 1.63, "learning_rate": 3.783399384751822e-06, "loss": 0.8059, "step": 19650 }, { "epoch": 1.63, "learning_rate": 3.7832885292242885e-06, "loss": 0.8715, "step": 19660 }, { "epoch": 1.63, "learning_rate": 3.7831776736967543e-06, "loss": 0.8504, "step": 19670 }, { "epoch": 1.64, "learning_rate": 3.783066818169221e-06, "loss": 0.8154, "step": 19680 }, { "epoch": 1.64, "learning_rate": 3.782955962641687e-06, "loss": 0.9365, "step": 19690 }, { "epoch": 1.64, "learning_rate": 3.782845107114153e-06, "loss": 0.8619, "step": 19700 }, { "epoch": 1.64, "learning_rate": 3.7827342515866195e-06, "loss": 0.8453, "step": 19710 }, { "epoch": 1.64, "learning_rate": 3.782623396059086e-06, "loss": 0.7783, "step": 19720 }, { "epoch": 1.64, "learning_rate": 3.782512540531552e-06, "loss": 0.8168, "step": 19730 }, { "epoch": 1.64, "learning_rate": 3.7824016850040184e-06, "loss": 0.8914, "step": 19740 }, { "epoch": 1.64, "learning_rate": 3.7822908294764847e-06, "loss": 0.7926, "step": 19750 }, { "epoch": 1.64, "learning_rate": 3.782179973948951e-06, "loss": 0.8861, "step": 19760 }, { "epoch": 1.64, "learning_rate": 3.7820691184214173e-06, "loss": 0.7904, "step": 19770 }, { "epoch": 1.64, "learning_rate": 3.781958262893883e-06, "loss": 0.7838, "step": 19780 }, { "epoch": 1.64, "learning_rate": 3.78184740736635e-06, "loss": 0.8528, "step": 19790 }, { "epoch": 1.65, "learning_rate": 3.7817365518388157e-06, "loss": 0.8132, "step": 19800 }, { "epoch": 1.65, "learning_rate": 3.7816256963112825e-06, "loss": 0.8198, "step": 19810 }, { "epoch": 1.65, "learning_rate": 3.7815148407837483e-06, "loss": 0.8148, "step": 19820 }, { "epoch": 1.65, "learning_rate": 3.7814039852562146e-06, "loss": 0.7985, "step": 19830 }, { "epoch": 1.65, "learning_rate": 3.781293129728681e-06, "loss": 0.8947, "step": 19840 }, { "epoch": 1.65, "learning_rate": 3.7811822742011472e-06, "loss": 0.8886, "step": 19850 }, { "epoch": 1.65, "learning_rate": 3.781071418673613e-06, "loss": 0.84, "step": 19860 }, { "epoch": 1.65, "learning_rate": 3.78096056314608e-06, "loss": 0.8036, "step": 19870 }, { "epoch": 1.65, "learning_rate": 3.780849707618546e-06, "loss": 0.8019, "step": 19880 }, { "epoch": 1.65, "learning_rate": 3.780738852091012e-06, "loss": 0.8702, "step": 19890 }, { "epoch": 1.65, "learning_rate": 3.7806279965634787e-06, "loss": 0.8706, "step": 19900 }, { "epoch": 1.65, "learning_rate": 3.7805171410359446e-06, "loss": 0.8385, "step": 19910 }, { "epoch": 1.66, "learning_rate": 3.7804062855084113e-06, "loss": 0.8227, "step": 19920 }, { "epoch": 1.66, "learning_rate": 3.780295429980877e-06, "loss": 0.8198, "step": 19930 }, { "epoch": 1.66, "learning_rate": 3.7801845744533434e-06, "loss": 0.8707, "step": 19940 }, { "epoch": 1.66, "learning_rate": 3.7800737189258097e-06, "loss": 0.824, "step": 19950 }, { "epoch": 1.66, "learning_rate": 3.779962863398276e-06, "loss": 0.8346, "step": 19960 }, { "epoch": 1.66, "learning_rate": 3.779852007870742e-06, "loss": 0.7912, "step": 19970 }, { "epoch": 1.66, "learning_rate": 3.7797411523432086e-06, "loss": 0.8483, "step": 19980 }, { "epoch": 1.66, "learning_rate": 3.7796302968156745e-06, "loss": 0.8931, "step": 19990 }, { "epoch": 1.66, "learning_rate": 3.7795194412881412e-06, "loss": 0.8363, "step": 20000 }, { "epoch": 1.66, "learning_rate": 3.7794085857606075e-06, "loss": 0.8637, "step": 20010 }, { "epoch": 1.66, "learning_rate": 3.7792977302330734e-06, "loss": 0.8742, "step": 20020 }, { "epoch": 1.66, "learning_rate": 3.77918687470554e-06, "loss": 0.869, "step": 20030 }, { "epoch": 1.67, "learning_rate": 3.779076019178006e-06, "loss": 0.8995, "step": 20040 }, { "epoch": 1.67, "learning_rate": 3.7789651636504723e-06, "loss": 0.8082, "step": 20050 }, { "epoch": 1.67, "learning_rate": 3.7788543081229386e-06, "loss": 0.8895, "step": 20060 }, { "epoch": 1.67, "learning_rate": 3.778743452595405e-06, "loss": 0.8295, "step": 20070 }, { "epoch": 1.67, "learning_rate": 3.778632597067871e-06, "loss": 0.8492, "step": 20080 }, { "epoch": 1.67, "learning_rate": 3.778532827093091e-06, "loss": 0.8567, "step": 20090 }, { "epoch": 1.67, "learning_rate": 3.778421971565557e-06, "loss": 0.8993, "step": 20100 }, { "epoch": 1.67, "learning_rate": 3.7783111160380233e-06, "loss": 0.9532, "step": 20110 }, { "epoch": 1.67, "learning_rate": 3.7782002605104896e-06, "loss": 0.9011, "step": 20120 }, { "epoch": 1.67, "learning_rate": 3.778089404982956e-06, "loss": 0.8769, "step": 20130 }, { "epoch": 1.67, "learning_rate": 3.7779785494554218e-06, "loss": 0.8646, "step": 20140 }, { "epoch": 1.67, "learning_rate": 3.7778676939278885e-06, "loss": 0.881, "step": 20150 }, { "epoch": 1.68, "learning_rate": 3.7777568384003543e-06, "loss": 0.9078, "step": 20160 }, { "epoch": 1.68, "learning_rate": 3.777645982872821e-06, "loss": 0.8072, "step": 20170 }, { "epoch": 1.68, "learning_rate": 3.777535127345287e-06, "loss": 0.8361, "step": 20180 }, { "epoch": 1.68, "learning_rate": 3.7774242718177532e-06, "loss": 0.9346, "step": 20190 }, { "epoch": 1.68, "learning_rate": 3.7773134162902195e-06, "loss": 0.7778, "step": 20200 }, { "epoch": 1.68, "learning_rate": 3.777202560762686e-06, "loss": 0.8751, "step": 20210 }, { "epoch": 1.68, "learning_rate": 3.777091705235152e-06, "loss": 0.9248, "step": 20220 }, { "epoch": 1.68, "learning_rate": 3.7769808497076184e-06, "loss": 0.8007, "step": 20230 }, { "epoch": 1.68, "learning_rate": 3.7768699941800847e-06, "loss": 0.9283, "step": 20240 }, { "epoch": 1.68, "learning_rate": 3.776759138652551e-06, "loss": 0.8941, "step": 20250 }, { "epoch": 1.68, "learning_rate": 3.7766482831250173e-06, "loss": 0.8284, "step": 20260 }, { "epoch": 1.68, "learning_rate": 3.776537427597483e-06, "loss": 0.7752, "step": 20270 }, { "epoch": 1.69, "learning_rate": 3.77642657206995e-06, "loss": 0.8423, "step": 20280 }, { "epoch": 1.69, "learning_rate": 3.7763157165424158e-06, "loss": 0.942, "step": 20290 }, { "epoch": 1.69, "learning_rate": 3.776204861014882e-06, "loss": 0.9066, "step": 20300 }, { "epoch": 1.69, "learning_rate": 3.7760940054873483e-06, "loss": 0.8503, "step": 20310 }, { "epoch": 1.69, "learning_rate": 3.7759831499598146e-06, "loss": 0.8209, "step": 20320 }, { "epoch": 1.69, "learning_rate": 3.7758722944322814e-06, "loss": 0.8524, "step": 20330 }, { "epoch": 1.69, "learning_rate": 3.7757614389047472e-06, "loss": 0.8547, "step": 20340 }, { "epoch": 1.69, "learning_rate": 3.7756505833772135e-06, "loss": 0.8428, "step": 20350 }, { "epoch": 1.69, "learning_rate": 3.77553972784968e-06, "loss": 0.7704, "step": 20360 }, { "epoch": 1.69, "learning_rate": 3.775428872322146e-06, "loss": 0.7811, "step": 20370 }, { "epoch": 1.69, "learning_rate": 3.775318016794612e-06, "loss": 0.8741, "step": 20380 }, { "epoch": 1.69, "learning_rate": 3.7752071612670787e-06, "loss": 0.8746, "step": 20390 }, { "epoch": 1.7, "learning_rate": 3.7750963057395446e-06, "loss": 0.7581, "step": 20400 }, { "epoch": 1.7, "learning_rate": 3.774985450212011e-06, "loss": 0.8144, "step": 20410 }, { "epoch": 1.7, "learning_rate": 3.774874594684477e-06, "loss": 0.8742, "step": 20420 }, { "epoch": 1.7, "learning_rate": 3.7747637391569435e-06, "loss": 0.8058, "step": 20430 }, { "epoch": 1.7, "learning_rate": 3.7746528836294098e-06, "loss": 0.8571, "step": 20440 }, { "epoch": 1.7, "learning_rate": 3.774542028101876e-06, "loss": 0.8718, "step": 20450 }, { "epoch": 1.7, "learning_rate": 3.7744311725743424e-06, "loss": 0.8508, "step": 20460 }, { "epoch": 1.7, "learning_rate": 3.7743203170468087e-06, "loss": 0.7777, "step": 20470 }, { "epoch": 1.7, "learning_rate": 3.774209461519275e-06, "loss": 0.793, "step": 20480 }, { "epoch": 1.7, "learning_rate": 3.774098605991741e-06, "loss": 0.8516, "step": 20490 }, { "epoch": 1.7, "learning_rate": 3.7739877504642075e-06, "loss": 0.8365, "step": 20500 }, { "epoch": 1.7, "learning_rate": 3.7738768949366734e-06, "loss": 0.8846, "step": 20510 }, { "epoch": 1.71, "learning_rate": 3.77376603940914e-06, "loss": 0.857, "step": 20520 }, { "epoch": 1.71, "learning_rate": 3.773655183881606e-06, "loss": 0.92, "step": 20530 }, { "epoch": 1.71, "learning_rate": 3.7735443283540723e-06, "loss": 0.8637, "step": 20540 }, { "epoch": 1.71, "learning_rate": 3.7734334728265386e-06, "loss": 0.9174, "step": 20550 }, { "epoch": 1.71, "learning_rate": 3.773322617299005e-06, "loss": 0.8469, "step": 20560 }, { "epoch": 1.71, "learning_rate": 3.773211761771471e-06, "loss": 0.86, "step": 20570 }, { "epoch": 1.71, "learning_rate": 3.7731009062439375e-06, "loss": 0.8098, "step": 20580 }, { "epoch": 1.71, "learning_rate": 3.7729900507164038e-06, "loss": 0.8824, "step": 20590 }, { "epoch": 1.71, "learning_rate": 3.77287919518887e-06, "loss": 0.8384, "step": 20600 }, { "epoch": 1.71, "learning_rate": 3.7727683396613364e-06, "loss": 0.9409, "step": 20610 }, { "epoch": 1.71, "learning_rate": 3.7726574841338022e-06, "loss": 0.8004, "step": 20620 }, { "epoch": 1.71, "learning_rate": 3.772546628606269e-06, "loss": 0.7698, "step": 20630 }, { "epoch": 1.72, "learning_rate": 3.772435773078735e-06, "loss": 0.8938, "step": 20640 }, { "epoch": 1.72, "learning_rate": 3.772324917551201e-06, "loss": 0.8794, "step": 20650 }, { "epoch": 1.72, "learning_rate": 3.7722140620236674e-06, "loss": 0.8701, "step": 20660 }, { "epoch": 1.72, "learning_rate": 3.7721032064961337e-06, "loss": 0.8602, "step": 20670 }, { "epoch": 1.72, "learning_rate": 3.7719923509686e-06, "loss": 0.8263, "step": 20680 }, { "epoch": 1.72, "learning_rate": 3.7718814954410663e-06, "loss": 0.8685, "step": 20690 }, { "epoch": 1.72, "learning_rate": 3.7717706399135326e-06, "loss": 0.9075, "step": 20700 }, { "epoch": 1.72, "learning_rate": 3.771659784385999e-06, "loss": 0.8591, "step": 20710 }, { "epoch": 1.72, "learning_rate": 3.771548928858465e-06, "loss": 0.8067, "step": 20720 }, { "epoch": 1.72, "learning_rate": 3.771438073330931e-06, "loss": 0.8598, "step": 20730 }, { "epoch": 1.72, "learning_rate": 3.7713272178033978e-06, "loss": 0.8975, "step": 20740 }, { "epoch": 1.72, "learning_rate": 3.7712163622758637e-06, "loss": 0.8236, "step": 20750 }, { "epoch": 1.73, "learning_rate": 3.7711055067483304e-06, "loss": 0.8122, "step": 20760 }, { "epoch": 1.73, "learning_rate": 3.7709946512207962e-06, "loss": 0.8576, "step": 20770 }, { "epoch": 1.73, "learning_rate": 3.7708837956932625e-06, "loss": 0.8593, "step": 20780 }, { "epoch": 1.73, "learning_rate": 3.770772940165729e-06, "loss": 0.8854, "step": 20790 }, { "epoch": 1.73, "learning_rate": 3.770662084638195e-06, "loss": 0.8708, "step": 20800 }, { "epoch": 1.73, "learning_rate": 3.770551229110661e-06, "loss": 0.8314, "step": 20810 }, { "epoch": 1.73, "learning_rate": 3.7704403735831277e-06, "loss": 0.7914, "step": 20820 }, { "epoch": 1.73, "learning_rate": 3.770329518055594e-06, "loss": 0.8755, "step": 20830 }, { "epoch": 1.73, "learning_rate": 3.77021866252806e-06, "loss": 0.8006, "step": 20840 }, { "epoch": 1.73, "learning_rate": 3.7701078070005266e-06, "loss": 0.874, "step": 20850 }, { "epoch": 1.73, "learning_rate": 3.7699969514729925e-06, "loss": 0.7985, "step": 20860 }, { "epoch": 1.73, "learning_rate": 3.769886095945459e-06, "loss": 0.8214, "step": 20870 }, { "epoch": 1.74, "learning_rate": 3.769775240417925e-06, "loss": 0.8767, "step": 20880 }, { "epoch": 1.74, "learning_rate": 3.7696643848903914e-06, "loss": 0.8455, "step": 20890 }, { "epoch": 1.74, "learning_rate": 3.7695535293628577e-06, "loss": 0.8096, "step": 20900 }, { "epoch": 1.74, "learning_rate": 3.769442673835324e-06, "loss": 0.8176, "step": 20910 }, { "epoch": 1.74, "learning_rate": 3.76933181830779e-06, "loss": 0.858, "step": 20920 }, { "epoch": 1.74, "learning_rate": 3.7692209627802565e-06, "loss": 0.8101, "step": 20930 }, { "epoch": 1.74, "learning_rate": 3.769110107252723e-06, "loss": 0.9012, "step": 20940 }, { "epoch": 1.74, "learning_rate": 3.768999251725189e-06, "loss": 0.791, "step": 20950 }, { "epoch": 1.74, "learning_rate": 3.7688883961976554e-06, "loss": 0.8853, "step": 20960 }, { "epoch": 1.74, "learning_rate": 3.7687775406701213e-06, "loss": 0.8386, "step": 20970 }, { "epoch": 1.74, "learning_rate": 3.768666685142588e-06, "loss": 0.7787, "step": 20980 }, { "epoch": 1.74, "learning_rate": 3.768555829615054e-06, "loss": 0.8915, "step": 20990 }, { "epoch": 1.75, "learning_rate": 3.76844497408752e-06, "loss": 0.7629, "step": 21000 }, { "epoch": 1.75, "learning_rate": 3.7683341185599865e-06, "loss": 0.8333, "step": 21010 }, { "epoch": 1.75, "learning_rate": 3.7682232630324528e-06, "loss": 0.8414, "step": 21020 }, { "epoch": 1.75, "learning_rate": 3.768112407504919e-06, "loss": 0.8546, "step": 21030 }, { "epoch": 1.75, "learning_rate": 3.7680015519773854e-06, "loss": 0.84, "step": 21040 }, { "epoch": 1.75, "learning_rate": 3.7678906964498512e-06, "loss": 0.8549, "step": 21050 }, { "epoch": 1.75, "learning_rate": 3.767779840922318e-06, "loss": 0.8721, "step": 21060 }, { "epoch": 1.75, "learning_rate": 3.7676689853947843e-06, "loss": 0.8458, "step": 21070 }, { "epoch": 1.75, "learning_rate": 3.76755812986725e-06, "loss": 0.7875, "step": 21080 }, { "epoch": 1.75, "learning_rate": 3.767447274339717e-06, "loss": 0.9537, "step": 21090 }, { "epoch": 1.75, "learning_rate": 3.7673364188121827e-06, "loss": 0.8597, "step": 21100 }, { "epoch": 1.75, "learning_rate": 3.7672255632846494e-06, "loss": 0.8179, "step": 21110 }, { "epoch": 1.76, "learning_rate": 3.7671147077571153e-06, "loss": 0.804, "step": 21120 }, { "epoch": 1.76, "learning_rate": 3.7670038522295816e-06, "loss": 0.8037, "step": 21130 }, { "epoch": 1.76, "learning_rate": 3.766892996702048e-06, "loss": 0.9569, "step": 21140 }, { "epoch": 1.76, "learning_rate": 3.766782141174514e-06, "loss": 0.89, "step": 21150 }, { "epoch": 1.76, "learning_rate": 3.76667128564698e-06, "loss": 0.8629, "step": 21160 }, { "epoch": 1.76, "learning_rate": 3.7665604301194468e-06, "loss": 0.8153, "step": 21170 }, { "epoch": 1.76, "learning_rate": 3.7664495745919127e-06, "loss": 0.8111, "step": 21180 }, { "epoch": 1.76, "learning_rate": 3.7663387190643794e-06, "loss": 0.9155, "step": 21190 }, { "epoch": 1.76, "learning_rate": 3.7662278635368457e-06, "loss": 0.8927, "step": 21200 }, { "epoch": 1.76, "learning_rate": 3.7661170080093115e-06, "loss": 0.8647, "step": 21210 }, { "epoch": 1.76, "learning_rate": 3.7660061524817783e-06, "loss": 0.866, "step": 21220 }, { "epoch": 1.76, "learning_rate": 3.765895296954244e-06, "loss": 0.7849, "step": 21230 }, { "epoch": 1.77, "learning_rate": 3.7657844414267104e-06, "loss": 0.8557, "step": 21240 }, { "epoch": 1.77, "learning_rate": 3.7656735858991767e-06, "loss": 0.8816, "step": 21250 }, { "epoch": 1.77, "learning_rate": 3.765562730371643e-06, "loss": 0.8812, "step": 21260 }, { "epoch": 1.77, "learning_rate": 3.765451874844109e-06, "loss": 0.8907, "step": 21270 }, { "epoch": 1.77, "learning_rate": 3.7653410193165756e-06, "loss": 0.8972, "step": 21280 }, { "epoch": 1.77, "learning_rate": 3.7652301637890415e-06, "loss": 0.8449, "step": 21290 }, { "epoch": 1.77, "learning_rate": 3.7651303938142614e-06, "loss": 0.8705, "step": 21300 }, { "epoch": 1.77, "learning_rate": 3.7650195382867277e-06, "loss": 0.8339, "step": 21310 }, { "epoch": 1.77, "learning_rate": 3.764908682759194e-06, "loss": 0.7948, "step": 21320 }, { "epoch": 1.77, "learning_rate": 3.76479782723166e-06, "loss": 0.817, "step": 21330 }, { "epoch": 1.77, "learning_rate": 3.7646869717041266e-06, "loss": 0.8456, "step": 21340 }, { "epoch": 1.77, "learning_rate": 3.7645761161765925e-06, "loss": 0.8432, "step": 21350 }, { "epoch": 1.78, "learning_rate": 3.7644652606490592e-06, "loss": 0.8435, "step": 21360 }, { "epoch": 1.78, "learning_rate": 3.764354405121525e-06, "loss": 0.8053, "step": 21370 }, { "epoch": 1.78, "learning_rate": 3.7642435495939914e-06, "loss": 0.8821, "step": 21380 }, { "epoch": 1.78, "learning_rate": 3.7641326940664577e-06, "loss": 0.8998, "step": 21390 }, { "epoch": 1.78, "learning_rate": 3.764021838538924e-06, "loss": 0.8073, "step": 21400 }, { "epoch": 1.78, "learning_rate": 3.7639109830113903e-06, "loss": 0.8609, "step": 21410 }, { "epoch": 1.78, "learning_rate": 3.7638001274838566e-06, "loss": 0.9372, "step": 21420 }, { "epoch": 1.78, "learning_rate": 3.763689271956323e-06, "loss": 0.7979, "step": 21430 }, { "epoch": 1.78, "learning_rate": 3.7635784164287887e-06, "loss": 0.8264, "step": 21440 }, { "epoch": 1.78, "learning_rate": 3.7634675609012554e-06, "loss": 0.8535, "step": 21450 }, { "epoch": 1.78, "learning_rate": 3.7633567053737213e-06, "loss": 0.8011, "step": 21460 }, { "epoch": 1.78, "learning_rate": 3.763245849846188e-06, "loss": 0.8542, "step": 21470 }, { "epoch": 1.79, "learning_rate": 3.763134994318654e-06, "loss": 0.8023, "step": 21480 }, { "epoch": 1.79, "learning_rate": 3.76302413879112e-06, "loss": 0.9522, "step": 21490 }, { "epoch": 1.79, "learning_rate": 3.7629132832635865e-06, "loss": 0.8155, "step": 21500 }, { "epoch": 1.79, "learning_rate": 3.762802427736053e-06, "loss": 0.8402, "step": 21510 }, { "epoch": 1.79, "learning_rate": 3.762691572208519e-06, "loss": 0.8495, "step": 21520 }, { "epoch": 1.79, "learning_rate": 3.7625807166809854e-06, "loss": 0.8494, "step": 21530 }, { "epoch": 1.79, "learning_rate": 3.7624698611534517e-06, "loss": 0.8933, "step": 21540 }, { "epoch": 1.79, "learning_rate": 3.762359005625918e-06, "loss": 0.8201, "step": 21550 }, { "epoch": 1.79, "learning_rate": 3.7622481500983843e-06, "loss": 0.8318, "step": 21560 }, { "epoch": 1.79, "learning_rate": 3.76213729457085e-06, "loss": 0.8427, "step": 21570 }, { "epoch": 1.79, "learning_rate": 3.762026439043317e-06, "loss": 0.7934, "step": 21580 }, { "epoch": 1.79, "learning_rate": 3.7619155835157827e-06, "loss": 0.8653, "step": 21590 }, { "epoch": 1.8, "learning_rate": 3.761804727988249e-06, "loss": 0.8812, "step": 21600 }, { "epoch": 1.8, "learning_rate": 3.7616938724607153e-06, "loss": 0.8503, "step": 21610 }, { "epoch": 1.8, "learning_rate": 3.7615830169331816e-06, "loss": 0.8342, "step": 21620 }, { "epoch": 1.8, "learning_rate": 3.761472161405648e-06, "loss": 0.8488, "step": 21630 }, { "epoch": 1.8, "learning_rate": 3.7613613058781142e-06, "loss": 0.9211, "step": 21640 }, { "epoch": 1.8, "learning_rate": 3.7612504503505805e-06, "loss": 0.8661, "step": 21650 }, { "epoch": 1.8, "learning_rate": 3.761139594823047e-06, "loss": 0.8606, "step": 21660 }, { "epoch": 1.8, "learning_rate": 3.761028739295513e-06, "loss": 0.7958, "step": 21670 }, { "epoch": 1.8, "learning_rate": 3.760917883767979e-06, "loss": 0.8933, "step": 21680 }, { "epoch": 1.8, "learning_rate": 3.7608070282404457e-06, "loss": 0.9876, "step": 21690 }, { "epoch": 1.8, "learning_rate": 3.7606961727129116e-06, "loss": 0.7734, "step": 21700 }, { "epoch": 1.8, "learning_rate": 3.7605853171853783e-06, "loss": 0.8284, "step": 21710 }, { "epoch": 1.81, "learning_rate": 3.760474461657844e-06, "loss": 0.7901, "step": 21720 }, { "epoch": 1.81, "learning_rate": 3.760374691683064e-06, "loss": 0.8324, "step": 21730 }, { "epoch": 1.81, "learning_rate": 3.76026383615553e-06, "loss": 0.8522, "step": 21740 }, { "epoch": 1.81, "learning_rate": 3.7601529806279967e-06, "loss": 0.9397, "step": 21750 }, { "epoch": 1.81, "learning_rate": 3.7600421251004626e-06, "loss": 0.8665, "step": 21760 }, { "epoch": 1.81, "learning_rate": 3.759931269572929e-06, "loss": 0.8154, "step": 21770 }, { "epoch": 1.81, "learning_rate": 3.759820414045395e-06, "loss": 0.9055, "step": 21780 }, { "epoch": 1.81, "learning_rate": 3.7597095585178615e-06, "loss": 0.886, "step": 21790 }, { "epoch": 1.81, "learning_rate": 3.7595987029903278e-06, "loss": 0.8336, "step": 21800 }, { "epoch": 1.81, "learning_rate": 3.759487847462794e-06, "loss": 0.8094, "step": 21810 }, { "epoch": 1.81, "learning_rate": 3.75937699193526e-06, "loss": 0.8411, "step": 21820 }, { "epoch": 1.81, "learning_rate": 3.7592661364077266e-06, "loss": 0.8413, "step": 21830 }, { "epoch": 1.82, "learning_rate": 3.7591552808801925e-06, "loss": 0.9302, "step": 21840 }, { "epoch": 1.82, "learning_rate": 3.759044425352659e-06, "loss": 0.7983, "step": 21850 }, { "epoch": 1.82, "learning_rate": 3.7589335698251255e-06, "loss": 0.8502, "step": 21860 }, { "epoch": 1.82, "learning_rate": 3.7588227142975914e-06, "loss": 0.8138, "step": 21870 }, { "epoch": 1.82, "learning_rate": 3.758711858770058e-06, "loss": 0.872, "step": 21880 }, { "epoch": 1.82, "learning_rate": 3.758601003242524e-06, "loss": 0.9364, "step": 21890 }, { "epoch": 1.82, "learning_rate": 3.7584901477149903e-06, "loss": 0.8577, "step": 21900 }, { "epoch": 1.82, "learning_rate": 3.7583792921874566e-06, "loss": 0.8332, "step": 21910 }, { "epoch": 1.82, "learning_rate": 3.758268436659923e-06, "loss": 0.8139, "step": 21920 }, { "epoch": 1.82, "learning_rate": 3.7581575811323888e-06, "loss": 0.8845, "step": 21930 }, { "epoch": 1.82, "learning_rate": 3.7580467256048555e-06, "loss": 0.9124, "step": 21940 }, { "epoch": 1.82, "learning_rate": 3.7579358700773213e-06, "loss": 0.8631, "step": 21950 }, { "epoch": 1.83, "learning_rate": 3.7578250145497876e-06, "loss": 0.8353, "step": 21960 }, { "epoch": 1.83, "learning_rate": 3.757714159022254e-06, "loss": 0.8143, "step": 21970 }, { "epoch": 1.83, "learning_rate": 3.7576033034947202e-06, "loss": 0.7817, "step": 21980 }, { "epoch": 1.83, "learning_rate": 3.757492447967187e-06, "loss": 0.9432, "step": 21990 }, { "epoch": 1.83, "learning_rate": 3.757381592439653e-06, "loss": 0.8546, "step": 22000 }, { "epoch": 1.83, "learning_rate": 3.757270736912119e-06, "loss": 0.8056, "step": 22010 }, { "epoch": 1.83, "learning_rate": 3.7571598813845854e-06, "loss": 0.9069, "step": 22020 }, { "epoch": 1.83, "learning_rate": 3.7570490258570517e-06, "loss": 0.7951, "step": 22030 }, { "epoch": 1.83, "learning_rate": 3.7569381703295176e-06, "loss": 0.8705, "step": 22040 }, { "epoch": 1.83, "learning_rate": 3.7568273148019843e-06, "loss": 0.8133, "step": 22050 }, { "epoch": 1.83, "learning_rate": 3.75671645927445e-06, "loss": 0.8385, "step": 22060 }, { "epoch": 1.83, "learning_rate": 3.756605603746917e-06, "loss": 0.8268, "step": 22070 }, { "epoch": 1.84, "learning_rate": 3.7564947482193828e-06, "loss": 0.8889, "step": 22080 }, { "epoch": 1.84, "learning_rate": 3.756383892691849e-06, "loss": 0.8937, "step": 22090 }, { "epoch": 1.84, "learning_rate": 3.7562730371643158e-06, "loss": 0.8244, "step": 22100 }, { "epoch": 1.84, "learning_rate": 3.7561621816367816e-06, "loss": 0.779, "step": 22110 }, { "epoch": 1.84, "learning_rate": 3.756051326109248e-06, "loss": 0.8286, "step": 22120 }, { "epoch": 1.84, "learning_rate": 3.7559404705817142e-06, "loss": 0.8154, "step": 22130 }, { "epoch": 1.84, "learning_rate": 3.7558296150541805e-06, "loss": 0.8994, "step": 22140 }, { "epoch": 1.84, "learning_rate": 3.755718759526647e-06, "loss": 0.8816, "step": 22150 }, { "epoch": 1.84, "learning_rate": 3.755607903999113e-06, "loss": 0.82, "step": 22160 }, { "epoch": 1.84, "learning_rate": 3.755497048471579e-06, "loss": 0.8533, "step": 22170 }, { "epoch": 1.84, "learning_rate": 3.7553861929440457e-06, "loss": 0.9313, "step": 22180 }, { "epoch": 1.84, "learning_rate": 3.7552753374165116e-06, "loss": 0.9092, "step": 22190 }, { "epoch": 1.85, "learning_rate": 3.755164481888978e-06, "loss": 0.8159, "step": 22200 }, { "epoch": 1.85, "learning_rate": 3.755053626361444e-06, "loss": 0.8731, "step": 22210 }, { "epoch": 1.85, "learning_rate": 3.7549427708339105e-06, "loss": 0.795, "step": 22220 }, { "epoch": 1.85, "learning_rate": 3.754831915306377e-06, "loss": 0.8203, "step": 22230 }, { "epoch": 1.85, "learning_rate": 3.754721059778843e-06, "loss": 0.8187, "step": 22240 }, { "epoch": 1.85, "learning_rate": 3.7546102042513094e-06, "loss": 0.783, "step": 22250 }, { "epoch": 1.85, "learning_rate": 3.7544993487237757e-06, "loss": 0.849, "step": 22260 }, { "epoch": 1.85, "learning_rate": 3.754388493196242e-06, "loss": 0.8508, "step": 22270 }, { "epoch": 1.85, "learning_rate": 3.754277637668708e-06, "loss": 0.7998, "step": 22280 }, { "epoch": 1.85, "learning_rate": 3.7541667821411745e-06, "loss": 0.9176, "step": 22290 }, { "epoch": 1.85, "learning_rate": 3.7540559266136404e-06, "loss": 0.8835, "step": 22300 }, { "epoch": 1.85, "learning_rate": 3.753945071086107e-06, "loss": 0.8454, "step": 22310 }, { "epoch": 1.86, "learning_rate": 3.753834215558573e-06, "loss": 0.8394, "step": 22320 }, { "epoch": 1.86, "learning_rate": 3.7537233600310393e-06, "loss": 0.8833, "step": 22330 }, { "epoch": 1.86, "learning_rate": 3.7536125045035056e-06, "loss": 0.8604, "step": 22340 }, { "epoch": 1.86, "learning_rate": 3.753501648975972e-06, "loss": 0.8055, "step": 22350 }, { "epoch": 1.86, "learning_rate": 3.753390793448438e-06, "loss": 0.9069, "step": 22360 }, { "epoch": 1.86, "learning_rate": 3.7532799379209045e-06, "loss": 0.8091, "step": 22370 }, { "epoch": 1.86, "learning_rate": 3.7531690823933708e-06, "loss": 0.8191, "step": 22380 }, { "epoch": 1.86, "learning_rate": 3.7530582268658366e-06, "loss": 0.9168, "step": 22390 }, { "epoch": 1.86, "learning_rate": 3.7529473713383034e-06, "loss": 0.8042, "step": 22400 }, { "epoch": 1.86, "learning_rate": 3.7528365158107692e-06, "loss": 0.8107, "step": 22410 }, { "epoch": 1.86, "learning_rate": 3.752725660283236e-06, "loss": 0.8303, "step": 22420 }, { "epoch": 1.86, "learning_rate": 3.752614804755702e-06, "loss": 0.8484, "step": 22430 }, { "epoch": 1.87, "learning_rate": 3.752503949228168e-06, "loss": 0.8857, "step": 22440 }, { "epoch": 1.87, "learning_rate": 3.7523930937006344e-06, "loss": 0.7943, "step": 22450 }, { "epoch": 1.87, "learning_rate": 3.7522822381731007e-06, "loss": 0.8412, "step": 22460 }, { "epoch": 1.87, "learning_rate": 3.752171382645567e-06, "loss": 0.8277, "step": 22470 }, { "epoch": 1.87, "learning_rate": 3.7520605271180333e-06, "loss": 0.823, "step": 22480 }, { "epoch": 1.87, "learning_rate": 3.7519496715904996e-06, "loss": 0.8419, "step": 22490 }, { "epoch": 1.87, "learning_rate": 3.751838816062966e-06, "loss": 0.8677, "step": 22500 }, { "epoch": 1.87, "learning_rate": 3.751727960535432e-06, "loss": 0.8502, "step": 22510 }, { "epoch": 1.87, "learning_rate": 3.751617105007898e-06, "loss": 0.8477, "step": 22520 }, { "epoch": 1.87, "learning_rate": 3.7515062494803648e-06, "loss": 0.8187, "step": 22530 }, { "epoch": 1.87, "learning_rate": 3.7513953939528307e-06, "loss": 0.875, "step": 22540 }, { "epoch": 1.87, "learning_rate": 3.751284538425297e-06, "loss": 0.8026, "step": 22550 }, { "epoch": 1.88, "learning_rate": 3.7511736828977632e-06, "loss": 0.8142, "step": 22560 }, { "epoch": 1.88, "learning_rate": 3.7510628273702295e-06, "loss": 0.8257, "step": 22570 }, { "epoch": 1.88, "learning_rate": 3.750951971842696e-06, "loss": 0.885, "step": 22580 }, { "epoch": 1.88, "learning_rate": 3.750841116315162e-06, "loss": 0.8786, "step": 22590 }, { "epoch": 1.88, "learning_rate": 3.7507413463403817e-06, "loss": 0.9056, "step": 22600 }, { "epoch": 1.88, "learning_rate": 3.750630490812848e-06, "loss": 0.8624, "step": 22610 }, { "epoch": 1.88, "learning_rate": 3.7505196352853143e-06, "loss": 0.827, "step": 22620 }, { "epoch": 1.88, "learning_rate": 3.7504087797577806e-06, "loss": 0.8858, "step": 22630 }, { "epoch": 1.88, "learning_rate": 3.7502979242302464e-06, "loss": 0.8671, "step": 22640 }, { "epoch": 1.88, "learning_rate": 3.750187068702713e-06, "loss": 0.8486, "step": 22650 }, { "epoch": 1.88, "learning_rate": 3.750076213175179e-06, "loss": 0.8455, "step": 22660 }, { "epoch": 1.88, "learning_rate": 3.7499653576476457e-06, "loss": 0.8074, "step": 22670 }, { "epoch": 1.89, "learning_rate": 3.749854502120112e-06, "loss": 0.8555, "step": 22680 }, { "epoch": 1.89, "learning_rate": 3.749743646592578e-06, "loss": 0.9562, "step": 22690 }, { "epoch": 1.89, "learning_rate": 3.7496327910650446e-06, "loss": 0.8166, "step": 22700 }, { "epoch": 1.89, "learning_rate": 3.7495219355375105e-06, "loss": 0.7503, "step": 22710 }, { "epoch": 1.89, "learning_rate": 3.7494110800099768e-06, "loss": 0.7728, "step": 22720 }, { "epoch": 1.89, "learning_rate": 3.749300224482443e-06, "loss": 0.8711, "step": 22730 }, { "epoch": 1.89, "learning_rate": 3.7491893689549094e-06, "loss": 0.9508, "step": 22740 }, { "epoch": 1.89, "learning_rate": 3.7490785134273757e-06, "loss": 0.8167, "step": 22750 }, { "epoch": 1.89, "learning_rate": 3.748967657899842e-06, "loss": 0.8621, "step": 22760 }, { "epoch": 1.89, "learning_rate": 3.748856802372308e-06, "loss": 0.8255, "step": 22770 }, { "epoch": 1.89, "learning_rate": 3.7487459468447746e-06, "loss": 0.8559, "step": 22780 }, { "epoch": 1.89, "learning_rate": 3.7486350913172404e-06, "loss": 0.8081, "step": 22790 }, { "epoch": 1.9, "learning_rate": 3.7485242357897067e-06, "loss": 0.8447, "step": 22800 }, { "epoch": 1.9, "learning_rate": 3.7484133802621734e-06, "loss": 0.8467, "step": 22810 }, { "epoch": 1.9, "learning_rate": 3.7483025247346393e-06, "loss": 0.9185, "step": 22820 }, { "epoch": 1.9, "learning_rate": 3.748191669207106e-06, "loss": 0.7964, "step": 22830 }, { "epoch": 1.9, "learning_rate": 3.748080813679572e-06, "loss": 0.8555, "step": 22840 }, { "epoch": 1.9, "learning_rate": 3.747969958152038e-06, "loss": 0.8112, "step": 22850 }, { "epoch": 1.9, "learning_rate": 3.7478591026245045e-06, "loss": 0.8079, "step": 22860 }, { "epoch": 1.9, "learning_rate": 3.747748247096971e-06, "loss": 0.925, "step": 22870 }, { "epoch": 1.9, "learning_rate": 3.7476373915694367e-06, "loss": 0.8535, "step": 22880 }, { "epoch": 1.9, "learning_rate": 3.7475265360419034e-06, "loss": 0.8444, "step": 22890 }, { "epoch": 1.9, "learning_rate": 3.7474156805143693e-06, "loss": 0.8321, "step": 22900 }, { "epoch": 1.9, "learning_rate": 3.7473048249868356e-06, "loss": 0.7954, "step": 22910 }, { "epoch": 1.91, "learning_rate": 3.747193969459302e-06, "loss": 0.8435, "step": 22920 }, { "epoch": 1.91, "learning_rate": 3.747083113931768e-06, "loss": 0.8304, "step": 22930 }, { "epoch": 1.91, "learning_rate": 3.746972258404235e-06, "loss": 0.8919, "step": 22940 }, { "epoch": 1.91, "learning_rate": 3.7468614028767007e-06, "loss": 0.8597, "step": 22950 }, { "epoch": 1.91, "learning_rate": 3.746750547349167e-06, "loss": 0.8381, "step": 22960 }, { "epoch": 1.91, "learning_rate": 3.7466396918216333e-06, "loss": 0.839, "step": 22970 }, { "epoch": 1.91, "learning_rate": 3.7465288362940996e-06, "loss": 0.8658, "step": 22980 }, { "epoch": 1.91, "learning_rate": 3.7464179807665655e-06, "loss": 0.8903, "step": 22990 }, { "epoch": 1.91, "learning_rate": 3.746307125239032e-06, "loss": 0.9459, "step": 23000 }, { "epoch": 1.91, "learning_rate": 3.746196269711498e-06, "loss": 0.797, "step": 23010 }, { "epoch": 1.91, "learning_rate": 3.746085414183965e-06, "loss": 0.8447, "step": 23020 }, { "epoch": 1.91, "learning_rate": 3.7459745586564307e-06, "loss": 0.8178, "step": 23030 }, { "epoch": 1.92, "learning_rate": 3.745863703128897e-06, "loss": 0.9338, "step": 23040 }, { "epoch": 1.92, "learning_rate": 3.7457528476013637e-06, "loss": 0.8267, "step": 23050 }, { "epoch": 1.92, "learning_rate": 3.7456419920738296e-06, "loss": 0.8395, "step": 23060 }, { "epoch": 1.92, "learning_rate": 3.745531136546296e-06, "loss": 0.8207, "step": 23070 }, { "epoch": 1.92, "learning_rate": 3.745420281018762e-06, "loss": 0.8561, "step": 23080 }, { "epoch": 1.92, "learning_rate": 3.7453094254912284e-06, "loss": 0.8461, "step": 23090 }, { "epoch": 1.92, "learning_rate": 3.7451985699636947e-06, "loss": 0.7738, "step": 23100 }, { "epoch": 1.92, "learning_rate": 3.745087714436161e-06, "loss": 0.8137, "step": 23110 }, { "epoch": 1.92, "learning_rate": 3.744976858908627e-06, "loss": 0.8764, "step": 23120 }, { "epoch": 1.92, "learning_rate": 3.7448660033810936e-06, "loss": 0.7719, "step": 23130 }, { "epoch": 1.92, "learning_rate": 3.7447551478535595e-06, "loss": 0.9844, "step": 23140 }, { "epoch": 1.92, "learning_rate": 3.744644292326026e-06, "loss": 0.7893, "step": 23150 }, { "epoch": 1.93, "learning_rate": 3.744533436798492e-06, "loss": 0.8673, "step": 23160 }, { "epoch": 1.93, "learning_rate": 3.7444225812709584e-06, "loss": 0.861, "step": 23170 }, { "epoch": 1.93, "learning_rate": 3.744311725743425e-06, "loss": 0.836, "step": 23180 }, { "epoch": 1.93, "learning_rate": 3.744200870215891e-06, "loss": 0.8526, "step": 23190 }, { "epoch": 1.93, "learning_rate": 3.7440900146883573e-06, "loss": 0.8303, "step": 23200 }, { "epoch": 1.93, "learning_rate": 3.7439791591608236e-06, "loss": 0.8862, "step": 23210 }, { "epoch": 1.93, "learning_rate": 3.74386830363329e-06, "loss": 0.822, "step": 23220 }, { "epoch": 1.93, "learning_rate": 3.7437574481057557e-06, "loss": 0.788, "step": 23230 }, { "epoch": 1.93, "learning_rate": 3.7436465925782224e-06, "loss": 0.9167, "step": 23240 }, { "epoch": 1.93, "learning_rate": 3.7435357370506883e-06, "loss": 0.8152, "step": 23250 }, { "epoch": 1.93, "learning_rate": 3.743424881523155e-06, "loss": 0.8152, "step": 23260 }, { "epoch": 1.93, "learning_rate": 3.743314025995621e-06, "loss": 0.8119, "step": 23270 }, { "epoch": 1.94, "learning_rate": 3.743203170468087e-06, "loss": 0.8504, "step": 23280 }, { "epoch": 1.94, "learning_rate": 3.743092314940554e-06, "loss": 0.8741, "step": 23290 }, { "epoch": 1.94, "learning_rate": 3.74298145941302e-06, "loss": 0.8565, "step": 23300 }, { "epoch": 1.94, "learning_rate": 3.742870603885486e-06, "loss": 0.8542, "step": 23310 }, { "epoch": 1.94, "learning_rate": 3.7427597483579524e-06, "loss": 0.7972, "step": 23320 }, { "epoch": 1.94, "learning_rate": 3.7426488928304187e-06, "loss": 0.8293, "step": 23330 }, { "epoch": 1.94, "learning_rate": 3.7425380373028846e-06, "loss": 0.8936, "step": 23340 }, { "epoch": 1.94, "learning_rate": 3.7424271817753513e-06, "loss": 0.7979, "step": 23350 }, { "epoch": 1.94, "learning_rate": 3.742316326247817e-06, "loss": 0.8227, "step": 23360 }, { "epoch": 1.94, "learning_rate": 3.742205470720284e-06, "loss": 0.8291, "step": 23370 }, { "epoch": 1.94, "learning_rate": 3.7420946151927497e-06, "loss": 0.8235, "step": 23380 }, { "epoch": 1.94, "learning_rate": 3.741983759665216e-06, "loss": 0.8822, "step": 23390 }, { "epoch": 1.94, "learning_rate": 3.7418729041376823e-06, "loss": 0.8116, "step": 23400 }, { "epoch": 1.95, "learning_rate": 3.7417620486101486e-06, "loss": 0.919, "step": 23410 }, { "epoch": 1.95, "learning_rate": 3.741651193082615e-06, "loss": 0.8694, "step": 23420 }, { "epoch": 1.95, "learning_rate": 3.7415403375550812e-06, "loss": 0.7998, "step": 23430 }, { "epoch": 1.95, "learning_rate": 3.7414294820275475e-06, "loss": 0.9073, "step": 23440 }, { "epoch": 1.95, "learning_rate": 3.741318626500014e-06, "loss": 0.84, "step": 23450 }, { "epoch": 1.95, "learning_rate": 3.74120777097248e-06, "loss": 0.8254, "step": 23460 }, { "epoch": 1.95, "learning_rate": 3.741096915444946e-06, "loss": 0.8604, "step": 23470 }, { "epoch": 1.95, "learning_rate": 3.7409860599174127e-06, "loss": 0.8501, "step": 23480 }, { "epoch": 1.95, "learning_rate": 3.7408752043898786e-06, "loss": 0.8591, "step": 23490 }, { "epoch": 1.95, "learning_rate": 3.740764348862345e-06, "loss": 0.8234, "step": 23500 }, { "epoch": 1.95, "learning_rate": 3.740653493334811e-06, "loss": 0.7844, "step": 23510 }, { "epoch": 1.95, "learning_rate": 3.7405426378072774e-06, "loss": 0.8215, "step": 23520 }, { "epoch": 1.96, "learning_rate": 3.7404317822797437e-06, "loss": 0.784, "step": 23530 }, { "epoch": 1.96, "learning_rate": 3.74032092675221e-06, "loss": 0.8254, "step": 23540 }, { "epoch": 1.96, "learning_rate": 3.7402100712246763e-06, "loss": 0.8952, "step": 23550 }, { "epoch": 1.96, "learning_rate": 3.7400992156971426e-06, "loss": 0.8209, "step": 23560 }, { "epoch": 1.96, "learning_rate": 3.739988360169609e-06, "loss": 0.7907, "step": 23570 }, { "epoch": 1.96, "learning_rate": 3.739877504642075e-06, "loss": 0.8191, "step": 23580 }, { "epoch": 1.96, "learning_rate": 3.7397666491145415e-06, "loss": 0.8441, "step": 23590 }, { "epoch": 1.96, "learning_rate": 3.7396557935870074e-06, "loss": 0.7745, "step": 23600 }, { "epoch": 1.96, "learning_rate": 3.739544938059474e-06, "loss": 0.8326, "step": 23610 }, { "epoch": 1.96, "learning_rate": 3.73943408253194e-06, "loss": 0.8137, "step": 23620 }, { "epoch": 1.96, "learning_rate": 3.7393232270044063e-06, "loss": 0.8156, "step": 23630 }, { "epoch": 1.96, "learning_rate": 3.7392123714768726e-06, "loss": 0.9342, "step": 23640 }, { "epoch": 1.97, "learning_rate": 3.739101515949339e-06, "loss": 0.918, "step": 23650 }, { "epoch": 1.97, "learning_rate": 3.738990660421805e-06, "loss": 0.8587, "step": 23660 }, { "epoch": 1.97, "learning_rate": 3.7388798048942715e-06, "loss": 0.8531, "step": 23670 }, { "epoch": 1.97, "learning_rate": 3.7387689493667378e-06, "loss": 0.8272, "step": 23680 }, { "epoch": 1.97, "learning_rate": 3.7386580938392036e-06, "loss": 0.9029, "step": 23690 }, { "epoch": 1.97, "learning_rate": 3.7385472383116703e-06, "loss": 0.9144, "step": 23700 }, { "epoch": 1.97, "learning_rate": 3.7384363827841362e-06, "loss": 0.8512, "step": 23710 }, { "epoch": 1.97, "learning_rate": 3.738325527256603e-06, "loss": 0.8184, "step": 23720 }, { "epoch": 1.97, "learning_rate": 3.738214671729069e-06, "loss": 0.8289, "step": 23730 }, { "epoch": 1.97, "learning_rate": 3.738103816201535e-06, "loss": 0.8587, "step": 23740 }, { "epoch": 1.97, "learning_rate": 3.7379929606740014e-06, "loss": 0.7933, "step": 23750 }, { "epoch": 1.97, "learning_rate": 3.7378821051464677e-06, "loss": 0.8701, "step": 23760 }, { "epoch": 1.98, "learning_rate": 3.7377712496189336e-06, "loss": 0.7749, "step": 23770 }, { "epoch": 1.98, "learning_rate": 3.7376603940914003e-06, "loss": 0.769, "step": 23780 }, { "epoch": 1.98, "learning_rate": 3.7375495385638666e-06, "loss": 0.907, "step": 23790 }, { "epoch": 1.98, "learning_rate": 3.737438683036333e-06, "loss": 0.8615, "step": 23800 }, { "epoch": 1.98, "learning_rate": 3.737327827508799e-06, "loss": 0.8786, "step": 23810 }, { "epoch": 1.98, "learning_rate": 3.737216971981265e-06, "loss": 0.828, "step": 23820 }, { "epoch": 1.98, "learning_rate": 3.7371061164537318e-06, "loss": 0.8681, "step": 23830 }, { "epoch": 1.98, "learning_rate": 3.7369952609261976e-06, "loss": 0.8284, "step": 23840 }, { "epoch": 1.98, "learning_rate": 3.736884405398664e-06, "loss": 0.8291, "step": 23850 }, { "epoch": 1.98, "learning_rate": 3.7367735498711302e-06, "loss": 0.8443, "step": 23860 }, { "epoch": 1.98, "learning_rate": 3.7366626943435965e-06, "loss": 0.7853, "step": 23870 }, { "epoch": 1.98, "learning_rate": 3.736551838816063e-06, "loss": 0.888, "step": 23880 }, { "epoch": 1.99, "learning_rate": 3.736440983288529e-06, "loss": 0.8801, "step": 23890 }, { "epoch": 1.99, "learning_rate": 3.736330127760995e-06, "loss": 0.845, "step": 23900 }, { "epoch": 1.99, "learning_rate": 3.7362192722334617e-06, "loss": 0.8244, "step": 23910 }, { "epoch": 1.99, "learning_rate": 3.736108416705928e-06, "loss": 0.7866, "step": 23920 }, { "epoch": 1.99, "learning_rate": 3.735997561178394e-06, "loss": 0.792, "step": 23930 }, { "epoch": 1.99, "learning_rate": 3.7358867056508606e-06, "loss": 0.9954, "step": 23940 }, { "epoch": 1.99, "learning_rate": 3.7357758501233265e-06, "loss": 0.7744, "step": 23950 }, { "epoch": 1.99, "learning_rate": 3.735664994595793e-06, "loss": 0.8785, "step": 23960 }, { "epoch": 1.99, "learning_rate": 3.735554139068259e-06, "loss": 0.8698, "step": 23970 }, { "epoch": 1.99, "learning_rate": 3.7354432835407253e-06, "loss": 0.7821, "step": 23980 }, { "epoch": 1.99, "learning_rate": 3.7353324280131916e-06, "loss": 0.9747, "step": 23990 }, { "epoch": 1.99, "learning_rate": 3.735221572485658e-06, "loss": 0.8317, "step": 24000 }, { "epoch": 2.0, "learning_rate": 3.735110716958124e-06, "loss": 0.8972, "step": 24010 }, { "epoch": 2.0, "learning_rate": 3.7349998614305905e-06, "loss": 0.8185, "step": 24020 }, { "epoch": 2.0, "learning_rate": 3.734889005903057e-06, "loss": 0.8127, "step": 24030 }, { "epoch": 2.0, "learning_rate": 3.734778150375523e-06, "loss": 0.815, "step": 24040 }, { "epoch": 2.0, "learning_rate": 3.7346672948479894e-06, "loss": 0.7932, "step": 24050 }, { "epoch": 2.0, "learning_rate": 3.7345564393204553e-06, "loss": 0.8181, "step": 24060 }, { "epoch": 2.0, "eval_loss": 1.0600695610046387, "eval_runtime": 346.2432, "eval_samples_per_second": 7.723, "eval_steps_per_second": 3.861, "eval_wer": 0.6608231743206529, "step": 24062 }, { "epoch": 2.0, "learning_rate": 3.734445583792922e-06, "loss": 0.8769, "step": 24070 }, { "epoch": 2.0, "learning_rate": 3.734334728265388e-06, "loss": 0.8543, "step": 24080 }, { "epoch": 2.0, "learning_rate": 3.734223872737854e-06, "loss": 0.8482, "step": 24090 }, { "epoch": 2.0, "learning_rate": 3.7341130172103205e-06, "loss": 0.8428, "step": 24100 }, { "epoch": 2.0, "learning_rate": 3.7340021616827868e-06, "loss": 0.8456, "step": 24110 }, { "epoch": 2.0, "learning_rate": 3.7338913061552526e-06, "loss": 0.862, "step": 24120 }, { "epoch": 2.01, "learning_rate": 3.7337804506277193e-06, "loss": 0.7614, "step": 24130 }, { "epoch": 2.01, "learning_rate": 3.7336695951001852e-06, "loss": 0.8155, "step": 24140 }, { "epoch": 2.01, "learning_rate": 3.733558739572652e-06, "loss": 0.87, "step": 24150 }, { "epoch": 2.01, "learning_rate": 3.7334478840451182e-06, "loss": 0.7489, "step": 24160 }, { "epoch": 2.01, "learning_rate": 3.733337028517584e-06, "loss": 0.8382, "step": 24170 }, { "epoch": 2.01, "learning_rate": 3.733226172990051e-06, "loss": 0.8771, "step": 24180 }, { "epoch": 2.01, "learning_rate": 3.7331153174625167e-06, "loss": 0.933, "step": 24190 }, { "epoch": 2.01, "learning_rate": 3.733004461934983e-06, "loss": 0.801, "step": 24200 }, { "epoch": 2.01, "learning_rate": 3.7328936064074493e-06, "loss": 0.795, "step": 24210 }, { "epoch": 2.01, "learning_rate": 3.7327827508799156e-06, "loss": 0.898, "step": 24220 }, { "epoch": 2.01, "learning_rate": 3.732671895352382e-06, "loss": 0.8477, "step": 24230 }, { "epoch": 2.01, "learning_rate": 3.732561039824848e-06, "loss": 0.8416, "step": 24240 }, { "epoch": 2.02, "learning_rate": 3.732450184297314e-06, "loss": 0.9069, "step": 24250 }, { "epoch": 2.02, "learning_rate": 3.7323393287697808e-06, "loss": 0.8143, "step": 24260 }, { "epoch": 2.02, "learning_rate": 3.7322284732422466e-06, "loss": 0.8887, "step": 24270 }, { "epoch": 2.02, "learning_rate": 3.732117617714713e-06, "loss": 0.7791, "step": 24280 }, { "epoch": 2.02, "learning_rate": 3.7320067621871796e-06, "loss": 0.826, "step": 24290 }, { "epoch": 2.02, "learning_rate": 3.7318959066596455e-06, "loss": 0.7984, "step": 24300 }, { "epoch": 2.02, "learning_rate": 3.7317850511321122e-06, "loss": 0.8795, "step": 24310 }, { "epoch": 2.02, "learning_rate": 3.731674195604578e-06, "loss": 0.9193, "step": 24320 }, { "epoch": 2.02, "learning_rate": 3.7315633400770444e-06, "loss": 0.8234, "step": 24330 }, { "epoch": 2.02, "learning_rate": 3.7314524845495107e-06, "loss": 0.8411, "step": 24340 }, { "epoch": 2.02, "learning_rate": 3.731341629021977e-06, "loss": 0.7718, "step": 24350 }, { "epoch": 2.02, "learning_rate": 3.731230773494443e-06, "loss": 0.8508, "step": 24360 }, { "epoch": 2.03, "learning_rate": 3.7311199179669096e-06, "loss": 0.9078, "step": 24370 }, { "epoch": 2.03, "learning_rate": 3.7310090624393755e-06, "loss": 0.9002, "step": 24380 }, { "epoch": 2.03, "learning_rate": 3.730898206911842e-06, "loss": 0.8376, "step": 24390 }, { "epoch": 2.03, "learning_rate": 3.7307873513843085e-06, "loss": 0.7663, "step": 24400 }, { "epoch": 2.03, "learning_rate": 3.7306764958567743e-06, "loss": 0.7968, "step": 24410 }, { "epoch": 2.03, "learning_rate": 3.730565640329241e-06, "loss": 0.8988, "step": 24420 }, { "epoch": 2.03, "learning_rate": 3.730454784801707e-06, "loss": 0.9337, "step": 24430 }, { "epoch": 2.03, "learning_rate": 3.7303439292741732e-06, "loss": 0.8197, "step": 24440 }, { "epoch": 2.03, "learning_rate": 3.7302330737466395e-06, "loss": 0.8708, "step": 24450 }, { "epoch": 2.03, "learning_rate": 3.730122218219106e-06, "loss": 0.7877, "step": 24460 }, { "epoch": 2.03, "learning_rate": 3.7300113626915717e-06, "loss": 0.8818, "step": 24470 }, { "epoch": 2.03, "learning_rate": 3.7299005071640384e-06, "loss": 0.8199, "step": 24480 }, { "epoch": 2.04, "learning_rate": 3.7297896516365043e-06, "loss": 0.7282, "step": 24490 }, { "epoch": 2.04, "learning_rate": 3.729678796108971e-06, "loss": 0.8946, "step": 24500 }, { "epoch": 2.04, "learning_rate": 3.729567940581437e-06, "loss": 0.7654, "step": 24510 }, { "epoch": 2.04, "learning_rate": 3.729457085053903e-06, "loss": 0.9162, "step": 24520 }, { "epoch": 2.04, "learning_rate": 3.72934622952637e-06, "loss": 0.8067, "step": 24530 }, { "epoch": 2.04, "learning_rate": 3.7292353739988358e-06, "loss": 0.834, "step": 24540 }, { "epoch": 2.04, "learning_rate": 3.7291245184713025e-06, "loss": 0.8397, "step": 24550 }, { "epoch": 2.04, "learning_rate": 3.7290136629437684e-06, "loss": 0.7962, "step": 24560 }, { "epoch": 2.04, "learning_rate": 3.7289028074162346e-06, "loss": 0.8291, "step": 24570 }, { "epoch": 2.04, "learning_rate": 3.728791951888701e-06, "loss": 0.838, "step": 24580 }, { "epoch": 2.04, "learning_rate": 3.7286810963611672e-06, "loss": 0.8958, "step": 24590 }, { "epoch": 2.04, "learning_rate": 3.728570240833633e-06, "loss": 0.8267, "step": 24600 }, { "epoch": 2.05, "learning_rate": 3.7284593853061e-06, "loss": 0.8458, "step": 24610 }, { "epoch": 2.05, "learning_rate": 3.7283485297785657e-06, "loss": 0.8589, "step": 24620 }, { "epoch": 2.05, "learning_rate": 3.728237674251032e-06, "loss": 0.8566, "step": 24630 }, { "epoch": 2.05, "learning_rate": 3.7281268187234983e-06, "loss": 0.8779, "step": 24640 }, { "epoch": 2.05, "learning_rate": 3.7280159631959646e-06, "loss": 0.7882, "step": 24650 }, { "epoch": 2.05, "learning_rate": 3.7279051076684313e-06, "loss": 0.7832, "step": 24660 }, { "epoch": 2.05, "learning_rate": 3.727794252140897e-06, "loss": 0.8582, "step": 24670 }, { "epoch": 2.05, "learning_rate": 3.7276833966133635e-06, "loss": 0.8529, "step": 24680 }, { "epoch": 2.05, "learning_rate": 3.7275725410858298e-06, "loss": 0.8335, "step": 24690 }, { "epoch": 2.05, "learning_rate": 3.727461685558296e-06, "loss": 0.8017, "step": 24700 }, { "epoch": 2.05, "learning_rate": 3.727350830030762e-06, "loss": 0.8439, "step": 24710 }, { "epoch": 2.05, "learning_rate": 3.7272399745032287e-06, "loss": 0.93, "step": 24720 }, { "epoch": 2.06, "learning_rate": 3.7271291189756945e-06, "loss": 0.8364, "step": 24730 }, { "epoch": 2.06, "learning_rate": 3.7270182634481612e-06, "loss": 0.8689, "step": 24740 }, { "epoch": 2.06, "learning_rate": 3.726907407920627e-06, "loss": 0.8044, "step": 24750 }, { "epoch": 2.06, "learning_rate": 3.7267965523930934e-06, "loss": 0.8704, "step": 24760 }, { "epoch": 2.06, "learning_rate": 3.72668569686556e-06, "loss": 0.876, "step": 24770 }, { "epoch": 2.06, "learning_rate": 3.726574841338026e-06, "loss": 0.8133, "step": 24780 }, { "epoch": 2.06, "learning_rate": 3.7264639858104923e-06, "loss": 0.7907, "step": 24790 }, { "epoch": 2.06, "learning_rate": 3.7263531302829586e-06, "loss": 0.8111, "step": 24800 }, { "epoch": 2.06, "learning_rate": 3.726242274755425e-06, "loss": 0.854, "step": 24810 }, { "epoch": 2.06, "learning_rate": 3.726131419227891e-06, "loss": 0.8905, "step": 24820 }, { "epoch": 2.06, "learning_rate": 3.7260205637003575e-06, "loss": 0.8317, "step": 24830 }, { "epoch": 2.06, "learning_rate": 3.7259097081728234e-06, "loss": 0.8016, "step": 24840 }, { "epoch": 2.07, "learning_rate": 3.72579885264529e-06, "loss": 0.849, "step": 24850 }, { "epoch": 2.07, "learning_rate": 3.725687997117756e-06, "loss": 0.7785, "step": 24860 }, { "epoch": 2.07, "learning_rate": 3.7255771415902222e-06, "loss": 0.9457, "step": 24870 }, { "epoch": 2.07, "learning_rate": 3.7254662860626885e-06, "loss": 0.849, "step": 24880 }, { "epoch": 2.07, "learning_rate": 3.725355430535155e-06, "loss": 0.8239, "step": 24890 }, { "epoch": 2.07, "learning_rate": 3.7252445750076215e-06, "loss": 0.8511, "step": 24900 }, { "epoch": 2.07, "learning_rate": 3.7251337194800874e-06, "loss": 0.8577, "step": 24910 }, { "epoch": 2.07, "learning_rate": 3.7250228639525537e-06, "loss": 0.8899, "step": 24920 }, { "epoch": 2.07, "learning_rate": 3.72491200842502e-06, "loss": 0.8409, "step": 24930 }, { "epoch": 2.07, "learning_rate": 3.7248011528974863e-06, "loss": 0.7997, "step": 24940 }, { "epoch": 2.07, "learning_rate": 3.724690297369952e-06, "loss": 0.7956, "step": 24950 }, { "epoch": 2.07, "learning_rate": 3.724579441842419e-06, "loss": 0.8007, "step": 24960 }, { "epoch": 2.08, "learning_rate": 3.7244685863148848e-06, "loss": 0.9367, "step": 24970 }, { "epoch": 2.08, "learning_rate": 3.724357730787351e-06, "loss": 0.8802, "step": 24980 }, { "epoch": 2.08, "learning_rate": 3.7242468752598174e-06, "loss": 0.8621, "step": 24990 }, { "epoch": 2.08, "learning_rate": 3.7241360197322837e-06, "loss": 0.8552, "step": 25000 }, { "epoch": 2.08, "learning_rate": 3.72402516420475e-06, "loss": 0.8951, "step": 25010 }, { "epoch": 2.08, "learning_rate": 3.7239143086772162e-06, "loss": 0.8853, "step": 25020 }, { "epoch": 2.08, "learning_rate": 3.7238034531496825e-06, "loss": 0.8747, "step": 25030 }, { "epoch": 2.08, "learning_rate": 3.723692597622149e-06, "loss": 0.8545, "step": 25040 }, { "epoch": 2.08, "learning_rate": 3.723581742094615e-06, "loss": 0.8435, "step": 25050 }, { "epoch": 2.08, "learning_rate": 3.723470886567081e-06, "loss": 0.8142, "step": 25060 }, { "epoch": 2.08, "learning_rate": 3.7233600310395477e-06, "loss": 0.8849, "step": 25070 }, { "epoch": 2.08, "learning_rate": 3.7232491755120136e-06, "loss": 0.7909, "step": 25080 }, { "epoch": 2.09, "learning_rate": 3.7231383199844803e-06, "loss": 0.8004, "step": 25090 }, { "epoch": 2.09, "learning_rate": 3.723027464456946e-06, "loss": 0.7727, "step": 25100 }, { "epoch": 2.09, "learning_rate": 3.7229166089294125e-06, "loss": 0.8233, "step": 25110 }, { "epoch": 2.09, "learning_rate": 3.7228057534018788e-06, "loss": 0.7798, "step": 25120 }, { "epoch": 2.09, "learning_rate": 3.722694897874345e-06, "loss": 0.8053, "step": 25130 }, { "epoch": 2.09, "learning_rate": 3.7225840423468114e-06, "loss": 0.8545, "step": 25140 }, { "epoch": 2.09, "learning_rate": 3.7224731868192777e-06, "loss": 0.8281, "step": 25150 }, { "epoch": 2.09, "learning_rate": 3.722362331291744e-06, "loss": 0.7567, "step": 25160 }, { "epoch": 2.09, "learning_rate": 3.7222514757642103e-06, "loss": 0.9451, "step": 25170 }, { "epoch": 2.09, "learning_rate": 3.7221406202366765e-06, "loss": 0.782, "step": 25180 }, { "epoch": 2.09, "learning_rate": 3.7220297647091424e-06, "loss": 0.8322, "step": 25190 }, { "epoch": 2.09, "learning_rate": 3.721918909181609e-06, "loss": 0.8759, "step": 25200 }, { "epoch": 2.1, "learning_rate": 3.721808053654075e-06, "loss": 0.7804, "step": 25210 }, { "epoch": 2.1, "learning_rate": 3.7216971981265413e-06, "loss": 0.8084, "step": 25220 }, { "epoch": 2.1, "learning_rate": 3.7215863425990076e-06, "loss": 0.8272, "step": 25230 }, { "epoch": 2.1, "learning_rate": 3.721475487071474e-06, "loss": 0.9528, "step": 25240 }, { "epoch": 2.1, "learning_rate": 3.72136463154394e-06, "loss": 0.8482, "step": 25250 }, { "epoch": 2.1, "learning_rate": 3.7212537760164065e-06, "loss": 0.8746, "step": 25260 }, { "epoch": 2.1, "learning_rate": 3.7211429204888728e-06, "loss": 0.9144, "step": 25270 }, { "epoch": 2.1, "learning_rate": 3.721032064961339e-06, "loss": 0.8836, "step": 25280 }, { "epoch": 2.1, "learning_rate": 3.7209212094338054e-06, "loss": 0.8099, "step": 25290 }, { "epoch": 2.1, "learning_rate": 3.7208103539062712e-06, "loss": 0.8507, "step": 25300 }, { "epoch": 2.1, "learning_rate": 3.720699498378738e-06, "loss": 0.8325, "step": 25310 }, { "epoch": 2.1, "learning_rate": 3.720588642851204e-06, "loss": 0.8204, "step": 25320 }, { "epoch": 2.11, "learning_rate": 3.7204777873236706e-06, "loss": 0.748, "step": 25330 }, { "epoch": 2.11, "learning_rate": 3.7203669317961364e-06, "loss": 0.9338, "step": 25340 }, { "epoch": 2.11, "learning_rate": 3.7202560762686027e-06, "loss": 0.8477, "step": 25350 }, { "epoch": 2.11, "learning_rate": 3.720145220741069e-06, "loss": 0.8054, "step": 25360 }, { "epoch": 2.11, "learning_rate": 3.7200343652135353e-06, "loss": 0.8547, "step": 25370 }, { "epoch": 2.11, "learning_rate": 3.7199235096860016e-06, "loss": 0.8554, "step": 25380 }, { "epoch": 2.11, "learning_rate": 3.719812654158468e-06, "loss": 0.7976, "step": 25390 }, { "epoch": 2.11, "learning_rate": 3.719701798630934e-06, "loss": 0.8065, "step": 25400 }, { "epoch": 2.11, "learning_rate": 3.7195909431034e-06, "loss": 0.791, "step": 25410 }, { "epoch": 2.11, "learning_rate": 3.7194800875758668e-06, "loss": 0.8851, "step": 25420 }, { "epoch": 2.11, "learning_rate": 3.7193692320483327e-06, "loss": 0.864, "step": 25430 }, { "epoch": 2.11, "learning_rate": 3.7192583765207994e-06, "loss": 0.8244, "step": 25440 }, { "epoch": 2.12, "learning_rate": 3.7191475209932652e-06, "loss": 0.8917, "step": 25450 }, { "epoch": 2.12, "learning_rate": 3.7190366654657315e-06, "loss": 0.7934, "step": 25460 }, { "epoch": 2.12, "learning_rate": 3.718925809938198e-06, "loss": 0.8515, "step": 25470 }, { "epoch": 2.12, "learning_rate": 3.718814954410664e-06, "loss": 0.7992, "step": 25480 }, { "epoch": 2.12, "learning_rate": 3.71870409888313e-06, "loss": 0.8321, "step": 25490 }, { "epoch": 2.12, "learning_rate": 3.7185932433555967e-06, "loss": 0.8628, "step": 25500 }, { "epoch": 2.12, "learning_rate": 3.718482387828063e-06, "loss": 0.7755, "step": 25510 }, { "epoch": 2.12, "learning_rate": 3.7183715323005293e-06, "loss": 0.8969, "step": 25520 }, { "epoch": 2.12, "learning_rate": 3.7182606767729956e-06, "loss": 0.867, "step": 25530 }, { "epoch": 2.12, "learning_rate": 3.7181498212454615e-06, "loss": 0.883, "step": 25540 }, { "epoch": 2.12, "learning_rate": 3.718038965717928e-06, "loss": 0.8302, "step": 25550 }, { "epoch": 2.12, "learning_rate": 3.717928110190394e-06, "loss": 0.8583, "step": 25560 }, { "epoch": 2.13, "learning_rate": 3.7178172546628604e-06, "loss": 0.8738, "step": 25570 }, { "epoch": 2.13, "learning_rate": 3.7177063991353267e-06, "loss": 0.8975, "step": 25580 }, { "epoch": 2.13, "learning_rate": 3.717595543607793e-06, "loss": 0.8321, "step": 25590 }, { "epoch": 2.13, "learning_rate": 3.7174846880802593e-06, "loss": 0.8493, "step": 25600 }, { "epoch": 2.13, "learning_rate": 3.7173738325527256e-06, "loss": 0.8916, "step": 25610 }, { "epoch": 2.13, "learning_rate": 3.7172629770251914e-06, "loss": 0.9252, "step": 25620 }, { "epoch": 2.13, "learning_rate": 3.717152121497658e-06, "loss": 0.8078, "step": 25630 }, { "epoch": 2.13, "learning_rate": 3.7170412659701244e-06, "loss": 0.8436, "step": 25640 }, { "epoch": 2.13, "learning_rate": 3.7169304104425903e-06, "loss": 0.7898, "step": 25650 }, { "epoch": 2.13, "learning_rate": 3.716819554915057e-06, "loss": 0.8374, "step": 25660 }, { "epoch": 2.13, "learning_rate": 3.716708699387523e-06, "loss": 0.9214, "step": 25670 }, { "epoch": 2.13, "learning_rate": 3.7165978438599896e-06, "loss": 0.8255, "step": 25680 }, { "epoch": 2.14, "learning_rate": 3.7164869883324555e-06, "loss": 0.8467, "step": 25690 }, { "epoch": 2.14, "learning_rate": 3.7163761328049218e-06, "loss": 0.7759, "step": 25700 }, { "epoch": 2.14, "learning_rate": 3.716265277277388e-06, "loss": 0.8391, "step": 25710 }, { "epoch": 2.14, "learning_rate": 3.7161544217498544e-06, "loss": 0.907, "step": 25720 }, { "epoch": 2.14, "learning_rate": 3.7160435662223202e-06, "loss": 0.7797, "step": 25730 }, { "epoch": 2.14, "learning_rate": 3.715932710694787e-06, "loss": 0.8506, "step": 25740 }, { "epoch": 2.14, "learning_rate": 3.7158218551672533e-06, "loss": 0.7567, "step": 25750 }, { "epoch": 2.14, "learning_rate": 3.7157109996397196e-06, "loss": 0.8442, "step": 25760 }, { "epoch": 2.14, "learning_rate": 3.715600144112186e-06, "loss": 0.9032, "step": 25770 }, { "epoch": 2.14, "learning_rate": 3.7154892885846517e-06, "loss": 0.8489, "step": 25780 }, { "epoch": 2.14, "learning_rate": 3.7153784330571184e-06, "loss": 0.8001, "step": 25790 }, { "epoch": 2.14, "learning_rate": 3.7152675775295843e-06, "loss": 0.864, "step": 25800 }, { "epoch": 2.15, "learning_rate": 3.7151567220020506e-06, "loss": 0.8308, "step": 25810 }, { "epoch": 2.15, "learning_rate": 3.715045866474517e-06, "loss": 0.9425, "step": 25820 }, { "epoch": 2.15, "learning_rate": 3.714935010946983e-06, "loss": 0.8673, "step": 25830 }, { "epoch": 2.15, "learning_rate": 3.714824155419449e-06, "loss": 0.8186, "step": 25840 }, { "epoch": 2.15, "learning_rate": 3.714713299891916e-06, "loss": 0.8113, "step": 25850 }, { "epoch": 2.15, "learning_rate": 3.7146024443643817e-06, "loss": 0.8764, "step": 25860 }, { "epoch": 2.15, "learning_rate": 3.7144915888368484e-06, "loss": 0.9125, "step": 25870 }, { "epoch": 2.15, "learning_rate": 3.7143807333093147e-06, "loss": 0.7746, "step": 25880 }, { "epoch": 2.15, "learning_rate": 3.7142698777817805e-06, "loss": 0.8921, "step": 25890 }, { "epoch": 2.15, "learning_rate": 3.7141590222542473e-06, "loss": 0.7772, "step": 25900 }, { "epoch": 2.15, "learning_rate": 3.714048166726713e-06, "loss": 0.7998, "step": 25910 }, { "epoch": 2.15, "learning_rate": 3.7139373111991794e-06, "loss": 0.879, "step": 25920 }, { "epoch": 2.16, "learning_rate": 3.7138264556716457e-06, "loss": 0.9046, "step": 25930 }, { "epoch": 2.16, "learning_rate": 3.713715600144112e-06, "loss": 0.8364, "step": 25940 }, { "epoch": 2.16, "learning_rate": 3.7136047446165783e-06, "loss": 0.8032, "step": 25950 }, { "epoch": 2.16, "learning_rate": 3.7134938890890446e-06, "loss": 0.7866, "step": 25960 }, { "epoch": 2.16, "learning_rate": 3.7133830335615105e-06, "loss": 0.8391, "step": 25970 }, { "epoch": 2.16, "learning_rate": 3.713272178033977e-06, "loss": 0.8886, "step": 25980 }, { "epoch": 2.16, "learning_rate": 3.713161322506443e-06, "loss": 0.8486, "step": 25990 }, { "epoch": 2.16, "learning_rate": 3.7130504669789094e-06, "loss": 0.8942, "step": 26000 }, { "epoch": 2.16, "learning_rate": 3.712939611451376e-06, "loss": 0.8039, "step": 26010 }, { "epoch": 2.16, "learning_rate": 3.712828755923842e-06, "loss": 0.898, "step": 26020 }, { "epoch": 2.16, "learning_rate": 3.7127179003963087e-06, "loss": 0.7782, "step": 26030 }, { "epoch": 2.16, "learning_rate": 3.7126070448687746e-06, "loss": 0.8309, "step": 26040 }, { "epoch": 2.17, "learning_rate": 3.712496189341241e-06, "loss": 0.7943, "step": 26050 }, { "epoch": 2.17, "learning_rate": 3.712385333813707e-06, "loss": 0.8756, "step": 26060 }, { "epoch": 2.17, "learning_rate": 3.7122744782861734e-06, "loss": 0.9143, "step": 26070 }, { "epoch": 2.17, "learning_rate": 3.7121636227586393e-06, "loss": 0.7813, "step": 26080 }, { "epoch": 2.17, "learning_rate": 3.712052767231106e-06, "loss": 0.9154, "step": 26090 }, { "epoch": 2.17, "learning_rate": 3.711941911703572e-06, "loss": 0.8847, "step": 26100 }, { "epoch": 2.17, "learning_rate": 3.7118310561760386e-06, "loss": 0.8892, "step": 26110 }, { "epoch": 2.17, "learning_rate": 3.711720200648505e-06, "loss": 0.8669, "step": 26120 }, { "epoch": 2.17, "learning_rate": 3.711609345120971e-06, "loss": 0.8095, "step": 26130 }, { "epoch": 2.17, "learning_rate": 3.7114984895934375e-06, "loss": 0.7631, "step": 26140 }, { "epoch": 2.17, "learning_rate": 3.7113876340659034e-06, "loss": 0.8396, "step": 26150 }, { "epoch": 2.17, "learning_rate": 3.7112767785383697e-06, "loss": 0.8132, "step": 26160 }, { "epoch": 2.18, "learning_rate": 3.711165923010836e-06, "loss": 0.8675, "step": 26170 }, { "epoch": 2.18, "learning_rate": 3.7110550674833023e-06, "loss": 0.9049, "step": 26180 }, { "epoch": 2.18, "learning_rate": 3.710944211955768e-06, "loss": 0.8827, "step": 26190 }, { "epoch": 2.18, "learning_rate": 3.710833356428235e-06, "loss": 0.7479, "step": 26200 }, { "epoch": 2.18, "learning_rate": 3.7107225009007007e-06, "loss": 0.7723, "step": 26210 }, { "epoch": 2.18, "learning_rate": 3.7106116453731674e-06, "loss": 0.8258, "step": 26220 }, { "epoch": 2.18, "learning_rate": 3.7105007898456333e-06, "loss": 0.8156, "step": 26230 }, { "epoch": 2.18, "learning_rate": 3.7103899343180996e-06, "loss": 0.7722, "step": 26240 }, { "epoch": 2.18, "learning_rate": 3.7102790787905663e-06, "loss": 0.8123, "step": 26250 }, { "epoch": 2.18, "learning_rate": 3.710168223263032e-06, "loss": 0.7639, "step": 26260 }, { "epoch": 2.18, "learning_rate": 3.7100573677354985e-06, "loss": 0.8421, "step": 26270 }, { "epoch": 2.18, "learning_rate": 3.709946512207965e-06, "loss": 0.7964, "step": 26280 }, { "epoch": 2.19, "learning_rate": 3.709835656680431e-06, "loss": 0.8683, "step": 26290 }, { "epoch": 2.19, "learning_rate": 3.7097248011528974e-06, "loss": 0.8282, "step": 26300 }, { "epoch": 2.19, "learning_rate": 3.7096139456253637e-06, "loss": 0.7572, "step": 26310 }, { "epoch": 2.19, "learning_rate": 3.7095030900978296e-06, "loss": 0.8703, "step": 26320 }, { "epoch": 2.19, "learning_rate": 3.7093922345702963e-06, "loss": 0.8585, "step": 26330 }, { "epoch": 2.19, "learning_rate": 3.709281379042762e-06, "loss": 0.7918, "step": 26340 }, { "epoch": 2.19, "learning_rate": 3.7091705235152284e-06, "loss": 0.8426, "step": 26350 }, { "epoch": 2.19, "learning_rate": 3.7090596679876947e-06, "loss": 0.8198, "step": 26360 }, { "epoch": 2.19, "learning_rate": 3.708948812460161e-06, "loss": 0.831, "step": 26370 }, { "epoch": 2.19, "learning_rate": 3.7088379569326278e-06, "loss": 0.8485, "step": 26380 }, { "epoch": 2.19, "learning_rate": 3.7087271014050936e-06, "loss": 0.801, "step": 26390 }, { "epoch": 2.19, "learning_rate": 3.70861624587756e-06, "loss": 0.8016, "step": 26400 }, { "epoch": 2.2, "learning_rate": 3.7085053903500262e-06, "loss": 0.894, "step": 26410 }, { "epoch": 2.2, "learning_rate": 3.7083945348224925e-06, "loss": 0.861, "step": 26420 }, { "epoch": 2.2, "learning_rate": 3.7082836792949584e-06, "loss": 0.8434, "step": 26430 }, { "epoch": 2.2, "learning_rate": 3.708172823767425e-06, "loss": 0.7761, "step": 26440 }, { "epoch": 2.2, "learning_rate": 3.708061968239891e-06, "loss": 0.8291, "step": 26450 }, { "epoch": 2.2, "learning_rate": 3.7079511127123577e-06, "loss": 0.8113, "step": 26460 }, { "epoch": 2.2, "learning_rate": 3.7078402571848236e-06, "loss": 0.8803, "step": 26470 }, { "epoch": 2.2, "learning_rate": 3.70772940165729e-06, "loss": 0.9076, "step": 26480 }, { "epoch": 2.2, "learning_rate": 3.7076185461297566e-06, "loss": 0.8881, "step": 26490 }, { "epoch": 2.2, "learning_rate": 3.7075076906022224e-06, "loss": 0.8927, "step": 26500 }, { "epoch": 2.2, "learning_rate": 3.7073968350746887e-06, "loss": 0.8149, "step": 26510 }, { "epoch": 2.2, "learning_rate": 3.707285979547155e-06, "loss": 0.8972, "step": 26520 }, { "epoch": 2.21, "learning_rate": 3.7071751240196213e-06, "loss": 0.8858, "step": 26530 }, { "epoch": 2.21, "learning_rate": 3.7070642684920876e-06, "loss": 0.8739, "step": 26540 }, { "epoch": 2.21, "learning_rate": 3.706953412964554e-06, "loss": 0.8671, "step": 26550 }, { "epoch": 2.21, "learning_rate": 3.70684255743702e-06, "loss": 0.8459, "step": 26560 }, { "epoch": 2.21, "learning_rate": 3.7067317019094865e-06, "loss": 0.9651, "step": 26570 }, { "epoch": 2.21, "learning_rate": 3.7066208463819524e-06, "loss": 0.8363, "step": 26580 }, { "epoch": 2.21, "learning_rate": 3.7065099908544187e-06, "loss": 0.8766, "step": 26590 }, { "epoch": 2.21, "learning_rate": 3.706399135326885e-06, "loss": 0.7936, "step": 26600 }, { "epoch": 2.21, "learning_rate": 3.7062882797993513e-06, "loss": 0.8401, "step": 26610 }, { "epoch": 2.21, "learning_rate": 3.706177424271818e-06, "loss": 0.9094, "step": 26620 }, { "epoch": 2.21, "learning_rate": 3.706066568744284e-06, "loss": 0.8212, "step": 26630 }, { "epoch": 2.21, "learning_rate": 3.70595571321675e-06, "loss": 0.8409, "step": 26640 }, { "epoch": 2.22, "learning_rate": 3.7058448576892165e-06, "loss": 0.9045, "step": 26650 }, { "epoch": 2.22, "learning_rate": 3.7057340021616827e-06, "loss": 0.7997, "step": 26660 }, { "epoch": 2.22, "learning_rate": 3.7056231466341486e-06, "loss": 0.878, "step": 26670 }, { "epoch": 2.22, "learning_rate": 3.7055122911066153e-06, "loss": 0.8203, "step": 26680 }, { "epoch": 2.22, "learning_rate": 3.7054014355790812e-06, "loss": 0.7846, "step": 26690 }, { "epoch": 2.22, "learning_rate": 3.7052905800515475e-06, "loss": 0.8497, "step": 26700 }, { "epoch": 2.22, "learning_rate": 3.705179724524014e-06, "loss": 0.7962, "step": 26710 }, { "epoch": 2.22, "learning_rate": 3.70506886899648e-06, "loss": 0.9094, "step": 26720 }, { "epoch": 2.22, "learning_rate": 3.7049580134689464e-06, "loss": 0.8339, "step": 26730 }, { "epoch": 2.22, "learning_rate": 3.7048471579414127e-06, "loss": 0.891, "step": 26740 }, { "epoch": 2.22, "learning_rate": 3.704736302413879e-06, "loss": 0.8165, "step": 26750 }, { "epoch": 2.22, "learning_rate": 3.7046254468863453e-06, "loss": 0.8464, "step": 26760 }, { "epoch": 2.23, "learning_rate": 3.7045145913588116e-06, "loss": 0.8623, "step": 26770 }, { "epoch": 2.23, "learning_rate": 3.7044037358312774e-06, "loss": 0.8467, "step": 26780 }, { "epoch": 2.23, "learning_rate": 3.704292880303744e-06, "loss": 0.8398, "step": 26790 }, { "epoch": 2.23, "learning_rate": 3.70418202477621e-06, "loss": 0.8299, "step": 26800 }, { "epoch": 2.23, "learning_rate": 3.7040711692486768e-06, "loss": 0.8354, "step": 26810 }, { "epoch": 2.23, "learning_rate": 3.7039603137211426e-06, "loss": 0.8802, "step": 26820 }, { "epoch": 2.23, "learning_rate": 3.703849458193609e-06, "loss": 0.8462, "step": 26830 }, { "epoch": 2.23, "learning_rate": 3.7037386026660752e-06, "loss": 0.7908, "step": 26840 }, { "epoch": 2.23, "learning_rate": 3.7036277471385415e-06, "loss": 0.796, "step": 26850 }, { "epoch": 2.23, "learning_rate": 3.703516891611008e-06, "loss": 0.8515, "step": 26860 }, { "epoch": 2.23, "learning_rate": 3.703406036083474e-06, "loss": 0.9124, "step": 26870 }, { "epoch": 2.23, "learning_rate": 3.7032951805559404e-06, "loss": 0.8854, "step": 26880 }, { "epoch": 2.24, "learning_rate": 3.7031843250284067e-06, "loss": 0.7951, "step": 26890 }, { "epoch": 2.24, "learning_rate": 3.703073469500873e-06, "loss": 0.8277, "step": 26900 }, { "epoch": 2.24, "learning_rate": 3.702962613973339e-06, "loss": 0.8732, "step": 26910 }, { "epoch": 2.24, "learning_rate": 3.7028517584458056e-06, "loss": 0.8677, "step": 26920 }, { "epoch": 2.24, "learning_rate": 3.7027409029182715e-06, "loss": 0.8575, "step": 26930 }, { "epoch": 2.24, "learning_rate": 3.7026300473907377e-06, "loss": 0.7971, "step": 26940 }, { "epoch": 2.24, "learning_rate": 3.702519191863204e-06, "loss": 0.8979, "step": 26950 }, { "epoch": 2.24, "learning_rate": 3.7024083363356703e-06, "loss": 0.7693, "step": 26960 }, { "epoch": 2.24, "learning_rate": 3.702297480808136e-06, "loss": 0.8903, "step": 26970 }, { "epoch": 2.24, "learning_rate": 3.702186625280603e-06, "loss": 0.843, "step": 26980 }, { "epoch": 2.24, "learning_rate": 3.7020757697530692e-06, "loss": 0.8327, "step": 26990 }, { "epoch": 2.24, "learning_rate": 3.7019649142255355e-06, "loss": 0.8654, "step": 27000 }, { "epoch": 2.25, "learning_rate": 3.701854058698002e-06, "loss": 0.862, "step": 27010 }, { "epoch": 2.25, "learning_rate": 3.7017432031704677e-06, "loss": 0.8517, "step": 27020 }, { "epoch": 2.25, "learning_rate": 3.7016323476429344e-06, "loss": 0.8393, "step": 27030 }, { "epoch": 2.25, "learning_rate": 3.7015214921154003e-06, "loss": 0.8603, "step": 27040 }, { "epoch": 2.25, "learning_rate": 3.701410636587867e-06, "loss": 0.8571, "step": 27050 }, { "epoch": 2.25, "learning_rate": 3.701299781060333e-06, "loss": 0.8394, "step": 27060 }, { "epoch": 2.25, "learning_rate": 3.701188925532799e-06, "loss": 0.8124, "step": 27070 }, { "epoch": 2.25, "learning_rate": 3.7010780700052655e-06, "loss": 0.76, "step": 27080 }, { "epoch": 2.25, "learning_rate": 3.7009672144777318e-06, "loss": 0.7871, "step": 27090 }, { "epoch": 2.25, "learning_rate": 3.7008563589501976e-06, "loss": 0.8958, "step": 27100 }, { "epoch": 2.25, "learning_rate": 3.7007455034226643e-06, "loss": 0.8079, "step": 27110 }, { "epoch": 2.25, "learning_rate": 3.7006346478951306e-06, "loss": 0.8602, "step": 27120 }, { "epoch": 2.26, "learning_rate": 3.7005237923675965e-06, "loss": 0.8449, "step": 27130 }, { "epoch": 2.26, "learning_rate": 3.7004129368400632e-06, "loss": 0.8814, "step": 27140 }, { "epoch": 2.26, "learning_rate": 3.700302081312529e-06, "loss": 0.773, "step": 27150 }, { "epoch": 2.26, "learning_rate": 3.700191225784996e-06, "loss": 0.8664, "step": 27160 }, { "epoch": 2.26, "learning_rate": 3.7000803702574617e-06, "loss": 0.8886, "step": 27170 }, { "epoch": 2.26, "learning_rate": 3.699969514729928e-06, "loss": 0.8257, "step": 27180 }, { "epoch": 2.26, "learning_rate": 3.6998586592023943e-06, "loss": 0.7904, "step": 27190 }, { "epoch": 2.26, "learning_rate": 3.6997478036748606e-06, "loss": 0.8612, "step": 27200 }, { "epoch": 2.26, "learning_rate": 3.6996369481473265e-06, "loss": 0.8244, "step": 27210 }, { "epoch": 2.26, "learning_rate": 3.699526092619793e-06, "loss": 0.8505, "step": 27220 }, { "epoch": 2.26, "learning_rate": 3.6994152370922595e-06, "loss": 0.8575, "step": 27230 }, { "epoch": 2.26, "learning_rate": 3.6993043815647258e-06, "loss": 0.8174, "step": 27240 }, { "epoch": 2.26, "learning_rate": 3.699193526037192e-06, "loss": 0.839, "step": 27250 }, { "epoch": 2.27, "learning_rate": 3.699082670509658e-06, "loss": 0.81, "step": 27260 }, { "epoch": 2.27, "learning_rate": 3.6989718149821246e-06, "loss": 0.8013, "step": 27270 }, { "epoch": 2.27, "learning_rate": 3.6988609594545905e-06, "loss": 0.8242, "step": 27280 }, { "epoch": 2.27, "learning_rate": 3.698750103927057e-06, "loss": 0.8064, "step": 27290 }, { "epoch": 2.27, "learning_rate": 3.698639248399523e-06, "loss": 0.8087, "step": 27300 }, { "epoch": 2.27, "learning_rate": 3.6985283928719894e-06, "loss": 0.7795, "step": 27310 }, { "epoch": 2.27, "learning_rate": 3.6984175373444557e-06, "loss": 0.9148, "step": 27320 }, { "epoch": 2.27, "learning_rate": 3.698306681816922e-06, "loss": 0.8887, "step": 27330 }, { "epoch": 2.27, "learning_rate": 3.698195826289388e-06, "loss": 0.8304, "step": 27340 }, { "epoch": 2.27, "learning_rate": 3.6980849707618546e-06, "loss": 0.8603, "step": 27350 }, { "epoch": 2.27, "learning_rate": 3.697974115234321e-06, "loss": 0.7765, "step": 27360 }, { "epoch": 2.27, "learning_rate": 3.6978632597067868e-06, "loss": 0.944, "step": 27370 }, { "epoch": 2.28, "learning_rate": 3.6977524041792535e-06, "loss": 0.8664, "step": 27380 }, { "epoch": 2.28, "learning_rate": 3.6976415486517193e-06, "loss": 0.8335, "step": 27390 }, { "epoch": 2.28, "learning_rate": 3.697530693124186e-06, "loss": 0.8146, "step": 27400 }, { "epoch": 2.28, "learning_rate": 3.697419837596652e-06, "loss": 0.8039, "step": 27410 }, { "epoch": 2.28, "learning_rate": 3.6973089820691182e-06, "loss": 0.8898, "step": 27420 }, { "epoch": 2.28, "learning_rate": 3.6971981265415845e-06, "loss": 0.8189, "step": 27430 }, { "epoch": 2.28, "learning_rate": 3.697087271014051e-06, "loss": 0.8033, "step": 27440 }, { "epoch": 2.28, "learning_rate": 3.6969764154865167e-06, "loss": 0.8031, "step": 27450 }, { "epoch": 2.28, "learning_rate": 3.6968655599589834e-06, "loss": 0.8448, "step": 27460 }, { "epoch": 2.28, "learning_rate": 3.6967547044314497e-06, "loss": 0.9187, "step": 27470 }, { "epoch": 2.28, "learning_rate": 3.6966438489039156e-06, "loss": 0.804, "step": 27480 }, { "epoch": 2.28, "learning_rate": 3.6965329933763823e-06, "loss": 0.8383, "step": 27490 }, { "epoch": 2.29, "learning_rate": 3.696422137848848e-06, "loss": 0.8029, "step": 27500 }, { "epoch": 2.29, "learning_rate": 3.696311282321315e-06, "loss": 0.8519, "step": 27510 }, { "epoch": 2.29, "learning_rate": 3.6962004267937808e-06, "loss": 0.8707, "step": 27520 }, { "epoch": 2.29, "learning_rate": 3.696089571266247e-06, "loss": 0.869, "step": 27530 }, { "epoch": 2.29, "learning_rate": 3.6959787157387134e-06, "loss": 0.7919, "step": 27540 }, { "epoch": 2.29, "learning_rate": 3.6958678602111796e-06, "loss": 0.8546, "step": 27550 }, { "epoch": 2.29, "learning_rate": 3.6957570046836455e-06, "loss": 0.8273, "step": 27560 }, { "epoch": 2.29, "learning_rate": 3.6956461491561122e-06, "loss": 0.8528, "step": 27570 }, { "epoch": 2.29, "learning_rate": 3.695535293628578e-06, "loss": 0.8198, "step": 27580 }, { "epoch": 2.29, "learning_rate": 3.695424438101045e-06, "loss": 0.8135, "step": 27590 }, { "epoch": 2.29, "learning_rate": 3.695313582573511e-06, "loss": 0.9039, "step": 27600 }, { "epoch": 2.29, "learning_rate": 3.695202727045977e-06, "loss": 0.8562, "step": 27610 }, { "epoch": 2.3, "learning_rate": 3.6950918715184437e-06, "loss": 0.8834, "step": 27620 }, { "epoch": 2.3, "learning_rate": 3.6949810159909096e-06, "loss": 0.8528, "step": 27630 }, { "epoch": 2.3, "learning_rate": 3.694870160463376e-06, "loss": 0.9072, "step": 27640 }, { "epoch": 2.3, "learning_rate": 3.694759304935842e-06, "loss": 0.785, "step": 27650 }, { "epoch": 2.3, "learning_rate": 3.6946484494083085e-06, "loss": 0.7935, "step": 27660 }, { "epoch": 2.3, "learning_rate": 3.6945375938807748e-06, "loss": 0.8722, "step": 27670 }, { "epoch": 2.3, "learning_rate": 3.694426738353241e-06, "loss": 0.8698, "step": 27680 }, { "epoch": 2.3, "learning_rate": 3.694315882825707e-06, "loss": 0.7781, "step": 27690 }, { "epoch": 2.3, "learning_rate": 3.6942050272981737e-06, "loss": 0.8731, "step": 27700 }, { "epoch": 2.3, "learning_rate": 3.6940941717706395e-06, "loss": 0.9054, "step": 27710 }, { "epoch": 2.3, "learning_rate": 3.693983316243106e-06, "loss": 0.8849, "step": 27720 }, { "epoch": 2.3, "learning_rate": 3.6938724607155725e-06, "loss": 0.8008, "step": 27730 }, { "epoch": 2.31, "learning_rate": 3.6937616051880384e-06, "loss": 0.8295, "step": 27740 }, { "epoch": 2.31, "learning_rate": 3.693650749660505e-06, "loss": 0.875, "step": 27750 }, { "epoch": 2.31, "learning_rate": 3.693539894132971e-06, "loss": 0.9223, "step": 27760 }, { "epoch": 2.31, "learning_rate": 3.6934290386054373e-06, "loss": 0.8767, "step": 27770 }, { "epoch": 2.31, "learning_rate": 3.6933181830779036e-06, "loss": 0.7588, "step": 27780 }, { "epoch": 2.31, "learning_rate": 3.69320732755037e-06, "loss": 0.8297, "step": 27790 }, { "epoch": 2.31, "learning_rate": 3.6930964720228358e-06, "loss": 0.7834, "step": 27800 }, { "epoch": 2.31, "learning_rate": 3.6929856164953025e-06, "loss": 0.798, "step": 27810 }, { "epoch": 2.31, "learning_rate": 3.6928747609677684e-06, "loss": 0.9435, "step": 27820 }, { "epoch": 2.31, "learning_rate": 3.692763905440235e-06, "loss": 0.8509, "step": 27830 }, { "epoch": 2.31, "learning_rate": 3.6926530499127014e-06, "loss": 0.8236, "step": 27840 }, { "epoch": 2.31, "learning_rate": 3.6925421943851672e-06, "loss": 0.8294, "step": 27850 }, { "epoch": 2.32, "learning_rate": 3.692431338857634e-06, "loss": 0.8442, "step": 27860 }, { "epoch": 2.32, "learning_rate": 3.6923204833301e-06, "loss": 0.8305, "step": 27870 }, { "epoch": 2.32, "learning_rate": 3.692209627802566e-06, "loss": 0.7914, "step": 27880 }, { "epoch": 2.32, "learning_rate": 3.6920987722750324e-06, "loss": 0.847, "step": 27890 }, { "epoch": 2.32, "learning_rate": 3.6919879167474987e-06, "loss": 0.8599, "step": 27900 }, { "epoch": 2.32, "learning_rate": 3.6918770612199646e-06, "loss": 0.8182, "step": 27910 }, { "epoch": 2.32, "learning_rate": 3.6917662056924313e-06, "loss": 0.8384, "step": 27920 }, { "epoch": 2.32, "learning_rate": 3.691655350164897e-06, "loss": 0.8919, "step": 27930 }, { "epoch": 2.32, "learning_rate": 3.691544494637364e-06, "loss": 0.8435, "step": 27940 }, { "epoch": 2.32, "learning_rate": 3.6914336391098298e-06, "loss": 0.7581, "step": 27950 }, { "epoch": 2.32, "learning_rate": 3.691322783582296e-06, "loss": 0.8104, "step": 27960 }, { "epoch": 2.32, "learning_rate": 3.6912119280547628e-06, "loss": 0.8914, "step": 27970 }, { "epoch": 2.33, "learning_rate": 3.6911010725272287e-06, "loss": 0.8909, "step": 27980 }, { "epoch": 2.33, "learning_rate": 3.690990216999695e-06, "loss": 0.8517, "step": 27990 }, { "epoch": 2.33, "learning_rate": 3.6908793614721612e-06, "loss": 0.8375, "step": 28000 }, { "epoch": 2.33, "learning_rate": 3.6907685059446275e-06, "loss": 0.8481, "step": 28010 }, { "epoch": 2.33, "learning_rate": 3.690657650417094e-06, "loss": 0.888, "step": 28020 }, { "epoch": 2.33, "learning_rate": 3.69054679488956e-06, "loss": 0.7603, "step": 28030 }, { "epoch": 2.33, "learning_rate": 3.690435939362026e-06, "loss": 0.8067, "step": 28040 }, { "epoch": 2.33, "learning_rate": 3.6903250838344927e-06, "loss": 0.8559, "step": 28050 }, { "epoch": 2.33, "learning_rate": 3.6902142283069586e-06, "loss": 0.8504, "step": 28060 }, { "epoch": 2.33, "learning_rate": 3.690103372779425e-06, "loss": 0.8423, "step": 28070 }, { "epoch": 2.33, "learning_rate": 3.689992517251891e-06, "loss": 0.8195, "step": 28080 }, { "epoch": 2.33, "learning_rate": 3.6898816617243575e-06, "loss": 0.7912, "step": 28090 }, { "epoch": 2.34, "learning_rate": 3.689770806196824e-06, "loss": 0.9285, "step": 28100 }, { "epoch": 2.34, "learning_rate": 3.68965995066929e-06, "loss": 0.8664, "step": 28110 }, { "epoch": 2.34, "learning_rate": 3.6895490951417564e-06, "loss": 0.8698, "step": 28120 }, { "epoch": 2.34, "learning_rate": 3.6894382396142227e-06, "loss": 0.8556, "step": 28130 }, { "epoch": 2.34, "learning_rate": 3.689327384086689e-06, "loss": 0.8345, "step": 28140 }, { "epoch": 2.34, "learning_rate": 3.689216528559155e-06, "loss": 0.89, "step": 28150 }, { "epoch": 2.34, "learning_rate": 3.6891056730316215e-06, "loss": 0.8677, "step": 28160 }, { "epoch": 2.34, "learning_rate": 3.6889948175040874e-06, "loss": 0.8971, "step": 28170 }, { "epoch": 2.34, "learning_rate": 3.688883961976554e-06, "loss": 0.8407, "step": 28180 }, { "epoch": 2.34, "learning_rate": 3.68877310644902e-06, "loss": 0.858, "step": 28190 }, { "epoch": 2.34, "learning_rate": 3.6886622509214863e-06, "loss": 0.7942, "step": 28200 }, { "epoch": 2.34, "learning_rate": 3.688551395393953e-06, "loss": 0.8541, "step": 28210 }, { "epoch": 2.35, "learning_rate": 3.688440539866419e-06, "loss": 0.8521, "step": 28220 }, { "epoch": 2.35, "learning_rate": 3.688329684338885e-06, "loss": 0.909, "step": 28230 }, { "epoch": 2.35, "learning_rate": 3.6882188288113515e-06, "loss": 0.8679, "step": 28240 }, { "epoch": 2.35, "learning_rate": 3.6881079732838178e-06, "loss": 0.8649, "step": 28250 }, { "epoch": 2.35, "learning_rate": 3.6879971177562837e-06, "loss": 0.8235, "step": 28260 }, { "epoch": 2.35, "learning_rate": 3.6878862622287504e-06, "loss": 0.8592, "step": 28270 }, { "epoch": 2.35, "learning_rate": 3.6877754067012162e-06, "loss": 0.8553, "step": 28280 }, { "epoch": 2.35, "learning_rate": 3.687664551173683e-06, "loss": 0.8541, "step": 28290 }, { "epoch": 2.35, "learning_rate": 3.687553695646149e-06, "loss": 0.8602, "step": 28300 }, { "epoch": 2.35, "learning_rate": 3.687442840118615e-06, "loss": 0.8394, "step": 28310 }, { "epoch": 2.35, "learning_rate": 3.6873319845910814e-06, "loss": 0.8702, "step": 28320 }, { "epoch": 2.35, "learning_rate": 3.6872211290635477e-06, "loss": 0.8759, "step": 28330 }, { "epoch": 2.36, "learning_rate": 3.6871102735360144e-06, "loss": 0.8253, "step": 28340 }, { "epoch": 2.36, "learning_rate": 3.6869994180084803e-06, "loss": 0.8265, "step": 28350 }, { "epoch": 2.36, "learning_rate": 3.6868885624809466e-06, "loss": 0.9161, "step": 28360 }, { "epoch": 2.36, "learning_rate": 3.686777706953413e-06, "loss": 0.8445, "step": 28370 }, { "epoch": 2.36, "learning_rate": 3.686666851425879e-06, "loss": 0.8634, "step": 28380 }, { "epoch": 2.36, "learning_rate": 3.686555995898345e-06, "loss": 0.8357, "step": 28390 }, { "epoch": 2.36, "learning_rate": 3.6864451403708118e-06, "loss": 0.8609, "step": 28400 }, { "epoch": 2.36, "learning_rate": 3.6863342848432777e-06, "loss": 0.8277, "step": 28410 }, { "epoch": 2.36, "learning_rate": 3.686223429315744e-06, "loss": 0.896, "step": 28420 }, { "epoch": 2.36, "learning_rate": 3.6861125737882102e-06, "loss": 0.8337, "step": 28430 }, { "epoch": 2.36, "learning_rate": 3.6860017182606765e-06, "loss": 0.8099, "step": 28440 }, { "epoch": 2.36, "learning_rate": 3.685890862733143e-06, "loss": 0.7594, "step": 28450 }, { "epoch": 2.37, "learning_rate": 3.685780007205609e-06, "loss": 0.8421, "step": 28460 }, { "epoch": 2.37, "learning_rate": 3.6856691516780754e-06, "loss": 0.9423, "step": 28470 }, { "epoch": 2.37, "learning_rate": 3.6855582961505417e-06, "loss": 0.792, "step": 28480 }, { "epoch": 2.37, "learning_rate": 3.685447440623008e-06, "loss": 0.7902, "step": 28490 }, { "epoch": 2.37, "learning_rate": 3.685336585095474e-06, "loss": 0.8603, "step": 28500 }, { "epoch": 2.37, "learning_rate": 3.6852257295679406e-06, "loss": 0.8936, "step": 28510 }, { "epoch": 2.37, "learning_rate": 3.6851148740404065e-06, "loss": 0.8919, "step": 28520 }, { "epoch": 2.37, "learning_rate": 3.685004018512873e-06, "loss": 0.8706, "step": 28530 }, { "epoch": 2.37, "learning_rate": 3.684893162985339e-06, "loss": 0.8233, "step": 28540 }, { "epoch": 2.37, "learning_rate": 3.6847823074578054e-06, "loss": 0.7843, "step": 28550 }, { "epoch": 2.37, "learning_rate": 3.6846714519302717e-06, "loss": 0.8086, "step": 28560 }, { "epoch": 2.37, "learning_rate": 3.684560596402738e-06, "loss": 0.8071, "step": 28570 }, { "epoch": 2.38, "learning_rate": 3.6844497408752043e-06, "loss": 0.8707, "step": 28580 }, { "epoch": 2.38, "learning_rate": 3.6843388853476706e-06, "loss": 0.78, "step": 28590 }, { "epoch": 2.38, "learning_rate": 3.684228029820137e-06, "loss": 0.8192, "step": 28600 }, { "epoch": 2.38, "learning_rate": 3.684117174292603e-06, "loss": 0.7967, "step": 28610 }, { "epoch": 2.38, "learning_rate": 3.6840063187650694e-06, "loss": 0.9142, "step": 28620 }, { "epoch": 2.38, "learning_rate": 3.6838954632375353e-06, "loss": 0.7715, "step": 28630 }, { "epoch": 2.38, "learning_rate": 3.683784607710002e-06, "loss": 0.8507, "step": 28640 }, { "epoch": 2.38, "learning_rate": 3.683673752182468e-06, "loss": 0.8221, "step": 28650 }, { "epoch": 2.38, "learning_rate": 3.683562896654934e-06, "loss": 0.7572, "step": 28660 }, { "epoch": 2.38, "learning_rate": 3.6834520411274005e-06, "loss": 0.9261, "step": 28670 }, { "epoch": 2.38, "learning_rate": 3.6833411855998668e-06, "loss": 0.9014, "step": 28680 }, { "epoch": 2.38, "learning_rate": 3.6832303300723327e-06, "loss": 0.8205, "step": 28690 }, { "epoch": 2.39, "learning_rate": 3.6831194745447994e-06, "loss": 0.8364, "step": 28700 }, { "epoch": 2.39, "learning_rate": 3.6830086190172657e-06, "loss": 0.8973, "step": 28710 }, { "epoch": 2.39, "learning_rate": 3.682897763489732e-06, "loss": 0.8501, "step": 28720 }, { "epoch": 2.39, "learning_rate": 3.6827869079621983e-06, "loss": 0.858, "step": 28730 }, { "epoch": 2.39, "learning_rate": 3.682676052434664e-06, "loss": 0.8716, "step": 28740 }, { "epoch": 2.39, "learning_rate": 3.682565196907131e-06, "loss": 0.8414, "step": 28750 }, { "epoch": 2.39, "learning_rate": 3.6824543413795967e-06, "loss": 0.8481, "step": 28760 }, { "epoch": 2.39, "learning_rate": 3.682343485852063e-06, "loss": 0.8938, "step": 28770 }, { "epoch": 2.39, "learning_rate": 3.6822326303245293e-06, "loss": 0.8998, "step": 28780 }, { "epoch": 2.39, "learning_rate": 3.6821217747969956e-06, "loss": 0.8414, "step": 28790 }, { "epoch": 2.39, "learning_rate": 3.682010919269462e-06, "loss": 0.7845, "step": 28800 }, { "epoch": 2.39, "learning_rate": 3.681900063741928e-06, "loss": 0.8135, "step": 28810 }, { "epoch": 2.4, "learning_rate": 3.681789208214394e-06, "loss": 0.801, "step": 28820 }, { "epoch": 2.4, "learning_rate": 3.681678352686861e-06, "loss": 0.8647, "step": 28830 }, { "epoch": 2.4, "learning_rate": 3.681567497159327e-06, "loss": 0.8558, "step": 28840 }, { "epoch": 2.4, "learning_rate": 3.681456641631793e-06, "loss": 0.7535, "step": 28850 }, { "epoch": 2.4, "learning_rate": 3.6813457861042597e-06, "loss": 0.7973, "step": 28860 }, { "epoch": 2.4, "learning_rate": 3.6812349305767255e-06, "loss": 0.8937, "step": 28870 }, { "epoch": 2.4, "learning_rate": 3.6811240750491923e-06, "loss": 0.8455, "step": 28880 }, { "epoch": 2.4, "learning_rate": 3.681013219521658e-06, "loss": 0.7747, "step": 28890 }, { "epoch": 2.4, "learning_rate": 3.6809023639941244e-06, "loss": 0.8323, "step": 28900 }, { "epoch": 2.4, "learning_rate": 3.6807915084665907e-06, "loss": 0.8657, "step": 28910 }, { "epoch": 2.4, "learning_rate": 3.680680652939057e-06, "loss": 0.8751, "step": 28920 }, { "epoch": 2.4, "learning_rate": 3.680569797411523e-06, "loss": 0.8211, "step": 28930 }, { "epoch": 2.41, "learning_rate": 3.680470027436743e-06, "loss": 0.8005, "step": 28940 }, { "epoch": 2.41, "learning_rate": 3.680359171909209e-06, "loss": 0.788, "step": 28950 }, { "epoch": 2.41, "learning_rate": 3.6802483163816755e-06, "loss": 0.8254, "step": 28960 }, { "epoch": 2.41, "learning_rate": 3.6801374608541417e-06, "loss": 0.8699, "step": 28970 }, { "epoch": 2.41, "learning_rate": 3.680026605326608e-06, "loss": 0.8152, "step": 28980 }, { "epoch": 2.41, "learning_rate": 3.679915749799074e-06, "loss": 0.7602, "step": 28990 }, { "epoch": 2.41, "learning_rate": 3.6798048942715406e-06, "loss": 0.8215, "step": 29000 }, { "epoch": 2.41, "learning_rate": 3.6796940387440065e-06, "loss": 0.844, "step": 29010 }, { "epoch": 2.41, "learning_rate": 3.679583183216473e-06, "loss": 0.894, "step": 29020 }, { "epoch": 2.41, "learning_rate": 3.679472327688939e-06, "loss": 0.8761, "step": 29030 }, { "epoch": 2.41, "learning_rate": 3.6793614721614054e-06, "loss": 0.8619, "step": 29040 }, { "epoch": 2.41, "learning_rate": 3.679250616633872e-06, "loss": 0.7854, "step": 29050 }, { "epoch": 2.42, "learning_rate": 3.679139761106338e-06, "loss": 0.8068, "step": 29060 }, { "epoch": 2.42, "learning_rate": 3.6790289055788043e-06, "loss": 0.8354, "step": 29070 }, { "epoch": 2.42, "learning_rate": 3.6789180500512706e-06, "loss": 0.7861, "step": 29080 }, { "epoch": 2.42, "learning_rate": 3.678807194523737e-06, "loss": 0.7562, "step": 29090 }, { "epoch": 2.42, "learning_rate": 3.6786963389962027e-06, "loss": 0.8314, "step": 29100 }, { "epoch": 2.42, "learning_rate": 3.6785854834686695e-06, "loss": 0.845, "step": 29110 }, { "epoch": 2.42, "learning_rate": 3.6784746279411353e-06, "loss": 0.8827, "step": 29120 }, { "epoch": 2.42, "learning_rate": 3.678363772413602e-06, "loss": 0.8074, "step": 29130 }, { "epoch": 2.42, "learning_rate": 3.678252916886068e-06, "loss": 0.7348, "step": 29140 }, { "epoch": 2.42, "learning_rate": 3.6781420613585342e-06, "loss": 0.8256, "step": 29150 }, { "epoch": 2.42, "learning_rate": 3.678031205831001e-06, "loss": 0.8877, "step": 29160 }, { "epoch": 2.42, "learning_rate": 3.677920350303467e-06, "loss": 0.8569, "step": 29170 }, { "epoch": 2.43, "learning_rate": 3.677809494775933e-06, "loss": 0.8272, "step": 29180 }, { "epoch": 2.43, "learning_rate": 3.6776986392483994e-06, "loss": 0.8158, "step": 29190 }, { "epoch": 2.43, "learning_rate": 3.6775877837208657e-06, "loss": 0.7725, "step": 29200 }, { "epoch": 2.43, "learning_rate": 3.6774769281933316e-06, "loss": 0.8257, "step": 29210 }, { "epoch": 2.43, "learning_rate": 3.6773660726657983e-06, "loss": 0.8954, "step": 29220 }, { "epoch": 2.43, "learning_rate": 3.677255217138264e-06, "loss": 0.8075, "step": 29230 }, { "epoch": 2.43, "learning_rate": 3.677144361610731e-06, "loss": 0.8604, "step": 29240 }, { "epoch": 2.43, "learning_rate": 3.6770335060831967e-06, "loss": 0.8015, "step": 29250 }, { "epoch": 2.43, "learning_rate": 3.676922650555663e-06, "loss": 0.845, "step": 29260 }, { "epoch": 2.43, "learning_rate": 3.6768117950281293e-06, "loss": 0.8649, "step": 29270 }, { "epoch": 2.43, "learning_rate": 3.6767009395005956e-06, "loss": 0.7963, "step": 29280 }, { "epoch": 2.43, "learning_rate": 3.6765900839730623e-06, "loss": 0.7604, "step": 29290 }, { "epoch": 2.44, "learning_rate": 3.6764792284455282e-06, "loss": 0.8698, "step": 29300 }, { "epoch": 2.44, "learning_rate": 3.6763683729179945e-06, "loss": 0.8461, "step": 29310 }, { "epoch": 2.44, "learning_rate": 3.676257517390461e-06, "loss": 0.9001, "step": 29320 }, { "epoch": 2.44, "learning_rate": 3.676146661862927e-06, "loss": 0.8813, "step": 29330 }, { "epoch": 2.44, "learning_rate": 3.676035806335393e-06, "loss": 0.8328, "step": 29340 }, { "epoch": 2.44, "learning_rate": 3.6759249508078597e-06, "loss": 0.8203, "step": 29350 }, { "epoch": 2.44, "learning_rate": 3.6758140952803256e-06, "loss": 0.7633, "step": 29360 }, { "epoch": 2.44, "learning_rate": 3.675703239752792e-06, "loss": 0.8401, "step": 29370 }, { "epoch": 2.44, "learning_rate": 3.675592384225258e-06, "loss": 0.8237, "step": 29380 }, { "epoch": 2.44, "learning_rate": 3.6754815286977245e-06, "loss": 0.8771, "step": 29390 }, { "epoch": 2.44, "learning_rate": 3.6753706731701908e-06, "loss": 0.8723, "step": 29400 }, { "epoch": 2.44, "learning_rate": 3.675259817642657e-06, "loss": 0.8909, "step": 29410 }, { "epoch": 2.45, "learning_rate": 3.6751489621151233e-06, "loss": 0.9325, "step": 29420 }, { "epoch": 2.45, "learning_rate": 3.6750381065875896e-06, "loss": 0.8683, "step": 29430 }, { "epoch": 2.45, "learning_rate": 3.674927251060056e-06, "loss": 0.8427, "step": 29440 }, { "epoch": 2.45, "learning_rate": 3.674816395532522e-06, "loss": 0.7912, "step": 29450 }, { "epoch": 2.45, "learning_rate": 3.6747055400049885e-06, "loss": 0.8519, "step": 29460 }, { "epoch": 2.45, "learning_rate": 3.6745946844774544e-06, "loss": 0.8535, "step": 29470 }, { "epoch": 2.45, "learning_rate": 3.674483828949921e-06, "loss": 0.8489, "step": 29480 }, { "epoch": 2.45, "learning_rate": 3.674372973422387e-06, "loss": 0.8789, "step": 29490 }, { "epoch": 2.45, "learning_rate": 3.6742621178948533e-06, "loss": 0.8411, "step": 29500 }, { "epoch": 2.45, "learning_rate": 3.6741512623673196e-06, "loss": 0.784, "step": 29510 }, { "epoch": 2.45, "learning_rate": 3.674040406839786e-06, "loss": 0.8513, "step": 29520 }, { "epoch": 2.45, "learning_rate": 3.673929551312252e-06, "loss": 0.7901, "step": 29530 }, { "epoch": 2.46, "learning_rate": 3.6738186957847185e-06, "loss": 0.795, "step": 29540 }, { "epoch": 2.46, "learning_rate": 3.6737078402571848e-06, "loss": 0.8321, "step": 29550 }, { "epoch": 2.46, "learning_rate": 3.673596984729651e-06, "loss": 0.7929, "step": 29560 }, { "epoch": 2.46, "learning_rate": 3.6734861292021173e-06, "loss": 0.8926, "step": 29570 }, { "epoch": 2.46, "learning_rate": 3.6733752736745832e-06, "loss": 0.7719, "step": 29580 }, { "epoch": 2.46, "learning_rate": 3.67326441814705e-06, "loss": 0.8575, "step": 29590 }, { "epoch": 2.46, "learning_rate": 3.673153562619516e-06, "loss": 0.8172, "step": 29600 }, { "epoch": 2.46, "learning_rate": 3.673042707091982e-06, "loss": 0.8429, "step": 29610 }, { "epoch": 2.46, "learning_rate": 3.6729318515644484e-06, "loss": 0.886, "step": 29620 }, { "epoch": 2.46, "learning_rate": 3.6728209960369147e-06, "loss": 0.7768, "step": 29630 }, { "epoch": 2.46, "learning_rate": 3.6727101405093806e-06, "loss": 0.79, "step": 29640 }, { "epoch": 2.46, "learning_rate": 3.6725992849818473e-06, "loss": 0.8947, "step": 29650 }, { "epoch": 2.47, "learning_rate": 3.6724884294543136e-06, "loss": 0.8568, "step": 29660 }, { "epoch": 2.47, "learning_rate": 3.67237757392678e-06, "loss": 0.9037, "step": 29670 }, { "epoch": 2.47, "learning_rate": 3.672266718399246e-06, "loss": 0.7913, "step": 29680 }, { "epoch": 2.47, "learning_rate": 3.672155862871712e-06, "loss": 0.85, "step": 29690 }, { "epoch": 2.47, "learning_rate": 3.6720450073441788e-06, "loss": 0.7667, "step": 29700 }, { "epoch": 2.47, "learning_rate": 3.6719341518166446e-06, "loss": 0.8596, "step": 29710 }, { "epoch": 2.47, "learning_rate": 3.671823296289111e-06, "loss": 0.8966, "step": 29720 }, { "epoch": 2.47, "learning_rate": 3.6717124407615772e-06, "loss": 0.8483, "step": 29730 }, { "epoch": 2.47, "learning_rate": 3.6716015852340435e-06, "loss": 0.8589, "step": 29740 }, { "epoch": 2.47, "learning_rate": 3.67149072970651e-06, "loss": 0.8802, "step": 29750 }, { "epoch": 2.47, "learning_rate": 3.671379874178976e-06, "loss": 0.7834, "step": 29760 }, { "epoch": 2.47, "learning_rate": 3.6712690186514424e-06, "loss": 0.8948, "step": 29770 }, { "epoch": 2.48, "learning_rate": 3.6711581631239087e-06, "loss": 0.7945, "step": 29780 }, { "epoch": 2.48, "learning_rate": 3.671047307596375e-06, "loss": 0.7775, "step": 29790 }, { "epoch": 2.48, "learning_rate": 3.670936452068841e-06, "loss": 0.7998, "step": 29800 }, { "epoch": 2.48, "learning_rate": 3.6708255965413076e-06, "loss": 0.8749, "step": 29810 }, { "epoch": 2.48, "learning_rate": 3.6707147410137735e-06, "loss": 0.8771, "step": 29820 }, { "epoch": 2.48, "learning_rate": 3.67060388548624e-06, "loss": 0.8147, "step": 29830 }, { "epoch": 2.48, "learning_rate": 3.670493029958706e-06, "loss": 0.8816, "step": 29840 }, { "epoch": 2.48, "learning_rate": 3.6703821744311723e-06, "loss": 0.7744, "step": 29850 }, { "epoch": 2.48, "learning_rate": 3.6702713189036386e-06, "loss": 0.826, "step": 29860 }, { "epoch": 2.48, "learning_rate": 3.670160463376105e-06, "loss": 0.8576, "step": 29870 }, { "epoch": 2.48, "learning_rate": 3.670049607848571e-06, "loss": 0.8982, "step": 29880 }, { "epoch": 2.48, "learning_rate": 3.6699387523210375e-06, "loss": 0.7963, "step": 29890 }, { "epoch": 2.49, "learning_rate": 3.669827896793504e-06, "loss": 0.8612, "step": 29900 }, { "epoch": 2.49, "learning_rate": 3.66971704126597e-06, "loss": 0.8072, "step": 29910 }, { "epoch": 2.49, "learning_rate": 3.6696061857384364e-06, "loss": 0.8607, "step": 29920 }, { "epoch": 2.49, "learning_rate": 3.6694953302109023e-06, "loss": 0.8124, "step": 29930 }, { "epoch": 2.49, "learning_rate": 3.669384474683369e-06, "loss": 0.8426, "step": 29940 }, { "epoch": 2.49, "learning_rate": 3.669273619155835e-06, "loss": 0.8145, "step": 29950 }, { "epoch": 2.49, "learning_rate": 3.669162763628301e-06, "loss": 0.9166, "step": 29960 }, { "epoch": 2.49, "learning_rate": 3.6690519081007675e-06, "loss": 0.9486, "step": 29970 }, { "epoch": 2.49, "learning_rate": 3.6689410525732338e-06, "loss": 0.8036, "step": 29980 }, { "epoch": 2.49, "learning_rate": 3.6688301970457e-06, "loss": 0.8005, "step": 29990 }, { "epoch": 2.49, "learning_rate": 3.6687193415181664e-06, "loss": 0.7503, "step": 30000 }, { "epoch": 2.49, "learning_rate": 3.6686084859906322e-06, "loss": 0.8231, "step": 30010 }, { "epoch": 2.5, "learning_rate": 3.668497630463099e-06, "loss": 0.8511, "step": 30020 }, { "epoch": 2.5, "learning_rate": 3.6683867749355652e-06, "loss": 0.7959, "step": 30030 }, { "epoch": 2.5, "learning_rate": 3.668275919408031e-06, "loss": 0.9186, "step": 30040 }, { "epoch": 2.5, "learning_rate": 3.668165063880498e-06, "loss": 0.8398, "step": 30050 }, { "epoch": 2.5, "learning_rate": 3.6680542083529637e-06, "loss": 0.8612, "step": 30060 }, { "epoch": 2.5, "learning_rate": 3.6679433528254304e-06, "loss": 0.8004, "step": 30070 }, { "epoch": 2.5, "learning_rate": 3.6678324972978963e-06, "loss": 0.8049, "step": 30080 }, { "epoch": 2.5, "learning_rate": 3.6677216417703626e-06, "loss": 0.812, "step": 30090 }, { "epoch": 2.5, "learning_rate": 3.667610786242829e-06, "loss": 0.8807, "step": 30100 }, { "epoch": 2.5, "learning_rate": 3.667499930715295e-06, "loss": 0.8268, "step": 30110 }, { "epoch": 2.5, "learning_rate": 3.667389075187761e-06, "loss": 0.9064, "step": 30120 }, { "epoch": 2.5, "learning_rate": 3.6672782196602278e-06, "loss": 0.8111, "step": 30130 }, { "epoch": 2.51, "learning_rate": 3.667167364132694e-06, "loss": 0.8079, "step": 30140 }, { "epoch": 2.51, "learning_rate": 3.66705650860516e-06, "loss": 0.8917, "step": 30150 }, { "epoch": 2.51, "learning_rate": 3.6669456530776267e-06, "loss": 0.7586, "step": 30160 }, { "epoch": 2.51, "learning_rate": 3.6668347975500925e-06, "loss": 0.9128, "step": 30170 }, { "epoch": 2.51, "learning_rate": 3.6667239420225592e-06, "loss": 0.8624, "step": 30180 }, { "epoch": 2.51, "learning_rate": 3.666613086495025e-06, "loss": 0.8202, "step": 30190 }, { "epoch": 2.51, "learning_rate": 3.6665022309674914e-06, "loss": 0.8779, "step": 30200 }, { "epoch": 2.51, "learning_rate": 3.6663913754399577e-06, "loss": 0.8427, "step": 30210 }, { "epoch": 2.51, "learning_rate": 3.666280519912424e-06, "loss": 0.8545, "step": 30220 }, { "epoch": 2.51, "learning_rate": 3.66616966438489e-06, "loss": 0.8383, "step": 30230 }, { "epoch": 2.51, "learning_rate": 3.6660588088573566e-06, "loss": 0.8759, "step": 30240 }, { "epoch": 2.51, "learning_rate": 3.6659479533298225e-06, "loss": 0.7797, "step": 30250 }, { "epoch": 2.52, "learning_rate": 3.665837097802289e-06, "loss": 0.7894, "step": 30260 }, { "epoch": 2.52, "learning_rate": 3.6657262422747555e-06, "loss": 0.8171, "step": 30270 }, { "epoch": 2.52, "learning_rate": 3.6656153867472214e-06, "loss": 0.8613, "step": 30280 }, { "epoch": 2.52, "learning_rate": 3.665504531219688e-06, "loss": 0.8247, "step": 30290 }, { "epoch": 2.52, "learning_rate": 3.665393675692154e-06, "loss": 0.8201, "step": 30300 }, { "epoch": 2.52, "learning_rate": 3.6652828201646202e-06, "loss": 0.8366, "step": 30310 }, { "epoch": 2.52, "learning_rate": 3.6651719646370865e-06, "loss": 0.8499, "step": 30320 }, { "epoch": 2.52, "learning_rate": 3.665061109109553e-06, "loss": 0.887, "step": 30330 }, { "epoch": 2.52, "learning_rate": 3.664950253582019e-06, "loss": 0.8307, "step": 30340 }, { "epoch": 2.52, "learning_rate": 3.6648393980544854e-06, "loss": 0.814, "step": 30350 }, { "epoch": 2.52, "learning_rate": 3.6647285425269513e-06, "loss": 0.8222, "step": 30360 }, { "epoch": 2.52, "learning_rate": 3.664617686999418e-06, "loss": 0.8842, "step": 30370 }, { "epoch": 2.53, "learning_rate": 3.6645179170246375e-06, "loss": 0.8395, "step": 30380 }, { "epoch": 2.53, "learning_rate": 3.664407061497104e-06, "loss": 0.8668, "step": 30390 }, { "epoch": 2.53, "learning_rate": 3.6642962059695697e-06, "loss": 0.815, "step": 30400 }, { "epoch": 2.53, "learning_rate": 3.6641853504420364e-06, "loss": 0.8342, "step": 30410 }, { "epoch": 2.53, "learning_rate": 3.6640744949145023e-06, "loss": 0.9548, "step": 30420 }, { "epoch": 2.53, "learning_rate": 3.663963639386969e-06, "loss": 0.9215, "step": 30430 }, { "epoch": 2.53, "learning_rate": 3.663852783859435e-06, "loss": 0.8484, "step": 30440 }, { "epoch": 2.53, "learning_rate": 3.663741928331901e-06, "loss": 0.7907, "step": 30450 }, { "epoch": 2.53, "learning_rate": 3.6636310728043675e-06, "loss": 0.7786, "step": 30460 }, { "epoch": 2.53, "learning_rate": 3.6635202172768338e-06, "loss": 0.8681, "step": 30470 }, { "epoch": 2.53, "learning_rate": 3.6634093617493e-06, "loss": 0.8458, "step": 30480 }, { "epoch": 2.53, "learning_rate": 3.6632985062217664e-06, "loss": 0.8289, "step": 30490 }, { "epoch": 2.54, "learning_rate": 3.6631876506942327e-06, "loss": 0.7868, "step": 30500 }, { "epoch": 2.54, "learning_rate": 3.663076795166699e-06, "loss": 0.7846, "step": 30510 }, { "epoch": 2.54, "learning_rate": 3.6629659396391653e-06, "loss": 0.8781, "step": 30520 }, { "epoch": 2.54, "learning_rate": 3.662855084111631e-06, "loss": 0.8183, "step": 30530 }, { "epoch": 2.54, "learning_rate": 3.662744228584098e-06, "loss": 0.81, "step": 30540 }, { "epoch": 2.54, "learning_rate": 3.6626333730565637e-06, "loss": 0.7729, "step": 30550 }, { "epoch": 2.54, "learning_rate": 3.66252251752903e-06, "loss": 0.847, "step": 30560 }, { "epoch": 2.54, "learning_rate": 3.6624116620014963e-06, "loss": 0.8648, "step": 30570 }, { "epoch": 2.54, "learning_rate": 3.6623008064739626e-06, "loss": 0.7599, "step": 30580 }, { "epoch": 2.54, "learning_rate": 3.6621899509464285e-06, "loss": 0.8362, "step": 30590 }, { "epoch": 2.54, "learning_rate": 3.662079095418895e-06, "loss": 0.7942, "step": 30600 }, { "epoch": 2.54, "learning_rate": 3.6619682398913615e-06, "loss": 0.8662, "step": 30610 }, { "epoch": 2.55, "learning_rate": 3.661857384363828e-06, "loss": 0.8512, "step": 30620 }, { "epoch": 2.55, "learning_rate": 3.661746528836294e-06, "loss": 0.7851, "step": 30630 }, { "epoch": 2.55, "learning_rate": 3.66163567330876e-06, "loss": 0.8705, "step": 30640 }, { "epoch": 2.55, "learning_rate": 3.6615248177812267e-06, "loss": 0.7967, "step": 30650 }, { "epoch": 2.55, "learning_rate": 3.6614139622536925e-06, "loss": 0.8897, "step": 30660 }, { "epoch": 2.55, "learning_rate": 3.661303106726159e-06, "loss": 0.9469, "step": 30670 }, { "epoch": 2.55, "learning_rate": 3.661192251198625e-06, "loss": 0.8437, "step": 30680 }, { "epoch": 2.55, "learning_rate": 3.6610813956710914e-06, "loss": 0.8278, "step": 30690 }, { "epoch": 2.55, "learning_rate": 3.6609705401435577e-06, "loss": 0.8358, "step": 30700 }, { "epoch": 2.55, "learning_rate": 3.660859684616024e-06, "loss": 0.7613, "step": 30710 }, { "epoch": 2.55, "learning_rate": 3.6607488290884903e-06, "loss": 0.8879, "step": 30720 }, { "epoch": 2.55, "learning_rate": 3.6606379735609566e-06, "loss": 0.8678, "step": 30730 }, { "epoch": 2.56, "learning_rate": 3.660527118033423e-06, "loss": 0.8233, "step": 30740 }, { "epoch": 2.56, "learning_rate": 3.6604162625058888e-06, "loss": 0.7937, "step": 30750 }, { "epoch": 2.56, "learning_rate": 3.6603054069783555e-06, "loss": 0.809, "step": 30760 }, { "epoch": 2.56, "learning_rate": 3.6601945514508214e-06, "loss": 0.9007, "step": 30770 }, { "epoch": 2.56, "learning_rate": 3.660083695923288e-06, "loss": 0.8313, "step": 30780 }, { "epoch": 2.56, "learning_rate": 3.659972840395754e-06, "loss": 0.7915, "step": 30790 }, { "epoch": 2.56, "learning_rate": 3.6598619848682203e-06, "loss": 0.8428, "step": 30800 }, { "epoch": 2.56, "learning_rate": 3.6597511293406866e-06, "loss": 0.7805, "step": 30810 }, { "epoch": 2.56, "learning_rate": 3.659640273813153e-06, "loss": 0.8455, "step": 30820 }, { "epoch": 2.56, "learning_rate": 3.6595294182856187e-06, "loss": 0.8993, "step": 30830 }, { "epoch": 2.56, "learning_rate": 3.6594185627580854e-06, "loss": 0.7771, "step": 30840 }, { "epoch": 2.56, "learning_rate": 3.6593077072305517e-06, "loss": 0.8222, "step": 30850 }, { "epoch": 2.57, "learning_rate": 3.659196851703018e-06, "loss": 0.8245, "step": 30860 }, { "epoch": 2.57, "learning_rate": 3.6590859961754843e-06, "loss": 0.9161, "step": 30870 }, { "epoch": 2.57, "learning_rate": 3.65897514064795e-06, "loss": 0.8532, "step": 30880 }, { "epoch": 2.57, "learning_rate": 3.658864285120417e-06, "loss": 0.7763, "step": 30890 }, { "epoch": 2.57, "learning_rate": 3.658753429592883e-06, "loss": 0.8043, "step": 30900 }, { "epoch": 2.57, "learning_rate": 3.658642574065349e-06, "loss": 0.8448, "step": 30910 }, { "epoch": 2.57, "learning_rate": 3.6585317185378154e-06, "loss": 0.883, "step": 30920 }, { "epoch": 2.57, "learning_rate": 3.6584208630102817e-06, "loss": 0.8408, "step": 30930 }, { "epoch": 2.57, "learning_rate": 3.658310007482748e-06, "loss": 0.8166, "step": 30940 }, { "epoch": 2.57, "learning_rate": 3.6581991519552143e-06, "loss": 0.7789, "step": 30950 }, { "epoch": 2.57, "learning_rate": 3.65808829642768e-06, "loss": 0.8052, "step": 30960 }, { "epoch": 2.57, "learning_rate": 3.657977440900147e-06, "loss": 0.9045, "step": 30970 }, { "epoch": 2.58, "learning_rate": 3.657866585372613e-06, "loss": 0.8581, "step": 30980 }, { "epoch": 2.58, "learning_rate": 3.657755729845079e-06, "loss": 0.8206, "step": 30990 }, { "epoch": 2.58, "learning_rate": 3.6576448743175457e-06, "loss": 0.7801, "step": 31000 }, { "epoch": 2.58, "learning_rate": 3.6575340187900116e-06, "loss": 0.8137, "step": 31010 }, { "epoch": 2.58, "learning_rate": 3.6574231632624783e-06, "loss": 0.9285, "step": 31020 }, { "epoch": 2.58, "learning_rate": 3.657312307734944e-06, "loss": 0.8143, "step": 31030 }, { "epoch": 2.58, "learning_rate": 3.6572014522074105e-06, "loss": 0.8385, "step": 31040 }, { "epoch": 2.58, "learning_rate": 3.657090596679877e-06, "loss": 0.81, "step": 31050 }, { "epoch": 2.58, "learning_rate": 3.656979741152343e-06, "loss": 0.8182, "step": 31060 }, { "epoch": 2.58, "learning_rate": 3.656868885624809e-06, "loss": 0.8792, "step": 31070 }, { "epoch": 2.58, "learning_rate": 3.6567580300972757e-06, "loss": 0.7697, "step": 31080 }, { "epoch": 2.58, "learning_rate": 3.656647174569742e-06, "loss": 0.8314, "step": 31090 }, { "epoch": 2.58, "learning_rate": 3.656536319042208e-06, "loss": 0.8154, "step": 31100 }, { "epoch": 2.59, "learning_rate": 3.6564254635146746e-06, "loss": 0.7633, "step": 31110 }, { "epoch": 2.59, "learning_rate": 3.6563146079871404e-06, "loss": 0.8681, "step": 31120 }, { "epoch": 2.59, "learning_rate": 3.656203752459607e-06, "loss": 0.8097, "step": 31130 }, { "epoch": 2.59, "learning_rate": 3.656092896932073e-06, "loss": 0.8073, "step": 31140 }, { "epoch": 2.59, "learning_rate": 3.6559820414045393e-06, "loss": 0.8436, "step": 31150 }, { "epoch": 2.59, "learning_rate": 3.6558711858770056e-06, "loss": 0.8003, "step": 31160 }, { "epoch": 2.59, "learning_rate": 3.655760330349472e-06, "loss": 0.7834, "step": 31170 }, { "epoch": 2.59, "learning_rate": 3.655649474821938e-06, "loss": 0.8482, "step": 31180 }, { "epoch": 2.59, "learning_rate": 3.6555386192944045e-06, "loss": 0.8624, "step": 31190 }, { "epoch": 2.59, "learning_rate": 3.6554277637668704e-06, "loss": 0.8114, "step": 31200 }, { "epoch": 2.59, "learning_rate": 3.655316908239337e-06, "loss": 0.8604, "step": 31210 }, { "epoch": 2.59, "learning_rate": 3.6552060527118034e-06, "loss": 0.8541, "step": 31220 }, { "epoch": 2.6, "learning_rate": 3.6550951971842693e-06, "loss": 0.7938, "step": 31230 }, { "epoch": 2.6, "learning_rate": 3.654984341656736e-06, "loss": 0.7472, "step": 31240 }, { "epoch": 2.6, "learning_rate": 3.654873486129202e-06, "loss": 0.8455, "step": 31250 }, { "epoch": 2.6, "learning_rate": 3.654762630601668e-06, "loss": 0.8325, "step": 31260 }, { "epoch": 2.6, "learning_rate": 3.6546517750741344e-06, "loss": 0.9177, "step": 31270 }, { "epoch": 2.6, "learning_rate": 3.6545409195466007e-06, "loss": 0.8229, "step": 31280 }, { "epoch": 2.6, "learning_rate": 3.654430064019067e-06, "loss": 0.8452, "step": 31290 }, { "epoch": 2.6, "learning_rate": 3.6543192084915333e-06, "loss": 0.8214, "step": 31300 }, { "epoch": 2.6, "learning_rate": 3.654208352963999e-06, "loss": 0.8264, "step": 31310 }, { "epoch": 2.6, "learning_rate": 3.654097497436466e-06, "loss": 0.8328, "step": 31320 }, { "epoch": 2.6, "learning_rate": 3.653986641908932e-06, "loss": 0.8193, "step": 31330 }, { "epoch": 2.6, "learning_rate": 3.653875786381398e-06, "loss": 0.8637, "step": 31340 }, { "epoch": 2.61, "learning_rate": 3.653764930853865e-06, "loss": 0.8196, "step": 31350 }, { "epoch": 2.61, "learning_rate": 3.6536540753263307e-06, "loss": 0.8216, "step": 31360 }, { "epoch": 2.61, "learning_rate": 3.6535432197987974e-06, "loss": 0.8911, "step": 31370 }, { "epoch": 2.61, "learning_rate": 3.6534323642712633e-06, "loss": 0.7949, "step": 31380 }, { "epoch": 2.61, "learning_rate": 3.6533215087437296e-06, "loss": 0.7441, "step": 31390 }, { "epoch": 2.61, "learning_rate": 3.653210653216196e-06, "loss": 0.7997, "step": 31400 }, { "epoch": 2.61, "learning_rate": 3.653099797688662e-06, "loss": 0.8422, "step": 31410 }, { "epoch": 2.61, "learning_rate": 3.652988942161128e-06, "loss": 0.855, "step": 31420 }, { "epoch": 2.61, "learning_rate": 3.6528780866335947e-06, "loss": 0.816, "step": 31430 }, { "epoch": 2.61, "learning_rate": 3.6527672311060606e-06, "loss": 0.766, "step": 31440 }, { "epoch": 2.61, "learning_rate": 3.652656375578527e-06, "loss": 0.8905, "step": 31450 }, { "epoch": 2.61, "learning_rate": 3.6525455200509936e-06, "loss": 0.7942, "step": 31460 }, { "epoch": 2.62, "learning_rate": 3.6524346645234595e-06, "loss": 0.9059, "step": 31470 }, { "epoch": 2.62, "learning_rate": 3.6523238089959262e-06, "loss": 0.8384, "step": 31480 }, { "epoch": 2.62, "learning_rate": 3.652212953468392e-06, "loss": 0.8637, "step": 31490 }, { "epoch": 2.62, "learning_rate": 3.6521020979408584e-06, "loss": 0.8119, "step": 31500 }, { "epoch": 2.62, "learning_rate": 3.6519912424133247e-06, "loss": 0.7906, "step": 31510 }, { "epoch": 2.62, "learning_rate": 3.651880386885791e-06, "loss": 0.9157, "step": 31520 }, { "epoch": 2.62, "learning_rate": 3.651769531358257e-06, "loss": 0.8422, "step": 31530 }, { "epoch": 2.62, "learning_rate": 3.6516586758307236e-06, "loss": 0.9256, "step": 31540 }, { "epoch": 2.62, "learning_rate": 3.6515478203031894e-06, "loss": 0.8271, "step": 31550 }, { "epoch": 2.62, "learning_rate": 3.651436964775656e-06, "loss": 0.8437, "step": 31560 }, { "epoch": 2.62, "learning_rate": 3.651326109248122e-06, "loss": 0.8694, "step": 31570 }, { "epoch": 2.62, "learning_rate": 3.6512152537205883e-06, "loss": 0.8499, "step": 31580 }, { "epoch": 2.63, "learning_rate": 3.651104398193055e-06, "loss": 0.8779, "step": 31590 }, { "epoch": 2.63, "learning_rate": 3.650993542665521e-06, "loss": 0.9016, "step": 31600 }, { "epoch": 2.63, "learning_rate": 3.6508826871379872e-06, "loss": 0.7901, "step": 31610 }, { "epoch": 2.63, "learning_rate": 3.6507718316104535e-06, "loss": 0.8945, "step": 31620 }, { "epoch": 2.63, "learning_rate": 3.65066097608292e-06, "loss": 0.7515, "step": 31630 }, { "epoch": 2.63, "learning_rate": 3.650550120555386e-06, "loss": 0.8892, "step": 31640 }, { "epoch": 2.63, "learning_rate": 3.6504392650278524e-06, "loss": 0.7848, "step": 31650 }, { "epoch": 2.63, "learning_rate": 3.6503284095003183e-06, "loss": 0.9081, "step": 31660 }, { "epoch": 2.63, "learning_rate": 3.650217553972785e-06, "loss": 0.8348, "step": 31670 }, { "epoch": 2.63, "learning_rate": 3.650106698445251e-06, "loss": 0.8355, "step": 31680 }, { "epoch": 2.63, "learning_rate": 3.649995842917717e-06, "loss": 0.8575, "step": 31690 }, { "epoch": 2.63, "learning_rate": 3.6498849873901835e-06, "loss": 0.8234, "step": 31700 }, { "epoch": 2.64, "learning_rate": 3.6497741318626497e-06, "loss": 0.774, "step": 31710 }, { "epoch": 2.64, "learning_rate": 3.6496632763351165e-06, "loss": 0.8874, "step": 31720 }, { "epoch": 2.64, "learning_rate": 3.6495524208075823e-06, "loss": 0.8812, "step": 31730 }, { "epoch": 2.64, "learning_rate": 3.6494415652800486e-06, "loss": 0.789, "step": 31740 }, { "epoch": 2.64, "learning_rate": 3.649330709752515e-06, "loss": 0.8806, "step": 31750 }, { "epoch": 2.64, "learning_rate": 3.6492198542249812e-06, "loss": 0.8462, "step": 31760 }, { "epoch": 2.64, "learning_rate": 3.649108998697447e-06, "loss": 0.7933, "step": 31770 }, { "epoch": 2.64, "learning_rate": 3.648998143169914e-06, "loss": 0.8792, "step": 31780 }, { "epoch": 2.64, "learning_rate": 3.6488872876423797e-06, "loss": 0.8111, "step": 31790 }, { "epoch": 2.64, "learning_rate": 3.6487764321148464e-06, "loss": 0.7795, "step": 31800 }, { "epoch": 2.64, "learning_rate": 3.6486655765873123e-06, "loss": 0.8021, "step": 31810 }, { "epoch": 2.64, "learning_rate": 3.6485547210597786e-06, "loss": 0.8501, "step": 31820 }, { "epoch": 2.65, "learning_rate": 3.6484438655322453e-06, "loss": 0.7962, "step": 31830 }, { "epoch": 2.65, "learning_rate": 3.648333010004711e-06, "loss": 0.8389, "step": 31840 }, { "epoch": 2.65, "learning_rate": 3.6482221544771775e-06, "loss": 0.7907, "step": 31850 }, { "epoch": 2.65, "learning_rate": 3.6481112989496438e-06, "loss": 0.8077, "step": 31860 }, { "epoch": 2.65, "learning_rate": 3.64800044342211e-06, "loss": 0.8518, "step": 31870 }, { "epoch": 2.65, "learning_rate": 3.647889587894576e-06, "loss": 0.8483, "step": 31880 }, { "epoch": 2.65, "learning_rate": 3.6477787323670426e-06, "loss": 0.8039, "step": 31890 }, { "epoch": 2.65, "learning_rate": 3.6476678768395085e-06, "loss": 0.813, "step": 31900 }, { "epoch": 2.65, "learning_rate": 3.6475570213119752e-06, "loss": 0.8684, "step": 31910 }, { "epoch": 2.65, "learning_rate": 3.647446165784441e-06, "loss": 0.8409, "step": 31920 }, { "epoch": 2.65, "learning_rate": 3.6473353102569074e-06, "loss": 0.8697, "step": 31930 }, { "epoch": 2.65, "learning_rate": 3.6472244547293737e-06, "loss": 0.8422, "step": 31940 }, { "epoch": 2.66, "learning_rate": 3.64711359920184e-06, "loss": 0.8231, "step": 31950 }, { "epoch": 2.66, "learning_rate": 3.6470027436743063e-06, "loss": 0.8525, "step": 31960 }, { "epoch": 2.66, "learning_rate": 3.6468918881467726e-06, "loss": 0.892, "step": 31970 }, { "epoch": 2.66, "learning_rate": 3.646781032619239e-06, "loss": 0.7874, "step": 31980 }, { "epoch": 2.66, "learning_rate": 3.646670177091705e-06, "loss": 0.7846, "step": 31990 }, { "epoch": 2.66, "learning_rate": 3.6465593215641715e-06, "loss": 0.8488, "step": 32000 }, { "epoch": 2.66, "learning_rate": 3.6464484660366373e-06, "loss": 0.8471, "step": 32010 }, { "epoch": 2.66, "learning_rate": 3.646337610509104e-06, "loss": 0.9221, "step": 32020 }, { "epoch": 2.66, "learning_rate": 3.64622675498157e-06, "loss": 0.7967, "step": 32030 }, { "epoch": 2.66, "learning_rate": 3.6461158994540362e-06, "loss": 0.8371, "step": 32040 }, { "epoch": 2.66, "learning_rate": 3.6460050439265025e-06, "loss": 0.8353, "step": 32050 }, { "epoch": 2.66, "learning_rate": 3.645894188398969e-06, "loss": 0.8378, "step": 32060 }, { "epoch": 2.67, "learning_rate": 3.6457833328714355e-06, "loss": 0.8381, "step": 32070 }, { "epoch": 2.67, "learning_rate": 3.6456724773439014e-06, "loss": 0.923, "step": 32080 }, { "epoch": 2.67, "learning_rate": 3.6455616218163677e-06, "loss": 0.8471, "step": 32090 }, { "epoch": 2.67, "learning_rate": 3.645450766288834e-06, "loss": 0.7901, "step": 32100 }, { "epoch": 2.67, "learning_rate": 3.6453399107613003e-06, "loss": 0.8145, "step": 32110 }, { "epoch": 2.67, "learning_rate": 3.645229055233766e-06, "loss": 0.8385, "step": 32120 }, { "epoch": 2.67, "learning_rate": 3.645118199706233e-06, "loss": 0.8331, "step": 32130 }, { "epoch": 2.67, "learning_rate": 3.6450073441786988e-06, "loss": 0.8884, "step": 32140 }, { "epoch": 2.67, "learning_rate": 3.6448964886511655e-06, "loss": 0.815, "step": 32150 }, { "epoch": 2.67, "learning_rate": 3.6447856331236313e-06, "loss": 0.8568, "step": 32160 }, { "epoch": 2.67, "learning_rate": 3.6446747775960976e-06, "loss": 0.8815, "step": 32170 }, { "epoch": 2.67, "learning_rate": 3.644563922068564e-06, "loss": 0.8799, "step": 32180 }, { "epoch": 2.68, "learning_rate": 3.6444530665410302e-06, "loss": 0.8283, "step": 32190 }, { "epoch": 2.68, "learning_rate": 3.6443422110134965e-06, "loss": 0.8505, "step": 32200 }, { "epoch": 2.68, "learning_rate": 3.644231355485963e-06, "loss": 0.7911, "step": 32210 }, { "epoch": 2.68, "learning_rate": 3.644120499958429e-06, "loss": 0.8387, "step": 32220 }, { "epoch": 2.68, "learning_rate": 3.6440096444308954e-06, "loss": 0.8325, "step": 32230 }, { "epoch": 2.68, "learning_rate": 3.6438987889033617e-06, "loss": 0.8417, "step": 32240 }, { "epoch": 2.68, "learning_rate": 3.6437879333758276e-06, "loss": 0.8525, "step": 32250 }, { "epoch": 2.68, "learning_rate": 3.6436770778482943e-06, "loss": 0.8372, "step": 32260 }, { "epoch": 2.68, "learning_rate": 3.64356622232076e-06, "loss": 0.9382, "step": 32270 }, { "epoch": 2.68, "learning_rate": 3.6434553667932265e-06, "loss": 0.8468, "step": 32280 }, { "epoch": 2.68, "learning_rate": 3.6433445112656928e-06, "loss": 0.8402, "step": 32290 }, { "epoch": 2.68, "learning_rate": 3.643233655738159e-06, "loss": 0.8261, "step": 32300 }, { "epoch": 2.69, "learning_rate": 3.643122800210625e-06, "loss": 0.8787, "step": 32310 }, { "epoch": 2.69, "learning_rate": 3.6430119446830916e-06, "loss": 0.9178, "step": 32320 }, { "epoch": 2.69, "learning_rate": 3.642901089155558e-06, "loss": 0.878, "step": 32330 }, { "epoch": 2.69, "learning_rate": 3.6427902336280242e-06, "loss": 0.9079, "step": 32340 }, { "epoch": 2.69, "learning_rate": 3.6426793781004905e-06, "loss": 0.8027, "step": 32350 }, { "epoch": 2.69, "learning_rate": 3.6425685225729564e-06, "loss": 0.8561, "step": 32360 }, { "epoch": 2.69, "learning_rate": 3.642457667045423e-06, "loss": 0.8736, "step": 32370 }, { "epoch": 2.69, "learning_rate": 3.642346811517889e-06, "loss": 0.7717, "step": 32380 }, { "epoch": 2.69, "learning_rate": 3.6422359559903553e-06, "loss": 0.7595, "step": 32390 }, { "epoch": 2.69, "learning_rate": 3.6421251004628216e-06, "loss": 0.7963, "step": 32400 }, { "epoch": 2.69, "learning_rate": 3.642014244935288e-06, "loss": 0.8127, "step": 32410 }, { "epoch": 2.69, "learning_rate": 3.641903389407754e-06, "loss": 0.85, "step": 32420 }, { "epoch": 2.7, "learning_rate": 3.6417925338802205e-06, "loss": 0.8673, "step": 32430 }, { "epoch": 2.7, "learning_rate": 3.6416816783526868e-06, "loss": 0.808, "step": 32440 }, { "epoch": 2.7, "learning_rate": 3.641570822825153e-06, "loss": 0.8457, "step": 32450 }, { "epoch": 2.7, "learning_rate": 3.6414599672976194e-06, "loss": 0.8464, "step": 32460 }, { "epoch": 2.7, "learning_rate": 3.6413491117700852e-06, "loss": 0.8565, "step": 32470 }, { "epoch": 2.7, "learning_rate": 3.641238256242552e-06, "loss": 0.837, "step": 32480 }, { "epoch": 2.7, "learning_rate": 3.641127400715018e-06, "loss": 0.795, "step": 32490 }, { "epoch": 2.7, "learning_rate": 3.6410165451874845e-06, "loss": 0.7947, "step": 32500 }, { "epoch": 2.7, "learning_rate": 3.6409056896599504e-06, "loss": 0.8565, "step": 32510 }, { "epoch": 2.7, "learning_rate": 3.6407948341324167e-06, "loss": 0.8723, "step": 32520 }, { "epoch": 2.7, "learning_rate": 3.640683978604883e-06, "loss": 0.7799, "step": 32530 }, { "epoch": 2.7, "learning_rate": 3.6405731230773493e-06, "loss": 0.8662, "step": 32540 }, { "epoch": 2.71, "learning_rate": 3.640462267549815e-06, "loss": 0.7931, "step": 32550 }, { "epoch": 2.71, "learning_rate": 3.640351412022282e-06, "loss": 0.9163, "step": 32560 }, { "epoch": 2.71, "learning_rate": 3.640240556494748e-06, "loss": 0.9412, "step": 32570 }, { "epoch": 2.71, "learning_rate": 3.6401297009672145e-06, "loss": 0.8397, "step": 32580 }, { "epoch": 2.71, "learning_rate": 3.6400188454396808e-06, "loss": 0.8148, "step": 32590 }, { "epoch": 2.71, "learning_rate": 3.6399079899121466e-06, "loss": 0.8689, "step": 32600 }, { "epoch": 2.71, "learning_rate": 3.6397971343846134e-06, "loss": 0.8818, "step": 32610 }, { "epoch": 2.71, "learning_rate": 3.6396862788570792e-06, "loss": 0.8995, "step": 32620 }, { "epoch": 2.71, "learning_rate": 3.6395754233295455e-06, "loss": 0.959, "step": 32630 }, { "epoch": 2.71, "learning_rate": 3.639464567802012e-06, "loss": 0.8441, "step": 32640 }, { "epoch": 2.71, "learning_rate": 3.639353712274478e-06, "loss": 0.8381, "step": 32650 }, { "epoch": 2.71, "learning_rate": 3.639242856746944e-06, "loss": 0.8589, "step": 32660 }, { "epoch": 2.72, "learning_rate": 3.6391320012194107e-06, "loss": 0.8713, "step": 32670 }, { "epoch": 2.72, "learning_rate": 3.6390211456918766e-06, "loss": 0.8837, "step": 32680 }, { "epoch": 2.72, "learning_rate": 3.6389102901643433e-06, "loss": 0.8258, "step": 32690 }, { "epoch": 2.72, "learning_rate": 3.6387994346368096e-06, "loss": 0.843, "step": 32700 }, { "epoch": 2.72, "learning_rate": 3.6386885791092755e-06, "loss": 0.8499, "step": 32710 }, { "epoch": 2.72, "learning_rate": 3.638577723581742e-06, "loss": 0.9163, "step": 32720 }, { "epoch": 2.72, "learning_rate": 3.638466868054208e-06, "loss": 0.8397, "step": 32730 }, { "epoch": 2.72, "learning_rate": 3.6383560125266748e-06, "loss": 0.8192, "step": 32740 }, { "epoch": 2.72, "learning_rate": 3.6382451569991407e-06, "loss": 0.7659, "step": 32750 }, { "epoch": 2.72, "learning_rate": 3.638134301471607e-06, "loss": 0.7657, "step": 32760 }, { "epoch": 2.72, "learning_rate": 3.6380234459440732e-06, "loss": 0.8626, "step": 32770 }, { "epoch": 2.72, "learning_rate": 3.6379125904165395e-06, "loss": 0.8677, "step": 32780 }, { "epoch": 2.73, "learning_rate": 3.6378017348890054e-06, "loss": 0.8185, "step": 32790 }, { "epoch": 2.73, "learning_rate": 3.637690879361472e-06, "loss": 0.8176, "step": 32800 }, { "epoch": 2.73, "learning_rate": 3.6375800238339384e-06, "loss": 0.8017, "step": 32810 }, { "epoch": 2.73, "learning_rate": 3.6374691683064043e-06, "loss": 0.8626, "step": 32820 }, { "epoch": 2.73, "learning_rate": 3.637358312778871e-06, "loss": 0.8507, "step": 32830 }, { "epoch": 2.73, "learning_rate": 3.637247457251337e-06, "loss": 0.8067, "step": 32840 }, { "epoch": 2.73, "learning_rate": 3.6371366017238036e-06, "loss": 0.8428, "step": 32850 }, { "epoch": 2.73, "learning_rate": 3.6370257461962695e-06, "loss": 0.8307, "step": 32860 }, { "epoch": 2.73, "learning_rate": 3.6369148906687358e-06, "loss": 0.7888, "step": 32870 }, { "epoch": 2.73, "learning_rate": 3.636804035141202e-06, "loss": 0.8298, "step": 32880 }, { "epoch": 2.73, "learning_rate": 3.6366931796136684e-06, "loss": 0.7947, "step": 32890 }, { "epoch": 2.73, "learning_rate": 3.6365823240861342e-06, "loss": 0.8721, "step": 32900 }, { "epoch": 2.74, "learning_rate": 3.636471468558601e-06, "loss": 0.8672, "step": 32910 }, { "epoch": 2.74, "learning_rate": 3.636360613031067e-06, "loss": 0.915, "step": 32920 }, { "epoch": 2.74, "learning_rate": 3.6362497575035335e-06, "loss": 0.7838, "step": 32930 }, { "epoch": 2.74, "learning_rate": 3.636138901976e-06, "loss": 0.855, "step": 32940 }, { "epoch": 2.74, "learning_rate": 3.6360280464484657e-06, "loss": 0.8074, "step": 32950 }, { "epoch": 2.74, "learning_rate": 3.6359171909209324e-06, "loss": 0.8019, "step": 32960 }, { "epoch": 2.74, "learning_rate": 3.6358063353933983e-06, "loss": 0.9413, "step": 32970 }, { "epoch": 2.74, "learning_rate": 3.6356954798658646e-06, "loss": 0.8006, "step": 32980 }, { "epoch": 2.74, "learning_rate": 3.635584624338331e-06, "loss": 0.8177, "step": 32990 }, { "epoch": 2.74, "learning_rate": 3.635473768810797e-06, "loss": 0.7883, "step": 33000 }, { "epoch": 2.74, "learning_rate": 3.6353629132832635e-06, "loss": 0.8118, "step": 33010 }, { "epoch": 2.74, "learning_rate": 3.6352520577557298e-06, "loss": 0.8768, "step": 33020 }, { "epoch": 2.75, "learning_rate": 3.6351412022281956e-06, "loss": 0.8143, "step": 33030 }, { "epoch": 2.75, "learning_rate": 3.6350303467006624e-06, "loss": 0.7742, "step": 33040 }, { "epoch": 2.75, "learning_rate": 3.6349194911731282e-06, "loss": 0.8372, "step": 33050 }, { "epoch": 2.75, "learning_rate": 3.6348086356455945e-06, "loss": 0.8652, "step": 33060 }, { "epoch": 2.75, "learning_rate": 3.6346977801180613e-06, "loss": 0.873, "step": 33070 }, { "epoch": 2.75, "learning_rate": 3.634586924590527e-06, "loss": 0.8323, "step": 33080 }, { "epoch": 2.75, "learning_rate": 3.634476069062994e-06, "loss": 0.8714, "step": 33090 }, { "epoch": 2.75, "learning_rate": 3.6343652135354597e-06, "loss": 0.825, "step": 33100 }, { "epoch": 2.75, "learning_rate": 3.634254358007926e-06, "loss": 0.8572, "step": 33110 }, { "epoch": 2.75, "learning_rate": 3.6341435024803923e-06, "loss": 0.8296, "step": 33120 }, { "epoch": 2.75, "learning_rate": 3.6340326469528586e-06, "loss": 0.7752, "step": 33130 }, { "epoch": 2.75, "learning_rate": 3.6339217914253245e-06, "loss": 0.8187, "step": 33140 }, { "epoch": 2.76, "learning_rate": 3.633810935897791e-06, "loss": 0.8916, "step": 33150 }, { "epoch": 2.76, "learning_rate": 3.633700080370257e-06, "loss": 0.8649, "step": 33160 }, { "epoch": 2.76, "learning_rate": 3.6335892248427234e-06, "loss": 0.9086, "step": 33170 }, { "epoch": 2.76, "learning_rate": 3.63347836931519e-06, "loss": 0.8698, "step": 33180 }, { "epoch": 2.76, "learning_rate": 3.6333785993404096e-06, "loss": 0.8105, "step": 33190 }, { "epoch": 2.76, "learning_rate": 3.6332677438128755e-06, "loss": 0.8565, "step": 33200 }, { "epoch": 2.76, "learning_rate": 3.633156888285342e-06, "loss": 0.8644, "step": 33210 }, { "epoch": 2.76, "learning_rate": 3.633046032757808e-06, "loss": 0.8982, "step": 33220 }, { "epoch": 2.76, "learning_rate": 3.6329351772302744e-06, "loss": 0.832, "step": 33230 }, { "epoch": 2.76, "learning_rate": 3.6328243217027407e-06, "loss": 0.8469, "step": 33240 }, { "epoch": 2.76, "learning_rate": 3.632713466175207e-06, "loss": 0.8258, "step": 33250 }, { "epoch": 2.76, "learning_rate": 3.632602610647673e-06, "loss": 0.849, "step": 33260 }, { "epoch": 2.77, "learning_rate": 3.6324917551201396e-06, "loss": 0.8167, "step": 33270 }, { "epoch": 2.77, "learning_rate": 3.632380899592606e-06, "loss": 0.8284, "step": 33280 }, { "epoch": 2.77, "learning_rate": 3.632270044065072e-06, "loss": 0.8294, "step": 33290 }, { "epoch": 2.77, "learning_rate": 3.6321591885375384e-06, "loss": 0.8601, "step": 33300 }, { "epoch": 2.77, "learning_rate": 3.6320483330100043e-06, "loss": 0.8434, "step": 33310 }, { "epoch": 2.77, "learning_rate": 3.631937477482471e-06, "loss": 0.869, "step": 33320 }, { "epoch": 2.77, "learning_rate": 3.631826621954937e-06, "loss": 0.8364, "step": 33330 }, { "epoch": 2.77, "learning_rate": 3.631715766427403e-06, "loss": 0.8913, "step": 33340 }, { "epoch": 2.77, "learning_rate": 3.6316049108998695e-06, "loss": 0.8257, "step": 33350 }, { "epoch": 2.77, "learning_rate": 3.631494055372336e-06, "loss": 0.8935, "step": 33360 }, { "epoch": 2.77, "learning_rate": 3.631383199844802e-06, "loss": 0.8993, "step": 33370 }, { "epoch": 2.77, "learning_rate": 3.6312723443172684e-06, "loss": 0.8574, "step": 33380 }, { "epoch": 2.78, "learning_rate": 3.6311614887897347e-06, "loss": 0.8315, "step": 33390 }, { "epoch": 2.78, "learning_rate": 3.631050633262201e-06, "loss": 0.7829, "step": 33400 }, { "epoch": 2.78, "learning_rate": 3.6309397777346673e-06, "loss": 0.8631, "step": 33410 }, { "epoch": 2.78, "learning_rate": 3.630828922207133e-06, "loss": 0.8124, "step": 33420 }, { "epoch": 2.78, "learning_rate": 3.6307180666796e-06, "loss": 0.794, "step": 33430 }, { "epoch": 2.78, "learning_rate": 3.6306072111520657e-06, "loss": 0.8673, "step": 33440 }, { "epoch": 2.78, "learning_rate": 3.6304963556245325e-06, "loss": 0.8764, "step": 33450 }, { "epoch": 2.78, "learning_rate": 3.6303855000969983e-06, "loss": 0.8254, "step": 33460 }, { "epoch": 2.78, "learning_rate": 3.6302746445694646e-06, "loss": 0.9149, "step": 33470 }, { "epoch": 2.78, "learning_rate": 3.630163789041931e-06, "loss": 0.8062, "step": 33480 }, { "epoch": 2.78, "learning_rate": 3.630052933514397e-06, "loss": 0.9668, "step": 33490 }, { "epoch": 2.78, "learning_rate": 3.629942077986863e-06, "loss": 0.8137, "step": 33500 }, { "epoch": 2.79, "learning_rate": 3.62983122245933e-06, "loss": 0.8559, "step": 33510 }, { "epoch": 2.79, "learning_rate": 3.629720366931796e-06, "loss": 0.8176, "step": 33520 }, { "epoch": 2.79, "learning_rate": 3.6296095114042624e-06, "loss": 0.8007, "step": 33530 }, { "epoch": 2.79, "learning_rate": 3.6294986558767287e-06, "loss": 0.8673, "step": 33540 }, { "epoch": 2.79, "learning_rate": 3.6293878003491946e-06, "loss": 0.8352, "step": 33550 }, { "epoch": 2.79, "learning_rate": 3.6292769448216613e-06, "loss": 0.8866, "step": 33560 }, { "epoch": 2.79, "learning_rate": 3.629166089294127e-06, "loss": 0.8963, "step": 33570 }, { "epoch": 2.79, "learning_rate": 3.6290552337665934e-06, "loss": 0.8396, "step": 33580 }, { "epoch": 2.79, "learning_rate": 3.6289443782390597e-06, "loss": 0.8074, "step": 33590 }, { "epoch": 2.79, "learning_rate": 3.628833522711526e-06, "loss": 0.847, "step": 33600 }, { "epoch": 2.79, "learning_rate": 3.628722667183992e-06, "loss": 0.9303, "step": 33610 }, { "epoch": 2.79, "learning_rate": 3.6286118116564586e-06, "loss": 0.8462, "step": 33620 }, { "epoch": 2.8, "learning_rate": 3.6285009561289245e-06, "loss": 0.7707, "step": 33630 }, { "epoch": 2.8, "learning_rate": 3.6283901006013912e-06, "loss": 0.9105, "step": 33640 }, { "epoch": 2.8, "learning_rate": 3.6282792450738575e-06, "loss": 0.8629, "step": 33650 }, { "epoch": 2.8, "learning_rate": 3.6281683895463234e-06, "loss": 0.8639, "step": 33660 }, { "epoch": 2.8, "learning_rate": 3.62805753401879e-06, "loss": 0.892, "step": 33670 }, { "epoch": 2.8, "learning_rate": 3.627946678491256e-06, "loss": 0.8115, "step": 33680 }, { "epoch": 2.8, "learning_rate": 3.6278358229637227e-06, "loss": 0.8196, "step": 33690 }, { "epoch": 2.8, "learning_rate": 3.6277249674361886e-06, "loss": 0.8137, "step": 33700 }, { "epoch": 2.8, "learning_rate": 3.627614111908655e-06, "loss": 0.7844, "step": 33710 }, { "epoch": 2.8, "learning_rate": 3.627503256381121e-06, "loss": 0.8666, "step": 33720 }, { "epoch": 2.8, "learning_rate": 3.6273924008535874e-06, "loss": 0.843, "step": 33730 }, { "epoch": 2.8, "learning_rate": 3.6272815453260533e-06, "loss": 0.7995, "step": 33740 }, { "epoch": 2.81, "learning_rate": 3.62717068979852e-06, "loss": 0.8092, "step": 33750 }, { "epoch": 2.81, "learning_rate": 3.6270598342709863e-06, "loss": 0.8974, "step": 33760 }, { "epoch": 2.81, "learning_rate": 3.626948978743452e-06, "loss": 0.8537, "step": 33770 }, { "epoch": 2.81, "learning_rate": 3.626838123215919e-06, "loss": 0.8499, "step": 33780 }, { "epoch": 2.81, "learning_rate": 3.626727267688385e-06, "loss": 0.8503, "step": 33790 }, { "epoch": 2.81, "learning_rate": 3.6266164121608515e-06, "loss": 0.8337, "step": 33800 }, { "epoch": 2.81, "learning_rate": 3.6265055566333174e-06, "loss": 0.8372, "step": 33810 }, { "epoch": 2.81, "learning_rate": 3.6263947011057837e-06, "loss": 0.8964, "step": 33820 }, { "epoch": 2.81, "learning_rate": 3.62628384557825e-06, "loss": 0.7464, "step": 33830 }, { "epoch": 2.81, "learning_rate": 3.6261729900507163e-06, "loss": 0.7544, "step": 33840 }, { "epoch": 2.81, "learning_rate": 3.626062134523182e-06, "loss": 0.8746, "step": 33850 }, { "epoch": 2.81, "learning_rate": 3.625951278995649e-06, "loss": 0.7721, "step": 33860 }, { "epoch": 2.82, "learning_rate": 3.6258404234681147e-06, "loss": 0.8749, "step": 33870 }, { "epoch": 2.82, "learning_rate": 3.6257295679405815e-06, "loss": 0.8109, "step": 33880 }, { "epoch": 2.82, "learning_rate": 3.6256187124130478e-06, "loss": 0.803, "step": 33890 }, { "epoch": 2.82, "learning_rate": 3.6255078568855136e-06, "loss": 0.9106, "step": 33900 }, { "epoch": 2.82, "learning_rate": 3.6253970013579803e-06, "loss": 0.8523, "step": 33910 }, { "epoch": 2.82, "learning_rate": 3.6252861458304462e-06, "loss": 0.9094, "step": 33920 }, { "epoch": 2.82, "learning_rate": 3.6251752903029125e-06, "loss": 0.7692, "step": 33930 }, { "epoch": 2.82, "learning_rate": 3.625064434775379e-06, "loss": 0.8556, "step": 33940 }, { "epoch": 2.82, "learning_rate": 3.624953579247845e-06, "loss": 0.7754, "step": 33950 }, { "epoch": 2.82, "learning_rate": 3.6248427237203114e-06, "loss": 0.8522, "step": 33960 }, { "epoch": 2.82, "learning_rate": 3.6247318681927777e-06, "loss": 0.7969, "step": 33970 }, { "epoch": 2.82, "learning_rate": 3.6246210126652436e-06, "loss": 0.8679, "step": 33980 }, { "epoch": 2.83, "learning_rate": 3.6245101571377103e-06, "loss": 0.8176, "step": 33990 }, { "epoch": 2.83, "learning_rate": 3.624399301610176e-06, "loss": 0.8524, "step": 34000 }, { "epoch": 2.83, "learning_rate": 3.6242884460826424e-06, "loss": 0.787, "step": 34010 }, { "epoch": 2.83, "learning_rate": 3.624177590555109e-06, "loss": 0.863, "step": 34020 }, { "epoch": 2.83, "learning_rate": 3.624066735027575e-06, "loss": 0.8508, "step": 34030 }, { "epoch": 2.83, "learning_rate": 3.6239558795000418e-06, "loss": 0.8078, "step": 34040 }, { "epoch": 2.83, "learning_rate": 3.6238450239725076e-06, "loss": 0.8126, "step": 34050 }, { "epoch": 2.83, "learning_rate": 3.623734168444974e-06, "loss": 0.7841, "step": 34060 }, { "epoch": 2.83, "learning_rate": 3.6236233129174402e-06, "loss": 0.8562, "step": 34070 }, { "epoch": 2.83, "learning_rate": 3.6235124573899065e-06, "loss": 0.8053, "step": 34080 }, { "epoch": 2.83, "learning_rate": 3.6234016018623724e-06, "loss": 0.8564, "step": 34090 }, { "epoch": 2.83, "learning_rate": 3.623290746334839e-06, "loss": 0.8318, "step": 34100 }, { "epoch": 2.84, "learning_rate": 3.623179890807305e-06, "loss": 0.7743, "step": 34110 }, { "epoch": 2.84, "learning_rate": 3.6230690352797713e-06, "loss": 0.9689, "step": 34120 }, { "epoch": 2.84, "learning_rate": 3.622958179752238e-06, "loss": 0.792, "step": 34130 }, { "epoch": 2.84, "learning_rate": 3.622847324224704e-06, "loss": 0.8495, "step": 34140 }, { "epoch": 2.84, "learning_rate": 3.6227364686971706e-06, "loss": 0.866, "step": 34150 }, { "epoch": 2.84, "learning_rate": 3.6226256131696365e-06, "loss": 0.8288, "step": 34160 }, { "epoch": 2.84, "learning_rate": 3.6225147576421028e-06, "loss": 0.8676, "step": 34170 }, { "epoch": 2.84, "learning_rate": 3.622403902114569e-06, "loss": 0.8519, "step": 34180 }, { "epoch": 2.84, "learning_rate": 3.6222930465870353e-06, "loss": 0.8685, "step": 34190 }, { "epoch": 2.84, "learning_rate": 3.6221821910595012e-06, "loss": 0.8516, "step": 34200 }, { "epoch": 2.84, "learning_rate": 3.622071335531968e-06, "loss": 0.8456, "step": 34210 }, { "epoch": 2.84, "learning_rate": 3.621960480004434e-06, "loss": 0.882, "step": 34220 }, { "epoch": 2.85, "learning_rate": 3.6218496244769005e-06, "loss": 0.8136, "step": 34230 }, { "epoch": 2.85, "learning_rate": 3.6217387689493664e-06, "loss": 0.9049, "step": 34240 }, { "epoch": 2.85, "learning_rate": 3.6216279134218327e-06, "loss": 0.8312, "step": 34250 }, { "epoch": 2.85, "learning_rate": 3.6215170578942994e-06, "loss": 0.8075, "step": 34260 }, { "epoch": 2.85, "learning_rate": 3.6214062023667653e-06, "loss": 0.9089, "step": 34270 }, { "epoch": 2.85, "learning_rate": 3.6212953468392316e-06, "loss": 0.848, "step": 34280 }, { "epoch": 2.85, "learning_rate": 3.621184491311698e-06, "loss": 0.8412, "step": 34290 }, { "epoch": 2.85, "learning_rate": 3.621073635784164e-06, "loss": 0.8522, "step": 34300 }, { "epoch": 2.85, "learning_rate": 3.6209627802566305e-06, "loss": 0.838, "step": 34310 }, { "epoch": 2.85, "learning_rate": 3.6208519247290968e-06, "loss": 0.8807, "step": 34320 }, { "epoch": 2.85, "learning_rate": 3.6207410692015626e-06, "loss": 0.8098, "step": 34330 }, { "epoch": 2.85, "learning_rate": 3.6206302136740293e-06, "loss": 0.7961, "step": 34340 }, { "epoch": 2.86, "learning_rate": 3.6205193581464952e-06, "loss": 0.8557, "step": 34350 }, { "epoch": 2.86, "learning_rate": 3.6204085026189615e-06, "loss": 0.8235, "step": 34360 }, { "epoch": 2.86, "learning_rate": 3.6202976470914282e-06, "loss": 0.8284, "step": 34370 }, { "epoch": 2.86, "learning_rate": 3.620186791563894e-06, "loss": 0.8541, "step": 34380 }, { "epoch": 2.86, "learning_rate": 3.620075936036361e-06, "loss": 0.7984, "step": 34390 }, { "epoch": 2.86, "learning_rate": 3.6199650805088267e-06, "loss": 0.8338, "step": 34400 }, { "epoch": 2.86, "learning_rate": 3.619854224981293e-06, "loss": 0.8055, "step": 34410 }, { "epoch": 2.86, "learning_rate": 3.6197433694537593e-06, "loss": 0.8099, "step": 34420 }, { "epoch": 2.86, "learning_rate": 3.6196325139262256e-06, "loss": 0.8379, "step": 34430 }, { "epoch": 2.86, "learning_rate": 3.6195216583986915e-06, "loss": 0.7973, "step": 34440 }, { "epoch": 2.86, "learning_rate": 3.619410802871158e-06, "loss": 0.803, "step": 34450 }, { "epoch": 2.86, "learning_rate": 3.619299947343624e-06, "loss": 0.7523, "step": 34460 }, { "epoch": 2.87, "learning_rate": 3.6191890918160908e-06, "loss": 0.9003, "step": 34470 }, { "epoch": 2.87, "learning_rate": 3.6190782362885566e-06, "loss": 0.8178, "step": 34480 }, { "epoch": 2.87, "learning_rate": 3.618967380761023e-06, "loss": 0.8427, "step": 34490 }, { "epoch": 2.87, "learning_rate": 3.6188565252334896e-06, "loss": 0.8314, "step": 34500 }, { "epoch": 2.87, "learning_rate": 3.6187456697059555e-06, "loss": 0.8507, "step": 34510 }, { "epoch": 2.87, "learning_rate": 3.618634814178422e-06, "loss": 0.8856, "step": 34520 }, { "epoch": 2.87, "learning_rate": 3.618523958650888e-06, "loss": 0.9211, "step": 34530 }, { "epoch": 2.87, "learning_rate": 3.6184131031233544e-06, "loss": 0.8465, "step": 34540 }, { "epoch": 2.87, "learning_rate": 3.6183022475958203e-06, "loss": 0.8101, "step": 34550 }, { "epoch": 2.87, "learning_rate": 3.618191392068287e-06, "loss": 0.7967, "step": 34560 }, { "epoch": 2.87, "learning_rate": 3.618080536540753e-06, "loss": 0.9044, "step": 34570 }, { "epoch": 2.87, "learning_rate": 3.6179696810132196e-06, "loss": 0.8215, "step": 34580 }, { "epoch": 2.88, "learning_rate": 3.6178588254856855e-06, "loss": 0.7741, "step": 34590 }, { "epoch": 2.88, "learning_rate": 3.6177479699581518e-06, "loss": 0.7874, "step": 34600 }, { "epoch": 2.88, "learning_rate": 3.617637114430618e-06, "loss": 0.8723, "step": 34610 }, { "epoch": 2.88, "learning_rate": 3.6175262589030843e-06, "loss": 0.8581, "step": 34620 }, { "epoch": 2.88, "learning_rate": 3.6174154033755506e-06, "loss": 0.8488, "step": 34630 }, { "epoch": 2.88, "learning_rate": 3.617304547848017e-06, "loss": 0.7421, "step": 34640 }, { "epoch": 2.88, "learning_rate": 3.6171936923204832e-06, "loss": 0.8393, "step": 34650 }, { "epoch": 2.88, "learning_rate": 3.6170828367929495e-06, "loss": 0.8311, "step": 34660 }, { "epoch": 2.88, "learning_rate": 3.616971981265416e-06, "loss": 0.8926, "step": 34670 }, { "epoch": 2.88, "learning_rate": 3.6168611257378817e-06, "loss": 0.8684, "step": 34680 }, { "epoch": 2.88, "learning_rate": 3.6167502702103484e-06, "loss": 0.8267, "step": 34690 }, { "epoch": 2.88, "learning_rate": 3.6166394146828143e-06, "loss": 0.8099, "step": 34700 }, { "epoch": 2.89, "learning_rate": 3.6165285591552806e-06, "loss": 0.8587, "step": 34710 }, { "epoch": 2.89, "learning_rate": 3.616417703627747e-06, "loss": 0.8634, "step": 34720 }, { "epoch": 2.89, "learning_rate": 3.616306848100213e-06, "loss": 0.8546, "step": 34730 }, { "epoch": 2.89, "learning_rate": 3.61619599257268e-06, "loss": 0.9186, "step": 34740 }, { "epoch": 2.89, "learning_rate": 3.6160851370451458e-06, "loss": 0.7625, "step": 34750 }, { "epoch": 2.89, "learning_rate": 3.615974281517612e-06, "loss": 0.7546, "step": 34760 }, { "epoch": 2.89, "learning_rate": 3.6158634259900784e-06, "loss": 0.8581, "step": 34770 }, { "epoch": 2.89, "learning_rate": 3.6157525704625446e-06, "loss": 0.8806, "step": 34780 }, { "epoch": 2.89, "learning_rate": 3.6156417149350105e-06, "loss": 0.8149, "step": 34790 }, { "epoch": 2.89, "learning_rate": 3.6155308594074772e-06, "loss": 0.8398, "step": 34800 }, { "epoch": 2.89, "learning_rate": 3.615420003879943e-06, "loss": 0.811, "step": 34810 }, { "epoch": 2.89, "learning_rate": 3.61530914835241e-06, "loss": 0.8443, "step": 34820 }, { "epoch": 2.9, "learning_rate": 3.6151982928248757e-06, "loss": 0.7993, "step": 34830 }, { "epoch": 2.9, "learning_rate": 3.615087437297342e-06, "loss": 0.7715, "step": 34840 }, { "epoch": 2.9, "learning_rate": 3.6149765817698083e-06, "loss": 0.826, "step": 34850 }, { "epoch": 2.9, "learning_rate": 3.6148657262422746e-06, "loss": 0.8173, "step": 34860 }, { "epoch": 2.9, "learning_rate": 3.614754870714741e-06, "loss": 0.8907, "step": 34870 }, { "epoch": 2.9, "learning_rate": 3.614644015187207e-06, "loss": 0.8236, "step": 34880 }, { "epoch": 2.9, "learning_rate": 3.6145331596596735e-06, "loss": 0.8121, "step": 34890 }, { "epoch": 2.9, "learning_rate": 3.6144223041321393e-06, "loss": 0.7574, "step": 34900 }, { "epoch": 2.9, "learning_rate": 3.614311448604606e-06, "loss": 0.7733, "step": 34910 }, { "epoch": 2.9, "learning_rate": 3.614200593077072e-06, "loss": 0.9212, "step": 34920 }, { "epoch": 2.9, "learning_rate": 3.6140897375495387e-06, "loss": 0.754, "step": 34930 }, { "epoch": 2.9, "learning_rate": 3.6139788820220045e-06, "loss": 0.8428, "step": 34940 }, { "epoch": 2.9, "learning_rate": 3.613868026494471e-06, "loss": 0.8066, "step": 34950 }, { "epoch": 2.91, "learning_rate": 3.613757170966937e-06, "loss": 0.8336, "step": 34960 }, { "epoch": 2.91, "learning_rate": 3.6136463154394034e-06, "loss": 0.8547, "step": 34970 }, { "epoch": 2.91, "learning_rate": 3.6135354599118693e-06, "loss": 0.8483, "step": 34980 }, { "epoch": 2.91, "learning_rate": 3.613424604384336e-06, "loss": 0.8358, "step": 34990 }, { "epoch": 2.91, "learning_rate": 3.6133137488568023e-06, "loss": 0.8466, "step": 35000 }, { "epoch": 2.91, "learning_rate": 3.6132028933292686e-06, "loss": 0.8129, "step": 35010 }, { "epoch": 2.91, "learning_rate": 3.613092037801735e-06, "loss": 0.8608, "step": 35020 }, { "epoch": 2.91, "learning_rate": 3.6129811822742008e-06, "loss": 0.8037, "step": 35030 }, { "epoch": 2.91, "learning_rate": 3.6128703267466675e-06, "loss": 0.8335, "step": 35040 }, { "epoch": 2.91, "learning_rate": 3.6127594712191334e-06, "loss": 0.801, "step": 35050 }, { "epoch": 2.91, "learning_rate": 3.6126486156915996e-06, "loss": 0.7847, "step": 35060 }, { "epoch": 2.91, "learning_rate": 3.612537760164066e-06, "loss": 0.9072, "step": 35070 }, { "epoch": 2.92, "learning_rate": 3.6124269046365322e-06, "loss": 0.7942, "step": 35080 }, { "epoch": 2.92, "learning_rate": 3.6123160491089985e-06, "loss": 0.822, "step": 35090 }, { "epoch": 2.92, "learning_rate": 3.612205193581465e-06, "loss": 0.8524, "step": 35100 }, { "epoch": 2.92, "learning_rate": 3.612094338053931e-06, "loss": 0.8152, "step": 35110 }, { "epoch": 2.92, "learning_rate": 3.6119834825263974e-06, "loss": 0.925, "step": 35120 }, { "epoch": 2.92, "learning_rate": 3.6118726269988637e-06, "loss": 0.7917, "step": 35130 }, { "epoch": 2.92, "learning_rate": 3.6117617714713296e-06, "loss": 0.8249, "step": 35140 }, { "epoch": 2.92, "learning_rate": 3.6116509159437963e-06, "loss": 0.8542, "step": 35150 }, { "epoch": 2.92, "learning_rate": 3.611540060416262e-06, "loss": 0.9197, "step": 35160 }, { "epoch": 2.92, "learning_rate": 3.611429204888729e-06, "loss": 0.917, "step": 35170 }, { "epoch": 2.92, "learning_rate": 3.6113183493611948e-06, "loss": 0.7701, "step": 35180 }, { "epoch": 2.92, "learning_rate": 3.611207493833661e-06, "loss": 0.8357, "step": 35190 }, { "epoch": 2.93, "learning_rate": 3.6110966383061274e-06, "loss": 0.7692, "step": 35200 }, { "epoch": 2.93, "learning_rate": 3.6109857827785937e-06, "loss": 0.7905, "step": 35210 }, { "epoch": 2.93, "learning_rate": 3.6108749272510595e-06, "loss": 0.8359, "step": 35220 }, { "epoch": 2.93, "learning_rate": 3.6107640717235262e-06, "loss": 0.8345, "step": 35230 }, { "epoch": 2.93, "learning_rate": 3.6106532161959925e-06, "loss": 0.8032, "step": 35240 }, { "epoch": 2.93, "learning_rate": 3.610542360668459e-06, "loss": 0.9416, "step": 35250 }, { "epoch": 2.93, "learning_rate": 3.610431505140925e-06, "loss": 0.8691, "step": 35260 }, { "epoch": 2.93, "learning_rate": 3.610320649613391e-06, "loss": 0.8802, "step": 35270 }, { "epoch": 2.93, "learning_rate": 3.6102097940858577e-06, "loss": 0.8471, "step": 35280 }, { "epoch": 2.93, "learning_rate": 3.6100989385583236e-06, "loss": 0.8801, "step": 35290 }, { "epoch": 2.93, "learning_rate": 3.60998808303079e-06, "loss": 0.8189, "step": 35300 }, { "epoch": 2.93, "learning_rate": 3.609877227503256e-06, "loss": 0.8077, "step": 35310 }, { "epoch": 2.94, "learning_rate": 3.6097663719757225e-06, "loss": 0.9613, "step": 35320 }, { "epoch": 2.94, "learning_rate": 3.6096555164481884e-06, "loss": 0.8227, "step": 35330 }, { "epoch": 2.94, "learning_rate": 3.609544660920655e-06, "loss": 0.8381, "step": 35340 }, { "epoch": 2.94, "learning_rate": 3.609433805393121e-06, "loss": 0.7818, "step": 35350 }, { "epoch": 2.94, "learning_rate": 3.6093229498655877e-06, "loss": 0.834, "step": 35360 }, { "epoch": 2.94, "learning_rate": 3.609212094338054e-06, "loss": 0.885, "step": 35370 }, { "epoch": 2.94, "learning_rate": 3.60910123881052e-06, "loss": 0.8398, "step": 35380 }, { "epoch": 2.94, "learning_rate": 3.6089903832829865e-06, "loss": 0.8345, "step": 35390 }, { "epoch": 2.94, "learning_rate": 3.6088795277554524e-06, "loss": 0.8599, "step": 35400 }, { "epoch": 2.94, "learning_rate": 3.6087686722279187e-06, "loss": 0.8095, "step": 35410 }, { "epoch": 2.94, "learning_rate": 3.608657816700385e-06, "loss": 0.9291, "step": 35420 }, { "epoch": 2.94, "learning_rate": 3.6085469611728513e-06, "loss": 0.7917, "step": 35430 }, { "epoch": 2.95, "learning_rate": 3.6084361056453176e-06, "loss": 0.841, "step": 35440 }, { "epoch": 2.95, "learning_rate": 3.608325250117784e-06, "loss": 0.8396, "step": 35450 }, { "epoch": 2.95, "learning_rate": 3.6082143945902498e-06, "loss": 0.8705, "step": 35460 }, { "epoch": 2.95, "learning_rate": 3.6081035390627165e-06, "loss": 0.9035, "step": 35470 }, { "epoch": 2.95, "learning_rate": 3.6079926835351828e-06, "loss": 0.8602, "step": 35480 }, { "epoch": 2.95, "learning_rate": 3.6078818280076487e-06, "loss": 0.7991, "step": 35490 }, { "epoch": 2.95, "learning_rate": 3.6077709724801154e-06, "loss": 0.8191, "step": 35500 }, { "epoch": 2.95, "learning_rate": 3.6076601169525812e-06, "loss": 0.8088, "step": 35510 }, { "epoch": 2.95, "learning_rate": 3.607549261425048e-06, "loss": 0.9311, "step": 35520 }, { "epoch": 2.95, "learning_rate": 3.607438405897514e-06, "loss": 0.7991, "step": 35530 }, { "epoch": 2.95, "learning_rate": 3.60732755036998e-06, "loss": 0.7891, "step": 35540 }, { "epoch": 2.95, "learning_rate": 3.6072166948424464e-06, "loss": 0.8099, "step": 35550 }, { "epoch": 2.96, "learning_rate": 3.6071058393149127e-06, "loss": 0.8812, "step": 35560 }, { "epoch": 2.96, "learning_rate": 3.6069949837873786e-06, "loss": 0.8477, "step": 35570 }, { "epoch": 2.96, "learning_rate": 3.6068841282598453e-06, "loss": 0.8079, "step": 35580 }, { "epoch": 2.96, "learning_rate": 3.606773272732311e-06, "loss": 0.8192, "step": 35590 }, { "epoch": 2.96, "learning_rate": 3.606662417204778e-06, "loss": 0.7533, "step": 35600 }, { "epoch": 2.96, "learning_rate": 3.606551561677244e-06, "loss": 0.8749, "step": 35610 }, { "epoch": 2.96, "learning_rate": 3.60644070614971e-06, "loss": 0.841, "step": 35620 }, { "epoch": 2.96, "learning_rate": 3.6063298506221768e-06, "loss": 0.773, "step": 35630 }, { "epoch": 2.96, "learning_rate": 3.6062189950946427e-06, "loss": 0.8883, "step": 35640 }, { "epoch": 2.96, "learning_rate": 3.606108139567109e-06, "loss": 0.8777, "step": 35650 }, { "epoch": 2.96, "learning_rate": 3.6059972840395752e-06, "loss": 0.7852, "step": 35660 }, { "epoch": 2.96, "learning_rate": 3.6058864285120415e-06, "loss": 0.9065, "step": 35670 }, { "epoch": 2.97, "learning_rate": 3.605775572984508e-06, "loss": 0.84, "step": 35680 }, { "epoch": 2.97, "learning_rate": 3.605664717456974e-06, "loss": 0.7933, "step": 35690 }, { "epoch": 2.97, "learning_rate": 3.60555386192944e-06, "loss": 0.7814, "step": 35700 }, { "epoch": 2.97, "learning_rate": 3.6054430064019067e-06, "loss": 0.8989, "step": 35710 }, { "epoch": 2.97, "learning_rate": 3.6053321508743726e-06, "loss": 0.8892, "step": 35720 }, { "epoch": 2.97, "learning_rate": 3.605221295346839e-06, "loss": 0.8517, "step": 35730 }, { "epoch": 2.97, "learning_rate": 3.6051104398193056e-06, "loss": 0.7884, "step": 35740 }, { "epoch": 2.97, "learning_rate": 3.6049995842917715e-06, "loss": 0.8414, "step": 35750 }, { "epoch": 2.97, "learning_rate": 3.604888728764238e-06, "loss": 0.754, "step": 35760 }, { "epoch": 2.97, "learning_rate": 3.604777873236704e-06, "loss": 0.8243, "step": 35770 }, { "epoch": 2.97, "learning_rate": 3.6046670177091704e-06, "loss": 0.791, "step": 35780 }, { "epoch": 2.97, "learning_rate": 3.6045561621816367e-06, "loss": 0.8054, "step": 35790 }, { "epoch": 2.98, "learning_rate": 3.604445306654103e-06, "loss": 0.7498, "step": 35800 }, { "epoch": 2.98, "learning_rate": 3.604334451126569e-06, "loss": 0.8399, "step": 35810 }, { "epoch": 2.98, "learning_rate": 3.6042235955990356e-06, "loss": 0.9129, "step": 35820 }, { "epoch": 2.98, "learning_rate": 3.6041127400715014e-06, "loss": 0.7899, "step": 35830 }, { "epoch": 2.98, "learning_rate": 3.6040018845439677e-06, "loss": 0.7852, "step": 35840 }, { "epoch": 2.98, "learning_rate": 3.6038910290164344e-06, "loss": 0.8366, "step": 35850 }, { "epoch": 2.98, "learning_rate": 3.6037801734889003e-06, "loss": 0.8332, "step": 35860 }, { "epoch": 2.98, "learning_rate": 3.603669317961367e-06, "loss": 0.8682, "step": 35870 }, { "epoch": 2.98, "learning_rate": 3.603558462433833e-06, "loss": 0.8014, "step": 35880 }, { "epoch": 2.98, "learning_rate": 3.603447606906299e-06, "loss": 0.7949, "step": 35890 }, { "epoch": 2.98, "learning_rate": 3.6033367513787655e-06, "loss": 0.9145, "step": 35900 }, { "epoch": 2.98, "learning_rate": 3.6032258958512318e-06, "loss": 0.8305, "step": 35910 }, { "epoch": 2.99, "learning_rate": 3.6031150403236977e-06, "loss": 0.8563, "step": 35920 }, { "epoch": 2.99, "learning_rate": 3.6030041847961644e-06, "loss": 0.9269, "step": 35930 }, { "epoch": 2.99, "learning_rate": 3.6028933292686302e-06, "loss": 0.8551, "step": 35940 }, { "epoch": 2.99, "learning_rate": 3.602782473741097e-06, "loss": 0.8077, "step": 35950 }, { "epoch": 2.99, "learning_rate": 3.602671618213563e-06, "loss": 0.8414, "step": 35960 }, { "epoch": 2.99, "learning_rate": 3.602560762686029e-06, "loss": 0.8965, "step": 35970 }, { "epoch": 2.99, "learning_rate": 3.602449907158496e-06, "loss": 0.9171, "step": 35980 }, { "epoch": 2.99, "learning_rate": 3.6023390516309617e-06, "loss": 0.8283, "step": 35990 }, { "epoch": 2.99, "learning_rate": 3.602228196103428e-06, "loss": 0.9003, "step": 36000 }, { "epoch": 2.99, "learning_rate": 3.6021173405758943e-06, "loss": 0.8094, "step": 36010 }, { "epoch": 2.99, "learning_rate": 3.6020064850483606e-06, "loss": 0.9075, "step": 36020 }, { "epoch": 2.99, "learning_rate": 3.601895629520827e-06, "loss": 0.8329, "step": 36030 }, { "epoch": 3.0, "learning_rate": 3.601784773993293e-06, "loss": 0.814, "step": 36040 }, { "epoch": 3.0, "learning_rate": 3.601673918465759e-06, "loss": 0.8223, "step": 36050 }, { "epoch": 3.0, "learning_rate": 3.601563062938226e-06, "loss": 0.7945, "step": 36060 }, { "epoch": 3.0, "learning_rate": 3.6014522074106917e-06, "loss": 0.7757, "step": 36070 }, { "epoch": 3.0, "learning_rate": 3.601341351883158e-06, "loss": 0.8728, "step": 36080 }, { "epoch": 3.0, "learning_rate": 3.6012304963556243e-06, "loss": 0.7861, "step": 36090 }, { "epoch": 3.0, "eval_loss": 1.0478405952453613, "eval_runtime": 344.8216, "eval_samples_per_second": 7.755, "eval_steps_per_second": 3.877, "eval_wer": 0.6519943683989962, "step": 36093 }, { "epoch": 3.0, "learning_rate": 3.6011196408280906e-06, "loss": 0.8939, "step": 36100 }, { "epoch": 3.0, "learning_rate": 3.6010087853005573e-06, "loss": 0.8065, "step": 36110 }, { "epoch": 3.0, "learning_rate": 3.600897929773023e-06, "loss": 0.804, "step": 36120 }, { "epoch": 3.0, "learning_rate": 3.6007870742454894e-06, "loss": 0.8011, "step": 36130 }, { "epoch": 3.0, "learning_rate": 3.6006762187179557e-06, "loss": 0.8108, "step": 36140 }, { "epoch": 3.0, "learning_rate": 3.600565363190422e-06, "loss": 0.8772, "step": 36150 }, { "epoch": 3.01, "learning_rate": 3.600454507662888e-06, "loss": 0.8238, "step": 36160 }, { "epoch": 3.01, "learning_rate": 3.6003436521353546e-06, "loss": 0.8076, "step": 36170 }, { "epoch": 3.01, "learning_rate": 3.6002327966078205e-06, "loss": 0.8232, "step": 36180 }, { "epoch": 3.01, "learning_rate": 3.6001219410802868e-06, "loss": 0.7843, "step": 36190 }, { "epoch": 3.01, "learning_rate": 3.600011085552753e-06, "loss": 0.871, "step": 36200 }, { "epoch": 3.01, "learning_rate": 3.5999002300252194e-06, "loss": 0.8058, "step": 36210 }, { "epoch": 3.01, "learning_rate": 3.599789374497686e-06, "loss": 0.8198, "step": 36220 }, { "epoch": 3.01, "learning_rate": 3.599678518970152e-06, "loss": 0.7689, "step": 36230 }, { "epoch": 3.01, "learning_rate": 3.5995676634426183e-06, "loss": 0.7623, "step": 36240 }, { "epoch": 3.01, "learning_rate": 3.5994568079150846e-06, "loss": 0.8915, "step": 36250 }, { "epoch": 3.01, "learning_rate": 3.599345952387551e-06, "loss": 0.8125, "step": 36260 }, { "epoch": 3.01, "learning_rate": 3.5992350968600167e-06, "loss": 0.8235, "step": 36270 }, { "epoch": 3.02, "learning_rate": 3.5991242413324834e-06, "loss": 0.8425, "step": 36280 }, { "epoch": 3.02, "learning_rate": 3.5990133858049493e-06, "loss": 0.8196, "step": 36290 }, { "epoch": 3.02, "learning_rate": 3.598902530277416e-06, "loss": 0.7949, "step": 36300 }, { "epoch": 3.02, "learning_rate": 3.598791674749882e-06, "loss": 0.8155, "step": 36310 }, { "epoch": 3.02, "learning_rate": 3.598680819222348e-06, "loss": 0.8497, "step": 36320 }, { "epoch": 3.02, "learning_rate": 3.5985699636948145e-06, "loss": 0.8772, "step": 36330 }, { "epoch": 3.02, "learning_rate": 3.598459108167281e-06, "loss": 0.8131, "step": 36340 }, { "epoch": 3.02, "learning_rate": 3.598348252639747e-06, "loss": 0.8693, "step": 36350 }, { "epoch": 3.02, "learning_rate": 3.5982373971122134e-06, "loss": 0.801, "step": 36360 }, { "epoch": 3.02, "learning_rate": 3.5981265415846797e-06, "loss": 0.8321, "step": 36370 }, { "epoch": 3.02, "learning_rate": 3.598015686057146e-06, "loss": 0.8558, "step": 36380 }, { "epoch": 3.02, "learning_rate": 3.5979048305296123e-06, "loss": 0.8936, "step": 36390 }, { "epoch": 3.03, "learning_rate": 3.597793975002078e-06, "loss": 0.9278, "step": 36400 }, { "epoch": 3.03, "learning_rate": 3.597683119474545e-06, "loss": 0.8596, "step": 36410 }, { "epoch": 3.03, "learning_rate": 3.5975722639470107e-06, "loss": 0.7752, "step": 36420 }, { "epoch": 3.03, "learning_rate": 3.597461408419477e-06, "loss": 0.8838, "step": 36430 }, { "epoch": 3.03, "learning_rate": 3.5973505528919433e-06, "loss": 0.8466, "step": 36440 }, { "epoch": 3.03, "learning_rate": 3.5972396973644096e-06, "loss": 0.8207, "step": 36450 }, { "epoch": 3.03, "learning_rate": 3.5971288418368763e-06, "loss": 0.7926, "step": 36460 }, { "epoch": 3.03, "learning_rate": 3.597017986309342e-06, "loss": 0.893, "step": 36470 }, { "epoch": 3.03, "learning_rate": 3.5969071307818085e-06, "loss": 0.8914, "step": 36480 }, { "epoch": 3.03, "learning_rate": 3.596796275254275e-06, "loss": 0.8396, "step": 36490 }, { "epoch": 3.03, "learning_rate": 3.596685419726741e-06, "loss": 0.8647, "step": 36500 }, { "epoch": 3.03, "learning_rate": 3.596574564199207e-06, "loss": 0.8674, "step": 36510 }, { "epoch": 3.04, "learning_rate": 3.5964637086716737e-06, "loss": 0.8622, "step": 36520 }, { "epoch": 3.04, "learning_rate": 3.5963528531441396e-06, "loss": 0.8846, "step": 36530 }, { "epoch": 3.04, "learning_rate": 3.5962419976166063e-06, "loss": 0.8647, "step": 36540 }, { "epoch": 3.04, "learning_rate": 3.596131142089072e-06, "loss": 0.8924, "step": 36550 }, { "epoch": 3.04, "learning_rate": 3.5960202865615384e-06, "loss": 0.8324, "step": 36560 }, { "epoch": 3.04, "learning_rate": 3.5959094310340047e-06, "loss": 0.8184, "step": 36570 }, { "epoch": 3.04, "learning_rate": 3.595798575506471e-06, "loss": 0.8939, "step": 36580 }, { "epoch": 3.04, "learning_rate": 3.5956877199789373e-06, "loss": 0.8379, "step": 36590 }, { "epoch": 3.04, "learning_rate": 3.5955768644514036e-06, "loss": 0.9234, "step": 36600 }, { "epoch": 3.04, "learning_rate": 3.59546600892387e-06, "loss": 0.7938, "step": 36610 }, { "epoch": 3.04, "learning_rate": 3.595355153396336e-06, "loss": 0.7915, "step": 36620 }, { "epoch": 3.04, "learning_rate": 3.5952442978688025e-06, "loss": 0.899, "step": 36630 }, { "epoch": 3.05, "learning_rate": 3.5951334423412684e-06, "loss": 0.821, "step": 36640 }, { "epoch": 3.05, "learning_rate": 3.595022586813735e-06, "loss": 0.9484, "step": 36650 }, { "epoch": 3.05, "learning_rate": 3.594911731286201e-06, "loss": 0.8627, "step": 36660 }, { "epoch": 3.05, "learning_rate": 3.5948008757586673e-06, "loss": 0.8527, "step": 36670 }, { "epoch": 3.05, "learning_rate": 3.5946900202311336e-06, "loss": 0.8154, "step": 36680 }, { "epoch": 3.05, "learning_rate": 3.5945791647036e-06, "loss": 0.827, "step": 36690 }, { "epoch": 3.05, "learning_rate": 3.5944683091760657e-06, "loss": 0.8563, "step": 36700 }, { "epoch": 3.05, "learning_rate": 3.5943574536485324e-06, "loss": 0.8073, "step": 36710 }, { "epoch": 3.05, "learning_rate": 3.5942465981209987e-06, "loss": 0.8416, "step": 36720 }, { "epoch": 3.05, "learning_rate": 3.594135742593465e-06, "loss": 0.7751, "step": 36730 }, { "epoch": 3.05, "learning_rate": 3.5940248870659313e-06, "loss": 0.8387, "step": 36740 }, { "epoch": 3.05, "learning_rate": 3.593914031538397e-06, "loss": 0.8839, "step": 36750 }, { "epoch": 3.06, "learning_rate": 3.593803176010864e-06, "loss": 0.7863, "step": 36760 }, { "epoch": 3.06, "learning_rate": 3.59369232048333e-06, "loss": 0.7699, "step": 36770 }, { "epoch": 3.06, "learning_rate": 3.593581464955796e-06, "loss": 0.8255, "step": 36780 }, { "epoch": 3.06, "learning_rate": 3.5934706094282624e-06, "loss": 0.8156, "step": 36790 }, { "epoch": 3.06, "learning_rate": 3.5933597539007287e-06, "loss": 0.9066, "step": 36800 }, { "epoch": 3.06, "learning_rate": 3.593248898373195e-06, "loss": 0.8756, "step": 36810 }, { "epoch": 3.06, "learning_rate": 3.5931380428456613e-06, "loss": 0.8144, "step": 36820 }, { "epoch": 3.06, "learning_rate": 3.5930271873181276e-06, "loss": 0.7954, "step": 36830 }, { "epoch": 3.06, "learning_rate": 3.592916331790594e-06, "loss": 0.8027, "step": 36840 }, { "epoch": 3.06, "learning_rate": 3.59280547626306e-06, "loss": 0.8945, "step": 36850 }, { "epoch": 3.06, "learning_rate": 3.592694620735526e-06, "loss": 0.9149, "step": 36860 }, { "epoch": 3.06, "learning_rate": 3.5925837652079928e-06, "loss": 0.8584, "step": 36870 }, { "epoch": 3.07, "learning_rate": 3.5924729096804586e-06, "loss": 0.8441, "step": 36880 }, { "epoch": 3.07, "learning_rate": 3.5923620541529253e-06, "loss": 0.8707, "step": 36890 }, { "epoch": 3.07, "learning_rate": 3.5922511986253912e-06, "loss": 0.8303, "step": 36900 }, { "epoch": 3.07, "learning_rate": 3.5921403430978575e-06, "loss": 0.8405, "step": 36910 }, { "epoch": 3.07, "learning_rate": 3.592029487570324e-06, "loss": 0.8641, "step": 36920 }, { "epoch": 3.07, "learning_rate": 3.59191863204279e-06, "loss": 0.8819, "step": 36930 }, { "epoch": 3.07, "learning_rate": 3.591807776515256e-06, "loss": 0.8014, "step": 36940 }, { "epoch": 3.07, "learning_rate": 3.5916969209877227e-06, "loss": 0.86, "step": 36950 }, { "epoch": 3.07, "learning_rate": 3.591586065460189e-06, "loss": 0.7897, "step": 36960 }, { "epoch": 3.07, "learning_rate": 3.5914752099326553e-06, "loss": 0.8315, "step": 36970 }, { "epoch": 3.07, "learning_rate": 3.5913643544051216e-06, "loss": 0.7662, "step": 36980 }, { "epoch": 3.07, "learning_rate": 3.5912534988775874e-06, "loss": 0.8285, "step": 36990 }, { "epoch": 3.08, "learning_rate": 3.591142643350054e-06, "loss": 0.8265, "step": 37000 }, { "epoch": 3.08, "learning_rate": 3.59103178782252e-06, "loss": 0.821, "step": 37010 }, { "epoch": 3.08, "learning_rate": 3.5909209322949863e-06, "loss": 0.8034, "step": 37020 }, { "epoch": 3.08, "learning_rate": 3.5908100767674526e-06, "loss": 0.7631, "step": 37030 }, { "epoch": 3.08, "learning_rate": 3.590699221239919e-06, "loss": 0.8444, "step": 37040 }, { "epoch": 3.08, "learning_rate": 3.590588365712385e-06, "loss": 0.8642, "step": 37050 }, { "epoch": 3.08, "learning_rate": 3.5904775101848515e-06, "loss": 0.8895, "step": 37060 }, { "epoch": 3.08, "learning_rate": 3.5903666546573174e-06, "loss": 0.9063, "step": 37070 }, { "epoch": 3.08, "learning_rate": 3.590255799129784e-06, "loss": 0.7455, "step": 37080 }, { "epoch": 3.08, "learning_rate": 3.5901449436022504e-06, "loss": 0.8303, "step": 37090 }, { "epoch": 3.08, "learning_rate": 3.5900340880747163e-06, "loss": 0.8482, "step": 37100 }, { "epoch": 3.08, "learning_rate": 3.589923232547183e-06, "loss": 0.8236, "step": 37110 }, { "epoch": 3.09, "learning_rate": 3.589812377019649e-06, "loss": 0.8598, "step": 37120 }, { "epoch": 3.09, "learning_rate": 3.589701521492115e-06, "loss": 0.7598, "step": 37130 }, { "epoch": 3.09, "learning_rate": 3.5895906659645815e-06, "loss": 0.8647, "step": 37140 }, { "epoch": 3.09, "learning_rate": 3.5894798104370477e-06, "loss": 0.8832, "step": 37150 }, { "epoch": 3.09, "learning_rate": 3.589368954909514e-06, "loss": 0.7762, "step": 37160 }, { "epoch": 3.09, "learning_rate": 3.5892580993819803e-06, "loss": 0.8474, "step": 37170 }, { "epoch": 3.09, "learning_rate": 3.5891472438544462e-06, "loss": 0.8315, "step": 37180 }, { "epoch": 3.09, "learning_rate": 3.589036388326913e-06, "loss": 0.8063, "step": 37190 }, { "epoch": 3.09, "learning_rate": 3.5889255327993792e-06, "loss": 0.8219, "step": 37200 }, { "epoch": 3.09, "learning_rate": 3.588814677271845e-06, "loss": 0.8275, "step": 37210 }, { "epoch": 3.09, "learning_rate": 3.588703821744312e-06, "loss": 0.8298, "step": 37220 }, { "epoch": 3.09, "learning_rate": 3.5885929662167777e-06, "loss": 0.8657, "step": 37230 }, { "epoch": 3.1, "learning_rate": 3.5884821106892444e-06, "loss": 0.8231, "step": 37240 }, { "epoch": 3.1, "learning_rate": 3.5883712551617103e-06, "loss": 0.9208, "step": 37250 }, { "epoch": 3.1, "learning_rate": 3.5882603996341766e-06, "loss": 0.8161, "step": 37260 }, { "epoch": 3.1, "learning_rate": 3.588149544106643e-06, "loss": 0.8876, "step": 37270 }, { "epoch": 3.1, "learning_rate": 3.588038688579109e-06, "loss": 0.8405, "step": 37280 }, { "epoch": 3.1, "learning_rate": 3.587927833051575e-06, "loss": 0.8142, "step": 37290 }, { "epoch": 3.1, "learning_rate": 3.5878169775240418e-06, "loss": 0.8206, "step": 37300 }, { "epoch": 3.1, "learning_rate": 3.5877061219965076e-06, "loss": 0.8792, "step": 37310 }, { "epoch": 3.1, "learning_rate": 3.5875952664689743e-06, "loss": 0.8709, "step": 37320 }, { "epoch": 3.1, "learning_rate": 3.5874844109414406e-06, "loss": 0.7925, "step": 37330 }, { "epoch": 3.1, "learning_rate": 3.5873735554139065e-06, "loss": 0.8655, "step": 37340 }, { "epoch": 3.1, "learning_rate": 3.5872626998863732e-06, "loss": 0.857, "step": 37350 }, { "epoch": 3.11, "learning_rate": 3.587151844358839e-06, "loss": 0.8222, "step": 37360 }, { "epoch": 3.11, "learning_rate": 3.5870409888313054e-06, "loss": 0.8343, "step": 37370 }, { "epoch": 3.11, "learning_rate": 3.5869301333037717e-06, "loss": 0.7994, "step": 37380 }, { "epoch": 3.11, "learning_rate": 3.586819277776238e-06, "loss": 0.7871, "step": 37390 }, { "epoch": 3.11, "learning_rate": 3.586708422248704e-06, "loss": 0.901, "step": 37400 }, { "epoch": 3.11, "learning_rate": 3.5865975667211706e-06, "loss": 0.7548, "step": 37410 }, { "epoch": 3.11, "learning_rate": 3.5864867111936365e-06, "loss": 0.8212, "step": 37420 }, { "epoch": 3.11, "learning_rate": 3.586375855666103e-06, "loss": 0.8793, "step": 37430 }, { "epoch": 3.11, "learning_rate": 3.586265000138569e-06, "loss": 0.7931, "step": 37440 }, { "epoch": 3.11, "learning_rate": 3.5861541446110353e-06, "loss": 0.8788, "step": 37450 }, { "epoch": 3.11, "learning_rate": 3.586043289083502e-06, "loss": 0.8742, "step": 37460 }, { "epoch": 3.11, "learning_rate": 3.585932433555968e-06, "loss": 0.8181, "step": 37470 }, { "epoch": 3.12, "learning_rate": 3.5858215780284342e-06, "loss": 0.8087, "step": 37480 }, { "epoch": 3.12, "learning_rate": 3.5857107225009005e-06, "loss": 0.8092, "step": 37490 }, { "epoch": 3.12, "learning_rate": 3.585599866973367e-06, "loss": 0.9027, "step": 37500 }, { "epoch": 3.12, "learning_rate": 3.585489011445833e-06, "loss": 0.787, "step": 37510 }, { "epoch": 3.12, "learning_rate": 3.5853781559182994e-06, "loss": 0.8439, "step": 37520 }, { "epoch": 3.12, "learning_rate": 3.5852673003907653e-06, "loss": 0.8307, "step": 37530 }, { "epoch": 3.12, "learning_rate": 3.585156444863232e-06, "loss": 0.7768, "step": 37540 }, { "epoch": 3.12, "learning_rate": 3.585045589335698e-06, "loss": 0.911, "step": 37550 }, { "epoch": 3.12, "learning_rate": 3.584934733808164e-06, "loss": 0.812, "step": 37560 }, { "epoch": 3.12, "learning_rate": 3.584823878280631e-06, "loss": 0.8015, "step": 37570 }, { "epoch": 3.12, "learning_rate": 3.5847130227530968e-06, "loss": 0.817, "step": 37580 }, { "epoch": 3.12, "learning_rate": 3.5846021672255635e-06, "loss": 0.865, "step": 37590 }, { "epoch": 3.13, "learning_rate": 3.5844913116980293e-06, "loss": 0.8161, "step": 37600 }, { "epoch": 3.13, "learning_rate": 3.5843804561704956e-06, "loss": 0.8149, "step": 37610 }, { "epoch": 3.13, "learning_rate": 3.584269600642962e-06, "loss": 0.8671, "step": 37620 }, { "epoch": 3.13, "learning_rate": 3.5841587451154282e-06, "loss": 0.7865, "step": 37630 }, { "epoch": 3.13, "learning_rate": 3.584047889587894e-06, "loss": 0.7848, "step": 37640 }, { "epoch": 3.13, "learning_rate": 3.583937034060361e-06, "loss": 0.9167, "step": 37650 }, { "epoch": 3.13, "learning_rate": 3.5838261785328267e-06, "loss": 0.8492, "step": 37660 }, { "epoch": 3.13, "learning_rate": 3.5837153230052934e-06, "loss": 0.8074, "step": 37670 }, { "epoch": 3.13, "learning_rate": 3.5836044674777593e-06, "loss": 0.7943, "step": 37680 }, { "epoch": 3.13, "learning_rate": 3.5834936119502256e-06, "loss": 0.7651, "step": 37690 }, { "epoch": 3.13, "learning_rate": 3.5833827564226923e-06, "loss": 0.8652, "step": 37700 }, { "epoch": 3.13, "learning_rate": 3.583271900895158e-06, "loss": 0.8734, "step": 37710 }, { "epoch": 3.14, "learning_rate": 3.5831610453676245e-06, "loss": 0.8117, "step": 37720 }, { "epoch": 3.14, "learning_rate": 3.5830501898400908e-06, "loss": 0.8195, "step": 37730 }, { "epoch": 3.14, "learning_rate": 3.582939334312557e-06, "loss": 0.8437, "step": 37740 }, { "epoch": 3.14, "learning_rate": 3.5828284787850234e-06, "loss": 0.8664, "step": 37750 }, { "epoch": 3.14, "learning_rate": 3.5827176232574896e-06, "loss": 0.8276, "step": 37760 }, { "epoch": 3.14, "learning_rate": 3.5826067677299555e-06, "loss": 0.8497, "step": 37770 }, { "epoch": 3.14, "learning_rate": 3.5824959122024222e-06, "loss": 0.7975, "step": 37780 }, { "epoch": 3.14, "learning_rate": 3.582385056674888e-06, "loss": 0.8134, "step": 37790 }, { "epoch": 3.14, "learning_rate": 3.5822742011473544e-06, "loss": 0.7998, "step": 37800 }, { "epoch": 3.14, "learning_rate": 3.5821633456198207e-06, "loss": 0.7811, "step": 37810 }, { "epoch": 3.14, "learning_rate": 3.582052490092287e-06, "loss": 0.83, "step": 37820 }, { "epoch": 3.14, "learning_rate": 3.5819416345647537e-06, "loss": 0.8771, "step": 37830 }, { "epoch": 3.15, "learning_rate": 3.5818307790372196e-06, "loss": 0.8234, "step": 37840 }, { "epoch": 3.15, "learning_rate": 3.581719923509686e-06, "loss": 0.8698, "step": 37850 }, { "epoch": 3.15, "learning_rate": 3.581609067982152e-06, "loss": 0.8367, "step": 37860 }, { "epoch": 3.15, "learning_rate": 3.5814982124546185e-06, "loss": 0.8615, "step": 37870 }, { "epoch": 3.15, "learning_rate": 3.5813873569270843e-06, "loss": 0.7583, "step": 37880 }, { "epoch": 3.15, "learning_rate": 3.581276501399551e-06, "loss": 0.7991, "step": 37890 }, { "epoch": 3.15, "learning_rate": 3.581165645872017e-06, "loss": 0.8724, "step": 37900 }, { "epoch": 3.15, "learning_rate": 3.5810547903444832e-06, "loss": 0.8667, "step": 37910 }, { "epoch": 3.15, "learning_rate": 3.5809439348169495e-06, "loss": 0.8009, "step": 37920 }, { "epoch": 3.15, "learning_rate": 3.580833079289416e-06, "loss": 0.8485, "step": 37930 }, { "epoch": 3.15, "learning_rate": 3.5807222237618825e-06, "loss": 0.823, "step": 37940 }, { "epoch": 3.15, "learning_rate": 3.5806113682343484e-06, "loss": 0.8273, "step": 37950 }, { "epoch": 3.16, "learning_rate": 3.5805005127068147e-06, "loss": 0.7804, "step": 37960 }, { "epoch": 3.16, "learning_rate": 3.580389657179281e-06, "loss": 0.8403, "step": 37970 }, { "epoch": 3.16, "learning_rate": 3.5802788016517473e-06, "loss": 0.8837, "step": 37980 }, { "epoch": 3.16, "learning_rate": 3.580167946124213e-06, "loss": 0.8314, "step": 37990 }, { "epoch": 3.16, "learning_rate": 3.58005709059668e-06, "loss": 0.8527, "step": 38000 }, { "epoch": 3.16, "learning_rate": 3.5799462350691458e-06, "loss": 0.8167, "step": 38010 }, { "epoch": 3.16, "learning_rate": 3.5798353795416125e-06, "loss": 0.8598, "step": 38020 }, { "epoch": 3.16, "learning_rate": 3.5797245240140784e-06, "loss": 0.8245, "step": 38030 }, { "epoch": 3.16, "learning_rate": 3.5796136684865446e-06, "loss": 0.898, "step": 38040 }, { "epoch": 3.16, "learning_rate": 3.579502812959011e-06, "loss": 0.8818, "step": 38050 }, { "epoch": 3.16, "learning_rate": 3.5793919574314772e-06, "loss": 0.747, "step": 38060 }, { "epoch": 3.16, "learning_rate": 3.5792811019039435e-06, "loss": 0.8165, "step": 38070 }, { "epoch": 3.17, "learning_rate": 3.57917024637641e-06, "loss": 0.8228, "step": 38080 }, { "epoch": 3.17, "learning_rate": 3.579059390848876e-06, "loss": 0.7039, "step": 38090 }, { "epoch": 3.17, "learning_rate": 3.5789485353213424e-06, "loss": 0.8491, "step": 38100 }, { "epoch": 3.17, "learning_rate": 3.5788376797938087e-06, "loss": 0.8522, "step": 38110 }, { "epoch": 3.17, "learning_rate": 3.5787268242662746e-06, "loss": 0.8221, "step": 38120 }, { "epoch": 3.17, "learning_rate": 3.5786159687387413e-06, "loss": 0.8204, "step": 38130 }, { "epoch": 3.17, "learning_rate": 3.578505113211207e-06, "loss": 0.875, "step": 38140 }, { "epoch": 3.17, "learning_rate": 3.5783942576836735e-06, "loss": 0.8609, "step": 38150 }, { "epoch": 3.17, "learning_rate": 3.5782834021561398e-06, "loss": 0.8642, "step": 38160 }, { "epoch": 3.17, "learning_rate": 3.578172546628606e-06, "loss": 0.8138, "step": 38170 }, { "epoch": 3.17, "learning_rate": 3.578061691101072e-06, "loss": 0.8487, "step": 38180 }, { "epoch": 3.17, "learning_rate": 3.5779508355735387e-06, "loss": 0.8244, "step": 38190 }, { "epoch": 3.18, "learning_rate": 3.577839980046005e-06, "loss": 0.8034, "step": 38200 }, { "epoch": 3.18, "learning_rate": 3.5777291245184712e-06, "loss": 0.79, "step": 38210 }, { "epoch": 3.18, "learning_rate": 3.5776182689909375e-06, "loss": 0.7789, "step": 38220 }, { "epoch": 3.18, "learning_rate": 3.5775074134634034e-06, "loss": 0.8003, "step": 38230 }, { "epoch": 3.18, "learning_rate": 3.57739655793587e-06, "loss": 0.8254, "step": 38240 }, { "epoch": 3.18, "learning_rate": 3.577285702408336e-06, "loss": 0.8617, "step": 38250 }, { "epoch": 3.18, "learning_rate": 3.5771748468808027e-06, "loss": 0.8541, "step": 38260 }, { "epoch": 3.18, "learning_rate": 3.5770639913532686e-06, "loss": 0.8098, "step": 38270 }, { "epoch": 3.18, "learning_rate": 3.576953135825735e-06, "loss": 0.7645, "step": 38280 }, { "epoch": 3.18, "learning_rate": 3.576842280298201e-06, "loss": 0.8398, "step": 38290 }, { "epoch": 3.18, "learning_rate": 3.5767314247706675e-06, "loss": 0.8524, "step": 38300 }, { "epoch": 3.18, "learning_rate": 3.5766205692431338e-06, "loss": 0.7975, "step": 38310 }, { "epoch": 3.19, "learning_rate": 3.5765097137156e-06, "loss": 0.7983, "step": 38320 }, { "epoch": 3.19, "learning_rate": 3.5763988581880664e-06, "loss": 0.9241, "step": 38330 }, { "epoch": 3.19, "learning_rate": 3.5762880026605322e-06, "loss": 0.8889, "step": 38340 }, { "epoch": 3.19, "learning_rate": 3.576177147132999e-06, "loss": 0.8902, "step": 38350 }, { "epoch": 3.19, "learning_rate": 3.576066291605465e-06, "loss": 0.8022, "step": 38360 }, { "epoch": 3.19, "learning_rate": 3.5759554360779315e-06, "loss": 0.8811, "step": 38370 }, { "epoch": 3.19, "learning_rate": 3.5758445805503974e-06, "loss": 0.8023, "step": 38380 }, { "epoch": 3.19, "learning_rate": 3.5757337250228637e-06, "loss": 0.8546, "step": 38390 }, { "epoch": 3.19, "learning_rate": 3.57562286949533e-06, "loss": 0.8759, "step": 38400 }, { "epoch": 3.19, "learning_rate": 3.5755120139677963e-06, "loss": 0.8156, "step": 38410 }, { "epoch": 3.19, "learning_rate": 3.575401158440262e-06, "loss": 0.8558, "step": 38420 }, { "epoch": 3.19, "learning_rate": 3.575290302912729e-06, "loss": 0.7983, "step": 38430 }, { "epoch": 3.2, "learning_rate": 3.575179447385195e-06, "loss": 0.8404, "step": 38440 }, { "epoch": 3.2, "learning_rate": 3.5750685918576615e-06, "loss": 0.837, "step": 38450 }, { "epoch": 3.2, "learning_rate": 3.5749577363301278e-06, "loss": 0.7721, "step": 38460 }, { "epoch": 3.2, "learning_rate": 3.5748468808025937e-06, "loss": 0.7971, "step": 38470 }, { "epoch": 3.2, "learning_rate": 3.5747360252750604e-06, "loss": 0.8692, "step": 38480 }, { "epoch": 3.2, "learning_rate": 3.5746251697475262e-06, "loss": 0.855, "step": 38490 }, { "epoch": 3.2, "learning_rate": 3.5745143142199925e-06, "loss": 0.9186, "step": 38500 }, { "epoch": 3.2, "learning_rate": 3.574403458692459e-06, "loss": 0.8104, "step": 38510 }, { "epoch": 3.2, "learning_rate": 3.574292603164925e-06, "loss": 0.7858, "step": 38520 }, { "epoch": 3.2, "learning_rate": 3.5741817476373914e-06, "loss": 0.8133, "step": 38530 }, { "epoch": 3.2, "learning_rate": 3.5740708921098577e-06, "loss": 0.802, "step": 38540 }, { "epoch": 3.2, "learning_rate": 3.573960036582324e-06, "loss": 0.8455, "step": 38550 }, { "epoch": 3.21, "learning_rate": 3.5738491810547903e-06, "loss": 0.808, "step": 38560 }, { "epoch": 3.21, "learning_rate": 3.5737383255272566e-06, "loss": 0.84, "step": 38570 }, { "epoch": 3.21, "learning_rate": 3.5736274699997225e-06, "loss": 0.8191, "step": 38580 }, { "epoch": 3.21, "learning_rate": 3.573516614472189e-06, "loss": 0.8406, "step": 38590 }, { "epoch": 3.21, "learning_rate": 3.573405758944655e-06, "loss": 0.8772, "step": 38600 }, { "epoch": 3.21, "learning_rate": 3.5732949034171218e-06, "loss": 0.7916, "step": 38610 }, { "epoch": 3.21, "learning_rate": 3.5731840478895877e-06, "loss": 0.8582, "step": 38620 }, { "epoch": 3.21, "learning_rate": 3.573073192362054e-06, "loss": 0.8913, "step": 38630 }, { "epoch": 3.21, "learning_rate": 3.5729623368345202e-06, "loss": 0.7771, "step": 38640 }, { "epoch": 3.21, "learning_rate": 3.5728514813069865e-06, "loss": 0.8839, "step": 38650 }, { "epoch": 3.21, "learning_rate": 3.5727406257794524e-06, "loss": 0.8392, "step": 38660 }, { "epoch": 3.21, "learning_rate": 3.572629770251919e-06, "loss": 0.7777, "step": 38670 }, { "epoch": 3.22, "learning_rate": 3.5725189147243854e-06, "loss": 0.8642, "step": 38680 }, { "epoch": 3.22, "learning_rate": 3.5724080591968513e-06, "loss": 0.8689, "step": 38690 }, { "epoch": 3.22, "learning_rate": 3.572297203669318e-06, "loss": 0.8941, "step": 38700 }, { "epoch": 3.22, "learning_rate": 3.572186348141784e-06, "loss": 0.7847, "step": 38710 }, { "epoch": 3.22, "learning_rate": 3.5720754926142506e-06, "loss": 0.8129, "step": 38720 }, { "epoch": 3.22, "learning_rate": 3.5719646370867165e-06, "loss": 0.7883, "step": 38730 }, { "epoch": 3.22, "learning_rate": 3.5718537815591828e-06, "loss": 0.8781, "step": 38740 }, { "epoch": 3.22, "learning_rate": 3.571742926031649e-06, "loss": 0.8905, "step": 38750 }, { "epoch": 3.22, "learning_rate": 3.5716320705041154e-06, "loss": 0.8228, "step": 38760 }, { "epoch": 3.22, "learning_rate": 3.5715212149765812e-06, "loss": 0.8439, "step": 38770 }, { "epoch": 3.22, "learning_rate": 3.571410359449048e-06, "loss": 0.803, "step": 38780 }, { "epoch": 3.22, "learning_rate": 3.571299503921514e-06, "loss": 0.8385, "step": 38790 }, { "epoch": 3.23, "learning_rate": 3.5711886483939806e-06, "loss": 0.8781, "step": 38800 }, { "epoch": 3.23, "learning_rate": 3.571077792866447e-06, "loss": 0.7655, "step": 38810 }, { "epoch": 3.23, "learning_rate": 3.5709669373389127e-06, "loss": 0.8605, "step": 38820 }, { "epoch": 3.23, "learning_rate": 3.5708560818113794e-06, "loss": 0.816, "step": 38830 }, { "epoch": 3.23, "learning_rate": 3.5707452262838453e-06, "loss": 0.8211, "step": 38840 }, { "epoch": 3.23, "learning_rate": 3.5706343707563116e-06, "loss": 0.8085, "step": 38850 }, { "epoch": 3.23, "learning_rate": 3.570523515228778e-06, "loss": 0.8467, "step": 38860 }, { "epoch": 3.23, "learning_rate": 3.570412659701244e-06, "loss": 0.8095, "step": 38870 }, { "epoch": 3.23, "learning_rate": 3.5703018041737105e-06, "loss": 0.8066, "step": 38880 }, { "epoch": 3.23, "learning_rate": 3.5701909486461768e-06, "loss": 0.7988, "step": 38890 }, { "epoch": 3.23, "learning_rate": 3.5700800931186427e-06, "loss": 0.8077, "step": 38900 }, { "epoch": 3.23, "learning_rate": 3.5699692375911094e-06, "loss": 0.8506, "step": 38910 }, { "epoch": 3.23, "learning_rate": 3.5698583820635757e-06, "loss": 0.8172, "step": 38920 }, { "epoch": 3.24, "learning_rate": 3.5697475265360415e-06, "loss": 0.8506, "step": 38930 }, { "epoch": 3.24, "learning_rate": 3.5696366710085083e-06, "loss": 0.832, "step": 38940 }, { "epoch": 3.24, "learning_rate": 3.569525815480974e-06, "loss": 0.783, "step": 38950 }, { "epoch": 3.24, "learning_rate": 3.569414959953441e-06, "loss": 0.8592, "step": 38960 }, { "epoch": 3.24, "learning_rate": 3.5693041044259067e-06, "loss": 0.8055, "step": 38970 }, { "epoch": 3.24, "learning_rate": 3.569193248898373e-06, "loss": 0.8513, "step": 38980 }, { "epoch": 3.24, "learning_rate": 3.5690823933708393e-06, "loss": 0.8607, "step": 38990 }, { "epoch": 3.24, "learning_rate": 3.5689715378433056e-06, "loss": 0.8849, "step": 39000 }, { "epoch": 3.24, "learning_rate": 3.5688606823157715e-06, "loss": 0.8793, "step": 39010 }, { "epoch": 3.24, "learning_rate": 3.5687609123409914e-06, "loss": 0.855, "step": 39020 }, { "epoch": 3.24, "learning_rate": 3.5686500568134577e-06, "loss": 0.8632, "step": 39030 }, { "epoch": 3.24, "learning_rate": 3.568539201285924e-06, "loss": 0.8431, "step": 39040 }, { "epoch": 3.25, "learning_rate": 3.5684283457583903e-06, "loss": 0.8558, "step": 39050 }, { "epoch": 3.25, "learning_rate": 3.5683174902308566e-06, "loss": 0.8424, "step": 39060 }, { "epoch": 3.25, "learning_rate": 3.5682066347033225e-06, "loss": 0.804, "step": 39070 }, { "epoch": 3.25, "learning_rate": 3.5680957791757892e-06, "loss": 0.793, "step": 39080 }, { "epoch": 3.25, "learning_rate": 3.567984923648255e-06, "loss": 0.76, "step": 39090 }, { "epoch": 3.25, "learning_rate": 3.5678740681207214e-06, "loss": 0.8081, "step": 39100 }, { "epoch": 3.25, "learning_rate": 3.5677632125931877e-06, "loss": 0.8986, "step": 39110 }, { "epoch": 3.25, "learning_rate": 3.567652357065654e-06, "loss": 0.8032, "step": 39120 }, { "epoch": 3.25, "learning_rate": 3.5675415015381207e-06, "loss": 0.8556, "step": 39130 }, { "epoch": 3.25, "learning_rate": 3.5674306460105866e-06, "loss": 0.8427, "step": 39140 }, { "epoch": 3.25, "learning_rate": 3.567319790483053e-06, "loss": 0.9033, "step": 39150 }, { "epoch": 3.25, "learning_rate": 3.567208934955519e-06, "loss": 0.8578, "step": 39160 }, { "epoch": 3.26, "learning_rate": 3.5670980794279855e-06, "loss": 0.8837, "step": 39170 }, { "epoch": 3.26, "learning_rate": 3.5669872239004513e-06, "loss": 0.7847, "step": 39180 }, { "epoch": 3.26, "learning_rate": 3.566876368372918e-06, "loss": 0.8107, "step": 39190 }, { "epoch": 3.26, "learning_rate": 3.566765512845384e-06, "loss": 0.8513, "step": 39200 }, { "epoch": 3.26, "learning_rate": 3.5666546573178506e-06, "loss": 0.7501, "step": 39210 }, { "epoch": 3.26, "learning_rate": 3.5665438017903165e-06, "loss": 0.8229, "step": 39220 }, { "epoch": 3.26, "learning_rate": 3.566432946262783e-06, "loss": 0.8077, "step": 39230 }, { "epoch": 3.26, "learning_rate": 3.566322090735249e-06, "loss": 0.8216, "step": 39240 }, { "epoch": 3.26, "learning_rate": 3.5662112352077154e-06, "loss": 0.8331, "step": 39250 }, { "epoch": 3.26, "learning_rate": 3.5661003796801817e-06, "loss": 0.821, "step": 39260 }, { "epoch": 3.26, "learning_rate": 3.565989524152648e-06, "loss": 0.8301, "step": 39270 }, { "epoch": 3.26, "learning_rate": 3.5658786686251143e-06, "loss": 0.8133, "step": 39280 }, { "epoch": 3.27, "learning_rate": 3.56576781309758e-06, "loss": 0.8705, "step": 39290 }, { "epoch": 3.27, "learning_rate": 3.565656957570047e-06, "loss": 0.9284, "step": 39300 }, { "epoch": 3.27, "learning_rate": 3.5655461020425127e-06, "loss": 0.8499, "step": 39310 }, { "epoch": 3.27, "learning_rate": 3.5654352465149795e-06, "loss": 0.7594, "step": 39320 }, { "epoch": 3.27, "learning_rate": 3.5653243909874453e-06, "loss": 0.8438, "step": 39330 }, { "epoch": 3.27, "learning_rate": 3.5652135354599116e-06, "loss": 0.8456, "step": 39340 }, { "epoch": 3.27, "learning_rate": 3.565102679932378e-06, "loss": 0.9325, "step": 39350 }, { "epoch": 3.27, "learning_rate": 3.5649918244048442e-06, "loss": 0.7659, "step": 39360 }, { "epoch": 3.27, "learning_rate": 3.56488096887731e-06, "loss": 0.7954, "step": 39370 }, { "epoch": 3.27, "learning_rate": 3.564770113349777e-06, "loss": 0.7727, "step": 39380 }, { "epoch": 3.27, "learning_rate": 3.564659257822243e-06, "loss": 0.8472, "step": 39390 }, { "epoch": 3.27, "learning_rate": 3.5645484022947094e-06, "loss": 0.848, "step": 39400 }, { "epoch": 3.28, "learning_rate": 3.5644375467671757e-06, "loss": 0.851, "step": 39410 }, { "epoch": 3.28, "learning_rate": 3.5643266912396416e-06, "loss": 0.8818, "step": 39420 }, { "epoch": 3.28, "learning_rate": 3.5642158357121083e-06, "loss": 0.8273, "step": 39430 }, { "epoch": 3.28, "learning_rate": 3.564104980184574e-06, "loss": 0.8234, "step": 39440 }, { "epoch": 3.28, "learning_rate": 3.5639941246570405e-06, "loss": 0.839, "step": 39450 }, { "epoch": 3.28, "learning_rate": 3.5638832691295067e-06, "loss": 0.8346, "step": 39460 }, { "epoch": 3.28, "learning_rate": 3.563772413601973e-06, "loss": 0.7455, "step": 39470 }, { "epoch": 3.28, "learning_rate": 3.5636615580744393e-06, "loss": 0.79, "step": 39480 }, { "epoch": 3.28, "learning_rate": 3.5635507025469056e-06, "loss": 0.7544, "step": 39490 }, { "epoch": 3.28, "learning_rate": 3.563439847019372e-06, "loss": 0.8846, "step": 39500 }, { "epoch": 3.28, "learning_rate": 3.5633289914918382e-06, "loss": 0.7478, "step": 39510 }, { "epoch": 3.28, "learning_rate": 3.5632181359643045e-06, "loss": 0.7963, "step": 39520 }, { "epoch": 3.29, "learning_rate": 3.5631072804367704e-06, "loss": 0.7637, "step": 39530 }, { "epoch": 3.29, "learning_rate": 3.562996424909237e-06, "loss": 0.7798, "step": 39540 }, { "epoch": 3.29, "learning_rate": 3.562885569381703e-06, "loss": 0.9508, "step": 39550 }, { "epoch": 3.29, "learning_rate": 3.5627747138541697e-06, "loss": 0.8221, "step": 39560 }, { "epoch": 3.29, "learning_rate": 3.5626638583266356e-06, "loss": 0.8363, "step": 39570 }, { "epoch": 3.29, "learning_rate": 3.562553002799102e-06, "loss": 0.8339, "step": 39580 }, { "epoch": 3.29, "learning_rate": 3.562442147271568e-06, "loss": 0.8298, "step": 39590 }, { "epoch": 3.29, "learning_rate": 3.5623312917440345e-06, "loss": 0.8627, "step": 39600 }, { "epoch": 3.29, "learning_rate": 3.5622204362165003e-06, "loss": 0.8185, "step": 39610 }, { "epoch": 3.29, "learning_rate": 3.562109580688967e-06, "loss": 0.7664, "step": 39620 }, { "epoch": 3.29, "learning_rate": 3.5619987251614333e-06, "loss": 0.8217, "step": 39630 }, { "epoch": 3.29, "learning_rate": 3.5618878696338992e-06, "loss": 0.7838, "step": 39640 }, { "epoch": 3.3, "learning_rate": 3.561777014106366e-06, "loss": 0.8711, "step": 39650 }, { "epoch": 3.3, "learning_rate": 3.561666158578832e-06, "loss": 0.8462, "step": 39660 }, { "epoch": 3.3, "learning_rate": 3.5615553030512985e-06, "loss": 0.8278, "step": 39670 }, { "epoch": 3.3, "learning_rate": 3.5614444475237644e-06, "loss": 0.8351, "step": 39680 }, { "epoch": 3.3, "learning_rate": 3.5613335919962307e-06, "loss": 0.8684, "step": 39690 }, { "epoch": 3.3, "learning_rate": 3.561222736468697e-06, "loss": 0.8158, "step": 39700 }, { "epoch": 3.3, "learning_rate": 3.5611118809411633e-06, "loss": 0.8281, "step": 39710 }, { "epoch": 3.3, "learning_rate": 3.561001025413629e-06, "loss": 0.7991, "step": 39720 }, { "epoch": 3.3, "learning_rate": 3.560890169886096e-06, "loss": 0.755, "step": 39730 }, { "epoch": 3.3, "learning_rate": 3.5607793143585617e-06, "loss": 0.8285, "step": 39740 }, { "epoch": 3.3, "learning_rate": 3.5606684588310285e-06, "loss": 0.8536, "step": 39750 }, { "epoch": 3.3, "learning_rate": 3.5605576033034948e-06, "loss": 0.8476, "step": 39760 }, { "epoch": 3.31, "learning_rate": 3.5604467477759606e-06, "loss": 0.811, "step": 39770 }, { "epoch": 3.31, "learning_rate": 3.5603358922484273e-06, "loss": 0.7902, "step": 39780 }, { "epoch": 3.31, "learning_rate": 3.5602250367208932e-06, "loss": 0.8455, "step": 39790 }, { "epoch": 3.31, "learning_rate": 3.5601141811933595e-06, "loss": 0.891, "step": 39800 }, { "epoch": 3.31, "learning_rate": 3.560003325665826e-06, "loss": 0.8153, "step": 39810 }, { "epoch": 3.31, "learning_rate": 3.559892470138292e-06, "loss": 0.823, "step": 39820 }, { "epoch": 3.31, "learning_rate": 3.5597816146107584e-06, "loss": 0.8473, "step": 39830 }, { "epoch": 3.31, "learning_rate": 3.5596707590832247e-06, "loss": 0.8681, "step": 39840 }, { "epoch": 3.31, "learning_rate": 3.5595599035556906e-06, "loss": 0.8207, "step": 39850 }, { "epoch": 3.31, "learning_rate": 3.5594490480281573e-06, "loss": 0.8529, "step": 39860 }, { "epoch": 3.31, "learning_rate": 3.5593381925006236e-06, "loss": 0.839, "step": 39870 }, { "epoch": 3.31, "learning_rate": 3.5592273369730895e-06, "loss": 0.8214, "step": 39880 }, { "epoch": 3.32, "learning_rate": 3.559116481445556e-06, "loss": 0.821, "step": 39890 }, { "epoch": 3.32, "learning_rate": 3.559005625918022e-06, "loss": 0.8862, "step": 39900 }, { "epoch": 3.32, "learning_rate": 3.5588947703904888e-06, "loss": 0.8479, "step": 39910 }, { "epoch": 3.32, "learning_rate": 3.5587839148629546e-06, "loss": 0.8302, "step": 39920 }, { "epoch": 3.32, "learning_rate": 3.558673059335421e-06, "loss": 0.8435, "step": 39930 }, { "epoch": 3.32, "learning_rate": 3.5585622038078872e-06, "loss": 0.8901, "step": 39940 }, { "epoch": 3.32, "learning_rate": 3.5584513482803535e-06, "loss": 0.8444, "step": 39950 }, { "epoch": 3.32, "learning_rate": 3.5583404927528194e-06, "loss": 0.7436, "step": 39960 }, { "epoch": 3.32, "learning_rate": 3.558229637225286e-06, "loss": 0.8627, "step": 39970 }, { "epoch": 3.32, "learning_rate": 3.558118781697752e-06, "loss": 0.8073, "step": 39980 }, { "epoch": 3.32, "learning_rate": 3.5580079261702187e-06, "loss": 0.8284, "step": 39990 }, { "epoch": 3.32, "learning_rate": 3.557897070642685e-06, "loss": 0.9125, "step": 40000 }, { "epoch": 3.33, "learning_rate": 3.557786215115151e-06, "loss": 0.8647, "step": 40010 }, { "epoch": 3.33, "learning_rate": 3.5576753595876176e-06, "loss": 0.8062, "step": 40020 }, { "epoch": 3.33, "learning_rate": 3.5575645040600835e-06, "loss": 0.8172, "step": 40030 }, { "epoch": 3.33, "learning_rate": 3.5574536485325498e-06, "loss": 0.808, "step": 40040 }, { "epoch": 3.33, "learning_rate": 3.557342793005016e-06, "loss": 0.8445, "step": 40050 }, { "epoch": 3.33, "learning_rate": 3.5572319374774823e-06, "loss": 0.9065, "step": 40060 }, { "epoch": 3.33, "learning_rate": 3.5571210819499482e-06, "loss": 0.8285, "step": 40070 }, { "epoch": 3.33, "learning_rate": 3.557010226422415e-06, "loss": 0.7783, "step": 40080 }, { "epoch": 3.33, "learning_rate": 3.556899370894881e-06, "loss": 0.8763, "step": 40090 }, { "epoch": 3.33, "learning_rate": 3.5567885153673475e-06, "loss": 0.9366, "step": 40100 }, { "epoch": 3.33, "learning_rate": 3.5566776598398134e-06, "loss": 0.8681, "step": 40110 }, { "epoch": 3.33, "learning_rate": 3.5565668043122797e-06, "loss": 0.7965, "step": 40120 }, { "epoch": 3.34, "learning_rate": 3.5564559487847464e-06, "loss": 0.8971, "step": 40130 }, { "epoch": 3.34, "learning_rate": 3.5563450932572123e-06, "loss": 0.7921, "step": 40140 }, { "epoch": 3.34, "learning_rate": 3.5562342377296786e-06, "loss": 0.9086, "step": 40150 }, { "epoch": 3.34, "learning_rate": 3.556123382202145e-06, "loss": 0.8184, "step": 40160 }, { "epoch": 3.34, "learning_rate": 3.556012526674611e-06, "loss": 0.8307, "step": 40170 }, { "epoch": 3.34, "learning_rate": 3.5559016711470775e-06, "loss": 0.8375, "step": 40180 }, { "epoch": 3.34, "learning_rate": 3.5557908156195438e-06, "loss": 0.7858, "step": 40190 }, { "epoch": 3.34, "learning_rate": 3.5556799600920096e-06, "loss": 0.8926, "step": 40200 }, { "epoch": 3.34, "learning_rate": 3.5555691045644764e-06, "loss": 0.8591, "step": 40210 }, { "epoch": 3.34, "learning_rate": 3.5554582490369422e-06, "loss": 0.8127, "step": 40220 }, { "epoch": 3.34, "learning_rate": 3.5553473935094085e-06, "loss": 0.8575, "step": 40230 }, { "epoch": 3.34, "learning_rate": 3.5552365379818752e-06, "loss": 0.7686, "step": 40240 }, { "epoch": 3.35, "learning_rate": 3.555125682454341e-06, "loss": 0.8825, "step": 40250 }, { "epoch": 3.35, "learning_rate": 3.555014826926808e-06, "loss": 0.8808, "step": 40260 }, { "epoch": 3.35, "learning_rate": 3.5549039713992737e-06, "loss": 0.8792, "step": 40270 }, { "epoch": 3.35, "learning_rate": 3.55479311587174e-06, "loss": 0.7888, "step": 40280 }, { "epoch": 3.35, "learning_rate": 3.5546822603442063e-06, "loss": 0.8259, "step": 40290 }, { "epoch": 3.35, "learning_rate": 3.5545714048166726e-06, "loss": 0.8756, "step": 40300 }, { "epoch": 3.35, "learning_rate": 3.5544605492891385e-06, "loss": 0.8602, "step": 40310 }, { "epoch": 3.35, "learning_rate": 3.554349693761605e-06, "loss": 0.761, "step": 40320 }, { "epoch": 3.35, "learning_rate": 3.554238838234071e-06, "loss": 0.8097, "step": 40330 }, { "epoch": 3.35, "learning_rate": 3.5541279827065378e-06, "loss": 0.7519, "step": 40340 }, { "epoch": 3.35, "learning_rate": 3.5540171271790036e-06, "loss": 0.896, "step": 40350 }, { "epoch": 3.35, "learning_rate": 3.55390627165147e-06, "loss": 0.902, "step": 40360 }, { "epoch": 3.36, "learning_rate": 3.5537954161239367e-06, "loss": 0.7391, "step": 40370 }, { "epoch": 3.36, "learning_rate": 3.5536845605964025e-06, "loss": 0.864, "step": 40380 }, { "epoch": 3.36, "learning_rate": 3.553573705068869e-06, "loss": 0.8005, "step": 40390 }, { "epoch": 3.36, "learning_rate": 3.553462849541335e-06, "loss": 0.8507, "step": 40400 }, { "epoch": 3.36, "learning_rate": 3.5533519940138014e-06, "loss": 0.8654, "step": 40410 }, { "epoch": 3.36, "learning_rate": 3.5532411384862673e-06, "loss": 0.7859, "step": 40420 }, { "epoch": 3.36, "learning_rate": 3.553130282958734e-06, "loss": 0.821, "step": 40430 }, { "epoch": 3.36, "learning_rate": 3.5530194274312e-06, "loss": 0.8247, "step": 40440 }, { "epoch": 3.36, "learning_rate": 3.5529085719036666e-06, "loss": 0.817, "step": 40450 }, { "epoch": 3.36, "learning_rate": 3.5527977163761325e-06, "loss": 0.7222, "step": 40460 }, { "epoch": 3.36, "learning_rate": 3.5526868608485988e-06, "loss": 0.7786, "step": 40470 }, { "epoch": 3.36, "learning_rate": 3.552576005321065e-06, "loss": 0.8566, "step": 40480 }, { "epoch": 3.37, "learning_rate": 3.5524651497935314e-06, "loss": 0.7884, "step": 40490 }, { "epoch": 3.37, "learning_rate": 3.552354294265998e-06, "loss": 0.8596, "step": 40500 }, { "epoch": 3.37, "learning_rate": 3.552243438738464e-06, "loss": 0.8199, "step": 40510 }, { "epoch": 3.37, "learning_rate": 3.5521325832109302e-06, "loss": 0.879, "step": 40520 }, { "epoch": 3.37, "learning_rate": 3.5520217276833965e-06, "loss": 0.8485, "step": 40530 }, { "epoch": 3.37, "learning_rate": 3.551910872155863e-06, "loss": 0.8501, "step": 40540 }, { "epoch": 3.37, "learning_rate": 3.5518000166283287e-06, "loss": 0.7944, "step": 40550 }, { "epoch": 3.37, "learning_rate": 3.5516891611007954e-06, "loss": 0.9077, "step": 40560 }, { "epoch": 3.37, "learning_rate": 3.5515783055732613e-06, "loss": 0.8149, "step": 40570 }, { "epoch": 3.37, "learning_rate": 3.5514674500457276e-06, "loss": 0.8078, "step": 40580 }, { "epoch": 3.37, "learning_rate": 3.551356594518194e-06, "loss": 0.7867, "step": 40590 }, { "epoch": 3.37, "learning_rate": 3.55124573899066e-06, "loss": 0.8914, "step": 40600 }, { "epoch": 3.38, "learning_rate": 3.551134883463127e-06, "loss": 0.851, "step": 40610 }, { "epoch": 3.38, "learning_rate": 3.5510240279355928e-06, "loss": 0.8044, "step": 40620 }, { "epoch": 3.38, "learning_rate": 3.550913172408059e-06, "loss": 0.859, "step": 40630 }, { "epoch": 3.38, "learning_rate": 3.5508023168805254e-06, "loss": 0.8565, "step": 40640 }, { "epoch": 3.38, "learning_rate": 3.5506914613529917e-06, "loss": 0.8813, "step": 40650 }, { "epoch": 3.38, "learning_rate": 3.5505806058254575e-06, "loss": 0.855, "step": 40660 }, { "epoch": 3.38, "learning_rate": 3.5504697502979242e-06, "loss": 0.7911, "step": 40670 }, { "epoch": 3.38, "learning_rate": 3.55035889477039e-06, "loss": 0.8461, "step": 40680 }, { "epoch": 3.38, "learning_rate": 3.550248039242857e-06, "loss": 0.792, "step": 40690 }, { "epoch": 3.38, "learning_rate": 3.5501371837153227e-06, "loss": 0.874, "step": 40700 }, { "epoch": 3.38, "learning_rate": 3.550026328187789e-06, "loss": 0.828, "step": 40710 }, { "epoch": 3.38, "learning_rate": 3.5499154726602553e-06, "loss": 0.8525, "step": 40720 }, { "epoch": 3.39, "learning_rate": 3.5498046171327216e-06, "loss": 0.7827, "step": 40730 }, { "epoch": 3.39, "learning_rate": 3.549693761605188e-06, "loss": 0.8314, "step": 40740 }, { "epoch": 3.39, "learning_rate": 3.549582906077654e-06, "loss": 0.8379, "step": 40750 }, { "epoch": 3.39, "learning_rate": 3.5494720505501205e-06, "loss": 0.7956, "step": 40760 }, { "epoch": 3.39, "learning_rate": 3.5493611950225868e-06, "loss": 0.805, "step": 40770 }, { "epoch": 3.39, "learning_rate": 3.549250339495053e-06, "loss": 0.7649, "step": 40780 }, { "epoch": 3.39, "learning_rate": 3.549139483967519e-06, "loss": 0.8203, "step": 40790 }, { "epoch": 3.39, "learning_rate": 3.5490286284399857e-06, "loss": 0.8583, "step": 40800 }, { "epoch": 3.39, "learning_rate": 3.5489177729124515e-06, "loss": 0.8281, "step": 40810 }, { "epoch": 3.39, "learning_rate": 3.548806917384918e-06, "loss": 0.7922, "step": 40820 }, { "epoch": 3.39, "learning_rate": 3.548696061857384e-06, "loss": 0.8629, "step": 40830 }, { "epoch": 3.39, "learning_rate": 3.5485852063298504e-06, "loss": 0.8758, "step": 40840 }, { "epoch": 3.4, "learning_rate": 3.548474350802317e-06, "loss": 0.8793, "step": 40850 }, { "epoch": 3.4, "learning_rate": 3.548363495274783e-06, "loss": 0.8924, "step": 40860 }, { "epoch": 3.4, "learning_rate": 3.5482526397472493e-06, "loss": 0.8148, "step": 40870 }, { "epoch": 3.4, "learning_rate": 3.5481417842197156e-06, "loss": 0.7841, "step": 40880 }, { "epoch": 3.4, "learning_rate": 3.548030928692182e-06, "loss": 0.8278, "step": 40890 }, { "epoch": 3.4, "learning_rate": 3.5479200731646478e-06, "loss": 0.8917, "step": 40900 }, { "epoch": 3.4, "learning_rate": 3.5478092176371145e-06, "loss": 0.7893, "step": 40910 }, { "epoch": 3.4, "learning_rate": 3.5476983621095804e-06, "loss": 0.761, "step": 40920 }, { "epoch": 3.4, "learning_rate": 3.5475875065820467e-06, "loss": 0.7997, "step": 40930 }, { "epoch": 3.4, "learning_rate": 3.547476651054513e-06, "loss": 0.7945, "step": 40940 }, { "epoch": 3.4, "learning_rate": 3.5473657955269792e-06, "loss": 0.8945, "step": 40950 }, { "epoch": 3.4, "learning_rate": 3.5472549399994455e-06, "loss": 0.7896, "step": 40960 }, { "epoch": 3.41, "learning_rate": 3.547144084471912e-06, "loss": 0.8376, "step": 40970 }, { "epoch": 3.41, "learning_rate": 3.547033228944378e-06, "loss": 0.8789, "step": 40980 }, { "epoch": 3.41, "learning_rate": 3.5469223734168444e-06, "loss": 0.849, "step": 40990 }, { "epoch": 3.41, "learning_rate": 3.5468115178893107e-06, "loss": 0.8452, "step": 41000 }, { "epoch": 3.41, "learning_rate": 3.5467006623617766e-06, "loss": 0.7514, "step": 41010 }, { "epoch": 3.41, "learning_rate": 3.5465898068342433e-06, "loss": 0.8417, "step": 41020 }, { "epoch": 3.41, "learning_rate": 3.546478951306709e-06, "loss": 0.8438, "step": 41030 }, { "epoch": 3.41, "learning_rate": 3.546368095779176e-06, "loss": 0.7828, "step": 41040 }, { "epoch": 3.41, "learning_rate": 3.5462572402516418e-06, "loss": 0.8781, "step": 41050 }, { "epoch": 3.41, "learning_rate": 3.546146384724108e-06, "loss": 0.7963, "step": 41060 }, { "epoch": 3.41, "learning_rate": 3.5460355291965744e-06, "loss": 0.8188, "step": 41070 }, { "epoch": 3.41, "learning_rate": 3.5459246736690407e-06, "loss": 0.8246, "step": 41080 }, { "epoch": 3.42, "learning_rate": 3.5458138181415065e-06, "loss": 0.8147, "step": 41090 }, { "epoch": 3.42, "learning_rate": 3.5457029626139733e-06, "loss": 0.8927, "step": 41100 }, { "epoch": 3.42, "learning_rate": 3.5455921070864395e-06, "loss": 0.8611, "step": 41110 }, { "epoch": 3.42, "learning_rate": 3.545481251558906e-06, "loss": 0.8043, "step": 41120 }, { "epoch": 3.42, "learning_rate": 3.545370396031372e-06, "loss": 0.8177, "step": 41130 }, { "epoch": 3.42, "learning_rate": 3.545259540503838e-06, "loss": 0.782, "step": 41140 }, { "epoch": 3.42, "learning_rate": 3.5451486849763047e-06, "loss": 0.8454, "step": 41150 }, { "epoch": 3.42, "learning_rate": 3.5450378294487706e-06, "loss": 0.9239, "step": 41160 }, { "epoch": 3.42, "learning_rate": 3.544926973921237e-06, "loss": 0.8718, "step": 41170 }, { "epoch": 3.42, "learning_rate": 3.544816118393703e-06, "loss": 0.875, "step": 41180 }, { "epoch": 3.42, "learning_rate": 3.5447052628661695e-06, "loss": 0.8457, "step": 41190 }, { "epoch": 3.42, "learning_rate": 3.5445944073386358e-06, "loss": 0.8373, "step": 41200 }, { "epoch": 3.43, "learning_rate": 3.544483551811102e-06, "loss": 0.8356, "step": 41210 }, { "epoch": 3.43, "learning_rate": 3.5443726962835684e-06, "loss": 0.8234, "step": 41220 }, { "epoch": 3.43, "learning_rate": 3.5442618407560347e-06, "loss": 0.841, "step": 41230 }, { "epoch": 3.43, "learning_rate": 3.544150985228501e-06, "loss": 0.8204, "step": 41240 }, { "epoch": 3.43, "learning_rate": 3.544040129700967e-06, "loss": 0.8524, "step": 41250 }, { "epoch": 3.43, "learning_rate": 3.5439292741734336e-06, "loss": 0.8631, "step": 41260 }, { "epoch": 3.43, "learning_rate": 3.5438184186458994e-06, "loss": 0.7608, "step": 41270 }, { "epoch": 3.43, "learning_rate": 3.543707563118366e-06, "loss": 0.846, "step": 41280 }, { "epoch": 3.43, "learning_rate": 3.543596707590832e-06, "loss": 0.8371, "step": 41290 }, { "epoch": 3.43, "learning_rate": 3.5434858520632983e-06, "loss": 0.8875, "step": 41300 }, { "epoch": 3.43, "learning_rate": 3.5433749965357646e-06, "loss": 0.9253, "step": 41310 }, { "epoch": 3.43, "learning_rate": 3.543264141008231e-06, "loss": 0.8093, "step": 41320 }, { "epoch": 3.44, "learning_rate": 3.5431532854806968e-06, "loss": 0.8196, "step": 41330 }, { "epoch": 3.44, "learning_rate": 3.5430424299531635e-06, "loss": 0.8155, "step": 41340 }, { "epoch": 3.44, "learning_rate": 3.54293157442563e-06, "loss": 0.8227, "step": 41350 }, { "epoch": 3.44, "learning_rate": 3.5428207188980957e-06, "loss": 0.7799, "step": 41360 }, { "epoch": 3.44, "learning_rate": 3.5427098633705624e-06, "loss": 0.8413, "step": 41370 }, { "epoch": 3.44, "learning_rate": 3.5425990078430283e-06, "loss": 0.879, "step": 41380 }, { "epoch": 3.44, "learning_rate": 3.542488152315495e-06, "loss": 0.818, "step": 41390 }, { "epoch": 3.44, "learning_rate": 3.542377296787961e-06, "loss": 0.8287, "step": 41400 }, { "epoch": 3.44, "learning_rate": 3.542266441260427e-06, "loss": 0.863, "step": 41410 }, { "epoch": 3.44, "learning_rate": 3.5421555857328934e-06, "loss": 0.8304, "step": 41420 }, { "epoch": 3.44, "learning_rate": 3.5420447302053597e-06, "loss": 0.8334, "step": 41430 }, { "epoch": 3.44, "learning_rate": 3.5419338746778256e-06, "loss": 0.8408, "step": 41440 }, { "epoch": 3.45, "learning_rate": 3.5418230191502923e-06, "loss": 0.8671, "step": 41450 }, { "epoch": 3.45, "learning_rate": 3.541712163622758e-06, "loss": 0.7994, "step": 41460 }, { "epoch": 3.45, "learning_rate": 3.541601308095225e-06, "loss": 0.7883, "step": 41470 }, { "epoch": 3.45, "learning_rate": 3.541490452567691e-06, "loss": 0.7712, "step": 41480 }, { "epoch": 3.45, "learning_rate": 3.541379597040157e-06, "loss": 0.8119, "step": 41490 }, { "epoch": 3.45, "learning_rate": 3.541268741512624e-06, "loss": 0.824, "step": 41500 }, { "epoch": 3.45, "learning_rate": 3.5411578859850897e-06, "loss": 0.8737, "step": 41510 }, { "epoch": 3.45, "learning_rate": 3.541047030457556e-06, "loss": 0.7961, "step": 41520 }, { "epoch": 3.45, "learning_rate": 3.5409361749300223e-06, "loss": 0.8159, "step": 41530 }, { "epoch": 3.45, "learning_rate": 3.5408253194024886e-06, "loss": 0.8052, "step": 41540 }, { "epoch": 3.45, "learning_rate": 3.540714463874955e-06, "loss": 0.8861, "step": 41550 }, { "epoch": 3.45, "learning_rate": 3.540603608347421e-06, "loss": 0.8347, "step": 41560 }, { "epoch": 3.46, "learning_rate": 3.540492752819887e-06, "loss": 0.8735, "step": 41570 }, { "epoch": 3.46, "learning_rate": 3.5403818972923537e-06, "loss": 0.8391, "step": 41580 }, { "epoch": 3.46, "learning_rate": 3.54027104176482e-06, "loss": 0.8383, "step": 41590 }, { "epoch": 3.46, "learning_rate": 3.540160186237286e-06, "loss": 0.8886, "step": 41600 }, { "epoch": 3.46, "learning_rate": 3.5400493307097526e-06, "loss": 0.8398, "step": 41610 }, { "epoch": 3.46, "learning_rate": 3.5399384751822185e-06, "loss": 0.8109, "step": 41620 }, { "epoch": 3.46, "learning_rate": 3.539827619654685e-06, "loss": 0.8404, "step": 41630 }, { "epoch": 3.46, "learning_rate": 3.539716764127151e-06, "loss": 0.8056, "step": 41640 }, { "epoch": 3.46, "learning_rate": 3.5396059085996174e-06, "loss": 0.9059, "step": 41650 }, { "epoch": 3.46, "learning_rate": 3.5394950530720837e-06, "loss": 0.7661, "step": 41660 }, { "epoch": 3.46, "learning_rate": 3.53938419754455e-06, "loss": 0.8454, "step": 41670 }, { "epoch": 3.46, "learning_rate": 3.539273342017016e-06, "loss": 0.7519, "step": 41680 }, { "epoch": 3.47, "learning_rate": 3.5391624864894826e-06, "loss": 0.8036, "step": 41690 }, { "epoch": 3.47, "learning_rate": 3.5390516309619484e-06, "loss": 0.8777, "step": 41700 }, { "epoch": 3.47, "learning_rate": 3.5389407754344147e-06, "loss": 0.7813, "step": 41710 }, { "epoch": 3.47, "learning_rate": 3.5388299199068814e-06, "loss": 0.8467, "step": 41720 }, { "epoch": 3.47, "learning_rate": 3.5387190643793473e-06, "loss": 0.8324, "step": 41730 }, { "epoch": 3.47, "learning_rate": 3.538608208851814e-06, "loss": 0.8063, "step": 41740 }, { "epoch": 3.47, "learning_rate": 3.53849735332428e-06, "loss": 0.8744, "step": 41750 }, { "epoch": 3.47, "learning_rate": 3.538386497796746e-06, "loss": 0.7737, "step": 41760 }, { "epoch": 3.47, "learning_rate": 3.5382756422692125e-06, "loss": 0.8107, "step": 41770 }, { "epoch": 3.47, "learning_rate": 3.538164786741679e-06, "loss": 0.8907, "step": 41780 }, { "epoch": 3.47, "learning_rate": 3.5380539312141447e-06, "loss": 0.8282, "step": 41790 }, { "epoch": 3.47, "learning_rate": 3.5379430756866114e-06, "loss": 0.8037, "step": 41800 }, { "epoch": 3.48, "learning_rate": 3.5378322201590773e-06, "loss": 0.8495, "step": 41810 }, { "epoch": 3.48, "learning_rate": 3.537721364631544e-06, "loss": 0.8608, "step": 41820 }, { "epoch": 3.48, "learning_rate": 3.53761050910401e-06, "loss": 0.77, "step": 41830 }, { "epoch": 3.48, "learning_rate": 3.537499653576476e-06, "loss": 0.8592, "step": 41840 }, { "epoch": 3.48, "learning_rate": 3.537388798048943e-06, "loss": 0.8404, "step": 41850 }, { "epoch": 3.48, "learning_rate": 3.5372779425214087e-06, "loss": 0.8708, "step": 41860 }, { "epoch": 3.48, "learning_rate": 3.537167086993875e-06, "loss": 0.777, "step": 41870 }, { "epoch": 3.48, "learning_rate": 3.5370562314663413e-06, "loss": 0.8616, "step": 41880 }, { "epoch": 3.48, "learning_rate": 3.5369453759388076e-06, "loss": 0.8043, "step": 41890 }, { "epoch": 3.48, "learning_rate": 3.536834520411274e-06, "loss": 0.8342, "step": 41900 }, { "epoch": 3.48, "learning_rate": 3.53672366488374e-06, "loss": 0.8082, "step": 41910 }, { "epoch": 3.48, "learning_rate": 3.536612809356206e-06, "loss": 0.8844, "step": 41920 }, { "epoch": 3.49, "learning_rate": 3.536501953828673e-06, "loss": 0.8236, "step": 41930 }, { "epoch": 3.49, "learning_rate": 3.5363910983011387e-06, "loss": 0.7895, "step": 41940 }, { "epoch": 3.49, "learning_rate": 3.536280242773605e-06, "loss": 0.9084, "step": 41950 }, { "epoch": 3.49, "learning_rate": 3.5361693872460717e-06, "loss": 0.8363, "step": 41960 }, { "epoch": 3.49, "learning_rate": 3.5360585317185376e-06, "loss": 0.7692, "step": 41970 }, { "epoch": 3.49, "learning_rate": 3.5359476761910043e-06, "loss": 0.8083, "step": 41980 }, { "epoch": 3.49, "learning_rate": 3.53583682066347e-06, "loss": 0.8477, "step": 41990 }, { "epoch": 3.49, "learning_rate": 3.5357259651359364e-06, "loss": 0.8408, "step": 42000 }, { "epoch": 3.49, "learning_rate": 3.5356151096084027e-06, "loss": 0.8264, "step": 42010 }, { "epoch": 3.49, "learning_rate": 3.535504254080869e-06, "loss": 0.8334, "step": 42020 }, { "epoch": 3.49, "learning_rate": 3.535393398553335e-06, "loss": 0.8267, "step": 42030 }, { "epoch": 3.49, "learning_rate": 3.5352825430258016e-06, "loss": 0.813, "step": 42040 }, { "epoch": 3.5, "learning_rate": 3.5351716874982675e-06, "loss": 0.8701, "step": 42050 }, { "epoch": 3.5, "learning_rate": 3.5350608319707342e-06, "loss": 0.8522, "step": 42060 }, { "epoch": 3.5, "learning_rate": 3.5349499764432e-06, "loss": 0.868, "step": 42070 }, { "epoch": 3.5, "learning_rate": 3.5348391209156664e-06, "loss": 0.7537, "step": 42080 }, { "epoch": 3.5, "learning_rate": 3.534728265388133e-06, "loss": 0.8782, "step": 42090 }, { "epoch": 3.5, "learning_rate": 3.534617409860599e-06, "loss": 0.8816, "step": 42100 }, { "epoch": 3.5, "learning_rate": 3.5345065543330653e-06, "loss": 0.7826, "step": 42110 }, { "epoch": 3.5, "learning_rate": 3.5343956988055316e-06, "loss": 0.8128, "step": 42120 }, { "epoch": 3.5, "learning_rate": 3.534284843277998e-06, "loss": 0.8703, "step": 42130 }, { "epoch": 3.5, "learning_rate": 3.5341850733032174e-06, "loss": 0.8642, "step": 42140 }, { "epoch": 3.5, "learning_rate": 3.5340742177756837e-06, "loss": 0.8899, "step": 42150 }, { "epoch": 3.5, "learning_rate": 3.53396336224815e-06, "loss": 0.7635, "step": 42160 }, { "epoch": 3.51, "learning_rate": 3.5338525067206163e-06, "loss": 0.8213, "step": 42170 }, { "epoch": 3.51, "learning_rate": 3.5337416511930826e-06, "loss": 0.8379, "step": 42180 }, { "epoch": 3.51, "learning_rate": 3.533630795665549e-06, "loss": 0.7829, "step": 42190 }, { "epoch": 3.51, "learning_rate": 3.5335199401380147e-06, "loss": 0.9453, "step": 42200 }, { "epoch": 3.51, "learning_rate": 3.5334090846104815e-06, "loss": 0.8961, "step": 42210 }, { "epoch": 3.51, "learning_rate": 3.5332982290829473e-06, "loss": 0.8136, "step": 42220 }, { "epoch": 3.51, "learning_rate": 3.533187373555414e-06, "loss": 0.8102, "step": 42230 }, { "epoch": 3.51, "learning_rate": 3.53307651802788e-06, "loss": 0.8102, "step": 42240 }, { "epoch": 3.51, "learning_rate": 3.5329656625003462e-06, "loss": 0.8395, "step": 42250 }, { "epoch": 3.51, "learning_rate": 3.5328548069728125e-06, "loss": 0.8544, "step": 42260 }, { "epoch": 3.51, "learning_rate": 3.532743951445279e-06, "loss": 0.7616, "step": 42270 }, { "epoch": 3.51, "learning_rate": 3.5326330959177447e-06, "loss": 0.8217, "step": 42280 }, { "epoch": 3.52, "learning_rate": 3.5325222403902114e-06, "loss": 0.8736, "step": 42290 }, { "epoch": 3.52, "learning_rate": 3.5324113848626777e-06, "loss": 0.8449, "step": 42300 }, { "epoch": 3.52, "learning_rate": 3.5323005293351436e-06, "loss": 0.8801, "step": 42310 }, { "epoch": 3.52, "learning_rate": 3.5321896738076103e-06, "loss": 0.8242, "step": 42320 }, { "epoch": 3.52, "learning_rate": 3.532078818280076e-06, "loss": 0.883, "step": 42330 }, { "epoch": 3.52, "learning_rate": 3.531967962752543e-06, "loss": 0.7951, "step": 42340 }, { "epoch": 3.52, "learning_rate": 3.5318571072250088e-06, "loss": 0.9442, "step": 42350 }, { "epoch": 3.52, "learning_rate": 3.531746251697475e-06, "loss": 0.8748, "step": 42360 }, { "epoch": 3.52, "learning_rate": 3.5316353961699413e-06, "loss": 0.8449, "step": 42370 }, { "epoch": 3.52, "learning_rate": 3.5315245406424076e-06, "loss": 0.8718, "step": 42380 }, { "epoch": 3.52, "learning_rate": 3.5314136851148735e-06, "loss": 0.7946, "step": 42390 }, { "epoch": 3.52, "learning_rate": 3.5313028295873402e-06, "loss": 0.9327, "step": 42400 }, { "epoch": 3.53, "learning_rate": 3.531191974059806e-06, "loss": 0.8184, "step": 42410 }, { "epoch": 3.53, "learning_rate": 3.531081118532273e-06, "loss": 0.9034, "step": 42420 }, { "epoch": 3.53, "learning_rate": 3.530970263004739e-06, "loss": 0.7902, "step": 42430 }, { "epoch": 3.53, "learning_rate": 3.530859407477205e-06, "loss": 0.8723, "step": 42440 }, { "epoch": 3.53, "learning_rate": 3.5307485519496717e-06, "loss": 0.846, "step": 42450 }, { "epoch": 3.53, "learning_rate": 3.5306376964221376e-06, "loss": 0.7863, "step": 42460 }, { "epoch": 3.53, "learning_rate": 3.530526840894604e-06, "loss": 0.8248, "step": 42470 }, { "epoch": 3.53, "learning_rate": 3.53041598536707e-06, "loss": 0.793, "step": 42480 }, { "epoch": 3.53, "learning_rate": 3.5303051298395365e-06, "loss": 0.8686, "step": 42490 }, { "epoch": 3.53, "learning_rate": 3.5301942743120028e-06, "loss": 0.8789, "step": 42500 }, { "epoch": 3.53, "learning_rate": 3.530083418784469e-06, "loss": 0.8201, "step": 42510 }, { "epoch": 3.53, "learning_rate": 3.529972563256935e-06, "loss": 0.8061, "step": 42520 }, { "epoch": 3.54, "learning_rate": 3.5298617077294016e-06, "loss": 0.797, "step": 42530 }, { "epoch": 3.54, "learning_rate": 3.529750852201868e-06, "loss": 0.7796, "step": 42540 }, { "epoch": 3.54, "learning_rate": 3.529639996674334e-06, "loss": 0.8729, "step": 42550 }, { "epoch": 3.54, "learning_rate": 3.5295291411468005e-06, "loss": 0.8472, "step": 42560 }, { "epoch": 3.54, "learning_rate": 3.5294182856192664e-06, "loss": 0.876, "step": 42570 }, { "epoch": 3.54, "learning_rate": 3.529307430091733e-06, "loss": 0.8219, "step": 42580 }, { "epoch": 3.54, "learning_rate": 3.529196574564199e-06, "loss": 0.8214, "step": 42590 }, { "epoch": 3.54, "learning_rate": 3.5290857190366653e-06, "loss": 0.9184, "step": 42600 }, { "epoch": 3.54, "learning_rate": 3.5289748635091316e-06, "loss": 0.8122, "step": 42610 }, { "epoch": 3.54, "learning_rate": 3.528864007981598e-06, "loss": 0.8138, "step": 42620 }, { "epoch": 3.54, "learning_rate": 3.5287531524540638e-06, "loss": 0.83, "step": 42630 }, { "epoch": 3.54, "learning_rate": 3.5286422969265305e-06, "loss": 0.8499, "step": 42640 }, { "epoch": 3.55, "learning_rate": 3.5285314413989963e-06, "loss": 0.8276, "step": 42650 }, { "epoch": 3.55, "learning_rate": 3.528420585871463e-06, "loss": 0.8415, "step": 42660 }, { "epoch": 3.55, "learning_rate": 3.5283097303439294e-06, "loss": 0.7892, "step": 42670 }, { "epoch": 3.55, "learning_rate": 3.5281988748163952e-06, "loss": 0.8284, "step": 42680 }, { "epoch": 3.55, "learning_rate": 3.528088019288862e-06, "loss": 0.7821, "step": 42690 }, { "epoch": 3.55, "learning_rate": 3.527977163761328e-06, "loss": 0.8846, "step": 42700 }, { "epoch": 3.55, "learning_rate": 3.527866308233794e-06, "loss": 0.8891, "step": 42710 }, { "epoch": 3.55, "learning_rate": 3.5277554527062604e-06, "loss": 0.7848, "step": 42720 }, { "epoch": 3.55, "learning_rate": 3.5276445971787267e-06, "loss": 0.8989, "step": 42730 }, { "epoch": 3.55, "learning_rate": 3.5275337416511926e-06, "loss": 0.8431, "step": 42740 }, { "epoch": 3.55, "learning_rate": 3.5274228861236593e-06, "loss": 0.8588, "step": 42750 }, { "epoch": 3.55, "learning_rate": 3.527312030596125e-06, "loss": 0.8369, "step": 42760 }, { "epoch": 3.55, "learning_rate": 3.527201175068592e-06, "loss": 0.8142, "step": 42770 }, { "epoch": 3.56, "learning_rate": 3.5270903195410578e-06, "loss": 0.8495, "step": 42780 }, { "epoch": 3.56, "learning_rate": 3.526979464013524e-06, "loss": 0.822, "step": 42790 }, { "epoch": 3.56, "learning_rate": 3.5268686084859908e-06, "loss": 0.8268, "step": 42800 }, { "epoch": 3.56, "learning_rate": 3.5267577529584566e-06, "loss": 0.8273, "step": 42810 }, { "epoch": 3.56, "learning_rate": 3.526646897430923e-06, "loss": 0.8853, "step": 42820 }, { "epoch": 3.56, "learning_rate": 3.5265360419033892e-06, "loss": 0.8412, "step": 42830 }, { "epoch": 3.56, "learning_rate": 3.5264251863758555e-06, "loss": 0.822, "step": 42840 }, { "epoch": 3.56, "learning_rate": 3.526314330848322e-06, "loss": 0.9065, "step": 42850 }, { "epoch": 3.56, "learning_rate": 3.526203475320788e-06, "loss": 0.8825, "step": 42860 }, { "epoch": 3.56, "learning_rate": 3.526092619793254e-06, "loss": 0.8403, "step": 42870 }, { "epoch": 3.56, "learning_rate": 3.5259817642657207e-06, "loss": 0.8616, "step": 42880 }, { "epoch": 3.56, "learning_rate": 3.5258709087381866e-06, "loss": 0.8328, "step": 42890 }, { "epoch": 3.57, "learning_rate": 3.525760053210653e-06, "loss": 0.8117, "step": 42900 }, { "epoch": 3.57, "learning_rate": 3.5256491976831196e-06, "loss": 0.8499, "step": 42910 }, { "epoch": 3.57, "learning_rate": 3.5255383421555855e-06, "loss": 0.8215, "step": 42920 }, { "epoch": 3.57, "learning_rate": 3.525427486628052e-06, "loss": 0.8062, "step": 42930 }, { "epoch": 3.57, "learning_rate": 3.525316631100518e-06, "loss": 0.8301, "step": 42940 }, { "epoch": 3.57, "learning_rate": 3.5252057755729844e-06, "loss": 0.8715, "step": 42950 }, { "epoch": 3.57, "learning_rate": 3.5250949200454507e-06, "loss": 0.844, "step": 42960 }, { "epoch": 3.57, "learning_rate": 3.524984064517917e-06, "loss": 0.7827, "step": 42970 }, { "epoch": 3.57, "learning_rate": 3.524873208990383e-06, "loss": 0.8083, "step": 42980 }, { "epoch": 3.57, "learning_rate": 3.5247623534628495e-06, "loss": 0.8592, "step": 42990 }, { "epoch": 3.57, "learning_rate": 3.5246514979353154e-06, "loss": 0.9133, "step": 43000 }, { "epoch": 3.57, "learning_rate": 3.524540642407782e-06, "loss": 0.8941, "step": 43010 }, { "epoch": 3.58, "learning_rate": 3.524429786880248e-06, "loss": 0.769, "step": 43020 }, { "epoch": 3.58, "learning_rate": 3.5243189313527143e-06, "loss": 0.7706, "step": 43030 }, { "epoch": 3.58, "learning_rate": 3.524208075825181e-06, "loss": 0.772, "step": 43040 }, { "epoch": 3.58, "learning_rate": 3.524097220297647e-06, "loss": 0.9555, "step": 43050 }, { "epoch": 3.58, "learning_rate": 3.523986364770113e-06, "loss": 0.8211, "step": 43060 }, { "epoch": 3.58, "learning_rate": 3.5238755092425795e-06, "loss": 0.8158, "step": 43070 }, { "epoch": 3.58, "learning_rate": 3.5237646537150458e-06, "loss": 0.7789, "step": 43080 }, { "epoch": 3.58, "learning_rate": 3.5236537981875116e-06, "loss": 0.7922, "step": 43090 }, { "epoch": 3.58, "learning_rate": 3.5235429426599784e-06, "loss": 0.9292, "step": 43100 }, { "epoch": 3.58, "learning_rate": 3.5234320871324442e-06, "loss": 0.9011, "step": 43110 }, { "epoch": 3.58, "learning_rate": 3.523321231604911e-06, "loss": 0.7748, "step": 43120 }, { "epoch": 3.58, "learning_rate": 3.523210376077377e-06, "loss": 0.8166, "step": 43130 }, { "epoch": 3.59, "learning_rate": 3.523099520549843e-06, "loss": 0.8881, "step": 43140 }, { "epoch": 3.59, "learning_rate": 3.52298866502231e-06, "loss": 0.8066, "step": 43150 }, { "epoch": 3.59, "learning_rate": 3.5228778094947757e-06, "loss": 0.8712, "step": 43160 }, { "epoch": 3.59, "learning_rate": 3.522766953967242e-06, "loss": 0.8984, "step": 43170 }, { "epoch": 3.59, "learning_rate": 3.5226560984397083e-06, "loss": 0.8388, "step": 43180 }, { "epoch": 3.59, "learning_rate": 3.5225452429121746e-06, "loss": 0.8148, "step": 43190 }, { "epoch": 3.59, "learning_rate": 3.522434387384641e-06, "loss": 0.8891, "step": 43200 }, { "epoch": 3.59, "learning_rate": 3.522323531857107e-06, "loss": 0.8831, "step": 43210 }, { "epoch": 3.59, "learning_rate": 3.522212676329573e-06, "loss": 0.7929, "step": 43220 }, { "epoch": 3.59, "learning_rate": 3.5221018208020398e-06, "loss": 0.811, "step": 43230 }, { "epoch": 3.59, "learning_rate": 3.5219909652745057e-06, "loss": 0.8257, "step": 43240 }, { "epoch": 3.59, "learning_rate": 3.521880109746972e-06, "loss": 0.9322, "step": 43250 }, { "epoch": 3.6, "learning_rate": 3.5217692542194382e-06, "loss": 0.8175, "step": 43260 }, { "epoch": 3.6, "learning_rate": 3.5216583986919045e-06, "loss": 0.7446, "step": 43270 }, { "epoch": 3.6, "learning_rate": 3.5215475431643713e-06, "loss": 0.8352, "step": 43280 }, { "epoch": 3.6, "learning_rate": 3.521436687636837e-06, "loss": 0.8312, "step": 43290 }, { "epoch": 3.6, "learning_rate": 3.5213258321093034e-06, "loss": 0.9225, "step": 43300 }, { "epoch": 3.6, "learning_rate": 3.5212149765817697e-06, "loss": 0.7898, "step": 43310 }, { "epoch": 3.6, "learning_rate": 3.521104121054236e-06, "loss": 0.7507, "step": 43320 }, { "epoch": 3.6, "learning_rate": 3.520993265526702e-06, "loss": 0.7867, "step": 43330 }, { "epoch": 3.6, "learning_rate": 3.5208824099991686e-06, "loss": 0.8049, "step": 43340 }, { "epoch": 3.6, "learning_rate": 3.5207715544716345e-06, "loss": 0.9218, "step": 43350 }, { "epoch": 3.6, "learning_rate": 3.520660698944101e-06, "loss": 0.8397, "step": 43360 }, { "epoch": 3.6, "learning_rate": 3.520549843416567e-06, "loss": 0.8323, "step": 43370 }, { "epoch": 3.61, "learning_rate": 3.5204389878890334e-06, "loss": 0.8887, "step": 43380 }, { "epoch": 3.61, "learning_rate": 3.5203281323614997e-06, "loss": 0.8266, "step": 43390 }, { "epoch": 3.61, "learning_rate": 3.520217276833966e-06, "loss": 0.8155, "step": 43400 }, { "epoch": 3.61, "learning_rate": 3.5201064213064322e-06, "loss": 0.8776, "step": 43410 }, { "epoch": 3.61, "learning_rate": 3.5199955657788985e-06, "loss": 0.8266, "step": 43420 }, { "epoch": 3.61, "learning_rate": 3.519884710251365e-06, "loss": 0.8069, "step": 43430 }, { "epoch": 3.61, "learning_rate": 3.519773854723831e-06, "loss": 0.8887, "step": 43440 }, { "epoch": 3.61, "learning_rate": 3.5196629991962974e-06, "loss": 0.9234, "step": 43450 }, { "epoch": 3.61, "learning_rate": 3.5195521436687633e-06, "loss": 0.7876, "step": 43460 }, { "epoch": 3.61, "learning_rate": 3.51944128814123e-06, "loss": 0.8502, "step": 43470 }, { "epoch": 3.61, "learning_rate": 3.519330432613696e-06, "loss": 0.834, "step": 43480 }, { "epoch": 3.61, "learning_rate": 3.519219577086162e-06, "loss": 0.8181, "step": 43490 }, { "epoch": 3.62, "learning_rate": 3.5191087215586285e-06, "loss": 0.9009, "step": 43500 }, { "epoch": 3.62, "learning_rate": 3.5189978660310948e-06, "loss": 0.846, "step": 43510 }, { "epoch": 3.62, "learning_rate": 3.5188870105035615e-06, "loss": 0.8835, "step": 43520 }, { "epoch": 3.62, "learning_rate": 3.5187761549760274e-06, "loss": 0.7876, "step": 43530 }, { "epoch": 3.62, "learning_rate": 3.5186652994484937e-06, "loss": 0.8743, "step": 43540 }, { "epoch": 3.62, "learning_rate": 3.51855444392096e-06, "loss": 0.8738, "step": 43550 }, { "epoch": 3.62, "learning_rate": 3.5184435883934263e-06, "loss": 0.8287, "step": 43560 }, { "epoch": 3.62, "learning_rate": 3.518332732865892e-06, "loss": 0.8255, "step": 43570 }, { "epoch": 3.62, "learning_rate": 3.518221877338359e-06, "loss": 0.815, "step": 43580 }, { "epoch": 3.62, "learning_rate": 3.5181110218108247e-06, "loss": 0.8111, "step": 43590 }, { "epoch": 3.62, "learning_rate": 3.518000166283291e-06, "loss": 0.9067, "step": 43600 }, { "epoch": 3.62, "learning_rate": 3.5178893107557573e-06, "loss": 0.898, "step": 43610 }, { "epoch": 3.63, "learning_rate": 3.5177784552282236e-06, "loss": 0.7848, "step": 43620 }, { "epoch": 3.63, "learning_rate": 3.51766759970069e-06, "loss": 0.7761, "step": 43630 }, { "epoch": 3.63, "learning_rate": 3.517556744173156e-06, "loss": 0.7865, "step": 43640 }, { "epoch": 3.63, "learning_rate": 3.5174458886456225e-06, "loss": 0.8563, "step": 43650 }, { "epoch": 3.63, "learning_rate": 3.5173350331180888e-06, "loss": 0.8364, "step": 43660 }, { "epoch": 3.63, "learning_rate": 3.517224177590555e-06, "loss": 0.8019, "step": 43670 }, { "epoch": 3.63, "learning_rate": 3.517113322063021e-06, "loss": 0.7773, "step": 43680 }, { "epoch": 3.63, "learning_rate": 3.5170024665354877e-06, "loss": 0.8607, "step": 43690 }, { "epoch": 3.63, "learning_rate": 3.5168916110079535e-06, "loss": 0.8586, "step": 43700 }, { "epoch": 3.63, "learning_rate": 3.5167807554804203e-06, "loss": 0.923, "step": 43710 }, { "epoch": 3.63, "learning_rate": 3.516669899952886e-06, "loss": 0.843, "step": 43720 }, { "epoch": 3.63, "learning_rate": 3.5165590444253524e-06, "loss": 0.895, "step": 43730 }, { "epoch": 3.64, "learning_rate": 3.5164481888978187e-06, "loss": 0.781, "step": 43740 }, { "epoch": 3.64, "learning_rate": 3.516337333370285e-06, "loss": 0.9013, "step": 43750 }, { "epoch": 3.64, "learning_rate": 3.516226477842751e-06, "loss": 0.7916, "step": 43760 }, { "epoch": 3.64, "learning_rate": 3.5161156223152176e-06, "loss": 0.8334, "step": 43770 }, { "epoch": 3.64, "learning_rate": 3.516004766787684e-06, "loss": 0.8659, "step": 43780 }, { "epoch": 3.64, "learning_rate": 3.51589391126015e-06, "loss": 0.7376, "step": 43790 }, { "epoch": 3.64, "learning_rate": 3.5157830557326165e-06, "loss": 0.8852, "step": 43800 }, { "epoch": 3.64, "learning_rate": 3.5156722002050824e-06, "loss": 0.8338, "step": 43810 }, { "epoch": 3.64, "learning_rate": 3.515561344677549e-06, "loss": 0.8225, "step": 43820 }, { "epoch": 3.64, "learning_rate": 3.515450489150015e-06, "loss": 0.8259, "step": 43830 }, { "epoch": 3.64, "learning_rate": 3.5153396336224813e-06, "loss": 0.7985, "step": 43840 }, { "epoch": 3.64, "learning_rate": 3.5152287780949475e-06, "loss": 0.8406, "step": 43850 }, { "epoch": 3.65, "learning_rate": 3.515117922567414e-06, "loss": 0.8106, "step": 43860 }, { "epoch": 3.65, "learning_rate": 3.5150070670398797e-06, "loss": 0.8967, "step": 43870 }, { "epoch": 3.65, "learning_rate": 3.5148962115123464e-06, "loss": 0.7925, "step": 43880 }, { "epoch": 3.65, "learning_rate": 3.5147853559848127e-06, "loss": 0.8347, "step": 43890 }, { "epoch": 3.65, "learning_rate": 3.514674500457279e-06, "loss": 0.8935, "step": 43900 }, { "epoch": 3.65, "learning_rate": 3.5145636449297453e-06, "loss": 0.7913, "step": 43910 }, { "epoch": 3.65, "learning_rate": 3.514452789402211e-06, "loss": 0.8484, "step": 43920 }, { "epoch": 3.65, "learning_rate": 3.514341933874678e-06, "loss": 0.8087, "step": 43930 }, { "epoch": 3.65, "learning_rate": 3.5142310783471438e-06, "loss": 0.8648, "step": 43940 }, { "epoch": 3.65, "learning_rate": 3.5141202228196105e-06, "loss": 0.8781, "step": 43950 }, { "epoch": 3.65, "learning_rate": 3.5140093672920764e-06, "loss": 0.7941, "step": 43960 }, { "epoch": 3.65, "learning_rate": 3.5138985117645427e-06, "loss": 0.824, "step": 43970 }, { "epoch": 3.66, "learning_rate": 3.513787656237009e-06, "loss": 0.8284, "step": 43980 }, { "epoch": 3.66, "learning_rate": 3.5136768007094753e-06, "loss": 0.8463, "step": 43990 }, { "epoch": 3.66, "learning_rate": 3.513565945181941e-06, "loss": 0.8253, "step": 44000 }, { "epoch": 3.66, "learning_rate": 3.513455089654408e-06, "loss": 0.8899, "step": 44010 }, { "epoch": 3.66, "learning_rate": 3.513344234126874e-06, "loss": 0.8469, "step": 44020 }, { "epoch": 3.66, "learning_rate": 3.51323337859934e-06, "loss": 0.8242, "step": 44030 }, { "epoch": 3.66, "learning_rate": 3.5131225230718067e-06, "loss": 0.8051, "step": 44040 }, { "epoch": 3.66, "learning_rate": 3.5130116675442726e-06, "loss": 0.9389, "step": 44050 }, { "epoch": 3.66, "learning_rate": 3.5129008120167393e-06, "loss": 0.8862, "step": 44060 }, { "epoch": 3.66, "learning_rate": 3.512789956489205e-06, "loss": 0.8177, "step": 44070 }, { "epoch": 3.66, "learning_rate": 3.5126791009616715e-06, "loss": 0.8322, "step": 44080 }, { "epoch": 3.66, "learning_rate": 3.512568245434138e-06, "loss": 0.8518, "step": 44090 }, { "epoch": 3.67, "learning_rate": 3.512457389906604e-06, "loss": 0.8323, "step": 44100 }, { "epoch": 3.67, "learning_rate": 3.51234653437907e-06, "loss": 0.9432, "step": 44110 }, { "epoch": 3.67, "learning_rate": 3.5122356788515367e-06, "loss": 0.8788, "step": 44120 }, { "epoch": 3.67, "learning_rate": 3.5121248233240025e-06, "loss": 0.8332, "step": 44130 }, { "epoch": 3.67, "learning_rate": 3.5120139677964693e-06, "loss": 0.8659, "step": 44140 }, { "epoch": 3.67, "learning_rate": 3.5119031122689356e-06, "loss": 0.9168, "step": 44150 }, { "epoch": 3.67, "learning_rate": 3.5117922567414014e-06, "loss": 0.818, "step": 44160 }, { "epoch": 3.67, "learning_rate": 3.511681401213868e-06, "loss": 0.8404, "step": 44170 }, { "epoch": 3.67, "learning_rate": 3.511570545686334e-06, "loss": 0.8334, "step": 44180 }, { "epoch": 3.67, "learning_rate": 3.5114596901588003e-06, "loss": 0.7217, "step": 44190 }, { "epoch": 3.67, "learning_rate": 3.5113488346312666e-06, "loss": 0.8467, "step": 44200 }, { "epoch": 3.67, "learning_rate": 3.511237979103733e-06, "loss": 0.8274, "step": 44210 }, { "epoch": 3.68, "learning_rate": 3.511127123576199e-06, "loss": 0.7977, "step": 44220 }, { "epoch": 3.68, "learning_rate": 3.5110162680486655e-06, "loss": 0.793, "step": 44230 }, { "epoch": 3.68, "learning_rate": 3.5109054125211314e-06, "loss": 0.7702, "step": 44240 }, { "epoch": 3.68, "learning_rate": 3.510794556993598e-06, "loss": 0.8523, "step": 44250 }, { "epoch": 3.68, "learning_rate": 3.5106837014660644e-06, "loss": 0.822, "step": 44260 }, { "epoch": 3.68, "learning_rate": 3.5105728459385303e-06, "loss": 0.7671, "step": 44270 }, { "epoch": 3.68, "learning_rate": 3.510461990410997e-06, "loss": 0.8012, "step": 44280 }, { "epoch": 3.68, "learning_rate": 3.510351134883463e-06, "loss": 0.8228, "step": 44290 }, { "epoch": 3.68, "learning_rate": 3.5102402793559296e-06, "loss": 0.8392, "step": 44300 }, { "epoch": 3.68, "learning_rate": 3.5101294238283954e-06, "loss": 0.8752, "step": 44310 }, { "epoch": 3.68, "learning_rate": 3.5100185683008617e-06, "loss": 0.7865, "step": 44320 }, { "epoch": 3.68, "learning_rate": 3.509907712773328e-06, "loss": 0.8551, "step": 44330 }, { "epoch": 3.69, "learning_rate": 3.5097968572457943e-06, "loss": 0.7753, "step": 44340 }, { "epoch": 3.69, "learning_rate": 3.50968600171826e-06, "loss": 0.8326, "step": 44350 }, { "epoch": 3.69, "learning_rate": 3.509575146190727e-06, "loss": 0.793, "step": 44360 }, { "epoch": 3.69, "learning_rate": 3.509464290663193e-06, "loss": 0.7941, "step": 44370 }, { "epoch": 3.69, "learning_rate": 3.509353435135659e-06, "loss": 0.855, "step": 44380 }, { "epoch": 3.69, "learning_rate": 3.509242579608126e-06, "loss": 0.8007, "step": 44390 }, { "epoch": 3.69, "learning_rate": 3.5091317240805917e-06, "loss": 0.8809, "step": 44400 }, { "epoch": 3.69, "learning_rate": 3.5090208685530584e-06, "loss": 0.8325, "step": 44410 }, { "epoch": 3.69, "learning_rate": 3.5089100130255243e-06, "loss": 0.7975, "step": 44420 }, { "epoch": 3.69, "learning_rate": 3.508810243050744e-06, "loss": 0.7781, "step": 44430 }, { "epoch": 3.69, "learning_rate": 3.50869938752321e-06, "loss": 0.8408, "step": 44440 }, { "epoch": 3.69, "learning_rate": 3.5085885319956764e-06, "loss": 0.8502, "step": 44450 }, { "epoch": 3.7, "learning_rate": 3.5084776764681427e-06, "loss": 0.8055, "step": 44460 }, { "epoch": 3.7, "learning_rate": 3.5083668209406094e-06, "loss": 0.8759, "step": 44470 }, { "epoch": 3.7, "learning_rate": 3.5082559654130753e-06, "loss": 0.8203, "step": 44480 }, { "epoch": 3.7, "learning_rate": 3.5081451098855416e-06, "loss": 0.821, "step": 44490 }, { "epoch": 3.7, "learning_rate": 3.508034254358008e-06, "loss": 0.9652, "step": 44500 }, { "epoch": 3.7, "learning_rate": 3.507923398830474e-06, "loss": 0.8915, "step": 44510 }, { "epoch": 3.7, "learning_rate": 3.50781254330294e-06, "loss": 0.8169, "step": 44520 }, { "epoch": 3.7, "learning_rate": 3.5077016877754068e-06, "loss": 0.8126, "step": 44530 }, { "epoch": 3.7, "learning_rate": 3.5075908322478726e-06, "loss": 0.888, "step": 44540 }, { "epoch": 3.7, "learning_rate": 3.507479976720339e-06, "loss": 0.8659, "step": 44550 }, { "epoch": 3.7, "learning_rate": 3.5073691211928052e-06, "loss": 0.768, "step": 44560 }, { "epoch": 3.7, "learning_rate": 3.5072582656652715e-06, "loss": 0.8184, "step": 44570 }, { "epoch": 3.71, "learning_rate": 3.507147410137738e-06, "loss": 0.8539, "step": 44580 }, { "epoch": 3.71, "learning_rate": 3.507036554610204e-06, "loss": 0.7845, "step": 44590 }, { "epoch": 3.71, "learning_rate": 3.5069256990826704e-06, "loss": 0.899, "step": 44600 }, { "epoch": 3.71, "learning_rate": 3.5068148435551367e-06, "loss": 0.8153, "step": 44610 }, { "epoch": 3.71, "learning_rate": 3.506703988027603e-06, "loss": 0.8272, "step": 44620 }, { "epoch": 3.71, "learning_rate": 3.506593132500069e-06, "loss": 0.8637, "step": 44630 }, { "epoch": 3.71, "learning_rate": 3.5064822769725356e-06, "loss": 0.8329, "step": 44640 }, { "epoch": 3.71, "learning_rate": 3.5063714214450015e-06, "loss": 0.86, "step": 44650 }, { "epoch": 3.71, "learning_rate": 3.506260565917468e-06, "loss": 0.8313, "step": 44660 }, { "epoch": 3.71, "learning_rate": 3.506149710389934e-06, "loss": 0.8142, "step": 44670 }, { "epoch": 3.71, "learning_rate": 3.5060388548624003e-06, "loss": 0.8497, "step": 44680 }, { "epoch": 3.71, "learning_rate": 3.5059279993348666e-06, "loss": 0.8347, "step": 44690 }, { "epoch": 3.72, "learning_rate": 3.505817143807333e-06, "loss": 0.8813, "step": 44700 }, { "epoch": 3.72, "learning_rate": 3.505706288279799e-06, "loss": 0.7867, "step": 44710 }, { "epoch": 3.72, "learning_rate": 3.5055954327522655e-06, "loss": 0.7932, "step": 44720 }, { "epoch": 3.72, "learning_rate": 3.505484577224732e-06, "loss": 0.7782, "step": 44730 }, { "epoch": 3.72, "learning_rate": 3.505373721697198e-06, "loss": 0.7983, "step": 44740 }, { "epoch": 3.72, "learning_rate": 3.5052628661696644e-06, "loss": 0.8739, "step": 44750 }, { "epoch": 3.72, "learning_rate": 3.5051520106421303e-06, "loss": 0.813, "step": 44760 }, { "epoch": 3.72, "learning_rate": 3.505041155114597e-06, "loss": 0.8589, "step": 44770 }, { "epoch": 3.72, "learning_rate": 3.504930299587063e-06, "loss": 0.8328, "step": 44780 }, { "epoch": 3.72, "learning_rate": 3.504819444059529e-06, "loss": 0.872, "step": 44790 }, { "epoch": 3.72, "learning_rate": 3.5047085885319955e-06, "loss": 0.8708, "step": 44800 }, { "epoch": 3.72, "learning_rate": 3.5045977330044618e-06, "loss": 0.8975, "step": 44810 }, { "epoch": 3.73, "learning_rate": 3.5044868774769276e-06, "loss": 0.8167, "step": 44820 }, { "epoch": 3.73, "learning_rate": 3.5043760219493943e-06, "loss": 0.7417, "step": 44830 }, { "epoch": 3.73, "learning_rate": 3.5042651664218606e-06, "loss": 0.781, "step": 44840 }, { "epoch": 3.73, "learning_rate": 3.504154310894327e-06, "loss": 0.8997, "step": 44850 }, { "epoch": 3.73, "learning_rate": 3.5040434553667932e-06, "loss": 0.8779, "step": 44860 }, { "epoch": 3.73, "learning_rate": 3.503932599839259e-06, "loss": 0.7695, "step": 44870 }, { "epoch": 3.73, "learning_rate": 3.503821744311726e-06, "loss": 0.8102, "step": 44880 }, { "epoch": 3.73, "learning_rate": 3.5037108887841917e-06, "loss": 0.767, "step": 44890 }, { "epoch": 3.73, "learning_rate": 3.5036000332566584e-06, "loss": 0.9259, "step": 44900 }, { "epoch": 3.73, "learning_rate": 3.5034891777291243e-06, "loss": 0.8014, "step": 44910 }, { "epoch": 3.73, "learning_rate": 3.5033783222015906e-06, "loss": 0.8189, "step": 44920 }, { "epoch": 3.73, "learning_rate": 3.503267466674057e-06, "loss": 0.8664, "step": 44930 }, { "epoch": 3.74, "learning_rate": 3.503156611146523e-06, "loss": 0.831, "step": 44940 }, { "epoch": 3.74, "learning_rate": 3.503045755618989e-06, "loss": 0.9342, "step": 44950 }, { "epoch": 3.74, "learning_rate": 3.5029349000914558e-06, "loss": 0.8089, "step": 44960 }, { "epoch": 3.74, "learning_rate": 3.502824044563922e-06, "loss": 0.8592, "step": 44970 }, { "epoch": 3.74, "learning_rate": 3.502713189036388e-06, "loss": 0.7935, "step": 44980 }, { "epoch": 3.74, "learning_rate": 3.5026023335088546e-06, "loss": 0.7586, "step": 44990 }, { "epoch": 3.74, "learning_rate": 3.5024914779813205e-06, "loss": 0.8447, "step": 45000 }, { "epoch": 3.74, "learning_rate": 3.5023806224537872e-06, "loss": 0.8862, "step": 45010 }, { "epoch": 3.74, "learning_rate": 3.502269766926253e-06, "loss": 0.7856, "step": 45020 }, { "epoch": 3.74, "learning_rate": 3.5021589113987194e-06, "loss": 0.87, "step": 45030 }, { "epoch": 3.74, "learning_rate": 3.5020480558711857e-06, "loss": 0.7913, "step": 45040 }, { "epoch": 3.74, "learning_rate": 3.501937200343652e-06, "loss": 0.8809, "step": 45050 }, { "epoch": 3.75, "learning_rate": 3.501826344816118e-06, "loss": 0.848, "step": 45060 }, { "epoch": 3.75, "learning_rate": 3.5017154892885846e-06, "loss": 0.806, "step": 45070 }, { "epoch": 3.75, "learning_rate": 3.5016046337610505e-06, "loss": 0.8363, "step": 45080 }, { "epoch": 3.75, "learning_rate": 3.501493778233517e-06, "loss": 0.8419, "step": 45090 }, { "epoch": 3.75, "learning_rate": 3.5013829227059835e-06, "loss": 0.8795, "step": 45100 }, { "epoch": 3.75, "learning_rate": 3.5012720671784493e-06, "loss": 0.859, "step": 45110 }, { "epoch": 3.75, "learning_rate": 3.501161211650916e-06, "loss": 0.7615, "step": 45120 }, { "epoch": 3.75, "learning_rate": 3.501050356123382e-06, "loss": 0.8551, "step": 45130 }, { "epoch": 3.75, "learning_rate": 3.5009395005958482e-06, "loss": 0.8254, "step": 45140 }, { "epoch": 3.75, "learning_rate": 3.5008286450683145e-06, "loss": 0.8988, "step": 45150 }, { "epoch": 3.75, "learning_rate": 3.500717789540781e-06, "loss": 0.8074, "step": 45160 }, { "epoch": 3.75, "learning_rate": 3.500606934013247e-06, "loss": 0.8085, "step": 45170 }, { "epoch": 3.76, "learning_rate": 3.5004960784857134e-06, "loss": 0.7836, "step": 45180 }, { "epoch": 3.76, "learning_rate": 3.5003852229581793e-06, "loss": 0.8411, "step": 45190 }, { "epoch": 3.76, "learning_rate": 3.500274367430646e-06, "loss": 0.8743, "step": 45200 }, { "epoch": 3.76, "learning_rate": 3.5001635119031123e-06, "loss": 0.8301, "step": 45210 }, { "epoch": 3.76, "learning_rate": 3.500052656375578e-06, "loss": 0.8175, "step": 45220 }, { "epoch": 3.76, "learning_rate": 3.499941800848045e-06, "loss": 0.8519, "step": 45230 }, { "epoch": 3.76, "learning_rate": 3.4998309453205108e-06, "loss": 0.8618, "step": 45240 }, { "epoch": 3.76, "learning_rate": 3.4997200897929775e-06, "loss": 0.8769, "step": 45250 }, { "epoch": 3.76, "learning_rate": 3.4996092342654434e-06, "loss": 0.8142, "step": 45260 }, { "epoch": 3.76, "learning_rate": 3.4994983787379096e-06, "loss": 0.8316, "step": 45270 }, { "epoch": 3.76, "learning_rate": 3.499387523210376e-06, "loss": 0.7513, "step": 45280 }, { "epoch": 3.76, "learning_rate": 3.4992766676828422e-06, "loss": 0.8618, "step": 45290 }, { "epoch": 3.77, "learning_rate": 3.499165812155308e-06, "loss": 0.8294, "step": 45300 }, { "epoch": 3.77, "learning_rate": 3.499054956627775e-06, "loss": 0.8566, "step": 45310 }, { "epoch": 3.77, "learning_rate": 3.4989441011002407e-06, "loss": 0.7979, "step": 45320 }, { "epoch": 3.77, "learning_rate": 3.498833245572707e-06, "loss": 0.814, "step": 45330 }, { "epoch": 3.77, "learning_rate": 3.4987223900451737e-06, "loss": 0.7923, "step": 45340 }, { "epoch": 3.77, "learning_rate": 3.4986115345176396e-06, "loss": 0.9065, "step": 45350 }, { "epoch": 3.77, "learning_rate": 3.4985006789901063e-06, "loss": 0.8245, "step": 45360 }, { "epoch": 3.77, "learning_rate": 3.498389823462572e-06, "loss": 0.8561, "step": 45370 }, { "epoch": 3.77, "learning_rate": 3.4982789679350385e-06, "loss": 0.8191, "step": 45380 }, { "epoch": 3.77, "learning_rate": 3.4981681124075048e-06, "loss": 0.8289, "step": 45390 }, { "epoch": 3.77, "learning_rate": 3.498057256879971e-06, "loss": 0.8602, "step": 45400 }, { "epoch": 3.77, "learning_rate": 3.497946401352437e-06, "loss": 0.8478, "step": 45410 }, { "epoch": 3.78, "learning_rate": 3.4978355458249037e-06, "loss": 0.7952, "step": 45420 }, { "epoch": 3.78, "learning_rate": 3.4977246902973695e-06, "loss": 0.8371, "step": 45430 }, { "epoch": 3.78, "learning_rate": 3.4976138347698362e-06, "loss": 0.755, "step": 45440 }, { "epoch": 3.78, "learning_rate": 3.4975029792423025e-06, "loss": 0.8554, "step": 45450 }, { "epoch": 3.78, "learning_rate": 3.4973921237147684e-06, "loss": 0.8407, "step": 45460 }, { "epoch": 3.78, "learning_rate": 3.497281268187235e-06, "loss": 0.8173, "step": 45470 }, { "epoch": 3.78, "learning_rate": 3.497170412659701e-06, "loss": 0.8413, "step": 45480 }, { "epoch": 3.78, "learning_rate": 3.4970595571321673e-06, "loss": 0.7498, "step": 45490 }, { "epoch": 3.78, "learning_rate": 3.4969487016046336e-06, "loss": 0.953, "step": 45500 }, { "epoch": 3.78, "learning_rate": 3.4968378460771e-06, "loss": 0.7944, "step": 45510 }, { "epoch": 3.78, "learning_rate": 3.496726990549566e-06, "loss": 0.8116, "step": 45520 }, { "epoch": 3.78, "learning_rate": 3.4966161350220325e-06, "loss": 0.8473, "step": 45530 }, { "epoch": 3.79, "learning_rate": 3.4965052794944984e-06, "loss": 0.8349, "step": 45540 }, { "epoch": 3.79, "learning_rate": 3.496394423966965e-06, "loss": 0.8546, "step": 45550 }, { "epoch": 3.79, "learning_rate": 3.496283568439431e-06, "loss": 0.8601, "step": 45560 }, { "epoch": 3.79, "learning_rate": 3.4961727129118972e-06, "loss": 0.7412, "step": 45570 }, { "epoch": 3.79, "learning_rate": 3.496061857384364e-06, "loss": 0.8607, "step": 45580 }, { "epoch": 3.79, "learning_rate": 3.49595100185683e-06, "loss": 0.8679, "step": 45590 }, { "epoch": 3.79, "learning_rate": 3.4958401463292965e-06, "loss": 0.9096, "step": 45600 }, { "epoch": 3.79, "learning_rate": 3.4957292908017624e-06, "loss": 0.8339, "step": 45610 }, { "epoch": 3.79, "learning_rate": 3.4956184352742287e-06, "loss": 0.8029, "step": 45620 }, { "epoch": 3.79, "learning_rate": 3.495507579746695e-06, "loss": 0.7827, "step": 45630 }, { "epoch": 3.79, "learning_rate": 3.4953967242191613e-06, "loss": 0.8322, "step": 45640 }, { "epoch": 3.79, "learning_rate": 3.495285868691627e-06, "loss": 0.8569, "step": 45650 }, { "epoch": 3.8, "learning_rate": 3.495175013164094e-06, "loss": 0.8327, "step": 45660 }, { "epoch": 3.8, "learning_rate": 3.4950641576365598e-06, "loss": 0.8423, "step": 45670 }, { "epoch": 3.8, "learning_rate": 3.4949533021090265e-06, "loss": 0.763, "step": 45680 }, { "epoch": 3.8, "learning_rate": 3.4948424465814924e-06, "loss": 0.8356, "step": 45690 }, { "epoch": 3.8, "learning_rate": 3.4947315910539587e-06, "loss": 0.886, "step": 45700 }, { "epoch": 3.8, "learning_rate": 3.4946207355264254e-06, "loss": 0.7907, "step": 45710 }, { "epoch": 3.8, "learning_rate": 3.4945098799988912e-06, "loss": 0.7902, "step": 45720 }, { "epoch": 3.8, "learning_rate": 3.4943990244713575e-06, "loss": 0.8624, "step": 45730 }, { "epoch": 3.8, "learning_rate": 3.494288168943824e-06, "loss": 0.8423, "step": 45740 }, { "epoch": 3.8, "learning_rate": 3.49417731341629e-06, "loss": 0.836, "step": 45750 }, { "epoch": 3.8, "learning_rate": 3.494066457888756e-06, "loss": 0.8696, "step": 45760 }, { "epoch": 3.8, "learning_rate": 3.4939556023612227e-06, "loss": 0.7961, "step": 45770 }, { "epoch": 3.81, "learning_rate": 3.4938447468336886e-06, "loss": 0.8037, "step": 45780 }, { "epoch": 3.81, "learning_rate": 3.4937338913061553e-06, "loss": 0.8516, "step": 45790 }, { "epoch": 3.81, "learning_rate": 3.493623035778621e-06, "loss": 0.845, "step": 45800 }, { "epoch": 3.81, "learning_rate": 3.4935121802510875e-06, "loss": 0.8253, "step": 45810 }, { "epoch": 3.81, "learning_rate": 3.493401324723554e-06, "loss": 0.8135, "step": 45820 }, { "epoch": 3.81, "learning_rate": 3.49329046919602e-06, "loss": 0.8241, "step": 45830 }, { "epoch": 3.81, "learning_rate": 3.4931796136684864e-06, "loss": 0.8752, "step": 45840 }, { "epoch": 3.81, "learning_rate": 3.4930687581409527e-06, "loss": 0.8158, "step": 45850 }, { "epoch": 3.81, "learning_rate": 3.492957902613419e-06, "loss": 0.8083, "step": 45860 }, { "epoch": 3.81, "learning_rate": 3.4928470470858853e-06, "loss": 0.8604, "step": 45870 }, { "epoch": 3.81, "learning_rate": 3.4927361915583515e-06, "loss": 0.7858, "step": 45880 }, { "epoch": 3.81, "learning_rate": 3.4926253360308174e-06, "loss": 0.9156, "step": 45890 }, { "epoch": 3.82, "learning_rate": 3.492514480503284e-06, "loss": 0.9174, "step": 45900 }, { "epoch": 3.82, "learning_rate": 3.49240362497575e-06, "loss": 0.8573, "step": 45910 }, { "epoch": 3.82, "learning_rate": 3.4922927694482163e-06, "loss": 0.8193, "step": 45920 }, { "epoch": 3.82, "learning_rate": 3.4921819139206826e-06, "loss": 0.8502, "step": 45930 }, { "epoch": 3.82, "learning_rate": 3.492071058393149e-06, "loss": 0.8087, "step": 45940 }, { "epoch": 3.82, "learning_rate": 3.4919602028656156e-06, "loss": 0.8269, "step": 45950 }, { "epoch": 3.82, "learning_rate": 3.4918493473380815e-06, "loss": 0.8655, "step": 45960 }, { "epoch": 3.82, "learning_rate": 3.4917384918105478e-06, "loss": 0.7967, "step": 45970 }, { "epoch": 3.82, "learning_rate": 3.491627636283014e-06, "loss": 0.8211, "step": 45980 }, { "epoch": 3.82, "learning_rate": 3.4915167807554804e-06, "loss": 0.8212, "step": 45990 }, { "epoch": 3.82, "learning_rate": 3.4914059252279462e-06, "loss": 0.8757, "step": 46000 }, { "epoch": 3.82, "learning_rate": 3.491295069700413e-06, "loss": 0.8552, "step": 46010 }, { "epoch": 3.83, "learning_rate": 3.491184214172879e-06, "loss": 0.7505, "step": 46020 }, { "epoch": 3.83, "learning_rate": 3.4910733586453456e-06, "loss": 0.9507, "step": 46030 }, { "epoch": 3.83, "learning_rate": 3.4909625031178114e-06, "loss": 0.8585, "step": 46040 }, { "epoch": 3.83, "learning_rate": 3.4908516475902777e-06, "loss": 0.8172, "step": 46050 }, { "epoch": 3.83, "learning_rate": 3.490740792062744e-06, "loss": 0.8354, "step": 46060 }, { "epoch": 3.83, "learning_rate": 3.4906299365352103e-06, "loss": 0.8002, "step": 46070 }, { "epoch": 3.83, "learning_rate": 3.4905190810076766e-06, "loss": 0.8643, "step": 46080 }, { "epoch": 3.83, "learning_rate": 3.490408225480143e-06, "loss": 0.8135, "step": 46090 }, { "epoch": 3.83, "learning_rate": 3.490297369952609e-06, "loss": 0.8183, "step": 46100 }, { "epoch": 3.83, "learning_rate": 3.490186514425075e-06, "loss": 0.7625, "step": 46110 }, { "epoch": 3.83, "learning_rate": 3.4900756588975418e-06, "loss": 0.8178, "step": 46120 }, { "epoch": 3.83, "learning_rate": 3.4899648033700077e-06, "loss": 0.7453, "step": 46130 }, { "epoch": 3.84, "learning_rate": 3.4898539478424744e-06, "loss": 0.7794, "step": 46140 }, { "epoch": 3.84, "learning_rate": 3.4897430923149402e-06, "loss": 0.8903, "step": 46150 }, { "epoch": 3.84, "learning_rate": 3.4896322367874065e-06, "loss": 0.8336, "step": 46160 }, { "epoch": 3.84, "learning_rate": 3.489521381259873e-06, "loss": 0.8005, "step": 46170 }, { "epoch": 3.84, "learning_rate": 3.489410525732339e-06, "loss": 0.8376, "step": 46180 }, { "epoch": 3.84, "learning_rate": 3.489299670204806e-06, "loss": 0.8389, "step": 46190 }, { "epoch": 3.84, "learning_rate": 3.4891888146772717e-06, "loss": 0.8931, "step": 46200 }, { "epoch": 3.84, "learning_rate": 3.489077959149738e-06, "loss": 0.8198, "step": 46210 }, { "epoch": 3.84, "learning_rate": 3.4889671036222043e-06, "loss": 0.84, "step": 46220 }, { "epoch": 3.84, "learning_rate": 3.4888562480946706e-06, "loss": 0.7833, "step": 46230 }, { "epoch": 3.84, "learning_rate": 3.4887453925671365e-06, "loss": 0.8534, "step": 46240 }, { "epoch": 3.84, "learning_rate": 3.488634537039603e-06, "loss": 0.9146, "step": 46250 }, { "epoch": 3.85, "learning_rate": 3.488523681512069e-06, "loss": 0.8689, "step": 46260 }, { "epoch": 3.85, "learning_rate": 3.4884128259845354e-06, "loss": 0.8023, "step": 46270 }, { "epoch": 3.85, "learning_rate": 3.4883019704570017e-06, "loss": 0.7544, "step": 46280 }, { "epoch": 3.85, "learning_rate": 3.488191114929468e-06, "loss": 0.7982, "step": 46290 }, { "epoch": 3.85, "learning_rate": 3.4880802594019343e-06, "loss": 0.8582, "step": 46300 }, { "epoch": 3.85, "learning_rate": 3.4879694038744006e-06, "loss": 0.8221, "step": 46310 }, { "epoch": 3.85, "learning_rate": 3.487858548346867e-06, "loss": 0.8468, "step": 46320 }, { "epoch": 3.85, "learning_rate": 3.487747692819333e-06, "loss": 0.8667, "step": 46330 }, { "epoch": 3.85, "learning_rate": 3.4876368372917994e-06, "loss": 0.7476, "step": 46340 }, { "epoch": 3.85, "learning_rate": 3.4875259817642653e-06, "loss": 0.8495, "step": 46350 }, { "epoch": 3.85, "learning_rate": 3.487415126236732e-06, "loss": 0.86, "step": 46360 }, { "epoch": 3.85, "learning_rate": 3.487304270709198e-06, "loss": 0.7519, "step": 46370 }, { "epoch": 3.86, "learning_rate": 3.4871934151816646e-06, "loss": 0.9129, "step": 46380 }, { "epoch": 3.86, "learning_rate": 3.4870825596541305e-06, "loss": 0.7757, "step": 46390 }, { "epoch": 3.86, "learning_rate": 3.4869717041265968e-06, "loss": 0.9334, "step": 46400 }, { "epoch": 3.86, "learning_rate": 3.486860848599063e-06, "loss": 0.8115, "step": 46410 }, { "epoch": 3.86, "learning_rate": 3.4867499930715294e-06, "loss": 0.7661, "step": 46420 }, { "epoch": 3.86, "learning_rate": 3.4866391375439952e-06, "loss": 0.8566, "step": 46430 }, { "epoch": 3.86, "learning_rate": 3.486528282016462e-06, "loss": 0.7704, "step": 46440 }, { "epoch": 3.86, "learning_rate": 3.4864174264889283e-06, "loss": 0.91, "step": 46450 }, { "epoch": 3.86, "learning_rate": 3.4863065709613946e-06, "loss": 0.8201, "step": 46460 }, { "epoch": 3.86, "learning_rate": 3.486195715433861e-06, "loss": 0.822, "step": 46470 }, { "epoch": 3.86, "learning_rate": 3.4860848599063267e-06, "loss": 0.7861, "step": 46480 }, { "epoch": 3.86, "learning_rate": 3.4859740043787934e-06, "loss": 0.914, "step": 46490 }, { "epoch": 3.87, "learning_rate": 3.4858631488512593e-06, "loss": 0.8196, "step": 46500 }, { "epoch": 3.87, "learning_rate": 3.4857522933237256e-06, "loss": 0.7775, "step": 46510 }, { "epoch": 3.87, "learning_rate": 3.485641437796192e-06, "loss": 0.7676, "step": 46520 }, { "epoch": 3.87, "learning_rate": 3.485530582268658e-06, "loss": 0.7755, "step": 46530 }, { "epoch": 3.87, "learning_rate": 3.485419726741124e-06, "loss": 0.8148, "step": 46540 }, { "epoch": 3.87, "learning_rate": 3.485308871213591e-06, "loss": 0.8992, "step": 46550 }, { "epoch": 3.87, "learning_rate": 3.485198015686057e-06, "loss": 0.8226, "step": 46560 }, { "epoch": 3.87, "learning_rate": 3.4850871601585234e-06, "loss": 0.8302, "step": 46570 }, { "epoch": 3.87, "learning_rate": 3.4849763046309897e-06, "loss": 0.7981, "step": 46580 }, { "epoch": 3.87, "learning_rate": 3.4848654491034556e-06, "loss": 0.8323, "step": 46590 }, { "epoch": 3.87, "learning_rate": 3.4847545935759223e-06, "loss": 0.8015, "step": 46600 }, { "epoch": 3.87, "learning_rate": 3.484643738048388e-06, "loss": 0.8173, "step": 46610 }, { "epoch": 3.87, "learning_rate": 3.4845328825208544e-06, "loss": 0.8624, "step": 46620 }, { "epoch": 3.88, "learning_rate": 3.4844220269933207e-06, "loss": 0.8633, "step": 46630 }, { "epoch": 3.88, "learning_rate": 3.484311171465787e-06, "loss": 0.856, "step": 46640 }, { "epoch": 3.88, "learning_rate": 3.4842003159382533e-06, "loss": 0.8382, "step": 46650 }, { "epoch": 3.88, "learning_rate": 3.4840894604107196e-06, "loss": 0.8623, "step": 46660 }, { "epoch": 3.88, "learning_rate": 3.4839786048831855e-06, "loss": 0.8408, "step": 46670 }, { "epoch": 3.88, "learning_rate": 3.483867749355652e-06, "loss": 0.6999, "step": 46680 }, { "epoch": 3.88, "learning_rate": 3.4837568938281185e-06, "loss": 0.8017, "step": 46690 }, { "epoch": 3.88, "learning_rate": 3.4836460383005844e-06, "loss": 0.8785, "step": 46700 }, { "epoch": 3.88, "learning_rate": 3.483535182773051e-06, "loss": 0.8005, "step": 46710 }, { "epoch": 3.88, "learning_rate": 3.483424327245517e-06, "loss": 0.8226, "step": 46720 }, { "epoch": 3.88, "learning_rate": 3.4833134717179837e-06, "loss": 0.8377, "step": 46730 }, { "epoch": 3.88, "learning_rate": 3.4832026161904496e-06, "loss": 0.7742, "step": 46740 }, { "epoch": 3.89, "learning_rate": 3.483091760662916e-06, "loss": 0.8505, "step": 46750 }, { "epoch": 3.89, "learning_rate": 3.482980905135382e-06, "loss": 0.8801, "step": 46760 }, { "epoch": 3.89, "learning_rate": 3.4828700496078484e-06, "loss": 0.7422, "step": 46770 }, { "epoch": 3.89, "learning_rate": 3.4827591940803143e-06, "loss": 0.8527, "step": 46780 }, { "epoch": 3.89, "learning_rate": 3.482648338552781e-06, "loss": 0.7918, "step": 46790 }, { "epoch": 3.89, "learning_rate": 3.482537483025247e-06, "loss": 0.8551, "step": 46800 }, { "epoch": 3.89, "learning_rate": 3.4824266274977136e-06, "loss": 0.8543, "step": 46810 }, { "epoch": 3.89, "learning_rate": 3.48231577197018e-06, "loss": 0.8152, "step": 46820 }, { "epoch": 3.89, "learning_rate": 3.482204916442646e-06, "loss": 0.8116, "step": 46830 }, { "epoch": 3.89, "learning_rate": 3.4820940609151125e-06, "loss": 0.8498, "step": 46840 }, { "epoch": 3.89, "learning_rate": 3.4819832053875784e-06, "loss": 0.8671, "step": 46850 }, { "epoch": 3.89, "learning_rate": 3.4818723498600447e-06, "loss": 0.8843, "step": 46860 }, { "epoch": 3.9, "learning_rate": 3.481761494332511e-06, "loss": 0.814, "step": 46870 }, { "epoch": 3.9, "learning_rate": 3.4816506388049773e-06, "loss": 0.7826, "step": 46880 }, { "epoch": 3.9, "learning_rate": 3.4815397832774436e-06, "loss": 0.7994, "step": 46890 }, { "epoch": 3.9, "learning_rate": 3.48142892774991e-06, "loss": 0.8878, "step": 46900 }, { "epoch": 3.9, "learning_rate": 3.4813180722223757e-06, "loss": 0.7818, "step": 46910 }, { "epoch": 3.9, "learning_rate": 3.4812072166948424e-06, "loss": 0.8076, "step": 46920 }, { "epoch": 3.9, "learning_rate": 3.4810963611673087e-06, "loss": 0.8672, "step": 46930 }, { "epoch": 3.9, "learning_rate": 3.4809855056397746e-06, "loss": 0.7602, "step": 46940 }, { "epoch": 3.9, "learning_rate": 3.4808746501122413e-06, "loss": 0.8392, "step": 46950 }, { "epoch": 3.9, "learning_rate": 3.480763794584707e-06, "loss": 0.8854, "step": 46960 }, { "epoch": 3.9, "learning_rate": 3.480652939057174e-06, "loss": 0.8163, "step": 46970 }, { "epoch": 3.9, "learning_rate": 3.48054208352964e-06, "loss": 0.814, "step": 46980 }, { "epoch": 3.91, "learning_rate": 3.480431228002106e-06, "loss": 0.8645, "step": 46990 }, { "epoch": 3.91, "learning_rate": 3.4803203724745724e-06, "loss": 0.8696, "step": 47000 }, { "epoch": 3.91, "learning_rate": 3.4802095169470387e-06, "loss": 0.85, "step": 47010 }, { "epoch": 3.91, "learning_rate": 3.4800986614195046e-06, "loss": 0.7744, "step": 47020 }, { "epoch": 3.91, "learning_rate": 3.4799878058919713e-06, "loss": 0.8366, "step": 47030 }, { "epoch": 3.91, "learning_rate": 3.479876950364437e-06, "loss": 0.8103, "step": 47040 }, { "epoch": 3.91, "learning_rate": 3.4797660948369034e-06, "loss": 0.8609, "step": 47050 }, { "epoch": 3.91, "learning_rate": 3.47965523930937e-06, "loss": 0.8085, "step": 47060 }, { "epoch": 3.91, "learning_rate": 3.479544383781836e-06, "loss": 0.8039, "step": 47070 }, { "epoch": 3.91, "learning_rate": 3.4794335282543028e-06, "loss": 0.8275, "step": 47080 }, { "epoch": 3.91, "learning_rate": 3.4793226727267686e-06, "loss": 0.8034, "step": 47090 }, { "epoch": 3.91, "learning_rate": 3.479211817199235e-06, "loss": 0.8648, "step": 47100 }, { "epoch": 3.92, "learning_rate": 3.4791009616717012e-06, "loss": 0.8665, "step": 47110 }, { "epoch": 3.92, "learning_rate": 3.4789901061441675e-06, "loss": 0.8148, "step": 47120 }, { "epoch": 3.92, "learning_rate": 3.4788792506166334e-06, "loss": 0.9079, "step": 47130 }, { "epoch": 3.92, "learning_rate": 3.4787683950891e-06, "loss": 0.8747, "step": 47140 }, { "epoch": 3.92, "learning_rate": 3.478657539561566e-06, "loss": 0.8301, "step": 47150 }, { "epoch": 3.92, "learning_rate": 3.4785466840340327e-06, "loss": 0.851, "step": 47160 }, { "epoch": 3.92, "learning_rate": 3.4784358285064986e-06, "loss": 0.8656, "step": 47170 }, { "epoch": 3.92, "learning_rate": 3.478324972978965e-06, "loss": 0.8782, "step": 47180 }, { "epoch": 3.92, "learning_rate": 3.4782141174514316e-06, "loss": 0.8119, "step": 47190 }, { "epoch": 3.92, "learning_rate": 3.4781032619238974e-06, "loss": 0.8458, "step": 47200 }, { "epoch": 3.92, "learning_rate": 3.4779924063963637e-06, "loss": 0.866, "step": 47210 }, { "epoch": 3.92, "learning_rate": 3.47788155086883e-06, "loss": 0.881, "step": 47220 }, { "epoch": 3.93, "learning_rate": 3.4777706953412963e-06, "loss": 0.8578, "step": 47230 }, { "epoch": 3.93, "learning_rate": 3.4776598398137626e-06, "loss": 0.7769, "step": 47240 }, { "epoch": 3.93, "learning_rate": 3.477548984286229e-06, "loss": 0.8708, "step": 47250 }, { "epoch": 3.93, "learning_rate": 3.477438128758695e-06, "loss": 0.789, "step": 47260 }, { "epoch": 3.93, "learning_rate": 3.4773272732311615e-06, "loss": 0.8173, "step": 47270 }, { "epoch": 3.93, "learning_rate": 3.4772164177036274e-06, "loss": 0.7845, "step": 47280 }, { "epoch": 3.93, "learning_rate": 3.4771055621760937e-06, "loss": 0.7847, "step": 47290 }, { "epoch": 3.93, "learning_rate": 3.4769947066485604e-06, "loss": 0.9625, "step": 47300 }, { "epoch": 3.93, "learning_rate": 3.4768838511210263e-06, "loss": 0.8192, "step": 47310 }, { "epoch": 3.93, "learning_rate": 3.476772995593493e-06, "loss": 0.7822, "step": 47320 }, { "epoch": 3.93, "learning_rate": 3.476662140065959e-06, "loss": 0.8205, "step": 47330 }, { "epoch": 3.93, "learning_rate": 3.476551284538425e-06, "loss": 0.8158, "step": 47340 }, { "epoch": 3.94, "learning_rate": 3.4764404290108915e-06, "loss": 0.8539, "step": 47350 }, { "epoch": 3.94, "learning_rate": 3.4763295734833578e-06, "loss": 0.8085, "step": 47360 }, { "epoch": 3.94, "learning_rate": 3.4762187179558236e-06, "loss": 0.8587, "step": 47370 }, { "epoch": 3.94, "learning_rate": 3.4761078624282903e-06, "loss": 0.7949, "step": 47380 }, { "epoch": 3.94, "learning_rate": 3.4759970069007562e-06, "loss": 0.8089, "step": 47390 }, { "epoch": 3.94, "learning_rate": 3.4758861513732225e-06, "loss": 0.8887, "step": 47400 }, { "epoch": 3.94, "learning_rate": 3.475775295845689e-06, "loss": 0.8107, "step": 47410 }, { "epoch": 3.94, "learning_rate": 3.475664440318155e-06, "loss": 0.8012, "step": 47420 }, { "epoch": 3.94, "learning_rate": 3.475553584790622e-06, "loss": 0.9214, "step": 47430 }, { "epoch": 3.94, "learning_rate": 3.4754427292630877e-06, "loss": 0.886, "step": 47440 }, { "epoch": 3.94, "learning_rate": 3.475331873735554e-06, "loss": 0.8988, "step": 47450 }, { "epoch": 3.94, "learning_rate": 3.4752210182080203e-06, "loss": 0.866, "step": 47460 }, { "epoch": 3.95, "learning_rate": 3.4751101626804866e-06, "loss": 0.8799, "step": 47470 }, { "epoch": 3.95, "learning_rate": 3.4749993071529524e-06, "loss": 0.8548, "step": 47480 }, { "epoch": 3.95, "learning_rate": 3.474888451625419e-06, "loss": 0.8538, "step": 47490 }, { "epoch": 3.95, "learning_rate": 3.474777596097885e-06, "loss": 0.8669, "step": 47500 }, { "epoch": 3.95, "learning_rate": 3.4746667405703518e-06, "loss": 0.8598, "step": 47510 }, { "epoch": 3.95, "learning_rate": 3.4745558850428176e-06, "loss": 0.8133, "step": 47520 }, { "epoch": 3.95, "learning_rate": 3.474445029515284e-06, "loss": 0.8151, "step": 47530 }, { "epoch": 3.95, "learning_rate": 3.4743341739877506e-06, "loss": 0.8112, "step": 47540 }, { "epoch": 3.95, "learning_rate": 3.4742233184602165e-06, "loss": 0.891, "step": 47550 }, { "epoch": 3.95, "learning_rate": 3.474112462932683e-06, "loss": 0.7985, "step": 47560 }, { "epoch": 3.95, "learning_rate": 3.474001607405149e-06, "loss": 0.8223, "step": 47570 }, { "epoch": 3.95, "learning_rate": 3.4738907518776154e-06, "loss": 0.8209, "step": 47580 }, { "epoch": 3.96, "learning_rate": 3.4737798963500817e-06, "loss": 0.8389, "step": 47590 }, { "epoch": 3.96, "learning_rate": 3.473669040822548e-06, "loss": 0.8497, "step": 47600 }, { "epoch": 3.96, "learning_rate": 3.473558185295014e-06, "loss": 0.8036, "step": 47610 }, { "epoch": 3.96, "learning_rate": 3.4734473297674806e-06, "loss": 0.8747, "step": 47620 }, { "epoch": 3.96, "learning_rate": 3.4733364742399465e-06, "loss": 0.76, "step": 47630 }, { "epoch": 3.96, "learning_rate": 3.4732256187124127e-06, "loss": 0.8084, "step": 47640 }, { "epoch": 3.96, "learning_rate": 3.473114763184879e-06, "loss": 0.8989, "step": 47650 }, { "epoch": 3.96, "learning_rate": 3.4730039076573453e-06, "loss": 0.8501, "step": 47660 }, { "epoch": 3.96, "learning_rate": 3.472893052129812e-06, "loss": 0.8174, "step": 47670 }, { "epoch": 3.96, "learning_rate": 3.472782196602278e-06, "loss": 0.8232, "step": 47680 }, { "epoch": 3.96, "learning_rate": 3.4726713410747442e-06, "loss": 0.8179, "step": 47690 }, { "epoch": 3.96, "learning_rate": 3.4725604855472105e-06, "loss": 0.7989, "step": 47700 }, { "epoch": 3.97, "learning_rate": 3.472449630019677e-06, "loss": 0.8595, "step": 47710 }, { "epoch": 3.97, "learning_rate": 3.4723387744921427e-06, "loss": 0.8354, "step": 47720 }, { "epoch": 3.97, "learning_rate": 3.4722279189646094e-06, "loss": 0.8469, "step": 47730 }, { "epoch": 3.97, "learning_rate": 3.4721170634370753e-06, "loss": 0.869, "step": 47740 }, { "epoch": 3.97, "learning_rate": 3.472006207909542e-06, "loss": 0.8493, "step": 47750 }, { "epoch": 3.97, "learning_rate": 3.471895352382008e-06, "loss": 0.8564, "step": 47760 }, { "epoch": 3.97, "learning_rate": 3.471784496854474e-06, "loss": 0.7715, "step": 47770 }, { "epoch": 3.97, "learning_rate": 3.4716736413269405e-06, "loss": 0.7944, "step": 47780 }, { "epoch": 3.97, "learning_rate": 3.4715627857994068e-06, "loss": 0.8231, "step": 47790 }, { "epoch": 3.97, "learning_rate": 3.471451930271873e-06, "loss": 0.8709, "step": 47800 }, { "epoch": 3.97, "learning_rate": 3.4713410747443393e-06, "loss": 0.9156, "step": 47810 }, { "epoch": 3.97, "learning_rate": 3.4712302192168056e-06, "loss": 0.8522, "step": 47820 }, { "epoch": 3.98, "learning_rate": 3.4711193636892715e-06, "loss": 0.8316, "step": 47830 }, { "epoch": 3.98, "learning_rate": 3.4710085081617382e-06, "loss": 0.8325, "step": 47840 }, { "epoch": 3.98, "learning_rate": 3.470897652634204e-06, "loss": 0.8897, "step": 47850 }, { "epoch": 3.98, "learning_rate": 3.470786797106671e-06, "loss": 0.8723, "step": 47860 }, { "epoch": 3.98, "learning_rate": 3.4706759415791367e-06, "loss": 0.8086, "step": 47870 }, { "epoch": 3.98, "learning_rate": 3.470565086051603e-06, "loss": 0.8106, "step": 47880 }, { "epoch": 3.98, "learning_rate": 3.4704542305240693e-06, "loss": 0.865, "step": 47890 }, { "epoch": 3.98, "learning_rate": 3.4703433749965356e-06, "loss": 0.8842, "step": 47900 }, { "epoch": 3.98, "learning_rate": 3.470232519469002e-06, "loss": 0.8703, "step": 47910 }, { "epoch": 3.98, "learning_rate": 3.470121663941468e-06, "loss": 0.755, "step": 47920 }, { "epoch": 3.98, "learning_rate": 3.4700108084139345e-06, "loss": 0.818, "step": 47930 }, { "epoch": 3.98, "learning_rate": 3.4698999528864008e-06, "loss": 0.7993, "step": 47940 }, { "epoch": 3.99, "learning_rate": 3.469789097358867e-06, "loss": 0.8528, "step": 47950 }, { "epoch": 3.99, "learning_rate": 3.469678241831333e-06, "loss": 0.8275, "step": 47960 }, { "epoch": 3.99, "learning_rate": 3.4695673863037996e-06, "loss": 0.803, "step": 47970 }, { "epoch": 3.99, "learning_rate": 3.4694565307762655e-06, "loss": 0.8432, "step": 47980 }, { "epoch": 3.99, "learning_rate": 3.469345675248732e-06, "loss": 0.8616, "step": 47990 }, { "epoch": 3.99, "learning_rate": 3.469234819721198e-06, "loss": 0.8864, "step": 48000 }, { "epoch": 3.99, "learning_rate": 3.4691239641936644e-06, "loss": 0.805, "step": 48010 }, { "epoch": 3.99, "learning_rate": 3.4690131086661307e-06, "loss": 0.8156, "step": 48020 }, { "epoch": 3.99, "learning_rate": 3.468902253138597e-06, "loss": 0.8356, "step": 48030 }, { "epoch": 3.99, "learning_rate": 3.4687913976110633e-06, "loss": 0.7822, "step": 48040 }, { "epoch": 3.99, "learning_rate": 3.4686805420835296e-06, "loss": 0.926, "step": 48050 }, { "epoch": 3.99, "learning_rate": 3.468569686555996e-06, "loss": 0.8284, "step": 48060 }, { "epoch": 4.0, "learning_rate": 3.4684588310284618e-06, "loss": 0.8471, "step": 48070 }, { "epoch": 4.0, "learning_rate": 3.4683479755009285e-06, "loss": 0.8395, "step": 48080 }, { "epoch": 4.0, "learning_rate": 3.4682371199733943e-06, "loss": 0.882, "step": 48090 }, { "epoch": 4.0, "learning_rate": 3.468126264445861e-06, "loss": 0.784, "step": 48100 }, { "epoch": 4.0, "learning_rate": 3.468015408918327e-06, "loss": 0.9066, "step": 48110 }, { "epoch": 4.0, "learning_rate": 3.4679045533907932e-06, "loss": 0.767, "step": 48120 }, { "epoch": 4.0, "eval_loss": 1.061669111251831, "eval_runtime": 346.8441, "eval_samples_per_second": 7.71, "eval_steps_per_second": 3.855, "eval_wer": 0.6526253337288639, "step": 48124 }, { "epoch": 4.0, "learning_rate": 3.4677936978632595e-06, "loss": 0.8082, "step": 48130 }, { "epoch": 4.0, "learning_rate": 3.467682842335726e-06, "loss": 0.804, "step": 48140 }, { "epoch": 4.0, "learning_rate": 3.4675719868081917e-06, "loss": 0.8498, "step": 48150 }, { "epoch": 4.0, "learning_rate": 3.4674611312806584e-06, "loss": 0.8567, "step": 48160 }, { "epoch": 4.0, "learning_rate": 3.4673502757531247e-06, "loss": 0.835, "step": 48170 }, { "epoch": 4.0, "learning_rate": 3.467239420225591e-06, "loss": 0.841, "step": 48180 }, { "epoch": 4.01, "learning_rate": 3.4671285646980573e-06, "loss": 0.8051, "step": 48190 }, { "epoch": 4.01, "learning_rate": 3.467017709170523e-06, "loss": 0.8412, "step": 48200 }, { "epoch": 4.01, "learning_rate": 3.46690685364299e-06, "loss": 0.7802, "step": 48210 }, { "epoch": 4.01, "learning_rate": 3.4667959981154558e-06, "loss": 0.812, "step": 48220 }, { "epoch": 4.01, "learning_rate": 3.466685142587922e-06, "loss": 0.8411, "step": 48230 }, { "epoch": 4.01, "learning_rate": 3.4665742870603884e-06, "loss": 0.8403, "step": 48240 }, { "epoch": 4.01, "learning_rate": 3.4664634315328546e-06, "loss": 0.8039, "step": 48250 }, { "epoch": 4.01, "learning_rate": 3.4663525760053205e-06, "loss": 0.8627, "step": 48260 }, { "epoch": 4.01, "learning_rate": 3.4662417204777872e-06, "loss": 0.8312, "step": 48270 }, { "epoch": 4.01, "learning_rate": 3.4661308649502535e-06, "loss": 0.9038, "step": 48280 }, { "epoch": 4.01, "learning_rate": 3.46602000942272e-06, "loss": 0.7702, "step": 48290 }, { "epoch": 4.01, "learning_rate": 3.465909153895186e-06, "loss": 0.7988, "step": 48300 }, { "epoch": 4.02, "learning_rate": 3.465798298367652e-06, "loss": 0.7796, "step": 48310 }, { "epoch": 4.02, "learning_rate": 3.4656874428401187e-06, "loss": 0.877, "step": 48320 }, { "epoch": 4.02, "learning_rate": 3.4655765873125846e-06, "loss": 0.8894, "step": 48330 }, { "epoch": 4.02, "learning_rate": 3.465465731785051e-06, "loss": 0.8642, "step": 48340 }, { "epoch": 4.02, "learning_rate": 3.465354876257517e-06, "loss": 0.839, "step": 48350 }, { "epoch": 4.02, "learning_rate": 3.4652440207299835e-06, "loss": 0.8273, "step": 48360 }, { "epoch": 4.02, "learning_rate": 3.4651331652024498e-06, "loss": 0.7741, "step": 48370 }, { "epoch": 4.02, "learning_rate": 3.465022309674916e-06, "loss": 0.8812, "step": 48380 }, { "epoch": 4.02, "learning_rate": 3.464911454147382e-06, "loss": 0.7723, "step": 48390 }, { "epoch": 4.02, "learning_rate": 3.4648005986198487e-06, "loss": 0.9332, "step": 48400 }, { "epoch": 4.02, "learning_rate": 3.464689743092315e-06, "loss": 0.8164, "step": 48410 }, { "epoch": 4.02, "learning_rate": 3.464578887564781e-06, "loss": 0.7384, "step": 48420 }, { "epoch": 4.03, "learning_rate": 3.4644680320372475e-06, "loss": 0.8387, "step": 48430 }, { "epoch": 4.03, "learning_rate": 3.4643571765097134e-06, "loss": 0.8734, "step": 48440 }, { "epoch": 4.03, "learning_rate": 3.46424632098218e-06, "loss": 0.8173, "step": 48450 }, { "epoch": 4.03, "learning_rate": 3.464135465454646e-06, "loss": 0.8044, "step": 48460 }, { "epoch": 4.03, "learning_rate": 3.4640246099271123e-06, "loss": 0.8368, "step": 48470 }, { "epoch": 4.03, "learning_rate": 3.4639137543995786e-06, "loss": 0.8502, "step": 48480 }, { "epoch": 4.03, "learning_rate": 3.463802898872045e-06, "loss": 0.8417, "step": 48490 }, { "epoch": 4.03, "learning_rate": 3.4637031288972644e-06, "loss": 0.7893, "step": 48500 }, { "epoch": 4.03, "learning_rate": 3.4635922733697307e-06, "loss": 0.7786, "step": 48510 }, { "epoch": 4.03, "learning_rate": 3.463481417842197e-06, "loss": 0.7628, "step": 48520 }, { "epoch": 4.03, "learning_rate": 3.4633705623146633e-06, "loss": 0.8499, "step": 48530 }, { "epoch": 4.03, "learning_rate": 3.4632597067871296e-06, "loss": 0.8201, "step": 48540 }, { "epoch": 4.04, "learning_rate": 3.463148851259596e-06, "loss": 0.8025, "step": 48550 }, { "epoch": 4.04, "learning_rate": 3.4630379957320618e-06, "loss": 0.8163, "step": 48560 }, { "epoch": 4.04, "learning_rate": 3.4629271402045285e-06, "loss": 0.7889, "step": 48570 }, { "epoch": 4.04, "learning_rate": 3.4628162846769944e-06, "loss": 0.8755, "step": 48580 }, { "epoch": 4.04, "learning_rate": 3.4627054291494607e-06, "loss": 0.8835, "step": 48590 }, { "epoch": 4.04, "learning_rate": 3.462594573621927e-06, "loss": 0.8475, "step": 48600 }, { "epoch": 4.04, "learning_rate": 3.4624837180943933e-06, "loss": 0.8949, "step": 48610 }, { "epoch": 4.04, "learning_rate": 3.46237286256686e-06, "loss": 0.7651, "step": 48620 }, { "epoch": 4.04, "learning_rate": 3.462262007039326e-06, "loss": 0.9289, "step": 48630 }, { "epoch": 4.04, "learning_rate": 3.462151151511792e-06, "loss": 0.7821, "step": 48640 }, { "epoch": 4.04, "learning_rate": 3.4620402959842584e-06, "loss": 0.7984, "step": 48650 }, { "epoch": 4.04, "learning_rate": 3.4619294404567247e-06, "loss": 0.7885, "step": 48660 }, { "epoch": 4.05, "learning_rate": 3.4618185849291906e-06, "loss": 0.8353, "step": 48670 }, { "epoch": 4.05, "learning_rate": 3.4617077294016573e-06, "loss": 0.9352, "step": 48680 }, { "epoch": 4.05, "learning_rate": 3.461596873874123e-06, "loss": 0.7823, "step": 48690 }, { "epoch": 4.05, "learning_rate": 3.46148601834659e-06, "loss": 0.8764, "step": 48700 }, { "epoch": 4.05, "learning_rate": 3.4613751628190558e-06, "loss": 0.8603, "step": 48710 }, { "epoch": 4.05, "learning_rate": 3.461264307291522e-06, "loss": 0.8992, "step": 48720 }, { "epoch": 4.05, "learning_rate": 3.4611534517639884e-06, "loss": 0.9079, "step": 48730 }, { "epoch": 4.05, "learning_rate": 3.4610425962364547e-06, "loss": 0.8023, "step": 48740 }, { "epoch": 4.05, "learning_rate": 3.460931740708921e-06, "loss": 0.7679, "step": 48750 }, { "epoch": 4.05, "learning_rate": 3.4608208851813873e-06, "loss": 0.9023, "step": 48760 }, { "epoch": 4.05, "learning_rate": 3.4607100296538536e-06, "loss": 0.8299, "step": 48770 }, { "epoch": 4.05, "learning_rate": 3.4605991741263194e-06, "loss": 0.8719, "step": 48780 }, { "epoch": 4.06, "learning_rate": 3.460488318598786e-06, "loss": 0.7904, "step": 48790 }, { "epoch": 4.06, "learning_rate": 3.460377463071252e-06, "loss": 0.8736, "step": 48800 }, { "epoch": 4.06, "learning_rate": 3.4602666075437187e-06, "loss": 0.7832, "step": 48810 }, { "epoch": 4.06, "learning_rate": 3.4601557520161846e-06, "loss": 0.7401, "step": 48820 }, { "epoch": 4.06, "learning_rate": 3.460044896488651e-06, "loss": 0.854, "step": 48830 }, { "epoch": 4.06, "learning_rate": 3.459934040961117e-06, "loss": 0.859, "step": 48840 }, { "epoch": 4.06, "learning_rate": 3.4598231854335835e-06, "loss": 0.8352, "step": 48850 }, { "epoch": 4.06, "learning_rate": 3.45971232990605e-06, "loss": 0.8278, "step": 48860 }, { "epoch": 4.06, "learning_rate": 3.459601474378516e-06, "loss": 0.8192, "step": 48870 }, { "epoch": 4.06, "learning_rate": 3.4594906188509824e-06, "loss": 0.8986, "step": 48880 }, { "epoch": 4.06, "learning_rate": 3.4593797633234487e-06, "loss": 0.8245, "step": 48890 }, { "epoch": 4.06, "learning_rate": 3.459268907795915e-06, "loss": 0.8303, "step": 48900 }, { "epoch": 4.07, "learning_rate": 3.459158052268381e-06, "loss": 0.7932, "step": 48910 }, { "epoch": 4.07, "learning_rate": 3.4590471967408476e-06, "loss": 0.8353, "step": 48920 }, { "epoch": 4.07, "learning_rate": 3.4589363412133134e-06, "loss": 0.8349, "step": 48930 }, { "epoch": 4.07, "learning_rate": 3.4588254856857797e-06, "loss": 0.8255, "step": 48940 }, { "epoch": 4.07, "learning_rate": 3.458714630158246e-06, "loss": 0.7936, "step": 48950 }, { "epoch": 4.07, "learning_rate": 3.4586037746307123e-06, "loss": 0.7724, "step": 48960 }, { "epoch": 4.07, "learning_rate": 3.4584929191031786e-06, "loss": 0.8159, "step": 48970 }, { "epoch": 4.07, "learning_rate": 3.458382063575645e-06, "loss": 0.9101, "step": 48980 }, { "epoch": 4.07, "learning_rate": 3.458271208048111e-06, "loss": 0.8722, "step": 48990 }, { "epoch": 4.07, "learning_rate": 3.4581603525205775e-06, "loss": 0.8145, "step": 49000 }, { "epoch": 4.07, "learning_rate": 3.458049496993044e-06, "loss": 0.816, "step": 49010 }, { "epoch": 4.07, "learning_rate": 3.4579386414655097e-06, "loss": 0.7729, "step": 49020 }, { "epoch": 4.08, "learning_rate": 3.4578277859379764e-06, "loss": 0.8173, "step": 49030 }, { "epoch": 4.08, "learning_rate": 3.4577169304104423e-06, "loss": 0.8163, "step": 49040 }, { "epoch": 4.08, "learning_rate": 3.457606074882909e-06, "loss": 0.8308, "step": 49050 }, { "epoch": 4.08, "learning_rate": 3.457495219355375e-06, "loss": 0.7595, "step": 49060 }, { "epoch": 4.08, "learning_rate": 3.457384363827841e-06, "loss": 0.8116, "step": 49070 }, { "epoch": 4.08, "learning_rate": 3.4572735083003074e-06, "loss": 0.9142, "step": 49080 }, { "epoch": 4.08, "learning_rate": 3.4571626527727737e-06, "loss": 0.8261, "step": 49090 }, { "epoch": 4.08, "learning_rate": 3.4570517972452396e-06, "loss": 0.897, "step": 49100 }, { "epoch": 4.08, "learning_rate": 3.4569409417177063e-06, "loss": 0.8288, "step": 49110 }, { "epoch": 4.08, "learning_rate": 3.4568300861901726e-06, "loss": 0.7804, "step": 49120 }, { "epoch": 4.08, "learning_rate": 3.456719230662639e-06, "loss": 0.9175, "step": 49130 }, { "epoch": 4.08, "learning_rate": 3.456608375135105e-06, "loss": 0.8684, "step": 49140 }, { "epoch": 4.09, "learning_rate": 3.456497519607571e-06, "loss": 0.8306, "step": 49150 }, { "epoch": 4.09, "learning_rate": 3.456386664080038e-06, "loss": 0.9425, "step": 49160 }, { "epoch": 4.09, "learning_rate": 3.4562758085525037e-06, "loss": 0.8414, "step": 49170 }, { "epoch": 4.09, "learning_rate": 3.45616495302497e-06, "loss": 0.8379, "step": 49180 }, { "epoch": 4.09, "learning_rate": 3.4560540974974363e-06, "loss": 0.8691, "step": 49190 }, { "epoch": 4.09, "learning_rate": 3.4559432419699026e-06, "loss": 0.8305, "step": 49200 }, { "epoch": 4.09, "learning_rate": 3.4558323864423684e-06, "loss": 0.8462, "step": 49210 }, { "epoch": 4.09, "learning_rate": 3.455721530914835e-06, "loss": 0.8252, "step": 49220 }, { "epoch": 4.09, "learning_rate": 3.4556106753873014e-06, "loss": 0.8153, "step": 49230 }, { "epoch": 4.09, "learning_rate": 3.4554998198597677e-06, "loss": 0.8076, "step": 49240 }, { "epoch": 4.09, "learning_rate": 3.455388964332234e-06, "loss": 0.8515, "step": 49250 }, { "epoch": 4.09, "learning_rate": 3.4552891943574536e-06, "loss": 0.8125, "step": 49260 }, { "epoch": 4.1, "learning_rate": 3.4551783388299194e-06, "loss": 0.8606, "step": 49270 }, { "epoch": 4.1, "learning_rate": 3.455067483302386e-06, "loss": 0.9014, "step": 49280 }, { "epoch": 4.1, "learning_rate": 3.454956627774852e-06, "loss": 0.826, "step": 49290 }, { "epoch": 4.1, "learning_rate": 3.4548457722473188e-06, "loss": 0.7639, "step": 49300 }, { "epoch": 4.1, "learning_rate": 3.4547349167197846e-06, "loss": 0.7877, "step": 49310 }, { "epoch": 4.1, "learning_rate": 3.454624061192251e-06, "loss": 0.8341, "step": 49320 }, { "epoch": 4.1, "learning_rate": 3.4545132056647176e-06, "loss": 0.8552, "step": 49330 }, { "epoch": 4.1, "learning_rate": 3.4544023501371835e-06, "loss": 0.8206, "step": 49340 }, { "epoch": 4.1, "learning_rate": 3.45429149460965e-06, "loss": 0.818, "step": 49350 }, { "epoch": 4.1, "learning_rate": 3.454180639082116e-06, "loss": 0.794, "step": 49360 }, { "epoch": 4.1, "learning_rate": 3.4540697835545824e-06, "loss": 0.7963, "step": 49370 }, { "epoch": 4.1, "learning_rate": 3.4539589280270483e-06, "loss": 0.8679, "step": 49380 }, { "epoch": 4.11, "learning_rate": 3.453848072499515e-06, "loss": 0.8846, "step": 49390 }, { "epoch": 4.11, "learning_rate": 3.453737216971981e-06, "loss": 0.8501, "step": 49400 }, { "epoch": 4.11, "learning_rate": 3.4536263614444476e-06, "loss": 0.8183, "step": 49410 }, { "epoch": 4.11, "learning_rate": 3.4535155059169135e-06, "loss": 0.8107, "step": 49420 }, { "epoch": 4.11, "learning_rate": 3.4534046503893797e-06, "loss": 0.849, "step": 49430 }, { "epoch": 4.11, "learning_rate": 3.4532937948618465e-06, "loss": 0.9008, "step": 49440 }, { "epoch": 4.11, "learning_rate": 3.4531829393343123e-06, "loss": 0.8467, "step": 49450 }, { "epoch": 4.11, "learning_rate": 3.4530720838067786e-06, "loss": 0.8854, "step": 49460 }, { "epoch": 4.11, "learning_rate": 3.452961228279245e-06, "loss": 0.818, "step": 49470 }, { "epoch": 4.11, "learning_rate": 3.4528503727517112e-06, "loss": 0.8718, "step": 49480 }, { "epoch": 4.11, "learning_rate": 3.4527395172241775e-06, "loss": 0.7928, "step": 49490 }, { "epoch": 4.11, "learning_rate": 3.452628661696644e-06, "loss": 0.7587, "step": 49500 }, { "epoch": 4.12, "learning_rate": 3.4525178061691097e-06, "loss": 0.8694, "step": 49510 }, { "epoch": 4.12, "learning_rate": 3.4524069506415764e-06, "loss": 0.855, "step": 49520 }, { "epoch": 4.12, "learning_rate": 3.4522960951140423e-06, "loss": 0.7739, "step": 49530 }, { "epoch": 4.12, "learning_rate": 3.4521852395865086e-06, "loss": 0.8452, "step": 49540 }, { "epoch": 4.12, "learning_rate": 3.452074384058975e-06, "loss": 0.8375, "step": 49550 }, { "epoch": 4.12, "learning_rate": 3.451963528531441e-06, "loss": 0.7805, "step": 49560 }, { "epoch": 4.12, "learning_rate": 3.451852673003908e-06, "loss": 0.8597, "step": 49570 }, { "epoch": 4.12, "learning_rate": 3.4517418174763738e-06, "loss": 0.8739, "step": 49580 }, { "epoch": 4.12, "learning_rate": 3.45163096194884e-06, "loss": 0.7824, "step": 49590 }, { "epoch": 4.12, "learning_rate": 3.4515201064213063e-06, "loss": 0.7633, "step": 49600 }, { "epoch": 4.12, "learning_rate": 3.4514092508937726e-06, "loss": 0.7707, "step": 49610 }, { "epoch": 4.12, "learning_rate": 3.4512983953662385e-06, "loss": 0.8696, "step": 49620 }, { "epoch": 4.13, "learning_rate": 3.4511875398387052e-06, "loss": 0.8631, "step": 49630 }, { "epoch": 4.13, "learning_rate": 3.451076684311171e-06, "loss": 0.813, "step": 49640 }, { "epoch": 4.13, "learning_rate": 3.450965828783638e-06, "loss": 0.882, "step": 49650 }, { "epoch": 4.13, "learning_rate": 3.4508549732561037e-06, "loss": 0.8567, "step": 49660 }, { "epoch": 4.13, "learning_rate": 3.45074411772857e-06, "loss": 0.8323, "step": 49670 }, { "epoch": 4.13, "learning_rate": 3.4506332622010363e-06, "loss": 0.9134, "step": 49680 }, { "epoch": 4.13, "learning_rate": 3.4505224066735026e-06, "loss": 0.8256, "step": 49690 }, { "epoch": 4.13, "learning_rate": 3.450411551145969e-06, "loss": 0.8464, "step": 49700 }, { "epoch": 4.13, "learning_rate": 3.450300695618435e-06, "loss": 0.7879, "step": 49710 }, { "epoch": 4.13, "learning_rate": 3.4501898400909015e-06, "loss": 0.8235, "step": 49720 }, { "epoch": 4.13, "learning_rate": 3.4500789845633673e-06, "loss": 0.8465, "step": 49730 }, { "epoch": 4.13, "learning_rate": 3.449968129035834e-06, "loss": 0.8793, "step": 49740 }, { "epoch": 4.14, "learning_rate": 3.4498572735083e-06, "loss": 0.8288, "step": 49750 }, { "epoch": 4.14, "learning_rate": 3.4497464179807666e-06, "loss": 0.796, "step": 49760 }, { "epoch": 4.14, "learning_rate": 3.4496355624532325e-06, "loss": 0.8344, "step": 49770 }, { "epoch": 4.14, "learning_rate": 3.449524706925699e-06, "loss": 0.8661, "step": 49780 }, { "epoch": 4.14, "learning_rate": 3.449413851398165e-06, "loss": 0.8201, "step": 49790 }, { "epoch": 4.14, "learning_rate": 3.4493029958706314e-06, "loss": 0.8277, "step": 49800 }, { "epoch": 4.14, "learning_rate": 3.4491921403430977e-06, "loss": 0.8645, "step": 49810 }, { "epoch": 4.14, "learning_rate": 3.449081284815564e-06, "loss": 0.8402, "step": 49820 }, { "epoch": 4.14, "learning_rate": 3.4489704292880303e-06, "loss": 0.8641, "step": 49830 }, { "epoch": 4.14, "learning_rate": 3.4488595737604966e-06, "loss": 0.7829, "step": 49840 }, { "epoch": 4.14, "learning_rate": 3.448748718232963e-06, "loss": 0.7713, "step": 49850 }, { "epoch": 4.14, "learning_rate": 3.4486378627054288e-06, "loss": 0.8184, "step": 49860 }, { "epoch": 4.15, "learning_rate": 3.4485270071778955e-06, "loss": 0.8114, "step": 49870 }, { "epoch": 4.15, "learning_rate": 3.4484161516503613e-06, "loss": 0.9061, "step": 49880 }, { "epoch": 4.15, "learning_rate": 3.4483052961228276e-06, "loss": 0.8018, "step": 49890 }, { "epoch": 4.15, "learning_rate": 3.448194440595294e-06, "loss": 0.8067, "step": 49900 }, { "epoch": 4.15, "learning_rate": 3.4480835850677602e-06, "loss": 0.8429, "step": 49910 }, { "epoch": 4.15, "learning_rate": 3.4479727295402265e-06, "loss": 0.7814, "step": 49920 }, { "epoch": 4.15, "learning_rate": 3.447861874012693e-06, "loss": 0.8665, "step": 49930 }, { "epoch": 4.15, "learning_rate": 3.447751018485159e-06, "loss": 0.8619, "step": 49940 }, { "epoch": 4.15, "learning_rate": 3.4476401629576254e-06, "loss": 0.8138, "step": 49950 }, { "epoch": 4.15, "learning_rate": 3.4475293074300917e-06, "loss": 0.8048, "step": 49960 }, { "epoch": 4.15, "learning_rate": 3.4474184519025576e-06, "loss": 0.8321, "step": 49970 }, { "epoch": 4.15, "learning_rate": 3.4473075963750243e-06, "loss": 0.8777, "step": 49980 }, { "epoch": 4.16, "learning_rate": 3.44719674084749e-06, "loss": 0.8521, "step": 49990 }, { "epoch": 4.16, "learning_rate": 3.447085885319957e-06, "loss": 0.8809, "step": 50000 }, { "epoch": 4.16, "learning_rate": 3.4469750297924228e-06, "loss": 0.7673, "step": 50010 }, { "epoch": 4.16, "learning_rate": 3.446864174264889e-06, "loss": 0.7925, "step": 50020 }, { "epoch": 4.16, "learning_rate": 3.4467533187373554e-06, "loss": 0.8584, "step": 50030 }, { "epoch": 4.16, "learning_rate": 3.4466424632098216e-06, "loss": 0.7823, "step": 50040 }, { "epoch": 4.16, "learning_rate": 3.446531607682288e-06, "loss": 0.823, "step": 50050 }, { "epoch": 4.16, "learning_rate": 3.4464207521547542e-06, "loss": 0.8276, "step": 50060 }, { "epoch": 4.16, "learning_rate": 3.4463098966272205e-06, "loss": 0.7674, "step": 50070 }, { "epoch": 4.16, "learning_rate": 3.446199041099687e-06, "loss": 0.8618, "step": 50080 }, { "epoch": 4.16, "learning_rate": 3.446088185572153e-06, "loss": 0.8478, "step": 50090 }, { "epoch": 4.16, "learning_rate": 3.445977330044619e-06, "loss": 0.8126, "step": 50100 }, { "epoch": 4.17, "learning_rate": 3.4458664745170857e-06, "loss": 0.7695, "step": 50110 }, { "epoch": 4.17, "learning_rate": 3.4457556189895516e-06, "loss": 0.8356, "step": 50120 }, { "epoch": 4.17, "learning_rate": 3.445644763462018e-06, "loss": 0.8575, "step": 50130 }, { "epoch": 4.17, "learning_rate": 3.445533907934484e-06, "loss": 0.867, "step": 50140 }, { "epoch": 4.17, "learning_rate": 3.4454230524069505e-06, "loss": 0.7967, "step": 50150 }, { "epoch": 4.17, "learning_rate": 3.4453121968794163e-06, "loss": 0.8515, "step": 50160 }, { "epoch": 4.17, "learning_rate": 3.445201341351883e-06, "loss": 0.831, "step": 50170 }, { "epoch": 4.17, "learning_rate": 3.4450904858243494e-06, "loss": 0.8934, "step": 50180 }, { "epoch": 4.17, "learning_rate": 3.4449796302968157e-06, "loss": 0.8348, "step": 50190 }, { "epoch": 4.17, "learning_rate": 3.444868774769282e-06, "loss": 0.825, "step": 50200 }, { "epoch": 4.17, "learning_rate": 3.444757919241748e-06, "loss": 0.8247, "step": 50210 }, { "epoch": 4.17, "learning_rate": 3.4446470637142145e-06, "loss": 0.7543, "step": 50220 }, { "epoch": 4.18, "learning_rate": 3.4445362081866804e-06, "loss": 0.7706, "step": 50230 }, { "epoch": 4.18, "learning_rate": 3.4444253526591467e-06, "loss": 0.8237, "step": 50240 }, { "epoch": 4.18, "learning_rate": 3.444314497131613e-06, "loss": 0.8326, "step": 50250 }, { "epoch": 4.18, "learning_rate": 3.4442036416040793e-06, "loss": 0.8371, "step": 50260 }, { "epoch": 4.18, "learning_rate": 3.4440927860765456e-06, "loss": 0.8141, "step": 50270 }, { "epoch": 4.18, "learning_rate": 3.443981930549012e-06, "loss": 0.8657, "step": 50280 }, { "epoch": 4.18, "learning_rate": 3.4438710750214778e-06, "loss": 0.7862, "step": 50290 }, { "epoch": 4.18, "learning_rate": 3.4437602194939445e-06, "loss": 0.8047, "step": 50300 }, { "epoch": 4.18, "learning_rate": 3.4436493639664108e-06, "loss": 0.7901, "step": 50310 }, { "epoch": 4.18, "learning_rate": 3.4435385084388766e-06, "loss": 0.7948, "step": 50320 }, { "epoch": 4.18, "learning_rate": 3.4434276529113434e-06, "loss": 0.8142, "step": 50330 }, { "epoch": 4.18, "learning_rate": 3.4433167973838092e-06, "loss": 0.8491, "step": 50340 }, { "epoch": 4.19, "learning_rate": 3.443205941856276e-06, "loss": 0.8784, "step": 50350 }, { "epoch": 4.19, "learning_rate": 3.443095086328742e-06, "loss": 0.8038, "step": 50360 }, { "epoch": 4.19, "learning_rate": 3.442984230801208e-06, "loss": 0.8507, "step": 50370 }, { "epoch": 4.19, "learning_rate": 3.4428733752736744e-06, "loss": 0.8155, "step": 50380 }, { "epoch": 4.19, "learning_rate": 3.4427625197461407e-06, "loss": 0.8424, "step": 50390 }, { "epoch": 4.19, "learning_rate": 3.4426516642186066e-06, "loss": 0.7669, "step": 50400 }, { "epoch": 4.19, "learning_rate": 3.4425408086910733e-06, "loss": 0.8278, "step": 50410 }, { "epoch": 4.19, "learning_rate": 3.4424299531635396e-06, "loss": 0.8522, "step": 50420 }, { "epoch": 4.19, "learning_rate": 3.442319097636006e-06, "loss": 0.8201, "step": 50430 }, { "epoch": 4.19, "learning_rate": 3.442208242108472e-06, "loss": 0.7941, "step": 50440 }, { "epoch": 4.19, "learning_rate": 3.442097386580938e-06, "loss": 0.759, "step": 50450 }, { "epoch": 4.19, "learning_rate": 3.4419865310534048e-06, "loss": 0.7952, "step": 50460 }, { "epoch": 4.19, "learning_rate": 3.4418756755258707e-06, "loss": 0.803, "step": 50470 }, { "epoch": 4.2, "learning_rate": 3.441764819998337e-06, "loss": 0.7916, "step": 50480 }, { "epoch": 4.2, "learning_rate": 3.4416539644708032e-06, "loss": 0.7765, "step": 50490 }, { "epoch": 4.2, "learning_rate": 3.4415431089432695e-06, "loss": 0.7739, "step": 50500 }, { "epoch": 4.2, "learning_rate": 3.4414322534157354e-06, "loss": 0.7916, "step": 50510 }, { "epoch": 4.2, "learning_rate": 3.441321397888202e-06, "loss": 0.8726, "step": 50520 }, { "epoch": 4.2, "learning_rate": 3.441210542360668e-06, "loss": 0.8812, "step": 50530 }, { "epoch": 4.2, "learning_rate": 3.4410996868331347e-06, "loss": 0.8703, "step": 50540 }, { "epoch": 4.2, "learning_rate": 3.440988831305601e-06, "loss": 0.779, "step": 50550 }, { "epoch": 4.2, "learning_rate": 3.440877975778067e-06, "loss": 0.7925, "step": 50560 }, { "epoch": 4.2, "learning_rate": 3.4407671202505336e-06, "loss": 0.8208, "step": 50570 }, { "epoch": 4.2, "learning_rate": 3.4406562647229995e-06, "loss": 0.8939, "step": 50580 }, { "epoch": 4.2, "learning_rate": 3.440545409195466e-06, "loss": 0.8292, "step": 50590 }, { "epoch": 4.21, "learning_rate": 3.440434553667932e-06, "loss": 0.7589, "step": 50600 }, { "epoch": 4.21, "learning_rate": 3.4403236981403984e-06, "loss": 0.8402, "step": 50610 }, { "epoch": 4.21, "learning_rate": 3.4402128426128647e-06, "loss": 0.7394, "step": 50620 }, { "epoch": 4.21, "learning_rate": 3.440101987085331e-06, "loss": 0.8713, "step": 50630 }, { "epoch": 4.21, "learning_rate": 3.439991131557797e-06, "loss": 0.8493, "step": 50640 }, { "epoch": 4.21, "learning_rate": 3.4398802760302635e-06, "loss": 0.7954, "step": 50650 }, { "epoch": 4.21, "learning_rate": 3.4397694205027294e-06, "loss": 0.8475, "step": 50660 }, { "epoch": 4.21, "learning_rate": 3.4396585649751957e-06, "loss": 0.8017, "step": 50670 }, { "epoch": 4.21, "learning_rate": 3.4395477094476624e-06, "loss": 0.8337, "step": 50680 }, { "epoch": 4.21, "learning_rate": 3.4394368539201283e-06, "loss": 0.8144, "step": 50690 }, { "epoch": 4.21, "learning_rate": 3.439325998392595e-06, "loss": 0.8867, "step": 50700 }, { "epoch": 4.21, "learning_rate": 3.439215142865061e-06, "loss": 0.7921, "step": 50710 }, { "epoch": 4.22, "learning_rate": 3.439104287337527e-06, "loss": 0.7908, "step": 50720 }, { "epoch": 4.22, "learning_rate": 3.4389934318099935e-06, "loss": 0.8795, "step": 50730 }, { "epoch": 4.22, "learning_rate": 3.4388825762824598e-06, "loss": 0.8586, "step": 50740 }, { "epoch": 4.22, "learning_rate": 3.4387717207549257e-06, "loss": 0.829, "step": 50750 }, { "epoch": 4.22, "learning_rate": 3.4386608652273924e-06, "loss": 0.7809, "step": 50760 }, { "epoch": 4.22, "learning_rate": 3.4385500096998582e-06, "loss": 0.83, "step": 50770 }, { "epoch": 4.22, "learning_rate": 3.438439154172325e-06, "loss": 0.8501, "step": 50780 }, { "epoch": 4.22, "learning_rate": 3.4383282986447913e-06, "loss": 0.7976, "step": 50790 }, { "epoch": 4.22, "learning_rate": 3.438217443117257e-06, "loss": 0.7993, "step": 50800 }, { "epoch": 4.22, "learning_rate": 3.438106587589724e-06, "loss": 0.9039, "step": 50810 }, { "epoch": 4.22, "learning_rate": 3.4379957320621897e-06, "loss": 0.8299, "step": 50820 }, { "epoch": 4.22, "learning_rate": 3.437884876534656e-06, "loss": 0.9006, "step": 50830 }, { "epoch": 4.23, "learning_rate": 3.4377740210071223e-06, "loss": 0.7883, "step": 50840 }, { "epoch": 4.23, "learning_rate": 3.4376631654795886e-06, "loss": 0.8164, "step": 50850 }, { "epoch": 4.23, "learning_rate": 3.437552309952055e-06, "loss": 0.8134, "step": 50860 }, { "epoch": 4.23, "learning_rate": 3.437441454424521e-06, "loss": 0.88, "step": 50870 }, { "epoch": 4.23, "learning_rate": 3.437330598896987e-06, "loss": 0.8791, "step": 50880 }, { "epoch": 4.23, "learning_rate": 3.4372197433694538e-06, "loss": 0.8912, "step": 50890 }, { "epoch": 4.23, "learning_rate": 3.4371088878419197e-06, "loss": 0.7785, "step": 50900 }, { "epoch": 4.23, "learning_rate": 3.436998032314386e-06, "loss": 0.8048, "step": 50910 }, { "epoch": 4.23, "learning_rate": 3.4368871767868527e-06, "loss": 0.7878, "step": 50920 }, { "epoch": 4.23, "learning_rate": 3.4367763212593185e-06, "loss": 0.8378, "step": 50930 }, { "epoch": 4.23, "learning_rate": 3.4366654657317853e-06, "loss": 0.7868, "step": 50940 }, { "epoch": 4.23, "learning_rate": 3.436554610204251e-06, "loss": 0.7917, "step": 50950 }, { "epoch": 4.24, "learning_rate": 3.4364437546767174e-06, "loss": 0.7785, "step": 50960 }, { "epoch": 4.24, "learning_rate": 3.4363328991491837e-06, "loss": 0.8039, "step": 50970 }, { "epoch": 4.24, "learning_rate": 3.43622204362165e-06, "loss": 0.8644, "step": 50980 }, { "epoch": 4.24, "learning_rate": 3.436111188094116e-06, "loss": 0.8551, "step": 50990 }, { "epoch": 4.24, "learning_rate": 3.4360003325665826e-06, "loss": 0.8084, "step": 51000 }, { "epoch": 4.24, "learning_rate": 3.4358894770390485e-06, "loss": 0.8504, "step": 51010 }, { "epoch": 4.24, "learning_rate": 3.4357786215115148e-06, "loss": 0.8718, "step": 51020 }, { "epoch": 4.24, "learning_rate": 3.435667765983981e-06, "loss": 0.8311, "step": 51030 }, { "epoch": 4.24, "learning_rate": 3.4355569104564474e-06, "loss": 0.8823, "step": 51040 }, { "epoch": 4.24, "learning_rate": 3.435446054928914e-06, "loss": 0.7978, "step": 51050 }, { "epoch": 4.24, "learning_rate": 3.43533519940138e-06, "loss": 0.8566, "step": 51060 }, { "epoch": 4.24, "learning_rate": 3.4352243438738463e-06, "loss": 0.8503, "step": 51070 }, { "epoch": 4.25, "learning_rate": 3.4351134883463126e-06, "loss": 0.9296, "step": 51080 }, { "epoch": 4.25, "learning_rate": 3.435002632818779e-06, "loss": 0.7697, "step": 51090 }, { "epoch": 4.25, "learning_rate": 3.4348917772912447e-06, "loss": 0.7768, "step": 51100 }, { "epoch": 4.25, "learning_rate": 3.4347809217637114e-06, "loss": 0.8676, "step": 51110 }, { "epoch": 4.25, "learning_rate": 3.4346700662361773e-06, "loss": 0.8655, "step": 51120 }, { "epoch": 4.25, "learning_rate": 3.434559210708644e-06, "loss": 0.8217, "step": 51130 }, { "epoch": 4.25, "learning_rate": 3.43444835518111e-06, "loss": 0.827, "step": 51140 }, { "epoch": 4.25, "learning_rate": 3.434337499653576e-06, "loss": 0.7961, "step": 51150 }, { "epoch": 4.25, "learning_rate": 3.434226644126043e-06, "loss": 0.8751, "step": 51160 }, { "epoch": 4.25, "learning_rate": 3.4341157885985088e-06, "loss": 0.8331, "step": 51170 }, { "epoch": 4.25, "learning_rate": 3.434004933070975e-06, "loss": 0.8753, "step": 51180 }, { "epoch": 4.25, "learning_rate": 3.4338940775434414e-06, "loss": 0.8342, "step": 51190 }, { "epoch": 4.26, "learning_rate": 3.4337832220159077e-06, "loss": 0.7887, "step": 51200 }, { "epoch": 4.26, "learning_rate": 3.433672366488374e-06, "loss": 0.8486, "step": 51210 }, { "epoch": 4.26, "learning_rate": 3.4335615109608403e-06, "loss": 0.7896, "step": 51220 }, { "epoch": 4.26, "learning_rate": 3.433450655433306e-06, "loss": 0.8722, "step": 51230 }, { "epoch": 4.26, "learning_rate": 3.433339799905773e-06, "loss": 0.8414, "step": 51240 }, { "epoch": 4.26, "learning_rate": 3.4332289443782387e-06, "loss": 0.8842, "step": 51250 }, { "epoch": 4.26, "learning_rate": 3.433118088850705e-06, "loss": 0.8143, "step": 51260 }, { "epoch": 4.26, "learning_rate": 3.4330072333231713e-06, "loss": 0.8632, "step": 51270 }, { "epoch": 4.26, "learning_rate": 3.4328963777956376e-06, "loss": 0.8685, "step": 51280 }, { "epoch": 4.26, "learning_rate": 3.4327855222681043e-06, "loss": 0.8809, "step": 51290 }, { "epoch": 4.26, "learning_rate": 3.43267466674057e-06, "loss": 0.8269, "step": 51300 }, { "epoch": 4.26, "learning_rate": 3.4325638112130365e-06, "loss": 0.8147, "step": 51310 }, { "epoch": 4.27, "learning_rate": 3.432452955685503e-06, "loss": 0.8361, "step": 51320 }, { "epoch": 4.27, "learning_rate": 3.432342100157969e-06, "loss": 0.8714, "step": 51330 }, { "epoch": 4.27, "learning_rate": 3.432231244630435e-06, "loss": 0.8473, "step": 51340 }, { "epoch": 4.27, "learning_rate": 3.4321203891029017e-06, "loss": 0.8312, "step": 51350 }, { "epoch": 4.27, "learning_rate": 3.4320095335753675e-06, "loss": 0.89, "step": 51360 }, { "epoch": 4.27, "learning_rate": 3.4318986780478343e-06, "loss": 0.8832, "step": 51370 }, { "epoch": 4.27, "learning_rate": 3.4317878225203e-06, "loss": 0.9094, "step": 51380 }, { "epoch": 4.27, "learning_rate": 3.4316769669927664e-06, "loss": 0.8613, "step": 51390 }, { "epoch": 4.27, "learning_rate": 3.4315661114652327e-06, "loss": 0.8204, "step": 51400 }, { "epoch": 4.27, "learning_rate": 3.431455255937699e-06, "loss": 0.8263, "step": 51410 }, { "epoch": 4.27, "learning_rate": 3.4313444004101653e-06, "loss": 0.7928, "step": 51420 }, { "epoch": 4.27, "learning_rate": 3.4312335448826316e-06, "loss": 0.8346, "step": 51430 }, { "epoch": 4.28, "learning_rate": 3.431122689355098e-06, "loss": 0.7539, "step": 51440 }, { "epoch": 4.28, "learning_rate": 3.4310118338275638e-06, "loss": 0.7587, "step": 51450 }, { "epoch": 4.28, "learning_rate": 3.4309009783000305e-06, "loss": 0.7938, "step": 51460 }, { "epoch": 4.28, "learning_rate": 3.4307901227724964e-06, "loss": 0.8644, "step": 51470 }, { "epoch": 4.28, "learning_rate": 3.430679267244963e-06, "loss": 0.9069, "step": 51480 }, { "epoch": 4.28, "learning_rate": 3.430568411717429e-06, "loss": 0.782, "step": 51490 }, { "epoch": 4.28, "learning_rate": 3.4304575561898953e-06, "loss": 0.7867, "step": 51500 }, { "epoch": 4.28, "learning_rate": 3.4303467006623616e-06, "loss": 0.7796, "step": 51510 }, { "epoch": 4.28, "learning_rate": 3.430235845134828e-06, "loss": 0.8481, "step": 51520 }, { "epoch": 4.28, "learning_rate": 3.430124989607294e-06, "loss": 0.8842, "step": 51530 }, { "epoch": 4.28, "learning_rate": 3.4300141340797604e-06, "loss": 0.8771, "step": 51540 }, { "epoch": 4.28, "learning_rate": 3.4299032785522267e-06, "loss": 0.8475, "step": 51550 }, { "epoch": 4.29, "learning_rate": 3.429792423024693e-06, "loss": 0.8206, "step": 51560 }, { "epoch": 4.29, "learning_rate": 3.4296815674971593e-06, "loss": 0.7801, "step": 51570 }, { "epoch": 4.29, "learning_rate": 3.429570711969625e-06, "loss": 0.8041, "step": 51580 }, { "epoch": 4.29, "learning_rate": 3.429459856442092e-06, "loss": 0.8353, "step": 51590 }, { "epoch": 4.29, "learning_rate": 3.429349000914558e-06, "loss": 0.8759, "step": 51600 }, { "epoch": 4.29, "learning_rate": 3.429238145387024e-06, "loss": 0.8182, "step": 51610 }, { "epoch": 4.29, "learning_rate": 3.4291272898594904e-06, "loss": 0.8799, "step": 51620 }, { "epoch": 4.29, "learning_rate": 3.4290164343319567e-06, "loss": 0.8403, "step": 51630 }, { "epoch": 4.29, "learning_rate": 3.428905578804423e-06, "loss": 0.7964, "step": 51640 }, { "epoch": 4.29, "learning_rate": 3.4287947232768893e-06, "loss": 0.7869, "step": 51650 }, { "epoch": 4.29, "learning_rate": 3.4286838677493556e-06, "loss": 0.8261, "step": 51660 }, { "epoch": 4.29, "learning_rate": 3.428573012221822e-06, "loss": 0.871, "step": 51670 }, { "epoch": 4.3, "learning_rate": 3.428462156694288e-06, "loss": 0.9539, "step": 51680 }, { "epoch": 4.3, "learning_rate": 3.428351301166754e-06, "loss": 0.8599, "step": 51690 }, { "epoch": 4.3, "learning_rate": 3.4282404456392207e-06, "loss": 0.7495, "step": 51700 }, { "epoch": 4.3, "learning_rate": 3.4281295901116866e-06, "loss": 0.7701, "step": 51710 }, { "epoch": 4.3, "learning_rate": 3.4280187345841533e-06, "loss": 0.7947, "step": 51720 }, { "epoch": 4.3, "learning_rate": 3.427907879056619e-06, "loss": 0.8135, "step": 51730 }, { "epoch": 4.3, "learning_rate": 3.4277970235290855e-06, "loss": 0.849, "step": 51740 }, { "epoch": 4.3, "learning_rate": 3.427686168001552e-06, "loss": 0.8097, "step": 51750 }, { "epoch": 4.3, "learning_rate": 3.427575312474018e-06, "loss": 0.8224, "step": 51760 }, { "epoch": 4.3, "learning_rate": 3.427464456946484e-06, "loss": 0.7541, "step": 51770 }, { "epoch": 4.3, "learning_rate": 3.4273536014189507e-06, "loss": 0.8107, "step": 51780 }, { "epoch": 4.3, "learning_rate": 3.427242745891417e-06, "loss": 0.896, "step": 51790 }, { "epoch": 4.31, "learning_rate": 3.427131890363883e-06, "loss": 0.7707, "step": 51800 }, { "epoch": 4.31, "learning_rate": 3.4270210348363496e-06, "loss": 0.8746, "step": 51810 }, { "epoch": 4.31, "learning_rate": 3.4269101793088154e-06, "loss": 0.7592, "step": 51820 }, { "epoch": 4.31, "learning_rate": 3.426799323781282e-06, "loss": 0.9085, "step": 51830 }, { "epoch": 4.31, "learning_rate": 3.426688468253748e-06, "loss": 0.8528, "step": 51840 }, { "epoch": 4.31, "learning_rate": 3.4265776127262143e-06, "loss": 0.8224, "step": 51850 }, { "epoch": 4.31, "learning_rate": 3.4264667571986806e-06, "loss": 0.8078, "step": 51860 }, { "epoch": 4.31, "learning_rate": 3.426355901671147e-06, "loss": 0.8241, "step": 51870 }, { "epoch": 4.31, "learning_rate": 3.426245046143613e-06, "loss": 0.8298, "step": 51880 }, { "epoch": 4.31, "learning_rate": 3.4261341906160795e-06, "loss": 0.8627, "step": 51890 }, { "epoch": 4.31, "learning_rate": 3.426023335088546e-06, "loss": 0.8135, "step": 51900 }, { "epoch": 4.31, "learning_rate": 3.425912479561012e-06, "loss": 0.8196, "step": 51910 }, { "epoch": 4.32, "learning_rate": 3.4258016240334784e-06, "loss": 0.7667, "step": 51920 }, { "epoch": 4.32, "learning_rate": 3.4256907685059443e-06, "loss": 0.85, "step": 51930 }, { "epoch": 4.32, "learning_rate": 3.425579912978411e-06, "loss": 0.871, "step": 51940 }, { "epoch": 4.32, "learning_rate": 3.425469057450877e-06, "loss": 0.8732, "step": 51950 }, { "epoch": 4.32, "learning_rate": 3.425358201923343e-06, "loss": 0.7734, "step": 51960 }, { "epoch": 4.32, "learning_rate": 3.4252473463958094e-06, "loss": 0.8096, "step": 51970 }, { "epoch": 4.32, "learning_rate": 3.4251364908682757e-06, "loss": 0.9278, "step": 51980 }, { "epoch": 4.32, "learning_rate": 3.425025635340742e-06, "loss": 0.8447, "step": 51990 }, { "epoch": 4.32, "learning_rate": 3.4249147798132083e-06, "loss": 0.8669, "step": 52000 }, { "epoch": 4.32, "learning_rate": 3.424803924285674e-06, "loss": 0.8322, "step": 52010 }, { "epoch": 4.32, "learning_rate": 3.424693068758141e-06, "loss": 0.8867, "step": 52020 }, { "epoch": 4.32, "learning_rate": 3.4245822132306072e-06, "loss": 0.8541, "step": 52030 }, { "epoch": 4.33, "learning_rate": 3.424471357703073e-06, "loss": 0.8758, "step": 52040 }, { "epoch": 4.33, "learning_rate": 3.42436050217554e-06, "loss": 0.8342, "step": 52050 }, { "epoch": 4.33, "learning_rate": 3.4242496466480057e-06, "loss": 0.7747, "step": 52060 }, { "epoch": 4.33, "learning_rate": 3.4241387911204724e-06, "loss": 0.8054, "step": 52070 }, { "epoch": 4.33, "learning_rate": 3.4240279355929383e-06, "loss": 0.8097, "step": 52080 }, { "epoch": 4.33, "learning_rate": 3.4239170800654046e-06, "loss": 0.8797, "step": 52090 }, { "epoch": 4.33, "learning_rate": 3.423806224537871e-06, "loss": 0.8332, "step": 52100 }, { "epoch": 4.33, "learning_rate": 3.423695369010337e-06, "loss": 0.7806, "step": 52110 }, { "epoch": 4.33, "learning_rate": 3.423584513482803e-06, "loss": 0.8197, "step": 52120 }, { "epoch": 4.33, "learning_rate": 3.4234736579552697e-06, "loss": 0.885, "step": 52130 }, { "epoch": 4.33, "learning_rate": 3.423362802427736e-06, "loss": 0.8224, "step": 52140 }, { "epoch": 4.33, "learning_rate": 3.4232519469002023e-06, "loss": 0.811, "step": 52150 }, { "epoch": 4.34, "learning_rate": 3.4231410913726686e-06, "loss": 0.8157, "step": 52160 }, { "epoch": 4.34, "learning_rate": 3.4230302358451345e-06, "loss": 0.842, "step": 52170 }, { "epoch": 4.34, "learning_rate": 3.4229193803176012e-06, "loss": 0.8532, "step": 52180 }, { "epoch": 4.34, "learning_rate": 3.422808524790067e-06, "loss": 0.8383, "step": 52190 }, { "epoch": 4.34, "learning_rate": 3.4226976692625334e-06, "loss": 0.9031, "step": 52200 }, { "epoch": 4.34, "learning_rate": 3.4225868137349997e-06, "loss": 0.813, "step": 52210 }, { "epoch": 4.34, "learning_rate": 3.422475958207466e-06, "loss": 0.8203, "step": 52220 }, { "epoch": 4.34, "learning_rate": 3.422365102679932e-06, "loss": 0.8359, "step": 52230 }, { "epoch": 4.34, "learning_rate": 3.4222542471523986e-06, "loss": 0.8136, "step": 52240 }, { "epoch": 4.34, "learning_rate": 3.4221433916248644e-06, "loss": 0.8508, "step": 52250 }, { "epoch": 4.34, "learning_rate": 3.422032536097331e-06, "loss": 0.8288, "step": 52260 }, { "epoch": 4.34, "learning_rate": 3.4219216805697975e-06, "loss": 0.8716, "step": 52270 }, { "epoch": 4.35, "learning_rate": 3.4218108250422633e-06, "loss": 0.8936, "step": 52280 }, { "epoch": 4.35, "learning_rate": 3.42169996951473e-06, "loss": 0.8399, "step": 52290 }, { "epoch": 4.35, "learning_rate": 3.421589113987196e-06, "loss": 0.8208, "step": 52300 }, { "epoch": 4.35, "learning_rate": 3.4214893440124155e-06, "loss": 0.8401, "step": 52310 }, { "epoch": 4.35, "learning_rate": 3.421378488484882e-06, "loss": 0.7565, "step": 52320 }, { "epoch": 4.35, "learning_rate": 3.421267632957348e-06, "loss": 0.8262, "step": 52330 }, { "epoch": 4.35, "learning_rate": 3.4211567774298143e-06, "loss": 0.8322, "step": 52340 }, { "epoch": 4.35, "learning_rate": 3.421045921902281e-06, "loss": 0.7699, "step": 52350 }, { "epoch": 4.35, "learning_rate": 3.420935066374747e-06, "loss": 0.8903, "step": 52360 }, { "epoch": 4.35, "learning_rate": 3.4208242108472132e-06, "loss": 0.8463, "step": 52370 }, { "epoch": 4.35, "learning_rate": 3.4207133553196795e-06, "loss": 0.8634, "step": 52380 }, { "epoch": 4.35, "learning_rate": 3.420602499792146e-06, "loss": 0.8408, "step": 52390 }, { "epoch": 4.36, "learning_rate": 3.4204916442646117e-06, "loss": 0.8809, "step": 52400 }, { "epoch": 4.36, "learning_rate": 3.4203807887370784e-06, "loss": 0.8693, "step": 52410 }, { "epoch": 4.36, "learning_rate": 3.4202699332095443e-06, "loss": 0.8298, "step": 52420 }, { "epoch": 4.36, "learning_rate": 3.420159077682011e-06, "loss": 0.8477, "step": 52430 }, { "epoch": 4.36, "learning_rate": 3.420048222154477e-06, "loss": 0.8135, "step": 52440 }, { "epoch": 4.36, "learning_rate": 3.419937366626943e-06, "loss": 0.8152, "step": 52450 }, { "epoch": 4.36, "learning_rate": 3.4198265110994095e-06, "loss": 0.815, "step": 52460 }, { "epoch": 4.36, "learning_rate": 3.4197156555718758e-06, "loss": 0.8345, "step": 52470 }, { "epoch": 4.36, "learning_rate": 3.419604800044342e-06, "loss": 0.8192, "step": 52480 }, { "epoch": 4.36, "learning_rate": 3.4194939445168084e-06, "loss": 0.8391, "step": 52490 }, { "epoch": 4.36, "learning_rate": 3.4193830889892746e-06, "loss": 0.8364, "step": 52500 }, { "epoch": 4.36, "learning_rate": 3.419272233461741e-06, "loss": 0.7626, "step": 52510 }, { "epoch": 4.37, "learning_rate": 3.4191613779342072e-06, "loss": 0.8436, "step": 52520 }, { "epoch": 4.37, "learning_rate": 3.419050522406673e-06, "loss": 0.8359, "step": 52530 }, { "epoch": 4.37, "learning_rate": 3.41893966687914e-06, "loss": 0.7665, "step": 52540 }, { "epoch": 4.37, "learning_rate": 3.4188288113516057e-06, "loss": 0.7971, "step": 52550 }, { "epoch": 4.37, "learning_rate": 3.418717955824072e-06, "loss": 0.823, "step": 52560 }, { "epoch": 4.37, "learning_rate": 3.4186071002965383e-06, "loss": 0.8346, "step": 52570 }, { "epoch": 4.37, "learning_rate": 3.4184962447690046e-06, "loss": 0.8295, "step": 52580 }, { "epoch": 4.37, "learning_rate": 3.418385389241471e-06, "loss": 0.8052, "step": 52590 }, { "epoch": 4.37, "learning_rate": 3.418274533713937e-06, "loss": 0.7575, "step": 52600 }, { "epoch": 4.37, "learning_rate": 3.4181636781864035e-06, "loss": 0.8763, "step": 52610 }, { "epoch": 4.37, "learning_rate": 3.4180528226588698e-06, "loss": 0.8183, "step": 52620 }, { "epoch": 4.37, "learning_rate": 3.417941967131336e-06, "loss": 0.8369, "step": 52630 }, { "epoch": 4.38, "learning_rate": 3.417831111603802e-06, "loss": 0.8687, "step": 52640 }, { "epoch": 4.38, "learning_rate": 3.4177202560762687e-06, "loss": 0.791, "step": 52650 }, { "epoch": 4.38, "learning_rate": 3.4176094005487345e-06, "loss": 0.7943, "step": 52660 }, { "epoch": 4.38, "learning_rate": 3.4174985450212012e-06, "loss": 0.847, "step": 52670 }, { "epoch": 4.38, "learning_rate": 3.417387689493667e-06, "loss": 0.9138, "step": 52680 }, { "epoch": 4.38, "learning_rate": 3.4172768339661334e-06, "loss": 0.845, "step": 52690 }, { "epoch": 4.38, "learning_rate": 3.4171659784385997e-06, "loss": 0.7758, "step": 52700 }, { "epoch": 4.38, "learning_rate": 3.417055122911066e-06, "loss": 0.82, "step": 52710 }, { "epoch": 4.38, "learning_rate": 3.4169442673835323e-06, "loss": 0.8292, "step": 52720 }, { "epoch": 4.38, "learning_rate": 3.4168334118559986e-06, "loss": 0.827, "step": 52730 }, { "epoch": 4.38, "learning_rate": 3.416722556328465e-06, "loss": 0.7672, "step": 52740 }, { "epoch": 4.38, "learning_rate": 3.4166117008009308e-06, "loss": 0.8755, "step": 52750 }, { "epoch": 4.39, "learning_rate": 3.4165008452733975e-06, "loss": 0.8325, "step": 52760 }, { "epoch": 4.39, "learning_rate": 3.4163899897458634e-06, "loss": 0.8157, "step": 52770 }, { "epoch": 4.39, "learning_rate": 3.41627913421833e-06, "loss": 0.8536, "step": 52780 }, { "epoch": 4.39, "learning_rate": 3.416168278690796e-06, "loss": 0.8814, "step": 52790 }, { "epoch": 4.39, "learning_rate": 3.4160574231632622e-06, "loss": 0.807, "step": 52800 }, { "epoch": 4.39, "learning_rate": 3.4159465676357285e-06, "loss": 0.8002, "step": 52810 }, { "epoch": 4.39, "learning_rate": 3.415835712108195e-06, "loss": 0.8385, "step": 52820 }, { "epoch": 4.39, "learning_rate": 3.4157248565806607e-06, "loss": 0.8199, "step": 52830 }, { "epoch": 4.39, "learning_rate": 3.4156140010531274e-06, "loss": 0.7527, "step": 52840 }, { "epoch": 4.39, "learning_rate": 3.4155031455255937e-06, "loss": 0.8496, "step": 52850 }, { "epoch": 4.39, "learning_rate": 3.41539228999806e-06, "loss": 0.7858, "step": 52860 }, { "epoch": 4.39, "learning_rate": 3.4152814344705263e-06, "loss": 0.851, "step": 52870 }, { "epoch": 4.4, "learning_rate": 3.415170578942992e-06, "loss": 0.8641, "step": 52880 }, { "epoch": 4.4, "learning_rate": 3.415059723415459e-06, "loss": 0.828, "step": 52890 }, { "epoch": 4.4, "learning_rate": 3.4149488678879248e-06, "loss": 0.7934, "step": 52900 }, { "epoch": 4.4, "learning_rate": 3.414838012360391e-06, "loss": 0.7579, "step": 52910 }, { "epoch": 4.4, "learning_rate": 3.4147271568328574e-06, "loss": 0.7949, "step": 52920 }, { "epoch": 4.4, "learning_rate": 3.4146163013053237e-06, "loss": 0.8738, "step": 52930 }, { "epoch": 4.4, "learning_rate": 3.41450544577779e-06, "loss": 0.8324, "step": 52940 }, { "epoch": 4.4, "learning_rate": 3.4143945902502562e-06, "loss": 0.8393, "step": 52950 }, { "epoch": 4.4, "learning_rate": 3.414283734722722e-06, "loss": 0.7486, "step": 52960 }, { "epoch": 4.4, "learning_rate": 3.414172879195189e-06, "loss": 0.8287, "step": 52970 }, { "epoch": 4.4, "learning_rate": 3.414062023667655e-06, "loss": 0.8573, "step": 52980 }, { "epoch": 4.4, "learning_rate": 3.413951168140121e-06, "loss": 0.8424, "step": 52990 }, { "epoch": 4.41, "learning_rate": 3.4138403126125877e-06, "loss": 0.8677, "step": 53000 }, { "epoch": 4.41, "learning_rate": 3.4137294570850536e-06, "loss": 0.8248, "step": 53010 }, { "epoch": 4.41, "learning_rate": 3.4136186015575203e-06, "loss": 0.8501, "step": 53020 }, { "epoch": 4.41, "learning_rate": 3.413507746029986e-06, "loss": 0.9183, "step": 53030 }, { "epoch": 4.41, "learning_rate": 3.4133968905024525e-06, "loss": 0.8025, "step": 53040 }, { "epoch": 4.41, "learning_rate": 3.4132860349749188e-06, "loss": 0.8348, "step": 53050 }, { "epoch": 4.41, "learning_rate": 3.413175179447385e-06, "loss": 0.8355, "step": 53060 }, { "epoch": 4.41, "learning_rate": 3.413064323919851e-06, "loss": 0.7747, "step": 53070 }, { "epoch": 4.41, "learning_rate": 3.4129534683923177e-06, "loss": 0.8998, "step": 53080 }, { "epoch": 4.41, "learning_rate": 3.412842612864784e-06, "loss": 0.8469, "step": 53090 }, { "epoch": 4.41, "learning_rate": 3.4127317573372503e-06, "loss": 0.8468, "step": 53100 }, { "epoch": 4.41, "learning_rate": 3.4126209018097165e-06, "loss": 0.8212, "step": 53110 }, { "epoch": 4.42, "learning_rate": 3.4125100462821824e-06, "loss": 0.8318, "step": 53120 }, { "epoch": 4.42, "learning_rate": 3.412399190754649e-06, "loss": 0.8421, "step": 53130 }, { "epoch": 4.42, "learning_rate": 3.412288335227115e-06, "loss": 0.7666, "step": 53140 }, { "epoch": 4.42, "learning_rate": 3.4121774796995813e-06, "loss": 0.8436, "step": 53150 }, { "epoch": 4.42, "learning_rate": 3.4120666241720476e-06, "loss": 0.8186, "step": 53160 }, { "epoch": 4.42, "learning_rate": 3.411955768644514e-06, "loss": 0.8784, "step": 53170 }, { "epoch": 4.42, "learning_rate": 3.4118449131169798e-06, "loss": 0.8722, "step": 53180 }, { "epoch": 4.42, "learning_rate": 3.4117340575894465e-06, "loss": 0.8314, "step": 53190 }, { "epoch": 4.42, "learning_rate": 3.4116232020619124e-06, "loss": 0.8296, "step": 53200 }, { "epoch": 4.42, "learning_rate": 3.411512346534379e-06, "loss": 0.8478, "step": 53210 }, { "epoch": 4.42, "learning_rate": 3.4114014910068454e-06, "loss": 0.7642, "step": 53220 }, { "epoch": 4.42, "learning_rate": 3.4112906354793112e-06, "loss": 0.865, "step": 53230 }, { "epoch": 4.43, "learning_rate": 3.411179779951778e-06, "loss": 0.8715, "step": 53240 }, { "epoch": 4.43, "learning_rate": 3.411068924424244e-06, "loss": 0.911, "step": 53250 }, { "epoch": 4.43, "learning_rate": 3.41095806889671e-06, "loss": 0.8181, "step": 53260 }, { "epoch": 4.43, "learning_rate": 3.4108472133691764e-06, "loss": 0.7831, "step": 53270 }, { "epoch": 4.43, "learning_rate": 3.4107363578416427e-06, "loss": 0.8405, "step": 53280 }, { "epoch": 4.43, "learning_rate": 3.410625502314109e-06, "loss": 0.7991, "step": 53290 }, { "epoch": 4.43, "learning_rate": 3.4105146467865753e-06, "loss": 0.8209, "step": 53300 }, { "epoch": 4.43, "learning_rate": 3.410403791259041e-06, "loss": 0.8242, "step": 53310 }, { "epoch": 4.43, "learning_rate": 3.410292935731508e-06, "loss": 0.8654, "step": 53320 }, { "epoch": 4.43, "learning_rate": 3.4101820802039738e-06, "loss": 0.9147, "step": 53330 }, { "epoch": 4.43, "learning_rate": 3.41007122467644e-06, "loss": 0.8151, "step": 53340 }, { "epoch": 4.43, "learning_rate": 3.409960369148907e-06, "loss": 0.831, "step": 53350 }, { "epoch": 4.44, "learning_rate": 3.4098495136213727e-06, "loss": 0.7647, "step": 53360 }, { "epoch": 4.44, "learning_rate": 3.4097386580938394e-06, "loss": 0.8018, "step": 53370 }, { "epoch": 4.44, "learning_rate": 3.4096278025663053e-06, "loss": 0.9016, "step": 53380 }, { "epoch": 4.44, "learning_rate": 3.4095169470387715e-06, "loss": 0.7861, "step": 53390 }, { "epoch": 4.44, "learning_rate": 3.409406091511238e-06, "loss": 0.793, "step": 53400 }, { "epoch": 4.44, "learning_rate": 3.409295235983704e-06, "loss": 0.829, "step": 53410 }, { "epoch": 4.44, "learning_rate": 3.40918438045617e-06, "loss": 0.8341, "step": 53420 }, { "epoch": 4.44, "learning_rate": 3.4090735249286367e-06, "loss": 0.8195, "step": 53430 }, { "epoch": 4.44, "learning_rate": 3.4089626694011026e-06, "loss": 0.8793, "step": 53440 }, { "epoch": 4.44, "learning_rate": 3.4088518138735693e-06, "loss": 0.858, "step": 53450 }, { "epoch": 4.44, "learning_rate": 3.4087409583460356e-06, "loss": 0.7992, "step": 53460 }, { "epoch": 4.44, "learning_rate": 3.4086301028185015e-06, "loss": 0.9004, "step": 53470 }, { "epoch": 4.45, "learning_rate": 3.408519247290968e-06, "loss": 0.9411, "step": 53480 }, { "epoch": 4.45, "learning_rate": 3.408408391763434e-06, "loss": 0.8352, "step": 53490 }, { "epoch": 4.45, "learning_rate": 3.4082975362359004e-06, "loss": 0.8366, "step": 53500 }, { "epoch": 4.45, "learning_rate": 3.4081866807083667e-06, "loss": 0.7414, "step": 53510 }, { "epoch": 4.45, "learning_rate": 3.408075825180833e-06, "loss": 0.8331, "step": 53520 }, { "epoch": 4.45, "learning_rate": 3.4079649696532993e-06, "loss": 0.909, "step": 53530 }, { "epoch": 4.45, "learning_rate": 3.4078541141257656e-06, "loss": 0.8477, "step": 53540 }, { "epoch": 4.45, "learning_rate": 3.4077432585982314e-06, "loss": 0.7876, "step": 53550 }, { "epoch": 4.45, "learning_rate": 3.407632403070698e-06, "loss": 0.8118, "step": 53560 }, { "epoch": 4.45, "learning_rate": 3.407521547543164e-06, "loss": 0.8475, "step": 53570 }, { "epoch": 4.45, "learning_rate": 3.4074106920156303e-06, "loss": 0.8771, "step": 53580 }, { "epoch": 4.45, "learning_rate": 3.407299836488097e-06, "loss": 0.8519, "step": 53590 }, { "epoch": 4.46, "learning_rate": 3.407188980960563e-06, "loss": 0.8009, "step": 53600 }, { "epoch": 4.46, "learning_rate": 3.4070781254330296e-06, "loss": 0.854, "step": 53610 }, { "epoch": 4.46, "learning_rate": 3.4069672699054955e-06, "loss": 0.9083, "step": 53620 }, { "epoch": 4.46, "learning_rate": 3.4068564143779618e-06, "loss": 0.8733, "step": 53630 }, { "epoch": 4.46, "learning_rate": 3.406745558850428e-06, "loss": 0.8648, "step": 53640 }, { "epoch": 4.46, "learning_rate": 3.4066347033228944e-06, "loss": 0.7776, "step": 53650 }, { "epoch": 4.46, "learning_rate": 3.4065238477953603e-06, "loss": 0.8105, "step": 53660 }, { "epoch": 4.46, "learning_rate": 3.406412992267827e-06, "loss": 0.7748, "step": 53670 }, { "epoch": 4.46, "learning_rate": 3.406302136740293e-06, "loss": 0.8596, "step": 53680 }, { "epoch": 4.46, "learning_rate": 3.406191281212759e-06, "loss": 0.8151, "step": 53690 }, { "epoch": 4.46, "learning_rate": 3.4060804256852254e-06, "loss": 0.8714, "step": 53700 }, { "epoch": 4.46, "learning_rate": 3.4059695701576917e-06, "loss": 0.8417, "step": 53710 }, { "epoch": 4.47, "learning_rate": 3.4058587146301584e-06, "loss": 0.7756, "step": 53720 }, { "epoch": 4.47, "learning_rate": 3.4057478591026243e-06, "loss": 0.921, "step": 53730 }, { "epoch": 4.47, "learning_rate": 3.4056370035750906e-06, "loss": 0.8027, "step": 53740 }, { "epoch": 4.47, "learning_rate": 3.405526148047557e-06, "loss": 0.8051, "step": 53750 }, { "epoch": 4.47, "learning_rate": 3.405415292520023e-06, "loss": 0.7949, "step": 53760 }, { "epoch": 4.47, "learning_rate": 3.405304436992489e-06, "loss": 0.8722, "step": 53770 }, { "epoch": 4.47, "learning_rate": 3.405193581464956e-06, "loss": 0.8609, "step": 53780 }, { "epoch": 4.47, "learning_rate": 3.4050827259374217e-06, "loss": 0.8613, "step": 53790 }, { "epoch": 4.47, "learning_rate": 3.4049718704098884e-06, "loss": 0.7843, "step": 53800 }, { "epoch": 4.47, "learning_rate": 3.4048610148823543e-06, "loss": 0.8116, "step": 53810 }, { "epoch": 4.47, "learning_rate": 3.4047501593548206e-06, "loss": 0.8273, "step": 53820 }, { "epoch": 4.47, "learning_rate": 3.4046393038272873e-06, "loss": 0.8403, "step": 53830 }, { "epoch": 4.48, "learning_rate": 3.404528448299753e-06, "loss": 0.8625, "step": 53840 }, { "epoch": 4.48, "learning_rate": 3.4044175927722194e-06, "loss": 0.8614, "step": 53850 }, { "epoch": 4.48, "learning_rate": 3.4043067372446857e-06, "loss": 0.8241, "step": 53860 }, { "epoch": 4.48, "learning_rate": 3.404195881717152e-06, "loss": 0.7319, "step": 53870 }, { "epoch": 4.48, "learning_rate": 3.4040850261896183e-06, "loss": 0.8597, "step": 53880 }, { "epoch": 4.48, "learning_rate": 3.4039741706620846e-06, "loss": 0.8409, "step": 53890 }, { "epoch": 4.48, "learning_rate": 3.4038633151345505e-06, "loss": 0.8486, "step": 53900 }, { "epoch": 4.48, "learning_rate": 3.403752459607017e-06, "loss": 0.7975, "step": 53910 }, { "epoch": 4.48, "learning_rate": 3.403641604079483e-06, "loss": 0.8002, "step": 53920 }, { "epoch": 4.48, "learning_rate": 3.4035307485519494e-06, "loss": 0.8345, "step": 53930 }, { "epoch": 4.48, "learning_rate": 3.4034198930244157e-06, "loss": 0.7981, "step": 53940 }, { "epoch": 4.48, "learning_rate": 3.403309037496882e-06, "loss": 0.8156, "step": 53950 }, { "epoch": 4.49, "learning_rate": 3.4031981819693487e-06, "loss": 0.8412, "step": 53960 }, { "epoch": 4.49, "learning_rate": 3.4030873264418146e-06, "loss": 0.9121, "step": 53970 }, { "epoch": 4.49, "learning_rate": 3.402976470914281e-06, "loss": 0.83, "step": 53980 }, { "epoch": 4.49, "learning_rate": 3.402865615386747e-06, "loss": 0.8252, "step": 53990 }, { "epoch": 4.49, "learning_rate": 3.4027547598592134e-06, "loss": 0.8631, "step": 54000 }, { "epoch": 4.49, "learning_rate": 3.4026439043316793e-06, "loss": 0.8249, "step": 54010 }, { "epoch": 4.49, "learning_rate": 3.402533048804146e-06, "loss": 0.8509, "step": 54020 }, { "epoch": 4.49, "learning_rate": 3.402422193276612e-06, "loss": 0.9477, "step": 54030 }, { "epoch": 4.49, "learning_rate": 3.402311337749078e-06, "loss": 0.814, "step": 54040 }, { "epoch": 4.49, "learning_rate": 3.4022004822215445e-06, "loss": 0.805, "step": 54050 }, { "epoch": 4.49, "learning_rate": 3.402089626694011e-06, "loss": 0.867, "step": 54060 }, { "epoch": 4.49, "learning_rate": 3.401978771166477e-06, "loss": 0.856, "step": 54070 }, { "epoch": 4.5, "learning_rate": 3.4018679156389434e-06, "loss": 0.8556, "step": 54080 }, { "epoch": 4.5, "learning_rate": 3.4017570601114097e-06, "loss": 0.861, "step": 54090 }, { "epoch": 4.5, "learning_rate": 3.401646204583876e-06, "loss": 0.8319, "step": 54100 }, { "epoch": 4.5, "learning_rate": 3.4015353490563423e-06, "loss": 0.8091, "step": 54110 }, { "epoch": 4.5, "learning_rate": 3.401424493528808e-06, "loss": 0.8274, "step": 54120 }, { "epoch": 4.5, "learning_rate": 3.401313638001275e-06, "loss": 0.8884, "step": 54130 }, { "epoch": 4.5, "learning_rate": 3.4012027824737407e-06, "loss": 0.782, "step": 54140 }, { "epoch": 4.5, "learning_rate": 3.4010919269462075e-06, "loss": 0.8313, "step": 54150 }, { "epoch": 4.5, "learning_rate": 3.4009810714186733e-06, "loss": 0.8018, "step": 54160 }, { "epoch": 4.5, "learning_rate": 3.4008702158911396e-06, "loss": 0.8296, "step": 54170 }, { "epoch": 4.5, "learning_rate": 3.400759360363606e-06, "loss": 0.8264, "step": 54180 }, { "epoch": 4.5, "learning_rate": 3.400648504836072e-06, "loss": 0.8426, "step": 54190 }, { "epoch": 4.51, "learning_rate": 3.4005376493085385e-06, "loss": 0.8301, "step": 54200 }, { "epoch": 4.51, "learning_rate": 3.400426793781005e-06, "loss": 0.8548, "step": 54210 }, { "epoch": 4.51, "learning_rate": 3.400315938253471e-06, "loss": 0.8113, "step": 54220 }, { "epoch": 4.51, "learning_rate": 3.4002050827259374e-06, "loss": 0.8473, "step": 54230 }, { "epoch": 4.51, "learning_rate": 3.4000942271984037e-06, "loss": 0.7626, "step": 54240 }, { "epoch": 4.51, "learning_rate": 3.3999833716708696e-06, "loss": 0.8158, "step": 54250 }, { "epoch": 4.51, "learning_rate": 3.3998725161433363e-06, "loss": 0.8487, "step": 54260 }, { "epoch": 4.51, "learning_rate": 3.399761660615802e-06, "loss": 0.8677, "step": 54270 }, { "epoch": 4.51, "learning_rate": 3.3996508050882684e-06, "loss": 0.8787, "step": 54280 }, { "epoch": 4.51, "learning_rate": 3.3995399495607347e-06, "loss": 0.8273, "step": 54290 }, { "epoch": 4.51, "learning_rate": 3.399429094033201e-06, "loss": 0.797, "step": 54300 }, { "epoch": 4.51, "learning_rate": 3.3993182385056673e-06, "loss": 0.8665, "step": 54310 }, { "epoch": 4.52, "learning_rate": 3.3992073829781336e-06, "loss": 0.9114, "step": 54320 }, { "epoch": 4.52, "learning_rate": 3.3990965274506e-06, "loss": 0.8613, "step": 54330 }, { "epoch": 4.52, "learning_rate": 3.3989856719230662e-06, "loss": 0.7851, "step": 54340 }, { "epoch": 4.52, "learning_rate": 3.3988748163955325e-06, "loss": 0.752, "step": 54350 }, { "epoch": 4.52, "learning_rate": 3.3987639608679984e-06, "loss": 0.7763, "step": 54360 }, { "epoch": 4.52, "learning_rate": 3.398653105340465e-06, "loss": 0.8246, "step": 54370 }, { "epoch": 4.52, "learning_rate": 3.398542249812931e-06, "loss": 0.8569, "step": 54380 }, { "epoch": 4.52, "learning_rate": 3.3984313942853977e-06, "loss": 0.8523, "step": 54390 }, { "epoch": 4.52, "learning_rate": 3.3983205387578636e-06, "loss": 0.785, "step": 54400 }, { "epoch": 4.52, "learning_rate": 3.39820968323033e-06, "loss": 0.7842, "step": 54410 }, { "epoch": 4.52, "learning_rate": 3.398098827702796e-06, "loss": 0.8469, "step": 54420 }, { "epoch": 4.52, "learning_rate": 3.3979879721752625e-06, "loss": 0.8358, "step": 54430 }, { "epoch": 4.52, "learning_rate": 3.3978771166477287e-06, "loss": 0.8224, "step": 54440 }, { "epoch": 4.53, "learning_rate": 3.397766261120195e-06, "loss": 0.8695, "step": 54450 }, { "epoch": 4.53, "learning_rate": 3.3976554055926613e-06, "loss": 0.8175, "step": 54460 }, { "epoch": 4.53, "learning_rate": 3.397544550065127e-06, "loss": 0.8491, "step": 54470 }, { "epoch": 4.53, "learning_rate": 3.397433694537594e-06, "loss": 0.8184, "step": 54480 }, { "epoch": 4.53, "learning_rate": 3.39732283901006e-06, "loss": 0.8371, "step": 54490 }, { "epoch": 4.53, "learning_rate": 3.3972119834825265e-06, "loss": 0.8477, "step": 54500 }, { "epoch": 4.53, "learning_rate": 3.3971011279549924e-06, "loss": 0.8187, "step": 54510 }, { "epoch": 4.53, "learning_rate": 3.3969902724274587e-06, "loss": 0.7503, "step": 54520 }, { "epoch": 4.53, "learning_rate": 3.396879416899925e-06, "loss": 0.8433, "step": 54530 }, { "epoch": 4.53, "learning_rate": 3.3967685613723913e-06, "loss": 0.8196, "step": 54540 }, { "epoch": 4.53, "learning_rate": 3.396657705844857e-06, "loss": 0.8614, "step": 54550 }, { "epoch": 4.53, "learning_rate": 3.396546850317324e-06, "loss": 0.8609, "step": 54560 }, { "epoch": 4.54, "learning_rate": 3.39643599478979e-06, "loss": 0.8373, "step": 54570 }, { "epoch": 4.54, "learning_rate": 3.3963251392622565e-06, "loss": 0.8962, "step": 54580 }, { "epoch": 4.54, "learning_rate": 3.3962142837347228e-06, "loss": 0.802, "step": 54590 }, { "epoch": 4.54, "learning_rate": 3.3961034282071886e-06, "loss": 0.826, "step": 54600 }, { "epoch": 4.54, "learning_rate": 3.3959925726796553e-06, "loss": 0.8215, "step": 54610 }, { "epoch": 4.54, "learning_rate": 3.3958817171521212e-06, "loss": 0.8014, "step": 54620 }, { "epoch": 4.54, "learning_rate": 3.3957708616245875e-06, "loss": 0.839, "step": 54630 }, { "epoch": 4.54, "learning_rate": 3.395660006097054e-06, "loss": 0.8779, "step": 54640 }, { "epoch": 4.54, "learning_rate": 3.39554915056952e-06, "loss": 0.8068, "step": 54650 }, { "epoch": 4.54, "learning_rate": 3.3954382950419864e-06, "loss": 0.8299, "step": 54660 }, { "epoch": 4.54, "learning_rate": 3.3953274395144527e-06, "loss": 0.8603, "step": 54670 }, { "epoch": 4.54, "learning_rate": 3.3952165839869186e-06, "loss": 0.9241, "step": 54680 }, { "epoch": 4.55, "learning_rate": 3.3951057284593853e-06, "loss": 0.8796, "step": 54690 }, { "epoch": 4.55, "learning_rate": 3.3949948729318516e-06, "loss": 0.7504, "step": 54700 }, { "epoch": 4.55, "learning_rate": 3.3948840174043174e-06, "loss": 0.7292, "step": 54710 }, { "epoch": 4.55, "learning_rate": 3.394773161876784e-06, "loss": 0.8456, "step": 54720 }, { "epoch": 4.55, "learning_rate": 3.39466230634925e-06, "loss": 0.8626, "step": 54730 }, { "epoch": 4.55, "learning_rate": 3.3945514508217168e-06, "loss": 0.8248, "step": 54740 }, { "epoch": 4.55, "learning_rate": 3.3944405952941826e-06, "loss": 0.7375, "step": 54750 }, { "epoch": 4.55, "learning_rate": 3.394329739766649e-06, "loss": 0.7948, "step": 54760 }, { "epoch": 4.55, "learning_rate": 3.3942188842391152e-06, "loss": 0.9199, "step": 54770 }, { "epoch": 4.55, "learning_rate": 3.3941080287115815e-06, "loss": 0.8469, "step": 54780 }, { "epoch": 4.55, "learning_rate": 3.3939971731840474e-06, "loss": 0.8275, "step": 54790 }, { "epoch": 4.55, "learning_rate": 3.393886317656514e-06, "loss": 0.7589, "step": 54800 }, { "epoch": 4.56, "learning_rate": 3.3937754621289804e-06, "loss": 0.8147, "step": 54810 }, { "epoch": 4.56, "learning_rate": 3.3936646066014467e-06, "loss": 0.7884, "step": 54820 }, { "epoch": 4.56, "learning_rate": 3.393553751073913e-06, "loss": 0.8637, "step": 54830 }, { "epoch": 4.56, "learning_rate": 3.393442895546379e-06, "loss": 0.829, "step": 54840 }, { "epoch": 4.56, "learning_rate": 3.3933320400188456e-06, "loss": 0.796, "step": 54850 }, { "epoch": 4.56, "learning_rate": 3.3932211844913115e-06, "loss": 0.8495, "step": 54860 }, { "epoch": 4.56, "learning_rate": 3.3931103289637778e-06, "loss": 0.8527, "step": 54870 }, { "epoch": 4.56, "learning_rate": 3.392999473436244e-06, "loss": 0.8561, "step": 54880 }, { "epoch": 4.56, "learning_rate": 3.3928886179087103e-06, "loss": 0.8346, "step": 54890 }, { "epoch": 4.56, "learning_rate": 3.3927777623811762e-06, "loss": 0.8376, "step": 54900 }, { "epoch": 4.56, "learning_rate": 3.392666906853643e-06, "loss": 0.8131, "step": 54910 }, { "epoch": 4.56, "learning_rate": 3.392556051326109e-06, "loss": 0.9056, "step": 54920 }, { "epoch": 4.57, "learning_rate": 3.3924451957985755e-06, "loss": 0.8827, "step": 54930 }, { "epoch": 4.57, "learning_rate": 3.392334340271042e-06, "loss": 0.836, "step": 54940 }, { "epoch": 4.57, "learning_rate": 3.3922234847435077e-06, "loss": 0.8304, "step": 54950 }, { "epoch": 4.57, "learning_rate": 3.3921126292159744e-06, "loss": 0.8343, "step": 54960 }, { "epoch": 4.57, "learning_rate": 3.3920017736884403e-06, "loss": 0.8315, "step": 54970 }, { "epoch": 4.57, "learning_rate": 3.3918909181609066e-06, "loss": 0.8898, "step": 54980 }, { "epoch": 4.57, "learning_rate": 3.391780062633373e-06, "loss": 0.8277, "step": 54990 }, { "epoch": 4.57, "learning_rate": 3.391669207105839e-06, "loss": 0.8094, "step": 55000 }, { "epoch": 4.57, "learning_rate": 3.3915583515783055e-06, "loss": 0.7947, "step": 55010 }, { "epoch": 4.57, "learning_rate": 3.3914474960507718e-06, "loss": 0.8324, "step": 55020 }, { "epoch": 4.57, "learning_rate": 3.3913366405232376e-06, "loss": 0.8913, "step": 55030 }, { "epoch": 4.57, "learning_rate": 3.3912257849957043e-06, "loss": 0.8036, "step": 55040 }, { "epoch": 4.58, "learning_rate": 3.3911149294681702e-06, "loss": 0.758, "step": 55050 }, { "epoch": 4.58, "learning_rate": 3.3910040739406365e-06, "loss": 0.8332, "step": 55060 }, { "epoch": 4.58, "learning_rate": 3.3908932184131032e-06, "loss": 0.8671, "step": 55070 }, { "epoch": 4.58, "learning_rate": 3.390782362885569e-06, "loss": 0.8434, "step": 55080 }, { "epoch": 4.58, "learning_rate": 3.390671507358036e-06, "loss": 0.9338, "step": 55090 }, { "epoch": 4.58, "learning_rate": 3.3905606518305017e-06, "loss": 0.8127, "step": 55100 }, { "epoch": 4.58, "learning_rate": 3.390449796302968e-06, "loss": 0.7888, "step": 55110 }, { "epoch": 4.58, "learning_rate": 3.3903389407754343e-06, "loss": 0.8512, "step": 55120 }, { "epoch": 4.58, "learning_rate": 3.3902280852479006e-06, "loss": 0.8585, "step": 55130 }, { "epoch": 4.58, "learning_rate": 3.3901172297203665e-06, "loss": 0.8126, "step": 55140 }, { "epoch": 4.58, "learning_rate": 3.390006374192833e-06, "loss": 0.8641, "step": 55150 }, { "epoch": 4.58, "learning_rate": 3.389895518665299e-06, "loss": 0.8192, "step": 55160 }, { "epoch": 4.59, "learning_rate": 3.3897846631377658e-06, "loss": 0.7462, "step": 55170 }, { "epoch": 4.59, "learning_rate": 3.389673807610232e-06, "loss": 0.8774, "step": 55180 }, { "epoch": 4.59, "learning_rate": 3.389562952082698e-06, "loss": 0.895, "step": 55190 }, { "epoch": 4.59, "learning_rate": 3.3894520965551647e-06, "loss": 0.8274, "step": 55200 }, { "epoch": 4.59, "learning_rate": 3.3893412410276305e-06, "loss": 0.8323, "step": 55210 }, { "epoch": 4.59, "learning_rate": 3.389230385500097e-06, "loss": 0.877, "step": 55220 }, { "epoch": 4.59, "learning_rate": 3.389119529972563e-06, "loss": 0.87, "step": 55230 }, { "epoch": 4.59, "learning_rate": 3.3890086744450294e-06, "loss": 0.8584, "step": 55240 }, { "epoch": 4.59, "learning_rate": 3.3888978189174953e-06, "loss": 0.8525, "step": 55250 }, { "epoch": 4.59, "learning_rate": 3.388786963389962e-06, "loss": 0.8096, "step": 55260 }, { "epoch": 4.59, "learning_rate": 3.388676107862428e-06, "loss": 0.8406, "step": 55270 }, { "epoch": 4.59, "learning_rate": 3.3885652523348946e-06, "loss": 0.8512, "step": 55280 }, { "epoch": 4.6, "learning_rate": 3.3884543968073605e-06, "loss": 0.8649, "step": 55290 }, { "epoch": 4.6, "learning_rate": 3.3883435412798268e-06, "loss": 0.8079, "step": 55300 }, { "epoch": 4.6, "learning_rate": 3.3882326857522935e-06, "loss": 0.8129, "step": 55310 }, { "epoch": 4.6, "learning_rate": 3.3881218302247593e-06, "loss": 0.7934, "step": 55320 }, { "epoch": 4.6, "learning_rate": 3.388010974697226e-06, "loss": 0.8561, "step": 55330 }, { "epoch": 4.6, "learning_rate": 3.387900119169692e-06, "loss": 0.8401, "step": 55340 }, { "epoch": 4.6, "learning_rate": 3.3877892636421582e-06, "loss": 0.8322, "step": 55350 }, { "epoch": 4.6, "learning_rate": 3.3876784081146245e-06, "loss": 0.8153, "step": 55360 }, { "epoch": 4.6, "learning_rate": 3.387567552587091e-06, "loss": 0.826, "step": 55370 }, { "epoch": 4.6, "learning_rate": 3.3874566970595567e-06, "loss": 0.8286, "step": 55380 }, { "epoch": 4.6, "learning_rate": 3.3873458415320234e-06, "loss": 0.8164, "step": 55390 }, { "epoch": 4.6, "learning_rate": 3.3872349860044893e-06, "loss": 0.7526, "step": 55400 }, { "epoch": 4.61, "learning_rate": 3.3871241304769556e-06, "loss": 0.8249, "step": 55410 }, { "epoch": 4.61, "learning_rate": 3.387013274949422e-06, "loss": 0.8429, "step": 55420 }, { "epoch": 4.61, "learning_rate": 3.386902419421888e-06, "loss": 0.855, "step": 55430 }, { "epoch": 4.61, "learning_rate": 3.386791563894355e-06, "loss": 0.7546, "step": 55440 }, { "epoch": 4.61, "learning_rate": 3.3866807083668208e-06, "loss": 0.733, "step": 55450 }, { "epoch": 4.61, "learning_rate": 3.386569852839287e-06, "loss": 0.8914, "step": 55460 }, { "epoch": 4.61, "learning_rate": 3.3864589973117534e-06, "loss": 0.7516, "step": 55470 }, { "epoch": 4.61, "learning_rate": 3.3863481417842196e-06, "loss": 0.8922, "step": 55480 }, { "epoch": 4.61, "learning_rate": 3.3862372862566855e-06, "loss": 0.8457, "step": 55490 }, { "epoch": 4.61, "learning_rate": 3.3861264307291522e-06, "loss": 0.8235, "step": 55500 }, { "epoch": 4.61, "learning_rate": 3.386015575201618e-06, "loss": 0.7951, "step": 55510 }, { "epoch": 4.61, "learning_rate": 3.385904719674085e-06, "loss": 0.8516, "step": 55520 }, { "epoch": 4.62, "learning_rate": 3.3857938641465507e-06, "loss": 0.8456, "step": 55530 }, { "epoch": 4.62, "learning_rate": 3.385683008619017e-06, "loss": 0.799, "step": 55540 }, { "epoch": 4.62, "learning_rate": 3.3855721530914837e-06, "loss": 0.8184, "step": 55550 }, { "epoch": 4.62, "learning_rate": 3.3854612975639496e-06, "loss": 0.7776, "step": 55560 }, { "epoch": 4.62, "learning_rate": 3.385350442036416e-06, "loss": 0.8437, "step": 55570 }, { "epoch": 4.62, "learning_rate": 3.385239586508882e-06, "loss": 0.8873, "step": 55580 }, { "epoch": 4.62, "learning_rate": 3.3851287309813485e-06, "loss": 0.8134, "step": 55590 }, { "epoch": 4.62, "learning_rate": 3.3850178754538148e-06, "loss": 0.8048, "step": 55600 }, { "epoch": 4.62, "learning_rate": 3.384907019926281e-06, "loss": 0.7754, "step": 55610 }, { "epoch": 4.62, "learning_rate": 3.384796164398747e-06, "loss": 0.7685, "step": 55620 }, { "epoch": 4.62, "learning_rate": 3.3846853088712137e-06, "loss": 0.8431, "step": 55630 }, { "epoch": 4.62, "learning_rate": 3.3845744533436795e-06, "loss": 0.8498, "step": 55640 }, { "epoch": 4.63, "learning_rate": 3.384463597816146e-06, "loss": 0.8788, "step": 55650 }, { "epoch": 4.63, "learning_rate": 3.384352742288612e-06, "loss": 0.8086, "step": 55660 }, { "epoch": 4.63, "learning_rate": 3.3842418867610784e-06, "loss": 0.7907, "step": 55670 }, { "epoch": 4.63, "learning_rate": 3.384131031233545e-06, "loss": 0.8236, "step": 55680 }, { "epoch": 4.63, "learning_rate": 3.384020175706011e-06, "loss": 0.8289, "step": 55690 }, { "epoch": 4.63, "learning_rate": 3.3839093201784773e-06, "loss": 0.8209, "step": 55700 }, { "epoch": 4.63, "learning_rate": 3.3837984646509436e-06, "loss": 0.7946, "step": 55710 }, { "epoch": 4.63, "learning_rate": 3.38368760912341e-06, "loss": 0.8298, "step": 55720 }, { "epoch": 4.63, "learning_rate": 3.3835767535958758e-06, "loss": 0.812, "step": 55730 }, { "epoch": 4.63, "learning_rate": 3.3834658980683425e-06, "loss": 0.9111, "step": 55740 }, { "epoch": 4.63, "learning_rate": 3.3833550425408084e-06, "loss": 0.8623, "step": 55750 }, { "epoch": 4.63, "learning_rate": 3.3832441870132746e-06, "loss": 0.7733, "step": 55760 }, { "epoch": 4.64, "learning_rate": 3.383133331485741e-06, "loss": 0.7817, "step": 55770 }, { "epoch": 4.64, "learning_rate": 3.3830224759582072e-06, "loss": 0.817, "step": 55780 }, { "epoch": 4.64, "learning_rate": 3.3829116204306735e-06, "loss": 0.867, "step": 55790 }, { "epoch": 4.64, "learning_rate": 3.38280076490314e-06, "loss": 0.8327, "step": 55800 }, { "epoch": 4.64, "learning_rate": 3.382689909375606e-06, "loss": 0.7911, "step": 55810 }, { "epoch": 4.64, "learning_rate": 3.3825790538480724e-06, "loss": 0.8108, "step": 55820 }, { "epoch": 4.64, "learning_rate": 3.382479283873292e-06, "loss": 0.8488, "step": 55830 }, { "epoch": 4.64, "learning_rate": 3.3823684283457583e-06, "loss": 0.7575, "step": 55840 }, { "epoch": 4.64, "learning_rate": 3.382257572818224e-06, "loss": 0.7122, "step": 55850 }, { "epoch": 4.64, "learning_rate": 3.382146717290691e-06, "loss": 0.857, "step": 55860 }, { "epoch": 4.64, "learning_rate": 3.3820358617631567e-06, "loss": 0.8586, "step": 55870 }, { "epoch": 4.64, "learning_rate": 3.3819250062356234e-06, "loss": 0.8232, "step": 55880 }, { "epoch": 4.65, "learning_rate": 3.3818141507080897e-06, "loss": 0.8228, "step": 55890 }, { "epoch": 4.65, "learning_rate": 3.3817032951805556e-06, "loss": 0.7827, "step": 55900 }, { "epoch": 4.65, "learning_rate": 3.3815924396530223e-06, "loss": 0.8494, "step": 55910 }, { "epoch": 4.65, "learning_rate": 3.381481584125488e-06, "loss": 0.8743, "step": 55920 }, { "epoch": 4.65, "learning_rate": 3.3813707285979545e-06, "loss": 0.8544, "step": 55930 }, { "epoch": 4.65, "learning_rate": 3.3812598730704208e-06, "loss": 0.8828, "step": 55940 }, { "epoch": 4.65, "learning_rate": 3.381149017542887e-06, "loss": 0.8181, "step": 55950 }, { "epoch": 4.65, "learning_rate": 3.3810381620153534e-06, "loss": 0.8599, "step": 55960 }, { "epoch": 4.65, "learning_rate": 3.3809273064878197e-06, "loss": 0.781, "step": 55970 }, { "epoch": 4.65, "learning_rate": 3.3808164509602855e-06, "loss": 0.9268, "step": 55980 }, { "epoch": 4.65, "learning_rate": 3.3807055954327523e-06, "loss": 0.8507, "step": 55990 }, { "epoch": 4.65, "learning_rate": 3.380594739905218e-06, "loss": 0.8153, "step": 56000 }, { "epoch": 4.66, "learning_rate": 3.3804838843776844e-06, "loss": 0.7937, "step": 56010 }, { "epoch": 4.66, "learning_rate": 3.380373028850151e-06, "loss": 0.94, "step": 56020 }, { "epoch": 4.66, "learning_rate": 3.380262173322617e-06, "loss": 0.8895, "step": 56030 }, { "epoch": 4.66, "learning_rate": 3.3801513177950837e-06, "loss": 0.8807, "step": 56040 }, { "epoch": 4.66, "learning_rate": 3.3800404622675496e-06, "loss": 0.7876, "step": 56050 }, { "epoch": 4.66, "learning_rate": 3.379929606740016e-06, "loss": 0.7975, "step": 56060 }, { "epoch": 4.66, "learning_rate": 3.379818751212482e-06, "loss": 0.8009, "step": 56070 }, { "epoch": 4.66, "learning_rate": 3.3797078956849485e-06, "loss": 0.8689, "step": 56080 }, { "epoch": 4.66, "learning_rate": 3.3795970401574144e-06, "loss": 0.8738, "step": 56090 }, { "epoch": 4.66, "learning_rate": 3.379486184629881e-06, "loss": 0.8435, "step": 56100 }, { "epoch": 4.66, "learning_rate": 3.379375329102347e-06, "loss": 0.8446, "step": 56110 }, { "epoch": 4.66, "learning_rate": 3.3792644735748137e-06, "loss": 0.8115, "step": 56120 }, { "epoch": 4.67, "learning_rate": 3.37915361804728e-06, "loss": 0.8241, "step": 56130 }, { "epoch": 4.67, "learning_rate": 3.379042762519746e-06, "loss": 0.838, "step": 56140 }, { "epoch": 4.67, "learning_rate": 3.3789319069922126e-06, "loss": 0.811, "step": 56150 }, { "epoch": 4.67, "learning_rate": 3.3788210514646784e-06, "loss": 0.8656, "step": 56160 }, { "epoch": 4.67, "learning_rate": 3.3787101959371447e-06, "loss": 0.8022, "step": 56170 }, { "epoch": 4.67, "learning_rate": 3.378599340409611e-06, "loss": 0.8675, "step": 56180 }, { "epoch": 4.67, "learning_rate": 3.3784884848820773e-06, "loss": 0.8556, "step": 56190 }, { "epoch": 4.67, "learning_rate": 3.378377629354543e-06, "loss": 0.7715, "step": 56200 }, { "epoch": 4.67, "learning_rate": 3.37826677382701e-06, "loss": 0.8649, "step": 56210 }, { "epoch": 4.67, "learning_rate": 3.3781559182994758e-06, "loss": 0.7912, "step": 56220 }, { "epoch": 4.67, "learning_rate": 3.3780450627719425e-06, "loss": 0.8263, "step": 56230 }, { "epoch": 4.67, "learning_rate": 3.3779342072444084e-06, "loss": 0.7913, "step": 56240 }, { "epoch": 4.68, "learning_rate": 3.3778233517168747e-06, "loss": 0.7755, "step": 56250 }, { "epoch": 4.68, "learning_rate": 3.3777124961893414e-06, "loss": 0.7803, "step": 56260 }, { "epoch": 4.68, "learning_rate": 3.3776016406618073e-06, "loss": 0.8779, "step": 56270 }, { "epoch": 4.68, "learning_rate": 3.377490785134274e-06, "loss": 0.8671, "step": 56280 }, { "epoch": 4.68, "learning_rate": 3.37737992960674e-06, "loss": 0.8122, "step": 56290 }, { "epoch": 4.68, "learning_rate": 3.377269074079206e-06, "loss": 0.8928, "step": 56300 }, { "epoch": 4.68, "learning_rate": 3.3771582185516724e-06, "loss": 0.7564, "step": 56310 }, { "epoch": 4.68, "learning_rate": 3.3770473630241387e-06, "loss": 0.788, "step": 56320 }, { "epoch": 4.68, "learning_rate": 3.3769365074966046e-06, "loss": 0.8667, "step": 56330 }, { "epoch": 4.68, "learning_rate": 3.3768256519690713e-06, "loss": 0.8585, "step": 56340 }, { "epoch": 4.68, "learning_rate": 3.376714796441537e-06, "loss": 0.8049, "step": 56350 }, { "epoch": 4.68, "learning_rate": 3.3766039409140035e-06, "loss": 0.8323, "step": 56360 }, { "epoch": 4.69, "learning_rate": 3.37649308538647e-06, "loss": 0.7968, "step": 56370 }, { "epoch": 4.69, "learning_rate": 3.376382229858936e-06, "loss": 0.8268, "step": 56380 }, { "epoch": 4.69, "learning_rate": 3.376271374331403e-06, "loss": 0.7825, "step": 56390 }, { "epoch": 4.69, "learning_rate": 3.3761605188038687e-06, "loss": 0.8949, "step": 56400 }, { "epoch": 4.69, "learning_rate": 3.376049663276335e-06, "loss": 0.8355, "step": 56410 }, { "epoch": 4.69, "learning_rate": 3.3759388077488013e-06, "loss": 0.8024, "step": 56420 }, { "epoch": 4.69, "learning_rate": 3.3758279522212676e-06, "loss": 0.8557, "step": 56430 }, { "epoch": 4.69, "learning_rate": 3.3757170966937334e-06, "loss": 0.8015, "step": 56440 }, { "epoch": 4.69, "learning_rate": 3.3756062411662e-06, "loss": 0.8127, "step": 56450 }, { "epoch": 4.69, "learning_rate": 3.375495385638666e-06, "loss": 0.853, "step": 56460 }, { "epoch": 4.69, "learning_rate": 3.3753845301111327e-06, "loss": 0.8049, "step": 56470 }, { "epoch": 4.69, "learning_rate": 3.3752736745835986e-06, "loss": 0.8465, "step": 56480 }, { "epoch": 4.7, "learning_rate": 3.375162819056065e-06, "loss": 0.8209, "step": 56490 }, { "epoch": 4.7, "learning_rate": 3.3750519635285316e-06, "loss": 0.8321, "step": 56500 }, { "epoch": 4.7, "learning_rate": 3.3749411080009975e-06, "loss": 0.8663, "step": 56510 }, { "epoch": 4.7, "learning_rate": 3.374830252473464e-06, "loss": 0.952, "step": 56520 }, { "epoch": 4.7, "learning_rate": 3.37471939694593e-06, "loss": 0.8611, "step": 56530 }, { "epoch": 4.7, "learning_rate": 3.3746085414183964e-06, "loss": 0.9481, "step": 56540 }, { "epoch": 4.7, "learning_rate": 3.3744976858908627e-06, "loss": 0.9318, "step": 56550 }, { "epoch": 4.7, "learning_rate": 3.374386830363329e-06, "loss": 0.8115, "step": 56560 }, { "epoch": 4.7, "learning_rate": 3.374275974835795e-06, "loss": 0.8902, "step": 56570 }, { "epoch": 4.7, "learning_rate": 3.3741651193082616e-06, "loss": 0.8431, "step": 56580 }, { "epoch": 4.7, "learning_rate": 3.3740542637807274e-06, "loss": 0.832, "step": 56590 }, { "epoch": 4.7, "learning_rate": 3.3739434082531937e-06, "loss": 0.8279, "step": 56600 }, { "epoch": 4.71, "learning_rate": 3.37383255272566e-06, "loss": 0.8245, "step": 56610 }, { "epoch": 4.71, "learning_rate": 3.3737216971981263e-06, "loss": 0.7653, "step": 56620 }, { "epoch": 4.71, "learning_rate": 3.373610841670593e-06, "loss": 0.9008, "step": 56630 }, { "epoch": 4.71, "learning_rate": 3.373499986143059e-06, "loss": 0.8578, "step": 56640 }, { "epoch": 4.71, "learning_rate": 3.373389130615525e-06, "loss": 0.7575, "step": 56650 }, { "epoch": 4.71, "learning_rate": 3.3732782750879915e-06, "loss": 0.7808, "step": 56660 }, { "epoch": 4.71, "learning_rate": 3.373167419560458e-06, "loss": 0.8256, "step": 56670 }, { "epoch": 4.71, "learning_rate": 3.3730565640329237e-06, "loss": 0.8141, "step": 56680 }, { "epoch": 4.71, "learning_rate": 3.3729457085053904e-06, "loss": 0.8324, "step": 56690 }, { "epoch": 4.71, "learning_rate": 3.3728348529778563e-06, "loss": 0.8386, "step": 56700 }, { "epoch": 4.71, "learning_rate": 3.3727239974503226e-06, "loss": 0.8768, "step": 56710 }, { "epoch": 4.71, "learning_rate": 3.372613141922789e-06, "loss": 0.8646, "step": 56720 }, { "epoch": 4.72, "learning_rate": 3.372502286395255e-06, "loss": 0.9274, "step": 56730 }, { "epoch": 4.72, "learning_rate": 3.372391430867722e-06, "loss": 0.8368, "step": 56740 }, { "epoch": 4.72, "learning_rate": 3.3722805753401877e-06, "loss": 0.8859, "step": 56750 }, { "epoch": 4.72, "learning_rate": 3.372169719812654e-06, "loss": 0.724, "step": 56760 }, { "epoch": 4.72, "learning_rate": 3.3720588642851203e-06, "loss": 0.8138, "step": 56770 }, { "epoch": 4.72, "learning_rate": 3.3719480087575866e-06, "loss": 0.8599, "step": 56780 }, { "epoch": 4.72, "learning_rate": 3.3718371532300525e-06, "loss": 0.8542, "step": 56790 }, { "epoch": 4.72, "learning_rate": 3.3717262977025192e-06, "loss": 0.7983, "step": 56800 }, { "epoch": 4.72, "learning_rate": 3.371615442174985e-06, "loss": 0.8017, "step": 56810 }, { "epoch": 4.72, "learning_rate": 3.371504586647452e-06, "loss": 0.8178, "step": 56820 }, { "epoch": 4.72, "learning_rate": 3.3713937311199177e-06, "loss": 0.8643, "step": 56830 }, { "epoch": 4.72, "learning_rate": 3.371282875592384e-06, "loss": 0.8268, "step": 56840 }, { "epoch": 4.73, "learning_rate": 3.3711720200648503e-06, "loss": 0.7666, "step": 56850 }, { "epoch": 4.73, "learning_rate": 3.3710611645373166e-06, "loss": 0.7809, "step": 56860 }, { "epoch": 4.73, "learning_rate": 3.370950309009783e-06, "loss": 0.7302, "step": 56870 }, { "epoch": 4.73, "learning_rate": 3.370839453482249e-06, "loss": 0.8987, "step": 56880 }, { "epoch": 4.73, "learning_rate": 3.3707285979547155e-06, "loss": 0.9093, "step": 56890 }, { "epoch": 4.73, "learning_rate": 3.3706177424271817e-06, "loss": 0.8434, "step": 56900 }, { "epoch": 4.73, "learning_rate": 3.370506886899648e-06, "loss": 0.8091, "step": 56910 }, { "epoch": 4.73, "learning_rate": 3.370396031372114e-06, "loss": 0.8011, "step": 56920 }, { "epoch": 4.73, "learning_rate": 3.3702851758445806e-06, "loss": 0.8624, "step": 56930 }, { "epoch": 4.73, "learning_rate": 3.3701743203170465e-06, "loss": 0.7942, "step": 56940 }, { "epoch": 4.73, "learning_rate": 3.370063464789513e-06, "loss": 0.8426, "step": 56950 }, { "epoch": 4.73, "learning_rate": 3.369952609261979e-06, "loss": 0.7905, "step": 56960 }, { "epoch": 4.74, "learning_rate": 3.3698417537344454e-06, "loss": 0.7695, "step": 56970 }, { "epoch": 4.74, "learning_rate": 3.3697308982069117e-06, "loss": 0.819, "step": 56980 }, { "epoch": 4.74, "learning_rate": 3.369620042679378e-06, "loss": 0.8516, "step": 56990 }, { "epoch": 4.74, "learning_rate": 3.3695091871518443e-06, "loss": 0.7788, "step": 57000 }, { "epoch": 4.74, "learning_rate": 3.3693983316243106e-06, "loss": 0.8141, "step": 57010 }, { "epoch": 4.74, "learning_rate": 3.369287476096777e-06, "loss": 0.819, "step": 57020 }, { "epoch": 4.74, "learning_rate": 3.3691766205692427e-06, "loss": 0.8969, "step": 57030 }, { "epoch": 4.74, "learning_rate": 3.3690657650417095e-06, "loss": 0.8215, "step": 57040 }, { "epoch": 4.74, "learning_rate": 3.3689549095141753e-06, "loss": 0.8483, "step": 57050 }, { "epoch": 4.74, "learning_rate": 3.368844053986642e-06, "loss": 0.8134, "step": 57060 }, { "epoch": 4.74, "learning_rate": 3.368733198459108e-06, "loss": 0.8729, "step": 57070 }, { "epoch": 4.74, "learning_rate": 3.3686223429315742e-06, "loss": 0.8691, "step": 57080 }, { "epoch": 4.75, "learning_rate": 3.3685114874040405e-06, "loss": 0.7624, "step": 57090 }, { "epoch": 4.75, "learning_rate": 3.368400631876507e-06, "loss": 0.8737, "step": 57100 }, { "epoch": 4.75, "learning_rate": 3.368289776348973e-06, "loss": 0.8758, "step": 57110 }, { "epoch": 4.75, "learning_rate": 3.3681789208214394e-06, "loss": 0.8089, "step": 57120 }, { "epoch": 4.75, "learning_rate": 3.3680680652939057e-06, "loss": 0.859, "step": 57130 }, { "epoch": 4.75, "learning_rate": 3.3679572097663716e-06, "loss": 0.8015, "step": 57140 }, { "epoch": 4.75, "learning_rate": 3.3678463542388383e-06, "loss": 0.8446, "step": 57150 }, { "epoch": 4.75, "learning_rate": 3.367735498711304e-06, "loss": 0.8479, "step": 57160 }, { "epoch": 4.75, "learning_rate": 3.367624643183771e-06, "loss": 0.7675, "step": 57170 }, { "epoch": 4.75, "learning_rate": 3.3675137876562367e-06, "loss": 0.8963, "step": 57180 }, { "epoch": 4.75, "learning_rate": 3.367402932128703e-06, "loss": 0.7969, "step": 57190 }, { "epoch": 4.75, "learning_rate": 3.3672920766011693e-06, "loss": 0.834, "step": 57200 }, { "epoch": 4.76, "learning_rate": 3.3671812210736356e-06, "loss": 0.8711, "step": 57210 }, { "epoch": 4.76, "learning_rate": 3.3670703655461015e-06, "loss": 0.8261, "step": 57220 }, { "epoch": 4.76, "learning_rate": 3.3669595100185682e-06, "loss": 0.8705, "step": 57230 }, { "epoch": 4.76, "learning_rate": 3.3668486544910345e-06, "loss": 0.7434, "step": 57240 }, { "epoch": 4.76, "learning_rate": 3.366737798963501e-06, "loss": 0.7834, "step": 57250 }, { "epoch": 4.76, "learning_rate": 3.366626943435967e-06, "loss": 0.8461, "step": 57260 }, { "epoch": 4.76, "learning_rate": 3.366516087908433e-06, "loss": 0.8359, "step": 57270 }, { "epoch": 4.76, "learning_rate": 3.3664052323808997e-06, "loss": 0.8742, "step": 57280 }, { "epoch": 4.76, "learning_rate": 3.3662943768533656e-06, "loss": 0.8356, "step": 57290 }, { "epoch": 4.76, "learning_rate": 3.366183521325832e-06, "loss": 0.798, "step": 57300 }, { "epoch": 4.76, "learning_rate": 3.366072665798298e-06, "loss": 0.7759, "step": 57310 }, { "epoch": 4.76, "learning_rate": 3.3659618102707645e-06, "loss": 0.8134, "step": 57320 }, { "epoch": 4.77, "learning_rate": 3.3658509547432308e-06, "loss": 0.8515, "step": 57330 }, { "epoch": 4.77, "learning_rate": 3.365740099215697e-06, "loss": 0.8331, "step": 57340 }, { "epoch": 4.77, "learning_rate": 3.365629243688163e-06, "loss": 0.7863, "step": 57350 }, { "epoch": 4.77, "learning_rate": 3.3655183881606296e-06, "loss": 0.8021, "step": 57360 }, { "epoch": 4.77, "learning_rate": 3.365407532633096e-06, "loss": 0.8718, "step": 57370 }, { "epoch": 4.77, "learning_rate": 3.365296677105562e-06, "loss": 0.8534, "step": 57380 }, { "epoch": 4.77, "learning_rate": 3.3651858215780285e-06, "loss": 0.8469, "step": 57390 }, { "epoch": 4.77, "learning_rate": 3.3650749660504944e-06, "loss": 0.8608, "step": 57400 }, { "epoch": 4.77, "learning_rate": 3.364964110522961e-06, "loss": 0.8441, "step": 57410 }, { "epoch": 4.77, "learning_rate": 3.364853254995427e-06, "loss": 0.8173, "step": 57420 }, { "epoch": 4.77, "learning_rate": 3.3647423994678933e-06, "loss": 0.8384, "step": 57430 }, { "epoch": 4.77, "learning_rate": 3.3646315439403596e-06, "loss": 0.8372, "step": 57440 }, { "epoch": 4.78, "learning_rate": 3.364520688412826e-06, "loss": 0.8244, "step": 57450 }, { "epoch": 4.78, "learning_rate": 3.3644098328852917e-06, "loss": 0.8402, "step": 57460 }, { "epoch": 4.78, "learning_rate": 3.3642989773577585e-06, "loss": 0.8316, "step": 57470 }, { "epoch": 4.78, "learning_rate": 3.3641881218302248e-06, "loss": 0.8707, "step": 57480 }, { "epoch": 4.78, "learning_rate": 3.3640772663026906e-06, "loss": 0.8017, "step": 57490 }, { "epoch": 4.78, "learning_rate": 3.3639664107751574e-06, "loss": 0.8144, "step": 57500 }, { "epoch": 4.78, "learning_rate": 3.3638555552476232e-06, "loss": 0.8841, "step": 57510 }, { "epoch": 4.78, "learning_rate": 3.36374469972009e-06, "loss": 0.8115, "step": 57520 }, { "epoch": 4.78, "learning_rate": 3.363633844192556e-06, "loss": 0.8502, "step": 57530 }, { "epoch": 4.78, "learning_rate": 3.363522988665022e-06, "loss": 0.8247, "step": 57540 }, { "epoch": 4.78, "learning_rate": 3.3634121331374884e-06, "loss": 0.8689, "step": 57550 }, { "epoch": 4.78, "learning_rate": 3.3633012776099547e-06, "loss": 0.7911, "step": 57560 }, { "epoch": 4.79, "learning_rate": 3.3631904220824206e-06, "loss": 0.7942, "step": 57570 }, { "epoch": 4.79, "learning_rate": 3.3630795665548873e-06, "loss": 0.8706, "step": 57580 }, { "epoch": 4.79, "learning_rate": 3.362968711027353e-06, "loss": 0.9212, "step": 57590 }, { "epoch": 4.79, "learning_rate": 3.36285785549982e-06, "loss": 0.832, "step": 57600 }, { "epoch": 4.79, "learning_rate": 3.362746999972286e-06, "loss": 0.8387, "step": 57610 }, { "epoch": 4.79, "learning_rate": 3.362636144444752e-06, "loss": 0.6902, "step": 57620 }, { "epoch": 4.79, "learning_rate": 3.3625252889172188e-06, "loss": 0.8234, "step": 57630 }, { "epoch": 4.79, "learning_rate": 3.3624144333896846e-06, "loss": 0.8565, "step": 57640 }, { "epoch": 4.79, "learning_rate": 3.362303577862151e-06, "loss": 0.7646, "step": 57650 }, { "epoch": 4.79, "learning_rate": 3.3621927223346172e-06, "loss": 0.9089, "step": 57660 }, { "epoch": 4.79, "learning_rate": 3.3620818668070835e-06, "loss": 0.8052, "step": 57670 }, { "epoch": 4.79, "learning_rate": 3.36197101127955e-06, "loss": 0.8717, "step": 57680 }, { "epoch": 4.8, "learning_rate": 3.361860155752016e-06, "loss": 0.7891, "step": 57690 }, { "epoch": 4.8, "learning_rate": 3.361749300224482e-06, "loss": 0.9025, "step": 57700 }, { "epoch": 4.8, "learning_rate": 3.3616384446969487e-06, "loss": 0.8228, "step": 57710 }, { "epoch": 4.8, "learning_rate": 3.3615275891694146e-06, "loss": 0.8234, "step": 57720 }, { "epoch": 4.8, "learning_rate": 3.361416733641881e-06, "loss": 0.8605, "step": 57730 }, { "epoch": 4.8, "learning_rate": 3.3613058781143476e-06, "loss": 0.8405, "step": 57740 }, { "epoch": 4.8, "learning_rate": 3.3611950225868135e-06, "loss": 0.765, "step": 57750 }, { "epoch": 4.8, "learning_rate": 3.36108416705928e-06, "loss": 0.8343, "step": 57760 }, { "epoch": 4.8, "learning_rate": 3.360973311531746e-06, "loss": 0.823, "step": 57770 }, { "epoch": 4.8, "learning_rate": 3.3608624560042123e-06, "loss": 0.8246, "step": 57780 }, { "epoch": 4.8, "learning_rate": 3.3607516004766786e-06, "loss": 0.8742, "step": 57790 }, { "epoch": 4.8, "learning_rate": 3.360640744949145e-06, "loss": 0.8106, "step": 57800 }, { "epoch": 4.81, "learning_rate": 3.360529889421611e-06, "loss": 0.7718, "step": 57810 }, { "epoch": 4.81, "learning_rate": 3.3604190338940775e-06, "loss": 0.8333, "step": 57820 }, { "epoch": 4.81, "learning_rate": 3.3603081783665434e-06, "loss": 0.7597, "step": 57830 }, { "epoch": 4.81, "learning_rate": 3.36019732283901e-06, "loss": 0.7923, "step": 57840 }, { "epoch": 4.81, "learning_rate": 3.3600864673114764e-06, "loss": 0.8636, "step": 57850 }, { "epoch": 4.81, "learning_rate": 3.3599756117839423e-06, "loss": 0.8277, "step": 57860 }, { "epoch": 4.81, "learning_rate": 3.359864756256409e-06, "loss": 0.8457, "step": 57870 }, { "epoch": 4.81, "learning_rate": 3.359753900728875e-06, "loss": 0.8863, "step": 57880 }, { "epoch": 4.81, "learning_rate": 3.359643045201341e-06, "loss": 0.8183, "step": 57890 }, { "epoch": 4.81, "learning_rate": 3.3595321896738075e-06, "loss": 0.8598, "step": 57900 }, { "epoch": 4.81, "learning_rate": 3.3594213341462738e-06, "loss": 0.8441, "step": 57910 }, { "epoch": 4.81, "learning_rate": 3.3593104786187396e-06, "loss": 0.8157, "step": 57920 }, { "epoch": 4.82, "learning_rate": 3.3591996230912064e-06, "loss": 0.8607, "step": 57930 }, { "epoch": 4.82, "learning_rate": 3.3590887675636722e-06, "loss": 0.8314, "step": 57940 }, { "epoch": 4.82, "learning_rate": 3.358977912036139e-06, "loss": 0.8187, "step": 57950 }, { "epoch": 4.82, "learning_rate": 3.358867056508605e-06, "loss": 0.8243, "step": 57960 }, { "epoch": 4.82, "learning_rate": 3.358756200981071e-06, "loss": 0.9102, "step": 57970 }, { "epoch": 4.82, "learning_rate": 3.358645345453538e-06, "loss": 0.8511, "step": 57980 }, { "epoch": 4.82, "learning_rate": 3.3585344899260037e-06, "loss": 0.8464, "step": 57990 }, { "epoch": 4.82, "learning_rate": 3.35842363439847e-06, "loss": 0.8002, "step": 58000 }, { "epoch": 4.82, "learning_rate": 3.3583127788709363e-06, "loss": 0.8662, "step": 58010 }, { "epoch": 4.82, "learning_rate": 3.3582019233434026e-06, "loss": 0.7959, "step": 58020 }, { "epoch": 4.82, "learning_rate": 3.358091067815869e-06, "loss": 0.9104, "step": 58030 }, { "epoch": 4.82, "learning_rate": 3.357980212288335e-06, "loss": 0.7814, "step": 58040 }, { "epoch": 4.83, "learning_rate": 3.357869356760801e-06, "loss": 0.8254, "step": 58050 }, { "epoch": 4.83, "learning_rate": 3.3577585012332678e-06, "loss": 0.8096, "step": 58060 }, { "epoch": 4.83, "learning_rate": 3.3576476457057336e-06, "loss": 0.8551, "step": 58070 }, { "epoch": 4.83, "learning_rate": 3.3575367901782e-06, "loss": 0.8201, "step": 58080 }, { "epoch": 4.83, "learning_rate": 3.3574259346506662e-06, "loss": 0.8281, "step": 58090 }, { "epoch": 4.83, "learning_rate": 3.3573150791231325e-06, "loss": 0.8418, "step": 58100 }, { "epoch": 4.83, "learning_rate": 3.3572042235955992e-06, "loss": 0.8047, "step": 58110 }, { "epoch": 4.83, "learning_rate": 3.357093368068065e-06, "loss": 0.8086, "step": 58120 }, { "epoch": 4.83, "learning_rate": 3.3569825125405314e-06, "loss": 0.9091, "step": 58130 }, { "epoch": 4.83, "learning_rate": 3.3568716570129977e-06, "loss": 0.8685, "step": 58140 }, { "epoch": 4.83, "learning_rate": 3.356760801485464e-06, "loss": 0.764, "step": 58150 }, { "epoch": 4.83, "learning_rate": 3.35664994595793e-06, "loss": 0.7756, "step": 58160 }, { "epoch": 4.84, "learning_rate": 3.3565390904303966e-06, "loss": 0.8714, "step": 58170 }, { "epoch": 4.84, "learning_rate": 3.3564282349028625e-06, "loss": 0.854, "step": 58180 }, { "epoch": 4.84, "learning_rate": 3.356317379375329e-06, "loss": 0.8401, "step": 58190 }, { "epoch": 4.84, "learning_rate": 3.356206523847795e-06, "loss": 0.8015, "step": 58200 }, { "epoch": 4.84, "learning_rate": 3.3560956683202614e-06, "loss": 0.7827, "step": 58210 }, { "epoch": 4.84, "learning_rate": 3.355984812792728e-06, "loss": 0.7751, "step": 58220 }, { "epoch": 4.84, "learning_rate": 3.355873957265194e-06, "loss": 0.8912, "step": 58230 }, { "epoch": 4.84, "learning_rate": 3.3557631017376602e-06, "loss": 0.8166, "step": 58240 }, { "epoch": 4.84, "learning_rate": 3.3556522462101265e-06, "loss": 0.7766, "step": 58250 }, { "epoch": 4.84, "learning_rate": 3.355541390682593e-06, "loss": 0.8005, "step": 58260 }, { "epoch": 4.84, "learning_rate": 3.355430535155059e-06, "loss": 0.8253, "step": 58270 }, { "epoch": 4.84, "learning_rate": 3.3553196796275254e-06, "loss": 0.8223, "step": 58280 }, { "epoch": 4.84, "learning_rate": 3.3552088240999913e-06, "loss": 0.8213, "step": 58290 }, { "epoch": 4.85, "learning_rate": 3.355097968572458e-06, "loss": 0.7804, "step": 58300 }, { "epoch": 4.85, "learning_rate": 3.354987113044924e-06, "loss": 0.8961, "step": 58310 }, { "epoch": 4.85, "learning_rate": 3.35487625751739e-06, "loss": 0.8045, "step": 58320 }, { "epoch": 4.85, "learning_rate": 3.3547654019898565e-06, "loss": 0.8952, "step": 58330 }, { "epoch": 4.85, "learning_rate": 3.3546545464623228e-06, "loss": 0.8114, "step": 58340 }, { "epoch": 4.85, "learning_rate": 3.3545436909347895e-06, "loss": 0.7693, "step": 58350 }, { "epoch": 4.85, "learning_rate": 3.3544328354072554e-06, "loss": 0.8514, "step": 58360 }, { "epoch": 4.85, "learning_rate": 3.3543219798797217e-06, "loss": 0.824, "step": 58370 }, { "epoch": 4.85, "learning_rate": 3.354211124352188e-06, "loss": 0.8571, "step": 58380 }, { "epoch": 4.85, "learning_rate": 3.3541002688246542e-06, "loss": 0.7932, "step": 58390 }, { "epoch": 4.85, "learning_rate": 3.35398941329712e-06, "loss": 0.8541, "step": 58400 }, { "epoch": 4.85, "learning_rate": 3.353878557769587e-06, "loss": 0.8466, "step": 58410 }, { "epoch": 4.86, "learning_rate": 3.3537677022420527e-06, "loss": 0.7457, "step": 58420 }, { "epoch": 4.86, "learning_rate": 3.353656846714519e-06, "loss": 0.887, "step": 58430 }, { "epoch": 4.86, "learning_rate": 3.3535459911869853e-06, "loss": 0.83, "step": 58440 }, { "epoch": 4.86, "learning_rate": 3.3534351356594516e-06, "loss": 0.833, "step": 58450 }, { "epoch": 4.86, "learning_rate": 3.353324280131918e-06, "loss": 0.8443, "step": 58460 }, { "epoch": 4.86, "learning_rate": 3.353213424604384e-06, "loss": 0.8135, "step": 58470 }, { "epoch": 4.86, "learning_rate": 3.3531025690768505e-06, "loss": 0.9176, "step": 58480 }, { "epoch": 4.86, "learning_rate": 3.3529917135493168e-06, "loss": 0.8647, "step": 58490 }, { "epoch": 4.86, "learning_rate": 3.352880858021783e-06, "loss": 0.812, "step": 58500 }, { "epoch": 4.86, "learning_rate": 3.352770002494249e-06, "loss": 0.8409, "step": 58510 }, { "epoch": 4.86, "learning_rate": 3.3526591469667157e-06, "loss": 0.7673, "step": 58520 }, { "epoch": 4.86, "learning_rate": 3.3525482914391815e-06, "loss": 0.886, "step": 58530 }, { "epoch": 4.87, "learning_rate": 3.3524374359116483e-06, "loss": 0.8567, "step": 58540 }, { "epoch": 4.87, "learning_rate": 3.352326580384114e-06, "loss": 0.8259, "step": 58550 }, { "epoch": 4.87, "learning_rate": 3.3522157248565804e-06, "loss": 0.7716, "step": 58560 }, { "epoch": 4.87, "learning_rate": 3.3521048693290467e-06, "loss": 0.8335, "step": 58570 }, { "epoch": 4.87, "learning_rate": 3.351994013801513e-06, "loss": 0.8808, "step": 58580 }, { "epoch": 4.87, "learning_rate": 3.3518831582739793e-06, "loss": 0.7714, "step": 58590 }, { "epoch": 4.87, "learning_rate": 3.3517723027464456e-06, "loss": 0.8785, "step": 58600 }, { "epoch": 4.87, "learning_rate": 3.351661447218912e-06, "loss": 0.873, "step": 58610 }, { "epoch": 4.87, "learning_rate": 3.351550591691378e-06, "loss": 0.8224, "step": 58620 }, { "epoch": 4.87, "learning_rate": 3.3514397361638445e-06, "loss": 0.8809, "step": 58630 }, { "epoch": 4.87, "learning_rate": 3.351339966189064e-06, "loss": 0.7841, "step": 58640 }, { "epoch": 4.87, "learning_rate": 3.35122911066153e-06, "loss": 0.7722, "step": 58650 }, { "epoch": 4.88, "learning_rate": 3.3511182551339966e-06, "loss": 0.7938, "step": 58660 }, { "epoch": 4.88, "learning_rate": 3.3510073996064625e-06, "loss": 0.8364, "step": 58670 }, { "epoch": 4.88, "learning_rate": 3.3508965440789288e-06, "loss": 0.8816, "step": 58680 }, { "epoch": 4.88, "learning_rate": 3.3507856885513955e-06, "loss": 0.8349, "step": 58690 }, { "epoch": 4.88, "learning_rate": 3.3506748330238614e-06, "loss": 0.8127, "step": 58700 }, { "epoch": 4.88, "learning_rate": 3.350563977496328e-06, "loss": 0.8046, "step": 58710 }, { "epoch": 4.88, "learning_rate": 3.350453121968794e-06, "loss": 0.7692, "step": 58720 }, { "epoch": 4.88, "learning_rate": 3.3503422664412603e-06, "loss": 0.8858, "step": 58730 }, { "epoch": 4.88, "learning_rate": 3.3502314109137266e-06, "loss": 0.8347, "step": 58740 }, { "epoch": 4.88, "learning_rate": 3.350120555386193e-06, "loss": 0.8489, "step": 58750 }, { "epoch": 4.88, "learning_rate": 3.3500096998586587e-06, "loss": 0.8185, "step": 58760 }, { "epoch": 4.88, "learning_rate": 3.3498988443311254e-06, "loss": 0.8059, "step": 58770 }, { "epoch": 4.89, "learning_rate": 3.3497879888035913e-06, "loss": 0.9167, "step": 58780 }, { "epoch": 4.89, "learning_rate": 3.349677133276058e-06, "loss": 0.8084, "step": 58790 }, { "epoch": 4.89, "learning_rate": 3.3495662777485243e-06, "loss": 0.7979, "step": 58800 }, { "epoch": 4.89, "learning_rate": 3.34945542222099e-06, "loss": 0.8315, "step": 58810 }, { "epoch": 4.89, "learning_rate": 3.349344566693457e-06, "loss": 0.8127, "step": 58820 }, { "epoch": 4.89, "learning_rate": 3.349233711165923e-06, "loss": 0.8607, "step": 58830 }, { "epoch": 4.89, "learning_rate": 3.349122855638389e-06, "loss": 0.8577, "step": 58840 }, { "epoch": 4.89, "learning_rate": 3.3490120001108554e-06, "loss": 0.8271, "step": 58850 }, { "epoch": 4.89, "learning_rate": 3.3489011445833217e-06, "loss": 0.872, "step": 58860 }, { "epoch": 4.89, "learning_rate": 3.3487902890557875e-06, "loss": 0.8302, "step": 58870 }, { "epoch": 4.89, "learning_rate": 3.3486794335282543e-06, "loss": 0.8657, "step": 58880 }, { "epoch": 4.89, "learning_rate": 3.34856857800072e-06, "loss": 0.7891, "step": 58890 }, { "epoch": 4.9, "learning_rate": 3.348457722473187e-06, "loss": 0.7848, "step": 58900 }, { "epoch": 4.9, "learning_rate": 3.3483468669456527e-06, "loss": 0.8052, "step": 58910 }, { "epoch": 4.9, "learning_rate": 3.348236011418119e-06, "loss": 0.7691, "step": 58920 }, { "epoch": 4.9, "learning_rate": 3.3481251558905857e-06, "loss": 0.8726, "step": 58930 }, { "epoch": 4.9, "learning_rate": 3.3480143003630516e-06, "loss": 0.8755, "step": 58940 }, { "epoch": 4.9, "learning_rate": 3.347903444835518e-06, "loss": 0.7847, "step": 58950 }, { "epoch": 4.9, "learning_rate": 3.347792589307984e-06, "loss": 0.8509, "step": 58960 }, { "epoch": 4.9, "learning_rate": 3.3476817337804505e-06, "loss": 0.7499, "step": 58970 }, { "epoch": 4.9, "learning_rate": 3.347570878252917e-06, "loss": 0.8477, "step": 58980 }, { "epoch": 4.9, "learning_rate": 3.347460022725383e-06, "loss": 0.8247, "step": 58990 }, { "epoch": 4.9, "learning_rate": 3.347349167197849e-06, "loss": 0.8667, "step": 59000 }, { "epoch": 4.9, "learning_rate": 3.3472383116703157e-06, "loss": 0.7978, "step": 59010 }, { "epoch": 4.91, "learning_rate": 3.3471274561427816e-06, "loss": 0.7998, "step": 59020 }, { "epoch": 4.91, "learning_rate": 3.347016600615248e-06, "loss": 0.8997, "step": 59030 }, { "epoch": 4.91, "learning_rate": 3.3469057450877146e-06, "loss": 0.8145, "step": 59040 }, { "epoch": 4.91, "learning_rate": 3.3467948895601804e-06, "loss": 0.849, "step": 59050 }, { "epoch": 4.91, "learning_rate": 3.346684034032647e-06, "loss": 0.8047, "step": 59060 }, { "epoch": 4.91, "learning_rate": 3.346573178505113e-06, "loss": 0.7894, "step": 59070 }, { "epoch": 4.91, "learning_rate": 3.3464623229775793e-06, "loss": 0.9387, "step": 59080 }, { "epoch": 4.91, "learning_rate": 3.3463514674500456e-06, "loss": 0.8376, "step": 59090 }, { "epoch": 4.91, "learning_rate": 3.346240611922512e-06, "loss": 0.7862, "step": 59100 }, { "epoch": 4.91, "learning_rate": 3.346129756394978e-06, "loss": 0.8161, "step": 59110 }, { "epoch": 4.91, "learning_rate": 3.3460189008674445e-06, "loss": 0.8651, "step": 59120 }, { "epoch": 4.91, "learning_rate": 3.3459080453399104e-06, "loss": 0.889, "step": 59130 }, { "epoch": 4.92, "learning_rate": 3.345797189812377e-06, "loss": 0.913, "step": 59140 }, { "epoch": 4.92, "learning_rate": 3.345686334284843e-06, "loss": 0.7862, "step": 59150 }, { "epoch": 4.92, "learning_rate": 3.3455754787573093e-06, "loss": 0.7889, "step": 59160 }, { "epoch": 4.92, "learning_rate": 3.345464623229776e-06, "loss": 0.8324, "step": 59170 }, { "epoch": 4.92, "learning_rate": 3.345353767702242e-06, "loss": 0.8958, "step": 59180 }, { "epoch": 4.92, "learning_rate": 3.345242912174708e-06, "loss": 0.8344, "step": 59190 }, { "epoch": 4.92, "learning_rate": 3.3451320566471744e-06, "loss": 0.8525, "step": 59200 }, { "epoch": 4.92, "learning_rate": 3.3450212011196407e-06, "loss": 0.7886, "step": 59210 }, { "epoch": 4.92, "learning_rate": 3.344910345592107e-06, "loss": 0.8453, "step": 59220 }, { "epoch": 4.92, "learning_rate": 3.3447994900645733e-06, "loss": 0.874, "step": 59230 }, { "epoch": 4.92, "learning_rate": 3.344688634537039e-06, "loss": 0.886, "step": 59240 }, { "epoch": 4.92, "learning_rate": 3.344577779009506e-06, "loss": 0.7629, "step": 59250 }, { "epoch": 4.93, "learning_rate": 3.344466923481972e-06, "loss": 0.8244, "step": 59260 }, { "epoch": 4.93, "learning_rate": 3.344356067954438e-06, "loss": 0.8154, "step": 59270 }, { "epoch": 4.93, "learning_rate": 3.3442452124269044e-06, "loss": 0.8871, "step": 59280 }, { "epoch": 4.93, "learning_rate": 3.3441343568993707e-06, "loss": 0.8326, "step": 59290 }, { "epoch": 4.93, "learning_rate": 3.3440235013718374e-06, "loss": 0.7764, "step": 59300 }, { "epoch": 4.93, "learning_rate": 3.3439126458443033e-06, "loss": 0.843, "step": 59310 }, { "epoch": 4.93, "learning_rate": 3.3438017903167696e-06, "loss": 0.8666, "step": 59320 }, { "epoch": 4.93, "learning_rate": 3.343690934789236e-06, "loss": 0.8359, "step": 59330 }, { "epoch": 4.93, "learning_rate": 3.343580079261702e-06, "loss": 0.8497, "step": 59340 }, { "epoch": 4.93, "learning_rate": 3.343469223734168e-06, "loss": 0.8587, "step": 59350 }, { "epoch": 4.93, "learning_rate": 3.3433583682066348e-06, "loss": 0.8419, "step": 59360 }, { "epoch": 4.93, "learning_rate": 3.3432475126791006e-06, "loss": 0.777, "step": 59370 }, { "epoch": 4.94, "learning_rate": 3.343136657151567e-06, "loss": 0.9153, "step": 59380 }, { "epoch": 4.94, "learning_rate": 3.3430258016240332e-06, "loss": 0.7882, "step": 59390 }, { "epoch": 4.94, "learning_rate": 3.3429149460964995e-06, "loss": 0.7696, "step": 59400 }, { "epoch": 4.94, "learning_rate": 3.3428040905689662e-06, "loss": 0.7937, "step": 59410 }, { "epoch": 4.94, "learning_rate": 3.342693235041432e-06, "loss": 0.792, "step": 59420 }, { "epoch": 4.94, "learning_rate": 3.3425823795138984e-06, "loss": 0.8946, "step": 59430 }, { "epoch": 4.94, "learning_rate": 3.3424715239863647e-06, "loss": 0.7749, "step": 59440 }, { "epoch": 4.94, "learning_rate": 3.342360668458831e-06, "loss": 0.8059, "step": 59450 }, { "epoch": 4.94, "learning_rate": 3.342249812931297e-06, "loss": 0.8001, "step": 59460 }, { "epoch": 4.94, "learning_rate": 3.3421389574037636e-06, "loss": 0.7496, "step": 59470 }, { "epoch": 4.94, "learning_rate": 3.3420281018762294e-06, "loss": 0.8347, "step": 59480 }, { "epoch": 4.94, "learning_rate": 3.341917246348696e-06, "loss": 0.8417, "step": 59490 }, { "epoch": 4.95, "learning_rate": 3.341806390821162e-06, "loss": 0.786, "step": 59500 }, { "epoch": 4.95, "learning_rate": 3.3416955352936283e-06, "loss": 0.7934, "step": 59510 }, { "epoch": 4.95, "learning_rate": 3.3415846797660946e-06, "loss": 0.7741, "step": 59520 }, { "epoch": 4.95, "learning_rate": 3.341473824238561e-06, "loss": 0.8829, "step": 59530 }, { "epoch": 4.95, "learning_rate": 3.3413629687110272e-06, "loss": 0.84, "step": 59540 }, { "epoch": 4.95, "learning_rate": 3.3412521131834935e-06, "loss": 0.8386, "step": 59550 }, { "epoch": 4.95, "learning_rate": 3.34114125765596e-06, "loss": 0.8087, "step": 59560 }, { "epoch": 4.95, "learning_rate": 3.341030402128426e-06, "loss": 0.9367, "step": 59570 }, { "epoch": 4.95, "learning_rate": 3.3409195466008924e-06, "loss": 0.8918, "step": 59580 }, { "epoch": 4.95, "learning_rate": 3.3408086910733583e-06, "loss": 0.7786, "step": 59590 }, { "epoch": 4.95, "learning_rate": 3.340697835545825e-06, "loss": 0.7546, "step": 59600 }, { "epoch": 4.95, "learning_rate": 3.340586980018291e-06, "loss": 0.8203, "step": 59610 }, { "epoch": 4.96, "learning_rate": 3.340476124490757e-06, "loss": 0.8469, "step": 59620 }, { "epoch": 4.96, "learning_rate": 3.3403652689632235e-06, "loss": 0.8379, "step": 59630 }, { "epoch": 4.96, "learning_rate": 3.3402544134356897e-06, "loss": 0.8408, "step": 59640 }, { "epoch": 4.96, "learning_rate": 3.3401435579081556e-06, "loss": 0.7693, "step": 59650 }, { "epoch": 4.96, "learning_rate": 3.3400327023806223e-06, "loss": 0.813, "step": 59660 }, { "epoch": 4.96, "learning_rate": 3.3399218468530886e-06, "loss": 0.7711, "step": 59670 }, { "epoch": 4.96, "learning_rate": 3.339810991325555e-06, "loss": 0.9002, "step": 59680 }, { "epoch": 4.96, "learning_rate": 3.3397001357980212e-06, "loss": 0.8268, "step": 59690 }, { "epoch": 4.96, "learning_rate": 3.339589280270487e-06, "loss": 0.7927, "step": 59700 }, { "epoch": 4.96, "learning_rate": 3.339478424742954e-06, "loss": 0.8203, "step": 59710 }, { "epoch": 4.96, "learning_rate": 3.3393675692154197e-06, "loss": 0.8596, "step": 59720 }, { "epoch": 4.96, "learning_rate": 3.339256713687886e-06, "loss": 0.8357, "step": 59730 }, { "epoch": 4.97, "learning_rate": 3.3391458581603523e-06, "loss": 0.838, "step": 59740 }, { "epoch": 4.97, "learning_rate": 3.3390350026328186e-06, "loss": 0.826, "step": 59750 }, { "epoch": 4.97, "learning_rate": 3.338924147105285e-06, "loss": 0.8489, "step": 59760 }, { "epoch": 4.97, "learning_rate": 3.338813291577751e-06, "loss": 0.8095, "step": 59770 }, { "epoch": 4.97, "learning_rate": 3.3387024360502175e-06, "loss": 0.8634, "step": 59780 }, { "epoch": 4.97, "learning_rate": 3.3385915805226838e-06, "loss": 0.8027, "step": 59790 }, { "epoch": 4.97, "learning_rate": 3.33848072499515e-06, "loss": 0.7943, "step": 59800 }, { "epoch": 4.97, "learning_rate": 3.338369869467616e-06, "loss": 0.8602, "step": 59810 }, { "epoch": 4.97, "learning_rate": 3.3382590139400826e-06, "loss": 0.8096, "step": 59820 }, { "epoch": 4.97, "learning_rate": 3.3381481584125485e-06, "loss": 0.8683, "step": 59830 }, { "epoch": 4.97, "learning_rate": 3.3380373028850152e-06, "loss": 0.875, "step": 59840 }, { "epoch": 4.97, "learning_rate": 3.337926447357481e-06, "loss": 0.7741, "step": 59850 }, { "epoch": 4.98, "learning_rate": 3.3378155918299474e-06, "loss": 0.7743, "step": 59860 }, { "epoch": 4.98, "learning_rate": 3.3377047363024137e-06, "loss": 0.8286, "step": 59870 }, { "epoch": 4.98, "learning_rate": 3.33759388077488e-06, "loss": 0.8185, "step": 59880 }, { "epoch": 4.98, "learning_rate": 3.337483025247346e-06, "loss": 0.7838, "step": 59890 }, { "epoch": 4.98, "learning_rate": 3.3373721697198126e-06, "loss": 0.7525, "step": 59900 }, { "epoch": 4.98, "learning_rate": 3.337261314192279e-06, "loss": 0.8114, "step": 59910 }, { "epoch": 4.98, "learning_rate": 3.337150458664745e-06, "loss": 0.7703, "step": 59920 }, { "epoch": 4.98, "learning_rate": 3.3370396031372115e-06, "loss": 0.8071, "step": 59930 }, { "epoch": 4.98, "learning_rate": 3.3369287476096773e-06, "loss": 0.7708, "step": 59940 }, { "epoch": 4.98, "learning_rate": 3.336817892082144e-06, "loss": 0.7379, "step": 59950 }, { "epoch": 4.98, "learning_rate": 3.33670703655461e-06, "loss": 0.7955, "step": 59960 }, { "epoch": 4.98, "learning_rate": 3.3365961810270762e-06, "loss": 0.8322, "step": 59970 }, { "epoch": 4.99, "learning_rate": 3.3364853254995425e-06, "loss": 0.9039, "step": 59980 }, { "epoch": 4.99, "learning_rate": 3.336374469972009e-06, "loss": 0.7663, "step": 59990 }, { "epoch": 4.99, "learning_rate": 3.336263614444475e-06, "loss": 0.8139, "step": 60000 }, { "epoch": 4.99, "learning_rate": 3.3361527589169414e-06, "loss": 0.7987, "step": 60010 }, { "epoch": 4.99, "learning_rate": 3.3360419033894073e-06, "loss": 0.8357, "step": 60020 }, { "epoch": 4.99, "learning_rate": 3.335931047861874e-06, "loss": 0.8213, "step": 60030 }, { "epoch": 4.99, "learning_rate": 3.3358201923343403e-06, "loss": 0.8527, "step": 60040 }, { "epoch": 4.99, "learning_rate": 3.335709336806806e-06, "loss": 0.8365, "step": 60050 }, { "epoch": 4.99, "learning_rate": 3.335598481279273e-06, "loss": 0.8059, "step": 60060 }, { "epoch": 4.99, "learning_rate": 3.3354876257517388e-06, "loss": 0.7887, "step": 60070 }, { "epoch": 4.99, "learning_rate": 3.3353767702242055e-06, "loss": 0.8658, "step": 60080 }, { "epoch": 4.99, "learning_rate": 3.3352659146966713e-06, "loss": 0.7966, "step": 60090 }, { "epoch": 5.0, "learning_rate": 3.3351550591691376e-06, "loss": 0.911, "step": 60100 }, { "epoch": 5.0, "learning_rate": 3.335044203641604e-06, "loss": 0.788, "step": 60110 }, { "epoch": 5.0, "learning_rate": 3.3349333481140702e-06, "loss": 0.8267, "step": 60120 }, { "epoch": 5.0, "learning_rate": 3.334822492586536e-06, "loss": 0.8479, "step": 60130 }, { "epoch": 5.0, "learning_rate": 3.334711637059003e-06, "loss": 0.8431, "step": 60140 }, { "epoch": 5.0, "learning_rate": 3.334600781531469e-06, "loss": 0.797, "step": 60150 }, { "epoch": 5.0, "eval_loss": 1.0423674583435059, "eval_runtime": 346.1726, "eval_samples_per_second": 7.724, "eval_steps_per_second": 3.862, "eval_wer": 0.6512456856568396, "step": 60155 }, { "epoch": 5.0, "learning_rate": 3.334489926003935e-06, "loss": 0.8424, "step": 60160 }, { "epoch": 5.0, "learning_rate": 3.3343790704764017e-06, "loss": 0.8064, "step": 60170 }, { "epoch": 5.0, "learning_rate": 3.3342682149488676e-06, "loss": 0.9275, "step": 60180 }, { "epoch": 5.0, "learning_rate": 3.3341573594213343e-06, "loss": 0.8371, "step": 60190 }, { "epoch": 5.0, "learning_rate": 3.3340465038938e-06, "loss": 0.8288, "step": 60200 }, { "epoch": 5.0, "learning_rate": 3.3339356483662665e-06, "loss": 0.8635, "step": 60210 }, { "epoch": 5.01, "learning_rate": 3.3338247928387328e-06, "loss": 0.802, "step": 60220 }, { "epoch": 5.01, "learning_rate": 3.333713937311199e-06, "loss": 0.8386, "step": 60230 }, { "epoch": 5.01, "learning_rate": 3.333603081783665e-06, "loss": 0.8571, "step": 60240 }, { "epoch": 5.01, "learning_rate": 3.3334922262561316e-06, "loss": 0.7916, "step": 60250 }, { "epoch": 5.01, "learning_rate": 3.3333813707285975e-06, "loss": 0.8657, "step": 60260 }, { "epoch": 5.01, "learning_rate": 3.3332705152010642e-06, "loss": 0.8684, "step": 60270 }, { "epoch": 5.01, "learning_rate": 3.3331596596735305e-06, "loss": 0.816, "step": 60280 }, { "epoch": 5.01, "learning_rate": 3.3330488041459964e-06, "loss": 0.8129, "step": 60290 }, { "epoch": 5.01, "learning_rate": 3.332937948618463e-06, "loss": 0.7585, "step": 60300 }, { "epoch": 5.01, "learning_rate": 3.332827093090929e-06, "loss": 0.8424, "step": 60310 }, { "epoch": 5.01, "learning_rate": 3.3327162375633953e-06, "loss": 0.8122, "step": 60320 }, { "epoch": 5.01, "learning_rate": 3.3326053820358616e-06, "loss": 0.7725, "step": 60330 }, { "epoch": 5.02, "learning_rate": 3.332494526508328e-06, "loss": 0.7743, "step": 60340 }, { "epoch": 5.02, "learning_rate": 3.332383670980794e-06, "loss": 0.8213, "step": 60350 }, { "epoch": 5.02, "learning_rate": 3.3322728154532605e-06, "loss": 0.8975, "step": 60360 }, { "epoch": 5.02, "learning_rate": 3.3321619599257263e-06, "loss": 0.7692, "step": 60370 }, { "epoch": 5.02, "learning_rate": 3.332051104398193e-06, "loss": 0.7576, "step": 60380 }, { "epoch": 5.02, "learning_rate": 3.331940248870659e-06, "loss": 0.7884, "step": 60390 }, { "epoch": 5.02, "learning_rate": 3.3318293933431252e-06, "loss": 0.7958, "step": 60400 }, { "epoch": 5.02, "learning_rate": 3.331718537815592e-06, "loss": 0.8508, "step": 60410 }, { "epoch": 5.02, "learning_rate": 3.331607682288058e-06, "loss": 0.8873, "step": 60420 }, { "epoch": 5.02, "learning_rate": 3.3314968267605245e-06, "loss": 0.758, "step": 60430 }, { "epoch": 5.02, "learning_rate": 3.3313859712329904e-06, "loss": 0.7767, "step": 60440 }, { "epoch": 5.02, "learning_rate": 3.3312751157054567e-06, "loss": 0.9015, "step": 60450 }, { "epoch": 5.03, "learning_rate": 3.331164260177923e-06, "loss": 0.8419, "step": 60460 }, { "epoch": 5.03, "learning_rate": 3.3310534046503893e-06, "loss": 0.8633, "step": 60470 }, { "epoch": 5.03, "learning_rate": 3.330942549122855e-06, "loss": 0.8187, "step": 60480 }, { "epoch": 5.03, "learning_rate": 3.330831693595322e-06, "loss": 0.8081, "step": 60490 }, { "epoch": 5.03, "learning_rate": 3.3307208380677878e-06, "loss": 0.8606, "step": 60500 }, { "epoch": 5.03, "learning_rate": 3.3306099825402545e-06, "loss": 0.8827, "step": 60510 }, { "epoch": 5.03, "learning_rate": 3.3304991270127208e-06, "loss": 0.7829, "step": 60520 }, { "epoch": 5.03, "learning_rate": 3.3303882714851866e-06, "loss": 0.8296, "step": 60530 }, { "epoch": 5.03, "learning_rate": 3.3302774159576534e-06, "loss": 0.8307, "step": 60540 }, { "epoch": 5.03, "learning_rate": 3.3301665604301192e-06, "loss": 0.8243, "step": 60550 }, { "epoch": 5.03, "learning_rate": 3.3300557049025855e-06, "loss": 0.821, "step": 60560 }, { "epoch": 5.03, "learning_rate": 3.329944849375052e-06, "loss": 0.8595, "step": 60570 }, { "epoch": 5.04, "learning_rate": 3.329833993847518e-06, "loss": 0.7725, "step": 60580 }, { "epoch": 5.04, "learning_rate": 3.329723138319984e-06, "loss": 0.7229, "step": 60590 }, { "epoch": 5.04, "learning_rate": 3.3296122827924507e-06, "loss": 0.8434, "step": 60600 }, { "epoch": 5.04, "learning_rate": 3.3295014272649166e-06, "loss": 0.8172, "step": 60610 }, { "epoch": 5.04, "learning_rate": 3.3293905717373833e-06, "loss": 0.8178, "step": 60620 }, { "epoch": 5.04, "learning_rate": 3.329279716209849e-06, "loss": 0.8484, "step": 60630 }, { "epoch": 5.04, "learning_rate": 3.3291688606823155e-06, "loss": 0.8086, "step": 60640 }, { "epoch": 5.04, "learning_rate": 3.329058005154782e-06, "loss": 0.8151, "step": 60650 }, { "epoch": 5.04, "learning_rate": 3.328947149627248e-06, "loss": 0.8917, "step": 60660 }, { "epoch": 5.04, "learning_rate": 3.3288362940997144e-06, "loss": 0.8466, "step": 60670 }, { "epoch": 5.04, "learning_rate": 3.3287254385721807e-06, "loss": 0.7157, "step": 60680 }, { "epoch": 5.04, "learning_rate": 3.328614583044647e-06, "loss": 0.8089, "step": 60690 }, { "epoch": 5.05, "learning_rate": 3.3285037275171132e-06, "loss": 0.7859, "step": 60700 }, { "epoch": 5.05, "learning_rate": 3.3283928719895795e-06, "loss": 0.8858, "step": 60710 }, { "epoch": 5.05, "learning_rate": 3.3282820164620454e-06, "loss": 0.8405, "step": 60720 }, { "epoch": 5.05, "learning_rate": 3.328171160934512e-06, "loss": 0.8104, "step": 60730 }, { "epoch": 5.05, "learning_rate": 3.328060305406978e-06, "loss": 0.857, "step": 60740 }, { "epoch": 5.05, "learning_rate": 3.3279494498794443e-06, "loss": 0.7938, "step": 60750 }, { "epoch": 5.05, "learning_rate": 3.3278385943519106e-06, "loss": 0.8204, "step": 60760 }, { "epoch": 5.05, "learning_rate": 3.327727738824377e-06, "loss": 0.7867, "step": 60770 }, { "epoch": 5.05, "learning_rate": 3.3276168832968436e-06, "loss": 0.822, "step": 60780 }, { "epoch": 5.05, "learning_rate": 3.3275060277693095e-06, "loss": 0.8242, "step": 60790 }, { "epoch": 5.05, "learning_rate": 3.3273951722417758e-06, "loss": 0.8423, "step": 60800 }, { "epoch": 5.05, "learning_rate": 3.327284316714242e-06, "loss": 0.7955, "step": 60810 }, { "epoch": 5.06, "learning_rate": 3.3271734611867084e-06, "loss": 0.8237, "step": 60820 }, { "epoch": 5.06, "learning_rate": 3.3270626056591742e-06, "loss": 0.8338, "step": 60830 }, { "epoch": 5.06, "learning_rate": 3.326951750131641e-06, "loss": 0.8982, "step": 60840 }, { "epoch": 5.06, "learning_rate": 3.326840894604107e-06, "loss": 0.8099, "step": 60850 }, { "epoch": 5.06, "learning_rate": 3.3267300390765735e-06, "loss": 0.8268, "step": 60860 }, { "epoch": 5.06, "learning_rate": 3.3266191835490394e-06, "loss": 0.8034, "step": 60870 }, { "epoch": 5.06, "learning_rate": 3.3265083280215057e-06, "loss": 0.7997, "step": 60880 }, { "epoch": 5.06, "learning_rate": 3.3263974724939724e-06, "loss": 0.8252, "step": 60890 }, { "epoch": 5.06, "learning_rate": 3.3262866169664383e-06, "loss": 0.8832, "step": 60900 }, { "epoch": 5.06, "learning_rate": 3.3261757614389046e-06, "loss": 0.8901, "step": 60910 }, { "epoch": 5.06, "learning_rate": 3.326064905911371e-06, "loss": 0.851, "step": 60920 }, { "epoch": 5.06, "learning_rate": 3.325954050383837e-06, "loss": 0.8156, "step": 60930 }, { "epoch": 5.07, "learning_rate": 3.325843194856303e-06, "loss": 0.8095, "step": 60940 }, { "epoch": 5.07, "learning_rate": 3.3257323393287698e-06, "loss": 0.808, "step": 60950 }, { "epoch": 5.07, "learning_rate": 3.3256214838012357e-06, "loss": 0.8874, "step": 60960 }, { "epoch": 5.07, "learning_rate": 3.3255106282737024e-06, "loss": 0.8908, "step": 60970 }, { "epoch": 5.07, "learning_rate": 3.3253997727461682e-06, "loss": 0.8493, "step": 60980 }, { "epoch": 5.07, "learning_rate": 3.3252889172186345e-06, "loss": 0.7982, "step": 60990 }, { "epoch": 5.07, "learning_rate": 3.325178061691101e-06, "loss": 0.8036, "step": 61000 }, { "epoch": 5.07, "learning_rate": 3.325067206163567e-06, "loss": 0.7953, "step": 61010 }, { "epoch": 5.07, "learning_rate": 3.3249563506360334e-06, "loss": 0.8142, "step": 61020 }, { "epoch": 5.07, "learning_rate": 3.3248454951084997e-06, "loss": 0.8105, "step": 61030 }, { "epoch": 5.07, "learning_rate": 3.324734639580966e-06, "loss": 0.8548, "step": 61040 }, { "epoch": 5.07, "learning_rate": 3.3246237840534323e-06, "loss": 0.7987, "step": 61050 }, { "epoch": 5.08, "learning_rate": 3.3245129285258986e-06, "loss": 0.9058, "step": 61060 }, { "epoch": 5.08, "learning_rate": 3.3244020729983645e-06, "loss": 0.8274, "step": 61070 }, { "epoch": 5.08, "learning_rate": 3.324291217470831e-06, "loss": 0.8672, "step": 61080 }, { "epoch": 5.08, "learning_rate": 3.324180361943297e-06, "loss": 0.8035, "step": 61090 }, { "epoch": 5.08, "learning_rate": 3.3240695064157634e-06, "loss": 0.8118, "step": 61100 }, { "epoch": 5.08, "learning_rate": 3.3239586508882297e-06, "loss": 0.8575, "step": 61110 }, { "epoch": 5.08, "learning_rate": 3.323847795360696e-06, "loss": 0.7841, "step": 61120 }, { "epoch": 5.08, "learning_rate": 3.3237369398331627e-06, "loss": 0.8007, "step": 61130 }, { "epoch": 5.08, "learning_rate": 3.3236260843056285e-06, "loss": 0.8531, "step": 61140 }, { "epoch": 5.08, "learning_rate": 3.323515228778095e-06, "loss": 0.7942, "step": 61150 }, { "epoch": 5.08, "learning_rate": 3.323404373250561e-06, "loss": 0.7996, "step": 61160 }, { "epoch": 5.08, "learning_rate": 3.3232935177230274e-06, "loss": 0.8318, "step": 61170 }, { "epoch": 5.09, "learning_rate": 3.3231826621954933e-06, "loss": 0.8587, "step": 61180 }, { "epoch": 5.09, "learning_rate": 3.32307180666796e-06, "loss": 0.8433, "step": 61190 }, { "epoch": 5.09, "learning_rate": 3.322960951140426e-06, "loss": 0.7801, "step": 61200 }, { "epoch": 5.09, "learning_rate": 3.3228500956128926e-06, "loss": 0.811, "step": 61210 }, { "epoch": 5.09, "learning_rate": 3.3227392400853585e-06, "loss": 0.8224, "step": 61220 }, { "epoch": 5.09, "learning_rate": 3.3226283845578248e-06, "loss": 0.8421, "step": 61230 }, { "epoch": 5.09, "learning_rate": 3.322517529030291e-06, "loss": 0.8509, "step": 61240 }, { "epoch": 5.09, "learning_rate": 3.3224066735027574e-06, "loss": 0.8417, "step": 61250 }, { "epoch": 5.09, "learning_rate": 3.3222958179752237e-06, "loss": 0.8684, "step": 61260 }, { "epoch": 5.09, "learning_rate": 3.32218496244769e-06, "loss": 0.929, "step": 61270 }, { "epoch": 5.09, "learning_rate": 3.3220741069201563e-06, "loss": 0.8689, "step": 61280 }, { "epoch": 5.09, "learning_rate": 3.3219632513926226e-06, "loss": 0.8592, "step": 61290 }, { "epoch": 5.1, "learning_rate": 3.321852395865089e-06, "loss": 0.8936, "step": 61300 }, { "epoch": 5.1, "learning_rate": 3.3217415403375547e-06, "loss": 0.8381, "step": 61310 }, { "epoch": 5.1, "learning_rate": 3.3216306848100214e-06, "loss": 0.8417, "step": 61320 }, { "epoch": 5.1, "learning_rate": 3.3215198292824873e-06, "loss": 0.7951, "step": 61330 }, { "epoch": 5.1, "learning_rate": 3.3214089737549536e-06, "loss": 0.8387, "step": 61340 }, { "epoch": 5.1, "learning_rate": 3.32129811822742e-06, "loss": 0.8296, "step": 61350 }, { "epoch": 5.1, "learning_rate": 3.321187262699886e-06, "loss": 0.8609, "step": 61360 }, { "epoch": 5.1, "learning_rate": 3.321076407172352e-06, "loss": 0.8322, "step": 61370 }, { "epoch": 5.1, "learning_rate": 3.3209655516448188e-06, "loss": 0.7962, "step": 61380 }, { "epoch": 5.1, "learning_rate": 3.320854696117285e-06, "loss": 0.8276, "step": 61390 }, { "epoch": 5.1, "learning_rate": 3.3207438405897514e-06, "loss": 0.826, "step": 61400 }, { "epoch": 5.1, "learning_rate": 3.3206329850622177e-06, "loss": 0.8526, "step": 61410 }, { "epoch": 5.11, "learning_rate": 3.3205221295346835e-06, "loss": 0.7671, "step": 61420 }, { "epoch": 5.11, "learning_rate": 3.3204112740071503e-06, "loss": 0.8431, "step": 61430 }, { "epoch": 5.11, "learning_rate": 3.320300418479616e-06, "loss": 0.8492, "step": 61440 }, { "epoch": 5.11, "learning_rate": 3.3201895629520824e-06, "loss": 0.7977, "step": 61450 }, { "epoch": 5.11, "learning_rate": 3.3200787074245487e-06, "loss": 0.813, "step": 61460 }, { "epoch": 5.11, "learning_rate": 3.319967851897015e-06, "loss": 0.7893, "step": 61470 }, { "epoch": 5.11, "learning_rate": 3.3198569963694813e-06, "loss": 0.8322, "step": 61480 }, { "epoch": 5.11, "learning_rate": 3.3197461408419476e-06, "loss": 0.822, "step": 61490 }, { "epoch": 5.11, "learning_rate": 3.319635285314414e-06, "loss": 0.8704, "step": 61500 }, { "epoch": 5.11, "learning_rate": 3.31952442978688e-06, "loss": 0.8501, "step": 61510 }, { "epoch": 5.11, "learning_rate": 3.3194135742593465e-06, "loss": 0.8464, "step": 61520 }, { "epoch": 5.11, "learning_rate": 3.3193027187318124e-06, "loss": 0.8216, "step": 61530 }, { "epoch": 5.12, "learning_rate": 3.319191863204279e-06, "loss": 0.7725, "step": 61540 }, { "epoch": 5.12, "learning_rate": 3.319081007676745e-06, "loss": 0.7758, "step": 61550 }, { "epoch": 5.12, "learning_rate": 3.3189701521492117e-06, "loss": 0.8646, "step": 61560 }, { "epoch": 5.12, "learning_rate": 3.3188592966216776e-06, "loss": 0.824, "step": 61570 }, { "epoch": 5.12, "learning_rate": 3.318748441094144e-06, "loss": 0.8131, "step": 61580 }, { "epoch": 5.12, "learning_rate": 3.31863758556661e-06, "loss": 0.7478, "step": 61590 }, { "epoch": 5.12, "learning_rate": 3.3185267300390764e-06, "loss": 0.8185, "step": 61600 }, { "epoch": 5.12, "learning_rate": 3.3184158745115423e-06, "loss": 0.8762, "step": 61610 }, { "epoch": 5.12, "learning_rate": 3.318305018984009e-06, "loss": 0.7997, "step": 61620 }, { "epoch": 5.12, "learning_rate": 3.3181941634564753e-06, "loss": 0.8002, "step": 61630 }, { "epoch": 5.12, "learning_rate": 3.3180833079289416e-06, "loss": 0.8532, "step": 61640 }, { "epoch": 5.12, "learning_rate": 3.317972452401408e-06, "loss": 0.8506, "step": 61650 }, { "epoch": 5.13, "learning_rate": 3.3178615968738738e-06, "loss": 0.8761, "step": 61660 }, { "epoch": 5.13, "learning_rate": 3.3177507413463405e-06, "loss": 0.826, "step": 61670 }, { "epoch": 5.13, "learning_rate": 3.3176398858188064e-06, "loss": 0.8376, "step": 61680 }, { "epoch": 5.13, "learning_rate": 3.3175290302912727e-06, "loss": 0.8345, "step": 61690 }, { "epoch": 5.13, "learning_rate": 3.317418174763739e-06, "loss": 0.8598, "step": 61700 }, { "epoch": 5.13, "learning_rate": 3.3173073192362053e-06, "loss": 0.8181, "step": 61710 }, { "epoch": 5.13, "learning_rate": 3.317196463708671e-06, "loss": 0.8686, "step": 61720 }, { "epoch": 5.13, "learning_rate": 3.317085608181138e-06, "loss": 0.813, "step": 61730 }, { "epoch": 5.13, "learning_rate": 3.3169747526536037e-06, "loss": 0.8236, "step": 61740 }, { "epoch": 5.13, "learning_rate": 3.3168638971260704e-06, "loss": 0.8171, "step": 61750 }, { "epoch": 5.13, "learning_rate": 3.3167530415985367e-06, "loss": 0.8758, "step": 61760 }, { "epoch": 5.13, "learning_rate": 3.3166421860710026e-06, "loss": 0.7919, "step": 61770 }, { "epoch": 5.14, "learning_rate": 3.3165313305434693e-06, "loss": 0.7916, "step": 61780 }, { "epoch": 5.14, "learning_rate": 3.316420475015935e-06, "loss": 0.765, "step": 61790 }, { "epoch": 5.14, "learning_rate": 3.316309619488402e-06, "loss": 0.8358, "step": 61800 }, { "epoch": 5.14, "learning_rate": 3.316198763960868e-06, "loss": 0.8954, "step": 61810 }, { "epoch": 5.14, "learning_rate": 3.316087908433334e-06, "loss": 0.7832, "step": 61820 }, { "epoch": 5.14, "learning_rate": 3.3159770529058004e-06, "loss": 0.8164, "step": 61830 }, { "epoch": 5.14, "learning_rate": 3.3158661973782667e-06, "loss": 0.8091, "step": 61840 }, { "epoch": 5.14, "learning_rate": 3.3157553418507325e-06, "loss": 0.9011, "step": 61850 }, { "epoch": 5.14, "learning_rate": 3.3156444863231993e-06, "loss": 0.8205, "step": 61860 }, { "epoch": 5.14, "learning_rate": 3.3155336307956656e-06, "loss": 0.8362, "step": 61870 }, { "epoch": 5.14, "learning_rate": 3.3154227752681314e-06, "loss": 0.9148, "step": 61880 }, { "epoch": 5.14, "learning_rate": 3.315311919740598e-06, "loss": 0.8053, "step": 61890 }, { "epoch": 5.15, "learning_rate": 3.315201064213064e-06, "loss": 0.8766, "step": 61900 }, { "epoch": 5.15, "learning_rate": 3.3150902086855307e-06, "loss": 0.8483, "step": 61910 }, { "epoch": 5.15, "learning_rate": 3.3149793531579966e-06, "loss": 0.877, "step": 61920 }, { "epoch": 5.15, "learning_rate": 3.314868497630463e-06, "loss": 0.8035, "step": 61930 }, { "epoch": 5.15, "learning_rate": 3.314757642102929e-06, "loss": 0.8501, "step": 61940 }, { "epoch": 5.15, "learning_rate": 3.3146467865753955e-06, "loss": 0.8197, "step": 61950 }, { "epoch": 5.15, "learning_rate": 3.3145359310478614e-06, "loss": 0.8268, "step": 61960 }, { "epoch": 5.15, "learning_rate": 3.314425075520328e-06, "loss": 0.8194, "step": 61970 }, { "epoch": 5.15, "learning_rate": 3.314314219992794e-06, "loss": 0.7688, "step": 61980 }, { "epoch": 5.15, "learning_rate": 3.3142033644652607e-06, "loss": 0.8331, "step": 61990 }, { "epoch": 5.15, "learning_rate": 3.314092508937727e-06, "loss": 0.83, "step": 62000 }, { "epoch": 5.15, "learning_rate": 3.313981653410193e-06, "loss": 0.8913, "step": 62010 }, { "epoch": 5.16, "learning_rate": 3.3138707978826596e-06, "loss": 0.8263, "step": 62020 }, { "epoch": 5.16, "learning_rate": 3.3137599423551254e-06, "loss": 0.8645, "step": 62030 }, { "epoch": 5.16, "learning_rate": 3.3136490868275917e-06, "loss": 0.8283, "step": 62040 }, { "epoch": 5.16, "learning_rate": 3.313538231300058e-06, "loss": 0.7757, "step": 62050 }, { "epoch": 5.16, "learning_rate": 3.3134273757725243e-06, "loss": 0.8396, "step": 62060 }, { "epoch": 5.16, "learning_rate": 3.3133165202449906e-06, "loss": 0.7976, "step": 62070 }, { "epoch": 5.16, "learning_rate": 3.313205664717457e-06, "loss": 0.8578, "step": 62080 }, { "epoch": 5.16, "learning_rate": 3.313094809189923e-06, "loss": 0.7961, "step": 62090 }, { "epoch": 5.16, "learning_rate": 3.3129839536623895e-06, "loss": 0.8063, "step": 62100 }, { "epoch": 5.16, "learning_rate": 3.3128730981348554e-06, "loss": 0.8551, "step": 62110 }, { "epoch": 5.16, "learning_rate": 3.3127622426073217e-06, "loss": 0.845, "step": 62120 }, { "epoch": 5.16, "learning_rate": 3.3126513870797884e-06, "loss": 0.8633, "step": 62130 }, { "epoch": 5.16, "learning_rate": 3.3125405315522543e-06, "loss": 0.8028, "step": 62140 }, { "epoch": 5.17, "learning_rate": 3.312429676024721e-06, "loss": 0.7722, "step": 62150 }, { "epoch": 5.17, "learning_rate": 3.312318820497187e-06, "loss": 0.8565, "step": 62160 }, { "epoch": 5.17, "learning_rate": 3.312207964969653e-06, "loss": 0.8147, "step": 62170 }, { "epoch": 5.17, "learning_rate": 3.3121081949948727e-06, "loss": 0.7851, "step": 62180 }, { "epoch": 5.17, "learning_rate": 3.311997339467339e-06, "loss": 0.8378, "step": 62190 }, { "epoch": 5.17, "learning_rate": 3.3118864839398053e-06, "loss": 0.8137, "step": 62200 }, { "epoch": 5.17, "learning_rate": 3.3117756284122716e-06, "loss": 0.801, "step": 62210 }, { "epoch": 5.17, "learning_rate": 3.311664772884738e-06, "loss": 0.8513, "step": 62220 }, { "epoch": 5.17, "learning_rate": 3.311553917357204e-06, "loss": 0.8344, "step": 62230 }, { "epoch": 5.17, "learning_rate": 3.3114430618296705e-06, "loss": 0.8185, "step": 62240 }, { "epoch": 5.17, "learning_rate": 3.3113322063021368e-06, "loss": 0.816, "step": 62250 }, { "epoch": 5.17, "learning_rate": 3.3112213507746026e-06, "loss": 0.8325, "step": 62260 }, { "epoch": 5.18, "learning_rate": 3.3111104952470693e-06, "loss": 0.8117, "step": 62270 }, { "epoch": 5.18, "learning_rate": 3.3109996397195352e-06, "loss": 0.8702, "step": 62280 }, { "epoch": 5.18, "learning_rate": 3.3108887841920015e-06, "loss": 0.7874, "step": 62290 }, { "epoch": 5.18, "learning_rate": 3.310777928664468e-06, "loss": 0.7881, "step": 62300 }, { "epoch": 5.18, "learning_rate": 3.310667073136934e-06, "loss": 0.9182, "step": 62310 }, { "epoch": 5.18, "learning_rate": 3.3105562176094e-06, "loss": 0.7838, "step": 62320 }, { "epoch": 5.18, "learning_rate": 3.3104453620818667e-06, "loss": 0.8459, "step": 62330 }, { "epoch": 5.18, "learning_rate": 3.310334506554333e-06, "loss": 0.8829, "step": 62340 }, { "epoch": 5.18, "learning_rate": 3.3102236510267993e-06, "loss": 0.8332, "step": 62350 }, { "epoch": 5.18, "learning_rate": 3.3101127954992656e-06, "loss": 0.8499, "step": 62360 }, { "epoch": 5.18, "learning_rate": 3.3100019399717315e-06, "loss": 0.8957, "step": 62370 }, { "epoch": 5.18, "learning_rate": 3.309891084444198e-06, "loss": 0.839, "step": 62380 }, { "epoch": 5.19, "learning_rate": 3.309780228916664e-06, "loss": 0.8779, "step": 62390 }, { "epoch": 5.19, "learning_rate": 3.3096693733891303e-06, "loss": 0.8139, "step": 62400 }, { "epoch": 5.19, "learning_rate": 3.3095585178615966e-06, "loss": 0.8306, "step": 62410 }, { "epoch": 5.19, "learning_rate": 3.309447662334063e-06, "loss": 0.8364, "step": 62420 }, { "epoch": 5.19, "learning_rate": 3.3093368068065292e-06, "loss": 0.8522, "step": 62430 }, { "epoch": 5.19, "learning_rate": 3.3092259512789955e-06, "loss": 0.7886, "step": 62440 }, { "epoch": 5.19, "learning_rate": 3.309115095751462e-06, "loss": 0.7556, "step": 62450 }, { "epoch": 5.19, "learning_rate": 3.309004240223928e-06, "loss": 0.8479, "step": 62460 }, { "epoch": 5.19, "learning_rate": 3.3088933846963944e-06, "loss": 0.9401, "step": 62470 }, { "epoch": 5.19, "learning_rate": 3.3087825291688603e-06, "loss": 0.8112, "step": 62480 }, { "epoch": 5.19, "learning_rate": 3.308671673641327e-06, "loss": 0.7764, "step": 62490 }, { "epoch": 5.19, "learning_rate": 3.308560818113793e-06, "loss": 0.7958, "step": 62500 }, { "epoch": 5.2, "learning_rate": 3.3084499625862596e-06, "loss": 0.8612, "step": 62510 }, { "epoch": 5.2, "learning_rate": 3.3083391070587255e-06, "loss": 0.8214, "step": 62520 }, { "epoch": 5.2, "learning_rate": 3.3082282515311918e-06, "loss": 0.8234, "step": 62530 }, { "epoch": 5.2, "learning_rate": 3.308117396003658e-06, "loss": 0.7729, "step": 62540 }, { "epoch": 5.2, "learning_rate": 3.3080065404761243e-06, "loss": 0.8678, "step": 62550 }, { "epoch": 5.2, "learning_rate": 3.3078956849485902e-06, "loss": 0.931, "step": 62560 }, { "epoch": 5.2, "learning_rate": 3.307784829421057e-06, "loss": 0.8136, "step": 62570 }, { "epoch": 5.2, "learning_rate": 3.3076739738935232e-06, "loss": 0.9196, "step": 62580 }, { "epoch": 5.2, "learning_rate": 3.3075631183659895e-06, "loss": 0.858, "step": 62590 }, { "epoch": 5.2, "learning_rate": 3.307452262838456e-06, "loss": 0.8355, "step": 62600 }, { "epoch": 5.2, "learning_rate": 3.3073414073109217e-06, "loss": 0.8737, "step": 62610 }, { "epoch": 5.2, "learning_rate": 3.3072305517833884e-06, "loss": 0.8544, "step": 62620 }, { "epoch": 5.21, "learning_rate": 3.3071196962558543e-06, "loss": 0.8356, "step": 62630 }, { "epoch": 5.21, "learning_rate": 3.3070088407283206e-06, "loss": 0.8122, "step": 62640 }, { "epoch": 5.21, "learning_rate": 3.306897985200787e-06, "loss": 0.8076, "step": 62650 }, { "epoch": 5.21, "learning_rate": 3.306787129673253e-06, "loss": 0.8383, "step": 62660 }, { "epoch": 5.21, "learning_rate": 3.3066762741457195e-06, "loss": 0.7993, "step": 62670 }, { "epoch": 5.21, "learning_rate": 3.3065654186181858e-06, "loss": 0.8114, "step": 62680 }, { "epoch": 5.21, "learning_rate": 3.3064545630906516e-06, "loss": 0.771, "step": 62690 }, { "epoch": 5.21, "learning_rate": 3.3063437075631184e-06, "loss": 0.7918, "step": 62700 }, { "epoch": 5.21, "learning_rate": 3.3062328520355847e-06, "loss": 0.8277, "step": 62710 }, { "epoch": 5.21, "learning_rate": 3.3061219965080505e-06, "loss": 0.8801, "step": 62720 }, { "epoch": 5.21, "learning_rate": 3.3060111409805172e-06, "loss": 0.835, "step": 62730 }, { "epoch": 5.21, "learning_rate": 3.305900285452983e-06, "loss": 0.7896, "step": 62740 }, { "epoch": 5.22, "learning_rate": 3.30578942992545e-06, "loss": 0.8031, "step": 62750 }, { "epoch": 5.22, "learning_rate": 3.3056785743979157e-06, "loss": 0.8542, "step": 62760 }, { "epoch": 5.22, "learning_rate": 3.305567718870382e-06, "loss": 0.8497, "step": 62770 }, { "epoch": 5.22, "learning_rate": 3.3054568633428483e-06, "loss": 0.7903, "step": 62780 }, { "epoch": 5.22, "learning_rate": 3.3053460078153146e-06, "loss": 0.8416, "step": 62790 }, { "epoch": 5.22, "learning_rate": 3.3052351522877805e-06, "loss": 0.8284, "step": 62800 }, { "epoch": 5.22, "learning_rate": 3.305124296760247e-06, "loss": 0.8558, "step": 62810 }, { "epoch": 5.22, "learning_rate": 3.3050134412327135e-06, "loss": 0.8773, "step": 62820 }, { "epoch": 5.22, "learning_rate": 3.3049025857051793e-06, "loss": 0.7994, "step": 62830 }, { "epoch": 5.22, "learning_rate": 3.304791730177646e-06, "loss": 0.8433, "step": 62840 }, { "epoch": 5.22, "learning_rate": 3.304680874650112e-06, "loss": 0.8886, "step": 62850 }, { "epoch": 5.22, "learning_rate": 3.3045700191225787e-06, "loss": 0.7918, "step": 62860 }, { "epoch": 5.23, "learning_rate": 3.3044591635950445e-06, "loss": 0.8188, "step": 62870 }, { "epoch": 5.23, "learning_rate": 3.304348308067511e-06, "loss": 0.8834, "step": 62880 }, { "epoch": 5.23, "learning_rate": 3.304237452539977e-06, "loss": 0.8072, "step": 62890 }, { "epoch": 5.23, "learning_rate": 3.3041265970124434e-06, "loss": 0.8278, "step": 62900 }, { "epoch": 5.23, "learning_rate": 3.3040157414849093e-06, "loss": 0.8822, "step": 62910 }, { "epoch": 5.23, "learning_rate": 3.303904885957376e-06, "loss": 0.8418, "step": 62920 }, { "epoch": 5.23, "learning_rate": 3.303794030429842e-06, "loss": 0.8339, "step": 62930 }, { "epoch": 5.23, "learning_rate": 3.3036831749023086e-06, "loss": 0.7569, "step": 62940 }, { "epoch": 5.23, "learning_rate": 3.303572319374775e-06, "loss": 0.7864, "step": 62950 }, { "epoch": 5.23, "learning_rate": 3.3034614638472408e-06, "loss": 0.8563, "step": 62960 }, { "epoch": 5.23, "learning_rate": 3.3033506083197075e-06, "loss": 0.8767, "step": 62970 }, { "epoch": 5.23, "learning_rate": 3.3032397527921734e-06, "loss": 0.8617, "step": 62980 }, { "epoch": 5.24, "learning_rate": 3.3031288972646396e-06, "loss": 0.7879, "step": 62990 }, { "epoch": 5.24, "learning_rate": 3.303018041737106e-06, "loss": 0.8423, "step": 63000 }, { "epoch": 5.24, "learning_rate": 3.3029071862095722e-06, "loss": 0.8277, "step": 63010 }, { "epoch": 5.24, "learning_rate": 3.3027963306820385e-06, "loss": 0.7161, "step": 63020 }, { "epoch": 5.24, "learning_rate": 3.302685475154505e-06, "loss": 0.745, "step": 63030 }, { "epoch": 5.24, "learning_rate": 3.3025746196269707e-06, "loss": 0.853, "step": 63040 }, { "epoch": 5.24, "learning_rate": 3.3024637640994374e-06, "loss": 0.8413, "step": 63050 }, { "epoch": 5.24, "learning_rate": 3.3023529085719033e-06, "loss": 0.8564, "step": 63060 }, { "epoch": 5.24, "learning_rate": 3.3022420530443696e-06, "loss": 0.8953, "step": 63070 }, { "epoch": 5.24, "learning_rate": 3.3021311975168363e-06, "loss": 0.8067, "step": 63080 }, { "epoch": 5.24, "learning_rate": 3.302020341989302e-06, "loss": 0.8259, "step": 63090 }, { "epoch": 5.24, "learning_rate": 3.301909486461769e-06, "loss": 0.9218, "step": 63100 }, { "epoch": 5.25, "learning_rate": 3.3017986309342348e-06, "loss": 0.7714, "step": 63110 }, { "epoch": 5.25, "learning_rate": 3.301687775406701e-06, "loss": 0.8442, "step": 63120 }, { "epoch": 5.25, "learning_rate": 3.3015769198791674e-06, "loss": 0.8184, "step": 63130 }, { "epoch": 5.25, "learning_rate": 3.3014660643516337e-06, "loss": 0.8639, "step": 63140 }, { "epoch": 5.25, "learning_rate": 3.3013552088240995e-06, "loss": 0.9453, "step": 63150 }, { "epoch": 5.25, "learning_rate": 3.3012443532965662e-06, "loss": 0.8758, "step": 63160 }, { "epoch": 5.25, "learning_rate": 3.301133497769032e-06, "loss": 0.7859, "step": 63170 }, { "epoch": 5.25, "learning_rate": 3.3010226422414984e-06, "loss": 0.7815, "step": 63180 }, { "epoch": 5.25, "learning_rate": 3.300911786713965e-06, "loss": 0.8261, "step": 63190 }, { "epoch": 5.25, "learning_rate": 3.300800931186431e-06, "loss": 0.8477, "step": 63200 }, { "epoch": 5.25, "learning_rate": 3.3006900756588977e-06, "loss": 0.8793, "step": 63210 }, { "epoch": 5.25, "learning_rate": 3.3005792201313636e-06, "loss": 0.7812, "step": 63220 }, { "epoch": 5.26, "learning_rate": 3.30046836460383e-06, "loss": 0.8065, "step": 63230 }, { "epoch": 5.26, "learning_rate": 3.300357509076296e-06, "loss": 0.865, "step": 63240 }, { "epoch": 5.26, "learning_rate": 3.3002466535487625e-06, "loss": 0.8139, "step": 63250 }, { "epoch": 5.26, "learning_rate": 3.3001357980212284e-06, "loss": 0.8186, "step": 63260 }, { "epoch": 5.26, "learning_rate": 3.300024942493695e-06, "loss": 0.8072, "step": 63270 }, { "epoch": 5.26, "learning_rate": 3.299914086966161e-06, "loss": 0.8097, "step": 63280 }, { "epoch": 5.26, "learning_rate": 3.2998032314386277e-06, "loss": 0.839, "step": 63290 }, { "epoch": 5.26, "learning_rate": 3.2996923759110935e-06, "loss": 0.9073, "step": 63300 }, { "epoch": 5.26, "learning_rate": 3.29958152038356e-06, "loss": 0.8686, "step": 63310 }, { "epoch": 5.26, "learning_rate": 3.2994706648560265e-06, "loss": 0.7886, "step": 63320 }, { "epoch": 5.26, "learning_rate": 3.2993598093284924e-06, "loss": 0.7686, "step": 63330 }, { "epoch": 5.26, "learning_rate": 3.2992489538009587e-06, "loss": 0.7867, "step": 63340 }, { "epoch": 5.27, "learning_rate": 3.299138098273425e-06, "loss": 0.7826, "step": 63350 }, { "epoch": 5.27, "learning_rate": 3.2990272427458913e-06, "loss": 0.847, "step": 63360 }, { "epoch": 5.27, "learning_rate": 3.2989163872183576e-06, "loss": 0.8807, "step": 63370 }, { "epoch": 5.27, "learning_rate": 3.298805531690824e-06, "loss": 0.8073, "step": 63380 }, { "epoch": 5.27, "learning_rate": 3.2986946761632898e-06, "loss": 0.7873, "step": 63390 }, { "epoch": 5.27, "learning_rate": 3.2985838206357565e-06, "loss": 0.802, "step": 63400 }, { "epoch": 5.27, "learning_rate": 3.2984729651082224e-06, "loss": 0.8786, "step": 63410 }, { "epoch": 5.27, "learning_rate": 3.2983621095806887e-06, "loss": 0.8036, "step": 63420 }, { "epoch": 5.27, "learning_rate": 3.2982512540531554e-06, "loss": 0.7913, "step": 63430 }, { "epoch": 5.27, "learning_rate": 3.2981403985256212e-06, "loss": 0.8393, "step": 63440 }, { "epoch": 5.27, "learning_rate": 3.298029542998088e-06, "loss": 0.7843, "step": 63450 }, { "epoch": 5.27, "learning_rate": 3.297918687470554e-06, "loss": 0.8504, "step": 63460 }, { "epoch": 5.28, "learning_rate": 3.29780783194302e-06, "loss": 0.801, "step": 63470 }, { "epoch": 5.28, "learning_rate": 3.2976969764154864e-06, "loss": 0.8335, "step": 63480 }, { "epoch": 5.28, "learning_rate": 3.2975861208879527e-06, "loss": 0.8054, "step": 63490 }, { "epoch": 5.28, "learning_rate": 3.2974752653604186e-06, "loss": 0.8703, "step": 63500 }, { "epoch": 5.28, "learning_rate": 3.2973644098328853e-06, "loss": 0.8487, "step": 63510 }, { "epoch": 5.28, "learning_rate": 3.297253554305351e-06, "loss": 0.8049, "step": 63520 }, { "epoch": 5.28, "learning_rate": 3.297142698777818e-06, "loss": 0.793, "step": 63530 }, { "epoch": 5.28, "learning_rate": 3.2970318432502838e-06, "loss": 0.8475, "step": 63540 }, { "epoch": 5.28, "learning_rate": 3.29692098772275e-06, "loss": 0.737, "step": 63550 }, { "epoch": 5.28, "learning_rate": 3.296810132195217e-06, "loss": 0.8344, "step": 63560 }, { "epoch": 5.28, "learning_rate": 3.2966992766676827e-06, "loss": 0.8577, "step": 63570 }, { "epoch": 5.28, "learning_rate": 3.296588421140149e-06, "loss": 0.7911, "step": 63580 }, { "epoch": 5.29, "learning_rate": 3.2964775656126153e-06, "loss": 0.8956, "step": 63590 }, { "epoch": 5.29, "learning_rate": 3.2963667100850815e-06, "loss": 0.8289, "step": 63600 }, { "epoch": 5.29, "learning_rate": 3.2962558545575474e-06, "loss": 0.8416, "step": 63610 }, { "epoch": 5.29, "learning_rate": 3.296144999030014e-06, "loss": 0.8123, "step": 63620 }, { "epoch": 5.29, "learning_rate": 3.29603414350248e-06, "loss": 0.7983, "step": 63630 }, { "epoch": 5.29, "learning_rate": 3.2959232879749467e-06, "loss": 0.8734, "step": 63640 }, { "epoch": 5.29, "learning_rate": 3.2958124324474126e-06, "loss": 0.84, "step": 63650 }, { "epoch": 5.29, "learning_rate": 3.295701576919879e-06, "loss": 0.8446, "step": 63660 }, { "epoch": 5.29, "learning_rate": 3.295590721392345e-06, "loss": 0.8445, "step": 63670 }, { "epoch": 5.29, "learning_rate": 3.2954798658648115e-06, "loss": 0.766, "step": 63680 }, { "epoch": 5.29, "learning_rate": 3.2953690103372778e-06, "loss": 0.8616, "step": 63690 }, { "epoch": 5.29, "learning_rate": 3.295258154809744e-06, "loss": 0.8223, "step": 63700 }, { "epoch": 5.3, "learning_rate": 3.2951472992822104e-06, "loss": 0.7829, "step": 63710 }, { "epoch": 5.3, "learning_rate": 3.2950364437546767e-06, "loss": 0.8864, "step": 63720 }, { "epoch": 5.3, "learning_rate": 3.294925588227143e-06, "loss": 0.8518, "step": 63730 }, { "epoch": 5.3, "learning_rate": 3.294814732699609e-06, "loss": 0.8376, "step": 63740 }, { "epoch": 5.3, "learning_rate": 3.2947038771720756e-06, "loss": 0.7782, "step": 63750 }, { "epoch": 5.3, "learning_rate": 3.2945930216445414e-06, "loss": 0.8877, "step": 63760 }, { "epoch": 5.3, "learning_rate": 3.2944821661170077e-06, "loss": 0.8467, "step": 63770 }, { "epoch": 5.3, "learning_rate": 3.294371310589474e-06, "loss": 0.7938, "step": 63780 }, { "epoch": 5.3, "learning_rate": 3.2942604550619403e-06, "loss": 0.8441, "step": 63790 }, { "epoch": 5.3, "learning_rate": 3.294149599534407e-06, "loss": 0.756, "step": 63800 }, { "epoch": 5.3, "learning_rate": 3.294038744006873e-06, "loss": 0.8119, "step": 63810 }, { "epoch": 5.3, "learning_rate": 3.293927888479339e-06, "loss": 0.8025, "step": 63820 }, { "epoch": 5.31, "learning_rate": 3.2938170329518055e-06, "loss": 0.8862, "step": 63830 }, { "epoch": 5.31, "learning_rate": 3.293706177424272e-06, "loss": 0.8989, "step": 63840 }, { "epoch": 5.31, "learning_rate": 3.2935953218967377e-06, "loss": 0.7729, "step": 63850 }, { "epoch": 5.31, "learning_rate": 3.2934844663692044e-06, "loss": 0.8644, "step": 63860 }, { "epoch": 5.31, "learning_rate": 3.2933736108416703e-06, "loss": 0.8286, "step": 63870 }, { "epoch": 5.31, "learning_rate": 3.293262755314137e-06, "loss": 0.7492, "step": 63880 }, { "epoch": 5.31, "learning_rate": 3.293151899786603e-06, "loss": 0.8506, "step": 63890 }, { "epoch": 5.31, "learning_rate": 3.293041044259069e-06, "loss": 0.7979, "step": 63900 }, { "epoch": 5.31, "learning_rate": 3.2929301887315354e-06, "loss": 0.8385, "step": 63910 }, { "epoch": 5.31, "learning_rate": 3.2928193332040017e-06, "loss": 0.8755, "step": 63920 }, { "epoch": 5.31, "learning_rate": 3.292708477676468e-06, "loss": 0.8419, "step": 63930 }, { "epoch": 5.31, "learning_rate": 3.2925976221489343e-06, "loss": 0.8164, "step": 63940 }, { "epoch": 5.32, "learning_rate": 3.2924867666214006e-06, "loss": 0.7952, "step": 63950 }, { "epoch": 5.32, "learning_rate": 3.292375911093867e-06, "loss": 0.8296, "step": 63960 }, { "epoch": 5.32, "learning_rate": 3.292265055566333e-06, "loss": 0.7702, "step": 63970 }, { "epoch": 5.32, "learning_rate": 3.292154200038799e-06, "loss": 0.8096, "step": 63980 }, { "epoch": 5.32, "learning_rate": 3.292043344511266e-06, "loss": 0.8052, "step": 63990 }, { "epoch": 5.32, "learning_rate": 3.2919324889837317e-06, "loss": 0.7915, "step": 64000 }, { "epoch": 5.32, "learning_rate": 3.291821633456198e-06, "loss": 0.8211, "step": 64010 }, { "epoch": 5.32, "learning_rate": 3.2917107779286643e-06, "loss": 0.83, "step": 64020 }, { "epoch": 5.32, "learning_rate": 3.2915999224011306e-06, "loss": 0.7973, "step": 64030 }, { "epoch": 5.32, "learning_rate": 3.2914890668735964e-06, "loss": 0.8373, "step": 64040 }, { "epoch": 5.32, "learning_rate": 3.291378211346063e-06, "loss": 0.7993, "step": 64050 }, { "epoch": 5.32, "learning_rate": 3.2912673558185294e-06, "loss": 0.8612, "step": 64060 }, { "epoch": 5.33, "learning_rate": 3.2911565002909957e-06, "loss": 0.8208, "step": 64070 }, { "epoch": 5.33, "learning_rate": 3.291045644763462e-06, "loss": 0.8579, "step": 64080 }, { "epoch": 5.33, "learning_rate": 3.290934789235928e-06, "loss": 0.7857, "step": 64090 }, { "epoch": 5.33, "learning_rate": 3.2908239337083946e-06, "loss": 0.8371, "step": 64100 }, { "epoch": 5.33, "learning_rate": 3.2907130781808605e-06, "loss": 0.7753, "step": 64110 }, { "epoch": 5.33, "learning_rate": 3.2906022226533268e-06, "loss": 0.8331, "step": 64120 }, { "epoch": 5.33, "learning_rate": 3.290491367125793e-06, "loss": 0.8129, "step": 64130 }, { "epoch": 5.33, "learning_rate": 3.2903805115982594e-06, "loss": 0.8321, "step": 64140 }, { "epoch": 5.33, "learning_rate": 3.2902696560707257e-06, "loss": 0.8234, "step": 64150 }, { "epoch": 5.33, "learning_rate": 3.290158800543192e-06, "loss": 0.8681, "step": 64160 }, { "epoch": 5.33, "learning_rate": 3.2900479450156583e-06, "loss": 0.8106, "step": 64170 }, { "epoch": 5.33, "learning_rate": 3.2899370894881246e-06, "loss": 0.7862, "step": 64180 }, { "epoch": 5.34, "learning_rate": 3.289837319513344e-06, "loss": 0.8074, "step": 64190 }, { "epoch": 5.34, "learning_rate": 3.2897264639858104e-06, "loss": 0.9104, "step": 64200 }, { "epoch": 5.34, "learning_rate": 3.2896156084582763e-06, "loss": 0.7667, "step": 64210 }, { "epoch": 5.34, "learning_rate": 3.289504752930743e-06, "loss": 0.8696, "step": 64220 }, { "epoch": 5.34, "learning_rate": 3.289393897403209e-06, "loss": 0.8647, "step": 64230 }, { "epoch": 5.34, "learning_rate": 3.2892830418756756e-06, "loss": 0.8296, "step": 64240 }, { "epoch": 5.34, "learning_rate": 3.2891721863481414e-06, "loss": 0.7687, "step": 64250 }, { "epoch": 5.34, "learning_rate": 3.2890613308206077e-06, "loss": 0.8212, "step": 64260 }, { "epoch": 5.34, "learning_rate": 3.2889504752930745e-06, "loss": 0.8381, "step": 64270 }, { "epoch": 5.34, "learning_rate": 3.2888396197655403e-06, "loss": 0.7768, "step": 64280 }, { "epoch": 5.34, "learning_rate": 3.2887287642380066e-06, "loss": 0.8506, "step": 64290 }, { "epoch": 5.34, "learning_rate": 3.288617908710473e-06, "loss": 0.874, "step": 64300 }, { "epoch": 5.35, "learning_rate": 3.2885070531829392e-06, "loss": 0.7695, "step": 64310 }, { "epoch": 5.35, "learning_rate": 3.2883961976554055e-06, "loss": 0.8295, "step": 64320 }, { "epoch": 5.35, "learning_rate": 3.288285342127872e-06, "loss": 0.7842, "step": 64330 }, { "epoch": 5.35, "learning_rate": 3.2881744866003377e-06, "loss": 0.7866, "step": 64340 }, { "epoch": 5.35, "learning_rate": 3.2880636310728044e-06, "loss": 0.8225, "step": 64350 }, { "epoch": 5.35, "learning_rate": 3.2879527755452703e-06, "loss": 0.8429, "step": 64360 }, { "epoch": 5.35, "learning_rate": 3.2878419200177366e-06, "loss": 0.8095, "step": 64370 }, { "epoch": 5.35, "learning_rate": 3.2877310644902033e-06, "loss": 0.7927, "step": 64380 }, { "epoch": 5.35, "learning_rate": 3.287620208962669e-06, "loss": 0.7651, "step": 64390 }, { "epoch": 5.35, "learning_rate": 3.287509353435136e-06, "loss": 0.9063, "step": 64400 }, { "epoch": 5.35, "learning_rate": 3.2873984979076017e-06, "loss": 0.9041, "step": 64410 }, { "epoch": 5.35, "learning_rate": 3.287287642380068e-06, "loss": 0.8129, "step": 64420 }, { "epoch": 5.36, "learning_rate": 3.2871767868525343e-06, "loss": 0.8388, "step": 64430 }, { "epoch": 5.36, "learning_rate": 3.2870659313250006e-06, "loss": 0.8624, "step": 64440 }, { "epoch": 5.36, "learning_rate": 3.2869550757974665e-06, "loss": 0.8488, "step": 64450 }, { "epoch": 5.36, "learning_rate": 3.2868442202699332e-06, "loss": 0.8393, "step": 64460 }, { "epoch": 5.36, "learning_rate": 3.286733364742399e-06, "loss": 0.8332, "step": 64470 }, { "epoch": 5.36, "learning_rate": 3.286622509214866e-06, "loss": 0.791, "step": 64480 }, { "epoch": 5.36, "learning_rate": 3.2865116536873317e-06, "loss": 0.8653, "step": 64490 }, { "epoch": 5.36, "learning_rate": 3.286400798159798e-06, "loss": 0.7968, "step": 64500 }, { "epoch": 5.36, "learning_rate": 3.2862899426322647e-06, "loss": 0.7884, "step": 64510 }, { "epoch": 5.36, "learning_rate": 3.2861790871047306e-06, "loss": 0.7954, "step": 64520 }, { "epoch": 5.36, "learning_rate": 3.286068231577197e-06, "loss": 0.8559, "step": 64530 }, { "epoch": 5.36, "learning_rate": 3.285957376049663e-06, "loss": 0.7729, "step": 64540 }, { "epoch": 5.37, "learning_rate": 3.2858465205221295e-06, "loss": 0.8608, "step": 64550 }, { "epoch": 5.37, "learning_rate": 3.2857356649945953e-06, "loss": 0.8409, "step": 64560 }, { "epoch": 5.37, "learning_rate": 3.285624809467062e-06, "loss": 0.7525, "step": 64570 }, { "epoch": 5.37, "learning_rate": 3.285513953939528e-06, "loss": 0.7792, "step": 64580 }, { "epoch": 5.37, "learning_rate": 3.2854030984119946e-06, "loss": 0.8282, "step": 64590 }, { "epoch": 5.37, "learning_rate": 3.2852922428844605e-06, "loss": 0.8109, "step": 64600 }, { "epoch": 5.37, "learning_rate": 3.285181387356927e-06, "loss": 0.8418, "step": 64610 }, { "epoch": 5.37, "learning_rate": 3.285070531829393e-06, "loss": 0.8358, "step": 64620 }, { "epoch": 5.37, "learning_rate": 3.284970761854613e-06, "loss": 0.8278, "step": 64630 }, { "epoch": 5.37, "learning_rate": 3.284859906327079e-06, "loss": 0.7821, "step": 64640 }, { "epoch": 5.37, "learning_rate": 3.2847490507995457e-06, "loss": 0.8363, "step": 64650 }, { "epoch": 5.37, "learning_rate": 3.2846381952720115e-06, "loss": 0.8418, "step": 64660 }, { "epoch": 5.38, "learning_rate": 3.284527339744478e-06, "loss": 0.8566, "step": 64670 }, { "epoch": 5.38, "learning_rate": 3.284416484216944e-06, "loss": 0.8515, "step": 64680 }, { "epoch": 5.38, "learning_rate": 3.2843056286894104e-06, "loss": 0.7598, "step": 64690 }, { "epoch": 5.38, "learning_rate": 3.2841947731618763e-06, "loss": 0.8103, "step": 64700 }, { "epoch": 5.38, "learning_rate": 3.284083917634343e-06, "loss": 0.8742, "step": 64710 }, { "epoch": 5.38, "learning_rate": 3.2839730621068093e-06, "loss": 0.8776, "step": 64720 }, { "epoch": 5.38, "learning_rate": 3.283862206579275e-06, "loss": 0.8479, "step": 64730 }, { "epoch": 5.38, "learning_rate": 3.283751351051742e-06, "loss": 0.8818, "step": 64740 }, { "epoch": 5.38, "learning_rate": 3.2836404955242078e-06, "loss": 0.7953, "step": 64750 }, { "epoch": 5.38, "learning_rate": 3.2835296399966745e-06, "loss": 0.9505, "step": 64760 }, { "epoch": 5.38, "learning_rate": 3.2834187844691404e-06, "loss": 0.8803, "step": 64770 }, { "epoch": 5.38, "learning_rate": 3.2833079289416066e-06, "loss": 0.8127, "step": 64780 }, { "epoch": 5.39, "learning_rate": 3.283197073414073e-06, "loss": 0.8265, "step": 64790 }, { "epoch": 5.39, "learning_rate": 3.2830862178865392e-06, "loss": 0.8199, "step": 64800 }, { "epoch": 5.39, "learning_rate": 3.282975362359005e-06, "loss": 0.8465, "step": 64810 }, { "epoch": 5.39, "learning_rate": 3.282864506831472e-06, "loss": 0.802, "step": 64820 }, { "epoch": 5.39, "learning_rate": 3.2827536513039377e-06, "loss": 0.8878, "step": 64830 }, { "epoch": 5.39, "learning_rate": 3.2826427957764044e-06, "loss": 0.8068, "step": 64840 }, { "epoch": 5.39, "learning_rate": 3.2825319402488707e-06, "loss": 0.8117, "step": 64850 }, { "epoch": 5.39, "learning_rate": 3.2824210847213366e-06, "loss": 0.8349, "step": 64860 }, { "epoch": 5.39, "learning_rate": 3.2823102291938033e-06, "loss": 0.8482, "step": 64870 }, { "epoch": 5.39, "learning_rate": 3.282199373666269e-06, "loss": 0.8706, "step": 64880 }, { "epoch": 5.39, "learning_rate": 3.2820885181387355e-06, "loss": 0.808, "step": 64890 }, { "epoch": 5.39, "learning_rate": 3.2819776626112018e-06, "loss": 0.8532, "step": 64900 }, { "epoch": 5.4, "learning_rate": 3.281866807083668e-06, "loss": 0.8056, "step": 64910 }, { "epoch": 5.4, "learning_rate": 3.2817559515561344e-06, "loss": 0.7786, "step": 64920 }, { "epoch": 5.4, "learning_rate": 3.2816450960286007e-06, "loss": 0.8114, "step": 64930 }, { "epoch": 5.4, "learning_rate": 3.2815342405010665e-06, "loss": 0.7898, "step": 64940 }, { "epoch": 5.4, "learning_rate": 3.2814233849735332e-06, "loss": 0.8138, "step": 64950 }, { "epoch": 5.4, "learning_rate": 3.2813125294459995e-06, "loss": 0.8387, "step": 64960 }, { "epoch": 5.4, "learning_rate": 3.2812016739184654e-06, "loss": 0.7945, "step": 64970 }, { "epoch": 5.4, "learning_rate": 3.281090818390932e-06, "loss": 0.8478, "step": 64980 }, { "epoch": 5.4, "learning_rate": 3.280979962863398e-06, "loss": 0.7777, "step": 64990 }, { "epoch": 5.4, "learning_rate": 3.2808691073358647e-06, "loss": 0.7772, "step": 65000 }, { "epoch": 5.4, "learning_rate": 3.2807582518083306e-06, "loss": 0.8189, "step": 65010 }, { "epoch": 5.4, "learning_rate": 3.280647396280797e-06, "loss": 0.7938, "step": 65020 }, { "epoch": 5.41, "learning_rate": 3.280536540753263e-06, "loss": 0.7908, "step": 65030 }, { "epoch": 5.41, "learning_rate": 3.2804256852257295e-06, "loss": 0.7667, "step": 65040 }, { "epoch": 5.41, "learning_rate": 3.2803148296981954e-06, "loss": 0.8574, "step": 65050 }, { "epoch": 5.41, "learning_rate": 3.280203974170662e-06, "loss": 0.8479, "step": 65060 }, { "epoch": 5.41, "learning_rate": 3.280093118643128e-06, "loss": 0.812, "step": 65070 }, { "epoch": 5.41, "learning_rate": 3.2799822631155942e-06, "loss": 0.8622, "step": 65080 }, { "epoch": 5.41, "learning_rate": 3.279871407588061e-06, "loss": 0.8144, "step": 65090 }, { "epoch": 5.41, "learning_rate": 3.279760552060527e-06, "loss": 0.8456, "step": 65100 }, { "epoch": 5.41, "learning_rate": 3.2796496965329935e-06, "loss": 0.8659, "step": 65110 }, { "epoch": 5.41, "learning_rate": 3.2795388410054594e-06, "loss": 0.7953, "step": 65120 }, { "epoch": 5.41, "learning_rate": 3.2794279854779257e-06, "loss": 0.7897, "step": 65130 }, { "epoch": 5.41, "learning_rate": 3.279317129950392e-06, "loss": 0.8085, "step": 65140 }, { "epoch": 5.42, "learning_rate": 3.2792062744228583e-06, "loss": 0.7854, "step": 65150 }, { "epoch": 5.42, "learning_rate": 3.279095418895324e-06, "loss": 0.8685, "step": 65160 }, { "epoch": 5.42, "learning_rate": 3.278984563367791e-06, "loss": 0.8349, "step": 65170 }, { "epoch": 5.42, "learning_rate": 3.2788737078402568e-06, "loss": 0.8514, "step": 65180 }, { "epoch": 5.42, "learning_rate": 3.2787628523127235e-06, "loss": 0.8977, "step": 65190 }, { "epoch": 5.42, "learning_rate": 3.2786519967851894e-06, "loss": 0.8404, "step": 65200 }, { "epoch": 5.42, "learning_rate": 3.2785411412576557e-06, "loss": 0.9005, "step": 65210 }, { "epoch": 5.42, "learning_rate": 3.2784302857301224e-06, "loss": 0.7699, "step": 65220 }, { "epoch": 5.42, "learning_rate": 3.2783194302025882e-06, "loss": 0.7868, "step": 65230 }, { "epoch": 5.42, "learning_rate": 3.2782085746750545e-06, "loss": 0.7777, "step": 65240 }, { "epoch": 5.42, "learning_rate": 3.278097719147521e-06, "loss": 0.8855, "step": 65250 }, { "epoch": 5.42, "learning_rate": 3.277986863619987e-06, "loss": 0.8469, "step": 65260 }, { "epoch": 5.43, "learning_rate": 3.2778760080924534e-06, "loss": 0.8286, "step": 65270 }, { "epoch": 5.43, "learning_rate": 3.2777651525649197e-06, "loss": 0.8302, "step": 65280 }, { "epoch": 5.43, "learning_rate": 3.2776542970373856e-06, "loss": 0.8183, "step": 65290 }, { "epoch": 5.43, "learning_rate": 3.2775434415098523e-06, "loss": 0.7462, "step": 65300 }, { "epoch": 5.43, "learning_rate": 3.277432585982318e-06, "loss": 0.8282, "step": 65310 }, { "epoch": 5.43, "learning_rate": 3.2773217304547845e-06, "loss": 0.8156, "step": 65320 }, { "epoch": 5.43, "learning_rate": 3.277210874927251e-06, "loss": 0.788, "step": 65330 }, { "epoch": 5.43, "learning_rate": 3.277100019399717e-06, "loss": 0.7954, "step": 65340 }, { "epoch": 5.43, "learning_rate": 3.276989163872184e-06, "loss": 0.7541, "step": 65350 }, { "epoch": 5.43, "learning_rate": 3.2768783083446497e-06, "loss": 0.8958, "step": 65360 }, { "epoch": 5.43, "learning_rate": 3.276767452817116e-06, "loss": 0.8331, "step": 65370 }, { "epoch": 5.43, "learning_rate": 3.2766565972895823e-06, "loss": 0.8146, "step": 65380 }, { "epoch": 5.44, "learning_rate": 3.2765457417620485e-06, "loss": 0.8083, "step": 65390 }, { "epoch": 5.44, "learning_rate": 3.2764348862345144e-06, "loss": 0.7758, "step": 65400 }, { "epoch": 5.44, "learning_rate": 3.276324030706981e-06, "loss": 0.9051, "step": 65410 }, { "epoch": 5.44, "learning_rate": 3.276213175179447e-06, "loss": 0.7436, "step": 65420 }, { "epoch": 5.44, "learning_rate": 3.2761023196519137e-06, "loss": 0.8049, "step": 65430 }, { "epoch": 5.44, "learning_rate": 3.2759914641243796e-06, "loss": 0.8094, "step": 65440 }, { "epoch": 5.44, "learning_rate": 3.275880608596846e-06, "loss": 0.8285, "step": 65450 }, { "epoch": 5.44, "learning_rate": 3.2757697530693126e-06, "loss": 0.9369, "step": 65460 }, { "epoch": 5.44, "learning_rate": 3.2756588975417785e-06, "loss": 0.8291, "step": 65470 }, { "epoch": 5.44, "learning_rate": 3.2755480420142448e-06, "loss": 0.8423, "step": 65480 }, { "epoch": 5.44, "learning_rate": 3.275437186486711e-06, "loss": 0.7712, "step": 65490 }, { "epoch": 5.44, "learning_rate": 3.2753263309591774e-06, "loss": 0.7727, "step": 65500 }, { "epoch": 5.45, "learning_rate": 3.2752154754316432e-06, "loss": 0.8849, "step": 65510 }, { "epoch": 5.45, "learning_rate": 3.27510461990411e-06, "loss": 0.8146, "step": 65520 }, { "epoch": 5.45, "learning_rate": 3.274993764376576e-06, "loss": 0.8498, "step": 65530 }, { "epoch": 5.45, "learning_rate": 3.2748829088490426e-06, "loss": 0.8267, "step": 65540 }, { "epoch": 5.45, "learning_rate": 3.2747720533215084e-06, "loss": 0.7892, "step": 65550 }, { "epoch": 5.45, "learning_rate": 3.2746611977939747e-06, "loss": 0.8247, "step": 65560 }, { "epoch": 5.45, "learning_rate": 3.274550342266441e-06, "loss": 0.8287, "step": 65570 }, { "epoch": 5.45, "learning_rate": 3.2744394867389073e-06, "loss": 0.8047, "step": 65580 }, { "epoch": 5.45, "learning_rate": 3.2743286312113736e-06, "loss": 0.7939, "step": 65590 }, { "epoch": 5.45, "learning_rate": 3.27421777568384e-06, "loss": 0.7887, "step": 65600 }, { "epoch": 5.45, "learning_rate": 3.274106920156306e-06, "loss": 0.8285, "step": 65610 }, { "epoch": 5.45, "learning_rate": 3.2739960646287725e-06, "loss": 0.8116, "step": 65620 }, { "epoch": 5.46, "learning_rate": 3.2738852091012388e-06, "loss": 0.7755, "step": 65630 }, { "epoch": 5.46, "learning_rate": 3.2737743535737047e-06, "loss": 0.7881, "step": 65640 }, { "epoch": 5.46, "learning_rate": 3.2736634980461714e-06, "loss": 0.8005, "step": 65650 }, { "epoch": 5.46, "learning_rate": 3.2735526425186373e-06, "loss": 0.8736, "step": 65660 }, { "epoch": 5.46, "learning_rate": 3.2734417869911035e-06, "loss": 0.883, "step": 65670 }, { "epoch": 5.46, "learning_rate": 3.27333093146357e-06, "loss": 0.7881, "step": 65680 }, { "epoch": 5.46, "learning_rate": 3.273220075936036e-06, "loss": 0.808, "step": 65690 }, { "epoch": 5.46, "learning_rate": 3.273109220408503e-06, "loss": 0.8168, "step": 65700 }, { "epoch": 5.46, "learning_rate": 3.2729983648809687e-06, "loss": 0.9111, "step": 65710 }, { "epoch": 5.46, "learning_rate": 3.272887509353435e-06, "loss": 0.7605, "step": 65720 }, { "epoch": 5.46, "learning_rate": 3.2727766538259013e-06, "loss": 0.8647, "step": 65730 }, { "epoch": 5.46, "learning_rate": 3.2726657982983676e-06, "loss": 0.8515, "step": 65740 }, { "epoch": 5.47, "learning_rate": 3.2725549427708335e-06, "loss": 0.7893, "step": 65750 }, { "epoch": 5.47, "learning_rate": 3.2724440872433e-06, "loss": 0.8233, "step": 65760 }, { "epoch": 5.47, "learning_rate": 3.272333231715766e-06, "loss": 0.7441, "step": 65770 }, { "epoch": 5.47, "learning_rate": 3.272222376188233e-06, "loss": 0.8152, "step": 65780 }, { "epoch": 5.47, "learning_rate": 3.2721115206606987e-06, "loss": 0.7341, "step": 65790 }, { "epoch": 5.47, "learning_rate": 3.272000665133165e-06, "loss": 0.8293, "step": 65800 }, { "epoch": 5.47, "learning_rate": 3.2718898096056313e-06, "loss": 0.8259, "step": 65810 }, { "epoch": 5.47, "learning_rate": 3.2717789540780976e-06, "loss": 0.797, "step": 65820 }, { "epoch": 5.47, "learning_rate": 3.271668098550564e-06, "loss": 0.8267, "step": 65830 }, { "epoch": 5.47, "learning_rate": 3.27155724302303e-06, "loss": 0.7662, "step": 65840 }, { "epoch": 5.47, "learning_rate": 3.2714463874954964e-06, "loss": 0.789, "step": 65850 }, { "epoch": 5.47, "learning_rate": 3.2713355319679627e-06, "loss": 0.8395, "step": 65860 }, { "epoch": 5.48, "learning_rate": 3.271224676440429e-06, "loss": 0.8301, "step": 65870 }, { "epoch": 5.48, "learning_rate": 3.271113820912895e-06, "loss": 0.747, "step": 65880 }, { "epoch": 5.48, "learning_rate": 3.2710029653853616e-06, "loss": 0.8103, "step": 65890 }, { "epoch": 5.48, "learning_rate": 3.2708921098578275e-06, "loss": 0.8842, "step": 65900 }, { "epoch": 5.48, "learning_rate": 3.2707812543302938e-06, "loss": 0.8028, "step": 65910 }, { "epoch": 5.48, "learning_rate": 3.27067039880276e-06, "loss": 0.7884, "step": 65920 }, { "epoch": 5.48, "learning_rate": 3.2705595432752264e-06, "loss": 0.7819, "step": 65930 }, { "epoch": 5.48, "learning_rate": 3.270448687747693e-06, "loss": 0.8326, "step": 65940 }, { "epoch": 5.48, "learning_rate": 3.270337832220159e-06, "loss": 0.8165, "step": 65950 }, { "epoch": 5.48, "learning_rate": 3.2702269766926253e-06, "loss": 0.7877, "step": 65960 }, { "epoch": 5.48, "learning_rate": 3.2701161211650916e-06, "loss": 0.8046, "step": 65970 }, { "epoch": 5.48, "learning_rate": 3.270005265637558e-06, "loss": 0.7771, "step": 65980 }, { "epoch": 5.48, "learning_rate": 3.2698944101100237e-06, "loss": 0.7845, "step": 65990 }, { "epoch": 5.49, "learning_rate": 3.2697835545824904e-06, "loss": 0.8169, "step": 66000 }, { "epoch": 5.49, "learning_rate": 3.2696726990549563e-06, "loss": 0.8928, "step": 66010 }, { "epoch": 5.49, "learning_rate": 3.2695618435274226e-06, "loss": 0.8497, "step": 66020 }, { "epoch": 5.49, "learning_rate": 3.269450987999889e-06, "loss": 0.843, "step": 66030 }, { "epoch": 5.49, "learning_rate": 3.269340132472355e-06, "loss": 0.7868, "step": 66040 }, { "epoch": 5.49, "learning_rate": 3.2692292769448215e-06, "loss": 0.8561, "step": 66050 }, { "epoch": 5.49, "learning_rate": 3.269118421417288e-06, "loss": 0.856, "step": 66060 }, { "epoch": 5.49, "learning_rate": 3.269007565889754e-06, "loss": 0.8084, "step": 66070 }, { "epoch": 5.49, "learning_rate": 3.2688967103622204e-06, "loss": 0.8663, "step": 66080 }, { "epoch": 5.49, "learning_rate": 3.2687858548346867e-06, "loss": 0.8146, "step": 66090 }, { "epoch": 5.49, "learning_rate": 3.2686749993071526e-06, "loss": 0.7972, "step": 66100 }, { "epoch": 5.49, "learning_rate": 3.2685641437796193e-06, "loss": 0.9151, "step": 66110 }, { "epoch": 5.5, "learning_rate": 3.268453288252085e-06, "loss": 0.808, "step": 66120 }, { "epoch": 5.5, "learning_rate": 3.268342432724552e-06, "loss": 0.8224, "step": 66130 }, { "epoch": 5.5, "learning_rate": 3.2682315771970177e-06, "loss": 0.765, "step": 66140 }, { "epoch": 5.5, "learning_rate": 3.268120721669484e-06, "loss": 0.8198, "step": 66150 }, { "epoch": 5.5, "learning_rate": 3.2680098661419503e-06, "loss": 0.8526, "step": 66160 }, { "epoch": 5.5, "learning_rate": 3.2678990106144166e-06, "loss": 0.8525, "step": 66170 }, { "epoch": 5.5, "learning_rate": 3.2677881550868825e-06, "loss": 0.8117, "step": 66180 }, { "epoch": 5.5, "learning_rate": 3.267677299559349e-06, "loss": 0.7928, "step": 66190 }, { "epoch": 5.5, "learning_rate": 3.2675664440318155e-06, "loss": 0.7582, "step": 66200 }, { "epoch": 5.5, "learning_rate": 3.267455588504282e-06, "loss": 0.8176, "step": 66210 }, { "epoch": 5.5, "learning_rate": 3.267344732976748e-06, "loss": 0.7971, "step": 66220 }, { "epoch": 5.5, "learning_rate": 3.267233877449214e-06, "loss": 0.8187, "step": 66230 }, { "epoch": 5.51, "learning_rate": 3.2671230219216807e-06, "loss": 0.7616, "step": 66240 }, { "epoch": 5.51, "learning_rate": 3.2670121663941466e-06, "loss": 0.7745, "step": 66250 }, { "epoch": 5.51, "learning_rate": 3.266901310866613e-06, "loss": 0.8828, "step": 66260 }, { "epoch": 5.51, "learning_rate": 3.266790455339079e-06, "loss": 0.7669, "step": 66270 }, { "epoch": 5.51, "learning_rate": 3.2666795998115454e-06, "loss": 0.8004, "step": 66280 }, { "epoch": 5.51, "learning_rate": 3.2665687442840113e-06, "loss": 0.7941, "step": 66290 }, { "epoch": 5.51, "learning_rate": 3.266457888756478e-06, "loss": 0.8727, "step": 66300 }, { "epoch": 5.51, "learning_rate": 3.2663470332289443e-06, "loss": 0.8417, "step": 66310 }, { "epoch": 5.51, "learning_rate": 3.2662361777014106e-06, "loss": 0.828, "step": 66320 }, { "epoch": 5.51, "learning_rate": 3.266125322173877e-06, "loss": 0.8362, "step": 66330 }, { "epoch": 5.51, "learning_rate": 3.266014466646343e-06, "loss": 0.7642, "step": 66340 }, { "epoch": 5.51, "learning_rate": 3.2659036111188095e-06, "loss": 0.8323, "step": 66350 }, { "epoch": 5.52, "learning_rate": 3.2657927555912754e-06, "loss": 0.8432, "step": 66360 }, { "epoch": 5.52, "learning_rate": 3.2656819000637417e-06, "loss": 0.8847, "step": 66370 }, { "epoch": 5.52, "learning_rate": 3.265571044536208e-06, "loss": 0.8188, "step": 66380 }, { "epoch": 5.52, "learning_rate": 3.2654601890086743e-06, "loss": 0.757, "step": 66390 }, { "epoch": 5.52, "learning_rate": 3.2653493334811406e-06, "loss": 0.7628, "step": 66400 }, { "epoch": 5.52, "learning_rate": 3.265238477953607e-06, "loss": 0.846, "step": 66410 }, { "epoch": 5.52, "learning_rate": 3.2651276224260727e-06, "loss": 0.8263, "step": 66420 }, { "epoch": 5.52, "learning_rate": 3.2650167668985395e-06, "loss": 0.8319, "step": 66430 }, { "epoch": 5.52, "learning_rate": 3.2649059113710057e-06, "loss": 0.7812, "step": 66440 }, { "epoch": 5.52, "learning_rate": 3.2647950558434716e-06, "loss": 0.7976, "step": 66450 }, { "epoch": 5.52, "learning_rate": 3.2646842003159383e-06, "loss": 0.8215, "step": 66460 }, { "epoch": 5.52, "learning_rate": 3.264573344788404e-06, "loss": 0.7967, "step": 66470 }, { "epoch": 5.53, "learning_rate": 3.264462489260871e-06, "loss": 0.8376, "step": 66480 }, { "epoch": 5.53, "learning_rate": 3.264351633733337e-06, "loss": 0.8318, "step": 66490 }, { "epoch": 5.53, "learning_rate": 3.264240778205803e-06, "loss": 0.8738, "step": 66500 }, { "epoch": 5.53, "learning_rate": 3.2641299226782694e-06, "loss": 0.9241, "step": 66510 }, { "epoch": 5.53, "learning_rate": 3.2640190671507357e-06, "loss": 0.8561, "step": 66520 }, { "epoch": 5.53, "learning_rate": 3.2639082116232016e-06, "loss": 0.9743, "step": 66530 }, { "epoch": 5.53, "learning_rate": 3.2637973560956683e-06, "loss": 0.8498, "step": 66540 }, { "epoch": 5.53, "learning_rate": 3.263686500568134e-06, "loss": 0.7746, "step": 66550 }, { "epoch": 5.53, "learning_rate": 3.263575645040601e-06, "loss": 0.8499, "step": 66560 }, { "epoch": 5.53, "learning_rate": 3.263464789513067e-06, "loss": 0.8389, "step": 66570 }, { "epoch": 5.53, "learning_rate": 3.263353933985533e-06, "loss": 0.8121, "step": 66580 }, { "epoch": 5.53, "learning_rate": 3.2632430784579998e-06, "loss": 0.8172, "step": 66590 }, { "epoch": 5.54, "learning_rate": 3.2631322229304656e-06, "loss": 0.8905, "step": 66600 }, { "epoch": 5.54, "learning_rate": 3.263021367402932e-06, "loss": 0.8401, "step": 66610 }, { "epoch": 5.54, "learning_rate": 3.2629105118753982e-06, "loss": 0.8583, "step": 66620 }, { "epoch": 5.54, "learning_rate": 3.2627996563478645e-06, "loss": 0.7888, "step": 66630 }, { "epoch": 5.54, "learning_rate": 3.262688800820331e-06, "loss": 0.7894, "step": 66640 }, { "epoch": 5.54, "learning_rate": 3.262577945292797e-06, "loss": 0.7982, "step": 66650 }, { "epoch": 5.54, "learning_rate": 3.262467089765263e-06, "loss": 0.8705, "step": 66660 }, { "epoch": 5.54, "learning_rate": 3.2623562342377297e-06, "loss": 0.8485, "step": 66670 }, { "epoch": 5.54, "learning_rate": 3.262245378710196e-06, "loss": 0.8181, "step": 66680 }, { "epoch": 5.54, "learning_rate": 3.262134523182662e-06, "loss": 0.7922, "step": 66690 }, { "epoch": 5.54, "learning_rate": 3.2620236676551286e-06, "loss": 0.7964, "step": 66700 }, { "epoch": 5.54, "learning_rate": 3.2619128121275944e-06, "loss": 0.8513, "step": 66710 }, { "epoch": 5.55, "learning_rate": 3.261801956600061e-06, "loss": 0.8378, "step": 66720 }, { "epoch": 5.55, "learning_rate": 3.261691101072527e-06, "loss": 0.7969, "step": 66730 }, { "epoch": 5.55, "learning_rate": 3.2615802455449933e-06, "loss": 0.765, "step": 66740 }, { "epoch": 5.55, "learning_rate": 3.2614693900174596e-06, "loss": 0.894, "step": 66750 }, { "epoch": 5.55, "learning_rate": 3.261358534489926e-06, "loss": 0.8732, "step": 66760 }, { "epoch": 5.55, "learning_rate": 3.261247678962392e-06, "loss": 0.7398, "step": 66770 }, { "epoch": 5.55, "learning_rate": 3.2611368234348585e-06, "loss": 0.7712, "step": 66780 }, { "epoch": 5.55, "learning_rate": 3.2610259679073244e-06, "loss": 0.8115, "step": 66790 }, { "epoch": 5.55, "learning_rate": 3.2609151123797907e-06, "loss": 0.8222, "step": 66800 }, { "epoch": 5.55, "learning_rate": 3.2608042568522574e-06, "loss": 0.8729, "step": 66810 }, { "epoch": 5.55, "learning_rate": 3.2606934013247233e-06, "loss": 0.7868, "step": 66820 }, { "epoch": 5.55, "learning_rate": 3.26058254579719e-06, "loss": 0.8558, "step": 66830 }, { "epoch": 5.56, "learning_rate": 3.260471690269656e-06, "loss": 0.8998, "step": 66840 }, { "epoch": 5.56, "learning_rate": 3.260360834742122e-06, "loss": 0.8167, "step": 66850 }, { "epoch": 5.56, "learning_rate": 3.2602499792145885e-06, "loss": 0.836, "step": 66860 }, { "epoch": 5.56, "learning_rate": 3.2601391236870548e-06, "loss": 0.8336, "step": 66870 }, { "epoch": 5.56, "learning_rate": 3.2600282681595206e-06, "loss": 0.7746, "step": 66880 }, { "epoch": 5.56, "learning_rate": 3.2599174126319873e-06, "loss": 0.8354, "step": 66890 }, { "epoch": 5.56, "learning_rate": 3.2598065571044532e-06, "loss": 0.7601, "step": 66900 }, { "epoch": 5.56, "learning_rate": 3.25969570157692e-06, "loss": 0.8688, "step": 66910 }, { "epoch": 5.56, "learning_rate": 3.259584846049386e-06, "loss": 0.8629, "step": 66920 }, { "epoch": 5.56, "learning_rate": 3.259473990521852e-06, "loss": 0.8043, "step": 66930 }, { "epoch": 5.56, "learning_rate": 3.259363134994319e-06, "loss": 0.8673, "step": 66940 }, { "epoch": 5.56, "learning_rate": 3.2592522794667847e-06, "loss": 0.7997, "step": 66950 }, { "epoch": 5.57, "learning_rate": 3.259141423939251e-06, "loss": 0.826, "step": 66960 }, { "epoch": 5.57, "learning_rate": 3.2590305684117173e-06, "loss": 0.7733, "step": 66970 }, { "epoch": 5.57, "learning_rate": 3.2589197128841836e-06, "loss": 0.8306, "step": 66980 }, { "epoch": 5.57, "learning_rate": 3.25880885735665e-06, "loss": 0.849, "step": 66990 }, { "epoch": 5.57, "learning_rate": 3.258698001829116e-06, "loss": 0.8631, "step": 67000 }, { "epoch": 5.57, "learning_rate": 3.258587146301582e-06, "loss": 0.7947, "step": 67010 }, { "epoch": 5.57, "learning_rate": 3.2584762907740488e-06, "loss": 0.8062, "step": 67020 }, { "epoch": 5.57, "learning_rate": 3.2583654352465146e-06, "loss": 0.8833, "step": 67030 }, { "epoch": 5.57, "learning_rate": 3.258254579718981e-06, "loss": 0.7831, "step": 67040 }, { "epoch": 5.57, "learning_rate": 3.2581437241914476e-06, "loss": 0.8056, "step": 67050 }, { "epoch": 5.57, "learning_rate": 3.2580328686639135e-06, "loss": 0.8648, "step": 67060 }, { "epoch": 5.57, "learning_rate": 3.2579220131363802e-06, "loss": 0.845, "step": 67070 }, { "epoch": 5.58, "learning_rate": 3.257811157608846e-06, "loss": 0.7666, "step": 67080 }, { "epoch": 5.58, "learning_rate": 3.2577003020813124e-06, "loss": 0.8008, "step": 67090 }, { "epoch": 5.58, "learning_rate": 3.2575894465537787e-06, "loss": 0.7966, "step": 67100 }, { "epoch": 5.58, "learning_rate": 3.257478591026245e-06, "loss": 0.8754, "step": 67110 }, { "epoch": 5.58, "learning_rate": 3.257367735498711e-06, "loss": 0.7789, "step": 67120 }, { "epoch": 5.58, "learning_rate": 3.2572568799711776e-06, "loss": 0.8737, "step": 67130 }, { "epoch": 5.58, "learning_rate": 3.2571460244436435e-06, "loss": 0.7785, "step": 67140 }, { "epoch": 5.58, "learning_rate": 3.25703516891611e-06, "loss": 0.8926, "step": 67150 }, { "epoch": 5.58, "learning_rate": 3.256924313388576e-06, "loss": 0.8324, "step": 67160 }, { "epoch": 5.58, "learning_rate": 3.2568134578610423e-06, "loss": 0.8207, "step": 67170 }, { "epoch": 5.58, "learning_rate": 3.256702602333509e-06, "loss": 0.9025, "step": 67180 }, { "epoch": 5.58, "learning_rate": 3.256591746805975e-06, "loss": 0.7938, "step": 67190 }, { "epoch": 5.59, "learning_rate": 3.2564808912784412e-06, "loss": 0.8178, "step": 67200 }, { "epoch": 5.59, "learning_rate": 3.2563700357509075e-06, "loss": 0.8727, "step": 67210 }, { "epoch": 5.59, "learning_rate": 3.256259180223374e-06, "loss": 0.8122, "step": 67220 }, { "epoch": 5.59, "learning_rate": 3.2561483246958397e-06, "loss": 0.8013, "step": 67230 }, { "epoch": 5.59, "learning_rate": 3.2560374691683064e-06, "loss": 0.7912, "step": 67240 }, { "epoch": 5.59, "learning_rate": 3.2559266136407723e-06, "loss": 0.7738, "step": 67250 }, { "epoch": 5.59, "learning_rate": 3.255815758113239e-06, "loss": 0.8477, "step": 67260 }, { "epoch": 5.59, "learning_rate": 3.255704902585705e-06, "loss": 0.794, "step": 67270 }, { "epoch": 5.59, "learning_rate": 3.255594047058171e-06, "loss": 0.7961, "step": 67280 }, { "epoch": 5.59, "learning_rate": 3.2554831915306375e-06, "loss": 0.8208, "step": 67290 }, { "epoch": 5.59, "learning_rate": 3.2553723360031038e-06, "loss": 0.8202, "step": 67300 }, { "epoch": 5.59, "learning_rate": 3.25526148047557e-06, "loss": 0.9178, "step": 67310 }, { "epoch": 5.6, "learning_rate": 3.2551506249480363e-06, "loss": 0.8092, "step": 67320 }, { "epoch": 5.6, "learning_rate": 3.2550397694205026e-06, "loss": 0.8317, "step": 67330 }, { "epoch": 5.6, "learning_rate": 3.254928913892969e-06, "loss": 0.8037, "step": 67340 }, { "epoch": 5.6, "learning_rate": 3.2548180583654352e-06, "loss": 0.7966, "step": 67350 }, { "epoch": 5.6, "learning_rate": 3.254707202837901e-06, "loss": 0.812, "step": 67360 }, { "epoch": 5.6, "learning_rate": 3.254596347310368e-06, "loss": 0.8192, "step": 67370 }, { "epoch": 5.6, "learning_rate": 3.2544854917828337e-06, "loss": 0.7368, "step": 67380 }, { "epoch": 5.6, "learning_rate": 3.2543746362553e-06, "loss": 0.8125, "step": 67390 }, { "epoch": 5.6, "learning_rate": 3.2542637807277663e-06, "loss": 0.794, "step": 67400 }, { "epoch": 5.6, "learning_rate": 3.2541529252002326e-06, "loss": 0.781, "step": 67410 }, { "epoch": 5.6, "learning_rate": 3.2540420696726993e-06, "loss": 0.8049, "step": 67420 }, { "epoch": 5.6, "learning_rate": 3.253931214145165e-06, "loss": 0.8423, "step": 67430 }, { "epoch": 5.61, "learning_rate": 3.2538203586176315e-06, "loss": 0.8442, "step": 67440 }, { "epoch": 5.61, "learning_rate": 3.2537095030900978e-06, "loss": 0.7888, "step": 67450 }, { "epoch": 5.61, "learning_rate": 3.253598647562564e-06, "loss": 0.8545, "step": 67460 }, { "epoch": 5.61, "learning_rate": 3.25348779203503e-06, "loss": 0.851, "step": 67470 }, { "epoch": 5.61, "learning_rate": 3.2533769365074966e-06, "loss": 0.8628, "step": 67480 }, { "epoch": 5.61, "learning_rate": 3.2532660809799625e-06, "loss": 0.8299, "step": 67490 }, { "epoch": 5.61, "learning_rate": 3.2531552254524292e-06, "loss": 0.8563, "step": 67500 }, { "epoch": 5.61, "learning_rate": 3.253044369924895e-06, "loss": 0.8368, "step": 67510 }, { "epoch": 5.61, "learning_rate": 3.2529335143973614e-06, "loss": 0.8514, "step": 67520 }, { "epoch": 5.61, "learning_rate": 3.2528226588698277e-06, "loss": 0.8047, "step": 67530 }, { "epoch": 5.61, "learning_rate": 3.252711803342294e-06, "loss": 0.7766, "step": 67540 }, { "epoch": 5.61, "learning_rate": 3.2526009478147603e-06, "loss": 0.8326, "step": 67550 }, { "epoch": 5.62, "learning_rate": 3.2524900922872266e-06, "loss": 0.7942, "step": 67560 }, { "epoch": 5.62, "learning_rate": 3.252379236759693e-06, "loss": 0.8635, "step": 67570 }, { "epoch": 5.62, "learning_rate": 3.2522683812321588e-06, "loss": 0.8013, "step": 67580 }, { "epoch": 5.62, "learning_rate": 3.2521575257046255e-06, "loss": 0.8075, "step": 67590 }, { "epoch": 5.62, "learning_rate": 3.2520466701770913e-06, "loss": 0.8424, "step": 67600 }, { "epoch": 5.62, "learning_rate": 3.251935814649558e-06, "loss": 0.8623, "step": 67610 }, { "epoch": 5.62, "learning_rate": 3.251824959122024e-06, "loss": 0.8091, "step": 67620 }, { "epoch": 5.62, "learning_rate": 3.2517141035944902e-06, "loss": 0.8559, "step": 67630 }, { "epoch": 5.62, "learning_rate": 3.2516032480669565e-06, "loss": 0.876, "step": 67640 }, { "epoch": 5.62, "learning_rate": 3.251492392539423e-06, "loss": 0.8102, "step": 67650 }, { "epoch": 5.62, "learning_rate": 3.2513815370118887e-06, "loss": 0.816, "step": 67660 }, { "epoch": 5.62, "learning_rate": 3.2512706814843554e-06, "loss": 0.7963, "step": 67670 }, { "epoch": 5.63, "learning_rate": 3.2511598259568217e-06, "loss": 0.8221, "step": 67680 }, { "epoch": 5.63, "learning_rate": 3.251048970429288e-06, "loss": 0.8085, "step": 67690 }, { "epoch": 5.63, "learning_rate": 3.2509381149017543e-06, "loss": 0.8257, "step": 67700 }, { "epoch": 5.63, "learning_rate": 3.25082725937422e-06, "loss": 0.8764, "step": 67710 }, { "epoch": 5.63, "learning_rate": 3.250716403846687e-06, "loss": 0.8352, "step": 67720 }, { "epoch": 5.63, "learning_rate": 3.2506055483191528e-06, "loss": 0.7646, "step": 67730 }, { "epoch": 5.63, "learning_rate": 3.250494692791619e-06, "loss": 0.83, "step": 67740 }, { "epoch": 5.63, "learning_rate": 3.2503838372640854e-06, "loss": 0.8065, "step": 67750 }, { "epoch": 5.63, "learning_rate": 3.2502729817365516e-06, "loss": 0.827, "step": 67760 }, { "epoch": 5.63, "learning_rate": 3.250162126209018e-06, "loss": 0.8205, "step": 67770 }, { "epoch": 5.63, "learning_rate": 3.2500512706814842e-06, "loss": 0.763, "step": 67780 }, { "epoch": 5.63, "learning_rate": 3.2499404151539505e-06, "loss": 0.7479, "step": 67790 }, { "epoch": 5.64, "learning_rate": 3.249829559626417e-06, "loss": 0.7997, "step": 67800 }, { "epoch": 5.64, "learning_rate": 3.249718704098883e-06, "loss": 0.8528, "step": 67810 }, { "epoch": 5.64, "learning_rate": 3.249607848571349e-06, "loss": 0.7961, "step": 67820 }, { "epoch": 5.64, "learning_rate": 3.2494969930438157e-06, "loss": 0.8005, "step": 67830 }, { "epoch": 5.64, "learning_rate": 3.2493861375162816e-06, "loss": 0.8565, "step": 67840 }, { "epoch": 5.64, "learning_rate": 3.2492752819887483e-06, "loss": 0.8548, "step": 67850 }, { "epoch": 5.64, "learning_rate": 3.249164426461214e-06, "loss": 0.7905, "step": 67860 }, { "epoch": 5.64, "learning_rate": 3.2490535709336805e-06, "loss": 0.8752, "step": 67870 }, { "epoch": 5.64, "learning_rate": 3.2489427154061468e-06, "loss": 0.7853, "step": 67880 }, { "epoch": 5.64, "learning_rate": 3.248831859878613e-06, "loss": 0.7983, "step": 67890 }, { "epoch": 5.64, "learning_rate": 3.248721004351079e-06, "loss": 0.8432, "step": 67900 }, { "epoch": 5.64, "learning_rate": 3.2486101488235457e-06, "loss": 0.8303, "step": 67910 }, { "epoch": 5.65, "learning_rate": 3.248499293296012e-06, "loss": 0.8595, "step": 67920 }, { "epoch": 5.65, "learning_rate": 3.2483884377684782e-06, "loss": 0.8011, "step": 67930 }, { "epoch": 5.65, "learning_rate": 3.2482775822409445e-06, "loss": 0.7657, "step": 67940 }, { "epoch": 5.65, "learning_rate": 3.2481667267134104e-06, "loss": 0.8148, "step": 67950 }, { "epoch": 5.65, "learning_rate": 3.248055871185877e-06, "loss": 0.8568, "step": 67960 }, { "epoch": 5.65, "learning_rate": 3.247945015658343e-06, "loss": 0.8452, "step": 67970 }, { "epoch": 5.65, "learning_rate": 3.2478341601308093e-06, "loss": 0.8385, "step": 67980 }, { "epoch": 5.65, "learning_rate": 3.2477233046032756e-06, "loss": 0.8208, "step": 67990 }, { "epoch": 5.65, "learning_rate": 3.247612449075742e-06, "loss": 0.7577, "step": 68000 }, { "epoch": 5.65, "learning_rate": 3.2475015935482078e-06, "loss": 0.8585, "step": 68010 }, { "epoch": 5.65, "learning_rate": 3.2473907380206745e-06, "loss": 0.8249, "step": 68020 }, { "epoch": 5.65, "learning_rate": 3.2472798824931408e-06, "loss": 0.7842, "step": 68030 }, { "epoch": 5.66, "learning_rate": 3.247169026965607e-06, "loss": 0.7965, "step": 68040 }, { "epoch": 5.66, "learning_rate": 3.2470581714380734e-06, "loss": 0.8271, "step": 68050 }, { "epoch": 5.66, "learning_rate": 3.2469473159105392e-06, "loss": 0.8511, "step": 68060 }, { "epoch": 5.66, "learning_rate": 3.246836460383006e-06, "loss": 0.7861, "step": 68070 }, { "epoch": 5.66, "learning_rate": 3.246725604855472e-06, "loss": 0.7542, "step": 68080 }, { "epoch": 5.66, "learning_rate": 3.246614749327938e-06, "loss": 0.7773, "step": 68090 }, { "epoch": 5.66, "learning_rate": 3.2465038938004044e-06, "loss": 0.8117, "step": 68100 }, { "epoch": 5.66, "learning_rate": 3.2463930382728707e-06, "loss": 0.9041, "step": 68110 }, { "epoch": 5.66, "learning_rate": 3.246282182745337e-06, "loss": 0.8055, "step": 68120 }, { "epoch": 5.66, "learning_rate": 3.2461713272178033e-06, "loss": 0.8083, "step": 68130 }, { "epoch": 5.66, "learning_rate": 3.246060471690269e-06, "loss": 0.803, "step": 68140 }, { "epoch": 5.66, "learning_rate": 3.245949616162736e-06, "loss": 0.7118, "step": 68150 }, { "epoch": 5.67, "learning_rate": 3.245838760635202e-06, "loss": 0.8213, "step": 68160 }, { "epoch": 5.67, "learning_rate": 3.245727905107668e-06, "loss": 0.8742, "step": 68170 }, { "epoch": 5.67, "learning_rate": 3.2456170495801348e-06, "loss": 0.7981, "step": 68180 }, { "epoch": 5.67, "learning_rate": 3.2455061940526007e-06, "loss": 0.8276, "step": 68190 }, { "epoch": 5.67, "learning_rate": 3.2453953385250674e-06, "loss": 0.8301, "step": 68200 }, { "epoch": 5.67, "learning_rate": 3.2452844829975332e-06, "loss": 0.7953, "step": 68210 }, { "epoch": 5.67, "learning_rate": 3.2451736274699995e-06, "loss": 0.8419, "step": 68220 }, { "epoch": 5.67, "learning_rate": 3.245062771942466e-06, "loss": 0.8212, "step": 68230 }, { "epoch": 5.67, "learning_rate": 3.244951916414932e-06, "loss": 0.8215, "step": 68240 }, { "epoch": 5.67, "learning_rate": 3.244841060887398e-06, "loss": 0.7174, "step": 68250 }, { "epoch": 5.67, "learning_rate": 3.2447302053598647e-06, "loss": 0.8367, "step": 68260 }, { "epoch": 5.67, "learning_rate": 3.2446193498323306e-06, "loss": 0.7946, "step": 68270 }, { "epoch": 5.68, "learning_rate": 3.2445084943047973e-06, "loss": 0.7932, "step": 68280 }, { "epoch": 5.68, "learning_rate": 3.2443976387772636e-06, "loss": 0.8255, "step": 68290 }, { "epoch": 5.68, "learning_rate": 3.2442867832497295e-06, "loss": 0.8517, "step": 68300 }, { "epoch": 5.68, "learning_rate": 3.244175927722196e-06, "loss": 0.7912, "step": 68310 }, { "epoch": 5.68, "learning_rate": 3.244065072194662e-06, "loss": 0.8932, "step": 68320 }, { "epoch": 5.68, "learning_rate": 3.2439542166671284e-06, "loss": 0.7479, "step": 68330 }, { "epoch": 5.68, "learning_rate": 3.2438433611395947e-06, "loss": 0.8814, "step": 68340 }, { "epoch": 5.68, "learning_rate": 3.243732505612061e-06, "loss": 0.8186, "step": 68350 }, { "epoch": 5.68, "learning_rate": 3.243621650084527e-06, "loss": 0.9039, "step": 68360 }, { "epoch": 5.68, "learning_rate": 3.2435107945569935e-06, "loss": 0.824, "step": 68370 }, { "epoch": 5.68, "learning_rate": 3.2433999390294594e-06, "loss": 0.775, "step": 68380 }, { "epoch": 5.68, "learning_rate": 3.243289083501926e-06, "loss": 0.7678, "step": 68390 }, { "epoch": 5.69, "learning_rate": 3.2431782279743924e-06, "loss": 0.816, "step": 68400 }, { "epoch": 5.69, "learning_rate": 3.2430673724468583e-06, "loss": 0.8436, "step": 68410 }, { "epoch": 5.69, "learning_rate": 3.242956516919325e-06, "loss": 0.8027, "step": 68420 }, { "epoch": 5.69, "learning_rate": 3.242845661391791e-06, "loss": 0.7933, "step": 68430 }, { "epoch": 5.69, "learning_rate": 3.2427348058642576e-06, "loss": 0.8279, "step": 68440 }, { "epoch": 5.69, "learning_rate": 3.2426239503367235e-06, "loss": 0.812, "step": 68450 }, { "epoch": 5.69, "learning_rate": 3.2425130948091898e-06, "loss": 0.8491, "step": 68460 }, { "epoch": 5.69, "learning_rate": 3.242402239281656e-06, "loss": 0.8332, "step": 68470 }, { "epoch": 5.69, "learning_rate": 3.2422913837541224e-06, "loss": 0.8002, "step": 68480 }, { "epoch": 5.69, "learning_rate": 3.2421805282265882e-06, "loss": 0.794, "step": 68490 }, { "epoch": 5.69, "learning_rate": 3.242069672699055e-06, "loss": 0.8203, "step": 68500 }, { "epoch": 5.69, "learning_rate": 3.241958817171521e-06, "loss": 0.8286, "step": 68510 }, { "epoch": 5.7, "learning_rate": 3.241847961643987e-06, "loss": 0.8565, "step": 68520 }, { "epoch": 5.7, "learning_rate": 3.241737106116454e-06, "loss": 0.8, "step": 68530 }, { "epoch": 5.7, "learning_rate": 3.2416262505889197e-06, "loss": 0.8116, "step": 68540 }, { "epoch": 5.7, "learning_rate": 3.2415153950613864e-06, "loss": 0.8342, "step": 68550 }, { "epoch": 5.7, "learning_rate": 3.2414045395338523e-06, "loss": 0.8533, "step": 68560 }, { "epoch": 5.7, "learning_rate": 3.2412936840063186e-06, "loss": 0.8705, "step": 68570 }, { "epoch": 5.7, "learning_rate": 3.241182828478785e-06, "loss": 0.7138, "step": 68580 }, { "epoch": 5.7, "learning_rate": 3.241071972951251e-06, "loss": 0.7921, "step": 68590 }, { "epoch": 5.7, "learning_rate": 3.240961117423717e-06, "loss": 0.7607, "step": 68600 }, { "epoch": 5.7, "learning_rate": 3.2408502618961838e-06, "loss": 0.8537, "step": 68610 }, { "epoch": 5.7, "learning_rate": 3.2407394063686497e-06, "loss": 0.8005, "step": 68620 }, { "epoch": 5.7, "learning_rate": 3.2406285508411164e-06, "loss": 0.8137, "step": 68630 }, { "epoch": 5.71, "learning_rate": 3.2405176953135822e-06, "loss": 0.8001, "step": 68640 }, { "epoch": 5.71, "learning_rate": 3.2404068397860485e-06, "loss": 0.8209, "step": 68650 }, { "epoch": 5.71, "learning_rate": 3.2402959842585153e-06, "loss": 0.7925, "step": 68660 }, { "epoch": 5.71, "learning_rate": 3.240185128730981e-06, "loss": 0.819, "step": 68670 }, { "epoch": 5.71, "learning_rate": 3.2400742732034474e-06, "loss": 0.8137, "step": 68680 }, { "epoch": 5.71, "learning_rate": 3.2399634176759137e-06, "loss": 0.7483, "step": 68690 }, { "epoch": 5.71, "learning_rate": 3.23985256214838e-06, "loss": 0.822, "step": 68700 }, { "epoch": 5.71, "learning_rate": 3.2397417066208463e-06, "loss": 0.8352, "step": 68710 }, { "epoch": 5.71, "learning_rate": 3.2396308510933126e-06, "loss": 0.8676, "step": 68720 }, { "epoch": 5.71, "learning_rate": 3.2395199955657785e-06, "loss": 0.8165, "step": 68730 }, { "epoch": 5.71, "learning_rate": 3.239409140038245e-06, "loss": 0.8295, "step": 68740 }, { "epoch": 5.71, "learning_rate": 3.239298284510711e-06, "loss": 0.7993, "step": 68750 }, { "epoch": 5.72, "learning_rate": 3.2391874289831774e-06, "loss": 0.8114, "step": 68760 }, { "epoch": 5.72, "learning_rate": 3.239076573455644e-06, "loss": 0.7977, "step": 68770 }, { "epoch": 5.72, "learning_rate": 3.23896571792811e-06, "loss": 0.8024, "step": 68780 }, { "epoch": 5.72, "learning_rate": 3.2388548624005767e-06, "loss": 0.8511, "step": 68790 }, { "epoch": 5.72, "learning_rate": 3.2387440068730426e-06, "loss": 0.8806, "step": 68800 }, { "epoch": 5.72, "learning_rate": 3.238633151345509e-06, "loss": 0.9154, "step": 68810 }, { "epoch": 5.72, "learning_rate": 3.238522295817975e-06, "loss": 0.872, "step": 68820 }, { "epoch": 5.72, "learning_rate": 3.2384114402904414e-06, "loss": 0.845, "step": 68830 }, { "epoch": 5.72, "learning_rate": 3.2383005847629073e-06, "loss": 0.8854, "step": 68840 }, { "epoch": 5.72, "learning_rate": 3.238189729235374e-06, "loss": 0.8248, "step": 68850 }, { "epoch": 5.72, "learning_rate": 3.23807887370784e-06, "loss": 0.8936, "step": 68860 }, { "epoch": 5.72, "learning_rate": 3.237968018180306e-06, "loss": 0.9011, "step": 68870 }, { "epoch": 5.73, "learning_rate": 3.2378571626527725e-06, "loss": 0.855, "step": 68880 }, { "epoch": 5.73, "learning_rate": 3.2377463071252388e-06, "loss": 0.7644, "step": 68890 }, { "epoch": 5.73, "learning_rate": 3.2376354515977055e-06, "loss": 0.8423, "step": 68900 }, { "epoch": 5.73, "learning_rate": 3.2375245960701714e-06, "loss": 0.879, "step": 68910 }, { "epoch": 5.73, "learning_rate": 3.2374137405426377e-06, "loss": 0.8106, "step": 68920 }, { "epoch": 5.73, "learning_rate": 3.237302885015104e-06, "loss": 0.8558, "step": 68930 }, { "epoch": 5.73, "learning_rate": 3.2371920294875703e-06, "loss": 0.8772, "step": 68940 }, { "epoch": 5.73, "learning_rate": 3.237081173960036e-06, "loss": 0.8276, "step": 68950 }, { "epoch": 5.73, "learning_rate": 3.236970318432503e-06, "loss": 0.8786, "step": 68960 }, { "epoch": 5.73, "learning_rate": 3.2368594629049687e-06, "loss": 0.8165, "step": 68970 }, { "epoch": 5.73, "learning_rate": 3.2367486073774354e-06, "loss": 0.8627, "step": 68980 }, { "epoch": 5.73, "learning_rate": 3.2366377518499013e-06, "loss": 0.8279, "step": 68990 }, { "epoch": 5.74, "learning_rate": 3.2365268963223676e-06, "loss": 0.7712, "step": 69000 }, { "epoch": 5.74, "learning_rate": 3.236416040794834e-06, "loss": 0.8905, "step": 69010 }, { "epoch": 5.74, "learning_rate": 3.2363051852673e-06, "loss": 0.8664, "step": 69020 }, { "epoch": 5.74, "learning_rate": 3.2361943297397665e-06, "loss": 0.8283, "step": 69030 }, { "epoch": 5.74, "learning_rate": 3.236083474212233e-06, "loss": 0.8719, "step": 69040 }, { "epoch": 5.74, "learning_rate": 3.235972618684699e-06, "loss": 0.743, "step": 69050 }, { "epoch": 5.74, "learning_rate": 3.2358617631571654e-06, "loss": 0.8925, "step": 69060 }, { "epoch": 5.74, "learning_rate": 3.2357509076296317e-06, "loss": 0.769, "step": 69070 }, { "epoch": 5.74, "learning_rate": 3.2356400521020976e-06, "loss": 0.8564, "step": 69080 }, { "epoch": 5.74, "learning_rate": 3.2355291965745643e-06, "loss": 0.8214, "step": 69090 }, { "epoch": 5.74, "learning_rate": 3.23541834104703e-06, "loss": 0.8421, "step": 69100 }, { "epoch": 5.74, "learning_rate": 3.2353074855194964e-06, "loss": 0.8145, "step": 69110 }, { "epoch": 5.75, "learning_rate": 3.2351966299919627e-06, "loss": 0.8355, "step": 69120 }, { "epoch": 5.75, "learning_rate": 3.235085774464429e-06, "loss": 0.7675, "step": 69130 }, { "epoch": 5.75, "learning_rate": 3.2349749189368957e-06, "loss": 0.8509, "step": 69140 }, { "epoch": 5.75, "learning_rate": 3.2348640634093616e-06, "loss": 0.7707, "step": 69150 }, { "epoch": 5.75, "learning_rate": 3.234753207881828e-06, "loss": 0.868, "step": 69160 }, { "epoch": 5.75, "learning_rate": 3.234642352354294e-06, "loss": 0.7764, "step": 69170 }, { "epoch": 5.75, "learning_rate": 3.2345314968267605e-06, "loss": 0.8262, "step": 69180 }, { "epoch": 5.75, "learning_rate": 3.2344206412992264e-06, "loss": 0.7981, "step": 69190 }, { "epoch": 5.75, "learning_rate": 3.234309785771693e-06, "loss": 0.8453, "step": 69200 }, { "epoch": 5.75, "learning_rate": 3.234198930244159e-06, "loss": 0.8022, "step": 69210 }, { "epoch": 5.75, "learning_rate": 3.2340880747166257e-06, "loss": 0.7765, "step": 69220 }, { "epoch": 5.75, "learning_rate": 3.2339772191890916e-06, "loss": 0.7745, "step": 69230 }, { "epoch": 5.76, "learning_rate": 3.233866363661558e-06, "loss": 0.8514, "step": 69240 }, { "epoch": 5.76, "learning_rate": 3.233755508134024e-06, "loss": 0.7743, "step": 69250 }, { "epoch": 5.76, "learning_rate": 3.2336446526064904e-06, "loss": 0.9058, "step": 69260 }, { "epoch": 5.76, "learning_rate": 3.2335337970789567e-06, "loss": 0.8827, "step": 69270 }, { "epoch": 5.76, "learning_rate": 3.233422941551423e-06, "loss": 0.8348, "step": 69280 }, { "epoch": 5.76, "learning_rate": 3.2333120860238893e-06, "loss": 0.8459, "step": 69290 }, { "epoch": 5.76, "learning_rate": 3.233201230496355e-06, "loss": 0.8138, "step": 69300 }, { "epoch": 5.76, "learning_rate": 3.233090374968822e-06, "loss": 0.838, "step": 69310 }, { "epoch": 5.76, "learning_rate": 3.232979519441288e-06, "loss": 0.7936, "step": 69320 }, { "epoch": 5.76, "learning_rate": 3.2328686639137545e-06, "loss": 0.8669, "step": 69330 }, { "epoch": 5.76, "learning_rate": 3.2327578083862204e-06, "loss": 0.8156, "step": 69340 }, { "epoch": 5.76, "learning_rate": 3.2326469528586867e-06, "loss": 0.7923, "step": 69350 }, { "epoch": 5.77, "learning_rate": 3.232536097331153e-06, "loss": 0.9244, "step": 69360 }, { "epoch": 5.77, "learning_rate": 3.2324252418036193e-06, "loss": 0.7328, "step": 69370 }, { "epoch": 5.77, "learning_rate": 3.232314386276085e-06, "loss": 0.8668, "step": 69380 }, { "epoch": 5.77, "learning_rate": 3.232203530748552e-06, "loss": 0.8552, "step": 69390 }, { "epoch": 5.77, "learning_rate": 3.232092675221018e-06, "loss": 0.8189, "step": 69400 }, { "epoch": 5.77, "learning_rate": 3.2319818196934844e-06, "loss": 0.8718, "step": 69410 }, { "epoch": 5.77, "learning_rate": 3.2318709641659507e-06, "loss": 0.7886, "step": 69420 }, { "epoch": 5.77, "learning_rate": 3.2317601086384166e-06, "loss": 0.7628, "step": 69430 }, { "epoch": 5.77, "learning_rate": 3.2316492531108833e-06, "loss": 0.8351, "step": 69440 }, { "epoch": 5.77, "learning_rate": 3.231538397583349e-06, "loss": 0.7763, "step": 69450 }, { "epoch": 5.77, "learning_rate": 3.2314275420558155e-06, "loss": 0.8497, "step": 69460 }, { "epoch": 5.77, "learning_rate": 3.231316686528282e-06, "loss": 0.8584, "step": 69470 }, { "epoch": 5.78, "learning_rate": 3.231205831000748e-06, "loss": 0.8432, "step": 69480 }, { "epoch": 5.78, "learning_rate": 3.2310949754732144e-06, "loss": 0.8545, "step": 69490 }, { "epoch": 5.78, "learning_rate": 3.2309841199456807e-06, "loss": 0.7811, "step": 69500 }, { "epoch": 5.78, "learning_rate": 3.230873264418147e-06, "loss": 0.8995, "step": 69510 }, { "epoch": 5.78, "learning_rate": 3.2307624088906133e-06, "loss": 0.8292, "step": 69520 }, { "epoch": 5.78, "learning_rate": 3.2306515533630796e-06, "loss": 0.7989, "step": 69530 }, { "epoch": 5.78, "learning_rate": 3.2305406978355454e-06, "loss": 0.8949, "step": 69540 }, { "epoch": 5.78, "learning_rate": 3.230429842308012e-06, "loss": 0.7839, "step": 69550 }, { "epoch": 5.78, "learning_rate": 3.230318986780478e-06, "loss": 0.8393, "step": 69560 }, { "epoch": 5.78, "learning_rate": 3.2302081312529448e-06, "loss": 0.779, "step": 69570 }, { "epoch": 5.78, "learning_rate": 3.2300972757254106e-06, "loss": 0.792, "step": 69580 }, { "epoch": 5.78, "learning_rate": 3.229986420197877e-06, "loss": 0.8119, "step": 69590 }, { "epoch": 5.79, "learning_rate": 3.2298755646703432e-06, "loss": 0.8463, "step": 69600 }, { "epoch": 5.79, "learning_rate": 3.2297647091428095e-06, "loss": 0.8732, "step": 69610 }, { "epoch": 5.79, "learning_rate": 3.2296538536152754e-06, "loss": 0.7977, "step": 69620 }, { "epoch": 5.79, "learning_rate": 3.229542998087742e-06, "loss": 0.8202, "step": 69630 }, { "epoch": 5.79, "learning_rate": 3.2294321425602084e-06, "loss": 0.8591, "step": 69640 }, { "epoch": 5.79, "learning_rate": 3.2293212870326747e-06, "loss": 0.8251, "step": 69650 }, { "epoch": 5.79, "learning_rate": 3.229210431505141e-06, "loss": 0.8325, "step": 69660 }, { "epoch": 5.79, "learning_rate": 3.229099575977607e-06, "loss": 0.811, "step": 69670 }, { "epoch": 5.79, "learning_rate": 3.2289887204500736e-06, "loss": 0.8089, "step": 69680 }, { "epoch": 5.79, "learning_rate": 3.2288778649225394e-06, "loss": 0.813, "step": 69690 }, { "epoch": 5.79, "learning_rate": 3.228778094947759e-06, "loss": 0.9282, "step": 69700 }, { "epoch": 5.79, "learning_rate": 3.2286672394202253e-06, "loss": 0.8927, "step": 69710 }, { "epoch": 5.8, "learning_rate": 3.228556383892692e-06, "loss": 0.8157, "step": 69720 }, { "epoch": 5.8, "learning_rate": 3.228445528365158e-06, "loss": 0.8163, "step": 69730 }, { "epoch": 5.8, "learning_rate": 3.2283346728376246e-06, "loss": 0.8333, "step": 69740 }, { "epoch": 5.8, "learning_rate": 3.2282238173100905e-06, "loss": 0.8612, "step": 69750 }, { "epoch": 5.8, "learning_rate": 3.2281129617825568e-06, "loss": 0.8746, "step": 69760 }, { "epoch": 5.8, "learning_rate": 3.228002106255023e-06, "loss": 0.8429, "step": 69770 }, { "epoch": 5.8, "learning_rate": 3.2278912507274894e-06, "loss": 0.8522, "step": 69780 }, { "epoch": 5.8, "learning_rate": 3.2277803951999552e-06, "loss": 0.8401, "step": 69790 }, { "epoch": 5.8, "learning_rate": 3.227669539672422e-06, "loss": 0.8832, "step": 69800 }, { "epoch": 5.8, "learning_rate": 3.227558684144888e-06, "loss": 0.8411, "step": 69810 }, { "epoch": 5.8, "learning_rate": 3.227447828617354e-06, "loss": 0.8678, "step": 69820 }, { "epoch": 5.8, "learning_rate": 3.2273369730898204e-06, "loss": 0.811, "step": 69830 }, { "epoch": 5.81, "learning_rate": 3.2272261175622867e-06, "loss": 0.821, "step": 69840 }, { "epoch": 5.81, "learning_rate": 3.2271152620347534e-06, "loss": 0.8518, "step": 69850 }, { "epoch": 5.81, "learning_rate": 3.2270044065072193e-06, "loss": 0.8553, "step": 69860 }, { "epoch": 5.81, "learning_rate": 3.2268935509796856e-06, "loss": 0.8861, "step": 69870 }, { "epoch": 5.81, "learning_rate": 3.226782695452152e-06, "loss": 0.7697, "step": 69880 }, { "epoch": 5.81, "learning_rate": 3.226671839924618e-06, "loss": 0.8498, "step": 69890 }, { "epoch": 5.81, "learning_rate": 3.226560984397084e-06, "loss": 0.7908, "step": 69900 }, { "epoch": 5.81, "learning_rate": 3.2264501288695508e-06, "loss": 0.8056, "step": 69910 }, { "epoch": 5.81, "learning_rate": 3.2263392733420166e-06, "loss": 0.8816, "step": 69920 }, { "epoch": 5.81, "learning_rate": 3.2262284178144834e-06, "loss": 0.8258, "step": 69930 }, { "epoch": 5.81, "learning_rate": 3.2261175622869492e-06, "loss": 0.8182, "step": 69940 }, { "epoch": 5.81, "learning_rate": 3.2260067067594155e-06, "loss": 0.802, "step": 69950 }, { "epoch": 5.81, "learning_rate": 3.225895851231882e-06, "loss": 0.8425, "step": 69960 }, { "epoch": 5.82, "learning_rate": 3.225784995704348e-06, "loss": 0.806, "step": 69970 }, { "epoch": 5.82, "learning_rate": 3.2256741401768144e-06, "loss": 0.8021, "step": 69980 }, { "epoch": 5.82, "learning_rate": 3.2255632846492807e-06, "loss": 0.8915, "step": 69990 }, { "epoch": 5.82, "learning_rate": 3.225452429121747e-06, "loss": 0.8732, "step": 70000 }, { "epoch": 5.82, "learning_rate": 3.2253415735942133e-06, "loss": 0.8476, "step": 70010 }, { "epoch": 5.82, "learning_rate": 3.2252307180666796e-06, "loss": 0.7541, "step": 70020 }, { "epoch": 5.82, "learning_rate": 3.2251198625391455e-06, "loss": 0.8599, "step": 70030 }, { "epoch": 5.82, "learning_rate": 3.225009007011612e-06, "loss": 0.7912, "step": 70040 }, { "epoch": 5.82, "learning_rate": 3.224898151484078e-06, "loss": 0.7868, "step": 70050 }, { "epoch": 5.82, "learning_rate": 3.2247872959565443e-06, "loss": 0.854, "step": 70060 }, { "epoch": 5.82, "learning_rate": 3.2246764404290106e-06, "loss": 0.8233, "step": 70070 }, { "epoch": 5.82, "learning_rate": 3.224565584901477e-06, "loss": 0.7995, "step": 70080 }, { "epoch": 5.83, "learning_rate": 3.2244547293739437e-06, "loss": 0.8406, "step": 70090 }, { "epoch": 5.83, "learning_rate": 3.2243438738464095e-06, "loss": 0.8143, "step": 70100 }, { "epoch": 5.83, "learning_rate": 3.224233018318876e-06, "loss": 0.8355, "step": 70110 }, { "epoch": 5.83, "learning_rate": 3.224122162791342e-06, "loss": 0.7996, "step": 70120 }, { "epoch": 5.83, "learning_rate": 3.2240113072638084e-06, "loss": 0.7966, "step": 70130 }, { "epoch": 5.83, "learning_rate": 3.2239004517362743e-06, "loss": 0.8085, "step": 70140 }, { "epoch": 5.83, "learning_rate": 3.223789596208741e-06, "loss": 0.8091, "step": 70150 }, { "epoch": 5.83, "learning_rate": 3.223678740681207e-06, "loss": 0.8794, "step": 70160 }, { "epoch": 5.83, "learning_rate": 3.2235678851536736e-06, "loss": 0.8227, "step": 70170 }, { "epoch": 5.83, "learning_rate": 3.2234570296261395e-06, "loss": 0.7982, "step": 70180 }, { "epoch": 5.83, "learning_rate": 3.2233461740986058e-06, "loss": 0.8123, "step": 70190 }, { "epoch": 5.83, "learning_rate": 3.223235318571072e-06, "loss": 0.7905, "step": 70200 }, { "epoch": 5.84, "learning_rate": 3.2231244630435384e-06, "loss": 0.8359, "step": 70210 }, { "epoch": 5.84, "learning_rate": 3.2230136075160047e-06, "loss": 0.8596, "step": 70220 }, { "epoch": 5.84, "learning_rate": 3.222902751988471e-06, "loss": 0.8736, "step": 70230 }, { "epoch": 5.84, "learning_rate": 3.2227918964609372e-06, "loss": 0.8528, "step": 70240 }, { "epoch": 5.84, "learning_rate": 3.222681040933403e-06, "loss": 0.8157, "step": 70250 }, { "epoch": 5.84, "learning_rate": 3.22257018540587e-06, "loss": 0.8006, "step": 70260 }, { "epoch": 5.84, "learning_rate": 3.2224593298783357e-06, "loss": 0.8297, "step": 70270 }, { "epoch": 5.84, "learning_rate": 3.2223484743508024e-06, "loss": 0.8341, "step": 70280 }, { "epoch": 5.84, "learning_rate": 3.2222376188232683e-06, "loss": 0.8049, "step": 70290 }, { "epoch": 5.84, "learning_rate": 3.2221267632957346e-06, "loss": 0.792, "step": 70300 }, { "epoch": 5.84, "learning_rate": 3.222015907768201e-06, "loss": 0.8159, "step": 70310 }, { "epoch": 5.84, "learning_rate": 3.221905052240667e-06, "loss": 0.8352, "step": 70320 }, { "epoch": 5.85, "learning_rate": 3.2217941967131335e-06, "loss": 0.818, "step": 70330 }, { "epoch": 5.85, "learning_rate": 3.2216833411855998e-06, "loss": 0.8497, "step": 70340 }, { "epoch": 5.85, "learning_rate": 3.221572485658066e-06, "loss": 0.7612, "step": 70350 }, { "epoch": 5.85, "learning_rate": 3.2214616301305324e-06, "loss": 0.8413, "step": 70360 }, { "epoch": 5.85, "learning_rate": 3.2213507746029987e-06, "loss": 0.8602, "step": 70370 }, { "epoch": 5.85, "learning_rate": 3.2212399190754645e-06, "loss": 0.7511, "step": 70380 }, { "epoch": 5.85, "learning_rate": 3.2211290635479312e-06, "loss": 0.8226, "step": 70390 }, { "epoch": 5.85, "learning_rate": 3.221018208020397e-06, "loss": 0.872, "step": 70400 }, { "epoch": 5.85, "learning_rate": 3.2209073524928634e-06, "loss": 0.8222, "step": 70410 }, { "epoch": 5.85, "learning_rate": 3.2207964969653297e-06, "loss": 0.8485, "step": 70420 }, { "epoch": 5.85, "learning_rate": 3.220685641437796e-06, "loss": 0.857, "step": 70430 }, { "epoch": 5.85, "learning_rate": 3.2205747859102623e-06, "loss": 0.8644, "step": 70440 }, { "epoch": 5.86, "learning_rate": 3.2204639303827286e-06, "loss": 0.7468, "step": 70450 }, { "epoch": 5.86, "learning_rate": 3.220353074855195e-06, "loss": 0.8528, "step": 70460 }, { "epoch": 5.86, "learning_rate": 3.220242219327661e-06, "loss": 0.904, "step": 70470 }, { "epoch": 5.86, "learning_rate": 3.2201313638001275e-06, "loss": 0.7455, "step": 70480 }, { "epoch": 5.86, "learning_rate": 3.2200205082725934e-06, "loss": 0.7433, "step": 70490 }, { "epoch": 5.86, "learning_rate": 3.21990965274506e-06, "loss": 0.8292, "step": 70500 }, { "epoch": 5.86, "learning_rate": 3.219798797217526e-06, "loss": 0.856, "step": 70510 }, { "epoch": 5.86, "learning_rate": 3.2196879416899927e-06, "loss": 0.8353, "step": 70520 }, { "epoch": 5.86, "learning_rate": 3.2195770861624585e-06, "loss": 0.8603, "step": 70530 }, { "epoch": 5.86, "learning_rate": 3.219466230634925e-06, "loss": 0.8404, "step": 70540 }, { "epoch": 5.86, "learning_rate": 3.219355375107391e-06, "loss": 0.7736, "step": 70550 }, { "epoch": 5.86, "learning_rate": 3.2192445195798574e-06, "loss": 0.8344, "step": 70560 }, { "epoch": 5.87, "learning_rate": 3.2191336640523233e-06, "loss": 0.8634, "step": 70570 }, { "epoch": 5.87, "learning_rate": 3.21902280852479e-06, "loss": 0.7885, "step": 70580 }, { "epoch": 5.87, "learning_rate": 3.2189119529972563e-06, "loss": 0.8638, "step": 70590 }, { "epoch": 5.87, "learning_rate": 3.2188010974697226e-06, "loss": 0.8229, "step": 70600 }, { "epoch": 5.87, "learning_rate": 3.218690241942189e-06, "loss": 0.8905, "step": 70610 }, { "epoch": 5.87, "learning_rate": 3.2185793864146548e-06, "loss": 0.8168, "step": 70620 }, { "epoch": 5.87, "learning_rate": 3.2184685308871215e-06, "loss": 0.8111, "step": 70630 }, { "epoch": 5.87, "learning_rate": 3.2183576753595874e-06, "loss": 0.8188, "step": 70640 }, { "epoch": 5.87, "learning_rate": 3.2182468198320537e-06, "loss": 0.7955, "step": 70650 }, { "epoch": 5.87, "learning_rate": 3.21813596430452e-06, "loss": 0.8037, "step": 70660 }, { "epoch": 5.87, "learning_rate": 3.2180251087769862e-06, "loss": 0.7534, "step": 70670 }, { "epoch": 5.87, "learning_rate": 3.217914253249452e-06, "loss": 0.8349, "step": 70680 }, { "epoch": 5.88, "learning_rate": 3.217803397721919e-06, "loss": 0.7994, "step": 70690 }, { "epoch": 5.88, "learning_rate": 3.217692542194385e-06, "loss": 0.8104, "step": 70700 }, { "epoch": 5.88, "learning_rate": 3.2175816866668514e-06, "loss": 0.7796, "step": 70710 }, { "epoch": 5.88, "learning_rate": 3.2174708311393177e-06, "loss": 0.826, "step": 70720 }, { "epoch": 5.88, "learning_rate": 3.2173599756117836e-06, "loss": 0.8296, "step": 70730 }, { "epoch": 5.88, "learning_rate": 3.2172491200842503e-06, "loss": 0.8814, "step": 70740 }, { "epoch": 5.88, "learning_rate": 3.217138264556716e-06, "loss": 0.8495, "step": 70750 }, { "epoch": 5.88, "learning_rate": 3.2170274090291825e-06, "loss": 0.8642, "step": 70760 }, { "epoch": 5.88, "learning_rate": 3.2169165535016488e-06, "loss": 0.8087, "step": 70770 }, { "epoch": 5.88, "learning_rate": 3.216805697974115e-06, "loss": 0.8118, "step": 70780 }, { "epoch": 5.88, "learning_rate": 3.2166948424465814e-06, "loss": 0.8111, "step": 70790 }, { "epoch": 5.88, "learning_rate": 3.2165839869190477e-06, "loss": 0.8162, "step": 70800 }, { "epoch": 5.89, "learning_rate": 3.2164731313915135e-06, "loss": 0.8267, "step": 70810 }, { "epoch": 5.89, "learning_rate": 3.2163622758639803e-06, "loss": 0.842, "step": 70820 }, { "epoch": 5.89, "learning_rate": 3.2162514203364465e-06, "loss": 0.8498, "step": 70830 }, { "epoch": 5.89, "learning_rate": 3.2161405648089124e-06, "loss": 0.8683, "step": 70840 }, { "epoch": 5.89, "learning_rate": 3.216029709281379e-06, "loss": 0.8698, "step": 70850 }, { "epoch": 5.89, "learning_rate": 3.215918853753845e-06, "loss": 0.8198, "step": 70860 }, { "epoch": 5.89, "learning_rate": 3.2158079982263117e-06, "loss": 0.8354, "step": 70870 }, { "epoch": 5.89, "learning_rate": 3.2156971426987776e-06, "loss": 0.7399, "step": 70880 }, { "epoch": 5.89, "learning_rate": 3.215586287171244e-06, "loss": 0.7953, "step": 70890 }, { "epoch": 5.89, "learning_rate": 3.21547543164371e-06, "loss": 0.8353, "step": 70900 }, { "epoch": 5.89, "learning_rate": 3.2153645761161765e-06, "loss": 0.8505, "step": 70910 }, { "epoch": 5.89, "learning_rate": 3.2152537205886424e-06, "loss": 0.77, "step": 70920 }, { "epoch": 5.9, "learning_rate": 3.215142865061109e-06, "loss": 0.7756, "step": 70930 }, { "epoch": 5.9, "learning_rate": 3.215032009533575e-06, "loss": 0.7401, "step": 70940 }, { "epoch": 5.9, "learning_rate": 3.2149211540060417e-06, "loss": 0.7924, "step": 70950 }, { "epoch": 5.9, "learning_rate": 3.214810298478508e-06, "loss": 0.8088, "step": 70960 }, { "epoch": 5.9, "learning_rate": 3.214699442950974e-06, "loss": 0.8222, "step": 70970 }, { "epoch": 5.9, "learning_rate": 3.2145885874234406e-06, "loss": 0.8192, "step": 70980 }, { "epoch": 5.9, "learning_rate": 3.2144777318959064e-06, "loss": 0.8256, "step": 70990 }, { "epoch": 5.9, "learning_rate": 3.2143668763683727e-06, "loss": 0.8375, "step": 71000 }, { "epoch": 5.9, "learning_rate": 3.214256020840839e-06, "loss": 0.8557, "step": 71010 }, { "epoch": 5.9, "learning_rate": 3.2141451653133053e-06, "loss": 0.7847, "step": 71020 }, { "epoch": 5.9, "learning_rate": 3.214034309785771e-06, "loss": 0.8423, "step": 71030 }, { "epoch": 5.9, "learning_rate": 3.213923454258238e-06, "loss": 0.749, "step": 71040 }, { "epoch": 5.91, "learning_rate": 3.2138125987307038e-06, "loss": 0.8214, "step": 71050 }, { "epoch": 5.91, "learning_rate": 3.2137017432031705e-06, "loss": 0.7981, "step": 71060 }, { "epoch": 5.91, "learning_rate": 3.213590887675637e-06, "loss": 0.8398, "step": 71070 }, { "epoch": 5.91, "learning_rate": 3.2134800321481027e-06, "loss": 0.8379, "step": 71080 }, { "epoch": 5.91, "learning_rate": 3.2133691766205694e-06, "loss": 0.7761, "step": 71090 }, { "epoch": 5.91, "learning_rate": 3.2132583210930353e-06, "loss": 0.7984, "step": 71100 }, { "epoch": 5.91, "learning_rate": 3.2131474655655015e-06, "loss": 0.7958, "step": 71110 }, { "epoch": 5.91, "learning_rate": 3.213036610037968e-06, "loss": 0.8742, "step": 71120 }, { "epoch": 5.91, "learning_rate": 3.212925754510434e-06, "loss": 0.8451, "step": 71130 }, { "epoch": 5.91, "learning_rate": 3.2128148989829004e-06, "loss": 0.8883, "step": 71140 }, { "epoch": 5.91, "learning_rate": 3.2127040434553667e-06, "loss": 0.8104, "step": 71150 }, { "epoch": 5.91, "learning_rate": 3.2125931879278326e-06, "loss": 0.8906, "step": 71160 }, { "epoch": 5.92, "learning_rate": 3.2124823324002993e-06, "loss": 0.8177, "step": 71170 }, { "epoch": 5.92, "learning_rate": 3.212371476872765e-06, "loss": 0.8124, "step": 71180 }, { "epoch": 5.92, "learning_rate": 3.2122606213452315e-06, "loss": 0.8552, "step": 71190 }, { "epoch": 5.92, "learning_rate": 3.212149765817698e-06, "loss": 0.8835, "step": 71200 }, { "epoch": 5.92, "learning_rate": 3.212038910290164e-06, "loss": 0.8259, "step": 71210 }, { "epoch": 5.92, "learning_rate": 3.211928054762631e-06, "loss": 0.7866, "step": 71220 }, { "epoch": 5.92, "learning_rate": 3.2118171992350967e-06, "loss": 0.8424, "step": 71230 }, { "epoch": 5.92, "learning_rate": 3.211706343707563e-06, "loss": 0.8433, "step": 71240 }, { "epoch": 5.92, "learning_rate": 3.2115954881800293e-06, "loss": 0.8195, "step": 71250 }, { "epoch": 5.92, "learning_rate": 3.2114846326524956e-06, "loss": 0.8132, "step": 71260 }, { "epoch": 5.92, "learning_rate": 3.2113737771249614e-06, "loss": 0.8831, "step": 71270 }, { "epoch": 5.92, "learning_rate": 3.211262921597428e-06, "loss": 0.8077, "step": 71280 }, { "epoch": 5.93, "learning_rate": 3.211152066069894e-06, "loss": 0.8288, "step": 71290 }, { "epoch": 5.93, "learning_rate": 3.2110412105423607e-06, "loss": 0.771, "step": 71300 }, { "epoch": 5.93, "learning_rate": 3.2109303550148266e-06, "loss": 0.8252, "step": 71310 }, { "epoch": 5.93, "learning_rate": 3.210819499487293e-06, "loss": 0.8378, "step": 71320 }, { "epoch": 5.93, "learning_rate": 3.2107086439597596e-06, "loss": 0.8478, "step": 71330 }, { "epoch": 5.93, "learning_rate": 3.2105977884322255e-06, "loss": 0.8414, "step": 71340 }, { "epoch": 5.93, "learning_rate": 3.210486932904692e-06, "loss": 0.8489, "step": 71350 }, { "epoch": 5.93, "learning_rate": 3.210376077377158e-06, "loss": 0.8648, "step": 71360 }, { "epoch": 5.93, "learning_rate": 3.2102652218496244e-06, "loss": 0.8508, "step": 71370 }, { "epoch": 5.93, "learning_rate": 3.2101543663220907e-06, "loss": 0.8344, "step": 71380 }, { "epoch": 5.93, "learning_rate": 3.210043510794557e-06, "loss": 0.8301, "step": 71390 }, { "epoch": 5.93, "learning_rate": 3.209932655267023e-06, "loss": 0.7573, "step": 71400 }, { "epoch": 5.94, "learning_rate": 3.2098217997394896e-06, "loss": 0.8445, "step": 71410 }, { "epoch": 5.94, "learning_rate": 3.2097109442119554e-06, "loss": 0.8136, "step": 71420 }, { "epoch": 5.94, "learning_rate": 3.2096000886844217e-06, "loss": 0.7792, "step": 71430 }, { "epoch": 5.94, "learning_rate": 3.2094892331568884e-06, "loss": 0.8644, "step": 71440 }, { "epoch": 5.94, "learning_rate": 3.2093783776293543e-06, "loss": 0.8126, "step": 71450 }, { "epoch": 5.94, "learning_rate": 3.209267522101821e-06, "loss": 0.7839, "step": 71460 }, { "epoch": 5.94, "learning_rate": 3.209156666574287e-06, "loss": 0.804, "step": 71470 }, { "epoch": 5.94, "learning_rate": 3.209045811046753e-06, "loss": 0.743, "step": 71480 }, { "epoch": 5.94, "learning_rate": 3.2089349555192195e-06, "loss": 0.796, "step": 71490 }, { "epoch": 5.94, "learning_rate": 3.208824099991686e-06, "loss": 0.8296, "step": 71500 }, { "epoch": 5.94, "learning_rate": 3.2087132444641517e-06, "loss": 0.8413, "step": 71510 }, { "epoch": 5.94, "learning_rate": 3.2086023889366184e-06, "loss": 0.7898, "step": 71520 }, { "epoch": 5.95, "learning_rate": 3.2084915334090843e-06, "loss": 0.8227, "step": 71530 }, { "epoch": 5.95, "learning_rate": 3.2083806778815506e-06, "loss": 0.7597, "step": 71540 }, { "epoch": 5.95, "learning_rate": 3.208269822354017e-06, "loss": 0.8548, "step": 71550 }, { "epoch": 5.95, "learning_rate": 3.208158966826483e-06, "loss": 0.8219, "step": 71560 }, { "epoch": 5.95, "learning_rate": 3.20804811129895e-06, "loss": 0.8438, "step": 71570 }, { "epoch": 5.95, "learning_rate": 3.2079372557714157e-06, "loss": 0.8156, "step": 71580 }, { "epoch": 5.95, "learning_rate": 3.207826400243882e-06, "loss": 0.7682, "step": 71590 }, { "epoch": 5.95, "learning_rate": 3.2077155447163483e-06, "loss": 0.8155, "step": 71600 }, { "epoch": 5.95, "learning_rate": 3.2076046891888146e-06, "loss": 0.8381, "step": 71610 }, { "epoch": 5.95, "learning_rate": 3.2074938336612805e-06, "loss": 0.8016, "step": 71620 }, { "epoch": 5.95, "learning_rate": 3.207382978133747e-06, "loss": 0.7589, "step": 71630 }, { "epoch": 5.95, "learning_rate": 3.207272122606213e-06, "loss": 0.8599, "step": 71640 }, { "epoch": 5.96, "learning_rate": 3.20716126707868e-06, "loss": 0.8024, "step": 71650 }, { "epoch": 5.96, "learning_rate": 3.2070504115511457e-06, "loss": 0.8952, "step": 71660 }, { "epoch": 5.96, "learning_rate": 3.206939556023612e-06, "loss": 0.8234, "step": 71670 }, { "epoch": 5.96, "learning_rate": 3.2068287004960783e-06, "loss": 0.8639, "step": 71680 }, { "epoch": 5.96, "learning_rate": 3.2067178449685446e-06, "loss": 0.8097, "step": 71690 }, { "epoch": 5.96, "learning_rate": 3.206606989441011e-06, "loss": 0.8025, "step": 71700 }, { "epoch": 5.96, "learning_rate": 3.206496133913477e-06, "loss": 0.8719, "step": 71710 }, { "epoch": 5.96, "learning_rate": 3.2063852783859434e-06, "loss": 0.8034, "step": 71720 }, { "epoch": 5.96, "learning_rate": 3.2062744228584097e-06, "loss": 0.8227, "step": 71730 }, { "epoch": 5.96, "learning_rate": 3.206163567330876e-06, "loss": 0.7757, "step": 71740 }, { "epoch": 5.96, "learning_rate": 3.206052711803342e-06, "loss": 0.8406, "step": 71750 }, { "epoch": 5.96, "learning_rate": 3.2059418562758086e-06, "loss": 0.7882, "step": 71760 }, { "epoch": 5.97, "learning_rate": 3.2058310007482745e-06, "loss": 0.8261, "step": 71770 }, { "epoch": 5.97, "learning_rate": 3.205720145220741e-06, "loss": 0.8433, "step": 71780 }, { "epoch": 5.97, "learning_rate": 3.205609289693207e-06, "loss": 0.8579, "step": 71790 }, { "epoch": 5.97, "learning_rate": 3.2054984341656734e-06, "loss": 0.8886, "step": 71800 }, { "epoch": 5.97, "learning_rate": 3.20538757863814e-06, "loss": 0.8614, "step": 71810 }, { "epoch": 5.97, "learning_rate": 3.205276723110606e-06, "loss": 0.8393, "step": 71820 }, { "epoch": 5.97, "learning_rate": 3.2051658675830723e-06, "loss": 0.79, "step": 71830 }, { "epoch": 5.97, "learning_rate": 3.2050550120555386e-06, "loss": 0.7685, "step": 71840 }, { "epoch": 5.97, "learning_rate": 3.204944156528005e-06, "loss": 0.8395, "step": 71850 }, { "epoch": 5.97, "learning_rate": 3.2048333010004707e-06, "loss": 0.8832, "step": 71860 }, { "epoch": 5.97, "learning_rate": 3.2047224454729375e-06, "loss": 0.8574, "step": 71870 }, { "epoch": 5.97, "learning_rate": 3.2046115899454033e-06, "loss": 0.8394, "step": 71880 }, { "epoch": 5.98, "learning_rate": 3.20450073441787e-06, "loss": 0.797, "step": 71890 }, { "epoch": 5.98, "learning_rate": 3.204389878890336e-06, "loss": 0.8442, "step": 71900 }, { "epoch": 5.98, "learning_rate": 3.204279023362802e-06, "loss": 0.8258, "step": 71910 }, { "epoch": 5.98, "learning_rate": 3.2041681678352685e-06, "loss": 0.8477, "step": 71920 }, { "epoch": 5.98, "learning_rate": 3.204057312307735e-06, "loss": 0.8609, "step": 71930 }, { "epoch": 5.98, "learning_rate": 3.203946456780201e-06, "loss": 0.8118, "step": 71940 }, { "epoch": 5.98, "learning_rate": 3.2038356012526674e-06, "loss": 0.7933, "step": 71950 }, { "epoch": 5.98, "learning_rate": 3.2037247457251337e-06, "loss": 0.8464, "step": 71960 }, { "epoch": 5.98, "learning_rate": 3.2036138901975996e-06, "loss": 0.9258, "step": 71970 }, { "epoch": 5.98, "learning_rate": 3.2035030346700663e-06, "loss": 0.8085, "step": 71980 }, { "epoch": 5.98, "learning_rate": 3.203392179142532e-06, "loss": 0.8513, "step": 71990 }, { "epoch": 5.98, "learning_rate": 3.203281323614999e-06, "loss": 0.7658, "step": 72000 }, { "epoch": 5.99, "learning_rate": 3.2031704680874647e-06, "loss": 0.8465, "step": 72010 }, { "epoch": 5.99, "learning_rate": 3.203059612559931e-06, "loss": 0.7655, "step": 72020 }, { "epoch": 5.99, "learning_rate": 3.2029487570323973e-06, "loss": 0.8076, "step": 72030 }, { "epoch": 5.99, "learning_rate": 3.2028379015048636e-06, "loss": 0.8302, "step": 72040 }, { "epoch": 5.99, "learning_rate": 3.2027270459773295e-06, "loss": 0.7948, "step": 72050 }, { "epoch": 5.99, "learning_rate": 3.2026161904497962e-06, "loss": 0.8778, "step": 72060 }, { "epoch": 5.99, "learning_rate": 3.2025053349222625e-06, "loss": 0.8434, "step": 72070 }, { "epoch": 5.99, "learning_rate": 3.202394479394729e-06, "loss": 0.7898, "step": 72080 }, { "epoch": 5.99, "learning_rate": 3.202283623867195e-06, "loss": 0.7808, "step": 72090 }, { "epoch": 5.99, "learning_rate": 3.202172768339661e-06, "loss": 0.8548, "step": 72100 }, { "epoch": 5.99, "learning_rate": 3.2020619128121277e-06, "loss": 0.9519, "step": 72110 }, { "epoch": 5.99, "learning_rate": 3.2019510572845936e-06, "loss": 0.8395, "step": 72120 }, { "epoch": 6.0, "learning_rate": 3.20184020175706e-06, "loss": 0.882, "step": 72130 }, { "epoch": 6.0, "learning_rate": 3.201729346229526e-06, "loss": 0.8146, "step": 72140 }, { "epoch": 6.0, "learning_rate": 3.2016184907019925e-06, "loss": 0.8654, "step": 72150 }, { "epoch": 6.0, "learning_rate": 3.2015076351744587e-06, "loss": 0.821, "step": 72160 }, { "epoch": 6.0, "learning_rate": 3.201396779646925e-06, "loss": 0.8265, "step": 72170 }, { "epoch": 6.0, "learning_rate": 3.2012859241193913e-06, "loss": 0.834, "step": 72180 }, { "epoch": 6.0, "eval_loss": 1.0519319772720337, "eval_runtime": 350.1841, "eval_samples_per_second": 7.636, "eval_steps_per_second": 3.818, "eval_wer": 0.654235707928974, "step": 72186 }, { "epoch": 6.0, "learning_rate": 3.2011750685918576e-06, "loss": 0.9048, "step": 72190 }, { "epoch": 6.0, "learning_rate": 3.201064213064324e-06, "loss": 0.7787, "step": 72200 }, { "epoch": 6.0, "learning_rate": 3.20095335753679e-06, "loss": 0.8153, "step": 72210 }, { "epoch": 6.0, "learning_rate": 3.2008425020092565e-06, "loss": 0.7801, "step": 72220 }, { "epoch": 6.0, "learning_rate": 3.2007316464817224e-06, "loss": 0.7554, "step": 72230 }, { "epoch": 6.0, "learning_rate": 3.200620790954189e-06, "loss": 0.8347, "step": 72240 }, { "epoch": 6.01, "learning_rate": 3.200509935426655e-06, "loss": 0.8636, "step": 72250 }, { "epoch": 6.01, "learning_rate": 3.2003990798991213e-06, "loss": 0.8349, "step": 72260 }, { "epoch": 6.01, "learning_rate": 3.2002882243715876e-06, "loss": 0.855, "step": 72270 }, { "epoch": 6.01, "learning_rate": 3.200177368844054e-06, "loss": 0.8306, "step": 72280 }, { "epoch": 6.01, "learning_rate": 3.2000665133165197e-06, "loss": 0.8921, "step": 72290 }, { "epoch": 6.01, "learning_rate": 3.1999556577889865e-06, "loss": 0.8296, "step": 72300 }, { "epoch": 6.01, "learning_rate": 3.1998448022614528e-06, "loss": 0.7823, "step": 72310 }, { "epoch": 6.01, "learning_rate": 3.1997339467339186e-06, "loss": 0.8255, "step": 72320 }, { "epoch": 6.01, "learning_rate": 3.1996230912063853e-06, "loss": 0.8426, "step": 72330 }, { "epoch": 6.01, "learning_rate": 3.1995122356788512e-06, "loss": 0.8384, "step": 72340 }, { "epoch": 6.01, "learning_rate": 3.199401380151318e-06, "loss": 0.8359, "step": 72350 }, { "epoch": 6.01, "learning_rate": 3.199290524623784e-06, "loss": 0.7734, "step": 72360 }, { "epoch": 6.02, "learning_rate": 3.19917966909625e-06, "loss": 0.8092, "step": 72370 }, { "epoch": 6.02, "learning_rate": 3.1990688135687164e-06, "loss": 0.8234, "step": 72380 }, { "epoch": 6.02, "learning_rate": 3.1989579580411827e-06, "loss": 0.8074, "step": 72390 }, { "epoch": 6.02, "learning_rate": 3.1988471025136486e-06, "loss": 0.8327, "step": 72400 }, { "epoch": 6.02, "learning_rate": 3.1987362469861153e-06, "loss": 0.8684, "step": 72410 }, { "epoch": 6.02, "learning_rate": 3.1986253914585816e-06, "loss": 0.8225, "step": 72420 }, { "epoch": 6.02, "learning_rate": 3.198514535931048e-06, "loss": 0.814, "step": 72430 }, { "epoch": 6.02, "learning_rate": 3.198403680403514e-06, "loss": 0.8361, "step": 72440 }, { "epoch": 6.02, "learning_rate": 3.19829282487598e-06, "loss": 0.8297, "step": 72450 }, { "epoch": 6.02, "learning_rate": 3.1981819693484468e-06, "loss": 0.8441, "step": 72460 }, { "epoch": 6.02, "learning_rate": 3.1980711138209126e-06, "loss": 0.8817, "step": 72470 }, { "epoch": 6.02, "learning_rate": 3.197960258293379e-06, "loss": 0.7578, "step": 72480 }, { "epoch": 6.03, "learning_rate": 3.1978494027658452e-06, "loss": 0.8456, "step": 72490 }, { "epoch": 6.03, "learning_rate": 3.1977385472383115e-06, "loss": 0.8418, "step": 72500 }, { "epoch": 6.03, "learning_rate": 3.197627691710778e-06, "loss": 0.8832, "step": 72510 }, { "epoch": 6.03, "learning_rate": 3.197516836183244e-06, "loss": 0.7787, "step": 72520 }, { "epoch": 6.03, "learning_rate": 3.19740598065571e-06, "loss": 0.7649, "step": 72530 }, { "epoch": 6.03, "learning_rate": 3.1972951251281767e-06, "loss": 0.8297, "step": 72540 }, { "epoch": 6.03, "learning_rate": 3.197184269600643e-06, "loss": 0.8536, "step": 72550 }, { "epoch": 6.03, "learning_rate": 3.197073414073109e-06, "loss": 0.7916, "step": 72560 }, { "epoch": 6.03, "learning_rate": 3.1969625585455756e-06, "loss": 0.8218, "step": 72570 }, { "epoch": 6.03, "learning_rate": 3.1968517030180415e-06, "loss": 0.8217, "step": 72580 }, { "epoch": 6.03, "learning_rate": 3.196740847490508e-06, "loss": 0.8242, "step": 72590 }, { "epoch": 6.03, "learning_rate": 3.196629991962974e-06, "loss": 0.8401, "step": 72600 }, { "epoch": 6.04, "learning_rate": 3.1965191364354403e-06, "loss": 0.8744, "step": 72610 }, { "epoch": 6.04, "learning_rate": 3.1964082809079066e-06, "loss": 0.8525, "step": 72620 }, { "epoch": 6.04, "learning_rate": 3.196297425380373e-06, "loss": 0.787, "step": 72630 }, { "epoch": 6.04, "learning_rate": 3.196186569852839e-06, "loss": 0.8713, "step": 72640 }, { "epoch": 6.04, "learning_rate": 3.1960757143253055e-06, "loss": 0.8438, "step": 72650 }, { "epoch": 6.04, "learning_rate": 3.1959648587977714e-06, "loss": 0.8409, "step": 72660 }, { "epoch": 6.04, "learning_rate": 3.195854003270238e-06, "loss": 0.8404, "step": 72670 }, { "epoch": 6.04, "learning_rate": 3.1957431477427044e-06, "loss": 0.7815, "step": 72680 }, { "epoch": 6.04, "learning_rate": 3.1956322922151703e-06, "loss": 0.7983, "step": 72690 }, { "epoch": 6.04, "learning_rate": 3.195521436687637e-06, "loss": 0.8344, "step": 72700 }, { "epoch": 6.04, "learning_rate": 3.195410581160103e-06, "loss": 0.7739, "step": 72710 }, { "epoch": 6.04, "learning_rate": 3.195299725632569e-06, "loss": 0.7969, "step": 72720 }, { "epoch": 6.05, "learning_rate": 3.1951888701050355e-06, "loss": 0.8934, "step": 72730 }, { "epoch": 6.05, "learning_rate": 3.1950780145775018e-06, "loss": 0.8362, "step": 72740 }, { "epoch": 6.05, "learning_rate": 3.1949671590499676e-06, "loss": 0.8551, "step": 72750 }, { "epoch": 6.05, "learning_rate": 3.1948563035224343e-06, "loss": 0.8152, "step": 72760 }, { "epoch": 6.05, "learning_rate": 3.1947454479949002e-06, "loss": 0.7587, "step": 72770 }, { "epoch": 6.05, "learning_rate": 3.194634592467367e-06, "loss": 0.7601, "step": 72780 }, { "epoch": 6.05, "learning_rate": 3.1945237369398332e-06, "loss": 0.7913, "step": 72790 }, { "epoch": 6.05, "learning_rate": 3.194412881412299e-06, "loss": 0.8777, "step": 72800 }, { "epoch": 6.05, "learning_rate": 3.194302025884766e-06, "loss": 0.7709, "step": 72810 }, { "epoch": 6.05, "learning_rate": 3.1941911703572317e-06, "loss": 0.8321, "step": 72820 }, { "epoch": 6.05, "learning_rate": 3.194080314829698e-06, "loss": 0.8886, "step": 72830 }, { "epoch": 6.05, "learning_rate": 3.1939694593021643e-06, "loss": 0.8171, "step": 72840 }, { "epoch": 6.06, "learning_rate": 3.1938586037746306e-06, "loss": 0.8434, "step": 72850 }, { "epoch": 6.06, "learning_rate": 3.193747748247097e-06, "loss": 0.8328, "step": 72860 }, { "epoch": 6.06, "learning_rate": 3.193636892719563e-06, "loss": 0.7822, "step": 72870 }, { "epoch": 6.06, "learning_rate": 3.193526037192029e-06, "loss": 0.7647, "step": 72880 }, { "epoch": 6.06, "learning_rate": 3.1934151816644958e-06, "loss": 0.8342, "step": 72890 }, { "epoch": 6.06, "learning_rate": 3.1933043261369616e-06, "loss": 0.8201, "step": 72900 }, { "epoch": 6.06, "learning_rate": 3.193193470609428e-06, "loss": 0.7967, "step": 72910 }, { "epoch": 6.06, "learning_rate": 3.1930826150818947e-06, "loss": 0.7675, "step": 72920 }, { "epoch": 6.06, "learning_rate": 3.1929717595543605e-06, "loss": 0.785, "step": 72930 }, { "epoch": 6.06, "learning_rate": 3.1928609040268272e-06, "loss": 0.772, "step": 72940 }, { "epoch": 6.06, "learning_rate": 3.192750048499293e-06, "loss": 0.9105, "step": 72950 }, { "epoch": 6.06, "learning_rate": 3.1926391929717594e-06, "loss": 0.8084, "step": 72960 }, { "epoch": 6.07, "learning_rate": 3.1925283374442257e-06, "loss": 0.819, "step": 72970 }, { "epoch": 6.07, "learning_rate": 3.192417481916692e-06, "loss": 0.781, "step": 72980 }, { "epoch": 6.07, "learning_rate": 3.192306626389158e-06, "loss": 0.8297, "step": 72990 }, { "epoch": 6.07, "learning_rate": 3.1921957708616246e-06, "loss": 0.851, "step": 73000 }, { "epoch": 6.07, "learning_rate": 3.1920849153340905e-06, "loss": 0.7845, "step": 73010 }, { "epoch": 6.07, "learning_rate": 3.191974059806557e-06, "loss": 0.8168, "step": 73020 }, { "epoch": 6.07, "learning_rate": 3.191863204279023e-06, "loss": 0.8028, "step": 73030 }, { "epoch": 6.07, "learning_rate": 3.1917523487514893e-06, "loss": 0.8351, "step": 73040 }, { "epoch": 6.07, "learning_rate": 3.191641493223956e-06, "loss": 0.7737, "step": 73050 }, { "epoch": 6.07, "learning_rate": 3.191530637696422e-06, "loss": 0.8272, "step": 73060 }, { "epoch": 6.07, "learning_rate": 3.1914197821688882e-06, "loss": 0.8818, "step": 73070 }, { "epoch": 6.07, "learning_rate": 3.1913089266413545e-06, "loss": 0.8197, "step": 73080 }, { "epoch": 6.08, "learning_rate": 3.191198071113821e-06, "loss": 0.7603, "step": 73090 }, { "epoch": 6.08, "learning_rate": 3.1910872155862867e-06, "loss": 0.7945, "step": 73100 }, { "epoch": 6.08, "learning_rate": 3.1909874456115067e-06, "loss": 0.7777, "step": 73110 }, { "epoch": 6.08, "learning_rate": 3.190876590083973e-06, "loss": 0.7873, "step": 73120 }, { "epoch": 6.08, "learning_rate": 3.1907657345564392e-06, "loss": 0.8227, "step": 73130 }, { "epoch": 6.08, "learning_rate": 3.1906548790289055e-06, "loss": 0.8442, "step": 73140 }, { "epoch": 6.08, "learning_rate": 3.190544023501372e-06, "loss": 0.9222, "step": 73150 }, { "epoch": 6.08, "learning_rate": 3.1904331679738377e-06, "loss": 0.7742, "step": 73160 }, { "epoch": 6.08, "learning_rate": 3.1903223124463044e-06, "loss": 0.7668, "step": 73170 }, { "epoch": 6.08, "learning_rate": 3.1902114569187703e-06, "loss": 0.7922, "step": 73180 }, { "epoch": 6.08, "learning_rate": 3.190100601391237e-06, "loss": 0.8246, "step": 73190 }, { "epoch": 6.08, "learning_rate": 3.189989745863703e-06, "loss": 0.8481, "step": 73200 }, { "epoch": 6.09, "learning_rate": 3.189878890336169e-06, "loss": 0.8195, "step": 73210 }, { "epoch": 6.09, "learning_rate": 3.1897680348086355e-06, "loss": 0.776, "step": 73220 }, { "epoch": 6.09, "learning_rate": 3.1896571792811018e-06, "loss": 0.7694, "step": 73230 }, { "epoch": 6.09, "learning_rate": 3.1895463237535677e-06, "loss": 0.7895, "step": 73240 }, { "epoch": 6.09, "learning_rate": 3.1894354682260344e-06, "loss": 0.7976, "step": 73250 }, { "epoch": 6.09, "learning_rate": 3.1893246126985007e-06, "loss": 0.8268, "step": 73260 }, { "epoch": 6.09, "learning_rate": 3.1892137571709665e-06, "loss": 0.8067, "step": 73270 }, { "epoch": 6.09, "learning_rate": 3.1891029016434333e-06, "loss": 0.8368, "step": 73280 }, { "epoch": 6.09, "learning_rate": 3.188992046115899e-06, "loss": 0.8621, "step": 73290 }, { "epoch": 6.09, "learning_rate": 3.188881190588366e-06, "loss": 0.8164, "step": 73300 }, { "epoch": 6.09, "learning_rate": 3.1887703350608317e-06, "loss": 0.8492, "step": 73310 }, { "epoch": 6.09, "learning_rate": 3.188659479533298e-06, "loss": 0.8185, "step": 73320 }, { "epoch": 6.1, "learning_rate": 3.1885486240057643e-06, "loss": 0.8083, "step": 73330 }, { "epoch": 6.1, "learning_rate": 3.1884377684782306e-06, "loss": 0.8225, "step": 73340 }, { "epoch": 6.1, "learning_rate": 3.1883269129506965e-06, "loss": 0.9089, "step": 73350 }, { "epoch": 6.1, "learning_rate": 3.188216057423163e-06, "loss": 0.8358, "step": 73360 }, { "epoch": 6.1, "learning_rate": 3.1881052018956295e-06, "loss": 0.8116, "step": 73370 }, { "epoch": 6.1, "learning_rate": 3.1879943463680958e-06, "loss": 0.8437, "step": 73380 }, { "epoch": 6.1, "learning_rate": 3.187883490840562e-06, "loss": 0.8538, "step": 73390 }, { "epoch": 6.1, "learning_rate": 3.187772635313028e-06, "loss": 0.8008, "step": 73400 }, { "epoch": 6.1, "learning_rate": 3.1876617797854947e-06, "loss": 0.8114, "step": 73410 }, { "epoch": 6.1, "learning_rate": 3.1875509242579605e-06, "loss": 0.7854, "step": 73420 }, { "epoch": 6.1, "learning_rate": 3.187440068730427e-06, "loss": 0.8022, "step": 73430 }, { "epoch": 6.1, "learning_rate": 3.187329213202893e-06, "loss": 0.8853, "step": 73440 }, { "epoch": 6.11, "learning_rate": 3.1872183576753594e-06, "loss": 0.8493, "step": 73450 }, { "epoch": 6.11, "learning_rate": 3.1871075021478257e-06, "loss": 0.7941, "step": 73460 }, { "epoch": 6.11, "learning_rate": 3.186996646620292e-06, "loss": 0.8216, "step": 73470 }, { "epoch": 6.11, "learning_rate": 3.186885791092758e-06, "loss": 0.7895, "step": 73480 }, { "epoch": 6.11, "learning_rate": 3.1867749355652246e-06, "loss": 0.8675, "step": 73490 }, { "epoch": 6.11, "learning_rate": 3.186664080037691e-06, "loss": 0.8537, "step": 73500 }, { "epoch": 6.11, "learning_rate": 3.1865532245101568e-06, "loss": 0.818, "step": 73510 }, { "epoch": 6.11, "learning_rate": 3.1864423689826235e-06, "loss": 0.7755, "step": 73520 }, { "epoch": 6.11, "learning_rate": 3.1863315134550894e-06, "loss": 0.8048, "step": 73530 }, { "epoch": 6.11, "learning_rate": 3.186220657927556e-06, "loss": 0.8558, "step": 73540 }, { "epoch": 6.11, "learning_rate": 3.186109802400022e-06, "loss": 0.8186, "step": 73550 }, { "epoch": 6.11, "learning_rate": 3.1859989468724883e-06, "loss": 0.7745, "step": 73560 }, { "epoch": 6.12, "learning_rate": 3.1858880913449546e-06, "loss": 0.8309, "step": 73570 }, { "epoch": 6.12, "learning_rate": 3.185777235817421e-06, "loss": 0.7823, "step": 73580 }, { "epoch": 6.12, "learning_rate": 3.1856663802898867e-06, "loss": 0.8297, "step": 73590 }, { "epoch": 6.12, "learning_rate": 3.1855555247623534e-06, "loss": 0.8416, "step": 73600 }, { "epoch": 6.12, "learning_rate": 3.1854446692348193e-06, "loss": 0.7902, "step": 73610 }, { "epoch": 6.12, "learning_rate": 3.185333813707286e-06, "loss": 0.7844, "step": 73620 }, { "epoch": 6.12, "learning_rate": 3.1852229581797523e-06, "loss": 0.7786, "step": 73630 }, { "epoch": 6.12, "learning_rate": 3.185112102652218e-06, "loss": 0.8893, "step": 73640 }, { "epoch": 6.12, "learning_rate": 3.185001247124685e-06, "loss": 0.8463, "step": 73650 }, { "epoch": 6.12, "learning_rate": 3.1848903915971508e-06, "loss": 0.8069, "step": 73660 }, { "epoch": 6.12, "learning_rate": 3.184779536069617e-06, "loss": 0.8363, "step": 73670 }, { "epoch": 6.12, "learning_rate": 3.1846686805420834e-06, "loss": 0.8643, "step": 73680 }, { "epoch": 6.13, "learning_rate": 3.1845578250145497e-06, "loss": 0.877, "step": 73690 }, { "epoch": 6.13, "learning_rate": 3.1844469694870155e-06, "loss": 0.7991, "step": 73700 }, { "epoch": 6.13, "learning_rate": 3.1843361139594823e-06, "loss": 0.8945, "step": 73710 }, { "epoch": 6.13, "learning_rate": 3.184225258431948e-06, "loss": 0.8906, "step": 73720 }, { "epoch": 6.13, "learning_rate": 3.184114402904415e-06, "loss": 0.7736, "step": 73730 }, { "epoch": 6.13, "learning_rate": 3.184003547376881e-06, "loss": 0.8392, "step": 73740 }, { "epoch": 6.13, "learning_rate": 3.183892691849347e-06, "loss": 0.833, "step": 73750 }, { "epoch": 6.13, "learning_rate": 3.1837818363218137e-06, "loss": 0.8137, "step": 73760 }, { "epoch": 6.13, "learning_rate": 3.1836709807942796e-06, "loss": 0.8075, "step": 73770 }, { "epoch": 6.13, "learning_rate": 3.183560125266746e-06, "loss": 0.8242, "step": 73780 }, { "epoch": 6.13, "learning_rate": 3.183449269739212e-06, "loss": 0.8902, "step": 73790 }, { "epoch": 6.13, "learning_rate": 3.1833384142116785e-06, "loss": 0.8095, "step": 73800 }, { "epoch": 6.13, "learning_rate": 3.183227558684145e-06, "loss": 0.8136, "step": 73810 }, { "epoch": 6.14, "learning_rate": 3.183116703156611e-06, "loss": 0.7987, "step": 73820 }, { "epoch": 6.14, "learning_rate": 3.183005847629077e-06, "loss": 0.7852, "step": 73830 }, { "epoch": 6.14, "learning_rate": 3.1828949921015437e-06, "loss": 0.8384, "step": 73840 }, { "epoch": 6.14, "learning_rate": 3.1827841365740095e-06, "loss": 0.8426, "step": 73850 }, { "epoch": 6.14, "learning_rate": 3.182673281046476e-06, "loss": 0.7926, "step": 73860 }, { "epoch": 6.14, "learning_rate": 3.1825624255189426e-06, "loss": 0.8053, "step": 73870 }, { "epoch": 6.14, "learning_rate": 3.1824515699914084e-06, "loss": 0.7697, "step": 73880 }, { "epoch": 6.14, "learning_rate": 3.182340714463875e-06, "loss": 0.8319, "step": 73890 }, { "epoch": 6.14, "learning_rate": 3.182229858936341e-06, "loss": 0.8808, "step": 73900 }, { "epoch": 6.14, "learning_rate": 3.1821190034088073e-06, "loss": 0.7433, "step": 73910 }, { "epoch": 6.14, "learning_rate": 3.1820081478812736e-06, "loss": 0.8064, "step": 73920 }, { "epoch": 6.14, "learning_rate": 3.18189729235374e-06, "loss": 0.8799, "step": 73930 }, { "epoch": 6.15, "learning_rate": 3.1817864368262058e-06, "loss": 0.8841, "step": 73940 }, { "epoch": 6.15, "learning_rate": 3.1816755812986725e-06, "loss": 0.8691, "step": 73950 }, { "epoch": 6.15, "learning_rate": 3.1815647257711384e-06, "loss": 0.8032, "step": 73960 }, { "epoch": 6.15, "learning_rate": 3.181453870243605e-06, "loss": 0.8513, "step": 73970 }, { "epoch": 6.15, "learning_rate": 3.181343014716071e-06, "loss": 0.7661, "step": 73980 }, { "epoch": 6.15, "learning_rate": 3.1812321591885373e-06, "loss": 0.8859, "step": 73990 }, { "epoch": 6.15, "learning_rate": 3.181121303661004e-06, "loss": 0.8751, "step": 74000 }, { "epoch": 6.15, "learning_rate": 3.18101044813347e-06, "loss": 0.8404, "step": 74010 }, { "epoch": 6.15, "learning_rate": 3.180899592605936e-06, "loss": 0.8166, "step": 74020 }, { "epoch": 6.15, "learning_rate": 3.1807887370784024e-06, "loss": 0.8207, "step": 74030 }, { "epoch": 6.15, "learning_rate": 3.1806778815508687e-06, "loss": 0.8575, "step": 74040 }, { "epoch": 6.15, "learning_rate": 3.1805670260233346e-06, "loss": 0.8319, "step": 74050 }, { "epoch": 6.16, "learning_rate": 3.1804561704958013e-06, "loss": 0.8052, "step": 74060 }, { "epoch": 6.16, "learning_rate": 3.180345314968267e-06, "loss": 0.8087, "step": 74070 }, { "epoch": 6.16, "learning_rate": 3.180234459440734e-06, "loss": 0.79, "step": 74080 }, { "epoch": 6.16, "learning_rate": 3.1801236039132e-06, "loss": 0.8548, "step": 74090 }, { "epoch": 6.16, "learning_rate": 3.180012748385666e-06, "loss": 0.8335, "step": 74100 }, { "epoch": 6.16, "learning_rate": 3.179901892858133e-06, "loss": 0.8065, "step": 74110 }, { "epoch": 6.16, "learning_rate": 3.1797910373305987e-06, "loss": 0.8594, "step": 74120 }, { "epoch": 6.16, "learning_rate": 3.1796801818030654e-06, "loss": 0.8067, "step": 74130 }, { "epoch": 6.16, "learning_rate": 3.1795693262755313e-06, "loss": 0.8232, "step": 74140 }, { "epoch": 6.16, "learning_rate": 3.1794584707479976e-06, "loss": 0.8292, "step": 74150 }, { "epoch": 6.16, "learning_rate": 3.179347615220464e-06, "loss": 0.7788, "step": 74160 }, { "epoch": 6.16, "learning_rate": 3.17923675969293e-06, "loss": 0.8214, "step": 74170 }, { "epoch": 6.17, "learning_rate": 3.179125904165396e-06, "loss": 0.7883, "step": 74180 }, { "epoch": 6.17, "learning_rate": 3.1790150486378627e-06, "loss": 0.829, "step": 74190 }, { "epoch": 6.17, "learning_rate": 3.1789041931103286e-06, "loss": 0.7484, "step": 74200 }, { "epoch": 6.17, "learning_rate": 3.178793337582795e-06, "loss": 0.8327, "step": 74210 }, { "epoch": 6.17, "learning_rate": 3.178682482055261e-06, "loss": 0.8247, "step": 74220 }, { "epoch": 6.17, "learning_rate": 3.1785716265277275e-06, "loss": 0.8626, "step": 74230 }, { "epoch": 6.17, "learning_rate": 3.1784607710001942e-06, "loss": 0.8685, "step": 74240 }, { "epoch": 6.17, "learning_rate": 3.17834991547266e-06, "loss": 0.8069, "step": 74250 }, { "epoch": 6.17, "learning_rate": 3.1782390599451264e-06, "loss": 0.8073, "step": 74260 }, { "epoch": 6.17, "learning_rate": 3.1781282044175927e-06, "loss": 0.7854, "step": 74270 }, { "epoch": 6.17, "learning_rate": 3.178017348890059e-06, "loss": 0.8531, "step": 74280 }, { "epoch": 6.17, "learning_rate": 3.177906493362525e-06, "loss": 0.8633, "step": 74290 }, { "epoch": 6.18, "learning_rate": 3.1777956378349916e-06, "loss": 0.8877, "step": 74300 }, { "epoch": 6.18, "learning_rate": 3.1776847823074574e-06, "loss": 0.8338, "step": 74310 }, { "epoch": 6.18, "learning_rate": 3.177573926779924e-06, "loss": 0.779, "step": 74320 }, { "epoch": 6.18, "learning_rate": 3.17746307125239e-06, "loss": 0.8914, "step": 74330 }, { "epoch": 6.18, "learning_rate": 3.1773522157248563e-06, "loss": 0.9015, "step": 74340 }, { "epoch": 6.18, "learning_rate": 3.1772413601973226e-06, "loss": 0.85, "step": 74350 }, { "epoch": 6.18, "learning_rate": 3.177130504669789e-06, "loss": 0.8095, "step": 74360 }, { "epoch": 6.18, "learning_rate": 3.1770196491422552e-06, "loss": 0.7358, "step": 74370 }, { "epoch": 6.18, "learning_rate": 3.1769087936147215e-06, "loss": 0.7964, "step": 74380 }, { "epoch": 6.18, "learning_rate": 3.176797938087188e-06, "loss": 0.784, "step": 74390 }, { "epoch": 6.18, "learning_rate": 3.176687082559654e-06, "loss": 0.8545, "step": 74400 }, { "epoch": 6.18, "learning_rate": 3.1765762270321204e-06, "loss": 0.8768, "step": 74410 }, { "epoch": 6.19, "learning_rate": 3.1764653715045863e-06, "loss": 0.8129, "step": 74420 }, { "epoch": 6.19, "learning_rate": 3.176354515977053e-06, "loss": 0.8537, "step": 74430 }, { "epoch": 6.19, "learning_rate": 3.176243660449519e-06, "loss": 0.7941, "step": 74440 }, { "epoch": 6.19, "learning_rate": 3.176132804921985e-06, "loss": 0.8304, "step": 74450 }, { "epoch": 6.19, "learning_rate": 3.1760219493944514e-06, "loss": 0.8118, "step": 74460 }, { "epoch": 6.19, "learning_rate": 3.1759110938669177e-06, "loss": 0.8768, "step": 74470 }, { "epoch": 6.19, "learning_rate": 3.1758002383393845e-06, "loss": 0.8309, "step": 74480 }, { "epoch": 6.19, "learning_rate": 3.1756893828118503e-06, "loss": 0.8383, "step": 74490 }, { "epoch": 6.19, "learning_rate": 3.1755785272843166e-06, "loss": 0.8231, "step": 74500 }, { "epoch": 6.19, "learning_rate": 3.175467671756783e-06, "loss": 0.7643, "step": 74510 }, { "epoch": 6.19, "learning_rate": 3.1753568162292492e-06, "loss": 0.8194, "step": 74520 }, { "epoch": 6.19, "learning_rate": 3.175245960701715e-06, "loss": 0.7315, "step": 74530 }, { "epoch": 6.2, "learning_rate": 3.175135105174182e-06, "loss": 0.8508, "step": 74540 }, { "epoch": 6.2, "learning_rate": 3.1750242496466477e-06, "loss": 0.832, "step": 74550 }, { "epoch": 6.2, "learning_rate": 3.174913394119114e-06, "loss": 0.7622, "step": 74560 }, { "epoch": 6.2, "learning_rate": 3.1748025385915803e-06, "loss": 0.778, "step": 74570 }, { "epoch": 6.2, "learning_rate": 3.1746916830640466e-06, "loss": 0.7753, "step": 74580 }, { "epoch": 6.2, "learning_rate": 3.174580827536513e-06, "loss": 0.8407, "step": 74590 }, { "epoch": 6.2, "learning_rate": 3.174469972008979e-06, "loss": 0.8141, "step": 74600 }, { "epoch": 6.2, "learning_rate": 3.1743591164814455e-06, "loss": 0.803, "step": 74610 }, { "epoch": 6.2, "learning_rate": 3.1742482609539117e-06, "loss": 0.7857, "step": 74620 }, { "epoch": 6.2, "learning_rate": 3.174137405426378e-06, "loss": 0.8294, "step": 74630 }, { "epoch": 6.2, "learning_rate": 3.174026549898844e-06, "loss": 0.8355, "step": 74640 }, { "epoch": 6.2, "learning_rate": 3.1739156943713106e-06, "loss": 0.7713, "step": 74650 }, { "epoch": 6.21, "learning_rate": 3.1738048388437765e-06, "loss": 0.7752, "step": 74660 }, { "epoch": 6.21, "learning_rate": 3.1736939833162432e-06, "loss": 0.7481, "step": 74670 }, { "epoch": 6.21, "learning_rate": 3.173583127788709e-06, "loss": 0.7858, "step": 74680 }, { "epoch": 6.21, "learning_rate": 3.1734722722611754e-06, "loss": 0.8367, "step": 74690 }, { "epoch": 6.21, "learning_rate": 3.1733614167336417e-06, "loss": 0.8836, "step": 74700 }, { "epoch": 6.21, "learning_rate": 3.173250561206108e-06, "loss": 0.8351, "step": 74710 }, { "epoch": 6.21, "learning_rate": 3.1731397056785743e-06, "loss": 0.818, "step": 74720 }, { "epoch": 6.21, "learning_rate": 3.1730288501510406e-06, "loss": 0.7889, "step": 74730 }, { "epoch": 6.21, "learning_rate": 3.172917994623507e-06, "loss": 0.8333, "step": 74740 }, { "epoch": 6.21, "learning_rate": 3.172807139095973e-06, "loss": 0.7955, "step": 74750 }, { "epoch": 6.21, "learning_rate": 3.1726962835684395e-06, "loss": 0.8036, "step": 74760 }, { "epoch": 6.21, "learning_rate": 3.1725854280409053e-06, "loss": 0.8148, "step": 74770 }, { "epoch": 6.22, "learning_rate": 3.172474572513372e-06, "loss": 0.7791, "step": 74780 }, { "epoch": 6.22, "learning_rate": 3.172363716985838e-06, "loss": 0.7989, "step": 74790 }, { "epoch": 6.22, "learning_rate": 3.1722528614583042e-06, "loss": 0.84, "step": 74800 }, { "epoch": 6.22, "learning_rate": 3.1721420059307705e-06, "loss": 0.7504, "step": 74810 }, { "epoch": 6.22, "learning_rate": 3.172031150403237e-06, "loss": 0.8017, "step": 74820 }, { "epoch": 6.22, "learning_rate": 3.171920294875703e-06, "loss": 0.8416, "step": 74830 }, { "epoch": 6.22, "learning_rate": 3.1718094393481694e-06, "loss": 0.7728, "step": 74840 }, { "epoch": 6.22, "learning_rate": 3.1716985838206357e-06, "loss": 0.8807, "step": 74850 }, { "epoch": 6.22, "learning_rate": 3.171587728293102e-06, "loss": 0.8075, "step": 74860 }, { "epoch": 6.22, "learning_rate": 3.1714768727655683e-06, "loss": 0.78, "step": 74870 }, { "epoch": 6.22, "learning_rate": 3.171366017238034e-06, "loss": 0.7515, "step": 74880 }, { "epoch": 6.22, "learning_rate": 3.171255161710501e-06, "loss": 0.8428, "step": 74890 }, { "epoch": 6.23, "learning_rate": 3.1711443061829667e-06, "loss": 0.8739, "step": 74900 }, { "epoch": 6.23, "learning_rate": 3.1710334506554335e-06, "loss": 0.7911, "step": 74910 }, { "epoch": 6.23, "learning_rate": 3.1709225951278993e-06, "loss": 0.8415, "step": 74920 }, { "epoch": 6.23, "learning_rate": 3.1708117396003656e-06, "loss": 0.7929, "step": 74930 }, { "epoch": 6.23, "learning_rate": 3.170700884072832e-06, "loss": 0.8601, "step": 74940 }, { "epoch": 6.23, "learning_rate": 3.1705900285452982e-06, "loss": 0.8287, "step": 74950 }, { "epoch": 6.23, "learning_rate": 3.170479173017764e-06, "loss": 0.8432, "step": 74960 }, { "epoch": 6.23, "learning_rate": 3.170368317490231e-06, "loss": 0.8198, "step": 74970 }, { "epoch": 6.23, "learning_rate": 3.170257461962697e-06, "loss": 0.8036, "step": 74980 }, { "epoch": 6.23, "learning_rate": 3.170146606435163e-06, "loss": 0.8367, "step": 74990 }, { "epoch": 6.23, "learning_rate": 3.1700357509076297e-06, "loss": 0.8146, "step": 75000 }, { "epoch": 6.23, "learning_rate": 3.1699248953800956e-06, "loss": 0.835, "step": 75010 }, { "epoch": 6.24, "learning_rate": 3.1698140398525623e-06, "loss": 0.7978, "step": 75020 }, { "epoch": 6.24, "learning_rate": 3.169703184325028e-06, "loss": 0.7501, "step": 75030 }, { "epoch": 6.24, "learning_rate": 3.1695923287974945e-06, "loss": 0.8602, "step": 75040 }, { "epoch": 6.24, "learning_rate": 3.1694814732699608e-06, "loss": 0.8637, "step": 75050 }, { "epoch": 6.24, "learning_rate": 3.169370617742427e-06, "loss": 0.7786, "step": 75060 }, { "epoch": 6.24, "learning_rate": 3.169259762214893e-06, "loss": 0.8166, "step": 75070 }, { "epoch": 6.24, "learning_rate": 3.1691489066873596e-06, "loss": 0.8002, "step": 75080 }, { "epoch": 6.24, "learning_rate": 3.169038051159826e-06, "loss": 0.8084, "step": 75090 }, { "epoch": 6.24, "learning_rate": 3.1689271956322922e-06, "loss": 0.7964, "step": 75100 }, { "epoch": 6.24, "learning_rate": 3.1688163401047585e-06, "loss": 0.7711, "step": 75110 }, { "epoch": 6.24, "learning_rate": 3.1687054845772244e-06, "loss": 0.8027, "step": 75120 }, { "epoch": 6.24, "learning_rate": 3.168594629049691e-06, "loss": 0.8298, "step": 75130 }, { "epoch": 6.25, "learning_rate": 3.168483773522157e-06, "loss": 0.8333, "step": 75140 }, { "epoch": 6.25, "learning_rate": 3.1683729179946233e-06, "loss": 0.7866, "step": 75150 }, { "epoch": 6.25, "learning_rate": 3.1682620624670896e-06, "loss": 0.7723, "step": 75160 }, { "epoch": 6.25, "learning_rate": 3.168151206939556e-06, "loss": 0.8054, "step": 75170 }, { "epoch": 6.25, "learning_rate": 3.168040351412022e-06, "loss": 0.7896, "step": 75180 }, { "epoch": 6.25, "learning_rate": 3.1679294958844885e-06, "loss": 0.8561, "step": 75190 }, { "epoch": 6.25, "learning_rate": 3.1678186403569543e-06, "loss": 0.8141, "step": 75200 }, { "epoch": 6.25, "learning_rate": 3.167707784829421e-06, "loss": 0.8106, "step": 75210 }, { "epoch": 6.25, "learning_rate": 3.1675969293018874e-06, "loss": 0.8238, "step": 75220 }, { "epoch": 6.25, "learning_rate": 3.1674860737743532e-06, "loss": 0.8077, "step": 75230 }, { "epoch": 6.25, "learning_rate": 3.16737521824682e-06, "loss": 0.8169, "step": 75240 }, { "epoch": 6.25, "learning_rate": 3.167264362719286e-06, "loss": 0.8915, "step": 75250 }, { "epoch": 6.26, "learning_rate": 3.1671535071917525e-06, "loss": 0.7974, "step": 75260 }, { "epoch": 6.26, "learning_rate": 3.1670426516642184e-06, "loss": 0.777, "step": 75270 }, { "epoch": 6.26, "learning_rate": 3.1669317961366847e-06, "loss": 0.8501, "step": 75280 }, { "epoch": 6.26, "learning_rate": 3.166820940609151e-06, "loss": 0.8135, "step": 75290 }, { "epoch": 6.26, "learning_rate": 3.1667100850816173e-06, "loss": 0.865, "step": 75300 }, { "epoch": 6.26, "learning_rate": 3.166599229554083e-06, "loss": 0.8233, "step": 75310 }, { "epoch": 6.26, "learning_rate": 3.16648837402655e-06, "loss": 0.7957, "step": 75320 }, { "epoch": 6.26, "learning_rate": 3.1663775184990158e-06, "loss": 0.8364, "step": 75330 }, { "epoch": 6.26, "learning_rate": 3.166266662971482e-06, "loss": 0.8402, "step": 75340 }, { "epoch": 6.26, "learning_rate": 3.1661558074439488e-06, "loss": 0.8695, "step": 75350 }, { "epoch": 6.26, "learning_rate": 3.1660449519164146e-06, "loss": 0.8307, "step": 75360 }, { "epoch": 6.26, "learning_rate": 3.1659340963888814e-06, "loss": 0.8271, "step": 75370 }, { "epoch": 6.27, "learning_rate": 3.1658232408613472e-06, "loss": 0.8693, "step": 75380 }, { "epoch": 6.27, "learning_rate": 3.1657123853338135e-06, "loss": 0.8483, "step": 75390 }, { "epoch": 6.27, "learning_rate": 3.16560152980628e-06, "loss": 0.7926, "step": 75400 }, { "epoch": 6.27, "learning_rate": 3.165490674278746e-06, "loss": 0.7774, "step": 75410 }, { "epoch": 6.27, "learning_rate": 3.165379818751212e-06, "loss": 0.7608, "step": 75420 }, { "epoch": 6.27, "learning_rate": 3.1652689632236787e-06, "loss": 0.7994, "step": 75430 }, { "epoch": 6.27, "learning_rate": 3.1651581076961446e-06, "loss": 0.8634, "step": 75440 }, { "epoch": 6.27, "learning_rate": 3.1650472521686113e-06, "loss": 0.8691, "step": 75450 }, { "epoch": 6.27, "learning_rate": 3.1649363966410776e-06, "loss": 0.777, "step": 75460 }, { "epoch": 6.27, "learning_rate": 3.1648255411135435e-06, "loss": 0.778, "step": 75470 }, { "epoch": 6.27, "learning_rate": 3.16471468558601e-06, "loss": 0.8004, "step": 75480 }, { "epoch": 6.27, "learning_rate": 3.164603830058476e-06, "loss": 0.7932, "step": 75490 }, { "epoch": 6.28, "learning_rate": 3.1644929745309424e-06, "loss": 0.8, "step": 75500 }, { "epoch": 6.28, "learning_rate": 3.1643821190034086e-06, "loss": 0.7712, "step": 75510 }, { "epoch": 6.28, "learning_rate": 3.164271263475875e-06, "loss": 0.733, "step": 75520 }, { "epoch": 6.28, "learning_rate": 3.1641604079483412e-06, "loss": 0.7461, "step": 75530 }, { "epoch": 6.28, "learning_rate": 3.1640495524208075e-06, "loss": 0.8578, "step": 75540 }, { "epoch": 6.28, "learning_rate": 3.1639386968932734e-06, "loss": 0.8012, "step": 75550 }, { "epoch": 6.28, "learning_rate": 3.16382784136574e-06, "loss": 0.7132, "step": 75560 }, { "epoch": 6.28, "learning_rate": 3.163716985838206e-06, "loss": 0.8486, "step": 75570 }, { "epoch": 6.28, "learning_rate": 3.1636061303106723e-06, "loss": 0.8003, "step": 75580 }, { "epoch": 6.28, "learning_rate": 3.163495274783139e-06, "loss": 0.8382, "step": 75590 }, { "epoch": 6.28, "learning_rate": 3.163384419255605e-06, "loss": 0.8431, "step": 75600 }, { "epoch": 6.28, "learning_rate": 3.1632735637280716e-06, "loss": 0.8084, "step": 75610 }, { "epoch": 6.29, "learning_rate": 3.1631627082005375e-06, "loss": 0.7979, "step": 75620 }, { "epoch": 6.29, "learning_rate": 3.1630518526730038e-06, "loss": 0.832, "step": 75630 }, { "epoch": 6.29, "learning_rate": 3.16294099714547e-06, "loss": 0.8107, "step": 75640 }, { "epoch": 6.29, "learning_rate": 3.1628301416179364e-06, "loss": 0.7577, "step": 75650 }, { "epoch": 6.29, "learning_rate": 3.1627192860904022e-06, "loss": 0.8479, "step": 75660 }, { "epoch": 6.29, "learning_rate": 3.162608430562869e-06, "loss": 0.7919, "step": 75670 }, { "epoch": 6.29, "learning_rate": 3.162497575035335e-06, "loss": 0.7695, "step": 75680 }, { "epoch": 6.29, "learning_rate": 3.1623867195078015e-06, "loss": 0.8799, "step": 75690 }, { "epoch": 6.29, "learning_rate": 3.1622758639802674e-06, "loss": 0.8057, "step": 75700 }, { "epoch": 6.29, "learning_rate": 3.1621650084527337e-06, "loss": 0.8055, "step": 75710 }, { "epoch": 6.29, "learning_rate": 3.1620541529252004e-06, "loss": 0.9023, "step": 75720 }, { "epoch": 6.29, "learning_rate": 3.1619432973976663e-06, "loss": 0.8423, "step": 75730 }, { "epoch": 6.3, "learning_rate": 3.1618324418701326e-06, "loss": 0.7954, "step": 75740 }, { "epoch": 6.3, "learning_rate": 3.161721586342599e-06, "loss": 0.8778, "step": 75750 }, { "epoch": 6.3, "learning_rate": 3.161610730815065e-06, "loss": 0.772, "step": 75760 }, { "epoch": 6.3, "learning_rate": 3.161499875287531e-06, "loss": 0.7924, "step": 75770 }, { "epoch": 6.3, "learning_rate": 3.1613890197599978e-06, "loss": 0.7497, "step": 75780 }, { "epoch": 6.3, "learning_rate": 3.1612781642324636e-06, "loss": 0.8281, "step": 75790 }, { "epoch": 6.3, "learning_rate": 3.1611673087049304e-06, "loss": 0.7887, "step": 75800 }, { "epoch": 6.3, "learning_rate": 3.1610564531773962e-06, "loss": 0.8205, "step": 75810 }, { "epoch": 6.3, "learning_rate": 3.1609455976498625e-06, "loss": 0.7777, "step": 75820 }, { "epoch": 6.3, "learning_rate": 3.1608347421223293e-06, "loss": 0.7253, "step": 75830 }, { "epoch": 6.3, "learning_rate": 3.160723886594795e-06, "loss": 0.8631, "step": 75840 }, { "epoch": 6.3, "learning_rate": 3.1606130310672614e-06, "loss": 0.8186, "step": 75850 }, { "epoch": 6.31, "learning_rate": 3.1605021755397277e-06, "loss": 0.7478, "step": 75860 }, { "epoch": 6.31, "learning_rate": 3.160391320012194e-06, "loss": 0.7884, "step": 75870 }, { "epoch": 6.31, "learning_rate": 3.1602804644846603e-06, "loss": 0.8283, "step": 75880 }, { "epoch": 6.31, "learning_rate": 3.1601696089571266e-06, "loss": 0.8372, "step": 75890 }, { "epoch": 6.31, "learning_rate": 3.1600587534295925e-06, "loss": 0.8859, "step": 75900 }, { "epoch": 6.31, "learning_rate": 3.159947897902059e-06, "loss": 0.8582, "step": 75910 }, { "epoch": 6.31, "learning_rate": 3.159837042374525e-06, "loss": 0.7857, "step": 75920 }, { "epoch": 6.31, "learning_rate": 3.1597261868469914e-06, "loss": 0.8273, "step": 75930 }, { "epoch": 6.31, "learning_rate": 3.1596153313194577e-06, "loss": 0.8288, "step": 75940 }, { "epoch": 6.31, "learning_rate": 3.159504475791924e-06, "loss": 0.771, "step": 75950 }, { "epoch": 6.31, "learning_rate": 3.1593936202643907e-06, "loss": 0.8133, "step": 75960 }, { "epoch": 6.31, "learning_rate": 3.1592827647368565e-06, "loss": 0.8379, "step": 75970 }, { "epoch": 6.32, "learning_rate": 3.159171909209323e-06, "loss": 0.6959, "step": 75980 }, { "epoch": 6.32, "learning_rate": 3.159061053681789e-06, "loss": 0.837, "step": 75990 }, { "epoch": 6.32, "learning_rate": 3.1589501981542554e-06, "loss": 0.8534, "step": 76000 }, { "epoch": 6.32, "learning_rate": 3.1588393426267213e-06, "loss": 0.7615, "step": 76010 }, { "epoch": 6.32, "learning_rate": 3.158728487099188e-06, "loss": 0.844, "step": 76020 }, { "epoch": 6.32, "learning_rate": 3.158617631571654e-06, "loss": 0.8453, "step": 76030 }, { "epoch": 6.32, "learning_rate": 3.1585067760441206e-06, "loss": 0.7898, "step": 76040 }, { "epoch": 6.32, "learning_rate": 3.1583959205165865e-06, "loss": 0.7973, "step": 76050 }, { "epoch": 6.32, "learning_rate": 3.1582850649890528e-06, "loss": 0.7811, "step": 76060 }, { "epoch": 6.32, "learning_rate": 3.158174209461519e-06, "loss": 0.8034, "step": 76070 }, { "epoch": 6.32, "learning_rate": 3.1580633539339854e-06, "loss": 0.8227, "step": 76080 }, { "epoch": 6.32, "learning_rate": 3.1579524984064517e-06, "loss": 0.8484, "step": 76090 }, { "epoch": 6.33, "learning_rate": 3.157841642878918e-06, "loss": 0.8849, "step": 76100 }, { "epoch": 6.33, "learning_rate": 3.1577307873513842e-06, "loss": 0.7812, "step": 76110 }, { "epoch": 6.33, "learning_rate": 3.1576199318238505e-06, "loss": 0.8013, "step": 76120 }, { "epoch": 6.33, "learning_rate": 3.157509076296317e-06, "loss": 0.8663, "step": 76130 }, { "epoch": 6.33, "learning_rate": 3.1573982207687827e-06, "loss": 0.9295, "step": 76140 }, { "epoch": 6.33, "learning_rate": 3.1572873652412494e-06, "loss": 0.8197, "step": 76150 }, { "epoch": 6.33, "learning_rate": 3.1571765097137153e-06, "loss": 0.8844, "step": 76160 }, { "epoch": 6.33, "learning_rate": 3.1570656541861816e-06, "loss": 0.7411, "step": 76170 }, { "epoch": 6.33, "learning_rate": 3.156954798658648e-06, "loss": 0.8533, "step": 76180 }, { "epoch": 6.33, "learning_rate": 3.156843943131114e-06, "loss": 0.8323, "step": 76190 }, { "epoch": 6.33, "learning_rate": 3.156733087603581e-06, "loss": 0.806, "step": 76200 }, { "epoch": 6.33, "learning_rate": 3.1566222320760468e-06, "loss": 0.8355, "step": 76210 }, { "epoch": 6.34, "learning_rate": 3.156511376548513e-06, "loss": 0.785, "step": 76220 }, { "epoch": 6.34, "learning_rate": 3.1564005210209794e-06, "loss": 0.8027, "step": 76230 }, { "epoch": 6.34, "learning_rate": 3.1562896654934457e-06, "loss": 0.8634, "step": 76240 }, { "epoch": 6.34, "learning_rate": 3.1561788099659115e-06, "loss": 0.7667, "step": 76250 }, { "epoch": 6.34, "learning_rate": 3.1560679544383783e-06, "loss": 0.7721, "step": 76260 }, { "epoch": 6.34, "learning_rate": 3.155957098910844e-06, "loss": 0.8844, "step": 76270 }, { "epoch": 6.34, "learning_rate": 3.1558462433833104e-06, "loss": 0.7984, "step": 76280 }, { "epoch": 6.34, "learning_rate": 3.1557353878557767e-06, "loss": 0.8709, "step": 76290 }, { "epoch": 6.34, "learning_rate": 3.155624532328243e-06, "loss": 0.8238, "step": 76300 }, { "epoch": 6.34, "learning_rate": 3.1555136768007093e-06, "loss": 0.826, "step": 76310 }, { "epoch": 6.34, "learning_rate": 3.1554028212731756e-06, "loss": 0.7622, "step": 76320 }, { "epoch": 6.34, "learning_rate": 3.155291965745642e-06, "loss": 0.7847, "step": 76330 }, { "epoch": 6.35, "learning_rate": 3.155181110218108e-06, "loss": 0.7753, "step": 76340 }, { "epoch": 6.35, "learning_rate": 3.1550702546905745e-06, "loss": 0.8092, "step": 76350 }, { "epoch": 6.35, "learning_rate": 3.1549593991630404e-06, "loss": 0.8311, "step": 76360 }, { "epoch": 6.35, "learning_rate": 3.154848543635507e-06, "loss": 0.8588, "step": 76370 }, { "epoch": 6.35, "learning_rate": 3.154737688107973e-06, "loss": 0.7448, "step": 76380 }, { "epoch": 6.35, "learning_rate": 3.1546268325804397e-06, "loss": 0.7906, "step": 76390 }, { "epoch": 6.35, "learning_rate": 3.1545159770529055e-06, "loss": 0.8203, "step": 76400 }, { "epoch": 6.35, "learning_rate": 3.154405121525372e-06, "loss": 0.866, "step": 76410 }, { "epoch": 6.35, "learning_rate": 3.154294265997838e-06, "loss": 0.7717, "step": 76420 }, { "epoch": 6.35, "learning_rate": 3.1541834104703044e-06, "loss": 0.7708, "step": 76430 }, { "epoch": 6.35, "learning_rate": 3.1540725549427703e-06, "loss": 0.8663, "step": 76440 }, { "epoch": 6.35, "learning_rate": 3.153961699415237e-06, "loss": 0.7846, "step": 76450 }, { "epoch": 6.36, "learning_rate": 3.1538508438877033e-06, "loss": 0.8798, "step": 76460 }, { "epoch": 6.36, "learning_rate": 3.1537399883601696e-06, "loss": 0.8848, "step": 76470 }, { "epoch": 6.36, "learning_rate": 3.153629132832636e-06, "loss": 0.8718, "step": 76480 }, { "epoch": 6.36, "learning_rate": 3.1535182773051018e-06, "loss": 0.803, "step": 76490 }, { "epoch": 6.36, "learning_rate": 3.1534074217775685e-06, "loss": 0.8313, "step": 76500 }, { "epoch": 6.36, "learning_rate": 3.1532965662500344e-06, "loss": 0.7618, "step": 76510 }, { "epoch": 6.36, "learning_rate": 3.1531857107225007e-06, "loss": 0.792, "step": 76520 }, { "epoch": 6.36, "learning_rate": 3.153074855194967e-06, "loss": 0.7312, "step": 76530 }, { "epoch": 6.36, "learning_rate": 3.1529639996674333e-06, "loss": 0.8457, "step": 76540 }, { "epoch": 6.36, "learning_rate": 3.152853144139899e-06, "loss": 0.8871, "step": 76550 }, { "epoch": 6.36, "learning_rate": 3.152742288612366e-06, "loss": 0.8517, "step": 76560 }, { "epoch": 6.36, "learning_rate": 3.152631433084832e-06, "loss": 0.7606, "step": 76570 }, { "epoch": 6.37, "learning_rate": 3.1525205775572984e-06, "loss": 0.7852, "step": 76580 }, { "epoch": 6.37, "learning_rate": 3.1524097220297647e-06, "loss": 0.8568, "step": 76590 }, { "epoch": 6.37, "learning_rate": 3.1522988665022306e-06, "loss": 0.8616, "step": 76600 }, { "epoch": 6.37, "learning_rate": 3.1521880109746973e-06, "loss": 0.8133, "step": 76610 }, { "epoch": 6.37, "learning_rate": 3.152077155447163e-06, "loss": 0.7871, "step": 76620 }, { "epoch": 6.37, "learning_rate": 3.15196629991963e-06, "loss": 0.816, "step": 76630 }, { "epoch": 6.37, "learning_rate": 3.1518554443920958e-06, "loss": 0.859, "step": 76640 }, { "epoch": 6.37, "learning_rate": 3.151744588864562e-06, "loss": 0.8457, "step": 76650 }, { "epoch": 6.37, "learning_rate": 3.1516337333370284e-06, "loss": 0.7837, "step": 76660 }, { "epoch": 6.37, "learning_rate": 3.1515228778094947e-06, "loss": 0.8455, "step": 76670 }, { "epoch": 6.37, "learning_rate": 3.1514120222819605e-06, "loss": 0.7954, "step": 76680 }, { "epoch": 6.37, "learning_rate": 3.1513011667544273e-06, "loss": 0.8598, "step": 76690 }, { "epoch": 6.38, "learning_rate": 3.1511903112268936e-06, "loss": 0.8176, "step": 76700 }, { "epoch": 6.38, "learning_rate": 3.1510794556993594e-06, "loss": 0.8059, "step": 76710 }, { "epoch": 6.38, "learning_rate": 3.150968600171826e-06, "loss": 0.7554, "step": 76720 }, { "epoch": 6.38, "learning_rate": 3.150857744644292e-06, "loss": 0.8201, "step": 76730 }, { "epoch": 6.38, "learning_rate": 3.1507468891167587e-06, "loss": 0.8058, "step": 76740 }, { "epoch": 6.38, "learning_rate": 3.1506360335892246e-06, "loss": 0.8644, "step": 76750 }, { "epoch": 6.38, "learning_rate": 3.150525178061691e-06, "loss": 0.8705, "step": 76760 }, { "epoch": 6.38, "learning_rate": 3.150414322534157e-06, "loss": 0.8006, "step": 76770 }, { "epoch": 6.38, "learning_rate": 3.1503034670066235e-06, "loss": 0.8283, "step": 76780 }, { "epoch": 6.38, "learning_rate": 3.1501926114790894e-06, "loss": 0.7804, "step": 76790 }, { "epoch": 6.38, "learning_rate": 3.150081755951556e-06, "loss": 0.8248, "step": 76800 }, { "epoch": 6.38, "learning_rate": 3.1499709004240224e-06, "loss": 0.8273, "step": 76810 }, { "epoch": 6.39, "learning_rate": 3.1498600448964887e-06, "loss": 0.81, "step": 76820 }, { "epoch": 6.39, "learning_rate": 3.149749189368955e-06, "loss": 0.769, "step": 76830 }, { "epoch": 6.39, "learning_rate": 3.149638333841421e-06, "loss": 0.8574, "step": 76840 }, { "epoch": 6.39, "learning_rate": 3.1495274783138876e-06, "loss": 0.8419, "step": 76850 }, { "epoch": 6.39, "learning_rate": 3.1494166227863534e-06, "loss": 0.785, "step": 76860 }, { "epoch": 6.39, "learning_rate": 3.1493057672588197e-06, "loss": 0.8179, "step": 76870 }, { "epoch": 6.39, "learning_rate": 3.149194911731286e-06, "loss": 0.7753, "step": 76880 }, { "epoch": 6.39, "learning_rate": 3.1490840562037523e-06, "loss": 0.8622, "step": 76890 }, { "epoch": 6.39, "learning_rate": 3.1489732006762186e-06, "loss": 0.8582, "step": 76900 }, { "epoch": 6.39, "learning_rate": 3.148862345148685e-06, "loss": 0.8742, "step": 76910 }, { "epoch": 6.39, "learning_rate": 3.1487514896211508e-06, "loss": 0.8538, "step": 76920 }, { "epoch": 6.39, "learning_rate": 3.1486406340936175e-06, "loss": 0.8898, "step": 76930 }, { "epoch": 6.4, "learning_rate": 3.148529778566084e-06, "loss": 0.8726, "step": 76940 }, { "epoch": 6.4, "learning_rate": 3.1484189230385497e-06, "loss": 0.9027, "step": 76950 }, { "epoch": 6.4, "learning_rate": 3.1483080675110164e-06, "loss": 0.8363, "step": 76960 }, { "epoch": 6.4, "learning_rate": 3.1481972119834823e-06, "loss": 0.8562, "step": 76970 }, { "epoch": 6.4, "learning_rate": 3.148086356455949e-06, "loss": 0.8242, "step": 76980 }, { "epoch": 6.4, "learning_rate": 3.147975500928415e-06, "loss": 0.8822, "step": 76990 }, { "epoch": 6.4, "learning_rate": 3.147864645400881e-06, "loss": 0.8587, "step": 77000 }, { "epoch": 6.4, "learning_rate": 3.1477537898733474e-06, "loss": 0.8366, "step": 77010 }, { "epoch": 6.4, "learning_rate": 3.1476429343458137e-06, "loss": 0.8425, "step": 77020 }, { "epoch": 6.4, "learning_rate": 3.1475320788182796e-06, "loss": 0.7265, "step": 77030 }, { "epoch": 6.4, "learning_rate": 3.1474212232907463e-06, "loss": 0.8428, "step": 77040 }, { "epoch": 6.4, "learning_rate": 3.147310367763212e-06, "loss": 0.8301, "step": 77050 }, { "epoch": 6.41, "learning_rate": 3.1471995122356785e-06, "loss": 0.8006, "step": 77060 }, { "epoch": 6.41, "learning_rate": 3.1470886567081452e-06, "loss": 0.7721, "step": 77070 }, { "epoch": 6.41, "learning_rate": 3.146977801180611e-06, "loss": 0.7777, "step": 77080 }, { "epoch": 6.41, "learning_rate": 3.146866945653078e-06, "loss": 0.7778, "step": 77090 }, { "epoch": 6.41, "learning_rate": 3.1467560901255437e-06, "loss": 0.864, "step": 77100 }, { "epoch": 6.41, "learning_rate": 3.14664523459801e-06, "loss": 0.8084, "step": 77110 }, { "epoch": 6.41, "learning_rate": 3.1465343790704763e-06, "loss": 0.8002, "step": 77120 }, { "epoch": 6.41, "learning_rate": 3.1464235235429426e-06, "loss": 0.8554, "step": 77130 }, { "epoch": 6.41, "learning_rate": 3.1463126680154084e-06, "loss": 0.8943, "step": 77140 }, { "epoch": 6.41, "learning_rate": 3.146201812487875e-06, "loss": 0.789, "step": 77150 }, { "epoch": 6.41, "learning_rate": 3.146090956960341e-06, "loss": 0.8463, "step": 77160 }, { "epoch": 6.41, "learning_rate": 3.1459801014328077e-06, "loss": 0.7824, "step": 77170 }, { "epoch": 6.42, "learning_rate": 3.145869245905274e-06, "loss": 0.8174, "step": 77180 }, { "epoch": 6.42, "learning_rate": 3.14575839037774e-06, "loss": 0.8717, "step": 77190 }, { "epoch": 6.42, "learning_rate": 3.1456475348502066e-06, "loss": 0.8405, "step": 77200 }, { "epoch": 6.42, "learning_rate": 3.145547764875426e-06, "loss": 0.8034, "step": 77210 }, { "epoch": 6.42, "learning_rate": 3.145436909347892e-06, "loss": 0.8108, "step": 77220 }, { "epoch": 6.42, "learning_rate": 3.1453260538203583e-06, "loss": 0.7849, "step": 77230 }, { "epoch": 6.42, "learning_rate": 3.1452151982928246e-06, "loss": 0.8108, "step": 77240 }, { "epoch": 6.42, "learning_rate": 3.145104342765291e-06, "loss": 0.8437, "step": 77250 }, { "epoch": 6.42, "learning_rate": 3.1449934872377572e-06, "loss": 0.7873, "step": 77260 }, { "epoch": 6.42, "learning_rate": 3.1448826317102235e-06, "loss": 0.8205, "step": 77270 }, { "epoch": 6.42, "learning_rate": 3.14477177618269e-06, "loss": 0.7919, "step": 77280 }, { "epoch": 6.42, "learning_rate": 3.144660920655156e-06, "loss": 0.8309, "step": 77290 }, { "epoch": 6.43, "learning_rate": 3.1445500651276224e-06, "loss": 0.8898, "step": 77300 }, { "epoch": 6.43, "learning_rate": 3.1444392096000883e-06, "loss": 0.7403, "step": 77310 }, { "epoch": 6.43, "learning_rate": 3.144328354072555e-06, "loss": 0.8105, "step": 77320 }, { "epoch": 6.43, "learning_rate": 3.144217498545021e-06, "loss": 0.8015, "step": 77330 }, { "epoch": 6.43, "learning_rate": 3.1441066430174876e-06, "loss": 0.8477, "step": 77340 }, { "epoch": 6.43, "learning_rate": 3.1439957874899535e-06, "loss": 0.828, "step": 77350 }, { "epoch": 6.43, "learning_rate": 3.1438849319624198e-06, "loss": 0.8272, "step": 77360 }, { "epoch": 6.43, "learning_rate": 3.143774076434886e-06, "loss": 0.8242, "step": 77370 }, { "epoch": 6.43, "learning_rate": 3.1436632209073523e-06, "loss": 0.8304, "step": 77380 }, { "epoch": 6.43, "learning_rate": 3.1435523653798186e-06, "loss": 0.8017, "step": 77390 }, { "epoch": 6.43, "learning_rate": 3.143441509852285e-06, "loss": 0.8427, "step": 77400 }, { "epoch": 6.43, "learning_rate": 3.1433306543247512e-06, "loss": 0.748, "step": 77410 }, { "epoch": 6.44, "learning_rate": 3.1432197987972175e-06, "loss": 0.7773, "step": 77420 }, { "epoch": 6.44, "learning_rate": 3.143108943269684e-06, "loss": 0.8558, "step": 77430 }, { "epoch": 6.44, "learning_rate": 3.1429980877421497e-06, "loss": 0.8218, "step": 77440 }, { "epoch": 6.44, "learning_rate": 3.1428872322146164e-06, "loss": 0.8112, "step": 77450 }, { "epoch": 6.44, "learning_rate": 3.1427763766870823e-06, "loss": 0.8151, "step": 77460 }, { "epoch": 6.44, "learning_rate": 3.1426655211595486e-06, "loss": 0.8046, "step": 77470 }, { "epoch": 6.44, "learning_rate": 3.142554665632015e-06, "loss": 0.7468, "step": 77480 }, { "epoch": 6.44, "learning_rate": 3.142443810104481e-06, "loss": 0.8485, "step": 77490 }, { "epoch": 6.44, "learning_rate": 3.142332954576947e-06, "loss": 0.7449, "step": 77500 }, { "epoch": 6.44, "learning_rate": 3.1422220990494138e-06, "loss": 0.8256, "step": 77510 }, { "epoch": 6.44, "learning_rate": 3.14211124352188e-06, "loss": 0.7824, "step": 77520 }, { "epoch": 6.44, "learning_rate": 3.1420003879943463e-06, "loss": 0.8043, "step": 77530 }, { "epoch": 6.45, "learning_rate": 3.141900618019566e-06, "loss": 0.8451, "step": 77540 }, { "epoch": 6.45, "learning_rate": 3.141789762492032e-06, "loss": 0.7815, "step": 77550 }, { "epoch": 6.45, "learning_rate": 3.141678906964498e-06, "loss": 0.796, "step": 77560 }, { "epoch": 6.45, "learning_rate": 3.1415680514369648e-06, "loss": 0.8218, "step": 77570 }, { "epoch": 6.45, "learning_rate": 3.1414571959094306e-06, "loss": 0.799, "step": 77580 }, { "epoch": 6.45, "learning_rate": 3.1413463403818974e-06, "loss": 0.8303, "step": 77590 }, { "epoch": 6.45, "learning_rate": 3.1412354848543637e-06, "loss": 0.8166, "step": 77600 }, { "epoch": 6.45, "learning_rate": 3.1411246293268295e-06, "loss": 0.8096, "step": 77610 }, { "epoch": 6.45, "learning_rate": 3.1410137737992962e-06, "loss": 0.8804, "step": 77620 }, { "epoch": 6.45, "learning_rate": 3.140902918271762e-06, "loss": 0.7076, "step": 77630 }, { "epoch": 6.45, "learning_rate": 3.1407920627442284e-06, "loss": 0.822, "step": 77640 }, { "epoch": 6.45, "learning_rate": 3.1406812072166947e-06, "loss": 0.7916, "step": 77650 }, { "epoch": 6.45, "learning_rate": 3.140570351689161e-06, "loss": 0.7842, "step": 77660 }, { "epoch": 6.46, "learning_rate": 3.140459496161627e-06, "loss": 0.7805, "step": 77670 }, { "epoch": 6.46, "learning_rate": 3.1403486406340936e-06, "loss": 0.7856, "step": 77680 }, { "epoch": 6.46, "learning_rate": 3.1402377851065595e-06, "loss": 0.8645, "step": 77690 }, { "epoch": 6.46, "learning_rate": 3.140126929579026e-06, "loss": 0.8403, "step": 77700 }, { "epoch": 6.46, "learning_rate": 3.140016074051492e-06, "loss": 0.8078, "step": 77710 }, { "epoch": 6.46, "learning_rate": 3.1399052185239584e-06, "loss": 0.8046, "step": 77720 }, { "epoch": 6.46, "learning_rate": 3.139794362996425e-06, "loss": 0.7954, "step": 77730 }, { "epoch": 6.46, "learning_rate": 3.139683507468891e-06, "loss": 0.8693, "step": 77740 }, { "epoch": 6.46, "learning_rate": 3.1395726519413572e-06, "loss": 0.8487, "step": 77750 }, { "epoch": 6.46, "learning_rate": 3.1394617964138235e-06, "loss": 0.8672, "step": 77760 }, { "epoch": 6.46, "learning_rate": 3.13935094088629e-06, "loss": 0.8157, "step": 77770 }, { "epoch": 6.46, "learning_rate": 3.139240085358756e-06, "loss": 0.8149, "step": 77780 }, { "epoch": 6.47, "learning_rate": 3.1391292298312224e-06, "loss": 0.8557, "step": 77790 }, { "epoch": 6.47, "learning_rate": 3.1390183743036883e-06, "loss": 0.8117, "step": 77800 }, { "epoch": 6.47, "learning_rate": 3.138907518776155e-06, "loss": 0.8089, "step": 77810 }, { "epoch": 6.47, "learning_rate": 3.138796663248621e-06, "loss": 0.8467, "step": 77820 }, { "epoch": 6.47, "learning_rate": 3.138685807721087e-06, "loss": 0.8193, "step": 77830 }, { "epoch": 6.47, "learning_rate": 3.1385749521935535e-06, "loss": 0.8804, "step": 77840 }, { "epoch": 6.47, "learning_rate": 3.1384640966660198e-06, "loss": 0.8138, "step": 77850 }, { "epoch": 6.47, "learning_rate": 3.1383532411384865e-06, "loss": 0.8166, "step": 77860 }, { "epoch": 6.47, "learning_rate": 3.1382423856109524e-06, "loss": 0.7756, "step": 77870 }, { "epoch": 6.47, "learning_rate": 3.1381315300834187e-06, "loss": 0.8684, "step": 77880 }, { "epoch": 6.47, "learning_rate": 3.138020674555885e-06, "loss": 0.7858, "step": 77890 }, { "epoch": 6.47, "learning_rate": 3.1379098190283512e-06, "loss": 0.8381, "step": 77900 }, { "epoch": 6.48, "learning_rate": 3.137798963500817e-06, "loss": 0.8016, "step": 77910 }, { "epoch": 6.48, "learning_rate": 3.137688107973284e-06, "loss": 0.7977, "step": 77920 }, { "epoch": 6.48, "learning_rate": 3.1375772524457497e-06, "loss": 0.7587, "step": 77930 }, { "epoch": 6.48, "learning_rate": 3.1374663969182164e-06, "loss": 0.785, "step": 77940 }, { "epoch": 6.48, "learning_rate": 3.1373555413906823e-06, "loss": 0.8111, "step": 77950 }, { "epoch": 6.48, "learning_rate": 3.1372446858631486e-06, "loss": 0.8653, "step": 77960 }, { "epoch": 6.48, "learning_rate": 3.1371338303356153e-06, "loss": 0.7883, "step": 77970 }, { "epoch": 6.48, "learning_rate": 3.137022974808081e-06, "loss": 0.8385, "step": 77980 }, { "epoch": 6.48, "learning_rate": 3.1369121192805475e-06, "loss": 0.8216, "step": 77990 }, { "epoch": 6.48, "learning_rate": 3.1368012637530138e-06, "loss": 0.8121, "step": 78000 }, { "epoch": 6.48, "learning_rate": 3.13669040822548e-06, "loss": 0.7876, "step": 78010 }, { "epoch": 6.48, "learning_rate": 3.1365795526979464e-06, "loss": 0.7588, "step": 78020 }, { "epoch": 6.49, "learning_rate": 3.1364686971704127e-06, "loss": 0.7652, "step": 78030 }, { "epoch": 6.49, "learning_rate": 3.1363578416428785e-06, "loss": 0.8854, "step": 78040 }, { "epoch": 6.49, "learning_rate": 3.1362469861153453e-06, "loss": 0.8564, "step": 78050 }, { "epoch": 6.49, "learning_rate": 3.136136130587811e-06, "loss": 0.7738, "step": 78060 }, { "epoch": 6.49, "learning_rate": 3.1360252750602774e-06, "loss": 0.8556, "step": 78070 }, { "epoch": 6.49, "learning_rate": 3.1359144195327437e-06, "loss": 0.7785, "step": 78080 }, { "epoch": 6.49, "learning_rate": 3.13580356400521e-06, "loss": 0.8571, "step": 78090 }, { "epoch": 6.49, "learning_rate": 3.1356927084776767e-06, "loss": 0.8912, "step": 78100 }, { "epoch": 6.49, "learning_rate": 3.1355818529501426e-06, "loss": 0.7601, "step": 78110 }, { "epoch": 6.49, "learning_rate": 3.135470997422609e-06, "loss": 0.788, "step": 78120 }, { "epoch": 6.49, "learning_rate": 3.135360141895075e-06, "loss": 0.8555, "step": 78130 }, { "epoch": 6.49, "learning_rate": 3.1352492863675415e-06, "loss": 0.8292, "step": 78140 }, { "epoch": 6.5, "learning_rate": 3.1351384308400074e-06, "loss": 0.8313, "step": 78150 }, { "epoch": 6.5, "learning_rate": 3.135027575312474e-06, "loss": 0.7466, "step": 78160 }, { "epoch": 6.5, "learning_rate": 3.13491671978494e-06, "loss": 0.8249, "step": 78170 }, { "epoch": 6.5, "learning_rate": 3.1348058642574062e-06, "loss": 0.766, "step": 78180 }, { "epoch": 6.5, "learning_rate": 3.1346950087298725e-06, "loss": 0.8767, "step": 78190 }, { "epoch": 6.5, "learning_rate": 3.134584153202339e-06, "loss": 0.8302, "step": 78200 }, { "epoch": 6.5, "learning_rate": 3.134473297674805e-06, "loss": 0.8006, "step": 78210 }, { "epoch": 6.5, "learning_rate": 3.1343624421472714e-06, "loss": 0.7519, "step": 78220 }, { "epoch": 6.5, "learning_rate": 3.1342515866197377e-06, "loss": 0.8133, "step": 78230 }, { "epoch": 6.5, "learning_rate": 3.134140731092204e-06, "loss": 0.9171, "step": 78240 }, { "epoch": 6.5, "learning_rate": 3.1340298755646703e-06, "loss": 0.7617, "step": 78250 }, { "epoch": 6.5, "learning_rate": 3.133919020037136e-06, "loss": 0.8772, "step": 78260 }, { "epoch": 6.51, "learning_rate": 3.133808164509603e-06, "loss": 0.7934, "step": 78270 }, { "epoch": 6.51, "learning_rate": 3.1336973089820688e-06, "loss": 0.8178, "step": 78280 }, { "epoch": 6.51, "learning_rate": 3.1335864534545355e-06, "loss": 0.8425, "step": 78290 }, { "epoch": 6.51, "learning_rate": 3.1334755979270014e-06, "loss": 0.8721, "step": 78300 }, { "epoch": 6.51, "learning_rate": 3.1333647423994677e-06, "loss": 0.8579, "step": 78310 }, { "epoch": 6.51, "learning_rate": 3.133253886871934e-06, "loss": 0.8513, "step": 78320 }, { "epoch": 6.51, "learning_rate": 3.1331430313444003e-06, "loss": 0.8655, "step": 78330 }, { "epoch": 6.51, "learning_rate": 3.1330321758168665e-06, "loss": 0.8891, "step": 78340 }, { "epoch": 6.51, "learning_rate": 3.132921320289333e-06, "loss": 0.8203, "step": 78350 }, { "epoch": 6.51, "learning_rate": 3.132810464761799e-06, "loss": 0.7738, "step": 78360 }, { "epoch": 6.51, "learning_rate": 3.1326996092342654e-06, "loss": 0.7657, "step": 78370 }, { "epoch": 6.51, "learning_rate": 3.1325887537067317e-06, "loss": 0.8175, "step": 78380 }, { "epoch": 6.52, "learning_rate": 3.1324778981791976e-06, "loss": 0.8046, "step": 78390 }, { "epoch": 6.52, "learning_rate": 3.1323670426516643e-06, "loss": 0.8782, "step": 78400 }, { "epoch": 6.52, "learning_rate": 3.13225618712413e-06, "loss": 0.848, "step": 78410 }, { "epoch": 6.52, "learning_rate": 3.1321453315965965e-06, "loss": 0.7686, "step": 78420 }, { "epoch": 6.52, "learning_rate": 3.1320344760690628e-06, "loss": 0.8593, "step": 78430 }, { "epoch": 6.52, "learning_rate": 3.131923620541529e-06, "loss": 0.8593, "step": 78440 }, { "epoch": 6.52, "learning_rate": 3.131812765013995e-06, "loss": 0.8216, "step": 78450 }, { "epoch": 6.52, "learning_rate": 3.1317019094864617e-06, "loss": 0.8332, "step": 78460 }, { "epoch": 6.52, "learning_rate": 3.131591053958928e-06, "loss": 0.803, "step": 78470 }, { "epoch": 6.52, "learning_rate": 3.1314801984313943e-06, "loss": 0.7885, "step": 78480 }, { "epoch": 6.52, "learning_rate": 3.1313693429038606e-06, "loss": 0.8201, "step": 78490 }, { "epoch": 6.52, "learning_rate": 3.1312584873763264e-06, "loss": 0.8241, "step": 78500 }, { "epoch": 6.53, "learning_rate": 3.131147631848793e-06, "loss": 0.8247, "step": 78510 }, { "epoch": 6.53, "learning_rate": 3.131036776321259e-06, "loss": 0.8076, "step": 78520 }, { "epoch": 6.53, "learning_rate": 3.1309259207937257e-06, "loss": 0.8111, "step": 78530 }, { "epoch": 6.53, "learning_rate": 3.1308150652661916e-06, "loss": 0.8795, "step": 78540 }, { "epoch": 6.53, "learning_rate": 3.130704209738658e-06, "loss": 0.8644, "step": 78550 }, { "epoch": 6.53, "learning_rate": 3.130593354211124e-06, "loss": 0.8035, "step": 78560 }, { "epoch": 6.53, "learning_rate": 3.1304824986835905e-06, "loss": 0.8019, "step": 78570 }, { "epoch": 6.53, "learning_rate": 3.1303716431560564e-06, "loss": 0.8067, "step": 78580 }, { "epoch": 6.53, "learning_rate": 3.130260787628523e-06, "loss": 0.8529, "step": 78590 }, { "epoch": 6.53, "learning_rate": 3.1301499321009894e-06, "loss": 0.8472, "step": 78600 }, { "epoch": 6.53, "learning_rate": 3.1300390765734553e-06, "loss": 0.8069, "step": 78610 }, { "epoch": 6.53, "learning_rate": 3.129928221045922e-06, "loss": 0.7872, "step": 78620 }, { "epoch": 6.54, "learning_rate": 3.129817365518388e-06, "loss": 0.7979, "step": 78630 }, { "epoch": 6.54, "learning_rate": 3.1297065099908546e-06, "loss": 0.8587, "step": 78640 }, { "epoch": 6.54, "learning_rate": 3.1295956544633204e-06, "loss": 0.7861, "step": 78650 }, { "epoch": 6.54, "learning_rate": 3.1294847989357867e-06, "loss": 0.7548, "step": 78660 }, { "epoch": 6.54, "learning_rate": 3.129373943408253e-06, "loss": 0.7905, "step": 78670 }, { "epoch": 6.54, "learning_rate": 3.1292630878807193e-06, "loss": 0.8247, "step": 78680 }, { "epoch": 6.54, "learning_rate": 3.129152232353185e-06, "loss": 0.869, "step": 78690 }, { "epoch": 6.54, "learning_rate": 3.129041376825652e-06, "loss": 0.8887, "step": 78700 }, { "epoch": 6.54, "learning_rate": 3.128930521298118e-06, "loss": 0.8571, "step": 78710 }, { "epoch": 6.54, "learning_rate": 3.1288196657705845e-06, "loss": 0.7747, "step": 78720 }, { "epoch": 6.54, "learning_rate": 3.128708810243051e-06, "loss": 0.835, "step": 78730 }, { "epoch": 6.54, "learning_rate": 3.1285979547155167e-06, "loss": 0.7842, "step": 78740 }, { "epoch": 6.55, "learning_rate": 3.1284870991879834e-06, "loss": 0.9008, "step": 78750 }, { "epoch": 6.55, "learning_rate": 3.1283762436604493e-06, "loss": 0.8076, "step": 78760 }, { "epoch": 6.55, "learning_rate": 3.1282653881329156e-06, "loss": 0.7376, "step": 78770 }, { "epoch": 6.55, "learning_rate": 3.128154532605382e-06, "loss": 0.8043, "step": 78780 }, { "epoch": 6.55, "learning_rate": 3.128043677077848e-06, "loss": 0.8974, "step": 78790 }, { "epoch": 6.55, "learning_rate": 3.1279328215503144e-06, "loss": 0.7852, "step": 78800 }, { "epoch": 6.55, "learning_rate": 3.1278219660227807e-06, "loss": 0.8287, "step": 78810 }, { "epoch": 6.55, "learning_rate": 3.1277111104952466e-06, "loss": 0.7825, "step": 78820 }, { "epoch": 6.55, "learning_rate": 3.1276002549677133e-06, "loss": 0.8139, "step": 78830 }, { "epoch": 6.55, "learning_rate": 3.1274893994401796e-06, "loss": 0.8682, "step": 78840 }, { "epoch": 6.55, "learning_rate": 3.1273785439126455e-06, "loss": 0.8031, "step": 78850 }, { "epoch": 6.55, "learning_rate": 3.1272676883851122e-06, "loss": 0.7982, "step": 78860 }, { "epoch": 6.56, "learning_rate": 3.127156832857578e-06, "loss": 0.8394, "step": 78870 }, { "epoch": 6.56, "learning_rate": 3.127045977330045e-06, "loss": 0.8143, "step": 78880 }, { "epoch": 6.56, "learning_rate": 3.1269351218025107e-06, "loss": 0.8543, "step": 78890 }, { "epoch": 6.56, "learning_rate": 3.126824266274977e-06, "loss": 0.7591, "step": 78900 }, { "epoch": 6.56, "learning_rate": 3.1267134107474433e-06, "loss": 0.7399, "step": 78910 }, { "epoch": 6.56, "learning_rate": 3.1266025552199096e-06, "loss": 0.8686, "step": 78920 }, { "epoch": 6.56, "learning_rate": 3.1264916996923754e-06, "loss": 0.8558, "step": 78930 }, { "epoch": 6.56, "learning_rate": 3.126380844164842e-06, "loss": 0.8423, "step": 78940 }, { "epoch": 6.56, "learning_rate": 3.126269988637308e-06, "loss": 0.8712, "step": 78950 }, { "epoch": 6.56, "learning_rate": 3.1261591331097743e-06, "loss": 0.7757, "step": 78960 }, { "epoch": 6.56, "learning_rate": 3.126048277582241e-06, "loss": 0.7537, "step": 78970 }, { "epoch": 6.56, "learning_rate": 3.125937422054707e-06, "loss": 0.7712, "step": 78980 }, { "epoch": 6.57, "learning_rate": 3.1258265665271736e-06, "loss": 0.8322, "step": 78990 }, { "epoch": 6.57, "learning_rate": 3.1257157109996395e-06, "loss": 0.8887, "step": 79000 }, { "epoch": 6.57, "learning_rate": 3.125604855472106e-06, "loss": 0.8167, "step": 79010 }, { "epoch": 6.57, "learning_rate": 3.125493999944572e-06, "loss": 0.8133, "step": 79020 }, { "epoch": 6.57, "learning_rate": 3.1253831444170384e-06, "loss": 0.7719, "step": 79030 }, { "epoch": 6.57, "learning_rate": 3.1252722888895043e-06, "loss": 0.8221, "step": 79040 }, { "epoch": 6.57, "learning_rate": 3.125161433361971e-06, "loss": 0.9056, "step": 79050 }, { "epoch": 6.57, "learning_rate": 3.125050577834437e-06, "loss": 0.7949, "step": 79060 }, { "epoch": 6.57, "learning_rate": 3.1249397223069036e-06, "loss": 0.7883, "step": 79070 }, { "epoch": 6.57, "learning_rate": 3.12482886677937e-06, "loss": 0.8002, "step": 79080 }, { "epoch": 6.57, "learning_rate": 3.1247180112518357e-06, "loss": 0.8145, "step": 79090 }, { "epoch": 6.57, "learning_rate": 3.1246071557243025e-06, "loss": 0.8394, "step": 79100 }, { "epoch": 6.58, "learning_rate": 3.1244963001967683e-06, "loss": 0.78, "step": 79110 }, { "epoch": 6.58, "learning_rate": 3.1243854446692346e-06, "loss": 0.8362, "step": 79120 }, { "epoch": 6.58, "learning_rate": 3.124274589141701e-06, "loss": 0.7907, "step": 79130 }, { "epoch": 6.58, "learning_rate": 3.1241637336141672e-06, "loss": 0.8624, "step": 79140 }, { "epoch": 6.58, "learning_rate": 3.1240528780866335e-06, "loss": 0.822, "step": 79150 }, { "epoch": 6.58, "learning_rate": 3.1239420225591e-06, "loss": 0.7821, "step": 79160 }, { "epoch": 6.58, "learning_rate": 3.1238311670315657e-06, "loss": 0.8165, "step": 79170 }, { "epoch": 6.58, "learning_rate": 3.1237203115040324e-06, "loss": 0.8121, "step": 79180 }, { "epoch": 6.58, "learning_rate": 3.1236094559764983e-06, "loss": 0.8178, "step": 79190 }, { "epoch": 6.58, "learning_rate": 3.1234986004489646e-06, "loss": 0.7815, "step": 79200 }, { "epoch": 6.58, "learning_rate": 3.1233877449214313e-06, "loss": 0.8414, "step": 79210 }, { "epoch": 6.58, "learning_rate": 3.123276889393897e-06, "loss": 0.802, "step": 79220 }, { "epoch": 6.59, "learning_rate": 3.123166033866364e-06, "loss": 0.8225, "step": 79230 }, { "epoch": 6.59, "learning_rate": 3.1230551783388297e-06, "loss": 0.8393, "step": 79240 }, { "epoch": 6.59, "learning_rate": 3.122944322811296e-06, "loss": 0.849, "step": 79250 }, { "epoch": 6.59, "learning_rate": 3.1228334672837623e-06, "loss": 0.8465, "step": 79260 }, { "epoch": 6.59, "learning_rate": 3.1227226117562286e-06, "loss": 0.7966, "step": 79270 }, { "epoch": 6.59, "learning_rate": 3.1226117562286945e-06, "loss": 0.8603, "step": 79280 }, { "epoch": 6.59, "learning_rate": 3.1225009007011612e-06, "loss": 0.8909, "step": 79290 }, { "epoch": 6.59, "learning_rate": 3.122390045173627e-06, "loss": 0.8208, "step": 79300 }, { "epoch": 6.59, "learning_rate": 3.122279189646094e-06, "loss": 0.8201, "step": 79310 }, { "epoch": 6.59, "learning_rate": 3.12216833411856e-06, "loss": 0.8858, "step": 79320 }, { "epoch": 6.59, "learning_rate": 3.122057478591026e-06, "loss": 0.8388, "step": 79330 }, { "epoch": 6.59, "learning_rate": 3.1219466230634927e-06, "loss": 0.8702, "step": 79340 }, { "epoch": 6.6, "learning_rate": 3.1218357675359586e-06, "loss": 0.8131, "step": 79350 }, { "epoch": 6.6, "learning_rate": 3.121724912008425e-06, "loss": 0.817, "step": 79360 }, { "epoch": 6.6, "learning_rate": 3.121614056480891e-06, "loss": 0.7722, "step": 79370 }, { "epoch": 6.6, "learning_rate": 3.1215032009533575e-06, "loss": 0.7715, "step": 79380 }, { "epoch": 6.6, "learning_rate": 3.1213923454258233e-06, "loss": 0.8902, "step": 79390 }, { "epoch": 6.6, "learning_rate": 3.12128148989829e-06, "loss": 0.8256, "step": 79400 }, { "epoch": 6.6, "learning_rate": 3.121170634370756e-06, "loss": 0.8028, "step": 79410 }, { "epoch": 6.6, "learning_rate": 3.1210597788432226e-06, "loss": 0.7894, "step": 79420 }, { "epoch": 6.6, "learning_rate": 3.1209489233156885e-06, "loss": 0.8221, "step": 79430 }, { "epoch": 6.6, "learning_rate": 3.120838067788155e-06, "loss": 0.8409, "step": 79440 }, { "epoch": 6.6, "learning_rate": 3.1207272122606215e-06, "loss": 0.8319, "step": 79450 }, { "epoch": 6.6, "learning_rate": 3.1206163567330874e-06, "loss": 0.8173, "step": 79460 }, { "epoch": 6.61, "learning_rate": 3.1205055012055537e-06, "loss": 0.7999, "step": 79470 }, { "epoch": 6.61, "learning_rate": 3.12039464567802e-06, "loss": 0.8303, "step": 79480 }, { "epoch": 6.61, "learning_rate": 3.1202837901504863e-06, "loss": 0.7602, "step": 79490 }, { "epoch": 6.61, "learning_rate": 3.1201729346229526e-06, "loss": 0.8024, "step": 79500 }, { "epoch": 6.61, "learning_rate": 3.120062079095419e-06, "loss": 0.819, "step": 79510 }, { "epoch": 6.61, "learning_rate": 3.1199512235678847e-06, "loss": 0.8318, "step": 79520 }, { "epoch": 6.61, "learning_rate": 3.1198403680403515e-06, "loss": 0.7982, "step": 79530 }, { "epoch": 6.61, "learning_rate": 3.1197295125128173e-06, "loss": 0.8086, "step": 79540 }, { "epoch": 6.61, "learning_rate": 3.1196186569852836e-06, "loss": 0.9187, "step": 79550 }, { "epoch": 6.61, "learning_rate": 3.11950780145775e-06, "loss": 0.8301, "step": 79560 }, { "epoch": 6.61, "learning_rate": 3.1193969459302162e-06, "loss": 0.7749, "step": 79570 }, { "epoch": 6.61, "learning_rate": 3.119286090402683e-06, "loss": 0.9071, "step": 79580 }, { "epoch": 6.62, "learning_rate": 3.119175234875149e-06, "loss": 0.9266, "step": 79590 }, { "epoch": 6.62, "learning_rate": 3.119064379347615e-06, "loss": 0.8013, "step": 79600 }, { "epoch": 6.62, "learning_rate": 3.1189535238200814e-06, "loss": 0.8496, "step": 79610 }, { "epoch": 6.62, "learning_rate": 3.1188426682925477e-06, "loss": 0.8017, "step": 79620 }, { "epoch": 6.62, "learning_rate": 3.1187318127650136e-06, "loss": 0.8036, "step": 79630 }, { "epoch": 6.62, "learning_rate": 3.1186209572374803e-06, "loss": 0.8523, "step": 79640 }, { "epoch": 6.62, "learning_rate": 3.118510101709946e-06, "loss": 0.7897, "step": 79650 }, { "epoch": 6.62, "learning_rate": 3.118399246182413e-06, "loss": 0.8434, "step": 79660 }, { "epoch": 6.62, "learning_rate": 3.1182883906548787e-06, "loss": 0.8852, "step": 79670 }, { "epoch": 6.62, "learning_rate": 3.118177535127345e-06, "loss": 0.8222, "step": 79680 }, { "epoch": 6.62, "learning_rate": 3.1180666795998118e-06, "loss": 0.8225, "step": 79690 }, { "epoch": 6.62, "learning_rate": 3.1179558240722776e-06, "loss": 0.8455, "step": 79700 }, { "epoch": 6.63, "learning_rate": 3.117844968544744e-06, "loss": 0.8407, "step": 79710 }, { "epoch": 6.63, "learning_rate": 3.1177341130172102e-06, "loss": 0.7757, "step": 79720 }, { "epoch": 6.63, "learning_rate": 3.1176232574896765e-06, "loss": 0.7877, "step": 79730 }, { "epoch": 6.63, "learning_rate": 3.1175124019621424e-06, "loss": 0.84, "step": 79740 }, { "epoch": 6.63, "learning_rate": 3.117401546434609e-06, "loss": 0.851, "step": 79750 }, { "epoch": 6.63, "learning_rate": 3.117290690907075e-06, "loss": 0.8509, "step": 79760 }, { "epoch": 6.63, "learning_rate": 3.1171798353795417e-06, "loss": 0.8093, "step": 79770 }, { "epoch": 6.63, "learning_rate": 3.1170689798520076e-06, "loss": 0.7312, "step": 79780 }, { "epoch": 6.63, "learning_rate": 3.116958124324474e-06, "loss": 0.8188, "step": 79790 }, { "epoch": 6.63, "learning_rate": 3.11684726879694e-06, "loss": 0.7977, "step": 79800 }, { "epoch": 6.63, "learning_rate": 3.1167364132694065e-06, "loss": 0.7884, "step": 79810 }, { "epoch": 6.63, "learning_rate": 3.116625557741873e-06, "loss": 0.7781, "step": 79820 }, { "epoch": 6.64, "learning_rate": 3.116514702214339e-06, "loss": 0.8041, "step": 79830 }, { "epoch": 6.64, "learning_rate": 3.1164038466868053e-06, "loss": 0.8431, "step": 79840 }, { "epoch": 6.64, "learning_rate": 3.1162929911592716e-06, "loss": 0.8256, "step": 79850 }, { "epoch": 6.64, "learning_rate": 3.116182135631738e-06, "loss": 0.7898, "step": 79860 }, { "epoch": 6.64, "learning_rate": 3.116071280104204e-06, "loss": 0.875, "step": 79870 }, { "epoch": 6.64, "learning_rate": 3.1159604245766705e-06, "loss": 0.8079, "step": 79880 }, { "epoch": 6.64, "learning_rate": 3.1158495690491364e-06, "loss": 0.8689, "step": 79890 }, { "epoch": 6.64, "learning_rate": 3.1157387135216027e-06, "loss": 0.7658, "step": 79900 }, { "epoch": 6.64, "learning_rate": 3.115627857994069e-06, "loss": 0.7426, "step": 79910 }, { "epoch": 6.64, "learning_rate": 3.1155170024665353e-06, "loss": 0.8011, "step": 79920 }, { "epoch": 6.64, "learning_rate": 3.1154061469390016e-06, "loss": 0.8606, "step": 79930 }, { "epoch": 6.64, "learning_rate": 3.115295291411468e-06, "loss": 0.8804, "step": 79940 }, { "epoch": 6.65, "learning_rate": 3.115184435883934e-06, "loss": 0.8886, "step": 79950 }, { "epoch": 6.65, "learning_rate": 3.1150735803564005e-06, "loss": 0.8191, "step": 79960 }, { "epoch": 6.65, "learning_rate": 3.1149627248288668e-06, "loss": 0.7533, "step": 79970 }, { "epoch": 6.65, "learning_rate": 3.1148518693013326e-06, "loss": 0.7622, "step": 79980 }, { "epoch": 6.65, "learning_rate": 3.1147410137737994e-06, "loss": 0.8856, "step": 79990 }, { "epoch": 6.65, "learning_rate": 3.1146301582462652e-06, "loss": 0.8225, "step": 80000 }, { "epoch": 6.65, "learning_rate": 3.114519302718732e-06, "loss": 0.7726, "step": 80010 }, { "epoch": 6.65, "learning_rate": 3.114408447191198e-06, "loss": 0.7578, "step": 80020 }, { "epoch": 6.65, "learning_rate": 3.114297591663664e-06, "loss": 0.8388, "step": 80030 }, { "epoch": 6.65, "learning_rate": 3.1141867361361304e-06, "loss": 0.8609, "step": 80040 }, { "epoch": 6.65, "learning_rate": 3.1140758806085967e-06, "loss": 0.8587, "step": 80050 }, { "epoch": 6.65, "learning_rate": 3.113965025081063e-06, "loss": 0.8262, "step": 80060 }, { "epoch": 6.66, "learning_rate": 3.1138541695535293e-06, "loss": 0.7571, "step": 80070 }, { "epoch": 6.66, "learning_rate": 3.1137433140259956e-06, "loss": 0.7957, "step": 80080 }, { "epoch": 6.66, "learning_rate": 3.113632458498462e-06, "loss": 0.8884, "step": 80090 }, { "epoch": 6.66, "learning_rate": 3.113521602970928e-06, "loss": 0.8637, "step": 80100 }, { "epoch": 6.66, "learning_rate": 3.113410747443394e-06, "loss": 0.8391, "step": 80110 }, { "epoch": 6.66, "learning_rate": 3.1132998919158608e-06, "loss": 0.8961, "step": 80120 }, { "epoch": 6.66, "learning_rate": 3.1131890363883266e-06, "loss": 0.8439, "step": 80130 }, { "epoch": 6.66, "learning_rate": 3.113078180860793e-06, "loss": 0.7922, "step": 80140 }, { "epoch": 6.66, "learning_rate": 3.1129673253332592e-06, "loss": 0.8524, "step": 80150 }, { "epoch": 6.66, "learning_rate": 3.1128564698057255e-06, "loss": 0.7319, "step": 80160 }, { "epoch": 6.66, "learning_rate": 3.1127456142781914e-06, "loss": 0.7448, "step": 80170 }, { "epoch": 6.66, "learning_rate": 3.112634758750658e-06, "loss": 0.9002, "step": 80180 }, { "epoch": 6.67, "learning_rate": 3.1125239032231244e-06, "loss": 0.8448, "step": 80190 }, { "epoch": 6.67, "learning_rate": 3.1124130476955907e-06, "loss": 0.8474, "step": 80200 }, { "epoch": 6.67, "learning_rate": 3.112302192168057e-06, "loss": 0.8341, "step": 80210 }, { "epoch": 6.67, "learning_rate": 3.112191336640523e-06, "loss": 0.9171, "step": 80220 }, { "epoch": 6.67, "learning_rate": 3.1120804811129896e-06, "loss": 0.8131, "step": 80230 }, { "epoch": 6.67, "learning_rate": 3.1119696255854555e-06, "loss": 0.8141, "step": 80240 }, { "epoch": 6.67, "learning_rate": 3.1118587700579218e-06, "loss": 0.8474, "step": 80250 }, { "epoch": 6.67, "learning_rate": 3.111747914530388e-06, "loss": 0.8123, "step": 80260 }, { "epoch": 6.67, "learning_rate": 3.1116370590028544e-06, "loss": 0.7998, "step": 80270 }, { "epoch": 6.67, "learning_rate": 3.1115262034753206e-06, "loss": 0.7632, "step": 80280 }, { "epoch": 6.67, "learning_rate": 3.111415347947787e-06, "loss": 0.8016, "step": 80290 }, { "epoch": 6.67, "learning_rate": 3.111304492420253e-06, "loss": 0.7413, "step": 80300 }, { "epoch": 6.68, "learning_rate": 3.1111936368927195e-06, "loss": 0.822, "step": 80310 }, { "epoch": 6.68, "learning_rate": 3.111082781365186e-06, "loss": 0.8008, "step": 80320 }, { "epoch": 6.68, "learning_rate": 3.1109719258376517e-06, "loss": 0.7971, "step": 80330 }, { "epoch": 6.68, "learning_rate": 3.1108610703101184e-06, "loss": 0.9008, "step": 80340 }, { "epoch": 6.68, "learning_rate": 3.1107502147825843e-06, "loss": 0.8312, "step": 80350 }, { "epoch": 6.68, "learning_rate": 3.110639359255051e-06, "loss": 0.8088, "step": 80360 }, { "epoch": 6.68, "learning_rate": 3.110528503727517e-06, "loss": 0.713, "step": 80370 }, { "epoch": 6.68, "learning_rate": 3.110417648199983e-06, "loss": 0.8138, "step": 80380 }, { "epoch": 6.68, "learning_rate": 3.1103067926724495e-06, "loss": 0.8654, "step": 80390 }, { "epoch": 6.68, "learning_rate": 3.1101959371449158e-06, "loss": 0.8081, "step": 80400 }, { "epoch": 6.68, "learning_rate": 3.1100850816173816e-06, "loss": 0.7515, "step": 80410 }, { "epoch": 6.68, "learning_rate": 3.1099742260898484e-06, "loss": 0.7927, "step": 80420 }, { "epoch": 6.69, "learning_rate": 3.1098633705623147e-06, "loss": 0.7817, "step": 80430 }, { "epoch": 6.69, "learning_rate": 3.109752515034781e-06, "loss": 0.7949, "step": 80440 }, { "epoch": 6.69, "learning_rate": 3.1096416595072472e-06, "loss": 0.8465, "step": 80450 }, { "epoch": 6.69, "learning_rate": 3.109530803979713e-06, "loss": 0.7847, "step": 80460 }, { "epoch": 6.69, "learning_rate": 3.10941994845218e-06, "loss": 0.888, "step": 80470 }, { "epoch": 6.69, "learning_rate": 3.1093090929246457e-06, "loss": 0.7416, "step": 80480 }, { "epoch": 6.69, "learning_rate": 3.109198237397112e-06, "loss": 0.8217, "step": 80490 }, { "epoch": 6.69, "learning_rate": 3.1090873818695783e-06, "loss": 0.7885, "step": 80500 }, { "epoch": 6.69, "learning_rate": 3.1089765263420446e-06, "loss": 0.765, "step": 80510 }, { "epoch": 6.69, "learning_rate": 3.108865670814511e-06, "loss": 0.8865, "step": 80520 }, { "epoch": 6.69, "learning_rate": 3.108754815286977e-06, "loss": 0.8632, "step": 80530 }, { "epoch": 6.69, "learning_rate": 3.108643959759443e-06, "loss": 0.8554, "step": 80540 }, { "epoch": 6.7, "learning_rate": 3.1085331042319098e-06, "loss": 0.7693, "step": 80550 }, { "epoch": 6.7, "learning_rate": 3.108422248704376e-06, "loss": 0.796, "step": 80560 }, { "epoch": 6.7, "learning_rate": 3.108311393176842e-06, "loss": 0.8377, "step": 80570 }, { "epoch": 6.7, "learning_rate": 3.1082005376493087e-06, "loss": 0.7953, "step": 80580 }, { "epoch": 6.7, "learning_rate": 3.1080896821217745e-06, "loss": 0.8032, "step": 80590 }, { "epoch": 6.7, "learning_rate": 3.1079788265942412e-06, "loss": 0.8389, "step": 80600 }, { "epoch": 6.7, "learning_rate": 3.107867971066707e-06, "loss": 0.7944, "step": 80610 }, { "epoch": 6.7, "learning_rate": 3.1077571155391734e-06, "loss": 0.8221, "step": 80620 }, { "epoch": 6.7, "learning_rate": 3.1076462600116397e-06, "loss": 0.8282, "step": 80630 }, { "epoch": 6.7, "learning_rate": 3.107535404484106e-06, "loss": 0.8184, "step": 80640 }, { "epoch": 6.7, "learning_rate": 3.107424548956572e-06, "loss": 0.8986, "step": 80650 }, { "epoch": 6.7, "learning_rate": 3.1073136934290386e-06, "loss": 0.8427, "step": 80660 }, { "epoch": 6.71, "learning_rate": 3.1072028379015045e-06, "loss": 0.8195, "step": 80670 }, { "epoch": 6.71, "learning_rate": 3.1070919823739708e-06, "loss": 0.7199, "step": 80680 }, { "epoch": 6.71, "learning_rate": 3.1069811268464375e-06, "loss": 0.8681, "step": 80690 }, { "epoch": 6.71, "learning_rate": 3.1068702713189034e-06, "loss": 0.8842, "step": 80700 }, { "epoch": 6.71, "learning_rate": 3.10675941579137e-06, "loss": 0.7933, "step": 80710 }, { "epoch": 6.71, "learning_rate": 3.106648560263836e-06, "loss": 0.7895, "step": 80720 }, { "epoch": 6.71, "learning_rate": 3.1065377047363022e-06, "loss": 0.8115, "step": 80730 }, { "epoch": 6.71, "learning_rate": 3.1064268492087685e-06, "loss": 0.8941, "step": 80740 }, { "epoch": 6.71, "learning_rate": 3.106315993681235e-06, "loss": 0.8241, "step": 80750 }, { "epoch": 6.71, "learning_rate": 3.1062051381537007e-06, "loss": 0.8618, "step": 80760 }, { "epoch": 6.71, "learning_rate": 3.1060942826261674e-06, "loss": 0.7702, "step": 80770 }, { "epoch": 6.71, "learning_rate": 3.1059834270986333e-06, "loss": 0.8484, "step": 80780 }, { "epoch": 6.72, "learning_rate": 3.1058725715711e-06, "loss": 0.8077, "step": 80790 }, { "epoch": 6.72, "learning_rate": 3.1057617160435663e-06, "loss": 0.7918, "step": 80800 }, { "epoch": 6.72, "learning_rate": 3.105650860516032e-06, "loss": 0.7996, "step": 80810 }, { "epoch": 6.72, "learning_rate": 3.105540004988499e-06, "loss": 0.8419, "step": 80820 }, { "epoch": 6.72, "learning_rate": 3.1054291494609648e-06, "loss": 0.8773, "step": 80830 }, { "epoch": 6.72, "learning_rate": 3.105318293933431e-06, "loss": 0.8047, "step": 80840 }, { "epoch": 6.72, "learning_rate": 3.1052074384058974e-06, "loss": 0.8138, "step": 80850 }, { "epoch": 6.72, "learning_rate": 3.1050965828783637e-06, "loss": 0.8035, "step": 80860 }, { "epoch": 6.72, "learning_rate": 3.10498572735083e-06, "loss": 0.8483, "step": 80870 }, { "epoch": 6.72, "learning_rate": 3.1048748718232962e-06, "loss": 0.8601, "step": 80880 }, { "epoch": 6.72, "learning_rate": 3.104764016295762e-06, "loss": 0.8606, "step": 80890 }, { "epoch": 6.72, "learning_rate": 3.104653160768229e-06, "loss": 0.8398, "step": 80900 }, { "epoch": 6.73, "learning_rate": 3.1045423052406947e-06, "loss": 0.7563, "step": 80910 }, { "epoch": 6.73, "learning_rate": 3.104431449713161e-06, "loss": 0.7493, "step": 80920 }, { "epoch": 6.73, "learning_rate": 3.1043205941856277e-06, "loss": 0.7896, "step": 80930 }, { "epoch": 6.73, "learning_rate": 3.1042097386580936e-06, "loss": 0.8046, "step": 80940 }, { "epoch": 6.73, "learning_rate": 3.1040988831305603e-06, "loss": 0.7845, "step": 80950 }, { "epoch": 6.73, "learning_rate": 3.103988027603026e-06, "loss": 0.8087, "step": 80960 }, { "epoch": 6.73, "learning_rate": 3.1038771720754925e-06, "loss": 0.8142, "step": 80970 }, { "epoch": 6.73, "learning_rate": 3.1037663165479588e-06, "loss": 0.8496, "step": 80980 }, { "epoch": 6.73, "learning_rate": 3.103655461020425e-06, "loss": 0.8454, "step": 80990 }, { "epoch": 6.73, "learning_rate": 3.103544605492891e-06, "loss": 0.8356, "step": 81000 }, { "epoch": 6.73, "learning_rate": 3.1034337499653577e-06, "loss": 0.7733, "step": 81010 }, { "epoch": 6.73, "learning_rate": 3.1033228944378235e-06, "loss": 0.8134, "step": 81020 }, { "epoch": 6.74, "learning_rate": 3.10321203891029e-06, "loss": 0.8081, "step": 81030 }, { "epoch": 6.74, "learning_rate": 3.103101183382756e-06, "loss": 0.7932, "step": 81040 }, { "epoch": 6.74, "learning_rate": 3.1029903278552224e-06, "loss": 0.8093, "step": 81050 }, { "epoch": 6.74, "learning_rate": 3.102879472327689e-06, "loss": 0.7747, "step": 81060 }, { "epoch": 6.74, "learning_rate": 3.102768616800155e-06, "loss": 0.7394, "step": 81070 }, { "epoch": 6.74, "learning_rate": 3.1026577612726213e-06, "loss": 0.7797, "step": 81080 }, { "epoch": 6.74, "learning_rate": 3.1025469057450876e-06, "loss": 0.8591, "step": 81090 }, { "epoch": 6.74, "learning_rate": 3.102436050217554e-06, "loss": 0.8027, "step": 81100 }, { "epoch": 6.74, "learning_rate": 3.1023251946900198e-06, "loss": 0.7841, "step": 81110 }, { "epoch": 6.74, "learning_rate": 3.1022143391624865e-06, "loss": 0.7477, "step": 81120 }, { "epoch": 6.74, "learning_rate": 3.1021034836349524e-06, "loss": 0.8113, "step": 81130 }, { "epoch": 6.74, "learning_rate": 3.101992628107419e-06, "loss": 0.8673, "step": 81140 }, { "epoch": 6.75, "learning_rate": 3.101881772579885e-06, "loss": 0.8379, "step": 81150 }, { "epoch": 6.75, "learning_rate": 3.1017709170523512e-06, "loss": 0.7786, "step": 81160 }, { "epoch": 6.75, "learning_rate": 3.101660061524818e-06, "loss": 0.7919, "step": 81170 }, { "epoch": 6.75, "learning_rate": 3.101549205997284e-06, "loss": 0.894, "step": 81180 }, { "epoch": 6.75, "learning_rate": 3.10143835046975e-06, "loss": 0.7865, "step": 81190 }, { "epoch": 6.75, "learning_rate": 3.1013274949422164e-06, "loss": 0.9141, "step": 81200 }, { "epoch": 6.75, "learning_rate": 3.1012166394146827e-06, "loss": 0.8186, "step": 81210 }, { "epoch": 6.75, "learning_rate": 3.101105783887149e-06, "loss": 0.7583, "step": 81220 }, { "epoch": 6.75, "learning_rate": 3.1009949283596153e-06, "loss": 0.7761, "step": 81230 }, { "epoch": 6.75, "learning_rate": 3.100884072832081e-06, "loss": 0.8695, "step": 81240 }, { "epoch": 6.75, "learning_rate": 3.100773217304548e-06, "loss": 0.7835, "step": 81250 }, { "epoch": 6.75, "learning_rate": 3.1006623617770138e-06, "loss": 0.8896, "step": 81260 }, { "epoch": 6.76, "learning_rate": 3.10055150624948e-06, "loss": 0.8124, "step": 81270 }, { "epoch": 6.76, "learning_rate": 3.1004406507219464e-06, "loss": 0.8727, "step": 81280 }, { "epoch": 6.76, "learning_rate": 3.1003297951944127e-06, "loss": 0.8947, "step": 81290 }, { "epoch": 6.76, "learning_rate": 3.1002189396668794e-06, "loss": 0.8543, "step": 81300 }, { "epoch": 6.76, "learning_rate": 3.1001080841393453e-06, "loss": 0.7832, "step": 81310 }, { "epoch": 6.76, "learning_rate": 3.0999972286118115e-06, "loss": 0.7824, "step": 81320 }, { "epoch": 6.76, "learning_rate": 3.099886373084278e-06, "loss": 0.7673, "step": 81330 }, { "epoch": 6.76, "learning_rate": 3.099775517556744e-06, "loss": 0.8312, "step": 81340 }, { "epoch": 6.76, "learning_rate": 3.09966466202921e-06, "loss": 0.8601, "step": 81350 }, { "epoch": 6.76, "learning_rate": 3.0995538065016767e-06, "loss": 0.7942, "step": 81360 }, { "epoch": 6.76, "learning_rate": 3.0994429509741426e-06, "loss": 0.7386, "step": 81370 }, { "epoch": 6.76, "learning_rate": 3.0993320954466093e-06, "loss": 0.7538, "step": 81380 }, { "epoch": 6.77, "learning_rate": 3.099221239919075e-06, "loss": 0.7829, "step": 81390 }, { "epoch": 6.77, "learning_rate": 3.0991103843915415e-06, "loss": 0.8122, "step": 81400 }, { "epoch": 6.77, "learning_rate": 3.098999528864008e-06, "loss": 0.821, "step": 81410 }, { "epoch": 6.77, "learning_rate": 3.098888673336474e-06, "loss": 0.8065, "step": 81420 }, { "epoch": 6.77, "learning_rate": 3.0987778178089404e-06, "loss": 0.7666, "step": 81430 }, { "epoch": 6.77, "learning_rate": 3.0986669622814067e-06, "loss": 0.7232, "step": 81440 }, { "epoch": 6.77, "learning_rate": 3.098556106753873e-06, "loss": 0.8263, "step": 81450 }, { "epoch": 6.77, "learning_rate": 3.098445251226339e-06, "loss": 0.7906, "step": 81460 }, { "epoch": 6.77, "learning_rate": 3.0983343956988056e-06, "loss": 0.8368, "step": 81470 }, { "epoch": 6.77, "learning_rate": 3.0982235401712714e-06, "loss": 0.7585, "step": 81480 }, { "epoch": 6.77, "learning_rate": 3.098112684643738e-06, "loss": 0.8493, "step": 81490 }, { "epoch": 6.77, "learning_rate": 3.098001829116204e-06, "loss": 0.8253, "step": 81500 }, { "epoch": 6.77, "learning_rate": 3.0978909735886703e-06, "loss": 0.7988, "step": 81510 }, { "epoch": 6.78, "learning_rate": 3.0977801180611366e-06, "loss": 0.7776, "step": 81520 }, { "epoch": 6.78, "learning_rate": 3.097669262533603e-06, "loss": 0.7676, "step": 81530 }, { "epoch": 6.78, "learning_rate": 3.097558407006069e-06, "loss": 0.8696, "step": 81540 }, { "epoch": 6.78, "learning_rate": 3.0974475514785355e-06, "loss": 0.8013, "step": 81550 }, { "epoch": 6.78, "learning_rate": 3.097336695951002e-06, "loss": 0.8065, "step": 81560 }, { "epoch": 6.78, "learning_rate": 3.097225840423468e-06, "loss": 0.8251, "step": 81570 }, { "epoch": 6.78, "learning_rate": 3.0971149848959344e-06, "loss": 0.7926, "step": 81580 }, { "epoch": 6.78, "learning_rate": 3.0970041293684003e-06, "loss": 0.8419, "step": 81590 }, { "epoch": 6.78, "learning_rate": 3.096893273840867e-06, "loss": 0.8092, "step": 81600 }, { "epoch": 6.78, "learning_rate": 3.096782418313333e-06, "loss": 0.7578, "step": 81610 }, { "epoch": 6.78, "learning_rate": 3.096671562785799e-06, "loss": 0.8566, "step": 81620 }, { "epoch": 6.78, "learning_rate": 3.0965717928110187e-06, "loss": 0.7571, "step": 81630 }, { "epoch": 6.79, "learning_rate": 3.0964609372834854e-06, "loss": 0.8484, "step": 81640 }, { "epoch": 6.79, "learning_rate": 3.0963500817559513e-06, "loss": 0.8423, "step": 81650 }, { "epoch": 6.79, "learning_rate": 3.096239226228418e-06, "loss": 0.8357, "step": 81660 }, { "epoch": 6.79, "learning_rate": 3.096128370700884e-06, "loss": 0.8254, "step": 81670 }, { "epoch": 6.79, "learning_rate": 3.09601751517335e-06, "loss": 0.8514, "step": 81680 }, { "epoch": 6.79, "learning_rate": 3.0959066596458164e-06, "loss": 0.802, "step": 81690 }, { "epoch": 6.79, "learning_rate": 3.0957958041182827e-06, "loss": 0.7547, "step": 81700 }, { "epoch": 6.79, "learning_rate": 3.0956849485907486e-06, "loss": 0.7886, "step": 81710 }, { "epoch": 6.79, "learning_rate": 3.0955740930632153e-06, "loss": 0.7595, "step": 81720 }, { "epoch": 6.79, "learning_rate": 3.095463237535681e-06, "loss": 0.8556, "step": 81730 }, { "epoch": 6.79, "learning_rate": 3.095352382008148e-06, "loss": 0.8, "step": 81740 }, { "epoch": 6.79, "learning_rate": 3.0952415264806142e-06, "loss": 0.8267, "step": 81750 }, { "epoch": 6.8, "learning_rate": 3.09513067095308e-06, "loss": 0.8234, "step": 81760 }, { "epoch": 6.8, "learning_rate": 3.095019815425547e-06, "loss": 0.8085, "step": 81770 }, { "epoch": 6.8, "learning_rate": 3.0949089598980127e-06, "loss": 0.7527, "step": 81780 }, { "epoch": 6.8, "learning_rate": 3.094798104370479e-06, "loss": 0.8233, "step": 81790 }, { "epoch": 6.8, "learning_rate": 3.0946872488429453e-06, "loss": 0.8687, "step": 81800 }, { "epoch": 6.8, "learning_rate": 3.0945763933154116e-06, "loss": 0.8296, "step": 81810 }, { "epoch": 6.8, "learning_rate": 3.094465537787878e-06, "loss": 0.8116, "step": 81820 }, { "epoch": 6.8, "learning_rate": 3.094354682260344e-06, "loss": 0.8196, "step": 81830 }, { "epoch": 6.8, "learning_rate": 3.09424382673281e-06, "loss": 0.8108, "step": 81840 }, { "epoch": 6.8, "learning_rate": 3.0941329712052768e-06, "loss": 0.8673, "step": 81850 }, { "epoch": 6.8, "learning_rate": 3.0940221156777426e-06, "loss": 0.7952, "step": 81860 }, { "epoch": 6.8, "learning_rate": 3.093911260150209e-06, "loss": 0.8183, "step": 81870 }, { "epoch": 6.81, "learning_rate": 3.0938004046226756e-06, "loss": 0.7651, "step": 81880 }, { "epoch": 6.81, "learning_rate": 3.0936895490951415e-06, "loss": 0.8056, "step": 81890 }, { "epoch": 6.81, "learning_rate": 3.0935786935676082e-06, "loss": 0.8155, "step": 81900 }, { "epoch": 6.81, "learning_rate": 3.093467838040074e-06, "loss": 0.8243, "step": 81910 }, { "epoch": 6.81, "learning_rate": 3.0933569825125404e-06, "loss": 0.8528, "step": 81920 }, { "epoch": 6.81, "learning_rate": 3.0932461269850067e-06, "loss": 0.8071, "step": 81930 }, { "epoch": 6.81, "learning_rate": 3.093135271457473e-06, "loss": 0.8613, "step": 81940 }, { "epoch": 6.81, "learning_rate": 3.093024415929939e-06, "loss": 0.8257, "step": 81950 }, { "epoch": 6.81, "learning_rate": 3.0929135604024056e-06, "loss": 0.7885, "step": 81960 }, { "epoch": 6.81, "learning_rate": 3.0928027048748714e-06, "loss": 0.8455, "step": 81970 }, { "epoch": 6.81, "learning_rate": 3.092691849347338e-06, "loss": 0.8245, "step": 81980 }, { "epoch": 6.81, "learning_rate": 3.0925809938198045e-06, "loss": 0.7918, "step": 81990 }, { "epoch": 6.82, "learning_rate": 3.0924701382922703e-06, "loss": 0.8454, "step": 82000 }, { "epoch": 6.82, "learning_rate": 3.092359282764737e-06, "loss": 0.894, "step": 82010 }, { "epoch": 6.82, "learning_rate": 3.092248427237203e-06, "loss": 0.8001, "step": 82020 }, { "epoch": 6.82, "learning_rate": 3.0921375717096692e-06, "loss": 0.7802, "step": 82030 }, { "epoch": 6.82, "learning_rate": 3.0920267161821355e-06, "loss": 0.7937, "step": 82040 }, { "epoch": 6.82, "learning_rate": 3.091915860654602e-06, "loss": 0.8522, "step": 82050 }, { "epoch": 6.82, "learning_rate": 3.0918050051270677e-06, "loss": 0.8227, "step": 82060 }, { "epoch": 6.82, "learning_rate": 3.0916941495995344e-06, "loss": 0.8144, "step": 82070 }, { "epoch": 6.82, "learning_rate": 3.0915832940720003e-06, "loss": 0.8683, "step": 82080 }, { "epoch": 6.82, "learning_rate": 3.091472438544467e-06, "loss": 0.7802, "step": 82090 }, { "epoch": 6.82, "learning_rate": 3.091361583016933e-06, "loss": 0.804, "step": 82100 }, { "epoch": 6.82, "learning_rate": 3.091250727489399e-06, "loss": 0.8728, "step": 82110 }, { "epoch": 6.83, "learning_rate": 3.091139871961866e-06, "loss": 0.7696, "step": 82120 }, { "epoch": 6.83, "learning_rate": 3.0910290164343318e-06, "loss": 0.8456, "step": 82130 }, { "epoch": 6.83, "learning_rate": 3.090918160906798e-06, "loss": 0.8103, "step": 82140 }, { "epoch": 6.83, "learning_rate": 3.0908073053792643e-06, "loss": 0.8356, "step": 82150 }, { "epoch": 6.83, "learning_rate": 3.0906964498517306e-06, "loss": 0.7427, "step": 82160 }, { "epoch": 6.83, "learning_rate": 3.090585594324197e-06, "loss": 0.7361, "step": 82170 }, { "epoch": 6.83, "learning_rate": 3.0904747387966632e-06, "loss": 0.7385, "step": 82180 }, { "epoch": 6.83, "learning_rate": 3.090363883269129e-06, "loss": 0.8016, "step": 82190 }, { "epoch": 6.83, "learning_rate": 3.090253027741596e-06, "loss": 0.8745, "step": 82200 }, { "epoch": 6.83, "learning_rate": 3.0901421722140617e-06, "loss": 0.7797, "step": 82210 }, { "epoch": 6.83, "learning_rate": 3.090031316686528e-06, "loss": 0.8462, "step": 82220 }, { "epoch": 6.83, "learning_rate": 3.0899204611589943e-06, "loss": 0.8411, "step": 82230 }, { "epoch": 6.84, "learning_rate": 3.0898096056314606e-06, "loss": 0.8491, "step": 82240 }, { "epoch": 6.84, "learning_rate": 3.0896987501039273e-06, "loss": 0.7769, "step": 82250 }, { "epoch": 6.84, "learning_rate": 3.089587894576393e-06, "loss": 0.7873, "step": 82260 }, { "epoch": 6.84, "learning_rate": 3.0894770390488595e-06, "loss": 0.8357, "step": 82270 }, { "epoch": 6.84, "learning_rate": 3.0893661835213258e-06, "loss": 0.7864, "step": 82280 }, { "epoch": 6.84, "learning_rate": 3.089255327993792e-06, "loss": 0.8542, "step": 82290 }, { "epoch": 6.84, "learning_rate": 3.089144472466258e-06, "loss": 0.8627, "step": 82300 }, { "epoch": 6.84, "learning_rate": 3.0890336169387246e-06, "loss": 0.8022, "step": 82310 }, { "epoch": 6.84, "learning_rate": 3.0889227614111905e-06, "loss": 0.8135, "step": 82320 }, { "epoch": 6.84, "learning_rate": 3.0888119058836572e-06, "loss": 0.8555, "step": 82330 }, { "epoch": 6.84, "learning_rate": 3.088701050356123e-06, "loss": 0.832, "step": 82340 }, { "epoch": 6.84, "learning_rate": 3.0885901948285894e-06, "loss": 0.8564, "step": 82350 }, { "epoch": 6.85, "learning_rate": 3.088479339301056e-06, "loss": 0.8019, "step": 82360 }, { "epoch": 6.85, "learning_rate": 3.088368483773522e-06, "loss": 0.8076, "step": 82370 }, { "epoch": 6.85, "learning_rate": 3.0882576282459883e-06, "loss": 0.791, "step": 82380 }, { "epoch": 6.85, "learning_rate": 3.0881467727184546e-06, "loss": 0.8632, "step": 82390 }, { "epoch": 6.85, "learning_rate": 3.088035917190921e-06, "loss": 0.8317, "step": 82400 }, { "epoch": 6.85, "learning_rate": 3.0879250616633867e-06, "loss": 0.8278, "step": 82410 }, { "epoch": 6.85, "learning_rate": 3.0878142061358535e-06, "loss": 0.8326, "step": 82420 }, { "epoch": 6.85, "learning_rate": 3.0877033506083193e-06, "loss": 0.784, "step": 82430 }, { "epoch": 6.85, "learning_rate": 3.087592495080786e-06, "loss": 0.8836, "step": 82440 }, { "epoch": 6.85, "learning_rate": 3.087481639553252e-06, "loss": 0.7987, "step": 82450 }, { "epoch": 6.85, "learning_rate": 3.0873707840257182e-06, "loss": 0.7108, "step": 82460 }, { "epoch": 6.85, "learning_rate": 3.0872599284981845e-06, "loss": 0.8095, "step": 82470 }, { "epoch": 6.86, "learning_rate": 3.087149072970651e-06, "loss": 0.8306, "step": 82480 }, { "epoch": 6.86, "learning_rate": 3.087038217443117e-06, "loss": 0.8939, "step": 82490 }, { "epoch": 6.86, "learning_rate": 3.0869273619155834e-06, "loss": 0.8025, "step": 82500 }, { "epoch": 6.86, "learning_rate": 3.0868165063880497e-06, "loss": 0.7935, "step": 82510 }, { "epoch": 6.86, "learning_rate": 3.086705650860516e-06, "loss": 0.7939, "step": 82520 }, { "epoch": 6.86, "learning_rate": 3.0865947953329823e-06, "loss": 0.8028, "step": 82530 }, { "epoch": 6.86, "learning_rate": 3.086483939805448e-06, "loss": 0.8752, "step": 82540 }, { "epoch": 6.86, "learning_rate": 3.086373084277915e-06, "loss": 0.8457, "step": 82550 }, { "epoch": 6.86, "learning_rate": 3.0862622287503808e-06, "loss": 0.8689, "step": 82560 }, { "epoch": 6.86, "learning_rate": 3.086151373222847e-06, "loss": 0.8269, "step": 82570 }, { "epoch": 6.86, "learning_rate": 3.0860405176953133e-06, "loss": 0.8775, "step": 82580 }, { "epoch": 6.86, "learning_rate": 3.0859296621677796e-06, "loss": 0.7975, "step": 82590 }, { "epoch": 6.87, "learning_rate": 3.085818806640246e-06, "loss": 0.8207, "step": 82600 }, { "epoch": 6.87, "learning_rate": 3.0857079511127122e-06, "loss": 0.7824, "step": 82610 }, { "epoch": 6.87, "learning_rate": 3.0855970955851785e-06, "loss": 0.8632, "step": 82620 }, { "epoch": 6.87, "learning_rate": 3.085486240057645e-06, "loss": 0.7081, "step": 82630 }, { "epoch": 6.87, "learning_rate": 3.085375384530111e-06, "loss": 0.7921, "step": 82640 }, { "epoch": 6.87, "learning_rate": 3.085264529002577e-06, "loss": 0.8321, "step": 82650 }, { "epoch": 6.87, "learning_rate": 3.0851536734750437e-06, "loss": 0.856, "step": 82660 }, { "epoch": 6.87, "learning_rate": 3.0850428179475096e-06, "loss": 0.7884, "step": 82670 }, { "epoch": 6.87, "learning_rate": 3.0849319624199763e-06, "loss": 0.8116, "step": 82680 }, { "epoch": 6.87, "learning_rate": 3.084821106892442e-06, "loss": 0.8407, "step": 82690 }, { "epoch": 6.87, "learning_rate": 3.0847102513649085e-06, "loss": 0.8532, "step": 82700 }, { "epoch": 6.87, "learning_rate": 3.0845993958373748e-06, "loss": 0.8195, "step": 82710 }, { "epoch": 6.88, "learning_rate": 3.084488540309841e-06, "loss": 0.8711, "step": 82720 }, { "epoch": 6.88, "learning_rate": 3.0843776847823074e-06, "loss": 0.9174, "step": 82730 }, { "epoch": 6.88, "learning_rate": 3.0842668292547736e-06, "loss": 0.8435, "step": 82740 }, { "epoch": 6.88, "learning_rate": 3.08415597372724e-06, "loss": 0.8272, "step": 82750 }, { "epoch": 6.88, "learning_rate": 3.0840451181997062e-06, "loss": 0.8113, "step": 82760 }, { "epoch": 6.88, "learning_rate": 3.0839342626721725e-06, "loss": 0.8097, "step": 82770 }, { "epoch": 6.88, "learning_rate": 3.0838234071446384e-06, "loss": 0.7812, "step": 82780 }, { "epoch": 6.88, "learning_rate": 3.083712551617105e-06, "loss": 0.8135, "step": 82790 }, { "epoch": 6.88, "learning_rate": 3.083601696089571e-06, "loss": 0.889, "step": 82800 }, { "epoch": 6.88, "learning_rate": 3.0834908405620373e-06, "loss": 0.8514, "step": 82810 }, { "epoch": 6.88, "learning_rate": 3.0833799850345036e-06, "loss": 0.8377, "step": 82820 }, { "epoch": 6.88, "learning_rate": 3.08326912950697e-06, "loss": 0.8034, "step": 82830 }, { "epoch": 6.89, "learning_rate": 3.0831582739794358e-06, "loss": 0.8, "step": 82840 }, { "epoch": 6.89, "learning_rate": 3.0830474184519025e-06, "loss": 0.9422, "step": 82850 }, { "epoch": 6.89, "learning_rate": 3.0829365629243688e-06, "loss": 0.7349, "step": 82860 }, { "epoch": 6.89, "learning_rate": 3.082825707396835e-06, "loss": 0.8095, "step": 82870 }, { "epoch": 6.89, "learning_rate": 3.0827148518693014e-06, "loss": 0.8212, "step": 82880 }, { "epoch": 6.89, "learning_rate": 3.0826039963417672e-06, "loss": 0.8686, "step": 82890 }, { "epoch": 6.89, "learning_rate": 3.082493140814234e-06, "loss": 0.7463, "step": 82900 }, { "epoch": 6.89, "learning_rate": 3.0823822852867e-06, "loss": 0.7857, "step": 82910 }, { "epoch": 6.89, "learning_rate": 3.082271429759166e-06, "loss": 0.8019, "step": 82920 }, { "epoch": 6.89, "learning_rate": 3.0821605742316324e-06, "loss": 0.7967, "step": 82930 }, { "epoch": 6.89, "learning_rate": 3.0820497187040987e-06, "loss": 0.8064, "step": 82940 }, { "epoch": 6.89, "learning_rate": 3.081938863176565e-06, "loss": 0.8225, "step": 82950 }, { "epoch": 6.9, "learning_rate": 3.0818280076490313e-06, "loss": 0.7655, "step": 82960 }, { "epoch": 6.9, "learning_rate": 3.081717152121497e-06, "loss": 0.8154, "step": 82970 }, { "epoch": 6.9, "learning_rate": 3.081606296593964e-06, "loss": 0.8531, "step": 82980 }, { "epoch": 6.9, "learning_rate": 3.08149544106643e-06, "loss": 0.8383, "step": 82990 }, { "epoch": 6.9, "learning_rate": 3.081384585538896e-06, "loss": 0.8132, "step": 83000 }, { "epoch": 6.9, "learning_rate": 3.0812737300113628e-06, "loss": 0.7654, "step": 83010 }, { "epoch": 6.9, "learning_rate": 3.0811628744838286e-06, "loss": 0.8224, "step": 83020 }, { "epoch": 6.9, "learning_rate": 3.0810520189562954e-06, "loss": 0.8346, "step": 83030 }, { "epoch": 6.9, "learning_rate": 3.0809411634287612e-06, "loss": 0.7944, "step": 83040 }, { "epoch": 6.9, "learning_rate": 3.0808303079012275e-06, "loss": 0.8309, "step": 83050 }, { "epoch": 6.9, "learning_rate": 3.080719452373694e-06, "loss": 0.7622, "step": 83060 }, { "epoch": 6.9, "learning_rate": 3.08060859684616e-06, "loss": 0.8276, "step": 83070 }, { "epoch": 6.91, "learning_rate": 3.080497741318626e-06, "loss": 0.8447, "step": 83080 }, { "epoch": 6.91, "learning_rate": 3.0803868857910927e-06, "loss": 0.8237, "step": 83090 }, { "epoch": 6.91, "learning_rate": 3.080276030263559e-06, "loss": 0.8932, "step": 83100 }, { "epoch": 6.91, "learning_rate": 3.0801651747360253e-06, "loss": 0.8781, "step": 83110 }, { "epoch": 6.91, "learning_rate": 3.0800543192084916e-06, "loss": 0.8486, "step": 83120 }, { "epoch": 6.91, "learning_rate": 3.0799434636809575e-06, "loss": 0.7855, "step": 83130 }, { "epoch": 6.91, "learning_rate": 3.079832608153424e-06, "loss": 0.8015, "step": 83140 }, { "epoch": 6.91, "learning_rate": 3.07972175262589e-06, "loss": 0.8706, "step": 83150 }, { "epoch": 6.91, "learning_rate": 3.0796108970983564e-06, "loss": 0.8509, "step": 83160 }, { "epoch": 6.91, "learning_rate": 3.0795000415708227e-06, "loss": 0.8077, "step": 83170 }, { "epoch": 6.91, "learning_rate": 3.079389186043289e-06, "loss": 0.8771, "step": 83180 }, { "epoch": 6.91, "learning_rate": 3.079278330515755e-06, "loss": 0.8149, "step": 83190 }, { "epoch": 6.92, "learning_rate": 3.0791674749882215e-06, "loss": 0.8403, "step": 83200 }, { "epoch": 6.92, "learning_rate": 3.0790566194606874e-06, "loss": 0.8879, "step": 83210 }, { "epoch": 6.92, "learning_rate": 3.078945763933154e-06, "loss": 0.8524, "step": 83220 }, { "epoch": 6.92, "learning_rate": 3.0788349084056204e-06, "loss": 0.8543, "step": 83230 }, { "epoch": 6.92, "learning_rate": 3.0787240528780863e-06, "loss": 0.8534, "step": 83240 }, { "epoch": 6.92, "learning_rate": 3.078613197350553e-06, "loss": 0.8788, "step": 83250 }, { "epoch": 6.92, "learning_rate": 3.078502341823019e-06, "loss": 0.8026, "step": 83260 }, { "epoch": 6.92, "learning_rate": 3.0783914862954856e-06, "loss": 0.798, "step": 83270 }, { "epoch": 6.92, "learning_rate": 3.0782806307679515e-06, "loss": 0.7954, "step": 83280 }, { "epoch": 6.92, "learning_rate": 3.0781697752404178e-06, "loss": 0.8473, "step": 83290 }, { "epoch": 6.92, "learning_rate": 3.078058919712884e-06, "loss": 0.8174, "step": 83300 }, { "epoch": 6.92, "learning_rate": 3.0779480641853504e-06, "loss": 0.8007, "step": 83310 }, { "epoch": 6.93, "learning_rate": 3.0778372086578162e-06, "loss": 0.8161, "step": 83320 }, { "epoch": 6.93, "learning_rate": 3.077726353130283e-06, "loss": 0.7732, "step": 83330 }, { "epoch": 6.93, "learning_rate": 3.077615497602749e-06, "loss": 0.8511, "step": 83340 }, { "epoch": 6.93, "learning_rate": 3.077504642075215e-06, "loss": 0.8479, "step": 83350 }, { "epoch": 6.93, "learning_rate": 3.077393786547682e-06, "loss": 0.8195, "step": 83360 }, { "epoch": 6.93, "learning_rate": 3.0772829310201477e-06, "loss": 0.8873, "step": 83370 }, { "epoch": 6.93, "learning_rate": 3.0771720754926144e-06, "loss": 0.8289, "step": 83380 }, { "epoch": 6.93, "learning_rate": 3.0770612199650803e-06, "loss": 0.8362, "step": 83390 }, { "epoch": 6.93, "learning_rate": 3.0769503644375466e-06, "loss": 0.8324, "step": 83400 }, { "epoch": 6.93, "learning_rate": 3.076839508910013e-06, "loss": 0.834, "step": 83410 }, { "epoch": 6.93, "learning_rate": 3.076728653382479e-06, "loss": 0.8449, "step": 83420 }, { "epoch": 6.93, "learning_rate": 3.076617797854945e-06, "loss": 0.7573, "step": 83430 }, { "epoch": 6.94, "learning_rate": 3.0765069423274118e-06, "loss": 0.8676, "step": 83440 }, { "epoch": 6.94, "learning_rate": 3.0763960867998777e-06, "loss": 0.8676, "step": 83450 }, { "epoch": 6.94, "learning_rate": 3.0762852312723444e-06, "loss": 0.7906, "step": 83460 }, { "epoch": 6.94, "learning_rate": 3.0761743757448107e-06, "loss": 0.8295, "step": 83470 }, { "epoch": 6.94, "learning_rate": 3.0760635202172765e-06, "loss": 0.7725, "step": 83480 }, { "epoch": 6.94, "learning_rate": 3.0759526646897433e-06, "loss": 0.8721, "step": 83490 }, { "epoch": 6.94, "learning_rate": 3.075841809162209e-06, "loss": 0.8658, "step": 83500 }, { "epoch": 6.94, "learning_rate": 3.0757309536346754e-06, "loss": 0.7575, "step": 83510 }, { "epoch": 6.94, "learning_rate": 3.0756200981071417e-06, "loss": 0.8194, "step": 83520 }, { "epoch": 6.94, "learning_rate": 3.075509242579608e-06, "loss": 0.7672, "step": 83530 }, { "epoch": 6.94, "learning_rate": 3.0753983870520743e-06, "loss": 0.8541, "step": 83540 }, { "epoch": 6.94, "learning_rate": 3.0752875315245406e-06, "loss": 0.8423, "step": 83550 }, { "epoch": 6.95, "learning_rate": 3.0751766759970065e-06, "loss": 0.8114, "step": 83560 }, { "epoch": 6.95, "learning_rate": 3.075065820469473e-06, "loss": 0.8684, "step": 83570 }, { "epoch": 6.95, "learning_rate": 3.074954964941939e-06, "loss": 0.8322, "step": 83580 }, { "epoch": 6.95, "learning_rate": 3.0748441094144054e-06, "loss": 0.8726, "step": 83590 }, { "epoch": 6.95, "learning_rate": 3.074733253886872e-06, "loss": 0.8549, "step": 83600 }, { "epoch": 6.95, "learning_rate": 3.074622398359338e-06, "loss": 0.8152, "step": 83610 }, { "epoch": 6.95, "learning_rate": 3.0745115428318047e-06, "loss": 0.833, "step": 83620 }, { "epoch": 6.95, "learning_rate": 3.0744006873042705e-06, "loss": 0.7812, "step": 83630 }, { "epoch": 6.95, "learning_rate": 3.074289831776737e-06, "loss": 0.839, "step": 83640 }, { "epoch": 6.95, "learning_rate": 3.074178976249203e-06, "loss": 0.8607, "step": 83650 }, { "epoch": 6.95, "learning_rate": 3.0740681207216694e-06, "loss": 0.8179, "step": 83660 }, { "epoch": 6.95, "learning_rate": 3.0739572651941353e-06, "loss": 0.7891, "step": 83670 }, { "epoch": 6.96, "learning_rate": 3.073846409666602e-06, "loss": 0.7647, "step": 83680 }, { "epoch": 6.96, "learning_rate": 3.073735554139068e-06, "loss": 0.784, "step": 83690 }, { "epoch": 6.96, "learning_rate": 3.073624698611534e-06, "loss": 0.7908, "step": 83700 }, { "epoch": 6.96, "learning_rate": 3.073513843084001e-06, "loss": 0.7712, "step": 83710 }, { "epoch": 6.96, "learning_rate": 3.0734140731092204e-06, "loss": 0.7953, "step": 83720 }, { "epoch": 6.96, "learning_rate": 3.0733032175816863e-06, "loss": 0.8375, "step": 83730 }, { "epoch": 6.96, "learning_rate": 3.073192362054153e-06, "loss": 0.8534, "step": 83740 }, { "epoch": 6.96, "learning_rate": 3.073081506526619e-06, "loss": 0.8477, "step": 83750 }, { "epoch": 6.96, "learning_rate": 3.072970650999085e-06, "loss": 0.8675, "step": 83760 }, { "epoch": 6.96, "learning_rate": 3.0728597954715515e-06, "loss": 0.8298, "step": 83770 }, { "epoch": 6.96, "learning_rate": 3.072748939944018e-06, "loss": 0.8588, "step": 83780 }, { "epoch": 6.96, "learning_rate": 3.0726380844164837e-06, "loss": 0.8658, "step": 83790 }, { "epoch": 6.97, "learning_rate": 3.0725272288889504e-06, "loss": 0.8621, "step": 83800 }, { "epoch": 6.97, "learning_rate": 3.0724163733614167e-06, "loss": 0.8066, "step": 83810 }, { "epoch": 6.97, "learning_rate": 3.072305517833883e-06, "loss": 0.8118, "step": 83820 }, { "epoch": 6.97, "learning_rate": 3.0721946623063493e-06, "loss": 0.8386, "step": 83830 }, { "epoch": 6.97, "learning_rate": 3.072083806778815e-06, "loss": 0.7976, "step": 83840 }, { "epoch": 6.97, "learning_rate": 3.071972951251282e-06, "loss": 0.8103, "step": 83850 }, { "epoch": 6.97, "learning_rate": 3.0718620957237477e-06, "loss": 0.8198, "step": 83860 }, { "epoch": 6.97, "learning_rate": 3.071751240196214e-06, "loss": 0.8081, "step": 83870 }, { "epoch": 6.97, "learning_rate": 3.0716403846686803e-06, "loss": 0.7887, "step": 83880 }, { "epoch": 6.97, "learning_rate": 3.0715295291411466e-06, "loss": 0.8633, "step": 83890 }, { "epoch": 6.97, "learning_rate": 3.071418673613613e-06, "loss": 0.8534, "step": 83900 }, { "epoch": 6.97, "learning_rate": 3.071307818086079e-06, "loss": 0.8479, "step": 83910 }, { "epoch": 6.98, "learning_rate": 3.0711969625585455e-06, "loss": 0.8257, "step": 83920 }, { "epoch": 6.98, "learning_rate": 3.071086107031012e-06, "loss": 0.7908, "step": 83930 }, { "epoch": 6.98, "learning_rate": 3.070975251503478e-06, "loss": 0.8145, "step": 83940 }, { "epoch": 6.98, "learning_rate": 3.070864395975944e-06, "loss": 0.8253, "step": 83950 }, { "epoch": 6.98, "learning_rate": 3.0707535404484107e-06, "loss": 0.8566, "step": 83960 }, { "epoch": 6.98, "learning_rate": 3.0706426849208766e-06, "loss": 0.8463, "step": 83970 }, { "epoch": 6.98, "learning_rate": 3.0705318293933433e-06, "loss": 0.8311, "step": 83980 }, { "epoch": 6.98, "learning_rate": 3.070420973865809e-06, "loss": 0.8451, "step": 83990 }, { "epoch": 6.98, "learning_rate": 3.0703101183382754e-06, "loss": 0.8707, "step": 84000 }, { "epoch": 6.98, "learning_rate": 3.0701992628107417e-06, "loss": 0.8001, "step": 84010 }, { "epoch": 6.98, "learning_rate": 3.070088407283208e-06, "loss": 0.7955, "step": 84020 }, { "epoch": 6.98, "learning_rate": 3.069977551755674e-06, "loss": 0.816, "step": 84030 }, { "epoch": 6.99, "learning_rate": 3.0698666962281406e-06, "loss": 0.7909, "step": 84040 }, { "epoch": 6.99, "learning_rate": 3.069755840700607e-06, "loss": 0.9042, "step": 84050 }, { "epoch": 6.99, "learning_rate": 3.0696449851730732e-06, "loss": 0.8494, "step": 84060 }, { "epoch": 6.99, "learning_rate": 3.0695341296455395e-06, "loss": 0.7931, "step": 84070 }, { "epoch": 6.99, "learning_rate": 3.0694232741180054e-06, "loss": 0.8333, "step": 84080 }, { "epoch": 6.99, "learning_rate": 3.069312418590472e-06, "loss": 0.8544, "step": 84090 }, { "epoch": 6.99, "learning_rate": 3.069201563062938e-06, "loss": 0.8358, "step": 84100 }, { "epoch": 6.99, "learning_rate": 3.0690907075354043e-06, "loss": 0.7887, "step": 84110 }, { "epoch": 6.99, "learning_rate": 3.0689798520078706e-06, "loss": 0.8685, "step": 84120 }, { "epoch": 6.99, "learning_rate": 3.068868996480337e-06, "loss": 0.8321, "step": 84130 }, { "epoch": 6.99, "learning_rate": 3.0687581409528027e-06, "loss": 0.841, "step": 84140 }, { "epoch": 6.99, "learning_rate": 3.0686472854252695e-06, "loss": 0.8996, "step": 84150 }, { "epoch": 7.0, "learning_rate": 3.0685364298977353e-06, "loss": 0.7793, "step": 84160 }, { "epoch": 7.0, "learning_rate": 3.068425574370202e-06, "loss": 0.833, "step": 84170 }, { "epoch": 7.0, "learning_rate": 3.0683147188426683e-06, "loss": 0.8674, "step": 84180 }, { "epoch": 7.0, "learning_rate": 3.068203863315134e-06, "loss": 0.8122, "step": 84190 }, { "epoch": 7.0, "learning_rate": 3.068093007787601e-06, "loss": 0.8069, "step": 84200 }, { "epoch": 7.0, "learning_rate": 3.067982152260067e-06, "loss": 0.7915, "step": 84210 }, { "epoch": 7.0, "eval_loss": 1.0508244037628174, "eval_runtime": 351.9951, "eval_samples_per_second": 7.597, "eval_steps_per_second": 3.798, "eval_wer": 0.6494469635970674, "step": 84217 }, { "epoch": 7.0, "learning_rate": 3.0678712967325335e-06, "loss": 0.8332, "step": 84220 }, { "epoch": 7.0, "learning_rate": 3.0677604412049994e-06, "loss": 0.8227, "step": 84230 }, { "epoch": 7.0, "learning_rate": 3.0676495856774657e-06, "loss": 0.8017, "step": 84240 }, { "epoch": 7.0, "learning_rate": 3.067538730149932e-06, "loss": 0.7901, "step": 84250 }, { "epoch": 7.0, "learning_rate": 3.0674278746223983e-06, "loss": 0.7614, "step": 84260 }, { "epoch": 7.0, "learning_rate": 3.067317019094864e-06, "loss": 0.8204, "step": 84270 }, { "epoch": 7.01, "learning_rate": 3.067206163567331e-06, "loss": 0.8662, "step": 84280 }, { "epoch": 7.01, "learning_rate": 3.067095308039797e-06, "loss": 0.7838, "step": 84290 }, { "epoch": 7.01, "learning_rate": 3.066984452512263e-06, "loss": 0.8026, "step": 84300 }, { "epoch": 7.01, "learning_rate": 3.0668735969847298e-06, "loss": 0.8254, "step": 84310 }, { "epoch": 7.01, "learning_rate": 3.0667627414571956e-06, "loss": 0.8668, "step": 84320 }, { "epoch": 7.01, "learning_rate": 3.0666518859296623e-06, "loss": 0.8183, "step": 84330 }, { "epoch": 7.01, "learning_rate": 3.0665410304021282e-06, "loss": 0.7981, "step": 84340 }, { "epoch": 7.01, "learning_rate": 3.0664301748745945e-06, "loss": 0.8602, "step": 84350 }, { "epoch": 7.01, "learning_rate": 3.066319319347061e-06, "loss": 0.7261, "step": 84360 }, { "epoch": 7.01, "learning_rate": 3.066208463819527e-06, "loss": 0.8161, "step": 84370 }, { "epoch": 7.01, "learning_rate": 3.066097608291993e-06, "loss": 0.8726, "step": 84380 }, { "epoch": 7.01, "learning_rate": 3.0659867527644597e-06, "loss": 0.7474, "step": 84390 }, { "epoch": 7.02, "learning_rate": 3.0658758972369256e-06, "loss": 0.7627, "step": 84400 }, { "epoch": 7.02, "learning_rate": 3.0657650417093923e-06, "loss": 0.7343, "step": 84410 }, { "epoch": 7.02, "learning_rate": 3.0656541861818586e-06, "loss": 0.8657, "step": 84420 }, { "epoch": 7.02, "learning_rate": 3.0655433306543245e-06, "loss": 0.7832, "step": 84430 }, { "epoch": 7.02, "learning_rate": 3.065432475126791e-06, "loss": 0.7812, "step": 84440 }, { "epoch": 7.02, "learning_rate": 3.065321619599257e-06, "loss": 0.7298, "step": 84450 }, { "epoch": 7.02, "learning_rate": 3.0652107640717233e-06, "loss": 0.8412, "step": 84460 }, { "epoch": 7.02, "learning_rate": 3.0650999085441896e-06, "loss": 0.7787, "step": 84470 }, { "epoch": 7.02, "learning_rate": 3.064989053016656e-06, "loss": 0.7462, "step": 84480 }, { "epoch": 7.02, "learning_rate": 3.0648781974891222e-06, "loss": 0.9142, "step": 84490 }, { "epoch": 7.02, "learning_rate": 3.0647673419615885e-06, "loss": 0.814, "step": 84500 }, { "epoch": 7.02, "learning_rate": 3.0646564864340544e-06, "loss": 0.8007, "step": 84510 }, { "epoch": 7.03, "learning_rate": 3.064545630906521e-06, "loss": 0.7927, "step": 84520 }, { "epoch": 7.03, "learning_rate": 3.064434775378987e-06, "loss": 0.8543, "step": 84530 }, { "epoch": 7.03, "learning_rate": 3.0643239198514533e-06, "loss": 0.8974, "step": 84540 }, { "epoch": 7.03, "learning_rate": 3.06421306432392e-06, "loss": 0.8792, "step": 84550 }, { "epoch": 7.03, "learning_rate": 3.064102208796386e-06, "loss": 0.851, "step": 84560 }, { "epoch": 7.03, "learning_rate": 3.0639913532688526e-06, "loss": 0.8259, "step": 84570 }, { "epoch": 7.03, "learning_rate": 3.0638804977413185e-06, "loss": 0.8246, "step": 84580 }, { "epoch": 7.03, "learning_rate": 3.0637696422137848e-06, "loss": 0.8025, "step": 84590 }, { "epoch": 7.03, "learning_rate": 3.063658786686251e-06, "loss": 0.8195, "step": 84600 }, { "epoch": 7.03, "learning_rate": 3.0635479311587173e-06, "loss": 0.7699, "step": 84610 }, { "epoch": 7.03, "learning_rate": 3.0634370756311832e-06, "loss": 0.9223, "step": 84620 }, { "epoch": 7.03, "learning_rate": 3.06332622010365e-06, "loss": 0.8502, "step": 84630 }, { "epoch": 7.04, "learning_rate": 3.063215364576116e-06, "loss": 0.8535, "step": 84640 }, { "epoch": 7.04, "learning_rate": 3.063104509048582e-06, "loss": 0.7733, "step": 84650 }, { "epoch": 7.04, "learning_rate": 3.062993653521049e-06, "loss": 0.803, "step": 84660 }, { "epoch": 7.04, "learning_rate": 3.0628827979935147e-06, "loss": 0.8215, "step": 84670 }, { "epoch": 7.04, "learning_rate": 3.0627719424659814e-06, "loss": 0.8457, "step": 84680 }, { "epoch": 7.04, "learning_rate": 3.0626610869384473e-06, "loss": 0.8377, "step": 84690 }, { "epoch": 7.04, "learning_rate": 3.0625502314109136e-06, "loss": 0.7434, "step": 84700 }, { "epoch": 7.04, "learning_rate": 3.06243937588338e-06, "loss": 0.8468, "step": 84710 }, { "epoch": 7.04, "learning_rate": 3.062328520355846e-06, "loss": 0.7977, "step": 84720 }, { "epoch": 7.04, "learning_rate": 3.062217664828312e-06, "loss": 0.8575, "step": 84730 }, { "epoch": 7.04, "learning_rate": 3.0621068093007788e-06, "loss": 0.8548, "step": 84740 }, { "epoch": 7.04, "learning_rate": 3.0619959537732446e-06, "loss": 0.8317, "step": 84750 }, { "epoch": 7.05, "learning_rate": 3.0618850982457113e-06, "loss": 0.7724, "step": 84760 }, { "epoch": 7.05, "learning_rate": 3.0617742427181772e-06, "loss": 0.832, "step": 84770 }, { "epoch": 7.05, "learning_rate": 3.0616633871906435e-06, "loss": 0.8084, "step": 84780 }, { "epoch": 7.05, "learning_rate": 3.0615525316631102e-06, "loss": 0.7861, "step": 84790 }, { "epoch": 7.05, "learning_rate": 3.061441676135576e-06, "loss": 0.7697, "step": 84800 }, { "epoch": 7.05, "learning_rate": 3.0613308206080424e-06, "loss": 0.7559, "step": 84810 }, { "epoch": 7.05, "learning_rate": 3.0612199650805087e-06, "loss": 0.8389, "step": 84820 }, { "epoch": 7.05, "learning_rate": 3.061109109552975e-06, "loss": 0.8582, "step": 84830 }, { "epoch": 7.05, "learning_rate": 3.0609982540254413e-06, "loss": 0.8447, "step": 84840 }, { "epoch": 7.05, "learning_rate": 3.0608873984979076e-06, "loss": 0.7896, "step": 84850 }, { "epoch": 7.05, "learning_rate": 3.0607765429703735e-06, "loss": 0.9634, "step": 84860 }, { "epoch": 7.05, "learning_rate": 3.06066568744284e-06, "loss": 0.7482, "step": 84870 }, { "epoch": 7.06, "learning_rate": 3.060554831915306e-06, "loss": 0.8024, "step": 84880 }, { "epoch": 7.06, "learning_rate": 3.060455061940526e-06, "loss": 0.7905, "step": 84890 }, { "epoch": 7.06, "learning_rate": 3.060344206412992e-06, "loss": 0.7506, "step": 84900 }, { "epoch": 7.06, "learning_rate": 3.0602333508854586e-06, "loss": 0.7437, "step": 84910 }, { "epoch": 7.06, "learning_rate": 3.0601224953579245e-06, "loss": 0.7571, "step": 84920 }, { "epoch": 7.06, "learning_rate": 3.060011639830391e-06, "loss": 0.8605, "step": 84930 }, { "epoch": 7.06, "learning_rate": 3.059900784302857e-06, "loss": 0.7797, "step": 84940 }, { "epoch": 7.06, "learning_rate": 3.0597899287753234e-06, "loss": 0.7997, "step": 84950 }, { "epoch": 7.06, "learning_rate": 3.0596790732477897e-06, "loss": 0.8166, "step": 84960 }, { "epoch": 7.06, "learning_rate": 3.059568217720256e-06, "loss": 0.7828, "step": 84970 }, { "epoch": 7.06, "learning_rate": 3.059457362192722e-06, "loss": 0.9241, "step": 84980 }, { "epoch": 7.06, "learning_rate": 3.0593465066651885e-06, "loss": 0.8121, "step": 84990 }, { "epoch": 7.07, "learning_rate": 3.059235651137655e-06, "loss": 0.7827, "step": 85000 }, { "epoch": 7.07, "learning_rate": 3.059124795610121e-06, "loss": 0.8432, "step": 85010 }, { "epoch": 7.07, "learning_rate": 3.0590139400825874e-06, "loss": 0.8448, "step": 85020 }, { "epoch": 7.07, "learning_rate": 3.0589030845550533e-06, "loss": 0.7866, "step": 85030 }, { "epoch": 7.07, "learning_rate": 3.05879222902752e-06, "loss": 0.8155, "step": 85040 }, { "epoch": 7.07, "learning_rate": 3.058681373499986e-06, "loss": 0.7911, "step": 85050 }, { "epoch": 7.07, "learning_rate": 3.058570517972452e-06, "loss": 0.795, "step": 85060 }, { "epoch": 7.07, "learning_rate": 3.0584596624449185e-06, "loss": 0.8303, "step": 85070 }, { "epoch": 7.07, "learning_rate": 3.0583488069173848e-06, "loss": 0.8453, "step": 85080 }, { "epoch": 7.07, "learning_rate": 3.0582379513898506e-06, "loss": 0.7373, "step": 85090 }, { "epoch": 7.07, "learning_rate": 3.0581270958623174e-06, "loss": 0.8551, "step": 85100 }, { "epoch": 7.07, "learning_rate": 3.0580162403347832e-06, "loss": 0.8315, "step": 85110 }, { "epoch": 7.08, "learning_rate": 3.05790538480725e-06, "loss": 0.8059, "step": 85120 }, { "epoch": 7.08, "learning_rate": 3.0577945292797163e-06, "loss": 0.8406, "step": 85130 }, { "epoch": 7.08, "learning_rate": 3.057683673752182e-06, "loss": 0.7725, "step": 85140 }, { "epoch": 7.08, "learning_rate": 3.057572818224649e-06, "loss": 0.7614, "step": 85150 }, { "epoch": 7.08, "learning_rate": 3.0574619626971147e-06, "loss": 0.8398, "step": 85160 }, { "epoch": 7.08, "learning_rate": 3.0573511071695814e-06, "loss": 0.7942, "step": 85170 }, { "epoch": 7.08, "learning_rate": 3.0572402516420473e-06, "loss": 0.8878, "step": 85180 }, { "epoch": 7.08, "learning_rate": 3.0571293961145136e-06, "loss": 0.7878, "step": 85190 }, { "epoch": 7.08, "learning_rate": 3.05701854058698e-06, "loss": 0.7937, "step": 85200 }, { "epoch": 7.08, "learning_rate": 3.056907685059446e-06, "loss": 0.768, "step": 85210 }, { "epoch": 7.08, "learning_rate": 3.056796829531912e-06, "loss": 0.8481, "step": 85220 }, { "epoch": 7.08, "learning_rate": 3.0566859740043788e-06, "loss": 0.8563, "step": 85230 }, { "epoch": 7.09, "learning_rate": 3.056575118476845e-06, "loss": 0.7948, "step": 85240 }, { "epoch": 7.09, "learning_rate": 3.056464262949311e-06, "loss": 0.8348, "step": 85250 }, { "epoch": 7.09, "learning_rate": 3.0563534074217777e-06, "loss": 0.834, "step": 85260 }, { "epoch": 7.09, "learning_rate": 3.0562425518942435e-06, "loss": 0.8059, "step": 85270 }, { "epoch": 7.09, "learning_rate": 3.0561316963667103e-06, "loss": 0.8012, "step": 85280 }, { "epoch": 7.09, "learning_rate": 3.056020840839176e-06, "loss": 0.7925, "step": 85290 }, { "epoch": 7.09, "learning_rate": 3.0559099853116424e-06, "loss": 0.7762, "step": 85300 }, { "epoch": 7.09, "learning_rate": 3.0557991297841087e-06, "loss": 0.7517, "step": 85310 }, { "epoch": 7.09, "learning_rate": 3.055688274256575e-06, "loss": 0.8073, "step": 85320 }, { "epoch": 7.09, "learning_rate": 3.055577418729041e-06, "loss": 0.7879, "step": 85330 }, { "epoch": 7.09, "learning_rate": 3.0554665632015076e-06, "loss": 0.7275, "step": 85340 }, { "epoch": 7.09, "learning_rate": 3.0553557076739735e-06, "loss": 0.7731, "step": 85350 }, { "epoch": 7.1, "learning_rate": 3.05524485214644e-06, "loss": 0.8371, "step": 85360 }, { "epoch": 7.1, "learning_rate": 3.0551339966189065e-06, "loss": 0.8835, "step": 85370 }, { "epoch": 7.1, "learning_rate": 3.0550231410913724e-06, "loss": 0.9241, "step": 85380 }, { "epoch": 7.1, "learning_rate": 3.054912285563839e-06, "loss": 0.7699, "step": 85390 }, { "epoch": 7.1, "learning_rate": 3.054801430036305e-06, "loss": 0.8198, "step": 85400 }, { "epoch": 7.1, "learning_rate": 3.0546905745087712e-06, "loss": 0.82, "step": 85410 }, { "epoch": 7.1, "learning_rate": 3.0545797189812375e-06, "loss": 0.8328, "step": 85420 }, { "epoch": 7.1, "learning_rate": 3.054468863453704e-06, "loss": 0.8343, "step": 85430 }, { "epoch": 7.1, "learning_rate": 3.05435800792617e-06, "loss": 0.8395, "step": 85440 }, { "epoch": 7.1, "learning_rate": 3.0542471523986364e-06, "loss": 0.8154, "step": 85450 }, { "epoch": 7.1, "learning_rate": 3.0541362968711023e-06, "loss": 0.811, "step": 85460 }, { "epoch": 7.1, "learning_rate": 3.054025441343569e-06, "loss": 0.8205, "step": 85470 }, { "epoch": 7.1, "learning_rate": 3.053914585816035e-06, "loss": 0.7922, "step": 85480 }, { "epoch": 7.11, "learning_rate": 3.053803730288501e-06, "loss": 0.8313, "step": 85490 }, { "epoch": 7.11, "learning_rate": 3.053692874760968e-06, "loss": 0.7559, "step": 85500 }, { "epoch": 7.11, "learning_rate": 3.0535820192334338e-06, "loss": 0.8079, "step": 85510 }, { "epoch": 7.11, "learning_rate": 3.0534711637059005e-06, "loss": 0.8447, "step": 85520 }, { "epoch": 7.11, "learning_rate": 3.0533603081783664e-06, "loss": 0.7598, "step": 85530 }, { "epoch": 7.11, "learning_rate": 3.0532494526508327e-06, "loss": 0.8197, "step": 85540 }, { "epoch": 7.11, "learning_rate": 3.053138597123299e-06, "loss": 0.779, "step": 85550 }, { "epoch": 7.11, "learning_rate": 3.0530277415957653e-06, "loss": 0.7752, "step": 85560 }, { "epoch": 7.11, "learning_rate": 3.052916886068231e-06, "loss": 0.7772, "step": 85570 }, { "epoch": 7.11, "learning_rate": 3.052806030540698e-06, "loss": 0.8738, "step": 85580 }, { "epoch": 7.11, "learning_rate": 3.0526951750131637e-06, "loss": 0.7856, "step": 85590 }, { "epoch": 7.11, "learning_rate": 3.05258431948563e-06, "loss": 0.7391, "step": 85600 }, { "epoch": 7.12, "learning_rate": 3.0524734639580967e-06, "loss": 0.8767, "step": 85610 }, { "epoch": 7.12, "learning_rate": 3.0523626084305626e-06, "loss": 0.8354, "step": 85620 }, { "epoch": 7.12, "learning_rate": 3.0522517529030293e-06, "loss": 0.8394, "step": 85630 }, { "epoch": 7.12, "learning_rate": 3.052140897375495e-06, "loss": 0.8559, "step": 85640 }, { "epoch": 7.12, "learning_rate": 3.0520300418479615e-06, "loss": 0.7587, "step": 85650 }, { "epoch": 7.12, "learning_rate": 3.0519191863204278e-06, "loss": 0.8061, "step": 85660 }, { "epoch": 7.12, "learning_rate": 3.051808330792894e-06, "loss": 0.8064, "step": 85670 }, { "epoch": 7.12, "learning_rate": 3.05169747526536e-06, "loss": 0.8089, "step": 85680 }, { "epoch": 7.12, "learning_rate": 3.0515866197378267e-06, "loss": 0.8059, "step": 85690 }, { "epoch": 7.12, "learning_rate": 3.0514757642102925e-06, "loss": 0.818, "step": 85700 }, { "epoch": 7.12, "learning_rate": 3.0513649086827593e-06, "loss": 0.8323, "step": 85710 }, { "epoch": 7.12, "learning_rate": 3.051254053155225e-06, "loss": 0.8244, "step": 85720 }, { "epoch": 7.13, "learning_rate": 3.0511431976276914e-06, "loss": 0.8089, "step": 85730 }, { "epoch": 7.13, "learning_rate": 3.051032342100158e-06, "loss": 0.8105, "step": 85740 }, { "epoch": 7.13, "learning_rate": 3.050921486572624e-06, "loss": 0.8286, "step": 85750 }, { "epoch": 7.13, "learning_rate": 3.0508106310450903e-06, "loss": 0.8398, "step": 85760 }, { "epoch": 7.13, "learning_rate": 3.0506997755175566e-06, "loss": 0.795, "step": 85770 }, { "epoch": 7.13, "learning_rate": 3.050588919990023e-06, "loss": 0.8729, "step": 85780 }, { "epoch": 7.13, "learning_rate": 3.050478064462489e-06, "loss": 0.7669, "step": 85790 }, { "epoch": 7.13, "learning_rate": 3.0503672089349555e-06, "loss": 0.8163, "step": 85800 }, { "epoch": 7.13, "learning_rate": 3.0502563534074214e-06, "loss": 0.803, "step": 85810 }, { "epoch": 7.13, "learning_rate": 3.050145497879888e-06, "loss": 0.7728, "step": 85820 }, { "epoch": 7.13, "learning_rate": 3.050034642352354e-06, "loss": 0.8564, "step": 85830 }, { "epoch": 7.13, "learning_rate": 3.0499237868248203e-06, "loss": 0.7905, "step": 85840 }, { "epoch": 7.14, "learning_rate": 3.0498129312972866e-06, "loss": 0.8535, "step": 85850 }, { "epoch": 7.14, "learning_rate": 3.049702075769753e-06, "loss": 0.8892, "step": 85860 }, { "epoch": 7.14, "learning_rate": 3.0495912202422196e-06, "loss": 0.8176, "step": 85870 }, { "epoch": 7.14, "learning_rate": 3.0494803647146854e-06, "loss": 0.7917, "step": 85880 }, { "epoch": 7.14, "learning_rate": 3.0493695091871517e-06, "loss": 0.8182, "step": 85890 }, { "epoch": 7.14, "learning_rate": 3.049258653659618e-06, "loss": 0.816, "step": 85900 }, { "epoch": 7.14, "learning_rate": 3.0491477981320843e-06, "loss": 0.8053, "step": 85910 }, { "epoch": 7.14, "learning_rate": 3.04903694260455e-06, "loss": 0.79, "step": 85920 }, { "epoch": 7.14, "learning_rate": 3.048926087077017e-06, "loss": 0.8541, "step": 85930 }, { "epoch": 7.14, "learning_rate": 3.0488152315494828e-06, "loss": 0.9003, "step": 85940 }, { "epoch": 7.14, "learning_rate": 3.0487043760219495e-06, "loss": 0.7881, "step": 85950 }, { "epoch": 7.14, "learning_rate": 3.0485935204944154e-06, "loss": 0.8253, "step": 85960 }, { "epoch": 7.15, "learning_rate": 3.0484826649668817e-06, "loss": 0.8514, "step": 85970 }, { "epoch": 7.15, "learning_rate": 3.0483718094393484e-06, "loss": 0.8086, "step": 85980 }, { "epoch": 7.15, "learning_rate": 3.0482609539118143e-06, "loss": 0.7736, "step": 85990 }, { "epoch": 7.15, "learning_rate": 3.0481500983842806e-06, "loss": 0.7662, "step": 86000 }, { "epoch": 7.15, "learning_rate": 3.048039242856747e-06, "loss": 0.8041, "step": 86010 }, { "epoch": 7.15, "learning_rate": 3.047928387329213e-06, "loss": 0.8459, "step": 86020 }, { "epoch": 7.15, "learning_rate": 3.047817531801679e-06, "loss": 0.7826, "step": 86030 }, { "epoch": 7.15, "learning_rate": 3.0477066762741457e-06, "loss": 0.7803, "step": 86040 }, { "epoch": 7.15, "learning_rate": 3.0475958207466116e-06, "loss": 0.762, "step": 86050 }, { "epoch": 7.15, "learning_rate": 3.0474849652190783e-06, "loss": 0.7744, "step": 86060 }, { "epoch": 7.15, "learning_rate": 3.047374109691544e-06, "loss": 0.8508, "step": 86070 }, { "epoch": 7.15, "learning_rate": 3.0472632541640105e-06, "loss": 0.7958, "step": 86080 }, { "epoch": 7.16, "learning_rate": 3.047152398636477e-06, "loss": 0.748, "step": 86090 }, { "epoch": 7.16, "learning_rate": 3.047041543108943e-06, "loss": 0.78, "step": 86100 }, { "epoch": 7.16, "learning_rate": 3.0469306875814094e-06, "loss": 0.8364, "step": 86110 }, { "epoch": 7.16, "learning_rate": 3.0468198320538757e-06, "loss": 0.8451, "step": 86120 }, { "epoch": 7.16, "learning_rate": 3.046708976526342e-06, "loss": 0.8576, "step": 86130 }, { "epoch": 7.16, "learning_rate": 3.0465981209988083e-06, "loss": 0.7572, "step": 86140 }, { "epoch": 7.16, "learning_rate": 3.0464872654712746e-06, "loss": 0.8023, "step": 86150 }, { "epoch": 7.16, "learning_rate": 3.0463764099437404e-06, "loss": 0.8604, "step": 86160 }, { "epoch": 7.16, "learning_rate": 3.046265554416207e-06, "loss": 0.8323, "step": 86170 }, { "epoch": 7.16, "learning_rate": 3.046154698888673e-06, "loss": 0.8212, "step": 86180 }, { "epoch": 7.16, "learning_rate": 3.0460438433611393e-06, "loss": 0.7822, "step": 86190 }, { "epoch": 7.16, "learning_rate": 3.0459329878336056e-06, "loss": 0.7591, "step": 86200 }, { "epoch": 7.17, "learning_rate": 3.045822132306072e-06, "loss": 0.8245, "step": 86210 }, { "epoch": 7.17, "learning_rate": 3.0457112767785386e-06, "loss": 0.7885, "step": 86220 }, { "epoch": 7.17, "learning_rate": 3.0456004212510045e-06, "loss": 0.8311, "step": 86230 }, { "epoch": 7.17, "learning_rate": 3.045489565723471e-06, "loss": 0.8136, "step": 86240 }, { "epoch": 7.17, "learning_rate": 3.045378710195937e-06, "loss": 0.8053, "step": 86250 }, { "epoch": 7.17, "learning_rate": 3.0452678546684034e-06, "loss": 0.8023, "step": 86260 }, { "epoch": 7.17, "learning_rate": 3.0451569991408693e-06, "loss": 0.8411, "step": 86270 }, { "epoch": 7.17, "learning_rate": 3.045046143613336e-06, "loss": 0.8735, "step": 86280 }, { "epoch": 7.17, "learning_rate": 3.044935288085802e-06, "loss": 0.8668, "step": 86290 }, { "epoch": 7.17, "learning_rate": 3.0448244325582686e-06, "loss": 0.9004, "step": 86300 }, { "epoch": 7.17, "learning_rate": 3.0447135770307344e-06, "loss": 0.8071, "step": 86310 }, { "epoch": 7.17, "learning_rate": 3.0446027215032007e-06, "loss": 0.8035, "step": 86320 }, { "epoch": 7.18, "learning_rate": 3.044491865975667e-06, "loss": 0.8523, "step": 86330 }, { "epoch": 7.18, "learning_rate": 3.0443810104481333e-06, "loss": 0.8655, "step": 86340 }, { "epoch": 7.18, "learning_rate": 3.0442701549205996e-06, "loss": 0.7398, "step": 86350 }, { "epoch": 7.18, "learning_rate": 3.044159299393066e-06, "loss": 0.79, "step": 86360 }, { "epoch": 7.18, "learning_rate": 3.0440484438655322e-06, "loss": 0.8773, "step": 86370 }, { "epoch": 7.18, "learning_rate": 3.043937588337998e-06, "loss": 0.8484, "step": 86380 }, { "epoch": 7.18, "learning_rate": 3.043826732810465e-06, "loss": 0.7058, "step": 86390 }, { "epoch": 7.18, "learning_rate": 3.0437158772829307e-06, "loss": 0.7735, "step": 86400 }, { "epoch": 7.18, "learning_rate": 3.0436050217553974e-06, "loss": 0.82, "step": 86410 }, { "epoch": 7.18, "learning_rate": 3.0434941662278633e-06, "loss": 0.7913, "step": 86420 }, { "epoch": 7.18, "learning_rate": 3.0433833107003296e-06, "loss": 0.8874, "step": 86430 }, { "epoch": 7.18, "learning_rate": 3.043272455172796e-06, "loss": 0.7651, "step": 86440 }, { "epoch": 7.19, "learning_rate": 3.043161599645262e-06, "loss": 0.7996, "step": 86450 }, { "epoch": 7.19, "learning_rate": 3.043050744117728e-06, "loss": 0.797, "step": 86460 }, { "epoch": 7.19, "learning_rate": 3.0429398885901947e-06, "loss": 0.7796, "step": 86470 }, { "epoch": 7.19, "learning_rate": 3.042829033062661e-06, "loss": 0.7887, "step": 86480 }, { "epoch": 7.19, "learning_rate": 3.0427181775351273e-06, "loss": 0.7886, "step": 86490 }, { "epoch": 7.19, "learning_rate": 3.0426073220075936e-06, "loss": 0.8395, "step": 86500 }, { "epoch": 7.19, "learning_rate": 3.0424964664800595e-06, "loss": 0.7626, "step": 86510 }, { "epoch": 7.19, "learning_rate": 3.0423856109525262e-06, "loss": 0.8477, "step": 86520 }, { "epoch": 7.19, "learning_rate": 3.042274755424992e-06, "loss": 0.8278, "step": 86530 }, { "epoch": 7.19, "learning_rate": 3.0421638998974584e-06, "loss": 0.7948, "step": 86540 }, { "epoch": 7.19, "learning_rate": 3.0420530443699247e-06, "loss": 0.7549, "step": 86550 }, { "epoch": 7.19, "learning_rate": 3.041942188842391e-06, "loss": 0.8637, "step": 86560 }, { "epoch": 7.2, "learning_rate": 3.0418313333148573e-06, "loss": 0.7992, "step": 86570 }, { "epoch": 7.2, "learning_rate": 3.0417204777873236e-06, "loss": 0.8607, "step": 86580 }, { "epoch": 7.2, "learning_rate": 3.04160962225979e-06, "loss": 0.796, "step": 86590 }, { "epoch": 7.2, "learning_rate": 3.041498766732256e-06, "loss": 0.8326, "step": 86600 }, { "epoch": 7.2, "learning_rate": 3.0413879112047225e-06, "loss": 0.7851, "step": 86610 }, { "epoch": 7.2, "learning_rate": 3.0412770556771883e-06, "loss": 0.8831, "step": 86620 }, { "epoch": 7.2, "learning_rate": 3.041166200149655e-06, "loss": 0.7918, "step": 86630 }, { "epoch": 7.2, "learning_rate": 3.041055344622121e-06, "loss": 0.8957, "step": 86640 }, { "epoch": 7.2, "learning_rate": 3.0409444890945876e-06, "loss": 0.8619, "step": 86650 }, { "epoch": 7.2, "learning_rate": 3.0408336335670535e-06, "loss": 0.7691, "step": 86660 }, { "epoch": 7.2, "learning_rate": 3.04072277803952e-06, "loss": 0.883, "step": 86670 }, { "epoch": 7.2, "learning_rate": 3.040611922511986e-06, "loss": 0.8653, "step": 86680 }, { "epoch": 7.21, "learning_rate": 3.0405010669844524e-06, "loss": 0.7874, "step": 86690 }, { "epoch": 7.21, "learning_rate": 3.0403902114569183e-06, "loss": 0.884, "step": 86700 }, { "epoch": 7.21, "learning_rate": 3.040279355929385e-06, "loss": 0.7703, "step": 86710 }, { "epoch": 7.21, "learning_rate": 3.0401685004018513e-06, "loss": 0.7996, "step": 86720 }, { "epoch": 7.21, "learning_rate": 3.0400576448743176e-06, "loss": 0.7594, "step": 86730 }, { "epoch": 7.21, "learning_rate": 3.039946789346784e-06, "loss": 0.8278, "step": 86740 }, { "epoch": 7.21, "learning_rate": 3.0398359338192497e-06, "loss": 0.7205, "step": 86750 }, { "epoch": 7.21, "learning_rate": 3.0397250782917165e-06, "loss": 0.7351, "step": 86760 }, { "epoch": 7.21, "learning_rate": 3.0396142227641823e-06, "loss": 0.8007, "step": 86770 }, { "epoch": 7.21, "learning_rate": 3.0395033672366486e-06, "loss": 0.8516, "step": 86780 }, { "epoch": 7.21, "learning_rate": 3.039392511709115e-06, "loss": 0.8383, "step": 86790 }, { "epoch": 7.21, "learning_rate": 3.0392816561815812e-06, "loss": 0.7625, "step": 86800 }, { "epoch": 7.22, "learning_rate": 3.039170800654047e-06, "loss": 0.8275, "step": 86810 }, { "epoch": 7.22, "learning_rate": 3.039059945126514e-06, "loss": 0.801, "step": 86820 }, { "epoch": 7.22, "learning_rate": 3.0389490895989797e-06, "loss": 0.8343, "step": 86830 }, { "epoch": 7.22, "learning_rate": 3.0388382340714464e-06, "loss": 0.8133, "step": 86840 }, { "epoch": 7.22, "learning_rate": 3.0387273785439127e-06, "loss": 0.8317, "step": 86850 }, { "epoch": 7.22, "learning_rate": 3.0386165230163786e-06, "loss": 0.9016, "step": 86860 }, { "epoch": 7.22, "learning_rate": 3.0385056674888453e-06, "loss": 0.7896, "step": 86870 }, { "epoch": 7.22, "learning_rate": 3.038394811961311e-06, "loss": 0.8913, "step": 86880 }, { "epoch": 7.22, "learning_rate": 3.0382839564337775e-06, "loss": 0.817, "step": 86890 }, { "epoch": 7.22, "learning_rate": 3.0381731009062437e-06, "loss": 0.8215, "step": 86900 }, { "epoch": 7.22, "learning_rate": 3.03806224537871e-06, "loss": 0.7999, "step": 86910 }, { "epoch": 7.22, "learning_rate": 3.0379513898511763e-06, "loss": 0.8371, "step": 86920 }, { "epoch": 7.23, "learning_rate": 3.0378405343236426e-06, "loss": 0.8211, "step": 86930 }, { "epoch": 7.23, "learning_rate": 3.0377296787961085e-06, "loss": 0.7469, "step": 86940 }, { "epoch": 7.23, "learning_rate": 3.0376188232685752e-06, "loss": 0.8895, "step": 86950 }, { "epoch": 7.23, "learning_rate": 3.0375079677410415e-06, "loss": 0.8218, "step": 86960 }, { "epoch": 7.23, "learning_rate": 3.0373971122135074e-06, "loss": 0.7933, "step": 86970 }, { "epoch": 7.23, "learning_rate": 3.037286256685974e-06, "loss": 0.7893, "step": 86980 }, { "epoch": 7.23, "learning_rate": 3.03717540115844e-06, "loss": 0.7502, "step": 86990 }, { "epoch": 7.23, "learning_rate": 3.0370645456309067e-06, "loss": 0.8221, "step": 87000 }, { "epoch": 7.23, "learning_rate": 3.0369536901033726e-06, "loss": 0.8485, "step": 87010 }, { "epoch": 7.23, "learning_rate": 3.036842834575839e-06, "loss": 0.7769, "step": 87020 }, { "epoch": 7.23, "learning_rate": 3.036731979048305e-06, "loss": 0.8114, "step": 87030 }, { "epoch": 7.23, "learning_rate": 3.0366211235207715e-06, "loss": 0.7825, "step": 87040 }, { "epoch": 7.24, "learning_rate": 3.0365102679932373e-06, "loss": 0.7796, "step": 87050 }, { "epoch": 7.24, "learning_rate": 3.036399412465704e-06, "loss": 0.7886, "step": 87060 }, { "epoch": 7.24, "learning_rate": 3.03628855693817e-06, "loss": 0.7899, "step": 87070 }, { "epoch": 7.24, "learning_rate": 3.0361777014106366e-06, "loss": 0.8481, "step": 87080 }, { "epoch": 7.24, "learning_rate": 3.036066845883103e-06, "loss": 0.853, "step": 87090 }, { "epoch": 7.24, "learning_rate": 3.035955990355569e-06, "loss": 0.75, "step": 87100 }, { "epoch": 7.24, "learning_rate": 3.0358451348280355e-06, "loss": 0.8429, "step": 87110 }, { "epoch": 7.24, "learning_rate": 3.0357342793005014e-06, "loss": 0.8065, "step": 87120 }, { "epoch": 7.24, "learning_rate": 3.0356234237729677e-06, "loss": 0.8424, "step": 87130 }, { "epoch": 7.24, "learning_rate": 3.035512568245434e-06, "loss": 0.7682, "step": 87140 }, { "epoch": 7.24, "learning_rate": 3.0354017127179003e-06, "loss": 0.8347, "step": 87150 }, { "epoch": 7.24, "learning_rate": 3.0352908571903666e-06, "loss": 0.7629, "step": 87160 }, { "epoch": 7.25, "learning_rate": 3.035180001662833e-06, "loss": 0.8632, "step": 87170 }, { "epoch": 7.25, "learning_rate": 3.0350691461352987e-06, "loss": 0.8416, "step": 87180 }, { "epoch": 7.25, "learning_rate": 3.0349582906077655e-06, "loss": 0.7636, "step": 87190 }, { "epoch": 7.25, "learning_rate": 3.0348474350802313e-06, "loss": 0.8243, "step": 87200 }, { "epoch": 7.25, "learning_rate": 3.0347365795526976e-06, "loss": 0.823, "step": 87210 }, { "epoch": 7.25, "learning_rate": 3.0346257240251644e-06, "loss": 0.8077, "step": 87220 }, { "epoch": 7.25, "learning_rate": 3.0345148684976302e-06, "loss": 0.8033, "step": 87230 }, { "epoch": 7.25, "learning_rate": 3.034404012970097e-06, "loss": 0.7792, "step": 87240 }, { "epoch": 7.25, "learning_rate": 3.034293157442563e-06, "loss": 0.79, "step": 87250 }, { "epoch": 7.25, "learning_rate": 3.034182301915029e-06, "loss": 0.8018, "step": 87260 }, { "epoch": 7.25, "learning_rate": 3.0340714463874954e-06, "loss": 0.7915, "step": 87270 }, { "epoch": 7.25, "learning_rate": 3.0339605908599617e-06, "loss": 0.8719, "step": 87280 }, { "epoch": 7.26, "learning_rate": 3.0338497353324276e-06, "loss": 0.7547, "step": 87290 }, { "epoch": 7.26, "learning_rate": 3.0337388798048943e-06, "loss": 0.7681, "step": 87300 }, { "epoch": 7.26, "learning_rate": 3.03362802427736e-06, "loss": 0.8356, "step": 87310 }, { "epoch": 7.26, "learning_rate": 3.0335171687498265e-06, "loss": 0.8307, "step": 87320 }, { "epoch": 7.26, "learning_rate": 3.033406313222293e-06, "loss": 0.8632, "step": 87330 }, { "epoch": 7.26, "learning_rate": 3.033295457694759e-06, "loss": 1.0202, "step": 87340 }, { "epoch": 7.26, "learning_rate": 3.0331846021672258e-06, "loss": 0.8258, "step": 87350 }, { "epoch": 7.26, "learning_rate": 3.0330737466396916e-06, "loss": 0.7784, "step": 87360 }, { "epoch": 7.26, "learning_rate": 3.032962891112158e-06, "loss": 0.8021, "step": 87370 }, { "epoch": 7.26, "learning_rate": 3.0328520355846242e-06, "loss": 0.7804, "step": 87380 }, { "epoch": 7.26, "learning_rate": 3.0327411800570905e-06, "loss": 0.8086, "step": 87390 }, { "epoch": 7.26, "learning_rate": 3.0326303245295564e-06, "loss": 0.7935, "step": 87400 }, { "epoch": 7.27, "learning_rate": 3.032519469002023e-06, "loss": 0.8154, "step": 87410 }, { "epoch": 7.27, "learning_rate": 3.032408613474489e-06, "loss": 0.8537, "step": 87420 }, { "epoch": 7.27, "learning_rate": 3.0322977579469557e-06, "loss": 0.8389, "step": 87430 }, { "epoch": 7.27, "learning_rate": 3.0321869024194216e-06, "loss": 0.7781, "step": 87440 }, { "epoch": 7.27, "learning_rate": 3.032076046891888e-06, "loss": 0.8391, "step": 87450 }, { "epoch": 7.27, "learning_rate": 3.0319651913643546e-06, "loss": 0.8415, "step": 87460 }, { "epoch": 7.27, "learning_rate": 3.0318543358368205e-06, "loss": 0.785, "step": 87470 }, { "epoch": 7.27, "learning_rate": 3.0317434803092868e-06, "loss": 0.8843, "step": 87480 }, { "epoch": 7.27, "learning_rate": 3.031632624781753e-06, "loss": 0.7804, "step": 87490 }, { "epoch": 7.27, "learning_rate": 3.0315217692542194e-06, "loss": 0.8057, "step": 87500 }, { "epoch": 7.27, "learning_rate": 3.0314109137266856e-06, "loss": 0.802, "step": 87510 }, { "epoch": 7.27, "learning_rate": 3.031300058199152e-06, "loss": 0.8083, "step": 87520 }, { "epoch": 7.28, "learning_rate": 3.031189202671618e-06, "loss": 0.8725, "step": 87530 }, { "epoch": 7.28, "learning_rate": 3.0310783471440845e-06, "loss": 0.7856, "step": 87540 }, { "epoch": 7.28, "learning_rate": 3.0309674916165504e-06, "loss": 0.8616, "step": 87550 }, { "epoch": 7.28, "learning_rate": 3.0308566360890167e-06, "loss": 0.8821, "step": 87560 }, { "epoch": 7.28, "learning_rate": 3.030745780561483e-06, "loss": 0.8542, "step": 87570 }, { "epoch": 7.28, "learning_rate": 3.030646010586703e-06, "loss": 0.8518, "step": 87580 }, { "epoch": 7.28, "learning_rate": 3.030535155059169e-06, "loss": 0.8599, "step": 87590 }, { "epoch": 7.28, "learning_rate": 3.0304242995316355e-06, "loss": 0.7666, "step": 87600 }, { "epoch": 7.28, "learning_rate": 3.0303134440041014e-06, "loss": 0.8668, "step": 87610 }, { "epoch": 7.28, "learning_rate": 3.0302025884765677e-06, "loss": 0.797, "step": 87620 }, { "epoch": 7.28, "learning_rate": 3.030091732949034e-06, "loss": 0.8067, "step": 87630 }, { "epoch": 7.28, "learning_rate": 3.0299808774215003e-06, "loss": 0.8043, "step": 87640 }, { "epoch": 7.29, "learning_rate": 3.029870021893966e-06, "loss": 0.8171, "step": 87650 }, { "epoch": 7.29, "learning_rate": 3.029759166366433e-06, "loss": 0.7853, "step": 87660 }, { "epoch": 7.29, "learning_rate": 3.029648310838899e-06, "loss": 0.8445, "step": 87670 }, { "epoch": 7.29, "learning_rate": 3.0295374553113655e-06, "loss": 0.8761, "step": 87680 }, { "epoch": 7.29, "learning_rate": 3.0294265997838318e-06, "loss": 0.7894, "step": 87690 }, { "epoch": 7.29, "learning_rate": 3.0293157442562977e-06, "loss": 0.7897, "step": 87700 }, { "epoch": 7.29, "learning_rate": 3.0292048887287644e-06, "loss": 0.8087, "step": 87710 }, { "epoch": 7.29, "learning_rate": 3.0290940332012302e-06, "loss": 0.8605, "step": 87720 }, { "epoch": 7.29, "learning_rate": 3.0289831776736965e-06, "loss": 0.8005, "step": 87730 }, { "epoch": 7.29, "learning_rate": 3.028872322146163e-06, "loss": 0.7665, "step": 87740 }, { "epoch": 7.29, "learning_rate": 3.028761466618629e-06, "loss": 0.7729, "step": 87750 }, { "epoch": 7.29, "learning_rate": 3.028650611091095e-06, "loss": 0.7747, "step": 87760 }, { "epoch": 7.3, "learning_rate": 3.0285397555635617e-06, "loss": 0.8115, "step": 87770 }, { "epoch": 7.3, "learning_rate": 3.0284289000360276e-06, "loss": 0.791, "step": 87780 }, { "epoch": 7.3, "learning_rate": 3.0283180445084943e-06, "loss": 0.8162, "step": 87790 }, { "epoch": 7.3, "learning_rate": 3.0282071889809606e-06, "loss": 0.789, "step": 87800 }, { "epoch": 7.3, "learning_rate": 3.0280963334534265e-06, "loss": 0.8899, "step": 87810 }, { "epoch": 7.3, "learning_rate": 3.027985477925893e-06, "loss": 0.8208, "step": 87820 }, { "epoch": 7.3, "learning_rate": 3.027874622398359e-06, "loss": 0.8635, "step": 87830 }, { "epoch": 7.3, "learning_rate": 3.0277637668708254e-06, "loss": 0.7539, "step": 87840 }, { "epoch": 7.3, "learning_rate": 3.0276529113432917e-06, "loss": 0.7887, "step": 87850 }, { "epoch": 7.3, "learning_rate": 3.027542055815758e-06, "loss": 0.7514, "step": 87860 }, { "epoch": 7.3, "learning_rate": 3.0274312002882243e-06, "loss": 0.8518, "step": 87870 }, { "epoch": 7.3, "learning_rate": 3.0273203447606905e-06, "loss": 0.8823, "step": 87880 }, { "epoch": 7.31, "learning_rate": 3.0272094892331564e-06, "loss": 0.8026, "step": 87890 }, { "epoch": 7.31, "learning_rate": 3.027098633705623e-06, "loss": 0.8036, "step": 87900 }, { "epoch": 7.31, "learning_rate": 3.0269877781780894e-06, "loss": 0.7967, "step": 87910 }, { "epoch": 7.31, "learning_rate": 3.0268769226505553e-06, "loss": 0.8495, "step": 87920 }, { "epoch": 7.31, "learning_rate": 3.026766067123022e-06, "loss": 0.8412, "step": 87930 }, { "epoch": 7.31, "learning_rate": 3.026655211595488e-06, "loss": 0.7815, "step": 87940 }, { "epoch": 7.31, "learning_rate": 3.0265443560679546e-06, "loss": 0.8035, "step": 87950 }, { "epoch": 7.31, "learning_rate": 3.0264335005404205e-06, "loss": 0.7959, "step": 87960 }, { "epoch": 7.31, "learning_rate": 3.0263226450128868e-06, "loss": 0.7975, "step": 87970 }, { "epoch": 7.31, "learning_rate": 3.026211789485353e-06, "loss": 0.8941, "step": 87980 }, { "epoch": 7.31, "learning_rate": 3.0261009339578194e-06, "loss": 0.8179, "step": 87990 }, { "epoch": 7.31, "learning_rate": 3.0259900784302852e-06, "loss": 0.8049, "step": 88000 }, { "epoch": 7.32, "learning_rate": 3.025879222902752e-06, "loss": 0.7353, "step": 88010 }, { "epoch": 7.32, "learning_rate": 3.025768367375218e-06, "loss": 0.7887, "step": 88020 }, { "epoch": 7.32, "learning_rate": 3.0256575118476846e-06, "loss": 0.8198, "step": 88030 }, { "epoch": 7.32, "learning_rate": 3.025546656320151e-06, "loss": 0.811, "step": 88040 }, { "epoch": 7.32, "learning_rate": 3.0254358007926167e-06, "loss": 0.823, "step": 88050 }, { "epoch": 7.32, "learning_rate": 3.0253249452650834e-06, "loss": 0.8532, "step": 88060 }, { "epoch": 7.32, "learning_rate": 3.0252140897375493e-06, "loss": 0.8499, "step": 88070 }, { "epoch": 7.32, "learning_rate": 3.0251032342100156e-06, "loss": 0.8469, "step": 88080 }, { "epoch": 7.32, "learning_rate": 3.024992378682482e-06, "loss": 0.7799, "step": 88090 }, { "epoch": 7.32, "learning_rate": 3.024881523154948e-06, "loss": 0.8249, "step": 88100 }, { "epoch": 7.32, "learning_rate": 3.0247706676274145e-06, "loss": 0.7499, "step": 88110 }, { "epoch": 7.32, "learning_rate": 3.024659812099881e-06, "loss": 0.8214, "step": 88120 }, { "epoch": 7.33, "learning_rate": 3.0245489565723467e-06, "loss": 0.7709, "step": 88130 }, { "epoch": 7.33, "learning_rate": 3.0244381010448134e-06, "loss": 0.7772, "step": 88140 }, { "epoch": 7.33, "learning_rate": 3.0243272455172793e-06, "loss": 0.8163, "step": 88150 }, { "epoch": 7.33, "learning_rate": 3.0242163899897455e-06, "loss": 0.8635, "step": 88160 }, { "epoch": 7.33, "learning_rate": 3.0241055344622123e-06, "loss": 0.7991, "step": 88170 }, { "epoch": 7.33, "learning_rate": 3.023994678934678e-06, "loss": 0.8262, "step": 88180 }, { "epoch": 7.33, "learning_rate": 3.023883823407145e-06, "loss": 0.8489, "step": 88190 }, { "epoch": 7.33, "learning_rate": 3.0237729678796107e-06, "loss": 0.833, "step": 88200 }, { "epoch": 7.33, "learning_rate": 3.023662112352077e-06, "loss": 0.8316, "step": 88210 }, { "epoch": 7.33, "learning_rate": 3.0235512568245433e-06, "loss": 0.8194, "step": 88220 }, { "epoch": 7.33, "learning_rate": 3.0234404012970096e-06, "loss": 0.8269, "step": 88230 }, { "epoch": 7.33, "learning_rate": 3.0233295457694755e-06, "loss": 0.8005, "step": 88240 }, { "epoch": 7.34, "learning_rate": 3.023218690241942e-06, "loss": 0.7191, "step": 88250 }, { "epoch": 7.34, "learning_rate": 3.023107834714408e-06, "loss": 0.8035, "step": 88260 }, { "epoch": 7.34, "learning_rate": 3.0229969791868744e-06, "loss": 0.8096, "step": 88270 }, { "epoch": 7.34, "learning_rate": 3.022886123659341e-06, "loss": 0.8664, "step": 88280 }, { "epoch": 7.34, "learning_rate": 3.022775268131807e-06, "loss": 0.7789, "step": 88290 }, { "epoch": 7.34, "learning_rate": 3.0226644126042737e-06, "loss": 0.8272, "step": 88300 }, { "epoch": 7.34, "learning_rate": 3.0225535570767396e-06, "loss": 0.7926, "step": 88310 }, { "epoch": 7.34, "learning_rate": 3.022442701549206e-06, "loss": 0.8244, "step": 88320 }, { "epoch": 7.34, "learning_rate": 3.022331846021672e-06, "loss": 0.8328, "step": 88330 }, { "epoch": 7.34, "learning_rate": 3.0222209904941384e-06, "loss": 0.8307, "step": 88340 }, { "epoch": 7.34, "learning_rate": 3.0221101349666043e-06, "loss": 0.7867, "step": 88350 }, { "epoch": 7.34, "learning_rate": 3.021999279439071e-06, "loss": 0.7905, "step": 88360 }, { "epoch": 7.35, "learning_rate": 3.021888423911537e-06, "loss": 0.8533, "step": 88370 }, { "epoch": 7.35, "learning_rate": 3.0217775683840036e-06, "loss": 0.8276, "step": 88380 }, { "epoch": 7.35, "learning_rate": 3.0216667128564695e-06, "loss": 0.8236, "step": 88390 }, { "epoch": 7.35, "learning_rate": 3.0215558573289358e-06, "loss": 0.7544, "step": 88400 }, { "epoch": 7.35, "learning_rate": 3.0214450018014025e-06, "loss": 0.7621, "step": 88410 }, { "epoch": 7.35, "learning_rate": 3.0213341462738684e-06, "loss": 0.833, "step": 88420 }, { "epoch": 7.35, "learning_rate": 3.0212232907463347e-06, "loss": 0.9089, "step": 88430 }, { "epoch": 7.35, "learning_rate": 3.021112435218801e-06, "loss": 0.7572, "step": 88440 }, { "epoch": 7.35, "learning_rate": 3.0210015796912673e-06, "loss": 0.8072, "step": 88450 }, { "epoch": 7.35, "learning_rate": 3.0208907241637336e-06, "loss": 0.8631, "step": 88460 }, { "epoch": 7.35, "learning_rate": 3.0207798686362e-06, "loss": 0.7626, "step": 88470 }, { "epoch": 7.35, "learning_rate": 3.0206690131086657e-06, "loss": 0.8592, "step": 88480 }, { "epoch": 7.36, "learning_rate": 3.0205581575811324e-06, "loss": 0.8614, "step": 88490 }, { "epoch": 7.36, "learning_rate": 3.0204473020535983e-06, "loss": 0.8292, "step": 88500 }, { "epoch": 7.36, "learning_rate": 3.0203364465260646e-06, "loss": 0.8295, "step": 88510 }, { "epoch": 7.36, "learning_rate": 3.0202255909985313e-06, "loss": 0.8562, "step": 88520 }, { "epoch": 7.36, "learning_rate": 3.020114735470997e-06, "loss": 0.8014, "step": 88530 }, { "epoch": 7.36, "learning_rate": 3.020003879943464e-06, "loss": 0.8592, "step": 88540 }, { "epoch": 7.36, "learning_rate": 3.01989302441593e-06, "loss": 0.7314, "step": 88550 }, { "epoch": 7.36, "learning_rate": 3.019782168888396e-06, "loss": 0.8113, "step": 88560 }, { "epoch": 7.36, "learning_rate": 3.0196713133608624e-06, "loss": 0.8199, "step": 88570 }, { "epoch": 7.36, "learning_rate": 3.0195604578333287e-06, "loss": 0.913, "step": 88580 }, { "epoch": 7.36, "learning_rate": 3.0194496023057946e-06, "loss": 0.814, "step": 88590 }, { "epoch": 7.36, "learning_rate": 3.0193387467782613e-06, "loss": 0.913, "step": 88600 }, { "epoch": 7.37, "learning_rate": 3.019227891250727e-06, "loss": 0.7377, "step": 88610 }, { "epoch": 7.37, "learning_rate": 3.019117035723194e-06, "loss": 0.8027, "step": 88620 }, { "epoch": 7.37, "learning_rate": 3.0190061801956597e-06, "loss": 0.9042, "step": 88630 }, { "epoch": 7.37, "learning_rate": 3.018895324668126e-06, "loss": 0.7939, "step": 88640 }, { "epoch": 7.37, "learning_rate": 3.0187844691405927e-06, "loss": 0.8067, "step": 88650 }, { "epoch": 7.37, "learning_rate": 3.0186736136130586e-06, "loss": 0.8407, "step": 88660 }, { "epoch": 7.37, "learning_rate": 3.018562758085525e-06, "loss": 0.8527, "step": 88670 }, { "epoch": 7.37, "learning_rate": 3.018451902557991e-06, "loss": 0.8248, "step": 88680 }, { "epoch": 7.37, "learning_rate": 3.0183410470304575e-06, "loss": 0.7737, "step": 88690 }, { "epoch": 7.37, "learning_rate": 3.0182301915029234e-06, "loss": 0.8105, "step": 88700 }, { "epoch": 7.37, "learning_rate": 3.01811933597539e-06, "loss": 0.7997, "step": 88710 }, { "epoch": 7.37, "learning_rate": 3.018008480447856e-06, "loss": 0.8327, "step": 88720 }, { "epoch": 7.38, "learning_rate": 3.0178976249203227e-06, "loss": 0.8281, "step": 88730 }, { "epoch": 7.38, "learning_rate": 3.0177867693927886e-06, "loss": 0.7758, "step": 88740 }, { "epoch": 7.38, "learning_rate": 3.017675913865255e-06, "loss": 0.7981, "step": 88750 }, { "epoch": 7.38, "learning_rate": 3.017565058337721e-06, "loss": 0.8809, "step": 88760 }, { "epoch": 7.38, "learning_rate": 3.0174542028101874e-06, "loss": 0.8218, "step": 88770 }, { "epoch": 7.38, "learning_rate": 3.0173433472826537e-06, "loss": 0.8908, "step": 88780 }, { "epoch": 7.38, "learning_rate": 3.01723249175512e-06, "loss": 0.7739, "step": 88790 }, { "epoch": 7.38, "learning_rate": 3.0171216362275863e-06, "loss": 0.788, "step": 88800 }, { "epoch": 7.38, "learning_rate": 3.0170107807000526e-06, "loss": 0.8373, "step": 88810 }, { "epoch": 7.38, "learning_rate": 3.016899925172519e-06, "loss": 0.8212, "step": 88820 }, { "epoch": 7.38, "learning_rate": 3.016789069644985e-06, "loss": 0.8486, "step": 88830 }, { "epoch": 7.38, "learning_rate": 3.0166782141174515e-06, "loss": 0.826, "step": 88840 }, { "epoch": 7.39, "learning_rate": 3.0165673585899174e-06, "loss": 0.7771, "step": 88850 }, { "epoch": 7.39, "learning_rate": 3.0164565030623837e-06, "loss": 0.7789, "step": 88860 }, { "epoch": 7.39, "learning_rate": 3.01634564753485e-06, "loss": 0.8701, "step": 88870 }, { "epoch": 7.39, "learning_rate": 3.0162347920073163e-06, "loss": 0.8473, "step": 88880 }, { "epoch": 7.39, "learning_rate": 3.016123936479783e-06, "loss": 0.8271, "step": 88890 }, { "epoch": 7.39, "learning_rate": 3.016013080952249e-06, "loss": 0.832, "step": 88900 }, { "epoch": 7.39, "learning_rate": 3.015902225424715e-06, "loss": 0.8136, "step": 88910 }, { "epoch": 7.39, "learning_rate": 3.0157913698971815e-06, "loss": 0.7629, "step": 88920 }, { "epoch": 7.39, "learning_rate": 3.0156805143696477e-06, "loss": 0.8935, "step": 88930 }, { "epoch": 7.39, "learning_rate": 3.0155696588421136e-06, "loss": 0.8152, "step": 88940 }, { "epoch": 7.39, "learning_rate": 3.0154588033145803e-06, "loss": 0.7911, "step": 88950 }, { "epoch": 7.39, "learning_rate": 3.015347947787046e-06, "loss": 0.8129, "step": 88960 }, { "epoch": 7.4, "learning_rate": 3.015237092259513e-06, "loss": 0.8211, "step": 88970 }, { "epoch": 7.4, "learning_rate": 3.015126236731979e-06, "loss": 0.8904, "step": 88980 }, { "epoch": 7.4, "learning_rate": 3.015015381204445e-06, "loss": 0.7916, "step": 88990 }, { "epoch": 7.4, "learning_rate": 3.0149045256769114e-06, "loss": 0.8144, "step": 89000 }, { "epoch": 7.4, "learning_rate": 3.0147936701493777e-06, "loss": 0.8817, "step": 89010 }, { "epoch": 7.4, "learning_rate": 3.014682814621844e-06, "loss": 0.8474, "step": 89020 }, { "epoch": 7.4, "learning_rate": 3.0145719590943103e-06, "loss": 0.7952, "step": 89030 }, { "epoch": 7.4, "learning_rate": 3.0144611035667766e-06, "loss": 0.7883, "step": 89040 }, { "epoch": 7.4, "learning_rate": 3.0143502480392424e-06, "loss": 0.7823, "step": 89050 }, { "epoch": 7.4, "learning_rate": 3.014239392511709e-06, "loss": 0.7493, "step": 89060 }, { "epoch": 7.4, "learning_rate": 3.014128536984175e-06, "loss": 0.8004, "step": 89070 }, { "epoch": 7.4, "learning_rate": 3.0140176814566418e-06, "loss": 0.8469, "step": 89080 }, { "epoch": 7.41, "learning_rate": 3.0139068259291076e-06, "loss": 0.8332, "step": 89090 }, { "epoch": 7.41, "learning_rate": 3.013795970401574e-06, "loss": 0.8023, "step": 89100 }, { "epoch": 7.41, "learning_rate": 3.0136851148740402e-06, "loss": 0.8326, "step": 89110 }, { "epoch": 7.41, "learning_rate": 3.0135742593465065e-06, "loss": 0.8039, "step": 89120 }, { "epoch": 7.41, "learning_rate": 3.0134634038189724e-06, "loss": 0.7691, "step": 89130 }, { "epoch": 7.41, "learning_rate": 3.013352548291439e-06, "loss": 0.8233, "step": 89140 }, { "epoch": 7.41, "learning_rate": 3.0132416927639054e-06, "loss": 0.7966, "step": 89150 }, { "epoch": 7.41, "learning_rate": 3.0131308372363717e-06, "loss": 0.7991, "step": 89160 }, { "epoch": 7.41, "learning_rate": 3.013019981708838e-06, "loss": 0.8326, "step": 89170 }, { "epoch": 7.41, "learning_rate": 3.012909126181304e-06, "loss": 0.8333, "step": 89180 }, { "epoch": 7.41, "learning_rate": 3.0127982706537706e-06, "loss": 0.7467, "step": 89190 }, { "epoch": 7.41, "learning_rate": 3.0126874151262364e-06, "loss": 0.8532, "step": 89200 }, { "epoch": 7.42, "learning_rate": 3.0125765595987027e-06, "loss": 0.8245, "step": 89210 }, { "epoch": 7.42, "learning_rate": 3.012465704071169e-06, "loss": 0.8183, "step": 89220 }, { "epoch": 7.42, "learning_rate": 3.0123548485436353e-06, "loss": 0.8071, "step": 89230 }, { "epoch": 7.42, "learning_rate": 3.0122439930161016e-06, "loss": 0.7782, "step": 89240 }, { "epoch": 7.42, "learning_rate": 3.012133137488568e-06, "loss": 0.8202, "step": 89250 }, { "epoch": 7.42, "learning_rate": 3.0120222819610342e-06, "loss": 0.8068, "step": 89260 }, { "epoch": 7.42, "learning_rate": 3.0119114264335005e-06, "loss": 0.8046, "step": 89270 }, { "epoch": 7.42, "learning_rate": 3.011800570905967e-06, "loss": 0.8215, "step": 89280 }, { "epoch": 7.42, "learning_rate": 3.0116897153784327e-06, "loss": 0.7626, "step": 89290 }, { "epoch": 7.42, "learning_rate": 3.0115788598508994e-06, "loss": 0.8028, "step": 89300 }, { "epoch": 7.42, "learning_rate": 3.0114680043233653e-06, "loss": 0.8009, "step": 89310 }, { "epoch": 7.42, "learning_rate": 3.011357148795832e-06, "loss": 0.7836, "step": 89320 }, { "epoch": 7.42, "learning_rate": 3.011246293268298e-06, "loss": 0.8302, "step": 89330 }, { "epoch": 7.43, "learning_rate": 3.011135437740764e-06, "loss": 0.8036, "step": 89340 }, { "epoch": 7.43, "learning_rate": 3.0110245822132305e-06, "loss": 0.8549, "step": 89350 }, { "epoch": 7.43, "learning_rate": 3.0109137266856968e-06, "loss": 0.8202, "step": 89360 }, { "epoch": 7.43, "learning_rate": 3.0108028711581626e-06, "loss": 0.8571, "step": 89370 }, { "epoch": 7.43, "learning_rate": 3.0106920156306293e-06, "loss": 0.8802, "step": 89380 }, { "epoch": 7.43, "learning_rate": 3.0105811601030956e-06, "loss": 0.7698, "step": 89390 }, { "epoch": 7.43, "learning_rate": 3.010470304575562e-06, "loss": 0.7452, "step": 89400 }, { "epoch": 7.43, "learning_rate": 3.0103594490480282e-06, "loss": 0.7464, "step": 89410 }, { "epoch": 7.43, "learning_rate": 3.010248593520494e-06, "loss": 0.8511, "step": 89420 }, { "epoch": 7.43, "learning_rate": 3.010137737992961e-06, "loss": 0.7728, "step": 89430 }, { "epoch": 7.43, "learning_rate": 3.0100268824654267e-06, "loss": 0.9277, "step": 89440 }, { "epoch": 7.43, "learning_rate": 3.009916026937893e-06, "loss": 0.8022, "step": 89450 }, { "epoch": 7.44, "learning_rate": 3.0098051714103593e-06, "loss": 0.8069, "step": 89460 }, { "epoch": 7.44, "learning_rate": 3.0096943158828256e-06, "loss": 0.8808, "step": 89470 }, { "epoch": 7.44, "learning_rate": 3.0095834603552914e-06, "loss": 0.8819, "step": 89480 }, { "epoch": 7.44, "learning_rate": 3.009472604827758e-06, "loss": 0.8267, "step": 89490 }, { "epoch": 7.44, "learning_rate": 3.009361749300224e-06, "loss": 0.8284, "step": 89500 }, { "epoch": 7.44, "learning_rate": 3.0092508937726908e-06, "loss": 0.7796, "step": 89510 }, { "epoch": 7.44, "learning_rate": 3.009140038245157e-06, "loss": 0.8221, "step": 89520 }, { "epoch": 7.44, "learning_rate": 3.009029182717623e-06, "loss": 0.8546, "step": 89530 }, { "epoch": 7.44, "learning_rate": 3.0089183271900896e-06, "loss": 0.8267, "step": 89540 }, { "epoch": 7.44, "learning_rate": 3.0088074716625555e-06, "loss": 0.7559, "step": 89550 }, { "epoch": 7.44, "learning_rate": 3.008696616135022e-06, "loss": 0.8057, "step": 89560 }, { "epoch": 7.44, "learning_rate": 3.008585760607488e-06, "loss": 0.8205, "step": 89570 }, { "epoch": 7.45, "learning_rate": 3.0084749050799544e-06, "loss": 0.9204, "step": 89580 }, { "epoch": 7.45, "learning_rate": 3.0083640495524207e-06, "loss": 0.861, "step": 89590 }, { "epoch": 7.45, "learning_rate": 3.008253194024887e-06, "loss": 0.8002, "step": 89600 }, { "epoch": 7.45, "learning_rate": 3.008142338497353e-06, "loss": 0.7408, "step": 89610 }, { "epoch": 7.45, "learning_rate": 3.0080314829698196e-06, "loss": 0.8566, "step": 89620 }, { "epoch": 7.45, "learning_rate": 3.007920627442286e-06, "loss": 0.9, "step": 89630 }, { "epoch": 7.45, "learning_rate": 3.0078097719147518e-06, "loss": 0.8253, "step": 89640 }, { "epoch": 7.45, "learning_rate": 3.0076989163872185e-06, "loss": 0.7911, "step": 89650 }, { "epoch": 7.45, "learning_rate": 3.0075880608596843e-06, "loss": 0.78, "step": 89660 }, { "epoch": 7.45, "learning_rate": 3.007477205332151e-06, "loss": 0.802, "step": 89670 }, { "epoch": 7.45, "learning_rate": 3.007366349804617e-06, "loss": 0.8887, "step": 89680 }, { "epoch": 7.45, "learning_rate": 3.0072554942770832e-06, "loss": 0.8412, "step": 89690 }, { "epoch": 7.46, "learning_rate": 3.0071446387495495e-06, "loss": 0.823, "step": 89700 }, { "epoch": 7.46, "learning_rate": 3.007033783222016e-06, "loss": 0.784, "step": 89710 }, { "epoch": 7.46, "learning_rate": 3.0069229276944817e-06, "loss": 0.9085, "step": 89720 }, { "epoch": 7.46, "learning_rate": 3.0068120721669484e-06, "loss": 0.8319, "step": 89730 }, { "epoch": 7.46, "learning_rate": 3.0067012166394143e-06, "loss": 0.8167, "step": 89740 }, { "epoch": 7.46, "learning_rate": 3.006590361111881e-06, "loss": 0.7694, "step": 89750 }, { "epoch": 7.46, "learning_rate": 3.0064795055843473e-06, "loss": 0.7896, "step": 89760 }, { "epoch": 7.46, "learning_rate": 3.006368650056813e-06, "loss": 0.8232, "step": 89770 }, { "epoch": 7.46, "learning_rate": 3.00625779452928e-06, "loss": 0.8659, "step": 89780 }, { "epoch": 7.46, "learning_rate": 3.0061469390017458e-06, "loss": 0.8549, "step": 89790 }, { "epoch": 7.46, "learning_rate": 3.006036083474212e-06, "loss": 0.7687, "step": 89800 }, { "epoch": 7.46, "learning_rate": 3.0059252279466783e-06, "loss": 0.7929, "step": 89810 }, { "epoch": 7.47, "learning_rate": 3.0058143724191446e-06, "loss": 0.8184, "step": 89820 }, { "epoch": 7.47, "learning_rate": 3.0057035168916105e-06, "loss": 0.8905, "step": 89830 }, { "epoch": 7.47, "learning_rate": 3.0055926613640772e-06, "loss": 0.8081, "step": 89840 }, { "epoch": 7.47, "learning_rate": 3.005481805836543e-06, "loss": 0.7975, "step": 89850 }, { "epoch": 7.47, "learning_rate": 3.00537095030901e-06, "loss": 0.815, "step": 89860 }, { "epoch": 7.47, "learning_rate": 3.0052600947814757e-06, "loss": 0.8329, "step": 89870 }, { "epoch": 7.47, "learning_rate": 3.005149239253942e-06, "loss": 0.7519, "step": 89880 }, { "epoch": 7.47, "learning_rate": 3.0050383837264087e-06, "loss": 0.7845, "step": 89890 }, { "epoch": 7.47, "learning_rate": 3.0049275281988746e-06, "loss": 0.8244, "step": 89900 }, { "epoch": 7.47, "learning_rate": 3.0048166726713413e-06, "loss": 0.7638, "step": 89910 }, { "epoch": 7.47, "learning_rate": 3.004705817143807e-06, "loss": 0.8647, "step": 89920 }, { "epoch": 7.47, "learning_rate": 3.0045949616162735e-06, "loss": 0.8389, "step": 89930 }, { "epoch": 7.48, "learning_rate": 3.0044841060887398e-06, "loss": 0.8317, "step": 89940 }, { "epoch": 7.48, "learning_rate": 3.004373250561206e-06, "loss": 0.8087, "step": 89950 }, { "epoch": 7.48, "learning_rate": 3.004262395033672e-06, "loss": 0.7895, "step": 89960 }, { "epoch": 7.48, "learning_rate": 3.0041515395061386e-06, "loss": 0.8169, "step": 89970 }, { "epoch": 7.48, "learning_rate": 3.0040406839786045e-06, "loss": 0.8765, "step": 89980 }, { "epoch": 7.48, "learning_rate": 3.003929828451071e-06, "loss": 0.8149, "step": 89990 }, { "epoch": 7.48, "learning_rate": 3.0038189729235375e-06, "loss": 0.762, "step": 90000 }, { "epoch": 7.48, "learning_rate": 3.0037081173960034e-06, "loss": 0.7781, "step": 90010 }, { "epoch": 7.48, "learning_rate": 3.00359726186847e-06, "loss": 0.8139, "step": 90020 }, { "epoch": 7.48, "learning_rate": 3.003486406340936e-06, "loss": 0.8616, "step": 90030 }, { "epoch": 7.48, "learning_rate": 3.0033755508134023e-06, "loss": 0.8054, "step": 90040 }, { "epoch": 7.48, "learning_rate": 3.0032646952858686e-06, "loss": 0.7886, "step": 90050 }, { "epoch": 7.49, "learning_rate": 3.003153839758335e-06, "loss": 0.8235, "step": 90060 }, { "epoch": 7.49, "learning_rate": 3.0030429842308008e-06, "loss": 0.8169, "step": 90070 }, { "epoch": 7.49, "learning_rate": 3.0029321287032675e-06, "loss": 0.7862, "step": 90080 }, { "epoch": 7.49, "learning_rate": 3.0028212731757333e-06, "loss": 0.8504, "step": 90090 }, { "epoch": 7.49, "learning_rate": 3.0027104176482e-06, "loss": 0.7754, "step": 90100 }, { "epoch": 7.49, "learning_rate": 3.002599562120666e-06, "loss": 0.8219, "step": 90110 }, { "epoch": 7.49, "learning_rate": 3.0024887065931322e-06, "loss": 0.8089, "step": 90120 }, { "epoch": 7.49, "learning_rate": 3.002377851065599e-06, "loss": 0.9067, "step": 90130 }, { "epoch": 7.49, "learning_rate": 3.002266995538065e-06, "loss": 0.8336, "step": 90140 }, { "epoch": 7.49, "learning_rate": 3.002156140010531e-06, "loss": 0.8098, "step": 90150 }, { "epoch": 7.49, "learning_rate": 3.0020452844829974e-06, "loss": 0.8606, "step": 90160 }, { "epoch": 7.49, "learning_rate": 3.0019344289554637e-06, "loss": 0.8104, "step": 90170 }, { "epoch": 7.5, "learning_rate": 3.00182357342793e-06, "loss": 0.8547, "step": 90180 }, { "epoch": 7.5, "learning_rate": 3.0017127179003963e-06, "loss": 0.7817, "step": 90190 }, { "epoch": 7.5, "learning_rate": 3.001612947925616e-06, "loss": 0.7842, "step": 90200 }, { "epoch": 7.5, "learning_rate": 3.001502092398082e-06, "loss": 0.7731, "step": 90210 }, { "epoch": 7.5, "learning_rate": 3.0013912368705484e-06, "loss": 0.8564, "step": 90220 }, { "epoch": 7.5, "learning_rate": 3.0012803813430147e-06, "loss": 0.8705, "step": 90230 }, { "epoch": 7.5, "learning_rate": 3.0011695258154806e-06, "loss": 0.8225, "step": 90240 }, { "epoch": 7.5, "learning_rate": 3.0010586702879473e-06, "loss": 0.8219, "step": 90250 }, { "epoch": 7.5, "learning_rate": 3.000947814760413e-06, "loss": 0.8491, "step": 90260 }, { "epoch": 7.5, "learning_rate": 3.00083695923288e-06, "loss": 0.8093, "step": 90270 }, { "epoch": 7.5, "learning_rate": 3.0007261037053458e-06, "loss": 0.8837, "step": 90280 }, { "epoch": 7.5, "learning_rate": 3.000615248177812e-06, "loss": 0.7911, "step": 90290 }, { "epoch": 7.51, "learning_rate": 3.0005043926502784e-06, "loss": 0.8451, "step": 90300 }, { "epoch": 7.51, "learning_rate": 3.0003935371227447e-06, "loss": 0.813, "step": 90310 }, { "epoch": 7.51, "learning_rate": 3.0002826815952105e-06, "loss": 0.8486, "step": 90320 }, { "epoch": 7.51, "learning_rate": 3.0001718260676773e-06, "loss": 0.8404, "step": 90330 }, { "epoch": 7.51, "learning_rate": 3.0000609705401436e-06, "loss": 0.756, "step": 90340 }, { "epoch": 7.51, "learning_rate": 2.99995011501261e-06, "loss": 0.7866, "step": 90350 }, { "epoch": 7.51, "learning_rate": 2.999839259485076e-06, "loss": 0.7954, "step": 90360 }, { "epoch": 7.51, "learning_rate": 2.999728403957542e-06, "loss": 0.8521, "step": 90370 }, { "epoch": 7.51, "learning_rate": 2.9996175484300087e-06, "loss": 0.8663, "step": 90380 }, { "epoch": 7.51, "learning_rate": 2.9995066929024746e-06, "loss": 0.8432, "step": 90390 }, { "epoch": 7.51, "learning_rate": 2.999395837374941e-06, "loss": 0.8646, "step": 90400 }, { "epoch": 7.51, "learning_rate": 2.999284981847407e-06, "loss": 0.8536, "step": 90410 }, { "epoch": 7.52, "learning_rate": 2.9991741263198735e-06, "loss": 0.8464, "step": 90420 }, { "epoch": 7.52, "learning_rate": 2.9990632707923394e-06, "loss": 0.7823, "step": 90430 }, { "epoch": 7.52, "learning_rate": 2.998952415264806e-06, "loss": 0.7679, "step": 90440 }, { "epoch": 7.52, "learning_rate": 2.9988415597372724e-06, "loss": 0.8215, "step": 90450 }, { "epoch": 7.52, "learning_rate": 2.9987307042097387e-06, "loss": 0.755, "step": 90460 }, { "epoch": 7.52, "learning_rate": 2.998619848682205e-06, "loss": 0.8208, "step": 90470 }, { "epoch": 7.52, "learning_rate": 2.998508993154671e-06, "loss": 0.8005, "step": 90480 }, { "epoch": 7.52, "learning_rate": 2.9983981376271376e-06, "loss": 0.7386, "step": 90490 }, { "epoch": 7.52, "learning_rate": 2.9982872820996034e-06, "loss": 0.7855, "step": 90500 }, { "epoch": 7.52, "learning_rate": 2.9981764265720697e-06, "loss": 0.843, "step": 90510 }, { "epoch": 7.52, "learning_rate": 2.998065571044536e-06, "loss": 0.8492, "step": 90520 }, { "epoch": 7.52, "learning_rate": 2.9979547155170023e-06, "loss": 0.8281, "step": 90530 }, { "epoch": 7.53, "learning_rate": 2.9978438599894686e-06, "loss": 0.8043, "step": 90540 }, { "epoch": 7.53, "learning_rate": 2.997733004461935e-06, "loss": 0.8473, "step": 90550 }, { "epoch": 7.53, "learning_rate": 2.9976221489344008e-06, "loss": 0.7952, "step": 90560 }, { "epoch": 7.53, "learning_rate": 2.9975112934068675e-06, "loss": 0.8521, "step": 90570 }, { "epoch": 7.53, "learning_rate": 2.997400437879334e-06, "loss": 0.8351, "step": 90580 }, { "epoch": 7.53, "learning_rate": 2.9972895823517997e-06, "loss": 0.7861, "step": 90590 }, { "epoch": 7.53, "learning_rate": 2.9971787268242664e-06, "loss": 0.8563, "step": 90600 }, { "epoch": 7.53, "learning_rate": 2.9970678712967323e-06, "loss": 0.8973, "step": 90610 }, { "epoch": 7.53, "learning_rate": 2.996957015769199e-06, "loss": 0.9121, "step": 90620 }, { "epoch": 7.53, "learning_rate": 2.996846160241665e-06, "loss": 0.8705, "step": 90630 }, { "epoch": 7.53, "learning_rate": 2.996735304714131e-06, "loss": 0.8454, "step": 90640 }, { "epoch": 7.53, "learning_rate": 2.9966244491865974e-06, "loss": 0.7659, "step": 90650 }, { "epoch": 7.54, "learning_rate": 2.9965135936590637e-06, "loss": 0.8128, "step": 90660 }, { "epoch": 7.54, "learning_rate": 2.9964027381315296e-06, "loss": 0.7996, "step": 90670 }, { "epoch": 7.54, "learning_rate": 2.9962918826039963e-06, "loss": 0.8484, "step": 90680 }, { "epoch": 7.54, "learning_rate": 2.996181027076462e-06, "loss": 0.7865, "step": 90690 }, { "epoch": 7.54, "learning_rate": 2.996070171548929e-06, "loss": 0.9034, "step": 90700 }, { "epoch": 7.54, "learning_rate": 2.995959316021395e-06, "loss": 0.8885, "step": 90710 }, { "epoch": 7.54, "learning_rate": 2.995848460493861e-06, "loss": 0.7884, "step": 90720 }, { "epoch": 7.54, "learning_rate": 2.995737604966328e-06, "loss": 0.8731, "step": 90730 }, { "epoch": 7.54, "learning_rate": 2.9956267494387937e-06, "loss": 0.7806, "step": 90740 }, { "epoch": 7.54, "learning_rate": 2.995526979464013e-06, "loss": 0.8159, "step": 90750 }, { "epoch": 7.54, "learning_rate": 2.9954161239364795e-06, "loss": 0.7801, "step": 90760 }, { "epoch": 7.54, "learning_rate": 2.995305268408946e-06, "loss": 0.8853, "step": 90770 }, { "epoch": 7.55, "learning_rate": 2.995194412881412e-06, "loss": 0.7995, "step": 90780 }, { "epoch": 7.55, "learning_rate": 2.995083557353879e-06, "loss": 0.7608, "step": 90790 }, { "epoch": 7.55, "learning_rate": 2.9949727018263447e-06, "loss": 0.7721, "step": 90800 }, { "epoch": 7.55, "learning_rate": 2.994861846298811e-06, "loss": 0.8894, "step": 90810 }, { "epoch": 7.55, "learning_rate": 2.9947509907712773e-06, "loss": 0.7854, "step": 90820 }, { "epoch": 7.55, "learning_rate": 2.9946401352437436e-06, "loss": 0.7859, "step": 90830 }, { "epoch": 7.55, "learning_rate": 2.9945292797162094e-06, "loss": 0.8575, "step": 90840 }, { "epoch": 7.55, "learning_rate": 2.994418424188676e-06, "loss": 0.9034, "step": 90850 }, { "epoch": 7.55, "learning_rate": 2.994307568661142e-06, "loss": 0.8247, "step": 90860 }, { "epoch": 7.55, "learning_rate": 2.9941967131336088e-06, "loss": 0.8183, "step": 90870 }, { "epoch": 7.55, "learning_rate": 2.9940858576060746e-06, "loss": 0.8384, "step": 90880 }, { "epoch": 7.55, "learning_rate": 2.993975002078541e-06, "loss": 0.8416, "step": 90890 }, { "epoch": 7.56, "learning_rate": 2.9938641465510072e-06, "loss": 0.8523, "step": 90900 }, { "epoch": 7.56, "learning_rate": 2.9937532910234735e-06, "loss": 0.829, "step": 90910 }, { "epoch": 7.56, "learning_rate": 2.99364243549594e-06, "loss": 0.7604, "step": 90920 }, { "epoch": 7.56, "learning_rate": 2.993531579968406e-06, "loss": 0.8291, "step": 90930 }, { "epoch": 7.56, "learning_rate": 2.9934207244408724e-06, "loss": 0.8394, "step": 90940 }, { "epoch": 7.56, "learning_rate": 2.9933098689133383e-06, "loss": 0.8492, "step": 90950 }, { "epoch": 7.56, "learning_rate": 2.993199013385805e-06, "loss": 0.8633, "step": 90960 }, { "epoch": 7.56, "learning_rate": 2.993088157858271e-06, "loss": 0.8379, "step": 90970 }, { "epoch": 7.56, "learning_rate": 2.9929773023307376e-06, "loss": 0.8722, "step": 90980 }, { "epoch": 7.56, "learning_rate": 2.9928664468032034e-06, "loss": 0.8003, "step": 90990 }, { "epoch": 7.56, "learning_rate": 2.9927555912756697e-06, "loss": 0.7508, "step": 91000 }, { "epoch": 7.56, "learning_rate": 2.992644735748136e-06, "loss": 0.8194, "step": 91010 }, { "epoch": 7.57, "learning_rate": 2.9925338802206023e-06, "loss": 0.8159, "step": 91020 }, { "epoch": 7.57, "learning_rate": 2.992423024693069e-06, "loss": 0.8149, "step": 91030 }, { "epoch": 7.57, "learning_rate": 2.992312169165535e-06, "loss": 0.7938, "step": 91040 }, { "epoch": 7.57, "learning_rate": 2.9922013136380012e-06, "loss": 0.7792, "step": 91050 }, { "epoch": 7.57, "learning_rate": 2.9920904581104675e-06, "loss": 0.849, "step": 91060 }, { "epoch": 7.57, "learning_rate": 2.991979602582934e-06, "loss": 0.8175, "step": 91070 }, { "epoch": 7.57, "learning_rate": 2.9918687470553997e-06, "loss": 0.8275, "step": 91080 }, { "epoch": 7.57, "learning_rate": 2.9917578915278664e-06, "loss": 0.8258, "step": 91090 }, { "epoch": 7.57, "learning_rate": 2.9916470360003323e-06, "loss": 0.7876, "step": 91100 }, { "epoch": 7.57, "learning_rate": 2.9915361804727986e-06, "loss": 0.852, "step": 91110 }, { "epoch": 7.57, "learning_rate": 2.991425324945265e-06, "loss": 0.8038, "step": 91120 }, { "epoch": 7.57, "learning_rate": 2.991314469417731e-06, "loss": 0.828, "step": 91130 }, { "epoch": 7.58, "learning_rate": 2.9912036138901975e-06, "loss": 0.783, "step": 91140 }, { "epoch": 7.58, "learning_rate": 2.9910927583626638e-06, "loss": 0.7664, "step": 91150 }, { "epoch": 7.58, "learning_rate": 2.99098190283513e-06, "loss": 0.7768, "step": 91160 }, { "epoch": 7.58, "learning_rate": 2.9908710473075963e-06, "loss": 0.7998, "step": 91170 }, { "epoch": 7.58, "learning_rate": 2.9907601917800626e-06, "loss": 0.8366, "step": 91180 }, { "epoch": 7.58, "learning_rate": 2.9906493362525285e-06, "loss": 0.7998, "step": 91190 }, { "epoch": 7.58, "learning_rate": 2.9905384807249952e-06, "loss": 0.7906, "step": 91200 }, { "epoch": 7.58, "learning_rate": 2.990427625197461e-06, "loss": 0.8448, "step": 91210 }, { "epoch": 7.58, "learning_rate": 2.990316769669928e-06, "loss": 0.8281, "step": 91220 }, { "epoch": 7.58, "learning_rate": 2.9902059141423937e-06, "loss": 0.8496, "step": 91230 }, { "epoch": 7.58, "learning_rate": 2.99009505861486e-06, "loss": 0.8344, "step": 91240 }, { "epoch": 7.58, "learning_rate": 2.9899842030873263e-06, "loss": 0.8436, "step": 91250 }, { "epoch": 7.59, "learning_rate": 2.9898733475597926e-06, "loss": 0.8206, "step": 91260 }, { "epoch": 7.59, "learning_rate": 2.9897624920322584e-06, "loss": 0.8632, "step": 91270 }, { "epoch": 7.59, "learning_rate": 2.989651636504725e-06, "loss": 0.7891, "step": 91280 }, { "epoch": 7.59, "learning_rate": 2.9895407809771915e-06, "loss": 0.8074, "step": 91290 }, { "epoch": 7.59, "learning_rate": 2.9894299254496578e-06, "loss": 0.7856, "step": 91300 }, { "epoch": 7.59, "learning_rate": 2.989319069922124e-06, "loss": 0.8316, "step": 91310 }, { "epoch": 7.59, "learning_rate": 2.98920821439459e-06, "loss": 0.8477, "step": 91320 }, { "epoch": 7.59, "learning_rate": 2.9890973588670566e-06, "loss": 0.8335, "step": 91330 }, { "epoch": 7.59, "learning_rate": 2.9889865033395225e-06, "loss": 0.7995, "step": 91340 }, { "epoch": 7.59, "learning_rate": 2.988875647811989e-06, "loss": 0.7353, "step": 91350 }, { "epoch": 7.59, "learning_rate": 2.988764792284455e-06, "loss": 0.8413, "step": 91360 }, { "epoch": 7.59, "learning_rate": 2.9886539367569214e-06, "loss": 0.8356, "step": 91370 }, { "epoch": 7.6, "learning_rate": 2.9885430812293873e-06, "loss": 0.8311, "step": 91380 }, { "epoch": 7.6, "learning_rate": 2.988432225701854e-06, "loss": 0.8521, "step": 91390 }, { "epoch": 7.6, "learning_rate": 2.9883213701743203e-06, "loss": 0.7408, "step": 91400 }, { "epoch": 7.6, "learning_rate": 2.9882105146467866e-06, "loss": 0.7921, "step": 91410 }, { "epoch": 7.6, "learning_rate": 2.988099659119253e-06, "loss": 0.8045, "step": 91420 }, { "epoch": 7.6, "learning_rate": 2.9879888035917188e-06, "loss": 0.8295, "step": 91430 }, { "epoch": 7.6, "learning_rate": 2.9878779480641855e-06, "loss": 0.8428, "step": 91440 }, { "epoch": 7.6, "learning_rate": 2.9877670925366513e-06, "loss": 0.7552, "step": 91450 }, { "epoch": 7.6, "learning_rate": 2.9876562370091176e-06, "loss": 0.7827, "step": 91460 }, { "epoch": 7.6, "learning_rate": 2.987545381481584e-06, "loss": 0.8509, "step": 91470 }, { "epoch": 7.6, "learning_rate": 2.9874345259540502e-06, "loss": 0.8335, "step": 91480 }, { "epoch": 7.6, "learning_rate": 2.9873236704265165e-06, "loss": 0.7779, "step": 91490 }, { "epoch": 7.61, "learning_rate": 2.987212814898983e-06, "loss": 0.8029, "step": 91500 }, { "epoch": 7.61, "learning_rate": 2.9871019593714487e-06, "loss": 0.8224, "step": 91510 }, { "epoch": 7.61, "learning_rate": 2.9869911038439154e-06, "loss": 0.862, "step": 91520 }, { "epoch": 7.61, "learning_rate": 2.9868802483163817e-06, "loss": 0.8019, "step": 91530 }, { "epoch": 7.61, "learning_rate": 2.9867693927888476e-06, "loss": 0.7932, "step": 91540 }, { "epoch": 7.61, "learning_rate": 2.9866585372613143e-06, "loss": 0.8082, "step": 91550 }, { "epoch": 7.61, "learning_rate": 2.98654768173378e-06, "loss": 0.8636, "step": 91560 }, { "epoch": 7.61, "learning_rate": 2.986436826206247e-06, "loss": 0.791, "step": 91570 }, { "epoch": 7.61, "learning_rate": 2.9863259706787128e-06, "loss": 0.8089, "step": 91580 }, { "epoch": 7.61, "learning_rate": 2.986215115151179e-06, "loss": 0.8382, "step": 91590 }, { "epoch": 7.61, "learning_rate": 2.9861042596236453e-06, "loss": 0.8126, "step": 91600 }, { "epoch": 7.61, "learning_rate": 2.9859934040961116e-06, "loss": 0.8739, "step": 91610 }, { "epoch": 7.62, "learning_rate": 2.9858825485685775e-06, "loss": 0.8075, "step": 91620 }, { "epoch": 7.62, "learning_rate": 2.9857716930410442e-06, "loss": 0.8352, "step": 91630 }, { "epoch": 7.62, "learning_rate": 2.98566083751351e-06, "loss": 0.79, "step": 91640 }, { "epoch": 7.62, "learning_rate": 2.985549981985977e-06, "loss": 0.8348, "step": 91650 }, { "epoch": 7.62, "learning_rate": 2.985439126458443e-06, "loss": 0.8357, "step": 91660 }, { "epoch": 7.62, "learning_rate": 2.985328270930909e-06, "loss": 0.8308, "step": 91670 }, { "epoch": 7.62, "learning_rate": 2.9852174154033757e-06, "loss": 0.8252, "step": 91680 }, { "epoch": 7.62, "learning_rate": 2.9851065598758416e-06, "loss": 0.8366, "step": 91690 }, { "epoch": 7.62, "learning_rate": 2.984995704348308e-06, "loss": 0.8067, "step": 91700 }, { "epoch": 7.62, "learning_rate": 2.984884848820774e-06, "loss": 0.8562, "step": 91710 }, { "epoch": 7.62, "learning_rate": 2.9847739932932405e-06, "loss": 0.8227, "step": 91720 }, { "epoch": 7.62, "learning_rate": 2.9846631377657063e-06, "loss": 0.8223, "step": 91730 }, { "epoch": 7.63, "learning_rate": 2.984552282238173e-06, "loss": 0.8237, "step": 91740 }, { "epoch": 7.63, "learning_rate": 2.984441426710639e-06, "loss": 0.8428, "step": 91750 }, { "epoch": 7.63, "learning_rate": 2.9843305711831056e-06, "loss": 0.8499, "step": 91760 }, { "epoch": 7.63, "learning_rate": 2.984219715655572e-06, "loss": 0.8423, "step": 91770 }, { "epoch": 7.63, "learning_rate": 2.984108860128038e-06, "loss": 0.8303, "step": 91780 }, { "epoch": 7.63, "learning_rate": 2.9839980046005045e-06, "loss": 0.7632, "step": 91790 }, { "epoch": 7.63, "learning_rate": 2.9838871490729704e-06, "loss": 0.8045, "step": 91800 }, { "epoch": 7.63, "learning_rate": 2.983776293545437e-06, "loss": 0.8132, "step": 91810 }, { "epoch": 7.63, "learning_rate": 2.983665438017903e-06, "loss": 0.8065, "step": 91820 }, { "epoch": 7.63, "learning_rate": 2.9835545824903693e-06, "loss": 0.8563, "step": 91830 }, { "epoch": 7.63, "learning_rate": 2.9834437269628356e-06, "loss": 0.7708, "step": 91840 }, { "epoch": 7.63, "learning_rate": 2.983332871435302e-06, "loss": 0.8103, "step": 91850 }, { "epoch": 7.64, "learning_rate": 2.9832220159077678e-06, "loss": 0.86, "step": 91860 }, { "epoch": 7.64, "learning_rate": 2.9831111603802345e-06, "loss": 0.781, "step": 91870 }, { "epoch": 7.64, "learning_rate": 2.9830003048527003e-06, "loss": 0.7969, "step": 91880 }, { "epoch": 7.64, "learning_rate": 2.9828894493251666e-06, "loss": 0.7938, "step": 91890 }, { "epoch": 7.64, "learning_rate": 2.9827785937976334e-06, "loss": 0.8111, "step": 91900 }, { "epoch": 7.64, "learning_rate": 2.9826677382700992e-06, "loss": 0.7883, "step": 91910 }, { "epoch": 7.64, "learning_rate": 2.982556882742566e-06, "loss": 0.8182, "step": 91920 }, { "epoch": 7.64, "learning_rate": 2.982446027215032e-06, "loss": 0.824, "step": 91930 }, { "epoch": 7.64, "learning_rate": 2.982335171687498e-06, "loss": 0.8001, "step": 91940 }, { "epoch": 7.64, "learning_rate": 2.9822243161599644e-06, "loss": 0.8458, "step": 91950 }, { "epoch": 7.64, "learning_rate": 2.9821134606324307e-06, "loss": 0.7937, "step": 91960 }, { "epoch": 7.64, "learning_rate": 2.9820026051048966e-06, "loss": 0.7931, "step": 91970 }, { "epoch": 7.65, "learning_rate": 2.9818917495773633e-06, "loss": 0.8824, "step": 91980 }, { "epoch": 7.65, "learning_rate": 2.981780894049829e-06, "loss": 0.7827, "step": 91990 }, { "epoch": 7.65, "learning_rate": 2.981670038522296e-06, "loss": 0.8016, "step": 92000 }, { "epoch": 7.65, "learning_rate": 2.9815591829947618e-06, "loss": 0.86, "step": 92010 }, { "epoch": 7.65, "learning_rate": 2.981448327467228e-06, "loss": 0.8118, "step": 92020 }, { "epoch": 7.65, "learning_rate": 2.9813374719396948e-06, "loss": 0.8134, "step": 92030 }, { "epoch": 7.65, "learning_rate": 2.9812266164121606e-06, "loss": 0.8383, "step": 92040 }, { "epoch": 7.65, "learning_rate": 2.981115760884627e-06, "loss": 0.7762, "step": 92050 }, { "epoch": 7.65, "learning_rate": 2.9810049053570932e-06, "loss": 0.8166, "step": 92060 }, { "epoch": 7.65, "learning_rate": 2.9808940498295595e-06, "loss": 0.7287, "step": 92070 }, { "epoch": 7.65, "learning_rate": 2.980783194302026e-06, "loss": 0.7413, "step": 92080 }, { "epoch": 7.65, "learning_rate": 2.980672338774492e-06, "loss": 0.8705, "step": 92090 }, { "epoch": 7.66, "learning_rate": 2.980561483246958e-06, "loss": 0.7617, "step": 92100 }, { "epoch": 7.66, "learning_rate": 2.9804506277194247e-06, "loss": 0.8021, "step": 92110 }, { "epoch": 7.66, "learning_rate": 2.9803397721918906e-06, "loss": 0.8289, "step": 92120 }, { "epoch": 7.66, "learning_rate": 2.980228916664357e-06, "loss": 0.7923, "step": 92130 }, { "epoch": 7.66, "learning_rate": 2.9801180611368236e-06, "loss": 0.745, "step": 92140 }, { "epoch": 7.66, "learning_rate": 2.9800072056092895e-06, "loss": 0.8023, "step": 92150 }, { "epoch": 7.66, "learning_rate": 2.979896350081756e-06, "loss": 0.8921, "step": 92160 }, { "epoch": 7.66, "learning_rate": 2.979785494554222e-06, "loss": 0.7734, "step": 92170 }, { "epoch": 7.66, "learning_rate": 2.9796746390266884e-06, "loss": 0.8141, "step": 92180 }, { "epoch": 7.66, "learning_rate": 2.9795637834991547e-06, "loss": 0.8593, "step": 92190 }, { "epoch": 7.66, "learning_rate": 2.979452927971621e-06, "loss": 0.8005, "step": 92200 }, { "epoch": 7.66, "learning_rate": 2.979342072444087e-06, "loss": 0.8039, "step": 92210 }, { "epoch": 7.67, "learning_rate": 2.9792312169165535e-06, "loss": 0.8461, "step": 92220 }, { "epoch": 7.67, "learning_rate": 2.9791203613890194e-06, "loss": 0.8286, "step": 92230 }, { "epoch": 7.67, "learning_rate": 2.9790095058614857e-06, "loss": 0.7497, "step": 92240 }, { "epoch": 7.67, "learning_rate": 2.978898650333952e-06, "loss": 0.7983, "step": 92250 }, { "epoch": 7.67, "learning_rate": 2.9787877948064183e-06, "loss": 0.8048, "step": 92260 }, { "epoch": 7.67, "learning_rate": 2.978676939278885e-06, "loss": 0.8011, "step": 92270 }, { "epoch": 7.67, "learning_rate": 2.978566083751351e-06, "loss": 0.7848, "step": 92280 }, { "epoch": 7.67, "learning_rate": 2.978455228223817e-06, "loss": 0.7958, "step": 92290 }, { "epoch": 7.67, "learning_rate": 2.9783443726962835e-06, "loss": 0.7707, "step": 92300 }, { "epoch": 7.67, "learning_rate": 2.9782335171687498e-06, "loss": 0.8038, "step": 92310 }, { "epoch": 7.67, "learning_rate": 2.9781226616412156e-06, "loss": 0.8316, "step": 92320 }, { "epoch": 7.67, "learning_rate": 2.9780118061136824e-06, "loss": 0.8721, "step": 92330 }, { "epoch": 7.68, "learning_rate": 2.9779009505861482e-06, "loss": 0.8925, "step": 92340 }, { "epoch": 7.68, "learning_rate": 2.977790095058615e-06, "loss": 0.8267, "step": 92350 }, { "epoch": 7.68, "learning_rate": 2.977679239531081e-06, "loss": 0.8097, "step": 92360 }, { "epoch": 7.68, "learning_rate": 2.977568384003547e-06, "loss": 0.8502, "step": 92370 }, { "epoch": 7.68, "learning_rate": 2.9774575284760134e-06, "loss": 0.7901, "step": 92380 }, { "epoch": 7.68, "learning_rate": 2.9773466729484797e-06, "loss": 0.7969, "step": 92390 }, { "epoch": 7.68, "learning_rate": 2.977235817420946e-06, "loss": 0.846, "step": 92400 }, { "epoch": 7.68, "learning_rate": 2.9771249618934123e-06, "loss": 0.7411, "step": 92410 }, { "epoch": 7.68, "learning_rate": 2.9770141063658786e-06, "loss": 0.8483, "step": 92420 }, { "epoch": 7.68, "learning_rate": 2.976903250838345e-06, "loss": 0.8651, "step": 92430 }, { "epoch": 7.68, "learning_rate": 2.976792395310811e-06, "loss": 0.8662, "step": 92440 }, { "epoch": 7.68, "learning_rate": 2.976681539783277e-06, "loss": 0.8314, "step": 92450 }, { "epoch": 7.69, "learning_rate": 2.9765706842557438e-06, "loss": 0.8346, "step": 92460 }, { "epoch": 7.69, "learning_rate": 2.9764598287282097e-06, "loss": 0.8351, "step": 92470 }, { "epoch": 7.69, "learning_rate": 2.976348973200676e-06, "loss": 0.8181, "step": 92480 }, { "epoch": 7.69, "learning_rate": 2.9762381176731422e-06, "loss": 0.8416, "step": 92490 }, { "epoch": 7.69, "learning_rate": 2.9761272621456085e-06, "loss": 0.7865, "step": 92500 }, { "epoch": 7.69, "learning_rate": 2.9760164066180753e-06, "loss": 0.8913, "step": 92510 }, { "epoch": 7.69, "learning_rate": 2.975905551090541e-06, "loss": 0.8487, "step": 92520 }, { "epoch": 7.69, "learning_rate": 2.9757946955630074e-06, "loss": 0.8709, "step": 92530 }, { "epoch": 7.69, "learning_rate": 2.9756838400354737e-06, "loss": 0.762, "step": 92540 }, { "epoch": 7.69, "learning_rate": 2.97557298450794e-06, "loss": 0.8069, "step": 92550 }, { "epoch": 7.69, "learning_rate": 2.975462128980406e-06, "loss": 0.7985, "step": 92560 }, { "epoch": 7.69, "learning_rate": 2.9753512734528726e-06, "loss": 0.8482, "step": 92570 }, { "epoch": 7.7, "learning_rate": 2.9752404179253385e-06, "loss": 0.8579, "step": 92580 }, { "epoch": 7.7, "learning_rate": 2.975129562397805e-06, "loss": 0.7908, "step": 92590 }, { "epoch": 7.7, "learning_rate": 2.975018706870271e-06, "loss": 0.8224, "step": 92600 }, { "epoch": 7.7, "learning_rate": 2.9749078513427374e-06, "loss": 0.8126, "step": 92610 }, { "epoch": 7.7, "learning_rate": 2.9747969958152037e-06, "loss": 0.7422, "step": 92620 }, { "epoch": 7.7, "learning_rate": 2.97468614028767e-06, "loss": 0.8664, "step": 92630 }, { "epoch": 7.7, "learning_rate": 2.9745752847601363e-06, "loss": 0.8013, "step": 92640 }, { "epoch": 7.7, "learning_rate": 2.9744644292326025e-06, "loss": 0.7551, "step": 92650 }, { "epoch": 7.7, "learning_rate": 2.974353573705069e-06, "loss": 0.8126, "step": 92660 }, { "epoch": 7.7, "learning_rate": 2.9742427181775347e-06, "loss": 0.8275, "step": 92670 }, { "epoch": 7.7, "learning_rate": 2.9741318626500014e-06, "loss": 0.8335, "step": 92680 }, { "epoch": 7.7, "learning_rate": 2.9740210071224673e-06, "loss": 0.8447, "step": 92690 }, { "epoch": 7.71, "learning_rate": 2.973910151594934e-06, "loss": 0.8538, "step": 92700 }, { "epoch": 7.71, "learning_rate": 2.9737992960674e-06, "loss": 0.8417, "step": 92710 }, { "epoch": 7.71, "learning_rate": 2.973688440539866e-06, "loss": 0.8684, "step": 92720 }, { "epoch": 7.71, "learning_rate": 2.9735775850123325e-06, "loss": 0.8014, "step": 92730 }, { "epoch": 7.71, "learning_rate": 2.9734667294847988e-06, "loss": 0.7657, "step": 92740 }, { "epoch": 7.71, "learning_rate": 2.973355873957265e-06, "loss": 0.7742, "step": 92750 }, { "epoch": 7.71, "learning_rate": 2.9732450184297314e-06, "loss": 0.8008, "step": 92760 }, { "epoch": 7.71, "learning_rate": 2.9731341629021977e-06, "loss": 0.7565, "step": 92770 }, { "epoch": 7.71, "learning_rate": 2.973023307374664e-06, "loss": 0.7768, "step": 92780 }, { "epoch": 7.71, "learning_rate": 2.9729124518471303e-06, "loss": 0.821, "step": 92790 }, { "epoch": 7.71, "learning_rate": 2.972801596319596e-06, "loss": 0.8118, "step": 92800 }, { "epoch": 7.71, "learning_rate": 2.972690740792063e-06, "loss": 0.7726, "step": 92810 }, { "epoch": 7.72, "learning_rate": 2.9725798852645287e-06, "loss": 0.7649, "step": 92820 }, { "epoch": 7.72, "learning_rate": 2.972469029736995e-06, "loss": 0.7974, "step": 92830 }, { "epoch": 7.72, "learning_rate": 2.9723581742094613e-06, "loss": 0.8645, "step": 92840 }, { "epoch": 7.72, "learning_rate": 2.9722473186819276e-06, "loss": 0.8039, "step": 92850 }, { "epoch": 7.72, "learning_rate": 2.972136463154394e-06, "loss": 0.8274, "step": 92860 }, { "epoch": 7.72, "learning_rate": 2.97202560762686e-06, "loss": 0.8172, "step": 92870 }, { "epoch": 7.72, "learning_rate": 2.9719147520993265e-06, "loss": 0.8683, "step": 92880 }, { "epoch": 7.72, "learning_rate": 2.9718038965717928e-06, "loss": 0.8084, "step": 92890 }, { "epoch": 7.72, "learning_rate": 2.971693041044259e-06, "loss": 0.8309, "step": 92900 }, { "epoch": 7.72, "learning_rate": 2.971582185516725e-06, "loss": 0.8369, "step": 92910 }, { "epoch": 7.72, "learning_rate": 2.9714713299891917e-06, "loss": 0.8486, "step": 92920 }, { "epoch": 7.72, "learning_rate": 2.9713604744616575e-06, "loss": 0.8392, "step": 92930 }, { "epoch": 7.73, "learning_rate": 2.9712496189341243e-06, "loss": 0.7597, "step": 92940 }, { "epoch": 7.73, "learning_rate": 2.97113876340659e-06, "loss": 0.8043, "step": 92950 }, { "epoch": 7.73, "learning_rate": 2.9710279078790564e-06, "loss": 0.71, "step": 92960 }, { "epoch": 7.73, "learning_rate": 2.9709170523515227e-06, "loss": 0.8436, "step": 92970 }, { "epoch": 7.73, "learning_rate": 2.970806196823989e-06, "loss": 0.8503, "step": 92980 }, { "epoch": 7.73, "learning_rate": 2.970695341296455e-06, "loss": 0.8067, "step": 92990 }, { "epoch": 7.73, "learning_rate": 2.9705844857689216e-06, "loss": 0.8404, "step": 93000 }, { "epoch": 7.73, "learning_rate": 2.970473630241388e-06, "loss": 0.8663, "step": 93010 }, { "epoch": 7.73, "learning_rate": 2.970362774713854e-06, "loss": 0.7793, "step": 93020 }, { "epoch": 7.73, "learning_rate": 2.9702519191863205e-06, "loss": 0.8785, "step": 93030 }, { "epoch": 7.73, "learning_rate": 2.9701410636587864e-06, "loss": 0.8446, "step": 93040 }, { "epoch": 7.73, "learning_rate": 2.970030208131253e-06, "loss": 0.7957, "step": 93050 }, { "epoch": 7.74, "learning_rate": 2.969919352603719e-06, "loss": 0.7747, "step": 93060 }, { "epoch": 7.74, "learning_rate": 2.9698084970761853e-06, "loss": 0.8012, "step": 93070 }, { "epoch": 7.74, "learning_rate": 2.9696976415486516e-06, "loss": 0.8502, "step": 93080 }, { "epoch": 7.74, "learning_rate": 2.969586786021118e-06, "loss": 0.7608, "step": 93090 }, { "epoch": 7.74, "learning_rate": 2.9694759304935837e-06, "loss": 0.8045, "step": 93100 }, { "epoch": 7.74, "learning_rate": 2.9693650749660504e-06, "loss": 0.7865, "step": 93110 }, { "epoch": 7.74, "learning_rate": 2.9692542194385167e-06, "loss": 0.7545, "step": 93120 }, { "epoch": 7.74, "learning_rate": 2.969143363910983e-06, "loss": 0.8302, "step": 93130 }, { "epoch": 7.74, "learning_rate": 2.9690325083834493e-06, "loss": 0.8339, "step": 93140 }, { "epoch": 7.74, "learning_rate": 2.968921652855915e-06, "loss": 0.8676, "step": 93150 }, { "epoch": 7.74, "learning_rate": 2.968810797328382e-06, "loss": 0.7898, "step": 93160 }, { "epoch": 7.74, "learning_rate": 2.9686999418008478e-06, "loss": 0.8112, "step": 93170 }, { "epoch": 7.74, "learning_rate": 2.968589086273314e-06, "loss": 0.7796, "step": 93180 }, { "epoch": 7.75, "learning_rate": 2.9684782307457804e-06, "loss": 0.7965, "step": 93190 }, { "epoch": 7.75, "learning_rate": 2.9683673752182467e-06, "loss": 0.8316, "step": 93200 }, { "epoch": 7.75, "learning_rate": 2.968256519690713e-06, "loss": 0.8108, "step": 93210 }, { "epoch": 7.75, "learning_rate": 2.9681456641631793e-06, "loss": 0.8429, "step": 93220 }, { "epoch": 7.75, "learning_rate": 2.968034808635645e-06, "loss": 0.8284, "step": 93230 }, { "epoch": 7.75, "learning_rate": 2.967923953108112e-06, "loss": 0.7992, "step": 93240 }, { "epoch": 7.75, "learning_rate": 2.967813097580578e-06, "loss": 0.7902, "step": 93250 }, { "epoch": 7.75, "learning_rate": 2.967702242053044e-06, "loss": 0.8468, "step": 93260 }, { "epoch": 7.75, "learning_rate": 2.9675913865255107e-06, "loss": 0.828, "step": 93270 }, { "epoch": 7.75, "learning_rate": 2.9674805309979766e-06, "loss": 0.8445, "step": 93280 }, { "epoch": 7.75, "learning_rate": 2.9673696754704433e-06, "loss": 0.787, "step": 93290 }, { "epoch": 7.75, "learning_rate": 2.967258819942909e-06, "loss": 0.7994, "step": 93300 }, { "epoch": 7.76, "learning_rate": 2.9671479644153755e-06, "loss": 0.7811, "step": 93310 }, { "epoch": 7.76, "learning_rate": 2.967037108887842e-06, "loss": 0.8084, "step": 93320 }, { "epoch": 7.76, "learning_rate": 2.966926253360308e-06, "loss": 0.859, "step": 93330 }, { "epoch": 7.76, "learning_rate": 2.966815397832774e-06, "loss": 0.8205, "step": 93340 }, { "epoch": 7.76, "learning_rate": 2.9667045423052407e-06, "loss": 0.7847, "step": 93350 }, { "epoch": 7.76, "learning_rate": 2.9665936867777066e-06, "loss": 0.8219, "step": 93360 }, { "epoch": 7.76, "learning_rate": 2.9664828312501733e-06, "loss": 0.8128, "step": 93370 }, { "epoch": 7.76, "learning_rate": 2.9663719757226396e-06, "loss": 0.7766, "step": 93380 }, { "epoch": 7.76, "learning_rate": 2.9662611201951054e-06, "loss": 0.8047, "step": 93390 }, { "epoch": 7.76, "learning_rate": 2.966150264667572e-06, "loss": 0.8013, "step": 93400 }, { "epoch": 7.76, "learning_rate": 2.966039409140038e-06, "loss": 0.7483, "step": 93410 }, { "epoch": 7.76, "learning_rate": 2.9659285536125043e-06, "loss": 0.853, "step": 93420 }, { "epoch": 7.77, "learning_rate": 2.9658176980849706e-06, "loss": 0.8686, "step": 93430 }, { "epoch": 7.77, "learning_rate": 2.965706842557437e-06, "loss": 0.7757, "step": 93440 }, { "epoch": 7.77, "learning_rate": 2.9655959870299028e-06, "loss": 1.6804, "step": 93450 }, { "epoch": 7.77, "learning_rate": 2.9654851315023695e-06, "loss": 0.7777, "step": 93460 }, { "epoch": 7.77, "learning_rate": 2.9653742759748354e-06, "loss": 0.8054, "step": 93470 }, { "epoch": 7.77, "learning_rate": 2.965263420447302e-06, "loss": 0.8468, "step": 93480 }, { "epoch": 7.77, "learning_rate": 2.9651525649197684e-06, "loss": 0.7411, "step": 93490 }, { "epoch": 7.77, "learning_rate": 2.9650417093922343e-06, "loss": 0.8746, "step": 93500 }, { "epoch": 7.77, "learning_rate": 2.964930853864701e-06, "loss": 0.7642, "step": 93510 }, { "epoch": 7.77, "learning_rate": 2.964819998337167e-06, "loss": 0.8464, "step": 93520 }, { "epoch": 7.77, "learning_rate": 2.964709142809633e-06, "loss": 0.8337, "step": 93530 }, { "epoch": 7.77, "learning_rate": 2.9645982872820994e-06, "loss": 0.8237, "step": 93540 }, { "epoch": 7.78, "learning_rate": 2.9644874317545657e-06, "loss": 0.7518, "step": 93550 }, { "epoch": 7.78, "learning_rate": 2.964376576227032e-06, "loss": 0.8269, "step": 93560 }, { "epoch": 7.78, "learning_rate": 2.9642657206994983e-06, "loss": 0.8449, "step": 93570 }, { "epoch": 7.78, "learning_rate": 2.964154865171964e-06, "loss": 0.7951, "step": 93580 }, { "epoch": 7.78, "learning_rate": 2.964044009644431e-06, "loss": 0.8685, "step": 93590 }, { "epoch": 7.78, "learning_rate": 2.963933154116897e-06, "loss": 0.8348, "step": 93600 }, { "epoch": 7.78, "learning_rate": 2.963822298589363e-06, "loss": 0.8016, "step": 93610 }, { "epoch": 7.78, "learning_rate": 2.96371144306183e-06, "loss": 0.8208, "step": 93620 }, { "epoch": 7.78, "learning_rate": 2.9636005875342957e-06, "loss": 0.8499, "step": 93630 }, { "epoch": 7.78, "learning_rate": 2.9634897320067624e-06, "loss": 0.7365, "step": 93640 }, { "epoch": 7.78, "learning_rate": 2.9633788764792283e-06, "loss": 0.7865, "step": 93650 }, { "epoch": 7.78, "learning_rate": 2.9632680209516946e-06, "loss": 0.7529, "step": 93660 }, { "epoch": 7.79, "learning_rate": 2.963157165424161e-06, "loss": 0.8859, "step": 93670 }, { "epoch": 7.79, "learning_rate": 2.963046309896627e-06, "loss": 0.8123, "step": 93680 }, { "epoch": 7.79, "learning_rate": 2.962935454369093e-06, "loss": 0.8143, "step": 93690 }, { "epoch": 7.79, "learning_rate": 2.9628245988415597e-06, "loss": 0.8134, "step": 93700 }, { "epoch": 7.79, "learning_rate": 2.9627137433140256e-06, "loss": 0.7743, "step": 93710 }, { "epoch": 7.79, "learning_rate": 2.9626028877864923e-06, "loss": 0.8573, "step": 93720 }, { "epoch": 7.79, "learning_rate": 2.962492032258958e-06, "loss": 0.7904, "step": 93730 }, { "epoch": 7.79, "learning_rate": 2.9623811767314245e-06, "loss": 0.8288, "step": 93740 }, { "epoch": 7.79, "learning_rate": 2.9622703212038912e-06, "loss": 0.8119, "step": 93750 }, { "epoch": 7.79, "learning_rate": 2.962159465676357e-06, "loss": 0.8228, "step": 93760 }, { "epoch": 7.79, "learning_rate": 2.9620486101488234e-06, "loss": 0.7904, "step": 93770 }, { "epoch": 7.79, "learning_rate": 2.9619377546212897e-06, "loss": 0.8736, "step": 93780 }, { "epoch": 7.8, "learning_rate": 2.961826899093756e-06, "loss": 0.7381, "step": 93790 }, { "epoch": 7.8, "learning_rate": 2.9617160435662223e-06, "loss": 0.7516, "step": 93800 }, { "epoch": 7.8, "learning_rate": 2.9616051880386886e-06, "loss": 0.8083, "step": 93810 }, { "epoch": 7.8, "learning_rate": 2.9614943325111544e-06, "loss": 0.7794, "step": 93820 }, { "epoch": 7.8, "learning_rate": 2.961383476983621e-06, "loss": 0.7711, "step": 93830 }, { "epoch": 7.8, "learning_rate": 2.961272621456087e-06, "loss": 0.7575, "step": 93840 }, { "epoch": 7.8, "learning_rate": 2.9611617659285533e-06, "loss": 0.8364, "step": 93850 }, { "epoch": 7.8, "learning_rate": 2.96105091040102e-06, "loss": 0.7881, "step": 93860 }, { "epoch": 7.8, "learning_rate": 2.960940054873486e-06, "loss": 0.8553, "step": 93870 }, { "epoch": 7.8, "learning_rate": 2.9608291993459526e-06, "loss": 0.8723, "step": 93880 }, { "epoch": 7.8, "learning_rate": 2.9607183438184185e-06, "loss": 0.8151, "step": 93890 }, { "epoch": 7.8, "learning_rate": 2.960607488290885e-06, "loss": 0.7797, "step": 93900 }, { "epoch": 7.81, "learning_rate": 2.960496632763351e-06, "loss": 0.8254, "step": 93910 }, { "epoch": 7.81, "learning_rate": 2.9603857772358174e-06, "loss": 0.8486, "step": 93920 }, { "epoch": 7.81, "learning_rate": 2.9602749217082833e-06, "loss": 0.7938, "step": 93930 }, { "epoch": 7.81, "learning_rate": 2.96016406618075e-06, "loss": 0.877, "step": 93940 }, { "epoch": 7.81, "learning_rate": 2.960053210653216e-06, "loss": 0.7894, "step": 93950 }, { "epoch": 7.81, "learning_rate": 2.959942355125682e-06, "loss": 0.7927, "step": 93960 }, { "epoch": 7.81, "learning_rate": 2.9598314995981484e-06, "loss": 0.8183, "step": 93970 }, { "epoch": 7.81, "learning_rate": 2.9597206440706147e-06, "loss": 0.8695, "step": 93980 }, { "epoch": 7.81, "learning_rate": 2.9596097885430815e-06, "loss": 0.8131, "step": 93990 }, { "epoch": 7.81, "learning_rate": 2.9594989330155473e-06, "loss": 0.7375, "step": 94000 }, { "epoch": 7.81, "learning_rate": 2.9593880774880136e-06, "loss": 0.8226, "step": 94010 }, { "epoch": 7.81, "learning_rate": 2.95927722196048e-06, "loss": 0.8229, "step": 94020 }, { "epoch": 7.82, "learning_rate": 2.9591663664329462e-06, "loss": 0.8467, "step": 94030 }, { "epoch": 7.82, "learning_rate": 2.959055510905412e-06, "loss": 0.7885, "step": 94040 }, { "epoch": 7.82, "learning_rate": 2.958944655377879e-06, "loss": 0.8814, "step": 94050 }, { "epoch": 7.82, "learning_rate": 2.9588337998503447e-06, "loss": 0.8354, "step": 94060 }, { "epoch": 7.82, "learning_rate": 2.9587229443228114e-06, "loss": 0.8186, "step": 94070 }, { "epoch": 7.82, "learning_rate": 2.9586120887952773e-06, "loss": 0.8603, "step": 94080 }, { "epoch": 7.82, "learning_rate": 2.9585012332677436e-06, "loss": 0.8217, "step": 94090 }, { "epoch": 7.82, "learning_rate": 2.95839037774021e-06, "loss": 0.7629, "step": 94100 }, { "epoch": 7.82, "learning_rate": 2.958279522212676e-06, "loss": 0.8286, "step": 94110 }, { "epoch": 7.82, "learning_rate": 2.9581686666851425e-06, "loss": 0.8176, "step": 94120 }, { "epoch": 7.82, "learning_rate": 2.9580578111576088e-06, "loss": 0.8511, "step": 94130 }, { "epoch": 7.82, "learning_rate": 2.957946955630075e-06, "loss": 0.8319, "step": 94140 }, { "epoch": 7.83, "learning_rate": 2.9578361001025413e-06, "loss": 0.8515, "step": 94150 }, { "epoch": 7.83, "learning_rate": 2.9577252445750076e-06, "loss": 0.7975, "step": 94160 }, { "epoch": 7.83, "learning_rate": 2.9576143890474735e-06, "loss": 0.8417, "step": 94170 }, { "epoch": 7.83, "learning_rate": 2.9575035335199402e-06, "loss": 0.8446, "step": 94180 }, { "epoch": 7.83, "learning_rate": 2.957392677992406e-06, "loss": 0.8647, "step": 94190 }, { "epoch": 7.83, "learning_rate": 2.9572818224648724e-06, "loss": 0.8408, "step": 94200 }, { "epoch": 7.83, "learning_rate": 2.9571709669373387e-06, "loss": 0.8365, "step": 94210 }, { "epoch": 7.83, "learning_rate": 2.957060111409805e-06, "loss": 0.7764, "step": 94220 }, { "epoch": 7.83, "learning_rate": 2.9569492558822717e-06, "loss": 0.8075, "step": 94230 }, { "epoch": 7.83, "learning_rate": 2.9568384003547376e-06, "loss": 0.7701, "step": 94240 }, { "epoch": 7.83, "learning_rate": 2.956727544827204e-06, "loss": 0.8438, "step": 94250 }, { "epoch": 7.83, "learning_rate": 2.95661668929967e-06, "loss": 0.7889, "step": 94260 }, { "epoch": 7.84, "learning_rate": 2.9565058337721365e-06, "loss": 0.8465, "step": 94270 }, { "epoch": 7.84, "learning_rate": 2.9563949782446023e-06, "loss": 0.776, "step": 94280 }, { "epoch": 7.84, "learning_rate": 2.956284122717069e-06, "loss": 0.7575, "step": 94290 }, { "epoch": 7.84, "learning_rate": 2.956173267189535e-06, "loss": 0.7629, "step": 94300 }, { "epoch": 7.84, "learning_rate": 2.9560624116620016e-06, "loss": 0.7542, "step": 94310 }, { "epoch": 7.84, "learning_rate": 2.9559515561344675e-06, "loss": 0.7544, "step": 94320 }, { "epoch": 7.84, "learning_rate": 2.955840700606934e-06, "loss": 0.8101, "step": 94330 }, { "epoch": 7.84, "learning_rate": 2.9557298450794e-06, "loss": 0.7687, "step": 94340 }, { "epoch": 7.84, "learning_rate": 2.9556189895518664e-06, "loss": 0.8115, "step": 94350 }, { "epoch": 7.84, "learning_rate": 2.9555081340243327e-06, "loss": 0.7819, "step": 94360 }, { "epoch": 7.84, "learning_rate": 2.955397278496799e-06, "loss": 0.8441, "step": 94370 }, { "epoch": 7.84, "learning_rate": 2.9552864229692653e-06, "loss": 0.8471, "step": 94380 }, { "epoch": 7.85, "learning_rate": 2.955175567441731e-06, "loss": 0.8031, "step": 94390 }, { "epoch": 7.85, "learning_rate": 2.955064711914198e-06, "loss": 0.7581, "step": 94400 }, { "epoch": 7.85, "learning_rate": 2.9549538563866637e-06, "loss": 0.7966, "step": 94410 }, { "epoch": 7.85, "learning_rate": 2.9548430008591305e-06, "loss": 0.7748, "step": 94420 }, { "epoch": 7.85, "learning_rate": 2.9547321453315963e-06, "loss": 0.7374, "step": 94430 }, { "epoch": 7.85, "learning_rate": 2.9546212898040626e-06, "loss": 0.7822, "step": 94440 }, { "epoch": 7.85, "learning_rate": 2.954510434276529e-06, "loss": 0.8138, "step": 94450 }, { "epoch": 7.85, "learning_rate": 2.9543995787489952e-06, "loss": 0.7741, "step": 94460 }, { "epoch": 7.85, "learning_rate": 2.954288723221461e-06, "loss": 0.8148, "step": 94470 }, { "epoch": 7.85, "learning_rate": 2.954177867693928e-06, "loss": 0.9095, "step": 94480 }, { "epoch": 7.85, "learning_rate": 2.954067012166394e-06, "loss": 0.8513, "step": 94490 }, { "epoch": 7.85, "learning_rate": 2.9539561566388604e-06, "loss": 0.7821, "step": 94500 }, { "epoch": 7.86, "learning_rate": 2.9538453011113267e-06, "loss": 0.8293, "step": 94510 }, { "epoch": 7.86, "learning_rate": 2.9537344455837926e-06, "loss": 0.8321, "step": 94520 }, { "epoch": 7.86, "learning_rate": 2.9536235900562593e-06, "loss": 0.8003, "step": 94530 }, { "epoch": 7.86, "learning_rate": 2.953512734528725e-06, "loss": 0.863, "step": 94540 }, { "epoch": 7.86, "learning_rate": 2.9534018790011915e-06, "loss": 0.8277, "step": 94550 }, { "epoch": 7.86, "learning_rate": 2.9532910234736578e-06, "loss": 0.8323, "step": 94560 }, { "epoch": 7.86, "learning_rate": 2.953180167946124e-06, "loss": 0.8199, "step": 94570 }, { "epoch": 7.86, "learning_rate": 2.9530693124185903e-06, "loss": 0.8352, "step": 94580 }, { "epoch": 7.86, "learning_rate": 2.9529584568910566e-06, "loss": 0.8623, "step": 94590 }, { "epoch": 7.86, "learning_rate": 2.952847601363523e-06, "loss": 0.7717, "step": 94600 }, { "epoch": 7.86, "learning_rate": 2.9527367458359892e-06, "loss": 0.7874, "step": 94610 }, { "epoch": 7.86, "learning_rate": 2.9526258903084555e-06, "loss": 0.8344, "step": 94620 }, { "epoch": 7.87, "learning_rate": 2.9525150347809214e-06, "loss": 0.8218, "step": 94630 }, { "epoch": 7.87, "learning_rate": 2.952404179253388e-06, "loss": 0.7774, "step": 94640 }, { "epoch": 7.87, "learning_rate": 2.952293323725854e-06, "loss": 0.7436, "step": 94650 }, { "epoch": 7.87, "learning_rate": 2.9521824681983207e-06, "loss": 0.7974, "step": 94660 }, { "epoch": 7.87, "learning_rate": 2.9520716126707866e-06, "loss": 0.8342, "step": 94670 }, { "epoch": 7.87, "learning_rate": 2.951960757143253e-06, "loss": 0.8317, "step": 94680 }, { "epoch": 7.87, "learning_rate": 2.951849901615719e-06, "loss": 0.8114, "step": 94690 }, { "epoch": 7.87, "learning_rate": 2.9517390460881855e-06, "loss": 0.8001, "step": 94700 }, { "epoch": 7.87, "learning_rate": 2.9516281905606513e-06, "loss": 0.7459, "step": 94710 }, { "epoch": 7.87, "learning_rate": 2.951517335033118e-06, "loss": 0.8276, "step": 94720 }, { "epoch": 7.87, "learning_rate": 2.9514064795055844e-06, "loss": 0.8339, "step": 94730 }, { "epoch": 7.87, "learning_rate": 2.9512956239780502e-06, "loss": 0.8229, "step": 94740 }, { "epoch": 7.88, "learning_rate": 2.951184768450517e-06, "loss": 0.7813, "step": 94750 }, { "epoch": 7.88, "learning_rate": 2.951073912922983e-06, "loss": 0.8327, "step": 94760 }, { "epoch": 7.88, "learning_rate": 2.9509630573954495e-06, "loss": 0.8279, "step": 94770 }, { "epoch": 7.88, "learning_rate": 2.9508522018679154e-06, "loss": 0.7934, "step": 94780 }, { "epoch": 7.88, "learning_rate": 2.9507413463403817e-06, "loss": 0.8385, "step": 94790 }, { "epoch": 7.88, "learning_rate": 2.950630490812848e-06, "loss": 0.7645, "step": 94800 }, { "epoch": 7.88, "learning_rate": 2.9505196352853143e-06, "loss": 0.799, "step": 94810 }, { "epoch": 7.88, "learning_rate": 2.95040877975778e-06, "loss": 0.7999, "step": 94820 }, { "epoch": 7.88, "learning_rate": 2.950297924230247e-06, "loss": 0.8381, "step": 94830 }, { "epoch": 7.88, "learning_rate": 2.950187068702713e-06, "loss": 0.8201, "step": 94840 }, { "epoch": 7.88, "learning_rate": 2.9500762131751795e-06, "loss": 0.7567, "step": 94850 }, { "epoch": 7.88, "learning_rate": 2.9499653576476458e-06, "loss": 0.7524, "step": 94860 }, { "epoch": 7.89, "learning_rate": 2.9498545021201116e-06, "loss": 0.7949, "step": 94870 }, { "epoch": 7.89, "learning_rate": 2.9497436465925784e-06, "loss": 0.8987, "step": 94880 }, { "epoch": 7.89, "learning_rate": 2.9496327910650442e-06, "loss": 0.8466, "step": 94890 }, { "epoch": 7.89, "learning_rate": 2.9495219355375105e-06, "loss": 0.7952, "step": 94900 }, { "epoch": 7.89, "learning_rate": 2.949411080009977e-06, "loss": 0.7735, "step": 94910 }, { "epoch": 7.89, "learning_rate": 2.949300224482443e-06, "loss": 0.7831, "step": 94920 }, { "epoch": 7.89, "learning_rate": 2.9491893689549094e-06, "loss": 0.872, "step": 94930 }, { "epoch": 7.89, "learning_rate": 2.9490785134273757e-06, "loss": 0.8008, "step": 94940 }, { "epoch": 7.89, "learning_rate": 2.9489676578998416e-06, "loss": 0.835, "step": 94950 }, { "epoch": 7.89, "learning_rate": 2.9488568023723083e-06, "loss": 0.813, "step": 94960 }, { "epoch": 7.89, "learning_rate": 2.9487459468447746e-06, "loss": 0.8822, "step": 94970 }, { "epoch": 7.89, "learning_rate": 2.9486350913172405e-06, "loss": 0.893, "step": 94980 }, { "epoch": 7.9, "learning_rate": 2.948524235789707e-06, "loss": 0.7964, "step": 94990 }, { "epoch": 7.9, "learning_rate": 2.948413380262173e-06, "loss": 0.7856, "step": 95000 }, { "epoch": 7.9, "learning_rate": 2.9483136102873926e-06, "loss": 0.7255, "step": 95010 }, { "epoch": 7.9, "learning_rate": 2.9482027547598593e-06, "loss": 0.8243, "step": 95020 }, { "epoch": 7.9, "learning_rate": 2.948091899232325e-06, "loss": 0.8323, "step": 95030 }, { "epoch": 7.9, "learning_rate": 2.9479810437047915e-06, "loss": 0.7747, "step": 95040 }, { "epoch": 7.9, "learning_rate": 2.947870188177258e-06, "loss": 0.7798, "step": 95050 }, { "epoch": 7.9, "learning_rate": 2.947759332649724e-06, "loss": 0.7684, "step": 95060 }, { "epoch": 7.9, "learning_rate": 2.9476484771221904e-06, "loss": 0.8175, "step": 95070 }, { "epoch": 7.9, "learning_rate": 2.9475376215946567e-06, "loss": 0.8102, "step": 95080 }, { "epoch": 7.9, "learning_rate": 2.947426766067123e-06, "loss": 0.7996, "step": 95090 }, { "epoch": 7.9, "learning_rate": 2.9473159105395893e-06, "loss": 0.7957, "step": 95100 }, { "epoch": 7.91, "learning_rate": 2.9472050550120555e-06, "loss": 0.7863, "step": 95110 }, { "epoch": 7.91, "learning_rate": 2.9470941994845214e-06, "loss": 0.7936, "step": 95120 }, { "epoch": 7.91, "learning_rate": 2.946983343956988e-06, "loss": 0.8534, "step": 95130 }, { "epoch": 7.91, "learning_rate": 2.946872488429454e-06, "loss": 0.7409, "step": 95140 }, { "epoch": 7.91, "learning_rate": 2.9467616329019203e-06, "loss": 0.7762, "step": 95150 }, { "epoch": 7.91, "learning_rate": 2.9466507773743866e-06, "loss": 0.7675, "step": 95160 }, { "epoch": 7.91, "learning_rate": 2.946539921846853e-06, "loss": 0.7982, "step": 95170 }, { "epoch": 7.91, "learning_rate": 2.9464290663193196e-06, "loss": 0.8035, "step": 95180 }, { "epoch": 7.91, "learning_rate": 2.9463182107917855e-06, "loss": 0.8957, "step": 95190 }, { "epoch": 7.91, "learning_rate": 2.9462073552642518e-06, "loss": 0.7912, "step": 95200 }, { "epoch": 7.91, "learning_rate": 2.946096499736718e-06, "loss": 0.8222, "step": 95210 }, { "epoch": 7.91, "learning_rate": 2.9459856442091844e-06, "loss": 0.8435, "step": 95220 }, { "epoch": 7.92, "learning_rate": 2.9458747886816502e-06, "loss": 0.8178, "step": 95230 }, { "epoch": 7.92, "learning_rate": 2.945763933154117e-06, "loss": 0.8337, "step": 95240 }, { "epoch": 7.92, "learning_rate": 2.945653077626583e-06, "loss": 0.7925, "step": 95250 }, { "epoch": 7.92, "learning_rate": 2.9455422220990496e-06, "loss": 0.7873, "step": 95260 }, { "epoch": 7.92, "learning_rate": 2.9454313665715154e-06, "loss": 0.8339, "step": 95270 }, { "epoch": 7.92, "learning_rate": 2.9453205110439817e-06, "loss": 0.7954, "step": 95280 }, { "epoch": 7.92, "learning_rate": 2.945209655516448e-06, "loss": 0.7931, "step": 95290 }, { "epoch": 7.92, "learning_rate": 2.9450987999889143e-06, "loss": 0.8465, "step": 95300 }, { "epoch": 7.92, "learning_rate": 2.9449879444613806e-06, "loss": 0.7956, "step": 95310 }, { "epoch": 7.92, "learning_rate": 2.944877088933847e-06, "loss": 0.7872, "step": 95320 }, { "epoch": 7.92, "learning_rate": 2.944766233406313e-06, "loss": 0.8623, "step": 95330 }, { "epoch": 7.92, "learning_rate": 2.944655377878779e-06, "loss": 0.7696, "step": 95340 }, { "epoch": 7.93, "learning_rate": 2.944544522351246e-06, "loss": 0.7783, "step": 95350 }, { "epoch": 7.93, "learning_rate": 2.9444336668237117e-06, "loss": 0.8526, "step": 95360 }, { "epoch": 7.93, "learning_rate": 2.9443228112961784e-06, "loss": 0.9045, "step": 95370 }, { "epoch": 7.93, "learning_rate": 2.9442119557686443e-06, "loss": 0.8504, "step": 95380 }, { "epoch": 7.93, "learning_rate": 2.9441011002411105e-06, "loss": 0.8194, "step": 95390 }, { "epoch": 7.93, "learning_rate": 2.943990244713577e-06, "loss": 0.7473, "step": 95400 }, { "epoch": 7.93, "learning_rate": 2.943879389186043e-06, "loss": 0.7924, "step": 95410 }, { "epoch": 7.93, "learning_rate": 2.9437685336585094e-06, "loss": 0.8282, "step": 95420 }, { "epoch": 7.93, "learning_rate": 2.9436576781309757e-06, "loss": 0.8259, "step": 95430 }, { "epoch": 7.93, "learning_rate": 2.9435579081561953e-06, "loss": 0.7875, "step": 95440 }, { "epoch": 7.93, "learning_rate": 2.9434470526286616e-06, "loss": 0.7932, "step": 95450 }, { "epoch": 7.93, "learning_rate": 2.943336197101128e-06, "loss": 0.7747, "step": 95460 }, { "epoch": 7.94, "learning_rate": 2.943225341573594e-06, "loss": 0.7954, "step": 95470 }, { "epoch": 7.94, "learning_rate": 2.94311448604606e-06, "loss": 0.8051, "step": 95480 }, { "epoch": 7.94, "learning_rate": 2.9430036305185267e-06, "loss": 0.8011, "step": 95490 }, { "epoch": 7.94, "learning_rate": 2.9428927749909926e-06, "loss": 0.8059, "step": 95500 }, { "epoch": 7.94, "learning_rate": 2.942781919463459e-06, "loss": 0.7881, "step": 95510 }, { "epoch": 7.94, "learning_rate": 2.9426710639359256e-06, "loss": 0.7767, "step": 95520 }, { "epoch": 7.94, "learning_rate": 2.9425602084083915e-06, "loss": 0.787, "step": 95530 }, { "epoch": 7.94, "learning_rate": 2.9424493528808582e-06, "loss": 0.7849, "step": 95540 }, { "epoch": 7.94, "learning_rate": 2.942338497353324e-06, "loss": 0.8517, "step": 95550 }, { "epoch": 7.94, "learning_rate": 2.9422276418257904e-06, "loss": 0.845, "step": 95560 }, { "epoch": 7.94, "learning_rate": 2.9421167862982567e-06, "loss": 0.8432, "step": 95570 }, { "epoch": 7.94, "learning_rate": 2.942005930770723e-06, "loss": 0.8266, "step": 95580 }, { "epoch": 7.95, "learning_rate": 2.941895075243189e-06, "loss": 0.7878, "step": 95590 }, { "epoch": 7.95, "learning_rate": 2.9417842197156556e-06, "loss": 0.7391, "step": 95600 }, { "epoch": 7.95, "learning_rate": 2.9416733641881214e-06, "loss": 0.7928, "step": 95610 }, { "epoch": 7.95, "learning_rate": 2.941562508660588e-06, "loss": 0.7631, "step": 95620 }, { "epoch": 7.95, "learning_rate": 2.9414516531330545e-06, "loss": 0.8606, "step": 95630 }, { "epoch": 7.95, "learning_rate": 2.9413407976055203e-06, "loss": 0.7773, "step": 95640 }, { "epoch": 7.95, "learning_rate": 2.941229942077987e-06, "loss": 0.9062, "step": 95650 }, { "epoch": 7.95, "learning_rate": 2.941119086550453e-06, "loss": 0.8321, "step": 95660 }, { "epoch": 7.95, "learning_rate": 2.9410082310229192e-06, "loss": 0.8328, "step": 95670 }, { "epoch": 7.95, "learning_rate": 2.9408973754953855e-06, "loss": 0.9066, "step": 95680 }, { "epoch": 7.95, "learning_rate": 2.940786519967852e-06, "loss": 0.8201, "step": 95690 }, { "epoch": 7.95, "learning_rate": 2.940675664440318e-06, "loss": 0.8209, "step": 95700 }, { "epoch": 7.96, "learning_rate": 2.9405648089127844e-06, "loss": 0.8013, "step": 95710 }, { "epoch": 7.96, "learning_rate": 2.9404539533852503e-06, "loss": 0.8559, "step": 95720 }, { "epoch": 7.96, "learning_rate": 2.940343097857717e-06, "loss": 0.9217, "step": 95730 }, { "epoch": 7.96, "learning_rate": 2.940232242330183e-06, "loss": 0.8843, "step": 95740 }, { "epoch": 7.96, "learning_rate": 2.940121386802649e-06, "loss": 0.8378, "step": 95750 }, { "epoch": 7.96, "learning_rate": 2.940010531275116e-06, "loss": 0.7915, "step": 95760 }, { "epoch": 7.96, "learning_rate": 2.9398996757475817e-06, "loss": 0.8095, "step": 95770 }, { "epoch": 7.96, "learning_rate": 2.9397888202200485e-06, "loss": 0.8619, "step": 95780 }, { "epoch": 7.96, "learning_rate": 2.9396779646925143e-06, "loss": 0.7689, "step": 95790 }, { "epoch": 7.96, "learning_rate": 2.9395671091649806e-06, "loss": 0.8031, "step": 95800 }, { "epoch": 7.96, "learning_rate": 2.939456253637447e-06, "loss": 0.7894, "step": 95810 }, { "epoch": 7.96, "learning_rate": 2.9393453981099132e-06, "loss": 0.7615, "step": 95820 }, { "epoch": 7.97, "learning_rate": 2.939234542582379e-06, "loss": 0.8676, "step": 95830 }, { "epoch": 7.97, "learning_rate": 2.939123687054846e-06, "loss": 0.7937, "step": 95840 }, { "epoch": 7.97, "learning_rate": 2.9390128315273117e-06, "loss": 0.7925, "step": 95850 }, { "epoch": 7.97, "learning_rate": 2.938901975999778e-06, "loss": 0.8053, "step": 95860 }, { "epoch": 7.97, "learning_rate": 2.9387911204722443e-06, "loss": 0.7954, "step": 95870 }, { "epoch": 7.97, "learning_rate": 2.9386802649447106e-06, "loss": 0.845, "step": 95880 }, { "epoch": 7.97, "learning_rate": 2.9385694094171773e-06, "loss": 0.6874, "step": 95890 }, { "epoch": 7.97, "learning_rate": 2.938458553889643e-06, "loss": 0.7183, "step": 95900 }, { "epoch": 7.97, "learning_rate": 2.9383476983621095e-06, "loss": 0.9202, "step": 95910 }, { "epoch": 7.97, "learning_rate": 2.9382368428345758e-06, "loss": 0.7924, "step": 95920 }, { "epoch": 7.97, "learning_rate": 2.938125987307042e-06, "loss": 0.8573, "step": 95930 }, { "epoch": 7.97, "learning_rate": 2.938015131779508e-06, "loss": 0.8235, "step": 95940 }, { "epoch": 7.98, "learning_rate": 2.9379042762519746e-06, "loss": 0.8308, "step": 95950 }, { "epoch": 7.98, "learning_rate": 2.9377934207244405e-06, "loss": 0.8261, "step": 95960 }, { "epoch": 7.98, "learning_rate": 2.9376825651969072e-06, "loss": 0.8586, "step": 95970 }, { "epoch": 7.98, "learning_rate": 2.937571709669373e-06, "loss": 0.8058, "step": 95980 }, { "epoch": 7.98, "learning_rate": 2.9374608541418394e-06, "loss": 0.9196, "step": 95990 }, { "epoch": 7.98, "learning_rate": 2.937349998614306e-06, "loss": 0.8128, "step": 96000 }, { "epoch": 7.98, "learning_rate": 2.937239143086772e-06, "loss": 0.85, "step": 96010 }, { "epoch": 7.98, "learning_rate": 2.9371282875592383e-06, "loss": 0.8138, "step": 96020 }, { "epoch": 7.98, "learning_rate": 2.9370174320317046e-06, "loss": 0.8071, "step": 96030 }, { "epoch": 7.98, "learning_rate": 2.936906576504171e-06, "loss": 0.7637, "step": 96040 }, { "epoch": 7.98, "learning_rate": 2.936795720976637e-06, "loss": 0.8394, "step": 96050 }, { "epoch": 7.98, "learning_rate": 2.9366848654491035e-06, "loss": 0.7963, "step": 96060 }, { "epoch": 7.99, "learning_rate": 2.9365740099215693e-06, "loss": 0.8159, "step": 96070 }, { "epoch": 7.99, "learning_rate": 2.936463154394036e-06, "loss": 0.8691, "step": 96080 }, { "epoch": 7.99, "learning_rate": 2.936352298866502e-06, "loss": 0.7778, "step": 96090 }, { "epoch": 7.99, "learning_rate": 2.9362414433389682e-06, "loss": 0.7866, "step": 96100 }, { "epoch": 7.99, "learning_rate": 2.9361305878114345e-06, "loss": 0.8255, "step": 96110 }, { "epoch": 7.99, "learning_rate": 2.936019732283901e-06, "loss": 0.8215, "step": 96120 }, { "epoch": 7.99, "learning_rate": 2.9359088767563675e-06, "loss": 0.8835, "step": 96130 }, { "epoch": 7.99, "learning_rate": 2.9357980212288334e-06, "loss": 0.7784, "step": 96140 }, { "epoch": 7.99, "learning_rate": 2.9356871657012997e-06, "loss": 0.8046, "step": 96150 }, { "epoch": 7.99, "learning_rate": 2.935576310173766e-06, "loss": 0.8247, "step": 96160 }, { "epoch": 7.99, "learning_rate": 2.9354654546462323e-06, "loss": 0.8379, "step": 96170 }, { "epoch": 7.99, "learning_rate": 2.935354599118698e-06, "loss": 0.8222, "step": 96180 }, { "epoch": 8.0, "learning_rate": 2.935243743591165e-06, "loss": 0.8187, "step": 96190 }, { "epoch": 8.0, "learning_rate": 2.9351328880636307e-06, "loss": 0.8772, "step": 96200 }, { "epoch": 8.0, "learning_rate": 2.9350220325360975e-06, "loss": 0.8443, "step": 96210 }, { "epoch": 8.0, "learning_rate": 2.9349111770085633e-06, "loss": 0.7708, "step": 96220 }, { "epoch": 8.0, "learning_rate": 2.9348003214810296e-06, "loss": 0.7734, "step": 96230 }, { "epoch": 8.0, "learning_rate": 2.934689465953496e-06, "loss": 0.8106, "step": 96240 }, { "epoch": 8.0, "eval_loss": 1.0752809047698975, "eval_runtime": 349.0309, "eval_samples_per_second": 7.661, "eval_steps_per_second": 3.831, "eval_wer": 0.6448795280002637, "step": 96248 }, { "epoch": 8.0, "learning_rate": 2.9345786104259622e-06, "loss": 0.8367, "step": 96250 }, { "epoch": 8.0, "learning_rate": 2.9344677548984285e-06, "loss": 0.8296, "step": 96260 }, { "epoch": 8.0, "learning_rate": 2.934356899370895e-06, "loss": 0.7334, "step": 96270 }, { "epoch": 8.0, "learning_rate": 2.934246043843361e-06, "loss": 0.8431, "step": 96280 }, { "epoch": 8.0, "learning_rate": 2.934135188315827e-06, "loss": 0.7719, "step": 96290 }, { "epoch": 8.0, "learning_rate": 2.9340243327882937e-06, "loss": 0.7733, "step": 96300 }, { "epoch": 8.01, "learning_rate": 2.9339134772607596e-06, "loss": 0.8221, "step": 96310 }, { "epoch": 8.01, "learning_rate": 2.9338026217332263e-06, "loss": 0.7668, "step": 96320 }, { "epoch": 8.01, "learning_rate": 2.933691766205692e-06, "loss": 0.8323, "step": 96330 }, { "epoch": 8.01, "learning_rate": 2.9335809106781585e-06, "loss": 0.7949, "step": 96340 }, { "epoch": 8.01, "learning_rate": 2.9334700551506248e-06, "loss": 0.7865, "step": 96350 }, { "epoch": 8.01, "learning_rate": 2.933359199623091e-06, "loss": 0.8466, "step": 96360 }, { "epoch": 8.01, "learning_rate": 2.9332483440955573e-06, "loss": 0.7833, "step": 96370 }, { "epoch": 8.01, "learning_rate": 2.9331374885680236e-06, "loss": 0.8147, "step": 96380 }, { "epoch": 8.01, "learning_rate": 2.93302663304049e-06, "loss": 0.7931, "step": 96390 }, { "epoch": 8.01, "learning_rate": 2.9329157775129562e-06, "loss": 0.8458, "step": 96400 }, { "epoch": 8.01, "learning_rate": 2.9328049219854225e-06, "loss": 0.84, "step": 96410 }, { "epoch": 8.01, "learning_rate": 2.9326940664578884e-06, "loss": 0.7704, "step": 96420 }, { "epoch": 8.02, "learning_rate": 2.932583210930355e-06, "loss": 0.8224, "step": 96430 }, { "epoch": 8.02, "learning_rate": 2.932472355402821e-06, "loss": 0.7644, "step": 96440 }, { "epoch": 8.02, "learning_rate": 2.9323614998752873e-06, "loss": 0.8275, "step": 96450 }, { "epoch": 8.02, "learning_rate": 2.9322506443477536e-06, "loss": 0.8402, "step": 96460 }, { "epoch": 8.02, "learning_rate": 2.93213978882022e-06, "loss": 0.8644, "step": 96470 }, { "epoch": 8.02, "learning_rate": 2.932028933292686e-06, "loss": 0.7862, "step": 96480 }, { "epoch": 8.02, "learning_rate": 2.9319180777651525e-06, "loss": 0.7873, "step": 96490 }, { "epoch": 8.02, "learning_rate": 2.9318072222376188e-06, "loss": 0.7092, "step": 96500 }, { "epoch": 8.02, "learning_rate": 2.931696366710085e-06, "loss": 0.839, "step": 96510 }, { "epoch": 8.02, "learning_rate": 2.9315855111825514e-06, "loss": 0.8571, "step": 96520 }, { "epoch": 8.02, "learning_rate": 2.9314746556550172e-06, "loss": 0.7882, "step": 96530 }, { "epoch": 8.02, "learning_rate": 2.931363800127484e-06, "loss": 0.7976, "step": 96540 }, { "epoch": 8.03, "learning_rate": 2.93125294459995e-06, "loss": 0.8191, "step": 96550 }, { "epoch": 8.03, "learning_rate": 2.9311420890724165e-06, "loss": 0.8371, "step": 96560 }, { "epoch": 8.03, "learning_rate": 2.9310312335448824e-06, "loss": 0.8128, "step": 96570 }, { "epoch": 8.03, "learning_rate": 2.9309203780173487e-06, "loss": 0.8406, "step": 96580 }, { "epoch": 8.03, "learning_rate": 2.930809522489815e-06, "loss": 0.7676, "step": 96590 }, { "epoch": 8.03, "learning_rate": 2.9306986669622813e-06, "loss": 0.8369, "step": 96600 }, { "epoch": 8.03, "learning_rate": 2.930587811434747e-06, "loss": 0.861, "step": 96610 }, { "epoch": 8.03, "learning_rate": 2.930476955907214e-06, "loss": 0.8655, "step": 96620 }, { "epoch": 8.03, "learning_rate": 2.93036610037968e-06, "loss": 0.8361, "step": 96630 }, { "epoch": 8.03, "learning_rate": 2.930255244852146e-06, "loss": 0.784, "step": 96640 }, { "epoch": 8.03, "learning_rate": 2.9301443893246128e-06, "loss": 0.8153, "step": 96650 }, { "epoch": 8.03, "learning_rate": 2.9300335337970786e-06, "loss": 0.8729, "step": 96660 }, { "epoch": 8.04, "learning_rate": 2.9299226782695454e-06, "loss": 0.8427, "step": 96670 }, { "epoch": 8.04, "learning_rate": 2.9298118227420112e-06, "loss": 0.7438, "step": 96680 }, { "epoch": 8.04, "learning_rate": 2.9297009672144775e-06, "loss": 0.7532, "step": 96690 }, { "epoch": 8.04, "learning_rate": 2.929590111686944e-06, "loss": 0.7952, "step": 96700 }, { "epoch": 8.04, "learning_rate": 2.92947925615941e-06, "loss": 0.8098, "step": 96710 }, { "epoch": 8.04, "learning_rate": 2.929368400631876e-06, "loss": 0.8334, "step": 96720 }, { "epoch": 8.04, "learning_rate": 2.9292575451043427e-06, "loss": 0.757, "step": 96730 }, { "epoch": 8.04, "learning_rate": 2.929146689576809e-06, "loss": 0.7743, "step": 96740 }, { "epoch": 8.04, "learning_rate": 2.9290358340492753e-06, "loss": 0.7436, "step": 96750 }, { "epoch": 8.04, "learning_rate": 2.9289249785217416e-06, "loss": 0.8337, "step": 96760 }, { "epoch": 8.04, "learning_rate": 2.9288141229942075e-06, "loss": 0.8093, "step": 96770 }, { "epoch": 8.04, "learning_rate": 2.928703267466674e-06, "loss": 0.7911, "step": 96780 }, { "epoch": 8.05, "learning_rate": 2.92859241193914e-06, "loss": 0.8313, "step": 96790 }, { "epoch": 8.05, "learning_rate": 2.9284815564116064e-06, "loss": 0.768, "step": 96800 }, { "epoch": 8.05, "learning_rate": 2.9283707008840726e-06, "loss": 0.8332, "step": 96810 }, { "epoch": 8.05, "learning_rate": 2.928259845356539e-06, "loss": 0.7938, "step": 96820 }, { "epoch": 8.05, "learning_rate": 2.9281489898290052e-06, "loss": 0.8409, "step": 96830 }, { "epoch": 8.05, "learning_rate": 2.9280381343014715e-06, "loss": 0.7562, "step": 96840 }, { "epoch": 8.05, "learning_rate": 2.9279272787739374e-06, "loss": 0.8015, "step": 96850 }, { "epoch": 8.05, "learning_rate": 2.927816423246404e-06, "loss": 0.7811, "step": 96860 }, { "epoch": 8.05, "learning_rate": 2.9277055677188704e-06, "loss": 0.8279, "step": 96870 }, { "epoch": 8.05, "learning_rate": 2.9275947121913363e-06, "loss": 0.7776, "step": 96880 }, { "epoch": 8.05, "learning_rate": 2.927483856663803e-06, "loss": 0.7832, "step": 96890 }, { "epoch": 8.05, "learning_rate": 2.927373001136269e-06, "loss": 0.7762, "step": 96900 }, { "epoch": 8.06, "learning_rate": 2.9272621456087356e-06, "loss": 0.8851, "step": 96910 }, { "epoch": 8.06, "learning_rate": 2.9271512900812015e-06, "loss": 0.8282, "step": 96920 }, { "epoch": 8.06, "learning_rate": 2.9270404345536678e-06, "loss": 0.8444, "step": 96930 }, { "epoch": 8.06, "learning_rate": 2.926929579026134e-06, "loss": 0.7775, "step": 96940 }, { "epoch": 8.06, "learning_rate": 2.9268187234986004e-06, "loss": 0.7936, "step": 96950 }, { "epoch": 8.06, "learning_rate": 2.9267078679710662e-06, "loss": 0.8815, "step": 96960 }, { "epoch": 8.06, "learning_rate": 2.926597012443533e-06, "loss": 0.7876, "step": 96970 }, { "epoch": 8.06, "learning_rate": 2.926486156915999e-06, "loss": 0.807, "step": 96980 }, { "epoch": 8.06, "learning_rate": 2.9263753013884655e-06, "loss": 0.768, "step": 96990 }, { "epoch": 8.06, "learning_rate": 2.926264445860932e-06, "loss": 0.8156, "step": 97000 }, { "epoch": 8.06, "learning_rate": 2.9261535903333977e-06, "loss": 0.8657, "step": 97010 }, { "epoch": 8.06, "learning_rate": 2.9260427348058644e-06, "loss": 0.785, "step": 97020 }, { "epoch": 8.06, "learning_rate": 2.9259318792783303e-06, "loss": 0.7675, "step": 97030 }, { "epoch": 8.07, "learning_rate": 2.9258210237507966e-06, "loss": 0.8365, "step": 97040 }, { "epoch": 8.07, "learning_rate": 2.925710168223263e-06, "loss": 0.8458, "step": 97050 }, { "epoch": 8.07, "learning_rate": 2.925599312695729e-06, "loss": 0.8165, "step": 97060 }, { "epoch": 8.07, "learning_rate": 2.925488457168195e-06, "loss": 0.7449, "step": 97070 }, { "epoch": 8.07, "learning_rate": 2.9253776016406618e-06, "loss": 0.8135, "step": 97080 }, { "epoch": 8.07, "learning_rate": 2.9252667461131276e-06, "loss": 0.8134, "step": 97090 }, { "epoch": 8.07, "learning_rate": 2.9251558905855944e-06, "loss": 0.8199, "step": 97100 }, { "epoch": 8.07, "learning_rate": 2.9250450350580607e-06, "loss": 0.8346, "step": 97110 }, { "epoch": 8.07, "learning_rate": 2.9249341795305265e-06, "loss": 0.8334, "step": 97120 }, { "epoch": 8.07, "learning_rate": 2.9248233240029933e-06, "loss": 0.8907, "step": 97130 }, { "epoch": 8.07, "learning_rate": 2.924712468475459e-06, "loss": 0.8316, "step": 97140 }, { "epoch": 8.07, "learning_rate": 2.9246016129479254e-06, "loss": 0.7835, "step": 97150 }, { "epoch": 8.08, "learning_rate": 2.9244907574203917e-06, "loss": 0.8373, "step": 97160 }, { "epoch": 8.08, "learning_rate": 2.924379901892858e-06, "loss": 0.7547, "step": 97170 }, { "epoch": 8.08, "learning_rate": 2.9242690463653243e-06, "loss": 0.8401, "step": 97180 }, { "epoch": 8.08, "learning_rate": 2.9241581908377906e-06, "loss": 0.7739, "step": 97190 }, { "epoch": 8.08, "learning_rate": 2.9240473353102565e-06, "loss": 0.8179, "step": 97200 }, { "epoch": 8.08, "learning_rate": 2.923936479782723e-06, "loss": 0.8129, "step": 97210 }, { "epoch": 8.08, "learning_rate": 2.923825624255189e-06, "loss": 0.8002, "step": 97220 }, { "epoch": 8.08, "learning_rate": 2.9237147687276554e-06, "loss": 0.7436, "step": 97230 }, { "epoch": 8.08, "learning_rate": 2.923603913200122e-06, "loss": 0.7766, "step": 97240 }, { "epoch": 8.08, "learning_rate": 2.923493057672588e-06, "loss": 0.8274, "step": 97250 }, { "epoch": 8.08, "learning_rate": 2.9233822021450547e-06, "loss": 0.7932, "step": 97260 }, { "epoch": 8.08, "learning_rate": 2.9232713466175205e-06, "loss": 0.7544, "step": 97270 }, { "epoch": 8.09, "learning_rate": 2.923160491089987e-06, "loss": 0.8627, "step": 97280 }, { "epoch": 8.09, "learning_rate": 2.923049635562453e-06, "loss": 0.764, "step": 97290 }, { "epoch": 8.09, "learning_rate": 2.9229387800349194e-06, "loss": 0.8634, "step": 97300 }, { "epoch": 8.09, "learning_rate": 2.9228279245073853e-06, "loss": 0.8286, "step": 97310 }, { "epoch": 8.09, "learning_rate": 2.922717068979852e-06, "loss": 0.7866, "step": 97320 }, { "epoch": 8.09, "learning_rate": 2.922606213452318e-06, "loss": 0.8196, "step": 97330 }, { "epoch": 8.09, "learning_rate": 2.9224953579247846e-06, "loss": 0.8445, "step": 97340 }, { "epoch": 8.09, "learning_rate": 2.922384502397251e-06, "loss": 0.7915, "step": 97350 }, { "epoch": 8.09, "learning_rate": 2.9222736468697168e-06, "loss": 0.8627, "step": 97360 }, { "epoch": 8.09, "learning_rate": 2.9221627913421835e-06, "loss": 0.7511, "step": 97370 }, { "epoch": 8.09, "learning_rate": 2.9220519358146494e-06, "loss": 0.8636, "step": 97380 }, { "epoch": 8.09, "learning_rate": 2.9219410802871157e-06, "loss": 0.7886, "step": 97390 }, { "epoch": 8.1, "learning_rate": 2.921830224759582e-06, "loss": 0.8583, "step": 97400 }, { "epoch": 8.1, "learning_rate": 2.9217193692320482e-06, "loss": 0.79, "step": 97410 }, { "epoch": 8.1, "learning_rate": 2.921608513704514e-06, "loss": 0.8012, "step": 97420 }, { "epoch": 8.1, "learning_rate": 2.921497658176981e-06, "loss": 0.8513, "step": 97430 }, { "epoch": 8.1, "learning_rate": 2.9213868026494467e-06, "loss": 0.7511, "step": 97440 }, { "epoch": 8.1, "learning_rate": 2.9212759471219134e-06, "loss": 0.8843, "step": 97450 }, { "epoch": 8.1, "learning_rate": 2.9211650915943793e-06, "loss": 0.8914, "step": 97460 }, { "epoch": 8.1, "learning_rate": 2.9210542360668456e-06, "loss": 0.8296, "step": 97470 }, { "epoch": 8.1, "learning_rate": 2.9209433805393123e-06, "loss": 0.734, "step": 97480 }, { "epoch": 8.1, "learning_rate": 2.920832525011778e-06, "loss": 0.7603, "step": 97490 }, { "epoch": 8.1, "learning_rate": 2.920721669484245e-06, "loss": 0.7873, "step": 97500 }, { "epoch": 8.1, "learning_rate": 2.9206108139567108e-06, "loss": 0.7857, "step": 97510 }, { "epoch": 8.11, "learning_rate": 2.920499958429177e-06, "loss": 0.7897, "step": 97520 }, { "epoch": 8.11, "learning_rate": 2.9203891029016434e-06, "loss": 0.7179, "step": 97530 }, { "epoch": 8.11, "learning_rate": 2.9202782473741097e-06, "loss": 0.7882, "step": 97540 }, { "epoch": 8.11, "learning_rate": 2.9201673918465755e-06, "loss": 0.7835, "step": 97550 }, { "epoch": 8.11, "learning_rate": 2.9200565363190423e-06, "loss": 0.8369, "step": 97560 }, { "epoch": 8.11, "learning_rate": 2.919945680791508e-06, "loss": 0.7552, "step": 97570 }, { "epoch": 8.11, "learning_rate": 2.9198348252639744e-06, "loss": 0.8081, "step": 97580 }, { "epoch": 8.11, "learning_rate": 2.9197239697364407e-06, "loss": 0.8217, "step": 97590 }, { "epoch": 8.11, "learning_rate": 2.919613114208907e-06, "loss": 0.7935, "step": 97600 }, { "epoch": 8.11, "learning_rate": 2.9195022586813737e-06, "loss": 0.8394, "step": 97610 }, { "epoch": 8.11, "learning_rate": 2.9193914031538396e-06, "loss": 0.8317, "step": 97620 }, { "epoch": 8.11, "learning_rate": 2.919280547626306e-06, "loss": 0.8555, "step": 97630 }, { "epoch": 8.12, "learning_rate": 2.919169692098772e-06, "loss": 0.7958, "step": 97640 }, { "epoch": 8.12, "learning_rate": 2.9190588365712385e-06, "loss": 0.8154, "step": 97650 }, { "epoch": 8.12, "learning_rate": 2.9189479810437044e-06, "loss": 0.8547, "step": 97660 }, { "epoch": 8.12, "learning_rate": 2.918837125516171e-06, "loss": 0.7451, "step": 97670 }, { "epoch": 8.12, "learning_rate": 2.918726269988637e-06, "loss": 0.8323, "step": 97680 }, { "epoch": 8.12, "learning_rate": 2.9186154144611037e-06, "loss": 0.8617, "step": 97690 }, { "epoch": 8.12, "learning_rate": 2.9185045589335695e-06, "loss": 0.8626, "step": 97700 }, { "epoch": 8.12, "learning_rate": 2.918393703406036e-06, "loss": 0.8502, "step": 97710 }, { "epoch": 8.12, "learning_rate": 2.9182828478785026e-06, "loss": 0.7739, "step": 97720 }, { "epoch": 8.12, "learning_rate": 2.9181719923509684e-06, "loss": 0.8385, "step": 97730 }, { "epoch": 8.12, "learning_rate": 2.9180611368234347e-06, "loss": 0.7524, "step": 97740 }, { "epoch": 8.12, "learning_rate": 2.917950281295901e-06, "loss": 0.7744, "step": 97750 }, { "epoch": 8.13, "learning_rate": 2.9178394257683673e-06, "loss": 0.8644, "step": 97760 }, { "epoch": 8.13, "learning_rate": 2.9177285702408336e-06, "loss": 0.7702, "step": 97770 }, { "epoch": 8.13, "learning_rate": 2.9176177147133e-06, "loss": 0.8038, "step": 97780 }, { "epoch": 8.13, "learning_rate": 2.9175068591857658e-06, "loss": 0.8489, "step": 97790 }, { "epoch": 8.13, "learning_rate": 2.9173960036582325e-06, "loss": 0.8105, "step": 97800 }, { "epoch": 8.13, "learning_rate": 2.9172851481306984e-06, "loss": 0.8166, "step": 97810 }, { "epoch": 8.13, "learning_rate": 2.9171742926031647e-06, "loss": 0.8061, "step": 97820 }, { "epoch": 8.13, "learning_rate": 2.917063437075631e-06, "loss": 0.7953, "step": 97830 }, { "epoch": 8.13, "learning_rate": 2.9169525815480973e-06, "loss": 0.7775, "step": 97840 }, { "epoch": 8.13, "learning_rate": 2.916841726020564e-06, "loss": 0.842, "step": 97850 }, { "epoch": 8.13, "learning_rate": 2.91673087049303e-06, "loss": 0.8016, "step": 97860 }, { "epoch": 8.13, "learning_rate": 2.916620014965496e-06, "loss": 0.7562, "step": 97870 }, { "epoch": 8.14, "learning_rate": 2.9165091594379624e-06, "loss": 0.7142, "step": 97880 }, { "epoch": 8.14, "learning_rate": 2.9163983039104287e-06, "loss": 0.8027, "step": 97890 }, { "epoch": 8.14, "learning_rate": 2.9162874483828946e-06, "loss": 0.7857, "step": 97900 }, { "epoch": 8.14, "learning_rate": 2.9161765928553613e-06, "loss": 0.8269, "step": 97910 }, { "epoch": 8.14, "learning_rate": 2.916065737327827e-06, "loss": 0.802, "step": 97920 }, { "epoch": 8.14, "learning_rate": 2.9159548818002935e-06, "loss": 0.8836, "step": 97930 }, { "epoch": 8.14, "learning_rate": 2.9158440262727598e-06, "loss": 0.7724, "step": 97940 }, { "epoch": 8.14, "learning_rate": 2.915733170745226e-06, "loss": 0.7514, "step": 97950 }, { "epoch": 8.14, "learning_rate": 2.9156223152176924e-06, "loss": 0.8523, "step": 97960 }, { "epoch": 8.14, "learning_rate": 2.9155114596901587e-06, "loss": 0.7355, "step": 97970 }, { "epoch": 8.14, "learning_rate": 2.915400604162625e-06, "loss": 0.9145, "step": 97980 }, { "epoch": 8.14, "learning_rate": 2.9152897486350913e-06, "loss": 0.7769, "step": 97990 }, { "epoch": 8.15, "learning_rate": 2.9151788931075576e-06, "loss": 0.8203, "step": 98000 }, { "epoch": 8.15, "learning_rate": 2.9150680375800234e-06, "loss": 0.7714, "step": 98010 }, { "epoch": 8.15, "learning_rate": 2.91495718205249e-06, "loss": 0.8514, "step": 98020 }, { "epoch": 8.15, "learning_rate": 2.914846326524956e-06, "loss": 0.7982, "step": 98030 }, { "epoch": 8.15, "learning_rate": 2.9147354709974227e-06, "loss": 0.8259, "step": 98040 }, { "epoch": 8.15, "learning_rate": 2.9146246154698886e-06, "loss": 0.8166, "step": 98050 }, { "epoch": 8.15, "learning_rate": 2.914513759942355e-06, "loss": 0.8495, "step": 98060 }, { "epoch": 8.15, "learning_rate": 2.914402904414821e-06, "loss": 0.8282, "step": 98070 }, { "epoch": 8.15, "learning_rate": 2.9142920488872875e-06, "loss": 0.8241, "step": 98080 }, { "epoch": 8.15, "learning_rate": 2.914181193359754e-06, "loss": 0.8033, "step": 98090 }, { "epoch": 8.15, "learning_rate": 2.91407033783222e-06, "loss": 0.8441, "step": 98100 }, { "epoch": 8.15, "learning_rate": 2.9139594823046864e-06, "loss": 0.8845, "step": 98110 }, { "epoch": 8.16, "learning_rate": 2.9138486267771527e-06, "loss": 0.7876, "step": 98120 }, { "epoch": 8.16, "learning_rate": 2.913737771249619e-06, "loss": 0.8467, "step": 98130 }, { "epoch": 8.16, "learning_rate": 2.913626915722085e-06, "loss": 0.8415, "step": 98140 }, { "epoch": 8.16, "learning_rate": 2.9135160601945516e-06, "loss": 0.8236, "step": 98150 }, { "epoch": 8.16, "learning_rate": 2.9134052046670174e-06, "loss": 0.8594, "step": 98160 }, { "epoch": 8.16, "learning_rate": 2.9132943491394837e-06, "loss": 0.83, "step": 98170 }, { "epoch": 8.16, "learning_rate": 2.91318349361195e-06, "loss": 0.7312, "step": 98180 }, { "epoch": 8.16, "learning_rate": 2.9130726380844163e-06, "loss": 0.7445, "step": 98190 }, { "epoch": 8.16, "learning_rate": 2.9129617825568826e-06, "loss": 0.7737, "step": 98200 }, { "epoch": 8.16, "learning_rate": 2.912850927029349e-06, "loss": 0.8236, "step": 98210 }, { "epoch": 8.16, "learning_rate": 2.912740071501815e-06, "loss": 0.7702, "step": 98220 }, { "epoch": 8.16, "learning_rate": 2.9126292159742815e-06, "loss": 0.7664, "step": 98230 }, { "epoch": 8.17, "learning_rate": 2.912518360446748e-06, "loss": 0.8241, "step": 98240 }, { "epoch": 8.17, "learning_rate": 2.9124075049192137e-06, "loss": 0.8151, "step": 98250 }, { "epoch": 8.17, "learning_rate": 2.9122966493916804e-06, "loss": 0.8487, "step": 98260 }, { "epoch": 8.17, "learning_rate": 2.9121857938641463e-06, "loss": 0.8443, "step": 98270 }, { "epoch": 8.17, "learning_rate": 2.912074938336613e-06, "loss": 0.8667, "step": 98280 }, { "epoch": 8.17, "learning_rate": 2.911964082809079e-06, "loss": 0.7904, "step": 98290 }, { "epoch": 8.17, "learning_rate": 2.911853227281545e-06, "loss": 0.9137, "step": 98300 }, { "epoch": 8.17, "learning_rate": 2.9117423717540114e-06, "loss": 0.8452, "step": 98310 }, { "epoch": 8.17, "learning_rate": 2.9116315162264777e-06, "loss": 0.8084, "step": 98320 }, { "epoch": 8.17, "learning_rate": 2.9115206606989436e-06, "loss": 0.744, "step": 98330 }, { "epoch": 8.17, "learning_rate": 2.9114098051714103e-06, "loss": 0.7902, "step": 98340 }, { "epoch": 8.17, "learning_rate": 2.9112989496438766e-06, "loss": 0.8468, "step": 98350 }, { "epoch": 8.18, "learning_rate": 2.9111880941163425e-06, "loss": 0.8539, "step": 98360 }, { "epoch": 8.18, "learning_rate": 2.9110772385888092e-06, "loss": 0.7336, "step": 98370 }, { "epoch": 8.18, "learning_rate": 2.910966383061275e-06, "loss": 0.8089, "step": 98380 }, { "epoch": 8.18, "learning_rate": 2.910855527533742e-06, "loss": 0.8374, "step": 98390 }, { "epoch": 8.18, "learning_rate": 2.9107446720062077e-06, "loss": 0.8508, "step": 98400 }, { "epoch": 8.18, "learning_rate": 2.910633816478674e-06, "loss": 0.7739, "step": 98410 }, { "epoch": 8.18, "learning_rate": 2.9105229609511403e-06, "loss": 0.7492, "step": 98420 }, { "epoch": 8.18, "learning_rate": 2.9104121054236066e-06, "loss": 0.7995, "step": 98430 }, { "epoch": 8.18, "learning_rate": 2.9103012498960724e-06, "loss": 0.8045, "step": 98440 }, { "epoch": 8.18, "learning_rate": 2.910190394368539e-06, "loss": 0.8448, "step": 98450 }, { "epoch": 8.18, "learning_rate": 2.9100795388410054e-06, "loss": 0.9034, "step": 98460 }, { "epoch": 8.18, "learning_rate": 2.9099686833134717e-06, "loss": 0.8054, "step": 98470 }, { "epoch": 8.19, "learning_rate": 2.909857827785938e-06, "loss": 0.7643, "step": 98480 }, { "epoch": 8.19, "learning_rate": 2.909746972258404e-06, "loss": 0.8477, "step": 98490 }, { "epoch": 8.19, "learning_rate": 2.9096361167308706e-06, "loss": 0.8207, "step": 98500 }, { "epoch": 8.19, "learning_rate": 2.9095252612033365e-06, "loss": 0.9095, "step": 98510 }, { "epoch": 8.19, "learning_rate": 2.909414405675803e-06, "loss": 0.7577, "step": 98520 }, { "epoch": 8.19, "learning_rate": 2.909303550148269e-06, "loss": 0.7445, "step": 98530 }, { "epoch": 8.19, "learning_rate": 2.9091926946207354e-06, "loss": 0.8656, "step": 98540 }, { "epoch": 8.19, "learning_rate": 2.9090818390932017e-06, "loss": 0.8491, "step": 98550 }, { "epoch": 8.19, "learning_rate": 2.908970983565668e-06, "loss": 0.8256, "step": 98560 }, { "epoch": 8.19, "learning_rate": 2.908860128038134e-06, "loss": 0.7411, "step": 98570 }, { "epoch": 8.19, "learning_rate": 2.9087492725106006e-06, "loss": 0.7502, "step": 98580 }, { "epoch": 8.19, "learning_rate": 2.908638416983067e-06, "loss": 0.8142, "step": 98590 }, { "epoch": 8.2, "learning_rate": 2.9085275614555327e-06, "loss": 0.7901, "step": 98600 }, { "epoch": 8.2, "learning_rate": 2.9084167059279995e-06, "loss": 0.8522, "step": 98610 }, { "epoch": 8.2, "learning_rate": 2.9083058504004653e-06, "loss": 0.8298, "step": 98620 }, { "epoch": 8.2, "learning_rate": 2.908194994872932e-06, "loss": 0.9048, "step": 98630 }, { "epoch": 8.2, "learning_rate": 2.908084139345398e-06, "loss": 0.8112, "step": 98640 }, { "epoch": 8.2, "learning_rate": 2.9079732838178642e-06, "loss": 0.8566, "step": 98650 }, { "epoch": 8.2, "learning_rate": 2.9078624282903305e-06, "loss": 0.7893, "step": 98660 }, { "epoch": 8.2, "learning_rate": 2.907751572762797e-06, "loss": 0.8185, "step": 98670 }, { "epoch": 8.2, "learning_rate": 2.9076407172352627e-06, "loss": 0.7702, "step": 98680 }, { "epoch": 8.2, "learning_rate": 2.9075298617077294e-06, "loss": 0.827, "step": 98690 }, { "epoch": 8.2, "learning_rate": 2.9074190061801953e-06, "loss": 0.8904, "step": 98700 }, { "epoch": 8.2, "learning_rate": 2.9073081506526616e-06, "loss": 0.8721, "step": 98710 }, { "epoch": 8.21, "learning_rate": 2.9071972951251283e-06, "loss": 0.8115, "step": 98720 }, { "epoch": 8.21, "learning_rate": 2.907086439597594e-06, "loss": 0.7929, "step": 98730 }, { "epoch": 8.21, "learning_rate": 2.906975584070061e-06, "loss": 0.7457, "step": 98740 }, { "epoch": 8.21, "learning_rate": 2.9068647285425267e-06, "loss": 0.846, "step": 98750 }, { "epoch": 8.21, "learning_rate": 2.906753873014993e-06, "loss": 0.8146, "step": 98760 }, { "epoch": 8.21, "learning_rate": 2.9066430174874593e-06, "loss": 0.7787, "step": 98770 }, { "epoch": 8.21, "learning_rate": 2.9065321619599256e-06, "loss": 0.775, "step": 98780 }, { "epoch": 8.21, "learning_rate": 2.9064213064323915e-06, "loss": 0.8327, "step": 98790 }, { "epoch": 8.21, "learning_rate": 2.9063104509048582e-06, "loss": 0.7721, "step": 98800 }, { "epoch": 8.21, "learning_rate": 2.906199595377324e-06, "loss": 0.8052, "step": 98810 }, { "epoch": 8.21, "learning_rate": 2.906088739849791e-06, "loss": 0.7787, "step": 98820 }, { "epoch": 8.21, "learning_rate": 2.905977884322257e-06, "loss": 0.7325, "step": 98830 }, { "epoch": 8.22, "learning_rate": 2.905867028794723e-06, "loss": 0.7674, "step": 98840 }, { "epoch": 8.22, "learning_rate": 2.9057561732671897e-06, "loss": 0.7748, "step": 98850 }, { "epoch": 8.22, "learning_rate": 2.9056453177396556e-06, "loss": 0.7966, "step": 98860 }, { "epoch": 8.22, "learning_rate": 2.905534462212122e-06, "loss": 0.8596, "step": 98870 }, { "epoch": 8.22, "learning_rate": 2.905423606684588e-06, "loss": 0.7571, "step": 98880 }, { "epoch": 8.22, "learning_rate": 2.9053127511570545e-06, "loss": 0.7565, "step": 98890 }, { "epoch": 8.22, "learning_rate": 2.9052018956295207e-06, "loss": 0.7588, "step": 98900 }, { "epoch": 8.22, "learning_rate": 2.905091040101987e-06, "loss": 0.8621, "step": 98910 }, { "epoch": 8.22, "learning_rate": 2.904980184574453e-06, "loss": 0.7945, "step": 98920 }, { "epoch": 8.22, "learning_rate": 2.9048693290469196e-06, "loss": 0.7862, "step": 98930 }, { "epoch": 8.22, "learning_rate": 2.9047584735193855e-06, "loss": 0.823, "step": 98940 }, { "epoch": 8.22, "learning_rate": 2.904647617991852e-06, "loss": 0.7715, "step": 98950 }, { "epoch": 8.23, "learning_rate": 2.9045367624643185e-06, "loss": 0.8475, "step": 98960 }, { "epoch": 8.23, "learning_rate": 2.9044259069367844e-06, "loss": 0.7476, "step": 98970 }, { "epoch": 8.23, "learning_rate": 2.904315051409251e-06, "loss": 0.8314, "step": 98980 }, { "epoch": 8.23, "learning_rate": 2.904204195881717e-06, "loss": 0.7661, "step": 98990 }, { "epoch": 8.23, "learning_rate": 2.9040933403541833e-06, "loss": 0.8059, "step": 99000 }, { "epoch": 8.23, "learning_rate": 2.9039824848266496e-06, "loss": 0.9202, "step": 99010 }, { "epoch": 8.23, "learning_rate": 2.903871629299116e-06, "loss": 0.7469, "step": 99020 }, { "epoch": 8.23, "learning_rate": 2.9037607737715817e-06, "loss": 0.7837, "step": 99030 }, { "epoch": 8.23, "learning_rate": 2.9036499182440485e-06, "loss": 0.8021, "step": 99040 }, { "epoch": 8.23, "learning_rate": 2.9035390627165143e-06, "loss": 0.8344, "step": 99050 }, { "epoch": 8.23, "learning_rate": 2.903428207188981e-06, "loss": 0.8148, "step": 99060 }, { "epoch": 8.23, "learning_rate": 2.903317351661447e-06, "loss": 0.802, "step": 99070 }, { "epoch": 8.24, "learning_rate": 2.9032064961339132e-06, "loss": 0.7996, "step": 99080 }, { "epoch": 8.24, "learning_rate": 2.90309564060638e-06, "loss": 0.8502, "step": 99090 }, { "epoch": 8.24, "learning_rate": 2.902984785078846e-06, "loss": 0.8538, "step": 99100 }, { "epoch": 8.24, "learning_rate": 2.902873929551312e-06, "loss": 0.8509, "step": 99110 }, { "epoch": 8.24, "learning_rate": 2.9027630740237784e-06, "loss": 0.8283, "step": 99120 }, { "epoch": 8.24, "learning_rate": 2.9026522184962447e-06, "loss": 0.7997, "step": 99130 }, { "epoch": 8.24, "learning_rate": 2.9025413629687106e-06, "loss": 0.8241, "step": 99140 }, { "epoch": 8.24, "learning_rate": 2.9024305074411773e-06, "loss": 0.7903, "step": 99150 }, { "epoch": 8.24, "learning_rate": 2.902319651913643e-06, "loss": 0.8557, "step": 99160 }, { "epoch": 8.24, "learning_rate": 2.90220879638611e-06, "loss": 0.7621, "step": 99170 }, { "epoch": 8.24, "learning_rate": 2.9020979408585757e-06, "loss": 0.8201, "step": 99180 }, { "epoch": 8.24, "learning_rate": 2.901987085331042e-06, "loss": 0.8369, "step": 99190 }, { "epoch": 8.25, "learning_rate": 2.9018762298035088e-06, "loss": 0.7914, "step": 99200 }, { "epoch": 8.25, "learning_rate": 2.9017653742759746e-06, "loss": 0.8598, "step": 99210 }, { "epoch": 8.25, "learning_rate": 2.901654518748441e-06, "loss": 0.8477, "step": 99220 }, { "epoch": 8.25, "learning_rate": 2.9015436632209072e-06, "loss": 0.778, "step": 99230 }, { "epoch": 8.25, "learning_rate": 2.9014328076933735e-06, "loss": 0.7614, "step": 99240 }, { "epoch": 8.25, "learning_rate": 2.90132195216584e-06, "loss": 0.8013, "step": 99250 }, { "epoch": 8.25, "learning_rate": 2.901211096638306e-06, "loss": 0.8512, "step": 99260 }, { "epoch": 8.25, "learning_rate": 2.901100241110772e-06, "loss": 0.7389, "step": 99270 }, { "epoch": 8.25, "learning_rate": 2.9009893855832387e-06, "loss": 0.7809, "step": 99280 }, { "epoch": 8.25, "learning_rate": 2.9008785300557046e-06, "loss": 0.8013, "step": 99290 }, { "epoch": 8.25, "learning_rate": 2.900767674528171e-06, "loss": 0.802, "step": 99300 }, { "epoch": 8.25, "learning_rate": 2.900656819000637e-06, "loss": 0.9187, "step": 99310 }, { "epoch": 8.26, "learning_rate": 2.9005459634731035e-06, "loss": 0.8524, "step": 99320 }, { "epoch": 8.26, "learning_rate": 2.90043510794557e-06, "loss": 0.7504, "step": 99330 }, { "epoch": 8.26, "learning_rate": 2.900324252418036e-06, "loss": 0.7814, "step": 99340 }, { "epoch": 8.26, "learning_rate": 2.9002133968905023e-06, "loss": 0.8207, "step": 99350 }, { "epoch": 8.26, "learning_rate": 2.9001025413629686e-06, "loss": 0.7856, "step": 99360 }, { "epoch": 8.26, "learning_rate": 2.899991685835435e-06, "loss": 0.7947, "step": 99370 }, { "epoch": 8.26, "learning_rate": 2.899880830307901e-06, "loss": 0.7769, "step": 99380 }, { "epoch": 8.26, "learning_rate": 2.8997699747803675e-06, "loss": 0.74, "step": 99390 }, { "epoch": 8.26, "learning_rate": 2.8996591192528334e-06, "loss": 0.8526, "step": 99400 }, { "epoch": 8.26, "learning_rate": 2.8995482637253e-06, "loss": 0.8656, "step": 99410 }, { "epoch": 8.26, "learning_rate": 2.899437408197766e-06, "loss": 0.8107, "step": 99420 }, { "epoch": 8.26, "learning_rate": 2.8993265526702323e-06, "loss": 0.7751, "step": 99430 }, { "epoch": 8.27, "learning_rate": 2.899215697142699e-06, "loss": 0.8046, "step": 99440 }, { "epoch": 8.27, "learning_rate": 2.899104841615165e-06, "loss": 0.723, "step": 99450 }, { "epoch": 8.27, "learning_rate": 2.898993986087631e-06, "loss": 0.8551, "step": 99460 }, { "epoch": 8.27, "learning_rate": 2.8988831305600975e-06, "loss": 0.7943, "step": 99470 }, { "epoch": 8.27, "learning_rate": 2.8987722750325638e-06, "loss": 0.7884, "step": 99480 }, { "epoch": 8.27, "learning_rate": 2.89866141950503e-06, "loss": 0.8334, "step": 99490 }, { "epoch": 8.27, "learning_rate": 2.8985505639774964e-06, "loss": 0.8627, "step": 99500 }, { "epoch": 8.27, "learning_rate": 2.8984397084499622e-06, "loss": 0.8556, "step": 99510 }, { "epoch": 8.27, "learning_rate": 2.898328852922429e-06, "loss": 0.8094, "step": 99520 }, { "epoch": 8.27, "learning_rate": 2.898217997394895e-06, "loss": 0.8507, "step": 99530 }, { "epoch": 8.27, "learning_rate": 2.898107141867361e-06, "loss": 0.7987, "step": 99540 }, { "epoch": 8.27, "learning_rate": 2.8979962863398274e-06, "loss": 0.7994, "step": 99550 }, { "epoch": 8.28, "learning_rate": 2.8978854308122937e-06, "loss": 0.8262, "step": 99560 }, { "epoch": 8.28, "learning_rate": 2.8977745752847604e-06, "loss": 0.7825, "step": 99570 }, { "epoch": 8.28, "learning_rate": 2.8976637197572263e-06, "loss": 0.8146, "step": 99580 }, { "epoch": 8.28, "learning_rate": 2.8975528642296926e-06, "loss": 0.8077, "step": 99590 }, { "epoch": 8.28, "learning_rate": 2.897442008702159e-06, "loss": 0.7773, "step": 99600 }, { "epoch": 8.28, "learning_rate": 2.897331153174625e-06, "loss": 0.8637, "step": 99610 }, { "epoch": 8.28, "learning_rate": 2.897220297647091e-06, "loss": 0.8039, "step": 99620 }, { "epoch": 8.28, "learning_rate": 2.8971094421195578e-06, "loss": 0.8228, "step": 99630 }, { "epoch": 8.28, "learning_rate": 2.8969985865920236e-06, "loss": 0.8101, "step": 99640 }, { "epoch": 8.28, "learning_rate": 2.89688773106449e-06, "loss": 0.8174, "step": 99650 }, { "epoch": 8.28, "learning_rate": 2.8967768755369562e-06, "loss": 0.8088, "step": 99660 }, { "epoch": 8.28, "learning_rate": 2.8966660200094225e-06, "loss": 0.7941, "step": 99670 }, { "epoch": 8.29, "learning_rate": 2.896555164481889e-06, "loss": 0.841, "step": 99680 }, { "epoch": 8.29, "learning_rate": 2.896444308954355e-06, "loss": 0.8821, "step": 99690 }, { "epoch": 8.29, "learning_rate": 2.8963334534268214e-06, "loss": 0.8514, "step": 99700 }, { "epoch": 8.29, "learning_rate": 2.8962225978992877e-06, "loss": 0.8502, "step": 99710 }, { "epoch": 8.29, "learning_rate": 2.896111742371754e-06, "loss": 0.7669, "step": 99720 }, { "epoch": 8.29, "learning_rate": 2.89600088684422e-06, "loss": 0.8781, "step": 99730 }, { "epoch": 8.29, "learning_rate": 2.8958900313166866e-06, "loss": 0.8123, "step": 99740 }, { "epoch": 8.29, "learning_rate": 2.8957791757891525e-06, "loss": 0.8391, "step": 99750 }, { "epoch": 8.29, "learning_rate": 2.895668320261619e-06, "loss": 0.8594, "step": 99760 }, { "epoch": 8.29, "learning_rate": 2.895557464734085e-06, "loss": 0.8309, "step": 99770 }, { "epoch": 8.29, "learning_rate": 2.8954466092065514e-06, "loss": 0.7484, "step": 99780 }, { "epoch": 8.29, "learning_rate": 2.8953357536790176e-06, "loss": 0.77, "step": 99790 }, { "epoch": 8.3, "learning_rate": 2.895224898151484e-06, "loss": 0.8131, "step": 99800 }, { "epoch": 8.3, "learning_rate": 2.8951140426239502e-06, "loss": 0.8368, "step": 99810 }, { "epoch": 8.3, "learning_rate": 2.8950031870964165e-06, "loss": 0.7739, "step": 99820 }, { "epoch": 8.3, "learning_rate": 2.894892331568883e-06, "loss": 0.8707, "step": 99830 }, { "epoch": 8.3, "learning_rate": 2.894781476041349e-06, "loss": 0.854, "step": 99840 }, { "epoch": 8.3, "learning_rate": 2.8946706205138154e-06, "loss": 0.8268, "step": 99850 }, { "epoch": 8.3, "learning_rate": 2.8945597649862813e-06, "loss": 0.8139, "step": 99860 }, { "epoch": 8.3, "learning_rate": 2.894448909458748e-06, "loss": 0.7534, "step": 99870 }, { "epoch": 8.3, "learning_rate": 2.894338053931214e-06, "loss": 0.76, "step": 99880 }, { "epoch": 8.3, "learning_rate": 2.89422719840368e-06, "loss": 0.823, "step": 99890 }, { "epoch": 8.3, "learning_rate": 2.8941163428761465e-06, "loss": 0.7882, "step": 99900 }, { "epoch": 8.3, "learning_rate": 2.8940054873486128e-06, "loss": 0.8718, "step": 99910 }, { "epoch": 8.31, "learning_rate": 2.8938946318210786e-06, "loss": 0.751, "step": 99920 }, { "epoch": 8.31, "learning_rate": 2.8937837762935454e-06, "loss": 0.7801, "step": 99930 }, { "epoch": 8.31, "learning_rate": 2.8936729207660117e-06, "loss": 0.7658, "step": 99940 }, { "epoch": 8.31, "learning_rate": 2.893562065238478e-06, "loss": 0.8342, "step": 99950 }, { "epoch": 8.31, "learning_rate": 2.8934512097109442e-06, "loss": 0.8182, "step": 99960 }, { "epoch": 8.31, "learning_rate": 2.89334035418341e-06, "loss": 0.8237, "step": 99970 }, { "epoch": 8.31, "learning_rate": 2.893229498655877e-06, "loss": 0.7283, "step": 99980 }, { "epoch": 8.31, "learning_rate": 2.8931186431283427e-06, "loss": 0.8055, "step": 99990 }, { "epoch": 8.31, "learning_rate": 2.893007787600809e-06, "loss": 0.8077, "step": 100000 }, { "epoch": 8.31, "learning_rate": 2.8928969320732753e-06, "loss": 0.7809, "step": 100010 }, { "epoch": 8.31, "learning_rate": 2.8927860765457416e-06, "loss": 0.7134, "step": 100020 }, { "epoch": 8.31, "learning_rate": 2.892675221018208e-06, "loss": 0.7527, "step": 100030 }, { "epoch": 8.32, "learning_rate": 2.892564365490674e-06, "loss": 0.7703, "step": 100040 }, { "epoch": 8.32, "learning_rate": 2.89245350996314e-06, "loss": 0.8479, "step": 100050 }, { "epoch": 8.32, "learning_rate": 2.8923426544356068e-06, "loss": 0.8999, "step": 100060 }, { "epoch": 8.32, "learning_rate": 2.892231798908073e-06, "loss": 0.7828, "step": 100070 }, { "epoch": 8.32, "learning_rate": 2.892120943380539e-06, "loss": 0.864, "step": 100080 }, { "epoch": 8.32, "learning_rate": 2.8920100878530057e-06, "loss": 0.811, "step": 100090 }, { "epoch": 8.32, "learning_rate": 2.8918992323254715e-06, "loss": 0.7735, "step": 100100 }, { "epoch": 8.32, "learning_rate": 2.8917883767979383e-06, "loss": 0.8276, "step": 100110 }, { "epoch": 8.32, "learning_rate": 2.891677521270404e-06, "loss": 0.8122, "step": 100120 }, { "epoch": 8.32, "learning_rate": 2.8915666657428704e-06, "loss": 0.8361, "step": 100130 }, { "epoch": 8.32, "learning_rate": 2.8914558102153367e-06, "loss": 0.7882, "step": 100140 }, { "epoch": 8.32, "learning_rate": 2.891344954687803e-06, "loss": 0.7939, "step": 100150 }, { "epoch": 8.33, "learning_rate": 2.891234099160269e-06, "loss": 0.7824, "step": 100160 }, { "epoch": 8.33, "learning_rate": 2.8911232436327356e-06, "loss": 0.7726, "step": 100170 }, { "epoch": 8.33, "learning_rate": 2.891012388105202e-06, "loss": 0.7889, "step": 100180 }, { "epoch": 8.33, "learning_rate": 2.890901532577668e-06, "loss": 0.8466, "step": 100190 }, { "epoch": 8.33, "learning_rate": 2.8907906770501345e-06, "loss": 0.7974, "step": 100200 }, { "epoch": 8.33, "learning_rate": 2.8906798215226004e-06, "loss": 0.8674, "step": 100210 }, { "epoch": 8.33, "learning_rate": 2.890568965995067e-06, "loss": 0.8561, "step": 100220 }, { "epoch": 8.33, "learning_rate": 2.890458110467533e-06, "loss": 0.8279, "step": 100230 }, { "epoch": 8.33, "learning_rate": 2.8903472549399992e-06, "loss": 0.7303, "step": 100240 }, { "epoch": 8.33, "learning_rate": 2.8902363994124655e-06, "loss": 0.7989, "step": 100250 }, { "epoch": 8.33, "learning_rate": 2.890125543884932e-06, "loss": 0.8209, "step": 100260 }, { "epoch": 8.33, "learning_rate": 2.890014688357398e-06, "loss": 0.8041, "step": 100270 }, { "epoch": 8.34, "learning_rate": 2.8899038328298644e-06, "loss": 0.8348, "step": 100280 }, { "epoch": 8.34, "learning_rate": 2.8897929773023303e-06, "loss": 0.8508, "step": 100290 }, { "epoch": 8.34, "learning_rate": 2.889682121774797e-06, "loss": 0.8164, "step": 100300 }, { "epoch": 8.34, "learning_rate": 2.8895712662472633e-06, "loss": 0.9056, "step": 100310 }, { "epoch": 8.34, "learning_rate": 2.889460410719729e-06, "loss": 0.7883, "step": 100320 }, { "epoch": 8.34, "learning_rate": 2.889349555192196e-06, "loss": 0.8045, "step": 100330 }, { "epoch": 8.34, "learning_rate": 2.8892386996646618e-06, "loss": 0.7828, "step": 100340 }, { "epoch": 8.34, "learning_rate": 2.8891278441371285e-06, "loss": 0.8474, "step": 100350 }, { "epoch": 8.34, "learning_rate": 2.8890169886095944e-06, "loss": 0.8304, "step": 100360 }, { "epoch": 8.34, "learning_rate": 2.8889061330820607e-06, "loss": 0.7778, "step": 100370 }, { "epoch": 8.34, "learning_rate": 2.888795277554527e-06, "loss": 0.8495, "step": 100380 }, { "epoch": 8.34, "learning_rate": 2.8886844220269932e-06, "loss": 0.7807, "step": 100390 }, { "epoch": 8.35, "learning_rate": 2.888573566499459e-06, "loss": 0.7922, "step": 100400 }, { "epoch": 8.35, "learning_rate": 2.888462710971926e-06, "loss": 0.8442, "step": 100410 }, { "epoch": 8.35, "learning_rate": 2.8883518554443917e-06, "loss": 0.8092, "step": 100420 }, { "epoch": 8.35, "learning_rate": 2.888240999916858e-06, "loss": 0.8066, "step": 100430 }, { "epoch": 8.35, "learning_rate": 2.8881301443893247e-06, "loss": 0.8414, "step": 100440 }, { "epoch": 8.35, "learning_rate": 2.8880192888617906e-06, "loss": 0.7845, "step": 100450 }, { "epoch": 8.35, "learning_rate": 2.8879084333342573e-06, "loss": 0.8639, "step": 100460 }, { "epoch": 8.35, "learning_rate": 2.887797577806723e-06, "loss": 0.7525, "step": 100470 }, { "epoch": 8.35, "learning_rate": 2.8876867222791895e-06, "loss": 0.8546, "step": 100480 }, { "epoch": 8.35, "learning_rate": 2.8875758667516558e-06, "loss": 0.7492, "step": 100490 }, { "epoch": 8.35, "learning_rate": 2.887465011224122e-06, "loss": 0.7926, "step": 100500 }, { "epoch": 8.35, "learning_rate": 2.887354155696588e-06, "loss": 0.8247, "step": 100510 }, { "epoch": 8.36, "learning_rate": 2.8872433001690547e-06, "loss": 0.7626, "step": 100520 }, { "epoch": 8.36, "learning_rate": 2.8871324446415205e-06, "loss": 0.7593, "step": 100530 }, { "epoch": 8.36, "learning_rate": 2.8870215891139873e-06, "loss": 0.7704, "step": 100540 }, { "epoch": 8.36, "learning_rate": 2.8869107335864536e-06, "loss": 0.7373, "step": 100550 }, { "epoch": 8.36, "learning_rate": 2.8867998780589194e-06, "loss": 0.9053, "step": 100560 }, { "epoch": 8.36, "learning_rate": 2.886689022531386e-06, "loss": 0.8633, "step": 100570 }, { "epoch": 8.36, "learning_rate": 2.886578167003852e-06, "loss": 0.8559, "step": 100580 }, { "epoch": 8.36, "learning_rate": 2.8864673114763183e-06, "loss": 0.8348, "step": 100590 }, { "epoch": 8.36, "learning_rate": 2.8863564559487846e-06, "loss": 0.7568, "step": 100600 }, { "epoch": 8.36, "learning_rate": 2.886245600421251e-06, "loss": 0.8926, "step": 100610 }, { "epoch": 8.36, "learning_rate": 2.886134744893717e-06, "loss": 0.7853, "step": 100620 }, { "epoch": 8.36, "learning_rate": 2.8860238893661835e-06, "loss": 0.8198, "step": 100630 }, { "epoch": 8.37, "learning_rate": 2.8859130338386494e-06, "loss": 0.7984, "step": 100640 }, { "epoch": 8.37, "learning_rate": 2.885802178311116e-06, "loss": 0.7973, "step": 100650 }, { "epoch": 8.37, "learning_rate": 2.885691322783582e-06, "loss": 0.8303, "step": 100660 }, { "epoch": 8.37, "learning_rate": 2.8855804672560482e-06, "loss": 0.7862, "step": 100670 }, { "epoch": 8.37, "learning_rate": 2.885469611728515e-06, "loss": 0.8864, "step": 100680 }, { "epoch": 8.37, "learning_rate": 2.885358756200981e-06, "loss": 0.7482, "step": 100690 }, { "epoch": 8.37, "learning_rate": 2.8852479006734476e-06, "loss": 0.749, "step": 100700 }, { "epoch": 8.37, "learning_rate": 2.8851370451459134e-06, "loss": 0.8518, "step": 100710 }, { "epoch": 8.37, "learning_rate": 2.8850261896183797e-06, "loss": 0.7714, "step": 100720 }, { "epoch": 8.37, "learning_rate": 2.884915334090846e-06, "loss": 0.8156, "step": 100730 }, { "epoch": 8.37, "learning_rate": 2.8848044785633123e-06, "loss": 0.8207, "step": 100740 }, { "epoch": 8.37, "learning_rate": 2.884693623035778e-06, "loss": 0.848, "step": 100750 }, { "epoch": 8.38, "learning_rate": 2.884582767508245e-06, "loss": 0.7776, "step": 100760 }, { "epoch": 8.38, "learning_rate": 2.8844719119807108e-06, "loss": 0.7875, "step": 100770 }, { "epoch": 8.38, "learning_rate": 2.8843610564531775e-06, "loss": 0.8231, "step": 100780 }, { "epoch": 8.38, "learning_rate": 2.8842502009256434e-06, "loss": 0.8247, "step": 100790 }, { "epoch": 8.38, "learning_rate": 2.8841393453981097e-06, "loss": 0.8256, "step": 100800 }, { "epoch": 8.38, "learning_rate": 2.8840284898705764e-06, "loss": 0.9019, "step": 100810 }, { "epoch": 8.38, "learning_rate": 2.8839176343430423e-06, "loss": 0.8829, "step": 100820 }, { "epoch": 8.38, "learning_rate": 2.8838067788155085e-06, "loss": 0.878, "step": 100830 }, { "epoch": 8.38, "learning_rate": 2.883695923287975e-06, "loss": 0.7759, "step": 100840 }, { "epoch": 8.38, "learning_rate": 2.883585067760441e-06, "loss": 0.8123, "step": 100850 }, { "epoch": 8.38, "learning_rate": 2.883474212232907e-06, "loss": 0.9063, "step": 100860 }, { "epoch": 8.38, "learning_rate": 2.8833633567053737e-06, "loss": 0.8021, "step": 100870 }, { "epoch": 8.39, "learning_rate": 2.8832525011778396e-06, "loss": 0.8163, "step": 100880 }, { "epoch": 8.39, "learning_rate": 2.8831416456503063e-06, "loss": 0.7675, "step": 100890 }, { "epoch": 8.39, "learning_rate": 2.883041875675526e-06, "loss": 0.8371, "step": 100900 }, { "epoch": 8.39, "learning_rate": 2.882931020147992e-06, "loss": 0.782, "step": 100910 }, { "epoch": 8.39, "learning_rate": 2.882820164620458e-06, "loss": 0.8281, "step": 100920 }, { "epoch": 8.39, "learning_rate": 2.8827093090929247e-06, "loss": 0.7151, "step": 100930 }, { "epoch": 8.39, "learning_rate": 2.8825984535653906e-06, "loss": 0.8709, "step": 100940 }, { "epoch": 8.39, "learning_rate": 2.8824875980378573e-06, "loss": 0.8043, "step": 100950 }, { "epoch": 8.39, "learning_rate": 2.882376742510323e-06, "loss": 0.8246, "step": 100960 }, { "epoch": 8.39, "learning_rate": 2.8822658869827895e-06, "loss": 0.8349, "step": 100970 }, { "epoch": 8.39, "learning_rate": 2.882155031455256e-06, "loss": 0.7846, "step": 100980 }, { "epoch": 8.39, "learning_rate": 2.882044175927722e-06, "loss": 0.7302, "step": 100990 }, { "epoch": 8.39, "learning_rate": 2.881933320400188e-06, "loss": 0.7384, "step": 101000 }, { "epoch": 8.4, "learning_rate": 2.8818224648726547e-06, "loss": 0.7855, "step": 101010 }, { "epoch": 8.4, "learning_rate": 2.881711609345121e-06, "loss": 0.8357, "step": 101020 }, { "epoch": 8.4, "learning_rate": 2.881600753817587e-06, "loss": 0.8695, "step": 101030 }, { "epoch": 8.4, "learning_rate": 2.8814898982900536e-06, "loss": 0.8119, "step": 101040 }, { "epoch": 8.4, "learning_rate": 2.8813790427625194e-06, "loss": 0.7731, "step": 101050 }, { "epoch": 8.4, "learning_rate": 2.881268187234986e-06, "loss": 0.8231, "step": 101060 }, { "epoch": 8.4, "learning_rate": 2.881157331707452e-06, "loss": 0.7674, "step": 101070 }, { "epoch": 8.4, "learning_rate": 2.8810464761799183e-06, "loss": 0.7557, "step": 101080 }, { "epoch": 8.4, "learning_rate": 2.8809356206523846e-06, "loss": 0.727, "step": 101090 }, { "epoch": 8.4, "learning_rate": 2.880824765124851e-06, "loss": 0.8222, "step": 101100 }, { "epoch": 8.4, "learning_rate": 2.880713909597317e-06, "loss": 0.9091, "step": 101110 }, { "epoch": 8.4, "learning_rate": 2.8806030540697835e-06, "loss": 0.8275, "step": 101120 }, { "epoch": 8.41, "learning_rate": 2.88049219854225e-06, "loss": 0.7795, "step": 101130 }, { "epoch": 8.41, "learning_rate": 2.880381343014716e-06, "loss": 0.7699, "step": 101140 }, { "epoch": 8.41, "learning_rate": 2.8802704874871824e-06, "loss": 0.8331, "step": 101150 }, { "epoch": 8.41, "learning_rate": 2.8801596319596483e-06, "loss": 0.8713, "step": 101160 }, { "epoch": 8.41, "learning_rate": 2.880048776432115e-06, "loss": 0.8044, "step": 101170 }, { "epoch": 8.41, "learning_rate": 2.879937920904581e-06, "loss": 0.8227, "step": 101180 }, { "epoch": 8.41, "learning_rate": 2.879827065377047e-06, "loss": 0.7847, "step": 101190 }, { "epoch": 8.41, "learning_rate": 2.8797162098495135e-06, "loss": 0.8175, "step": 101200 }, { "epoch": 8.41, "learning_rate": 2.8796053543219797e-06, "loss": 0.8841, "step": 101210 }, { "epoch": 8.41, "learning_rate": 2.879494498794446e-06, "loss": 0.8047, "step": 101220 }, { "epoch": 8.41, "learning_rate": 2.8793836432669123e-06, "loss": 0.7732, "step": 101230 }, { "epoch": 8.41, "learning_rate": 2.879272787739378e-06, "loss": 0.7921, "step": 101240 }, { "epoch": 8.42, "learning_rate": 2.879161932211845e-06, "loss": 0.7397, "step": 101250 }, { "epoch": 8.42, "learning_rate": 2.8790510766843112e-06, "loss": 0.8368, "step": 101260 }, { "epoch": 8.42, "learning_rate": 2.878940221156777e-06, "loss": 0.7668, "step": 101270 }, { "epoch": 8.42, "learning_rate": 2.878829365629244e-06, "loss": 0.7076, "step": 101280 }, { "epoch": 8.42, "learning_rate": 2.8787185101017097e-06, "loss": 0.7978, "step": 101290 }, { "epoch": 8.42, "learning_rate": 2.8786076545741764e-06, "loss": 0.8478, "step": 101300 }, { "epoch": 8.42, "learning_rate": 2.8784967990466423e-06, "loss": 0.8333, "step": 101310 }, { "epoch": 8.42, "learning_rate": 2.8783859435191086e-06, "loss": 0.7976, "step": 101320 }, { "epoch": 8.42, "learning_rate": 2.878275087991575e-06, "loss": 0.7708, "step": 101330 }, { "epoch": 8.42, "learning_rate": 2.878164232464041e-06, "loss": 0.7862, "step": 101340 }, { "epoch": 8.42, "learning_rate": 2.878053376936507e-06, "loss": 0.8009, "step": 101350 }, { "epoch": 8.42, "learning_rate": 2.8779425214089738e-06, "loss": 0.8611, "step": 101360 }, { "epoch": 8.43, "learning_rate": 2.8778316658814396e-06, "loss": 0.8352, "step": 101370 }, { "epoch": 8.43, "learning_rate": 2.877720810353906e-06, "loss": 0.7458, "step": 101380 }, { "epoch": 8.43, "learning_rate": 2.8776099548263726e-06, "loss": 0.8405, "step": 101390 }, { "epoch": 8.43, "learning_rate": 2.8774990992988385e-06, "loss": 0.8064, "step": 101400 }, { "epoch": 8.43, "learning_rate": 2.8773882437713052e-06, "loss": 0.8492, "step": 101410 }, { "epoch": 8.43, "learning_rate": 2.877277388243771e-06, "loss": 0.767, "step": 101420 }, { "epoch": 8.43, "learning_rate": 2.8771665327162374e-06, "loss": 0.825, "step": 101430 }, { "epoch": 8.43, "learning_rate": 2.8770556771887037e-06, "loss": 0.722, "step": 101440 }, { "epoch": 8.43, "learning_rate": 2.87694482166117e-06, "loss": 0.829, "step": 101450 }, { "epoch": 8.43, "learning_rate": 2.876833966133636e-06, "loss": 0.7811, "step": 101460 }, { "epoch": 8.43, "learning_rate": 2.8767231106061026e-06, "loss": 0.7469, "step": 101470 }, { "epoch": 8.43, "learning_rate": 2.8766122550785684e-06, "loss": 0.823, "step": 101480 }, { "epoch": 8.44, "learning_rate": 2.876501399551035e-06, "loss": 0.8232, "step": 101490 }, { "epoch": 8.44, "learning_rate": 2.8763905440235015e-06, "loss": 0.8322, "step": 101500 }, { "epoch": 8.44, "learning_rate": 2.8762796884959673e-06, "loss": 0.8504, "step": 101510 }, { "epoch": 8.44, "learning_rate": 2.876168832968434e-06, "loss": 0.7937, "step": 101520 }, { "epoch": 8.44, "learning_rate": 2.8760579774409e-06, "loss": 0.804, "step": 101530 }, { "epoch": 8.44, "learning_rate": 2.8759471219133662e-06, "loss": 0.8114, "step": 101540 }, { "epoch": 8.44, "learning_rate": 2.8758362663858325e-06, "loss": 0.824, "step": 101550 }, { "epoch": 8.44, "learning_rate": 2.875725410858299e-06, "loss": 0.8049, "step": 101560 }, { "epoch": 8.44, "learning_rate": 2.875614555330765e-06, "loss": 0.7825, "step": 101570 }, { "epoch": 8.44, "learning_rate": 2.8755036998032314e-06, "loss": 0.7729, "step": 101580 }, { "epoch": 8.44, "learning_rate": 2.8753928442756973e-06, "loss": 0.8293, "step": 101590 }, { "epoch": 8.44, "learning_rate": 2.875281988748164e-06, "loss": 0.8018, "step": 101600 }, { "epoch": 8.45, "learning_rate": 2.87517113322063e-06, "loss": 0.8694, "step": 101610 }, { "epoch": 8.45, "learning_rate": 2.875060277693096e-06, "loss": 0.7846, "step": 101620 }, { "epoch": 8.45, "learning_rate": 2.874949422165563e-06, "loss": 0.742, "step": 101630 }, { "epoch": 8.45, "learning_rate": 2.8748385666380288e-06, "loss": 0.7956, "step": 101640 }, { "epoch": 8.45, "learning_rate": 2.8747277111104955e-06, "loss": 0.8374, "step": 101650 }, { "epoch": 8.45, "learning_rate": 2.8746168555829613e-06, "loss": 0.8254, "step": 101660 }, { "epoch": 8.45, "learning_rate": 2.8745060000554276e-06, "loss": 0.8197, "step": 101670 }, { "epoch": 8.45, "learning_rate": 2.874395144527894e-06, "loss": 0.737, "step": 101680 }, { "epoch": 8.45, "learning_rate": 2.8742842890003602e-06, "loss": 0.8495, "step": 101690 }, { "epoch": 8.45, "learning_rate": 2.874173433472826e-06, "loss": 0.7998, "step": 101700 }, { "epoch": 8.45, "learning_rate": 2.874062577945293e-06, "loss": 0.803, "step": 101710 }, { "epoch": 8.45, "learning_rate": 2.8739517224177587e-06, "loss": 0.8382, "step": 101720 }, { "epoch": 8.46, "learning_rate": 2.8738408668902254e-06, "loss": 0.8478, "step": 101730 }, { "epoch": 8.46, "learning_rate": 2.8737300113626917e-06, "loss": 0.8246, "step": 101740 }, { "epoch": 8.46, "learning_rate": 2.8736191558351576e-06, "loss": 0.7855, "step": 101750 }, { "epoch": 8.46, "learning_rate": 2.8735083003076243e-06, "loss": 0.7931, "step": 101760 }, { "epoch": 8.46, "learning_rate": 2.87339744478009e-06, "loss": 0.8442, "step": 101770 }, { "epoch": 8.46, "learning_rate": 2.8732865892525565e-06, "loss": 0.8268, "step": 101780 }, { "epoch": 8.46, "learning_rate": 2.8731757337250228e-06, "loss": 0.7926, "step": 101790 }, { "epoch": 8.46, "learning_rate": 2.873064878197489e-06, "loss": 0.8182, "step": 101800 }, { "epoch": 8.46, "learning_rate": 2.872954022669955e-06, "loss": 0.8049, "step": 101810 }, { "epoch": 8.46, "learning_rate": 2.8728431671424216e-06, "loss": 0.7789, "step": 101820 }, { "epoch": 8.46, "learning_rate": 2.8727323116148875e-06, "loss": 0.8476, "step": 101830 }, { "epoch": 8.46, "learning_rate": 2.8726214560873542e-06, "loss": 0.8698, "step": 101840 }, { "epoch": 8.47, "learning_rate": 2.87251060055982e-06, "loss": 0.812, "step": 101850 }, { "epoch": 8.47, "learning_rate": 2.8723997450322864e-06, "loss": 0.7934, "step": 101860 }, { "epoch": 8.47, "learning_rate": 2.872288889504753e-06, "loss": 0.8044, "step": 101870 }, { "epoch": 8.47, "learning_rate": 2.872178033977219e-06, "loss": 0.8259, "step": 101880 }, { "epoch": 8.47, "learning_rate": 2.8720671784496853e-06, "loss": 0.804, "step": 101890 }, { "epoch": 8.47, "learning_rate": 2.8719563229221516e-06, "loss": 0.7676, "step": 101900 }, { "epoch": 8.47, "learning_rate": 2.871845467394618e-06, "loss": 0.8175, "step": 101910 }, { "epoch": 8.47, "learning_rate": 2.871734611867084e-06, "loss": 0.8623, "step": 101920 }, { "epoch": 8.47, "learning_rate": 2.8716237563395505e-06, "loss": 0.8026, "step": 101930 }, { "epoch": 8.47, "learning_rate": 2.8715129008120163e-06, "loss": 0.7843, "step": 101940 }, { "epoch": 8.47, "learning_rate": 2.871402045284483e-06, "loss": 0.8384, "step": 101950 }, { "epoch": 8.47, "learning_rate": 2.871291189756949e-06, "loss": 0.8144, "step": 101960 }, { "epoch": 8.48, "learning_rate": 2.8711803342294152e-06, "loss": 0.751, "step": 101970 }, { "epoch": 8.48, "learning_rate": 2.8710694787018815e-06, "loss": 0.8199, "step": 101980 }, { "epoch": 8.48, "learning_rate": 2.870958623174348e-06, "loss": 0.8015, "step": 101990 }, { "epoch": 8.48, "learning_rate": 2.8708477676468145e-06, "loss": 0.8494, "step": 102000 }, { "epoch": 8.48, "learning_rate": 2.8707369121192804e-06, "loss": 0.8524, "step": 102010 }, { "epoch": 8.48, "learning_rate": 2.8706260565917467e-06, "loss": 0.8056, "step": 102020 }, { "epoch": 8.48, "learning_rate": 2.870515201064213e-06, "loss": 0.7591, "step": 102030 }, { "epoch": 8.48, "learning_rate": 2.8704043455366793e-06, "loss": 0.7908, "step": 102040 }, { "epoch": 8.48, "learning_rate": 2.870293490009145e-06, "loss": 0.8346, "step": 102050 }, { "epoch": 8.48, "learning_rate": 2.870182634481612e-06, "loss": 0.8509, "step": 102060 }, { "epoch": 8.48, "learning_rate": 2.8700717789540778e-06, "loss": 0.8, "step": 102070 }, { "epoch": 8.48, "learning_rate": 2.8699609234265445e-06, "loss": 0.7885, "step": 102080 }, { "epoch": 8.49, "learning_rate": 2.8698500678990103e-06, "loss": 0.8413, "step": 102090 }, { "epoch": 8.49, "learning_rate": 2.8697392123714766e-06, "loss": 0.8292, "step": 102100 }, { "epoch": 8.49, "learning_rate": 2.8696283568439434e-06, "loss": 0.7774, "step": 102110 }, { "epoch": 8.49, "learning_rate": 2.8695175013164092e-06, "loss": 0.8426, "step": 102120 }, { "epoch": 8.49, "learning_rate": 2.8694066457888755e-06, "loss": 0.7911, "step": 102130 }, { "epoch": 8.49, "learning_rate": 2.869295790261342e-06, "loss": 0.8302, "step": 102140 }, { "epoch": 8.49, "learning_rate": 2.869184934733808e-06, "loss": 0.8477, "step": 102150 }, { "epoch": 8.49, "learning_rate": 2.869074079206274e-06, "loss": 0.8462, "step": 102160 }, { "epoch": 8.49, "learning_rate": 2.8689632236787407e-06, "loss": 0.8194, "step": 102170 }, { "epoch": 8.49, "learning_rate": 2.8688523681512066e-06, "loss": 0.8026, "step": 102180 }, { "epoch": 8.49, "learning_rate": 2.8687415126236733e-06, "loss": 0.8163, "step": 102190 }, { "epoch": 8.49, "learning_rate": 2.868630657096139e-06, "loss": 0.8028, "step": 102200 }, { "epoch": 8.5, "learning_rate": 2.8685198015686055e-06, "loss": 0.9111, "step": 102210 }, { "epoch": 8.5, "learning_rate": 2.8684089460410718e-06, "loss": 0.8129, "step": 102220 }, { "epoch": 8.5, "learning_rate": 2.868298090513538e-06, "loss": 0.8374, "step": 102230 }, { "epoch": 8.5, "learning_rate": 2.8681872349860048e-06, "loss": 0.8374, "step": 102240 }, { "epoch": 8.5, "learning_rate": 2.8680763794584706e-06, "loss": 0.8638, "step": 102250 }, { "epoch": 8.5, "learning_rate": 2.867965523930937e-06, "loss": 0.8488, "step": 102260 }, { "epoch": 8.5, "learning_rate": 2.8678546684034032e-06, "loss": 0.7898, "step": 102270 }, { "epoch": 8.5, "learning_rate": 2.8677438128758695e-06, "loss": 0.7905, "step": 102280 }, { "epoch": 8.5, "learning_rate": 2.8676329573483354e-06, "loss": 0.7799, "step": 102290 }, { "epoch": 8.5, "learning_rate": 2.867522101820802e-06, "loss": 0.8587, "step": 102300 }, { "epoch": 8.5, "learning_rate": 2.867411246293268e-06, "loss": 0.8415, "step": 102310 }, { "epoch": 8.5, "learning_rate": 2.8673003907657343e-06, "loss": 0.8135, "step": 102320 }, { "epoch": 8.51, "learning_rate": 2.8671895352382006e-06, "loss": 0.771, "step": 102330 }, { "epoch": 8.51, "learning_rate": 2.867078679710667e-06, "loss": 0.8327, "step": 102340 }, { "epoch": 8.51, "learning_rate": 2.866967824183133e-06, "loss": 0.8645, "step": 102350 }, { "epoch": 8.51, "learning_rate": 2.8668569686555995e-06, "loss": 0.948, "step": 102360 }, { "epoch": 8.51, "learning_rate": 2.8667461131280658e-06, "loss": 0.8165, "step": 102370 }, { "epoch": 8.51, "learning_rate": 2.866635257600532e-06, "loss": 0.7979, "step": 102380 }, { "epoch": 8.51, "learning_rate": 2.8665244020729984e-06, "loss": 0.7606, "step": 102390 }, { "epoch": 8.51, "learning_rate": 2.8664135465454642e-06, "loss": 0.8743, "step": 102400 }, { "epoch": 8.51, "learning_rate": 2.866302691017931e-06, "loss": 0.811, "step": 102410 }, { "epoch": 8.51, "learning_rate": 2.866191835490397e-06, "loss": 0.8727, "step": 102420 }, { "epoch": 8.51, "learning_rate": 2.8660809799628635e-06, "loss": 0.8185, "step": 102430 }, { "epoch": 8.51, "learning_rate": 2.8659701244353294e-06, "loss": 0.7495, "step": 102440 }, { "epoch": 8.52, "learning_rate": 2.8658592689077957e-06, "loss": 0.7858, "step": 102450 }, { "epoch": 8.52, "learning_rate": 2.865748413380262e-06, "loss": 0.8593, "step": 102460 }, { "epoch": 8.52, "learning_rate": 2.8656375578527283e-06, "loss": 0.7494, "step": 102470 }, { "epoch": 8.52, "learning_rate": 2.8655267023251946e-06, "loss": 0.7979, "step": 102480 }, { "epoch": 8.52, "learning_rate": 2.865415846797661e-06, "loss": 0.7692, "step": 102490 }, { "epoch": 8.52, "learning_rate": 2.865304991270127e-06, "loss": 0.8692, "step": 102500 }, { "epoch": 8.52, "learning_rate": 2.8651941357425935e-06, "loss": 0.823, "step": 102510 }, { "epoch": 8.52, "learning_rate": 2.8650832802150598e-06, "loss": 0.8245, "step": 102520 }, { "epoch": 8.52, "learning_rate": 2.8649724246875256e-06, "loss": 0.7697, "step": 102530 }, { "epoch": 8.52, "learning_rate": 2.8648615691599924e-06, "loss": 0.8223, "step": 102540 }, { "epoch": 8.52, "learning_rate": 2.8647507136324582e-06, "loss": 0.8626, "step": 102550 }, { "epoch": 8.52, "learning_rate": 2.8646398581049245e-06, "loss": 0.8192, "step": 102560 }, { "epoch": 8.53, "learning_rate": 2.864529002577391e-06, "loss": 0.8041, "step": 102570 }, { "epoch": 8.53, "learning_rate": 2.864418147049857e-06, "loss": 0.7821, "step": 102580 }, { "epoch": 8.53, "learning_rate": 2.864307291522323e-06, "loss": 0.7448, "step": 102590 }, { "epoch": 8.53, "learning_rate": 2.8641964359947897e-06, "loss": 0.7901, "step": 102600 }, { "epoch": 8.53, "learning_rate": 2.864085580467256e-06, "loss": 0.8566, "step": 102610 }, { "epoch": 8.53, "learning_rate": 2.8639747249397223e-06, "loss": 0.8236, "step": 102620 }, { "epoch": 8.53, "learning_rate": 2.8638638694121886e-06, "loss": 0.7967, "step": 102630 }, { "epoch": 8.53, "learning_rate": 2.8637530138846545e-06, "loss": 0.8105, "step": 102640 }, { "epoch": 8.53, "learning_rate": 2.863642158357121e-06, "loss": 0.9118, "step": 102650 }, { "epoch": 8.53, "learning_rate": 2.863531302829587e-06, "loss": 0.8631, "step": 102660 }, { "epoch": 8.53, "learning_rate": 2.8634204473020534e-06, "loss": 0.7911, "step": 102670 }, { "epoch": 8.53, "learning_rate": 2.8633095917745197e-06, "loss": 0.8185, "step": 102680 }, { "epoch": 8.54, "learning_rate": 2.863198736246986e-06, "loss": 0.8274, "step": 102690 }, { "epoch": 8.54, "learning_rate": 2.8630878807194522e-06, "loss": 0.7882, "step": 102700 }, { "epoch": 8.54, "learning_rate": 2.8629770251919185e-06, "loss": 0.8869, "step": 102710 }, { "epoch": 8.54, "learning_rate": 2.8628661696643844e-06, "loss": 0.7366, "step": 102720 }, { "epoch": 8.54, "learning_rate": 2.862755314136851e-06, "loss": 0.863, "step": 102730 }, { "epoch": 8.54, "learning_rate": 2.8626444586093174e-06, "loss": 0.8636, "step": 102740 }, { "epoch": 8.54, "learning_rate": 2.8625336030817833e-06, "loss": 0.7987, "step": 102750 }, { "epoch": 8.54, "learning_rate": 2.86242274755425e-06, "loss": 0.8842, "step": 102760 }, { "epoch": 8.54, "learning_rate": 2.862311892026716e-06, "loss": 0.8299, "step": 102770 }, { "epoch": 8.54, "learning_rate": 2.8622010364991826e-06, "loss": 0.7577, "step": 102780 }, { "epoch": 8.54, "learning_rate": 2.8620901809716485e-06, "loss": 0.7717, "step": 102790 }, { "epoch": 8.54, "learning_rate": 2.8619793254441148e-06, "loss": 0.8109, "step": 102800 }, { "epoch": 8.55, "learning_rate": 2.861868469916581e-06, "loss": 0.8744, "step": 102810 }, { "epoch": 8.55, "learning_rate": 2.8617576143890474e-06, "loss": 0.834, "step": 102820 }, { "epoch": 8.55, "learning_rate": 2.8616467588615132e-06, "loss": 0.7781, "step": 102830 }, { "epoch": 8.55, "learning_rate": 2.86153590333398e-06, "loss": 0.7882, "step": 102840 }, { "epoch": 8.55, "learning_rate": 2.8614250478064463e-06, "loss": 0.7754, "step": 102850 }, { "epoch": 8.55, "learning_rate": 2.8613141922789125e-06, "loss": 0.9122, "step": 102860 }, { "epoch": 8.55, "learning_rate": 2.861203336751379e-06, "loss": 0.8242, "step": 102870 }, { "epoch": 8.55, "learning_rate": 2.8610924812238447e-06, "loss": 0.8321, "step": 102880 }, { "epoch": 8.55, "learning_rate": 2.8609816256963114e-06, "loss": 0.7853, "step": 102890 }, { "epoch": 8.55, "learning_rate": 2.8608707701687773e-06, "loss": 0.867, "step": 102900 }, { "epoch": 8.55, "learning_rate": 2.8607599146412436e-06, "loss": 0.829, "step": 102910 }, { "epoch": 8.55, "learning_rate": 2.86064905911371e-06, "loss": 0.8025, "step": 102920 }, { "epoch": 8.56, "learning_rate": 2.860538203586176e-06, "loss": 0.8117, "step": 102930 }, { "epoch": 8.56, "learning_rate": 2.8604273480586425e-06, "loss": 0.7466, "step": 102940 }, { "epoch": 8.56, "learning_rate": 2.8603164925311088e-06, "loss": 0.842, "step": 102950 }, { "epoch": 8.56, "learning_rate": 2.8602056370035747e-06, "loss": 0.8489, "step": 102960 }, { "epoch": 8.56, "learning_rate": 2.8600947814760414e-06, "loss": 0.8027, "step": 102970 }, { "epoch": 8.56, "learning_rate": 2.8599839259485077e-06, "loss": 0.7976, "step": 102980 }, { "epoch": 8.56, "learning_rate": 2.8598730704209735e-06, "loss": 0.8292, "step": 102990 }, { "epoch": 8.56, "learning_rate": 2.8597622148934403e-06, "loss": 0.7623, "step": 103000 }, { "epoch": 8.56, "learning_rate": 2.85966244491866e-06, "loss": 0.8479, "step": 103010 }, { "epoch": 8.56, "learning_rate": 2.8595515893911257e-06, "loss": 0.7911, "step": 103020 }, { "epoch": 8.56, "learning_rate": 2.8594407338635924e-06, "loss": 0.7428, "step": 103030 }, { "epoch": 8.56, "learning_rate": 2.8593298783360583e-06, "loss": 0.7711, "step": 103040 }, { "epoch": 8.57, "learning_rate": 2.8592190228085246e-06, "loss": 0.7885, "step": 103050 }, { "epoch": 8.57, "learning_rate": 2.8591081672809913e-06, "loss": 0.8042, "step": 103060 }, { "epoch": 8.57, "learning_rate": 2.858997311753457e-06, "loss": 0.788, "step": 103070 }, { "epoch": 8.57, "learning_rate": 2.8588864562259234e-06, "loss": 0.7727, "step": 103080 }, { "epoch": 8.57, "learning_rate": 2.8587756006983897e-06, "loss": 0.7271, "step": 103090 }, { "epoch": 8.57, "learning_rate": 2.858664745170856e-06, "loss": 0.8518, "step": 103100 }, { "epoch": 8.57, "learning_rate": 2.858553889643322e-06, "loss": 0.8635, "step": 103110 }, { "epoch": 8.57, "learning_rate": 2.8584430341157886e-06, "loss": 0.818, "step": 103120 }, { "epoch": 8.57, "learning_rate": 2.8583321785882545e-06, "loss": 0.8156, "step": 103130 }, { "epoch": 8.57, "learning_rate": 2.8582213230607212e-06, "loss": 0.8254, "step": 103140 }, { "epoch": 8.57, "learning_rate": 2.858110467533187e-06, "loss": 0.7856, "step": 103150 }, { "epoch": 8.57, "learning_rate": 2.8579996120056534e-06, "loss": 0.8793, "step": 103160 }, { "epoch": 8.58, "learning_rate": 2.8578887564781197e-06, "loss": 0.7744, "step": 103170 }, { "epoch": 8.58, "learning_rate": 2.857777900950586e-06, "loss": 0.7693, "step": 103180 }, { "epoch": 8.58, "learning_rate": 2.8576670454230527e-06, "loss": 0.8176, "step": 103190 }, { "epoch": 8.58, "learning_rate": 2.8575561898955186e-06, "loss": 0.7887, "step": 103200 }, { "epoch": 8.58, "learning_rate": 2.857445334367985e-06, "loss": 0.8685, "step": 103210 }, { "epoch": 8.58, "learning_rate": 2.857334478840451e-06, "loss": 0.7507, "step": 103220 }, { "epoch": 8.58, "learning_rate": 2.8572236233129174e-06, "loss": 0.8391, "step": 103230 }, { "epoch": 8.58, "learning_rate": 2.8571127677853833e-06, "loss": 0.8142, "step": 103240 }, { "epoch": 8.58, "learning_rate": 2.85700191225785e-06, "loss": 0.8577, "step": 103250 }, { "epoch": 8.58, "learning_rate": 2.856891056730316e-06, "loss": 0.8382, "step": 103260 }, { "epoch": 8.58, "learning_rate": 2.856780201202782e-06, "loss": 0.7079, "step": 103270 }, { "epoch": 8.58, "learning_rate": 2.8566693456752485e-06, "loss": 0.7501, "step": 103280 }, { "epoch": 8.59, "learning_rate": 2.856558490147715e-06, "loss": 0.8041, "step": 103290 }, { "epoch": 8.59, "learning_rate": 2.856447634620181e-06, "loss": 0.842, "step": 103300 }, { "epoch": 8.59, "learning_rate": 2.8563367790926474e-06, "loss": 0.8834, "step": 103310 }, { "epoch": 8.59, "learning_rate": 2.8562259235651137e-06, "loss": 0.8018, "step": 103320 }, { "epoch": 8.59, "learning_rate": 2.85611506803758e-06, "loss": 0.7936, "step": 103330 }, { "epoch": 8.59, "learning_rate": 2.8560042125100463e-06, "loss": 0.7922, "step": 103340 }, { "epoch": 8.59, "learning_rate": 2.855893356982512e-06, "loss": 0.7969, "step": 103350 }, { "epoch": 8.59, "learning_rate": 2.855782501454979e-06, "loss": 0.8713, "step": 103360 }, { "epoch": 8.59, "learning_rate": 2.8556716459274447e-06, "loss": 0.8569, "step": 103370 }, { "epoch": 8.59, "learning_rate": 2.8555607903999115e-06, "loss": 0.7992, "step": 103380 }, { "epoch": 8.59, "learning_rate": 2.8554499348723773e-06, "loss": 0.8739, "step": 103390 }, { "epoch": 8.59, "learning_rate": 2.8553390793448436e-06, "loss": 0.8411, "step": 103400 }, { "epoch": 8.6, "learning_rate": 2.85522822381731e-06, "loss": 0.7744, "step": 103410 }, { "epoch": 8.6, "learning_rate": 2.8551173682897762e-06, "loss": 0.8164, "step": 103420 }, { "epoch": 8.6, "learning_rate": 2.8550065127622425e-06, "loss": 0.7995, "step": 103430 }, { "epoch": 8.6, "learning_rate": 2.854895657234709e-06, "loss": 0.7613, "step": 103440 }, { "epoch": 8.6, "learning_rate": 2.854784801707175e-06, "loss": 0.8059, "step": 103450 }, { "epoch": 8.6, "learning_rate": 2.8546739461796414e-06, "loss": 0.8868, "step": 103460 }, { "epoch": 8.6, "learning_rate": 2.8545630906521077e-06, "loss": 0.8612, "step": 103470 }, { "epoch": 8.6, "learning_rate": 2.8544522351245736e-06, "loss": 0.7894, "step": 103480 }, { "epoch": 8.6, "learning_rate": 2.8543413795970403e-06, "loss": 0.775, "step": 103490 }, { "epoch": 8.6, "learning_rate": 2.854230524069506e-06, "loss": 0.7673, "step": 103500 }, { "epoch": 8.6, "learning_rate": 2.8541196685419724e-06, "loss": 0.8437, "step": 103510 }, { "epoch": 8.6, "learning_rate": 2.8540088130144387e-06, "loss": 0.821, "step": 103520 }, { "epoch": 8.61, "learning_rate": 2.853897957486905e-06, "loss": 0.7596, "step": 103530 }, { "epoch": 8.61, "learning_rate": 2.853787101959371e-06, "loss": 0.7768, "step": 103540 }, { "epoch": 8.61, "learning_rate": 2.8536762464318376e-06, "loss": 0.7825, "step": 103550 }, { "epoch": 8.61, "learning_rate": 2.853565390904304e-06, "loss": 0.9098, "step": 103560 }, { "epoch": 8.61, "learning_rate": 2.8534545353767702e-06, "loss": 0.7691, "step": 103570 }, { "epoch": 8.61, "learning_rate": 2.8533436798492365e-06, "loss": 0.8227, "step": 103580 }, { "epoch": 8.61, "learning_rate": 2.8532328243217024e-06, "loss": 0.8263, "step": 103590 }, { "epoch": 8.61, "learning_rate": 2.853121968794169e-06, "loss": 0.8545, "step": 103600 }, { "epoch": 8.61, "learning_rate": 2.853011113266635e-06, "loss": 0.8465, "step": 103610 }, { "epoch": 8.61, "learning_rate": 2.8529002577391013e-06, "loss": 0.7552, "step": 103620 }, { "epoch": 8.61, "learning_rate": 2.8527894022115676e-06, "loss": 0.8242, "step": 103630 }, { "epoch": 8.61, "learning_rate": 2.852678546684034e-06, "loss": 0.8007, "step": 103640 }, { "epoch": 8.62, "learning_rate": 2.8525676911565e-06, "loss": 0.8096, "step": 103650 }, { "epoch": 8.62, "learning_rate": 2.8524568356289665e-06, "loss": 0.8949, "step": 103660 }, { "epoch": 8.62, "learning_rate": 2.8523459801014323e-06, "loss": 0.871, "step": 103670 }, { "epoch": 8.62, "learning_rate": 2.852235124573899e-06, "loss": 0.7803, "step": 103680 }, { "epoch": 8.62, "learning_rate": 2.8521242690463653e-06, "loss": 0.8237, "step": 103690 }, { "epoch": 8.62, "learning_rate": 2.852013413518831e-06, "loss": 0.8168, "step": 103700 }, { "epoch": 8.62, "learning_rate": 2.851902557991298e-06, "loss": 0.8867, "step": 103710 }, { "epoch": 8.62, "learning_rate": 2.851791702463764e-06, "loss": 0.8615, "step": 103720 }, { "epoch": 8.62, "learning_rate": 2.8516808469362305e-06, "loss": 0.8726, "step": 103730 }, { "epoch": 8.62, "learning_rate": 2.8515699914086964e-06, "loss": 0.7751, "step": 103740 }, { "epoch": 8.62, "learning_rate": 2.8514591358811627e-06, "loss": 0.828, "step": 103750 }, { "epoch": 8.62, "learning_rate": 2.851348280353629e-06, "loss": 0.8029, "step": 103760 }, { "epoch": 8.63, "learning_rate": 2.8512374248260953e-06, "loss": 0.7931, "step": 103770 }, { "epoch": 8.63, "learning_rate": 2.851126569298561e-06, "loss": 0.8478, "step": 103780 }, { "epoch": 8.63, "learning_rate": 2.851015713771028e-06, "loss": 0.7058, "step": 103790 }, { "epoch": 8.63, "learning_rate": 2.850904858243494e-06, "loss": 0.7356, "step": 103800 }, { "epoch": 8.63, "learning_rate": 2.8507940027159605e-06, "loss": 0.8285, "step": 103810 }, { "epoch": 8.63, "learning_rate": 2.8506831471884268e-06, "loss": 0.7961, "step": 103820 }, { "epoch": 8.63, "learning_rate": 2.8505722916608926e-06, "loss": 0.7669, "step": 103830 }, { "epoch": 8.63, "learning_rate": 2.8504614361333593e-06, "loss": 0.8825, "step": 103840 }, { "epoch": 8.63, "learning_rate": 2.8503505806058252e-06, "loss": 0.7773, "step": 103850 }, { "epoch": 8.63, "learning_rate": 2.8502397250782915e-06, "loss": 0.8085, "step": 103860 }, { "epoch": 8.63, "learning_rate": 2.850128869550758e-06, "loss": 0.8597, "step": 103870 }, { "epoch": 8.63, "learning_rate": 2.850018014023224e-06, "loss": 0.8399, "step": 103880 }, { "epoch": 8.64, "learning_rate": 2.8499071584956904e-06, "loss": 0.9162, "step": 103890 }, { "epoch": 8.64, "learning_rate": 2.8497963029681567e-06, "loss": 0.8736, "step": 103900 }, { "epoch": 8.64, "learning_rate": 2.8496854474406226e-06, "loss": 0.846, "step": 103910 }, { "epoch": 8.64, "learning_rate": 2.8495745919130893e-06, "loss": 0.7614, "step": 103920 }, { "epoch": 8.64, "learning_rate": 2.8494637363855556e-06, "loss": 0.7985, "step": 103930 }, { "epoch": 8.64, "learning_rate": 2.8493528808580215e-06, "loss": 0.8023, "step": 103940 }, { "epoch": 8.64, "learning_rate": 2.849242025330488e-06, "loss": 0.8512, "step": 103950 }, { "epoch": 8.64, "learning_rate": 2.849131169802954e-06, "loss": 0.7846, "step": 103960 }, { "epoch": 8.64, "learning_rate": 2.8490203142754208e-06, "loss": 0.8585, "step": 103970 }, { "epoch": 8.64, "learning_rate": 2.8489094587478866e-06, "loss": 0.7918, "step": 103980 }, { "epoch": 8.64, "learning_rate": 2.848798603220353e-06, "loss": 0.8195, "step": 103990 }, { "epoch": 8.64, "learning_rate": 2.8486877476928192e-06, "loss": 0.7987, "step": 104000 }, { "epoch": 8.65, "learning_rate": 2.8485768921652855e-06, "loss": 0.8503, "step": 104010 }, { "epoch": 8.65, "learning_rate": 2.8484660366377514e-06, "loss": 0.8625, "step": 104020 }, { "epoch": 8.65, "learning_rate": 2.848355181110218e-06, "loss": 0.8283, "step": 104030 }, { "epoch": 8.65, "learning_rate": 2.8482443255826844e-06, "loss": 0.7271, "step": 104040 }, { "epoch": 8.65, "learning_rate": 2.8481334700551503e-06, "loss": 0.8288, "step": 104050 }, { "epoch": 8.65, "learning_rate": 2.848022614527617e-06, "loss": 0.8284, "step": 104060 }, { "epoch": 8.65, "learning_rate": 2.847911759000083e-06, "loss": 0.7538, "step": 104070 }, { "epoch": 8.65, "learning_rate": 2.8478009034725496e-06, "loss": 0.7863, "step": 104080 }, { "epoch": 8.65, "learning_rate": 2.8476900479450155e-06, "loss": 0.7726, "step": 104090 }, { "epoch": 8.65, "learning_rate": 2.8475791924174818e-06, "loss": 0.852, "step": 104100 }, { "epoch": 8.65, "learning_rate": 2.847468336889948e-06, "loss": 0.885, "step": 104110 }, { "epoch": 8.65, "learning_rate": 2.8473574813624143e-06, "loss": 0.8476, "step": 104120 }, { "epoch": 8.66, "learning_rate": 2.8472466258348802e-06, "loss": 0.7398, "step": 104130 }, { "epoch": 8.66, "learning_rate": 2.847135770307347e-06, "loss": 0.7624, "step": 104140 }, { "epoch": 8.66, "learning_rate": 2.847024914779813e-06, "loss": 0.8064, "step": 104150 }, { "epoch": 8.66, "learning_rate": 2.8469140592522795e-06, "loss": 0.8246, "step": 104160 }, { "epoch": 8.66, "learning_rate": 2.846803203724746e-06, "loss": 0.7737, "step": 104170 }, { "epoch": 8.66, "learning_rate": 2.8466923481972117e-06, "loss": 0.7998, "step": 104180 }, { "epoch": 8.66, "learning_rate": 2.8465814926696784e-06, "loss": 0.8156, "step": 104190 }, { "epoch": 8.66, "learning_rate": 2.8464706371421443e-06, "loss": 0.7636, "step": 104200 }, { "epoch": 8.66, "learning_rate": 2.8463597816146106e-06, "loss": 0.8478, "step": 104210 }, { "epoch": 8.66, "learning_rate": 2.846248926087077e-06, "loss": 0.8951, "step": 104220 }, { "epoch": 8.66, "learning_rate": 2.846138070559543e-06, "loss": 0.7578, "step": 104230 }, { "epoch": 8.66, "learning_rate": 2.8460272150320095e-06, "loss": 0.8801, "step": 104240 }, { "epoch": 8.67, "learning_rate": 2.8459163595044758e-06, "loss": 0.7809, "step": 104250 }, { "epoch": 8.67, "learning_rate": 2.8458055039769416e-06, "loss": 0.8625, "step": 104260 }, { "epoch": 8.67, "learning_rate": 2.8456946484494084e-06, "loss": 0.802, "step": 104270 }, { "epoch": 8.67, "learning_rate": 2.8455837929218742e-06, "loss": 0.6992, "step": 104280 }, { "epoch": 8.67, "learning_rate": 2.8454729373943405e-06, "loss": 0.7847, "step": 104290 }, { "epoch": 8.67, "learning_rate": 2.8453620818668072e-06, "loss": 0.7607, "step": 104300 }, { "epoch": 8.67, "learning_rate": 2.845251226339273e-06, "loss": 0.8397, "step": 104310 }, { "epoch": 8.67, "learning_rate": 2.84514037081174e-06, "loss": 0.7964, "step": 104320 }, { "epoch": 8.67, "learning_rate": 2.8450295152842057e-06, "loss": 0.7705, "step": 104330 }, { "epoch": 8.67, "learning_rate": 2.844918659756672e-06, "loss": 0.8216, "step": 104340 }, { "epoch": 8.67, "learning_rate": 2.8448078042291383e-06, "loss": 0.7839, "step": 104350 }, { "epoch": 8.67, "learning_rate": 2.8446969487016046e-06, "loss": 0.9056, "step": 104360 }, { "epoch": 8.68, "learning_rate": 2.8445860931740705e-06, "loss": 0.7939, "step": 104370 }, { "epoch": 8.68, "learning_rate": 2.844475237646537e-06, "loss": 0.7677, "step": 104380 }, { "epoch": 8.68, "learning_rate": 2.844364382119003e-06, "loss": 0.8094, "step": 104390 }, { "epoch": 8.68, "learning_rate": 2.8442535265914693e-06, "loss": 0.7665, "step": 104400 }, { "epoch": 8.68, "learning_rate": 2.844142671063936e-06, "loss": 0.8125, "step": 104410 }, { "epoch": 8.68, "learning_rate": 2.844031815536402e-06, "loss": 0.7739, "step": 104420 }, { "epoch": 8.68, "learning_rate": 2.8439209600088687e-06, "loss": 0.8057, "step": 104430 }, { "epoch": 8.68, "learning_rate": 2.8438101044813345e-06, "loss": 0.7429, "step": 104440 }, { "epoch": 8.68, "learning_rate": 2.843699248953801e-06, "loss": 0.785, "step": 104450 }, { "epoch": 8.68, "learning_rate": 2.843588393426267e-06, "loss": 0.8158, "step": 104460 }, { "epoch": 8.68, "learning_rate": 2.8434775378987334e-06, "loss": 0.7694, "step": 104470 }, { "epoch": 8.68, "learning_rate": 2.8433666823711993e-06, "loss": 0.8252, "step": 104480 }, { "epoch": 8.69, "learning_rate": 2.843255826843666e-06, "loss": 0.8033, "step": 104490 }, { "epoch": 8.69, "learning_rate": 2.843144971316132e-06, "loss": 0.8697, "step": 104500 }, { "epoch": 8.69, "learning_rate": 2.8430341157885986e-06, "loss": 0.8018, "step": 104510 }, { "epoch": 8.69, "learning_rate": 2.8429232602610645e-06, "loss": 0.7985, "step": 104520 }, { "epoch": 8.69, "learning_rate": 2.8428124047335308e-06, "loss": 0.7534, "step": 104530 }, { "epoch": 8.69, "learning_rate": 2.8427015492059975e-06, "loss": 0.804, "step": 104540 }, { "epoch": 8.69, "learning_rate": 2.8425906936784633e-06, "loss": 0.806, "step": 104550 }, { "epoch": 8.69, "learning_rate": 2.8424798381509296e-06, "loss": 0.8149, "step": 104560 }, { "epoch": 8.69, "learning_rate": 2.842368982623396e-06, "loss": 0.7947, "step": 104570 }, { "epoch": 8.69, "learning_rate": 2.8422581270958622e-06, "loss": 0.846, "step": 104580 }, { "epoch": 8.69, "learning_rate": 2.8421472715683285e-06, "loss": 0.7801, "step": 104590 }, { "epoch": 8.69, "learning_rate": 2.842036416040795e-06, "loss": 0.777, "step": 104600 }, { "epoch": 8.7, "learning_rate": 2.8419255605132607e-06, "loss": 0.853, "step": 104610 }, { "epoch": 8.7, "learning_rate": 2.8418147049857274e-06, "loss": 0.8099, "step": 104620 }, { "epoch": 8.7, "learning_rate": 2.8417038494581933e-06, "loss": 0.833, "step": 104630 }, { "epoch": 8.7, "learning_rate": 2.8415929939306596e-06, "loss": 0.822, "step": 104640 }, { "epoch": 8.7, "learning_rate": 2.841482138403126e-06, "loss": 0.8201, "step": 104650 }, { "epoch": 8.7, "learning_rate": 2.841371282875592e-06, "loss": 0.8436, "step": 104660 }, { "epoch": 8.7, "learning_rate": 2.841260427348059e-06, "loss": 0.8037, "step": 104670 }, { "epoch": 8.7, "learning_rate": 2.8411495718205248e-06, "loss": 0.7829, "step": 104680 }, { "epoch": 8.7, "learning_rate": 2.841038716292991e-06, "loss": 0.7739, "step": 104690 }, { "epoch": 8.7, "learning_rate": 2.8409278607654574e-06, "loss": 0.8209, "step": 104700 }, { "epoch": 8.7, "learning_rate": 2.8408170052379237e-06, "loss": 0.8379, "step": 104710 }, { "epoch": 8.7, "learning_rate": 2.8407061497103895e-06, "loss": 0.8231, "step": 104720 }, { "epoch": 8.71, "learning_rate": 2.8405952941828562e-06, "loss": 0.7155, "step": 104730 }, { "epoch": 8.71, "learning_rate": 2.840484438655322e-06, "loss": 0.7548, "step": 104740 }, { "epoch": 8.71, "learning_rate": 2.840373583127789e-06, "loss": 0.8856, "step": 104750 }, { "epoch": 8.71, "learning_rate": 2.8402627276002547e-06, "loss": 0.8229, "step": 104760 }, { "epoch": 8.71, "learning_rate": 2.840151872072721e-06, "loss": 0.7517, "step": 104770 }, { "epoch": 8.71, "learning_rate": 2.8400410165451877e-06, "loss": 0.8522, "step": 104780 }, { "epoch": 8.71, "learning_rate": 2.8399301610176536e-06, "loss": 0.7762, "step": 104790 }, { "epoch": 8.71, "learning_rate": 2.83981930549012e-06, "loss": 0.8595, "step": 104800 }, { "epoch": 8.71, "learning_rate": 2.839708449962586e-06, "loss": 0.7692, "step": 104810 }, { "epoch": 8.71, "learning_rate": 2.8395975944350525e-06, "loss": 0.758, "step": 104820 }, { "epoch": 8.71, "learning_rate": 2.8394867389075183e-06, "loss": 0.7716, "step": 104830 }, { "epoch": 8.71, "learning_rate": 2.839375883379985e-06, "loss": 0.7907, "step": 104840 }, { "epoch": 8.71, "learning_rate": 2.839265027852451e-06, "loss": 0.7809, "step": 104850 }, { "epoch": 8.72, "learning_rate": 2.8391541723249177e-06, "loss": 0.8329, "step": 104860 }, { "epoch": 8.72, "learning_rate": 2.8390433167973835e-06, "loss": 0.7905, "step": 104870 }, { "epoch": 8.72, "learning_rate": 2.83893246126985e-06, "loss": 0.7469, "step": 104880 }, { "epoch": 8.72, "learning_rate": 2.838821605742316e-06, "loss": 0.8025, "step": 104890 }, { "epoch": 8.72, "learning_rate": 2.8387107502147824e-06, "loss": 0.7977, "step": 104900 }, { "epoch": 8.72, "learning_rate": 2.8385998946872487e-06, "loss": 0.8391, "step": 104910 }, { "epoch": 8.72, "learning_rate": 2.838489039159715e-06, "loss": 0.7594, "step": 104920 }, { "epoch": 8.72, "learning_rate": 2.8383781836321813e-06, "loss": 0.795, "step": 104930 }, { "epoch": 8.72, "learning_rate": 2.8382673281046476e-06, "loss": 0.8096, "step": 104940 }, { "epoch": 8.72, "learning_rate": 2.838156472577114e-06, "loss": 0.7491, "step": 104950 }, { "epoch": 8.72, "learning_rate": 2.8380456170495798e-06, "loss": 0.7498, "step": 104960 }, { "epoch": 8.72, "learning_rate": 2.8379347615220465e-06, "loss": 0.7793, "step": 104970 }, { "epoch": 8.73, "learning_rate": 2.8378239059945124e-06, "loss": 0.8248, "step": 104980 }, { "epoch": 8.73, "learning_rate": 2.8377130504669787e-06, "loss": 0.8038, "step": 104990 }, { "epoch": 8.73, "learning_rate": 2.837602194939445e-06, "loss": 0.8096, "step": 105000 }, { "epoch": 8.73, "learning_rate": 2.8374913394119112e-06, "loss": 0.895, "step": 105010 }, { "epoch": 8.73, "learning_rate": 2.8373804838843775e-06, "loss": 0.7543, "step": 105020 }, { "epoch": 8.73, "learning_rate": 2.837269628356844e-06, "loss": 0.7986, "step": 105030 }, { "epoch": 8.73, "learning_rate": 2.83715877282931e-06, "loss": 0.8093, "step": 105040 }, { "epoch": 8.73, "learning_rate": 2.8370479173017764e-06, "loss": 0.7447, "step": 105050 }, { "epoch": 8.73, "learning_rate": 2.8369370617742427e-06, "loss": 0.7461, "step": 105060 }, { "epoch": 8.73, "learning_rate": 2.8368262062467086e-06, "loss": 0.7803, "step": 105070 }, { "epoch": 8.73, "learning_rate": 2.8367153507191753e-06, "loss": 0.8732, "step": 105080 }, { "epoch": 8.73, "learning_rate": 2.836604495191641e-06, "loss": 0.8164, "step": 105090 }, { "epoch": 8.74, "learning_rate": 2.836493639664108e-06, "loss": 0.7929, "step": 105100 }, { "epoch": 8.74, "learning_rate": 2.8363827841365738e-06, "loss": 0.858, "step": 105110 }, { "epoch": 8.74, "learning_rate": 2.83627192860904e-06, "loss": 0.7677, "step": 105120 }, { "epoch": 8.74, "learning_rate": 2.8361610730815064e-06, "loss": 0.7845, "step": 105130 }, { "epoch": 8.74, "learning_rate": 2.8360502175539727e-06, "loss": 0.8124, "step": 105140 }, { "epoch": 8.74, "learning_rate": 2.835939362026439e-06, "loss": 0.8266, "step": 105150 }, { "epoch": 8.74, "learning_rate": 2.8358285064989052e-06, "loss": 0.8576, "step": 105160 }, { "epoch": 8.74, "learning_rate": 2.8357176509713715e-06, "loss": 0.7655, "step": 105170 }, { "epoch": 8.74, "learning_rate": 2.835606795443838e-06, "loss": 0.6993, "step": 105180 }, { "epoch": 8.74, "learning_rate": 2.835495939916304e-06, "loss": 0.8685, "step": 105190 }, { "epoch": 8.74, "learning_rate": 2.83538508438877e-06, "loss": 0.8762, "step": 105200 }, { "epoch": 8.74, "learning_rate": 2.8352742288612367e-06, "loss": 0.879, "step": 105210 }, { "epoch": 8.75, "learning_rate": 2.8351633733337026e-06, "loss": 0.8225, "step": 105220 }, { "epoch": 8.75, "learning_rate": 2.835052517806169e-06, "loss": 0.7573, "step": 105230 }, { "epoch": 8.75, "learning_rate": 2.834941662278635e-06, "loss": 0.7666, "step": 105240 }, { "epoch": 8.75, "learning_rate": 2.8348308067511015e-06, "loss": 0.7841, "step": 105250 }, { "epoch": 8.75, "learning_rate": 2.8347199512235674e-06, "loss": 0.919, "step": 105260 }, { "epoch": 8.75, "learning_rate": 2.834609095696034e-06, "loss": 0.7543, "step": 105270 }, { "epoch": 8.75, "learning_rate": 2.8344982401685004e-06, "loss": 0.7842, "step": 105280 }, { "epoch": 8.75, "learning_rate": 2.8343873846409667e-06, "loss": 0.8926, "step": 105290 }, { "epoch": 8.75, "learning_rate": 2.834276529113433e-06, "loss": 0.7887, "step": 105300 }, { "epoch": 8.75, "learning_rate": 2.834165673585899e-06, "loss": 0.8019, "step": 105310 }, { "epoch": 8.75, "learning_rate": 2.8340548180583655e-06, "loss": 0.8084, "step": 105320 }, { "epoch": 8.75, "learning_rate": 2.8339439625308314e-06, "loss": 0.8256, "step": 105330 }, { "epoch": 8.76, "learning_rate": 2.8338331070032977e-06, "loss": 0.8257, "step": 105340 }, { "epoch": 8.76, "learning_rate": 2.833722251475764e-06, "loss": 0.8142, "step": 105350 }, { "epoch": 8.76, "learning_rate": 2.8336113959482303e-06, "loss": 0.8383, "step": 105360 }, { "epoch": 8.76, "learning_rate": 2.8335005404206966e-06, "loss": 0.8379, "step": 105370 }, { "epoch": 8.76, "learning_rate": 2.8334007704459166e-06, "loss": 0.7678, "step": 105380 }, { "epoch": 8.76, "learning_rate": 2.8332899149183824e-06, "loss": 0.819, "step": 105390 }, { "epoch": 8.76, "learning_rate": 2.8331790593908487e-06, "loss": 0.8487, "step": 105400 }, { "epoch": 8.76, "learning_rate": 2.833068203863315e-06, "loss": 0.8281, "step": 105410 }, { "epoch": 8.76, "learning_rate": 2.8329573483357813e-06, "loss": 0.771, "step": 105420 }, { "epoch": 8.76, "learning_rate": 2.832846492808247e-06, "loss": 0.8149, "step": 105430 }, { "epoch": 8.76, "learning_rate": 2.832735637280714e-06, "loss": 0.824, "step": 105440 }, { "epoch": 8.76, "learning_rate": 2.8326247817531798e-06, "loss": 0.8351, "step": 105450 }, { "epoch": 8.77, "learning_rate": 2.8325139262256465e-06, "loss": 0.8704, "step": 105460 }, { "epoch": 8.77, "learning_rate": 2.8324030706981124e-06, "loss": 0.7869, "step": 105470 }, { "epoch": 8.77, "learning_rate": 2.8322922151705787e-06, "loss": 0.8514, "step": 105480 }, { "epoch": 8.77, "learning_rate": 2.8321813596430454e-06, "loss": 0.8056, "step": 105490 }, { "epoch": 8.77, "learning_rate": 2.8320705041155113e-06, "loss": 0.7954, "step": 105500 }, { "epoch": 8.77, "learning_rate": 2.8319596485879776e-06, "loss": 0.8065, "step": 105510 }, { "epoch": 8.77, "learning_rate": 2.831848793060444e-06, "loss": 0.8178, "step": 105520 }, { "epoch": 8.77, "learning_rate": 2.83173793753291e-06, "loss": 0.782, "step": 105530 }, { "epoch": 8.77, "learning_rate": 2.8316270820053764e-06, "loss": 0.7683, "step": 105540 }, { "epoch": 8.77, "learning_rate": 2.8315162264778427e-06, "loss": 0.887, "step": 105550 }, { "epoch": 8.77, "learning_rate": 2.8314053709503086e-06, "loss": 0.8409, "step": 105560 }, { "epoch": 8.77, "learning_rate": 2.8312945154227753e-06, "loss": 0.8007, "step": 105570 }, { "epoch": 8.78, "learning_rate": 2.831183659895241e-06, "loss": 0.7666, "step": 105580 }, { "epoch": 8.78, "learning_rate": 2.8310728043677075e-06, "loss": 0.7735, "step": 105590 }, { "epoch": 8.78, "learning_rate": 2.830961948840174e-06, "loss": 0.781, "step": 105600 }, { "epoch": 8.78, "learning_rate": 2.83085109331264e-06, "loss": 0.826, "step": 105610 }, { "epoch": 8.78, "learning_rate": 2.830740237785107e-06, "loss": 0.7668, "step": 105620 }, { "epoch": 8.78, "learning_rate": 2.8306293822575727e-06, "loss": 0.7939, "step": 105630 }, { "epoch": 8.78, "learning_rate": 2.830518526730039e-06, "loss": 0.7754, "step": 105640 }, { "epoch": 8.78, "learning_rate": 2.8304076712025053e-06, "loss": 0.8083, "step": 105650 }, { "epoch": 8.78, "learning_rate": 2.8302968156749716e-06, "loss": 0.8714, "step": 105660 }, { "epoch": 8.78, "learning_rate": 2.8301859601474374e-06, "loss": 0.7941, "step": 105670 }, { "epoch": 8.78, "learning_rate": 2.830075104619904e-06, "loss": 0.8611, "step": 105680 }, { "epoch": 8.78, "learning_rate": 2.82996424909237e-06, "loss": 0.7978, "step": 105690 }, { "epoch": 8.79, "learning_rate": 2.8298533935648367e-06, "loss": 0.8228, "step": 105700 }, { "epoch": 8.79, "learning_rate": 2.8297425380373026e-06, "loss": 0.8098, "step": 105710 }, { "epoch": 8.79, "learning_rate": 2.829631682509769e-06, "loss": 0.7998, "step": 105720 }, { "epoch": 8.79, "learning_rate": 2.8295208269822356e-06, "loss": 0.7764, "step": 105730 }, { "epoch": 8.79, "learning_rate": 2.8294099714547015e-06, "loss": 0.777, "step": 105740 }, { "epoch": 8.79, "learning_rate": 2.829299115927168e-06, "loss": 0.8335, "step": 105750 }, { "epoch": 8.79, "learning_rate": 2.829188260399634e-06, "loss": 0.8687, "step": 105760 }, { "epoch": 8.79, "learning_rate": 2.8290774048721004e-06, "loss": 0.8035, "step": 105770 }, { "epoch": 8.79, "learning_rate": 2.8289665493445663e-06, "loss": 0.7341, "step": 105780 }, { "epoch": 8.79, "learning_rate": 2.828855693817033e-06, "loss": 0.7891, "step": 105790 }, { "epoch": 8.79, "learning_rate": 2.828744838289499e-06, "loss": 0.7396, "step": 105800 }, { "epoch": 8.79, "learning_rate": 2.8286339827619656e-06, "loss": 0.8381, "step": 105810 }, { "epoch": 8.8, "learning_rate": 2.8285231272344314e-06, "loss": 0.7852, "step": 105820 }, { "epoch": 8.8, "learning_rate": 2.8284122717068977e-06, "loss": 0.7621, "step": 105830 }, { "epoch": 8.8, "learning_rate": 2.828301416179364e-06, "loss": 0.8519, "step": 105840 }, { "epoch": 8.8, "learning_rate": 2.8281905606518303e-06, "loss": 0.7567, "step": 105850 }, { "epoch": 8.8, "learning_rate": 2.8280797051242966e-06, "loss": 0.8361, "step": 105860 }, { "epoch": 8.8, "learning_rate": 2.827968849596763e-06, "loss": 0.7352, "step": 105870 }, { "epoch": 8.8, "learning_rate": 2.8278579940692292e-06, "loss": 0.7933, "step": 105880 }, { "epoch": 8.8, "learning_rate": 2.8277471385416955e-06, "loss": 0.7362, "step": 105890 }, { "epoch": 8.8, "learning_rate": 2.827636283014162e-06, "loss": 0.8155, "step": 105900 }, { "epoch": 8.8, "learning_rate": 2.8275254274866277e-06, "loss": 0.8469, "step": 105910 }, { "epoch": 8.8, "learning_rate": 2.8274145719590944e-06, "loss": 0.7913, "step": 105920 }, { "epoch": 8.8, "learning_rate": 2.8273037164315603e-06, "loss": 0.7917, "step": 105930 }, { "epoch": 8.81, "learning_rate": 2.8271928609040266e-06, "loss": 0.8434, "step": 105940 }, { "epoch": 8.81, "learning_rate": 2.827082005376493e-06, "loss": 0.8301, "step": 105950 }, { "epoch": 8.81, "learning_rate": 2.826971149848959e-06, "loss": 0.8016, "step": 105960 }, { "epoch": 8.81, "learning_rate": 2.8268602943214254e-06, "loss": 0.7738, "step": 105970 }, { "epoch": 8.81, "learning_rate": 2.8267494387938917e-06, "loss": 0.8271, "step": 105980 }, { "epoch": 8.81, "learning_rate": 2.826638583266358e-06, "loss": 0.7911, "step": 105990 }, { "epoch": 8.81, "learning_rate": 2.8265277277388243e-06, "loss": 0.8345, "step": 106000 }, { "epoch": 8.81, "learning_rate": 2.8264168722112906e-06, "loss": 0.9058, "step": 106010 }, { "epoch": 8.81, "learning_rate": 2.8263060166837565e-06, "loss": 0.8505, "step": 106020 }, { "epoch": 8.81, "learning_rate": 2.8261951611562232e-06, "loss": 0.784, "step": 106030 }, { "epoch": 8.81, "learning_rate": 2.826084305628689e-06, "loss": 0.842, "step": 106040 }, { "epoch": 8.81, "learning_rate": 2.825973450101156e-06, "loss": 0.8246, "step": 106050 }, { "epoch": 8.82, "learning_rate": 2.8258625945736217e-06, "loss": 0.844, "step": 106060 }, { "epoch": 8.82, "learning_rate": 2.825751739046088e-06, "loss": 0.8316, "step": 106070 }, { "epoch": 8.82, "learning_rate": 2.8256408835185543e-06, "loss": 0.8104, "step": 106080 }, { "epoch": 8.82, "learning_rate": 2.8255300279910206e-06, "loss": 0.7958, "step": 106090 }, { "epoch": 8.82, "learning_rate": 2.825419172463487e-06, "loss": 0.781, "step": 106100 }, { "epoch": 8.82, "learning_rate": 2.825308316935953e-06, "loss": 0.937, "step": 106110 }, { "epoch": 8.82, "learning_rate": 2.8251974614084195e-06, "loss": 0.8225, "step": 106120 }, { "epoch": 8.82, "learning_rate": 2.8250866058808858e-06, "loss": 0.791, "step": 106130 }, { "epoch": 8.82, "learning_rate": 2.824975750353352e-06, "loss": 0.7445, "step": 106140 }, { "epoch": 8.82, "learning_rate": 2.824864894825818e-06, "loss": 0.7939, "step": 106150 }, { "epoch": 8.82, "learning_rate": 2.8247540392982846e-06, "loss": 0.863, "step": 106160 }, { "epoch": 8.82, "learning_rate": 2.8246431837707505e-06, "loss": 0.8144, "step": 106170 }, { "epoch": 8.83, "learning_rate": 2.824532328243217e-06, "loss": 0.7314, "step": 106180 }, { "epoch": 8.83, "learning_rate": 2.824421472715683e-06, "loss": 0.8419, "step": 106190 }, { "epoch": 8.83, "learning_rate": 2.8243106171881494e-06, "loss": 0.8055, "step": 106200 }, { "epoch": 8.83, "learning_rate": 2.8241997616606153e-06, "loss": 0.8415, "step": 106210 }, { "epoch": 8.83, "learning_rate": 2.824088906133082e-06, "loss": 0.8068, "step": 106220 }, { "epoch": 8.83, "learning_rate": 2.8239780506055483e-06, "loss": 0.7761, "step": 106230 }, { "epoch": 8.83, "learning_rate": 2.8238671950780146e-06, "loss": 0.8183, "step": 106240 }, { "epoch": 8.83, "learning_rate": 2.823756339550481e-06, "loss": 0.7469, "step": 106250 }, { "epoch": 8.83, "learning_rate": 2.8236454840229467e-06, "loss": 0.8731, "step": 106260 }, { "epoch": 8.83, "learning_rate": 2.8235346284954135e-06, "loss": 0.8632, "step": 106270 }, { "epoch": 8.83, "learning_rate": 2.8234237729678793e-06, "loss": 0.8307, "step": 106280 }, { "epoch": 8.83, "learning_rate": 2.8233129174403456e-06, "loss": 0.7465, "step": 106290 }, { "epoch": 8.84, "learning_rate": 2.823202061912812e-06, "loss": 0.8082, "step": 106300 }, { "epoch": 8.84, "learning_rate": 2.8230912063852782e-06, "loss": 0.8297, "step": 106310 }, { "epoch": 8.84, "learning_rate": 2.8229803508577445e-06, "loss": 0.8149, "step": 106320 }, { "epoch": 8.84, "learning_rate": 2.822869495330211e-06, "loss": 0.803, "step": 106330 }, { "epoch": 8.84, "learning_rate": 2.822758639802677e-06, "loss": 0.7911, "step": 106340 }, { "epoch": 8.84, "learning_rate": 2.8226477842751434e-06, "loss": 0.8201, "step": 106350 }, { "epoch": 8.84, "learning_rate": 2.8225369287476097e-06, "loss": 0.8075, "step": 106360 }, { "epoch": 8.84, "learning_rate": 2.8224260732200756e-06, "loss": 0.7822, "step": 106370 }, { "epoch": 8.84, "learning_rate": 2.8223152176925423e-06, "loss": 0.7643, "step": 106380 }, { "epoch": 8.84, "learning_rate": 2.822204362165008e-06, "loss": 0.7793, "step": 106390 }, { "epoch": 8.84, "learning_rate": 2.822093506637475e-06, "loss": 0.747, "step": 106400 }, { "epoch": 8.84, "learning_rate": 2.8219826511099407e-06, "loss": 0.8741, "step": 106410 }, { "epoch": 8.85, "learning_rate": 2.821871795582407e-06, "loss": 0.8987, "step": 106420 }, { "epoch": 8.85, "learning_rate": 2.8217609400548733e-06, "loss": 0.7602, "step": 106430 }, { "epoch": 8.85, "learning_rate": 2.8216500845273396e-06, "loss": 0.8446, "step": 106440 }, { "epoch": 8.85, "learning_rate": 2.8215392289998055e-06, "loss": 0.8013, "step": 106450 }, { "epoch": 8.85, "learning_rate": 2.8214283734722722e-06, "loss": 0.9073, "step": 106460 }, { "epoch": 8.85, "learning_rate": 2.8213175179447385e-06, "loss": 0.8472, "step": 106470 }, { "epoch": 8.85, "learning_rate": 2.821206662417205e-06, "loss": 0.8106, "step": 106480 }, { "epoch": 8.85, "learning_rate": 2.821095806889671e-06, "loss": 0.7706, "step": 106490 }, { "epoch": 8.85, "learning_rate": 2.820984951362137e-06, "loss": 0.7964, "step": 106500 }, { "epoch": 8.85, "learning_rate": 2.8208740958346037e-06, "loss": 0.8823, "step": 106510 }, { "epoch": 8.85, "learning_rate": 2.8207632403070696e-06, "loss": 0.7913, "step": 106520 }, { "epoch": 8.85, "learning_rate": 2.820652384779536e-06, "loss": 0.747, "step": 106530 }, { "epoch": 8.86, "learning_rate": 2.820541529252002e-06, "loss": 0.7515, "step": 106540 }, { "epoch": 8.86, "learning_rate": 2.8204306737244685e-06, "loss": 0.8272, "step": 106550 }, { "epoch": 8.86, "learning_rate": 2.8203198181969343e-06, "loss": 0.7845, "step": 106560 }, { "epoch": 8.86, "learning_rate": 2.820208962669401e-06, "loss": 0.7827, "step": 106570 }, { "epoch": 8.86, "learning_rate": 2.820098107141867e-06, "loss": 0.7731, "step": 106580 }, { "epoch": 8.86, "learning_rate": 2.8199872516143336e-06, "loss": 0.8167, "step": 106590 }, { "epoch": 8.86, "learning_rate": 2.8198763960868e-06, "loss": 0.8117, "step": 106600 }, { "epoch": 8.86, "learning_rate": 2.819765540559266e-06, "loss": 0.907, "step": 106610 }, { "epoch": 8.86, "learning_rate": 2.8196546850317325e-06, "loss": 0.7526, "step": 106620 }, { "epoch": 8.86, "learning_rate": 2.8195438295041984e-06, "loss": 0.789, "step": 106630 }, { "epoch": 8.86, "learning_rate": 2.819432973976665e-06, "loss": 0.8092, "step": 106640 }, { "epoch": 8.86, "learning_rate": 2.819322118449131e-06, "loss": 0.8048, "step": 106650 }, { "epoch": 8.87, "learning_rate": 2.8192112629215973e-06, "loss": 0.8704, "step": 106660 }, { "epoch": 8.87, "learning_rate": 2.8191004073940636e-06, "loss": 0.8772, "step": 106670 }, { "epoch": 8.87, "learning_rate": 2.81898955186653e-06, "loss": 0.8187, "step": 106680 }, { "epoch": 8.87, "learning_rate": 2.8188786963389957e-06, "loss": 0.7921, "step": 106690 }, { "epoch": 8.87, "learning_rate": 2.8187678408114625e-06, "loss": 0.7909, "step": 106700 }, { "epoch": 8.87, "learning_rate": 2.8186569852839288e-06, "loss": 0.8538, "step": 106710 }, { "epoch": 8.87, "learning_rate": 2.8185461297563946e-06, "loss": 0.8731, "step": 106720 }, { "epoch": 8.87, "learning_rate": 2.8184352742288614e-06, "loss": 0.8766, "step": 106730 }, { "epoch": 8.87, "learning_rate": 2.8183244187013272e-06, "loss": 0.8239, "step": 106740 }, { "epoch": 8.87, "learning_rate": 2.818213563173794e-06, "loss": 0.7609, "step": 106750 }, { "epoch": 8.87, "learning_rate": 2.81810270764626e-06, "loss": 0.8263, "step": 106760 }, { "epoch": 8.87, "learning_rate": 2.817991852118726e-06, "loss": 0.7811, "step": 106770 }, { "epoch": 8.88, "learning_rate": 2.8178809965911924e-06, "loss": 0.7606, "step": 106780 }, { "epoch": 8.88, "learning_rate": 2.8177701410636587e-06, "loss": 0.8223, "step": 106790 }, { "epoch": 8.88, "learning_rate": 2.8176592855361246e-06, "loss": 0.7502, "step": 106800 }, { "epoch": 8.88, "learning_rate": 2.8175484300085913e-06, "loss": 0.819, "step": 106810 }, { "epoch": 8.88, "learning_rate": 2.817437574481057e-06, "loss": 0.8249, "step": 106820 }, { "epoch": 8.88, "learning_rate": 2.817326718953524e-06, "loss": 0.7949, "step": 106830 }, { "epoch": 8.88, "learning_rate": 2.81721586342599e-06, "loss": 0.8591, "step": 106840 }, { "epoch": 8.88, "learning_rate": 2.817105007898456e-06, "loss": 0.8728, "step": 106850 }, { "epoch": 8.88, "learning_rate": 2.8169941523709228e-06, "loss": 0.8237, "step": 106860 }, { "epoch": 8.88, "learning_rate": 2.8168832968433886e-06, "loss": 0.787, "step": 106870 }, { "epoch": 8.88, "learning_rate": 2.816772441315855e-06, "loss": 0.7203, "step": 106880 }, { "epoch": 8.88, "learning_rate": 2.8166615857883212e-06, "loss": 0.7727, "step": 106890 }, { "epoch": 8.89, "learning_rate": 2.8165507302607875e-06, "loss": 0.8303, "step": 106900 }, { "epoch": 8.89, "learning_rate": 2.816439874733254e-06, "loss": 0.8388, "step": 106910 }, { "epoch": 8.89, "learning_rate": 2.81632901920572e-06, "loss": 0.8172, "step": 106920 }, { "epoch": 8.89, "learning_rate": 2.816218163678186e-06, "loss": 0.7584, "step": 106930 }, { "epoch": 8.89, "learning_rate": 2.8161073081506527e-06, "loss": 0.8201, "step": 106940 }, { "epoch": 8.89, "learning_rate": 2.8159964526231186e-06, "loss": 0.8214, "step": 106950 }, { "epoch": 8.89, "learning_rate": 2.815885597095585e-06, "loss": 0.7677, "step": 106960 }, { "epoch": 8.89, "learning_rate": 2.8157747415680516e-06, "loss": 0.7992, "step": 106970 }, { "epoch": 8.89, "learning_rate": 2.8156638860405175e-06, "loss": 0.7441, "step": 106980 }, { "epoch": 8.89, "learning_rate": 2.815553030512984e-06, "loss": 0.8259, "step": 106990 }, { "epoch": 8.89, "learning_rate": 2.81544217498545e-06, "loss": 0.7646, "step": 107000 }, { "epoch": 8.89, "learning_rate": 2.8153313194579164e-06, "loss": 0.8291, "step": 107010 }, { "epoch": 8.9, "learning_rate": 2.8152204639303826e-06, "loss": 0.7378, "step": 107020 }, { "epoch": 8.9, "learning_rate": 2.815109608402849e-06, "loss": 0.8945, "step": 107030 }, { "epoch": 8.9, "learning_rate": 2.814998752875315e-06, "loss": 0.8351, "step": 107040 }, { "epoch": 8.9, "learning_rate": 2.8148878973477815e-06, "loss": 0.7932, "step": 107050 }, { "epoch": 8.9, "learning_rate": 2.8147770418202474e-06, "loss": 0.7544, "step": 107060 }, { "epoch": 8.9, "learning_rate": 2.8146661862927137e-06, "loss": 0.8071, "step": 107070 }, { "epoch": 8.9, "learning_rate": 2.8145553307651804e-06, "loss": 0.7839, "step": 107080 }, { "epoch": 8.9, "learning_rate": 2.8144444752376463e-06, "loss": 0.842, "step": 107090 }, { "epoch": 8.9, "learning_rate": 2.814333619710113e-06, "loss": 0.7893, "step": 107100 }, { "epoch": 8.9, "learning_rate": 2.814222764182579e-06, "loss": 0.8215, "step": 107110 }, { "epoch": 8.9, "learning_rate": 2.814111908655045e-06, "loss": 0.7543, "step": 107120 }, { "epoch": 8.9, "learning_rate": 2.8140010531275115e-06, "loss": 0.777, "step": 107130 }, { "epoch": 8.91, "learning_rate": 2.8138901975999778e-06, "loss": 0.7858, "step": 107140 }, { "epoch": 8.91, "learning_rate": 2.8137793420724436e-06, "loss": 0.8217, "step": 107150 }, { "epoch": 8.91, "learning_rate": 2.8136684865449104e-06, "loss": 0.8238, "step": 107160 }, { "epoch": 8.91, "learning_rate": 2.8135576310173762e-06, "loss": 0.8599, "step": 107170 }, { "epoch": 8.91, "learning_rate": 2.813446775489843e-06, "loss": 0.8688, "step": 107180 }, { "epoch": 8.91, "learning_rate": 2.813335919962309e-06, "loss": 0.7675, "step": 107190 }, { "epoch": 8.91, "learning_rate": 2.813225064434775e-06, "loss": 0.82, "step": 107200 }, { "epoch": 8.91, "learning_rate": 2.813114208907242e-06, "loss": 0.8511, "step": 107210 }, { "epoch": 8.91, "learning_rate": 2.8130033533797077e-06, "loss": 0.837, "step": 107220 }, { "epoch": 8.91, "learning_rate": 2.812892497852174e-06, "loss": 0.7844, "step": 107230 }, { "epoch": 8.91, "learning_rate": 2.8127816423246403e-06, "loss": 0.7769, "step": 107240 }, { "epoch": 8.91, "learning_rate": 2.8126707867971066e-06, "loss": 0.8843, "step": 107250 }, { "epoch": 8.92, "learning_rate": 2.812559931269573e-06, "loss": 0.8679, "step": 107260 }, { "epoch": 8.92, "learning_rate": 2.812449075742039e-06, "loss": 0.7426, "step": 107270 }, { "epoch": 8.92, "learning_rate": 2.812338220214505e-06, "loss": 0.7912, "step": 107280 }, { "epoch": 8.92, "learning_rate": 2.8122273646869718e-06, "loss": 0.7671, "step": 107290 }, { "epoch": 8.92, "learning_rate": 2.8121165091594376e-06, "loss": 0.7727, "step": 107300 }, { "epoch": 8.92, "learning_rate": 2.812005653631904e-06, "loss": 0.8065, "step": 107310 }, { "epoch": 8.92, "learning_rate": 2.8118947981043702e-06, "loss": 0.804, "step": 107320 }, { "epoch": 8.92, "learning_rate": 2.8117839425768365e-06, "loss": 0.8168, "step": 107330 }, { "epoch": 8.92, "learning_rate": 2.8116730870493033e-06, "loss": 0.7628, "step": 107340 }, { "epoch": 8.92, "learning_rate": 2.811562231521769e-06, "loss": 0.7928, "step": 107350 }, { "epoch": 8.92, "learning_rate": 2.8114513759942354e-06, "loss": 0.8704, "step": 107360 }, { "epoch": 8.92, "learning_rate": 2.8113405204667017e-06, "loss": 0.7948, "step": 107370 }, { "epoch": 8.93, "learning_rate": 2.811229664939168e-06, "loss": 0.7897, "step": 107380 }, { "epoch": 8.93, "learning_rate": 2.811118809411634e-06, "loss": 0.756, "step": 107390 }, { "epoch": 8.93, "learning_rate": 2.8110079538841006e-06, "loss": 0.8045, "step": 107400 }, { "epoch": 8.93, "learning_rate": 2.8108970983565665e-06, "loss": 0.8462, "step": 107410 }, { "epoch": 8.93, "learning_rate": 2.810786242829033e-06, "loss": 0.8081, "step": 107420 }, { "epoch": 8.93, "learning_rate": 2.810675387301499e-06, "loss": 0.7627, "step": 107430 }, { "epoch": 8.93, "learning_rate": 2.8105645317739654e-06, "loss": 0.8288, "step": 107440 }, { "epoch": 8.93, "learning_rate": 2.810453676246432e-06, "loss": 0.745, "step": 107450 }, { "epoch": 8.93, "learning_rate": 2.810342820718898e-06, "loss": 0.8124, "step": 107460 }, { "epoch": 8.93, "learning_rate": 2.8102319651913642e-06, "loss": 0.7836, "step": 107470 }, { "epoch": 8.93, "learning_rate": 2.8101211096638305e-06, "loss": 0.7979, "step": 107480 }, { "epoch": 8.93, "learning_rate": 2.810010254136297e-06, "loss": 0.8038, "step": 107490 }, { "epoch": 8.94, "learning_rate": 2.8098993986087627e-06, "loss": 0.7816, "step": 107500 }, { "epoch": 8.94, "learning_rate": 2.8097885430812294e-06, "loss": 0.911, "step": 107510 }, { "epoch": 8.94, "learning_rate": 2.8096776875536953e-06, "loss": 0.772, "step": 107520 }, { "epoch": 8.94, "learning_rate": 2.809566832026162e-06, "loss": 0.7443, "step": 107530 }, { "epoch": 8.94, "learning_rate": 2.809455976498628e-06, "loss": 0.7905, "step": 107540 }, { "epoch": 8.94, "learning_rate": 2.809345120971094e-06, "loss": 0.8692, "step": 107550 }, { "epoch": 8.94, "learning_rate": 2.8092342654435605e-06, "loss": 0.8508, "step": 107560 }, { "epoch": 8.94, "learning_rate": 2.8091234099160268e-06, "loss": 0.7738, "step": 107570 }, { "epoch": 8.94, "learning_rate": 2.809012554388493e-06, "loss": 0.8685, "step": 107580 }, { "epoch": 8.94, "learning_rate": 2.8089016988609594e-06, "loss": 0.8397, "step": 107590 }, { "epoch": 8.94, "learning_rate": 2.8087908433334257e-06, "loss": 0.8451, "step": 107600 }, { "epoch": 8.94, "learning_rate": 2.808679987805892e-06, "loss": 0.8425, "step": 107610 }, { "epoch": 8.95, "learning_rate": 2.8085691322783583e-06, "loss": 0.8488, "step": 107620 }, { "epoch": 8.95, "learning_rate": 2.808458276750824e-06, "loss": 0.7853, "step": 107630 }, { "epoch": 8.95, "learning_rate": 2.808347421223291e-06, "loss": 0.838, "step": 107640 }, { "epoch": 8.95, "learning_rate": 2.8082365656957567e-06, "loss": 0.7945, "step": 107650 }, { "epoch": 8.95, "learning_rate": 2.808125710168223e-06, "loss": 0.8494, "step": 107660 }, { "epoch": 8.95, "learning_rate": 2.8080148546406893e-06, "loss": 0.7974, "step": 107670 }, { "epoch": 8.95, "learning_rate": 2.8079039991131556e-06, "loss": 0.7581, "step": 107680 }, { "epoch": 8.95, "learning_rate": 2.807793143585622e-06, "loss": 0.8024, "step": 107690 }, { "epoch": 8.95, "learning_rate": 2.807682288058088e-06, "loss": 0.8379, "step": 107700 }, { "epoch": 8.95, "learning_rate": 2.8075714325305545e-06, "loss": 0.8433, "step": 107710 }, { "epoch": 8.95, "learning_rate": 2.8074605770030208e-06, "loss": 0.8267, "step": 107720 }, { "epoch": 8.95, "learning_rate": 2.807349721475487e-06, "loss": 0.7602, "step": 107730 }, { "epoch": 8.96, "learning_rate": 2.807238865947953e-06, "loss": 0.7977, "step": 107740 }, { "epoch": 8.96, "learning_rate": 2.8071280104204197e-06, "loss": 0.8193, "step": 107750 }, { "epoch": 8.96, "learning_rate": 2.8070171548928855e-06, "loss": 0.8293, "step": 107760 }, { "epoch": 8.96, "learning_rate": 2.8069062993653523e-06, "loss": 0.8138, "step": 107770 }, { "epoch": 8.96, "learning_rate": 2.806795443837818e-06, "loss": 0.8336, "step": 107780 }, { "epoch": 8.96, "learning_rate": 2.8066845883102844e-06, "loss": 0.7612, "step": 107790 }, { "epoch": 8.96, "learning_rate": 2.8065737327827507e-06, "loss": 0.7829, "step": 107800 }, { "epoch": 8.96, "learning_rate": 2.806462877255217e-06, "loss": 0.7914, "step": 107810 }, { "epoch": 8.96, "learning_rate": 2.8063520217276833e-06, "loss": 0.8308, "step": 107820 }, { "epoch": 8.96, "learning_rate": 2.8062411662001496e-06, "loss": 0.7258, "step": 107830 }, { "epoch": 8.96, "learning_rate": 2.806130310672616e-06, "loss": 0.7336, "step": 107840 }, { "epoch": 8.96, "learning_rate": 2.8060194551450818e-06, "loss": 0.8051, "step": 107850 }, { "epoch": 8.97, "learning_rate": 2.8059085996175485e-06, "loss": 0.7908, "step": 107860 }, { "epoch": 8.97, "learning_rate": 2.8057977440900144e-06, "loss": 0.705, "step": 107870 }, { "epoch": 8.97, "learning_rate": 2.805686888562481e-06, "loss": 0.7902, "step": 107880 }, { "epoch": 8.97, "learning_rate": 2.805576033034947e-06, "loss": 0.8433, "step": 107890 }, { "epoch": 8.97, "learning_rate": 2.8054651775074132e-06, "loss": 0.8092, "step": 107900 }, { "epoch": 8.97, "learning_rate": 2.8053543219798795e-06, "loss": 0.7897, "step": 107910 }, { "epoch": 8.97, "learning_rate": 2.805243466452346e-06, "loss": 0.8333, "step": 107920 }, { "epoch": 8.97, "learning_rate": 2.8051326109248117e-06, "loss": 0.7813, "step": 107930 }, { "epoch": 8.97, "learning_rate": 2.8050217553972784e-06, "loss": 0.7764, "step": 107940 }, { "epoch": 8.97, "learning_rate": 2.8049108998697447e-06, "loss": 0.8065, "step": 107950 }, { "epoch": 8.97, "learning_rate": 2.804800044342211e-06, "loss": 0.8254, "step": 107960 }, { "epoch": 8.97, "learning_rate": 2.8046891888146773e-06, "loss": 0.7719, "step": 107970 }, { "epoch": 8.98, "learning_rate": 2.804578333287143e-06, "loss": 0.7864, "step": 107980 }, { "epoch": 8.98, "learning_rate": 2.80446747775961e-06, "loss": 0.7913, "step": 107990 }, { "epoch": 8.98, "learning_rate": 2.8043566222320758e-06, "loss": 0.8124, "step": 108000 }, { "epoch": 8.98, "learning_rate": 2.804245766704542e-06, "loss": 0.8503, "step": 108010 }, { "epoch": 8.98, "learning_rate": 2.8041349111770084e-06, "loss": 0.8144, "step": 108020 }, { "epoch": 8.98, "learning_rate": 2.8040240556494747e-06, "loss": 0.7809, "step": 108030 }, { "epoch": 8.98, "learning_rate": 2.803913200121941e-06, "loss": 0.7924, "step": 108040 }, { "epoch": 8.98, "learning_rate": 2.8038023445944073e-06, "loss": 0.7986, "step": 108050 }, { "epoch": 8.98, "learning_rate": 2.803691489066873e-06, "loss": 0.7917, "step": 108060 }, { "epoch": 8.98, "learning_rate": 2.80358063353934e-06, "loss": 0.8762, "step": 108070 }, { "epoch": 8.98, "learning_rate": 2.803469778011806e-06, "loss": 0.8379, "step": 108080 }, { "epoch": 8.98, "learning_rate": 2.803358922484272e-06, "loss": 0.8519, "step": 108090 }, { "epoch": 8.99, "learning_rate": 2.8032480669567387e-06, "loss": 0.8333, "step": 108100 }, { "epoch": 8.99, "learning_rate": 2.8031372114292046e-06, "loss": 0.8805, "step": 108110 }, { "epoch": 8.99, "learning_rate": 2.8030263559016713e-06, "loss": 0.8161, "step": 108120 }, { "epoch": 8.99, "learning_rate": 2.802915500374137e-06, "loss": 0.8058, "step": 108130 }, { "epoch": 8.99, "learning_rate": 2.8028046448466035e-06, "loss": 0.8005, "step": 108140 }, { "epoch": 8.99, "learning_rate": 2.8026937893190698e-06, "loss": 0.8214, "step": 108150 }, { "epoch": 8.99, "learning_rate": 2.802582933791536e-06, "loss": 0.8723, "step": 108160 }, { "epoch": 8.99, "learning_rate": 2.802472078264002e-06, "loss": 0.7721, "step": 108170 }, { "epoch": 8.99, "learning_rate": 2.8023612227364687e-06, "loss": 0.8261, "step": 108180 }, { "epoch": 8.99, "learning_rate": 2.802250367208935e-06, "loss": 0.8307, "step": 108190 }, { "epoch": 8.99, "learning_rate": 2.8021395116814013e-06, "loss": 0.7338, "step": 108200 }, { "epoch": 8.99, "learning_rate": 2.8020286561538676e-06, "loss": 0.8633, "step": 108210 }, { "epoch": 9.0, "learning_rate": 2.8019178006263334e-06, "loss": 0.7937, "step": 108220 }, { "epoch": 9.0, "learning_rate": 2.8018069450988e-06, "loss": 0.8396, "step": 108230 }, { "epoch": 9.0, "learning_rate": 2.801696089571266e-06, "loss": 0.8293, "step": 108240 }, { "epoch": 9.0, "learning_rate": 2.8015852340437323e-06, "loss": 0.804, "step": 108250 }, { "epoch": 9.0, "learning_rate": 2.8014743785161986e-06, "loss": 0.7534, "step": 108260 }, { "epoch": 9.0, "learning_rate": 2.801363522988665e-06, "loss": 0.7512, "step": 108270 }, { "epoch": 9.0, "eval_loss": 1.1222608089447021, "eval_runtime": 351.8913, "eval_samples_per_second": 7.599, "eval_steps_per_second": 3.799, "eval_wer": 0.6592457609959835, "step": 108279 }, { "epoch": 9.0, "learning_rate": 2.8012526674611308e-06, "loss": 0.857, "step": 108280 }, { "epoch": 9.0, "learning_rate": 2.8011418119335975e-06, "loss": 0.9194, "step": 108290 }, { "epoch": 9.0, "learning_rate": 2.8010309564060634e-06, "loss": 0.7355, "step": 108300 }, { "epoch": 9.0, "learning_rate": 2.80092010087853e-06, "loss": 0.8091, "step": 108310 }, { "epoch": 9.0, "learning_rate": 2.8008092453509964e-06, "loss": 0.7813, "step": 108320 }, { "epoch": 9.0, "learning_rate": 2.8006983898234623e-06, "loss": 0.8395, "step": 108330 }, { "epoch": 9.01, "learning_rate": 2.800587534295929e-06, "loss": 0.8232, "step": 108340 }, { "epoch": 9.01, "learning_rate": 2.800476678768395e-06, "loss": 0.7424, "step": 108350 }, { "epoch": 9.01, "learning_rate": 2.800365823240861e-06, "loss": 0.8656, "step": 108360 }, { "epoch": 9.01, "learning_rate": 2.8002549677133274e-06, "loss": 0.8446, "step": 108370 }, { "epoch": 9.01, "learning_rate": 2.8001441121857937e-06, "loss": 0.7528, "step": 108380 }, { "epoch": 9.01, "learning_rate": 2.80003325665826e-06, "loss": 0.7956, "step": 108390 }, { "epoch": 9.01, "learning_rate": 2.7999224011307263e-06, "loss": 0.8329, "step": 108400 }, { "epoch": 9.01, "learning_rate": 2.799811545603192e-06, "loss": 0.8302, "step": 108410 }, { "epoch": 9.01, "learning_rate": 2.799700690075659e-06, "loss": 0.8127, "step": 108420 }, { "epoch": 9.01, "learning_rate": 2.799589834548125e-06, "loss": 0.8166, "step": 108430 }, { "epoch": 9.01, "learning_rate": 2.799478979020591e-06, "loss": 0.8211, "step": 108440 }, { "epoch": 9.01, "learning_rate": 2.799368123493058e-06, "loss": 0.7781, "step": 108450 }, { "epoch": 9.02, "learning_rate": 2.7992572679655237e-06, "loss": 0.8113, "step": 108460 }, { "epoch": 9.02, "learning_rate": 2.7991464124379904e-06, "loss": 0.7698, "step": 108470 }, { "epoch": 9.02, "learning_rate": 2.7990355569104563e-06, "loss": 0.8492, "step": 108480 }, { "epoch": 9.02, "learning_rate": 2.7989247013829226e-06, "loss": 0.8145, "step": 108490 }, { "epoch": 9.02, "learning_rate": 2.798813845855389e-06, "loss": 0.8144, "step": 108500 }, { "epoch": 9.02, "learning_rate": 2.798702990327855e-06, "loss": 0.7892, "step": 108510 }, { "epoch": 9.02, "learning_rate": 2.798592134800321e-06, "loss": 0.836, "step": 108520 }, { "epoch": 9.02, "learning_rate": 2.7984812792727877e-06, "loss": 0.8329, "step": 108530 }, { "epoch": 9.02, "learning_rate": 2.7983704237452536e-06, "loss": 0.8446, "step": 108540 }, { "epoch": 9.02, "learning_rate": 2.7982595682177203e-06, "loss": 0.8432, "step": 108550 }, { "epoch": 9.02, "learning_rate": 2.7981487126901866e-06, "loss": 0.8161, "step": 108560 }, { "epoch": 9.02, "learning_rate": 2.7980378571626525e-06, "loss": 0.7224, "step": 108570 }, { "epoch": 9.03, "learning_rate": 2.7979270016351192e-06, "loss": 0.7761, "step": 108580 }, { "epoch": 9.03, "learning_rate": 2.797816146107585e-06, "loss": 0.8223, "step": 108590 }, { "epoch": 9.03, "learning_rate": 2.7977052905800514e-06, "loss": 0.8085, "step": 108600 }, { "epoch": 9.03, "learning_rate": 2.7975944350525177e-06, "loss": 0.8493, "step": 108610 }, { "epoch": 9.03, "learning_rate": 2.797483579524984e-06, "loss": 0.8633, "step": 108620 }, { "epoch": 9.03, "learning_rate": 2.7973727239974503e-06, "loss": 0.7769, "step": 108630 }, { "epoch": 9.03, "learning_rate": 2.7972618684699166e-06, "loss": 0.8924, "step": 108640 }, { "epoch": 9.03, "learning_rate": 2.7971510129423824e-06, "loss": 0.7307, "step": 108650 }, { "epoch": 9.03, "learning_rate": 2.797040157414849e-06, "loss": 0.8422, "step": 108660 }, { "epoch": 9.03, "learning_rate": 2.796929301887315e-06, "loss": 0.6896, "step": 108670 }, { "epoch": 9.03, "learning_rate": 2.7968184463597813e-06, "loss": 0.8194, "step": 108680 }, { "epoch": 9.03, "learning_rate": 2.796707590832248e-06, "loss": 0.845, "step": 108690 }, { "epoch": 9.03, "learning_rate": 2.796596735304714e-06, "loss": 0.8161, "step": 108700 }, { "epoch": 9.04, "learning_rate": 2.7964858797771806e-06, "loss": 0.852, "step": 108710 }, { "epoch": 9.04, "learning_rate": 2.7963750242496465e-06, "loss": 0.8215, "step": 108720 }, { "epoch": 9.04, "learning_rate": 2.796264168722113e-06, "loss": 0.8563, "step": 108730 }, { "epoch": 9.04, "learning_rate": 2.796153313194579e-06, "loss": 0.8436, "step": 108740 }, { "epoch": 9.04, "learning_rate": 2.7960424576670454e-06, "loss": 0.7819, "step": 108750 }, { "epoch": 9.04, "learning_rate": 2.7959316021395113e-06, "loss": 0.7927, "step": 108760 }, { "epoch": 9.04, "learning_rate": 2.795820746611978e-06, "loss": 0.7495, "step": 108770 }, { "epoch": 9.04, "learning_rate": 2.795709891084444e-06, "loss": 0.7809, "step": 108780 }, { "epoch": 9.04, "learning_rate": 2.79559903555691e-06, "loss": 0.8675, "step": 108790 }, { "epoch": 9.04, "learning_rate": 2.795488180029377e-06, "loss": 0.8551, "step": 108800 }, { "epoch": 9.04, "learning_rate": 2.7953773245018427e-06, "loss": 0.841, "step": 108810 }, { "epoch": 9.04, "learning_rate": 2.7952664689743095e-06, "loss": 0.8029, "step": 108820 }, { "epoch": 9.05, "learning_rate": 2.7951556134467753e-06, "loss": 0.7293, "step": 108830 }, { "epoch": 9.05, "learning_rate": 2.7950447579192416e-06, "loss": 0.8637, "step": 108840 }, { "epoch": 9.05, "learning_rate": 2.794933902391708e-06, "loss": 0.8352, "step": 108850 }, { "epoch": 9.05, "learning_rate": 2.7948230468641742e-06, "loss": 0.7968, "step": 108860 }, { "epoch": 9.05, "learning_rate": 2.79471219133664e-06, "loss": 0.8039, "step": 108870 }, { "epoch": 9.05, "learning_rate": 2.794601335809107e-06, "loss": 0.8045, "step": 108880 }, { "epoch": 9.05, "learning_rate": 2.7944904802815727e-06, "loss": 0.7816, "step": 108890 }, { "epoch": 9.05, "learning_rate": 2.7943796247540394e-06, "loss": 0.8081, "step": 108900 }, { "epoch": 9.05, "learning_rate": 2.7942687692265053e-06, "loss": 0.7435, "step": 108910 }, { "epoch": 9.05, "learning_rate": 2.7941579136989716e-06, "loss": 0.859, "step": 108920 }, { "epoch": 9.05, "learning_rate": 2.7940470581714383e-06, "loss": 0.847, "step": 108930 }, { "epoch": 9.05, "learning_rate": 2.793936202643904e-06, "loss": 0.9041, "step": 108940 }, { "epoch": 9.06, "learning_rate": 2.7938253471163704e-06, "loss": 0.7757, "step": 108950 }, { "epoch": 9.06, "learning_rate": 2.7937144915888367e-06, "loss": 0.8399, "step": 108960 }, { "epoch": 9.06, "learning_rate": 2.793603636061303e-06, "loss": 0.7939, "step": 108970 }, { "epoch": 9.06, "learning_rate": 2.7934927805337693e-06, "loss": 0.8582, "step": 108980 }, { "epoch": 9.06, "learning_rate": 2.7933819250062356e-06, "loss": 0.886, "step": 108990 }, { "epoch": 9.06, "learning_rate": 2.7932710694787015e-06, "loss": 0.834, "step": 109000 }, { "epoch": 9.06, "learning_rate": 2.7931602139511682e-06, "loss": 0.7589, "step": 109010 }, { "epoch": 9.06, "learning_rate": 2.793049358423634e-06, "loss": 0.765, "step": 109020 }, { "epoch": 9.06, "learning_rate": 2.7929385028961004e-06, "loss": 0.8249, "step": 109030 }, { "epoch": 9.06, "learning_rate": 2.7928276473685667e-06, "loss": 0.8837, "step": 109040 }, { "epoch": 9.06, "learning_rate": 2.792716791841033e-06, "loss": 0.7828, "step": 109050 }, { "epoch": 9.06, "learning_rate": 2.7926059363134997e-06, "loss": 0.7551, "step": 109060 }, { "epoch": 9.07, "learning_rate": 2.7924950807859656e-06, "loss": 0.7446, "step": 109070 }, { "epoch": 9.07, "learning_rate": 2.792384225258432e-06, "loss": 0.8622, "step": 109080 }, { "epoch": 9.07, "learning_rate": 2.792273369730898e-06, "loss": 0.8696, "step": 109090 }, { "epoch": 9.07, "learning_rate": 2.7921625142033645e-06, "loss": 0.8476, "step": 109100 }, { "epoch": 9.07, "learning_rate": 2.7920516586758303e-06, "loss": 0.7888, "step": 109110 }, { "epoch": 9.07, "learning_rate": 2.791940803148297e-06, "loss": 0.7921, "step": 109120 }, { "epoch": 9.07, "learning_rate": 2.791829947620763e-06, "loss": 0.8517, "step": 109130 }, { "epoch": 9.07, "learning_rate": 2.7917190920932292e-06, "loss": 0.7774, "step": 109140 }, { "epoch": 9.07, "learning_rate": 2.7916082365656955e-06, "loss": 0.825, "step": 109150 }, { "epoch": 9.07, "learning_rate": 2.791497381038162e-06, "loss": 0.8375, "step": 109160 }, { "epoch": 9.07, "learning_rate": 2.7913865255106285e-06, "loss": 0.8333, "step": 109170 }, { "epoch": 9.07, "learning_rate": 2.7912756699830944e-06, "loss": 0.8112, "step": 109180 }, { "epoch": 9.08, "learning_rate": 2.7911648144555607e-06, "loss": 0.8002, "step": 109190 }, { "epoch": 9.08, "learning_rate": 2.791053958928027e-06, "loss": 0.8215, "step": 109200 }, { "epoch": 9.08, "learning_rate": 2.7909431034004933e-06, "loss": 0.7781, "step": 109210 }, { "epoch": 9.08, "learning_rate": 2.790832247872959e-06, "loss": 0.9171, "step": 109220 }, { "epoch": 9.08, "learning_rate": 2.790721392345426e-06, "loss": 0.758, "step": 109230 }, { "epoch": 9.08, "learning_rate": 2.7906105368178917e-06, "loss": 0.8414, "step": 109240 }, { "epoch": 9.08, "learning_rate": 2.7904996812903585e-06, "loss": 0.8398, "step": 109250 }, { "epoch": 9.08, "learning_rate": 2.7903888257628243e-06, "loss": 0.8167, "step": 109260 }, { "epoch": 9.08, "learning_rate": 2.7902779702352906e-06, "loss": 0.8706, "step": 109270 }, { "epoch": 9.08, "learning_rate": 2.790167114707757e-06, "loss": 0.8152, "step": 109280 }, { "epoch": 9.08, "learning_rate": 2.7900562591802232e-06, "loss": 0.8085, "step": 109290 }, { "epoch": 9.08, "learning_rate": 2.7899454036526895e-06, "loss": 0.7577, "step": 109300 }, { "epoch": 9.09, "learning_rate": 2.789834548125156e-06, "loss": 0.7882, "step": 109310 }, { "epoch": 9.09, "learning_rate": 2.789723692597622e-06, "loss": 0.7783, "step": 109320 }, { "epoch": 9.09, "learning_rate": 2.7896128370700884e-06, "loss": 0.7559, "step": 109330 }, { "epoch": 9.09, "learning_rate": 2.7895019815425547e-06, "loss": 0.8348, "step": 109340 }, { "epoch": 9.09, "learning_rate": 2.7893911260150206e-06, "loss": 0.818, "step": 109350 }, { "epoch": 9.09, "learning_rate": 2.7892802704874873e-06, "loss": 0.802, "step": 109360 }, { "epoch": 9.09, "learning_rate": 2.789169414959953e-06, "loss": 0.7811, "step": 109370 }, { "epoch": 9.09, "learning_rate": 2.7890585594324195e-06, "loss": 0.7524, "step": 109380 }, { "epoch": 9.09, "learning_rate": 2.7889477039048857e-06, "loss": 0.8992, "step": 109390 }, { "epoch": 9.09, "learning_rate": 2.788836848377352e-06, "loss": 0.7718, "step": 109400 }, { "epoch": 9.09, "learning_rate": 2.7887259928498183e-06, "loss": 0.8237, "step": 109410 }, { "epoch": 9.09, "learning_rate": 2.7886151373222846e-06, "loss": 0.7848, "step": 109420 }, { "epoch": 9.1, "learning_rate": 2.788504281794751e-06, "loss": 0.8139, "step": 109430 }, { "epoch": 9.1, "learning_rate": 2.7883934262672172e-06, "loss": 0.8141, "step": 109440 }, { "epoch": 9.1, "learning_rate": 2.7882825707396835e-06, "loss": 0.7697, "step": 109450 }, { "epoch": 9.1, "learning_rate": 2.7881717152121494e-06, "loss": 0.8091, "step": 109460 }, { "epoch": 9.1, "learning_rate": 2.788060859684616e-06, "loss": 0.8022, "step": 109470 }, { "epoch": 9.1, "learning_rate": 2.787950004157082e-06, "loss": 0.8374, "step": 109480 }, { "epoch": 9.1, "learning_rate": 2.7878391486295487e-06, "loss": 0.8623, "step": 109490 }, { "epoch": 9.1, "learning_rate": 2.7877282931020146e-06, "loss": 0.8521, "step": 109500 }, { "epoch": 9.1, "learning_rate": 2.787617437574481e-06, "loss": 0.7565, "step": 109510 }, { "epoch": 9.1, "learning_rate": 2.787506582046947e-06, "loss": 0.8634, "step": 109520 }, { "epoch": 9.1, "learning_rate": 2.7873957265194135e-06, "loss": 0.8257, "step": 109530 }, { "epoch": 9.1, "learning_rate": 2.7872848709918798e-06, "loss": 0.8307, "step": 109540 }, { "epoch": 9.11, "learning_rate": 2.787174015464346e-06, "loss": 0.7848, "step": 109550 }, { "epoch": 9.11, "learning_rate": 2.7870631599368123e-06, "loss": 0.7042, "step": 109560 }, { "epoch": 9.11, "learning_rate": 2.7869523044092782e-06, "loss": 0.8159, "step": 109570 }, { "epoch": 9.11, "learning_rate": 2.786841448881745e-06, "loss": 0.8181, "step": 109580 }, { "epoch": 9.11, "learning_rate": 2.786730593354211e-06, "loss": 0.9032, "step": 109590 }, { "epoch": 9.11, "learning_rate": 2.7866197378266775e-06, "loss": 0.7852, "step": 109600 }, { "epoch": 9.11, "learning_rate": 2.7865088822991434e-06, "loss": 0.7467, "step": 109610 }, { "epoch": 9.11, "learning_rate": 2.7863980267716097e-06, "loss": 0.8175, "step": 109620 }, { "epoch": 9.11, "learning_rate": 2.786287171244076e-06, "loss": 0.8193, "step": 109630 }, { "epoch": 9.11, "learning_rate": 2.7861763157165423e-06, "loss": 0.8573, "step": 109640 }, { "epoch": 9.11, "learning_rate": 2.786065460189008e-06, "loss": 0.8479, "step": 109650 }, { "epoch": 9.11, "learning_rate": 2.785954604661475e-06, "loss": 0.7546, "step": 109660 }, { "epoch": 9.12, "learning_rate": 2.785843749133941e-06, "loss": 0.7516, "step": 109670 }, { "epoch": 9.12, "learning_rate": 2.7857439791591607e-06, "loss": 0.8541, "step": 109680 }, { "epoch": 9.12, "learning_rate": 2.785633123631627e-06, "loss": 0.81, "step": 109690 }, { "epoch": 9.12, "learning_rate": 2.7855222681040933e-06, "loss": 0.8275, "step": 109700 }, { "epoch": 9.12, "learning_rate": 2.785411412576559e-06, "loss": 0.7798, "step": 109710 }, { "epoch": 9.12, "learning_rate": 2.785300557049026e-06, "loss": 0.79, "step": 109720 }, { "epoch": 9.12, "learning_rate": 2.7851897015214918e-06, "loss": 0.722, "step": 109730 }, { "epoch": 9.12, "learning_rate": 2.785078845993958e-06, "loss": 0.7945, "step": 109740 }, { "epoch": 9.12, "learning_rate": 2.7849679904664248e-06, "loss": 0.8141, "step": 109750 }, { "epoch": 9.12, "learning_rate": 2.7848571349388906e-06, "loss": 0.777, "step": 109760 }, { "epoch": 9.12, "learning_rate": 2.7847462794113574e-06, "loss": 0.7518, "step": 109770 }, { "epoch": 9.12, "learning_rate": 2.7846354238838232e-06, "loss": 0.7753, "step": 109780 }, { "epoch": 9.13, "learning_rate": 2.7845245683562895e-06, "loss": 0.8068, "step": 109790 }, { "epoch": 9.13, "learning_rate": 2.784413712828756e-06, "loss": 0.759, "step": 109800 }, { "epoch": 9.13, "learning_rate": 2.784302857301222e-06, "loss": 0.7736, "step": 109810 }, { "epoch": 9.13, "learning_rate": 2.784192001773688e-06, "loss": 0.9008, "step": 109820 }, { "epoch": 9.13, "learning_rate": 2.7840811462461547e-06, "loss": 0.8428, "step": 109830 }, { "epoch": 9.13, "learning_rate": 2.7839702907186206e-06, "loss": 0.8291, "step": 109840 }, { "epoch": 9.13, "learning_rate": 2.7838594351910873e-06, "loss": 0.8132, "step": 109850 }, { "epoch": 9.13, "learning_rate": 2.783748579663553e-06, "loss": 0.7943, "step": 109860 }, { "epoch": 9.13, "learning_rate": 2.7836377241360195e-06, "loss": 0.8061, "step": 109870 }, { "epoch": 9.13, "learning_rate": 2.783526868608486e-06, "loss": 0.7943, "step": 109880 }, { "epoch": 9.13, "learning_rate": 2.783416013080952e-06, "loss": 0.7909, "step": 109890 }, { "epoch": 9.13, "learning_rate": 2.7833051575534184e-06, "loss": 0.7717, "step": 109900 }, { "epoch": 9.14, "learning_rate": 2.7831943020258847e-06, "loss": 0.7686, "step": 109910 }, { "epoch": 9.14, "learning_rate": 2.783083446498351e-06, "loss": 0.8097, "step": 109920 }, { "epoch": 9.14, "learning_rate": 2.7829725909708172e-06, "loss": 0.8222, "step": 109930 }, { "epoch": 9.14, "learning_rate": 2.7828617354432835e-06, "loss": 0.8214, "step": 109940 }, { "epoch": 9.14, "learning_rate": 2.7827508799157494e-06, "loss": 0.754, "step": 109950 }, { "epoch": 9.14, "learning_rate": 2.782640024388216e-06, "loss": 0.7618, "step": 109960 }, { "epoch": 9.14, "learning_rate": 2.782529168860682e-06, "loss": 0.7514, "step": 109970 }, { "epoch": 9.14, "learning_rate": 2.7824183133331483e-06, "loss": 0.84, "step": 109980 }, { "epoch": 9.14, "learning_rate": 2.7823074578056146e-06, "loss": 0.8387, "step": 109990 }, { "epoch": 9.14, "learning_rate": 2.782196602278081e-06, "loss": 0.8294, "step": 110000 }, { "epoch": 9.14, "learning_rate": 2.7820857467505476e-06, "loss": 0.7672, "step": 110010 }, { "epoch": 9.14, "learning_rate": 2.7819748912230135e-06, "loss": 0.7671, "step": 110020 }, { "epoch": 9.15, "learning_rate": 2.7818640356954798e-06, "loss": 0.7791, "step": 110030 }, { "epoch": 9.15, "learning_rate": 2.781753180167946e-06, "loss": 0.8287, "step": 110040 }, { "epoch": 9.15, "learning_rate": 2.7816423246404124e-06, "loss": 0.7392, "step": 110050 }, { "epoch": 9.15, "learning_rate": 2.7815314691128782e-06, "loss": 0.7587, "step": 110060 }, { "epoch": 9.15, "learning_rate": 2.781420613585345e-06, "loss": 0.8092, "step": 110070 }, { "epoch": 9.15, "learning_rate": 2.781309758057811e-06, "loss": 0.8169, "step": 110080 }, { "epoch": 9.15, "learning_rate": 2.781198902530277e-06, "loss": 0.8837, "step": 110090 }, { "epoch": 9.15, "learning_rate": 2.7810880470027434e-06, "loss": 0.8111, "step": 110100 }, { "epoch": 9.15, "learning_rate": 2.7809771914752097e-06, "loss": 0.8173, "step": 110110 }, { "epoch": 9.15, "learning_rate": 2.7808663359476764e-06, "loss": 0.7732, "step": 110120 }, { "epoch": 9.15, "learning_rate": 2.7807554804201423e-06, "loss": 0.8186, "step": 110130 }, { "epoch": 9.15, "learning_rate": 2.7806446248926086e-06, "loss": 0.8244, "step": 110140 }, { "epoch": 9.16, "learning_rate": 2.780533769365075e-06, "loss": 0.7923, "step": 110150 }, { "epoch": 9.16, "learning_rate": 2.780422913837541e-06, "loss": 0.7785, "step": 110160 }, { "epoch": 9.16, "learning_rate": 2.780312058310007e-06, "loss": 0.8004, "step": 110170 }, { "epoch": 9.16, "learning_rate": 2.7802012027824738e-06, "loss": 0.8543, "step": 110180 }, { "epoch": 9.16, "learning_rate": 2.7800903472549397e-06, "loss": 0.868, "step": 110190 }, { "epoch": 9.16, "learning_rate": 2.7799794917274064e-06, "loss": 0.7929, "step": 110200 }, { "epoch": 9.16, "learning_rate": 2.7798686361998722e-06, "loss": 0.7907, "step": 110210 }, { "epoch": 9.16, "learning_rate": 2.7797577806723385e-06, "loss": 0.7577, "step": 110220 }, { "epoch": 9.16, "learning_rate": 2.779646925144805e-06, "loss": 0.848, "step": 110230 }, { "epoch": 9.16, "learning_rate": 2.779536069617271e-06, "loss": 0.8646, "step": 110240 }, { "epoch": 9.16, "learning_rate": 2.7794252140897374e-06, "loss": 0.7298, "step": 110250 }, { "epoch": 9.16, "learning_rate": 2.7793143585622037e-06, "loss": 0.8072, "step": 110260 }, { "epoch": 9.17, "learning_rate": 2.77920350303467e-06, "loss": 0.7804, "step": 110270 }, { "epoch": 9.17, "learning_rate": 2.7790926475071363e-06, "loss": 0.8096, "step": 110280 }, { "epoch": 9.17, "learning_rate": 2.7789817919796026e-06, "loss": 0.8316, "step": 110290 }, { "epoch": 9.17, "learning_rate": 2.7788709364520685e-06, "loss": 0.8041, "step": 110300 }, { "epoch": 9.17, "learning_rate": 2.778760080924535e-06, "loss": 0.7956, "step": 110310 }, { "epoch": 9.17, "learning_rate": 2.778649225397001e-06, "loss": 0.7424, "step": 110320 }, { "epoch": 9.17, "learning_rate": 2.7785383698694674e-06, "loss": 0.8223, "step": 110330 }, { "epoch": 9.17, "learning_rate": 2.7784275143419337e-06, "loss": 0.8662, "step": 110340 }, { "epoch": 9.17, "learning_rate": 2.7783166588144e-06, "loss": 0.8131, "step": 110350 }, { "epoch": 9.17, "learning_rate": 2.7782058032868663e-06, "loss": 0.7424, "step": 110360 }, { "epoch": 9.17, "learning_rate": 2.7780949477593325e-06, "loss": 0.7925, "step": 110370 }, { "epoch": 9.17, "learning_rate": 2.777984092231799e-06, "loss": 0.7959, "step": 110380 }, { "epoch": 9.18, "learning_rate": 2.777873236704265e-06, "loss": 0.825, "step": 110390 }, { "epoch": 9.18, "learning_rate": 2.7777623811767314e-06, "loss": 0.8469, "step": 110400 }, { "epoch": 9.18, "learning_rate": 2.7776515256491973e-06, "loss": 0.8563, "step": 110410 }, { "epoch": 9.18, "learning_rate": 2.777540670121664e-06, "loss": 0.7712, "step": 110420 }, { "epoch": 9.18, "learning_rate": 2.77742981459413e-06, "loss": 0.7416, "step": 110430 }, { "epoch": 9.18, "learning_rate": 2.7773189590665966e-06, "loss": 0.8699, "step": 110440 }, { "epoch": 9.18, "learning_rate": 2.7772081035390625e-06, "loss": 0.7338, "step": 110450 }, { "epoch": 9.18, "learning_rate": 2.7770972480115288e-06, "loss": 0.7991, "step": 110460 }, { "epoch": 9.18, "learning_rate": 2.776986392483995e-06, "loss": 0.7755, "step": 110470 }, { "epoch": 9.18, "learning_rate": 2.7768755369564614e-06, "loss": 0.7683, "step": 110480 }, { "epoch": 9.18, "learning_rate": 2.7767646814289277e-06, "loss": 0.8291, "step": 110490 }, { "epoch": 9.18, "learning_rate": 2.776653825901394e-06, "loss": 0.835, "step": 110500 }, { "epoch": 9.19, "learning_rate": 2.7765429703738603e-06, "loss": 0.852, "step": 110510 }, { "epoch": 9.19, "learning_rate": 2.776432114846326e-06, "loss": 0.7417, "step": 110520 }, { "epoch": 9.19, "learning_rate": 2.776321259318793e-06, "loss": 0.7902, "step": 110530 }, { "epoch": 9.19, "learning_rate": 2.7762104037912587e-06, "loss": 0.8499, "step": 110540 }, { "epoch": 9.19, "learning_rate": 2.7760995482637254e-06, "loss": 0.8376, "step": 110550 }, { "epoch": 9.19, "learning_rate": 2.7759886927361913e-06, "loss": 0.7871, "step": 110560 }, { "epoch": 9.19, "learning_rate": 2.7758778372086576e-06, "loss": 0.829, "step": 110570 }, { "epoch": 9.19, "learning_rate": 2.775766981681124e-06, "loss": 0.8312, "step": 110580 }, { "epoch": 9.19, "learning_rate": 2.77565612615359e-06, "loss": 0.8502, "step": 110590 }, { "epoch": 9.19, "learning_rate": 2.775545270626056e-06, "loss": 0.8089, "step": 110600 }, { "epoch": 9.19, "learning_rate": 2.775434415098523e-06, "loss": 0.8503, "step": 110610 }, { "epoch": 9.19, "learning_rate": 2.775323559570989e-06, "loss": 0.8236, "step": 110620 }, { "epoch": 9.2, "learning_rate": 2.7752127040434554e-06, "loss": 0.7671, "step": 110630 }, { "epoch": 9.2, "learning_rate": 2.7751018485159217e-06, "loss": 0.7671, "step": 110640 }, { "epoch": 9.2, "learning_rate": 2.7749909929883875e-06, "loss": 0.7985, "step": 110650 }, { "epoch": 9.2, "learning_rate": 2.7748801374608543e-06, "loss": 0.7864, "step": 110660 }, { "epoch": 9.2, "learning_rate": 2.77476928193332e-06, "loss": 0.8384, "step": 110670 }, { "epoch": 9.2, "learning_rate": 2.7746584264057864e-06, "loss": 0.8624, "step": 110680 }, { "epoch": 9.2, "learning_rate": 2.7745475708782527e-06, "loss": 0.8254, "step": 110690 }, { "epoch": 9.2, "learning_rate": 2.774436715350719e-06, "loss": 0.7542, "step": 110700 }, { "epoch": 9.2, "learning_rate": 2.7743258598231853e-06, "loss": 0.7493, "step": 110710 }, { "epoch": 9.2, "learning_rate": 2.7742150042956516e-06, "loss": 0.7449, "step": 110720 }, { "epoch": 9.2, "learning_rate": 2.774104148768118e-06, "loss": 0.7895, "step": 110730 }, { "epoch": 9.2, "learning_rate": 2.773993293240584e-06, "loss": 0.8546, "step": 110740 }, { "epoch": 9.21, "learning_rate": 2.7738824377130505e-06, "loss": 0.7794, "step": 110750 }, { "epoch": 9.21, "learning_rate": 2.7737715821855164e-06, "loss": 0.795, "step": 110760 }, { "epoch": 9.21, "learning_rate": 2.773671812210736e-06, "loss": 0.7958, "step": 110770 }, { "epoch": 9.21, "learning_rate": 2.7735609566832026e-06, "loss": 0.7926, "step": 110780 }, { "epoch": 9.21, "learning_rate": 2.7734501011556685e-06, "loss": 0.8326, "step": 110790 }, { "epoch": 9.21, "learning_rate": 2.7733392456281352e-06, "loss": 0.804, "step": 110800 }, { "epoch": 9.21, "learning_rate": 2.773228390100601e-06, "loss": 0.7768, "step": 110810 }, { "epoch": 9.21, "learning_rate": 2.7731175345730674e-06, "loss": 0.7494, "step": 110820 }, { "epoch": 9.21, "learning_rate": 2.773006679045534e-06, "loss": 0.7855, "step": 110830 }, { "epoch": 9.21, "learning_rate": 2.772895823518e-06, "loss": 0.8544, "step": 110840 }, { "epoch": 9.21, "learning_rate": 2.7727849679904663e-06, "loss": 0.773, "step": 110850 }, { "epoch": 9.21, "learning_rate": 2.7726741124629326e-06, "loss": 0.8069, "step": 110860 }, { "epoch": 9.22, "learning_rate": 2.772563256935399e-06, "loss": 0.7656, "step": 110870 }, { "epoch": 9.22, "learning_rate": 2.772452401407865e-06, "loss": 0.7894, "step": 110880 }, { "epoch": 9.22, "learning_rate": 2.7723415458803315e-06, "loss": 0.8291, "step": 110890 }, { "epoch": 9.22, "learning_rate": 2.7722306903527973e-06, "loss": 0.7696, "step": 110900 }, { "epoch": 9.22, "learning_rate": 2.772119834825264e-06, "loss": 0.7805, "step": 110910 }, { "epoch": 9.22, "learning_rate": 2.77200897929773e-06, "loss": 0.8104, "step": 110920 }, { "epoch": 9.22, "learning_rate": 2.7718981237701962e-06, "loss": 0.7331, "step": 110930 }, { "epoch": 9.22, "learning_rate": 2.771787268242663e-06, "loss": 0.8077, "step": 110940 }, { "epoch": 9.22, "learning_rate": 2.771676412715129e-06, "loss": 0.752, "step": 110950 }, { "epoch": 9.22, "learning_rate": 2.7715655571875955e-06, "loss": 0.7703, "step": 110960 }, { "epoch": 9.22, "learning_rate": 2.7714547016600614e-06, "loss": 0.8582, "step": 110970 }, { "epoch": 9.22, "learning_rate": 2.7713438461325277e-06, "loss": 0.8309, "step": 110980 }, { "epoch": 9.23, "learning_rate": 2.771232990604994e-06, "loss": 0.8318, "step": 110990 }, { "epoch": 9.23, "learning_rate": 2.7711221350774603e-06, "loss": 0.77, "step": 111000 }, { "epoch": 9.23, "learning_rate": 2.771011279549926e-06, "loss": 0.7998, "step": 111010 }, { "epoch": 9.23, "learning_rate": 2.770900424022393e-06, "loss": 0.8602, "step": 111020 }, { "epoch": 9.23, "learning_rate": 2.7707895684948587e-06, "loss": 0.7884, "step": 111030 }, { "epoch": 9.23, "learning_rate": 2.770678712967325e-06, "loss": 0.7986, "step": 111040 }, { "epoch": 9.23, "learning_rate": 2.7705678574397913e-06, "loss": 0.7531, "step": 111050 }, { "epoch": 9.23, "learning_rate": 2.7704570019122576e-06, "loss": 0.7465, "step": 111060 }, { "epoch": 9.23, "learning_rate": 2.7703461463847243e-06, "loss": 0.8304, "step": 111070 }, { "epoch": 9.23, "learning_rate": 2.7702352908571902e-06, "loss": 0.826, "step": 111080 }, { "epoch": 9.23, "learning_rate": 2.7701244353296565e-06, "loss": 0.8372, "step": 111090 }, { "epoch": 9.23, "learning_rate": 2.770013579802123e-06, "loss": 0.7406, "step": 111100 }, { "epoch": 9.24, "learning_rate": 2.769902724274589e-06, "loss": 0.7898, "step": 111110 }, { "epoch": 9.24, "learning_rate": 2.769791868747055e-06, "loss": 0.7899, "step": 111120 }, { "epoch": 9.24, "learning_rate": 2.7696810132195217e-06, "loss": 0.8727, "step": 111130 }, { "epoch": 9.24, "learning_rate": 2.7695701576919876e-06, "loss": 0.8481, "step": 111140 }, { "epoch": 9.24, "learning_rate": 2.7694593021644543e-06, "loss": 0.7209, "step": 111150 }, { "epoch": 9.24, "learning_rate": 2.76934844663692e-06, "loss": 0.7823, "step": 111160 }, { "epoch": 9.24, "learning_rate": 2.7692375911093865e-06, "loss": 0.8667, "step": 111170 }, { "epoch": 9.24, "learning_rate": 2.7691267355818527e-06, "loss": 0.7779, "step": 111180 }, { "epoch": 9.24, "learning_rate": 2.769015880054319e-06, "loss": 0.7756, "step": 111190 }, { "epoch": 9.24, "learning_rate": 2.7689050245267853e-06, "loss": 0.7655, "step": 111200 }, { "epoch": 9.24, "learning_rate": 2.7687941689992516e-06, "loss": 0.7994, "step": 111210 }, { "epoch": 9.24, "learning_rate": 2.768683313471718e-06, "loss": 0.7638, "step": 111220 }, { "epoch": 9.25, "learning_rate": 2.7685724579441842e-06, "loss": 0.7566, "step": 111230 }, { "epoch": 9.25, "learning_rate": 2.7684616024166505e-06, "loss": 0.8075, "step": 111240 }, { "epoch": 9.25, "learning_rate": 2.7683507468891164e-06, "loss": 0.7946, "step": 111250 }, { "epoch": 9.25, "learning_rate": 2.768239891361583e-06, "loss": 0.7379, "step": 111260 }, { "epoch": 9.25, "learning_rate": 2.768129035834049e-06, "loss": 0.8237, "step": 111270 }, { "epoch": 9.25, "learning_rate": 2.7680181803065153e-06, "loss": 0.8372, "step": 111280 }, { "epoch": 9.25, "learning_rate": 2.7679073247789816e-06, "loss": 0.8286, "step": 111290 }, { "epoch": 9.25, "learning_rate": 2.767796469251448e-06, "loss": 0.7592, "step": 111300 }, { "epoch": 9.25, "learning_rate": 2.7676856137239146e-06, "loss": 0.8293, "step": 111310 }, { "epoch": 9.25, "learning_rate": 2.7675747581963805e-06, "loss": 0.8373, "step": 111320 }, { "epoch": 9.25, "learning_rate": 2.7674639026688468e-06, "loss": 0.7616, "step": 111330 }, { "epoch": 9.25, "learning_rate": 2.767353047141313e-06, "loss": 0.8455, "step": 111340 }, { "epoch": 9.26, "learning_rate": 2.7672421916137793e-06, "loss": 0.7828, "step": 111350 }, { "epoch": 9.26, "learning_rate": 2.7671313360862452e-06, "loss": 0.7737, "step": 111360 }, { "epoch": 9.26, "learning_rate": 2.767020480558712e-06, "loss": 0.7529, "step": 111370 }, { "epoch": 9.26, "learning_rate": 2.766909625031178e-06, "loss": 0.796, "step": 111380 }, { "epoch": 9.26, "learning_rate": 2.7667987695036445e-06, "loss": 0.8161, "step": 111390 }, { "epoch": 9.26, "learning_rate": 2.7666879139761104e-06, "loss": 0.8256, "step": 111400 }, { "epoch": 9.26, "learning_rate": 2.7665770584485767e-06, "loss": 0.7866, "step": 111410 }, { "epoch": 9.26, "learning_rate": 2.766466202921043e-06, "loss": 0.7761, "step": 111420 }, { "epoch": 9.26, "learning_rate": 2.7663553473935093e-06, "loss": 0.7977, "step": 111430 }, { "epoch": 9.26, "learning_rate": 2.7662444918659756e-06, "loss": 0.8541, "step": 111440 }, { "epoch": 9.26, "learning_rate": 2.766133636338442e-06, "loss": 0.7735, "step": 111450 }, { "epoch": 9.26, "learning_rate": 2.766022780810908e-06, "loss": 0.789, "step": 111460 }, { "epoch": 9.27, "learning_rate": 2.765911925283374e-06, "loss": 0.7576, "step": 111470 }, { "epoch": 9.27, "learning_rate": 2.7658010697558408e-06, "loss": 0.8067, "step": 111480 }, { "epoch": 9.27, "learning_rate": 2.7656902142283066e-06, "loss": 0.8084, "step": 111490 }, { "epoch": 9.27, "learning_rate": 2.7655793587007734e-06, "loss": 0.7707, "step": 111500 }, { "epoch": 9.27, "learning_rate": 2.7654685031732392e-06, "loss": 0.819, "step": 111510 }, { "epoch": 9.27, "learning_rate": 2.7653576476457055e-06, "loss": 0.7544, "step": 111520 }, { "epoch": 9.27, "learning_rate": 2.765246792118172e-06, "loss": 0.8658, "step": 111530 }, { "epoch": 9.27, "learning_rate": 2.765135936590638e-06, "loss": 0.8414, "step": 111540 }, { "epoch": 9.27, "learning_rate": 2.765025081063104e-06, "loss": 0.7514, "step": 111550 }, { "epoch": 9.27, "learning_rate": 2.7649142255355707e-06, "loss": 0.8399, "step": 111560 }, { "epoch": 9.27, "learning_rate": 2.764803370008037e-06, "loss": 0.8248, "step": 111570 }, { "epoch": 9.27, "learning_rate": 2.7646925144805033e-06, "loss": 0.8421, "step": 111580 }, { "epoch": 9.28, "learning_rate": 2.7645816589529696e-06, "loss": 0.8244, "step": 111590 }, { "epoch": 9.28, "learning_rate": 2.7644708034254355e-06, "loss": 0.8121, "step": 111600 }, { "epoch": 9.28, "learning_rate": 2.764359947897902e-06, "loss": 0.7701, "step": 111610 }, { "epoch": 9.28, "learning_rate": 2.764249092370368e-06, "loss": 0.7906, "step": 111620 }, { "epoch": 9.28, "learning_rate": 2.7641382368428343e-06, "loss": 0.8059, "step": 111630 }, { "epoch": 9.28, "learning_rate": 2.7640273813153006e-06, "loss": 0.9166, "step": 111640 }, { "epoch": 9.28, "learning_rate": 2.763916525787767e-06, "loss": 0.7997, "step": 111650 }, { "epoch": 9.28, "learning_rate": 2.7638056702602332e-06, "loss": 0.8066, "step": 111660 }, { "epoch": 9.28, "learning_rate": 2.7636948147326995e-06, "loss": 0.7832, "step": 111670 }, { "epoch": 9.28, "learning_rate": 2.763583959205166e-06, "loss": 0.7659, "step": 111680 }, { "epoch": 9.28, "learning_rate": 2.763473103677632e-06, "loss": 0.8386, "step": 111690 }, { "epoch": 9.28, "learning_rate": 2.7633622481500984e-06, "loss": 0.8095, "step": 111700 }, { "epoch": 9.29, "learning_rate": 2.7632513926225643e-06, "loss": 0.8295, "step": 111710 }, { "epoch": 9.29, "learning_rate": 2.763140537095031e-06, "loss": 0.773, "step": 111720 }, { "epoch": 9.29, "learning_rate": 2.763029681567497e-06, "loss": 0.8737, "step": 111730 }, { "epoch": 9.29, "learning_rate": 2.7629188260399636e-06, "loss": 0.8325, "step": 111740 }, { "epoch": 9.29, "learning_rate": 2.7628079705124295e-06, "loss": 0.7547, "step": 111750 }, { "epoch": 9.29, "learning_rate": 2.7626971149848958e-06, "loss": 0.7704, "step": 111760 }, { "epoch": 9.29, "learning_rate": 2.762586259457362e-06, "loss": 0.8372, "step": 111770 }, { "epoch": 9.29, "learning_rate": 2.7624754039298284e-06, "loss": 0.787, "step": 111780 }, { "epoch": 9.29, "learning_rate": 2.7623645484022942e-06, "loss": 0.8062, "step": 111790 }, { "epoch": 9.29, "learning_rate": 2.762253692874761e-06, "loss": 0.7584, "step": 111800 }, { "epoch": 9.29, "learning_rate": 2.7621428373472272e-06, "loss": 0.7612, "step": 111810 }, { "epoch": 9.29, "learning_rate": 2.7620319818196935e-06, "loss": 0.792, "step": 111820 }, { "epoch": 9.3, "learning_rate": 2.76192112629216e-06, "loss": 0.8047, "step": 111830 }, { "epoch": 9.3, "learning_rate": 2.7618102707646257e-06, "loss": 0.7938, "step": 111840 }, { "epoch": 9.3, "learning_rate": 2.7616994152370924e-06, "loss": 0.8192, "step": 111850 }, { "epoch": 9.3, "learning_rate": 2.7615885597095583e-06, "loss": 0.7981, "step": 111860 }, { "epoch": 9.3, "learning_rate": 2.7614777041820246e-06, "loss": 0.8458, "step": 111870 }, { "epoch": 9.3, "learning_rate": 2.761366848654491e-06, "loss": 0.8107, "step": 111880 }, { "epoch": 9.3, "learning_rate": 2.761255993126957e-06, "loss": 0.8551, "step": 111890 }, { "epoch": 9.3, "learning_rate": 2.761145137599423e-06, "loss": 0.7865, "step": 111900 }, { "epoch": 9.3, "learning_rate": 2.7610342820718898e-06, "loss": 0.826, "step": 111910 }, { "epoch": 9.3, "learning_rate": 2.7609234265443556e-06, "loss": 0.7477, "step": 111920 }, { "epoch": 9.3, "learning_rate": 2.7608125710168224e-06, "loss": 0.7762, "step": 111930 }, { "epoch": 9.3, "learning_rate": 2.7607017154892887e-06, "loss": 0.8198, "step": 111940 }, { "epoch": 9.31, "learning_rate": 2.7605908599617545e-06, "loss": 0.8523, "step": 111950 }, { "epoch": 9.31, "learning_rate": 2.7604800044342212e-06, "loss": 0.7878, "step": 111960 }, { "epoch": 9.31, "learning_rate": 2.760369148906687e-06, "loss": 0.7448, "step": 111970 }, { "epoch": 9.31, "learning_rate": 2.7602582933791534e-06, "loss": 0.8472, "step": 111980 }, { "epoch": 9.31, "learning_rate": 2.7601474378516197e-06, "loss": 0.8199, "step": 111990 }, { "epoch": 9.31, "learning_rate": 2.760036582324086e-06, "loss": 0.8435, "step": 112000 }, { "epoch": 9.31, "learning_rate": 2.7599257267965523e-06, "loss": 0.8489, "step": 112010 }, { "epoch": 9.31, "learning_rate": 2.7598148712690186e-06, "loss": 0.8092, "step": 112020 }, { "epoch": 9.31, "learning_rate": 2.7597040157414845e-06, "loss": 0.7914, "step": 112030 }, { "epoch": 9.31, "learning_rate": 2.759593160213951e-06, "loss": 0.8555, "step": 112040 }, { "epoch": 9.31, "learning_rate": 2.7594823046864175e-06, "loss": 0.7356, "step": 112050 }, { "epoch": 9.31, "learning_rate": 2.7593714491588834e-06, "loss": 0.7751, "step": 112060 }, { "epoch": 9.32, "learning_rate": 2.75926059363135e-06, "loss": 0.8015, "step": 112070 }, { "epoch": 9.32, "learning_rate": 2.759149738103816e-06, "loss": 0.7901, "step": 112080 }, { "epoch": 9.32, "learning_rate": 2.7590388825762827e-06, "loss": 0.8561, "step": 112090 }, { "epoch": 9.32, "learning_rate": 2.7589280270487485e-06, "loss": 0.7781, "step": 112100 }, { "epoch": 9.32, "learning_rate": 2.758817171521215e-06, "loss": 0.804, "step": 112110 }, { "epoch": 9.32, "learning_rate": 2.758706315993681e-06, "loss": 0.7816, "step": 112120 }, { "epoch": 9.32, "learning_rate": 2.7585954604661474e-06, "loss": 0.7914, "step": 112130 }, { "epoch": 9.32, "learning_rate": 2.7584846049386133e-06, "loss": 0.8566, "step": 112140 }, { "epoch": 9.32, "learning_rate": 2.75837374941108e-06, "loss": 0.826, "step": 112150 }, { "epoch": 9.32, "learning_rate": 2.758262893883546e-06, "loss": 0.8175, "step": 112160 }, { "epoch": 9.32, "learning_rate": 2.7581520383560126e-06, "loss": 0.746, "step": 112170 }, { "epoch": 9.32, "learning_rate": 2.758041182828479e-06, "loss": 0.8195, "step": 112180 }, { "epoch": 9.33, "learning_rate": 2.7579303273009448e-06, "loss": 0.894, "step": 112190 }, { "epoch": 9.33, "learning_rate": 2.7578194717734115e-06, "loss": 0.7987, "step": 112200 }, { "epoch": 9.33, "learning_rate": 2.7577086162458774e-06, "loss": 0.7336, "step": 112210 }, { "epoch": 9.33, "learning_rate": 2.7575977607183437e-06, "loss": 0.7316, "step": 112220 }, { "epoch": 9.33, "learning_rate": 2.75748690519081e-06, "loss": 0.797, "step": 112230 }, { "epoch": 9.33, "learning_rate": 2.7573760496632762e-06, "loss": 0.8279, "step": 112240 }, { "epoch": 9.33, "learning_rate": 2.757265194135742e-06, "loss": 0.8446, "step": 112250 }, { "epoch": 9.33, "learning_rate": 2.757154338608209e-06, "loss": 0.7598, "step": 112260 }, { "epoch": 9.33, "learning_rate": 2.7570434830806747e-06, "loss": 0.7982, "step": 112270 }, { "epoch": 9.33, "learning_rate": 2.7569326275531414e-06, "loss": 0.7539, "step": 112280 }, { "epoch": 9.33, "learning_rate": 2.7568217720256073e-06, "loss": 0.8899, "step": 112290 }, { "epoch": 9.33, "learning_rate": 2.7567109164980736e-06, "loss": 0.8422, "step": 112300 }, { "epoch": 9.34, "learning_rate": 2.7566000609705403e-06, "loss": 0.8239, "step": 112310 }, { "epoch": 9.34, "learning_rate": 2.756489205443006e-06, "loss": 0.8073, "step": 112320 }, { "epoch": 9.34, "learning_rate": 2.756378349915473e-06, "loss": 0.874, "step": 112330 }, { "epoch": 9.34, "learning_rate": 2.7562674943879388e-06, "loss": 0.8305, "step": 112340 }, { "epoch": 9.34, "learning_rate": 2.756156638860405e-06, "loss": 0.8109, "step": 112350 }, { "epoch": 9.34, "learning_rate": 2.7560457833328714e-06, "loss": 0.768, "step": 112360 }, { "epoch": 9.34, "learning_rate": 2.7559349278053377e-06, "loss": 0.8059, "step": 112370 }, { "epoch": 9.34, "learning_rate": 2.7558240722778035e-06, "loss": 0.8207, "step": 112380 }, { "epoch": 9.34, "learning_rate": 2.7557132167502702e-06, "loss": 0.865, "step": 112390 }, { "epoch": 9.34, "learning_rate": 2.755602361222736e-06, "loss": 0.7758, "step": 112400 }, { "epoch": 9.34, "learning_rate": 2.7554915056952024e-06, "loss": 0.7579, "step": 112410 }, { "epoch": 9.34, "learning_rate": 2.755380650167669e-06, "loss": 0.7826, "step": 112420 }, { "epoch": 9.35, "learning_rate": 2.755269794640135e-06, "loss": 0.8736, "step": 112430 }, { "epoch": 9.35, "learning_rate": 2.7551589391126017e-06, "loss": 0.8471, "step": 112440 }, { "epoch": 9.35, "learning_rate": 2.7550480835850676e-06, "loss": 0.7799, "step": 112450 }, { "epoch": 9.35, "learning_rate": 2.754937228057534e-06, "loss": 0.8275, "step": 112460 }, { "epoch": 9.35, "learning_rate": 2.75482637253e-06, "loss": 0.7328, "step": 112470 }, { "epoch": 9.35, "learning_rate": 2.7547155170024665e-06, "loss": 0.7538, "step": 112480 }, { "epoch": 9.35, "learning_rate": 2.7546046614749324e-06, "loss": 0.828, "step": 112490 }, { "epoch": 9.35, "learning_rate": 2.754493805947399e-06, "loss": 0.8819, "step": 112500 }, { "epoch": 9.35, "learning_rate": 2.754382950419865e-06, "loss": 0.7737, "step": 112510 }, { "epoch": 9.35, "learning_rate": 2.7542720948923317e-06, "loss": 0.8358, "step": 112520 }, { "epoch": 9.35, "learning_rate": 2.7541612393647975e-06, "loss": 0.8078, "step": 112530 }, { "epoch": 9.35, "learning_rate": 2.754050383837264e-06, "loss": 0.8316, "step": 112540 }, { "epoch": 9.35, "learning_rate": 2.7539395283097306e-06, "loss": 0.8033, "step": 112550 }, { "epoch": 9.36, "learning_rate": 2.7538286727821964e-06, "loss": 0.8866, "step": 112560 }, { "epoch": 9.36, "learning_rate": 2.7537178172546627e-06, "loss": 0.7846, "step": 112570 }, { "epoch": 9.36, "learning_rate": 2.753606961727129e-06, "loss": 0.8679, "step": 112580 }, { "epoch": 9.36, "learning_rate": 2.7534961061995953e-06, "loss": 0.8376, "step": 112590 }, { "epoch": 9.36, "learning_rate": 2.7533852506720616e-06, "loss": 0.8192, "step": 112600 }, { "epoch": 9.36, "learning_rate": 2.753274395144528e-06, "loss": 0.8304, "step": 112610 }, { "epoch": 9.36, "learning_rate": 2.7531635396169938e-06, "loss": 0.758, "step": 112620 }, { "epoch": 9.36, "learning_rate": 2.7530526840894605e-06, "loss": 0.8961, "step": 112630 }, { "epoch": 9.36, "learning_rate": 2.7529418285619264e-06, "loss": 0.8235, "step": 112640 }, { "epoch": 9.36, "learning_rate": 2.7528309730343927e-06, "loss": 0.7589, "step": 112650 }, { "epoch": 9.36, "learning_rate": 2.752720117506859e-06, "loss": 0.7499, "step": 112660 }, { "epoch": 9.36, "learning_rate": 2.7526092619793252e-06, "loss": 0.7928, "step": 112670 }, { "epoch": 9.37, "learning_rate": 2.752498406451792e-06, "loss": 0.7481, "step": 112680 }, { "epoch": 9.37, "learning_rate": 2.752387550924258e-06, "loss": 0.8961, "step": 112690 }, { "epoch": 9.37, "learning_rate": 2.752276695396724e-06, "loss": 0.8635, "step": 112700 }, { "epoch": 9.37, "learning_rate": 2.7521658398691904e-06, "loss": 0.863, "step": 112710 }, { "epoch": 9.37, "learning_rate": 2.7520549843416567e-06, "loss": 0.7896, "step": 112720 }, { "epoch": 9.37, "learning_rate": 2.7519441288141226e-06, "loss": 0.8605, "step": 112730 }, { "epoch": 9.37, "learning_rate": 2.7518332732865893e-06, "loss": 0.8172, "step": 112740 }, { "epoch": 9.37, "learning_rate": 2.751722417759055e-06, "loss": 0.7638, "step": 112750 }, { "epoch": 9.37, "learning_rate": 2.7516115622315215e-06, "loss": 0.764, "step": 112760 }, { "epoch": 9.37, "learning_rate": 2.7515007067039878e-06, "loss": 0.801, "step": 112770 }, { "epoch": 9.37, "learning_rate": 2.751389851176454e-06, "loss": 0.8457, "step": 112780 }, { "epoch": 9.37, "learning_rate": 2.751278995648921e-06, "loss": 0.7987, "step": 112790 }, { "epoch": 9.38, "learning_rate": 2.7511681401213867e-06, "loss": 0.7431, "step": 112800 }, { "epoch": 9.38, "learning_rate": 2.751057284593853e-06, "loss": 0.7938, "step": 112810 }, { "epoch": 9.38, "learning_rate": 2.7509464290663193e-06, "loss": 0.8092, "step": 112820 }, { "epoch": 9.38, "learning_rate": 2.7508355735387856e-06, "loss": 0.7721, "step": 112830 }, { "epoch": 9.38, "learning_rate": 2.7507247180112514e-06, "loss": 0.7962, "step": 112840 }, { "epoch": 9.38, "learning_rate": 2.750613862483718e-06, "loss": 0.7909, "step": 112850 }, { "epoch": 9.38, "learning_rate": 2.750503006956184e-06, "loss": 0.778, "step": 112860 }, { "epoch": 9.38, "learning_rate": 2.7503921514286507e-06, "loss": 0.7492, "step": 112870 }, { "epoch": 9.38, "learning_rate": 2.7502812959011166e-06, "loss": 0.7774, "step": 112880 }, { "epoch": 9.38, "learning_rate": 2.750170440373583e-06, "loss": 0.8623, "step": 112890 }, { "epoch": 9.38, "learning_rate": 2.750059584846049e-06, "loss": 0.8072, "step": 112900 }, { "epoch": 9.38, "learning_rate": 2.7499487293185155e-06, "loss": 0.7669, "step": 112910 }, { "epoch": 9.39, "learning_rate": 2.7498378737909818e-06, "loss": 0.758, "step": 112920 }, { "epoch": 9.39, "learning_rate": 2.749727018263448e-06, "loss": 0.8021, "step": 112930 }, { "epoch": 9.39, "learning_rate": 2.7496161627359144e-06, "loss": 0.839, "step": 112940 }, { "epoch": 9.39, "learning_rate": 2.7495053072083807e-06, "loss": 0.7099, "step": 112950 }, { "epoch": 9.39, "learning_rate": 2.749394451680847e-06, "loss": 0.8021, "step": 112960 }, { "epoch": 9.39, "learning_rate": 2.749283596153313e-06, "loss": 0.7979, "step": 112970 }, { "epoch": 9.39, "learning_rate": 2.7491727406257796e-06, "loss": 0.7569, "step": 112980 }, { "epoch": 9.39, "learning_rate": 2.7490618850982454e-06, "loss": 0.888, "step": 112990 }, { "epoch": 9.39, "learning_rate": 2.7489510295707117e-06, "loss": 0.7974, "step": 113000 }, { "epoch": 9.39, "learning_rate": 2.748840174043178e-06, "loss": 0.8334, "step": 113010 }, { "epoch": 9.39, "learning_rate": 2.7487293185156443e-06, "loss": 0.7859, "step": 113020 }, { "epoch": 9.39, "learning_rate": 2.748618462988111e-06, "loss": 0.86, "step": 113030 }, { "epoch": 9.4, "learning_rate": 2.748507607460577e-06, "loss": 0.8194, "step": 113040 }, { "epoch": 9.4, "learning_rate": 2.748396751933043e-06, "loss": 0.7751, "step": 113050 }, { "epoch": 9.4, "learning_rate": 2.7482858964055095e-06, "loss": 0.7893, "step": 113060 }, { "epoch": 9.4, "learning_rate": 2.748175040877976e-06, "loss": 0.7818, "step": 113070 }, { "epoch": 9.4, "learning_rate": 2.7480641853504417e-06, "loss": 0.8629, "step": 113080 }, { "epoch": 9.4, "learning_rate": 2.7479533298229084e-06, "loss": 0.867, "step": 113090 }, { "epoch": 9.4, "learning_rate": 2.7478424742953743e-06, "loss": 0.7408, "step": 113100 }, { "epoch": 9.4, "learning_rate": 2.747731618767841e-06, "loss": 0.7994, "step": 113110 }, { "epoch": 9.4, "learning_rate": 2.747620763240307e-06, "loss": 0.7807, "step": 113120 }, { "epoch": 9.4, "learning_rate": 2.747509907712773e-06, "loss": 0.7455, "step": 113130 }, { "epoch": 9.4, "learning_rate": 2.7473990521852394e-06, "loss": 0.8295, "step": 113140 }, { "epoch": 9.4, "learning_rate": 2.7472881966577057e-06, "loss": 0.733, "step": 113150 }, { "epoch": 9.41, "learning_rate": 2.747177341130172e-06, "loss": 0.853, "step": 113160 }, { "epoch": 9.41, "learning_rate": 2.7470664856026383e-06, "loss": 0.7719, "step": 113170 }, { "epoch": 9.41, "learning_rate": 2.7469556300751046e-06, "loss": 0.7733, "step": 113180 }, { "epoch": 9.41, "learning_rate": 2.7468447745475705e-06, "loss": 0.8155, "step": 113190 }, { "epoch": 9.41, "learning_rate": 2.746733919020037e-06, "loss": 0.7123, "step": 113200 }, { "epoch": 9.41, "learning_rate": 2.746623063492503e-06, "loss": 0.8261, "step": 113210 }, { "epoch": 9.41, "learning_rate": 2.74651220796497e-06, "loss": 0.7396, "step": 113220 }, { "epoch": 9.41, "learning_rate": 2.7464013524374357e-06, "loss": 0.7663, "step": 113230 }, { "epoch": 9.41, "learning_rate": 2.746290496909902e-06, "loss": 0.8376, "step": 113240 }, { "epoch": 9.41, "learning_rate": 2.7461796413823683e-06, "loss": 0.7887, "step": 113250 }, { "epoch": 9.41, "learning_rate": 2.7460687858548346e-06, "loss": 0.8342, "step": 113260 }, { "epoch": 9.41, "learning_rate": 2.7459579303273004e-06, "loss": 0.7782, "step": 113270 }, { "epoch": 9.42, "learning_rate": 2.745847074799767e-06, "loss": 0.8367, "step": 113280 }, { "epoch": 9.42, "learning_rate": 2.7457362192722334e-06, "loss": 0.8332, "step": 113290 }, { "epoch": 9.42, "learning_rate": 2.7456253637446997e-06, "loss": 0.8046, "step": 113300 }, { "epoch": 9.42, "learning_rate": 2.745514508217166e-06, "loss": 0.7902, "step": 113310 }, { "epoch": 9.42, "learning_rate": 2.745403652689632e-06, "loss": 0.7981, "step": 113320 }, { "epoch": 9.42, "learning_rate": 2.7452927971620986e-06, "loss": 0.8016, "step": 113330 }, { "epoch": 9.42, "learning_rate": 2.7451819416345645e-06, "loss": 0.8411, "step": 113340 }, { "epoch": 9.42, "learning_rate": 2.745071086107031e-06, "loss": 0.7735, "step": 113350 }, { "epoch": 9.42, "learning_rate": 2.744960230579497e-06, "loss": 0.7656, "step": 113360 }, { "epoch": 9.42, "learning_rate": 2.7448493750519634e-06, "loss": 0.8102, "step": 113370 }, { "epoch": 9.42, "learning_rate": 2.7447385195244297e-06, "loss": 0.7327, "step": 113380 }, { "epoch": 9.42, "learning_rate": 2.744627663996896e-06, "loss": 0.8121, "step": 113390 }, { "epoch": 9.43, "learning_rate": 2.7445168084693623e-06, "loss": 0.8611, "step": 113400 }, { "epoch": 9.43, "learning_rate": 2.7444059529418286e-06, "loss": 0.8677, "step": 113410 }, { "epoch": 9.43, "learning_rate": 2.744295097414295e-06, "loss": 0.7725, "step": 113420 }, { "epoch": 9.43, "learning_rate": 2.7441842418867607e-06, "loss": 0.7985, "step": 113430 }, { "epoch": 9.43, "learning_rate": 2.7440733863592274e-06, "loss": 0.8435, "step": 113440 }, { "epoch": 9.43, "learning_rate": 2.7439625308316933e-06, "loss": 0.7911, "step": 113450 }, { "epoch": 9.43, "learning_rate": 2.74385167530416e-06, "loss": 0.7833, "step": 113460 }, { "epoch": 9.43, "learning_rate": 2.743740819776626e-06, "loss": 0.7566, "step": 113470 }, { "epoch": 9.43, "learning_rate": 2.743629964249092e-06, "loss": 0.8808, "step": 113480 }, { "epoch": 9.43, "learning_rate": 2.7435191087215585e-06, "loss": 0.7757, "step": 113490 }, { "epoch": 9.43, "learning_rate": 2.743408253194025e-06, "loss": 0.7699, "step": 113500 }, { "epoch": 9.43, "learning_rate": 2.7432973976664907e-06, "loss": 0.8311, "step": 113510 }, { "epoch": 9.44, "learning_rate": 2.7431865421389574e-06, "loss": 0.7566, "step": 113520 }, { "epoch": 9.44, "learning_rate": 2.7430756866114237e-06, "loss": 0.8314, "step": 113530 }, { "epoch": 9.44, "learning_rate": 2.7429648310838896e-06, "loss": 0.7843, "step": 113540 }, { "epoch": 9.44, "learning_rate": 2.7428539755563563e-06, "loss": 0.7977, "step": 113550 }, { "epoch": 9.44, "learning_rate": 2.742743120028822e-06, "loss": 0.8014, "step": 113560 }, { "epoch": 9.44, "learning_rate": 2.742632264501289e-06, "loss": 0.7898, "step": 113570 }, { "epoch": 9.44, "learning_rate": 2.7425214089737547e-06, "loss": 0.8342, "step": 113580 }, { "epoch": 9.44, "learning_rate": 2.742410553446221e-06, "loss": 0.8362, "step": 113590 }, { "epoch": 9.44, "learning_rate": 2.7422996979186873e-06, "loss": 0.7778, "step": 113600 }, { "epoch": 9.44, "learning_rate": 2.7421888423911536e-06, "loss": 0.7639, "step": 113610 }, { "epoch": 9.44, "learning_rate": 2.7420779868636195e-06, "loss": 0.8157, "step": 113620 }, { "epoch": 9.44, "learning_rate": 2.7419671313360862e-06, "loss": 0.7789, "step": 113630 }, { "epoch": 9.45, "learning_rate": 2.741856275808552e-06, "loss": 0.8936, "step": 113640 }, { "epoch": 9.45, "learning_rate": 2.741745420281019e-06, "loss": 0.8057, "step": 113650 }, { "epoch": 9.45, "learning_rate": 2.741634564753485e-06, "loss": 0.7605, "step": 113660 }, { "epoch": 9.45, "learning_rate": 2.741523709225951e-06, "loss": 0.8938, "step": 113670 }, { "epoch": 9.45, "learning_rate": 2.7414128536984177e-06, "loss": 0.8571, "step": 113680 }, { "epoch": 9.45, "learning_rate": 2.7413019981708836e-06, "loss": 0.8721, "step": 113690 }, { "epoch": 9.45, "learning_rate": 2.74119114264335e-06, "loss": 0.8049, "step": 113700 }, { "epoch": 9.45, "learning_rate": 2.741080287115816e-06, "loss": 0.7614, "step": 113710 }, { "epoch": 9.45, "learning_rate": 2.7409694315882824e-06, "loss": 0.7553, "step": 113720 }, { "epoch": 9.45, "learning_rate": 2.7408585760607487e-06, "loss": 0.8397, "step": 113730 }, { "epoch": 9.45, "learning_rate": 2.740747720533215e-06, "loss": 0.8165, "step": 113740 }, { "epoch": 9.45, "learning_rate": 2.740636865005681e-06, "loss": 0.8041, "step": 113750 }, { "epoch": 9.46, "learning_rate": 2.7405260094781476e-06, "loss": 0.8005, "step": 113760 }, { "epoch": 9.46, "learning_rate": 2.740415153950614e-06, "loss": 0.7987, "step": 113770 }, { "epoch": 9.46, "learning_rate": 2.74030429842308e-06, "loss": 0.8347, "step": 113780 }, { "epoch": 9.46, "learning_rate": 2.7401934428955465e-06, "loss": 0.785, "step": 113790 }, { "epoch": 9.46, "learning_rate": 2.7400825873680124e-06, "loss": 0.851, "step": 113800 }, { "epoch": 9.46, "learning_rate": 2.739971731840479e-06, "loss": 0.7628, "step": 113810 }, { "epoch": 9.46, "learning_rate": 2.739860876312945e-06, "loss": 0.7487, "step": 113820 }, { "epoch": 9.46, "learning_rate": 2.7397500207854113e-06, "loss": 0.7958, "step": 113830 }, { "epoch": 9.46, "learning_rate": 2.7396391652578776e-06, "loss": 0.7312, "step": 113840 }, { "epoch": 9.46, "learning_rate": 2.739528309730344e-06, "loss": 0.7534, "step": 113850 }, { "epoch": 9.46, "learning_rate": 2.7394174542028097e-06, "loss": 0.8415, "step": 113860 }, { "epoch": 9.46, "learning_rate": 2.7393065986752765e-06, "loss": 0.8068, "step": 113870 }, { "epoch": 9.47, "learning_rate": 2.7391957431477423e-06, "loss": 0.7921, "step": 113880 }, { "epoch": 9.47, "learning_rate": 2.7390959731729623e-06, "loss": 0.8319, "step": 113890 }, { "epoch": 9.47, "learning_rate": 2.7389851176454286e-06, "loss": 0.7712, "step": 113900 }, { "epoch": 9.47, "learning_rate": 2.738874262117895e-06, "loss": 0.8555, "step": 113910 }, { "epoch": 9.47, "learning_rate": 2.7387634065903608e-06, "loss": 0.7605, "step": 113920 }, { "epoch": 9.47, "learning_rate": 2.7386525510628275e-06, "loss": 0.7895, "step": 113930 }, { "epoch": 9.47, "learning_rate": 2.7385416955352933e-06, "loss": 0.858, "step": 113940 }, { "epoch": 9.47, "learning_rate": 2.7384308400077596e-06, "loss": 0.7941, "step": 113950 }, { "epoch": 9.47, "learning_rate": 2.738319984480226e-06, "loss": 0.7793, "step": 113960 }, { "epoch": 9.47, "learning_rate": 2.7382091289526922e-06, "loss": 0.8279, "step": 113970 }, { "epoch": 9.47, "learning_rate": 2.738098273425159e-06, "loss": 0.7543, "step": 113980 }, { "epoch": 9.47, "learning_rate": 2.737987417897625e-06, "loss": 0.8229, "step": 113990 }, { "epoch": 9.48, "learning_rate": 2.737876562370091e-06, "loss": 0.8191, "step": 114000 }, { "epoch": 9.48, "learning_rate": 2.7377657068425574e-06, "loss": 0.7531, "step": 114010 }, { "epoch": 9.48, "learning_rate": 2.7376548513150237e-06, "loss": 0.7764, "step": 114020 }, { "epoch": 9.48, "learning_rate": 2.7375439957874896e-06, "loss": 0.8292, "step": 114030 }, { "epoch": 9.48, "learning_rate": 2.7374331402599563e-06, "loss": 0.8629, "step": 114040 }, { "epoch": 9.48, "learning_rate": 2.737322284732422e-06, "loss": 0.8167, "step": 114050 }, { "epoch": 9.48, "learning_rate": 2.737211429204889e-06, "loss": 0.7781, "step": 114060 }, { "epoch": 9.48, "learning_rate": 2.7371005736773548e-06, "loss": 0.7543, "step": 114070 }, { "epoch": 9.48, "learning_rate": 2.736989718149821e-06, "loss": 0.8166, "step": 114080 }, { "epoch": 9.48, "learning_rate": 2.7368788626222873e-06, "loss": 0.8918, "step": 114090 }, { "epoch": 9.48, "learning_rate": 2.7367680070947536e-06, "loss": 0.7912, "step": 114100 }, { "epoch": 9.48, "learning_rate": 2.73665715156722e-06, "loss": 0.8335, "step": 114110 }, { "epoch": 9.49, "learning_rate": 2.7365462960396862e-06, "loss": 0.7943, "step": 114120 }, { "epoch": 9.49, "learning_rate": 2.7364354405121525e-06, "loss": 0.7617, "step": 114130 }, { "epoch": 9.49, "learning_rate": 2.7363245849846184e-06, "loss": 0.8414, "step": 114140 }, { "epoch": 9.49, "learning_rate": 2.736213729457085e-06, "loss": 0.8295, "step": 114150 }, { "epoch": 9.49, "learning_rate": 2.736102873929551e-06, "loss": 0.7885, "step": 114160 }, { "epoch": 9.49, "learning_rate": 2.7359920184020177e-06, "loss": 0.7812, "step": 114170 }, { "epoch": 9.49, "learning_rate": 2.7358811628744836e-06, "loss": 0.8166, "step": 114180 }, { "epoch": 9.49, "learning_rate": 2.73577030734695e-06, "loss": 0.8283, "step": 114190 }, { "epoch": 9.49, "learning_rate": 2.735659451819416e-06, "loss": 0.777, "step": 114200 }, { "epoch": 9.49, "learning_rate": 2.7355485962918825e-06, "loss": 0.7984, "step": 114210 }, { "epoch": 9.49, "learning_rate": 2.7354377407643483e-06, "loss": 0.7125, "step": 114220 }, { "epoch": 9.49, "learning_rate": 2.735326885236815e-06, "loss": 0.8543, "step": 114230 }, { "epoch": 9.5, "learning_rate": 2.7352160297092814e-06, "loss": 0.8978, "step": 114240 }, { "epoch": 9.5, "learning_rate": 2.7351051741817476e-06, "loss": 0.7366, "step": 114250 }, { "epoch": 9.5, "learning_rate": 2.734994318654214e-06, "loss": 0.8332, "step": 114260 }, { "epoch": 9.5, "learning_rate": 2.73488346312668e-06, "loss": 0.8275, "step": 114270 }, { "epoch": 9.5, "learning_rate": 2.7347726075991465e-06, "loss": 0.7942, "step": 114280 }, { "epoch": 9.5, "learning_rate": 2.7346617520716124e-06, "loss": 0.8878, "step": 114290 }, { "epoch": 9.5, "learning_rate": 2.7345508965440787e-06, "loss": 0.8091, "step": 114300 }, { "epoch": 9.5, "learning_rate": 2.734440041016545e-06, "loss": 0.8023, "step": 114310 }, { "epoch": 9.5, "learning_rate": 2.7343291854890113e-06, "loss": 0.823, "step": 114320 }, { "epoch": 9.5, "learning_rate": 2.7342183299614776e-06, "loss": 0.7994, "step": 114330 }, { "epoch": 9.5, "learning_rate": 2.734107474433944e-06, "loss": 0.8496, "step": 114340 }, { "epoch": 9.5, "learning_rate": 2.73399661890641e-06, "loss": 0.7766, "step": 114350 }, { "epoch": 9.51, "learning_rate": 2.7338857633788765e-06, "loss": 0.7823, "step": 114360 }, { "epoch": 9.51, "learning_rate": 2.7337749078513428e-06, "loss": 0.7789, "step": 114370 }, { "epoch": 9.51, "learning_rate": 2.7336640523238086e-06, "loss": 0.8297, "step": 114380 }, { "epoch": 9.51, "learning_rate": 2.7335531967962754e-06, "loss": 0.7862, "step": 114390 }, { "epoch": 9.51, "learning_rate": 2.7334423412687412e-06, "loss": 0.7162, "step": 114400 }, { "epoch": 9.51, "learning_rate": 2.733331485741208e-06, "loss": 0.796, "step": 114410 }, { "epoch": 9.51, "learning_rate": 2.733220630213674e-06, "loss": 0.8357, "step": 114420 }, { "epoch": 9.51, "learning_rate": 2.73310977468614e-06, "loss": 0.8258, "step": 114430 }, { "epoch": 9.51, "learning_rate": 2.7329989191586064e-06, "loss": 0.7977, "step": 114440 }, { "epoch": 9.51, "learning_rate": 2.7328880636310727e-06, "loss": 0.8171, "step": 114450 }, { "epoch": 9.51, "learning_rate": 2.7327772081035386e-06, "loss": 0.8539, "step": 114460 }, { "epoch": 9.51, "learning_rate": 2.7326663525760053e-06, "loss": 0.8043, "step": 114470 }, { "epoch": 9.52, "learning_rate": 2.7325554970484716e-06, "loss": 0.8514, "step": 114480 }, { "epoch": 9.52, "learning_rate": 2.7324446415209375e-06, "loss": 0.8382, "step": 114490 }, { "epoch": 9.52, "learning_rate": 2.732333785993404e-06, "loss": 0.747, "step": 114500 }, { "epoch": 9.52, "learning_rate": 2.73222293046587e-06, "loss": 0.8015, "step": 114510 }, { "epoch": 9.52, "learning_rate": 2.7321120749383368e-06, "loss": 0.744, "step": 114520 }, { "epoch": 9.52, "learning_rate": 2.7320012194108026e-06, "loss": 0.8293, "step": 114530 }, { "epoch": 9.52, "learning_rate": 2.731890363883269e-06, "loss": 0.7987, "step": 114540 }, { "epoch": 9.52, "learning_rate": 2.7317795083557352e-06, "loss": 0.7613, "step": 114550 }, { "epoch": 9.52, "learning_rate": 2.7316686528282015e-06, "loss": 0.7747, "step": 114560 }, { "epoch": 9.52, "learning_rate": 2.7315577973006674e-06, "loss": 0.7821, "step": 114570 }, { "epoch": 9.52, "learning_rate": 2.731446941773134e-06, "loss": 0.773, "step": 114580 }, { "epoch": 9.52, "learning_rate": 2.7313360862456e-06, "loss": 0.8081, "step": 114590 }, { "epoch": 9.53, "learning_rate": 2.7312252307180667e-06, "loss": 0.8073, "step": 114600 }, { "epoch": 9.53, "learning_rate": 2.731114375190533e-06, "loss": 0.849, "step": 114610 }, { "epoch": 9.53, "learning_rate": 2.731003519662999e-06, "loss": 0.744, "step": 114620 }, { "epoch": 9.53, "learning_rate": 2.7308926641354656e-06, "loss": 0.8255, "step": 114630 }, { "epoch": 9.53, "learning_rate": 2.7307818086079315e-06, "loss": 0.8549, "step": 114640 }, { "epoch": 9.53, "learning_rate": 2.7306709530803978e-06, "loss": 0.7503, "step": 114650 }, { "epoch": 9.53, "learning_rate": 2.730560097552864e-06, "loss": 0.7042, "step": 114660 }, { "epoch": 9.53, "learning_rate": 2.7304492420253304e-06, "loss": 0.7872, "step": 114670 }, { "epoch": 9.53, "learning_rate": 2.7303383864977967e-06, "loss": 0.8133, "step": 114680 }, { "epoch": 9.53, "learning_rate": 2.730227530970263e-06, "loss": 0.8983, "step": 114690 }, { "epoch": 9.53, "learning_rate": 2.730116675442729e-06, "loss": 0.8533, "step": 114700 }, { "epoch": 9.53, "learning_rate": 2.7300058199151955e-06, "loss": 0.832, "step": 114710 }, { "epoch": 9.54, "learning_rate": 2.729894964387662e-06, "loss": 0.7864, "step": 114720 }, { "epoch": 9.54, "learning_rate": 2.7297841088601277e-06, "loss": 0.7561, "step": 114730 }, { "epoch": 9.54, "learning_rate": 2.7296732533325944e-06, "loss": 0.8139, "step": 114740 }, { "epoch": 9.54, "learning_rate": 2.7295623978050603e-06, "loss": 0.8187, "step": 114750 }, { "epoch": 9.54, "learning_rate": 2.729451542277527e-06, "loss": 0.8583, "step": 114760 }, { "epoch": 9.54, "learning_rate": 2.729340686749993e-06, "loss": 0.8542, "step": 114770 }, { "epoch": 9.54, "learning_rate": 2.729229831222459e-06, "loss": 0.7484, "step": 114780 }, { "epoch": 9.54, "learning_rate": 2.7291189756949255e-06, "loss": 0.8084, "step": 114790 }, { "epoch": 9.54, "learning_rate": 2.7290081201673918e-06, "loss": 0.771, "step": 114800 }, { "epoch": 9.54, "learning_rate": 2.7288972646398576e-06, "loss": 0.762, "step": 114810 }, { "epoch": 9.54, "learning_rate": 2.7287864091123244e-06, "loss": 0.8175, "step": 114820 }, { "epoch": 9.54, "learning_rate": 2.7286755535847902e-06, "loss": 0.7799, "step": 114830 }, { "epoch": 9.55, "learning_rate": 2.728564698057257e-06, "loss": 0.8612, "step": 114840 }, { "epoch": 9.55, "learning_rate": 2.7284538425297233e-06, "loss": 0.7769, "step": 114850 }, { "epoch": 9.55, "learning_rate": 2.728342987002189e-06, "loss": 0.7899, "step": 114860 }, { "epoch": 9.55, "learning_rate": 2.728232131474656e-06, "loss": 0.7237, "step": 114870 }, { "epoch": 9.55, "learning_rate": 2.7281212759471217e-06, "loss": 0.7893, "step": 114880 }, { "epoch": 9.55, "learning_rate": 2.728010420419588e-06, "loss": 0.7954, "step": 114890 }, { "epoch": 9.55, "learning_rate": 2.7278995648920543e-06, "loss": 0.7889, "step": 114900 }, { "epoch": 9.55, "learning_rate": 2.7277887093645206e-06, "loss": 0.749, "step": 114910 }, { "epoch": 9.55, "learning_rate": 2.7276778538369865e-06, "loss": 0.7768, "step": 114920 }, { "epoch": 9.55, "learning_rate": 2.727566998309453e-06, "loss": 0.7691, "step": 114930 }, { "epoch": 9.55, "learning_rate": 2.727456142781919e-06, "loss": 0.8218, "step": 114940 }, { "epoch": 9.55, "learning_rate": 2.7273452872543858e-06, "loss": 0.7395, "step": 114950 }, { "epoch": 9.56, "learning_rate": 2.7272344317268517e-06, "loss": 0.8545, "step": 114960 }, { "epoch": 9.56, "learning_rate": 2.727123576199318e-06, "loss": 0.7904, "step": 114970 }, { "epoch": 9.56, "learning_rate": 2.7270127206717847e-06, "loss": 0.8058, "step": 114980 }, { "epoch": 9.56, "learning_rate": 2.7269018651442505e-06, "loss": 0.9023, "step": 114990 }, { "epoch": 9.56, "learning_rate": 2.726791009616717e-06, "loss": 0.7982, "step": 115000 }, { "epoch": 9.56, "learning_rate": 2.726680154089183e-06, "loss": 0.8018, "step": 115010 }, { "epoch": 9.56, "learning_rate": 2.7265692985616494e-06, "loss": 0.7927, "step": 115020 }, { "epoch": 9.56, "learning_rate": 2.7264584430341157e-06, "loss": 0.8422, "step": 115030 }, { "epoch": 9.56, "learning_rate": 2.726347587506582e-06, "loss": 0.855, "step": 115040 }, { "epoch": 9.56, "learning_rate": 2.726236731979048e-06, "loss": 0.7085, "step": 115050 }, { "epoch": 9.56, "learning_rate": 2.7261258764515146e-06, "loss": 0.8291, "step": 115060 }, { "epoch": 9.56, "learning_rate": 2.7260150209239805e-06, "loss": 0.7606, "step": 115070 }, { "epoch": 9.57, "learning_rate": 2.7259041653964468e-06, "loss": 0.8358, "step": 115080 }, { "epoch": 9.57, "learning_rate": 2.7257933098689135e-06, "loss": 0.8847, "step": 115090 }, { "epoch": 9.57, "learning_rate": 2.7256824543413794e-06, "loss": 0.7921, "step": 115100 }, { "epoch": 9.57, "learning_rate": 2.725571598813846e-06, "loss": 0.7508, "step": 115110 }, { "epoch": 9.57, "learning_rate": 2.725460743286312e-06, "loss": 0.8011, "step": 115120 }, { "epoch": 9.57, "learning_rate": 2.7253498877587783e-06, "loss": 0.7791, "step": 115130 }, { "epoch": 9.57, "learning_rate": 2.7252390322312445e-06, "loss": 0.8761, "step": 115140 }, { "epoch": 9.57, "learning_rate": 2.725128176703711e-06, "loss": 0.8303, "step": 115150 }, { "epoch": 9.57, "learning_rate": 2.7250173211761767e-06, "loss": 0.765, "step": 115160 }, { "epoch": 9.57, "learning_rate": 2.7249064656486434e-06, "loss": 0.746, "step": 115170 }, { "epoch": 9.57, "learning_rate": 2.7247956101211093e-06, "loss": 0.7884, "step": 115180 }, { "epoch": 9.57, "learning_rate": 2.724684754593576e-06, "loss": 0.8062, "step": 115190 }, { "epoch": 9.58, "learning_rate": 2.724573899066042e-06, "loss": 0.8437, "step": 115200 }, { "epoch": 9.58, "learning_rate": 2.724463043538508e-06, "loss": 0.8381, "step": 115210 }, { "epoch": 9.58, "learning_rate": 2.724352188010975e-06, "loss": 0.8098, "step": 115220 }, { "epoch": 9.58, "learning_rate": 2.7242413324834408e-06, "loss": 0.7792, "step": 115230 }, { "epoch": 9.58, "learning_rate": 2.724130476955907e-06, "loss": 0.8334, "step": 115240 }, { "epoch": 9.58, "learning_rate": 2.7240196214283734e-06, "loss": 0.7515, "step": 115250 }, { "epoch": 9.58, "learning_rate": 2.7239087659008397e-06, "loss": 0.7699, "step": 115260 }, { "epoch": 9.58, "learning_rate": 2.723797910373306e-06, "loss": 0.7693, "step": 115270 }, { "epoch": 9.58, "learning_rate": 2.7236870548457723e-06, "loss": 0.8144, "step": 115280 }, { "epoch": 9.58, "learning_rate": 2.723576199318238e-06, "loss": 0.8592, "step": 115290 }, { "epoch": 9.58, "learning_rate": 2.723465343790705e-06, "loss": 0.8264, "step": 115300 }, { "epoch": 9.58, "learning_rate": 2.7233544882631707e-06, "loss": 0.8093, "step": 115310 }, { "epoch": 9.59, "learning_rate": 2.723243632735637e-06, "loss": 0.8523, "step": 115320 }, { "epoch": 9.59, "learning_rate": 2.7231327772081037e-06, "loss": 0.8338, "step": 115330 }, { "epoch": 9.59, "learning_rate": 2.7230219216805696e-06, "loss": 0.8558, "step": 115340 }, { "epoch": 9.59, "learning_rate": 2.7229110661530363e-06, "loss": 0.7883, "step": 115350 }, { "epoch": 9.59, "learning_rate": 2.722800210625502e-06, "loss": 0.8143, "step": 115360 }, { "epoch": 9.59, "learning_rate": 2.7226893550979685e-06, "loss": 0.8089, "step": 115370 }, { "epoch": 9.59, "learning_rate": 2.7225784995704348e-06, "loss": 0.8096, "step": 115380 }, { "epoch": 9.59, "learning_rate": 2.722467644042901e-06, "loss": 0.796, "step": 115390 }, { "epoch": 9.59, "learning_rate": 2.722356788515367e-06, "loss": 0.8475, "step": 115400 }, { "epoch": 9.59, "learning_rate": 2.7222459329878337e-06, "loss": 0.831, "step": 115410 }, { "epoch": 9.59, "learning_rate": 2.7221350774602995e-06, "loss": 0.833, "step": 115420 }, { "epoch": 9.59, "learning_rate": 2.722024221932766e-06, "loss": 0.8228, "step": 115430 }, { "epoch": 9.6, "learning_rate": 2.721913366405232e-06, "loss": 0.799, "step": 115440 }, { "epoch": 9.6, "learning_rate": 2.7218025108776984e-06, "loss": 0.8363, "step": 115450 }, { "epoch": 9.6, "learning_rate": 2.721691655350165e-06, "loss": 0.7894, "step": 115460 }, { "epoch": 9.6, "learning_rate": 2.721580799822631e-06, "loss": 0.7434, "step": 115470 }, { "epoch": 9.6, "learning_rate": 2.7214699442950973e-06, "loss": 0.8175, "step": 115480 }, { "epoch": 9.6, "learning_rate": 2.7213590887675636e-06, "loss": 0.8685, "step": 115490 }, { "epoch": 9.6, "learning_rate": 2.72124823324003e-06, "loss": 0.8512, "step": 115500 }, { "epoch": 9.6, "learning_rate": 2.7211373777124958e-06, "loss": 0.7498, "step": 115510 }, { "epoch": 9.6, "learning_rate": 2.7210265221849625e-06, "loss": 0.7567, "step": 115520 }, { "epoch": 9.6, "learning_rate": 2.7209156666574284e-06, "loss": 0.7692, "step": 115530 }, { "epoch": 9.6, "learning_rate": 2.720804811129895e-06, "loss": 0.8477, "step": 115540 }, { "epoch": 9.6, "learning_rate": 2.720693955602361e-06, "loss": 0.7883, "step": 115550 }, { "epoch": 9.61, "learning_rate": 2.7205831000748273e-06, "loss": 0.8149, "step": 115560 }, { "epoch": 9.61, "learning_rate": 2.7204722445472936e-06, "loss": 0.7583, "step": 115570 }, { "epoch": 9.61, "learning_rate": 2.72036138901976e-06, "loss": 0.7941, "step": 115580 }, { "epoch": 9.61, "learning_rate": 2.720250533492226e-06, "loss": 0.8622, "step": 115590 }, { "epoch": 9.61, "learning_rate": 2.7201396779646924e-06, "loss": 0.7738, "step": 115600 }, { "epoch": 9.61, "learning_rate": 2.7200288224371587e-06, "loss": 0.7631, "step": 115610 }, { "epoch": 9.61, "learning_rate": 2.719917966909625e-06, "loss": 0.8047, "step": 115620 }, { "epoch": 9.61, "learning_rate": 2.7198071113820913e-06, "loss": 0.834, "step": 115630 }, { "epoch": 9.61, "learning_rate": 2.719696255854557e-06, "loss": 0.8241, "step": 115640 }, { "epoch": 9.61, "learning_rate": 2.719585400327024e-06, "loss": 0.823, "step": 115650 }, { "epoch": 9.61, "learning_rate": 2.7194745447994898e-06, "loss": 0.8236, "step": 115660 }, { "epoch": 9.61, "learning_rate": 2.719363689271956e-06, "loss": 0.8076, "step": 115670 }, { "epoch": 9.62, "learning_rate": 2.7192528337444224e-06, "loss": 0.7651, "step": 115680 }, { "epoch": 9.62, "learning_rate": 2.7191419782168887e-06, "loss": 0.863, "step": 115690 }, { "epoch": 9.62, "learning_rate": 2.7190311226893554e-06, "loss": 0.8044, "step": 115700 }, { "epoch": 9.62, "learning_rate": 2.7189202671618213e-06, "loss": 0.8455, "step": 115710 }, { "epoch": 9.62, "learning_rate": 2.7188094116342876e-06, "loss": 0.8183, "step": 115720 }, { "epoch": 9.62, "learning_rate": 2.718698556106754e-06, "loss": 0.788, "step": 115730 }, { "epoch": 9.62, "learning_rate": 2.71858770057922e-06, "loss": 0.8547, "step": 115740 }, { "epoch": 9.62, "learning_rate": 2.718476845051686e-06, "loss": 0.7885, "step": 115750 }, { "epoch": 9.62, "learning_rate": 2.7183659895241527e-06, "loss": 0.7825, "step": 115760 }, { "epoch": 9.62, "learning_rate": 2.7182551339966186e-06, "loss": 0.7649, "step": 115770 }, { "epoch": 9.62, "learning_rate": 2.718144278469085e-06, "loss": 0.8346, "step": 115780 }, { "epoch": 9.62, "learning_rate": 2.718033422941551e-06, "loss": 0.8169, "step": 115790 }, { "epoch": 9.63, "learning_rate": 2.7179225674140175e-06, "loss": 0.7606, "step": 115800 }, { "epoch": 9.63, "learning_rate": 2.717811711886484e-06, "loss": 0.7766, "step": 115810 }, { "epoch": 9.63, "learning_rate": 2.71770085635895e-06, "loss": 0.8509, "step": 115820 }, { "epoch": 9.63, "learning_rate": 2.7175900008314164e-06, "loss": 0.7671, "step": 115830 }, { "epoch": 9.63, "learning_rate": 2.7174791453038827e-06, "loss": 0.883, "step": 115840 }, { "epoch": 9.63, "learning_rate": 2.717368289776349e-06, "loss": 0.8343, "step": 115850 }, { "epoch": 9.63, "learning_rate": 2.717257434248815e-06, "loss": 0.8602, "step": 115860 }, { "epoch": 9.63, "learning_rate": 2.7171465787212816e-06, "loss": 0.7908, "step": 115870 }, { "epoch": 9.63, "learning_rate": 2.7170357231937474e-06, "loss": 0.8319, "step": 115880 }, { "epoch": 9.63, "learning_rate": 2.716924867666214e-06, "loss": 0.9103, "step": 115890 }, { "epoch": 9.63, "learning_rate": 2.71681401213868e-06, "loss": 0.7984, "step": 115900 }, { "epoch": 9.63, "learning_rate": 2.7167031566111463e-06, "loss": 0.782, "step": 115910 }, { "epoch": 9.64, "learning_rate": 2.7165923010836126e-06, "loss": 0.7432, "step": 115920 }, { "epoch": 9.64, "learning_rate": 2.716481445556079e-06, "loss": 0.7718, "step": 115930 }, { "epoch": 9.64, "learning_rate": 2.7163705900285448e-06, "loss": 0.8806, "step": 115940 }, { "epoch": 9.64, "learning_rate": 2.7162597345010115e-06, "loss": 0.8697, "step": 115950 }, { "epoch": 9.64, "learning_rate": 2.716148878973478e-06, "loss": 0.7904, "step": 115960 }, { "epoch": 9.64, "learning_rate": 2.716038023445944e-06, "loss": 0.7727, "step": 115970 }, { "epoch": 9.64, "learning_rate": 2.7159271679184104e-06, "loss": 0.7981, "step": 115980 }, { "epoch": 9.64, "learning_rate": 2.7158163123908763e-06, "loss": 0.7643, "step": 115990 }, { "epoch": 9.64, "learning_rate": 2.715705456863343e-06, "loss": 0.8182, "step": 116000 }, { "epoch": 9.64, "learning_rate": 2.715594601335809e-06, "loss": 0.737, "step": 116010 }, { "epoch": 9.64, "learning_rate": 2.715483745808275e-06, "loss": 0.7463, "step": 116020 }, { "epoch": 9.64, "learning_rate": 2.7153728902807414e-06, "loss": 0.8018, "step": 116030 }, { "epoch": 9.65, "learning_rate": 2.7152620347532077e-06, "loss": 0.9004, "step": 116040 }, { "epoch": 9.65, "learning_rate": 2.715151179225674e-06, "loss": 0.8385, "step": 116050 }, { "epoch": 9.65, "learning_rate": 2.7150403236981403e-06, "loss": 0.795, "step": 116060 }, { "epoch": 9.65, "learning_rate": 2.7149294681706066e-06, "loss": 0.8274, "step": 116070 }, { "epoch": 9.65, "learning_rate": 2.714818612643073e-06, "loss": 0.8175, "step": 116080 }, { "epoch": 9.65, "learning_rate": 2.7147077571155392e-06, "loss": 0.7387, "step": 116090 }, { "epoch": 9.65, "learning_rate": 2.714596901588005e-06, "loss": 0.8233, "step": 116100 }, { "epoch": 9.65, "learning_rate": 2.714486046060472e-06, "loss": 0.8162, "step": 116110 }, { "epoch": 9.65, "learning_rate": 2.7143751905329377e-06, "loss": 0.782, "step": 116120 }, { "epoch": 9.65, "learning_rate": 2.7142643350054044e-06, "loss": 0.781, "step": 116130 }, { "epoch": 9.65, "learning_rate": 2.7141534794778703e-06, "loss": 0.8302, "step": 116140 }, { "epoch": 9.65, "learning_rate": 2.7140426239503366e-06, "loss": 0.8086, "step": 116150 }, { "epoch": 9.66, "learning_rate": 2.713931768422803e-06, "loss": 0.776, "step": 116160 }, { "epoch": 9.66, "learning_rate": 2.713820912895269e-06, "loss": 0.7419, "step": 116170 }, { "epoch": 9.66, "learning_rate": 2.713710057367735e-06, "loss": 0.8066, "step": 116180 }, { "epoch": 9.66, "learning_rate": 2.7135992018402017e-06, "loss": 0.8973, "step": 116190 }, { "epoch": 9.66, "learning_rate": 2.713488346312668e-06, "loss": 0.8044, "step": 116200 }, { "epoch": 9.66, "learning_rate": 2.713377490785134e-06, "loss": 0.7642, "step": 116210 }, { "epoch": 9.66, "learning_rate": 2.7132666352576006e-06, "loss": 0.7953, "step": 116220 }, { "epoch": 9.66, "learning_rate": 2.71316686528282e-06, "loss": 0.805, "step": 116230 }, { "epoch": 9.66, "learning_rate": 2.713056009755286e-06, "loss": 0.8557, "step": 116240 }, { "epoch": 9.66, "learning_rate": 2.7129451542277528e-06, "loss": 0.7821, "step": 116250 }, { "epoch": 9.66, "learning_rate": 2.7128342987002186e-06, "loss": 0.7563, "step": 116260 }, { "epoch": 9.66, "learning_rate": 2.712723443172685e-06, "loss": 0.7226, "step": 116270 }, { "epoch": 9.67, "learning_rate": 2.7126125876451516e-06, "loss": 0.8067, "step": 116280 }, { "epoch": 9.67, "learning_rate": 2.7125017321176175e-06, "loss": 0.9087, "step": 116290 }, { "epoch": 9.67, "learning_rate": 2.7123908765900842e-06, "loss": 0.7563, "step": 116300 }, { "epoch": 9.67, "learning_rate": 2.71228002106255e-06, "loss": 0.8549, "step": 116310 }, { "epoch": 9.67, "learning_rate": 2.7121691655350164e-06, "loss": 0.812, "step": 116320 }, { "epoch": 9.67, "learning_rate": 2.7120583100074827e-06, "loss": 0.7903, "step": 116330 }, { "epoch": 9.67, "learning_rate": 2.711947454479949e-06, "loss": 0.7905, "step": 116340 }, { "epoch": 9.67, "learning_rate": 2.711836598952415e-06, "loss": 0.7279, "step": 116350 }, { "epoch": 9.67, "learning_rate": 2.7117257434248816e-06, "loss": 0.7581, "step": 116360 }, { "epoch": 9.67, "learning_rate": 2.7116148878973475e-06, "loss": 0.8486, "step": 116370 }, { "epoch": 9.67, "learning_rate": 2.7115040323698138e-06, "loss": 0.8269, "step": 116380 }, { "epoch": 9.67, "learning_rate": 2.71139317684228e-06, "loss": 0.8056, "step": 116390 }, { "epoch": 9.68, "learning_rate": 2.7112823213147463e-06, "loss": 0.7852, "step": 116400 }, { "epoch": 9.68, "learning_rate": 2.711171465787213e-06, "loss": 0.8182, "step": 116410 }, { "epoch": 9.68, "learning_rate": 2.711060610259679e-06, "loss": 0.7281, "step": 116420 }, { "epoch": 9.68, "learning_rate": 2.7109497547321452e-06, "loss": 0.8143, "step": 116430 }, { "epoch": 9.68, "learning_rate": 2.7108388992046115e-06, "loss": 0.876, "step": 116440 }, { "epoch": 9.68, "learning_rate": 2.710728043677078e-06, "loss": 0.7505, "step": 116450 }, { "epoch": 9.68, "learning_rate": 2.7106171881495437e-06, "loss": 0.7981, "step": 116460 }, { "epoch": 9.68, "learning_rate": 2.7105063326220104e-06, "loss": 0.7775, "step": 116470 }, { "epoch": 9.68, "learning_rate": 2.7103954770944763e-06, "loss": 0.8298, "step": 116480 }, { "epoch": 9.68, "learning_rate": 2.710284621566943e-06, "loss": 0.8293, "step": 116490 }, { "epoch": 9.68, "learning_rate": 2.710173766039409e-06, "loss": 0.7698, "step": 116500 }, { "epoch": 9.68, "learning_rate": 2.710062910511875e-06, "loss": 0.8562, "step": 116510 }, { "epoch": 9.68, "learning_rate": 2.7099520549843415e-06, "loss": 0.7434, "step": 116520 }, { "epoch": 9.69, "learning_rate": 2.7098411994568078e-06, "loss": 0.8668, "step": 116530 }, { "epoch": 9.69, "learning_rate": 2.709730343929274e-06, "loss": 0.853, "step": 116540 }, { "epoch": 9.69, "learning_rate": 2.7096194884017404e-06, "loss": 0.8346, "step": 116550 }, { "epoch": 9.69, "learning_rate": 2.7095086328742066e-06, "loss": 0.8418, "step": 116560 }, { "epoch": 9.69, "learning_rate": 2.709397777346673e-06, "loss": 0.8324, "step": 116570 }, { "epoch": 9.69, "learning_rate": 2.7092869218191392e-06, "loss": 0.7986, "step": 116580 }, { "epoch": 9.69, "learning_rate": 2.709176066291605e-06, "loss": 0.8273, "step": 116590 }, { "epoch": 9.69, "learning_rate": 2.709065210764072e-06, "loss": 0.7263, "step": 116600 }, { "epoch": 9.69, "learning_rate": 2.7089543552365377e-06, "loss": 0.8256, "step": 116610 }, { "epoch": 9.69, "learning_rate": 2.708843499709004e-06, "loss": 0.8281, "step": 116620 }, { "epoch": 9.69, "learning_rate": 2.7087326441814703e-06, "loss": 0.8125, "step": 116630 }, { "epoch": 9.69, "learning_rate": 2.7086217886539366e-06, "loss": 0.8351, "step": 116640 }, { "epoch": 9.7, "learning_rate": 2.7085109331264033e-06, "loss": 0.8367, "step": 116650 }, { "epoch": 9.7, "learning_rate": 2.708400077598869e-06, "loss": 0.7731, "step": 116660 }, { "epoch": 9.7, "learning_rate": 2.7082892220713355e-06, "loss": 0.8582, "step": 116670 }, { "epoch": 9.7, "learning_rate": 2.7081783665438018e-06, "loss": 0.8091, "step": 116680 }, { "epoch": 9.7, "learning_rate": 2.708067511016268e-06, "loss": 0.8312, "step": 116690 }, { "epoch": 9.7, "learning_rate": 2.707956655488734e-06, "loss": 0.8619, "step": 116700 }, { "epoch": 9.7, "learning_rate": 2.7078457999612007e-06, "loss": 0.8235, "step": 116710 }, { "epoch": 9.7, "learning_rate": 2.7077349444336665e-06, "loss": 0.8183, "step": 116720 }, { "epoch": 9.7, "learning_rate": 2.707624088906133e-06, "loss": 0.7739, "step": 116730 }, { "epoch": 9.7, "learning_rate": 2.707513233378599e-06, "loss": 0.8368, "step": 116740 }, { "epoch": 9.7, "learning_rate": 2.7074023778510654e-06, "loss": 0.8978, "step": 116750 }, { "epoch": 9.7, "learning_rate": 2.7072915223235317e-06, "loss": 0.796, "step": 116760 }, { "epoch": 9.71, "learning_rate": 2.707180666795998e-06, "loss": 0.7692, "step": 116770 }, { "epoch": 9.71, "learning_rate": 2.7070698112684643e-06, "loss": 0.8493, "step": 116780 }, { "epoch": 9.71, "learning_rate": 2.7069589557409306e-06, "loss": 0.9089, "step": 116790 }, { "epoch": 9.71, "learning_rate": 2.706848100213397e-06, "loss": 0.7959, "step": 116800 }, { "epoch": 9.71, "learning_rate": 2.7067372446858628e-06, "loss": 0.704, "step": 116810 }, { "epoch": 9.71, "learning_rate": 2.7066263891583295e-06, "loss": 0.8124, "step": 116820 }, { "epoch": 9.71, "learning_rate": 2.7065155336307953e-06, "loss": 0.8186, "step": 116830 }, { "epoch": 9.71, "learning_rate": 2.706404678103262e-06, "loss": 0.8871, "step": 116840 }, { "epoch": 9.71, "learning_rate": 2.706293822575728e-06, "loss": 0.7815, "step": 116850 }, { "epoch": 9.71, "learning_rate": 2.7061829670481942e-06, "loss": 0.8064, "step": 116860 }, { "epoch": 9.71, "learning_rate": 2.7060721115206605e-06, "loss": 0.8008, "step": 116870 }, { "epoch": 9.71, "learning_rate": 2.705961255993127e-06, "loss": 0.8087, "step": 116880 }, { "epoch": 9.72, "learning_rate": 2.7058504004655927e-06, "loss": 0.8084, "step": 116890 }, { "epoch": 9.72, "learning_rate": 2.7057395449380594e-06, "loss": 0.7949, "step": 116900 }, { "epoch": 9.72, "learning_rate": 2.7056286894105257e-06, "loss": 0.7724, "step": 116910 }, { "epoch": 9.72, "learning_rate": 2.705517833882992e-06, "loss": 0.7365, "step": 116920 }, { "epoch": 9.72, "learning_rate": 2.7054069783554583e-06, "loss": 0.7766, "step": 116930 }, { "epoch": 9.72, "learning_rate": 2.705296122827924e-06, "loss": 0.8913, "step": 116940 }, { "epoch": 9.72, "learning_rate": 2.705185267300391e-06, "loss": 0.7677, "step": 116950 }, { "epoch": 9.72, "learning_rate": 2.7050744117728568e-06, "loss": 0.7796, "step": 116960 }, { "epoch": 9.72, "learning_rate": 2.704963556245323e-06, "loss": 0.7963, "step": 116970 }, { "epoch": 9.72, "learning_rate": 2.7048527007177894e-06, "loss": 0.7904, "step": 116980 }, { "epoch": 9.72, "learning_rate": 2.7047418451902557e-06, "loss": 0.8415, "step": 116990 }, { "epoch": 9.72, "learning_rate": 2.704630989662722e-06, "loss": 0.8377, "step": 117000 }, { "epoch": 9.73, "learning_rate": 2.7045201341351882e-06, "loss": 0.8169, "step": 117010 }, { "epoch": 9.73, "learning_rate": 2.7044092786076545e-06, "loss": 0.8464, "step": 117020 }, { "epoch": 9.73, "learning_rate": 2.704298423080121e-06, "loss": 0.8325, "step": 117030 }, { "epoch": 9.73, "learning_rate": 2.704187567552587e-06, "loss": 0.8695, "step": 117040 }, { "epoch": 9.73, "learning_rate": 2.704076712025053e-06, "loss": 0.7949, "step": 117050 }, { "epoch": 9.73, "learning_rate": 2.7039658564975197e-06, "loss": 0.8032, "step": 117060 }, { "epoch": 9.73, "learning_rate": 2.7038550009699856e-06, "loss": 0.8077, "step": 117070 }, { "epoch": 9.73, "learning_rate": 2.7037441454424523e-06, "loss": 0.8464, "step": 117080 }, { "epoch": 9.73, "learning_rate": 2.703633289914918e-06, "loss": 0.775, "step": 117090 }, { "epoch": 9.73, "learning_rate": 2.7035224343873845e-06, "loss": 0.8579, "step": 117100 }, { "epoch": 9.73, "learning_rate": 2.7034115788598508e-06, "loss": 0.7954, "step": 117110 }, { "epoch": 9.73, "learning_rate": 2.703300723332317e-06, "loss": 0.7686, "step": 117120 }, { "epoch": 9.74, "learning_rate": 2.703189867804783e-06, "loss": 0.7852, "step": 117130 }, { "epoch": 9.74, "learning_rate": 2.7030790122772497e-06, "loss": 0.8444, "step": 117140 }, { "epoch": 9.74, "learning_rate": 2.702968156749716e-06, "loss": 0.8033, "step": 117150 }, { "epoch": 9.74, "learning_rate": 2.702857301222182e-06, "loss": 0.808, "step": 117160 }, { "epoch": 9.74, "learning_rate": 2.7027464456946485e-06, "loss": 0.7516, "step": 117170 }, { "epoch": 9.74, "learning_rate": 2.7026355901671144e-06, "loss": 0.7744, "step": 117180 }, { "epoch": 9.74, "learning_rate": 2.702524734639581e-06, "loss": 0.8259, "step": 117190 }, { "epoch": 9.74, "learning_rate": 2.702413879112047e-06, "loss": 0.7907, "step": 117200 }, { "epoch": 9.74, "learning_rate": 2.7023030235845133e-06, "loss": 0.7709, "step": 117210 }, { "epoch": 9.74, "learning_rate": 2.7021921680569796e-06, "loss": 0.8247, "step": 117220 }, { "epoch": 9.74, "learning_rate": 2.702081312529446e-06, "loss": 0.7167, "step": 117230 }, { "epoch": 9.74, "learning_rate": 2.7019704570019118e-06, "loss": 0.8095, "step": 117240 }, { "epoch": 9.75, "learning_rate": 2.7018596014743785e-06, "loss": 0.7685, "step": 117250 }, { "epoch": 9.75, "learning_rate": 2.7017487459468444e-06, "loss": 0.8343, "step": 117260 }, { "epoch": 9.75, "learning_rate": 2.701637890419311e-06, "loss": 0.7644, "step": 117270 }, { "epoch": 9.75, "learning_rate": 2.7015270348917774e-06, "loss": 0.8835, "step": 117280 }, { "epoch": 9.75, "learning_rate": 2.7014161793642432e-06, "loss": 0.8092, "step": 117290 }, { "epoch": 9.75, "learning_rate": 2.70130532383671e-06, "loss": 0.7339, "step": 117300 }, { "epoch": 9.75, "learning_rate": 2.701194468309176e-06, "loss": 0.7271, "step": 117310 }, { "epoch": 9.75, "learning_rate": 2.701083612781642e-06, "loss": 0.8308, "step": 117320 }, { "epoch": 9.75, "learning_rate": 2.7009727572541084e-06, "loss": 0.7801, "step": 117330 }, { "epoch": 9.75, "learning_rate": 2.7008619017265747e-06, "loss": 0.8173, "step": 117340 }, { "epoch": 9.75, "learning_rate": 2.700751046199041e-06, "loss": 0.7754, "step": 117350 }, { "epoch": 9.75, "learning_rate": 2.7006401906715073e-06, "loss": 0.8249, "step": 117360 }, { "epoch": 9.76, "learning_rate": 2.700529335143973e-06, "loss": 0.852, "step": 117370 }, { "epoch": 9.76, "learning_rate": 2.70041847961644e-06, "loss": 0.7772, "step": 117380 }, { "epoch": 9.76, "learning_rate": 2.700307624088906e-06, "loss": 0.9043, "step": 117390 }, { "epoch": 9.76, "learning_rate": 2.700196768561372e-06, "loss": 0.7397, "step": 117400 }, { "epoch": 9.76, "learning_rate": 2.7000859130338388e-06, "loss": 0.7764, "step": 117410 }, { "epoch": 9.76, "learning_rate": 2.6999750575063047e-06, "loss": 0.7879, "step": 117420 }, { "epoch": 9.76, "learning_rate": 2.6998642019787714e-06, "loss": 0.8098, "step": 117430 }, { "epoch": 9.76, "learning_rate": 2.6997533464512372e-06, "loss": 0.8773, "step": 117440 }, { "epoch": 9.76, "learning_rate": 2.6996424909237035e-06, "loss": 0.7467, "step": 117450 }, { "epoch": 9.76, "learning_rate": 2.69953163539617e-06, "loss": 0.8201, "step": 117460 }, { "epoch": 9.76, "learning_rate": 2.699420779868636e-06, "loss": 0.7959, "step": 117470 }, { "epoch": 9.76, "learning_rate": 2.699309924341102e-06, "loss": 0.7522, "step": 117480 }, { "epoch": 9.77, "learning_rate": 2.6991990688135687e-06, "loss": 0.8376, "step": 117490 }, { "epoch": 9.77, "learning_rate": 2.6990882132860346e-06, "loss": 0.7892, "step": 117500 }, { "epoch": 9.77, "learning_rate": 2.6989773577585013e-06, "loss": 0.8015, "step": 117510 }, { "epoch": 9.77, "learning_rate": 2.6988665022309676e-06, "loss": 0.8138, "step": 117520 }, { "epoch": 9.77, "learning_rate": 2.6987556467034335e-06, "loss": 0.8637, "step": 117530 }, { "epoch": 9.77, "learning_rate": 2.6986447911759e-06, "loss": 0.8379, "step": 117540 }, { "epoch": 9.77, "learning_rate": 2.698533935648366e-06, "loss": 0.7799, "step": 117550 }, { "epoch": 9.77, "learning_rate": 2.6984230801208324e-06, "loss": 0.7491, "step": 117560 }, { "epoch": 9.77, "learning_rate": 2.6983122245932987e-06, "loss": 0.7856, "step": 117570 }, { "epoch": 9.77, "learning_rate": 2.698201369065765e-06, "loss": 0.8167, "step": 117580 }, { "epoch": 9.77, "learning_rate": 2.698090513538231e-06, "loss": 0.8297, "step": 117590 }, { "epoch": 9.77, "learning_rate": 2.6979796580106975e-06, "loss": 0.8034, "step": 117600 }, { "epoch": 9.78, "learning_rate": 2.6978688024831634e-06, "loss": 0.7519, "step": 117610 }, { "epoch": 9.78, "learning_rate": 2.69775794695563e-06, "loss": 0.795, "step": 117620 }, { "epoch": 9.78, "learning_rate": 2.6976470914280964e-06, "loss": 0.8149, "step": 117630 }, { "epoch": 9.78, "learning_rate": 2.6975362359005623e-06, "loss": 0.823, "step": 117640 }, { "epoch": 9.78, "learning_rate": 2.697425380373029e-06, "loss": 0.7708, "step": 117650 }, { "epoch": 9.78, "learning_rate": 2.697314524845495e-06, "loss": 0.7804, "step": 117660 }, { "epoch": 9.78, "learning_rate": 2.697203669317961e-06, "loss": 0.7866, "step": 117670 }, { "epoch": 9.78, "learning_rate": 2.6970928137904275e-06, "loss": 0.7923, "step": 117680 }, { "epoch": 9.78, "learning_rate": 2.6969819582628938e-06, "loss": 0.8769, "step": 117690 }, { "epoch": 9.78, "learning_rate": 2.69687110273536e-06, "loss": 0.7675, "step": 117700 }, { "epoch": 9.78, "learning_rate": 2.6967602472078264e-06, "loss": 0.8244, "step": 117710 }, { "epoch": 9.78, "learning_rate": 2.6966493916802922e-06, "loss": 0.7818, "step": 117720 }, { "epoch": 9.79, "learning_rate": 2.696538536152759e-06, "loss": 0.7945, "step": 117730 }, { "epoch": 9.79, "learning_rate": 2.696427680625225e-06, "loss": 0.8513, "step": 117740 }, { "epoch": 9.79, "learning_rate": 2.696316825097691e-06, "loss": 0.7618, "step": 117750 }, { "epoch": 9.79, "learning_rate": 2.696205969570158e-06, "loss": 0.8105, "step": 117760 }, { "epoch": 9.79, "learning_rate": 2.6960951140426237e-06, "loss": 0.7953, "step": 117770 }, { "epoch": 9.79, "learning_rate": 2.6959842585150904e-06, "loss": 0.8541, "step": 117780 }, { "epoch": 9.79, "learning_rate": 2.6958734029875563e-06, "loss": 0.8026, "step": 117790 }, { "epoch": 9.79, "learning_rate": 2.6957625474600226e-06, "loss": 0.7844, "step": 117800 }, { "epoch": 9.79, "learning_rate": 2.695651691932489e-06, "loss": 0.7686, "step": 117810 }, { "epoch": 9.79, "learning_rate": 2.695540836404955e-06, "loss": 0.7428, "step": 117820 }, { "epoch": 9.79, "learning_rate": 2.695429980877421e-06, "loss": 0.7554, "step": 117830 }, { "epoch": 9.79, "learning_rate": 2.695319125349888e-06, "loss": 0.7611, "step": 117840 }, { "epoch": 9.8, "learning_rate": 2.6952082698223537e-06, "loss": 0.7857, "step": 117850 }, { "epoch": 9.8, "learning_rate": 2.6950974142948204e-06, "loss": 0.7971, "step": 117860 }, { "epoch": 9.8, "learning_rate": 2.6949865587672863e-06, "loss": 0.7753, "step": 117870 }, { "epoch": 9.8, "learning_rate": 2.6948757032397525e-06, "loss": 0.8195, "step": 117880 }, { "epoch": 9.8, "learning_rate": 2.6947648477122193e-06, "loss": 0.8024, "step": 117890 }, { "epoch": 9.8, "learning_rate": 2.694653992184685e-06, "loss": 0.7495, "step": 117900 }, { "epoch": 9.8, "learning_rate": 2.6945431366571514e-06, "loss": 0.7893, "step": 117910 }, { "epoch": 9.8, "learning_rate": 2.6944322811296177e-06, "loss": 0.7516, "step": 117920 }, { "epoch": 9.8, "learning_rate": 2.694321425602084e-06, "loss": 0.7643, "step": 117930 }, { "epoch": 9.8, "learning_rate": 2.69421057007455e-06, "loss": 0.8574, "step": 117940 }, { "epoch": 9.8, "learning_rate": 2.6940997145470166e-06, "loss": 0.7583, "step": 117950 }, { "epoch": 9.8, "learning_rate": 2.6939888590194825e-06, "loss": 0.7601, "step": 117960 }, { "epoch": 9.81, "learning_rate": 2.693878003491949e-06, "loss": 0.8105, "step": 117970 }, { "epoch": 9.81, "learning_rate": 2.693767147964415e-06, "loss": 0.756, "step": 117980 }, { "epoch": 9.81, "learning_rate": 2.6936562924368814e-06, "loss": 0.9048, "step": 117990 }, { "epoch": 9.81, "learning_rate": 2.693545436909348e-06, "loss": 0.9097, "step": 118000 }, { "epoch": 9.81, "learning_rate": 2.693434581381814e-06, "loss": 0.8372, "step": 118010 }, { "epoch": 9.81, "learning_rate": 2.6933237258542803e-06, "loss": 0.7851, "step": 118020 }, { "epoch": 9.81, "learning_rate": 2.6932128703267466e-06, "loss": 0.7438, "step": 118030 }, { "epoch": 9.81, "learning_rate": 2.693102014799213e-06, "loss": 0.8164, "step": 118040 }, { "epoch": 9.81, "learning_rate": 2.692991159271679e-06, "loss": 0.7047, "step": 118050 }, { "epoch": 9.81, "learning_rate": 2.6928803037441454e-06, "loss": 0.8866, "step": 118060 }, { "epoch": 9.81, "learning_rate": 2.6927694482166113e-06, "loss": 0.7759, "step": 118070 }, { "epoch": 9.81, "learning_rate": 2.692658592689078e-06, "loss": 0.8076, "step": 118080 }, { "epoch": 9.82, "learning_rate": 2.692547737161544e-06, "loss": 0.8448, "step": 118090 }, { "epoch": 9.82, "learning_rate": 2.69243688163401e-06, "loss": 0.7989, "step": 118100 }, { "epoch": 9.82, "learning_rate": 2.6923260261064765e-06, "loss": 0.7809, "step": 118110 }, { "epoch": 9.82, "learning_rate": 2.692215170578943e-06, "loss": 0.744, "step": 118120 }, { "epoch": 9.82, "learning_rate": 2.6921043150514095e-06, "loss": 0.8483, "step": 118130 }, { "epoch": 9.82, "learning_rate": 2.6919934595238754e-06, "loss": 0.7888, "step": 118140 }, { "epoch": 9.82, "learning_rate": 2.6918826039963417e-06, "loss": 0.8036, "step": 118150 }, { "epoch": 9.82, "learning_rate": 2.691771748468808e-06, "loss": 0.804, "step": 118160 }, { "epoch": 9.82, "learning_rate": 2.6916608929412743e-06, "loss": 0.8413, "step": 118170 }, { "epoch": 9.82, "learning_rate": 2.69155003741374e-06, "loss": 0.818, "step": 118180 }, { "epoch": 9.82, "learning_rate": 2.691439181886207e-06, "loss": 0.7917, "step": 118190 }, { "epoch": 9.82, "learning_rate": 2.6913283263586727e-06, "loss": 0.7491, "step": 118200 }, { "epoch": 9.83, "learning_rate": 2.6912174708311394e-06, "loss": 0.7816, "step": 118210 }, { "epoch": 9.83, "learning_rate": 2.6911066153036053e-06, "loss": 0.8217, "step": 118220 }, { "epoch": 9.83, "learning_rate": 2.6909957597760716e-06, "loss": 0.8955, "step": 118230 }, { "epoch": 9.83, "learning_rate": 2.690884904248538e-06, "loss": 0.8168, "step": 118240 }, { "epoch": 9.83, "learning_rate": 2.690774048721004e-06, "loss": 0.7852, "step": 118250 }, { "epoch": 9.83, "learning_rate": 2.6906631931934705e-06, "loss": 0.8101, "step": 118260 }, { "epoch": 9.83, "learning_rate": 2.690552337665937e-06, "loss": 0.7524, "step": 118270 }, { "epoch": 9.83, "learning_rate": 2.690441482138403e-06, "loss": 0.816, "step": 118280 }, { "epoch": 9.83, "learning_rate": 2.6903306266108694e-06, "loss": 0.8501, "step": 118290 }, { "epoch": 9.83, "learning_rate": 2.6902197710833357e-06, "loss": 0.8046, "step": 118300 }, { "epoch": 9.83, "learning_rate": 2.6901089155558016e-06, "loss": 0.8057, "step": 118310 }, { "epoch": 9.83, "learning_rate": 2.6899980600282683e-06, "loss": 0.8229, "step": 118320 }, { "epoch": 9.84, "learning_rate": 2.689887204500734e-06, "loss": 0.8173, "step": 118330 }, { "epoch": 9.84, "learning_rate": 2.6897763489732004e-06, "loss": 0.8078, "step": 118340 }, { "epoch": 9.84, "learning_rate": 2.68967657899842e-06, "loss": 0.847, "step": 118350 }, { "epoch": 9.84, "learning_rate": 2.6895657234708867e-06, "loss": 0.7889, "step": 118360 }, { "epoch": 9.84, "learning_rate": 2.6894548679433526e-06, "loss": 0.7951, "step": 118370 }, { "epoch": 9.84, "learning_rate": 2.6893440124158193e-06, "loss": 0.8075, "step": 118380 }, { "epoch": 9.84, "learning_rate": 2.689233156888285e-06, "loss": 0.8774, "step": 118390 }, { "epoch": 9.84, "learning_rate": 2.6891223013607515e-06, "loss": 0.7699, "step": 118400 }, { "epoch": 9.84, "learning_rate": 2.6890114458332178e-06, "loss": 0.8108, "step": 118410 }, { "epoch": 9.84, "learning_rate": 2.688900590305684e-06, "loss": 0.7624, "step": 118420 }, { "epoch": 9.84, "learning_rate": 2.68878973477815e-06, "loss": 0.8177, "step": 118430 }, { "epoch": 9.84, "learning_rate": 2.6886788792506166e-06, "loss": 0.8187, "step": 118440 }, { "epoch": 9.85, "learning_rate": 2.6885680237230825e-06, "loss": 0.7906, "step": 118450 }, { "epoch": 9.85, "learning_rate": 2.6884571681955492e-06, "loss": 0.7813, "step": 118460 }, { "epoch": 9.85, "learning_rate": 2.6883463126680155e-06, "loss": 0.7556, "step": 118470 }, { "epoch": 9.85, "learning_rate": 2.6882354571404814e-06, "loss": 0.8621, "step": 118480 }, { "epoch": 9.85, "learning_rate": 2.688124601612948e-06, "loss": 0.8696, "step": 118490 }, { "epoch": 9.85, "learning_rate": 2.688013746085414e-06, "loss": 0.8317, "step": 118500 }, { "epoch": 9.85, "learning_rate": 2.6879028905578803e-06, "loss": 0.8384, "step": 118510 }, { "epoch": 9.85, "learning_rate": 2.6877920350303466e-06, "loss": 0.8439, "step": 118520 }, { "epoch": 9.85, "learning_rate": 2.687681179502813e-06, "loss": 0.791, "step": 118530 }, { "epoch": 9.85, "learning_rate": 2.6875703239752787e-06, "loss": 0.9, "step": 118540 }, { "epoch": 9.85, "learning_rate": 2.6874594684477455e-06, "loss": 0.7841, "step": 118550 }, { "epoch": 9.85, "learning_rate": 2.6873486129202113e-06, "loss": 0.7631, "step": 118560 }, { "epoch": 9.86, "learning_rate": 2.687237757392678e-06, "loss": 0.7652, "step": 118570 }, { "epoch": 9.86, "learning_rate": 2.6871269018651443e-06, "loss": 0.8183, "step": 118580 }, { "epoch": 9.86, "learning_rate": 2.6870160463376102e-06, "loss": 0.8275, "step": 118590 }, { "epoch": 9.86, "learning_rate": 2.686905190810077e-06, "loss": 0.8083, "step": 118600 }, { "epoch": 9.86, "learning_rate": 2.686794335282543e-06, "loss": 0.852, "step": 118610 }, { "epoch": 9.86, "learning_rate": 2.686683479755009e-06, "loss": 0.7491, "step": 118620 }, { "epoch": 9.86, "learning_rate": 2.6865726242274754e-06, "loss": 0.8175, "step": 118630 }, { "epoch": 9.86, "learning_rate": 2.6864617686999417e-06, "loss": 0.8326, "step": 118640 }, { "epoch": 9.86, "learning_rate": 2.686350913172408e-06, "loss": 0.8632, "step": 118650 }, { "epoch": 9.86, "learning_rate": 2.6862400576448743e-06, "loss": 0.7653, "step": 118660 }, { "epoch": 9.86, "learning_rate": 2.68612920211734e-06, "loss": 0.7834, "step": 118670 }, { "epoch": 9.86, "learning_rate": 2.686018346589807e-06, "loss": 0.8337, "step": 118680 }, { "epoch": 9.87, "learning_rate": 2.6859074910622727e-06, "loss": 0.7748, "step": 118690 }, { "epoch": 9.87, "learning_rate": 2.685796635534739e-06, "loss": 0.8517, "step": 118700 }, { "epoch": 9.87, "learning_rate": 2.6856857800072058e-06, "loss": 0.8597, "step": 118710 }, { "epoch": 9.87, "learning_rate": 2.6855749244796716e-06, "loss": 0.8161, "step": 118720 }, { "epoch": 9.87, "learning_rate": 2.6854640689521384e-06, "loss": 0.7771, "step": 118730 }, { "epoch": 9.87, "learning_rate": 2.6853532134246042e-06, "loss": 0.8281, "step": 118740 }, { "epoch": 9.87, "learning_rate": 2.6852423578970705e-06, "loss": 0.7767, "step": 118750 }, { "epoch": 9.87, "learning_rate": 2.685131502369537e-06, "loss": 0.7426, "step": 118760 }, { "epoch": 9.87, "learning_rate": 2.685020646842003e-06, "loss": 0.8463, "step": 118770 }, { "epoch": 9.87, "learning_rate": 2.684909791314469e-06, "loss": 0.7998, "step": 118780 }, { "epoch": 9.87, "learning_rate": 2.6847989357869357e-06, "loss": 0.7842, "step": 118790 }, { "epoch": 9.87, "learning_rate": 2.6846880802594016e-06, "loss": 0.7984, "step": 118800 }, { "epoch": 9.88, "learning_rate": 2.6845772247318683e-06, "loss": 0.7609, "step": 118810 }, { "epoch": 9.88, "learning_rate": 2.684466369204334e-06, "loss": 0.8208, "step": 118820 }, { "epoch": 9.88, "learning_rate": 2.6843555136768005e-06, "loss": 0.8576, "step": 118830 }, { "epoch": 9.88, "learning_rate": 2.684244658149267e-06, "loss": 0.8073, "step": 118840 }, { "epoch": 9.88, "learning_rate": 2.684133802621733e-06, "loss": 0.7621, "step": 118850 }, { "epoch": 9.88, "learning_rate": 2.6840229470941993e-06, "loss": 0.8096, "step": 118860 }, { "epoch": 9.88, "learning_rate": 2.6839120915666656e-06, "loss": 0.8118, "step": 118870 }, { "epoch": 9.88, "learning_rate": 2.683801236039132e-06, "loss": 0.7694, "step": 118880 }, { "epoch": 9.88, "learning_rate": 2.683690380511598e-06, "loss": 0.7995, "step": 118890 }, { "epoch": 9.88, "learning_rate": 2.6835795249840645e-06, "loss": 0.8604, "step": 118900 }, { "epoch": 9.88, "learning_rate": 2.6834686694565304e-06, "loss": 0.78, "step": 118910 }, { "epoch": 9.88, "learning_rate": 2.683357813928997e-06, "loss": 0.7759, "step": 118920 }, { "epoch": 9.89, "learning_rate": 2.683246958401463e-06, "loss": 0.7446, "step": 118930 }, { "epoch": 9.89, "learning_rate": 2.6831361028739293e-06, "loss": 0.8855, "step": 118940 }, { "epoch": 9.89, "learning_rate": 2.683025247346396e-06, "loss": 0.7628, "step": 118950 }, { "epoch": 9.89, "learning_rate": 2.682914391818862e-06, "loss": 0.7929, "step": 118960 }, { "epoch": 9.89, "learning_rate": 2.6828035362913286e-06, "loss": 0.7523, "step": 118970 }, { "epoch": 9.89, "learning_rate": 2.6826926807637945e-06, "loss": 0.8617, "step": 118980 }, { "epoch": 9.89, "learning_rate": 2.6825818252362608e-06, "loss": 0.8151, "step": 118990 }, { "epoch": 9.89, "learning_rate": 2.682470969708727e-06, "loss": 0.8393, "step": 119000 }, { "epoch": 9.89, "learning_rate": 2.6823601141811934e-06, "loss": 0.8266, "step": 119010 }, { "epoch": 9.89, "learning_rate": 2.6822492586536592e-06, "loss": 0.8083, "step": 119020 }, { "epoch": 9.89, "learning_rate": 2.682138403126126e-06, "loss": 0.7986, "step": 119030 }, { "epoch": 9.89, "learning_rate": 2.682027547598592e-06, "loss": 0.8685, "step": 119040 }, { "epoch": 9.9, "learning_rate": 2.681916692071058e-06, "loss": 0.8214, "step": 119050 }, { "epoch": 9.9, "learning_rate": 2.6818058365435244e-06, "loss": 0.7898, "step": 119060 }, { "epoch": 9.9, "learning_rate": 2.6816949810159907e-06, "loss": 0.75, "step": 119070 }, { "epoch": 9.9, "learning_rate": 2.6815841254884574e-06, "loss": 0.7954, "step": 119080 }, { "epoch": 9.9, "learning_rate": 2.6814732699609233e-06, "loss": 0.8597, "step": 119090 }, { "epoch": 9.9, "learning_rate": 2.6813624144333896e-06, "loss": 0.8297, "step": 119100 }, { "epoch": 9.9, "learning_rate": 2.681251558905856e-06, "loss": 0.8325, "step": 119110 }, { "epoch": 9.9, "learning_rate": 2.681140703378322e-06, "loss": 0.8, "step": 119120 }, { "epoch": 9.9, "learning_rate": 2.681029847850788e-06, "loss": 0.8189, "step": 119130 }, { "epoch": 9.9, "learning_rate": 2.6809189923232548e-06, "loss": 0.8515, "step": 119140 }, { "epoch": 9.9, "learning_rate": 2.6808081367957206e-06, "loss": 0.7357, "step": 119150 }, { "epoch": 9.9, "learning_rate": 2.6806972812681874e-06, "loss": 0.7955, "step": 119160 }, { "epoch": 9.91, "learning_rate": 2.6805864257406532e-06, "loss": 0.7906, "step": 119170 }, { "epoch": 9.91, "learning_rate": 2.6804755702131195e-06, "loss": 0.7991, "step": 119180 }, { "epoch": 9.91, "learning_rate": 2.680364714685586e-06, "loss": 0.8333, "step": 119190 }, { "epoch": 9.91, "learning_rate": 2.680253859158052e-06, "loss": 0.7792, "step": 119200 }, { "epoch": 9.91, "learning_rate": 2.6801430036305184e-06, "loss": 0.7517, "step": 119210 }, { "epoch": 9.91, "learning_rate": 2.6800321481029847e-06, "loss": 0.7417, "step": 119220 }, { "epoch": 9.91, "learning_rate": 2.679921292575451e-06, "loss": 0.8511, "step": 119230 }, { "epoch": 9.91, "learning_rate": 2.6798104370479173e-06, "loss": 0.8094, "step": 119240 }, { "epoch": 9.91, "learning_rate": 2.6796995815203836e-06, "loss": 0.7828, "step": 119250 }, { "epoch": 9.91, "learning_rate": 2.6795887259928495e-06, "loss": 0.7941, "step": 119260 }, { "epoch": 9.91, "learning_rate": 2.679477870465316e-06, "loss": 0.8543, "step": 119270 }, { "epoch": 9.91, "learning_rate": 2.679367014937782e-06, "loss": 0.7918, "step": 119280 }, { "epoch": 9.92, "learning_rate": 2.6792561594102484e-06, "loss": 0.8359, "step": 119290 }, { "epoch": 9.92, "learning_rate": 2.6791453038827146e-06, "loss": 0.7749, "step": 119300 }, { "epoch": 9.92, "learning_rate": 2.679034448355181e-06, "loss": 0.7879, "step": 119310 }, { "epoch": 9.92, "learning_rate": 2.6789235928276477e-06, "loss": 0.7862, "step": 119320 }, { "epoch": 9.92, "learning_rate": 2.6788127373001135e-06, "loss": 0.7812, "step": 119330 }, { "epoch": 9.92, "learning_rate": 2.67870188177258e-06, "loss": 0.8864, "step": 119340 }, { "epoch": 9.92, "learning_rate": 2.678591026245046e-06, "loss": 0.8194, "step": 119350 }, { "epoch": 9.92, "learning_rate": 2.6784801707175124e-06, "loss": 0.7893, "step": 119360 }, { "epoch": 9.92, "learning_rate": 2.6783693151899783e-06, "loss": 0.7774, "step": 119370 }, { "epoch": 9.92, "learning_rate": 2.678258459662445e-06, "loss": 0.7797, "step": 119380 }, { "epoch": 9.92, "learning_rate": 2.678147604134911e-06, "loss": 0.8824, "step": 119390 }, { "epoch": 9.92, "learning_rate": 2.678036748607377e-06, "loss": 0.7696, "step": 119400 }, { "epoch": 9.93, "learning_rate": 2.6779258930798435e-06, "loss": 0.7998, "step": 119410 }, { "epoch": 9.93, "learning_rate": 2.6778150375523098e-06, "loss": 0.7645, "step": 119420 }, { "epoch": 9.93, "learning_rate": 2.677704182024776e-06, "loss": 0.8457, "step": 119430 }, { "epoch": 9.93, "learning_rate": 2.6775933264972424e-06, "loss": 0.7915, "step": 119440 }, { "epoch": 9.93, "learning_rate": 2.6774824709697087e-06, "loss": 0.8923, "step": 119450 }, { "epoch": 9.93, "learning_rate": 2.677371615442175e-06, "loss": 0.7752, "step": 119460 }, { "epoch": 9.93, "learning_rate": 2.6772607599146412e-06, "loss": 0.8211, "step": 119470 }, { "epoch": 9.93, "learning_rate": 2.677149904387107e-06, "loss": 0.8008, "step": 119480 }, { "epoch": 9.93, "learning_rate": 2.677039048859574e-06, "loss": 0.7786, "step": 119490 }, { "epoch": 9.93, "learning_rate": 2.6769281933320397e-06, "loss": 0.7948, "step": 119500 }, { "epoch": 9.93, "learning_rate": 2.6768173378045064e-06, "loss": 0.7567, "step": 119510 }, { "epoch": 9.93, "learning_rate": 2.6767064822769723e-06, "loss": 0.7457, "step": 119520 }, { "epoch": 9.94, "learning_rate": 2.6765956267494386e-06, "loss": 0.803, "step": 119530 }, { "epoch": 9.94, "learning_rate": 2.676484771221905e-06, "loss": 0.8999, "step": 119540 }, { "epoch": 9.94, "learning_rate": 2.676373915694371e-06, "loss": 0.7962, "step": 119550 }, { "epoch": 9.94, "learning_rate": 2.676263060166837e-06, "loss": 0.7145, "step": 119560 }, { "epoch": 9.94, "learning_rate": 2.6761522046393038e-06, "loss": 0.7972, "step": 119570 }, { "epoch": 9.94, "learning_rate": 2.67604134911177e-06, "loss": 0.8129, "step": 119580 }, { "epoch": 9.94, "learning_rate": 2.6759304935842364e-06, "loss": 0.8048, "step": 119590 }, { "epoch": 9.94, "learning_rate": 2.6758196380567027e-06, "loss": 0.8008, "step": 119600 }, { "epoch": 9.94, "learning_rate": 2.6757087825291685e-06, "loss": 0.8042, "step": 119610 }, { "epoch": 9.94, "learning_rate": 2.6755979270016353e-06, "loss": 0.8585, "step": 119620 }, { "epoch": 9.94, "learning_rate": 2.675487071474101e-06, "loss": 0.7623, "step": 119630 }, { "epoch": 9.94, "learning_rate": 2.6753762159465674e-06, "loss": 0.809, "step": 119640 }, { "epoch": 9.95, "learning_rate": 2.6752653604190337e-06, "loss": 0.8098, "step": 119650 }, { "epoch": 9.95, "learning_rate": 2.6751545048915e-06, "loss": 0.8335, "step": 119660 }, { "epoch": 9.95, "learning_rate": 2.6750436493639663e-06, "loss": 0.7601, "step": 119670 }, { "epoch": 9.95, "learning_rate": 2.6749327938364326e-06, "loss": 0.8063, "step": 119680 }, { "epoch": 9.95, "learning_rate": 2.674821938308899e-06, "loss": 0.8003, "step": 119690 }, { "epoch": 9.95, "learning_rate": 2.674711082781365e-06, "loss": 0.749, "step": 119700 }, { "epoch": 9.95, "learning_rate": 2.6746002272538315e-06, "loss": 0.7618, "step": 119710 }, { "epoch": 9.95, "learning_rate": 2.6744893717262974e-06, "loss": 0.8314, "step": 119720 }, { "epoch": 9.95, "learning_rate": 2.674378516198764e-06, "loss": 0.799, "step": 119730 }, { "epoch": 9.95, "learning_rate": 2.67426766067123e-06, "loss": 0.8409, "step": 119740 }, { "epoch": 9.95, "learning_rate": 2.6741568051436967e-06, "loss": 0.7997, "step": 119750 }, { "epoch": 9.95, "learning_rate": 2.6740459496161625e-06, "loss": 0.7725, "step": 119760 }, { "epoch": 9.96, "learning_rate": 2.673935094088629e-06, "loss": 0.7602, "step": 119770 }, { "epoch": 9.96, "learning_rate": 2.673824238561095e-06, "loss": 0.8217, "step": 119780 }, { "epoch": 9.96, "learning_rate": 2.6737133830335614e-06, "loss": 0.8869, "step": 119790 }, { "epoch": 9.96, "learning_rate": 2.6736025275060273e-06, "loss": 0.7494, "step": 119800 }, { "epoch": 9.96, "learning_rate": 2.673491671978494e-06, "loss": 0.8271, "step": 119810 }, { "epoch": 9.96, "learning_rate": 2.6733808164509603e-06, "loss": 0.726, "step": 119820 }, { "epoch": 9.96, "learning_rate": 2.673269960923426e-06, "loss": 0.8185, "step": 119830 }, { "epoch": 9.96, "learning_rate": 2.673159105395893e-06, "loss": 0.8415, "step": 119840 }, { "epoch": 9.96, "learning_rate": 2.6730482498683588e-06, "loss": 0.82, "step": 119850 }, { "epoch": 9.96, "learning_rate": 2.6729373943408255e-06, "loss": 0.7852, "step": 119860 }, { "epoch": 9.96, "learning_rate": 2.6728265388132914e-06, "loss": 0.7745, "step": 119870 }, { "epoch": 9.96, "learning_rate": 2.6727156832857577e-06, "loss": 0.7888, "step": 119880 }, { "epoch": 9.97, "learning_rate": 2.672604827758224e-06, "loss": 0.8563, "step": 119890 }, { "epoch": 9.97, "learning_rate": 2.6724939722306903e-06, "loss": 0.7794, "step": 119900 }, { "epoch": 9.97, "learning_rate": 2.672383116703156e-06, "loss": 0.7932, "step": 119910 }, { "epoch": 9.97, "learning_rate": 2.672272261175623e-06, "loss": 0.7946, "step": 119920 }, { "epoch": 9.97, "learning_rate": 2.672161405648089e-06, "loss": 0.7616, "step": 119930 }, { "epoch": 9.97, "learning_rate": 2.6720505501205554e-06, "loss": 0.8018, "step": 119940 }, { "epoch": 9.97, "learning_rate": 2.6719396945930217e-06, "loss": 0.8086, "step": 119950 }, { "epoch": 9.97, "learning_rate": 2.6718288390654876e-06, "loss": 0.7774, "step": 119960 }, { "epoch": 9.97, "learning_rate": 2.6717179835379543e-06, "loss": 0.7825, "step": 119970 }, { "epoch": 9.97, "learning_rate": 2.67160712801042e-06, "loss": 0.7628, "step": 119980 }, { "epoch": 9.97, "learning_rate": 2.6714962724828865e-06, "loss": 0.8692, "step": 119990 }, { "epoch": 9.97, "learning_rate": 2.6713854169553528e-06, "loss": 0.8483, "step": 120000 }, { "epoch": 9.98, "learning_rate": 2.671274561427819e-06, "loss": 0.8236, "step": 120010 }, { "epoch": 9.98, "learning_rate": 2.6711637059002854e-06, "loss": 0.7622, "step": 120020 }, { "epoch": 9.98, "learning_rate": 2.6710528503727517e-06, "loss": 0.7006, "step": 120030 }, { "epoch": 9.98, "learning_rate": 2.6709419948452175e-06, "loss": 0.8432, "step": 120040 }, { "epoch": 9.98, "learning_rate": 2.6708311393176843e-06, "loss": 0.7792, "step": 120050 }, { "epoch": 9.98, "learning_rate": 2.6707202837901506e-06, "loss": 0.7732, "step": 120060 }, { "epoch": 9.98, "learning_rate": 2.6706094282626164e-06, "loss": 0.7208, "step": 120070 }, { "epoch": 9.98, "learning_rate": 2.670498572735083e-06, "loss": 0.787, "step": 120080 }, { "epoch": 9.98, "learning_rate": 2.670387717207549e-06, "loss": 0.8311, "step": 120090 }, { "epoch": 9.98, "learning_rate": 2.6702768616800157e-06, "loss": 0.8406, "step": 120100 }, { "epoch": 9.98, "learning_rate": 2.6701660061524816e-06, "loss": 0.8091, "step": 120110 }, { "epoch": 9.98, "learning_rate": 2.670055150624948e-06, "loss": 0.7656, "step": 120120 }, { "epoch": 9.99, "learning_rate": 2.669944295097414e-06, "loss": 0.8544, "step": 120130 }, { "epoch": 9.99, "learning_rate": 2.6698334395698805e-06, "loss": 0.748, "step": 120140 }, { "epoch": 9.99, "learning_rate": 2.6697225840423464e-06, "loss": 0.8123, "step": 120150 }, { "epoch": 9.99, "learning_rate": 2.669611728514813e-06, "loss": 0.7806, "step": 120160 }, { "epoch": 9.99, "learning_rate": 2.669500872987279e-06, "loss": 0.7592, "step": 120170 }, { "epoch": 9.99, "learning_rate": 2.6693900174597452e-06, "loss": 0.7885, "step": 120180 }, { "epoch": 9.99, "learning_rate": 2.669279161932212e-06, "loss": 0.8249, "step": 120190 }, { "epoch": 9.99, "learning_rate": 2.669168306404678e-06, "loss": 0.7471, "step": 120200 }, { "epoch": 9.99, "learning_rate": 2.6690574508771446e-06, "loss": 0.8719, "step": 120210 }, { "epoch": 9.99, "learning_rate": 2.6689465953496104e-06, "loss": 0.7694, "step": 120220 }, { "epoch": 9.99, "learning_rate": 2.6688357398220767e-06, "loss": 0.7501, "step": 120230 }, { "epoch": 9.99, "learning_rate": 2.668724884294543e-06, "loss": 0.8319, "step": 120240 }, { "epoch": 10.0, "learning_rate": 2.6686140287670093e-06, "loss": 0.8609, "step": 120250 }, { "epoch": 10.0, "learning_rate": 2.668503173239475e-06, "loss": 0.8388, "step": 120260 }, { "epoch": 10.0, "learning_rate": 2.668392317711942e-06, "loss": 0.8814, "step": 120270 }, { "epoch": 10.0, "learning_rate": 2.6682814621844078e-06, "loss": 0.8163, "step": 120280 }, { "epoch": 10.0, "learning_rate": 2.6681706066568745e-06, "loss": 0.8562, "step": 120290 }, { "epoch": 10.0, "learning_rate": 2.668059751129341e-06, "loss": 0.7376, "step": 120300 }, { "epoch": 10.0, "learning_rate": 2.6679488956018067e-06, "loss": 0.777, "step": 120310 }, { "epoch": 10.0, "eval_loss": 1.1200872659683228, "eval_runtime": 353.8745, "eval_samples_per_second": 7.556, "eval_steps_per_second": 3.778, "eval_wer": 0.6534870251868176, "step": 120310 }, { "epoch": 10.0, "learning_rate": 2.6678380400742734e-06, "loss": 0.8738, "step": 120320 }, { "epoch": 10.0, "learning_rate": 2.6677271845467393e-06, "loss": 0.7712, "step": 120330 }, { "epoch": 10.0, "learning_rate": 2.6676163290192056e-06, "loss": 0.7868, "step": 120340 }, { "epoch": 10.0, "learning_rate": 2.667505473491672e-06, "loss": 0.7374, "step": 120350 }, { "epoch": 10.0, "learning_rate": 2.667394617964138e-06, "loss": 0.7561, "step": 120360 }, { "epoch": 10.0, "learning_rate": 2.6672837624366044e-06, "loss": 0.8165, "step": 120370 }, { "epoch": 10.01, "learning_rate": 2.6671729069090707e-06, "loss": 0.7764, "step": 120380 }, { "epoch": 10.01, "learning_rate": 2.6670620513815366e-06, "loss": 0.7416, "step": 120390 }, { "epoch": 10.01, "learning_rate": 2.6669511958540033e-06, "loss": 0.7583, "step": 120400 }, { "epoch": 10.01, "learning_rate": 2.666840340326469e-06, "loss": 0.7687, "step": 120410 }, { "epoch": 10.01, "learning_rate": 2.6667294847989355e-06, "loss": 0.8692, "step": 120420 }, { "epoch": 10.01, "learning_rate": 2.666618629271402e-06, "loss": 0.8008, "step": 120430 }, { "epoch": 10.01, "learning_rate": 2.666507773743868e-06, "loss": 0.8059, "step": 120440 }, { "epoch": 10.01, "learning_rate": 2.666396918216335e-06, "loss": 0.7256, "step": 120450 }, { "epoch": 10.01, "learning_rate": 2.6662860626888007e-06, "loss": 0.8063, "step": 120460 }, { "epoch": 10.01, "learning_rate": 2.666175207161267e-06, "loss": 0.9076, "step": 120470 }, { "epoch": 10.01, "learning_rate": 2.6660643516337333e-06, "loss": 0.7759, "step": 120480 }, { "epoch": 10.01, "learning_rate": 2.6659534961061996e-06, "loss": 0.7527, "step": 120490 }, { "epoch": 10.02, "learning_rate": 2.6658426405786654e-06, "loss": 0.7479, "step": 120500 }, { "epoch": 10.02, "learning_rate": 2.665731785051132e-06, "loss": 0.817, "step": 120510 }, { "epoch": 10.02, "learning_rate": 2.665620929523598e-06, "loss": 0.864, "step": 120520 }, { "epoch": 10.02, "learning_rate": 2.6655100739960647e-06, "loss": 0.7609, "step": 120530 }, { "epoch": 10.02, "learning_rate": 2.6653992184685306e-06, "loss": 0.7536, "step": 120540 }, { "epoch": 10.02, "learning_rate": 2.665288362940997e-06, "loss": 0.7545, "step": 120550 }, { "epoch": 10.02, "learning_rate": 2.6651775074134636e-06, "loss": 0.7778, "step": 120560 }, { "epoch": 10.02, "learning_rate": 2.6650666518859295e-06, "loss": 0.8251, "step": 120570 }, { "epoch": 10.02, "learning_rate": 2.664955796358396e-06, "loss": 0.7866, "step": 120580 }, { "epoch": 10.02, "learning_rate": 2.664844940830862e-06, "loss": 0.8608, "step": 120590 }, { "epoch": 10.02, "learning_rate": 2.6647340853033284e-06, "loss": 0.8017, "step": 120600 }, { "epoch": 10.02, "learning_rate": 2.6646232297757943e-06, "loss": 0.7794, "step": 120610 }, { "epoch": 10.03, "learning_rate": 2.664512374248261e-06, "loss": 0.8255, "step": 120620 }, { "epoch": 10.03, "learning_rate": 2.664401518720727e-06, "loss": 0.848, "step": 120630 }, { "epoch": 10.03, "learning_rate": 2.6642906631931936e-06, "loss": 0.6999, "step": 120640 }, { "epoch": 10.03, "learning_rate": 2.6641798076656594e-06, "loss": 0.7714, "step": 120650 }, { "epoch": 10.03, "learning_rate": 2.6640689521381257e-06, "loss": 0.7793, "step": 120660 }, { "epoch": 10.03, "learning_rate": 2.6639580966105924e-06, "loss": 0.8129, "step": 120670 }, { "epoch": 10.03, "learning_rate": 2.6638472410830583e-06, "loss": 0.7805, "step": 120680 }, { "epoch": 10.03, "learning_rate": 2.6637363855555246e-06, "loss": 0.7823, "step": 120690 }, { "epoch": 10.03, "learning_rate": 2.663625530027991e-06, "loss": 0.8633, "step": 120700 }, { "epoch": 10.03, "learning_rate": 2.663514674500457e-06, "loss": 0.825, "step": 120710 }, { "epoch": 10.03, "learning_rate": 2.6634038189729235e-06, "loss": 0.8518, "step": 120720 }, { "epoch": 10.03, "learning_rate": 2.66329296344539e-06, "loss": 0.7727, "step": 120730 }, { "epoch": 10.04, "learning_rate": 2.6631821079178557e-06, "loss": 0.752, "step": 120740 }, { "epoch": 10.04, "learning_rate": 2.6630712523903224e-06, "loss": 0.804, "step": 120750 }, { "epoch": 10.04, "learning_rate": 2.6629603968627883e-06, "loss": 0.7776, "step": 120760 }, { "epoch": 10.04, "learning_rate": 2.6628495413352546e-06, "loss": 0.8716, "step": 120770 }, { "epoch": 10.04, "learning_rate": 2.662738685807721e-06, "loss": 0.8287, "step": 120780 }, { "epoch": 10.04, "learning_rate": 2.662627830280187e-06, "loss": 0.8284, "step": 120790 }, { "epoch": 10.04, "learning_rate": 2.662516974752654e-06, "loss": 0.7618, "step": 120800 }, { "epoch": 10.04, "learning_rate": 2.6624061192251197e-06, "loss": 0.8215, "step": 120810 }, { "epoch": 10.04, "learning_rate": 2.662295263697586e-06, "loss": 0.7975, "step": 120820 }, { "epoch": 10.04, "learning_rate": 2.6621844081700523e-06, "loss": 0.8253, "step": 120830 }, { "epoch": 10.04, "learning_rate": 2.6620735526425186e-06, "loss": 0.8493, "step": 120840 }, { "epoch": 10.04, "learning_rate": 2.6619626971149845e-06, "loss": 0.798, "step": 120850 }, { "epoch": 10.05, "learning_rate": 2.6618518415874512e-06, "loss": 0.7479, "step": 120860 }, { "epoch": 10.05, "learning_rate": 2.661740986059917e-06, "loss": 0.8224, "step": 120870 }, { "epoch": 10.05, "learning_rate": 2.661630130532384e-06, "loss": 0.7674, "step": 120880 }, { "epoch": 10.05, "learning_rate": 2.6615303605576033e-06, "loss": 0.7525, "step": 120890 }, { "epoch": 10.05, "learning_rate": 2.6614195050300696e-06, "loss": 0.7479, "step": 120900 }, { "epoch": 10.05, "learning_rate": 2.6613086495025355e-06, "loss": 0.7726, "step": 120910 }, { "epoch": 10.05, "learning_rate": 2.6611977939750022e-06, "loss": 0.9143, "step": 120920 }, { "epoch": 10.05, "learning_rate": 2.661086938447468e-06, "loss": 0.7915, "step": 120930 }, { "epoch": 10.05, "learning_rate": 2.6609760829199344e-06, "loss": 0.7009, "step": 120940 }, { "epoch": 10.05, "learning_rate": 2.6608652273924007e-06, "loss": 0.7362, "step": 120950 }, { "epoch": 10.05, "learning_rate": 2.660754371864867e-06, "loss": 0.768, "step": 120960 }, { "epoch": 10.05, "learning_rate": 2.6606435163373333e-06, "loss": 0.8855, "step": 120970 }, { "epoch": 10.06, "learning_rate": 2.6605326608097996e-06, "loss": 0.8005, "step": 120980 }, { "epoch": 10.06, "learning_rate": 2.6604218052822655e-06, "loss": 0.7907, "step": 120990 }, { "epoch": 10.06, "learning_rate": 2.660310949754732e-06, "loss": 0.8288, "step": 121000 }, { "epoch": 10.06, "learning_rate": 2.6602000942271985e-06, "loss": 0.7444, "step": 121010 }, { "epoch": 10.06, "learning_rate": 2.6600892386996643e-06, "loss": 0.7657, "step": 121020 }, { "epoch": 10.06, "learning_rate": 2.659978383172131e-06, "loss": 0.7682, "step": 121030 }, { "epoch": 10.06, "learning_rate": 2.659867527644597e-06, "loss": 0.8125, "step": 121040 }, { "epoch": 10.06, "learning_rate": 2.6597566721170636e-06, "loss": 0.8564, "step": 121050 }, { "epoch": 10.06, "learning_rate": 2.6596458165895295e-06, "loss": 0.8443, "step": 121060 }, { "epoch": 10.06, "learning_rate": 2.659534961061996e-06, "loss": 0.915, "step": 121070 }, { "epoch": 10.06, "learning_rate": 2.659424105534462e-06, "loss": 0.8032, "step": 121080 }, { "epoch": 10.06, "learning_rate": 2.6593132500069284e-06, "loss": 0.8842, "step": 121090 }, { "epoch": 10.07, "learning_rate": 2.6592023944793943e-06, "loss": 0.8401, "step": 121100 }, { "epoch": 10.07, "learning_rate": 2.659091538951861e-06, "loss": 0.7237, "step": 121110 }, { "epoch": 10.07, "learning_rate": 2.658980683424327e-06, "loss": 0.8923, "step": 121120 }, { "epoch": 10.07, "learning_rate": 2.658869827896793e-06, "loss": 0.76, "step": 121130 }, { "epoch": 10.07, "learning_rate": 2.65875897236926e-06, "loss": 0.7998, "step": 121140 }, { "epoch": 10.07, "learning_rate": 2.6586481168417258e-06, "loss": 0.8069, "step": 121150 }, { "epoch": 10.07, "learning_rate": 2.6585372613141925e-06, "loss": 0.776, "step": 121160 }, { "epoch": 10.07, "learning_rate": 2.6584264057866583e-06, "loss": 0.8683, "step": 121170 }, { "epoch": 10.07, "learning_rate": 2.6583155502591246e-06, "loss": 0.8856, "step": 121180 }, { "epoch": 10.07, "learning_rate": 2.658204694731591e-06, "loss": 0.939, "step": 121190 }, { "epoch": 10.07, "learning_rate": 2.6580938392040572e-06, "loss": 0.7498, "step": 121200 }, { "epoch": 10.07, "learning_rate": 2.657982983676523e-06, "loss": 0.8061, "step": 121210 }, { "epoch": 10.08, "learning_rate": 2.65787212814899e-06, "loss": 0.8576, "step": 121220 }, { "epoch": 10.08, "learning_rate": 2.6577612726214557e-06, "loss": 0.8223, "step": 121230 }, { "epoch": 10.08, "learning_rate": 2.6576504170939224e-06, "loss": 0.8196, "step": 121240 }, { "epoch": 10.08, "learning_rate": 2.6575395615663887e-06, "loss": 0.8138, "step": 121250 }, { "epoch": 10.08, "learning_rate": 2.6574287060388546e-06, "loss": 0.7976, "step": 121260 }, { "epoch": 10.08, "learning_rate": 2.6573178505113213e-06, "loss": 0.809, "step": 121270 }, { "epoch": 10.08, "learning_rate": 2.657206994983787e-06, "loss": 0.7525, "step": 121280 }, { "epoch": 10.08, "learning_rate": 2.6570961394562535e-06, "loss": 0.7972, "step": 121290 }, { "epoch": 10.08, "learning_rate": 2.6569852839287198e-06, "loss": 0.8109, "step": 121300 }, { "epoch": 10.08, "learning_rate": 2.656874428401186e-06, "loss": 0.7867, "step": 121310 }, { "epoch": 10.08, "learning_rate": 2.6567635728736523e-06, "loss": 0.8648, "step": 121320 }, { "epoch": 10.08, "learning_rate": 2.6566527173461186e-06, "loss": 0.8253, "step": 121330 }, { "epoch": 10.09, "learning_rate": 2.6565418618185845e-06, "loss": 0.7864, "step": 121340 }, { "epoch": 10.09, "learning_rate": 2.6564310062910512e-06, "loss": 0.6976, "step": 121350 }, { "epoch": 10.09, "learning_rate": 2.656320150763517e-06, "loss": 0.8185, "step": 121360 }, { "epoch": 10.09, "learning_rate": 2.6562092952359834e-06, "loss": 0.846, "step": 121370 }, { "epoch": 10.09, "learning_rate": 2.65609843970845e-06, "loss": 0.7763, "step": 121380 }, { "epoch": 10.09, "learning_rate": 2.655987584180916e-06, "loss": 0.8269, "step": 121390 }, { "epoch": 10.09, "learning_rate": 2.6558767286533827e-06, "loss": 0.7507, "step": 121400 }, { "epoch": 10.09, "learning_rate": 2.6557658731258486e-06, "loss": 0.8275, "step": 121410 }, { "epoch": 10.09, "learning_rate": 2.655655017598315e-06, "loss": 0.8435, "step": 121420 }, { "epoch": 10.09, "learning_rate": 2.655544162070781e-06, "loss": 0.8107, "step": 121430 }, { "epoch": 10.09, "learning_rate": 2.6554333065432475e-06, "loss": 0.7314, "step": 121440 }, { "epoch": 10.09, "learning_rate": 2.6553224510157133e-06, "loss": 0.7535, "step": 121450 }, { "epoch": 10.1, "learning_rate": 2.65521159548818e-06, "loss": 0.7946, "step": 121460 }, { "epoch": 10.1, "learning_rate": 2.655100739960646e-06, "loss": 0.8027, "step": 121470 }, { "epoch": 10.1, "learning_rate": 2.6549898844331127e-06, "loss": 0.8365, "step": 121480 }, { "epoch": 10.1, "learning_rate": 2.6548790289055785e-06, "loss": 0.7406, "step": 121490 }, { "epoch": 10.1, "learning_rate": 2.654768173378045e-06, "loss": 0.7598, "step": 121500 }, { "epoch": 10.1, "learning_rate": 2.6546573178505115e-06, "loss": 0.7826, "step": 121510 }, { "epoch": 10.1, "learning_rate": 2.6545464623229774e-06, "loss": 0.8069, "step": 121520 }, { "epoch": 10.1, "learning_rate": 2.6544356067954437e-06, "loss": 0.781, "step": 121530 }, { "epoch": 10.1, "learning_rate": 2.65432475126791e-06, "loss": 0.8484, "step": 121540 }, { "epoch": 10.1, "learning_rate": 2.6542138957403763e-06, "loss": 0.796, "step": 121550 }, { "epoch": 10.1, "learning_rate": 2.654103040212842e-06, "loss": 0.7771, "step": 121560 }, { "epoch": 10.1, "learning_rate": 2.653992184685309e-06, "loss": 0.8673, "step": 121570 }, { "epoch": 10.11, "learning_rate": 2.6538813291577748e-06, "loss": 0.791, "step": 121580 }, { "epoch": 10.11, "learning_rate": 2.6537704736302415e-06, "loss": 0.7393, "step": 121590 }, { "epoch": 10.11, "learning_rate": 2.6536596181027073e-06, "loss": 0.8425, "step": 121600 }, { "epoch": 10.11, "learning_rate": 2.6535487625751736e-06, "loss": 0.7682, "step": 121610 }, { "epoch": 10.11, "learning_rate": 2.6534379070476404e-06, "loss": 0.8356, "step": 121620 }, { "epoch": 10.11, "learning_rate": 2.6533270515201062e-06, "loss": 0.8205, "step": 121630 }, { "epoch": 10.11, "learning_rate": 2.6532161959925725e-06, "loss": 0.7623, "step": 121640 }, { "epoch": 10.11, "learning_rate": 2.653105340465039e-06, "loss": 0.7178, "step": 121650 }, { "epoch": 10.11, "learning_rate": 2.652994484937505e-06, "loss": 0.8684, "step": 121660 }, { "epoch": 10.11, "learning_rate": 2.6528836294099714e-06, "loss": 0.7747, "step": 121670 }, { "epoch": 10.11, "learning_rate": 2.6527727738824377e-06, "loss": 0.7627, "step": 121680 }, { "epoch": 10.11, "learning_rate": 2.6526619183549036e-06, "loss": 0.7393, "step": 121690 }, { "epoch": 10.12, "learning_rate": 2.6525510628273703e-06, "loss": 0.8179, "step": 121700 }, { "epoch": 10.12, "learning_rate": 2.652440207299836e-06, "loss": 0.8249, "step": 121710 }, { "epoch": 10.12, "learning_rate": 2.6523293517723025e-06, "loss": 0.8094, "step": 121720 }, { "epoch": 10.12, "learning_rate": 2.6522184962447688e-06, "loss": 0.8062, "step": 121730 }, { "epoch": 10.12, "learning_rate": 2.652107640717235e-06, "loss": 0.7262, "step": 121740 }, { "epoch": 10.12, "learning_rate": 2.6519967851897018e-06, "loss": 0.8096, "step": 121750 }, { "epoch": 10.12, "learning_rate": 2.6518859296621677e-06, "loss": 0.7293, "step": 121760 }, { "epoch": 10.12, "learning_rate": 2.651775074134634e-06, "loss": 0.8471, "step": 121770 }, { "epoch": 10.12, "learning_rate": 2.6516642186071002e-06, "loss": 0.813, "step": 121780 }, { "epoch": 10.12, "learning_rate": 2.6515533630795665e-06, "loss": 0.7932, "step": 121790 }, { "epoch": 10.12, "learning_rate": 2.6514425075520324e-06, "loss": 0.7121, "step": 121800 }, { "epoch": 10.12, "learning_rate": 2.651331652024499e-06, "loss": 0.7987, "step": 121810 }, { "epoch": 10.13, "learning_rate": 2.651220796496965e-06, "loss": 0.858, "step": 121820 }, { "epoch": 10.13, "learning_rate": 2.6511099409694317e-06, "loss": 0.8086, "step": 121830 }, { "epoch": 10.13, "learning_rate": 2.6509990854418976e-06, "loss": 0.7699, "step": 121840 }, { "epoch": 10.13, "learning_rate": 2.650888229914364e-06, "loss": 0.7836, "step": 121850 }, { "epoch": 10.13, "learning_rate": 2.65077737438683e-06, "loss": 0.7984, "step": 121860 }, { "epoch": 10.13, "learning_rate": 2.6506665188592965e-06, "loss": 0.8041, "step": 121870 }, { "epoch": 10.13, "learning_rate": 2.6505556633317628e-06, "loss": 0.7459, "step": 121880 }, { "epoch": 10.13, "learning_rate": 2.650444807804229e-06, "loss": 0.8576, "step": 121890 }, { "epoch": 10.13, "learning_rate": 2.6503339522766954e-06, "loss": 0.8117, "step": 121900 }, { "epoch": 10.13, "learning_rate": 2.6502230967491617e-06, "loss": 0.7461, "step": 121910 }, { "epoch": 10.13, "learning_rate": 2.650112241221628e-06, "loss": 0.8155, "step": 121920 }, { "epoch": 10.13, "learning_rate": 2.650001385694094e-06, "loss": 0.7621, "step": 121930 }, { "epoch": 10.14, "learning_rate": 2.6498905301665605e-06, "loss": 0.733, "step": 121940 }, { "epoch": 10.14, "learning_rate": 2.6497796746390264e-06, "loss": 0.782, "step": 121950 }, { "epoch": 10.14, "learning_rate": 2.6496688191114927e-06, "loss": 0.7835, "step": 121960 }, { "epoch": 10.14, "learning_rate": 2.649557963583959e-06, "loss": 0.8214, "step": 121970 }, { "epoch": 10.14, "learning_rate": 2.6494471080564253e-06, "loss": 0.8485, "step": 121980 }, { "epoch": 10.14, "learning_rate": 2.649336252528892e-06, "loss": 0.7932, "step": 121990 }, { "epoch": 10.14, "learning_rate": 2.649225397001358e-06, "loss": 0.7837, "step": 122000 }, { "epoch": 10.14, "learning_rate": 2.649114541473824e-06, "loss": 0.774, "step": 122010 }, { "epoch": 10.14, "learning_rate": 2.6490036859462905e-06, "loss": 0.8127, "step": 122020 }, { "epoch": 10.14, "learning_rate": 2.6488928304187568e-06, "loss": 0.8237, "step": 122030 }, { "epoch": 10.14, "learning_rate": 2.6487819748912226e-06, "loss": 0.7347, "step": 122040 }, { "epoch": 10.14, "learning_rate": 2.6486711193636894e-06, "loss": 0.7813, "step": 122050 }, { "epoch": 10.15, "learning_rate": 2.6485602638361552e-06, "loss": 0.7751, "step": 122060 }, { "epoch": 10.15, "learning_rate": 2.6484494083086215e-06, "loss": 0.8447, "step": 122070 }, { "epoch": 10.15, "learning_rate": 2.648338552781088e-06, "loss": 0.7783, "step": 122080 }, { "epoch": 10.15, "learning_rate": 2.648227697253554e-06, "loss": 0.786, "step": 122090 }, { "epoch": 10.15, "learning_rate": 2.6481168417260204e-06, "loss": 0.7235, "step": 122100 }, { "epoch": 10.15, "learning_rate": 2.6480059861984867e-06, "loss": 0.7995, "step": 122110 }, { "epoch": 10.15, "learning_rate": 2.647895130670953e-06, "loss": 0.8531, "step": 122120 }, { "epoch": 10.15, "learning_rate": 2.6477842751434193e-06, "loss": 0.794, "step": 122130 }, { "epoch": 10.15, "learning_rate": 2.6476734196158856e-06, "loss": 0.7517, "step": 122140 }, { "epoch": 10.15, "learning_rate": 2.6475625640883515e-06, "loss": 0.7953, "step": 122150 }, { "epoch": 10.15, "learning_rate": 2.647451708560818e-06, "loss": 0.7721, "step": 122160 }, { "epoch": 10.15, "learning_rate": 2.647340853033284e-06, "loss": 0.8261, "step": 122170 }, { "epoch": 10.16, "learning_rate": 2.6472299975057508e-06, "loss": 0.8312, "step": 122180 }, { "epoch": 10.16, "learning_rate": 2.6471191419782167e-06, "loss": 0.8109, "step": 122190 }, { "epoch": 10.16, "learning_rate": 2.647008286450683e-06, "loss": 0.7907, "step": 122200 }, { "epoch": 10.16, "learning_rate": 2.6468974309231492e-06, "loss": 0.7124, "step": 122210 }, { "epoch": 10.16, "learning_rate": 2.6467865753956155e-06, "loss": 0.8353, "step": 122220 }, { "epoch": 10.16, "learning_rate": 2.646675719868082e-06, "loss": 0.8516, "step": 122230 }, { "epoch": 10.16, "learning_rate": 2.646564864340548e-06, "loss": 0.7468, "step": 122240 }, { "epoch": 10.16, "learning_rate": 2.6464540088130144e-06, "loss": 0.7929, "step": 122250 }, { "epoch": 10.16, "learning_rate": 2.6463431532854807e-06, "loss": 0.8013, "step": 122260 }, { "epoch": 10.16, "learning_rate": 2.646232297757947e-06, "loss": 0.762, "step": 122270 }, { "epoch": 10.16, "learning_rate": 2.646121442230413e-06, "loss": 0.7872, "step": 122280 }, { "epoch": 10.16, "learning_rate": 2.6460105867028796e-06, "loss": 0.8127, "step": 122290 }, { "epoch": 10.17, "learning_rate": 2.6458997311753455e-06, "loss": 0.7723, "step": 122300 }, { "epoch": 10.17, "learning_rate": 2.6457888756478118e-06, "loss": 0.8051, "step": 122310 }, { "epoch": 10.17, "learning_rate": 2.645678020120278e-06, "loss": 0.8725, "step": 122320 }, { "epoch": 10.17, "learning_rate": 2.6455671645927444e-06, "loss": 0.7458, "step": 122330 }, { "epoch": 10.17, "learning_rate": 2.6454563090652102e-06, "loss": 0.8411, "step": 122340 }, { "epoch": 10.17, "learning_rate": 2.645345453537677e-06, "loss": 0.7708, "step": 122350 }, { "epoch": 10.17, "learning_rate": 2.6452345980101433e-06, "loss": 0.8075, "step": 122360 }, { "epoch": 10.17, "learning_rate": 2.6451237424826095e-06, "loss": 0.7844, "step": 122370 }, { "epoch": 10.17, "learning_rate": 2.645012886955076e-06, "loss": 0.775, "step": 122380 }, { "epoch": 10.17, "learning_rate": 2.6449020314275417e-06, "loss": 0.8638, "step": 122390 }, { "epoch": 10.17, "learning_rate": 2.6447911759000084e-06, "loss": 0.7957, "step": 122400 }, { "epoch": 10.17, "learning_rate": 2.6446803203724743e-06, "loss": 0.8245, "step": 122410 }, { "epoch": 10.18, "learning_rate": 2.6445694648449406e-06, "loss": 0.8438, "step": 122420 }, { "epoch": 10.18, "learning_rate": 2.644458609317407e-06, "loss": 0.7595, "step": 122430 }, { "epoch": 10.18, "learning_rate": 2.644347753789873e-06, "loss": 0.7932, "step": 122440 }, { "epoch": 10.18, "learning_rate": 2.6442368982623395e-06, "loss": 0.7924, "step": 122450 }, { "epoch": 10.18, "learning_rate": 2.6441260427348058e-06, "loss": 0.8038, "step": 122460 }, { "epoch": 10.18, "learning_rate": 2.6440151872072717e-06, "loss": 0.8616, "step": 122470 }, { "epoch": 10.18, "learning_rate": 2.6439043316797384e-06, "loss": 0.8345, "step": 122480 }, { "epoch": 10.18, "learning_rate": 2.6437934761522047e-06, "loss": 0.7217, "step": 122490 }, { "epoch": 10.18, "learning_rate": 2.6436826206246705e-06, "loss": 0.7896, "step": 122500 }, { "epoch": 10.18, "learning_rate": 2.6435717650971373e-06, "loss": 0.8201, "step": 122510 }, { "epoch": 10.18, "learning_rate": 2.643460909569603e-06, "loss": 0.894, "step": 122520 }, { "epoch": 10.18, "learning_rate": 2.64335005404207e-06, "loss": 0.7265, "step": 122530 }, { "epoch": 10.19, "learning_rate": 2.6432391985145357e-06, "loss": 0.7643, "step": 122540 }, { "epoch": 10.19, "learning_rate": 2.643128342987002e-06, "loss": 0.7994, "step": 122550 }, { "epoch": 10.19, "learning_rate": 2.6430174874594683e-06, "loss": 0.7211, "step": 122560 }, { "epoch": 10.19, "learning_rate": 2.6429066319319346e-06, "loss": 0.7957, "step": 122570 }, { "epoch": 10.19, "learning_rate": 2.6427957764044005e-06, "loss": 0.7948, "step": 122580 }, { "epoch": 10.19, "learning_rate": 2.642684920876867e-06, "loss": 0.7909, "step": 122590 }, { "epoch": 10.19, "learning_rate": 2.6425740653493335e-06, "loss": 0.7782, "step": 122600 }, { "epoch": 10.19, "learning_rate": 2.6424632098218e-06, "loss": 0.8262, "step": 122610 }, { "epoch": 10.19, "learning_rate": 2.642352354294266e-06, "loss": 0.878, "step": 122620 }, { "epoch": 10.19, "learning_rate": 2.642241498766732e-06, "loss": 0.8055, "step": 122630 }, { "epoch": 10.19, "learning_rate": 2.6421306432391987e-06, "loss": 0.8354, "step": 122640 }, { "epoch": 10.19, "learning_rate": 2.6420197877116645e-06, "loss": 0.8, "step": 122650 }, { "epoch": 10.2, "learning_rate": 2.641908932184131e-06, "loss": 0.8054, "step": 122660 }, { "epoch": 10.2, "learning_rate": 2.641798076656597e-06, "loss": 0.9029, "step": 122670 }, { "epoch": 10.2, "learning_rate": 2.6416872211290634e-06, "loss": 0.77, "step": 122680 }, { "epoch": 10.2, "learning_rate": 2.641587451154283e-06, "loss": 0.8561, "step": 122690 }, { "epoch": 10.2, "learning_rate": 2.6414765956267497e-06, "loss": 0.783, "step": 122700 }, { "epoch": 10.2, "learning_rate": 2.6413657400992156e-06, "loss": 0.8078, "step": 122710 }, { "epoch": 10.2, "learning_rate": 2.641254884571682e-06, "loss": 0.8206, "step": 122720 }, { "epoch": 10.2, "learning_rate": 2.641144029044148e-06, "loss": 0.8215, "step": 122730 }, { "epoch": 10.2, "learning_rate": 2.6410331735166144e-06, "loss": 0.8046, "step": 122740 }, { "epoch": 10.2, "learning_rate": 2.6409223179890803e-06, "loss": 0.7827, "step": 122750 }, { "epoch": 10.2, "learning_rate": 2.640811462461547e-06, "loss": 0.7157, "step": 122760 }, { "epoch": 10.2, "learning_rate": 2.640700606934013e-06, "loss": 0.808, "step": 122770 }, { "epoch": 10.21, "learning_rate": 2.6405897514064796e-06, "loss": 0.7673, "step": 122780 }, { "epoch": 10.21, "learning_rate": 2.6404788958789455e-06, "loss": 0.7918, "step": 122790 }, { "epoch": 10.21, "learning_rate": 2.640368040351412e-06, "loss": 0.7785, "step": 122800 }, { "epoch": 10.21, "learning_rate": 2.6402571848238785e-06, "loss": 0.7808, "step": 122810 }, { "epoch": 10.21, "learning_rate": 2.6401463292963444e-06, "loss": 0.8067, "step": 122820 }, { "epoch": 10.21, "learning_rate": 2.6400354737688107e-06, "loss": 0.8352, "step": 122830 }, { "epoch": 10.21, "learning_rate": 2.639924618241277e-06, "loss": 0.8085, "step": 122840 }, { "epoch": 10.21, "learning_rate": 2.6398137627137433e-06, "loss": 0.8179, "step": 122850 }, { "epoch": 10.21, "learning_rate": 2.6397029071862096e-06, "loss": 0.807, "step": 122860 }, { "epoch": 10.21, "learning_rate": 2.639592051658676e-06, "loss": 0.8298, "step": 122870 }, { "epoch": 10.21, "learning_rate": 2.6394811961311417e-06, "loss": 0.8138, "step": 122880 }, { "epoch": 10.21, "learning_rate": 2.6393703406036085e-06, "loss": 0.741, "step": 122890 }, { "epoch": 10.22, "learning_rate": 2.6392594850760743e-06, "loss": 0.7403, "step": 122900 }, { "epoch": 10.22, "learning_rate": 2.6391486295485406e-06, "loss": 0.8151, "step": 122910 }, { "epoch": 10.22, "learning_rate": 2.639037774021007e-06, "loss": 0.8502, "step": 122920 }, { "epoch": 10.22, "learning_rate": 2.6389269184934732e-06, "loss": 0.7808, "step": 122930 }, { "epoch": 10.22, "learning_rate": 2.63881606296594e-06, "loss": 0.7593, "step": 122940 }, { "epoch": 10.22, "learning_rate": 2.638705207438406e-06, "loss": 0.797, "step": 122950 }, { "epoch": 10.22, "learning_rate": 2.638594351910872e-06, "loss": 0.8651, "step": 122960 }, { "epoch": 10.22, "learning_rate": 2.6384834963833384e-06, "loss": 0.835, "step": 122970 }, { "epoch": 10.22, "learning_rate": 2.6383726408558047e-06, "loss": 0.7928, "step": 122980 }, { "epoch": 10.22, "learning_rate": 2.6382617853282706e-06, "loss": 0.7596, "step": 122990 }, { "epoch": 10.22, "learning_rate": 2.6381509298007373e-06, "loss": 0.805, "step": 123000 }, { "epoch": 10.22, "learning_rate": 2.638040074273203e-06, "loss": 0.7993, "step": 123010 }, { "epoch": 10.23, "learning_rate": 2.6379292187456694e-06, "loss": 0.7592, "step": 123020 }, { "epoch": 10.23, "learning_rate": 2.6378183632181357e-06, "loss": 0.8383, "step": 123030 }, { "epoch": 10.23, "learning_rate": 2.637707507690602e-06, "loss": 0.8326, "step": 123040 }, { "epoch": 10.23, "learning_rate": 2.6375966521630683e-06, "loss": 0.7897, "step": 123050 }, { "epoch": 10.23, "learning_rate": 2.6374857966355346e-06, "loss": 0.8135, "step": 123060 }, { "epoch": 10.23, "learning_rate": 2.637374941108001e-06, "loss": 0.8259, "step": 123070 }, { "epoch": 10.23, "learning_rate": 2.6372640855804672e-06, "loss": 0.7685, "step": 123080 }, { "epoch": 10.23, "learning_rate": 2.6371532300529335e-06, "loss": 0.8088, "step": 123090 }, { "epoch": 10.23, "learning_rate": 2.6370423745253994e-06, "loss": 0.8207, "step": 123100 }, { "epoch": 10.23, "learning_rate": 2.636931518997866e-06, "loss": 0.7714, "step": 123110 }, { "epoch": 10.23, "learning_rate": 2.636820663470332e-06, "loss": 0.8949, "step": 123120 }, { "epoch": 10.23, "learning_rate": 2.6367098079427987e-06, "loss": 0.7536, "step": 123130 }, { "epoch": 10.24, "learning_rate": 2.6365989524152646e-06, "loss": 0.7454, "step": 123140 }, { "epoch": 10.24, "learning_rate": 2.636488096887731e-06, "loss": 0.7889, "step": 123150 }, { "epoch": 10.24, "learning_rate": 2.636377241360197e-06, "loss": 0.7562, "step": 123160 }, { "epoch": 10.24, "learning_rate": 2.6362663858326635e-06, "loss": 0.8317, "step": 123170 }, { "epoch": 10.24, "learning_rate": 2.6361555303051297e-06, "loss": 0.7788, "step": 123180 }, { "epoch": 10.24, "learning_rate": 2.636044674777596e-06, "loss": 0.7468, "step": 123190 }, { "epoch": 10.24, "learning_rate": 2.6359338192500623e-06, "loss": 0.7673, "step": 123200 }, { "epoch": 10.24, "learning_rate": 2.6358229637225286e-06, "loss": 0.7625, "step": 123210 }, { "epoch": 10.24, "learning_rate": 2.635712108194995e-06, "loss": 0.7758, "step": 123220 }, { "epoch": 10.24, "learning_rate": 2.635601252667461e-06, "loss": 0.798, "step": 123230 }, { "epoch": 10.24, "learning_rate": 2.6354903971399275e-06, "loss": 0.7588, "step": 123240 }, { "epoch": 10.24, "learning_rate": 2.6353795416123934e-06, "loss": 0.7819, "step": 123250 }, { "epoch": 10.25, "learning_rate": 2.6352686860848597e-06, "loss": 0.7624, "step": 123260 }, { "epoch": 10.25, "learning_rate": 2.635157830557326e-06, "loss": 0.8193, "step": 123270 }, { "epoch": 10.25, "learning_rate": 2.6350469750297923e-06, "loss": 0.7353, "step": 123280 }, { "epoch": 10.25, "learning_rate": 2.634936119502258e-06, "loss": 0.7198, "step": 123290 }, { "epoch": 10.25, "learning_rate": 2.634825263974725e-06, "loss": 0.8663, "step": 123300 }, { "epoch": 10.25, "learning_rate": 2.634714408447191e-06, "loss": 0.7835, "step": 123310 }, { "epoch": 10.25, "learning_rate": 2.6346035529196575e-06, "loss": 0.8505, "step": 123320 }, { "epoch": 10.25, "learning_rate": 2.6344926973921238e-06, "loss": 0.7615, "step": 123330 }, { "epoch": 10.25, "learning_rate": 2.6343818418645896e-06, "loss": 0.811, "step": 123340 }, { "epoch": 10.25, "learning_rate": 2.6342709863370563e-06, "loss": 0.7307, "step": 123350 }, { "epoch": 10.25, "learning_rate": 2.6341601308095222e-06, "loss": 0.7684, "step": 123360 }, { "epoch": 10.25, "learning_rate": 2.6340492752819885e-06, "loss": 0.8617, "step": 123370 }, { "epoch": 10.26, "learning_rate": 2.633938419754455e-06, "loss": 0.8206, "step": 123380 }, { "epoch": 10.26, "learning_rate": 2.633827564226921e-06, "loss": 0.8685, "step": 123390 }, { "epoch": 10.26, "learning_rate": 2.6337167086993874e-06, "loss": 0.8047, "step": 123400 }, { "epoch": 10.26, "learning_rate": 2.6336058531718537e-06, "loss": 0.7732, "step": 123410 }, { "epoch": 10.26, "learning_rate": 2.6334949976443196e-06, "loss": 0.8022, "step": 123420 }, { "epoch": 10.26, "learning_rate": 2.6333841421167863e-06, "loss": 0.8126, "step": 123430 }, { "epoch": 10.26, "learning_rate": 2.6332732865892526e-06, "loss": 0.8071, "step": 123440 }, { "epoch": 10.26, "learning_rate": 2.6331624310617185e-06, "loss": 0.7273, "step": 123450 }, { "epoch": 10.26, "learning_rate": 2.633051575534185e-06, "loss": 0.8229, "step": 123460 }, { "epoch": 10.26, "learning_rate": 2.632940720006651e-06, "loss": 0.8191, "step": 123470 }, { "epoch": 10.26, "learning_rate": 2.6328298644791178e-06, "loss": 0.7607, "step": 123480 }, { "epoch": 10.26, "learning_rate": 2.6327190089515836e-06, "loss": 0.781, "step": 123490 }, { "epoch": 10.27, "learning_rate": 2.63260815342405e-06, "loss": 0.8176, "step": 123500 }, { "epoch": 10.27, "learning_rate": 2.6324972978965162e-06, "loss": 0.8198, "step": 123510 }, { "epoch": 10.27, "learning_rate": 2.6323864423689825e-06, "loss": 0.8588, "step": 123520 }, { "epoch": 10.27, "learning_rate": 2.6322755868414484e-06, "loss": 0.7452, "step": 123530 }, { "epoch": 10.27, "learning_rate": 2.632164731313915e-06, "loss": 0.7709, "step": 123540 }, { "epoch": 10.27, "learning_rate": 2.6320538757863814e-06, "loss": 0.7993, "step": 123550 }, { "epoch": 10.27, "learning_rate": 2.6319430202588477e-06, "loss": 0.8028, "step": 123560 }, { "epoch": 10.27, "learning_rate": 2.631832164731314e-06, "loss": 0.8103, "step": 123570 }, { "epoch": 10.27, "learning_rate": 2.63172130920378e-06, "loss": 0.7397, "step": 123580 }, { "epoch": 10.27, "learning_rate": 2.6316104536762466e-06, "loss": 0.7406, "step": 123590 }, { "epoch": 10.27, "learning_rate": 2.6314995981487125e-06, "loss": 0.8004, "step": 123600 }, { "epoch": 10.27, "learning_rate": 2.6313887426211788e-06, "loss": 0.7197, "step": 123610 }, { "epoch": 10.28, "learning_rate": 2.631277887093645e-06, "loss": 0.8275, "step": 123620 }, { "epoch": 10.28, "learning_rate": 2.6311670315661113e-06, "loss": 0.7717, "step": 123630 }, { "epoch": 10.28, "learning_rate": 2.6310561760385776e-06, "loss": 0.8504, "step": 123640 }, { "epoch": 10.28, "learning_rate": 2.630945320511044e-06, "loss": 0.7393, "step": 123650 }, { "epoch": 10.28, "learning_rate": 2.63083446498351e-06, "loss": 0.803, "step": 123660 }, { "epoch": 10.28, "learning_rate": 2.6307236094559765e-06, "loss": 0.8917, "step": 123670 }, { "epoch": 10.28, "learning_rate": 2.630612753928443e-06, "loss": 0.7905, "step": 123680 }, { "epoch": 10.28, "learning_rate": 2.6305018984009087e-06, "loss": 0.7883, "step": 123690 }, { "epoch": 10.28, "learning_rate": 2.6303910428733754e-06, "loss": 0.7913, "step": 123700 }, { "epoch": 10.28, "learning_rate": 2.6302801873458413e-06, "loss": 0.7603, "step": 123710 }, { "epoch": 10.28, "learning_rate": 2.630169331818308e-06, "loss": 0.9168, "step": 123720 }, { "epoch": 10.28, "learning_rate": 2.630058476290774e-06, "loss": 0.8016, "step": 123730 }, { "epoch": 10.29, "learning_rate": 2.62994762076324e-06, "loss": 0.7716, "step": 123740 }, { "epoch": 10.29, "learning_rate": 2.6298367652357065e-06, "loss": 0.771, "step": 123750 }, { "epoch": 10.29, "learning_rate": 2.6297259097081728e-06, "loss": 0.7828, "step": 123760 }, { "epoch": 10.29, "learning_rate": 2.6296150541806386e-06, "loss": 0.8552, "step": 123770 }, { "epoch": 10.29, "learning_rate": 2.6295041986531054e-06, "loss": 0.7921, "step": 123780 }, { "epoch": 10.29, "learning_rate": 2.6293933431255712e-06, "loss": 0.7872, "step": 123790 }, { "epoch": 10.29, "learning_rate": 2.6292824875980375e-06, "loss": 0.8196, "step": 123800 }, { "epoch": 10.29, "learning_rate": 2.6291716320705042e-06, "loss": 0.7671, "step": 123810 }, { "epoch": 10.29, "learning_rate": 2.62906077654297e-06, "loss": 0.8653, "step": 123820 }, { "epoch": 10.29, "learning_rate": 2.628949921015437e-06, "loss": 0.8174, "step": 123830 }, { "epoch": 10.29, "learning_rate": 2.6288390654879027e-06, "loss": 0.7521, "step": 123840 }, { "epoch": 10.29, "learning_rate": 2.628728209960369e-06, "loss": 0.8595, "step": 123850 }, { "epoch": 10.3, "learning_rate": 2.6286173544328353e-06, "loss": 0.8009, "step": 123860 }, { "epoch": 10.3, "learning_rate": 2.6285064989053016e-06, "loss": 0.8276, "step": 123870 }, { "epoch": 10.3, "learning_rate": 2.6283956433777675e-06, "loss": 0.7051, "step": 123880 }, { "epoch": 10.3, "learning_rate": 2.628284787850234e-06, "loss": 0.8535, "step": 123890 }, { "epoch": 10.3, "learning_rate": 2.6281739323227e-06, "loss": 0.7743, "step": 123900 }, { "epoch": 10.3, "learning_rate": 2.6280630767951668e-06, "loss": 0.7793, "step": 123910 }, { "epoch": 10.3, "learning_rate": 2.627952221267633e-06, "loss": 0.8344, "step": 123920 }, { "epoch": 10.3, "learning_rate": 2.627841365740099e-06, "loss": 0.757, "step": 123930 }, { "epoch": 10.3, "learning_rate": 2.6277305102125657e-06, "loss": 0.7547, "step": 123940 }, { "epoch": 10.3, "learning_rate": 2.6276196546850315e-06, "loss": 0.7484, "step": 123950 }, { "epoch": 10.3, "learning_rate": 2.627508799157498e-06, "loss": 0.7067, "step": 123960 }, { "epoch": 10.3, "learning_rate": 2.627397943629964e-06, "loss": 0.8045, "step": 123970 }, { "epoch": 10.31, "learning_rate": 2.6272870881024304e-06, "loss": 0.7993, "step": 123980 }, { "epoch": 10.31, "learning_rate": 2.6271762325748967e-06, "loss": 0.8575, "step": 123990 }, { "epoch": 10.31, "learning_rate": 2.627065377047363e-06, "loss": 0.804, "step": 124000 }, { "epoch": 10.31, "learning_rate": 2.626954521519829e-06, "loss": 0.8618, "step": 124010 }, { "epoch": 10.31, "learning_rate": 2.6268436659922956e-06, "loss": 0.8261, "step": 124020 }, { "epoch": 10.31, "learning_rate": 2.6267328104647615e-06, "loss": 0.7953, "step": 124030 }, { "epoch": 10.31, "learning_rate": 2.6266219549372278e-06, "loss": 0.8132, "step": 124040 }, { "epoch": 10.31, "learning_rate": 2.6265110994096945e-06, "loss": 0.7834, "step": 124050 }, { "epoch": 10.31, "learning_rate": 2.6264002438821604e-06, "loss": 0.7755, "step": 124060 }, { "epoch": 10.31, "learning_rate": 2.626289388354627e-06, "loss": 0.8162, "step": 124070 }, { "epoch": 10.31, "learning_rate": 2.626178532827093e-06, "loss": 0.8703, "step": 124080 }, { "epoch": 10.31, "learning_rate": 2.6260676772995592e-06, "loss": 0.7558, "step": 124090 }, { "epoch": 10.32, "learning_rate": 2.6259568217720255e-06, "loss": 0.7974, "step": 124100 }, { "epoch": 10.32, "learning_rate": 2.625845966244492e-06, "loss": 0.773, "step": 124110 }, { "epoch": 10.32, "learning_rate": 2.6257351107169577e-06, "loss": 0.805, "step": 124120 }, { "epoch": 10.32, "learning_rate": 2.6256242551894244e-06, "loss": 0.7523, "step": 124130 }, { "epoch": 10.32, "learning_rate": 2.6255133996618903e-06, "loss": 0.8099, "step": 124140 }, { "epoch": 10.32, "learning_rate": 2.625402544134357e-06, "loss": 0.7459, "step": 124150 }, { "epoch": 10.32, "learning_rate": 2.625291688606823e-06, "loss": 0.7045, "step": 124160 }, { "epoch": 10.32, "learning_rate": 2.625191918632043e-06, "loss": 0.9251, "step": 124170 }, { "epoch": 10.32, "learning_rate": 2.6250810631045087e-06, "loss": 0.7334, "step": 124180 }, { "epoch": 10.32, "learning_rate": 2.6249702075769754e-06, "loss": 0.7708, "step": 124190 }, { "epoch": 10.32, "learning_rate": 2.6248593520494413e-06, "loss": 0.7644, "step": 124200 }, { "epoch": 10.32, "learning_rate": 2.6247484965219076e-06, "loss": 0.8311, "step": 124210 }, { "epoch": 10.32, "learning_rate": 2.624637640994374e-06, "loss": 0.8495, "step": 124220 }, { "epoch": 10.33, "learning_rate": 2.62452678546684e-06, "loss": 0.7939, "step": 124230 }, { "epoch": 10.33, "learning_rate": 2.624415929939306e-06, "loss": 0.7843, "step": 124240 }, { "epoch": 10.33, "learning_rate": 2.6243050744117728e-06, "loss": 0.769, "step": 124250 }, { "epoch": 10.33, "learning_rate": 2.624194218884239e-06, "loss": 0.8201, "step": 124260 }, { "epoch": 10.33, "learning_rate": 2.6240833633567054e-06, "loss": 0.8689, "step": 124270 }, { "epoch": 10.33, "learning_rate": 2.6239725078291717e-06, "loss": 0.8954, "step": 124280 }, { "epoch": 10.33, "learning_rate": 2.6238616523016375e-06, "loss": 0.7836, "step": 124290 }, { "epoch": 10.33, "learning_rate": 2.6237507967741043e-06, "loss": 0.776, "step": 124300 }, { "epoch": 10.33, "learning_rate": 2.62363994124657e-06, "loss": 0.8527, "step": 124310 }, { "epoch": 10.33, "learning_rate": 2.623529085719037e-06, "loss": 0.7866, "step": 124320 }, { "epoch": 10.33, "learning_rate": 2.6234182301915027e-06, "loss": 0.8224, "step": 124330 }, { "epoch": 10.33, "learning_rate": 2.623307374663969e-06, "loss": 0.836, "step": 124340 }, { "epoch": 10.34, "learning_rate": 2.6231965191364353e-06, "loss": 0.7802, "step": 124350 }, { "epoch": 10.34, "learning_rate": 2.6230856636089016e-06, "loss": 0.794, "step": 124360 }, { "epoch": 10.34, "learning_rate": 2.6229748080813675e-06, "loss": 0.7553, "step": 124370 }, { "epoch": 10.34, "learning_rate": 2.622863952553834e-06, "loss": 0.8283, "step": 124380 }, { "epoch": 10.34, "learning_rate": 2.6227530970263005e-06, "loss": 0.7796, "step": 124390 }, { "epoch": 10.34, "learning_rate": 2.6226422414987664e-06, "loss": 0.8559, "step": 124400 }, { "epoch": 10.34, "learning_rate": 2.622531385971233e-06, "loss": 0.7613, "step": 124410 }, { "epoch": 10.34, "learning_rate": 2.622420530443699e-06, "loss": 0.8695, "step": 124420 }, { "epoch": 10.34, "learning_rate": 2.6223096749161657e-06, "loss": 0.8495, "step": 124430 }, { "epoch": 10.34, "learning_rate": 2.6221988193886315e-06, "loss": 0.8223, "step": 124440 }, { "epoch": 10.34, "learning_rate": 2.622087963861098e-06, "loss": 0.8257, "step": 124450 }, { "epoch": 10.34, "learning_rate": 2.621977108333564e-06, "loss": 0.7606, "step": 124460 }, { "epoch": 10.35, "learning_rate": 2.6218662528060304e-06, "loss": 0.8977, "step": 124470 }, { "epoch": 10.35, "learning_rate": 2.6217553972784963e-06, "loss": 0.7731, "step": 124480 }, { "epoch": 10.35, "learning_rate": 2.621644541750963e-06, "loss": 0.8223, "step": 124490 }, { "epoch": 10.35, "learning_rate": 2.6215336862234293e-06, "loss": 0.7217, "step": 124500 }, { "epoch": 10.35, "learning_rate": 2.6214228306958956e-06, "loss": 0.8058, "step": 124510 }, { "epoch": 10.35, "learning_rate": 2.621311975168362e-06, "loss": 0.9215, "step": 124520 }, { "epoch": 10.35, "learning_rate": 2.6212011196408278e-06, "loss": 0.7725, "step": 124530 }, { "epoch": 10.35, "learning_rate": 2.6210902641132945e-06, "loss": 0.7667, "step": 124540 }, { "epoch": 10.35, "learning_rate": 2.6209794085857604e-06, "loss": 0.7569, "step": 124550 }, { "epoch": 10.35, "learning_rate": 2.6208685530582267e-06, "loss": 0.7388, "step": 124560 }, { "epoch": 10.35, "learning_rate": 2.620757697530693e-06, "loss": 0.8064, "step": 124570 }, { "epoch": 10.35, "learning_rate": 2.6206468420031593e-06, "loss": 0.8737, "step": 124580 }, { "epoch": 10.36, "learning_rate": 2.6205359864756256e-06, "loss": 0.775, "step": 124590 }, { "epoch": 10.36, "learning_rate": 2.620425130948092e-06, "loss": 0.7848, "step": 124600 }, { "epoch": 10.36, "learning_rate": 2.6203142754205577e-06, "loss": 0.8225, "step": 124610 }, { "epoch": 10.36, "learning_rate": 2.6202034198930244e-06, "loss": 0.8359, "step": 124620 }, { "epoch": 10.36, "learning_rate": 2.6200925643654907e-06, "loss": 0.8134, "step": 124630 }, { "epoch": 10.36, "learning_rate": 2.6199817088379566e-06, "loss": 0.7719, "step": 124640 }, { "epoch": 10.36, "learning_rate": 2.6198708533104233e-06, "loss": 0.826, "step": 124650 }, { "epoch": 10.36, "learning_rate": 2.619759997782889e-06, "loss": 0.7628, "step": 124660 }, { "epoch": 10.36, "learning_rate": 2.619649142255356e-06, "loss": 0.8554, "step": 124670 }, { "epoch": 10.36, "learning_rate": 2.6195382867278218e-06, "loss": 0.7311, "step": 124680 }, { "epoch": 10.36, "learning_rate": 2.619427431200288e-06, "loss": 0.7545, "step": 124690 }, { "epoch": 10.36, "learning_rate": 2.6193165756727544e-06, "loss": 0.7439, "step": 124700 }, { "epoch": 10.37, "learning_rate": 2.6192057201452207e-06, "loss": 0.7478, "step": 124710 }, { "epoch": 10.37, "learning_rate": 2.6190948646176865e-06, "loss": 0.8265, "step": 124720 }, { "epoch": 10.37, "learning_rate": 2.6189840090901533e-06, "loss": 0.8319, "step": 124730 }, { "epoch": 10.37, "learning_rate": 2.6188731535626196e-06, "loss": 0.7296, "step": 124740 }, { "epoch": 10.37, "learning_rate": 2.6187622980350854e-06, "loss": 0.8354, "step": 124750 }, { "epoch": 10.37, "learning_rate": 2.618651442507552e-06, "loss": 0.7823, "step": 124760 }, { "epoch": 10.37, "learning_rate": 2.618540586980018e-06, "loss": 0.8765, "step": 124770 }, { "epoch": 10.37, "learning_rate": 2.6184297314524847e-06, "loss": 0.7949, "step": 124780 }, { "epoch": 10.37, "learning_rate": 2.6183188759249506e-06, "loss": 0.804, "step": 124790 }, { "epoch": 10.37, "learning_rate": 2.618208020397417e-06, "loss": 0.831, "step": 124800 }, { "epoch": 10.37, "learning_rate": 2.618097164869883e-06, "loss": 0.7788, "step": 124810 }, { "epoch": 10.37, "learning_rate": 2.6179863093423495e-06, "loss": 0.8527, "step": 124820 }, { "epoch": 10.38, "learning_rate": 2.6178754538148154e-06, "loss": 0.7734, "step": 124830 }, { "epoch": 10.38, "learning_rate": 2.617764598287282e-06, "loss": 0.8122, "step": 124840 }, { "epoch": 10.38, "learning_rate": 2.617653742759748e-06, "loss": 0.7214, "step": 124850 }, { "epoch": 10.38, "learning_rate": 2.6175428872322147e-06, "loss": 0.8091, "step": 124860 }, { "epoch": 10.38, "learning_rate": 2.617432031704681e-06, "loss": 0.7992, "step": 124870 }, { "epoch": 10.38, "learning_rate": 2.617321176177147e-06, "loss": 0.8072, "step": 124880 }, { "epoch": 10.38, "learning_rate": 2.6172103206496136e-06, "loss": 0.8268, "step": 124890 }, { "epoch": 10.38, "learning_rate": 2.6170994651220794e-06, "loss": 0.8147, "step": 124900 }, { "epoch": 10.38, "learning_rate": 2.6169886095945457e-06, "loss": 0.7903, "step": 124910 }, { "epoch": 10.38, "learning_rate": 2.616877754067012e-06, "loss": 0.863, "step": 124920 }, { "epoch": 10.38, "learning_rate": 2.6167668985394783e-06, "loss": 0.7506, "step": 124930 }, { "epoch": 10.38, "learning_rate": 2.6166560430119446e-06, "loss": 0.7982, "step": 124940 }, { "epoch": 10.39, "learning_rate": 2.616545187484411e-06, "loss": 0.7519, "step": 124950 }, { "epoch": 10.39, "learning_rate": 2.6164343319568768e-06, "loss": 0.7577, "step": 124960 }, { "epoch": 10.39, "learning_rate": 2.6163234764293435e-06, "loss": 0.8227, "step": 124970 }, { "epoch": 10.39, "learning_rate": 2.6162126209018094e-06, "loss": 0.7745, "step": 124980 }, { "epoch": 10.39, "learning_rate": 2.6161017653742757e-06, "loss": 0.7975, "step": 124990 }, { "epoch": 10.39, "learning_rate": 2.6159909098467424e-06, "loss": 0.8169, "step": 125000 }, { "epoch": 10.39, "learning_rate": 2.6158800543192083e-06, "loss": 0.8139, "step": 125010 }, { "epoch": 10.39, "learning_rate": 2.615769198791675e-06, "loss": 0.8388, "step": 125020 }, { "epoch": 10.39, "learning_rate": 2.615658343264141e-06, "loss": 0.7659, "step": 125030 }, { "epoch": 10.39, "learning_rate": 2.615547487736607e-06, "loss": 0.8785, "step": 125040 }, { "epoch": 10.39, "learning_rate": 2.6154366322090734e-06, "loss": 0.7511, "step": 125050 }, { "epoch": 10.39, "learning_rate": 2.6153257766815397e-06, "loss": 0.7284, "step": 125060 }, { "epoch": 10.4, "learning_rate": 2.6152149211540056e-06, "loss": 0.9113, "step": 125070 }, { "epoch": 10.4, "learning_rate": 2.6151040656264723e-06, "loss": 0.813, "step": 125080 }, { "epoch": 10.4, "learning_rate": 2.614993210098938e-06, "loss": 0.7928, "step": 125090 }, { "epoch": 10.4, "learning_rate": 2.614882354571405e-06, "loss": 0.7745, "step": 125100 }, { "epoch": 10.4, "learning_rate": 2.6147714990438712e-06, "loss": 0.8223, "step": 125110 }, { "epoch": 10.4, "learning_rate": 2.614660643516337e-06, "loss": 0.7908, "step": 125120 }, { "epoch": 10.4, "learning_rate": 2.614549787988804e-06, "loss": 0.8182, "step": 125130 }, { "epoch": 10.4, "learning_rate": 2.6144389324612697e-06, "loss": 0.8122, "step": 125140 }, { "epoch": 10.4, "learning_rate": 2.614328076933736e-06, "loss": 0.7668, "step": 125150 }, { "epoch": 10.4, "learning_rate": 2.6142172214062023e-06, "loss": 0.8096, "step": 125160 }, { "epoch": 10.4, "learning_rate": 2.6141063658786686e-06, "loss": 0.8361, "step": 125170 }, { "epoch": 10.4, "learning_rate": 2.6139955103511344e-06, "loss": 0.8415, "step": 125180 }, { "epoch": 10.41, "learning_rate": 2.613884654823601e-06, "loss": 0.7892, "step": 125190 }, { "epoch": 10.41, "learning_rate": 2.613773799296067e-06, "loss": 0.8037, "step": 125200 }, { "epoch": 10.41, "learning_rate": 2.6136629437685337e-06, "loss": 0.7831, "step": 125210 }, { "epoch": 10.41, "learning_rate": 2.6135520882409996e-06, "loss": 0.8559, "step": 125220 }, { "epoch": 10.41, "learning_rate": 2.613441232713466e-06, "loss": 0.8293, "step": 125230 }, { "epoch": 10.41, "learning_rate": 2.6133303771859326e-06, "loss": 0.8057, "step": 125240 }, { "epoch": 10.41, "learning_rate": 2.6132195216583985e-06, "loss": 0.7682, "step": 125250 }, { "epoch": 10.41, "learning_rate": 2.613108666130865e-06, "loss": 0.7518, "step": 125260 }, { "epoch": 10.41, "learning_rate": 2.612997810603331e-06, "loss": 0.7898, "step": 125270 }, { "epoch": 10.41, "learning_rate": 2.6128869550757974e-06, "loss": 0.7624, "step": 125280 }, { "epoch": 10.41, "learning_rate": 2.6127760995482637e-06, "loss": 0.7751, "step": 125290 }, { "epoch": 10.41, "learning_rate": 2.61266524402073e-06, "loss": 0.7621, "step": 125300 }, { "epoch": 10.42, "learning_rate": 2.612554388493196e-06, "loss": 0.8319, "step": 125310 }, { "epoch": 10.42, "learning_rate": 2.6124435329656626e-06, "loss": 0.856, "step": 125320 }, { "epoch": 10.42, "learning_rate": 2.6123326774381284e-06, "loss": 0.7652, "step": 125330 }, { "epoch": 10.42, "learning_rate": 2.6122218219105947e-06, "loss": 0.8129, "step": 125340 }, { "epoch": 10.42, "learning_rate": 2.612110966383061e-06, "loss": 0.781, "step": 125350 }, { "epoch": 10.42, "learning_rate": 2.6120001108555273e-06, "loss": 0.8271, "step": 125360 }, { "epoch": 10.42, "learning_rate": 2.611889255327994e-06, "loss": 0.8737, "step": 125370 }, { "epoch": 10.42, "learning_rate": 2.61177839980046e-06, "loss": 0.7554, "step": 125380 }, { "epoch": 10.42, "learning_rate": 2.6116675442729262e-06, "loss": 0.7968, "step": 125390 }, { "epoch": 10.42, "learning_rate": 2.6115566887453925e-06, "loss": 0.7809, "step": 125400 }, { "epoch": 10.42, "learning_rate": 2.611445833217859e-06, "loss": 0.7266, "step": 125410 }, { "epoch": 10.42, "learning_rate": 2.6113349776903247e-06, "loss": 0.7992, "step": 125420 }, { "epoch": 10.43, "learning_rate": 2.6112241221627914e-06, "loss": 0.7366, "step": 125430 }, { "epoch": 10.43, "learning_rate": 2.6111132666352573e-06, "loss": 0.7601, "step": 125440 }, { "epoch": 10.43, "learning_rate": 2.611002411107724e-06, "loss": 0.8389, "step": 125450 }, { "epoch": 10.43, "learning_rate": 2.61089155558019e-06, "loss": 0.792, "step": 125460 }, { "epoch": 10.43, "learning_rate": 2.610780700052656e-06, "loss": 0.8164, "step": 125470 }, { "epoch": 10.43, "learning_rate": 2.610669844525123e-06, "loss": 0.8182, "step": 125480 }, { "epoch": 10.43, "learning_rate": 2.6105589889975887e-06, "loss": 0.8252, "step": 125490 }, { "epoch": 10.43, "learning_rate": 2.610448133470055e-06, "loss": 0.7577, "step": 125500 }, { "epoch": 10.43, "learning_rate": 2.6103372779425213e-06, "loss": 0.8182, "step": 125510 }, { "epoch": 10.43, "learning_rate": 2.6102264224149876e-06, "loss": 0.8428, "step": 125520 }, { "epoch": 10.43, "learning_rate": 2.6101155668874535e-06, "loss": 0.7874, "step": 125530 }, { "epoch": 10.43, "learning_rate": 2.6100047113599202e-06, "loss": 0.7631, "step": 125540 }, { "epoch": 10.44, "learning_rate": 2.609893855832386e-06, "loss": 0.8422, "step": 125550 }, { "epoch": 10.44, "learning_rate": 2.609783000304853e-06, "loss": 0.8152, "step": 125560 }, { "epoch": 10.44, "learning_rate": 2.6096721447773187e-06, "loss": 0.8139, "step": 125570 }, { "epoch": 10.44, "learning_rate": 2.609561289249785e-06, "loss": 0.7983, "step": 125580 }, { "epoch": 10.44, "learning_rate": 2.6094504337222513e-06, "loss": 0.8244, "step": 125590 }, { "epoch": 10.44, "learning_rate": 2.6093395781947176e-06, "loss": 0.7859, "step": 125600 }, { "epoch": 10.44, "learning_rate": 2.6092287226671843e-06, "loss": 0.7625, "step": 125610 }, { "epoch": 10.44, "learning_rate": 2.60911786713965e-06, "loss": 0.8624, "step": 125620 }, { "epoch": 10.44, "learning_rate": 2.6090070116121165e-06, "loss": 0.7668, "step": 125630 }, { "epoch": 10.44, "learning_rate": 2.6088961560845828e-06, "loss": 0.7627, "step": 125640 }, { "epoch": 10.44, "learning_rate": 2.608785300557049e-06, "loss": 0.7892, "step": 125650 }, { "epoch": 10.44, "learning_rate": 2.608674445029515e-06, "loss": 0.8648, "step": 125660 }, { "epoch": 10.45, "learning_rate": 2.6085635895019816e-06, "loss": 0.8333, "step": 125670 }, { "epoch": 10.45, "learning_rate": 2.6084527339744475e-06, "loss": 0.7112, "step": 125680 }, { "epoch": 10.45, "learning_rate": 2.608341878446914e-06, "loss": 0.8391, "step": 125690 }, { "epoch": 10.45, "learning_rate": 2.60823102291938e-06, "loss": 0.7972, "step": 125700 }, { "epoch": 10.45, "learning_rate": 2.6081201673918464e-06, "loss": 0.7327, "step": 125710 }, { "epoch": 10.45, "learning_rate": 2.6080093118643127e-06, "loss": 0.8094, "step": 125720 }, { "epoch": 10.45, "learning_rate": 2.607898456336779e-06, "loss": 0.7339, "step": 125730 }, { "epoch": 10.45, "learning_rate": 2.6077876008092453e-06, "loss": 0.7865, "step": 125740 }, { "epoch": 10.45, "learning_rate": 2.6076767452817116e-06, "loss": 0.7537, "step": 125750 }, { "epoch": 10.45, "learning_rate": 2.607565889754178e-06, "loss": 0.7734, "step": 125760 }, { "epoch": 10.45, "learning_rate": 2.6074550342266437e-06, "loss": 0.8013, "step": 125770 }, { "epoch": 10.45, "learning_rate": 2.6073441786991105e-06, "loss": 0.8063, "step": 125780 }, { "epoch": 10.46, "learning_rate": 2.6072333231715763e-06, "loss": 0.8259, "step": 125790 }, { "epoch": 10.46, "learning_rate": 2.607122467644043e-06, "loss": 0.7853, "step": 125800 }, { "epoch": 10.46, "learning_rate": 2.607011612116509e-06, "loss": 0.7891, "step": 125810 }, { "epoch": 10.46, "learning_rate": 2.6069007565889752e-06, "loss": 0.8147, "step": 125820 }, { "epoch": 10.46, "learning_rate": 2.6067899010614415e-06, "loss": 0.8183, "step": 125830 }, { "epoch": 10.46, "learning_rate": 2.606679045533908e-06, "loss": 0.8321, "step": 125840 }, { "epoch": 10.46, "learning_rate": 2.606568190006374e-06, "loss": 0.7868, "step": 125850 }, { "epoch": 10.46, "learning_rate": 2.6064573344788404e-06, "loss": 0.7768, "step": 125860 }, { "epoch": 10.46, "learning_rate": 2.6063464789513067e-06, "loss": 0.8244, "step": 125870 }, { "epoch": 10.46, "learning_rate": 2.606235623423773e-06, "loss": 0.7461, "step": 125880 }, { "epoch": 10.46, "learning_rate": 2.6061247678962393e-06, "loss": 0.8362, "step": 125890 }, { "epoch": 10.46, "learning_rate": 2.606013912368705e-06, "loss": 0.7767, "step": 125900 }, { "epoch": 10.47, "learning_rate": 2.605903056841172e-06, "loss": 0.7659, "step": 125910 }, { "epoch": 10.47, "learning_rate": 2.6057922013136378e-06, "loss": 1.0605, "step": 125920 }, { "epoch": 10.47, "learning_rate": 2.605681345786104e-06, "loss": 0.6912, "step": 125930 }, { "epoch": 10.47, "learning_rate": 2.6055704902585703e-06, "loss": 0.7909, "step": 125940 }, { "epoch": 10.47, "learning_rate": 2.6054596347310366e-06, "loss": 0.7829, "step": 125950 }, { "epoch": 10.47, "learning_rate": 2.6053487792035025e-06, "loss": 0.7211, "step": 125960 }, { "epoch": 10.47, "learning_rate": 2.6052379236759692e-06, "loss": 0.9083, "step": 125970 }, { "epoch": 10.47, "learning_rate": 2.6051270681484355e-06, "loss": 0.7628, "step": 125980 }, { "epoch": 10.47, "learning_rate": 2.605016212620902e-06, "loss": 0.7738, "step": 125990 }, { "epoch": 10.47, "learning_rate": 2.604905357093368e-06, "loss": 0.7736, "step": 126000 }, { "epoch": 10.47, "learning_rate": 2.604794501565834e-06, "loss": 0.7139, "step": 126010 }, { "epoch": 10.47, "learning_rate": 2.6046836460383007e-06, "loss": 0.8319, "step": 126020 }, { "epoch": 10.48, "learning_rate": 2.6045727905107666e-06, "loss": 0.7894, "step": 126030 }, { "epoch": 10.48, "learning_rate": 2.604461934983233e-06, "loss": 0.7799, "step": 126040 }, { "epoch": 10.48, "learning_rate": 2.604351079455699e-06, "loss": 0.7355, "step": 126050 }, { "epoch": 10.48, "learning_rate": 2.6042402239281655e-06, "loss": 0.8111, "step": 126060 }, { "epoch": 10.48, "learning_rate": 2.6041293684006318e-06, "loss": 0.7756, "step": 126070 }, { "epoch": 10.48, "learning_rate": 2.604018512873098e-06, "loss": 0.7812, "step": 126080 }, { "epoch": 10.48, "learning_rate": 2.603907657345564e-06, "loss": 0.8378, "step": 126090 }, { "epoch": 10.48, "learning_rate": 2.6037968018180306e-06, "loss": 0.8191, "step": 126100 }, { "epoch": 10.48, "learning_rate": 2.603685946290497e-06, "loss": 0.8147, "step": 126110 }, { "epoch": 10.48, "learning_rate": 2.603575090762963e-06, "loss": 0.871, "step": 126120 }, { "epoch": 10.48, "learning_rate": 2.6034642352354295e-06, "loss": 0.7883, "step": 126130 }, { "epoch": 10.48, "learning_rate": 2.6033533797078954e-06, "loss": 0.7995, "step": 126140 }, { "epoch": 10.49, "learning_rate": 2.603242524180362e-06, "loss": 0.7528, "step": 126150 }, { "epoch": 10.49, "learning_rate": 2.603131668652828e-06, "loss": 0.7829, "step": 126160 }, { "epoch": 10.49, "learning_rate": 2.6030208131252943e-06, "loss": 0.846, "step": 126170 }, { "epoch": 10.49, "learning_rate": 2.6029099575977606e-06, "loss": 0.8178, "step": 126180 }, { "epoch": 10.49, "learning_rate": 2.602799102070227e-06, "loss": 0.769, "step": 126190 }, { "epoch": 10.49, "learning_rate": 2.6026882465426927e-06, "loss": 0.8038, "step": 126200 }, { "epoch": 10.49, "learning_rate": 2.6025773910151595e-06, "loss": 0.8165, "step": 126210 }, { "epoch": 10.49, "learning_rate": 2.6024665354876258e-06, "loss": 0.8262, "step": 126220 }, { "epoch": 10.49, "learning_rate": 2.602355679960092e-06, "loss": 0.9226, "step": 126230 }, { "epoch": 10.49, "learning_rate": 2.6022448244325584e-06, "loss": 0.7821, "step": 126240 }, { "epoch": 10.49, "learning_rate": 2.6021339689050242e-06, "loss": 0.7929, "step": 126250 }, { "epoch": 10.49, "learning_rate": 2.602023113377491e-06, "loss": 0.7932, "step": 126260 }, { "epoch": 10.5, "learning_rate": 2.601912257849957e-06, "loss": 0.8055, "step": 126270 }, { "epoch": 10.5, "learning_rate": 2.601801402322423e-06, "loss": 0.8127, "step": 126280 }, { "epoch": 10.5, "learning_rate": 2.6016905467948894e-06, "loss": 0.7328, "step": 126290 }, { "epoch": 10.5, "learning_rate": 2.6015796912673557e-06, "loss": 0.7378, "step": 126300 }, { "epoch": 10.5, "learning_rate": 2.601468835739822e-06, "loss": 0.802, "step": 126310 }, { "epoch": 10.5, "learning_rate": 2.6013579802122883e-06, "loss": 0.8068, "step": 126320 }, { "epoch": 10.5, "learning_rate": 2.601247124684754e-06, "loss": 0.8066, "step": 126330 }, { "epoch": 10.5, "learning_rate": 2.601136269157221e-06, "loss": 0.7659, "step": 126340 }, { "epoch": 10.5, "learning_rate": 2.601025413629687e-06, "loss": 0.7946, "step": 126350 }, { "epoch": 10.5, "learning_rate": 2.600914558102153e-06, "loss": 0.7989, "step": 126360 }, { "epoch": 10.5, "learning_rate": 2.6008037025746198e-06, "loss": 0.8671, "step": 126370 }, { "epoch": 10.5, "learning_rate": 2.6006928470470856e-06, "loss": 0.8166, "step": 126380 }, { "epoch": 10.51, "learning_rate": 2.6005819915195524e-06, "loss": 0.7172, "step": 126390 }, { "epoch": 10.51, "learning_rate": 2.6004711359920182e-06, "loss": 0.7396, "step": 126400 }, { "epoch": 10.51, "learning_rate": 2.6003602804644845e-06, "loss": 0.8215, "step": 126410 }, { "epoch": 10.51, "learning_rate": 2.600249424936951e-06, "loss": 0.8815, "step": 126420 }, { "epoch": 10.51, "learning_rate": 2.600138569409417e-06, "loss": 0.7828, "step": 126430 }, { "epoch": 10.51, "learning_rate": 2.600027713881883e-06, "loss": 0.8154, "step": 126440 }, { "epoch": 10.51, "learning_rate": 2.5999168583543497e-06, "loss": 0.7189, "step": 126450 }, { "epoch": 10.51, "learning_rate": 2.5998060028268156e-06, "loss": 0.8064, "step": 126460 }, { "epoch": 10.51, "learning_rate": 2.599695147299282e-06, "loss": 0.8811, "step": 126470 }, { "epoch": 10.51, "learning_rate": 2.5995842917717486e-06, "loss": 0.7837, "step": 126480 }, { "epoch": 10.51, "learning_rate": 2.5994734362442145e-06, "loss": 0.8316, "step": 126490 }, { "epoch": 10.51, "learning_rate": 2.599362580716681e-06, "loss": 0.7757, "step": 126500 }, { "epoch": 10.52, "learning_rate": 2.599251725189147e-06, "loss": 0.7816, "step": 126510 }, { "epoch": 10.52, "learning_rate": 2.5991408696616134e-06, "loss": 0.8969, "step": 126520 }, { "epoch": 10.52, "learning_rate": 2.5990300141340796e-06, "loss": 0.8381, "step": 126530 }, { "epoch": 10.52, "learning_rate": 2.598919158606546e-06, "loss": 0.7517, "step": 126540 }, { "epoch": 10.52, "learning_rate": 2.598808303079012e-06, "loss": 0.8839, "step": 126550 }, { "epoch": 10.52, "learning_rate": 2.5986974475514785e-06, "loss": 0.8031, "step": 126560 }, { "epoch": 10.52, "learning_rate": 2.5985865920239444e-06, "loss": 0.8135, "step": 126570 }, { "epoch": 10.52, "learning_rate": 2.598475736496411e-06, "loss": 0.8055, "step": 126580 }, { "epoch": 10.52, "learning_rate": 2.5983648809688774e-06, "loss": 0.8097, "step": 126590 }, { "epoch": 10.52, "learning_rate": 2.5982540254413433e-06, "loss": 0.8149, "step": 126600 }, { "epoch": 10.52, "learning_rate": 2.59814316991381e-06, "loss": 0.8198, "step": 126610 }, { "epoch": 10.52, "learning_rate": 2.598032314386276e-06, "loss": 0.832, "step": 126620 }, { "epoch": 10.53, "learning_rate": 2.597921458858742e-06, "loss": 0.7742, "step": 126630 }, { "epoch": 10.53, "learning_rate": 2.5978106033312085e-06, "loss": 0.776, "step": 126640 }, { "epoch": 10.53, "learning_rate": 2.5976997478036748e-06, "loss": 0.7795, "step": 126650 }, { "epoch": 10.53, "learning_rate": 2.597588892276141e-06, "loss": 0.8365, "step": 126660 }, { "epoch": 10.53, "learning_rate": 2.5974780367486074e-06, "loss": 0.9185, "step": 126670 }, { "epoch": 10.53, "learning_rate": 2.5973671812210732e-06, "loss": 0.7417, "step": 126680 }, { "epoch": 10.53, "learning_rate": 2.59725632569354e-06, "loss": 0.7114, "step": 126690 }, { "epoch": 10.53, "learning_rate": 2.597145470166006e-06, "loss": 0.8056, "step": 126700 }, { "epoch": 10.53, "learning_rate": 2.597034614638472e-06, "loss": 0.798, "step": 126710 }, { "epoch": 10.53, "learning_rate": 2.596923759110939e-06, "loss": 0.8764, "step": 126720 }, { "epoch": 10.53, "learning_rate": 2.5968129035834047e-06, "loss": 0.8062, "step": 126730 }, { "epoch": 10.53, "learning_rate": 2.5967020480558714e-06, "loss": 0.8174, "step": 126740 }, { "epoch": 10.54, "learning_rate": 2.5965911925283373e-06, "loss": 0.7313, "step": 126750 }, { "epoch": 10.54, "learning_rate": 2.5964803370008036e-06, "loss": 0.7677, "step": 126760 }, { "epoch": 10.54, "learning_rate": 2.59636948147327e-06, "loss": 0.8586, "step": 126770 }, { "epoch": 10.54, "learning_rate": 2.596258625945736e-06, "loss": 0.7876, "step": 126780 }, { "epoch": 10.54, "learning_rate": 2.596147770418202e-06, "loss": 0.7914, "step": 126790 }, { "epoch": 10.54, "learning_rate": 2.5960369148906688e-06, "loss": 0.8193, "step": 126800 }, { "epoch": 10.54, "learning_rate": 2.5959260593631346e-06, "loss": 0.8156, "step": 126810 }, { "epoch": 10.54, "learning_rate": 2.595815203835601e-06, "loss": 0.8476, "step": 126820 }, { "epoch": 10.54, "learning_rate": 2.5957043483080677e-06, "loss": 0.7652, "step": 126830 }, { "epoch": 10.54, "learning_rate": 2.5955934927805335e-06, "loss": 0.723, "step": 126840 }, { "epoch": 10.54, "learning_rate": 2.5954826372530003e-06, "loss": 0.7241, "step": 126850 }, { "epoch": 10.54, "learning_rate": 2.595371781725466e-06, "loss": 0.7721, "step": 126860 }, { "epoch": 10.55, "learning_rate": 2.5952609261979324e-06, "loss": 0.8606, "step": 126870 }, { "epoch": 10.55, "learning_rate": 2.5951500706703987e-06, "loss": 0.7675, "step": 126880 }, { "epoch": 10.55, "learning_rate": 2.595039215142865e-06, "loss": 0.7518, "step": 126890 }, { "epoch": 10.55, "learning_rate": 2.594928359615331e-06, "loss": 0.7846, "step": 126900 }, { "epoch": 10.55, "learning_rate": 2.5948175040877976e-06, "loss": 0.7862, "step": 126910 }, { "epoch": 10.55, "learning_rate": 2.5947066485602635e-06, "loss": 0.8583, "step": 126920 }, { "epoch": 10.55, "learning_rate": 2.59459579303273e-06, "loss": 0.7547, "step": 126930 }, { "epoch": 10.55, "learning_rate": 2.594484937505196e-06, "loss": 0.8707, "step": 126940 }, { "epoch": 10.55, "learning_rate": 2.5943740819776624e-06, "loss": 0.7847, "step": 126950 }, { "epoch": 10.55, "learning_rate": 2.594263226450129e-06, "loss": 0.7802, "step": 126960 }, { "epoch": 10.55, "learning_rate": 2.594152370922595e-06, "loss": 0.7818, "step": 126970 }, { "epoch": 10.55, "learning_rate": 2.5940415153950612e-06, "loss": 0.7975, "step": 126980 }, { "epoch": 10.56, "learning_rate": 2.5939306598675275e-06, "loss": 0.7371, "step": 126990 }, { "epoch": 10.56, "learning_rate": 2.593819804339994e-06, "loss": 0.7516, "step": 127000 }, { "epoch": 10.56, "learning_rate": 2.59370894881246e-06, "loss": 0.8031, "step": 127010 }, { "epoch": 10.56, "learning_rate": 2.5935980932849264e-06, "loss": 0.8216, "step": 127020 }, { "epoch": 10.56, "learning_rate": 2.5934872377573923e-06, "loss": 0.7403, "step": 127030 }, { "epoch": 10.56, "learning_rate": 2.593376382229859e-06, "loss": 0.8044, "step": 127040 }, { "epoch": 10.56, "learning_rate": 2.593265526702325e-06, "loss": 0.8288, "step": 127050 }, { "epoch": 10.56, "learning_rate": 2.593154671174791e-06, "loss": 0.8283, "step": 127060 }, { "epoch": 10.56, "learning_rate": 2.5930438156472575e-06, "loss": 0.8467, "step": 127070 }, { "epoch": 10.56, "learning_rate": 2.5929329601197238e-06, "loss": 0.7499, "step": 127080 }, { "epoch": 10.56, "learning_rate": 2.5928221045921905e-06, "loss": 0.786, "step": 127090 }, { "epoch": 10.56, "learning_rate": 2.5927112490646564e-06, "loss": 0.7805, "step": 127100 }, { "epoch": 10.57, "learning_rate": 2.5926003935371227e-06, "loss": 0.8118, "step": 127110 }, { "epoch": 10.57, "learning_rate": 2.592489538009589e-06, "loss": 0.8283, "step": 127120 }, { "epoch": 10.57, "learning_rate": 2.5923786824820553e-06, "loss": 0.8273, "step": 127130 }, { "epoch": 10.57, "learning_rate": 2.592267826954521e-06, "loss": 0.8173, "step": 127140 }, { "epoch": 10.57, "learning_rate": 2.592156971426988e-06, "loss": 0.8054, "step": 127150 }, { "epoch": 10.57, "learning_rate": 2.5920461158994537e-06, "loss": 0.7711, "step": 127160 }, { "epoch": 10.57, "learning_rate": 2.5919352603719204e-06, "loss": 0.8438, "step": 127170 }, { "epoch": 10.57, "learning_rate": 2.5918244048443863e-06, "loss": 0.8136, "step": 127180 }, { "epoch": 10.57, "learning_rate": 2.5917135493168526e-06, "loss": 0.8623, "step": 127190 }, { "epoch": 10.57, "learning_rate": 2.5916026937893193e-06, "loss": 0.7846, "step": 127200 }, { "epoch": 10.57, "learning_rate": 2.591491838261785e-06, "loss": 0.7865, "step": 127210 }, { "epoch": 10.57, "learning_rate": 2.5913809827342515e-06, "loss": 0.8071, "step": 127220 }, { "epoch": 10.58, "learning_rate": 2.5912701272067178e-06, "loss": 0.7653, "step": 127230 }, { "epoch": 10.58, "learning_rate": 2.591159271679184e-06, "loss": 0.8034, "step": 127240 }, { "epoch": 10.58, "learning_rate": 2.59104841615165e-06, "loss": 0.772, "step": 127250 }, { "epoch": 10.58, "learning_rate": 2.5909375606241167e-06, "loss": 0.7909, "step": 127260 }, { "epoch": 10.58, "learning_rate": 2.5908267050965825e-06, "loss": 0.8758, "step": 127270 }, { "epoch": 10.58, "learning_rate": 2.5907158495690493e-06, "loss": 0.8035, "step": 127280 }, { "epoch": 10.58, "learning_rate": 2.590604994041515e-06, "loss": 0.7418, "step": 127290 }, { "epoch": 10.58, "learning_rate": 2.5904941385139814e-06, "loss": 0.7677, "step": 127300 }, { "epoch": 10.58, "learning_rate": 2.5903832829864477e-06, "loss": 0.8637, "step": 127310 }, { "epoch": 10.58, "learning_rate": 2.590272427458914e-06, "loss": 0.8474, "step": 127320 }, { "epoch": 10.58, "learning_rate": 2.5901615719313803e-06, "loss": 0.771, "step": 127330 }, { "epoch": 10.58, "learning_rate": 2.5900507164038466e-06, "loss": 0.737, "step": 127340 }, { "epoch": 10.59, "learning_rate": 2.589939860876313e-06, "loss": 0.8013, "step": 127350 }, { "epoch": 10.59, "learning_rate": 2.589829005348779e-06, "loss": 0.7495, "step": 127360 }, { "epoch": 10.59, "learning_rate": 2.5897181498212455e-06, "loss": 0.8142, "step": 127370 }, { "epoch": 10.59, "learning_rate": 2.5896072942937114e-06, "loss": 0.7491, "step": 127380 }, { "epoch": 10.59, "learning_rate": 2.589496438766178e-06, "loss": 0.8388, "step": 127390 }, { "epoch": 10.59, "learning_rate": 2.589385583238644e-06, "loss": 0.7557, "step": 127400 }, { "epoch": 10.59, "learning_rate": 2.5892747277111103e-06, "loss": 0.8194, "step": 127410 }, { "epoch": 10.59, "learning_rate": 2.5891638721835765e-06, "loss": 0.8253, "step": 127420 }, { "epoch": 10.59, "learning_rate": 2.589053016656043e-06, "loss": 0.8105, "step": 127430 }, { "epoch": 10.59, "learning_rate": 2.588942161128509e-06, "loss": 0.7749, "step": 127440 }, { "epoch": 10.59, "learning_rate": 2.5888313056009754e-06, "loss": 0.7453, "step": 127450 }, { "epoch": 10.59, "learning_rate": 2.5887204500734417e-06, "loss": 0.8078, "step": 127460 }, { "epoch": 10.6, "learning_rate": 2.588609594545908e-06, "loss": 0.8922, "step": 127470 }, { "epoch": 10.6, "learning_rate": 2.5884987390183743e-06, "loss": 0.8576, "step": 127480 }, { "epoch": 10.6, "learning_rate": 2.58838788349084e-06, "loss": 0.7484, "step": 127490 }, { "epoch": 10.6, "learning_rate": 2.588277027963307e-06, "loss": 0.786, "step": 127500 }, { "epoch": 10.6, "learning_rate": 2.5881661724357728e-06, "loss": 0.7714, "step": 127510 }, { "epoch": 10.6, "learning_rate": 2.5880553169082395e-06, "loss": 0.7822, "step": 127520 }, { "epoch": 10.6, "learning_rate": 2.5879444613807054e-06, "loss": 0.8123, "step": 127530 }, { "epoch": 10.6, "learning_rate": 2.5878336058531717e-06, "loss": 0.8069, "step": 127540 }, { "epoch": 10.6, "learning_rate": 2.587722750325638e-06, "loss": 0.7431, "step": 127550 }, { "epoch": 10.6, "learning_rate": 2.5876118947981043e-06, "loss": 0.7403, "step": 127560 }, { "epoch": 10.6, "learning_rate": 2.5875010392705706e-06, "loss": 0.8604, "step": 127570 }, { "epoch": 10.6, "learning_rate": 2.587390183743037e-06, "loss": 0.8503, "step": 127580 }, { "epoch": 10.61, "learning_rate": 2.587279328215503e-06, "loss": 0.7591, "step": 127590 }, { "epoch": 10.61, "learning_rate": 2.5871684726879694e-06, "loss": 0.7655, "step": 127600 }, { "epoch": 10.61, "learning_rate": 2.5870576171604357e-06, "loss": 0.7564, "step": 127610 }, { "epoch": 10.61, "learning_rate": 2.5869467616329016e-06, "loss": 0.8252, "step": 127620 }, { "epoch": 10.61, "learning_rate": 2.5868359061053683e-06, "loss": 0.8022, "step": 127630 }, { "epoch": 10.61, "learning_rate": 2.586725050577834e-06, "loss": 0.7724, "step": 127640 }, { "epoch": 10.61, "learning_rate": 2.5866141950503005e-06, "loss": 0.7796, "step": 127650 }, { "epoch": 10.61, "learning_rate": 2.5865033395227668e-06, "loss": 0.7649, "step": 127660 }, { "epoch": 10.61, "learning_rate": 2.586392483995233e-06, "loss": 0.8109, "step": 127670 }, { "epoch": 10.61, "learning_rate": 2.586281628467699e-06, "loss": 0.7571, "step": 127680 }, { "epoch": 10.61, "learning_rate": 2.5861707729401657e-06, "loss": 0.7543, "step": 127690 }, { "epoch": 10.61, "learning_rate": 2.586059917412632e-06, "loss": 0.82, "step": 127700 }, { "epoch": 10.62, "learning_rate": 2.5859490618850983e-06, "loss": 0.8092, "step": 127710 }, { "epoch": 10.62, "learning_rate": 2.5858382063575646e-06, "loss": 0.7939, "step": 127720 }, { "epoch": 10.62, "learning_rate": 2.5857273508300304e-06, "loss": 0.7813, "step": 127730 }, { "epoch": 10.62, "learning_rate": 2.585616495302497e-06, "loss": 0.7823, "step": 127740 }, { "epoch": 10.62, "learning_rate": 2.585505639774963e-06, "loss": 0.791, "step": 127750 }, { "epoch": 10.62, "learning_rate": 2.5853947842474293e-06, "loss": 0.7868, "step": 127760 }, { "epoch": 10.62, "learning_rate": 2.5852839287198956e-06, "loss": 0.8145, "step": 127770 }, { "epoch": 10.62, "learning_rate": 2.585173073192362e-06, "loss": 0.7794, "step": 127780 }, { "epoch": 10.62, "learning_rate": 2.585062217664828e-06, "loss": 0.8138, "step": 127790 }, { "epoch": 10.62, "learning_rate": 2.5849513621372945e-06, "loss": 0.8241, "step": 127800 }, { "epoch": 10.62, "learning_rate": 2.5848405066097604e-06, "loss": 0.7934, "step": 127810 }, { "epoch": 10.62, "learning_rate": 2.584729651082227e-06, "loss": 0.8889, "step": 127820 }, { "epoch": 10.63, "learning_rate": 2.5846187955546934e-06, "loss": 0.8456, "step": 127830 }, { "epoch": 10.63, "learning_rate": 2.5845079400271593e-06, "loss": 0.8693, "step": 127840 }, { "epoch": 10.63, "learning_rate": 2.584397084499626e-06, "loss": 0.7442, "step": 127850 }, { "epoch": 10.63, "learning_rate": 2.584286228972092e-06, "loss": 0.7884, "step": 127860 }, { "epoch": 10.63, "learning_rate": 2.5841753734445586e-06, "loss": 0.8532, "step": 127870 }, { "epoch": 10.63, "learning_rate": 2.5840645179170244e-06, "loss": 0.8407, "step": 127880 }, { "epoch": 10.63, "learning_rate": 2.5839536623894907e-06, "loss": 0.7681, "step": 127890 }, { "epoch": 10.63, "learning_rate": 2.583842806861957e-06, "loss": 0.7976, "step": 127900 }, { "epoch": 10.63, "learning_rate": 2.5837319513344233e-06, "loss": 0.7581, "step": 127910 }, { "epoch": 10.63, "learning_rate": 2.583621095806889e-06, "loss": 0.8539, "step": 127920 }, { "epoch": 10.63, "learning_rate": 2.583510240279356e-06, "loss": 0.7357, "step": 127930 }, { "epoch": 10.63, "learning_rate": 2.583399384751822e-06, "loss": 0.8514, "step": 127940 }, { "epoch": 10.64, "learning_rate": 2.5832885292242885e-06, "loss": 0.7926, "step": 127950 }, { "epoch": 10.64, "learning_rate": 2.583177673696755e-06, "loss": 0.8433, "step": 127960 }, { "epoch": 10.64, "learning_rate": 2.5830668181692207e-06, "loss": 0.8898, "step": 127970 }, { "epoch": 10.64, "learning_rate": 2.5829559626416874e-06, "loss": 0.8015, "step": 127980 }, { "epoch": 10.64, "learning_rate": 2.5828451071141533e-06, "loss": 0.8283, "step": 127990 }, { "epoch": 10.64, "learning_rate": 2.5827342515866196e-06, "loss": 0.785, "step": 128000 }, { "epoch": 10.64, "learning_rate": 2.582623396059086e-06, "loss": 0.8157, "step": 128010 }, { "epoch": 10.64, "learning_rate": 2.582512540531552e-06, "loss": 0.8462, "step": 128020 }, { "epoch": 10.64, "learning_rate": 2.582401685004018e-06, "loss": 0.8088, "step": 128030 }, { "epoch": 10.64, "learning_rate": 2.5822908294764847e-06, "loss": 0.7445, "step": 128040 }, { "epoch": 10.64, "learning_rate": 2.5821799739489506e-06, "loss": 0.7897, "step": 128050 }, { "epoch": 10.64, "learning_rate": 2.5820691184214173e-06, "loss": 0.8384, "step": 128060 }, { "epoch": 10.65, "learning_rate": 2.5819582628938836e-06, "loss": 0.883, "step": 128070 }, { "epoch": 10.65, "learning_rate": 2.5818474073663495e-06, "loss": 0.7734, "step": 128080 }, { "epoch": 10.65, "learning_rate": 2.5817365518388162e-06, "loss": 0.8358, "step": 128090 }, { "epoch": 10.65, "learning_rate": 2.581625696311282e-06, "loss": 0.8307, "step": 128100 }, { "epoch": 10.65, "learning_rate": 2.5815148407837484e-06, "loss": 0.8211, "step": 128110 }, { "epoch": 10.65, "learning_rate": 2.5814039852562147e-06, "loss": 0.8401, "step": 128120 }, { "epoch": 10.65, "learning_rate": 2.581293129728681e-06, "loss": 0.778, "step": 128130 }, { "epoch": 10.65, "learning_rate": 2.5811822742011473e-06, "loss": 0.8188, "step": 128140 }, { "epoch": 10.65, "learning_rate": 2.5810714186736136e-06, "loss": 0.8117, "step": 128150 }, { "epoch": 10.65, "learning_rate": 2.5809605631460794e-06, "loss": 0.7891, "step": 128160 }, { "epoch": 10.65, "learning_rate": 2.580849707618546e-06, "loss": 0.8486, "step": 128170 }, { "epoch": 10.65, "learning_rate": 2.580738852091012e-06, "loss": 0.7694, "step": 128180 }, { "epoch": 10.65, "learning_rate": 2.5806279965634783e-06, "loss": 0.7583, "step": 128190 }, { "epoch": 10.66, "learning_rate": 2.580517141035945e-06, "loss": 0.7638, "step": 128200 }, { "epoch": 10.66, "learning_rate": 2.580406285508411e-06, "loss": 0.7946, "step": 128210 }, { "epoch": 10.66, "learning_rate": 2.5802954299808776e-06, "loss": 0.7986, "step": 128220 }, { "epoch": 10.66, "learning_rate": 2.5801845744533435e-06, "loss": 0.7765, "step": 128230 }, { "epoch": 10.66, "learning_rate": 2.58007371892581e-06, "loss": 0.8029, "step": 128240 }, { "epoch": 10.66, "learning_rate": 2.579962863398276e-06, "loss": 0.7931, "step": 128250 }, { "epoch": 10.66, "learning_rate": 2.5798520078707424e-06, "loss": 0.8491, "step": 128260 }, { "epoch": 10.66, "learning_rate": 2.5797411523432083e-06, "loss": 0.8073, "step": 128270 }, { "epoch": 10.66, "learning_rate": 2.579630296815675e-06, "loss": 0.7815, "step": 128280 }, { "epoch": 10.66, "learning_rate": 2.579519441288141e-06, "loss": 0.7327, "step": 128290 }, { "epoch": 10.66, "learning_rate": 2.5794085857606076e-06, "loss": 0.7819, "step": 128300 }, { "epoch": 10.66, "learning_rate": 2.579297730233074e-06, "loss": 0.846, "step": 128310 }, { "epoch": 10.67, "learning_rate": 2.5791868747055397e-06, "loss": 0.851, "step": 128320 }, { "epoch": 10.67, "learning_rate": 2.5790760191780065e-06, "loss": 0.7967, "step": 128330 }, { "epoch": 10.67, "learning_rate": 2.5789651636504723e-06, "loss": 0.8191, "step": 128340 }, { "epoch": 10.67, "learning_rate": 2.5788543081229386e-06, "loss": 0.7482, "step": 128350 }, { "epoch": 10.67, "learning_rate": 2.578743452595405e-06, "loss": 0.7157, "step": 128360 }, { "epoch": 10.67, "learning_rate": 2.5786325970678712e-06, "loss": 0.8249, "step": 128370 }, { "epoch": 10.67, "learning_rate": 2.5785217415403375e-06, "loss": 0.7626, "step": 128380 }, { "epoch": 10.67, "learning_rate": 2.578410886012804e-06, "loss": 0.7996, "step": 128390 }, { "epoch": 10.67, "learning_rate": 2.5783000304852697e-06, "loss": 0.8014, "step": 128400 }, { "epoch": 10.67, "learning_rate": 2.5781891749577364e-06, "loss": 0.8111, "step": 128410 }, { "epoch": 10.67, "learning_rate": 2.5780783194302023e-06, "loss": 0.8389, "step": 128420 }, { "epoch": 10.67, "learning_rate": 2.5779674639026686e-06, "loss": 0.7375, "step": 128430 }, { "epoch": 10.68, "learning_rate": 2.5778566083751353e-06, "loss": 0.8141, "step": 128440 }, { "epoch": 10.68, "learning_rate": 2.577745752847601e-06, "loss": 0.7527, "step": 128450 }, { "epoch": 10.68, "learning_rate": 2.577634897320068e-06, "loss": 0.8046, "step": 128460 }, { "epoch": 10.68, "learning_rate": 2.5775240417925337e-06, "loss": 0.8392, "step": 128470 }, { "epoch": 10.68, "learning_rate": 2.577413186265e-06, "loss": 0.8295, "step": 128480 }, { "epoch": 10.68, "learning_rate": 2.5773023307374663e-06, "loss": 0.7251, "step": 128490 }, { "epoch": 10.68, "learning_rate": 2.5771914752099326e-06, "loss": 0.8533, "step": 128500 }, { "epoch": 10.68, "learning_rate": 2.5770806196823985e-06, "loss": 0.7668, "step": 128510 }, { "epoch": 10.68, "learning_rate": 2.5769697641548652e-06, "loss": 0.8279, "step": 128520 }, { "epoch": 10.68, "learning_rate": 2.576858908627331e-06, "loss": 0.8044, "step": 128530 }, { "epoch": 10.68, "learning_rate": 2.5767480530997974e-06, "loss": 0.8135, "step": 128540 }, { "epoch": 10.68, "learning_rate": 2.5766371975722637e-06, "loss": 0.7627, "step": 128550 }, { "epoch": 10.69, "learning_rate": 2.57652634204473e-06, "loss": 0.8169, "step": 128560 }, { "epoch": 10.69, "learning_rate": 2.5764154865171967e-06, "loss": 0.8446, "step": 128570 }, { "epoch": 10.69, "learning_rate": 2.5763046309896626e-06, "loss": 0.7694, "step": 128580 }, { "epoch": 10.69, "learning_rate": 2.576193775462129e-06, "loss": 0.7543, "step": 128590 }, { "epoch": 10.69, "learning_rate": 2.576082919934595e-06, "loss": 0.7905, "step": 128600 }, { "epoch": 10.69, "learning_rate": 2.5759720644070615e-06, "loss": 0.8397, "step": 128610 }, { "epoch": 10.69, "learning_rate": 2.5758612088795273e-06, "loss": 0.8328, "step": 128620 }, { "epoch": 10.69, "learning_rate": 2.575750353351994e-06, "loss": 0.7875, "step": 128630 }, { "epoch": 10.69, "learning_rate": 2.57563949782446e-06, "loss": 0.7517, "step": 128640 }, { "epoch": 10.69, "learning_rate": 2.5755286422969266e-06, "loss": 0.7767, "step": 128650 }, { "epoch": 10.69, "learning_rate": 2.5754177867693925e-06, "loss": 0.784, "step": 128660 }, { "epoch": 10.69, "learning_rate": 2.575306931241859e-06, "loss": 0.8765, "step": 128670 }, { "epoch": 10.7, "learning_rate": 2.5751960757143255e-06, "loss": 0.7789, "step": 128680 }, { "epoch": 10.7, "learning_rate": 2.5750852201867914e-06, "loss": 0.7738, "step": 128690 }, { "epoch": 10.7, "learning_rate": 2.5749743646592577e-06, "loss": 0.7985, "step": 128700 }, { "epoch": 10.7, "learning_rate": 2.574863509131724e-06, "loss": 0.7914, "step": 128710 }, { "epoch": 10.7, "learning_rate": 2.5747526536041903e-06, "loss": 0.892, "step": 128720 }, { "epoch": 10.7, "learning_rate": 2.5746417980766566e-06, "loss": 0.8216, "step": 128730 }, { "epoch": 10.7, "learning_rate": 2.574530942549123e-06, "loss": 0.8349, "step": 128740 }, { "epoch": 10.7, "learning_rate": 2.5744200870215887e-06, "loss": 0.7949, "step": 128750 }, { "epoch": 10.7, "learning_rate": 2.5743092314940555e-06, "loss": 0.83, "step": 128760 }, { "epoch": 10.7, "learning_rate": 2.5741983759665213e-06, "loss": 0.7977, "step": 128770 }, { "epoch": 10.7, "learning_rate": 2.5740875204389876e-06, "loss": 0.8419, "step": 128780 }, { "epoch": 10.7, "learning_rate": 2.573976664911454e-06, "loss": 0.7507, "step": 128790 }, { "epoch": 10.71, "learning_rate": 2.5738658093839202e-06, "loss": 0.7791, "step": 128800 }, { "epoch": 10.71, "learning_rate": 2.573754953856387e-06, "loss": 0.7643, "step": 128810 }, { "epoch": 10.71, "learning_rate": 2.573644098328853e-06, "loss": 0.8455, "step": 128820 }, { "epoch": 10.71, "learning_rate": 2.573533242801319e-06, "loss": 0.8361, "step": 128830 }, { "epoch": 10.71, "learning_rate": 2.5734223872737854e-06, "loss": 0.8373, "step": 128840 }, { "epoch": 10.71, "learning_rate": 2.5733115317462517e-06, "loss": 0.7932, "step": 128850 }, { "epoch": 10.71, "learning_rate": 2.5732006762187176e-06, "loss": 0.8019, "step": 128860 }, { "epoch": 10.71, "learning_rate": 2.5730898206911843e-06, "loss": 0.8532, "step": 128870 }, { "epoch": 10.71, "learning_rate": 2.57297896516365e-06, "loss": 0.7931, "step": 128880 }, { "epoch": 10.71, "learning_rate": 2.572868109636117e-06, "loss": 0.746, "step": 128890 }, { "epoch": 10.71, "learning_rate": 2.5727572541085828e-06, "loss": 0.8665, "step": 128900 }, { "epoch": 10.71, "learning_rate": 2.572646398581049e-06, "loss": 0.8044, "step": 128910 }, { "epoch": 10.72, "learning_rate": 2.5725355430535158e-06, "loss": 0.8582, "step": 128920 }, { "epoch": 10.72, "learning_rate": 2.5724246875259816e-06, "loss": 0.7565, "step": 128930 }, { "epoch": 10.72, "learning_rate": 2.572313831998448e-06, "loss": 0.7803, "step": 128940 }, { "epoch": 10.72, "learning_rate": 2.5722029764709142e-06, "loss": 0.8007, "step": 128950 }, { "epoch": 10.72, "learning_rate": 2.5720921209433805e-06, "loss": 0.7849, "step": 128960 }, { "epoch": 10.72, "learning_rate": 2.5719812654158464e-06, "loss": 0.8619, "step": 128970 }, { "epoch": 10.72, "learning_rate": 2.571870409888313e-06, "loss": 0.803, "step": 128980 }, { "epoch": 10.72, "learning_rate": 2.571759554360779e-06, "loss": 0.7804, "step": 128990 }, { "epoch": 10.72, "learning_rate": 2.5716486988332457e-06, "loss": 0.725, "step": 129000 }, { "epoch": 10.72, "learning_rate": 2.5715378433057116e-06, "loss": 0.7784, "step": 129010 }, { "epoch": 10.72, "learning_rate": 2.571426987778178e-06, "loss": 0.8667, "step": 129020 }, { "epoch": 10.72, "learning_rate": 2.571316132250644e-06, "loss": 0.846, "step": 129030 }, { "epoch": 10.73, "learning_rate": 2.5712052767231105e-06, "loss": 0.8209, "step": 129040 }, { "epoch": 10.73, "learning_rate": 2.5710944211955768e-06, "loss": 0.8038, "step": 129050 }, { "epoch": 10.73, "learning_rate": 2.570983565668043e-06, "loss": 0.791, "step": 129060 }, { "epoch": 10.73, "learning_rate": 2.5708727101405093e-06, "loss": 0.8095, "step": 129070 }, { "epoch": 10.73, "learning_rate": 2.5707618546129756e-06, "loss": 0.7784, "step": 129080 }, { "epoch": 10.73, "learning_rate": 2.570650999085442e-06, "loss": 0.7462, "step": 129090 }, { "epoch": 10.73, "learning_rate": 2.570540143557908e-06, "loss": 0.7914, "step": 129100 }, { "epoch": 10.73, "learning_rate": 2.5704292880303745e-06, "loss": 0.7914, "step": 129110 }, { "epoch": 10.73, "learning_rate": 2.5703184325028404e-06, "loss": 0.8247, "step": 129120 }, { "epoch": 10.73, "learning_rate": 2.5702075769753067e-06, "loss": 0.8309, "step": 129130 }, { "epoch": 10.73, "learning_rate": 2.570096721447773e-06, "loss": 0.7451, "step": 129140 }, { "epoch": 10.73, "learning_rate": 2.5699858659202393e-06, "loss": 0.8533, "step": 129150 }, { "epoch": 10.74, "learning_rate": 2.5698750103927056e-06, "loss": 0.7797, "step": 129160 }, { "epoch": 10.74, "learning_rate": 2.569764154865172e-06, "loss": 0.8477, "step": 129170 }, { "epoch": 10.74, "learning_rate": 2.569653299337638e-06, "loss": 0.796, "step": 129180 }, { "epoch": 10.74, "learning_rate": 2.5695424438101045e-06, "loss": 0.8371, "step": 129190 }, { "epoch": 10.74, "learning_rate": 2.5694315882825708e-06, "loss": 0.7772, "step": 129200 }, { "epoch": 10.74, "learning_rate": 2.5693207327550366e-06, "loss": 0.7595, "step": 129210 }, { "epoch": 10.74, "learning_rate": 2.5692098772275034e-06, "loss": 0.883, "step": 129220 }, { "epoch": 10.74, "learning_rate": 2.5690990216999692e-06, "loss": 0.7662, "step": 129230 }, { "epoch": 10.74, "learning_rate": 2.568988166172436e-06, "loss": 0.7942, "step": 129240 }, { "epoch": 10.74, "learning_rate": 2.568877310644902e-06, "loss": 0.7805, "step": 129250 }, { "epoch": 10.74, "learning_rate": 2.568766455117368e-06, "loss": 0.7409, "step": 129260 }, { "epoch": 10.74, "learning_rate": 2.5686555995898344e-06, "loss": 0.8882, "step": 129270 }, { "epoch": 10.75, "learning_rate": 2.5685447440623007e-06, "loss": 0.733, "step": 129280 }, { "epoch": 10.75, "learning_rate": 2.568433888534767e-06, "loss": 0.8138, "step": 129290 }, { "epoch": 10.75, "learning_rate": 2.5683230330072333e-06, "loss": 0.8431, "step": 129300 }, { "epoch": 10.75, "learning_rate": 2.5682121774796996e-06, "loss": 0.7981, "step": 129310 }, { "epoch": 10.75, "learning_rate": 2.5681013219521655e-06, "loss": 0.8637, "step": 129320 }, { "epoch": 10.75, "learning_rate": 2.567990466424632e-06, "loss": 0.7564, "step": 129330 }, { "epoch": 10.75, "learning_rate": 2.567879610897098e-06, "loss": 0.787, "step": 129340 }, { "epoch": 10.75, "learning_rate": 2.5677687553695648e-06, "loss": 0.8023, "step": 129350 }, { "epoch": 10.75, "learning_rate": 2.5676578998420306e-06, "loss": 0.787, "step": 129360 }, { "epoch": 10.75, "learning_rate": 2.567547044314497e-06, "loss": 0.8604, "step": 129370 }, { "epoch": 10.75, "learning_rate": 2.5674361887869632e-06, "loss": 0.7386, "step": 129380 }, { "epoch": 10.75, "learning_rate": 2.5673253332594295e-06, "loss": 0.871, "step": 129390 }, { "epoch": 10.76, "learning_rate": 2.5672144777318954e-06, "loss": 0.8122, "step": 129400 }, { "epoch": 10.76, "learning_rate": 2.567103622204362e-06, "loss": 0.7628, "step": 129410 }, { "epoch": 10.76, "learning_rate": 2.5669927666768284e-06, "loss": 0.8482, "step": 129420 }, { "epoch": 10.76, "learning_rate": 2.5668819111492947e-06, "loss": 0.8531, "step": 129430 }, { "epoch": 10.76, "learning_rate": 2.566771055621761e-06, "loss": 0.8579, "step": 129440 }, { "epoch": 10.76, "learning_rate": 2.566660200094227e-06, "loss": 0.8246, "step": 129450 }, { "epoch": 10.76, "learning_rate": 2.5665493445666936e-06, "loss": 0.812, "step": 129460 }, { "epoch": 10.76, "learning_rate": 2.5664384890391595e-06, "loss": 0.7935, "step": 129470 }, { "epoch": 10.76, "learning_rate": 2.5663276335116258e-06, "loss": 0.9063, "step": 129480 }, { "epoch": 10.76, "learning_rate": 2.566216777984092e-06, "loss": 0.8195, "step": 129490 }, { "epoch": 10.76, "learning_rate": 2.5661059224565584e-06, "loss": 0.7464, "step": 129500 }, { "epoch": 10.76, "learning_rate": 2.5659950669290246e-06, "loss": 0.7468, "step": 129510 }, { "epoch": 10.77, "learning_rate": 2.565884211401491e-06, "loss": 0.8543, "step": 129520 }, { "epoch": 10.77, "learning_rate": 2.565773355873957e-06, "loss": 0.7597, "step": 129530 }, { "epoch": 10.77, "learning_rate": 2.5656625003464235e-06, "loss": 0.799, "step": 129540 }, { "epoch": 10.77, "learning_rate": 2.56555164481889e-06, "loss": 0.8065, "step": 129550 }, { "epoch": 10.77, "learning_rate": 2.5654407892913557e-06, "loss": 0.7754, "step": 129560 }, { "epoch": 10.77, "learning_rate": 2.5653299337638224e-06, "loss": 0.8767, "step": 129570 }, { "epoch": 10.77, "learning_rate": 2.5652190782362883e-06, "loss": 0.8413, "step": 129580 }, { "epoch": 10.77, "learning_rate": 2.565108222708755e-06, "loss": 0.809, "step": 129590 }, { "epoch": 10.77, "learning_rate": 2.564997367181221e-06, "loss": 0.7779, "step": 129600 }, { "epoch": 10.77, "learning_rate": 2.564886511653687e-06, "loss": 0.8128, "step": 129610 }, { "epoch": 10.77, "learning_rate": 2.5647756561261535e-06, "loss": 0.8287, "step": 129620 }, { "epoch": 10.77, "learning_rate": 2.5646648005986198e-06, "loss": 0.823, "step": 129630 }, { "epoch": 10.78, "learning_rate": 2.5645539450710856e-06, "loss": 0.8169, "step": 129640 }, { "epoch": 10.78, "learning_rate": 2.5644430895435524e-06, "loss": 0.8282, "step": 129650 }, { "epoch": 10.78, "learning_rate": 2.5643322340160187e-06, "loss": 0.7947, "step": 129660 }, { "epoch": 10.78, "learning_rate": 2.564221378488485e-06, "loss": 0.8957, "step": 129670 }, { "epoch": 10.78, "learning_rate": 2.5641105229609512e-06, "loss": 0.7962, "step": 129680 }, { "epoch": 10.78, "learning_rate": 2.563999667433417e-06, "loss": 0.7995, "step": 129690 }, { "epoch": 10.78, "learning_rate": 2.563888811905884e-06, "loss": 0.7945, "step": 129700 }, { "epoch": 10.78, "learning_rate": 2.5637779563783497e-06, "loss": 0.8278, "step": 129710 }, { "epoch": 10.78, "learning_rate": 2.563667100850816e-06, "loss": 0.8378, "step": 129720 }, { "epoch": 10.78, "learning_rate": 2.5635562453232823e-06, "loss": 0.8457, "step": 129730 }, { "epoch": 10.78, "learning_rate": 2.5634453897957486e-06, "loss": 0.7976, "step": 129740 }, { "epoch": 10.78, "learning_rate": 2.5633345342682145e-06, "loss": 0.7922, "step": 129750 }, { "epoch": 10.79, "learning_rate": 2.563223678740681e-06, "loss": 0.7838, "step": 129760 }, { "epoch": 10.79, "learning_rate": 2.563112823213147e-06, "loss": 0.8372, "step": 129770 }, { "epoch": 10.79, "learning_rate": 2.5630019676856138e-06, "loss": 0.7667, "step": 129780 }, { "epoch": 10.79, "learning_rate": 2.56289111215808e-06, "loss": 0.7679, "step": 129790 }, { "epoch": 10.79, "learning_rate": 2.562780256630546e-06, "loss": 0.805, "step": 129800 }, { "epoch": 10.79, "learning_rate": 2.5626694011030127e-06, "loss": 0.8055, "step": 129810 }, { "epoch": 10.79, "learning_rate": 2.5625585455754785e-06, "loss": 0.8479, "step": 129820 }, { "epoch": 10.79, "learning_rate": 2.562447690047945e-06, "loss": 0.784, "step": 129830 }, { "epoch": 10.79, "learning_rate": 2.562336834520411e-06, "loss": 0.7868, "step": 129840 }, { "epoch": 10.79, "learning_rate": 2.5622259789928774e-06, "loss": 0.7973, "step": 129850 }, { "epoch": 10.79, "learning_rate": 2.5621151234653437e-06, "loss": 0.8457, "step": 129860 }, { "epoch": 10.79, "learning_rate": 2.56200426793781e-06, "loss": 0.9004, "step": 129870 }, { "epoch": 10.8, "learning_rate": 2.561893412410276e-06, "loss": 0.8277, "step": 129880 }, { "epoch": 10.8, "learning_rate": 2.5617825568827426e-06, "loss": 0.7616, "step": 129890 }, { "epoch": 10.8, "learning_rate": 2.5616717013552085e-06, "loss": 0.8024, "step": 129900 }, { "epoch": 10.8, "learning_rate": 2.5615608458276748e-06, "loss": 0.8278, "step": 129910 }, { "epoch": 10.8, "learning_rate": 2.5614499903001415e-06, "loss": 0.8528, "step": 129920 }, { "epoch": 10.8, "learning_rate": 2.5613391347726074e-06, "loss": 0.8003, "step": 129930 }, { "epoch": 10.8, "learning_rate": 2.561228279245074e-06, "loss": 0.8171, "step": 129940 }, { "epoch": 10.8, "learning_rate": 2.56111742371754e-06, "loss": 0.7632, "step": 129950 }, { "epoch": 10.8, "learning_rate": 2.5610065681900062e-06, "loss": 0.7692, "step": 129960 }, { "epoch": 10.8, "learning_rate": 2.5608957126624725e-06, "loss": 0.8569, "step": 129970 }, { "epoch": 10.8, "learning_rate": 2.560784857134939e-06, "loss": 0.7774, "step": 129980 }, { "epoch": 10.8, "learning_rate": 2.5606740016074047e-06, "loss": 0.8019, "step": 129990 }, { "epoch": 10.81, "learning_rate": 2.5605631460798714e-06, "loss": 0.8591, "step": 130000 }, { "epoch": 10.81, "learning_rate": 2.5604522905523373e-06, "loss": 0.8376, "step": 130010 }, { "epoch": 10.81, "learning_rate": 2.560341435024804e-06, "loss": 0.8455, "step": 130020 }, { "epoch": 10.81, "learning_rate": 2.5602305794972703e-06, "loss": 0.7713, "step": 130030 }, { "epoch": 10.81, "learning_rate": 2.560119723969736e-06, "loss": 0.8329, "step": 130040 }, { "epoch": 10.81, "learning_rate": 2.560008868442203e-06, "loss": 0.7972, "step": 130050 }, { "epoch": 10.81, "learning_rate": 2.5598980129146688e-06, "loss": 0.7606, "step": 130060 }, { "epoch": 10.81, "learning_rate": 2.559787157387135e-06, "loss": 0.8039, "step": 130070 }, { "epoch": 10.81, "learning_rate": 2.5596763018596014e-06, "loss": 0.7703, "step": 130080 }, { "epoch": 10.81, "learning_rate": 2.5595654463320677e-06, "loss": 0.8462, "step": 130090 }, { "epoch": 10.81, "learning_rate": 2.5594545908045335e-06, "loss": 0.7973, "step": 130100 }, { "epoch": 10.81, "learning_rate": 2.5593437352770003e-06, "loss": 0.7975, "step": 130110 }, { "epoch": 10.82, "learning_rate": 2.559232879749466e-06, "loss": 0.8772, "step": 130120 }, { "epoch": 10.82, "learning_rate": 2.559122024221933e-06, "loss": 0.793, "step": 130130 }, { "epoch": 10.82, "learning_rate": 2.5590111686943987e-06, "loss": 0.8279, "step": 130140 }, { "epoch": 10.82, "learning_rate": 2.558900313166865e-06, "loss": 0.9073, "step": 130150 }, { "epoch": 10.82, "learning_rate": 2.5587894576393317e-06, "loss": 0.726, "step": 130160 }, { "epoch": 10.82, "learning_rate": 2.5586786021117976e-06, "loss": 0.9082, "step": 130170 }, { "epoch": 10.82, "learning_rate": 2.5585677465842643e-06, "loss": 0.805, "step": 130180 }, { "epoch": 10.82, "learning_rate": 2.55845689105673e-06, "loss": 0.7862, "step": 130190 }, { "epoch": 10.82, "learning_rate": 2.5583460355291965e-06, "loss": 0.7423, "step": 130200 }, { "epoch": 10.82, "learning_rate": 2.5582351800016628e-06, "loss": 0.7719, "step": 130210 }, { "epoch": 10.82, "learning_rate": 2.558124324474129e-06, "loss": 0.8293, "step": 130220 }, { "epoch": 10.82, "learning_rate": 2.558013468946595e-06, "loss": 0.763, "step": 130230 }, { "epoch": 10.83, "learning_rate": 2.5579026134190617e-06, "loss": 0.7812, "step": 130240 }, { "epoch": 10.83, "learning_rate": 2.5577917578915275e-06, "loss": 0.7531, "step": 130250 }, { "epoch": 10.83, "learning_rate": 2.557680902363994e-06, "loss": 0.7534, "step": 130260 }, { "epoch": 10.83, "learning_rate": 2.55757004683646e-06, "loss": 0.9075, "step": 130270 }, { "epoch": 10.83, "learning_rate": 2.5574591913089264e-06, "loss": 0.8022, "step": 130280 }, { "epoch": 10.83, "learning_rate": 2.557348335781393e-06, "loss": 0.774, "step": 130290 }, { "epoch": 10.83, "learning_rate": 2.557237480253859e-06, "loss": 0.8959, "step": 130300 }, { "epoch": 10.83, "learning_rate": 2.5571266247263253e-06, "loss": 0.8496, "step": 130310 }, { "epoch": 10.83, "learning_rate": 2.5570157691987916e-06, "loss": 0.8415, "step": 130320 }, { "epoch": 10.83, "learning_rate": 2.556904913671258e-06, "loss": 0.7947, "step": 130330 }, { "epoch": 10.83, "learning_rate": 2.5567940581437238e-06, "loss": 0.761, "step": 130340 }, { "epoch": 10.83, "learning_rate": 2.5566832026161905e-06, "loss": 0.77, "step": 130350 }, { "epoch": 10.84, "learning_rate": 2.5565723470886564e-06, "loss": 0.7969, "step": 130360 }, { "epoch": 10.84, "learning_rate": 2.556461491561123e-06, "loss": 0.8672, "step": 130370 }, { "epoch": 10.84, "learning_rate": 2.556350636033589e-06, "loss": 0.7787, "step": 130380 }, { "epoch": 10.84, "learning_rate": 2.5562397805060552e-06, "loss": 0.773, "step": 130390 }, { "epoch": 10.84, "learning_rate": 2.556128924978522e-06, "loss": 0.7515, "step": 130400 }, { "epoch": 10.84, "learning_rate": 2.556018069450988e-06, "loss": 0.8035, "step": 130410 }, { "epoch": 10.84, "learning_rate": 2.555907213923454e-06, "loss": 0.8293, "step": 130420 }, { "epoch": 10.84, "learning_rate": 2.5557963583959204e-06, "loss": 0.7671, "step": 130430 }, { "epoch": 10.84, "learning_rate": 2.5556855028683867e-06, "loss": 0.7961, "step": 130440 }, { "epoch": 10.84, "learning_rate": 2.555574647340853e-06, "loss": 0.8374, "step": 130450 }, { "epoch": 10.84, "learning_rate": 2.5554637918133193e-06, "loss": 0.7641, "step": 130460 }, { "epoch": 10.84, "learning_rate": 2.555352936285785e-06, "loss": 0.8959, "step": 130470 }, { "epoch": 10.85, "learning_rate": 2.555242080758252e-06, "loss": 0.7754, "step": 130480 }, { "epoch": 10.85, "learning_rate": 2.5551312252307178e-06, "loss": 0.7939, "step": 130490 }, { "epoch": 10.85, "learning_rate": 2.555020369703184e-06, "loss": 0.8188, "step": 130500 }, { "epoch": 10.85, "learning_rate": 2.5549095141756504e-06, "loss": 0.7842, "step": 130510 }, { "epoch": 10.85, "learning_rate": 2.5547986586481167e-06, "loss": 0.8284, "step": 130520 }, { "epoch": 10.85, "learning_rate": 2.5546878031205834e-06, "loss": 0.8007, "step": 130530 }, { "epoch": 10.85, "learning_rate": 2.5545769475930493e-06, "loss": 0.7503, "step": 130540 }, { "epoch": 10.85, "learning_rate": 2.5544660920655156e-06, "loss": 0.7231, "step": 130550 }, { "epoch": 10.85, "learning_rate": 2.554355236537982e-06, "loss": 0.7827, "step": 130560 }, { "epoch": 10.85, "learning_rate": 2.554244381010448e-06, "loss": 0.9048, "step": 130570 }, { "epoch": 10.85, "learning_rate": 2.554133525482914e-06, "loss": 0.7881, "step": 130580 }, { "epoch": 10.85, "learning_rate": 2.5540226699553807e-06, "loss": 0.8154, "step": 130590 }, { "epoch": 10.86, "learning_rate": 2.5539118144278466e-06, "loss": 0.7667, "step": 130600 }, { "epoch": 10.86, "learning_rate": 2.553800958900313e-06, "loss": 0.7698, "step": 130610 }, { "epoch": 10.86, "learning_rate": 2.553690103372779e-06, "loss": 0.7483, "step": 130620 }, { "epoch": 10.86, "learning_rate": 2.5535792478452455e-06, "loss": 0.7965, "step": 130630 }, { "epoch": 10.86, "learning_rate": 2.5534683923177118e-06, "loss": 0.755, "step": 130640 }, { "epoch": 10.86, "learning_rate": 2.553357536790178e-06, "loss": 0.847, "step": 130650 }, { "epoch": 10.86, "learning_rate": 2.5532466812626444e-06, "loss": 0.8692, "step": 130660 }, { "epoch": 10.86, "learning_rate": 2.5531358257351107e-06, "loss": 0.8596, "step": 130670 }, { "epoch": 10.86, "learning_rate": 2.553024970207577e-06, "loss": 0.8273, "step": 130680 }, { "epoch": 10.86, "learning_rate": 2.552914114680043e-06, "loss": 0.8527, "step": 130690 }, { "epoch": 10.86, "learning_rate": 2.5528032591525096e-06, "loss": 0.8001, "step": 130700 }, { "epoch": 10.86, "learning_rate": 2.5526924036249754e-06, "loss": 0.8153, "step": 130710 }, { "epoch": 10.87, "learning_rate": 2.552581548097442e-06, "loss": 0.8645, "step": 130720 }, { "epoch": 10.87, "learning_rate": 2.552470692569908e-06, "loss": 0.7966, "step": 130730 }, { "epoch": 10.87, "learning_rate": 2.5523598370423743e-06, "loss": 0.7615, "step": 130740 }, { "epoch": 10.87, "learning_rate": 2.5522489815148406e-06, "loss": 0.7464, "step": 130750 }, { "epoch": 10.87, "learning_rate": 2.552138125987307e-06, "loss": 0.7359, "step": 130760 }, { "epoch": 10.87, "learning_rate": 2.552027270459773e-06, "loss": 0.9108, "step": 130770 }, { "epoch": 10.87, "learning_rate": 2.5519164149322395e-06, "loss": 0.7637, "step": 130780 }, { "epoch": 10.87, "learning_rate": 2.551805559404706e-06, "loss": 0.7967, "step": 130790 }, { "epoch": 10.87, "learning_rate": 2.551694703877172e-06, "loss": 0.7883, "step": 130800 }, { "epoch": 10.87, "learning_rate": 2.5515838483496384e-06, "loss": 0.8537, "step": 130810 }, { "epoch": 10.87, "learning_rate": 2.5514729928221043e-06, "loss": 0.8373, "step": 130820 }, { "epoch": 10.87, "learning_rate": 2.551362137294571e-06, "loss": 0.7965, "step": 130830 }, { "epoch": 10.88, "learning_rate": 2.551251281767037e-06, "loss": 0.7281, "step": 130840 }, { "epoch": 10.88, "learning_rate": 2.551140426239503e-06, "loss": 0.7734, "step": 130850 }, { "epoch": 10.88, "learning_rate": 2.5510295707119694e-06, "loss": 0.7933, "step": 130860 }, { "epoch": 10.88, "learning_rate": 2.5509187151844357e-06, "loss": 0.8107, "step": 130870 }, { "epoch": 10.88, "learning_rate": 2.550807859656902e-06, "loss": 0.7233, "step": 130880 }, { "epoch": 10.88, "learning_rate": 2.5506970041293683e-06, "loss": 0.7366, "step": 130890 }, { "epoch": 10.88, "learning_rate": 2.5505861486018346e-06, "loss": 0.8063, "step": 130900 }, { "epoch": 10.88, "learning_rate": 2.550475293074301e-06, "loss": 0.7631, "step": 130910 }, { "epoch": 10.88, "learning_rate": 2.550364437546767e-06, "loss": 0.8298, "step": 130920 }, { "epoch": 10.88, "learning_rate": 2.550253582019233e-06, "loss": 0.7977, "step": 130930 }, { "epoch": 10.88, "learning_rate": 2.5501427264917e-06, "loss": 0.7398, "step": 130940 }, { "epoch": 10.88, "learning_rate": 2.5500318709641657e-06, "loss": 0.8121, "step": 130950 }, { "epoch": 10.89, "learning_rate": 2.5499210154366324e-06, "loss": 0.7979, "step": 130960 }, { "epoch": 10.89, "learning_rate": 2.5498101599090983e-06, "loss": 0.8136, "step": 130970 }, { "epoch": 10.89, "learning_rate": 2.5497103899343182e-06, "loss": 0.7772, "step": 130980 }, { "epoch": 10.89, "learning_rate": 2.549599534406784e-06, "loss": 0.8233, "step": 130990 }, { "epoch": 10.89, "learning_rate": 2.549488678879251e-06, "loss": 0.7893, "step": 131000 }, { "epoch": 10.89, "learning_rate": 2.5493778233517167e-06, "loss": 0.8469, "step": 131010 }, { "epoch": 10.89, "learning_rate": 2.549266967824183e-06, "loss": 0.7857, "step": 131020 }, { "epoch": 10.89, "learning_rate": 2.5491561122966493e-06, "loss": 0.8344, "step": 131030 }, { "epoch": 10.89, "learning_rate": 2.5490452567691156e-06, "loss": 0.7603, "step": 131040 }, { "epoch": 10.89, "learning_rate": 2.5489344012415814e-06, "loss": 0.807, "step": 131050 }, { "epoch": 10.89, "learning_rate": 2.5488346312668014e-06, "loss": 0.7971, "step": 131060 }, { "epoch": 10.89, "learning_rate": 2.5487237757392677e-06, "loss": 0.8481, "step": 131070 }, { "epoch": 10.9, "learning_rate": 2.548612920211734e-06, "loss": 0.749, "step": 131080 }, { "epoch": 10.9, "learning_rate": 2.5485020646842003e-06, "loss": 0.8018, "step": 131090 }, { "epoch": 10.9, "learning_rate": 2.5483912091566666e-06, "loss": 0.8232, "step": 131100 }, { "epoch": 10.9, "learning_rate": 2.5482803536291325e-06, "loss": 0.7591, "step": 131110 }, { "epoch": 10.9, "learning_rate": 2.548169498101599e-06, "loss": 0.8275, "step": 131120 }, { "epoch": 10.9, "learning_rate": 2.548058642574065e-06, "loss": 0.7249, "step": 131130 }, { "epoch": 10.9, "learning_rate": 2.5479477870465318e-06, "loss": 0.771, "step": 131140 }, { "epoch": 10.9, "learning_rate": 2.5478369315189976e-06, "loss": 0.7998, "step": 131150 }, { "epoch": 10.9, "learning_rate": 2.547726075991464e-06, "loss": 0.7639, "step": 131160 }, { "epoch": 10.9, "learning_rate": 2.5476152204639302e-06, "loss": 0.8746, "step": 131170 }, { "epoch": 10.9, "learning_rate": 2.5475043649363965e-06, "loss": 0.7459, "step": 131180 }, { "epoch": 10.9, "learning_rate": 2.547393509408863e-06, "loss": 0.8416, "step": 131190 }, { "epoch": 10.91, "learning_rate": 2.547282653881329e-06, "loss": 0.8053, "step": 131200 }, { "epoch": 10.91, "learning_rate": 2.5471717983537954e-06, "loss": 0.7633, "step": 131210 }, { "epoch": 10.91, "learning_rate": 2.5470609428262613e-06, "loss": 0.7786, "step": 131220 }, { "epoch": 10.91, "learning_rate": 2.546950087298728e-06, "loss": 0.8042, "step": 131230 }, { "epoch": 10.91, "learning_rate": 2.546839231771194e-06, "loss": 0.7811, "step": 131240 }, { "epoch": 10.91, "learning_rate": 2.5467283762436606e-06, "loss": 0.7586, "step": 131250 }, { "epoch": 10.91, "learning_rate": 2.5466175207161265e-06, "loss": 0.7752, "step": 131260 }, { "epoch": 10.91, "learning_rate": 2.5465066651885928e-06, "loss": 0.8001, "step": 131270 }, { "epoch": 10.91, "learning_rate": 2.546395809661059e-06, "loss": 0.8137, "step": 131280 }, { "epoch": 10.91, "learning_rate": 2.5462849541335254e-06, "loss": 0.7585, "step": 131290 }, { "epoch": 10.91, "learning_rate": 2.5461740986059912e-06, "loss": 0.7687, "step": 131300 }, { "epoch": 10.91, "learning_rate": 2.546063243078458e-06, "loss": 0.736, "step": 131310 }, { "epoch": 10.92, "learning_rate": 2.5459523875509242e-06, "loss": 0.8246, "step": 131320 }, { "epoch": 10.92, "learning_rate": 2.5458415320233905e-06, "loss": 0.8084, "step": 131330 }, { "epoch": 10.92, "learning_rate": 2.545730676495857e-06, "loss": 0.7945, "step": 131340 }, { "epoch": 10.92, "learning_rate": 2.5456198209683227e-06, "loss": 0.8075, "step": 131350 }, { "epoch": 10.92, "learning_rate": 2.5455089654407894e-06, "loss": 0.841, "step": 131360 }, { "epoch": 10.92, "learning_rate": 2.5453981099132553e-06, "loss": 0.8473, "step": 131370 }, { "epoch": 10.92, "learning_rate": 2.5452872543857216e-06, "loss": 0.8059, "step": 131380 }, { "epoch": 10.92, "learning_rate": 2.545176398858188e-06, "loss": 0.742, "step": 131390 }, { "epoch": 10.92, "learning_rate": 2.545065543330654e-06, "loss": 0.8002, "step": 131400 }, { "epoch": 10.92, "learning_rate": 2.5449546878031205e-06, "loss": 0.756, "step": 131410 }, { "epoch": 10.92, "learning_rate": 2.5448438322755868e-06, "loss": 0.8317, "step": 131420 }, { "epoch": 10.92, "learning_rate": 2.544732976748053e-06, "loss": 0.8275, "step": 131430 }, { "epoch": 10.93, "learning_rate": 2.5446221212205194e-06, "loss": 0.7604, "step": 131440 }, { "epoch": 10.93, "learning_rate": 2.5445112656929857e-06, "loss": 0.7524, "step": 131450 }, { "epoch": 10.93, "learning_rate": 2.5444004101654515e-06, "loss": 0.8229, "step": 131460 }, { "epoch": 10.93, "learning_rate": 2.5442895546379182e-06, "loss": 0.8797, "step": 131470 }, { "epoch": 10.93, "learning_rate": 2.544178699110384e-06, "loss": 0.7996, "step": 131480 }, { "epoch": 10.93, "learning_rate": 2.544067843582851e-06, "loss": 0.8308, "step": 131490 }, { "epoch": 10.93, "learning_rate": 2.5439569880553167e-06, "loss": 0.7682, "step": 131500 }, { "epoch": 10.93, "learning_rate": 2.543846132527783e-06, "loss": 0.7285, "step": 131510 }, { "epoch": 10.93, "learning_rate": 2.5437352770002493e-06, "loss": 0.7866, "step": 131520 }, { "epoch": 10.93, "learning_rate": 2.5436244214727156e-06, "loss": 0.8309, "step": 131530 }, { "epoch": 10.93, "learning_rate": 2.5435135659451815e-06, "loss": 0.7833, "step": 131540 }, { "epoch": 10.93, "learning_rate": 2.543402710417648e-06, "loss": 0.8087, "step": 131550 }, { "epoch": 10.94, "learning_rate": 2.5432918548901145e-06, "loss": 0.806, "step": 131560 }, { "epoch": 10.94, "learning_rate": 2.5431809993625808e-06, "loss": 0.8013, "step": 131570 }, { "epoch": 10.94, "learning_rate": 2.543070143835047e-06, "loss": 0.76, "step": 131580 }, { "epoch": 10.94, "learning_rate": 2.542959288307513e-06, "loss": 0.7817, "step": 131590 }, { "epoch": 10.94, "learning_rate": 2.5428484327799797e-06, "loss": 0.7826, "step": 131600 }, { "epoch": 10.94, "learning_rate": 2.5427375772524455e-06, "loss": 0.8314, "step": 131610 }, { "epoch": 10.94, "learning_rate": 2.542626721724912e-06, "loss": 0.8264, "step": 131620 }, { "epoch": 10.94, "learning_rate": 2.542515866197378e-06, "loss": 0.7551, "step": 131630 }, { "epoch": 10.94, "learning_rate": 2.5424050106698444e-06, "loss": 0.8187, "step": 131640 }, { "epoch": 10.94, "learning_rate": 2.5422941551423103e-06, "loss": 0.7798, "step": 131650 }, { "epoch": 10.94, "learning_rate": 2.542183299614777e-06, "loss": 0.806, "step": 131660 }, { "epoch": 10.94, "learning_rate": 2.542072444087243e-06, "loss": 0.859, "step": 131670 }, { "epoch": 10.95, "learning_rate": 2.5419615885597096e-06, "loss": 0.7859, "step": 131680 }, { "epoch": 10.95, "learning_rate": 2.541850733032176e-06, "loss": 0.7429, "step": 131690 }, { "epoch": 10.95, "learning_rate": 2.5417398775046418e-06, "loss": 0.73, "step": 131700 }, { "epoch": 10.95, "learning_rate": 2.5416290219771085e-06, "loss": 0.8227, "step": 131710 }, { "epoch": 10.95, "learning_rate": 2.5415181664495744e-06, "loss": 0.8349, "step": 131720 }, { "epoch": 10.95, "learning_rate": 2.5414073109220407e-06, "loss": 0.8615, "step": 131730 }, { "epoch": 10.95, "learning_rate": 2.541296455394507e-06, "loss": 0.841, "step": 131740 }, { "epoch": 10.95, "learning_rate": 2.5411855998669732e-06, "loss": 0.8281, "step": 131750 }, { "epoch": 10.95, "learning_rate": 2.5410747443394395e-06, "loss": 0.7826, "step": 131760 }, { "epoch": 10.95, "learning_rate": 2.540963888811906e-06, "loss": 0.8587, "step": 131770 }, { "epoch": 10.95, "learning_rate": 2.5408530332843717e-06, "loss": 0.7559, "step": 131780 }, { "epoch": 10.95, "learning_rate": 2.5407421777568384e-06, "loss": 0.8171, "step": 131790 }, { "epoch": 10.96, "learning_rate": 2.5406313222293047e-06, "loss": 0.7564, "step": 131800 }, { "epoch": 10.96, "learning_rate": 2.5405204667017706e-06, "loss": 0.7528, "step": 131810 }, { "epoch": 10.96, "learning_rate": 2.5404096111742373e-06, "loss": 0.8029, "step": 131820 }, { "epoch": 10.96, "learning_rate": 2.540298755646703e-06, "loss": 0.7766, "step": 131830 }, { "epoch": 10.96, "learning_rate": 2.54018790011917e-06, "loss": 0.795, "step": 131840 }, { "epoch": 10.96, "learning_rate": 2.5400770445916358e-06, "loss": 0.7825, "step": 131850 }, { "epoch": 10.96, "learning_rate": 2.539966189064102e-06, "loss": 0.7543, "step": 131860 }, { "epoch": 10.96, "learning_rate": 2.5398553335365684e-06, "loss": 0.7904, "step": 131870 }, { "epoch": 10.96, "learning_rate": 2.5397444780090347e-06, "loss": 0.7785, "step": 131880 }, { "epoch": 10.96, "learning_rate": 2.5396336224815005e-06, "loss": 0.769, "step": 131890 }, { "epoch": 10.96, "learning_rate": 2.5395227669539673e-06, "loss": 0.7926, "step": 131900 }, { "epoch": 10.96, "learning_rate": 2.539411911426433e-06, "loss": 0.716, "step": 131910 }, { "epoch": 10.97, "learning_rate": 2.5393010558989e-06, "loss": 0.8812, "step": 131920 }, { "epoch": 10.97, "learning_rate": 2.539190200371366e-06, "loss": 0.8166, "step": 131930 }, { "epoch": 10.97, "learning_rate": 2.539079344843832e-06, "loss": 0.8498, "step": 131940 }, { "epoch": 10.97, "learning_rate": 2.5389684893162987e-06, "loss": 0.8391, "step": 131950 }, { "epoch": 10.97, "learning_rate": 2.5388576337887646e-06, "loss": 0.7584, "step": 131960 }, { "epoch": 10.97, "learning_rate": 2.538746778261231e-06, "loss": 0.8484, "step": 131970 }, { "epoch": 10.97, "learning_rate": 2.538635922733697e-06, "loss": 0.7829, "step": 131980 }, { "epoch": 10.97, "learning_rate": 2.5385250672061635e-06, "loss": 0.788, "step": 131990 }, { "epoch": 10.97, "learning_rate": 2.5384142116786298e-06, "loss": 0.7444, "step": 132000 }, { "epoch": 10.97, "learning_rate": 2.538303356151096e-06, "loss": 0.7826, "step": 132010 }, { "epoch": 10.97, "learning_rate": 2.538192500623562e-06, "loss": 0.7994, "step": 132020 }, { "epoch": 10.97, "learning_rate": 2.5380816450960287e-06, "loss": 0.7844, "step": 132030 }, { "epoch": 10.97, "learning_rate": 2.5379707895684945e-06, "loss": 0.7597, "step": 132040 }, { "epoch": 10.98, "learning_rate": 2.537859934040961e-06, "loss": 0.7486, "step": 132050 }, { "epoch": 10.98, "learning_rate": 2.5377490785134276e-06, "loss": 0.7848, "step": 132060 }, { "epoch": 10.98, "learning_rate": 2.5376382229858934e-06, "loss": 0.8346, "step": 132070 }, { "epoch": 10.98, "learning_rate": 2.53752736745836e-06, "loss": 0.7761, "step": 132080 }, { "epoch": 10.98, "learning_rate": 2.537416511930826e-06, "loss": 0.7891, "step": 132090 }, { "epoch": 10.98, "learning_rate": 2.5373056564032923e-06, "loss": 0.8263, "step": 132100 }, { "epoch": 10.98, "learning_rate": 2.5371948008757586e-06, "loss": 0.8173, "step": 132110 }, { "epoch": 10.98, "learning_rate": 2.537083945348225e-06, "loss": 0.8029, "step": 132120 }, { "epoch": 10.98, "learning_rate": 2.5369730898206908e-06, "loss": 0.8033, "step": 132130 }, { "epoch": 10.98, "learning_rate": 2.5368622342931575e-06, "loss": 0.7804, "step": 132140 }, { "epoch": 10.98, "learning_rate": 2.5367513787656234e-06, "loss": 0.7938, "step": 132150 }, { "epoch": 10.98, "learning_rate": 2.5366405232380897e-06, "loss": 0.8057, "step": 132160 }, { "epoch": 10.99, "learning_rate": 2.5365296677105564e-06, "loss": 0.8549, "step": 132170 }, { "epoch": 10.99, "learning_rate": 2.5364188121830222e-06, "loss": 0.7939, "step": 132180 }, { "epoch": 10.99, "learning_rate": 2.536307956655489e-06, "loss": 0.7805, "step": 132190 }, { "epoch": 10.99, "learning_rate": 2.536197101127955e-06, "loss": 0.8323, "step": 132200 }, { "epoch": 10.99, "learning_rate": 2.536086245600421e-06, "loss": 0.833, "step": 132210 }, { "epoch": 10.99, "learning_rate": 2.5359753900728874e-06, "loss": 0.8098, "step": 132220 }, { "epoch": 10.99, "learning_rate": 2.5358645345453537e-06, "loss": 0.7738, "step": 132230 }, { "epoch": 10.99, "learning_rate": 2.5357536790178196e-06, "loss": 0.7812, "step": 132240 }, { "epoch": 10.99, "learning_rate": 2.5356428234902863e-06, "loss": 0.8322, "step": 132250 }, { "epoch": 10.99, "learning_rate": 2.535531967962752e-06, "loss": 0.8335, "step": 132260 }, { "epoch": 10.99, "learning_rate": 2.535421112435219e-06, "loss": 0.9158, "step": 132270 }, { "epoch": 10.99, "learning_rate": 2.5353102569076848e-06, "loss": 0.8295, "step": 132280 }, { "epoch": 11.0, "learning_rate": 2.535199401380151e-06, "loss": 0.719, "step": 132290 }, { "epoch": 11.0, "learning_rate": 2.535088545852618e-06, "loss": 0.7549, "step": 132300 }, { "epoch": 11.0, "learning_rate": 2.5349776903250837e-06, "loss": 0.8085, "step": 132310 }, { "epoch": 11.0, "learning_rate": 2.53486683479755e-06, "loss": 0.8362, "step": 132320 }, { "epoch": 11.0, "learning_rate": 2.5347559792700163e-06, "loss": 0.8327, "step": 132330 }, { "epoch": 11.0, "learning_rate": 2.5346451237424826e-06, "loss": 0.7631, "step": 132340 }, { "epoch": 11.0, "eval_loss": 1.0779563188552856, "eval_runtime": 353.9944, "eval_samples_per_second": 7.554, "eval_steps_per_second": 3.777, "eval_wer": 0.6511844726024495, "step": 132341 }, { "epoch": 11.0, "learning_rate": 2.534534268214949e-06, "loss": 0.8854, "step": 132350 }, { "epoch": 11.0, "learning_rate": 2.534423412687415e-06, "loss": 0.8231, "step": 132360 }, { "epoch": 11.0, "learning_rate": 2.534312557159881e-06, "loss": 0.8068, "step": 132370 }, { "epoch": 11.0, "learning_rate": 2.5342017016323477e-06, "loss": 0.8345, "step": 132380 }, { "epoch": 11.0, "learning_rate": 2.5340908461048136e-06, "loss": 0.7692, "step": 132390 }, { "epoch": 11.0, "learning_rate": 2.53397999057728e-06, "loss": 0.8261, "step": 132400 }, { "epoch": 11.01, "learning_rate": 2.533869135049746e-06, "loss": 0.7524, "step": 132410 }, { "epoch": 11.01, "learning_rate": 2.5337582795222125e-06, "loss": 0.7035, "step": 132420 }, { "epoch": 11.01, "learning_rate": 2.533647423994679e-06, "loss": 0.8155, "step": 132430 }, { "epoch": 11.01, "learning_rate": 2.533536568467145e-06, "loss": 0.7687, "step": 132440 }, { "epoch": 11.01, "learning_rate": 2.5334257129396114e-06, "loss": 0.8685, "step": 132450 }, { "epoch": 11.01, "learning_rate": 2.5333148574120777e-06, "loss": 0.8258, "step": 132460 }, { "epoch": 11.01, "learning_rate": 2.533204001884544e-06, "loss": 0.7339, "step": 132470 }, { "epoch": 11.01, "learning_rate": 2.53309314635701e-06, "loss": 0.7464, "step": 132480 }, { "epoch": 11.01, "learning_rate": 2.5329822908294766e-06, "loss": 0.7674, "step": 132490 }, { "epoch": 11.01, "learning_rate": 2.5328714353019424e-06, "loss": 0.7948, "step": 132500 }, { "epoch": 11.01, "learning_rate": 2.5327605797744087e-06, "loss": 0.7682, "step": 132510 }, { "epoch": 11.01, "learning_rate": 2.532649724246875e-06, "loss": 0.7901, "step": 132520 }, { "epoch": 11.02, "learning_rate": 2.5325388687193413e-06, "loss": 0.8031, "step": 132530 }, { "epoch": 11.02, "learning_rate": 2.532428013191808e-06, "loss": 0.8072, "step": 132540 }, { "epoch": 11.02, "learning_rate": 2.532317157664274e-06, "loss": 0.8109, "step": 132550 }, { "epoch": 11.02, "learning_rate": 2.53220630213674e-06, "loss": 0.754, "step": 132560 }, { "epoch": 11.02, "learning_rate": 2.5320954466092065e-06, "loss": 0.7948, "step": 132570 }, { "epoch": 11.02, "learning_rate": 2.531984591081673e-06, "loss": 0.7138, "step": 132580 }, { "epoch": 11.02, "learning_rate": 2.5318737355541387e-06, "loss": 0.7201, "step": 132590 }, { "epoch": 11.02, "learning_rate": 2.5317628800266054e-06, "loss": 0.851, "step": 132600 }, { "epoch": 11.02, "learning_rate": 2.5316520244990713e-06, "loss": 0.7806, "step": 132610 }, { "epoch": 11.02, "learning_rate": 2.531541168971538e-06, "loss": 0.8233, "step": 132620 }, { "epoch": 11.02, "learning_rate": 2.531430313444004e-06, "loss": 0.7841, "step": 132630 }, { "epoch": 11.02, "learning_rate": 2.53131945791647e-06, "loss": 0.7588, "step": 132640 }, { "epoch": 11.03, "learning_rate": 2.5312086023889364e-06, "loss": 0.8504, "step": 132650 }, { "epoch": 11.03, "learning_rate": 2.5310977468614027e-06, "loss": 0.7405, "step": 132660 }, { "epoch": 11.03, "learning_rate": 2.530986891333869e-06, "loss": 0.8046, "step": 132670 }, { "epoch": 11.03, "learning_rate": 2.5308760358063353e-06, "loss": 0.7688, "step": 132680 }, { "epoch": 11.03, "learning_rate": 2.5307651802788016e-06, "loss": 0.7805, "step": 132690 }, { "epoch": 11.03, "learning_rate": 2.530654324751268e-06, "loss": 0.891, "step": 132700 }, { "epoch": 11.03, "learning_rate": 2.530543469223734e-06, "loss": 0.7699, "step": 132710 }, { "epoch": 11.03, "learning_rate": 2.5304326136962e-06, "loss": 0.744, "step": 132720 }, { "epoch": 11.03, "learning_rate": 2.530321758168667e-06, "loss": 0.7307, "step": 132730 }, { "epoch": 11.03, "learning_rate": 2.5302109026411327e-06, "loss": 0.8478, "step": 132740 }, { "epoch": 11.03, "learning_rate": 2.530100047113599e-06, "loss": 0.8662, "step": 132750 }, { "epoch": 11.03, "learning_rate": 2.5299891915860653e-06, "loss": 0.851, "step": 132760 }, { "epoch": 11.04, "learning_rate": 2.5298783360585316e-06, "loss": 0.8205, "step": 132770 }, { "epoch": 11.04, "learning_rate": 2.529767480530998e-06, "loss": 0.8832, "step": 132780 }, { "epoch": 11.04, "learning_rate": 2.529656625003464e-06, "loss": 0.8382, "step": 132790 }, { "epoch": 11.04, "learning_rate": 2.5295457694759304e-06, "loss": 0.8731, "step": 132800 }, { "epoch": 11.04, "learning_rate": 2.5294349139483967e-06, "loss": 0.7879, "step": 132810 }, { "epoch": 11.04, "learning_rate": 2.529324058420863e-06, "loss": 0.7718, "step": 132820 }, { "epoch": 11.04, "learning_rate": 2.529213202893329e-06, "loss": 0.7412, "step": 132830 }, { "epoch": 11.04, "learning_rate": 2.5291023473657956e-06, "loss": 0.7985, "step": 132840 }, { "epoch": 11.04, "learning_rate": 2.5289914918382615e-06, "loss": 0.8768, "step": 132850 }, { "epoch": 11.04, "learning_rate": 2.5288806363107282e-06, "loss": 0.8168, "step": 132860 }, { "epoch": 11.04, "learning_rate": 2.528769780783194e-06, "loss": 0.7356, "step": 132870 }, { "epoch": 11.04, "learning_rate": 2.5286589252556604e-06, "loss": 0.8227, "step": 132880 }, { "epoch": 11.05, "learning_rate": 2.5285480697281267e-06, "loss": 0.8118, "step": 132890 }, { "epoch": 11.05, "learning_rate": 2.528437214200593e-06, "loss": 0.815, "step": 132900 }, { "epoch": 11.05, "learning_rate": 2.5283263586730593e-06, "loss": 0.8144, "step": 132910 }, { "epoch": 11.05, "learning_rate": 2.5282155031455256e-06, "loss": 0.7256, "step": 132920 }, { "epoch": 11.05, "learning_rate": 2.528104647617992e-06, "loss": 0.8748, "step": 132930 }, { "epoch": 11.05, "learning_rate": 2.5279937920904577e-06, "loss": 0.7662, "step": 132940 }, { "epoch": 11.05, "learning_rate": 2.5278829365629244e-06, "loss": 0.8583, "step": 132950 }, { "epoch": 11.05, "learning_rate": 2.5277720810353903e-06, "loss": 0.8101, "step": 132960 }, { "epoch": 11.05, "learning_rate": 2.527661225507857e-06, "loss": 0.7857, "step": 132970 }, { "epoch": 11.05, "learning_rate": 2.527550369980323e-06, "loss": 0.7797, "step": 132980 }, { "epoch": 11.05, "learning_rate": 2.527439514452789e-06, "loss": 0.8059, "step": 132990 }, { "epoch": 11.05, "learning_rate": 2.5273286589252555e-06, "loss": 0.8589, "step": 133000 }, { "epoch": 11.06, "learning_rate": 2.527217803397722e-06, "loss": 0.7985, "step": 133010 }, { "epoch": 11.06, "learning_rate": 2.5271069478701877e-06, "loss": 0.7282, "step": 133020 }, { "epoch": 11.06, "learning_rate": 2.5269960923426544e-06, "loss": 0.7404, "step": 133030 }, { "epoch": 11.06, "learning_rate": 2.5268852368151207e-06, "loss": 0.7847, "step": 133040 }, { "epoch": 11.06, "learning_rate": 2.526774381287587e-06, "loss": 0.8535, "step": 133050 }, { "epoch": 11.06, "learning_rate": 2.5266635257600533e-06, "loss": 0.7726, "step": 133060 }, { "epoch": 11.06, "learning_rate": 2.526552670232519e-06, "loss": 0.7827, "step": 133070 }, { "epoch": 11.06, "learning_rate": 2.526441814704986e-06, "loss": 0.8098, "step": 133080 }, { "epoch": 11.06, "learning_rate": 2.5263309591774517e-06, "loss": 0.7368, "step": 133090 }, { "epoch": 11.06, "learning_rate": 2.526220103649918e-06, "loss": 0.8642, "step": 133100 }, { "epoch": 11.06, "learning_rate": 2.5261092481223843e-06, "loss": 0.7735, "step": 133110 }, { "epoch": 11.06, "learning_rate": 2.5259983925948506e-06, "loss": 0.704, "step": 133120 }, { "epoch": 11.07, "learning_rate": 2.525887537067317e-06, "loss": 0.7776, "step": 133130 }, { "epoch": 11.07, "learning_rate": 2.5257766815397832e-06, "loss": 0.8089, "step": 133140 }, { "epoch": 11.07, "learning_rate": 2.525665826012249e-06, "loss": 0.8112, "step": 133150 }, { "epoch": 11.07, "learning_rate": 2.525554970484716e-06, "loss": 0.7774, "step": 133160 }, { "epoch": 11.07, "learning_rate": 2.525444114957182e-06, "loss": 0.7894, "step": 133170 }, { "epoch": 11.07, "learning_rate": 2.525333259429648e-06, "loss": 0.8465, "step": 133180 }, { "epoch": 11.07, "learning_rate": 2.5252224039021147e-06, "loss": 0.8039, "step": 133190 }, { "epoch": 11.07, "learning_rate": 2.5251115483745806e-06, "loss": 0.8831, "step": 133200 }, { "epoch": 11.07, "learning_rate": 2.5250006928470473e-06, "loss": 0.8548, "step": 133210 }, { "epoch": 11.07, "learning_rate": 2.524889837319513e-06, "loss": 0.7789, "step": 133220 }, { "epoch": 11.07, "learning_rate": 2.5247789817919794e-06, "loss": 0.8057, "step": 133230 }, { "epoch": 11.07, "learning_rate": 2.5246681262644457e-06, "loss": 0.8073, "step": 133240 }, { "epoch": 11.08, "learning_rate": 2.524557270736912e-06, "loss": 0.8313, "step": 133250 }, { "epoch": 11.08, "learning_rate": 2.524446415209378e-06, "loss": 0.8147, "step": 133260 }, { "epoch": 11.08, "learning_rate": 2.5243355596818446e-06, "loss": 0.7948, "step": 133270 }, { "epoch": 11.08, "learning_rate": 2.524224704154311e-06, "loss": 0.7187, "step": 133280 }, { "epoch": 11.08, "learning_rate": 2.5241138486267772e-06, "loss": 0.7416, "step": 133290 }, { "epoch": 11.08, "learning_rate": 2.5240029930992435e-06, "loss": 0.8165, "step": 133300 }, { "epoch": 11.08, "learning_rate": 2.5238921375717094e-06, "loss": 0.7933, "step": 133310 }, { "epoch": 11.08, "learning_rate": 2.523781282044176e-06, "loss": 0.7138, "step": 133320 }, { "epoch": 11.08, "learning_rate": 2.523670426516642e-06, "loss": 0.7345, "step": 133330 }, { "epoch": 11.08, "learning_rate": 2.5235595709891083e-06, "loss": 0.8184, "step": 133340 }, { "epoch": 11.08, "learning_rate": 2.5234487154615746e-06, "loss": 0.8548, "step": 133350 }, { "epoch": 11.08, "learning_rate": 2.523337859934041e-06, "loss": 0.8003, "step": 133360 }, { "epoch": 11.09, "learning_rate": 2.5232270044065067e-06, "loss": 0.7543, "step": 133370 }, { "epoch": 11.09, "learning_rate": 2.5231161488789735e-06, "loss": 0.7866, "step": 133380 }, { "epoch": 11.09, "learning_rate": 2.5230052933514393e-06, "loss": 0.7134, "step": 133390 }, { "epoch": 11.09, "learning_rate": 2.522894437823906e-06, "loss": 0.8491, "step": 133400 }, { "epoch": 11.09, "learning_rate": 2.5227835822963723e-06, "loss": 0.8469, "step": 133410 }, { "epoch": 11.09, "learning_rate": 2.5226727267688382e-06, "loss": 0.8406, "step": 133420 }, { "epoch": 11.09, "learning_rate": 2.522561871241305e-06, "loss": 0.7044, "step": 133430 }, { "epoch": 11.09, "learning_rate": 2.522451015713771e-06, "loss": 0.8088, "step": 133440 }, { "epoch": 11.09, "learning_rate": 2.522340160186237e-06, "loss": 0.8057, "step": 133450 }, { "epoch": 11.09, "learning_rate": 2.5222293046587034e-06, "loss": 0.7713, "step": 133460 }, { "epoch": 11.09, "learning_rate": 2.5221184491311697e-06, "loss": 0.7705, "step": 133470 }, { "epoch": 11.09, "learning_rate": 2.522007593603636e-06, "loss": 0.7348, "step": 133480 }, { "epoch": 11.1, "learning_rate": 2.5218967380761023e-06, "loss": 0.7637, "step": 133490 }, { "epoch": 11.1, "learning_rate": 2.521785882548568e-06, "loss": 0.8286, "step": 133500 }, { "epoch": 11.1, "learning_rate": 2.521675027021035e-06, "loss": 0.8007, "step": 133510 }, { "epoch": 11.1, "learning_rate": 2.521564171493501e-06, "loss": 0.7603, "step": 133520 }, { "epoch": 11.1, "learning_rate": 2.521453315965967e-06, "loss": 0.7172, "step": 133530 }, { "epoch": 11.1, "learning_rate": 2.5213424604384338e-06, "loss": 0.7456, "step": 133540 }, { "epoch": 11.1, "learning_rate": 2.5212316049108996e-06, "loss": 0.8742, "step": 133550 }, { "epoch": 11.1, "learning_rate": 2.5211207493833663e-06, "loss": 0.7489, "step": 133560 }, { "epoch": 11.1, "learning_rate": 2.5210098938558322e-06, "loss": 0.7833, "step": 133570 }, { "epoch": 11.1, "learning_rate": 2.5208990383282985e-06, "loss": 0.7788, "step": 133580 }, { "epoch": 11.1, "learning_rate": 2.520788182800765e-06, "loss": 0.7134, "step": 133590 }, { "epoch": 11.1, "learning_rate": 2.520677327273231e-06, "loss": 0.8087, "step": 133600 }, { "epoch": 11.11, "learning_rate": 2.520566471745697e-06, "loss": 0.7841, "step": 133610 }, { "epoch": 11.11, "learning_rate": 2.5204556162181637e-06, "loss": 0.8216, "step": 133620 }, { "epoch": 11.11, "learning_rate": 2.5203447606906296e-06, "loss": 0.7826, "step": 133630 }, { "epoch": 11.11, "learning_rate": 2.5202339051630963e-06, "loss": 0.8061, "step": 133640 }, { "epoch": 11.11, "learning_rate": 2.5201230496355626e-06, "loss": 0.8113, "step": 133650 }, { "epoch": 11.11, "learning_rate": 2.5200121941080285e-06, "loss": 0.7956, "step": 133660 }, { "epoch": 11.11, "learning_rate": 2.519901338580495e-06, "loss": 0.8388, "step": 133670 }, { "epoch": 11.11, "learning_rate": 2.519790483052961e-06, "loss": 0.7324, "step": 133680 }, { "epoch": 11.11, "learning_rate": 2.5196796275254273e-06, "loss": 0.7664, "step": 133690 }, { "epoch": 11.11, "learning_rate": 2.5195687719978936e-06, "loss": 0.8506, "step": 133700 }, { "epoch": 11.11, "learning_rate": 2.51945791647036e-06, "loss": 0.7585, "step": 133710 }, { "epoch": 11.11, "learning_rate": 2.519347060942826e-06, "loss": 0.7429, "step": 133720 }, { "epoch": 11.12, "learning_rate": 2.5192362054152925e-06, "loss": 0.8146, "step": 133730 }, { "epoch": 11.12, "learning_rate": 2.5191253498877584e-06, "loss": 0.7235, "step": 133740 }, { "epoch": 11.12, "learning_rate": 2.519014494360225e-06, "loss": 0.8345, "step": 133750 }, { "epoch": 11.12, "learning_rate": 2.518903638832691e-06, "loss": 0.8125, "step": 133760 }, { "epoch": 11.12, "learning_rate": 2.5187927833051573e-06, "loss": 0.7577, "step": 133770 }, { "epoch": 11.12, "learning_rate": 2.518681927777624e-06, "loss": 0.7969, "step": 133780 }, { "epoch": 11.12, "learning_rate": 2.51857107225009e-06, "loss": 0.7649, "step": 133790 }, { "epoch": 11.12, "learning_rate": 2.518460216722556e-06, "loss": 0.8223, "step": 133800 }, { "epoch": 11.12, "learning_rate": 2.5183493611950225e-06, "loss": 0.7524, "step": 133810 }, { "epoch": 11.12, "learning_rate": 2.5182385056674888e-06, "loss": 0.7446, "step": 133820 }, { "epoch": 11.12, "learning_rate": 2.518127650139955e-06, "loss": 0.7406, "step": 133830 }, { "epoch": 11.12, "learning_rate": 2.5180167946124213e-06, "loss": 0.8689, "step": 133840 }, { "epoch": 11.13, "learning_rate": 2.5179059390848872e-06, "loss": 0.8419, "step": 133850 }, { "epoch": 11.13, "learning_rate": 2.517795083557354e-06, "loss": 0.7803, "step": 133860 }, { "epoch": 11.13, "learning_rate": 2.51768422802982e-06, "loss": 0.8914, "step": 133870 }, { "epoch": 11.13, "learning_rate": 2.517573372502286e-06, "loss": 0.7718, "step": 133880 }, { "epoch": 11.13, "learning_rate": 2.517462516974753e-06, "loss": 0.8497, "step": 133890 }, { "epoch": 11.13, "learning_rate": 2.5173516614472187e-06, "loss": 0.8513, "step": 133900 }, { "epoch": 11.13, "learning_rate": 2.5172408059196854e-06, "loss": 0.8695, "step": 133910 }, { "epoch": 11.13, "learning_rate": 2.5171299503921513e-06, "loss": 0.8183, "step": 133920 }, { "epoch": 11.13, "learning_rate": 2.5170190948646176e-06, "loss": 0.8009, "step": 133930 }, { "epoch": 11.13, "learning_rate": 2.516908239337084e-06, "loss": 0.8116, "step": 133940 }, { "epoch": 11.13, "learning_rate": 2.51679738380955e-06, "loss": 0.8461, "step": 133950 }, { "epoch": 11.13, "learning_rate": 2.516686528282016e-06, "loss": 0.8157, "step": 133960 }, { "epoch": 11.14, "learning_rate": 2.5165756727544828e-06, "loss": 0.6852, "step": 133970 }, { "epoch": 11.14, "learning_rate": 2.5164648172269486e-06, "loss": 0.8031, "step": 133980 }, { "epoch": 11.14, "learning_rate": 2.5163539616994154e-06, "loss": 0.7851, "step": 133990 }, { "epoch": 11.14, "learning_rate": 2.5162431061718812e-06, "loss": 0.8504, "step": 134000 }, { "epoch": 11.14, "learning_rate": 2.5161322506443475e-06, "loss": 0.7882, "step": 134010 }, { "epoch": 11.14, "learning_rate": 2.5160213951168142e-06, "loss": 0.7619, "step": 134020 }, { "epoch": 11.14, "learning_rate": 2.51591053958928e-06, "loss": 0.8137, "step": 134030 }, { "epoch": 11.14, "learning_rate": 2.5157996840617464e-06, "loss": 0.7539, "step": 134040 }, { "epoch": 11.14, "learning_rate": 2.5156888285342127e-06, "loss": 0.8675, "step": 134050 }, { "epoch": 11.14, "learning_rate": 2.515577973006679e-06, "loss": 0.7828, "step": 134060 }, { "epoch": 11.14, "learning_rate": 2.5154671174791453e-06, "loss": 0.8237, "step": 134070 }, { "epoch": 11.14, "learning_rate": 2.5153562619516116e-06, "loss": 0.7761, "step": 134080 }, { "epoch": 11.15, "learning_rate": 2.5152454064240775e-06, "loss": 0.797, "step": 134090 }, { "epoch": 11.15, "learning_rate": 2.515134550896544e-06, "loss": 0.848, "step": 134100 }, { "epoch": 11.15, "learning_rate": 2.51502369536901e-06, "loss": 0.7459, "step": 134110 }, { "epoch": 11.15, "learning_rate": 2.5149128398414763e-06, "loss": 0.7672, "step": 134120 }, { "epoch": 11.15, "learning_rate": 2.5148019843139426e-06, "loss": 0.7586, "step": 134130 }, { "epoch": 11.15, "learning_rate": 2.514691128786409e-06, "loss": 0.7365, "step": 134140 }, { "epoch": 11.15, "learning_rate": 2.5145802732588757e-06, "loss": 0.8051, "step": 134150 }, { "epoch": 11.15, "learning_rate": 2.5144694177313415e-06, "loss": 0.7565, "step": 134160 }, { "epoch": 11.15, "learning_rate": 2.514358562203808e-06, "loss": 0.7278, "step": 134170 }, { "epoch": 11.15, "learning_rate": 2.514247706676274e-06, "loss": 0.7865, "step": 134180 }, { "epoch": 11.15, "learning_rate": 2.5141368511487404e-06, "loss": 0.7832, "step": 134190 }, { "epoch": 11.15, "learning_rate": 2.5140259956212063e-06, "loss": 0.826, "step": 134200 }, { "epoch": 11.16, "learning_rate": 2.513915140093673e-06, "loss": 0.8251, "step": 134210 }, { "epoch": 11.16, "learning_rate": 2.513804284566139e-06, "loss": 0.7807, "step": 134220 }, { "epoch": 11.16, "learning_rate": 2.513693429038605e-06, "loss": 0.7918, "step": 134230 }, { "epoch": 11.16, "learning_rate": 2.5135825735110715e-06, "loss": 0.7917, "step": 134240 }, { "epoch": 11.16, "learning_rate": 2.5134717179835378e-06, "loss": 0.842, "step": 134250 }, { "epoch": 11.16, "learning_rate": 2.5133608624560045e-06, "loss": 0.7657, "step": 134260 }, { "epoch": 11.16, "learning_rate": 2.5132500069284704e-06, "loss": 0.8669, "step": 134270 }, { "epoch": 11.16, "learning_rate": 2.5131391514009366e-06, "loss": 0.7958, "step": 134280 }, { "epoch": 11.16, "learning_rate": 2.513028295873403e-06, "loss": 0.7885, "step": 134290 }, { "epoch": 11.16, "learning_rate": 2.5129174403458692e-06, "loss": 0.856, "step": 134300 }, { "epoch": 11.16, "learning_rate": 2.512806584818335e-06, "loss": 0.7668, "step": 134310 }, { "epoch": 11.16, "learning_rate": 2.512695729290802e-06, "loss": 0.791, "step": 134320 }, { "epoch": 11.17, "learning_rate": 2.5125848737632677e-06, "loss": 0.7569, "step": 134330 }, { "epoch": 11.17, "learning_rate": 2.5124740182357344e-06, "loss": 0.7927, "step": 134340 }, { "epoch": 11.17, "learning_rate": 2.5123631627082003e-06, "loss": 0.8198, "step": 134350 }, { "epoch": 11.17, "learning_rate": 2.5122523071806666e-06, "loss": 0.7651, "step": 134360 }, { "epoch": 11.17, "learning_rate": 2.512141451653133e-06, "loss": 0.7782, "step": 134370 }, { "epoch": 11.17, "learning_rate": 2.512030596125599e-06, "loss": 0.7332, "step": 134380 }, { "epoch": 11.17, "learning_rate": 2.5119197405980655e-06, "loss": 0.779, "step": 134390 }, { "epoch": 11.17, "learning_rate": 2.5118088850705318e-06, "loss": 0.7865, "step": 134400 }, { "epoch": 11.17, "learning_rate": 2.511698029542998e-06, "loss": 0.8045, "step": 134410 }, { "epoch": 11.17, "learning_rate": 2.5115871740154644e-06, "loss": 0.7265, "step": 134420 }, { "epoch": 11.17, "learning_rate": 2.5114763184879307e-06, "loss": 0.7894, "step": 134430 }, { "epoch": 11.17, "learning_rate": 2.5113654629603965e-06, "loss": 0.8156, "step": 134440 }, { "epoch": 11.18, "learning_rate": 2.5112546074328632e-06, "loss": 0.7558, "step": 134450 }, { "epoch": 11.18, "learning_rate": 2.511143751905329e-06, "loss": 0.7709, "step": 134460 }, { "epoch": 11.18, "learning_rate": 2.5110328963777954e-06, "loss": 0.8492, "step": 134470 }, { "epoch": 11.18, "learning_rate": 2.5109220408502617e-06, "loss": 0.7915, "step": 134480 }, { "epoch": 11.18, "learning_rate": 2.510811185322728e-06, "loss": 0.8225, "step": 134490 }, { "epoch": 11.18, "learning_rate": 2.510700329795194e-06, "loss": 0.8122, "step": 134500 }, { "epoch": 11.18, "learning_rate": 2.5105894742676606e-06, "loss": 0.8381, "step": 134510 }, { "epoch": 11.18, "learning_rate": 2.510478618740127e-06, "loss": 0.7024, "step": 134520 }, { "epoch": 11.18, "learning_rate": 2.510367763212593e-06, "loss": 0.7339, "step": 134530 }, { "epoch": 11.18, "learning_rate": 2.5102569076850595e-06, "loss": 0.6996, "step": 134540 }, { "epoch": 11.18, "learning_rate": 2.5101460521575254e-06, "loss": 0.8287, "step": 134550 }, { "epoch": 11.18, "learning_rate": 2.510035196629992e-06, "loss": 0.8305, "step": 134560 }, { "epoch": 11.19, "learning_rate": 2.509924341102458e-06, "loss": 0.7847, "step": 134570 }, { "epoch": 11.19, "learning_rate": 2.5098134855749247e-06, "loss": 0.7763, "step": 134580 }, { "epoch": 11.19, "learning_rate": 2.5097026300473905e-06, "loss": 0.7576, "step": 134590 }, { "epoch": 11.19, "learning_rate": 2.509591774519857e-06, "loss": 0.8052, "step": 134600 }, { "epoch": 11.19, "learning_rate": 2.509480918992323e-06, "loss": 0.8568, "step": 134610 }, { "epoch": 11.19, "learning_rate": 2.5093700634647894e-06, "loss": 0.8016, "step": 134620 }, { "epoch": 11.19, "learning_rate": 2.5092592079372557e-06, "loss": 0.8603, "step": 134630 }, { "epoch": 11.19, "learning_rate": 2.509148352409722e-06, "loss": 0.7143, "step": 134640 }, { "epoch": 11.19, "learning_rate": 2.5090374968821883e-06, "loss": 0.8301, "step": 134650 }, { "epoch": 11.19, "learning_rate": 2.508926641354654e-06, "loss": 0.7708, "step": 134660 }, { "epoch": 11.19, "learning_rate": 2.508815785827121e-06, "loss": 0.7851, "step": 134670 }, { "epoch": 11.19, "learning_rate": 2.5087049302995868e-06, "loss": 0.7782, "step": 134680 }, { "epoch": 11.2, "learning_rate": 2.5085940747720535e-06, "loss": 0.8022, "step": 134690 }, { "epoch": 11.2, "learning_rate": 2.5084832192445194e-06, "loss": 0.8404, "step": 134700 }, { "epoch": 11.2, "learning_rate": 2.5083723637169857e-06, "loss": 0.783, "step": 134710 }, { "epoch": 11.2, "learning_rate": 2.508261508189452e-06, "loss": 0.8265, "step": 134720 }, { "epoch": 11.2, "learning_rate": 2.5081506526619182e-06, "loss": 0.7698, "step": 134730 }, { "epoch": 11.2, "learning_rate": 2.508039797134384e-06, "loss": 0.8123, "step": 134740 }, { "epoch": 11.2, "learning_rate": 2.507928941606851e-06, "loss": 0.817, "step": 134750 }, { "epoch": 11.2, "learning_rate": 2.507818086079317e-06, "loss": 0.8298, "step": 134760 }, { "epoch": 11.2, "learning_rate": 2.5077072305517834e-06, "loss": 0.8524, "step": 134770 }, { "epoch": 11.2, "learning_rate": 2.5075963750242497e-06, "loss": 0.8035, "step": 134780 }, { "epoch": 11.2, "learning_rate": 2.5074855194967156e-06, "loss": 0.81, "step": 134790 }, { "epoch": 11.2, "learning_rate": 2.5073746639691823e-06, "loss": 0.8133, "step": 134800 }, { "epoch": 11.21, "learning_rate": 2.507263808441648e-06, "loss": 0.7846, "step": 134810 }, { "epoch": 11.21, "learning_rate": 2.5071529529141145e-06, "loss": 0.7625, "step": 134820 }, { "epoch": 11.21, "learning_rate": 2.5070420973865808e-06, "loss": 0.8055, "step": 134830 }, { "epoch": 11.21, "learning_rate": 2.506931241859047e-06, "loss": 0.7857, "step": 134840 }, { "epoch": 11.21, "learning_rate": 2.5068203863315134e-06, "loss": 0.8635, "step": 134850 }, { "epoch": 11.21, "learning_rate": 2.5067095308039797e-06, "loss": 0.7922, "step": 134860 }, { "epoch": 11.21, "learning_rate": 2.5065986752764455e-06, "loss": 0.7907, "step": 134870 }, { "epoch": 11.21, "learning_rate": 2.5064878197489122e-06, "loss": 0.7958, "step": 134880 }, { "epoch": 11.21, "learning_rate": 2.5063769642213785e-06, "loss": 0.7871, "step": 134890 }, { "epoch": 11.21, "learning_rate": 2.5062661086938444e-06, "loss": 0.8744, "step": 134900 }, { "epoch": 11.21, "learning_rate": 2.506155253166311e-06, "loss": 0.742, "step": 134910 }, { "epoch": 11.21, "learning_rate": 2.506044397638777e-06, "loss": 0.7361, "step": 134920 }, { "epoch": 11.22, "learning_rate": 2.5059335421112437e-06, "loss": 0.769, "step": 134930 }, { "epoch": 11.22, "learning_rate": 2.5058226865837096e-06, "loss": 0.7606, "step": 134940 }, { "epoch": 11.22, "learning_rate": 2.505711831056176e-06, "loss": 0.8171, "step": 134950 }, { "epoch": 11.22, "learning_rate": 2.505600975528642e-06, "loss": 0.7821, "step": 134960 }, { "epoch": 11.22, "learning_rate": 2.5054901200011085e-06, "loss": 0.7411, "step": 134970 }, { "epoch": 11.22, "learning_rate": 2.5053792644735744e-06, "loss": 0.7909, "step": 134980 }, { "epoch": 11.22, "learning_rate": 2.505268408946041e-06, "loss": 0.7359, "step": 134990 }, { "epoch": 11.22, "learning_rate": 2.5051575534185074e-06, "loss": 0.845, "step": 135000 }, { "epoch": 11.22, "learning_rate": 2.5050466978909732e-06, "loss": 0.735, "step": 135010 }, { "epoch": 11.22, "learning_rate": 2.50493584236344e-06, "loss": 0.7977, "step": 135020 }, { "epoch": 11.22, "learning_rate": 2.504824986835906e-06, "loss": 0.781, "step": 135030 }, { "epoch": 11.22, "learning_rate": 2.5047141313083726e-06, "loss": 0.7852, "step": 135040 }, { "epoch": 11.23, "learning_rate": 2.5046032757808384e-06, "loss": 0.8368, "step": 135050 }, { "epoch": 11.23, "learning_rate": 2.5044924202533047e-06, "loss": 0.8065, "step": 135060 }, { "epoch": 11.23, "learning_rate": 2.504381564725771e-06, "loss": 0.8573, "step": 135070 }, { "epoch": 11.23, "learning_rate": 2.5042707091982373e-06, "loss": 0.7441, "step": 135080 }, { "epoch": 11.23, "learning_rate": 2.504159853670703e-06, "loss": 0.8244, "step": 135090 }, { "epoch": 11.23, "learning_rate": 2.50404899814317e-06, "loss": 0.845, "step": 135100 }, { "epoch": 11.23, "learning_rate": 2.5039381426156358e-06, "loss": 0.7854, "step": 135110 }, { "epoch": 11.23, "learning_rate": 2.5038272870881025e-06, "loss": 0.7177, "step": 135120 }, { "epoch": 11.23, "learning_rate": 2.5037164315605688e-06, "loss": 0.8353, "step": 135130 }, { "epoch": 11.23, "learning_rate": 2.5036055760330347e-06, "loss": 0.7766, "step": 135140 }, { "epoch": 11.23, "learning_rate": 2.5034947205055014e-06, "loss": 0.7638, "step": 135150 }, { "epoch": 11.23, "learning_rate": 2.5033838649779672e-06, "loss": 0.8223, "step": 135160 }, { "epoch": 11.24, "learning_rate": 2.5032730094504335e-06, "loss": 0.7652, "step": 135170 }, { "epoch": 11.24, "learning_rate": 2.5031621539229e-06, "loss": 0.8391, "step": 135180 }, { "epoch": 11.24, "learning_rate": 2.503051298395366e-06, "loss": 0.7778, "step": 135190 }, { "epoch": 11.24, "learning_rate": 2.5029404428678324e-06, "loss": 0.8814, "step": 135200 }, { "epoch": 11.24, "learning_rate": 2.5028295873402987e-06, "loss": 0.7878, "step": 135210 }, { "epoch": 11.24, "learning_rate": 2.5027187318127646e-06, "loss": 0.7467, "step": 135220 }, { "epoch": 11.24, "learning_rate": 2.5026078762852313e-06, "loss": 0.8263, "step": 135230 }, { "epoch": 11.24, "learning_rate": 2.502497020757697e-06, "loss": 0.8017, "step": 135240 }, { "epoch": 11.24, "learning_rate": 2.5023861652301635e-06, "loss": 0.8348, "step": 135250 }, { "epoch": 11.24, "learning_rate": 2.50227530970263e-06, "loss": 0.7435, "step": 135260 }, { "epoch": 11.24, "learning_rate": 2.502164454175096e-06, "loss": 0.7615, "step": 135270 }, { "epoch": 11.24, "learning_rate": 2.502053598647563e-06, "loss": 0.7821, "step": 135280 }, { "epoch": 11.25, "learning_rate": 2.5019427431200287e-06, "loss": 0.7253, "step": 135290 }, { "epoch": 11.25, "learning_rate": 2.501831887592495e-06, "loss": 0.8533, "step": 135300 }, { "epoch": 11.25, "learning_rate": 2.5017210320649613e-06, "loss": 0.7738, "step": 135310 }, { "epoch": 11.25, "learning_rate": 2.5016101765374276e-06, "loss": 0.746, "step": 135320 }, { "epoch": 11.25, "learning_rate": 2.5014993210098934e-06, "loss": 0.8438, "step": 135330 }, { "epoch": 11.25, "learning_rate": 2.50138846548236e-06, "loss": 0.832, "step": 135340 }, { "epoch": 11.25, "learning_rate": 2.501277609954826e-06, "loss": 0.8171, "step": 135350 }, { "epoch": 11.25, "learning_rate": 2.5011667544272927e-06, "loss": 0.7734, "step": 135360 }, { "epoch": 11.25, "learning_rate": 2.501055898899759e-06, "loss": 0.8133, "step": 135370 }, { "epoch": 11.25, "learning_rate": 2.500945043372225e-06, "loss": 0.7773, "step": 135380 }, { "epoch": 11.25, "learning_rate": 2.5008341878446916e-06, "loss": 0.766, "step": 135390 }, { "epoch": 11.25, "learning_rate": 2.5007233323171575e-06, "loss": 0.8459, "step": 135400 }, { "epoch": 11.26, "learning_rate": 2.5006124767896238e-06, "loss": 0.8092, "step": 135410 }, { "epoch": 11.26, "learning_rate": 2.50050162126209e-06, "loss": 0.838, "step": 135420 }, { "epoch": 11.26, "learning_rate": 2.5003907657345564e-06, "loss": 0.7532, "step": 135430 }, { "epoch": 11.26, "learning_rate": 2.5002799102070222e-06, "loss": 0.8344, "step": 135440 }, { "epoch": 11.26, "learning_rate": 2.500169054679489e-06, "loss": 0.8111, "step": 135450 }, { "epoch": 11.26, "learning_rate": 2.500058199151955e-06, "loss": 0.7945, "step": 135460 }, { "epoch": 11.26, "learning_rate": 2.4999473436244216e-06, "loss": 0.7389, "step": 135470 }, { "epoch": 11.26, "learning_rate": 2.4998364880968874e-06, "loss": 0.7604, "step": 135480 }, { "epoch": 11.26, "learning_rate": 2.4997256325693537e-06, "loss": 0.7874, "step": 135490 }, { "epoch": 11.26, "learning_rate": 2.4996147770418204e-06, "loss": 0.8274, "step": 135500 }, { "epoch": 11.26, "learning_rate": 2.4995039215142863e-06, "loss": 0.866, "step": 135510 }, { "epoch": 11.26, "learning_rate": 2.4993930659867526e-06, "loss": 0.778, "step": 135520 }, { "epoch": 11.27, "learning_rate": 2.499282210459219e-06, "loss": 0.7175, "step": 135530 }, { "epoch": 11.27, "learning_rate": 2.499171354931685e-06, "loss": 0.8017, "step": 135540 }, { "epoch": 11.27, "learning_rate": 2.4990604994041515e-06, "loss": 0.8424, "step": 135550 }, { "epoch": 11.27, "learning_rate": 2.498949643876618e-06, "loss": 0.8494, "step": 135560 }, { "epoch": 11.27, "learning_rate": 2.4988387883490837e-06, "loss": 0.7907, "step": 135570 }, { "epoch": 11.27, "learning_rate": 2.4987279328215504e-06, "loss": 0.754, "step": 135580 }, { "epoch": 11.27, "learning_rate": 2.4986170772940163e-06, "loss": 0.7672, "step": 135590 }, { "epoch": 11.27, "learning_rate": 2.4985062217664825e-06, "loss": 0.8321, "step": 135600 }, { "epoch": 11.27, "learning_rate": 2.4983953662389493e-06, "loss": 0.8681, "step": 135610 }, { "epoch": 11.27, "learning_rate": 2.498284510711415e-06, "loss": 0.8157, "step": 135620 }, { "epoch": 11.27, "learning_rate": 2.498173655183882e-06, "loss": 0.8106, "step": 135630 }, { "epoch": 11.27, "learning_rate": 2.4980627996563477e-06, "loss": 0.7882, "step": 135640 }, { "epoch": 11.28, "learning_rate": 2.497951944128814e-06, "loss": 0.8137, "step": 135650 }, { "epoch": 11.28, "learning_rate": 2.4978410886012803e-06, "loss": 0.8297, "step": 135660 }, { "epoch": 11.28, "learning_rate": 2.4977302330737466e-06, "loss": 0.787, "step": 135670 }, { "epoch": 11.28, "learning_rate": 2.4976193775462125e-06, "loss": 0.7562, "step": 135680 }, { "epoch": 11.28, "learning_rate": 2.497508522018679e-06, "loss": 0.7989, "step": 135690 }, { "epoch": 11.28, "learning_rate": 2.497397666491145e-06, "loss": 0.7879, "step": 135700 }, { "epoch": 11.28, "learning_rate": 2.497286810963612e-06, "loss": 0.7895, "step": 135710 }, { "epoch": 11.28, "learning_rate": 2.4971759554360777e-06, "loss": 0.7867, "step": 135720 }, { "epoch": 11.28, "learning_rate": 2.497065099908544e-06, "loss": 0.7844, "step": 135730 }, { "epoch": 11.28, "learning_rate": 2.4969542443810107e-06, "loss": 0.8028, "step": 135740 }, { "epoch": 11.28, "learning_rate": 2.4968433888534766e-06, "loss": 0.8738, "step": 135750 }, { "epoch": 11.28, "learning_rate": 2.496732533325943e-06, "loss": 0.7724, "step": 135760 }, { "epoch": 11.29, "learning_rate": 2.496621677798409e-06, "loss": 0.7868, "step": 135770 }, { "epoch": 11.29, "learning_rate": 2.4965108222708754e-06, "loss": 0.8299, "step": 135780 }, { "epoch": 11.29, "learning_rate": 2.4963999667433413e-06, "loss": 0.7592, "step": 135790 }, { "epoch": 11.29, "learning_rate": 2.496289111215808e-06, "loss": 0.8609, "step": 135800 }, { "epoch": 11.29, "learning_rate": 2.496178255688274e-06, "loss": 0.7579, "step": 135810 }, { "epoch": 11.29, "learning_rate": 2.4960674001607406e-06, "loss": 0.8523, "step": 135820 }, { "epoch": 11.29, "learning_rate": 2.4959565446332065e-06, "loss": 0.793, "step": 135830 }, { "epoch": 11.29, "learning_rate": 2.495845689105673e-06, "loss": 0.7887, "step": 135840 }, { "epoch": 11.29, "learning_rate": 2.495734833578139e-06, "loss": 0.7986, "step": 135850 }, { "epoch": 11.29, "learning_rate": 2.4956239780506054e-06, "loss": 0.8297, "step": 135860 }, { "epoch": 11.29, "learning_rate": 2.495513122523072e-06, "loss": 0.7562, "step": 135870 }, { "epoch": 11.29, "learning_rate": 2.495402266995538e-06, "loss": 0.7505, "step": 135880 }, { "epoch": 11.29, "learning_rate": 2.4952914114680043e-06, "loss": 0.8131, "step": 135890 }, { "epoch": 11.3, "learning_rate": 2.4951805559404706e-06, "loss": 0.8142, "step": 135900 }, { "epoch": 11.3, "learning_rate": 2.495069700412937e-06, "loss": 0.8403, "step": 135910 }, { "epoch": 11.3, "learning_rate": 2.4949588448854027e-06, "loss": 0.7726, "step": 135920 }, { "epoch": 11.3, "learning_rate": 2.4948479893578694e-06, "loss": 0.7639, "step": 135930 }, { "epoch": 11.3, "learning_rate": 2.4947371338303353e-06, "loss": 0.6704, "step": 135940 }, { "epoch": 11.3, "learning_rate": 2.4946262783028016e-06, "loss": 0.8317, "step": 135950 }, { "epoch": 11.3, "learning_rate": 2.494515422775268e-06, "loss": 0.796, "step": 135960 }, { "epoch": 11.3, "learning_rate": 2.494404567247734e-06, "loss": 0.7763, "step": 135970 }, { "epoch": 11.3, "learning_rate": 2.494293711720201e-06, "loss": 0.898, "step": 135980 }, { "epoch": 11.3, "learning_rate": 2.494182856192667e-06, "loss": 0.7781, "step": 135990 }, { "epoch": 11.3, "learning_rate": 2.494072000665133e-06, "loss": 0.7829, "step": 136000 }, { "epoch": 11.3, "learning_rate": 2.4939611451375994e-06, "loss": 0.7503, "step": 136010 }, { "epoch": 11.31, "learning_rate": 2.4938502896100657e-06, "loss": 0.8192, "step": 136020 }, { "epoch": 11.31, "learning_rate": 2.4937394340825316e-06, "loss": 0.7752, "step": 136030 }, { "epoch": 11.31, "learning_rate": 2.4936285785549983e-06, "loss": 0.8364, "step": 136040 }, { "epoch": 11.31, "learning_rate": 2.493517723027464e-06, "loss": 0.8375, "step": 136050 }, { "epoch": 11.31, "learning_rate": 2.493406867499931e-06, "loss": 0.8182, "step": 136060 }, { "epoch": 11.31, "learning_rate": 2.4932960119723967e-06, "loss": 0.7613, "step": 136070 }, { "epoch": 11.31, "learning_rate": 2.493185156444863e-06, "loss": 0.7806, "step": 136080 }, { "epoch": 11.31, "learning_rate": 2.4930743009173293e-06, "loss": 0.78, "step": 136090 }, { "epoch": 11.31, "learning_rate": 2.4929634453897956e-06, "loss": 0.8329, "step": 136100 }, { "epoch": 11.31, "learning_rate": 2.492852589862262e-06, "loss": 0.733, "step": 136110 }, { "epoch": 11.31, "learning_rate": 2.4927417343347282e-06, "loss": 0.7409, "step": 136120 }, { "epoch": 11.31, "learning_rate": 2.4926308788071945e-06, "loss": 0.7751, "step": 136130 }, { "epoch": 11.32, "learning_rate": 2.492520023279661e-06, "loss": 0.7611, "step": 136140 }, { "epoch": 11.32, "learning_rate": 2.492409167752127e-06, "loss": 0.8432, "step": 136150 }, { "epoch": 11.32, "learning_rate": 2.492298312224593e-06, "loss": 0.7522, "step": 136160 }, { "epoch": 11.32, "learning_rate": 2.4921874566970597e-06, "loss": 0.8031, "step": 136170 }, { "epoch": 11.32, "learning_rate": 2.4920766011695256e-06, "loss": 0.7624, "step": 136180 }, { "epoch": 11.32, "learning_rate": 2.491965745641992e-06, "loss": 0.7985, "step": 136190 }, { "epoch": 11.32, "learning_rate": 2.491854890114458e-06, "loss": 0.801, "step": 136200 }, { "epoch": 11.32, "learning_rate": 2.4917440345869244e-06, "loss": 0.8254, "step": 136210 }, { "epoch": 11.32, "learning_rate": 2.4916331790593903e-06, "loss": 0.8242, "step": 136220 }, { "epoch": 11.32, "learning_rate": 2.491522323531857e-06, "loss": 0.7577, "step": 136230 }, { "epoch": 11.32, "learning_rate": 2.4914114680043233e-06, "loss": 0.8288, "step": 136240 }, { "epoch": 11.32, "learning_rate": 2.4913006124767896e-06, "loss": 0.8812, "step": 136250 }, { "epoch": 11.33, "learning_rate": 2.491189756949256e-06, "loss": 0.7645, "step": 136260 }, { "epoch": 11.33, "learning_rate": 2.491078901421722e-06, "loss": 0.7793, "step": 136270 }, { "epoch": 11.33, "learning_rate": 2.4909680458941885e-06, "loss": 0.7636, "step": 136280 }, { "epoch": 11.33, "learning_rate": 2.4908571903666544e-06, "loss": 0.7514, "step": 136290 }, { "epoch": 11.33, "learning_rate": 2.4907463348391207e-06, "loss": 0.8186, "step": 136300 }, { "epoch": 11.33, "learning_rate": 2.490635479311587e-06, "loss": 0.7787, "step": 136310 }, { "epoch": 11.33, "learning_rate": 2.4905246237840533e-06, "loss": 0.7914, "step": 136320 }, { "epoch": 11.33, "learning_rate": 2.4904137682565196e-06, "loss": 0.7434, "step": 136330 }, { "epoch": 11.33, "learning_rate": 2.490302912728986e-06, "loss": 0.8085, "step": 136340 }, { "epoch": 11.33, "learning_rate": 2.490192057201452e-06, "loss": 0.8482, "step": 136350 }, { "epoch": 11.33, "learning_rate": 2.4900812016739185e-06, "loss": 0.8438, "step": 136360 }, { "epoch": 11.33, "learning_rate": 2.4899703461463847e-06, "loss": 0.7733, "step": 136370 }, { "epoch": 11.34, "learning_rate": 2.4898594906188506e-06, "loss": 0.7755, "step": 136380 }, { "epoch": 11.34, "learning_rate": 2.4897486350913173e-06, "loss": 0.8449, "step": 136390 }, { "epoch": 11.34, "learning_rate": 2.4896377795637832e-06, "loss": 0.8107, "step": 136400 }, { "epoch": 11.34, "learning_rate": 2.48952692403625e-06, "loss": 0.8039, "step": 136410 }, { "epoch": 11.34, "learning_rate": 2.489416068508716e-06, "loss": 0.837, "step": 136420 }, { "epoch": 11.34, "learning_rate": 2.489305212981182e-06, "loss": 0.7491, "step": 136430 }, { "epoch": 11.34, "learning_rate": 2.4891943574536484e-06, "loss": 0.817, "step": 136440 }, { "epoch": 11.34, "learning_rate": 2.4890835019261147e-06, "loss": 0.8681, "step": 136450 }, { "epoch": 11.34, "learning_rate": 2.4889726463985806e-06, "loss": 0.7271, "step": 136460 }, { "epoch": 11.34, "learning_rate": 2.4888617908710473e-06, "loss": 0.7152, "step": 136470 }, { "epoch": 11.34, "learning_rate": 2.4887509353435136e-06, "loss": 0.7672, "step": 136480 }, { "epoch": 11.34, "learning_rate": 2.48864007981598e-06, "loss": 0.8191, "step": 136490 }, { "epoch": 11.35, "learning_rate": 2.488529224288446e-06, "loss": 0.8824, "step": 136500 }, { "epoch": 11.35, "learning_rate": 2.488418368760912e-06, "loss": 0.7846, "step": 136510 }, { "epoch": 11.35, "learning_rate": 2.4883075132333788e-06, "loss": 0.7773, "step": 136520 }, { "epoch": 11.35, "learning_rate": 2.4881966577058446e-06, "loss": 0.7681, "step": 136530 }, { "epoch": 11.35, "learning_rate": 2.488085802178311e-06, "loss": 0.7609, "step": 136540 }, { "epoch": 11.35, "learning_rate": 2.4879749466507772e-06, "loss": 0.8178, "step": 136550 }, { "epoch": 11.35, "learning_rate": 2.4878640911232435e-06, "loss": 0.7907, "step": 136560 }, { "epoch": 11.35, "learning_rate": 2.48775323559571e-06, "loss": 0.7454, "step": 136570 }, { "epoch": 11.35, "learning_rate": 2.487642380068176e-06, "loss": 0.821, "step": 136580 }, { "epoch": 11.35, "learning_rate": 2.487531524540642e-06, "loss": 0.793, "step": 136590 }, { "epoch": 11.35, "learning_rate": 2.4874206690131087e-06, "loss": 0.8119, "step": 136600 }, { "epoch": 11.35, "learning_rate": 2.487309813485575e-06, "loss": 0.7986, "step": 136610 }, { "epoch": 11.36, "learning_rate": 2.487198957958041e-06, "loss": 0.7141, "step": 136620 }, { "epoch": 11.36, "learning_rate": 2.4870881024305076e-06, "loss": 0.7993, "step": 136630 }, { "epoch": 11.36, "learning_rate": 2.4869772469029735e-06, "loss": 0.8266, "step": 136640 }, { "epoch": 11.36, "learning_rate": 2.48686639137544e-06, "loss": 0.8725, "step": 136650 }, { "epoch": 11.36, "learning_rate": 2.486755535847906e-06, "loss": 0.7803, "step": 136660 }, { "epoch": 11.36, "learning_rate": 2.4866446803203723e-06, "loss": 0.7888, "step": 136670 }, { "epoch": 11.36, "learning_rate": 2.4865338247928386e-06, "loss": 0.8089, "step": 136680 }, { "epoch": 11.36, "learning_rate": 2.486422969265305e-06, "loss": 0.7811, "step": 136690 }, { "epoch": 11.36, "learning_rate": 2.486312113737771e-06, "loss": 0.7885, "step": 136700 }, { "epoch": 11.36, "learning_rate": 2.4862012582102375e-06, "loss": 0.8172, "step": 136710 }, { "epoch": 11.36, "learning_rate": 2.486090402682704e-06, "loss": 0.8374, "step": 136720 }, { "epoch": 11.36, "learning_rate": 2.4859795471551697e-06, "loss": 0.7701, "step": 136730 }, { "epoch": 11.37, "learning_rate": 2.4858686916276364e-06, "loss": 0.8742, "step": 136740 }, { "epoch": 11.37, "learning_rate": 2.4857578361001023e-06, "loss": 0.836, "step": 136750 }, { "epoch": 11.37, "learning_rate": 2.485646980572569e-06, "loss": 0.7229, "step": 136760 }, { "epoch": 11.37, "learning_rate": 2.485536125045035e-06, "loss": 0.83, "step": 136770 }, { "epoch": 11.37, "learning_rate": 2.485425269517501e-06, "loss": 0.7269, "step": 136780 }, { "epoch": 11.37, "learning_rate": 2.4853144139899675e-06, "loss": 0.78, "step": 136790 }, { "epoch": 11.37, "learning_rate": 2.4852035584624338e-06, "loss": 0.9519, "step": 136800 }, { "epoch": 11.37, "learning_rate": 2.4850927029348996e-06, "loss": 0.7568, "step": 136810 }, { "epoch": 11.37, "learning_rate": 2.4849818474073663e-06, "loss": 0.7625, "step": 136820 }, { "epoch": 11.37, "learning_rate": 2.4848709918798322e-06, "loss": 0.7762, "step": 136830 }, { "epoch": 11.37, "learning_rate": 2.484760136352299e-06, "loss": 0.8144, "step": 136840 }, { "epoch": 11.37, "learning_rate": 2.4846492808247652e-06, "loss": 0.8639, "step": 136850 }, { "epoch": 11.38, "learning_rate": 2.484538425297231e-06, "loss": 0.7342, "step": 136860 }, { "epoch": 11.38, "learning_rate": 2.484427569769698e-06, "loss": 0.7718, "step": 136870 }, { "epoch": 11.38, "learning_rate": 2.4843167142421637e-06, "loss": 0.8184, "step": 136880 }, { "epoch": 11.38, "learning_rate": 2.48420585871463e-06, "loss": 0.7855, "step": 136890 }, { "epoch": 11.38, "learning_rate": 2.4840950031870963e-06, "loss": 0.8004, "step": 136900 }, { "epoch": 11.38, "learning_rate": 2.4839841476595626e-06, "loss": 0.7584, "step": 136910 }, { "epoch": 11.38, "learning_rate": 2.483873292132029e-06, "loss": 0.7872, "step": 136920 }, { "epoch": 11.38, "learning_rate": 2.483762436604495e-06, "loss": 0.795, "step": 136930 }, { "epoch": 11.38, "learning_rate": 2.483651581076961e-06, "loss": 0.8204, "step": 136940 }, { "epoch": 11.38, "learning_rate": 2.4835407255494278e-06, "loss": 0.8467, "step": 136950 }, { "epoch": 11.38, "learning_rate": 2.4834298700218936e-06, "loss": 0.8072, "step": 136960 }, { "epoch": 11.38, "learning_rate": 2.48331901449436e-06, "loss": 0.8513, "step": 136970 }, { "epoch": 11.39, "learning_rate": 2.4832081589668266e-06, "loss": 0.7486, "step": 136980 }, { "epoch": 11.39, "learning_rate": 2.4830973034392925e-06, "loss": 0.6794, "step": 136990 }, { "epoch": 11.39, "learning_rate": 2.4829864479117592e-06, "loss": 0.9317, "step": 137000 }, { "epoch": 11.39, "learning_rate": 2.482875592384225e-06, "loss": 0.8454, "step": 137010 }, { "epoch": 11.39, "learning_rate": 2.4827647368566914e-06, "loss": 0.7882, "step": 137020 }, { "epoch": 11.39, "learning_rate": 2.4826538813291577e-06, "loss": 0.7562, "step": 137030 }, { "epoch": 11.39, "learning_rate": 2.482543025801624e-06, "loss": 0.764, "step": 137040 }, { "epoch": 11.39, "learning_rate": 2.48243217027409e-06, "loss": 0.8124, "step": 137050 }, { "epoch": 11.39, "learning_rate": 2.4823213147465566e-06, "loss": 0.7576, "step": 137060 }, { "epoch": 11.39, "learning_rate": 2.4822104592190225e-06, "loss": 0.819, "step": 137070 }, { "epoch": 11.39, "learning_rate": 2.4820996036914888e-06, "loss": 0.7564, "step": 137080 }, { "epoch": 11.39, "learning_rate": 2.4819887481639555e-06, "loss": 0.7723, "step": 137090 }, { "epoch": 11.4, "learning_rate": 2.4818778926364213e-06, "loss": 0.8455, "step": 137100 }, { "epoch": 11.4, "learning_rate": 2.481767037108888e-06, "loss": 0.7597, "step": 137110 }, { "epoch": 11.4, "learning_rate": 2.481656181581354e-06, "loss": 0.8238, "step": 137120 }, { "epoch": 11.4, "learning_rate": 2.4815453260538202e-06, "loss": 0.7755, "step": 137130 }, { "epoch": 11.4, "learning_rate": 2.4814344705262865e-06, "loss": 0.7355, "step": 137140 }, { "epoch": 11.4, "learning_rate": 2.481323614998753e-06, "loss": 0.8531, "step": 137150 }, { "epoch": 11.4, "learning_rate": 2.4812127594712187e-06, "loss": 0.8067, "step": 137160 }, { "epoch": 11.4, "learning_rate": 2.4811019039436854e-06, "loss": 0.7678, "step": 137170 }, { "epoch": 11.4, "learning_rate": 2.4809910484161513e-06, "loss": 0.7879, "step": 137180 }, { "epoch": 11.4, "learning_rate": 2.4808912784413712e-06, "loss": 0.7274, "step": 137190 }, { "epoch": 11.4, "learning_rate": 2.4807804229138375e-06, "loss": 0.8953, "step": 137200 }, { "epoch": 11.4, "learning_rate": 2.480669567386304e-06, "loss": 0.8096, "step": 137210 }, { "epoch": 11.41, "learning_rate": 2.4805587118587697e-06, "loss": 0.7416, "step": 137220 }, { "epoch": 11.41, "learning_rate": 2.4804478563312364e-06, "loss": 0.7027, "step": 137230 }, { "epoch": 11.41, "learning_rate": 2.4803370008037023e-06, "loss": 0.778, "step": 137240 }, { "epoch": 11.41, "learning_rate": 2.4802261452761686e-06, "loss": 0.8454, "step": 137250 }, { "epoch": 11.41, "learning_rate": 2.480115289748635e-06, "loss": 0.8233, "step": 137260 }, { "epoch": 11.41, "learning_rate": 2.480004434221101e-06, "loss": 0.7821, "step": 137270 }, { "epoch": 11.41, "learning_rate": 2.4798935786935675e-06, "loss": 0.7625, "step": 137280 }, { "epoch": 11.41, "learning_rate": 2.4797827231660338e-06, "loss": 0.8111, "step": 137290 }, { "epoch": 11.41, "learning_rate": 2.4796718676385e-06, "loss": 0.8078, "step": 137300 }, { "epoch": 11.41, "learning_rate": 2.4795610121109664e-06, "loss": 0.7538, "step": 137310 }, { "epoch": 11.41, "learning_rate": 2.4794501565834327e-06, "loss": 0.8484, "step": 137320 }, { "epoch": 11.41, "learning_rate": 2.4793393010558985e-06, "loss": 0.7726, "step": 137330 }, { "epoch": 11.42, "learning_rate": 2.4792284455283653e-06, "loss": 0.7425, "step": 137340 }, { "epoch": 11.42, "learning_rate": 2.479117590000831e-06, "loss": 0.8081, "step": 137350 }, { "epoch": 11.42, "learning_rate": 2.479006734473298e-06, "loss": 0.7456, "step": 137360 }, { "epoch": 11.42, "learning_rate": 2.4788958789457637e-06, "loss": 0.7856, "step": 137370 }, { "epoch": 11.42, "learning_rate": 2.47878502341823e-06, "loss": 0.7678, "step": 137380 }, { "epoch": 11.42, "learning_rate": 2.4786741678906963e-06, "loss": 0.7406, "step": 137390 }, { "epoch": 11.42, "learning_rate": 2.4785633123631626e-06, "loss": 0.8779, "step": 137400 }, { "epoch": 11.42, "learning_rate": 2.4784524568356285e-06, "loss": 0.7571, "step": 137410 }, { "epoch": 11.42, "learning_rate": 2.478341601308095e-06, "loss": 0.7593, "step": 137420 }, { "epoch": 11.42, "learning_rate": 2.4782307457805615e-06, "loss": 0.7486, "step": 137430 }, { "epoch": 11.42, "learning_rate": 2.4781198902530278e-06, "loss": 0.77, "step": 137440 }, { "epoch": 11.42, "learning_rate": 2.478009034725494e-06, "loss": 0.8647, "step": 137450 }, { "epoch": 11.43, "learning_rate": 2.47789817919796e-06, "loss": 0.8269, "step": 137460 }, { "epoch": 11.43, "learning_rate": 2.4777873236704267e-06, "loss": 0.8281, "step": 137470 }, { "epoch": 11.43, "learning_rate": 2.4776764681428925e-06, "loss": 0.7884, "step": 137480 }, { "epoch": 11.43, "learning_rate": 2.477565612615359e-06, "loss": 0.7486, "step": 137490 }, { "epoch": 11.43, "learning_rate": 2.477454757087825e-06, "loss": 0.8667, "step": 137500 }, { "epoch": 11.43, "learning_rate": 2.4773439015602914e-06, "loss": 0.779, "step": 137510 }, { "epoch": 11.43, "learning_rate": 2.4772330460327577e-06, "loss": 0.7591, "step": 137520 }, { "epoch": 11.43, "learning_rate": 2.477122190505224e-06, "loss": 0.7919, "step": 137530 }, { "epoch": 11.43, "learning_rate": 2.47701133497769e-06, "loss": 0.7828, "step": 137540 }, { "epoch": 11.43, "learning_rate": 2.4769004794501566e-06, "loss": 0.8405, "step": 137550 }, { "epoch": 11.43, "learning_rate": 2.476789623922623e-06, "loss": 0.7791, "step": 137560 }, { "epoch": 11.43, "learning_rate": 2.4766787683950888e-06, "loss": 0.8093, "step": 137570 }, { "epoch": 11.44, "learning_rate": 2.4765679128675555e-06, "loss": 0.7489, "step": 137580 }, { "epoch": 11.44, "learning_rate": 2.4764570573400214e-06, "loss": 0.7423, "step": 137590 }, { "epoch": 11.44, "learning_rate": 2.476346201812488e-06, "loss": 0.8642, "step": 137600 }, { "epoch": 11.44, "learning_rate": 2.476235346284954e-06, "loss": 0.8758, "step": 137610 }, { "epoch": 11.44, "learning_rate": 2.4761244907574203e-06, "loss": 0.7949, "step": 137620 }, { "epoch": 11.44, "learning_rate": 2.4760136352298865e-06, "loss": 0.797, "step": 137630 }, { "epoch": 11.44, "learning_rate": 2.475902779702353e-06, "loss": 0.7548, "step": 137640 }, { "epoch": 11.44, "learning_rate": 2.4757919241748187e-06, "loss": 0.8741, "step": 137650 }, { "epoch": 11.44, "learning_rate": 2.4756810686472854e-06, "loss": 0.7898, "step": 137660 }, { "epoch": 11.44, "learning_rate": 2.4755702131197517e-06, "loss": 0.87, "step": 137670 }, { "epoch": 11.44, "learning_rate": 2.4754593575922176e-06, "loss": 0.819, "step": 137680 }, { "epoch": 11.44, "learning_rate": 2.4753485020646843e-06, "loss": 0.8068, "step": 137690 }, { "epoch": 11.45, "learning_rate": 2.47523764653715e-06, "loss": 0.807, "step": 137700 }, { "epoch": 11.45, "learning_rate": 2.475126791009617e-06, "loss": 0.8539, "step": 137710 }, { "epoch": 11.45, "learning_rate": 2.4750159354820828e-06, "loss": 0.8031, "step": 137720 }, { "epoch": 11.45, "learning_rate": 2.474905079954549e-06, "loss": 0.7436, "step": 137730 }, { "epoch": 11.45, "learning_rate": 2.4747942244270154e-06, "loss": 0.7843, "step": 137740 }, { "epoch": 11.45, "learning_rate": 2.4746833688994817e-06, "loss": 0.8799, "step": 137750 }, { "epoch": 11.45, "learning_rate": 2.474583598924701e-06, "loss": 0.8284, "step": 137760 }, { "epoch": 11.45, "learning_rate": 2.474472743397168e-06, "loss": 0.7495, "step": 137770 }, { "epoch": 11.45, "learning_rate": 2.474361887869634e-06, "loss": 0.8043, "step": 137780 }, { "epoch": 11.45, "learning_rate": 2.4742510323421e-06, "loss": 0.7852, "step": 137790 }, { "epoch": 11.45, "learning_rate": 2.4741401768145664e-06, "loss": 0.8234, "step": 137800 }, { "epoch": 11.45, "learning_rate": 2.4740293212870327e-06, "loss": 0.7385, "step": 137810 }, { "epoch": 11.46, "learning_rate": 2.4739184657594986e-06, "loss": 0.7724, "step": 137820 }, { "epoch": 11.46, "learning_rate": 2.4738076102319653e-06, "loss": 0.7627, "step": 137830 }, { "epoch": 11.46, "learning_rate": 2.473696754704431e-06, "loss": 0.8326, "step": 137840 }, { "epoch": 11.46, "learning_rate": 2.4735858991768974e-06, "loss": 0.8124, "step": 137850 }, { "epoch": 11.46, "learning_rate": 2.4734750436493637e-06, "loss": 0.7616, "step": 137860 }, { "epoch": 11.46, "learning_rate": 2.47336418812183e-06, "loss": 0.7692, "step": 137870 }, { "epoch": 11.46, "learning_rate": 2.4732533325942968e-06, "loss": 0.8087, "step": 137880 }, { "epoch": 11.46, "learning_rate": 2.4731424770667626e-06, "loss": 0.8036, "step": 137890 }, { "epoch": 11.46, "learning_rate": 2.473031621539229e-06, "loss": 0.8395, "step": 137900 }, { "epoch": 11.46, "learning_rate": 2.4729207660116952e-06, "loss": 0.7947, "step": 137910 }, { "epoch": 11.46, "learning_rate": 2.4728099104841615e-06, "loss": 0.7714, "step": 137920 }, { "epoch": 11.46, "learning_rate": 2.4726990549566274e-06, "loss": 0.8312, "step": 137930 }, { "epoch": 11.47, "learning_rate": 2.472588199429094e-06, "loss": 0.7806, "step": 137940 }, { "epoch": 11.47, "learning_rate": 2.47247734390156e-06, "loss": 0.8673, "step": 137950 }, { "epoch": 11.47, "learning_rate": 2.4723664883740267e-06, "loss": 0.7822, "step": 137960 }, { "epoch": 11.47, "learning_rate": 2.4722556328464926e-06, "loss": 0.7946, "step": 137970 }, { "epoch": 11.47, "learning_rate": 2.472144777318959e-06, "loss": 0.7961, "step": 137980 }, { "epoch": 11.47, "learning_rate": 2.472033921791425e-06, "loss": 0.767, "step": 137990 }, { "epoch": 11.47, "learning_rate": 2.4719230662638914e-06, "loss": 0.7663, "step": 138000 }, { "epoch": 11.47, "learning_rate": 2.4718122107363577e-06, "loss": 0.7257, "step": 138010 }, { "epoch": 11.47, "learning_rate": 2.471701355208824e-06, "loss": 0.7291, "step": 138020 }, { "epoch": 11.47, "learning_rate": 2.4715904996812903e-06, "loss": 0.7722, "step": 138030 }, { "epoch": 11.47, "learning_rate": 2.4714796441537566e-06, "loss": 0.81, "step": 138040 }, { "epoch": 11.47, "learning_rate": 2.471368788626223e-06, "loss": 0.8059, "step": 138050 }, { "epoch": 11.48, "learning_rate": 2.471257933098689e-06, "loss": 0.8255, "step": 138060 }, { "epoch": 11.48, "learning_rate": 2.4711470775711555e-06, "loss": 0.7863, "step": 138070 }, { "epoch": 11.48, "learning_rate": 2.4710362220436214e-06, "loss": 0.7974, "step": 138080 }, { "epoch": 11.48, "learning_rate": 2.4709253665160877e-06, "loss": 0.7567, "step": 138090 }, { "epoch": 11.48, "learning_rate": 2.470814510988554e-06, "loss": 0.7947, "step": 138100 }, { "epoch": 11.48, "learning_rate": 2.4707036554610203e-06, "loss": 0.7574, "step": 138110 }, { "epoch": 11.48, "learning_rate": 2.470592799933487e-06, "loss": 0.7986, "step": 138120 }, { "epoch": 11.48, "learning_rate": 2.470481944405953e-06, "loss": 0.7668, "step": 138130 }, { "epoch": 11.48, "learning_rate": 2.470371088878419e-06, "loss": 0.7169, "step": 138140 }, { "epoch": 11.48, "learning_rate": 2.4702602333508855e-06, "loss": 0.7816, "step": 138150 }, { "epoch": 11.48, "learning_rate": 2.4701493778233517e-06, "loss": 0.7788, "step": 138160 }, { "epoch": 11.48, "learning_rate": 2.4700385222958176e-06, "loss": 0.7899, "step": 138170 }, { "epoch": 11.49, "learning_rate": 2.4699276667682843e-06, "loss": 0.7302, "step": 138180 }, { "epoch": 11.49, "learning_rate": 2.46981681124075e-06, "loss": 0.7544, "step": 138190 }, { "epoch": 11.49, "learning_rate": 2.4697059557132165e-06, "loss": 0.8292, "step": 138200 }, { "epoch": 11.49, "learning_rate": 2.469595100185683e-06, "loss": 0.7963, "step": 138210 }, { "epoch": 11.49, "learning_rate": 2.469484244658149e-06, "loss": 0.7438, "step": 138220 }, { "epoch": 11.49, "learning_rate": 2.4693733891306154e-06, "loss": 0.7833, "step": 138230 }, { "epoch": 11.49, "learning_rate": 2.4692625336030817e-06, "loss": 0.7956, "step": 138240 }, { "epoch": 11.49, "learning_rate": 2.469151678075548e-06, "loss": 0.8357, "step": 138250 }, { "epoch": 11.49, "learning_rate": 2.4690408225480143e-06, "loss": 0.8353, "step": 138260 }, { "epoch": 11.49, "learning_rate": 2.4689299670204806e-06, "loss": 0.7788, "step": 138270 }, { "epoch": 11.49, "learning_rate": 2.4688191114929464e-06, "loss": 0.8124, "step": 138280 }, { "epoch": 11.49, "learning_rate": 2.468708255965413e-06, "loss": 0.7606, "step": 138290 }, { "epoch": 11.5, "learning_rate": 2.468597400437879e-06, "loss": 0.9341, "step": 138300 }, { "epoch": 11.5, "learning_rate": 2.4684865449103458e-06, "loss": 0.7883, "step": 138310 }, { "epoch": 11.5, "learning_rate": 2.4683756893828116e-06, "loss": 0.7831, "step": 138320 }, { "epoch": 11.5, "learning_rate": 2.468264833855278e-06, "loss": 0.7755, "step": 138330 }, { "epoch": 11.5, "learning_rate": 2.4681539783277442e-06, "loss": 0.8025, "step": 138340 }, { "epoch": 11.5, "learning_rate": 2.4680431228002105e-06, "loss": 0.8141, "step": 138350 }, { "epoch": 11.5, "learning_rate": 2.4679322672726764e-06, "loss": 0.7722, "step": 138360 }, { "epoch": 11.5, "learning_rate": 2.467821411745143e-06, "loss": 0.7616, "step": 138370 }, { "epoch": 11.5, "learning_rate": 2.4677105562176094e-06, "loss": 0.7597, "step": 138380 }, { "epoch": 11.5, "learning_rate": 2.4675997006900757e-06, "loss": 0.7552, "step": 138390 }, { "epoch": 11.5, "learning_rate": 2.467488845162542e-06, "loss": 0.8681, "step": 138400 }, { "epoch": 11.5, "learning_rate": 2.467377989635008e-06, "loss": 0.782, "step": 138410 }, { "epoch": 11.51, "learning_rate": 2.4672671341074746e-06, "loss": 0.7568, "step": 138420 }, { "epoch": 11.51, "learning_rate": 2.4671562785799405e-06, "loss": 0.8143, "step": 138430 }, { "epoch": 11.51, "learning_rate": 2.4670454230524067e-06, "loss": 0.7987, "step": 138440 }, { "epoch": 11.51, "learning_rate": 2.466934567524873e-06, "loss": 0.8815, "step": 138450 }, { "epoch": 11.51, "learning_rate": 2.4668237119973393e-06, "loss": 0.7555, "step": 138460 }, { "epoch": 11.51, "learning_rate": 2.4667128564698056e-06, "loss": 0.772, "step": 138470 }, { "epoch": 11.51, "learning_rate": 2.466602000942272e-06, "loss": 0.7929, "step": 138480 }, { "epoch": 11.51, "learning_rate": 2.4664911454147382e-06, "loss": 0.7912, "step": 138490 }, { "epoch": 11.51, "learning_rate": 2.4663802898872045e-06, "loss": 0.8873, "step": 138500 }, { "epoch": 11.51, "learning_rate": 2.466269434359671e-06, "loss": 0.7814, "step": 138510 }, { "epoch": 11.51, "learning_rate": 2.4661585788321367e-06, "loss": 0.7849, "step": 138520 }, { "epoch": 11.51, "learning_rate": 2.4660477233046034e-06, "loss": 0.8199, "step": 138530 }, { "epoch": 11.52, "learning_rate": 2.4659368677770693e-06, "loss": 0.8096, "step": 138540 }, { "epoch": 11.52, "learning_rate": 2.465826012249536e-06, "loss": 0.8074, "step": 138550 }, { "epoch": 11.52, "learning_rate": 2.465715156722002e-06, "loss": 0.8356, "step": 138560 }, { "epoch": 11.52, "learning_rate": 2.465604301194468e-06, "loss": 0.7881, "step": 138570 }, { "epoch": 11.52, "learning_rate": 2.4654934456669345e-06, "loss": 0.8029, "step": 138580 }, { "epoch": 11.52, "learning_rate": 2.4653825901394008e-06, "loss": 0.8319, "step": 138590 }, { "epoch": 11.52, "learning_rate": 2.4652717346118666e-06, "loss": 0.8713, "step": 138600 }, { "epoch": 11.52, "learning_rate": 2.4651608790843333e-06, "loss": 0.7818, "step": 138610 }, { "epoch": 11.52, "learning_rate": 2.4650500235567996e-06, "loss": 0.7492, "step": 138620 }, { "epoch": 11.52, "learning_rate": 2.4649391680292655e-06, "loss": 0.8065, "step": 138630 }, { "epoch": 11.52, "learning_rate": 2.4648283125017322e-06, "loss": 0.8039, "step": 138640 }, { "epoch": 11.52, "learning_rate": 2.464717456974198e-06, "loss": 0.7957, "step": 138650 }, { "epoch": 11.53, "learning_rate": 2.464606601446665e-06, "loss": 0.7994, "step": 138660 }, { "epoch": 11.53, "learning_rate": 2.4644957459191307e-06, "loss": 0.7811, "step": 138670 }, { "epoch": 11.53, "learning_rate": 2.464384890391597e-06, "loss": 0.7848, "step": 138680 }, { "epoch": 11.53, "learning_rate": 2.4642740348640633e-06, "loss": 0.7777, "step": 138690 }, { "epoch": 11.53, "learning_rate": 2.4641631793365296e-06, "loss": 0.82, "step": 138700 }, { "epoch": 11.53, "learning_rate": 2.4640523238089955e-06, "loss": 0.7886, "step": 138710 }, { "epoch": 11.53, "learning_rate": 2.463941468281462e-06, "loss": 0.7186, "step": 138720 }, { "epoch": 11.53, "learning_rate": 2.463830612753928e-06, "loss": 0.7363, "step": 138730 }, { "epoch": 11.53, "learning_rate": 2.4637197572263948e-06, "loss": 0.8418, "step": 138740 }, { "epoch": 11.53, "learning_rate": 2.463608901698861e-06, "loss": 0.8784, "step": 138750 }, { "epoch": 11.53, "learning_rate": 2.463498046171327e-06, "loss": 0.8322, "step": 138760 }, { "epoch": 11.53, "learning_rate": 2.4633871906437936e-06, "loss": 0.8017, "step": 138770 }, { "epoch": 11.54, "learning_rate": 2.4632763351162595e-06, "loss": 0.8038, "step": 138780 }, { "epoch": 11.54, "learning_rate": 2.463165479588726e-06, "loss": 0.7079, "step": 138790 }, { "epoch": 11.54, "learning_rate": 2.463054624061192e-06, "loss": 0.8228, "step": 138800 }, { "epoch": 11.54, "learning_rate": 2.4629437685336584e-06, "loss": 0.8047, "step": 138810 }, { "epoch": 11.54, "learning_rate": 2.4628329130061247e-06, "loss": 0.8291, "step": 138820 }, { "epoch": 11.54, "learning_rate": 2.462722057478591e-06, "loss": 0.7957, "step": 138830 }, { "epoch": 11.54, "learning_rate": 2.462611201951057e-06, "loss": 0.7265, "step": 138840 }, { "epoch": 11.54, "learning_rate": 2.4625003464235236e-06, "loss": 0.8179, "step": 138850 }, { "epoch": 11.54, "learning_rate": 2.46238949089599e-06, "loss": 0.7263, "step": 138860 }, { "epoch": 11.54, "learning_rate": 2.4622786353684558e-06, "loss": 0.6791, "step": 138870 }, { "epoch": 11.54, "learning_rate": 2.4621677798409225e-06, "loss": 0.82, "step": 138880 }, { "epoch": 11.54, "learning_rate": 2.4620569243133883e-06, "loss": 0.7594, "step": 138890 }, { "epoch": 11.55, "learning_rate": 2.461946068785855e-06, "loss": 0.8665, "step": 138900 }, { "epoch": 11.55, "learning_rate": 2.461835213258321e-06, "loss": 0.8418, "step": 138910 }, { "epoch": 11.55, "learning_rate": 2.4617243577307872e-06, "loss": 0.7695, "step": 138920 }, { "epoch": 11.55, "learning_rate": 2.4616135022032535e-06, "loss": 0.7948, "step": 138930 }, { "epoch": 11.55, "learning_rate": 2.46150264667572e-06, "loss": 0.7807, "step": 138940 }, { "epoch": 11.55, "learning_rate": 2.4613917911481857e-06, "loss": 0.8688, "step": 138950 }, { "epoch": 11.55, "learning_rate": 2.4612809356206524e-06, "loss": 0.7481, "step": 138960 }, { "epoch": 11.55, "learning_rate": 2.4611700800931183e-06, "loss": 0.8385, "step": 138970 }, { "epoch": 11.55, "learning_rate": 2.461059224565585e-06, "loss": 0.8209, "step": 138980 }, { "epoch": 11.55, "learning_rate": 2.4609483690380513e-06, "loss": 0.8089, "step": 138990 }, { "epoch": 11.55, "learning_rate": 2.460837513510517e-06, "loss": 0.847, "step": 139000 }, { "epoch": 11.55, "learning_rate": 2.460726657982984e-06, "loss": 0.817, "step": 139010 }, { "epoch": 11.56, "learning_rate": 2.4606158024554498e-06, "loss": 0.7653, "step": 139020 }, { "epoch": 11.56, "learning_rate": 2.460504946927916e-06, "loss": 0.795, "step": 139030 }, { "epoch": 11.56, "learning_rate": 2.4603940914003824e-06, "loss": 0.7669, "step": 139040 }, { "epoch": 11.56, "learning_rate": 2.4602832358728486e-06, "loss": 0.8439, "step": 139050 }, { "epoch": 11.56, "learning_rate": 2.4601723803453145e-06, "loss": 0.8309, "step": 139060 }, { "epoch": 11.56, "learning_rate": 2.4600615248177812e-06, "loss": 0.816, "step": 139070 }, { "epoch": 11.56, "learning_rate": 2.459950669290247e-06, "loss": 0.7901, "step": 139080 }, { "epoch": 11.56, "learning_rate": 2.459839813762714e-06, "loss": 0.7522, "step": 139090 }, { "epoch": 11.56, "learning_rate": 2.4597289582351797e-06, "loss": 0.8169, "step": 139100 }, { "epoch": 11.56, "learning_rate": 2.459618102707646e-06, "loss": 0.7405, "step": 139110 }, { "epoch": 11.56, "learning_rate": 2.4595072471801127e-06, "loss": 0.7667, "step": 139120 }, { "epoch": 11.56, "learning_rate": 2.4593963916525786e-06, "loss": 0.8397, "step": 139130 }, { "epoch": 11.57, "learning_rate": 2.459285536125045e-06, "loss": 0.8538, "step": 139140 }, { "epoch": 11.57, "learning_rate": 2.459174680597511e-06, "loss": 0.8191, "step": 139150 }, { "epoch": 11.57, "learning_rate": 2.4590638250699775e-06, "loss": 0.795, "step": 139160 }, { "epoch": 11.57, "learning_rate": 2.4589529695424438e-06, "loss": 0.7897, "step": 139170 }, { "epoch": 11.57, "learning_rate": 2.45884211401491e-06, "loss": 0.7772, "step": 139180 }, { "epoch": 11.57, "learning_rate": 2.458731258487376e-06, "loss": 0.8236, "step": 139190 }, { "epoch": 11.57, "learning_rate": 2.4586204029598427e-06, "loss": 0.8527, "step": 139200 }, { "epoch": 11.57, "learning_rate": 2.4585095474323085e-06, "loss": 0.8132, "step": 139210 }, { "epoch": 11.57, "learning_rate": 2.458398691904775e-06, "loss": 0.7276, "step": 139220 }, { "epoch": 11.57, "learning_rate": 2.4582878363772415e-06, "loss": 0.7454, "step": 139230 }, { "epoch": 11.57, "learning_rate": 2.4581769808497074e-06, "loss": 0.788, "step": 139240 }, { "epoch": 11.57, "learning_rate": 2.458066125322174e-06, "loss": 0.8728, "step": 139250 }, { "epoch": 11.58, "learning_rate": 2.45795526979464e-06, "loss": 0.8268, "step": 139260 }, { "epoch": 11.58, "learning_rate": 2.4578444142671063e-06, "loss": 0.7732, "step": 139270 }, { "epoch": 11.58, "learning_rate": 2.4577335587395726e-06, "loss": 0.8172, "step": 139280 }, { "epoch": 11.58, "learning_rate": 2.457622703212039e-06, "loss": 0.7683, "step": 139290 }, { "epoch": 11.58, "learning_rate": 2.4575118476845048e-06, "loss": 0.8086, "step": 139300 }, { "epoch": 11.58, "learning_rate": 2.4574009921569715e-06, "loss": 0.7693, "step": 139310 }, { "epoch": 11.58, "learning_rate": 2.4572901366294373e-06, "loss": 0.8098, "step": 139320 }, { "epoch": 11.58, "learning_rate": 2.457179281101904e-06, "loss": 0.8252, "step": 139330 }, { "epoch": 11.58, "learning_rate": 2.45706842557437e-06, "loss": 0.7403, "step": 139340 }, { "epoch": 11.58, "learning_rate": 2.4569575700468362e-06, "loss": 0.8476, "step": 139350 }, { "epoch": 11.58, "learning_rate": 2.456846714519303e-06, "loss": 0.842, "step": 139360 }, { "epoch": 11.58, "learning_rate": 2.456735858991769e-06, "loss": 0.7585, "step": 139370 }, { "epoch": 11.59, "learning_rate": 2.456625003464235e-06, "loss": 0.7713, "step": 139380 }, { "epoch": 11.59, "learning_rate": 2.4565141479367014e-06, "loss": 0.7528, "step": 139390 }, { "epoch": 11.59, "learning_rate": 2.4564032924091677e-06, "loss": 0.8089, "step": 139400 }, { "epoch": 11.59, "learning_rate": 2.4562924368816336e-06, "loss": 0.7551, "step": 139410 }, { "epoch": 11.59, "learning_rate": 2.4561815813541003e-06, "loss": 0.792, "step": 139420 }, { "epoch": 11.59, "learning_rate": 2.456070725826566e-06, "loss": 0.8064, "step": 139430 }, { "epoch": 11.59, "learning_rate": 2.455959870299033e-06, "loss": 0.7724, "step": 139440 }, { "epoch": 11.59, "learning_rate": 2.4558490147714988e-06, "loss": 0.8793, "step": 139450 }, { "epoch": 11.59, "learning_rate": 2.455738159243965e-06, "loss": 0.7639, "step": 139460 }, { "epoch": 11.59, "learning_rate": 2.4556273037164314e-06, "loss": 0.7982, "step": 139470 }, { "epoch": 11.59, "learning_rate": 2.4555164481888977e-06, "loss": 0.8181, "step": 139480 }, { "epoch": 11.59, "learning_rate": 2.455405592661364e-06, "loss": 0.7699, "step": 139490 }, { "epoch": 11.6, "learning_rate": 2.4552947371338302e-06, "loss": 0.8164, "step": 139500 }, { "epoch": 11.6, "learning_rate": 2.4551838816062965e-06, "loss": 0.8396, "step": 139510 }, { "epoch": 11.6, "learning_rate": 2.455073026078763e-06, "loss": 0.786, "step": 139520 }, { "epoch": 11.6, "learning_rate": 2.454962170551229e-06, "loss": 0.8106, "step": 139530 }, { "epoch": 11.6, "learning_rate": 2.454851315023695e-06, "loss": 0.783, "step": 139540 }, { "epoch": 11.6, "learning_rate": 2.4547404594961617e-06, "loss": 0.8277, "step": 139550 }, { "epoch": 11.6, "learning_rate": 2.4546296039686276e-06, "loss": 0.8071, "step": 139560 }, { "epoch": 11.6, "learning_rate": 2.454518748441094e-06, "loss": 0.7552, "step": 139570 }, { "epoch": 11.6, "learning_rate": 2.45440789291356e-06, "loss": 0.7934, "step": 139580 }, { "epoch": 11.6, "learning_rate": 2.4542970373860265e-06, "loss": 0.8421, "step": 139590 }, { "epoch": 11.6, "learning_rate": 2.454186181858493e-06, "loss": 0.8861, "step": 139600 }, { "epoch": 11.6, "learning_rate": 2.454075326330959e-06, "loss": 0.73, "step": 139610 }, { "epoch": 11.61, "learning_rate": 2.4539644708034254e-06, "loss": 0.763, "step": 139620 }, { "epoch": 11.61, "learning_rate": 2.4538536152758917e-06, "loss": 0.7299, "step": 139630 }, { "epoch": 11.61, "learning_rate": 2.453742759748358e-06, "loss": 0.7714, "step": 139640 }, { "epoch": 11.61, "learning_rate": 2.453631904220824e-06, "loss": 0.812, "step": 139650 }, { "epoch": 11.61, "learning_rate": 2.4535210486932905e-06, "loss": 0.7839, "step": 139660 }, { "epoch": 11.61, "learning_rate": 2.4534101931657564e-06, "loss": 0.7579, "step": 139670 }, { "epoch": 11.61, "learning_rate": 2.453299337638223e-06, "loss": 0.8513, "step": 139680 }, { "epoch": 11.61, "learning_rate": 2.453188482110689e-06, "loss": 0.8276, "step": 139690 }, { "epoch": 11.61, "learning_rate": 2.4530776265831553e-06, "loss": 0.7807, "step": 139700 }, { "epoch": 11.61, "learning_rate": 2.4529667710556216e-06, "loss": 0.7854, "step": 139710 }, { "epoch": 11.61, "learning_rate": 2.452855915528088e-06, "loss": 0.7646, "step": 139720 }, { "epoch": 11.61, "learning_rate": 2.452745060000554e-06, "loss": 0.779, "step": 139730 }, { "epoch": 11.61, "learning_rate": 2.4526342044730205e-06, "loss": 0.7667, "step": 139740 }, { "epoch": 11.62, "learning_rate": 2.4525233489454868e-06, "loss": 0.9, "step": 139750 }, { "epoch": 11.62, "learning_rate": 2.452412493417953e-06, "loss": 0.7917, "step": 139760 }, { "epoch": 11.62, "learning_rate": 2.4523016378904194e-06, "loss": 0.7413, "step": 139770 }, { "epoch": 11.62, "learning_rate": 2.4521907823628852e-06, "loss": 0.8168, "step": 139780 }, { "epoch": 11.62, "learning_rate": 2.452079926835352e-06, "loss": 0.7546, "step": 139790 }, { "epoch": 11.62, "learning_rate": 2.451969071307818e-06, "loss": 0.843, "step": 139800 }, { "epoch": 11.62, "learning_rate": 2.451858215780284e-06, "loss": 0.801, "step": 139810 }, { "epoch": 11.62, "learning_rate": 2.4517473602527504e-06, "loss": 0.7929, "step": 139820 }, { "epoch": 11.62, "learning_rate": 2.4516365047252167e-06, "loss": 0.7685, "step": 139830 }, { "epoch": 11.62, "learning_rate": 2.4515256491976826e-06, "loss": 0.8449, "step": 139840 }, { "epoch": 11.62, "learning_rate": 2.4514147936701493e-06, "loss": 0.8397, "step": 139850 }, { "epoch": 11.62, "learning_rate": 2.4513039381426156e-06, "loss": 0.7689, "step": 139860 }, { "epoch": 11.63, "learning_rate": 2.451193082615082e-06, "loss": 0.7925, "step": 139870 }, { "epoch": 11.63, "learning_rate": 2.451082227087548e-06, "loss": 0.7999, "step": 139880 }, { "epoch": 11.63, "learning_rate": 2.450971371560014e-06, "loss": 0.7699, "step": 139890 }, { "epoch": 11.63, "learning_rate": 2.4508605160324808e-06, "loss": 0.8249, "step": 139900 }, { "epoch": 11.63, "learning_rate": 2.4507496605049467e-06, "loss": 0.7897, "step": 139910 }, { "epoch": 11.63, "learning_rate": 2.450638804977413e-06, "loss": 0.8181, "step": 139920 }, { "epoch": 11.63, "learning_rate": 2.4505279494498792e-06, "loss": 0.8534, "step": 139930 }, { "epoch": 11.63, "learning_rate": 2.4504170939223455e-06, "loss": 0.8348, "step": 139940 }, { "epoch": 11.63, "learning_rate": 2.450306238394812e-06, "loss": 0.8359, "step": 139950 }, { "epoch": 11.63, "learning_rate": 2.450195382867278e-06, "loss": 0.7719, "step": 139960 }, { "epoch": 11.63, "learning_rate": 2.4500845273397444e-06, "loss": 0.7937, "step": 139970 }, { "epoch": 11.63, "learning_rate": 2.4499736718122107e-06, "loss": 0.8158, "step": 139980 }, { "epoch": 11.64, "learning_rate": 2.449862816284677e-06, "loss": 0.8199, "step": 139990 }, { "epoch": 11.64, "learning_rate": 2.449751960757143e-06, "loss": 0.8361, "step": 140000 }, { "epoch": 11.64, "learning_rate": 2.4496411052296096e-06, "loss": 0.7395, "step": 140010 }, { "epoch": 11.64, "learning_rate": 2.4495302497020755e-06, "loss": 0.8577, "step": 140020 }, { "epoch": 11.64, "learning_rate": 2.449419394174542e-06, "loss": 0.7621, "step": 140030 }, { "epoch": 11.64, "learning_rate": 2.449308538647008e-06, "loss": 0.8107, "step": 140040 }, { "epoch": 11.64, "learning_rate": 2.4491976831194744e-06, "loss": 0.8626, "step": 140050 }, { "epoch": 11.64, "learning_rate": 2.4490868275919407e-06, "loss": 0.7818, "step": 140060 }, { "epoch": 11.64, "learning_rate": 2.448975972064407e-06, "loss": 0.8211, "step": 140070 }, { "epoch": 11.64, "learning_rate": 2.448865116536873e-06, "loss": 0.7766, "step": 140080 }, { "epoch": 11.64, "learning_rate": 2.4487542610093395e-06, "loss": 0.7776, "step": 140090 }, { "epoch": 11.64, "learning_rate": 2.448643405481806e-06, "loss": 0.7788, "step": 140100 }, { "epoch": 11.65, "learning_rate": 2.448532549954272e-06, "loss": 0.8254, "step": 140110 }, { "epoch": 11.65, "learning_rate": 2.4484216944267384e-06, "loss": 0.824, "step": 140120 }, { "epoch": 11.65, "learning_rate": 2.4483108388992043e-06, "loss": 0.7628, "step": 140130 }, { "epoch": 11.65, "learning_rate": 2.448199983371671e-06, "loss": 0.7968, "step": 140140 }, { "epoch": 11.65, "learning_rate": 2.448089127844137e-06, "loss": 0.8579, "step": 140150 }, { "epoch": 11.65, "learning_rate": 2.447978272316603e-06, "loss": 0.8462, "step": 140160 }, { "epoch": 11.65, "learning_rate": 2.4478674167890695e-06, "loss": 0.8067, "step": 140170 }, { "epoch": 11.65, "learning_rate": 2.4477565612615358e-06, "loss": 0.7396, "step": 140180 }, { "epoch": 11.65, "learning_rate": 2.4476457057340017e-06, "loss": 0.7245, "step": 140190 }, { "epoch": 11.65, "learning_rate": 2.4475348502064684e-06, "loss": 0.8015, "step": 140200 }, { "epoch": 11.65, "learning_rate": 2.4474239946789347e-06, "loss": 0.7613, "step": 140210 }, { "epoch": 11.65, "learning_rate": 2.447313139151401e-06, "loss": 0.7529, "step": 140220 }, { "epoch": 11.66, "learning_rate": 2.4472022836238673e-06, "loss": 0.7938, "step": 140230 }, { "epoch": 11.66, "learning_rate": 2.447091428096333e-06, "loss": 0.8131, "step": 140240 }, { "epoch": 11.66, "learning_rate": 2.4469805725688e-06, "loss": 0.8584, "step": 140250 }, { "epoch": 11.66, "learning_rate": 2.4468697170412657e-06, "loss": 0.7845, "step": 140260 }, { "epoch": 11.66, "learning_rate": 2.4467588615137324e-06, "loss": 0.7756, "step": 140270 }, { "epoch": 11.66, "learning_rate": 2.4466480059861983e-06, "loss": 0.8243, "step": 140280 }, { "epoch": 11.66, "learning_rate": 2.4465371504586646e-06, "loss": 0.8167, "step": 140290 }, { "epoch": 11.66, "learning_rate": 2.446426294931131e-06, "loss": 0.8895, "step": 140300 }, { "epoch": 11.66, "learning_rate": 2.446315439403597e-06, "loss": 0.7649, "step": 140310 }, { "epoch": 11.66, "learning_rate": 2.446204583876063e-06, "loss": 0.7561, "step": 140320 }, { "epoch": 11.66, "learning_rate": 2.44609372834853e-06, "loss": 0.7961, "step": 140330 }, { "epoch": 11.66, "learning_rate": 2.445982872820996e-06, "loss": 0.7776, "step": 140340 }, { "epoch": 11.67, "learning_rate": 2.445872017293462e-06, "loss": 0.836, "step": 140350 }, { "epoch": 11.67, "learning_rate": 2.4457611617659287e-06, "loss": 0.805, "step": 140360 }, { "epoch": 11.67, "learning_rate": 2.4456503062383945e-06, "loss": 0.8294, "step": 140370 }, { "epoch": 11.67, "learning_rate": 2.4455394507108613e-06, "loss": 0.7698, "step": 140380 }, { "epoch": 11.67, "learning_rate": 2.445428595183327e-06, "loss": 0.8051, "step": 140390 }, { "epoch": 11.67, "learning_rate": 2.4453177396557934e-06, "loss": 0.7703, "step": 140400 }, { "epoch": 11.67, "learning_rate": 2.4452068841282597e-06, "loss": 0.7872, "step": 140410 }, { "epoch": 11.67, "learning_rate": 2.445096028600726e-06, "loss": 0.814, "step": 140420 }, { "epoch": 11.67, "learning_rate": 2.444985173073192e-06, "loss": 0.7425, "step": 140430 }, { "epoch": 11.67, "learning_rate": 2.4448743175456586e-06, "loss": 0.7853, "step": 140440 }, { "epoch": 11.67, "learning_rate": 2.4447634620181245e-06, "loss": 0.8381, "step": 140450 }, { "epoch": 11.67, "learning_rate": 2.444652606490591e-06, "loss": 0.7567, "step": 140460 }, { "epoch": 11.68, "learning_rate": 2.4445417509630575e-06, "loss": 0.8113, "step": 140470 }, { "epoch": 11.68, "learning_rate": 2.4444308954355234e-06, "loss": 0.8044, "step": 140480 }, { "epoch": 11.68, "learning_rate": 2.44432003990799e-06, "loss": 0.7648, "step": 140490 }, { "epoch": 11.68, "learning_rate": 2.444209184380456e-06, "loss": 0.8369, "step": 140500 }, { "epoch": 11.68, "learning_rate": 2.4440983288529223e-06, "loss": 0.7837, "step": 140510 }, { "epoch": 11.68, "learning_rate": 2.4439874733253886e-06, "loss": 0.7564, "step": 140520 }, { "epoch": 11.68, "learning_rate": 2.443876617797855e-06, "loss": 0.7913, "step": 140530 }, { "epoch": 11.68, "learning_rate": 2.443765762270321e-06, "loss": 0.7579, "step": 140540 }, { "epoch": 11.68, "learning_rate": 2.4436549067427874e-06, "loss": 0.7981, "step": 140550 }, { "epoch": 11.68, "learning_rate": 2.4435440512152533e-06, "loss": 0.7592, "step": 140560 }, { "epoch": 11.68, "learning_rate": 2.44343319568772e-06, "loss": 0.8585, "step": 140570 }, { "epoch": 11.68, "learning_rate": 2.4433223401601863e-06, "loss": 0.8224, "step": 140580 }, { "epoch": 11.69, "learning_rate": 2.443211484632652e-06, "loss": 0.7647, "step": 140590 }, { "epoch": 11.69, "learning_rate": 2.443100629105119e-06, "loss": 0.7948, "step": 140600 }, { "epoch": 11.69, "learning_rate": 2.442989773577585e-06, "loss": 0.8143, "step": 140610 }, { "epoch": 11.69, "learning_rate": 2.4428789180500515e-06, "loss": 0.8322, "step": 140620 }, { "epoch": 11.69, "learning_rate": 2.4427680625225174e-06, "loss": 0.7641, "step": 140630 }, { "epoch": 11.69, "learning_rate": 2.4426572069949837e-06, "loss": 0.8768, "step": 140640 }, { "epoch": 11.69, "learning_rate": 2.44254635146745e-06, "loss": 0.8189, "step": 140650 }, { "epoch": 11.69, "learning_rate": 2.4424354959399163e-06, "loss": 0.8239, "step": 140660 }, { "epoch": 11.69, "learning_rate": 2.442324640412382e-06, "loss": 0.8058, "step": 140670 }, { "epoch": 11.69, "learning_rate": 2.442213784884849e-06, "loss": 0.8064, "step": 140680 }, { "epoch": 11.69, "learning_rate": 2.4421029293573147e-06, "loss": 0.8291, "step": 140690 }, { "epoch": 11.69, "learning_rate": 2.441992073829781e-06, "loss": 0.8811, "step": 140700 }, { "epoch": 11.7, "learning_rate": 2.4418812183022477e-06, "loss": 0.7776, "step": 140710 }, { "epoch": 11.7, "learning_rate": 2.4417703627747136e-06, "loss": 0.7615, "step": 140720 }, { "epoch": 11.7, "learning_rate": 2.4416595072471803e-06, "loss": 0.8155, "step": 140730 }, { "epoch": 11.7, "learning_rate": 2.441548651719646e-06, "loss": 0.7792, "step": 140740 }, { "epoch": 11.7, "learning_rate": 2.4414377961921125e-06, "loss": 0.8301, "step": 140750 }, { "epoch": 11.7, "learning_rate": 2.441326940664579e-06, "loss": 0.757, "step": 140760 }, { "epoch": 11.7, "learning_rate": 2.441216085137045e-06, "loss": 0.791, "step": 140770 }, { "epoch": 11.7, "learning_rate": 2.441105229609511e-06, "loss": 0.7573, "step": 140780 }, { "epoch": 11.7, "learning_rate": 2.4409943740819777e-06, "loss": 0.7449, "step": 140790 }, { "epoch": 11.7, "learning_rate": 2.4408835185544436e-06, "loss": 0.8039, "step": 140800 }, { "epoch": 11.7, "learning_rate": 2.4407726630269103e-06, "loss": 0.7213, "step": 140810 }, { "epoch": 11.7, "learning_rate": 2.440661807499376e-06, "loss": 0.7575, "step": 140820 }, { "epoch": 11.71, "learning_rate": 2.4405509519718424e-06, "loss": 0.738, "step": 140830 }, { "epoch": 11.71, "learning_rate": 2.440440096444309e-06, "loss": 0.724, "step": 140840 }, { "epoch": 11.71, "learning_rate": 2.4403403264695287e-06, "loss": 0.8595, "step": 140850 }, { "epoch": 11.71, "learning_rate": 2.4402294709419946e-06, "loss": 0.7657, "step": 140860 }, { "epoch": 11.71, "learning_rate": 2.440118615414461e-06, "loss": 0.753, "step": 140870 }, { "epoch": 11.71, "learning_rate": 2.440007759886927e-06, "loss": 0.8671, "step": 140880 }, { "epoch": 11.71, "learning_rate": 2.4398969043593935e-06, "loss": 0.7642, "step": 140890 }, { "epoch": 11.71, "learning_rate": 2.4397860488318598e-06, "loss": 0.8168, "step": 140900 }, { "epoch": 11.71, "learning_rate": 2.439675193304326e-06, "loss": 0.742, "step": 140910 }, { "epoch": 11.71, "learning_rate": 2.4395643377767923e-06, "loss": 0.7645, "step": 140920 }, { "epoch": 11.71, "learning_rate": 2.4394534822492586e-06, "loss": 0.7844, "step": 140930 }, { "epoch": 11.71, "learning_rate": 2.439342626721725e-06, "loss": 0.7783, "step": 140940 }, { "epoch": 11.72, "learning_rate": 2.439231771194191e-06, "loss": 0.8057, "step": 140950 }, { "epoch": 11.72, "learning_rate": 2.4391209156666575e-06, "loss": 0.8093, "step": 140960 }, { "epoch": 11.72, "learning_rate": 2.4390100601391234e-06, "loss": 0.7433, "step": 140970 }, { "epoch": 11.72, "learning_rate": 2.43889920461159e-06, "loss": 0.7795, "step": 140980 }, { "epoch": 11.72, "learning_rate": 2.438788349084056e-06, "loss": 0.7442, "step": 140990 }, { "epoch": 11.72, "learning_rate": 2.4386774935565223e-06, "loss": 0.8199, "step": 141000 }, { "epoch": 11.72, "learning_rate": 2.4385666380289886e-06, "loss": 0.7651, "step": 141010 }, { "epoch": 11.72, "learning_rate": 2.438455782501455e-06, "loss": 0.7943, "step": 141020 }, { "epoch": 11.72, "learning_rate": 2.4383449269739207e-06, "loss": 0.7443, "step": 141030 }, { "epoch": 11.72, "learning_rate": 2.4382340714463875e-06, "loss": 0.8022, "step": 141040 }, { "epoch": 11.72, "learning_rate": 2.4381232159188538e-06, "loss": 0.867, "step": 141050 }, { "epoch": 11.72, "learning_rate": 2.43801236039132e-06, "loss": 0.8162, "step": 141060 }, { "epoch": 11.73, "learning_rate": 2.4379015048637863e-06, "loss": 0.8234, "step": 141070 }, { "epoch": 11.73, "learning_rate": 2.4377906493362522e-06, "loss": 0.8355, "step": 141080 }, { "epoch": 11.73, "learning_rate": 2.437679793808719e-06, "loss": 0.7568, "step": 141090 }, { "epoch": 11.73, "learning_rate": 2.437568938281185e-06, "loss": 0.8673, "step": 141100 }, { "epoch": 11.73, "learning_rate": 2.437458082753651e-06, "loss": 0.7453, "step": 141110 }, { "epoch": 11.73, "learning_rate": 2.4373472272261174e-06, "loss": 0.7637, "step": 141120 }, { "epoch": 11.73, "learning_rate": 2.4372363716985837e-06, "loss": 0.7658, "step": 141130 }, { "epoch": 11.73, "learning_rate": 2.4371255161710496e-06, "loss": 0.7768, "step": 141140 }, { "epoch": 11.73, "learning_rate": 2.4370146606435163e-06, "loss": 0.8687, "step": 141150 }, { "epoch": 11.73, "learning_rate": 2.4369038051159826e-06, "loss": 0.8527, "step": 141160 }, { "epoch": 11.73, "learning_rate": 2.436792949588449e-06, "loss": 0.7466, "step": 141170 }, { "epoch": 11.73, "learning_rate": 2.436682094060915e-06, "loss": 0.832, "step": 141180 }, { "epoch": 11.74, "learning_rate": 2.436571238533381e-06, "loss": 0.7833, "step": 141190 }, { "epoch": 11.74, "learning_rate": 2.4364603830058478e-06, "loss": 0.8142, "step": 141200 }, { "epoch": 11.74, "learning_rate": 2.4363495274783136e-06, "loss": 0.821, "step": 141210 }, { "epoch": 11.74, "learning_rate": 2.4362386719507804e-06, "loss": 0.8442, "step": 141220 }, { "epoch": 11.74, "learning_rate": 2.4361278164232462e-06, "loss": 0.7671, "step": 141230 }, { "epoch": 11.74, "learning_rate": 2.4360169608957125e-06, "loss": 0.8189, "step": 141240 }, { "epoch": 11.74, "learning_rate": 2.435906105368179e-06, "loss": 0.7932, "step": 141250 }, { "epoch": 11.74, "learning_rate": 2.435795249840645e-06, "loss": 0.8288, "step": 141260 }, { "epoch": 11.74, "learning_rate": 2.435684394313111e-06, "loss": 0.7531, "step": 141270 }, { "epoch": 11.74, "learning_rate": 2.4355735387855777e-06, "loss": 0.7499, "step": 141280 }, { "epoch": 11.74, "learning_rate": 2.435462683258044e-06, "loss": 0.748, "step": 141290 }, { "epoch": 11.74, "learning_rate": 2.43535182773051e-06, "loss": 0.8554, "step": 141300 }, { "epoch": 11.75, "learning_rate": 2.4352409722029766e-06, "loss": 0.8123, "step": 141310 }, { "epoch": 11.75, "learning_rate": 2.4351301166754425e-06, "loss": 0.8068, "step": 141320 }, { "epoch": 11.75, "learning_rate": 2.435019261147909e-06, "loss": 0.7697, "step": 141330 }, { "epoch": 11.75, "learning_rate": 2.434908405620375e-06, "loss": 0.8495, "step": 141340 }, { "epoch": 11.75, "learning_rate": 2.4347975500928413e-06, "loss": 0.7792, "step": 141350 }, { "epoch": 11.75, "learning_rate": 2.4346866945653076e-06, "loss": 0.7746, "step": 141360 }, { "epoch": 11.75, "learning_rate": 2.434575839037774e-06, "loss": 0.7898, "step": 141370 }, { "epoch": 11.75, "learning_rate": 2.43446498351024e-06, "loss": 0.7588, "step": 141380 }, { "epoch": 11.75, "learning_rate": 2.4343541279827065e-06, "loss": 0.8299, "step": 141390 }, { "epoch": 11.75, "learning_rate": 2.4342432724551724e-06, "loss": 0.8007, "step": 141400 }, { "epoch": 11.75, "learning_rate": 2.434132416927639e-06, "loss": 0.8543, "step": 141410 }, { "epoch": 11.75, "learning_rate": 2.4340215614001054e-06, "loss": 0.7729, "step": 141420 }, { "epoch": 11.76, "learning_rate": 2.4339107058725713e-06, "loss": 0.7727, "step": 141430 }, { "epoch": 11.76, "learning_rate": 2.433799850345038e-06, "loss": 0.7192, "step": 141440 }, { "epoch": 11.76, "learning_rate": 2.433688994817504e-06, "loss": 0.8183, "step": 141450 }, { "epoch": 11.76, "learning_rate": 2.43357813928997e-06, "loss": 0.8291, "step": 141460 }, { "epoch": 11.76, "learning_rate": 2.4334672837624365e-06, "loss": 0.7473, "step": 141470 }, { "epoch": 11.76, "learning_rate": 2.4333564282349028e-06, "loss": 0.8293, "step": 141480 }, { "epoch": 11.76, "learning_rate": 2.433245572707369e-06, "loss": 0.7663, "step": 141490 }, { "epoch": 11.76, "learning_rate": 2.4331347171798354e-06, "loss": 0.7971, "step": 141500 }, { "epoch": 11.76, "learning_rate": 2.4330238616523012e-06, "loss": 0.7679, "step": 141510 }, { "epoch": 11.76, "learning_rate": 2.432913006124768e-06, "loss": 0.7851, "step": 141520 }, { "epoch": 11.76, "learning_rate": 2.4328021505972342e-06, "loss": 0.7574, "step": 141530 }, { "epoch": 11.76, "learning_rate": 2.4326912950697e-06, "loss": 0.7724, "step": 141540 }, { "epoch": 11.77, "learning_rate": 2.432580439542167e-06, "loss": 0.8255, "step": 141550 }, { "epoch": 11.77, "learning_rate": 2.4324695840146327e-06, "loss": 0.802, "step": 141560 }, { "epoch": 11.77, "learning_rate": 2.4323587284870994e-06, "loss": 0.7561, "step": 141570 }, { "epoch": 11.77, "learning_rate": 2.4322478729595653e-06, "loss": 0.7612, "step": 141580 }, { "epoch": 11.77, "learning_rate": 2.4321370174320316e-06, "loss": 0.8369, "step": 141590 }, { "epoch": 11.77, "learning_rate": 2.432026161904498e-06, "loss": 0.811, "step": 141600 }, { "epoch": 11.77, "learning_rate": 2.431915306376964e-06, "loss": 0.7587, "step": 141610 }, { "epoch": 11.77, "learning_rate": 2.43180445084943e-06, "loss": 0.7602, "step": 141620 }, { "epoch": 11.77, "learning_rate": 2.4316935953218968e-06, "loss": 0.7681, "step": 141630 }, { "epoch": 11.77, "learning_rate": 2.4315827397943626e-06, "loss": 0.8063, "step": 141640 }, { "epoch": 11.77, "learning_rate": 2.431471884266829e-06, "loss": 0.8574, "step": 141650 }, { "epoch": 11.77, "learning_rate": 2.4313610287392957e-06, "loss": 0.8009, "step": 141660 }, { "epoch": 11.78, "learning_rate": 2.4312501732117615e-06, "loss": 0.8244, "step": 141670 }, { "epoch": 11.78, "learning_rate": 2.4311393176842282e-06, "loss": 0.7397, "step": 141680 }, { "epoch": 11.78, "learning_rate": 2.431028462156694e-06, "loss": 0.7944, "step": 141690 }, { "epoch": 11.78, "learning_rate": 2.4309176066291604e-06, "loss": 0.7954, "step": 141700 }, { "epoch": 11.78, "learning_rate": 2.4308067511016267e-06, "loss": 0.8002, "step": 141710 }, { "epoch": 11.78, "learning_rate": 2.430695895574093e-06, "loss": 0.855, "step": 141720 }, { "epoch": 11.78, "learning_rate": 2.430585040046559e-06, "loss": 0.7375, "step": 141730 }, { "epoch": 11.78, "learning_rate": 2.4304741845190256e-06, "loss": 0.77, "step": 141740 }, { "epoch": 11.78, "learning_rate": 2.4303633289914915e-06, "loss": 0.827, "step": 141750 }, { "epoch": 11.78, "learning_rate": 2.430252473463958e-06, "loss": 0.8328, "step": 141760 }, { "epoch": 11.78, "learning_rate": 2.430141617936424e-06, "loss": 0.722, "step": 141770 }, { "epoch": 11.78, "learning_rate": 2.4300307624088904e-06, "loss": 0.8077, "step": 141780 }, { "epoch": 11.79, "learning_rate": 2.429919906881357e-06, "loss": 0.7677, "step": 141790 }, { "epoch": 11.79, "learning_rate": 2.429809051353823e-06, "loss": 0.7725, "step": 141800 }, { "epoch": 11.79, "learning_rate": 2.4296981958262892e-06, "loss": 0.7606, "step": 141810 }, { "epoch": 11.79, "learning_rate": 2.4295873402987555e-06, "loss": 0.7539, "step": 141820 }, { "epoch": 11.79, "learning_rate": 2.429476484771222e-06, "loss": 0.7238, "step": 141830 }, { "epoch": 11.79, "learning_rate": 2.429365629243688e-06, "loss": 0.8294, "step": 141840 }, { "epoch": 11.79, "learning_rate": 2.4292547737161544e-06, "loss": 0.8965, "step": 141850 }, { "epoch": 11.79, "learning_rate": 2.4291439181886203e-06, "loss": 0.7607, "step": 141860 }, { "epoch": 11.79, "learning_rate": 2.429033062661087e-06, "loss": 0.8348, "step": 141870 }, { "epoch": 11.79, "learning_rate": 2.428922207133553e-06, "loss": 0.8777, "step": 141880 }, { "epoch": 11.79, "learning_rate": 2.428811351606019e-06, "loss": 0.7994, "step": 141890 }, { "epoch": 11.79, "learning_rate": 2.428700496078486e-06, "loss": 0.8787, "step": 141900 }, { "epoch": 11.8, "learning_rate": 2.4285896405509518e-06, "loss": 0.7871, "step": 141910 }, { "epoch": 11.8, "learning_rate": 2.4284787850234185e-06, "loss": 0.6795, "step": 141920 }, { "epoch": 11.8, "learning_rate": 2.4283679294958844e-06, "loss": 0.8356, "step": 141930 }, { "epoch": 11.8, "learning_rate": 2.4282570739683507e-06, "loss": 0.7872, "step": 141940 }, { "epoch": 11.8, "learning_rate": 2.428146218440817e-06, "loss": 0.8329, "step": 141950 }, { "epoch": 11.8, "learning_rate": 2.4280353629132832e-06, "loss": 0.7839, "step": 141960 }, { "epoch": 11.8, "learning_rate": 2.427924507385749e-06, "loss": 0.8683, "step": 141970 }, { "epoch": 11.8, "learning_rate": 2.427813651858216e-06, "loss": 0.7846, "step": 141980 }, { "epoch": 11.8, "learning_rate": 2.4277027963306817e-06, "loss": 0.7449, "step": 141990 }, { "epoch": 11.8, "learning_rate": 2.4275919408031484e-06, "loss": 0.8375, "step": 142000 }, { "epoch": 11.8, "learning_rate": 2.4274810852756143e-06, "loss": 0.7605, "step": 142010 }, { "epoch": 11.8, "learning_rate": 2.4273702297480806e-06, "loss": 0.7642, "step": 142020 }, { "epoch": 11.81, "learning_rate": 2.4272593742205473e-06, "loss": 0.7942, "step": 142030 }, { "epoch": 11.81, "learning_rate": 2.427148518693013e-06, "loss": 0.8099, "step": 142040 }, { "epoch": 11.81, "learning_rate": 2.4270376631654795e-06, "loss": 0.8354, "step": 142050 }, { "epoch": 11.81, "learning_rate": 2.4269268076379458e-06, "loss": 0.7887, "step": 142060 }, { "epoch": 11.81, "learning_rate": 2.426815952110412e-06, "loss": 0.737, "step": 142070 }, { "epoch": 11.81, "learning_rate": 2.426705096582878e-06, "loss": 0.7873, "step": 142080 }, { "epoch": 11.81, "learning_rate": 2.4265942410553447e-06, "loss": 0.8184, "step": 142090 }, { "epoch": 11.81, "learning_rate": 2.4264833855278105e-06, "loss": 0.8324, "step": 142100 }, { "epoch": 11.81, "learning_rate": 2.4263725300002773e-06, "loss": 0.8045, "step": 142110 }, { "epoch": 11.81, "learning_rate": 2.426261674472743e-06, "loss": 0.8045, "step": 142120 }, { "epoch": 11.81, "learning_rate": 2.4261508189452094e-06, "loss": 0.7939, "step": 142130 }, { "epoch": 11.81, "learning_rate": 2.4260399634176757e-06, "loss": 0.7179, "step": 142140 }, { "epoch": 11.82, "learning_rate": 2.425929107890142e-06, "loss": 0.784, "step": 142150 }, { "epoch": 11.82, "learning_rate": 2.4258182523626083e-06, "loss": 0.7723, "step": 142160 }, { "epoch": 11.82, "learning_rate": 2.4257073968350746e-06, "loss": 0.7522, "step": 142170 }, { "epoch": 11.82, "learning_rate": 2.425596541307541e-06, "loss": 0.8299, "step": 142180 }, { "epoch": 11.82, "learning_rate": 2.425485685780007e-06, "loss": 0.7589, "step": 142190 }, { "epoch": 11.82, "learning_rate": 2.4253748302524735e-06, "loss": 0.8525, "step": 142200 }, { "epoch": 11.82, "learning_rate": 2.4252639747249394e-06, "loss": 0.8575, "step": 142210 }, { "epoch": 11.82, "learning_rate": 2.425153119197406e-06, "loss": 0.7605, "step": 142220 }, { "epoch": 11.82, "learning_rate": 2.425042263669872e-06, "loss": 0.7934, "step": 142230 }, { "epoch": 11.82, "learning_rate": 2.4249314081423382e-06, "loss": 0.758, "step": 142240 }, { "epoch": 11.82, "learning_rate": 2.4248205526148045e-06, "loss": 0.8262, "step": 142250 }, { "epoch": 11.82, "learning_rate": 2.424709697087271e-06, "loss": 0.8058, "step": 142260 }, { "epoch": 11.83, "learning_rate": 2.4245988415597376e-06, "loss": 0.8308, "step": 142270 }, { "epoch": 11.83, "learning_rate": 2.4244879860322034e-06, "loss": 0.8603, "step": 142280 }, { "epoch": 11.83, "learning_rate": 2.4243771305046697e-06, "loss": 0.7673, "step": 142290 }, { "epoch": 11.83, "learning_rate": 2.424266274977136e-06, "loss": 0.7898, "step": 142300 }, { "epoch": 11.83, "learning_rate": 2.4241554194496023e-06, "loss": 0.8386, "step": 142310 }, { "epoch": 11.83, "learning_rate": 2.424044563922068e-06, "loss": 0.7308, "step": 142320 }, { "epoch": 11.83, "learning_rate": 2.423933708394535e-06, "loss": 0.7622, "step": 142330 }, { "epoch": 11.83, "learning_rate": 2.4238228528670008e-06, "loss": 0.7948, "step": 142340 }, { "epoch": 11.83, "learning_rate": 2.4237119973394675e-06, "loss": 0.8637, "step": 142350 }, { "epoch": 11.83, "learning_rate": 2.4236011418119334e-06, "loss": 0.7779, "step": 142360 }, { "epoch": 11.83, "learning_rate": 2.4234902862843997e-06, "loss": 0.807, "step": 142370 }, { "epoch": 11.83, "learning_rate": 2.423379430756866e-06, "loss": 0.772, "step": 142380 }, { "epoch": 11.84, "learning_rate": 2.4232685752293323e-06, "loss": 0.8031, "step": 142390 }, { "epoch": 11.84, "learning_rate": 2.4231577197017985e-06, "loss": 0.7836, "step": 142400 }, { "epoch": 11.84, "learning_rate": 2.423046864174265e-06, "loss": 0.8065, "step": 142410 }, { "epoch": 11.84, "learning_rate": 2.422936008646731e-06, "loss": 0.7332, "step": 142420 }, { "epoch": 11.84, "learning_rate": 2.422825153119197e-06, "loss": 0.794, "step": 142430 }, { "epoch": 11.84, "learning_rate": 2.4227142975916637e-06, "loss": 0.8231, "step": 142440 }, { "epoch": 11.84, "learning_rate": 2.4226034420641296e-06, "loss": 0.8387, "step": 142450 }, { "epoch": 11.84, "learning_rate": 2.4224925865365963e-06, "loss": 0.7844, "step": 142460 }, { "epoch": 11.84, "learning_rate": 2.422381731009062e-06, "loss": 0.7552, "step": 142470 }, { "epoch": 11.84, "learning_rate": 2.4222708754815285e-06, "loss": 0.8309, "step": 142480 }, { "epoch": 11.84, "learning_rate": 2.4221600199539948e-06, "loss": 0.8138, "step": 142490 }, { "epoch": 11.84, "learning_rate": 2.422049164426461e-06, "loss": 0.8136, "step": 142500 }, { "epoch": 11.85, "learning_rate": 2.421938308898928e-06, "loss": 0.7903, "step": 142510 }, { "epoch": 11.85, "learning_rate": 2.4218274533713937e-06, "loss": 0.7607, "step": 142520 }, { "epoch": 11.85, "learning_rate": 2.42171659784386e-06, "loss": 0.7623, "step": 142530 }, { "epoch": 11.85, "learning_rate": 2.4216057423163263e-06, "loss": 0.8153, "step": 142540 }, { "epoch": 11.85, "learning_rate": 2.4214948867887926e-06, "loss": 0.8775, "step": 142550 }, { "epoch": 11.85, "learning_rate": 2.4213840312612584e-06, "loss": 0.7556, "step": 142560 }, { "epoch": 11.85, "learning_rate": 2.421273175733725e-06, "loss": 0.8202, "step": 142570 }, { "epoch": 11.85, "learning_rate": 2.421162320206191e-06, "loss": 0.7939, "step": 142580 }, { "epoch": 11.85, "learning_rate": 2.4210514646786573e-06, "loss": 0.7511, "step": 142590 }, { "epoch": 11.85, "learning_rate": 2.4209406091511236e-06, "loss": 0.8239, "step": 142600 }, { "epoch": 11.85, "learning_rate": 2.42082975362359e-06, "loss": 0.7521, "step": 142610 }, { "epoch": 11.85, "learning_rate": 2.420718898096056e-06, "loss": 0.7389, "step": 142620 }, { "epoch": 11.86, "learning_rate": 2.4206080425685225e-06, "loss": 0.8021, "step": 142630 }, { "epoch": 11.86, "learning_rate": 2.4204971870409888e-06, "loss": 0.8266, "step": 142640 }, { "epoch": 11.86, "learning_rate": 2.420386331513455e-06, "loss": 0.8628, "step": 142650 }, { "epoch": 11.86, "learning_rate": 2.4202754759859214e-06, "loss": 0.7741, "step": 142660 }, { "epoch": 11.86, "learning_rate": 2.4201646204583872e-06, "loss": 0.7558, "step": 142670 }, { "epoch": 11.86, "learning_rate": 2.420053764930854e-06, "loss": 0.7739, "step": 142680 }, { "epoch": 11.86, "learning_rate": 2.41994290940332e-06, "loss": 0.779, "step": 142690 }, { "epoch": 11.86, "learning_rate": 2.4198320538757866e-06, "loss": 0.7877, "step": 142700 }, { "epoch": 11.86, "learning_rate": 2.4197211983482524e-06, "loss": 0.8154, "step": 142710 }, { "epoch": 11.86, "learning_rate": 2.4196103428207187e-06, "loss": 0.7657, "step": 142720 }, { "epoch": 11.86, "learning_rate": 2.419499487293185e-06, "loss": 0.734, "step": 142730 }, { "epoch": 11.86, "learning_rate": 2.4193886317656513e-06, "loss": 0.8652, "step": 142740 }, { "epoch": 11.87, "learning_rate": 2.419277776238117e-06, "loss": 0.8755, "step": 142750 }, { "epoch": 11.87, "learning_rate": 2.419166920710584e-06, "loss": 0.7379, "step": 142760 }, { "epoch": 11.87, "learning_rate": 2.41905606518305e-06, "loss": 0.7824, "step": 142770 }, { "epoch": 11.87, "learning_rate": 2.4189452096555165e-06, "loss": 0.7626, "step": 142780 }, { "epoch": 11.87, "learning_rate": 2.418834354127983e-06, "loss": 0.7831, "step": 142790 }, { "epoch": 11.87, "learning_rate": 2.4187234986004487e-06, "loss": 0.8526, "step": 142800 }, { "epoch": 11.87, "learning_rate": 2.4186126430729154e-06, "loss": 0.7967, "step": 142810 }, { "epoch": 11.87, "learning_rate": 2.4185017875453813e-06, "loss": 0.7892, "step": 142820 }, { "epoch": 11.87, "learning_rate": 2.4183909320178476e-06, "loss": 0.8639, "step": 142830 }, { "epoch": 11.87, "learning_rate": 2.418280076490314e-06, "loss": 0.7668, "step": 142840 }, { "epoch": 11.87, "learning_rate": 2.41816922096278e-06, "loss": 0.811, "step": 142850 }, { "epoch": 11.87, "learning_rate": 2.418058365435246e-06, "loss": 0.8468, "step": 142860 }, { "epoch": 11.88, "learning_rate": 2.4179585954604664e-06, "loss": 0.7228, "step": 142870 }, { "epoch": 11.88, "learning_rate": 2.4178477399329323e-06, "loss": 0.8462, "step": 142880 }, { "epoch": 11.88, "learning_rate": 2.4177368844053986e-06, "loss": 0.8419, "step": 142890 }, { "epoch": 11.88, "learning_rate": 2.417626028877865e-06, "loss": 0.8706, "step": 142900 }, { "epoch": 11.88, "learning_rate": 2.417515173350331e-06, "loss": 0.7846, "step": 142910 }, { "epoch": 11.88, "learning_rate": 2.417404317822797e-06, "loss": 0.7881, "step": 142920 }, { "epoch": 11.88, "learning_rate": 2.4172934622952637e-06, "loss": 0.756, "step": 142930 }, { "epoch": 11.88, "learning_rate": 2.4171826067677296e-06, "loss": 0.7348, "step": 142940 }, { "epoch": 11.88, "learning_rate": 2.4170717512401963e-06, "loss": 0.8297, "step": 142950 }, { "epoch": 11.88, "learning_rate": 2.416960895712662e-06, "loss": 0.8126, "step": 142960 }, { "epoch": 11.88, "learning_rate": 2.4168500401851285e-06, "loss": 0.7624, "step": 142970 }, { "epoch": 11.88, "learning_rate": 2.4167391846575952e-06, "loss": 0.7795, "step": 142980 }, { "epoch": 11.89, "learning_rate": 2.416628329130061e-06, "loss": 0.7992, "step": 142990 }, { "epoch": 11.89, "learning_rate": 2.4165174736025274e-06, "loss": 0.8022, "step": 143000 }, { "epoch": 11.89, "learning_rate": 2.4164066180749937e-06, "loss": 0.8016, "step": 143010 }, { "epoch": 11.89, "learning_rate": 2.41629576254746e-06, "loss": 0.788, "step": 143020 }, { "epoch": 11.89, "learning_rate": 2.416184907019926e-06, "loss": 0.7662, "step": 143030 }, { "epoch": 11.89, "learning_rate": 2.4160740514923926e-06, "loss": 0.7825, "step": 143040 }, { "epoch": 11.89, "learning_rate": 2.4159631959648584e-06, "loss": 0.8393, "step": 143050 }, { "epoch": 11.89, "learning_rate": 2.415852340437325e-06, "loss": 0.7625, "step": 143060 }, { "epoch": 11.89, "learning_rate": 2.415741484909791e-06, "loss": 0.8506, "step": 143070 }, { "epoch": 11.89, "learning_rate": 2.4156306293822573e-06, "loss": 0.825, "step": 143080 }, { "epoch": 11.89, "learning_rate": 2.415519773854724e-06, "loss": 0.7891, "step": 143090 }, { "epoch": 11.89, "learning_rate": 2.41540891832719e-06, "loss": 0.8922, "step": 143100 }, { "epoch": 11.9, "learning_rate": 2.4152980627996562e-06, "loss": 0.7967, "step": 143110 }, { "epoch": 11.9, "learning_rate": 2.4151872072721225e-06, "loss": 0.8051, "step": 143120 }, { "epoch": 11.9, "learning_rate": 2.415076351744589e-06, "loss": 0.7544, "step": 143130 }, { "epoch": 11.9, "learning_rate": 2.414965496217055e-06, "loss": 0.7705, "step": 143140 }, { "epoch": 11.9, "learning_rate": 2.4148546406895214e-06, "loss": 0.8106, "step": 143150 }, { "epoch": 11.9, "learning_rate": 2.4147437851619873e-06, "loss": 0.8222, "step": 143160 }, { "epoch": 11.9, "learning_rate": 2.414632929634454e-06, "loss": 0.7567, "step": 143170 }, { "epoch": 11.9, "learning_rate": 2.41452207410692e-06, "loss": 0.8244, "step": 143180 }, { "epoch": 11.9, "learning_rate": 2.414411218579386e-06, "loss": 0.8319, "step": 143190 }, { "epoch": 11.9, "learning_rate": 2.4143003630518525e-06, "loss": 0.8569, "step": 143200 }, { "epoch": 11.9, "learning_rate": 2.4141895075243187e-06, "loss": 0.7744, "step": 143210 }, { "epoch": 11.9, "learning_rate": 2.4140786519967855e-06, "loss": 0.8669, "step": 143220 }, { "epoch": 11.91, "learning_rate": 2.4139677964692513e-06, "loss": 0.8296, "step": 143230 }, { "epoch": 11.91, "learning_rate": 2.4138569409417176e-06, "loss": 0.7553, "step": 143240 }, { "epoch": 11.91, "learning_rate": 2.413746085414184e-06, "loss": 0.8202, "step": 143250 }, { "epoch": 11.91, "learning_rate": 2.4136352298866502e-06, "loss": 0.7859, "step": 143260 }, { "epoch": 11.91, "learning_rate": 2.413524374359116e-06, "loss": 0.8105, "step": 143270 }, { "epoch": 11.91, "learning_rate": 2.413413518831583e-06, "loss": 0.774, "step": 143280 }, { "epoch": 11.91, "learning_rate": 2.4133026633040487e-06, "loss": 0.9163, "step": 143290 }, { "epoch": 11.91, "learning_rate": 2.4131918077765154e-06, "loss": 0.8664, "step": 143300 }, { "epoch": 11.91, "learning_rate": 2.4130809522489813e-06, "loss": 0.806, "step": 143310 }, { "epoch": 11.91, "learning_rate": 2.4129700967214476e-06, "loss": 0.7439, "step": 143320 }, { "epoch": 11.91, "learning_rate": 2.412859241193914e-06, "loss": 0.7314, "step": 143330 }, { "epoch": 11.91, "learning_rate": 2.41274838566638e-06, "loss": 0.838, "step": 143340 }, { "epoch": 11.92, "learning_rate": 2.4126375301388465e-06, "loss": 0.887, "step": 143350 }, { "epoch": 11.92, "learning_rate": 2.412537760164066e-06, "loss": 0.726, "step": 143360 }, { "epoch": 11.92, "learning_rate": 2.4124269046365323e-06, "loss": 0.7864, "step": 143370 }, { "epoch": 11.92, "learning_rate": 2.4123160491089986e-06, "loss": 0.7376, "step": 143380 }, { "epoch": 11.92, "learning_rate": 2.412205193581465e-06, "loss": 0.79, "step": 143390 }, { "epoch": 11.92, "learning_rate": 2.412094338053931e-06, "loss": 0.792, "step": 143400 }, { "epoch": 11.92, "learning_rate": 2.411983482526397e-06, "loss": 0.8156, "step": 143410 }, { "epoch": 11.92, "learning_rate": 2.4118726269988638e-06, "loss": 0.7365, "step": 143420 }, { "epoch": 11.92, "learning_rate": 2.41176177147133e-06, "loss": 0.7562, "step": 143430 }, { "epoch": 11.92, "learning_rate": 2.411650915943796e-06, "loss": 0.8414, "step": 143440 }, { "epoch": 11.92, "learning_rate": 2.4115400604162627e-06, "loss": 0.8381, "step": 143450 }, { "epoch": 11.92, "learning_rate": 2.4114292048887285e-06, "loss": 0.7979, "step": 143460 }, { "epoch": 11.93, "learning_rate": 2.4113183493611952e-06, "loss": 0.8051, "step": 143470 }, { "epoch": 11.93, "learning_rate": 2.411207493833661e-06, "loss": 0.7889, "step": 143480 }, { "epoch": 11.93, "learning_rate": 2.4110966383061274e-06, "loss": 0.8296, "step": 143490 }, { "epoch": 11.93, "learning_rate": 2.4109857827785937e-06, "loss": 0.7862, "step": 143500 }, { "epoch": 11.93, "learning_rate": 2.41087492725106e-06, "loss": 0.7832, "step": 143510 }, { "epoch": 11.93, "learning_rate": 2.410764071723526e-06, "loss": 0.7819, "step": 143520 }, { "epoch": 11.93, "learning_rate": 2.4106532161959926e-06, "loss": 0.8443, "step": 143530 }, { "epoch": 11.93, "learning_rate": 2.4105423606684585e-06, "loss": 0.7235, "step": 143540 }, { "epoch": 11.93, "learning_rate": 2.4104315051409248e-06, "loss": 0.8515, "step": 143550 }, { "epoch": 11.93, "learning_rate": 2.4103206496133915e-06, "loss": 0.7753, "step": 143560 }, { "epoch": 11.93, "learning_rate": 2.4102097940858574e-06, "loss": 0.792, "step": 143570 }, { "epoch": 11.93, "learning_rate": 2.410098938558324e-06, "loss": 0.7422, "step": 143580 }, { "epoch": 11.94, "learning_rate": 2.40998808303079e-06, "loss": 0.7423, "step": 143590 }, { "epoch": 11.94, "learning_rate": 2.4098772275032562e-06, "loss": 0.8527, "step": 143600 }, { "epoch": 11.94, "learning_rate": 2.4097663719757225e-06, "loss": 0.8314, "step": 143610 }, { "epoch": 11.94, "learning_rate": 2.409655516448189e-06, "loss": 0.703, "step": 143620 }, { "epoch": 11.94, "learning_rate": 2.4095446609206547e-06, "loss": 0.7622, "step": 143630 }, { "epoch": 11.94, "learning_rate": 2.4094338053931214e-06, "loss": 0.793, "step": 143640 }, { "epoch": 11.94, "learning_rate": 2.4093229498655873e-06, "loss": 0.8234, "step": 143650 }, { "epoch": 11.94, "learning_rate": 2.409212094338054e-06, "loss": 0.8337, "step": 143660 }, { "epoch": 11.94, "learning_rate": 2.4091012388105203e-06, "loss": 0.7769, "step": 143670 }, { "epoch": 11.94, "learning_rate": 2.408990383282986e-06, "loss": 0.8384, "step": 143680 }, { "epoch": 11.94, "learning_rate": 2.408879527755453e-06, "loss": 0.7693, "step": 143690 }, { "epoch": 11.94, "learning_rate": 2.4087686722279188e-06, "loss": 0.7639, "step": 143700 }, { "epoch": 11.94, "learning_rate": 2.408657816700385e-06, "loss": 0.7787, "step": 143710 }, { "epoch": 11.95, "learning_rate": 2.4085469611728514e-06, "loss": 0.7937, "step": 143720 }, { "epoch": 11.95, "learning_rate": 2.4084361056453177e-06, "loss": 0.8027, "step": 143730 }, { "epoch": 11.95, "learning_rate": 2.408325250117784e-06, "loss": 0.7884, "step": 143740 }, { "epoch": 11.95, "learning_rate": 2.4082143945902502e-06, "loss": 0.8069, "step": 143750 }, { "epoch": 11.95, "learning_rate": 2.408103539062716e-06, "loss": 0.7378, "step": 143760 }, { "epoch": 11.95, "learning_rate": 2.407992683535183e-06, "loss": 0.7243, "step": 143770 }, { "epoch": 11.95, "learning_rate": 2.4078818280076487e-06, "loss": 0.7693, "step": 143780 }, { "epoch": 11.95, "learning_rate": 2.407770972480115e-06, "loss": 0.7906, "step": 143790 }, { "epoch": 11.95, "learning_rate": 2.4076601169525817e-06, "loss": 0.8478, "step": 143800 }, { "epoch": 11.95, "learning_rate": 2.4075492614250476e-06, "loss": 0.7602, "step": 143810 }, { "epoch": 11.95, "learning_rate": 2.4074384058975143e-06, "loss": 0.7962, "step": 143820 }, { "epoch": 11.95, "learning_rate": 2.40732755036998e-06, "loss": 0.7977, "step": 143830 }, { "epoch": 11.96, "learning_rate": 2.4072166948424465e-06, "loss": 0.7694, "step": 143840 }, { "epoch": 11.96, "learning_rate": 2.4071058393149128e-06, "loss": 0.8534, "step": 143850 }, { "epoch": 11.96, "learning_rate": 2.406994983787379e-06, "loss": 0.763, "step": 143860 }, { "epoch": 11.96, "learning_rate": 2.406884128259845e-06, "loss": 0.7964, "step": 143870 }, { "epoch": 11.96, "learning_rate": 2.4067732727323117e-06, "loss": 0.7936, "step": 143880 }, { "epoch": 11.96, "learning_rate": 2.4066624172047775e-06, "loss": 0.747, "step": 143890 }, { "epoch": 11.96, "learning_rate": 2.4065515616772443e-06, "loss": 0.8572, "step": 143900 }, { "epoch": 11.96, "learning_rate": 2.40644070614971e-06, "loss": 0.828, "step": 143910 }, { "epoch": 11.96, "learning_rate": 2.4063298506221764e-06, "loss": 0.7397, "step": 143920 }, { "epoch": 11.96, "learning_rate": 2.406218995094643e-06, "loss": 0.7987, "step": 143930 }, { "epoch": 11.96, "learning_rate": 2.406108139567109e-06, "loss": 0.7418, "step": 143940 }, { "epoch": 11.96, "learning_rate": 2.4059972840395753e-06, "loss": 0.7962, "step": 143950 }, { "epoch": 11.97, "learning_rate": 2.4058864285120416e-06, "loss": 0.7791, "step": 143960 }, { "epoch": 11.97, "learning_rate": 2.405775572984508e-06, "loss": 0.7918, "step": 143970 }, { "epoch": 11.97, "learning_rate": 2.4056647174569738e-06, "loss": 0.7867, "step": 143980 }, { "epoch": 11.97, "learning_rate": 2.4055538619294405e-06, "loss": 0.7581, "step": 143990 }, { "epoch": 11.97, "learning_rate": 2.4054430064019064e-06, "loss": 0.8285, "step": 144000 }, { "epoch": 11.97, "learning_rate": 2.405332150874373e-06, "loss": 0.7895, "step": 144010 }, { "epoch": 11.97, "learning_rate": 2.405221295346839e-06, "loss": 0.795, "step": 144020 }, { "epoch": 11.97, "learning_rate": 2.4051104398193052e-06, "loss": 0.7644, "step": 144030 }, { "epoch": 11.97, "learning_rate": 2.404999584291772e-06, "loss": 0.7928, "step": 144040 }, { "epoch": 11.97, "learning_rate": 2.404888728764238e-06, "loss": 0.8667, "step": 144050 }, { "epoch": 11.97, "learning_rate": 2.404777873236704e-06, "loss": 0.7978, "step": 144060 }, { "epoch": 11.97, "learning_rate": 2.4046670177091704e-06, "loss": 0.7708, "step": 144070 }, { "epoch": 11.98, "learning_rate": 2.4045561621816367e-06, "loss": 0.8167, "step": 144080 }, { "epoch": 11.98, "learning_rate": 2.404445306654103e-06, "loss": 0.8494, "step": 144090 }, { "epoch": 11.98, "learning_rate": 2.4043344511265693e-06, "loss": 0.8651, "step": 144100 }, { "epoch": 11.98, "learning_rate": 2.404223595599035e-06, "loss": 0.7688, "step": 144110 }, { "epoch": 11.98, "learning_rate": 2.404112740071502e-06, "loss": 0.7697, "step": 144120 }, { "epoch": 11.98, "learning_rate": 2.4040018845439678e-06, "loss": 0.7869, "step": 144130 }, { "epoch": 11.98, "learning_rate": 2.403891029016434e-06, "loss": 0.7917, "step": 144140 }, { "epoch": 11.98, "learning_rate": 2.4037801734889004e-06, "loss": 0.7972, "step": 144150 }, { "epoch": 11.98, "learning_rate": 2.4036693179613667e-06, "loss": 0.8122, "step": 144160 }, { "epoch": 11.98, "learning_rate": 2.4035584624338334e-06, "loss": 0.842, "step": 144170 }, { "epoch": 11.98, "learning_rate": 2.4034476069062992e-06, "loss": 0.743, "step": 144180 }, { "epoch": 11.98, "learning_rate": 2.4033367513787655e-06, "loss": 0.785, "step": 144190 }, { "epoch": 11.99, "learning_rate": 2.403225895851232e-06, "loss": 0.8814, "step": 144200 }, { "epoch": 11.99, "learning_rate": 2.403115040323698e-06, "loss": 0.7572, "step": 144210 }, { "epoch": 11.99, "learning_rate": 2.403004184796164e-06, "loss": 0.7438, "step": 144220 }, { "epoch": 11.99, "learning_rate": 2.4028933292686307e-06, "loss": 0.7459, "step": 144230 }, { "epoch": 11.99, "learning_rate": 2.4027824737410966e-06, "loss": 0.7474, "step": 144240 }, { "epoch": 11.99, "learning_rate": 2.4026716182135633e-06, "loss": 0.8142, "step": 144250 }, { "epoch": 11.99, "learning_rate": 2.402560762686029e-06, "loss": 0.7767, "step": 144260 }, { "epoch": 11.99, "learning_rate": 2.4024499071584955e-06, "loss": 0.7699, "step": 144270 }, { "epoch": 11.99, "learning_rate": 2.4023390516309618e-06, "loss": 0.6968, "step": 144280 }, { "epoch": 11.99, "learning_rate": 2.402228196103428e-06, "loss": 0.8027, "step": 144290 }, { "epoch": 11.99, "learning_rate": 2.4021173405758944e-06, "loss": 0.7708, "step": 144300 }, { "epoch": 11.99, "learning_rate": 2.4020064850483607e-06, "loss": 0.8034, "step": 144310 }, { "epoch": 12.0, "learning_rate": 2.401895629520827e-06, "loss": 0.7551, "step": 144320 }, { "epoch": 12.0, "learning_rate": 2.4017847739932933e-06, "loss": 0.8038, "step": 144330 }, { "epoch": 12.0, "learning_rate": 2.4016739184657596e-06, "loss": 0.7865, "step": 144340 }, { "epoch": 12.0, "learning_rate": 2.4015630629382254e-06, "loss": 0.8968, "step": 144350 }, { "epoch": 12.0, "learning_rate": 2.401452207410692e-06, "loss": 0.8291, "step": 144360 }, { "epoch": 12.0, "learning_rate": 2.401341351883158e-06, "loss": 0.7465, "step": 144370 }, { "epoch": 12.0, "eval_loss": 1.0822076797485352, "eval_runtime": 351.4785, "eval_samples_per_second": 7.608, "eval_steps_per_second": 3.804, "eval_wer": 0.6498848723707816, "step": 144372 }, { "epoch": 12.0, "learning_rate": 2.4012304963556243e-06, "loss": 0.8024, "step": 144380 }, { "epoch": 12.0, "learning_rate": 2.4011196408280906e-06, "loss": 0.8328, "step": 144390 }, { "epoch": 12.0, "learning_rate": 2.401008785300557e-06, "loss": 0.7215, "step": 144400 }, { "epoch": 12.0, "learning_rate": 2.4008979297730236e-06, "loss": 0.8383, "step": 144410 }, { "epoch": 12.0, "learning_rate": 2.4007870742454895e-06, "loss": 0.7761, "step": 144420 }, { "epoch": 12.0, "learning_rate": 2.4006762187179558e-06, "loss": 0.796, "step": 144430 }, { "epoch": 12.01, "learning_rate": 2.400565363190422e-06, "loss": 0.756, "step": 144440 }, { "epoch": 12.01, "learning_rate": 2.4004545076628884e-06, "loss": 0.8149, "step": 144450 }, { "epoch": 12.01, "learning_rate": 2.4003436521353542e-06, "loss": 0.7959, "step": 144460 }, { "epoch": 12.01, "learning_rate": 2.400232796607821e-06, "loss": 0.7579, "step": 144470 }, { "epoch": 12.01, "learning_rate": 2.400121941080287e-06, "loss": 0.8348, "step": 144480 }, { "epoch": 12.01, "learning_rate": 2.400011085552753e-06, "loss": 0.7247, "step": 144490 }, { "epoch": 12.01, "learning_rate": 2.3999002300252194e-06, "loss": 0.7888, "step": 144500 }, { "epoch": 12.01, "learning_rate": 2.3997893744976857e-06, "loss": 0.7463, "step": 144510 }, { "epoch": 12.01, "learning_rate": 2.399678518970152e-06, "loss": 0.7463, "step": 144520 }, { "epoch": 12.01, "learning_rate": 2.3995676634426183e-06, "loss": 0.8498, "step": 144530 }, { "epoch": 12.01, "learning_rate": 2.3994568079150846e-06, "loss": 0.8403, "step": 144540 }, { "epoch": 12.01, "learning_rate": 2.399345952387551e-06, "loss": 0.7752, "step": 144550 }, { "epoch": 12.02, "learning_rate": 2.399235096860017e-06, "loss": 0.7391, "step": 144560 }, { "epoch": 12.02, "learning_rate": 2.399124241332483e-06, "loss": 0.8285, "step": 144570 }, { "epoch": 12.02, "learning_rate": 2.39901338580495e-06, "loss": 0.8399, "step": 144580 }, { "epoch": 12.02, "learning_rate": 2.3989025302774157e-06, "loss": 0.7516, "step": 144590 }, { "epoch": 12.02, "learning_rate": 2.3987916747498824e-06, "loss": 0.8265, "step": 144600 }, { "epoch": 12.02, "learning_rate": 2.3986808192223483e-06, "loss": 0.7473, "step": 144610 }, { "epoch": 12.02, "learning_rate": 2.3985699636948146e-06, "loss": 0.7801, "step": 144620 }, { "epoch": 12.02, "learning_rate": 2.398459108167281e-06, "loss": 0.9286, "step": 144630 }, { "epoch": 12.02, "learning_rate": 2.398348252639747e-06, "loss": 0.7702, "step": 144640 }, { "epoch": 12.02, "learning_rate": 2.398237397112213e-06, "loss": 0.7875, "step": 144650 }, { "epoch": 12.02, "learning_rate": 2.3981265415846797e-06, "loss": 0.8186, "step": 144660 }, { "epoch": 12.02, "learning_rate": 2.398015686057146e-06, "loss": 0.7602, "step": 144670 }, { "epoch": 12.03, "learning_rate": 2.3979048305296123e-06, "loss": 0.8238, "step": 144680 }, { "epoch": 12.03, "learning_rate": 2.3977939750020786e-06, "loss": 0.7952, "step": 144690 }, { "epoch": 12.03, "learning_rate": 2.3976831194745445e-06, "loss": 0.7505, "step": 144700 }, { "epoch": 12.03, "learning_rate": 2.397572263947011e-06, "loss": 0.771, "step": 144710 }, { "epoch": 12.03, "learning_rate": 2.397461408419477e-06, "loss": 0.8098, "step": 144720 }, { "epoch": 12.03, "learning_rate": 2.3973505528919434e-06, "loss": 0.8339, "step": 144730 }, { "epoch": 12.03, "learning_rate": 2.3972396973644097e-06, "loss": 0.821, "step": 144740 }, { "epoch": 12.03, "learning_rate": 2.397128841836876e-06, "loss": 0.8013, "step": 144750 }, { "epoch": 12.03, "learning_rate": 2.397017986309342e-06, "loss": 0.787, "step": 144760 }, { "epoch": 12.03, "learning_rate": 2.3969071307818086e-06, "loss": 0.7847, "step": 144770 }, { "epoch": 12.03, "learning_rate": 2.396796275254275e-06, "loss": 0.849, "step": 144780 }, { "epoch": 12.03, "learning_rate": 2.396685419726741e-06, "loss": 0.8405, "step": 144790 }, { "epoch": 12.04, "learning_rate": 2.3965745641992074e-06, "loss": 0.8105, "step": 144800 }, { "epoch": 12.04, "learning_rate": 2.3964637086716733e-06, "loss": 0.8403, "step": 144810 }, { "epoch": 12.04, "learning_rate": 2.39635285314414e-06, "loss": 0.7652, "step": 144820 }, { "epoch": 12.04, "learning_rate": 2.396241997616606e-06, "loss": 0.8314, "step": 144830 }, { "epoch": 12.04, "learning_rate": 2.396131142089072e-06, "loss": 0.7425, "step": 144840 }, { "epoch": 12.04, "learning_rate": 2.3960202865615385e-06, "loss": 0.7557, "step": 144850 }, { "epoch": 12.04, "learning_rate": 2.395909431034005e-06, "loss": 0.7525, "step": 144860 }, { "epoch": 12.04, "learning_rate": 2.395798575506471e-06, "loss": 0.7994, "step": 144870 }, { "epoch": 12.04, "learning_rate": 2.3956877199789374e-06, "loss": 0.7811, "step": 144880 }, { "epoch": 12.04, "learning_rate": 2.3955768644514033e-06, "loss": 0.7825, "step": 144890 }, { "epoch": 12.04, "learning_rate": 2.39546600892387e-06, "loss": 0.8034, "step": 144900 }, { "epoch": 12.04, "learning_rate": 2.3953551533963363e-06, "loss": 0.7648, "step": 144910 }, { "epoch": 12.05, "learning_rate": 2.395244297868802e-06, "loss": 0.8183, "step": 144920 }, { "epoch": 12.05, "learning_rate": 2.395133442341269e-06, "loss": 0.8722, "step": 144930 }, { "epoch": 12.05, "learning_rate": 2.3950225868137347e-06, "loss": 0.8143, "step": 144940 }, { "epoch": 12.05, "learning_rate": 2.3949117312862014e-06, "loss": 0.799, "step": 144950 }, { "epoch": 12.05, "learning_rate": 2.3948008757586673e-06, "loss": 0.7839, "step": 144960 }, { "epoch": 12.05, "learning_rate": 2.3946900202311336e-06, "loss": 0.7664, "step": 144970 }, { "epoch": 12.05, "learning_rate": 2.3945791647036e-06, "loss": 0.7813, "step": 144980 }, { "epoch": 12.05, "learning_rate": 2.394468309176066e-06, "loss": 0.8189, "step": 144990 }, { "epoch": 12.05, "learning_rate": 2.394357453648532e-06, "loss": 0.782, "step": 145000 }, { "epoch": 12.05, "learning_rate": 2.394246598120999e-06, "loss": 0.83, "step": 145010 }, { "epoch": 12.05, "learning_rate": 2.394135742593465e-06, "loss": 0.7478, "step": 145020 }, { "epoch": 12.05, "learning_rate": 2.3940248870659314e-06, "loss": 0.8356, "step": 145030 }, { "epoch": 12.06, "learning_rate": 2.3939140315383977e-06, "loss": 0.8236, "step": 145040 }, { "epoch": 12.06, "learning_rate": 2.3938031760108636e-06, "loss": 0.7873, "step": 145050 }, { "epoch": 12.06, "learning_rate": 2.3936923204833303e-06, "loss": 0.7985, "step": 145060 }, { "epoch": 12.06, "learning_rate": 2.393581464955796e-06, "loss": 0.7754, "step": 145070 }, { "epoch": 12.06, "learning_rate": 2.3934706094282624e-06, "loss": 0.8156, "step": 145080 }, { "epoch": 12.06, "learning_rate": 2.3933597539007287e-06, "loss": 0.784, "step": 145090 }, { "epoch": 12.06, "learning_rate": 2.393248898373195e-06, "loss": 0.7336, "step": 145100 }, { "epoch": 12.06, "learning_rate": 2.3931380428456613e-06, "loss": 0.7578, "step": 145110 }, { "epoch": 12.06, "learning_rate": 2.3930271873181276e-06, "loss": 0.7945, "step": 145120 }, { "epoch": 12.06, "learning_rate": 2.3929163317905935e-06, "loss": 0.8995, "step": 145130 }, { "epoch": 12.06, "learning_rate": 2.3928054762630602e-06, "loss": 0.7513, "step": 145140 }, { "epoch": 12.06, "learning_rate": 2.3926946207355265e-06, "loss": 0.7914, "step": 145150 }, { "epoch": 12.07, "learning_rate": 2.3925837652079924e-06, "loss": 0.8285, "step": 145160 }, { "epoch": 12.07, "learning_rate": 2.392472909680459e-06, "loss": 0.8174, "step": 145170 }, { "epoch": 12.07, "learning_rate": 2.392362054152925e-06, "loss": 0.7911, "step": 145180 }, { "epoch": 12.07, "learning_rate": 2.3922511986253917e-06, "loss": 0.8245, "step": 145190 }, { "epoch": 12.07, "learning_rate": 2.3921403430978576e-06, "loss": 0.763, "step": 145200 }, { "epoch": 12.07, "learning_rate": 2.392029487570324e-06, "loss": 0.8134, "step": 145210 }, { "epoch": 12.07, "learning_rate": 2.39191863204279e-06, "loss": 0.8251, "step": 145220 }, { "epoch": 12.07, "learning_rate": 2.3918077765152564e-06, "loss": 0.8325, "step": 145230 }, { "epoch": 12.07, "learning_rate": 2.3916969209877223e-06, "loss": 0.8188, "step": 145240 }, { "epoch": 12.07, "learning_rate": 2.391586065460189e-06, "loss": 0.8321, "step": 145250 }, { "epoch": 12.07, "learning_rate": 2.391475209932655e-06, "loss": 0.7963, "step": 145260 }, { "epoch": 12.07, "learning_rate": 2.391364354405121e-06, "loss": 0.8487, "step": 145270 }, { "epoch": 12.08, "learning_rate": 2.391253498877588e-06, "loss": 0.8819, "step": 145280 }, { "epoch": 12.08, "learning_rate": 2.391142643350054e-06, "loss": 0.8126, "step": 145290 }, { "epoch": 12.08, "learning_rate": 2.3910317878225205e-06, "loss": 0.7954, "step": 145300 }, { "epoch": 12.08, "learning_rate": 2.3909209322949864e-06, "loss": 0.7637, "step": 145310 }, { "epoch": 12.08, "learning_rate": 2.3908100767674527e-06, "loss": 0.8101, "step": 145320 }, { "epoch": 12.08, "learning_rate": 2.390699221239919e-06, "loss": 0.8299, "step": 145330 }, { "epoch": 12.08, "learning_rate": 2.3905883657123853e-06, "loss": 0.8058, "step": 145340 }, { "epoch": 12.08, "learning_rate": 2.390477510184851e-06, "loss": 0.7373, "step": 145350 }, { "epoch": 12.08, "learning_rate": 2.390366654657318e-06, "loss": 0.7995, "step": 145360 }, { "epoch": 12.08, "learning_rate": 2.3902557991297837e-06, "loss": 0.7822, "step": 145370 }, { "epoch": 12.08, "learning_rate": 2.3901449436022505e-06, "loss": 0.892, "step": 145380 }, { "epoch": 12.08, "learning_rate": 2.3900340880747168e-06, "loss": 0.7868, "step": 145390 }, { "epoch": 12.09, "learning_rate": 2.3899232325471826e-06, "loss": 0.7494, "step": 145400 }, { "epoch": 12.09, "learning_rate": 2.3898123770196493e-06, "loss": 0.7053, "step": 145410 }, { "epoch": 12.09, "learning_rate": 2.3897015214921152e-06, "loss": 0.7114, "step": 145420 }, { "epoch": 12.09, "learning_rate": 2.3895906659645815e-06, "loss": 0.7912, "step": 145430 }, { "epoch": 12.09, "learning_rate": 2.389479810437048e-06, "loss": 0.7529, "step": 145440 }, { "epoch": 12.09, "learning_rate": 2.389368954909514e-06, "loss": 0.8478, "step": 145450 }, { "epoch": 12.09, "learning_rate": 2.3892580993819804e-06, "loss": 0.8061, "step": 145460 }, { "epoch": 12.09, "learning_rate": 2.3891472438544467e-06, "loss": 0.7975, "step": 145470 }, { "epoch": 12.09, "learning_rate": 2.3890363883269126e-06, "loss": 0.8465, "step": 145480 }, { "epoch": 12.09, "learning_rate": 2.3889255327993793e-06, "loss": 0.7226, "step": 145490 }, { "epoch": 12.09, "learning_rate": 2.388814677271845e-06, "loss": 0.7647, "step": 145500 }, { "epoch": 12.09, "learning_rate": 2.3887038217443114e-06, "loss": 0.7561, "step": 145510 }, { "epoch": 12.1, "learning_rate": 2.388592966216778e-06, "loss": 0.7823, "step": 145520 }, { "epoch": 12.1, "learning_rate": 2.388482110689244e-06, "loss": 0.8227, "step": 145530 }, { "epoch": 12.1, "learning_rate": 2.3883712551617108e-06, "loss": 0.7909, "step": 145540 }, { "epoch": 12.1, "learning_rate": 2.3882603996341766e-06, "loss": 0.7818, "step": 145550 }, { "epoch": 12.1, "learning_rate": 2.388149544106643e-06, "loss": 0.8575, "step": 145560 }, { "epoch": 12.1, "learning_rate": 2.3880386885791092e-06, "loss": 0.7208, "step": 145570 }, { "epoch": 12.1, "learning_rate": 2.3879278330515755e-06, "loss": 0.8561, "step": 145580 }, { "epoch": 12.1, "learning_rate": 2.3878169775240414e-06, "loss": 0.796, "step": 145590 }, { "epoch": 12.1, "learning_rate": 2.387706121996508e-06, "loss": 0.784, "step": 145600 }, { "epoch": 12.1, "learning_rate": 2.387595266468974e-06, "loss": 0.7904, "step": 145610 }, { "epoch": 12.1, "learning_rate": 2.3874844109414407e-06, "loss": 0.7877, "step": 145620 }, { "epoch": 12.1, "learning_rate": 2.3873735554139066e-06, "loss": 0.8173, "step": 145630 }, { "epoch": 12.11, "learning_rate": 2.387262699886373e-06, "loss": 0.7832, "step": 145640 }, { "epoch": 12.11, "learning_rate": 2.3871518443588396e-06, "loss": 0.7944, "step": 145650 }, { "epoch": 12.11, "learning_rate": 2.3870409888313055e-06, "loss": 0.7997, "step": 145660 }, { "epoch": 12.11, "learning_rate": 2.3869301333037717e-06, "loss": 0.7796, "step": 145670 }, { "epoch": 12.11, "learning_rate": 2.386819277776238e-06, "loss": 0.8274, "step": 145680 }, { "epoch": 12.11, "learning_rate": 2.3867084222487043e-06, "loss": 0.8099, "step": 145690 }, { "epoch": 12.11, "learning_rate": 2.3865975667211702e-06, "loss": 0.7521, "step": 145700 }, { "epoch": 12.11, "learning_rate": 2.386486711193637e-06, "loss": 0.7553, "step": 145710 }, { "epoch": 12.11, "learning_rate": 2.386375855666103e-06, "loss": 0.7553, "step": 145720 }, { "epoch": 12.11, "learning_rate": 2.3862650001385695e-06, "loss": 0.7847, "step": 145730 }, { "epoch": 12.11, "learning_rate": 2.3861541446110354e-06, "loss": 0.7382, "step": 145740 }, { "epoch": 12.11, "learning_rate": 2.3860432890835017e-06, "loss": 0.7869, "step": 145750 }, { "epoch": 12.12, "learning_rate": 2.3859324335559684e-06, "loss": 0.7393, "step": 145760 }, { "epoch": 12.12, "learning_rate": 2.3858215780284343e-06, "loss": 0.7808, "step": 145770 }, { "epoch": 12.12, "learning_rate": 2.3857107225009006e-06, "loss": 0.8049, "step": 145780 }, { "epoch": 12.12, "learning_rate": 2.385599866973367e-06, "loss": 0.8305, "step": 145790 }, { "epoch": 12.12, "learning_rate": 2.385489011445833e-06, "loss": 0.8028, "step": 145800 }, { "epoch": 12.12, "learning_rate": 2.3853781559182995e-06, "loss": 0.7996, "step": 145810 }, { "epoch": 12.12, "learning_rate": 2.3852673003907658e-06, "loss": 0.9042, "step": 145820 }, { "epoch": 12.12, "learning_rate": 2.3851564448632316e-06, "loss": 0.8229, "step": 145830 }, { "epoch": 12.12, "learning_rate": 2.3850455893356983e-06, "loss": 0.7828, "step": 145840 }, { "epoch": 12.12, "learning_rate": 2.3849347338081642e-06, "loss": 0.8012, "step": 145850 }, { "epoch": 12.12, "learning_rate": 2.3848238782806305e-06, "loss": 0.8128, "step": 145860 }, { "epoch": 12.12, "learning_rate": 2.384713022753097e-06, "loss": 0.831, "step": 145870 }, { "epoch": 12.13, "learning_rate": 2.384602167225563e-06, "loss": 0.7948, "step": 145880 }, { "epoch": 12.13, "learning_rate": 2.38449131169803e-06, "loss": 0.8002, "step": 145890 }, { "epoch": 12.13, "learning_rate": 2.3843804561704957e-06, "loss": 0.8307, "step": 145900 }, { "epoch": 12.13, "learning_rate": 2.384269600642962e-06, "loss": 0.812, "step": 145910 }, { "epoch": 12.13, "learning_rate": 2.3841587451154283e-06, "loss": 0.8025, "step": 145920 }, { "epoch": 12.13, "learning_rate": 2.3840478895878946e-06, "loss": 0.8227, "step": 145930 }, { "epoch": 12.13, "learning_rate": 2.3839370340603605e-06, "loss": 0.7669, "step": 145940 }, { "epoch": 12.13, "learning_rate": 2.383826178532827e-06, "loss": 0.8117, "step": 145950 }, { "epoch": 12.13, "learning_rate": 2.383715323005293e-06, "loss": 0.8648, "step": 145960 }, { "epoch": 12.13, "learning_rate": 2.3836044674777598e-06, "loss": 0.7969, "step": 145970 }, { "epoch": 12.13, "learning_rate": 2.3834936119502256e-06, "loss": 0.791, "step": 145980 }, { "epoch": 12.13, "learning_rate": 2.383382756422692e-06, "loss": 0.742, "step": 145990 }, { "epoch": 12.14, "learning_rate": 2.3832719008951582e-06, "loss": 0.7642, "step": 146000 }, { "epoch": 12.14, "learning_rate": 2.3831610453676245e-06, "loss": 0.7408, "step": 146010 }, { "epoch": 12.14, "learning_rate": 2.383050189840091e-06, "loss": 0.746, "step": 146020 }, { "epoch": 12.14, "learning_rate": 2.382939334312557e-06, "loss": 0.8751, "step": 146030 }, { "epoch": 12.14, "learning_rate": 2.3828284787850234e-06, "loss": 0.7606, "step": 146040 }, { "epoch": 12.14, "learning_rate": 2.3827176232574893e-06, "loss": 0.8206, "step": 146050 }, { "epoch": 12.14, "learning_rate": 2.382606767729956e-06, "loss": 0.7544, "step": 146060 }, { "epoch": 12.14, "learning_rate": 2.382495912202422e-06, "loss": 0.7819, "step": 146070 }, { "epoch": 12.14, "learning_rate": 2.3823850566748886e-06, "loss": 0.8274, "step": 146080 }, { "epoch": 12.14, "learning_rate": 2.3822742011473545e-06, "loss": 0.8097, "step": 146090 }, { "epoch": 12.14, "learning_rate": 2.3821633456198208e-06, "loss": 0.7928, "step": 146100 }, { "epoch": 12.14, "learning_rate": 2.382052490092287e-06, "loss": 0.7273, "step": 146110 }, { "epoch": 12.15, "learning_rate": 2.3819416345647533e-06, "loss": 0.7708, "step": 146120 }, { "epoch": 12.15, "learning_rate": 2.3818307790372196e-06, "loss": 0.8069, "step": 146130 }, { "epoch": 12.15, "learning_rate": 2.381719923509686e-06, "loss": 0.8249, "step": 146140 }, { "epoch": 12.15, "learning_rate": 2.3816090679821522e-06, "loss": 0.7406, "step": 146150 }, { "epoch": 12.15, "learning_rate": 2.3814982124546185e-06, "loss": 0.8035, "step": 146160 }, { "epoch": 12.15, "learning_rate": 2.381387356927085e-06, "loss": 0.7103, "step": 146170 }, { "epoch": 12.15, "learning_rate": 2.3812765013995507e-06, "loss": 0.7881, "step": 146180 }, { "epoch": 12.15, "learning_rate": 2.3811656458720174e-06, "loss": 0.8042, "step": 146190 }, { "epoch": 12.15, "learning_rate": 2.3810547903444833e-06, "loss": 0.7752, "step": 146200 }, { "epoch": 12.15, "learning_rate": 2.3809439348169496e-06, "loss": 0.7625, "step": 146210 }, { "epoch": 12.15, "learning_rate": 2.380833079289416e-06, "loss": 0.8048, "step": 146220 }, { "epoch": 12.15, "learning_rate": 2.380722223761882e-06, "loss": 0.8527, "step": 146230 }, { "epoch": 12.16, "learning_rate": 2.3806113682343485e-06, "loss": 0.829, "step": 146240 }, { "epoch": 12.16, "learning_rate": 2.3805005127068148e-06, "loss": 0.802, "step": 146250 }, { "epoch": 12.16, "learning_rate": 2.380389657179281e-06, "loss": 0.8128, "step": 146260 }, { "epoch": 12.16, "learning_rate": 2.3802788016517474e-06, "loss": 0.7698, "step": 146270 }, { "epoch": 12.16, "learning_rate": 2.3801679461242136e-06, "loss": 0.827, "step": 146280 }, { "epoch": 12.16, "learning_rate": 2.3800570905966795e-06, "loss": 0.7656, "step": 146290 }, { "epoch": 12.16, "learning_rate": 2.3799462350691462e-06, "loss": 0.7786, "step": 146300 }, { "epoch": 12.16, "learning_rate": 2.379835379541612e-06, "loss": 0.7823, "step": 146310 }, { "epoch": 12.16, "learning_rate": 2.379724524014079e-06, "loss": 0.8008, "step": 146320 }, { "epoch": 12.16, "learning_rate": 2.3796136684865447e-06, "loss": 0.8209, "step": 146330 }, { "epoch": 12.16, "learning_rate": 2.379502812959011e-06, "loss": 0.768, "step": 146340 }, { "epoch": 12.16, "learning_rate": 2.3793919574314773e-06, "loss": 0.7638, "step": 146350 }, { "epoch": 12.17, "learning_rate": 2.3792811019039436e-06, "loss": 0.8041, "step": 146360 }, { "epoch": 12.17, "learning_rate": 2.3791702463764095e-06, "loss": 0.7419, "step": 146370 }, { "epoch": 12.17, "learning_rate": 2.379059390848876e-06, "loss": 0.8078, "step": 146380 }, { "epoch": 12.17, "learning_rate": 2.3789485353213425e-06, "loss": 0.7408, "step": 146390 }, { "epoch": 12.17, "learning_rate": 2.3788376797938088e-06, "loss": 0.7978, "step": 146400 }, { "epoch": 12.17, "learning_rate": 2.378726824266275e-06, "loss": 0.7877, "step": 146410 }, { "epoch": 12.17, "learning_rate": 2.378615968738741e-06, "loss": 0.8027, "step": 146420 }, { "epoch": 12.17, "learning_rate": 2.3785051132112077e-06, "loss": 0.8009, "step": 146430 }, { "epoch": 12.17, "learning_rate": 2.3783942576836735e-06, "loss": 0.7482, "step": 146440 }, { "epoch": 12.17, "learning_rate": 2.37828340215614e-06, "loss": 0.7645, "step": 146450 }, { "epoch": 12.17, "learning_rate": 2.378172546628606e-06, "loss": 0.772, "step": 146460 }, { "epoch": 12.17, "learning_rate": 2.3780616911010724e-06, "loss": 0.8314, "step": 146470 }, { "epoch": 12.18, "learning_rate": 2.3779508355735383e-06, "loss": 0.8952, "step": 146480 }, { "epoch": 12.18, "learning_rate": 2.377839980046005e-06, "loss": 0.7661, "step": 146490 }, { "epoch": 12.18, "learning_rate": 2.3777291245184713e-06, "loss": 0.8025, "step": 146500 }, { "epoch": 12.18, "learning_rate": 2.3776182689909376e-06, "loss": 0.73, "step": 146510 }, { "epoch": 12.18, "learning_rate": 2.377507413463404e-06, "loss": 0.8344, "step": 146520 }, { "epoch": 12.18, "learning_rate": 2.3773965579358698e-06, "loss": 0.8492, "step": 146530 }, { "epoch": 12.18, "learning_rate": 2.3772857024083365e-06, "loss": 0.8134, "step": 146540 }, { "epoch": 12.18, "learning_rate": 2.3771748468808024e-06, "loss": 0.8409, "step": 146550 }, { "epoch": 12.18, "learning_rate": 2.3770639913532686e-06, "loss": 0.7343, "step": 146560 }, { "epoch": 12.18, "learning_rate": 2.376953135825735e-06, "loss": 0.7987, "step": 146570 }, { "epoch": 12.18, "learning_rate": 2.3768422802982012e-06, "loss": 0.9013, "step": 146580 }, { "epoch": 12.18, "learning_rate": 2.3767314247706675e-06, "loss": 0.7985, "step": 146590 }, { "epoch": 12.19, "learning_rate": 2.376620569243134e-06, "loss": 0.7245, "step": 146600 }, { "epoch": 12.19, "learning_rate": 2.3765097137155997e-06, "loss": 0.83, "step": 146610 }, { "epoch": 12.19, "learning_rate": 2.3763988581880664e-06, "loss": 0.8019, "step": 146620 }, { "epoch": 12.19, "learning_rate": 2.3762880026605327e-06, "loss": 0.8306, "step": 146630 }, { "epoch": 12.19, "learning_rate": 2.3761771471329986e-06, "loss": 0.7602, "step": 146640 }, { "epoch": 12.19, "learning_rate": 2.3760662916054653e-06, "loss": 0.8014, "step": 146650 }, { "epoch": 12.19, "learning_rate": 2.375955436077931e-06, "loss": 0.7683, "step": 146660 }, { "epoch": 12.19, "learning_rate": 2.375844580550398e-06, "loss": 0.7787, "step": 146670 }, { "epoch": 12.19, "learning_rate": 2.3757337250228638e-06, "loss": 0.813, "step": 146680 }, { "epoch": 12.19, "learning_rate": 2.37562286949533e-06, "loss": 0.7251, "step": 146690 }, { "epoch": 12.19, "learning_rate": 2.3755120139677964e-06, "loss": 0.7713, "step": 146700 }, { "epoch": 12.19, "learning_rate": 2.3754011584402627e-06, "loss": 0.7304, "step": 146710 }, { "epoch": 12.2, "learning_rate": 2.3752903029127285e-06, "loss": 0.7154, "step": 146720 }, { "epoch": 12.2, "learning_rate": 2.3751794473851952e-06, "loss": 0.8437, "step": 146730 }, { "epoch": 12.2, "learning_rate": 2.375068591857661e-06, "loss": 0.7989, "step": 146740 }, { "epoch": 12.2, "learning_rate": 2.374957736330128e-06, "loss": 0.7416, "step": 146750 }, { "epoch": 12.2, "learning_rate": 2.374846880802594e-06, "loss": 0.8469, "step": 146760 }, { "epoch": 12.2, "learning_rate": 2.37473602527506e-06, "loss": 0.846, "step": 146770 }, { "epoch": 12.2, "learning_rate": 2.3746251697475267e-06, "loss": 0.7969, "step": 146780 }, { "epoch": 12.2, "learning_rate": 2.3745143142199926e-06, "loss": 0.8163, "step": 146790 }, { "epoch": 12.2, "learning_rate": 2.374403458692459e-06, "loss": 0.7899, "step": 146800 }, { "epoch": 12.2, "learning_rate": 2.374292603164925e-06, "loss": 0.829, "step": 146810 }, { "epoch": 12.2, "learning_rate": 2.3741817476373915e-06, "loss": 0.7595, "step": 146820 }, { "epoch": 12.2, "learning_rate": 2.3740708921098574e-06, "loss": 0.8401, "step": 146830 }, { "epoch": 12.21, "learning_rate": 2.373960036582324e-06, "loss": 0.7397, "step": 146840 }, { "epoch": 12.21, "learning_rate": 2.37384918105479e-06, "loss": 0.7512, "step": 146850 }, { "epoch": 12.21, "learning_rate": 2.3737383255272567e-06, "loss": 0.8144, "step": 146860 }, { "epoch": 12.21, "learning_rate": 2.373627469999723e-06, "loss": 0.7929, "step": 146870 }, { "epoch": 12.21, "learning_rate": 2.373516614472189e-06, "loss": 0.8098, "step": 146880 }, { "epoch": 12.21, "learning_rate": 2.3734057589446555e-06, "loss": 0.8626, "step": 146890 }, { "epoch": 12.21, "learning_rate": 2.3732949034171214e-06, "loss": 0.796, "step": 146900 }, { "epoch": 12.21, "learning_rate": 2.373184047889588e-06, "loss": 0.8058, "step": 146910 }, { "epoch": 12.21, "learning_rate": 2.373073192362054e-06, "loss": 0.7517, "step": 146920 }, { "epoch": 12.21, "learning_rate": 2.3729623368345203e-06, "loss": 0.8246, "step": 146930 }, { "epoch": 12.21, "learning_rate": 2.3728514813069866e-06, "loss": 0.7934, "step": 146940 }, { "epoch": 12.21, "learning_rate": 2.372740625779453e-06, "loss": 0.8122, "step": 146950 }, { "epoch": 12.22, "learning_rate": 2.3726297702519188e-06, "loss": 0.8144, "step": 146960 }, { "epoch": 12.22, "learning_rate": 2.3725189147243855e-06, "loss": 0.7472, "step": 146970 }, { "epoch": 12.22, "learning_rate": 2.3724080591968514e-06, "loss": 0.7961, "step": 146980 }, { "epoch": 12.22, "learning_rate": 2.3722972036693177e-06, "loss": 0.7854, "step": 146990 }, { "epoch": 12.22, "learning_rate": 2.3721863481417844e-06, "loss": 0.7517, "step": 147000 }, { "epoch": 12.22, "learning_rate": 2.3720754926142502e-06, "loss": 0.7894, "step": 147010 }, { "epoch": 12.22, "learning_rate": 2.371964637086717e-06, "loss": 0.7195, "step": 147020 }, { "epoch": 12.22, "learning_rate": 2.371853781559183e-06, "loss": 0.8455, "step": 147030 }, { "epoch": 12.22, "learning_rate": 2.371742926031649e-06, "loss": 0.7762, "step": 147040 }, { "epoch": 12.22, "learning_rate": 2.3716320705041154e-06, "loss": 0.7902, "step": 147050 }, { "epoch": 12.22, "learning_rate": 2.3715212149765817e-06, "loss": 0.7737, "step": 147060 }, { "epoch": 12.22, "learning_rate": 2.3714103594490476e-06, "loss": 0.798, "step": 147070 }, { "epoch": 12.23, "learning_rate": 2.3712995039215143e-06, "loss": 0.7573, "step": 147080 }, { "epoch": 12.23, "learning_rate": 2.37118864839398e-06, "loss": 0.8326, "step": 147090 }, { "epoch": 12.23, "learning_rate": 2.371077792866447e-06, "loss": 0.7618, "step": 147100 }, { "epoch": 12.23, "learning_rate": 2.370966937338913e-06, "loss": 0.735, "step": 147110 }, { "epoch": 12.23, "learning_rate": 2.370856081811379e-06, "loss": 0.8731, "step": 147120 }, { "epoch": 12.23, "learning_rate": 2.3707452262838458e-06, "loss": 0.8267, "step": 147130 }, { "epoch": 12.23, "learning_rate": 2.3706343707563117e-06, "loss": 0.8064, "step": 147140 }, { "epoch": 12.23, "learning_rate": 2.370523515228778e-06, "loss": 0.7968, "step": 147150 }, { "epoch": 12.23, "learning_rate": 2.3704126597012442e-06, "loss": 0.7916, "step": 147160 }, { "epoch": 12.23, "learning_rate": 2.3703018041737105e-06, "loss": 0.7526, "step": 147170 }, { "epoch": 12.23, "learning_rate": 2.370190948646177e-06, "loss": 0.8428, "step": 147180 }, { "epoch": 12.23, "learning_rate": 2.370080093118643e-06, "loss": 0.7892, "step": 147190 }, { "epoch": 12.24, "learning_rate": 2.369969237591109e-06, "loss": 0.735, "step": 147200 }, { "epoch": 12.24, "learning_rate": 2.3698583820635757e-06, "loss": 0.7424, "step": 147210 }, { "epoch": 12.24, "learning_rate": 2.3697475265360416e-06, "loss": 0.7836, "step": 147220 }, { "epoch": 12.24, "learning_rate": 2.369636671008508e-06, "loss": 0.7974, "step": 147230 }, { "epoch": 12.24, "learning_rate": 2.3695258154809746e-06, "loss": 0.7804, "step": 147240 }, { "epoch": 12.24, "learning_rate": 2.3694149599534405e-06, "loss": 0.8393, "step": 147250 }, { "epoch": 12.24, "learning_rate": 2.369304104425907e-06, "loss": 0.7553, "step": 147260 }, { "epoch": 12.24, "learning_rate": 2.369193248898373e-06, "loss": 0.7446, "step": 147270 }, { "epoch": 12.24, "learning_rate": 2.3690823933708394e-06, "loss": 0.8124, "step": 147280 }, { "epoch": 12.24, "learning_rate": 2.3689715378433057e-06, "loss": 0.7803, "step": 147290 }, { "epoch": 12.24, "learning_rate": 2.368860682315772e-06, "loss": 0.8568, "step": 147300 }, { "epoch": 12.24, "learning_rate": 2.368749826788238e-06, "loss": 0.8041, "step": 147310 }, { "epoch": 12.25, "learning_rate": 2.3686389712607046e-06, "loss": 0.6905, "step": 147320 }, { "epoch": 12.25, "learning_rate": 2.3685281157331704e-06, "loss": 0.8465, "step": 147330 }, { "epoch": 12.25, "learning_rate": 2.3684172602056367e-06, "loss": 0.7945, "step": 147340 }, { "epoch": 12.25, "learning_rate": 2.368306404678103e-06, "loss": 0.7745, "step": 147350 }, { "epoch": 12.25, "learning_rate": 2.3681955491505693e-06, "loss": 0.7431, "step": 147360 }, { "epoch": 12.25, "learning_rate": 2.368084693623036e-06, "loss": 0.7048, "step": 147370 }, { "epoch": 12.25, "learning_rate": 2.367973838095502e-06, "loss": 0.8765, "step": 147380 }, { "epoch": 12.25, "learning_rate": 2.367862982567968e-06, "loss": 0.7893, "step": 147390 }, { "epoch": 12.25, "learning_rate": 2.3677521270404345e-06, "loss": 0.77, "step": 147400 }, { "epoch": 12.25, "learning_rate": 2.3676412715129008e-06, "loss": 0.7471, "step": 147410 }, { "epoch": 12.25, "learning_rate": 2.3675304159853667e-06, "loss": 0.7361, "step": 147420 }, { "epoch": 12.25, "learning_rate": 2.3674195604578334e-06, "loss": 0.8419, "step": 147430 }, { "epoch": 12.26, "learning_rate": 2.3673087049302992e-06, "loss": 0.7452, "step": 147440 }, { "epoch": 12.26, "learning_rate": 2.367197849402766e-06, "loss": 0.7883, "step": 147450 }, { "epoch": 12.26, "learning_rate": 2.367086993875232e-06, "loss": 0.7715, "step": 147460 }, { "epoch": 12.26, "learning_rate": 2.366976138347698e-06, "loss": 0.7525, "step": 147470 }, { "epoch": 12.26, "learning_rate": 2.366865282820165e-06, "loss": 0.8329, "step": 147480 }, { "epoch": 12.26, "learning_rate": 2.3667544272926307e-06, "loss": 0.8723, "step": 147490 }, { "epoch": 12.26, "learning_rate": 2.366643571765097e-06, "loss": 0.7545, "step": 147500 }, { "epoch": 12.26, "learning_rate": 2.3665327162375633e-06, "loss": 0.8312, "step": 147510 }, { "epoch": 12.26, "learning_rate": 2.3664218607100296e-06, "loss": 0.7368, "step": 147520 }, { "epoch": 12.26, "learning_rate": 2.366311005182496e-06, "loss": 0.8372, "step": 147530 }, { "epoch": 12.26, "learning_rate": 2.366200149654962e-06, "loss": 0.7058, "step": 147540 }, { "epoch": 12.26, "learning_rate": 2.366089294127428e-06, "loss": 0.7757, "step": 147550 }, { "epoch": 12.26, "learning_rate": 2.365978438599895e-06, "loss": 0.7324, "step": 147560 }, { "epoch": 12.27, "learning_rate": 2.3658675830723607e-06, "loss": 0.8383, "step": 147570 }, { "epoch": 12.27, "learning_rate": 2.365756727544827e-06, "loss": 0.7507, "step": 147580 }, { "epoch": 12.27, "learning_rate": 2.3656458720172933e-06, "loss": 0.7769, "step": 147590 }, { "epoch": 12.27, "learning_rate": 2.3655350164897595e-06, "loss": 0.6998, "step": 147600 }, { "epoch": 12.27, "learning_rate": 2.3654241609622263e-06, "loss": 0.7522, "step": 147610 }, { "epoch": 12.27, "learning_rate": 2.365313305434692e-06, "loss": 0.7776, "step": 147620 }, { "epoch": 12.27, "learning_rate": 2.3652024499071584e-06, "loss": 0.8309, "step": 147630 }, { "epoch": 12.27, "learning_rate": 2.3650915943796247e-06, "loss": 0.7228, "step": 147640 }, { "epoch": 12.27, "learning_rate": 2.3649918244048443e-06, "loss": 0.7301, "step": 147650 }, { "epoch": 12.27, "learning_rate": 2.3648809688773106e-06, "loss": 0.7218, "step": 147660 }, { "epoch": 12.27, "learning_rate": 2.3647701133497764e-06, "loss": 0.7522, "step": 147670 }, { "epoch": 12.27, "learning_rate": 2.364659257822243e-06, "loss": 0.7629, "step": 147680 }, { "epoch": 12.28, "learning_rate": 2.3645484022947095e-06, "loss": 0.7946, "step": 147690 }, { "epoch": 12.28, "learning_rate": 2.3644375467671757e-06, "loss": 0.7511, "step": 147700 }, { "epoch": 12.28, "learning_rate": 2.364326691239642e-06, "loss": 0.762, "step": 147710 }, { "epoch": 12.28, "learning_rate": 2.364215835712108e-06, "loss": 0.8154, "step": 147720 }, { "epoch": 12.28, "learning_rate": 2.3641049801845746e-06, "loss": 0.8604, "step": 147730 }, { "epoch": 12.28, "learning_rate": 2.3639941246570405e-06, "loss": 0.7848, "step": 147740 }, { "epoch": 12.28, "learning_rate": 2.363883269129507e-06, "loss": 0.7372, "step": 147750 }, { "epoch": 12.28, "learning_rate": 2.363772413601973e-06, "loss": 0.71, "step": 147760 }, { "epoch": 12.28, "learning_rate": 2.3636615580744394e-06, "loss": 0.7575, "step": 147770 }, { "epoch": 12.28, "learning_rate": 2.3635507025469053e-06, "loss": 0.8191, "step": 147780 }, { "epoch": 12.28, "learning_rate": 2.363439847019372e-06, "loss": 0.7411, "step": 147790 }, { "epoch": 12.28, "learning_rate": 2.363328991491838e-06, "loss": 0.8051, "step": 147800 }, { "epoch": 12.29, "learning_rate": 2.3632181359643046e-06, "loss": 0.7862, "step": 147810 }, { "epoch": 12.29, "learning_rate": 2.363107280436771e-06, "loss": 0.7881, "step": 147820 }, { "epoch": 12.29, "learning_rate": 2.3629964249092367e-06, "loss": 0.7948, "step": 147830 }, { "epoch": 12.29, "learning_rate": 2.3628855693817035e-06, "loss": 0.7668, "step": 147840 }, { "epoch": 12.29, "learning_rate": 2.3627747138541693e-06, "loss": 0.7374, "step": 147850 }, { "epoch": 12.29, "learning_rate": 2.362663858326636e-06, "loss": 0.7487, "step": 147860 }, { "epoch": 12.29, "learning_rate": 2.362553002799102e-06, "loss": 0.7782, "step": 147870 }, { "epoch": 12.29, "learning_rate": 2.3624421472715682e-06, "loss": 0.8933, "step": 147880 }, { "epoch": 12.29, "learning_rate": 2.3623312917440345e-06, "loss": 0.7902, "step": 147890 }, { "epoch": 12.29, "learning_rate": 2.362220436216501e-06, "loss": 0.7623, "step": 147900 }, { "epoch": 12.29, "learning_rate": 2.3621095806889667e-06, "loss": 0.7595, "step": 147910 }, { "epoch": 12.29, "learning_rate": 2.3619987251614334e-06, "loss": 0.8159, "step": 147920 }, { "epoch": 12.3, "learning_rate": 2.3618878696338993e-06, "loss": 0.8742, "step": 147930 }, { "epoch": 12.3, "learning_rate": 2.3617770141063656e-06, "loss": 0.8229, "step": 147940 }, { "epoch": 12.3, "learning_rate": 2.3616661585788323e-06, "loss": 0.8064, "step": 147950 }, { "epoch": 12.3, "learning_rate": 2.361555303051298e-06, "loss": 0.7715, "step": 147960 }, { "epoch": 12.3, "learning_rate": 2.361444447523765e-06, "loss": 0.7306, "step": 147970 }, { "epoch": 12.3, "learning_rate": 2.3613335919962307e-06, "loss": 0.8183, "step": 147980 }, { "epoch": 12.3, "learning_rate": 2.361222736468697e-06, "loss": 0.7999, "step": 147990 }, { "epoch": 12.3, "learning_rate": 2.3611118809411633e-06, "loss": 0.7173, "step": 148000 }, { "epoch": 12.3, "learning_rate": 2.3610010254136296e-06, "loss": 0.7738, "step": 148010 }, { "epoch": 12.3, "learning_rate": 2.3608901698860955e-06, "loss": 0.7278, "step": 148020 }, { "epoch": 12.3, "learning_rate": 2.3607793143585622e-06, "loss": 0.8805, "step": 148030 }, { "epoch": 12.3, "learning_rate": 2.360668458831028e-06, "loss": 0.7248, "step": 148040 }, { "epoch": 12.31, "learning_rate": 2.360557603303495e-06, "loss": 0.809, "step": 148050 }, { "epoch": 12.31, "learning_rate": 2.360446747775961e-06, "loss": 0.7882, "step": 148060 }, { "epoch": 12.31, "learning_rate": 2.360335892248427e-06, "loss": 0.7648, "step": 148070 }, { "epoch": 12.31, "learning_rate": 2.3602250367208937e-06, "loss": 0.7925, "step": 148080 }, { "epoch": 12.31, "learning_rate": 2.3601141811933596e-06, "loss": 0.7673, "step": 148090 }, { "epoch": 12.31, "learning_rate": 2.360003325665826e-06, "loss": 0.8178, "step": 148100 }, { "epoch": 12.31, "learning_rate": 2.359892470138292e-06, "loss": 0.7141, "step": 148110 }, { "epoch": 12.31, "learning_rate": 2.3597816146107585e-06, "loss": 0.8401, "step": 148120 }, { "epoch": 12.31, "learning_rate": 2.3596707590832248e-06, "loss": 0.8254, "step": 148130 }, { "epoch": 12.31, "learning_rate": 2.359559903555691e-06, "loss": 0.7556, "step": 148140 }, { "epoch": 12.31, "learning_rate": 2.359449048028157e-06, "loss": 0.7363, "step": 148150 }, { "epoch": 12.31, "learning_rate": 2.3593381925006236e-06, "loss": 0.844, "step": 148160 }, { "epoch": 12.32, "learning_rate": 2.3592273369730895e-06, "loss": 0.7841, "step": 148170 }, { "epoch": 12.32, "learning_rate": 2.359116481445556e-06, "loss": 0.8527, "step": 148180 }, { "epoch": 12.32, "learning_rate": 2.3590056259180225e-06, "loss": 0.7367, "step": 148190 }, { "epoch": 12.32, "learning_rate": 2.3588947703904884e-06, "loss": 0.7983, "step": 148200 }, { "epoch": 12.32, "learning_rate": 2.358783914862955e-06, "loss": 0.7993, "step": 148210 }, { "epoch": 12.32, "learning_rate": 2.358673059335421e-06, "loss": 0.7583, "step": 148220 }, { "epoch": 12.32, "learning_rate": 2.3585622038078873e-06, "loss": 0.7841, "step": 148230 }, { "epoch": 12.32, "learning_rate": 2.3584513482803536e-06, "loss": 0.8132, "step": 148240 }, { "epoch": 12.32, "learning_rate": 2.35834049275282e-06, "loss": 0.7661, "step": 148250 }, { "epoch": 12.32, "learning_rate": 2.3582296372252857e-06, "loss": 0.7838, "step": 148260 }, { "epoch": 12.32, "learning_rate": 2.3581187816977525e-06, "loss": 0.7712, "step": 148270 }, { "epoch": 12.32, "learning_rate": 2.3580079261702183e-06, "loss": 0.8157, "step": 148280 }, { "epoch": 12.33, "learning_rate": 2.3578970706426846e-06, "loss": 0.7244, "step": 148290 }, { "epoch": 12.33, "learning_rate": 2.357786215115151e-06, "loss": 0.8306, "step": 148300 }, { "epoch": 12.33, "learning_rate": 2.3576753595876172e-06, "loss": 0.7702, "step": 148310 }, { "epoch": 12.33, "learning_rate": 2.357564504060084e-06, "loss": 0.8163, "step": 148320 }, { "epoch": 12.33, "learning_rate": 2.35745364853255e-06, "loss": 0.7942, "step": 148330 }, { "epoch": 12.33, "learning_rate": 2.357342793005016e-06, "loss": 0.8, "step": 148340 }, { "epoch": 12.33, "learning_rate": 2.3572319374774824e-06, "loss": 0.7775, "step": 148350 }, { "epoch": 12.33, "learning_rate": 2.3571210819499487e-06, "loss": 0.7524, "step": 148360 }, { "epoch": 12.33, "learning_rate": 2.3570102264224146e-06, "loss": 0.7961, "step": 148370 }, { "epoch": 12.33, "learning_rate": 2.3568993708948813e-06, "loss": 0.874, "step": 148380 }, { "epoch": 12.33, "learning_rate": 2.356788515367347e-06, "loss": 0.7546, "step": 148390 }, { "epoch": 12.33, "learning_rate": 2.356677659839814e-06, "loss": 0.768, "step": 148400 }, { "epoch": 12.34, "learning_rate": 2.3565668043122798e-06, "loss": 0.7064, "step": 148410 }, { "epoch": 12.34, "learning_rate": 2.356455948784746e-06, "loss": 0.7374, "step": 148420 }, { "epoch": 12.34, "learning_rate": 2.3563450932572128e-06, "loss": 0.8486, "step": 148430 }, { "epoch": 12.34, "learning_rate": 2.3562342377296786e-06, "loss": 0.775, "step": 148440 }, { "epoch": 12.34, "learning_rate": 2.356123382202145e-06, "loss": 0.7384, "step": 148450 }, { "epoch": 12.34, "learning_rate": 2.3560125266746112e-06, "loss": 0.7768, "step": 148460 }, { "epoch": 12.34, "learning_rate": 2.3559016711470775e-06, "loss": 0.8046, "step": 148470 }, { "epoch": 12.34, "learning_rate": 2.355790815619544e-06, "loss": 0.8319, "step": 148480 }, { "epoch": 12.34, "learning_rate": 2.35567996009201e-06, "loss": 0.8526, "step": 148490 }, { "epoch": 12.34, "learning_rate": 2.355569104564476e-06, "loss": 0.7564, "step": 148500 }, { "epoch": 12.34, "learning_rate": 2.3554582490369427e-06, "loss": 0.8185, "step": 148510 }, { "epoch": 12.34, "learning_rate": 2.3553473935094086e-06, "loss": 0.7472, "step": 148520 }, { "epoch": 12.35, "learning_rate": 2.355236537981875e-06, "loss": 0.856, "step": 148530 }, { "epoch": 12.35, "learning_rate": 2.355125682454341e-06, "loss": 0.7614, "step": 148540 }, { "epoch": 12.35, "learning_rate": 2.3550148269268075e-06, "loss": 0.7924, "step": 148550 }, { "epoch": 12.35, "learning_rate": 2.354903971399274e-06, "loss": 0.7922, "step": 148560 }, { "epoch": 12.35, "learning_rate": 2.35479311587174e-06, "loss": 0.7524, "step": 148570 }, { "epoch": 12.35, "learning_rate": 2.3546822603442063e-06, "loss": 0.8094, "step": 148580 }, { "epoch": 12.35, "learning_rate": 2.3545714048166726e-06, "loss": 0.8598, "step": 148590 }, { "epoch": 12.35, "learning_rate": 2.354460549289139e-06, "loss": 0.7951, "step": 148600 }, { "epoch": 12.35, "learning_rate": 2.354349693761605e-06, "loss": 0.7647, "step": 148610 }, { "epoch": 12.35, "learning_rate": 2.3542388382340715e-06, "loss": 0.8019, "step": 148620 }, { "epoch": 12.35, "learning_rate": 2.3541279827065374e-06, "loss": 0.8107, "step": 148630 }, { "epoch": 12.35, "learning_rate": 2.354017127179004e-06, "loss": 0.7209, "step": 148640 }, { "epoch": 12.36, "learning_rate": 2.35390627165147e-06, "loss": 0.8098, "step": 148650 }, { "epoch": 12.36, "learning_rate": 2.3537954161239363e-06, "loss": 0.7857, "step": 148660 }, { "epoch": 12.36, "learning_rate": 2.3536845605964026e-06, "loss": 0.8079, "step": 148670 }, { "epoch": 12.36, "learning_rate": 2.353573705068869e-06, "loss": 0.8478, "step": 148680 }, { "epoch": 12.36, "learning_rate": 2.353462849541335e-06, "loss": 0.8199, "step": 148690 }, { "epoch": 12.36, "learning_rate": 2.3533519940138015e-06, "loss": 0.8222, "step": 148700 }, { "epoch": 12.36, "learning_rate": 2.3532411384862678e-06, "loss": 0.8241, "step": 148710 }, { "epoch": 12.36, "learning_rate": 2.3531302829587336e-06, "loss": 0.7095, "step": 148720 }, { "epoch": 12.36, "learning_rate": 2.3530194274312004e-06, "loss": 0.8315, "step": 148730 }, { "epoch": 12.36, "learning_rate": 2.3529085719036662e-06, "loss": 0.8692, "step": 148740 }, { "epoch": 12.36, "learning_rate": 2.352797716376133e-06, "loss": 0.7779, "step": 148750 }, { "epoch": 12.36, "learning_rate": 2.352686860848599e-06, "loss": 0.7336, "step": 148760 }, { "epoch": 12.37, "learning_rate": 2.352576005321065e-06, "loss": 0.7876, "step": 148770 }, { "epoch": 12.37, "learning_rate": 2.3524651497935314e-06, "loss": 0.833, "step": 148780 }, { "epoch": 12.37, "learning_rate": 2.3523542942659977e-06, "loss": 0.776, "step": 148790 }, { "epoch": 12.37, "learning_rate": 2.352243438738464e-06, "loss": 0.7849, "step": 148800 }, { "epoch": 12.37, "learning_rate": 2.3521325832109303e-06, "loss": 0.784, "step": 148810 }, { "epoch": 12.37, "learning_rate": 2.3520217276833966e-06, "loss": 0.8229, "step": 148820 }, { "epoch": 12.37, "learning_rate": 2.351910872155863e-06, "loss": 0.8045, "step": 148830 }, { "epoch": 12.37, "learning_rate": 2.351800016628329e-06, "loss": 0.7694, "step": 148840 }, { "epoch": 12.37, "learning_rate": 2.351689161100795e-06, "loss": 0.7662, "step": 148850 }, { "epoch": 12.37, "learning_rate": 2.3515783055732618e-06, "loss": 0.7968, "step": 148860 }, { "epoch": 12.37, "learning_rate": 2.3514674500457276e-06, "loss": 0.7702, "step": 148870 }, { "epoch": 12.37, "learning_rate": 2.351356594518194e-06, "loss": 0.8533, "step": 148880 }, { "epoch": 12.38, "learning_rate": 2.3512457389906602e-06, "loss": 0.7595, "step": 148890 }, { "epoch": 12.38, "learning_rate": 2.3511348834631265e-06, "loss": 0.7993, "step": 148900 }, { "epoch": 12.38, "learning_rate": 2.351024027935593e-06, "loss": 0.7555, "step": 148910 }, { "epoch": 12.38, "learning_rate": 2.350913172408059e-06, "loss": 0.7724, "step": 148920 }, { "epoch": 12.38, "learning_rate": 2.3508023168805254e-06, "loss": 0.8446, "step": 148930 }, { "epoch": 12.38, "learning_rate": 2.3506914613529917e-06, "loss": 0.7457, "step": 148940 }, { "epoch": 12.38, "learning_rate": 2.350580605825458e-06, "loss": 0.7963, "step": 148950 }, { "epoch": 12.38, "learning_rate": 2.350469750297924e-06, "loss": 0.7394, "step": 148960 }, { "epoch": 12.38, "learning_rate": 2.3503588947703906e-06, "loss": 0.8497, "step": 148970 }, { "epoch": 12.38, "learning_rate": 2.3502480392428565e-06, "loss": 0.8183, "step": 148980 }, { "epoch": 12.38, "learning_rate": 2.350137183715323e-06, "loss": 0.7955, "step": 148990 }, { "epoch": 12.38, "learning_rate": 2.350026328187789e-06, "loss": 0.7512, "step": 149000 }, { "epoch": 12.39, "learning_rate": 2.3499154726602554e-06, "loss": 0.82, "step": 149010 }, { "epoch": 12.39, "learning_rate": 2.3498046171327216e-06, "loss": 0.7862, "step": 149020 }, { "epoch": 12.39, "learning_rate": 2.349693761605188e-06, "loss": 0.803, "step": 149030 }, { "epoch": 12.39, "learning_rate": 2.349582906077654e-06, "loss": 0.7941, "step": 149040 }, { "epoch": 12.39, "learning_rate": 2.3494720505501205e-06, "loss": 0.746, "step": 149050 }, { "epoch": 12.39, "learning_rate": 2.349361195022587e-06, "loss": 0.8028, "step": 149060 }, { "epoch": 12.39, "learning_rate": 2.3492503394950527e-06, "loss": 0.8056, "step": 149070 }, { "epoch": 12.39, "learning_rate": 2.3491394839675194e-06, "loss": 0.8305, "step": 149080 }, { "epoch": 12.39, "learning_rate": 2.3490286284399853e-06, "loss": 0.7816, "step": 149090 }, { "epoch": 12.39, "learning_rate": 2.348917772912452e-06, "loss": 0.7641, "step": 149100 }, { "epoch": 12.39, "learning_rate": 2.348806917384918e-06, "loss": 0.8263, "step": 149110 }, { "epoch": 12.39, "learning_rate": 2.348696061857384e-06, "loss": 0.7675, "step": 149120 }, { "epoch": 12.4, "learning_rate": 2.3485852063298505e-06, "loss": 0.89, "step": 149130 }, { "epoch": 12.4, "learning_rate": 2.3484743508023168e-06, "loss": 0.7622, "step": 149140 }, { "epoch": 12.4, "learning_rate": 2.3483634952747826e-06, "loss": 0.7063, "step": 149150 }, { "epoch": 12.4, "learning_rate": 2.3482526397472494e-06, "loss": 0.7689, "step": 149160 }, { "epoch": 12.4, "learning_rate": 2.3481417842197157e-06, "loss": 0.7623, "step": 149170 }, { "epoch": 12.4, "learning_rate": 2.348030928692182e-06, "loss": 0.8134, "step": 149180 }, { "epoch": 12.4, "learning_rate": 2.3479200731646482e-06, "loss": 0.7511, "step": 149190 }, { "epoch": 12.4, "learning_rate": 2.347809217637114e-06, "loss": 0.7728, "step": 149200 }, { "epoch": 12.4, "learning_rate": 2.347698362109581e-06, "loss": 0.7946, "step": 149210 }, { "epoch": 12.4, "learning_rate": 2.3475875065820467e-06, "loss": 0.818, "step": 149220 }, { "epoch": 12.4, "learning_rate": 2.347476651054513e-06, "loss": 0.8517, "step": 149230 }, { "epoch": 12.4, "learning_rate": 2.3473657955269793e-06, "loss": 0.786, "step": 149240 }, { "epoch": 12.41, "learning_rate": 2.3472549399994456e-06, "loss": 0.7847, "step": 149250 }, { "epoch": 12.41, "learning_rate": 2.347144084471912e-06, "loss": 0.8188, "step": 149260 }, { "epoch": 12.41, "learning_rate": 2.347033228944378e-06, "loss": 0.7289, "step": 149270 }, { "epoch": 12.41, "learning_rate": 2.346922373416844e-06, "loss": 0.8542, "step": 149280 }, { "epoch": 12.41, "learning_rate": 2.3468115178893108e-06, "loss": 0.7589, "step": 149290 }, { "epoch": 12.41, "learning_rate": 2.346700662361777e-06, "loss": 0.8405, "step": 149300 }, { "epoch": 12.41, "learning_rate": 2.346589806834243e-06, "loss": 0.8076, "step": 149310 }, { "epoch": 12.41, "learning_rate": 2.3464789513067097e-06, "loss": 0.8422, "step": 149320 }, { "epoch": 12.41, "learning_rate": 2.3463680957791755e-06, "loss": 0.828, "step": 149330 }, { "epoch": 12.41, "learning_rate": 2.3462572402516423e-06, "loss": 0.803, "step": 149340 }, { "epoch": 12.41, "learning_rate": 2.346146384724108e-06, "loss": 0.7887, "step": 149350 }, { "epoch": 12.41, "learning_rate": 2.3460355291965744e-06, "loss": 0.7517, "step": 149360 }, { "epoch": 12.42, "learning_rate": 2.3459246736690407e-06, "loss": 0.7872, "step": 149370 }, { "epoch": 12.42, "learning_rate": 2.345813818141507e-06, "loss": 0.8885, "step": 149380 }, { "epoch": 12.42, "learning_rate": 2.345702962613973e-06, "loss": 0.8043, "step": 149390 }, { "epoch": 12.42, "learning_rate": 2.3455921070864396e-06, "loss": 0.7623, "step": 149400 }, { "epoch": 12.42, "learning_rate": 2.345481251558906e-06, "loss": 0.7891, "step": 149410 }, { "epoch": 12.42, "learning_rate": 2.345370396031372e-06, "loss": 0.7804, "step": 149420 }, { "epoch": 12.42, "learning_rate": 2.3452595405038385e-06, "loss": 0.8415, "step": 149430 }, { "epoch": 12.42, "learning_rate": 2.3451486849763044e-06, "loss": 0.7839, "step": 149440 }, { "epoch": 12.42, "learning_rate": 2.345037829448771e-06, "loss": 0.8855, "step": 149450 }, { "epoch": 12.42, "learning_rate": 2.344926973921237e-06, "loss": 0.8019, "step": 149460 }, { "epoch": 12.42, "learning_rate": 2.3448161183937032e-06, "loss": 0.8013, "step": 149470 }, { "epoch": 12.42, "learning_rate": 2.3447052628661695e-06, "loss": 0.8451, "step": 149480 }, { "epoch": 12.43, "learning_rate": 2.344594407338636e-06, "loss": 0.7898, "step": 149490 }, { "epoch": 12.43, "learning_rate": 2.3444835518111017e-06, "loss": 0.7485, "step": 149500 }, { "epoch": 12.43, "learning_rate": 2.3443726962835684e-06, "loss": 0.8444, "step": 149510 }, { "epoch": 12.43, "learning_rate": 2.3442618407560343e-06, "loss": 0.7743, "step": 149520 }, { "epoch": 12.43, "learning_rate": 2.344150985228501e-06, "loss": 0.8194, "step": 149530 }, { "epoch": 12.43, "learning_rate": 2.3440401297009673e-06, "loss": 0.888, "step": 149540 }, { "epoch": 12.43, "learning_rate": 2.343929274173433e-06, "loss": 0.7687, "step": 149550 }, { "epoch": 12.43, "learning_rate": 2.3438184186459e-06, "loss": 0.7686, "step": 149560 }, { "epoch": 12.43, "learning_rate": 2.3437075631183658e-06, "loss": 0.7434, "step": 149570 }, { "epoch": 12.43, "learning_rate": 2.343596707590832e-06, "loss": 0.8309, "step": 149580 }, { "epoch": 12.43, "learning_rate": 2.3434858520632984e-06, "loss": 0.8337, "step": 149590 }, { "epoch": 12.43, "learning_rate": 2.3433749965357647e-06, "loss": 0.8744, "step": 149600 }, { "epoch": 12.44, "learning_rate": 2.343264141008231e-06, "loss": 0.8307, "step": 149610 }, { "epoch": 12.44, "learning_rate": 2.3431532854806973e-06, "loss": 0.7401, "step": 149620 }, { "epoch": 12.44, "learning_rate": 2.343042429953163e-06, "loss": 0.8143, "step": 149630 }, { "epoch": 12.44, "learning_rate": 2.34293157442563e-06, "loss": 0.7807, "step": 149640 }, { "epoch": 12.44, "learning_rate": 2.3428207188980957e-06, "loss": 0.7353, "step": 149650 }, { "epoch": 12.44, "learning_rate": 2.342709863370562e-06, "loss": 0.8104, "step": 149660 }, { "epoch": 12.44, "learning_rate": 2.3425990078430287e-06, "loss": 0.7923, "step": 149670 }, { "epoch": 12.44, "learning_rate": 2.3424881523154946e-06, "loss": 0.8653, "step": 149680 }, { "epoch": 12.44, "learning_rate": 2.3423772967879613e-06, "loss": 0.7931, "step": 149690 }, { "epoch": 12.44, "learning_rate": 2.342266441260427e-06, "loss": 0.7334, "step": 149700 }, { "epoch": 12.44, "learning_rate": 2.3421555857328935e-06, "loss": 0.741, "step": 149710 }, { "epoch": 12.44, "learning_rate": 2.3420447302053598e-06, "loss": 0.7197, "step": 149720 }, { "epoch": 12.45, "learning_rate": 2.341933874677826e-06, "loss": 0.8458, "step": 149730 }, { "epoch": 12.45, "learning_rate": 2.341823019150292e-06, "loss": 0.818, "step": 149740 }, { "epoch": 12.45, "learning_rate": 2.3417121636227587e-06, "loss": 0.8181, "step": 149750 }, { "epoch": 12.45, "learning_rate": 2.3416013080952245e-06, "loss": 0.7888, "step": 149760 }, { "epoch": 12.45, "learning_rate": 2.3414904525676913e-06, "loss": 0.7319, "step": 149770 }, { "epoch": 12.45, "learning_rate": 2.3413795970401576e-06, "loss": 0.869, "step": 149780 }, { "epoch": 12.45, "learning_rate": 2.3412687415126234e-06, "loss": 0.8212, "step": 149790 }, { "epoch": 12.45, "learning_rate": 2.34115788598509e-06, "loss": 0.8144, "step": 149800 }, { "epoch": 12.45, "learning_rate": 2.341047030457556e-06, "loss": 0.7332, "step": 149810 }, { "epoch": 12.45, "learning_rate": 2.3409361749300223e-06, "loss": 0.7523, "step": 149820 }, { "epoch": 12.45, "learning_rate": 2.3408253194024886e-06, "loss": 0.8327, "step": 149830 }, { "epoch": 12.45, "learning_rate": 2.340714463874955e-06, "loss": 0.7933, "step": 149840 }, { "epoch": 12.46, "learning_rate": 2.340603608347421e-06, "loss": 0.8148, "step": 149850 }, { "epoch": 12.46, "learning_rate": 2.3404927528198875e-06, "loss": 0.8029, "step": 149860 }, { "epoch": 12.46, "learning_rate": 2.3403818972923534e-06, "loss": 0.8339, "step": 149870 }, { "epoch": 12.46, "learning_rate": 2.34027104176482e-06, "loss": 0.8117, "step": 149880 }, { "epoch": 12.46, "learning_rate": 2.340160186237286e-06, "loss": 0.7421, "step": 149890 }, { "epoch": 12.46, "learning_rate": 2.3400493307097523e-06, "loss": 0.7644, "step": 149900 }, { "epoch": 12.46, "learning_rate": 2.339938475182219e-06, "loss": 0.7357, "step": 149910 }, { "epoch": 12.46, "learning_rate": 2.339827619654685e-06, "loss": 0.7478, "step": 149920 }, { "epoch": 12.46, "learning_rate": 2.3397167641271516e-06, "loss": 0.8093, "step": 149930 }, { "epoch": 12.46, "learning_rate": 2.3396059085996174e-06, "loss": 0.7494, "step": 149940 }, { "epoch": 12.46, "learning_rate": 2.3394950530720837e-06, "loss": 0.7592, "step": 149950 }, { "epoch": 12.46, "learning_rate": 2.33938419754455e-06, "loss": 0.8028, "step": 149960 }, { "epoch": 12.47, "learning_rate": 2.3392733420170163e-06, "loss": 0.7407, "step": 149970 }, { "epoch": 12.47, "learning_rate": 2.339162486489482e-06, "loss": 0.8522, "step": 149980 }, { "epoch": 12.47, "learning_rate": 2.339051630961949e-06, "loss": 0.7917, "step": 149990 }, { "epoch": 12.47, "learning_rate": 2.3389407754344148e-06, "loss": 0.8004, "step": 150000 }, { "epoch": 12.47, "learning_rate": 2.338829919906881e-06, "loss": 0.7469, "step": 150010 }, { "epoch": 12.47, "learning_rate": 2.3387190643793474e-06, "loss": 0.8242, "step": 150020 }, { "epoch": 12.47, "learning_rate": 2.3386082088518137e-06, "loss": 0.842, "step": 150030 }, { "epoch": 12.47, "learning_rate": 2.3384973533242804e-06, "loss": 0.8227, "step": 150040 }, { "epoch": 12.47, "learning_rate": 2.3383864977967463e-06, "loss": 0.7686, "step": 150050 }, { "epoch": 12.47, "learning_rate": 2.3382756422692126e-06, "loss": 0.7861, "step": 150060 }, { "epoch": 12.47, "learning_rate": 2.338164786741679e-06, "loss": 0.7776, "step": 150070 }, { "epoch": 12.47, "learning_rate": 2.338053931214145e-06, "loss": 0.8188, "step": 150080 }, { "epoch": 12.48, "learning_rate": 2.337943075686611e-06, "loss": 0.7977, "step": 150090 }, { "epoch": 12.48, "learning_rate": 2.3378322201590777e-06, "loss": 0.8412, "step": 150100 }, { "epoch": 12.48, "learning_rate": 2.3377213646315436e-06, "loss": 0.772, "step": 150110 }, { "epoch": 12.48, "learning_rate": 2.3376105091040103e-06, "loss": 0.8593, "step": 150120 }, { "epoch": 12.48, "learning_rate": 2.337499653576476e-06, "loss": 0.8347, "step": 150130 }, { "epoch": 12.48, "learning_rate": 2.3373887980489425e-06, "loss": 0.7374, "step": 150140 }, { "epoch": 12.48, "learning_rate": 2.337277942521409e-06, "loss": 0.7384, "step": 150150 }, { "epoch": 12.48, "learning_rate": 2.337167086993875e-06, "loss": 0.7648, "step": 150160 }, { "epoch": 12.48, "learning_rate": 2.3370562314663414e-06, "loss": 0.7644, "step": 150170 }, { "epoch": 12.48, "learning_rate": 2.3369453759388077e-06, "loss": 0.8, "step": 150180 }, { "epoch": 12.48, "learning_rate": 2.336834520411274e-06, "loss": 0.7726, "step": 150190 }, { "epoch": 12.48, "learning_rate": 2.3367236648837403e-06, "loss": 0.7694, "step": 150200 }, { "epoch": 12.49, "learning_rate": 2.3366128093562066e-06, "loss": 0.7673, "step": 150210 }, { "epoch": 12.49, "learning_rate": 2.3365019538286724e-06, "loss": 0.8201, "step": 150220 }, { "epoch": 12.49, "learning_rate": 2.336391098301139e-06, "loss": 0.9228, "step": 150230 }, { "epoch": 12.49, "learning_rate": 2.336280242773605e-06, "loss": 0.7877, "step": 150240 }, { "epoch": 12.49, "learning_rate": 2.3361693872460713e-06, "loss": 0.8011, "step": 150250 }, { "epoch": 12.49, "learning_rate": 2.3360585317185376e-06, "loss": 0.7735, "step": 150260 }, { "epoch": 12.49, "learning_rate": 2.3359587617437576e-06, "loss": 0.7695, "step": 150270 }, { "epoch": 12.49, "learning_rate": 2.3358479062162234e-06, "loss": 0.8459, "step": 150280 }, { "epoch": 12.49, "learning_rate": 2.33573705068869e-06, "loss": 0.8334, "step": 150290 }, { "epoch": 12.49, "learning_rate": 2.335626195161156e-06, "loss": 0.7347, "step": 150300 }, { "epoch": 12.49, "learning_rate": 2.3355153396336223e-06, "loss": 0.7406, "step": 150310 }, { "epoch": 12.49, "learning_rate": 2.3354044841060886e-06, "loss": 0.7958, "step": 150320 }, { "epoch": 12.5, "learning_rate": 2.335293628578555e-06, "loss": 0.8443, "step": 150330 }, { "epoch": 12.5, "learning_rate": 2.335182773051021e-06, "loss": 0.7532, "step": 150340 }, { "epoch": 12.5, "learning_rate": 2.3350719175234875e-06, "loss": 0.819, "step": 150350 }, { "epoch": 12.5, "learning_rate": 2.334961061995954e-06, "loss": 0.7498, "step": 150360 }, { "epoch": 12.5, "learning_rate": 2.33485020646842e-06, "loss": 0.7977, "step": 150370 }, { "epoch": 12.5, "learning_rate": 2.3347393509408864e-06, "loss": 0.8158, "step": 150380 }, { "epoch": 12.5, "learning_rate": 2.3346284954133523e-06, "loss": 0.7717, "step": 150390 }, { "epoch": 12.5, "learning_rate": 2.334517639885819e-06, "loss": 0.7505, "step": 150400 }, { "epoch": 12.5, "learning_rate": 2.334406784358285e-06, "loss": 0.8261, "step": 150410 }, { "epoch": 12.5, "learning_rate": 2.334295928830751e-06, "loss": 0.8236, "step": 150420 }, { "epoch": 12.5, "learning_rate": 2.3341850733032175e-06, "loss": 0.7498, "step": 150430 }, { "epoch": 12.5, "learning_rate": 2.3340742177756837e-06, "loss": 0.7856, "step": 150440 }, { "epoch": 12.51, "learning_rate": 2.3339633622481496e-06, "loss": 0.7891, "step": 150450 }, { "epoch": 12.51, "learning_rate": 2.3338525067206163e-06, "loss": 0.7335, "step": 150460 }, { "epoch": 12.51, "learning_rate": 2.333741651193082e-06, "loss": 0.782, "step": 150470 }, { "epoch": 12.51, "learning_rate": 2.333630795665549e-06, "loss": 0.8507, "step": 150480 }, { "epoch": 12.51, "learning_rate": 2.3335199401380152e-06, "loss": 0.8001, "step": 150490 }, { "epoch": 12.51, "learning_rate": 2.333409084610481e-06, "loss": 0.7081, "step": 150500 }, { "epoch": 12.51, "learning_rate": 2.333298229082948e-06, "loss": 0.7152, "step": 150510 }, { "epoch": 12.51, "learning_rate": 2.3331873735554137e-06, "loss": 0.8102, "step": 150520 }, { "epoch": 12.51, "learning_rate": 2.33307651802788e-06, "loss": 0.7948, "step": 150530 }, { "epoch": 12.51, "learning_rate": 2.3329656625003463e-06, "loss": 0.8218, "step": 150540 }, { "epoch": 12.51, "learning_rate": 2.3328548069728126e-06, "loss": 0.8097, "step": 150550 }, { "epoch": 12.51, "learning_rate": 2.332743951445279e-06, "loss": 0.7077, "step": 150560 }, { "epoch": 12.52, "learning_rate": 2.332633095917745e-06, "loss": 0.8185, "step": 150570 }, { "epoch": 12.52, "learning_rate": 2.332522240390211e-06, "loss": 0.849, "step": 150580 }, { "epoch": 12.52, "learning_rate": 2.3324113848626778e-06, "loss": 0.7608, "step": 150590 }, { "epoch": 12.52, "learning_rate": 2.3323005293351436e-06, "loss": 0.7951, "step": 150600 }, { "epoch": 12.52, "learning_rate": 2.33218967380761e-06, "loss": 0.7424, "step": 150610 }, { "epoch": 12.52, "learning_rate": 2.3320788182800766e-06, "loss": 0.7483, "step": 150620 }, { "epoch": 12.52, "learning_rate": 2.3319679627525425e-06, "loss": 0.8639, "step": 150630 }, { "epoch": 12.52, "learning_rate": 2.3318571072250092e-06, "loss": 0.8005, "step": 150640 }, { "epoch": 12.52, "learning_rate": 2.331746251697475e-06, "loss": 0.8152, "step": 150650 }, { "epoch": 12.52, "learning_rate": 2.3316353961699414e-06, "loss": 0.7626, "step": 150660 }, { "epoch": 12.52, "learning_rate": 2.3315245406424077e-06, "loss": 0.7731, "step": 150670 }, { "epoch": 12.52, "learning_rate": 2.331413685114874e-06, "loss": 0.8283, "step": 150680 }, { "epoch": 12.53, "learning_rate": 2.33130282958734e-06, "loss": 0.7621, "step": 150690 }, { "epoch": 12.53, "learning_rate": 2.3311919740598066e-06, "loss": 0.7524, "step": 150700 }, { "epoch": 12.53, "learning_rate": 2.3310811185322725e-06, "loss": 0.7851, "step": 150710 }, { "epoch": 12.53, "learning_rate": 2.330970263004739e-06, "loss": 0.801, "step": 150720 }, { "epoch": 12.53, "learning_rate": 2.3308594074772055e-06, "loss": 0.8987, "step": 150730 }, { "epoch": 12.53, "learning_rate": 2.3307485519496713e-06, "loss": 0.7792, "step": 150740 }, { "epoch": 12.53, "learning_rate": 2.330637696422138e-06, "loss": 0.7912, "step": 150750 }, { "epoch": 12.53, "learning_rate": 2.330526840894604e-06, "loss": 0.7907, "step": 150760 }, { "epoch": 12.53, "learning_rate": 2.3304159853670702e-06, "loss": 0.7986, "step": 150770 }, { "epoch": 12.53, "learning_rate": 2.3303051298395365e-06, "loss": 0.8836, "step": 150780 }, { "epoch": 12.53, "learning_rate": 2.330194274312003e-06, "loss": 0.7712, "step": 150790 }, { "epoch": 12.53, "learning_rate": 2.330083418784469e-06, "loss": 0.8256, "step": 150800 }, { "epoch": 12.54, "learning_rate": 2.3299725632569354e-06, "loss": 0.8043, "step": 150810 }, { "epoch": 12.54, "learning_rate": 2.3298617077294013e-06, "loss": 0.7773, "step": 150820 }, { "epoch": 12.54, "learning_rate": 2.329750852201868e-06, "loss": 0.8371, "step": 150830 }, { "epoch": 12.54, "learning_rate": 2.329639996674334e-06, "loss": 0.8144, "step": 150840 }, { "epoch": 12.54, "learning_rate": 2.3295291411468e-06, "loss": 0.7844, "step": 150850 }, { "epoch": 12.54, "learning_rate": 2.329418285619267e-06, "loss": 0.787, "step": 150860 }, { "epoch": 12.54, "learning_rate": 2.3293074300917328e-06, "loss": 0.7552, "step": 150870 }, { "epoch": 12.54, "learning_rate": 2.3291965745641995e-06, "loss": 0.8976, "step": 150880 }, { "epoch": 12.54, "learning_rate": 2.3290857190366653e-06, "loss": 0.7618, "step": 150890 }, { "epoch": 12.54, "learning_rate": 2.3289748635091316e-06, "loss": 0.7641, "step": 150900 }, { "epoch": 12.54, "learning_rate": 2.328864007981598e-06, "loss": 0.755, "step": 150910 }, { "epoch": 12.54, "learning_rate": 2.3287531524540642e-06, "loss": 0.8038, "step": 150920 }, { "epoch": 12.55, "learning_rate": 2.32864229692653e-06, "loss": 0.8186, "step": 150930 }, { "epoch": 12.55, "learning_rate": 2.328531441398997e-06, "loss": 0.8516, "step": 150940 }, { "epoch": 12.55, "learning_rate": 2.3284205858714627e-06, "loss": 0.7764, "step": 150950 }, { "epoch": 12.55, "learning_rate": 2.328309730343929e-06, "loss": 0.8133, "step": 150960 }, { "epoch": 12.55, "learning_rate": 2.3281988748163953e-06, "loss": 0.7518, "step": 150970 }, { "epoch": 12.55, "learning_rate": 2.3280880192888616e-06, "loss": 0.8941, "step": 150980 }, { "epoch": 12.55, "learning_rate": 2.3279771637613283e-06, "loss": 0.7836, "step": 150990 }, { "epoch": 12.55, "learning_rate": 2.327866308233794e-06, "loss": 0.8842, "step": 151000 }, { "epoch": 12.55, "learning_rate": 2.3277554527062605e-06, "loss": 0.7149, "step": 151010 }, { "epoch": 12.55, "learning_rate": 2.3276445971787268e-06, "loss": 0.6838, "step": 151020 }, { "epoch": 12.55, "learning_rate": 2.327533741651193e-06, "loss": 0.7806, "step": 151030 }, { "epoch": 12.55, "learning_rate": 2.327422886123659e-06, "loss": 0.7803, "step": 151040 }, { "epoch": 12.56, "learning_rate": 2.3273120305961256e-06, "loss": 0.7762, "step": 151050 }, { "epoch": 12.56, "learning_rate": 2.3272011750685915e-06, "loss": 0.7436, "step": 151060 }, { "epoch": 12.56, "learning_rate": 2.3270903195410582e-06, "loss": 0.7406, "step": 151070 }, { "epoch": 12.56, "learning_rate": 2.326979464013524e-06, "loss": 0.8253, "step": 151080 }, { "epoch": 12.56, "learning_rate": 2.3268686084859904e-06, "loss": 0.7742, "step": 151090 }, { "epoch": 12.56, "learning_rate": 2.326757752958457e-06, "loss": 0.7846, "step": 151100 }, { "epoch": 12.56, "learning_rate": 2.326646897430923e-06, "loss": 0.7772, "step": 151110 }, { "epoch": 12.56, "learning_rate": 2.3265360419033893e-06, "loss": 0.7496, "step": 151120 }, { "epoch": 12.56, "learning_rate": 2.3264251863758556e-06, "loss": 0.9302, "step": 151130 }, { "epoch": 12.56, "learning_rate": 2.326314330848322e-06, "loss": 0.7855, "step": 151140 }, { "epoch": 12.56, "learning_rate": 2.326203475320788e-06, "loss": 0.7732, "step": 151150 }, { "epoch": 12.56, "learning_rate": 2.3260926197932545e-06, "loss": 0.743, "step": 151160 }, { "epoch": 12.57, "learning_rate": 2.3259817642657203e-06, "loss": 0.7974, "step": 151170 }, { "epoch": 12.57, "learning_rate": 2.325870908738187e-06, "loss": 0.8151, "step": 151180 }, { "epoch": 12.57, "learning_rate": 2.325760053210653e-06, "loss": 0.8215, "step": 151190 }, { "epoch": 12.57, "learning_rate": 2.3256491976831192e-06, "loss": 0.8039, "step": 151200 }, { "epoch": 12.57, "learning_rate": 2.3255383421555855e-06, "loss": 0.7689, "step": 151210 }, { "epoch": 12.57, "learning_rate": 2.325427486628052e-06, "loss": 0.7979, "step": 151220 }, { "epoch": 12.57, "learning_rate": 2.3253166311005185e-06, "loss": 0.8784, "step": 151230 }, { "epoch": 12.57, "learning_rate": 2.3252057755729844e-06, "loss": 0.7577, "step": 151240 }, { "epoch": 12.57, "learning_rate": 2.3250949200454507e-06, "loss": 0.754, "step": 151250 }, { "epoch": 12.57, "learning_rate": 2.324984064517917e-06, "loss": 0.7299, "step": 151260 }, { "epoch": 12.57, "learning_rate": 2.3248732089903833e-06, "loss": 0.7431, "step": 151270 }, { "epoch": 12.57, "learning_rate": 2.324762353462849e-06, "loss": 0.8439, "step": 151280 }, { "epoch": 12.58, "learning_rate": 2.324651497935316e-06, "loss": 0.8054, "step": 151290 }, { "epoch": 12.58, "learning_rate": 2.3245406424077818e-06, "loss": 0.7336, "step": 151300 }, { "epoch": 12.58, "learning_rate": 2.3244297868802485e-06, "loss": 0.7051, "step": 151310 }, { "epoch": 12.58, "learning_rate": 2.3243189313527144e-06, "loss": 0.7489, "step": 151320 }, { "epoch": 12.58, "learning_rate": 2.3242080758251806e-06, "loss": 0.8059, "step": 151330 }, { "epoch": 12.58, "learning_rate": 2.324097220297647e-06, "loss": 0.7763, "step": 151340 }, { "epoch": 12.58, "learning_rate": 2.3239863647701132e-06, "loss": 0.7765, "step": 151350 }, { "epoch": 12.58, "learning_rate": 2.3238755092425795e-06, "loss": 0.7359, "step": 151360 }, { "epoch": 12.58, "learning_rate": 2.323764653715046e-06, "loss": 0.821, "step": 151370 }, { "epoch": 12.58, "learning_rate": 2.323653798187512e-06, "loss": 0.8469, "step": 151380 }, { "epoch": 12.58, "learning_rate": 2.323542942659978e-06, "loss": 0.7613, "step": 151390 }, { "epoch": 12.58, "learning_rate": 2.3234320871324447e-06, "loss": 0.7684, "step": 151400 }, { "epoch": 12.58, "learning_rate": 2.3233212316049106e-06, "loss": 0.7914, "step": 151410 }, { "epoch": 12.59, "learning_rate": 2.3232103760773773e-06, "loss": 0.7854, "step": 151420 }, { "epoch": 12.59, "learning_rate": 2.323099520549843e-06, "loss": 0.7893, "step": 151430 }, { "epoch": 12.59, "learning_rate": 2.3229886650223095e-06, "loss": 0.805, "step": 151440 }, { "epoch": 12.59, "learning_rate": 2.3228778094947758e-06, "loss": 0.7282, "step": 151450 }, { "epoch": 12.59, "learning_rate": 2.322766953967242e-06, "loss": 0.7541, "step": 151460 }, { "epoch": 12.59, "learning_rate": 2.3226560984397084e-06, "loss": 0.8127, "step": 151470 }, { "epoch": 12.59, "learning_rate": 2.3225452429121747e-06, "loss": 0.8276, "step": 151480 }, { "epoch": 12.59, "learning_rate": 2.322434387384641e-06, "loss": 0.7975, "step": 151490 }, { "epoch": 12.59, "learning_rate": 2.3223235318571072e-06, "loss": 0.7675, "step": 151500 }, { "epoch": 12.59, "learning_rate": 2.3222126763295735e-06, "loss": 0.7879, "step": 151510 }, { "epoch": 12.59, "learning_rate": 2.3221018208020394e-06, "loss": 0.7733, "step": 151520 }, { "epoch": 12.59, "learning_rate": 2.321990965274506e-06, "loss": 0.7931, "step": 151530 }, { "epoch": 12.6, "learning_rate": 2.321880109746972e-06, "loss": 0.7404, "step": 151540 }, { "epoch": 12.6, "learning_rate": 2.3217692542194383e-06, "loss": 0.8239, "step": 151550 }, { "epoch": 12.6, "learning_rate": 2.3216583986919046e-06, "loss": 0.8914, "step": 151560 }, { "epoch": 12.6, "learning_rate": 2.321547543164371e-06, "loss": 0.7856, "step": 151570 }, { "epoch": 12.6, "learning_rate": 2.321436687636837e-06, "loss": 0.841, "step": 151580 }, { "epoch": 12.6, "learning_rate": 2.3213258321093035e-06, "loss": 0.787, "step": 151590 }, { "epoch": 12.6, "learning_rate": 2.3212149765817698e-06, "loss": 0.7712, "step": 151600 }, { "epoch": 12.6, "learning_rate": 2.321104121054236e-06, "loss": 0.6721, "step": 151610 }, { "epoch": 12.6, "learning_rate": 2.3209932655267024e-06, "loss": 0.7488, "step": 151620 }, { "epoch": 12.6, "learning_rate": 2.3208824099991682e-06, "loss": 0.8261, "step": 151630 }, { "epoch": 12.6, "learning_rate": 2.320771554471635e-06, "loss": 0.748, "step": 151640 }, { "epoch": 12.6, "learning_rate": 2.320660698944101e-06, "loss": 0.7469, "step": 151650 }, { "epoch": 12.61, "learning_rate": 2.3205498434165675e-06, "loss": 0.7991, "step": 151660 }, { "epoch": 12.61, "learning_rate": 2.3204389878890334e-06, "loss": 0.7073, "step": 151670 }, { "epoch": 12.61, "learning_rate": 2.3203281323614997e-06, "loss": 0.8439, "step": 151680 }, { "epoch": 12.61, "learning_rate": 2.320217276833966e-06, "loss": 0.7722, "step": 151690 }, { "epoch": 12.61, "learning_rate": 2.3201064213064323e-06, "loss": 0.7541, "step": 151700 }, { "epoch": 12.61, "learning_rate": 2.3199955657788986e-06, "loss": 0.7531, "step": 151710 }, { "epoch": 12.61, "learning_rate": 2.319884710251365e-06, "loss": 0.749, "step": 151720 }, { "epoch": 12.61, "learning_rate": 2.319773854723831e-06, "loss": 0.8443, "step": 151730 }, { "epoch": 12.61, "learning_rate": 2.319662999196297e-06, "loss": 0.7748, "step": 151740 }, { "epoch": 12.61, "learning_rate": 2.3195521436687638e-06, "loss": 0.7696, "step": 151750 }, { "epoch": 12.61, "learning_rate": 2.3194412881412297e-06, "loss": 0.7367, "step": 151760 }, { "epoch": 12.61, "learning_rate": 2.3193304326136964e-06, "loss": 0.793, "step": 151770 }, { "epoch": 12.62, "learning_rate": 2.3192195770861622e-06, "loss": 0.8329, "step": 151780 }, { "epoch": 12.62, "learning_rate": 2.3191087215586285e-06, "loss": 0.7654, "step": 151790 }, { "epoch": 12.62, "learning_rate": 2.318997866031095e-06, "loss": 0.7817, "step": 151800 }, { "epoch": 12.62, "learning_rate": 2.318887010503561e-06, "loss": 0.702, "step": 151810 }, { "epoch": 12.62, "learning_rate": 2.318776154976027e-06, "loss": 0.7424, "step": 151820 }, { "epoch": 12.62, "learning_rate": 2.3186652994484937e-06, "loss": 0.8563, "step": 151830 }, { "epoch": 12.62, "learning_rate": 2.31855444392096e-06, "loss": 0.8612, "step": 151840 }, { "epoch": 12.62, "learning_rate": 2.3184435883934263e-06, "loss": 0.8106, "step": 151850 }, { "epoch": 12.62, "learning_rate": 2.3183327328658926e-06, "loss": 0.7189, "step": 151860 }, { "epoch": 12.62, "learning_rate": 2.3182218773383585e-06, "loss": 0.8117, "step": 151870 }, { "epoch": 12.62, "learning_rate": 2.318111021810825e-06, "loss": 0.8343, "step": 151880 }, { "epoch": 12.62, "learning_rate": 2.318000166283291e-06, "loss": 0.8214, "step": 151890 }, { "epoch": 12.63, "learning_rate": 2.3178893107557574e-06, "loss": 0.8071, "step": 151900 }, { "epoch": 12.63, "learning_rate": 2.3177784552282237e-06, "loss": 0.8128, "step": 151910 }, { "epoch": 12.63, "learning_rate": 2.31766759970069e-06, "loss": 0.7632, "step": 151920 }, { "epoch": 12.63, "learning_rate": 2.3175567441731562e-06, "loss": 0.8442, "step": 151930 }, { "epoch": 12.63, "learning_rate": 2.3174458886456225e-06, "loss": 0.7953, "step": 151940 }, { "epoch": 12.63, "learning_rate": 2.3173350331180884e-06, "loss": 0.7868, "step": 151950 }, { "epoch": 12.63, "learning_rate": 2.317224177590555e-06, "loss": 0.7472, "step": 151960 }, { "epoch": 12.63, "learning_rate": 2.3171133220630214e-06, "loss": 0.7632, "step": 151970 }, { "epoch": 12.63, "learning_rate": 2.3170024665354873e-06, "loss": 0.8533, "step": 151980 }, { "epoch": 12.63, "learning_rate": 2.316891611007954e-06, "loss": 0.7633, "step": 151990 }, { "epoch": 12.63, "learning_rate": 2.31678075548042e-06, "loss": 0.7731, "step": 152000 }, { "epoch": 12.63, "learning_rate": 2.3166698999528866e-06, "loss": 0.7534, "step": 152010 }, { "epoch": 12.64, "learning_rate": 2.3165590444253525e-06, "loss": 0.7869, "step": 152020 }, { "epoch": 12.64, "learning_rate": 2.3164481888978188e-06, "loss": 0.8296, "step": 152030 }, { "epoch": 12.64, "learning_rate": 2.316337333370285e-06, "loss": 0.8618, "step": 152040 }, { "epoch": 12.64, "learning_rate": 2.3162264778427514e-06, "loss": 0.7701, "step": 152050 }, { "epoch": 12.64, "learning_rate": 2.3161156223152172e-06, "loss": 0.748, "step": 152060 }, { "epoch": 12.64, "learning_rate": 2.316004766787684e-06, "loss": 0.7944, "step": 152070 }, { "epoch": 12.64, "learning_rate": 2.3158939112601503e-06, "loss": 0.8566, "step": 152080 }, { "epoch": 12.64, "learning_rate": 2.3157830557326165e-06, "loss": 0.754, "step": 152090 }, { "epoch": 12.64, "learning_rate": 2.315672200205083e-06, "loss": 0.717, "step": 152100 }, { "epoch": 12.64, "learning_rate": 2.3155613446775487e-06, "loss": 0.8, "step": 152110 }, { "epoch": 12.64, "learning_rate": 2.3154504891500154e-06, "loss": 0.8054, "step": 152120 }, { "epoch": 12.64, "learning_rate": 2.3153396336224813e-06, "loss": 0.8374, "step": 152130 }, { "epoch": 12.65, "learning_rate": 2.3152287780949476e-06, "loss": 0.7345, "step": 152140 }, { "epoch": 12.65, "learning_rate": 2.315117922567414e-06, "loss": 0.795, "step": 152150 }, { "epoch": 12.65, "learning_rate": 2.31500706703988e-06, "loss": 0.8348, "step": 152160 }, { "epoch": 12.65, "learning_rate": 2.314896211512346e-06, "loss": 0.8045, "step": 152170 }, { "epoch": 12.65, "learning_rate": 2.3147853559848128e-06, "loss": 0.8104, "step": 152180 }, { "epoch": 12.65, "learning_rate": 2.3146745004572787e-06, "loss": 0.7938, "step": 152190 }, { "epoch": 12.65, "learning_rate": 2.3145636449297454e-06, "loss": 0.8069, "step": 152200 }, { "epoch": 12.65, "learning_rate": 2.3144527894022117e-06, "loss": 0.7608, "step": 152210 }, { "epoch": 12.65, "learning_rate": 2.3143419338746775e-06, "loss": 0.8375, "step": 152220 }, { "epoch": 12.65, "learning_rate": 2.3142310783471443e-06, "loss": 0.8709, "step": 152230 }, { "epoch": 12.65, "learning_rate": 2.31412022281961e-06, "loss": 0.7594, "step": 152240 }, { "epoch": 12.65, "learning_rate": 2.3140093672920764e-06, "loss": 0.7601, "step": 152250 }, { "epoch": 12.66, "learning_rate": 2.3138985117645427e-06, "loss": 0.7608, "step": 152260 }, { "epoch": 12.66, "learning_rate": 2.313787656237009e-06, "loss": 0.7677, "step": 152270 }, { "epoch": 12.66, "learning_rate": 2.3136768007094753e-06, "loss": 0.8313, "step": 152280 }, { "epoch": 12.66, "learning_rate": 2.3135659451819416e-06, "loss": 0.6891, "step": 152290 }, { "epoch": 12.66, "learning_rate": 2.3134550896544075e-06, "loss": 0.7313, "step": 152300 }, { "epoch": 12.66, "learning_rate": 2.313344234126874e-06, "loss": 0.7718, "step": 152310 }, { "epoch": 12.66, "learning_rate": 2.31323337859934e-06, "loss": 0.744, "step": 152320 }, { "epoch": 12.66, "learning_rate": 2.3131225230718064e-06, "loss": 0.7928, "step": 152330 }, { "epoch": 12.66, "learning_rate": 2.313011667544273e-06, "loss": 0.7793, "step": 152340 }, { "epoch": 12.66, "learning_rate": 2.312900812016739e-06, "loss": 0.7775, "step": 152350 }, { "epoch": 12.66, "learning_rate": 2.3127899564892057e-06, "loss": 0.8132, "step": 152360 }, { "epoch": 12.66, "learning_rate": 2.3126791009616715e-06, "loss": 0.797, "step": 152370 }, { "epoch": 12.67, "learning_rate": 2.312568245434138e-06, "loss": 0.8784, "step": 152380 }, { "epoch": 12.67, "learning_rate": 2.312457389906604e-06, "loss": 0.7903, "step": 152390 }, { "epoch": 12.67, "learning_rate": 2.3123465343790704e-06, "loss": 0.7745, "step": 152400 }, { "epoch": 12.67, "learning_rate": 2.3122356788515363e-06, "loss": 0.767, "step": 152410 }, { "epoch": 12.67, "learning_rate": 2.312124823324003e-06, "loss": 0.7407, "step": 152420 }, { "epoch": 12.67, "learning_rate": 2.312013967796469e-06, "loss": 0.8278, "step": 152430 }, { "epoch": 12.67, "learning_rate": 2.3119031122689356e-06, "loss": 0.7217, "step": 152440 }, { "epoch": 12.67, "learning_rate": 2.311792256741402e-06, "loss": 0.8883, "step": 152450 }, { "epoch": 12.67, "learning_rate": 2.3116814012138678e-06, "loss": 0.7088, "step": 152460 }, { "epoch": 12.67, "learning_rate": 2.3115705456863345e-06, "loss": 0.8697, "step": 152470 }, { "epoch": 12.67, "learning_rate": 2.3114596901588004e-06, "loss": 0.7892, "step": 152480 }, { "epoch": 12.67, "learning_rate": 2.3113488346312667e-06, "loss": 0.7661, "step": 152490 }, { "epoch": 12.68, "learning_rate": 2.311237979103733e-06, "loss": 0.7723, "step": 152500 }, { "epoch": 12.68, "learning_rate": 2.3111271235761993e-06, "loss": 0.7786, "step": 152510 }, { "epoch": 12.68, "learning_rate": 2.311016268048665e-06, "loss": 0.7908, "step": 152520 }, { "epoch": 12.68, "learning_rate": 2.310905412521132e-06, "loss": 0.8637, "step": 152530 }, { "epoch": 12.68, "learning_rate": 2.3107945569935977e-06, "loss": 0.8083, "step": 152540 }, { "epoch": 12.68, "learning_rate": 2.3106837014660644e-06, "loss": 0.805, "step": 152550 }, { "epoch": 12.68, "learning_rate": 2.3105728459385303e-06, "loss": 0.7551, "step": 152560 }, { "epoch": 12.68, "learning_rate": 2.3104619904109966e-06, "loss": 0.8376, "step": 152570 }, { "epoch": 12.68, "learning_rate": 2.3103511348834633e-06, "loss": 0.8307, "step": 152580 }, { "epoch": 12.68, "learning_rate": 2.310240279355929e-06, "loss": 0.8216, "step": 152590 }, { "epoch": 12.68, "learning_rate": 2.310129423828396e-06, "loss": 0.7708, "step": 152600 }, { "epoch": 12.68, "learning_rate": 2.310018568300862e-06, "loss": 0.7074, "step": 152610 }, { "epoch": 12.69, "learning_rate": 2.309907712773328e-06, "loss": 0.7883, "step": 152620 }, { "epoch": 12.69, "learning_rate": 2.3097968572457944e-06, "loss": 0.8722, "step": 152630 }, { "epoch": 12.69, "learning_rate": 2.3096860017182607e-06, "loss": 0.7795, "step": 152640 }, { "epoch": 12.69, "learning_rate": 2.3095751461907265e-06, "loss": 0.8105, "step": 152650 }, { "epoch": 12.69, "learning_rate": 2.3094642906631933e-06, "loss": 0.7851, "step": 152660 }, { "epoch": 12.69, "learning_rate": 2.309353435135659e-06, "loss": 0.7817, "step": 152670 }, { "epoch": 12.69, "learning_rate": 2.3092425796081254e-06, "loss": 0.7865, "step": 152680 }, { "epoch": 12.69, "learning_rate": 2.3091317240805917e-06, "loss": 0.7793, "step": 152690 }, { "epoch": 12.69, "learning_rate": 2.309020868553058e-06, "loss": 0.7394, "step": 152700 }, { "epoch": 12.69, "learning_rate": 2.3089100130255247e-06, "loss": 0.7551, "step": 152710 }, { "epoch": 12.69, "learning_rate": 2.3087991574979906e-06, "loss": 0.8237, "step": 152720 }, { "epoch": 12.69, "learning_rate": 2.308688301970457e-06, "loss": 0.8455, "step": 152730 }, { "epoch": 12.7, "learning_rate": 2.308577446442923e-06, "loss": 0.7687, "step": 152740 }, { "epoch": 12.7, "learning_rate": 2.3084665909153895e-06, "loss": 0.8017, "step": 152750 }, { "epoch": 12.7, "learning_rate": 2.3083557353878554e-06, "loss": 0.7832, "step": 152760 }, { "epoch": 12.7, "learning_rate": 2.308244879860322e-06, "loss": 0.7872, "step": 152770 }, { "epoch": 12.7, "learning_rate": 2.308134024332788e-06, "loss": 0.7959, "step": 152780 }, { "epoch": 12.7, "learning_rate": 2.3080231688052547e-06, "loss": 0.7972, "step": 152790 }, { "epoch": 12.7, "learning_rate": 2.3079233988304742e-06, "loss": 0.8527, "step": 152800 }, { "epoch": 12.7, "learning_rate": 2.3078125433029405e-06, "loss": 0.805, "step": 152810 }, { "epoch": 12.7, "learning_rate": 2.3077016877754064e-06, "loss": 0.7835, "step": 152820 }, { "epoch": 12.7, "learning_rate": 2.307590832247873e-06, "loss": 0.836, "step": 152830 }, { "epoch": 12.7, "learning_rate": 2.307479976720339e-06, "loss": 0.7832, "step": 152840 }, { "epoch": 12.7, "learning_rate": 2.3073691211928053e-06, "loss": 0.7563, "step": 152850 }, { "epoch": 12.71, "learning_rate": 2.3072582656652716e-06, "loss": 0.7706, "step": 152860 }, { "epoch": 12.71, "learning_rate": 2.307147410137738e-06, "loss": 0.7708, "step": 152870 }, { "epoch": 12.71, "learning_rate": 2.307036554610204e-06, "loss": 0.7986, "step": 152880 }, { "epoch": 12.71, "learning_rate": 2.3069256990826705e-06, "loss": 0.7792, "step": 152890 }, { "epoch": 12.71, "learning_rate": 2.3068148435551363e-06, "loss": 0.7874, "step": 152900 }, { "epoch": 12.71, "learning_rate": 2.306703988027603e-06, "loss": 0.8414, "step": 152910 }, { "epoch": 12.71, "learning_rate": 2.3065931325000693e-06, "loss": 0.7724, "step": 152920 }, { "epoch": 12.71, "learning_rate": 2.3064822769725352e-06, "loss": 0.731, "step": 152930 }, { "epoch": 12.71, "learning_rate": 2.306371421445002e-06, "loss": 0.827, "step": 152940 }, { "epoch": 12.71, "learning_rate": 2.306260565917468e-06, "loss": 0.742, "step": 152950 }, { "epoch": 12.71, "learning_rate": 2.3061497103899345e-06, "loss": 0.8056, "step": 152960 }, { "epoch": 12.71, "learning_rate": 2.3060388548624004e-06, "loss": 0.8541, "step": 152970 }, { "epoch": 12.72, "learning_rate": 2.3059279993348667e-06, "loss": 0.8113, "step": 152980 }, { "epoch": 12.72, "learning_rate": 2.305817143807333e-06, "loss": 0.7826, "step": 152990 }, { "epoch": 12.72, "learning_rate": 2.3057062882797993e-06, "loss": 0.7354, "step": 153000 }, { "epoch": 12.72, "learning_rate": 2.305595432752265e-06, "loss": 0.8187, "step": 153010 }, { "epoch": 12.72, "learning_rate": 2.305484577224732e-06, "loss": 0.7827, "step": 153020 }, { "epoch": 12.72, "learning_rate": 2.305373721697198e-06, "loss": 0.863, "step": 153030 }, { "epoch": 12.72, "learning_rate": 2.3052628661696645e-06, "loss": 0.8345, "step": 153040 }, { "epoch": 12.72, "learning_rate": 2.3051520106421308e-06, "loss": 0.7627, "step": 153050 }, { "epoch": 12.72, "learning_rate": 2.3050411551145966e-06, "loss": 0.791, "step": 153060 }, { "epoch": 12.72, "learning_rate": 2.3049302995870633e-06, "loss": 0.8156, "step": 153070 }, { "epoch": 12.72, "learning_rate": 2.3048194440595292e-06, "loss": 0.8343, "step": 153080 }, { "epoch": 12.72, "learning_rate": 2.3047085885319955e-06, "loss": 0.7185, "step": 153090 }, { "epoch": 12.73, "learning_rate": 2.304597733004462e-06, "loss": 0.7506, "step": 153100 }, { "epoch": 12.73, "learning_rate": 2.304486877476928e-06, "loss": 0.8038, "step": 153110 }, { "epoch": 12.73, "learning_rate": 2.304376021949394e-06, "loss": 0.7856, "step": 153120 }, { "epoch": 12.73, "learning_rate": 2.3042651664218607e-06, "loss": 0.8738, "step": 153130 }, { "epoch": 12.73, "learning_rate": 2.3041543108943266e-06, "loss": 0.8069, "step": 153140 }, { "epoch": 12.73, "learning_rate": 2.3040434553667933e-06, "loss": 0.8226, "step": 153150 }, { "epoch": 12.73, "learning_rate": 2.3039325998392596e-06, "loss": 0.787, "step": 153160 }, { "epoch": 12.73, "learning_rate": 2.3038217443117255e-06, "loss": 0.7855, "step": 153170 }, { "epoch": 12.73, "learning_rate": 2.303710888784192e-06, "loss": 0.8567, "step": 153180 }, { "epoch": 12.73, "learning_rate": 2.303600033256658e-06, "loss": 0.7425, "step": 153190 }, { "epoch": 12.73, "learning_rate": 2.3034891777291243e-06, "loss": 0.7841, "step": 153200 }, { "epoch": 12.73, "learning_rate": 2.3033783222015906e-06, "loss": 0.767, "step": 153210 }, { "epoch": 12.74, "learning_rate": 2.303267466674057e-06, "loss": 0.7927, "step": 153220 }, { "epoch": 12.74, "learning_rate": 2.3031566111465232e-06, "loss": 0.7953, "step": 153230 }, { "epoch": 12.74, "learning_rate": 2.3030457556189895e-06, "loss": 0.8352, "step": 153240 }, { "epoch": 12.74, "learning_rate": 2.3029349000914554e-06, "loss": 0.8306, "step": 153250 }, { "epoch": 12.74, "learning_rate": 2.302824044563922e-06, "loss": 0.7794, "step": 153260 }, { "epoch": 12.74, "learning_rate": 2.302713189036388e-06, "loss": 0.7581, "step": 153270 }, { "epoch": 12.74, "learning_rate": 2.3026023335088543e-06, "loss": 0.8602, "step": 153280 }, { "epoch": 12.74, "learning_rate": 2.302491477981321e-06, "loss": 0.7959, "step": 153290 }, { "epoch": 12.74, "learning_rate": 2.302380622453787e-06, "loss": 0.7319, "step": 153300 }, { "epoch": 12.74, "learning_rate": 2.3022697669262536e-06, "loss": 0.7197, "step": 153310 }, { "epoch": 12.74, "learning_rate": 2.3021589113987195e-06, "loss": 0.7509, "step": 153320 }, { "epoch": 12.74, "learning_rate": 2.3020480558711858e-06, "loss": 0.834, "step": 153330 }, { "epoch": 12.75, "learning_rate": 2.301937200343652e-06, "loss": 0.8236, "step": 153340 }, { "epoch": 12.75, "learning_rate": 2.3018263448161183e-06, "loss": 0.7475, "step": 153350 }, { "epoch": 12.75, "learning_rate": 2.3017154892885842e-06, "loss": 0.7365, "step": 153360 }, { "epoch": 12.75, "learning_rate": 2.301604633761051e-06, "loss": 0.6926, "step": 153370 }, { "epoch": 12.75, "learning_rate": 2.301493778233517e-06, "loss": 0.8149, "step": 153380 }, { "epoch": 12.75, "learning_rate": 2.3013829227059835e-06, "loss": 0.813, "step": 153390 }, { "epoch": 12.75, "learning_rate": 2.30127206717845e-06, "loss": 0.8335, "step": 153400 }, { "epoch": 12.75, "learning_rate": 2.3011612116509157e-06, "loss": 0.8055, "step": 153410 }, { "epoch": 12.75, "learning_rate": 2.3010503561233824e-06, "loss": 0.772, "step": 153420 }, { "epoch": 12.75, "learning_rate": 2.3009395005958483e-06, "loss": 0.8111, "step": 153430 }, { "epoch": 12.75, "learning_rate": 2.3008286450683146e-06, "loss": 0.7542, "step": 153440 }, { "epoch": 12.75, "learning_rate": 2.300717789540781e-06, "loss": 0.8127, "step": 153450 }, { "epoch": 12.76, "learning_rate": 2.300606934013247e-06, "loss": 0.793, "step": 153460 }, { "epoch": 12.76, "learning_rate": 2.300496078485713e-06, "loss": 0.7709, "step": 153470 }, { "epoch": 12.76, "learning_rate": 2.3003852229581798e-06, "loss": 0.8218, "step": 153480 }, { "epoch": 12.76, "learning_rate": 2.3002743674306456e-06, "loss": 0.8296, "step": 153490 }, { "epoch": 12.76, "learning_rate": 2.3001635119031124e-06, "loss": 0.8418, "step": 153500 }, { "epoch": 12.76, "learning_rate": 2.3000526563755782e-06, "loss": 0.7883, "step": 153510 }, { "epoch": 12.76, "learning_rate": 2.2999418008480445e-06, "loss": 0.7513, "step": 153520 }, { "epoch": 12.76, "learning_rate": 2.2998309453205112e-06, "loss": 0.8433, "step": 153530 }, { "epoch": 12.76, "learning_rate": 2.299720089792977e-06, "loss": 0.7756, "step": 153540 }, { "epoch": 12.76, "learning_rate": 2.299609234265444e-06, "loss": 0.7479, "step": 153550 }, { "epoch": 12.76, "learning_rate": 2.2994983787379097e-06, "loss": 0.8206, "step": 153560 }, { "epoch": 12.76, "learning_rate": 2.299387523210376e-06, "loss": 0.79, "step": 153570 }, { "epoch": 12.77, "learning_rate": 2.2992766676828423e-06, "loss": 0.8306, "step": 153580 }, { "epoch": 12.77, "learning_rate": 2.2991658121553086e-06, "loss": 0.7621, "step": 153590 }, { "epoch": 12.77, "learning_rate": 2.2990549566277745e-06, "loss": 0.7643, "step": 153600 }, { "epoch": 12.77, "learning_rate": 2.298944101100241e-06, "loss": 0.7722, "step": 153610 }, { "epoch": 12.77, "learning_rate": 2.298833245572707e-06, "loss": 0.8187, "step": 153620 }, { "epoch": 12.77, "learning_rate": 2.2987223900451733e-06, "loss": 0.8495, "step": 153630 }, { "epoch": 12.77, "learning_rate": 2.2986115345176396e-06, "loss": 0.8268, "step": 153640 }, { "epoch": 12.77, "learning_rate": 2.2985117645428596e-06, "loss": 0.8028, "step": 153650 }, { "epoch": 12.77, "learning_rate": 2.2984009090153255e-06, "loss": 0.7488, "step": 153660 }, { "epoch": 12.77, "learning_rate": 2.298290053487792e-06, "loss": 0.7473, "step": 153670 }, { "epoch": 12.77, "learning_rate": 2.298179197960258e-06, "loss": 0.8133, "step": 153680 }, { "epoch": 12.77, "learning_rate": 2.2980683424327244e-06, "loss": 0.7799, "step": 153690 }, { "epoch": 12.78, "learning_rate": 2.2979574869051907e-06, "loss": 0.8073, "step": 153700 }, { "epoch": 12.78, "learning_rate": 2.297846631377657e-06, "loss": 0.7705, "step": 153710 }, { "epoch": 12.78, "learning_rate": 2.297735775850123e-06, "loss": 0.8405, "step": 153720 }, { "epoch": 12.78, "learning_rate": 2.2976249203225895e-06, "loss": 0.8746, "step": 153730 }, { "epoch": 12.78, "learning_rate": 2.297514064795056e-06, "loss": 0.8022, "step": 153740 }, { "epoch": 12.78, "learning_rate": 2.297403209267522e-06, "loss": 0.8326, "step": 153750 }, { "epoch": 12.78, "learning_rate": 2.2972923537399884e-06, "loss": 0.8393, "step": 153760 }, { "epoch": 12.78, "learning_rate": 2.2971814982124543e-06, "loss": 0.7883, "step": 153770 }, { "epoch": 12.78, "learning_rate": 2.297070642684921e-06, "loss": 0.7924, "step": 153780 }, { "epoch": 12.78, "learning_rate": 2.296959787157387e-06, "loss": 0.784, "step": 153790 }, { "epoch": 12.78, "learning_rate": 2.296848931629853e-06, "loss": 0.8337, "step": 153800 }, { "epoch": 12.78, "learning_rate": 2.2967380761023195e-06, "loss": 0.7991, "step": 153810 }, { "epoch": 12.79, "learning_rate": 2.2966272205747858e-06, "loss": 0.7963, "step": 153820 }, { "epoch": 12.79, "learning_rate": 2.296516365047252e-06, "loss": 0.823, "step": 153830 }, { "epoch": 12.79, "learning_rate": 2.2964055095197184e-06, "loss": 0.8336, "step": 153840 }, { "epoch": 12.79, "learning_rate": 2.2962946539921842e-06, "loss": 0.7805, "step": 153850 }, { "epoch": 12.79, "learning_rate": 2.296183798464651e-06, "loss": 0.8508, "step": 153860 }, { "epoch": 12.79, "learning_rate": 2.2960729429371173e-06, "loss": 0.792, "step": 153870 }, { "epoch": 12.79, "learning_rate": 2.295962087409583e-06, "loss": 0.8107, "step": 153880 }, { "epoch": 12.79, "learning_rate": 2.29585123188205e-06, "loss": 0.7883, "step": 153890 }, { "epoch": 12.79, "learning_rate": 2.2957403763545157e-06, "loss": 0.8273, "step": 153900 }, { "epoch": 12.79, "learning_rate": 2.2956295208269824e-06, "loss": 0.7836, "step": 153910 }, { "epoch": 12.79, "learning_rate": 2.2955186652994483e-06, "loss": 0.801, "step": 153920 }, { "epoch": 12.79, "learning_rate": 2.2954078097719146e-06, "loss": 0.8501, "step": 153930 }, { "epoch": 12.8, "learning_rate": 2.295296954244381e-06, "loss": 0.7583, "step": 153940 }, { "epoch": 12.8, "learning_rate": 2.295186098716847e-06, "loss": 0.7546, "step": 153950 }, { "epoch": 12.8, "learning_rate": 2.295075243189313e-06, "loss": 0.832, "step": 153960 }, { "epoch": 12.8, "learning_rate": 2.2949643876617798e-06, "loss": 0.7413, "step": 153970 }, { "epoch": 12.8, "learning_rate": 2.294853532134246e-06, "loss": 0.8002, "step": 153980 }, { "epoch": 12.8, "learning_rate": 2.2947426766067124e-06, "loss": 0.7886, "step": 153990 }, { "epoch": 12.8, "learning_rate": 2.2946318210791787e-06, "loss": 0.7078, "step": 154000 }, { "epoch": 12.8, "learning_rate": 2.2945209655516445e-06, "loss": 0.8496, "step": 154010 }, { "epoch": 12.8, "learning_rate": 2.2944101100241113e-06, "loss": 0.739, "step": 154020 }, { "epoch": 12.8, "learning_rate": 2.294299254496577e-06, "loss": 0.8246, "step": 154030 }, { "epoch": 12.8, "learning_rate": 2.2941883989690434e-06, "loss": 0.7866, "step": 154040 }, { "epoch": 12.8, "learning_rate": 2.2940775434415097e-06, "loss": 0.8348, "step": 154050 }, { "epoch": 12.81, "learning_rate": 2.293966687913976e-06, "loss": 0.7571, "step": 154060 }, { "epoch": 12.81, "learning_rate": 2.293855832386442e-06, "loss": 0.8635, "step": 154070 }, { "epoch": 12.81, "learning_rate": 2.2937449768589086e-06, "loss": 0.7847, "step": 154080 }, { "epoch": 12.81, "learning_rate": 2.2936341213313745e-06, "loss": 0.8107, "step": 154090 }, { "epoch": 12.81, "learning_rate": 2.293523265803841e-06, "loss": 0.7606, "step": 154100 }, { "epoch": 12.81, "learning_rate": 2.2934124102763075e-06, "loss": 0.7725, "step": 154110 }, { "epoch": 12.81, "learning_rate": 2.2933015547487734e-06, "loss": 0.7757, "step": 154120 }, { "epoch": 12.81, "learning_rate": 2.29319069922124e-06, "loss": 0.8622, "step": 154130 }, { "epoch": 12.81, "learning_rate": 2.293079843693706e-06, "loss": 0.7376, "step": 154140 }, { "epoch": 12.81, "learning_rate": 2.2929689881661723e-06, "loss": 0.8189, "step": 154150 }, { "epoch": 12.81, "learning_rate": 2.2928581326386385e-06, "loss": 0.774, "step": 154160 }, { "epoch": 12.81, "learning_rate": 2.292747277111105e-06, "loss": 0.8257, "step": 154170 }, { "epoch": 12.82, "learning_rate": 2.292636421583571e-06, "loss": 0.7881, "step": 154180 }, { "epoch": 12.82, "learning_rate": 2.2925255660560374e-06, "loss": 0.7502, "step": 154190 }, { "epoch": 12.82, "learning_rate": 2.2924147105285033e-06, "loss": 0.7713, "step": 154200 }, { "epoch": 12.82, "learning_rate": 2.29230385500097e-06, "loss": 0.7277, "step": 154210 }, { "epoch": 12.82, "learning_rate": 2.2921929994734363e-06, "loss": 0.7775, "step": 154220 }, { "epoch": 12.82, "learning_rate": 2.292082143945902e-06, "loss": 0.8369, "step": 154230 }, { "epoch": 12.82, "learning_rate": 2.291971288418369e-06, "loss": 0.7777, "step": 154240 }, { "epoch": 12.82, "learning_rate": 2.2918604328908348e-06, "loss": 0.7331, "step": 154250 }, { "epoch": 12.82, "learning_rate": 2.2917495773633015e-06, "loss": 0.7313, "step": 154260 }, { "epoch": 12.82, "learning_rate": 2.2916387218357674e-06, "loss": 0.7331, "step": 154270 }, { "epoch": 12.82, "learning_rate": 2.2915278663082337e-06, "loss": 0.7741, "step": 154280 }, { "epoch": 12.82, "learning_rate": 2.2914170107807e-06, "loss": 0.7854, "step": 154290 }, { "epoch": 12.83, "learning_rate": 2.2913061552531663e-06, "loss": 0.8606, "step": 154300 }, { "epoch": 12.83, "learning_rate": 2.291195299725632e-06, "loss": 0.7426, "step": 154310 }, { "epoch": 12.83, "learning_rate": 2.291084444198099e-06, "loss": 0.7919, "step": 154320 }, { "epoch": 12.83, "learning_rate": 2.2909735886705647e-06, "loss": 0.8313, "step": 154330 }, { "epoch": 12.83, "learning_rate": 2.2908627331430314e-06, "loss": 0.7929, "step": 154340 }, { "epoch": 12.83, "learning_rate": 2.2907518776154977e-06, "loss": 0.7937, "step": 154350 }, { "epoch": 12.83, "learning_rate": 2.2906410220879636e-06, "loss": 0.7717, "step": 154360 }, { "epoch": 12.83, "learning_rate": 2.2905301665604303e-06, "loss": 0.8228, "step": 154370 }, { "epoch": 12.83, "learning_rate": 2.290419311032896e-06, "loss": 0.8453, "step": 154380 }, { "epoch": 12.83, "learning_rate": 2.2903084555053625e-06, "loss": 0.8388, "step": 154390 }, { "epoch": 12.83, "learning_rate": 2.290197599977829e-06, "loss": 0.723, "step": 154400 }, { "epoch": 12.83, "learning_rate": 2.290086744450295e-06, "loss": 0.7142, "step": 154410 }, { "epoch": 12.84, "learning_rate": 2.289975888922761e-06, "loss": 0.7987, "step": 154420 }, { "epoch": 12.84, "learning_rate": 2.2898650333952277e-06, "loss": 0.8723, "step": 154430 }, { "epoch": 12.84, "learning_rate": 2.2897541778676935e-06, "loss": 0.8048, "step": 154440 }, { "epoch": 12.84, "learning_rate": 2.2896433223401603e-06, "loss": 0.8235, "step": 154450 }, { "epoch": 12.84, "learning_rate": 2.289532466812626e-06, "loss": 0.7699, "step": 154460 }, { "epoch": 12.84, "learning_rate": 2.2894216112850924e-06, "loss": 0.7753, "step": 154470 }, { "epoch": 12.84, "learning_rate": 2.289310755757559e-06, "loss": 0.7591, "step": 154480 }, { "epoch": 12.84, "learning_rate": 2.289199900230025e-06, "loss": 0.7476, "step": 154490 }, { "epoch": 12.84, "learning_rate": 2.2890890447024917e-06, "loss": 0.7765, "step": 154500 }, { "epoch": 12.84, "learning_rate": 2.2889781891749576e-06, "loss": 0.774, "step": 154510 }, { "epoch": 12.84, "learning_rate": 2.288867333647424e-06, "loss": 0.6904, "step": 154520 }, { "epoch": 12.84, "learning_rate": 2.28875647811989e-06, "loss": 0.8397, "step": 154530 }, { "epoch": 12.85, "learning_rate": 2.2886456225923565e-06, "loss": 0.862, "step": 154540 }, { "epoch": 12.85, "learning_rate": 2.2885347670648224e-06, "loss": 0.8337, "step": 154550 }, { "epoch": 12.85, "learning_rate": 2.288423911537289e-06, "loss": 0.7998, "step": 154560 }, { "epoch": 12.85, "learning_rate": 2.288313056009755e-06, "loss": 0.7889, "step": 154570 }, { "epoch": 12.85, "learning_rate": 2.2882022004822213e-06, "loss": 0.8387, "step": 154580 }, { "epoch": 12.85, "learning_rate": 2.288091344954688e-06, "loss": 0.7785, "step": 154590 }, { "epoch": 12.85, "learning_rate": 2.287980489427154e-06, "loss": 0.7669, "step": 154600 }, { "epoch": 12.85, "learning_rate": 2.2878696338996206e-06, "loss": 0.7136, "step": 154610 }, { "epoch": 12.85, "learning_rate": 2.2877587783720864e-06, "loss": 0.772, "step": 154620 }, { "epoch": 12.85, "learning_rate": 2.2876479228445527e-06, "loss": 0.8331, "step": 154630 }, { "epoch": 12.85, "learning_rate": 2.287537067317019e-06, "loss": 0.7898, "step": 154640 }, { "epoch": 12.85, "learning_rate": 2.2874262117894853e-06, "loss": 0.7776, "step": 154650 }, { "epoch": 12.86, "learning_rate": 2.287315356261951e-06, "loss": 0.7389, "step": 154660 }, { "epoch": 12.86, "learning_rate": 2.287204500734418e-06, "loss": 0.8209, "step": 154670 }, { "epoch": 12.86, "learning_rate": 2.287093645206884e-06, "loss": 0.8478, "step": 154680 }, { "epoch": 12.86, "learning_rate": 2.2869827896793505e-06, "loss": 0.7752, "step": 154690 }, { "epoch": 12.86, "learning_rate": 2.2868719341518164e-06, "loss": 0.7928, "step": 154700 }, { "epoch": 12.86, "learning_rate": 2.2867610786242827e-06, "loss": 0.7721, "step": 154710 }, { "epoch": 12.86, "learning_rate": 2.2866502230967494e-06, "loss": 0.7975, "step": 154720 }, { "epoch": 12.86, "learning_rate": 2.2865393675692153e-06, "loss": 0.8708, "step": 154730 }, { "epoch": 12.86, "learning_rate": 2.2864285120416816e-06, "loss": 0.7703, "step": 154740 }, { "epoch": 12.86, "learning_rate": 2.286317656514148e-06, "loss": 0.7501, "step": 154750 }, { "epoch": 12.86, "learning_rate": 2.286206800986614e-06, "loss": 0.8157, "step": 154760 }, { "epoch": 12.86, "learning_rate": 2.2860959454590804e-06, "loss": 0.823, "step": 154770 }, { "epoch": 12.87, "learning_rate": 2.2859850899315467e-06, "loss": 0.8676, "step": 154780 }, { "epoch": 12.87, "learning_rate": 2.2858742344040126e-06, "loss": 0.8103, "step": 154790 }, { "epoch": 12.87, "learning_rate": 2.2857633788764793e-06, "loss": 0.7113, "step": 154800 }, { "epoch": 12.87, "learning_rate": 2.285652523348945e-06, "loss": 0.8055, "step": 154810 }, { "epoch": 12.87, "learning_rate": 2.2855416678214115e-06, "loss": 0.7806, "step": 154820 }, { "epoch": 12.87, "learning_rate": 2.285430812293878e-06, "loss": 0.7811, "step": 154830 }, { "epoch": 12.87, "learning_rate": 2.285319956766344e-06, "loss": 0.7669, "step": 154840 }, { "epoch": 12.87, "learning_rate": 2.285209101238811e-06, "loss": 0.7886, "step": 154850 }, { "epoch": 12.87, "learning_rate": 2.2850982457112767e-06, "loss": 0.8091, "step": 154860 }, { "epoch": 12.87, "learning_rate": 2.284987390183743e-06, "loss": 0.7825, "step": 154870 }, { "epoch": 12.87, "learning_rate": 2.2848765346562093e-06, "loss": 0.8495, "step": 154880 }, { "epoch": 12.87, "learning_rate": 2.2847656791286756e-06, "loss": 0.8021, "step": 154890 }, { "epoch": 12.88, "learning_rate": 2.2846548236011414e-06, "loss": 0.7776, "step": 154900 }, { "epoch": 12.88, "learning_rate": 2.284543968073608e-06, "loss": 0.7927, "step": 154910 }, { "epoch": 12.88, "learning_rate": 2.284433112546074e-06, "loss": 0.7333, "step": 154920 }, { "epoch": 12.88, "learning_rate": 2.2843222570185403e-06, "loss": 0.87, "step": 154930 }, { "epoch": 12.88, "learning_rate": 2.2842114014910066e-06, "loss": 0.8017, "step": 154940 }, { "epoch": 12.88, "learning_rate": 2.284100545963473e-06, "loss": 0.7147, "step": 154950 }, { "epoch": 12.88, "learning_rate": 2.2839896904359396e-06, "loss": 0.8575, "step": 154960 }, { "epoch": 12.88, "learning_rate": 2.2838788349084055e-06, "loss": 0.7586, "step": 154970 }, { "epoch": 12.88, "learning_rate": 2.283767979380872e-06, "loss": 0.7932, "step": 154980 }, { "epoch": 12.88, "learning_rate": 2.283657123853338e-06, "loss": 0.7687, "step": 154990 }, { "epoch": 12.88, "learning_rate": 2.2835462683258044e-06, "loss": 0.7903, "step": 155000 }, { "epoch": 12.88, "learning_rate": 2.2834354127982703e-06, "loss": 0.7745, "step": 155010 }, { "epoch": 12.89, "learning_rate": 2.283324557270737e-06, "loss": 0.7673, "step": 155020 }, { "epoch": 12.89, "learning_rate": 2.283213701743203e-06, "loss": 0.8256, "step": 155030 }, { "epoch": 12.89, "learning_rate": 2.2831028462156696e-06, "loss": 0.7511, "step": 155040 }, { "epoch": 12.89, "learning_rate": 2.2829919906881354e-06, "loss": 0.7482, "step": 155050 }, { "epoch": 12.89, "learning_rate": 2.2828811351606017e-06, "loss": 0.8294, "step": 155060 }, { "epoch": 12.89, "learning_rate": 2.282770279633068e-06, "loss": 0.7933, "step": 155070 }, { "epoch": 12.89, "learning_rate": 2.2826594241055343e-06, "loss": 0.7545, "step": 155080 }, { "epoch": 12.89, "learning_rate": 2.2825485685780006e-06, "loss": 0.7781, "step": 155090 }, { "epoch": 12.89, "learning_rate": 2.282437713050467e-06, "loss": 0.7926, "step": 155100 }, { "epoch": 12.89, "learning_rate": 2.2823268575229332e-06, "loss": 0.7981, "step": 155110 }, { "epoch": 12.89, "learning_rate": 2.2822160019953995e-06, "loss": 0.7777, "step": 155120 }, { "epoch": 12.89, "learning_rate": 2.282105146467866e-06, "loss": 0.8286, "step": 155130 }, { "epoch": 12.9, "learning_rate": 2.2819942909403317e-06, "loss": 0.78, "step": 155140 }, { "epoch": 12.9, "learning_rate": 2.2818834354127984e-06, "loss": 0.8414, "step": 155150 }, { "epoch": 12.9, "learning_rate": 2.2817725798852643e-06, "loss": 0.8294, "step": 155160 }, { "epoch": 12.9, "learning_rate": 2.2816617243577306e-06, "loss": 0.8446, "step": 155170 }, { "epoch": 12.9, "learning_rate": 2.281550868830197e-06, "loss": 0.8059, "step": 155180 }, { "epoch": 12.9, "learning_rate": 2.281440013302663e-06, "loss": 0.7333, "step": 155190 }, { "epoch": 12.9, "learning_rate": 2.2813291577751295e-06, "loss": 0.7672, "step": 155200 }, { "epoch": 12.9, "learning_rate": 2.2812183022475957e-06, "loss": 0.7114, "step": 155210 }, { "epoch": 12.9, "learning_rate": 2.281107446720062e-06, "loss": 0.8113, "step": 155220 }, { "epoch": 12.9, "learning_rate": 2.2809965911925283e-06, "loss": 0.8282, "step": 155230 }, { "epoch": 12.9, "learning_rate": 2.2808857356649946e-06, "loss": 0.7987, "step": 155240 }, { "epoch": 12.9, "learning_rate": 2.2807748801374605e-06, "loss": 0.6808, "step": 155250 }, { "epoch": 12.9, "learning_rate": 2.2806640246099272e-06, "loss": 0.8153, "step": 155260 }, { "epoch": 12.91, "learning_rate": 2.280553169082393e-06, "loss": 0.7487, "step": 155270 }, { "epoch": 12.91, "learning_rate": 2.28044231355486e-06, "loss": 0.8496, "step": 155280 }, { "epoch": 12.91, "learning_rate": 2.2803314580273257e-06, "loss": 0.754, "step": 155290 }, { "epoch": 12.91, "learning_rate": 2.280220602499792e-06, "loss": 0.7661, "step": 155300 }, { "epoch": 12.91, "learning_rate": 2.2801097469722583e-06, "loss": 0.8037, "step": 155310 }, { "epoch": 12.91, "learning_rate": 2.2799988914447246e-06, "loss": 0.7238, "step": 155320 }, { "epoch": 12.91, "learning_rate": 2.279888035917191e-06, "loss": 0.8742, "step": 155330 }, { "epoch": 12.91, "learning_rate": 2.279777180389657e-06, "loss": 0.7265, "step": 155340 }, { "epoch": 12.91, "learning_rate": 2.2796663248621235e-06, "loss": 0.7677, "step": 155350 }, { "epoch": 12.91, "learning_rate": 2.2795554693345893e-06, "loss": 0.7447, "step": 155360 }, { "epoch": 12.91, "learning_rate": 2.279444613807056e-06, "loss": 0.7675, "step": 155370 }, { "epoch": 12.91, "learning_rate": 2.279333758279522e-06, "loss": 0.8293, "step": 155380 }, { "epoch": 12.92, "learning_rate": 2.2792229027519886e-06, "loss": 0.7157, "step": 155390 }, { "epoch": 12.92, "learning_rate": 2.2791120472244545e-06, "loss": 0.8054, "step": 155400 }, { "epoch": 12.92, "learning_rate": 2.279001191696921e-06, "loss": 0.7799, "step": 155410 }, { "epoch": 12.92, "learning_rate": 2.278890336169387e-06, "loss": 0.7868, "step": 155420 }, { "epoch": 12.92, "learning_rate": 2.2787794806418534e-06, "loss": 0.8276, "step": 155430 }, { "epoch": 12.92, "learning_rate": 2.2786686251143193e-06, "loss": 0.8309, "step": 155440 }, { "epoch": 12.92, "learning_rate": 2.278557769586786e-06, "loss": 0.7601, "step": 155450 }, { "epoch": 12.92, "learning_rate": 2.2784469140592523e-06, "loss": 0.715, "step": 155460 }, { "epoch": 12.92, "learning_rate": 2.2783360585317186e-06, "loss": 0.8607, "step": 155470 }, { "epoch": 12.92, "learning_rate": 2.278225203004185e-06, "loss": 0.8053, "step": 155480 }, { "epoch": 12.92, "learning_rate": 2.2781143474766507e-06, "loss": 0.7852, "step": 155490 }, { "epoch": 12.92, "learning_rate": 2.2780034919491175e-06, "loss": 0.7501, "step": 155500 }, { "epoch": 12.93, "learning_rate": 2.2778926364215833e-06, "loss": 0.7748, "step": 155510 }, { "epoch": 12.93, "learning_rate": 2.2777817808940496e-06, "loss": 0.7649, "step": 155520 }, { "epoch": 12.93, "learning_rate": 2.277670925366516e-06, "loss": 0.7827, "step": 155530 }, { "epoch": 12.93, "learning_rate": 2.2775600698389822e-06, "loss": 0.7979, "step": 155540 }, { "epoch": 12.93, "learning_rate": 2.2774492143114485e-06, "loss": 0.7569, "step": 155550 }, { "epoch": 12.93, "learning_rate": 2.277338358783915e-06, "loss": 0.7722, "step": 155560 }, { "epoch": 12.93, "learning_rate": 2.2772275032563807e-06, "loss": 0.728, "step": 155570 }, { "epoch": 12.93, "learning_rate": 2.2771166477288474e-06, "loss": 0.7926, "step": 155580 }, { "epoch": 12.93, "learning_rate": 2.2770057922013137e-06, "loss": 0.7803, "step": 155590 }, { "epoch": 12.93, "learning_rate": 2.2768949366737796e-06, "loss": 0.8148, "step": 155600 }, { "epoch": 12.93, "learning_rate": 2.2767840811462463e-06, "loss": 0.7477, "step": 155610 }, { "epoch": 12.93, "learning_rate": 2.276673225618712e-06, "loss": 0.7879, "step": 155620 }, { "epoch": 12.94, "learning_rate": 2.276562370091179e-06, "loss": 0.8282, "step": 155630 }, { "epoch": 12.94, "learning_rate": 2.2764515145636448e-06, "loss": 0.7774, "step": 155640 }, { "epoch": 12.94, "learning_rate": 2.276340659036111e-06, "loss": 0.7966, "step": 155650 }, { "epoch": 12.94, "learning_rate": 2.2762298035085773e-06, "loss": 0.8101, "step": 155660 }, { "epoch": 12.94, "learning_rate": 2.2761189479810436e-06, "loss": 0.7703, "step": 155670 }, { "epoch": 12.94, "learning_rate": 2.2760080924535095e-06, "loss": 0.8115, "step": 155680 }, { "epoch": 12.94, "learning_rate": 2.2758972369259762e-06, "loss": 0.7293, "step": 155690 }, { "epoch": 12.94, "learning_rate": 2.2757863813984425e-06, "loss": 0.7678, "step": 155700 }, { "epoch": 12.94, "learning_rate": 2.2756755258709084e-06, "loss": 0.7754, "step": 155710 }, { "epoch": 12.94, "learning_rate": 2.275564670343375e-06, "loss": 0.7402, "step": 155720 }, { "epoch": 12.94, "learning_rate": 2.275453814815841e-06, "loss": 0.8025, "step": 155730 }, { "epoch": 12.94, "learning_rate": 2.2753429592883077e-06, "loss": 0.7591, "step": 155740 }, { "epoch": 12.95, "learning_rate": 2.2752321037607736e-06, "loss": 0.7803, "step": 155750 }, { "epoch": 12.95, "learning_rate": 2.27512124823324e-06, "loss": 0.7664, "step": 155760 }, { "epoch": 12.95, "learning_rate": 2.275010392705706e-06, "loss": 0.7816, "step": 155770 }, { "epoch": 12.95, "learning_rate": 2.2748995371781725e-06, "loss": 0.8174, "step": 155780 }, { "epoch": 12.95, "learning_rate": 2.2747886816506383e-06, "loss": 0.7975, "step": 155790 }, { "epoch": 12.95, "learning_rate": 2.274677826123105e-06, "loss": 0.7902, "step": 155800 }, { "epoch": 12.95, "learning_rate": 2.274566970595571e-06, "loss": 0.7784, "step": 155810 }, { "epoch": 12.95, "learning_rate": 2.2744561150680376e-06, "loss": 0.7392, "step": 155820 }, { "epoch": 12.95, "learning_rate": 2.274345259540504e-06, "loss": 0.831, "step": 155830 }, { "epoch": 12.95, "learning_rate": 2.27423440401297e-06, "loss": 0.7707, "step": 155840 }, { "epoch": 12.95, "learning_rate": 2.2741235484854365e-06, "loss": 0.7936, "step": 155850 }, { "epoch": 12.95, "learning_rate": 2.2740126929579024e-06, "loss": 0.7647, "step": 155860 }, { "epoch": 12.96, "learning_rate": 2.2739018374303687e-06, "loss": 0.855, "step": 155870 }, { "epoch": 12.96, "learning_rate": 2.273790981902835e-06, "loss": 0.7918, "step": 155880 }, { "epoch": 12.96, "learning_rate": 2.2736801263753013e-06, "loss": 0.7536, "step": 155890 }, { "epoch": 12.96, "learning_rate": 2.2735692708477676e-06, "loss": 0.7532, "step": 155900 }, { "epoch": 12.96, "learning_rate": 2.273458415320234e-06, "loss": 0.7773, "step": 155910 }, { "epoch": 12.96, "learning_rate": 2.2733475597926998e-06, "loss": 0.7398, "step": 155920 }, { "epoch": 12.96, "learning_rate": 2.2732367042651665e-06, "loss": 0.864, "step": 155930 }, { "epoch": 12.96, "learning_rate": 2.2731258487376323e-06, "loss": 0.7904, "step": 155940 }, { "epoch": 12.96, "learning_rate": 2.2730149932100986e-06, "loss": 0.7768, "step": 155950 }, { "epoch": 12.96, "learning_rate": 2.2729041376825654e-06, "loss": 0.7654, "step": 155960 }, { "epoch": 12.96, "learning_rate": 2.2727932821550312e-06, "loss": 0.7703, "step": 155970 }, { "epoch": 12.96, "learning_rate": 2.272682426627498e-06, "loss": 0.7972, "step": 155980 }, { "epoch": 12.97, "learning_rate": 2.272571571099964e-06, "loss": 0.7896, "step": 155990 }, { "epoch": 12.97, "learning_rate": 2.27246071557243e-06, "loss": 0.7839, "step": 156000 }, { "epoch": 12.97, "learning_rate": 2.2723498600448964e-06, "loss": 0.7526, "step": 156010 }, { "epoch": 12.97, "learning_rate": 2.2722390045173627e-06, "loss": 0.7515, "step": 156020 }, { "epoch": 12.97, "learning_rate": 2.2721281489898286e-06, "loss": 0.8366, "step": 156030 }, { "epoch": 12.97, "learning_rate": 2.2720172934622953e-06, "loss": 0.7852, "step": 156040 }, { "epoch": 12.97, "learning_rate": 2.271906437934761e-06, "loss": 0.7474, "step": 156050 }, { "epoch": 12.97, "learning_rate": 2.271795582407228e-06, "loss": 0.733, "step": 156060 }, { "epoch": 12.97, "learning_rate": 2.271684726879694e-06, "loss": 0.829, "step": 156070 }, { "epoch": 12.97, "learning_rate": 2.27157387135216e-06, "loss": 0.8402, "step": 156080 }, { "epoch": 12.97, "learning_rate": 2.2714630158246268e-06, "loss": 0.7635, "step": 156090 }, { "epoch": 12.97, "learning_rate": 2.2713521602970926e-06, "loss": 0.7789, "step": 156100 }, { "epoch": 12.98, "learning_rate": 2.271241304769559e-06, "loss": 0.7889, "step": 156110 }, { "epoch": 12.98, "learning_rate": 2.2711304492420252e-06, "loss": 0.7729, "step": 156120 }, { "epoch": 12.98, "learning_rate": 2.2710195937144915e-06, "loss": 0.8692, "step": 156130 }, { "epoch": 12.98, "learning_rate": 2.2709087381869574e-06, "loss": 0.822, "step": 156140 }, { "epoch": 12.98, "learning_rate": 2.270797882659424e-06, "loss": 0.8579, "step": 156150 }, { "epoch": 12.98, "learning_rate": 2.27068702713189e-06, "loss": 0.7163, "step": 156160 }, { "epoch": 12.98, "learning_rate": 2.2705761716043567e-06, "loss": 0.746, "step": 156170 }, { "epoch": 12.98, "learning_rate": 2.2704653160768226e-06, "loss": 0.7824, "step": 156180 }, { "epoch": 12.98, "learning_rate": 2.270354460549289e-06, "loss": 0.7386, "step": 156190 }, { "epoch": 12.98, "learning_rate": 2.2702436050217556e-06, "loss": 0.794, "step": 156200 }, { "epoch": 12.98, "learning_rate": 2.2701327494942215e-06, "loss": 0.7736, "step": 156210 }, { "epoch": 12.98, "learning_rate": 2.2700218939666878e-06, "loss": 0.8216, "step": 156220 }, { "epoch": 12.99, "learning_rate": 2.269911038439154e-06, "loss": 0.7803, "step": 156230 }, { "epoch": 12.99, "learning_rate": 2.2698001829116204e-06, "loss": 0.7952, "step": 156240 }, { "epoch": 12.99, "learning_rate": 2.2696893273840867e-06, "loss": 0.7735, "step": 156250 }, { "epoch": 12.99, "learning_rate": 2.269578471856553e-06, "loss": 0.782, "step": 156260 }, { "epoch": 12.99, "learning_rate": 2.269467616329019e-06, "loss": 0.781, "step": 156270 }, { "epoch": 12.99, "learning_rate": 2.2693567608014855e-06, "loss": 0.8632, "step": 156280 }, { "epoch": 12.99, "learning_rate": 2.2692459052739514e-06, "loss": 0.8071, "step": 156290 }, { "epoch": 12.99, "learning_rate": 2.2691350497464177e-06, "loss": 0.7515, "step": 156300 }, { "epoch": 12.99, "learning_rate": 2.2690241942188844e-06, "loss": 0.7739, "step": 156310 }, { "epoch": 12.99, "learning_rate": 2.2689133386913503e-06, "loss": 0.727, "step": 156320 }, { "epoch": 12.99, "learning_rate": 2.268802483163817e-06, "loss": 0.8301, "step": 156330 }, { "epoch": 12.99, "learning_rate": 2.268691627636283e-06, "loss": 0.7446, "step": 156340 }, { "epoch": 13.0, "learning_rate": 2.268580772108749e-06, "loss": 0.8001, "step": 156350 }, { "epoch": 13.0, "learning_rate": 2.2684699165812155e-06, "loss": 0.7702, "step": 156360 }, { "epoch": 13.0, "learning_rate": 2.2683590610536818e-06, "loss": 0.7874, "step": 156370 }, { "epoch": 13.0, "learning_rate": 2.2682482055261476e-06, "loss": 0.7929, "step": 156380 }, { "epoch": 13.0, "learning_rate": 2.2681373499986144e-06, "loss": 0.7367, "step": 156390 }, { "epoch": 13.0, "learning_rate": 2.2680264944710802e-06, "loss": 0.826, "step": 156400 }, { "epoch": 13.0, "eval_loss": 1.0705888271331787, "eval_runtime": 358.1029, "eval_samples_per_second": 7.467, "eval_steps_per_second": 3.734, "eval_wer": 0.6445122496739227, "step": 156403 }, { "epoch": 13.0, "learning_rate": 2.267915638943547e-06, "loss": 0.8433, "step": 156410 }, { "epoch": 13.0, "learning_rate": 2.267804783416013e-06, "loss": 0.7792, "step": 156420 }, { "epoch": 13.0, "learning_rate": 2.267693927888479e-06, "loss": 0.7536, "step": 156430 }, { "epoch": 13.0, "learning_rate": 2.267583072360946e-06, "loss": 0.7792, "step": 156440 }, { "epoch": 13.0, "learning_rate": 2.2674722168334117e-06, "loss": 0.8076, "step": 156450 }, { "epoch": 13.0, "learning_rate": 2.267361361305878e-06, "loss": 0.7866, "step": 156460 }, { "epoch": 13.01, "learning_rate": 2.2672505057783443e-06, "loss": 0.7477, "step": 156470 }, { "epoch": 13.01, "learning_rate": 2.2671396502508106e-06, "loss": 0.7335, "step": 156480 }, { "epoch": 13.01, "learning_rate": 2.267028794723277e-06, "loss": 0.7697, "step": 156490 }, { "epoch": 13.01, "learning_rate": 2.266917939195743e-06, "loss": 0.7764, "step": 156500 }, { "epoch": 13.01, "learning_rate": 2.266807083668209e-06, "loss": 0.8649, "step": 156510 }, { "epoch": 13.01, "learning_rate": 2.2666962281406758e-06, "loss": 0.7716, "step": 156520 }, { "epoch": 13.01, "learning_rate": 2.2665853726131416e-06, "loss": 0.7294, "step": 156530 }, { "epoch": 13.01, "learning_rate": 2.266474517085608e-06, "loss": 0.7192, "step": 156540 }, { "epoch": 13.01, "learning_rate": 2.2663636615580742e-06, "loss": 0.7846, "step": 156550 }, { "epoch": 13.01, "learning_rate": 2.2662528060305405e-06, "loss": 0.836, "step": 156560 }, { "epoch": 13.01, "learning_rate": 2.2661419505030073e-06, "loss": 0.7973, "step": 156570 }, { "epoch": 13.01, "learning_rate": 2.266031094975473e-06, "loss": 0.8046, "step": 156580 }, { "epoch": 13.02, "learning_rate": 2.2659202394479394e-06, "loss": 0.7834, "step": 156590 }, { "epoch": 13.02, "learning_rate": 2.2658093839204057e-06, "loss": 0.7662, "step": 156600 }, { "epoch": 13.02, "learning_rate": 2.265698528392872e-06, "loss": 0.8188, "step": 156610 }, { "epoch": 13.02, "learning_rate": 2.265587672865338e-06, "loss": 0.7943, "step": 156620 }, { "epoch": 13.02, "learning_rate": 2.2654768173378046e-06, "loss": 0.7428, "step": 156630 }, { "epoch": 13.02, "learning_rate": 2.2653659618102705e-06, "loss": 0.7683, "step": 156640 }, { "epoch": 13.02, "learning_rate": 2.2652551062827368e-06, "loss": 0.7693, "step": 156650 }, { "epoch": 13.02, "learning_rate": 2.265144250755203e-06, "loss": 0.8272, "step": 156660 }, { "epoch": 13.02, "learning_rate": 2.2650333952276694e-06, "loss": 0.8237, "step": 156670 }, { "epoch": 13.02, "learning_rate": 2.264922539700136e-06, "loss": 0.8131, "step": 156680 }, { "epoch": 13.02, "learning_rate": 2.264811684172602e-06, "loss": 0.783, "step": 156690 }, { "epoch": 13.02, "learning_rate": 2.2647008286450682e-06, "loss": 0.7929, "step": 156700 }, { "epoch": 13.03, "learning_rate": 2.2645899731175345e-06, "loss": 0.8611, "step": 156710 }, { "epoch": 13.03, "learning_rate": 2.264479117590001e-06, "loss": 0.8232, "step": 156720 }, { "epoch": 13.03, "learning_rate": 2.2643682620624667e-06, "loss": 0.8047, "step": 156730 }, { "epoch": 13.03, "learning_rate": 2.2642574065349334e-06, "loss": 0.7822, "step": 156740 }, { "epoch": 13.03, "learning_rate": 2.2641465510073993e-06, "loss": 0.8243, "step": 156750 }, { "epoch": 13.03, "learning_rate": 2.264035695479866e-06, "loss": 0.8064, "step": 156760 }, { "epoch": 13.03, "learning_rate": 2.263924839952332e-06, "loss": 0.7849, "step": 156770 }, { "epoch": 13.03, "learning_rate": 2.263813984424798e-06, "loss": 0.7938, "step": 156780 }, { "epoch": 13.03, "learning_rate": 2.2637031288972645e-06, "loss": 0.769, "step": 156790 }, { "epoch": 13.03, "learning_rate": 2.2635922733697308e-06, "loss": 0.813, "step": 156800 }, { "epoch": 13.03, "learning_rate": 2.263481417842197e-06, "loss": 0.7966, "step": 156810 }, { "epoch": 13.03, "learning_rate": 2.2633705623146634e-06, "loss": 0.7258, "step": 156820 }, { "epoch": 13.04, "learning_rate": 2.2632597067871297e-06, "loss": 0.8016, "step": 156830 }, { "epoch": 13.04, "learning_rate": 2.263148851259596e-06, "loss": 0.781, "step": 156840 }, { "epoch": 13.04, "learning_rate": 2.2630379957320623e-06, "loss": 0.8039, "step": 156850 }, { "epoch": 13.04, "learning_rate": 2.262927140204528e-06, "loss": 0.8213, "step": 156860 }, { "epoch": 13.04, "learning_rate": 2.262816284676995e-06, "loss": 0.8161, "step": 156870 }, { "epoch": 13.04, "learning_rate": 2.2627054291494607e-06, "loss": 0.8028, "step": 156880 }, { "epoch": 13.04, "learning_rate": 2.262594573621927e-06, "loss": 0.7535, "step": 156890 }, { "epoch": 13.04, "learning_rate": 2.2624837180943933e-06, "loss": 0.776, "step": 156900 }, { "epoch": 13.04, "learning_rate": 2.2623728625668596e-06, "loss": 0.81, "step": 156910 }, { "epoch": 13.04, "learning_rate": 2.2622620070393255e-06, "loss": 0.8027, "step": 156920 }, { "epoch": 13.04, "learning_rate": 2.262151151511792e-06, "loss": 0.8077, "step": 156930 }, { "epoch": 13.04, "learning_rate": 2.2620402959842585e-06, "loss": 0.8214, "step": 156940 }, { "epoch": 13.05, "learning_rate": 2.2619294404567248e-06, "loss": 0.8282, "step": 156950 }, { "epoch": 13.05, "learning_rate": 2.261818584929191e-06, "loss": 0.7895, "step": 156960 }, { "epoch": 13.05, "learning_rate": 2.261707729401657e-06, "loss": 0.7474, "step": 156970 }, { "epoch": 13.05, "learning_rate": 2.2615968738741237e-06, "loss": 0.8379, "step": 156980 }, { "epoch": 13.05, "learning_rate": 2.2614860183465895e-06, "loss": 0.7341, "step": 156990 }, { "epoch": 13.05, "learning_rate": 2.261375162819056e-06, "loss": 0.8232, "step": 157000 }, { "epoch": 13.05, "learning_rate": 2.261264307291522e-06, "loss": 0.8221, "step": 157010 }, { "epoch": 13.05, "learning_rate": 2.2611534517639884e-06, "loss": 0.8049, "step": 157020 }, { "epoch": 13.05, "learning_rate": 2.2610425962364547e-06, "loss": 0.7843, "step": 157030 }, { "epoch": 13.05, "learning_rate": 2.260931740708921e-06, "loss": 0.7263, "step": 157040 }, { "epoch": 13.05, "learning_rate": 2.2608208851813873e-06, "loss": 0.7972, "step": 157050 }, { "epoch": 13.05, "learning_rate": 2.2607100296538536e-06, "loss": 0.841, "step": 157060 }, { "epoch": 13.06, "learning_rate": 2.26059917412632e-06, "loss": 0.7592, "step": 157070 }, { "epoch": 13.06, "learning_rate": 2.2604883185987858e-06, "loss": 0.8068, "step": 157080 }, { "epoch": 13.06, "learning_rate": 2.2603774630712525e-06, "loss": 0.8462, "step": 157090 }, { "epoch": 13.06, "learning_rate": 2.2602666075437184e-06, "loss": 0.8017, "step": 157100 }, { "epoch": 13.06, "learning_rate": 2.260155752016185e-06, "loss": 0.8368, "step": 157110 }, { "epoch": 13.06, "learning_rate": 2.260044896488651e-06, "loss": 0.7526, "step": 157120 }, { "epoch": 13.06, "learning_rate": 2.2599340409611173e-06, "loss": 0.7658, "step": 157130 }, { "epoch": 13.06, "learning_rate": 2.2598231854335835e-06, "loss": 0.7754, "step": 157140 }, { "epoch": 13.06, "learning_rate": 2.25971232990605e-06, "loss": 0.785, "step": 157150 }, { "epoch": 13.06, "learning_rate": 2.2596014743785157e-06, "loss": 0.8434, "step": 157160 }, { "epoch": 13.06, "learning_rate": 2.2594906188509824e-06, "loss": 0.7556, "step": 157170 }, { "epoch": 13.06, "learning_rate": 2.2593797633234487e-06, "loss": 0.7919, "step": 157180 }, { "epoch": 13.07, "learning_rate": 2.259268907795915e-06, "loss": 0.8108, "step": 157190 }, { "epoch": 13.07, "learning_rate": 2.2591580522683813e-06, "loss": 0.7776, "step": 157200 }, { "epoch": 13.07, "learning_rate": 2.259047196740847e-06, "loss": 0.7594, "step": 157210 }, { "epoch": 13.07, "learning_rate": 2.258936341213314e-06, "loss": 0.8089, "step": 157220 }, { "epoch": 13.07, "learning_rate": 2.2588254856857798e-06, "loss": 0.8191, "step": 157230 }, { "epoch": 13.07, "learning_rate": 2.258714630158246e-06, "loss": 0.8036, "step": 157240 }, { "epoch": 13.07, "learning_rate": 2.2586037746307124e-06, "loss": 0.7968, "step": 157250 }, { "epoch": 13.07, "learning_rate": 2.2584929191031787e-06, "loss": 0.8323, "step": 157260 }, { "epoch": 13.07, "learning_rate": 2.258382063575645e-06, "loss": 0.8279, "step": 157270 }, { "epoch": 13.07, "learning_rate": 2.2582712080481113e-06, "loss": 0.8375, "step": 157280 }, { "epoch": 13.07, "learning_rate": 2.258160352520577e-06, "loss": 0.7941, "step": 157290 }, { "epoch": 13.07, "learning_rate": 2.258049496993044e-06, "loss": 0.7503, "step": 157300 }, { "epoch": 13.08, "learning_rate": 2.25793864146551e-06, "loss": 0.7863, "step": 157310 }, { "epoch": 13.08, "learning_rate": 2.257827785937976e-06, "loss": 0.7949, "step": 157320 }, { "epoch": 13.08, "learning_rate": 2.2577169304104427e-06, "loss": 0.7871, "step": 157330 }, { "epoch": 13.08, "learning_rate": 2.2576060748829086e-06, "loss": 0.8207, "step": 157340 }, { "epoch": 13.08, "learning_rate": 2.2574952193553753e-06, "loss": 0.7588, "step": 157350 }, { "epoch": 13.08, "learning_rate": 2.257384363827841e-06, "loss": 0.8364, "step": 157360 }, { "epoch": 13.08, "learning_rate": 2.2572735083003075e-06, "loss": 0.7936, "step": 157370 }, { "epoch": 13.08, "learning_rate": 2.257162652772774e-06, "loss": 0.826, "step": 157380 }, { "epoch": 13.08, "learning_rate": 2.25705179724524e-06, "loss": 0.7536, "step": 157390 }, { "epoch": 13.08, "learning_rate": 2.256940941717706e-06, "loss": 0.7465, "step": 157400 }, { "epoch": 13.08, "learning_rate": 2.2568300861901727e-06, "loss": 0.7625, "step": 157410 }, { "epoch": 13.08, "learning_rate": 2.256719230662639e-06, "loss": 0.8329, "step": 157420 }, { "epoch": 13.09, "learning_rate": 2.256608375135105e-06, "loss": 0.7323, "step": 157430 }, { "epoch": 13.09, "learning_rate": 2.2564975196075716e-06, "loss": 0.8096, "step": 157440 }, { "epoch": 13.09, "learning_rate": 2.2563866640800374e-06, "loss": 0.8086, "step": 157450 }, { "epoch": 13.09, "learning_rate": 2.256275808552504e-06, "loss": 0.8462, "step": 157460 }, { "epoch": 13.09, "learning_rate": 2.25616495302497e-06, "loss": 0.8068, "step": 157470 }, { "epoch": 13.09, "learning_rate": 2.2560540974974363e-06, "loss": 0.8298, "step": 157480 }, { "epoch": 13.09, "learning_rate": 2.2559432419699026e-06, "loss": 0.8176, "step": 157490 }, { "epoch": 13.09, "learning_rate": 2.255832386442369e-06, "loss": 0.7905, "step": 157500 }, { "epoch": 13.09, "learning_rate": 2.2557215309148348e-06, "loss": 0.806, "step": 157510 }, { "epoch": 13.09, "learning_rate": 2.2556106753873015e-06, "loss": 0.7128, "step": 157520 }, { "epoch": 13.09, "learning_rate": 2.2554998198597674e-06, "loss": 0.6768, "step": 157530 }, { "epoch": 13.09, "learning_rate": 2.255388964332234e-06, "loss": 0.7619, "step": 157540 }, { "epoch": 13.1, "learning_rate": 2.2552781088047004e-06, "loss": 0.8208, "step": 157550 }, { "epoch": 13.1, "learning_rate": 2.2551672532771663e-06, "loss": 0.7824, "step": 157560 }, { "epoch": 13.1, "learning_rate": 2.255056397749633e-06, "loss": 0.784, "step": 157570 }, { "epoch": 13.1, "learning_rate": 2.254945542222099e-06, "loss": 0.7828, "step": 157580 }, { "epoch": 13.1, "learning_rate": 2.254834686694565e-06, "loss": 0.7728, "step": 157590 }, { "epoch": 13.1, "learning_rate": 2.2547238311670314e-06, "loss": 0.7673, "step": 157600 }, { "epoch": 13.1, "learning_rate": 2.2546129756394977e-06, "loss": 0.8618, "step": 157610 }, { "epoch": 13.1, "learning_rate": 2.254502120111964e-06, "loss": 0.7756, "step": 157620 }, { "epoch": 13.1, "learning_rate": 2.2543912645844303e-06, "loss": 0.7592, "step": 157630 }, { "epoch": 13.1, "learning_rate": 2.254280409056896e-06, "loss": 0.7737, "step": 157640 }, { "epoch": 13.1, "learning_rate": 2.254169553529363e-06, "loss": 0.7324, "step": 157650 }, { "epoch": 13.1, "learning_rate": 2.2540586980018288e-06, "loss": 0.846, "step": 157660 }, { "epoch": 13.11, "learning_rate": 2.253947842474295e-06, "loss": 0.7686, "step": 157670 }, { "epoch": 13.11, "learning_rate": 2.253836986946762e-06, "loss": 0.8032, "step": 157680 }, { "epoch": 13.11, "learning_rate": 2.2537261314192277e-06, "loss": 0.7906, "step": 157690 }, { "epoch": 13.11, "learning_rate": 2.2536152758916944e-06, "loss": 0.8217, "step": 157700 }, { "epoch": 13.11, "learning_rate": 2.2535044203641603e-06, "loss": 0.8095, "step": 157710 }, { "epoch": 13.11, "learning_rate": 2.2533935648366266e-06, "loss": 0.7774, "step": 157720 }, { "epoch": 13.11, "learning_rate": 2.253282709309093e-06, "loss": 0.8056, "step": 157730 }, { "epoch": 13.11, "learning_rate": 2.253171853781559e-06, "loss": 0.8039, "step": 157740 }, { "epoch": 13.11, "learning_rate": 2.253060998254025e-06, "loss": 0.7554, "step": 157750 }, { "epoch": 13.11, "learning_rate": 2.2529501427264917e-06, "loss": 0.8135, "step": 157760 }, { "epoch": 13.11, "learning_rate": 2.2528392871989576e-06, "loss": 0.7619, "step": 157770 }, { "epoch": 13.11, "learning_rate": 2.2527284316714243e-06, "loss": 0.7735, "step": 157780 }, { "epoch": 13.12, "learning_rate": 2.2526175761438906e-06, "loss": 0.7629, "step": 157790 }, { "epoch": 13.12, "learning_rate": 2.2525067206163565e-06, "loss": 0.8231, "step": 157800 }, { "epoch": 13.12, "learning_rate": 2.2523958650888232e-06, "loss": 0.8028, "step": 157810 }, { "epoch": 13.12, "learning_rate": 2.252285009561289e-06, "loss": 0.8098, "step": 157820 }, { "epoch": 13.12, "learning_rate": 2.2521741540337554e-06, "loss": 0.7521, "step": 157830 }, { "epoch": 13.12, "learning_rate": 2.2520632985062217e-06, "loss": 0.7412, "step": 157840 }, { "epoch": 13.12, "learning_rate": 2.251952442978688e-06, "loss": 0.7726, "step": 157850 }, { "epoch": 13.12, "learning_rate": 2.251841587451154e-06, "loss": 0.8335, "step": 157860 }, { "epoch": 13.12, "learning_rate": 2.2517307319236206e-06, "loss": 0.8133, "step": 157870 }, { "epoch": 13.12, "learning_rate": 2.2516198763960864e-06, "loss": 0.7623, "step": 157880 }, { "epoch": 13.12, "learning_rate": 2.251509020868553e-06, "loss": 0.7554, "step": 157890 }, { "epoch": 13.12, "learning_rate": 2.251398165341019e-06, "loss": 0.8012, "step": 157900 }, { "epoch": 13.13, "learning_rate": 2.2512873098134853e-06, "loss": 0.7839, "step": 157910 }, { "epoch": 13.13, "learning_rate": 2.251176454285952e-06, "loss": 0.8383, "step": 157920 }, { "epoch": 13.13, "learning_rate": 2.251065598758418e-06, "loss": 0.7851, "step": 157930 }, { "epoch": 13.13, "learning_rate": 2.250954743230884e-06, "loss": 0.7894, "step": 157940 }, { "epoch": 13.13, "learning_rate": 2.2508438877033505e-06, "loss": 0.7601, "step": 157950 }, { "epoch": 13.13, "learning_rate": 2.250733032175817e-06, "loss": 0.8147, "step": 157960 }, { "epoch": 13.13, "learning_rate": 2.250622176648283e-06, "loss": 0.7433, "step": 157970 }, { "epoch": 13.13, "learning_rate": 2.2505113211207494e-06, "loss": 0.7487, "step": 157980 }, { "epoch": 13.13, "learning_rate": 2.2504004655932153e-06, "loss": 0.831, "step": 157990 }, { "epoch": 13.13, "learning_rate": 2.250289610065682e-06, "loss": 0.7823, "step": 158000 }, { "epoch": 13.13, "learning_rate": 2.250178754538148e-06, "loss": 0.8418, "step": 158010 }, { "epoch": 13.13, "learning_rate": 2.250067899010614e-06, "loss": 0.7933, "step": 158020 }, { "epoch": 13.14, "learning_rate": 2.2499570434830804e-06, "loss": 0.7936, "step": 158030 }, { "epoch": 13.14, "learning_rate": 2.2498461879555467e-06, "loss": 0.7332, "step": 158040 }, { "epoch": 13.14, "learning_rate": 2.2497353324280135e-06, "loss": 0.7203, "step": 158050 }, { "epoch": 13.14, "learning_rate": 2.2496244769004793e-06, "loss": 0.8399, "step": 158060 }, { "epoch": 13.14, "learning_rate": 2.2495136213729456e-06, "loss": 0.7932, "step": 158070 }, { "epoch": 13.14, "learning_rate": 2.249402765845412e-06, "loss": 0.7142, "step": 158080 }, { "epoch": 13.14, "learning_rate": 2.2492919103178782e-06, "loss": 0.7556, "step": 158090 }, { "epoch": 13.14, "learning_rate": 2.249181054790344e-06, "loss": 0.7923, "step": 158100 }, { "epoch": 13.14, "learning_rate": 2.249070199262811e-06, "loss": 0.8639, "step": 158110 }, { "epoch": 13.14, "learning_rate": 2.2489593437352767e-06, "loss": 0.815, "step": 158120 }, { "epoch": 13.14, "learning_rate": 2.2488484882077434e-06, "loss": 0.7618, "step": 158130 }, { "epoch": 13.14, "learning_rate": 2.2487376326802093e-06, "loss": 0.7705, "step": 158140 }, { "epoch": 13.15, "learning_rate": 2.2486267771526756e-06, "loss": 0.7116, "step": 158150 }, { "epoch": 13.15, "learning_rate": 2.2485159216251423e-06, "loss": 0.8206, "step": 158160 }, { "epoch": 13.15, "learning_rate": 2.248405066097608e-06, "loss": 0.7429, "step": 158170 }, { "epoch": 13.15, "learning_rate": 2.2482942105700745e-06, "loss": 0.7253, "step": 158180 }, { "epoch": 13.15, "learning_rate": 2.2481833550425407e-06, "loss": 0.7586, "step": 158190 }, { "epoch": 13.15, "learning_rate": 2.248072499515007e-06, "loss": 0.7884, "step": 158200 }, { "epoch": 13.15, "learning_rate": 2.247961643987473e-06, "loss": 0.8007, "step": 158210 }, { "epoch": 13.15, "learning_rate": 2.2478507884599396e-06, "loss": 0.8063, "step": 158220 }, { "epoch": 13.15, "learning_rate": 2.2477399329324055e-06, "loss": 0.8115, "step": 158230 }, { "epoch": 13.15, "learning_rate": 2.2476290774048722e-06, "loss": 0.7895, "step": 158240 }, { "epoch": 13.15, "learning_rate": 2.247518221877338e-06, "loss": 0.8285, "step": 158250 }, { "epoch": 13.15, "learning_rate": 2.2474073663498044e-06, "loss": 0.8492, "step": 158260 }, { "epoch": 13.16, "learning_rate": 2.2472965108222707e-06, "loss": 0.8025, "step": 158270 }, { "epoch": 13.16, "learning_rate": 2.247185655294737e-06, "loss": 0.766, "step": 158280 }, { "epoch": 13.16, "learning_rate": 2.2470747997672037e-06, "loss": 0.7565, "step": 158290 }, { "epoch": 13.16, "learning_rate": 2.2469639442396696e-06, "loss": 0.7424, "step": 158300 }, { "epoch": 13.16, "learning_rate": 2.246853088712136e-06, "loss": 0.8233, "step": 158310 }, { "epoch": 13.16, "learning_rate": 2.246742233184602e-06, "loss": 0.7757, "step": 158320 }, { "epoch": 13.16, "learning_rate": 2.2466313776570685e-06, "loss": 0.7875, "step": 158330 }, { "epoch": 13.16, "learning_rate": 2.2465205221295343e-06, "loss": 0.7504, "step": 158340 }, { "epoch": 13.16, "learning_rate": 2.246420752154754e-06, "loss": 0.7678, "step": 158350 }, { "epoch": 13.16, "learning_rate": 2.2463098966272206e-06, "loss": 0.8085, "step": 158360 }, { "epoch": 13.16, "learning_rate": 2.246199041099687e-06, "loss": 0.7403, "step": 158370 }, { "epoch": 13.16, "learning_rate": 2.2460881855721528e-06, "loss": 0.7641, "step": 158380 }, { "epoch": 13.17, "learning_rate": 2.2459773300446195e-06, "loss": 0.7586, "step": 158390 }, { "epoch": 13.17, "learning_rate": 2.2458664745170853e-06, "loss": 0.7935, "step": 158400 }, { "epoch": 13.17, "learning_rate": 2.245755618989552e-06, "loss": 0.8904, "step": 158410 }, { "epoch": 13.17, "learning_rate": 2.245644763462018e-06, "loss": 0.7892, "step": 158420 }, { "epoch": 13.17, "learning_rate": 2.2455339079344842e-06, "loss": 0.7648, "step": 158430 }, { "epoch": 13.17, "learning_rate": 2.2454230524069505e-06, "loss": 0.7917, "step": 158440 }, { "epoch": 13.17, "learning_rate": 2.245312196879417e-06, "loss": 0.7616, "step": 158450 }, { "epoch": 13.17, "learning_rate": 2.2452013413518827e-06, "loss": 0.7866, "step": 158460 }, { "epoch": 13.17, "learning_rate": 2.2450904858243494e-06, "loss": 0.7482, "step": 158470 }, { "epoch": 13.17, "learning_rate": 2.2449796302968153e-06, "loss": 0.7231, "step": 158480 }, { "epoch": 13.17, "learning_rate": 2.244868774769282e-06, "loss": 0.8245, "step": 158490 }, { "epoch": 13.17, "learning_rate": 2.2447579192417483e-06, "loss": 0.7571, "step": 158500 }, { "epoch": 13.18, "learning_rate": 2.244647063714214e-06, "loss": 0.8432, "step": 158510 }, { "epoch": 13.18, "learning_rate": 2.244536208186681e-06, "loss": 0.7351, "step": 158520 }, { "epoch": 13.18, "learning_rate": 2.2444253526591468e-06, "loss": 0.7617, "step": 158530 }, { "epoch": 13.18, "learning_rate": 2.244314497131613e-06, "loss": 0.8126, "step": 158540 }, { "epoch": 13.18, "learning_rate": 2.2442036416040794e-06, "loss": 0.7718, "step": 158550 }, { "epoch": 13.18, "learning_rate": 2.2440927860765456e-06, "loss": 0.8427, "step": 158560 }, { "epoch": 13.18, "learning_rate": 2.243981930549012e-06, "loss": 0.8197, "step": 158570 }, { "epoch": 13.18, "learning_rate": 2.2438710750214782e-06, "loss": 0.7787, "step": 158580 }, { "epoch": 13.18, "learning_rate": 2.243760219493944e-06, "loss": 0.7309, "step": 158590 }, { "epoch": 13.18, "learning_rate": 2.243649363966411e-06, "loss": 0.7438, "step": 158600 }, { "epoch": 13.18, "learning_rate": 2.243538508438877e-06, "loss": 0.8222, "step": 158610 }, { "epoch": 13.18, "learning_rate": 2.243427652911343e-06, "loss": 0.7717, "step": 158620 }, { "epoch": 13.19, "learning_rate": 2.2433167973838097e-06, "loss": 0.7941, "step": 158630 }, { "epoch": 13.19, "learning_rate": 2.2432059418562756e-06, "loss": 0.8143, "step": 158640 }, { "epoch": 13.19, "learning_rate": 2.2430950863287423e-06, "loss": 0.8042, "step": 158650 }, { "epoch": 13.19, "learning_rate": 2.242984230801208e-06, "loss": 0.7897, "step": 158660 }, { "epoch": 13.19, "learning_rate": 2.2428733752736745e-06, "loss": 0.8045, "step": 158670 }, { "epoch": 13.19, "learning_rate": 2.2427625197461408e-06, "loss": 0.7747, "step": 158680 }, { "epoch": 13.19, "learning_rate": 2.242651664218607e-06, "loss": 0.7615, "step": 158690 }, { "epoch": 13.19, "learning_rate": 2.242540808691073e-06, "loss": 0.8169, "step": 158700 }, { "epoch": 13.19, "learning_rate": 2.2424299531635397e-06, "loss": 0.8163, "step": 158710 }, { "epoch": 13.19, "learning_rate": 2.2423190976360055e-06, "loss": 0.8463, "step": 158720 }, { "epoch": 13.19, "learning_rate": 2.2422082421084722e-06, "loss": 0.7953, "step": 158730 }, { "epoch": 13.19, "learning_rate": 2.2420973865809385e-06, "loss": 0.7521, "step": 158740 }, { "epoch": 13.2, "learning_rate": 2.2419865310534044e-06, "loss": 0.7611, "step": 158750 }, { "epoch": 13.2, "learning_rate": 2.241875675525871e-06, "loss": 0.8247, "step": 158760 }, { "epoch": 13.2, "learning_rate": 2.241764819998337e-06, "loss": 0.7527, "step": 158770 }, { "epoch": 13.2, "learning_rate": 2.2416539644708033e-06, "loss": 0.7306, "step": 158780 }, { "epoch": 13.2, "learning_rate": 2.2415431089432696e-06, "loss": 0.7497, "step": 158790 }, { "epoch": 13.2, "learning_rate": 2.241432253415736e-06, "loss": 0.8816, "step": 158800 }, { "epoch": 13.2, "learning_rate": 2.2413213978882018e-06, "loss": 0.9007, "step": 158810 }, { "epoch": 13.2, "learning_rate": 2.2412105423606685e-06, "loss": 0.7887, "step": 158820 }, { "epoch": 13.2, "learning_rate": 2.2410996868331344e-06, "loss": 0.7663, "step": 158830 }, { "epoch": 13.2, "learning_rate": 2.240988831305601e-06, "loss": 0.7824, "step": 158840 }, { "epoch": 13.2, "learning_rate": 2.240877975778067e-06, "loss": 0.7511, "step": 158850 }, { "epoch": 13.2, "learning_rate": 2.2407671202505332e-06, "loss": 0.8258, "step": 158860 }, { "epoch": 13.21, "learning_rate": 2.240656264723e-06, "loss": 0.7436, "step": 158870 }, { "epoch": 13.21, "learning_rate": 2.240545409195466e-06, "loss": 0.787, "step": 158880 }, { "epoch": 13.21, "learning_rate": 2.240434553667932e-06, "loss": 0.7402, "step": 158890 }, { "epoch": 13.21, "learning_rate": 2.2403236981403984e-06, "loss": 0.8479, "step": 158900 }, { "epoch": 13.21, "learning_rate": 2.2402128426128647e-06, "loss": 0.7801, "step": 158910 }, { "epoch": 13.21, "learning_rate": 2.240101987085331e-06, "loss": 0.7426, "step": 158920 }, { "epoch": 13.21, "learning_rate": 2.2399911315577973e-06, "loss": 0.7973, "step": 158930 }, { "epoch": 13.21, "learning_rate": 2.239880276030263e-06, "loss": 0.7499, "step": 158940 }, { "epoch": 13.21, "learning_rate": 2.239780506055483e-06, "loss": 0.7298, "step": 158950 }, { "epoch": 13.21, "learning_rate": 2.2396696505279494e-06, "loss": 0.8727, "step": 158960 }, { "epoch": 13.21, "learning_rate": 2.2395587950004157e-06, "loss": 0.7871, "step": 158970 }, { "epoch": 13.21, "learning_rate": 2.2394479394728816e-06, "loss": 0.7953, "step": 158980 }, { "epoch": 13.22, "learning_rate": 2.2393370839453483e-06, "loss": 0.7516, "step": 158990 }, { "epoch": 13.22, "learning_rate": 2.239226228417814e-06, "loss": 0.783, "step": 159000 }, { "epoch": 13.22, "learning_rate": 2.239115372890281e-06, "loss": 0.8505, "step": 159010 }, { "epoch": 13.22, "learning_rate": 2.2390045173627468e-06, "loss": 0.7197, "step": 159020 }, { "epoch": 13.22, "learning_rate": 2.238893661835213e-06, "loss": 0.8082, "step": 159030 }, { "epoch": 13.22, "learning_rate": 2.2387828063076794e-06, "loss": 0.7691, "step": 159040 }, { "epoch": 13.22, "learning_rate": 2.2386719507801457e-06, "loss": 0.8047, "step": 159050 }, { "epoch": 13.22, "learning_rate": 2.2385610952526115e-06, "loss": 0.7943, "step": 159060 }, { "epoch": 13.22, "learning_rate": 2.2384502397250783e-06, "loss": 0.8336, "step": 159070 }, { "epoch": 13.22, "learning_rate": 2.2383393841975446e-06, "loss": 0.7246, "step": 159080 }, { "epoch": 13.22, "learning_rate": 2.238228528670011e-06, "loss": 0.7247, "step": 159090 }, { "epoch": 13.22, "learning_rate": 2.238117673142477e-06, "loss": 0.8112, "step": 159100 }, { "epoch": 13.23, "learning_rate": 2.238006817614943e-06, "loss": 0.8187, "step": 159110 }, { "epoch": 13.23, "learning_rate": 2.2378959620874097e-06, "loss": 0.769, "step": 159120 }, { "epoch": 13.23, "learning_rate": 2.2377851065598756e-06, "loss": 0.7716, "step": 159130 }, { "epoch": 13.23, "learning_rate": 2.237674251032342e-06, "loss": 0.7912, "step": 159140 }, { "epoch": 13.23, "learning_rate": 2.237563395504808e-06, "loss": 0.7037, "step": 159150 }, { "epoch": 13.23, "learning_rate": 2.2374525399772745e-06, "loss": 0.7865, "step": 159160 }, { "epoch": 13.23, "learning_rate": 2.237341684449741e-06, "loss": 0.7826, "step": 159170 }, { "epoch": 13.23, "learning_rate": 2.237230828922207e-06, "loss": 0.6948, "step": 159180 }, { "epoch": 13.23, "learning_rate": 2.2371199733946734e-06, "loss": 0.7646, "step": 159190 }, { "epoch": 13.23, "learning_rate": 2.2370091178671397e-06, "loss": 0.7042, "step": 159200 }, { "epoch": 13.23, "learning_rate": 2.236898262339606e-06, "loss": 0.7948, "step": 159210 }, { "epoch": 13.23, "learning_rate": 2.236787406812072e-06, "loss": 0.8403, "step": 159220 }, { "epoch": 13.23, "learning_rate": 2.2366765512845386e-06, "loss": 0.7535, "step": 159230 }, { "epoch": 13.24, "learning_rate": 2.2365656957570044e-06, "loss": 0.748, "step": 159240 }, { "epoch": 13.24, "learning_rate": 2.236454840229471e-06, "loss": 0.7384, "step": 159250 }, { "epoch": 13.24, "learning_rate": 2.236343984701937e-06, "loss": 0.8407, "step": 159260 }, { "epoch": 13.24, "learning_rate": 2.2362331291744033e-06, "loss": 0.7599, "step": 159270 }, { "epoch": 13.24, "learning_rate": 2.2361222736468696e-06, "loss": 0.7978, "step": 159280 }, { "epoch": 13.24, "learning_rate": 2.236011418119336e-06, "loss": 0.8753, "step": 159290 }, { "epoch": 13.24, "learning_rate": 2.2359005625918018e-06, "loss": 0.7171, "step": 159300 }, { "epoch": 13.24, "learning_rate": 2.2357897070642685e-06, "loss": 0.7925, "step": 159310 }, { "epoch": 13.24, "learning_rate": 2.235678851536735e-06, "loss": 0.8193, "step": 159320 }, { "epoch": 13.24, "learning_rate": 2.2355679960092007e-06, "loss": 0.7974, "step": 159330 }, { "epoch": 13.24, "learning_rate": 2.2354571404816674e-06, "loss": 0.7878, "step": 159340 }, { "epoch": 13.24, "learning_rate": 2.2353462849541333e-06, "loss": 0.7823, "step": 159350 }, { "epoch": 13.25, "learning_rate": 2.2352354294266e-06, "loss": 0.8178, "step": 159360 }, { "epoch": 13.25, "learning_rate": 2.235124573899066e-06, "loss": 0.7745, "step": 159370 }, { "epoch": 13.25, "learning_rate": 2.235013718371532e-06, "loss": 0.7711, "step": 159380 }, { "epoch": 13.25, "learning_rate": 2.2349028628439984e-06, "loss": 0.7198, "step": 159390 }, { "epoch": 13.25, "learning_rate": 2.2347920073164647e-06, "loss": 0.7727, "step": 159400 }, { "epoch": 13.25, "learning_rate": 2.2346811517889306e-06, "loss": 0.8006, "step": 159410 }, { "epoch": 13.25, "learning_rate": 2.2345702962613973e-06, "loss": 0.8089, "step": 159420 }, { "epoch": 13.25, "learning_rate": 2.234459440733863e-06, "loss": 0.7651, "step": 159430 }, { "epoch": 13.25, "learning_rate": 2.23434858520633e-06, "loss": 0.8442, "step": 159440 }, { "epoch": 13.25, "learning_rate": 2.234237729678796e-06, "loss": 0.8343, "step": 159450 }, { "epoch": 13.25, "learning_rate": 2.234126874151262e-06, "loss": 0.8454, "step": 159460 }, { "epoch": 13.25, "learning_rate": 2.234016018623729e-06, "loss": 0.8061, "step": 159470 }, { "epoch": 13.26, "learning_rate": 2.2339051630961947e-06, "loss": 0.7107, "step": 159480 }, { "epoch": 13.26, "learning_rate": 2.233794307568661e-06, "loss": 0.7008, "step": 159490 }, { "epoch": 13.26, "learning_rate": 2.2336834520411273e-06, "loss": 0.7484, "step": 159500 }, { "epoch": 13.26, "learning_rate": 2.2335725965135936e-06, "loss": 0.8092, "step": 159510 }, { "epoch": 13.26, "learning_rate": 2.23346174098606e-06, "loss": 0.8388, "step": 159520 }, { "epoch": 13.26, "learning_rate": 2.233350885458526e-06, "loss": 0.824, "step": 159530 }, { "epoch": 13.26, "learning_rate": 2.233240029930992e-06, "loss": 0.7752, "step": 159540 }, { "epoch": 13.26, "learning_rate": 2.2331291744034587e-06, "loss": 0.7617, "step": 159550 }, { "epoch": 13.26, "learning_rate": 2.233018318875925e-06, "loss": 0.7739, "step": 159560 }, { "epoch": 13.26, "learning_rate": 2.232907463348391e-06, "loss": 0.7832, "step": 159570 }, { "epoch": 13.26, "learning_rate": 2.2327966078208576e-06, "loss": 0.7708, "step": 159580 }, { "epoch": 13.26, "learning_rate": 2.2326857522933235e-06, "loss": 0.7189, "step": 159590 }, { "epoch": 13.27, "learning_rate": 2.2325748967657902e-06, "loss": 0.7395, "step": 159600 }, { "epoch": 13.27, "learning_rate": 2.232464041238256e-06, "loss": 0.8836, "step": 159610 }, { "epoch": 13.27, "learning_rate": 2.2323531857107224e-06, "loss": 0.804, "step": 159620 }, { "epoch": 13.27, "learning_rate": 2.2322423301831887e-06, "loss": 0.782, "step": 159630 }, { "epoch": 13.27, "learning_rate": 2.232131474655655e-06, "loss": 0.7918, "step": 159640 }, { "epoch": 13.27, "learning_rate": 2.232020619128121e-06, "loss": 0.804, "step": 159650 }, { "epoch": 13.27, "learning_rate": 2.2319097636005876e-06, "loss": 0.7971, "step": 159660 }, { "epoch": 13.27, "learning_rate": 2.2317989080730534e-06, "loss": 0.7654, "step": 159670 }, { "epoch": 13.27, "learning_rate": 2.23168805254552e-06, "loss": 0.7767, "step": 159680 }, { "epoch": 13.27, "learning_rate": 2.2315771970179865e-06, "loss": 0.7786, "step": 159690 }, { "epoch": 13.27, "learning_rate": 2.2314663414904523e-06, "loss": 0.7601, "step": 159700 }, { "epoch": 13.27, "learning_rate": 2.231355485962919e-06, "loss": 0.7831, "step": 159710 }, { "epoch": 13.28, "learning_rate": 2.231244630435385e-06, "loss": 0.7491, "step": 159720 }, { "epoch": 13.28, "learning_rate": 2.231133774907851e-06, "loss": 0.8154, "step": 159730 }, { "epoch": 13.28, "learning_rate": 2.2310229193803175e-06, "loss": 0.7478, "step": 159740 }, { "epoch": 13.28, "learning_rate": 2.230912063852784e-06, "loss": 0.7982, "step": 159750 }, { "epoch": 13.28, "learning_rate": 2.2308012083252497e-06, "loss": 0.7838, "step": 159760 }, { "epoch": 13.28, "learning_rate": 2.2306903527977164e-06, "loss": 0.7785, "step": 159770 }, { "epoch": 13.28, "learning_rate": 2.2305794972701823e-06, "loss": 0.7749, "step": 159780 }, { "epoch": 13.28, "learning_rate": 2.230468641742649e-06, "loss": 0.7951, "step": 159790 }, { "epoch": 13.28, "learning_rate": 2.230357786215115e-06, "loss": 0.763, "step": 159800 }, { "epoch": 13.28, "learning_rate": 2.230246930687581e-06, "loss": 0.8135, "step": 159810 }, { "epoch": 13.28, "learning_rate": 2.230136075160048e-06, "loss": 0.7926, "step": 159820 }, { "epoch": 13.28, "learning_rate": 2.2300252196325137e-06, "loss": 0.7687, "step": 159830 }, { "epoch": 13.29, "learning_rate": 2.22991436410498e-06, "loss": 0.8156, "step": 159840 }, { "epoch": 13.29, "learning_rate": 2.2298035085774463e-06, "loss": 0.7903, "step": 159850 }, { "epoch": 13.29, "learning_rate": 2.2296926530499126e-06, "loss": 0.8258, "step": 159860 }, { "epoch": 13.29, "learning_rate": 2.229581797522379e-06, "loss": 0.8157, "step": 159870 }, { "epoch": 13.29, "learning_rate": 2.2294709419948452e-06, "loss": 0.795, "step": 159880 }, { "epoch": 13.29, "learning_rate": 2.229360086467311e-06, "loss": 0.7892, "step": 159890 }, { "epoch": 13.29, "learning_rate": 2.229249230939778e-06, "loss": 0.7979, "step": 159900 }, { "epoch": 13.29, "learning_rate": 2.2291383754122437e-06, "loss": 0.8191, "step": 159910 }, { "epoch": 13.29, "learning_rate": 2.22902751988471e-06, "loss": 0.8043, "step": 159920 }, { "epoch": 13.29, "learning_rate": 2.2289166643571767e-06, "loss": 0.7436, "step": 159930 }, { "epoch": 13.29, "learning_rate": 2.2288058088296426e-06, "loss": 0.7776, "step": 159940 }, { "epoch": 13.29, "learning_rate": 2.2286949533021093e-06, "loss": 0.8304, "step": 159950 }, { "epoch": 13.3, "learning_rate": 2.228584097774575e-06, "loss": 0.7479, "step": 159960 }, { "epoch": 13.3, "learning_rate": 2.2284732422470415e-06, "loss": 0.8176, "step": 159970 }, { "epoch": 13.3, "learning_rate": 2.2283623867195077e-06, "loss": 0.8094, "step": 159980 }, { "epoch": 13.3, "learning_rate": 2.228251531191974e-06, "loss": 0.752, "step": 159990 }, { "epoch": 13.3, "learning_rate": 2.22814067566444e-06, "loss": 0.7468, "step": 160000 }, { "epoch": 13.3, "learning_rate": 2.2280298201369066e-06, "loss": 0.7994, "step": 160010 }, { "epoch": 13.3, "learning_rate": 2.2279189646093725e-06, "loss": 0.7728, "step": 160020 }, { "epoch": 13.3, "learning_rate": 2.2278081090818392e-06, "loss": 0.8233, "step": 160030 }, { "epoch": 13.3, "learning_rate": 2.227697253554305e-06, "loss": 0.742, "step": 160040 }, { "epoch": 13.3, "learning_rate": 2.2275863980267714e-06, "loss": 0.7757, "step": 160050 }, { "epoch": 13.3, "learning_rate": 2.227475542499238e-06, "loss": 0.8208, "step": 160060 }, { "epoch": 13.3, "learning_rate": 2.227364686971704e-06, "loss": 0.7962, "step": 160070 }, { "epoch": 13.31, "learning_rate": 2.2272538314441703e-06, "loss": 0.7237, "step": 160080 }, { "epoch": 13.31, "learning_rate": 2.2271429759166366e-06, "loss": 0.8015, "step": 160090 }, { "epoch": 13.31, "learning_rate": 2.227032120389103e-06, "loss": 0.7715, "step": 160100 }, { "epoch": 13.31, "learning_rate": 2.2269212648615687e-06, "loss": 0.8138, "step": 160110 }, { "epoch": 13.31, "learning_rate": 2.2268104093340355e-06, "loss": 0.7202, "step": 160120 }, { "epoch": 13.31, "learning_rate": 2.2266995538065013e-06, "loss": 0.7775, "step": 160130 }, { "epoch": 13.31, "learning_rate": 2.226588698278968e-06, "loss": 0.76, "step": 160140 }, { "epoch": 13.31, "learning_rate": 2.226477842751434e-06, "loss": 0.8029, "step": 160150 }, { "epoch": 13.31, "learning_rate": 2.2263669872239002e-06, "loss": 0.786, "step": 160160 }, { "epoch": 13.31, "learning_rate": 2.2262561316963665e-06, "loss": 0.7068, "step": 160170 }, { "epoch": 13.31, "learning_rate": 2.226145276168833e-06, "loss": 0.711, "step": 160180 }, { "epoch": 13.31, "learning_rate": 2.2260344206412995e-06, "loss": 0.769, "step": 160190 }, { "epoch": 13.32, "learning_rate": 2.2259235651137654e-06, "loss": 0.8072, "step": 160200 }, { "epoch": 13.32, "learning_rate": 2.2258127095862317e-06, "loss": 0.8682, "step": 160210 }, { "epoch": 13.32, "learning_rate": 2.225701854058698e-06, "loss": 0.7412, "step": 160220 }, { "epoch": 13.32, "learning_rate": 2.2255909985311643e-06, "loss": 0.7893, "step": 160230 }, { "epoch": 13.32, "learning_rate": 2.22548014300363e-06, "loss": 0.7569, "step": 160240 }, { "epoch": 13.32, "learning_rate": 2.225369287476097e-06, "loss": 0.7942, "step": 160250 }, { "epoch": 13.32, "learning_rate": 2.2252584319485627e-06, "loss": 0.8165, "step": 160260 }, { "epoch": 13.32, "learning_rate": 2.225147576421029e-06, "loss": 0.8121, "step": 160270 }, { "epoch": 13.32, "learning_rate": 2.2250367208934953e-06, "loss": 0.7991, "step": 160280 }, { "epoch": 13.32, "learning_rate": 2.2249258653659616e-06, "loss": 0.7026, "step": 160290 }, { "epoch": 13.32, "learning_rate": 2.2248150098384283e-06, "loss": 0.7762, "step": 160300 }, { "epoch": 13.32, "learning_rate": 2.2247041543108942e-06, "loss": 0.8219, "step": 160310 }, { "epoch": 13.33, "learning_rate": 2.2245932987833605e-06, "loss": 0.7193, "step": 160320 }, { "epoch": 13.33, "learning_rate": 2.224482443255827e-06, "loss": 0.7781, "step": 160330 }, { "epoch": 13.33, "learning_rate": 2.224371587728293e-06, "loss": 0.7591, "step": 160340 }, { "epoch": 13.33, "learning_rate": 2.224260732200759e-06, "loss": 0.7764, "step": 160350 }, { "epoch": 13.33, "learning_rate": 2.2241498766732257e-06, "loss": 0.7957, "step": 160360 }, { "epoch": 13.33, "learning_rate": 2.2240390211456916e-06, "loss": 0.8208, "step": 160370 }, { "epoch": 13.33, "learning_rate": 2.2239281656181583e-06, "loss": 0.7582, "step": 160380 }, { "epoch": 13.33, "learning_rate": 2.223817310090624e-06, "loss": 0.7124, "step": 160390 }, { "epoch": 13.33, "learning_rate": 2.2237064545630905e-06, "loss": 0.8193, "step": 160400 }, { "epoch": 13.33, "learning_rate": 2.2235955990355568e-06, "loss": 0.8253, "step": 160410 }, { "epoch": 13.33, "learning_rate": 2.223484743508023e-06, "loss": 0.7494, "step": 160420 }, { "epoch": 13.33, "learning_rate": 2.2233738879804893e-06, "loss": 0.8523, "step": 160430 }, { "epoch": 13.34, "learning_rate": 2.2232630324529556e-06, "loss": 0.7732, "step": 160440 }, { "epoch": 13.34, "learning_rate": 2.223152176925422e-06, "loss": 0.7984, "step": 160450 }, { "epoch": 13.34, "learning_rate": 2.2230413213978882e-06, "loss": 0.8685, "step": 160460 }, { "epoch": 13.34, "learning_rate": 2.2229304658703545e-06, "loss": 0.7487, "step": 160470 }, { "epoch": 13.34, "learning_rate": 2.2228196103428204e-06, "loss": 0.8249, "step": 160480 }, { "epoch": 13.34, "learning_rate": 2.222708754815287e-06, "loss": 0.7685, "step": 160490 }, { "epoch": 13.34, "learning_rate": 2.222597899287753e-06, "loss": 0.7808, "step": 160500 }, { "epoch": 13.34, "learning_rate": 2.2224870437602193e-06, "loss": 0.9116, "step": 160510 }, { "epoch": 13.34, "learning_rate": 2.2223761882326856e-06, "loss": 0.8741, "step": 160520 }, { "epoch": 13.34, "learning_rate": 2.222265332705152e-06, "loss": 0.845, "step": 160530 }, { "epoch": 13.34, "learning_rate": 2.2221544771776177e-06, "loss": 0.727, "step": 160540 }, { "epoch": 13.34, "learning_rate": 2.2220436216500845e-06, "loss": 0.8559, "step": 160550 }, { "epoch": 13.35, "learning_rate": 2.2219327661225508e-06, "loss": 0.8237, "step": 160560 }, { "epoch": 13.35, "learning_rate": 2.221821910595017e-06, "loss": 0.7939, "step": 160570 }, { "epoch": 13.35, "learning_rate": 2.2217110550674833e-06, "loss": 0.7568, "step": 160580 }, { "epoch": 13.35, "learning_rate": 2.2216001995399492e-06, "loss": 0.7838, "step": 160590 }, { "epoch": 13.35, "learning_rate": 2.221489344012416e-06, "loss": 0.711, "step": 160600 }, { "epoch": 13.35, "learning_rate": 2.221378488484882e-06, "loss": 0.8469, "step": 160610 }, { "epoch": 13.35, "learning_rate": 2.221267632957348e-06, "loss": 0.7909, "step": 160620 }, { "epoch": 13.35, "learning_rate": 2.2211567774298144e-06, "loss": 0.7102, "step": 160630 }, { "epoch": 13.35, "learning_rate": 2.2210459219022807e-06, "loss": 0.8248, "step": 160640 }, { "epoch": 13.35, "learning_rate": 2.220935066374747e-06, "loss": 0.7721, "step": 160650 }, { "epoch": 13.35, "learning_rate": 2.2208242108472133e-06, "loss": 0.8286, "step": 160660 }, { "epoch": 13.35, "learning_rate": 2.2207133553196796e-06, "loss": 0.745, "step": 160670 }, { "epoch": 13.36, "learning_rate": 2.220602499792146e-06, "loss": 0.802, "step": 160680 }, { "epoch": 13.36, "learning_rate": 2.220491644264612e-06, "loss": 0.8068, "step": 160690 }, { "epoch": 13.36, "learning_rate": 2.220380788737078e-06, "loss": 0.7539, "step": 160700 }, { "epoch": 13.36, "learning_rate": 2.2202699332095448e-06, "loss": 0.8927, "step": 160710 }, { "epoch": 13.36, "learning_rate": 2.2201590776820106e-06, "loss": 0.7937, "step": 160720 }, { "epoch": 13.36, "learning_rate": 2.2200482221544774e-06, "loss": 0.742, "step": 160730 }, { "epoch": 13.36, "learning_rate": 2.2199373666269432e-06, "loss": 0.7204, "step": 160740 }, { "epoch": 13.36, "learning_rate": 2.2198265110994095e-06, "loss": 0.7291, "step": 160750 }, { "epoch": 13.36, "learning_rate": 2.219715655571876e-06, "loss": 0.8595, "step": 160760 }, { "epoch": 13.36, "learning_rate": 2.219604800044342e-06, "loss": 0.8243, "step": 160770 }, { "epoch": 13.36, "learning_rate": 2.219493944516808e-06, "loss": 0.8089, "step": 160780 }, { "epoch": 13.36, "learning_rate": 2.2193830889892747e-06, "loss": 0.7646, "step": 160790 }, { "epoch": 13.37, "learning_rate": 2.219272233461741e-06, "loss": 0.8134, "step": 160800 }, { "epoch": 13.37, "learning_rate": 2.2191613779342073e-06, "loss": 0.8493, "step": 160810 }, { "epoch": 13.37, "learning_rate": 2.2190505224066736e-06, "loss": 0.7697, "step": 160820 }, { "epoch": 13.37, "learning_rate": 2.2189396668791395e-06, "loss": 0.6953, "step": 160830 }, { "epoch": 13.37, "learning_rate": 2.218828811351606e-06, "loss": 0.789, "step": 160840 }, { "epoch": 13.37, "learning_rate": 2.218717955824072e-06, "loss": 0.7102, "step": 160850 }, { "epoch": 13.37, "learning_rate": 2.2186071002965383e-06, "loss": 0.7638, "step": 160860 }, { "epoch": 13.37, "learning_rate": 2.2184962447690046e-06, "loss": 0.804, "step": 160870 }, { "epoch": 13.37, "learning_rate": 2.218385389241471e-06, "loss": 0.7811, "step": 160880 }, { "epoch": 13.37, "learning_rate": 2.2182745337139372e-06, "loss": 0.7819, "step": 160890 }, { "epoch": 13.37, "learning_rate": 2.2181636781864035e-06, "loss": 0.7522, "step": 160900 }, { "epoch": 13.37, "learning_rate": 2.21805282265887e-06, "loss": 0.7787, "step": 160910 }, { "epoch": 13.38, "learning_rate": 2.217941967131336e-06, "loss": 0.7581, "step": 160920 }, { "epoch": 13.38, "learning_rate": 2.2178311116038024e-06, "loss": 0.7884, "step": 160930 }, { "epoch": 13.38, "learning_rate": 2.2177202560762683e-06, "loss": 0.807, "step": 160940 }, { "epoch": 13.38, "learning_rate": 2.217609400548735e-06, "loss": 0.7754, "step": 160950 }, { "epoch": 13.38, "learning_rate": 2.217498545021201e-06, "loss": 0.7874, "step": 160960 }, { "epoch": 13.38, "learning_rate": 2.2173876894936676e-06, "loss": 0.7385, "step": 160970 }, { "epoch": 13.38, "learning_rate": 2.2172768339661335e-06, "loss": 0.825, "step": 160980 }, { "epoch": 13.38, "learning_rate": 2.2171659784385998e-06, "loss": 0.7555, "step": 160990 }, { "epoch": 13.38, "learning_rate": 2.217055122911066e-06, "loss": 0.7596, "step": 161000 }, { "epoch": 13.38, "learning_rate": 2.2169442673835324e-06, "loss": 0.8539, "step": 161010 }, { "epoch": 13.38, "learning_rate": 2.2168334118559982e-06, "loss": 0.8005, "step": 161020 }, { "epoch": 13.38, "learning_rate": 2.216722556328465e-06, "loss": 0.8211, "step": 161030 }, { "epoch": 13.39, "learning_rate": 2.2166117008009312e-06, "loss": 0.8301, "step": 161040 }, { "epoch": 13.39, "learning_rate": 2.216500845273397e-06, "loss": 0.7658, "step": 161050 }, { "epoch": 13.39, "learning_rate": 2.216389989745864e-06, "loss": 0.873, "step": 161060 }, { "epoch": 13.39, "learning_rate": 2.2162791342183297e-06, "loss": 0.7701, "step": 161070 }, { "epoch": 13.39, "learning_rate": 2.2161682786907964e-06, "loss": 0.8, "step": 161080 }, { "epoch": 13.39, "learning_rate": 2.2160574231632623e-06, "loss": 0.7801, "step": 161090 }, { "epoch": 13.39, "learning_rate": 2.2159465676357286e-06, "loss": 0.8152, "step": 161100 }, { "epoch": 13.39, "learning_rate": 2.215835712108195e-06, "loss": 0.8595, "step": 161110 }, { "epoch": 13.39, "learning_rate": 2.215724856580661e-06, "loss": 0.7724, "step": 161120 }, { "epoch": 13.39, "learning_rate": 2.215614001053127e-06, "loss": 0.7696, "step": 161130 }, { "epoch": 13.39, "learning_rate": 2.2155031455255938e-06, "loss": 0.7743, "step": 161140 }, { "epoch": 13.39, "learning_rate": 2.2153922899980596e-06, "loss": 0.7583, "step": 161150 }, { "epoch": 13.4, "learning_rate": 2.2152814344705264e-06, "loss": 0.7452, "step": 161160 }, { "epoch": 13.4, "learning_rate": 2.2151705789429927e-06, "loss": 0.7886, "step": 161170 }, { "epoch": 13.4, "learning_rate": 2.2150597234154585e-06, "loss": 0.7629, "step": 161180 }, { "epoch": 13.4, "learning_rate": 2.2149488678879252e-06, "loss": 0.7409, "step": 161190 }, { "epoch": 13.4, "learning_rate": 2.214838012360391e-06, "loss": 0.7809, "step": 161200 }, { "epoch": 13.4, "learning_rate": 2.2147271568328574e-06, "loss": 0.8362, "step": 161210 }, { "epoch": 13.4, "learning_rate": 2.2146163013053237e-06, "loss": 0.7513, "step": 161220 }, { "epoch": 13.4, "learning_rate": 2.21450544577779e-06, "loss": 0.7542, "step": 161230 }, { "epoch": 13.4, "learning_rate": 2.2143945902502563e-06, "loss": 0.7793, "step": 161240 }, { "epoch": 13.4, "learning_rate": 2.2142837347227226e-06, "loss": 0.7125, "step": 161250 }, { "epoch": 13.4, "learning_rate": 2.2141728791951885e-06, "loss": 0.8599, "step": 161260 }, { "epoch": 13.4, "learning_rate": 2.214062023667655e-06, "loss": 0.8854, "step": 161270 }, { "epoch": 13.41, "learning_rate": 2.2139511681401215e-06, "loss": 0.785, "step": 161280 }, { "epoch": 13.41, "learning_rate": 2.2138403126125874e-06, "loss": 0.7521, "step": 161290 }, { "epoch": 13.41, "learning_rate": 2.213729457085054e-06, "loss": 0.7804, "step": 161300 }, { "epoch": 13.41, "learning_rate": 2.21361860155752e-06, "loss": 0.78, "step": 161310 }, { "epoch": 13.41, "learning_rate": 2.2135077460299867e-06, "loss": 0.7522, "step": 161320 }, { "epoch": 13.41, "learning_rate": 2.2133968905024525e-06, "loss": 0.7892, "step": 161330 }, { "epoch": 13.41, "learning_rate": 2.213286034974919e-06, "loss": 0.8005, "step": 161340 }, { "epoch": 13.41, "learning_rate": 2.213175179447385e-06, "loss": 0.8578, "step": 161350 }, { "epoch": 13.41, "learning_rate": 2.2130643239198514e-06, "loss": 0.7732, "step": 161360 }, { "epoch": 13.41, "learning_rate": 2.2129534683923173e-06, "loss": 0.8352, "step": 161370 }, { "epoch": 13.41, "learning_rate": 2.212842612864784e-06, "loss": 0.7657, "step": 161380 }, { "epoch": 13.41, "learning_rate": 2.21273175733725e-06, "loss": 0.7727, "step": 161390 }, { "epoch": 13.42, "learning_rate": 2.212620901809716e-06, "loss": 0.8097, "step": 161400 }, { "epoch": 13.42, "learning_rate": 2.212510046282183e-06, "loss": 0.8368, "step": 161410 }, { "epoch": 13.42, "learning_rate": 2.2123991907546488e-06, "loss": 0.7629, "step": 161420 }, { "epoch": 13.42, "learning_rate": 2.2122883352271155e-06, "loss": 0.7398, "step": 161430 }, { "epoch": 13.42, "learning_rate": 2.2121774796995814e-06, "loss": 0.8275, "step": 161440 }, { "epoch": 13.42, "learning_rate": 2.2120666241720477e-06, "loss": 0.8162, "step": 161450 }, { "epoch": 13.42, "learning_rate": 2.211955768644514e-06, "loss": 0.7808, "step": 161460 }, { "epoch": 13.42, "learning_rate": 2.2118449131169802e-06, "loss": 0.7987, "step": 161470 }, { "epoch": 13.42, "learning_rate": 2.211734057589446e-06, "loss": 0.7908, "step": 161480 }, { "epoch": 13.42, "learning_rate": 2.211623202061913e-06, "loss": 0.8122, "step": 161490 }, { "epoch": 13.42, "learning_rate": 2.2115234320871324e-06, "loss": 0.8009, "step": 161500 }, { "epoch": 13.42, "learning_rate": 2.2114125765595987e-06, "loss": 0.7744, "step": 161510 }, { "epoch": 13.43, "learning_rate": 2.211301721032065e-06, "loss": 0.7505, "step": 161520 }, { "epoch": 13.43, "learning_rate": 2.2111908655045313e-06, "loss": 0.8405, "step": 161530 }, { "epoch": 13.43, "learning_rate": 2.211080009976997e-06, "loss": 0.7728, "step": 161540 }, { "epoch": 13.43, "learning_rate": 2.210969154449464e-06, "loss": 0.7766, "step": 161550 }, { "epoch": 13.43, "learning_rate": 2.2108582989219297e-06, "loss": 0.8031, "step": 161560 }, { "epoch": 13.43, "learning_rate": 2.210747443394396e-06, "loss": 0.7343, "step": 161570 }, { "epoch": 13.43, "learning_rate": 2.2106365878668623e-06, "loss": 0.7241, "step": 161580 }, { "epoch": 13.43, "learning_rate": 2.2105257323393286e-06, "loss": 0.786, "step": 161590 }, { "epoch": 13.43, "learning_rate": 2.210414876811795e-06, "loss": 0.7733, "step": 161600 }, { "epoch": 13.43, "learning_rate": 2.210304021284261e-06, "loss": 0.8571, "step": 161610 }, { "epoch": 13.43, "learning_rate": 2.2101931657567275e-06, "loss": 0.8444, "step": 161620 }, { "epoch": 13.43, "learning_rate": 2.210082310229194e-06, "loss": 0.7509, "step": 161630 }, { "epoch": 13.44, "learning_rate": 2.20997145470166e-06, "loss": 0.738, "step": 161640 }, { "epoch": 13.44, "learning_rate": 2.209860599174126e-06, "loss": 0.7963, "step": 161650 }, { "epoch": 13.44, "learning_rate": 2.2097497436465927e-06, "loss": 0.8562, "step": 161660 }, { "epoch": 13.44, "learning_rate": 2.2096388881190585e-06, "loss": 0.7744, "step": 161670 }, { "epoch": 13.44, "learning_rate": 2.2095280325915253e-06, "loss": 0.7937, "step": 161680 }, { "epoch": 13.44, "learning_rate": 2.209417177063991e-06, "loss": 0.7743, "step": 161690 }, { "epoch": 13.44, "learning_rate": 2.2093063215364574e-06, "loss": 0.76, "step": 161700 }, { "epoch": 13.44, "learning_rate": 2.2091954660089237e-06, "loss": 0.8419, "step": 161710 }, { "epoch": 13.44, "learning_rate": 2.20908461048139e-06, "loss": 0.783, "step": 161720 }, { "epoch": 13.44, "learning_rate": 2.208973754953856e-06, "loss": 0.8353, "step": 161730 }, { "epoch": 13.44, "learning_rate": 2.2088628994263226e-06, "loss": 0.7941, "step": 161740 }, { "epoch": 13.44, "learning_rate": 2.208752043898789e-06, "loss": 0.78, "step": 161750 }, { "epoch": 13.45, "learning_rate": 2.208641188371255e-06, "loss": 0.7938, "step": 161760 }, { "epoch": 13.45, "learning_rate": 2.2085303328437215e-06, "loss": 0.8418, "step": 161770 }, { "epoch": 13.45, "learning_rate": 2.2084194773161874e-06, "loss": 0.8494, "step": 161780 }, { "epoch": 13.45, "learning_rate": 2.208308621788654e-06, "loss": 0.7845, "step": 161790 }, { "epoch": 13.45, "learning_rate": 2.20819776626112e-06, "loss": 0.7981, "step": 161800 }, { "epoch": 13.45, "learning_rate": 2.2080869107335863e-06, "loss": 0.7532, "step": 161810 }, { "epoch": 13.45, "learning_rate": 2.2079760552060526e-06, "loss": 0.818, "step": 161820 }, { "epoch": 13.45, "learning_rate": 2.207865199678519e-06, "loss": 0.8004, "step": 161830 }, { "epoch": 13.45, "learning_rate": 2.207754344150985e-06, "loss": 0.8083, "step": 161840 }, { "epoch": 13.45, "learning_rate": 2.2076434886234514e-06, "loss": 0.7903, "step": 161850 }, { "epoch": 13.45, "learning_rate": 2.2075326330959177e-06, "loss": 0.7983, "step": 161860 }, { "epoch": 13.45, "learning_rate": 2.207421777568384e-06, "loss": 0.8527, "step": 161870 }, { "epoch": 13.46, "learning_rate": 2.2073109220408503e-06, "loss": 0.7788, "step": 161880 }, { "epoch": 13.46, "learning_rate": 2.207200066513316e-06, "loss": 0.7355, "step": 161890 }, { "epoch": 13.46, "learning_rate": 2.207089210985783e-06, "loss": 0.8016, "step": 161900 }, { "epoch": 13.46, "learning_rate": 2.206978355458249e-06, "loss": 0.8556, "step": 161910 }, { "epoch": 13.46, "learning_rate": 2.2068674999307155e-06, "loss": 0.7743, "step": 161920 }, { "epoch": 13.46, "learning_rate": 2.2067566444031814e-06, "loss": 0.736, "step": 161930 }, { "epoch": 13.46, "learning_rate": 2.2066457888756477e-06, "loss": 0.793, "step": 161940 }, { "epoch": 13.46, "learning_rate": 2.206534933348114e-06, "loss": 0.8197, "step": 161950 }, { "epoch": 13.46, "learning_rate": 2.2064240778205803e-06, "loss": 0.8043, "step": 161960 }, { "epoch": 13.46, "learning_rate": 2.206313222293046e-06, "loss": 0.8118, "step": 161970 }, { "epoch": 13.46, "learning_rate": 2.206202366765513e-06, "loss": 0.7259, "step": 161980 }, { "epoch": 13.46, "learning_rate": 2.206091511237979e-06, "loss": 0.7771, "step": 161990 }, { "epoch": 13.47, "learning_rate": 2.205980655710445e-06, "loss": 0.7873, "step": 162000 }, { "epoch": 13.47, "learning_rate": 2.2058698001829117e-06, "loss": 0.7854, "step": 162010 }, { "epoch": 13.47, "learning_rate": 2.2057589446553776e-06, "loss": 0.8008, "step": 162020 }, { "epoch": 13.47, "learning_rate": 2.2056480891278443e-06, "loss": 0.749, "step": 162030 }, { "epoch": 13.47, "learning_rate": 2.20553723360031e-06, "loss": 0.7293, "step": 162040 }, { "epoch": 13.47, "learning_rate": 2.2054263780727765e-06, "loss": 0.7973, "step": 162050 }, { "epoch": 13.47, "learning_rate": 2.205315522545243e-06, "loss": 0.7807, "step": 162060 }, { "epoch": 13.47, "learning_rate": 2.205204667017709e-06, "loss": 0.7911, "step": 162070 }, { "epoch": 13.47, "learning_rate": 2.205093811490175e-06, "loss": 0.8138, "step": 162080 }, { "epoch": 13.47, "learning_rate": 2.2049829559626417e-06, "loss": 0.7419, "step": 162090 }, { "epoch": 13.47, "learning_rate": 2.2048721004351076e-06, "loss": 0.7482, "step": 162100 }, { "epoch": 13.47, "learning_rate": 2.2047612449075743e-06, "loss": 0.8328, "step": 162110 }, { "epoch": 13.48, "learning_rate": 2.2046503893800406e-06, "loss": 0.7771, "step": 162120 }, { "epoch": 13.48, "learning_rate": 2.2045395338525064e-06, "loss": 0.7525, "step": 162130 }, { "epoch": 13.48, "learning_rate": 2.204428678324973e-06, "loss": 0.7785, "step": 162140 }, { "epoch": 13.48, "learning_rate": 2.204317822797439e-06, "loss": 0.7666, "step": 162150 }, { "epoch": 13.48, "learning_rate": 2.2042069672699053e-06, "loss": 0.7101, "step": 162160 }, { "epoch": 13.48, "learning_rate": 2.2040961117423716e-06, "loss": 0.7664, "step": 162170 }, { "epoch": 13.48, "learning_rate": 2.203985256214838e-06, "loss": 0.7807, "step": 162180 }, { "epoch": 13.48, "learning_rate": 2.2038744006873042e-06, "loss": 0.762, "step": 162190 }, { "epoch": 13.48, "learning_rate": 2.2037635451597705e-06, "loss": 0.8183, "step": 162200 }, { "epoch": 13.48, "learning_rate": 2.2036526896322364e-06, "loss": 0.8398, "step": 162210 }, { "epoch": 13.48, "learning_rate": 2.203541834104703e-06, "loss": 0.763, "step": 162220 }, { "epoch": 13.48, "learning_rate": 2.2034309785771694e-06, "loss": 0.7589, "step": 162230 }, { "epoch": 13.49, "learning_rate": 2.2033201230496353e-06, "loss": 0.7921, "step": 162240 }, { "epoch": 13.49, "learning_rate": 2.203209267522102e-06, "loss": 0.7171, "step": 162250 }, { "epoch": 13.49, "learning_rate": 2.203098411994568e-06, "loss": 0.8188, "step": 162260 }, { "epoch": 13.49, "learning_rate": 2.2029875564670346e-06, "loss": 0.7772, "step": 162270 }, { "epoch": 13.49, "learning_rate": 2.2028767009395004e-06, "loss": 0.754, "step": 162280 }, { "epoch": 13.49, "learning_rate": 2.2027658454119667e-06, "loss": 0.7601, "step": 162290 }, { "epoch": 13.49, "learning_rate": 2.202654989884433e-06, "loss": 0.7448, "step": 162300 }, { "epoch": 13.49, "learning_rate": 2.2025441343568993e-06, "loss": 0.8582, "step": 162310 }, { "epoch": 13.49, "learning_rate": 2.202433278829365e-06, "loss": 0.7429, "step": 162320 }, { "epoch": 13.49, "learning_rate": 2.202322423301832e-06, "loss": 0.8238, "step": 162330 }, { "epoch": 13.49, "learning_rate": 2.202211567774298e-06, "loss": 0.7881, "step": 162340 }, { "epoch": 13.49, "learning_rate": 2.2021007122467645e-06, "loss": 0.7794, "step": 162350 }, { "epoch": 13.5, "learning_rate": 2.201989856719231e-06, "loss": 0.813, "step": 162360 }, { "epoch": 13.5, "learning_rate": 2.2018790011916967e-06, "loss": 0.7842, "step": 162370 }, { "epoch": 13.5, "learning_rate": 2.2017681456641634e-06, "loss": 0.7356, "step": 162380 }, { "epoch": 13.5, "learning_rate": 2.2016572901366293e-06, "loss": 0.7667, "step": 162390 }, { "epoch": 13.5, "learning_rate": 2.2015464346090956e-06, "loss": 0.799, "step": 162400 }, { "epoch": 13.5, "learning_rate": 2.201435579081562e-06, "loss": 0.7305, "step": 162410 }, { "epoch": 13.5, "learning_rate": 2.201324723554028e-06, "loss": 0.8048, "step": 162420 }, { "epoch": 13.5, "learning_rate": 2.201213868026494e-06, "loss": 0.7094, "step": 162430 }, { "epoch": 13.5, "learning_rate": 2.2011030124989607e-06, "loss": 0.8179, "step": 162440 }, { "epoch": 13.5, "learning_rate": 2.2009921569714266e-06, "loss": 0.7936, "step": 162450 }, { "epoch": 13.5, "learning_rate": 2.2008813014438933e-06, "loss": 0.804, "step": 162460 }, { "epoch": 13.5, "learning_rate": 2.200770445916359e-06, "loss": 0.8025, "step": 162470 }, { "epoch": 13.51, "learning_rate": 2.2006595903888255e-06, "loss": 0.8541, "step": 162480 }, { "epoch": 13.51, "learning_rate": 2.2005487348612922e-06, "loss": 0.828, "step": 162490 }, { "epoch": 13.51, "learning_rate": 2.200437879333758e-06, "loss": 0.7202, "step": 162500 }, { "epoch": 13.51, "learning_rate": 2.2003270238062244e-06, "loss": 0.8161, "step": 162510 }, { "epoch": 13.51, "learning_rate": 2.2002161682786907e-06, "loss": 0.8158, "step": 162520 }, { "epoch": 13.51, "learning_rate": 2.200105312751157e-06, "loss": 0.7936, "step": 162530 }, { "epoch": 13.51, "learning_rate": 2.1999944572236233e-06, "loss": 0.7735, "step": 162540 }, { "epoch": 13.51, "learning_rate": 2.1998836016960896e-06, "loss": 0.8187, "step": 162550 }, { "epoch": 13.51, "learning_rate": 2.1997727461685554e-06, "loss": 0.8154, "step": 162560 }, { "epoch": 13.51, "learning_rate": 2.199661890641022e-06, "loss": 0.7504, "step": 162570 }, { "epoch": 13.51, "learning_rate": 2.199551035113488e-06, "loss": 0.7515, "step": 162580 }, { "epoch": 13.51, "learning_rate": 2.1994401795859543e-06, "loss": 0.8025, "step": 162590 }, { "epoch": 13.52, "learning_rate": 2.199329324058421e-06, "loss": 0.7581, "step": 162600 }, { "epoch": 13.52, "learning_rate": 2.199218468530887e-06, "loss": 0.8211, "step": 162610 }, { "epoch": 13.52, "learning_rate": 2.1991076130033536e-06, "loss": 0.7483, "step": 162620 }, { "epoch": 13.52, "learning_rate": 2.1989967574758195e-06, "loss": 0.7712, "step": 162630 }, { "epoch": 13.52, "learning_rate": 2.198885901948286e-06, "loss": 0.8004, "step": 162640 }, { "epoch": 13.52, "learning_rate": 2.198775046420752e-06, "loss": 0.8085, "step": 162650 }, { "epoch": 13.52, "learning_rate": 2.1986641908932184e-06, "loss": 0.8169, "step": 162660 }, { "epoch": 13.52, "learning_rate": 2.1985533353656843e-06, "loss": 0.8411, "step": 162670 }, { "epoch": 13.52, "learning_rate": 2.198442479838151e-06, "loss": 0.7258, "step": 162680 }, { "epoch": 13.52, "learning_rate": 2.198331624310617e-06, "loss": 0.7193, "step": 162690 }, { "epoch": 13.52, "learning_rate": 2.1982207687830836e-06, "loss": 0.8482, "step": 162700 }, { "epoch": 13.52, "learning_rate": 2.1981099132555495e-06, "loss": 0.835, "step": 162710 }, { "epoch": 13.53, "learning_rate": 2.1979990577280157e-06, "loss": 0.8162, "step": 162720 }, { "epoch": 13.53, "learning_rate": 2.1978882022004825e-06, "loss": 0.7779, "step": 162730 }, { "epoch": 13.53, "learning_rate": 2.1977773466729483e-06, "loss": 0.768, "step": 162740 }, { "epoch": 13.53, "learning_rate": 2.1976664911454146e-06, "loss": 0.7865, "step": 162750 }, { "epoch": 13.53, "learning_rate": 2.197555635617881e-06, "loss": 0.8405, "step": 162760 }, { "epoch": 13.53, "learning_rate": 2.1974447800903472e-06, "loss": 0.7833, "step": 162770 }, { "epoch": 13.53, "learning_rate": 2.197333924562813e-06, "loss": 0.8081, "step": 162780 }, { "epoch": 13.53, "learning_rate": 2.19722306903528e-06, "loss": 0.7891, "step": 162790 }, { "epoch": 13.53, "learning_rate": 2.1971122135077457e-06, "loss": 0.7785, "step": 162800 }, { "epoch": 13.53, "learning_rate": 2.1970013579802124e-06, "loss": 0.8559, "step": 162810 }, { "epoch": 13.53, "learning_rate": 2.1968905024526783e-06, "loss": 0.819, "step": 162820 }, { "epoch": 13.53, "learning_rate": 2.1967796469251446e-06, "loss": 0.7761, "step": 162830 }, { "epoch": 13.54, "learning_rate": 2.196668791397611e-06, "loss": 0.7698, "step": 162840 }, { "epoch": 13.54, "learning_rate": 2.196557935870077e-06, "loss": 0.7167, "step": 162850 }, { "epoch": 13.54, "learning_rate": 2.1964470803425435e-06, "loss": 0.8461, "step": 162860 }, { "epoch": 13.54, "learning_rate": 2.1963362248150098e-06, "loss": 0.8262, "step": 162870 }, { "epoch": 13.54, "learning_rate": 2.196225369287476e-06, "loss": 0.8, "step": 162880 }, { "epoch": 13.54, "learning_rate": 2.1961145137599423e-06, "loss": 0.8234, "step": 162890 }, { "epoch": 13.54, "learning_rate": 2.1960036582324086e-06, "loss": 0.8382, "step": 162900 }, { "epoch": 13.54, "learning_rate": 2.1958928027048745e-06, "loss": 0.8469, "step": 162910 }, { "epoch": 13.54, "learning_rate": 2.1957819471773412e-06, "loss": 0.8188, "step": 162920 }, { "epoch": 13.54, "learning_rate": 2.195671091649807e-06, "loss": 0.7869, "step": 162930 }, { "epoch": 13.54, "learning_rate": 2.1955602361222734e-06, "loss": 0.771, "step": 162940 }, { "epoch": 13.54, "learning_rate": 2.1954493805947397e-06, "loss": 0.8561, "step": 162950 }, { "epoch": 13.55, "learning_rate": 2.195338525067206e-06, "loss": 0.8434, "step": 162960 }, { "epoch": 13.55, "learning_rate": 2.1952276695396727e-06, "loss": 0.7613, "step": 162970 }, { "epoch": 13.55, "learning_rate": 2.1951168140121386e-06, "loss": 0.7959, "step": 162980 }, { "epoch": 13.55, "learning_rate": 2.195005958484605e-06, "loss": 0.7543, "step": 162990 }, { "epoch": 13.55, "learning_rate": 2.194895102957071e-06, "loss": 0.7961, "step": 163000 }, { "epoch": 13.55, "learning_rate": 2.1947842474295375e-06, "loss": 0.8244, "step": 163010 }, { "epoch": 13.55, "learning_rate": 2.1946733919020033e-06, "loss": 0.7483, "step": 163020 }, { "epoch": 13.55, "learning_rate": 2.19456253637447e-06, "loss": 0.7911, "step": 163030 }, { "epoch": 13.55, "learning_rate": 2.194451680846936e-06, "loss": 0.7919, "step": 163040 }, { "epoch": 13.55, "learning_rate": 2.1943408253194026e-06, "loss": 0.7534, "step": 163050 }, { "epoch": 13.55, "learning_rate": 2.1942299697918685e-06, "loss": 0.8285, "step": 163060 }, { "epoch": 13.55, "learning_rate": 2.194119114264335e-06, "loss": 0.7803, "step": 163070 }, { "epoch": 13.55, "learning_rate": 2.194008258736801e-06, "loss": 0.8054, "step": 163080 }, { "epoch": 13.56, "learning_rate": 2.1938974032092674e-06, "loss": 0.7023, "step": 163090 }, { "epoch": 13.56, "learning_rate": 2.1937865476817337e-06, "loss": 0.8198, "step": 163100 }, { "epoch": 13.56, "learning_rate": 2.1936756921542e-06, "loss": 0.8575, "step": 163110 }, { "epoch": 13.56, "learning_rate": 2.1935648366266663e-06, "loss": 0.8329, "step": 163120 }, { "epoch": 13.56, "learning_rate": 2.1934539810991326e-06, "loss": 0.7996, "step": 163130 }, { "epoch": 13.56, "learning_rate": 2.193343125571599e-06, "loss": 0.7558, "step": 163140 }, { "epoch": 13.56, "learning_rate": 2.1932322700440648e-06, "loss": 0.7313, "step": 163150 }, { "epoch": 13.56, "learning_rate": 2.1931214145165315e-06, "loss": 0.7894, "step": 163160 }, { "epoch": 13.56, "learning_rate": 2.1930105589889973e-06, "loss": 0.744, "step": 163170 }, { "epoch": 13.56, "learning_rate": 2.1928997034614636e-06, "loss": 0.7918, "step": 163180 }, { "epoch": 13.56, "learning_rate": 2.19278884793393e-06, "loss": 0.7544, "step": 163190 }, { "epoch": 13.56, "learning_rate": 2.1926779924063962e-06, "loss": 0.7275, "step": 163200 }, { "epoch": 13.57, "learning_rate": 2.192567136878863e-06, "loss": 0.7866, "step": 163210 }, { "epoch": 13.57, "learning_rate": 2.192456281351329e-06, "loss": 0.6983, "step": 163220 }, { "epoch": 13.57, "learning_rate": 2.192345425823795e-06, "loss": 0.8744, "step": 163230 }, { "epoch": 13.57, "learning_rate": 2.1922345702962614e-06, "loss": 0.7813, "step": 163240 }, { "epoch": 13.57, "learning_rate": 2.1921237147687277e-06, "loss": 0.7469, "step": 163250 }, { "epoch": 13.57, "learning_rate": 2.1920128592411936e-06, "loss": 0.8386, "step": 163260 }, { "epoch": 13.57, "learning_rate": 2.1919020037136603e-06, "loss": 0.7888, "step": 163270 }, { "epoch": 13.57, "learning_rate": 2.191791148186126e-06, "loss": 0.814, "step": 163280 }, { "epoch": 13.57, "learning_rate": 2.1916802926585925e-06, "loss": 0.7292, "step": 163290 }, { "epoch": 13.57, "learning_rate": 2.1915694371310588e-06, "loss": 0.802, "step": 163300 }, { "epoch": 13.57, "learning_rate": 2.191458581603525e-06, "loss": 0.8654, "step": 163310 }, { "epoch": 13.57, "learning_rate": 2.1913477260759914e-06, "loss": 0.7816, "step": 163320 }, { "epoch": 13.58, "learning_rate": 2.1912368705484576e-06, "loss": 0.806, "step": 163330 }, { "epoch": 13.58, "learning_rate": 2.191126015020924e-06, "loss": 0.7847, "step": 163340 }, { "epoch": 13.58, "learning_rate": 2.1910151594933902e-06, "loss": 0.7956, "step": 163350 }, { "epoch": 13.58, "learning_rate": 2.1909043039658565e-06, "loss": 0.763, "step": 163360 }, { "epoch": 13.58, "learning_rate": 2.1907934484383224e-06, "loss": 0.7602, "step": 163370 }, { "epoch": 13.58, "learning_rate": 2.190682592910789e-06, "loss": 0.7417, "step": 163380 }, { "epoch": 13.58, "learning_rate": 2.190571737383255e-06, "loss": 0.7631, "step": 163390 }, { "epoch": 13.58, "learning_rate": 2.1904608818557217e-06, "loss": 0.7821, "step": 163400 }, { "epoch": 13.58, "learning_rate": 2.1903500263281876e-06, "loss": 0.8191, "step": 163410 }, { "epoch": 13.58, "learning_rate": 2.190239170800654e-06, "loss": 0.8413, "step": 163420 }, { "epoch": 13.58, "learning_rate": 2.19012831527312e-06, "loss": 0.7857, "step": 163430 }, { "epoch": 13.58, "learning_rate": 2.1900174597455865e-06, "loss": 0.7545, "step": 163440 }, { "epoch": 13.59, "learning_rate": 2.1899066042180523e-06, "loss": 0.7228, "step": 163450 }, { "epoch": 13.59, "learning_rate": 2.189795748690519e-06, "loss": 0.7735, "step": 163460 }, { "epoch": 13.59, "learning_rate": 2.1896848931629854e-06, "loss": 0.7605, "step": 163470 }, { "epoch": 13.59, "learning_rate": 2.1895740376354517e-06, "loss": 0.7948, "step": 163480 }, { "epoch": 13.59, "learning_rate": 2.189463182107918e-06, "loss": 0.7179, "step": 163490 }, { "epoch": 13.59, "learning_rate": 2.189352326580384e-06, "loss": 0.7944, "step": 163500 }, { "epoch": 13.59, "learning_rate": 2.1892414710528505e-06, "loss": 0.7455, "step": 163510 }, { "epoch": 13.59, "learning_rate": 2.1891306155253164e-06, "loss": 0.7796, "step": 163520 }, { "epoch": 13.59, "learning_rate": 2.1890197599977827e-06, "loss": 0.7632, "step": 163530 }, { "epoch": 13.59, "learning_rate": 2.188908904470249e-06, "loss": 0.8463, "step": 163540 }, { "epoch": 13.59, "learning_rate": 2.1887980489427153e-06, "loss": 0.7839, "step": 163550 }, { "epoch": 13.59, "learning_rate": 2.188687193415181e-06, "loss": 0.842, "step": 163560 }, { "epoch": 13.6, "learning_rate": 2.188576337887648e-06, "loss": 0.7547, "step": 163570 }, { "epoch": 13.6, "learning_rate": 2.188465482360114e-06, "loss": 0.7971, "step": 163580 }, { "epoch": 13.6, "learning_rate": 2.1883546268325805e-06, "loss": 0.7682, "step": 163590 }, { "epoch": 13.6, "learning_rate": 2.1882437713050468e-06, "loss": 0.7945, "step": 163600 }, { "epoch": 13.6, "learning_rate": 2.1881329157775126e-06, "loss": 0.8202, "step": 163610 }, { "epoch": 13.6, "learning_rate": 2.1880220602499794e-06, "loss": 0.7733, "step": 163620 }, { "epoch": 13.6, "learning_rate": 2.1879112047224452e-06, "loss": 0.7978, "step": 163630 }, { "epoch": 13.6, "learning_rate": 2.187800349194912e-06, "loss": 0.784, "step": 163640 }, { "epoch": 13.6, "learning_rate": 2.187689493667378e-06, "loss": 0.8521, "step": 163650 }, { "epoch": 13.6, "learning_rate": 2.187578638139844e-06, "loss": 0.8892, "step": 163660 }, { "epoch": 13.6, "learning_rate": 2.1874677826123104e-06, "loss": 0.7682, "step": 163670 }, { "epoch": 13.6, "learning_rate": 2.1873569270847767e-06, "loss": 0.7694, "step": 163680 }, { "epoch": 13.61, "learning_rate": 2.1872460715572426e-06, "loss": 0.7345, "step": 163690 }, { "epoch": 13.61, "learning_rate": 2.1871352160297093e-06, "loss": 0.8108, "step": 163700 }, { "epoch": 13.61, "learning_rate": 2.1870243605021756e-06, "loss": 0.8231, "step": 163710 }, { "epoch": 13.61, "learning_rate": 2.1869135049746415e-06, "loss": 0.7929, "step": 163720 }, { "epoch": 13.61, "learning_rate": 2.186802649447108e-06, "loss": 0.7388, "step": 163730 }, { "epoch": 13.61, "learning_rate": 2.186691793919574e-06, "loss": 0.7392, "step": 163740 }, { "epoch": 13.61, "learning_rate": 2.1865809383920408e-06, "loss": 0.8345, "step": 163750 }, { "epoch": 13.61, "learning_rate": 2.1864700828645067e-06, "loss": 0.7907, "step": 163760 }, { "epoch": 13.61, "learning_rate": 2.186359227336973e-06, "loss": 0.7051, "step": 163770 }, { "epoch": 13.61, "learning_rate": 2.1862483718094392e-06, "loss": 0.6444, "step": 163780 }, { "epoch": 13.61, "learning_rate": 2.1861375162819055e-06, "loss": 0.8224, "step": 163790 }, { "epoch": 13.61, "learning_rate": 2.1860266607543714e-06, "loss": 0.8187, "step": 163800 }, { "epoch": 13.62, "learning_rate": 2.185915805226838e-06, "loss": 0.8474, "step": 163810 }, { "epoch": 13.62, "learning_rate": 2.185804949699304e-06, "loss": 0.8139, "step": 163820 }, { "epoch": 13.62, "learning_rate": 2.1856940941717707e-06, "loss": 0.778, "step": 163830 }, { "epoch": 13.62, "learning_rate": 2.185583238644237e-06, "loss": 0.7062, "step": 163840 }, { "epoch": 13.62, "learning_rate": 2.185472383116703e-06, "loss": 0.7795, "step": 163850 }, { "epoch": 13.62, "learning_rate": 2.1853615275891696e-06, "loss": 0.7396, "step": 163860 }, { "epoch": 13.62, "learning_rate": 2.1852506720616355e-06, "loss": 0.7813, "step": 163870 }, { "epoch": 13.62, "learning_rate": 2.1851398165341018e-06, "loss": 0.7839, "step": 163880 }, { "epoch": 13.62, "learning_rate": 2.185028961006568e-06, "loss": 0.7739, "step": 163890 }, { "epoch": 13.62, "learning_rate": 2.1849181054790344e-06, "loss": 0.7487, "step": 163900 }, { "epoch": 13.62, "learning_rate": 2.1848072499515007e-06, "loss": 0.8358, "step": 163910 }, { "epoch": 13.62, "learning_rate": 2.184696394423967e-06, "loss": 0.7689, "step": 163920 }, { "epoch": 13.63, "learning_rate": 2.184585538896433e-06, "loss": 0.7949, "step": 163930 }, { "epoch": 13.63, "learning_rate": 2.1844746833688995e-06, "loss": 0.7746, "step": 163940 }, { "epoch": 13.63, "learning_rate": 2.184363827841366e-06, "loss": 0.7135, "step": 163950 }, { "epoch": 13.63, "learning_rate": 2.1842529723138317e-06, "loss": 0.7652, "step": 163960 }, { "epoch": 13.63, "learning_rate": 2.1841421167862984e-06, "loss": 0.7513, "step": 163970 }, { "epoch": 13.63, "learning_rate": 2.1840312612587643e-06, "loss": 0.7323, "step": 163980 }, { "epoch": 13.63, "learning_rate": 2.183920405731231e-06, "loss": 0.782, "step": 163990 }, { "epoch": 13.63, "learning_rate": 2.183809550203697e-06, "loss": 0.772, "step": 164000 }, { "epoch": 13.63, "learning_rate": 2.183698694676163e-06, "loss": 0.9095, "step": 164010 }, { "epoch": 13.63, "learning_rate": 2.1835878391486295e-06, "loss": 0.7485, "step": 164020 }, { "epoch": 13.63, "learning_rate": 2.1834769836210958e-06, "loss": 0.8285, "step": 164030 }, { "epoch": 13.63, "learning_rate": 2.1833661280935617e-06, "loss": 0.7967, "step": 164040 }, { "epoch": 13.64, "learning_rate": 2.1832552725660284e-06, "loss": 0.8117, "step": 164050 }, { "epoch": 13.64, "learning_rate": 2.1831444170384942e-06, "loss": 0.8298, "step": 164060 }, { "epoch": 13.64, "learning_rate": 2.1830335615109605e-06, "loss": 0.778, "step": 164070 }, { "epoch": 13.64, "learning_rate": 2.1829227059834273e-06, "loss": 0.7723, "step": 164080 }, { "epoch": 13.64, "learning_rate": 2.182811850455893e-06, "loss": 0.7394, "step": 164090 }, { "epoch": 13.64, "learning_rate": 2.18270099492836e-06, "loss": 0.7486, "step": 164100 }, { "epoch": 13.64, "learning_rate": 2.1825901394008257e-06, "loss": 0.8485, "step": 164110 }, { "epoch": 13.64, "learning_rate": 2.182479283873292e-06, "loss": 0.8277, "step": 164120 }, { "epoch": 13.64, "learning_rate": 2.1823684283457583e-06, "loss": 0.7556, "step": 164130 }, { "epoch": 13.64, "learning_rate": 2.1822575728182246e-06, "loss": 0.7655, "step": 164140 }, { "epoch": 13.64, "learning_rate": 2.1821467172906905e-06, "loss": 0.7711, "step": 164150 }, { "epoch": 13.64, "learning_rate": 2.182035861763157e-06, "loss": 0.774, "step": 164160 }, { "epoch": 13.65, "learning_rate": 2.181925006235623e-06, "loss": 0.7662, "step": 164170 }, { "epoch": 13.65, "learning_rate": 2.1818141507080898e-06, "loss": 0.7258, "step": 164180 }, { "epoch": 13.65, "learning_rate": 2.1817032951805557e-06, "loss": 0.7261, "step": 164190 }, { "epoch": 13.65, "learning_rate": 2.1816035252057756e-06, "loss": 0.7808, "step": 164200 }, { "epoch": 13.65, "learning_rate": 2.1814926696782415e-06, "loss": 0.8679, "step": 164210 }, { "epoch": 13.65, "learning_rate": 2.181381814150708e-06, "loss": 0.7244, "step": 164220 }, { "epoch": 13.65, "learning_rate": 2.181270958623174e-06, "loss": 0.7965, "step": 164230 }, { "epoch": 13.65, "learning_rate": 2.1811601030956404e-06, "loss": 0.7302, "step": 164240 }, { "epoch": 13.65, "learning_rate": 2.1810492475681067e-06, "loss": 0.8451, "step": 164250 }, { "epoch": 13.65, "learning_rate": 2.180938392040573e-06, "loss": 0.857, "step": 164260 }, { "epoch": 13.65, "learning_rate": 2.1808275365130393e-06, "loss": 0.7595, "step": 164270 }, { "epoch": 13.65, "learning_rate": 2.1807166809855056e-06, "loss": 0.7704, "step": 164280 }, { "epoch": 13.66, "learning_rate": 2.180605825457972e-06, "loss": 0.7877, "step": 164290 }, { "epoch": 13.66, "learning_rate": 2.180494969930438e-06, "loss": 0.7672, "step": 164300 }, { "epoch": 13.66, "learning_rate": 2.1803841144029044e-06, "loss": 0.8192, "step": 164310 }, { "epoch": 13.66, "learning_rate": 2.1802732588753703e-06, "loss": 0.8343, "step": 164320 }, { "epoch": 13.66, "learning_rate": 2.180162403347837e-06, "loss": 0.7793, "step": 164330 }, { "epoch": 13.66, "learning_rate": 2.180051547820303e-06, "loss": 0.7315, "step": 164340 }, { "epoch": 13.66, "learning_rate": 2.1799406922927696e-06, "loss": 0.7975, "step": 164350 }, { "epoch": 13.66, "learning_rate": 2.1798298367652355e-06, "loss": 0.8425, "step": 164360 }, { "epoch": 13.66, "learning_rate": 2.179718981237702e-06, "loss": 0.7239, "step": 164370 }, { "epoch": 13.66, "learning_rate": 2.179608125710168e-06, "loss": 0.7855, "step": 164380 }, { "epoch": 13.66, "learning_rate": 2.1794972701826344e-06, "loss": 0.7828, "step": 164390 }, { "epoch": 13.66, "learning_rate": 2.1793864146551003e-06, "loss": 0.7544, "step": 164400 }, { "epoch": 13.67, "learning_rate": 2.179275559127567e-06, "loss": 0.8243, "step": 164410 }, { "epoch": 13.67, "learning_rate": 2.1791647036000333e-06, "loss": 0.7925, "step": 164420 }, { "epoch": 13.67, "learning_rate": 2.1790538480724996e-06, "loss": 0.8019, "step": 164430 }, { "epoch": 13.67, "learning_rate": 2.178942992544966e-06, "loss": 0.7705, "step": 164440 }, { "epoch": 13.67, "learning_rate": 2.1788321370174317e-06, "loss": 0.7335, "step": 164450 }, { "epoch": 13.67, "learning_rate": 2.1787212814898985e-06, "loss": 0.8108, "step": 164460 }, { "epoch": 13.67, "learning_rate": 2.1786104259623643e-06, "loss": 0.7665, "step": 164470 }, { "epoch": 13.67, "learning_rate": 2.1784995704348306e-06, "loss": 0.7842, "step": 164480 }, { "epoch": 13.67, "learning_rate": 2.178388714907297e-06, "loss": 0.779, "step": 164490 }, { "epoch": 13.67, "learning_rate": 2.178277859379763e-06, "loss": 0.7554, "step": 164500 }, { "epoch": 13.67, "learning_rate": 2.178167003852229e-06, "loss": 0.8805, "step": 164510 }, { "epoch": 13.67, "learning_rate": 2.178056148324696e-06, "loss": 0.8134, "step": 164520 }, { "epoch": 13.68, "learning_rate": 2.177945292797162e-06, "loss": 0.754, "step": 164530 }, { "epoch": 13.68, "learning_rate": 2.1778344372696284e-06, "loss": 0.8114, "step": 164540 }, { "epoch": 13.68, "learning_rate": 2.1777235817420947e-06, "loss": 0.7868, "step": 164550 }, { "epoch": 13.68, "learning_rate": 2.1776127262145606e-06, "loss": 0.813, "step": 164560 }, { "epoch": 13.68, "learning_rate": 2.1775018706870273e-06, "loss": 0.7823, "step": 164570 }, { "epoch": 13.68, "learning_rate": 2.177391015159493e-06, "loss": 0.7715, "step": 164580 }, { "epoch": 13.68, "learning_rate": 2.17728015963196e-06, "loss": 0.8031, "step": 164590 }, { "epoch": 13.68, "learning_rate": 2.1771693041044257e-06, "loss": 0.7672, "step": 164600 }, { "epoch": 13.68, "learning_rate": 2.177058448576892e-06, "loss": 0.8021, "step": 164610 }, { "epoch": 13.68, "learning_rate": 2.1769475930493583e-06, "loss": 0.7723, "step": 164620 }, { "epoch": 13.68, "learning_rate": 2.1768367375218246e-06, "loss": 0.8453, "step": 164630 }, { "epoch": 13.68, "learning_rate": 2.1767258819942905e-06, "loss": 0.8411, "step": 164640 }, { "epoch": 13.69, "learning_rate": 2.1766150264667572e-06, "loss": 0.8151, "step": 164650 }, { "epoch": 13.69, "learning_rate": 2.1765041709392235e-06, "loss": 0.8343, "step": 164660 }, { "epoch": 13.69, "learning_rate": 2.1763933154116894e-06, "loss": 0.7234, "step": 164670 }, { "epoch": 13.69, "learning_rate": 2.176282459884156e-06, "loss": 0.8078, "step": 164680 }, { "epoch": 13.69, "learning_rate": 2.176171604356622e-06, "loss": 0.7835, "step": 164690 }, { "epoch": 13.69, "learning_rate": 2.1760607488290887e-06, "loss": 0.7254, "step": 164700 }, { "epoch": 13.69, "learning_rate": 2.1759498933015546e-06, "loss": 0.7977, "step": 164710 }, { "epoch": 13.69, "learning_rate": 2.175839037774021e-06, "loss": 0.7991, "step": 164720 }, { "epoch": 13.69, "learning_rate": 2.175728182246487e-06, "loss": 0.8206, "step": 164730 }, { "epoch": 13.69, "learning_rate": 2.1756173267189534e-06, "loss": 0.7693, "step": 164740 }, { "epoch": 13.69, "learning_rate": 2.1755064711914193e-06, "loss": 0.7051, "step": 164750 }, { "epoch": 13.69, "learning_rate": 2.175395615663886e-06, "loss": 0.8069, "step": 164760 }, { "epoch": 13.7, "learning_rate": 2.175284760136352e-06, "loss": 0.7544, "step": 164770 }, { "epoch": 13.7, "learning_rate": 2.1751739046088186e-06, "loss": 0.7734, "step": 164780 }, { "epoch": 13.7, "learning_rate": 2.175063049081285e-06, "loss": 0.7448, "step": 164790 }, { "epoch": 13.7, "learning_rate": 2.174952193553751e-06, "loss": 0.7207, "step": 164800 }, { "epoch": 13.7, "learning_rate": 2.1748413380262175e-06, "loss": 0.7769, "step": 164810 }, { "epoch": 13.7, "learning_rate": 2.1747304824986834e-06, "loss": 0.8292, "step": 164820 }, { "epoch": 13.7, "learning_rate": 2.1746196269711497e-06, "loss": 0.8199, "step": 164830 }, { "epoch": 13.7, "learning_rate": 2.174508771443616e-06, "loss": 0.7458, "step": 164840 }, { "epoch": 13.7, "learning_rate": 2.1743979159160823e-06, "loss": 0.8362, "step": 164850 }, { "epoch": 13.7, "learning_rate": 2.1742870603885486e-06, "loss": 0.7784, "step": 164860 }, { "epoch": 13.7, "learning_rate": 2.174176204861015e-06, "loss": 0.8296, "step": 164870 }, { "epoch": 13.7, "learning_rate": 2.1740653493334807e-06, "loss": 0.7294, "step": 164880 }, { "epoch": 13.71, "learning_rate": 2.1739544938059475e-06, "loss": 0.7803, "step": 164890 }, { "epoch": 13.71, "learning_rate": 2.1738436382784138e-06, "loss": 0.7324, "step": 164900 }, { "epoch": 13.71, "learning_rate": 2.1737327827508796e-06, "loss": 0.7785, "step": 164910 }, { "epoch": 13.71, "learning_rate": 2.1736219272233463e-06, "loss": 0.8307, "step": 164920 }, { "epoch": 13.71, "learning_rate": 2.1735110716958122e-06, "loss": 0.7514, "step": 164930 }, { "epoch": 13.71, "learning_rate": 2.173400216168279e-06, "loss": 0.7967, "step": 164940 }, { "epoch": 13.71, "learning_rate": 2.173289360640745e-06, "loss": 0.7809, "step": 164950 }, { "epoch": 13.71, "learning_rate": 2.173178505113211e-06, "loss": 0.8173, "step": 164960 }, { "epoch": 13.71, "learning_rate": 2.1730676495856774e-06, "loss": 0.85, "step": 164970 }, { "epoch": 13.71, "learning_rate": 2.1729567940581437e-06, "loss": 0.8037, "step": 164980 }, { "epoch": 13.71, "learning_rate": 2.1728459385306096e-06, "loss": 0.755, "step": 164990 }, { "epoch": 13.71, "learning_rate": 2.1727350830030763e-06, "loss": 0.7732, "step": 165000 }, { "epoch": 13.72, "learning_rate": 2.172624227475542e-06, "loss": 0.823, "step": 165010 }, { "epoch": 13.72, "learning_rate": 2.1725133719480084e-06, "loss": 0.7818, "step": 165020 }, { "epoch": 13.72, "learning_rate": 2.172402516420475e-06, "loss": 0.7118, "step": 165030 }, { "epoch": 13.72, "learning_rate": 2.172291660892941e-06, "loss": 0.7912, "step": 165040 }, { "epoch": 13.72, "learning_rate": 2.1721808053654078e-06, "loss": 0.7344, "step": 165050 }, { "epoch": 13.72, "learning_rate": 2.1720699498378736e-06, "loss": 0.8272, "step": 165060 }, { "epoch": 13.72, "learning_rate": 2.17195909431034e-06, "loss": 0.7603, "step": 165070 }, { "epoch": 13.72, "learning_rate": 2.1718482387828062e-06, "loss": 0.8059, "step": 165080 }, { "epoch": 13.72, "learning_rate": 2.1717373832552725e-06, "loss": 0.7542, "step": 165090 }, { "epoch": 13.72, "learning_rate": 2.1716265277277384e-06, "loss": 0.7318, "step": 165100 }, { "epoch": 13.72, "learning_rate": 2.171515672200205e-06, "loss": 0.8176, "step": 165110 }, { "epoch": 13.72, "learning_rate": 2.171404816672671e-06, "loss": 0.8165, "step": 165120 }, { "epoch": 13.73, "learning_rate": 2.1712939611451377e-06, "loss": 0.7647, "step": 165130 }, { "epoch": 13.73, "learning_rate": 2.1711831056176036e-06, "loss": 0.763, "step": 165140 }, { "epoch": 13.73, "learning_rate": 2.17107225009007e-06, "loss": 0.7613, "step": 165150 }, { "epoch": 13.73, "learning_rate": 2.1709613945625366e-06, "loss": 0.8057, "step": 165160 }, { "epoch": 13.73, "learning_rate": 2.1708505390350025e-06, "loss": 0.7798, "step": 165170 }, { "epoch": 13.73, "learning_rate": 2.1707396835074688e-06, "loss": 0.794, "step": 165180 }, { "epoch": 13.73, "learning_rate": 2.170628827979935e-06, "loss": 0.7577, "step": 165190 }, { "epoch": 13.73, "learning_rate": 2.1705179724524013e-06, "loss": 0.7641, "step": 165200 }, { "epoch": 13.73, "learning_rate": 2.1704071169248676e-06, "loss": 0.7993, "step": 165210 }, { "epoch": 13.73, "learning_rate": 2.170296261397334e-06, "loss": 0.845, "step": 165220 }, { "epoch": 13.73, "learning_rate": 2.1701854058698e-06, "loss": 0.884, "step": 165230 }, { "epoch": 13.73, "learning_rate": 2.1700745503422665e-06, "loss": 0.7732, "step": 165240 }, { "epoch": 13.74, "learning_rate": 2.1699636948147324e-06, "loss": 0.7967, "step": 165250 }, { "epoch": 13.74, "learning_rate": 2.1698528392871987e-06, "loss": 0.7981, "step": 165260 }, { "epoch": 13.74, "learning_rate": 2.1697419837596654e-06, "loss": 0.7628, "step": 165270 }, { "epoch": 13.74, "learning_rate": 2.1696311282321313e-06, "loss": 0.7474, "step": 165280 }, { "epoch": 13.74, "learning_rate": 2.169520272704598e-06, "loss": 0.7731, "step": 165290 }, { "epoch": 13.74, "learning_rate": 2.169409417177064e-06, "loss": 0.7914, "step": 165300 }, { "epoch": 13.74, "learning_rate": 2.16929856164953e-06, "loss": 0.8756, "step": 165310 }, { "epoch": 13.74, "learning_rate": 2.1691877061219965e-06, "loss": 0.8462, "step": 165320 }, { "epoch": 13.74, "learning_rate": 2.1690768505944628e-06, "loss": 0.8001, "step": 165330 }, { "epoch": 13.74, "learning_rate": 2.1689659950669286e-06, "loss": 0.7956, "step": 165340 }, { "epoch": 13.74, "learning_rate": 2.1688551395393953e-06, "loss": 0.7501, "step": 165350 }, { "epoch": 13.74, "learning_rate": 2.1687442840118612e-06, "loss": 0.8002, "step": 165360 }, { "epoch": 13.75, "learning_rate": 2.168633428484328e-06, "loss": 0.81, "step": 165370 }, { "epoch": 13.75, "learning_rate": 2.168522572956794e-06, "loss": 0.7795, "step": 165380 }, { "epoch": 13.75, "learning_rate": 2.16841171742926e-06, "loss": 0.723, "step": 165390 }, { "epoch": 13.75, "learning_rate": 2.168300861901727e-06, "loss": 0.7765, "step": 165400 }, { "epoch": 13.75, "learning_rate": 2.1681900063741927e-06, "loss": 0.7684, "step": 165410 }, { "epoch": 13.75, "learning_rate": 2.168079150846659e-06, "loss": 0.7881, "step": 165420 }, { "epoch": 13.75, "learning_rate": 2.1679682953191253e-06, "loss": 0.787, "step": 165430 }, { "epoch": 13.75, "learning_rate": 2.1678574397915916e-06, "loss": 0.7241, "step": 165440 }, { "epoch": 13.75, "learning_rate": 2.1677465842640575e-06, "loss": 0.7256, "step": 165450 }, { "epoch": 13.75, "learning_rate": 2.167635728736524e-06, "loss": 0.8807, "step": 165460 }, { "epoch": 13.75, "learning_rate": 2.16752487320899e-06, "loss": 0.7885, "step": 165470 }, { "epoch": 13.75, "learning_rate": 2.1674140176814568e-06, "loss": 0.765, "step": 165480 }, { "epoch": 13.76, "learning_rate": 2.1673031621539226e-06, "loss": 0.715, "step": 165490 }, { "epoch": 13.76, "learning_rate": 2.167192306626389e-06, "loss": 0.8859, "step": 165500 }, { "epoch": 13.76, "learning_rate": 2.1670814510988556e-06, "loss": 0.8063, "step": 165510 }, { "epoch": 13.76, "learning_rate": 2.1669705955713215e-06, "loss": 0.8809, "step": 165520 }, { "epoch": 13.76, "learning_rate": 2.166859740043788e-06, "loss": 0.795, "step": 165530 }, { "epoch": 13.76, "learning_rate": 2.166748884516254e-06, "loss": 0.7628, "step": 165540 }, { "epoch": 13.76, "learning_rate": 2.1666380289887204e-06, "loss": 0.7798, "step": 165550 }, { "epoch": 13.76, "learning_rate": 2.1665271734611867e-06, "loss": 0.8474, "step": 165560 }, { "epoch": 13.76, "learning_rate": 2.166416317933653e-06, "loss": 0.7327, "step": 165570 }, { "epoch": 13.76, "learning_rate": 2.166305462406119e-06, "loss": 0.8178, "step": 165580 }, { "epoch": 13.76, "learning_rate": 2.1661946068785856e-06, "loss": 0.7638, "step": 165590 }, { "epoch": 13.76, "learning_rate": 2.1660837513510515e-06, "loss": 0.7874, "step": 165600 }, { "epoch": 13.77, "learning_rate": 2.1659728958235178e-06, "loss": 0.7348, "step": 165610 }, { "epoch": 13.77, "learning_rate": 2.165862040295984e-06, "loss": 0.7892, "step": 165620 }, { "epoch": 13.77, "learning_rate": 2.1657511847684503e-06, "loss": 0.7022, "step": 165630 }, { "epoch": 13.77, "learning_rate": 2.165640329240917e-06, "loss": 0.8051, "step": 165640 }, { "epoch": 13.77, "learning_rate": 2.165529473713383e-06, "loss": 0.7136, "step": 165650 }, { "epoch": 13.77, "learning_rate": 2.1654186181858492e-06, "loss": 0.8362, "step": 165660 }, { "epoch": 13.77, "learning_rate": 2.1653077626583155e-06, "loss": 0.7059, "step": 165670 }, { "epoch": 13.77, "learning_rate": 2.165196907130782e-06, "loss": 0.6862, "step": 165680 }, { "epoch": 13.77, "learning_rate": 2.1650860516032477e-06, "loss": 0.8517, "step": 165690 }, { "epoch": 13.77, "learning_rate": 2.1649751960757144e-06, "loss": 0.7407, "step": 165700 }, { "epoch": 13.77, "learning_rate": 2.1648643405481803e-06, "loss": 0.7743, "step": 165710 }, { "epoch": 13.77, "learning_rate": 2.164753485020647e-06, "loss": 0.8027, "step": 165720 }, { "epoch": 13.78, "learning_rate": 2.164642629493113e-06, "loss": 0.8029, "step": 165730 }, { "epoch": 13.78, "learning_rate": 2.164531773965579e-06, "loss": 0.8133, "step": 165740 }, { "epoch": 13.78, "learning_rate": 2.1644209184380455e-06, "loss": 0.793, "step": 165750 }, { "epoch": 13.78, "learning_rate": 2.1643100629105118e-06, "loss": 0.8206, "step": 165760 }, { "epoch": 13.78, "learning_rate": 2.164199207382978e-06, "loss": 0.7864, "step": 165770 }, { "epoch": 13.78, "learning_rate": 2.1640883518554444e-06, "loss": 0.8073, "step": 165780 }, { "epoch": 13.78, "learning_rate": 2.1639774963279106e-06, "loss": 0.813, "step": 165790 }, { "epoch": 13.78, "learning_rate": 2.1638666408003765e-06, "loss": 0.7768, "step": 165800 }, { "epoch": 13.78, "learning_rate": 2.1637557852728432e-06, "loss": 0.8171, "step": 165810 }, { "epoch": 13.78, "learning_rate": 2.163644929745309e-06, "loss": 0.7296, "step": 165820 }, { "epoch": 13.78, "learning_rate": 2.163534074217776e-06, "loss": 0.7251, "step": 165830 }, { "epoch": 13.78, "learning_rate": 2.1634232186902417e-06, "loss": 0.7894, "step": 165840 }, { "epoch": 13.79, "learning_rate": 2.163312363162708e-06, "loss": 0.7559, "step": 165850 }, { "epoch": 13.79, "learning_rate": 2.1632015076351743e-06, "loss": 0.7977, "step": 165860 }, { "epoch": 13.79, "learning_rate": 2.1630906521076406e-06, "loss": 0.7839, "step": 165870 }, { "epoch": 13.79, "learning_rate": 2.1629797965801073e-06, "loss": 0.7463, "step": 165880 }, { "epoch": 13.79, "learning_rate": 2.162868941052573e-06, "loss": 0.827, "step": 165890 }, { "epoch": 13.79, "learning_rate": 2.1627580855250395e-06, "loss": 0.7591, "step": 165900 }, { "epoch": 13.79, "learning_rate": 2.1626472299975058e-06, "loss": 0.8307, "step": 165910 }, { "epoch": 13.79, "learning_rate": 2.162536374469972e-06, "loss": 0.7481, "step": 165920 }, { "epoch": 13.79, "learning_rate": 2.162425518942438e-06, "loss": 0.8355, "step": 165930 }, { "epoch": 13.79, "learning_rate": 2.1623146634149047e-06, "loss": 0.7568, "step": 165940 }, { "epoch": 13.79, "learning_rate": 2.1622038078873705e-06, "loss": 0.7427, "step": 165950 }, { "epoch": 13.79, "learning_rate": 2.162092952359837e-06, "loss": 0.7725, "step": 165960 }, { "epoch": 13.8, "learning_rate": 2.161982096832303e-06, "loss": 0.7891, "step": 165970 }, { "epoch": 13.8, "learning_rate": 2.1618712413047694e-06, "loss": 0.7405, "step": 165980 }, { "epoch": 13.8, "learning_rate": 2.1617603857772357e-06, "loss": 0.7392, "step": 165990 }, { "epoch": 13.8, "learning_rate": 2.161649530249702e-06, "loss": 0.8228, "step": 166000 }, { "epoch": 13.8, "learning_rate": 2.1615386747221683e-06, "loss": 0.8434, "step": 166010 }, { "epoch": 13.8, "learning_rate": 2.1614278191946346e-06, "loss": 0.782, "step": 166020 }, { "epoch": 13.8, "learning_rate": 2.161316963667101e-06, "loss": 0.7428, "step": 166030 }, { "epoch": 13.8, "learning_rate": 2.1612061081395668e-06, "loss": 0.7198, "step": 166040 }, { "epoch": 13.8, "learning_rate": 2.1610952526120335e-06, "loss": 0.7717, "step": 166050 }, { "epoch": 13.8, "learning_rate": 2.1609843970844994e-06, "loss": 0.8056, "step": 166060 }, { "epoch": 13.8, "learning_rate": 2.160873541556966e-06, "loss": 0.757, "step": 166070 }, { "epoch": 13.8, "learning_rate": 2.160762686029432e-06, "loss": 0.791, "step": 166080 }, { "epoch": 13.81, "learning_rate": 2.1606518305018982e-06, "loss": 0.798, "step": 166090 }, { "epoch": 13.81, "learning_rate": 2.1605409749743645e-06, "loss": 0.7464, "step": 166100 }, { "epoch": 13.81, "learning_rate": 2.160430119446831e-06, "loss": 0.8027, "step": 166110 }, { "epoch": 13.81, "learning_rate": 2.1603192639192967e-06, "loss": 0.8434, "step": 166120 }, { "epoch": 13.81, "learning_rate": 2.1602084083917634e-06, "loss": 0.8135, "step": 166130 }, { "epoch": 13.81, "learning_rate": 2.1600975528642297e-06, "loss": 0.8699, "step": 166140 }, { "epoch": 13.81, "learning_rate": 2.159986697336696e-06, "loss": 0.7878, "step": 166150 }, { "epoch": 13.81, "learning_rate": 2.1598758418091623e-06, "loss": 0.8335, "step": 166160 }, { "epoch": 13.81, "learning_rate": 2.159764986281628e-06, "loss": 0.8202, "step": 166170 }, { "epoch": 13.81, "learning_rate": 2.159654130754095e-06, "loss": 0.805, "step": 166180 }, { "epoch": 13.81, "learning_rate": 2.1595432752265608e-06, "loss": 0.7633, "step": 166190 }, { "epoch": 13.81, "learning_rate": 2.159432419699027e-06, "loss": 0.7675, "step": 166200 }, { "epoch": 13.82, "learning_rate": 2.1593215641714934e-06, "loss": 0.7357, "step": 166210 }, { "epoch": 13.82, "learning_rate": 2.1592107086439597e-06, "loss": 0.789, "step": 166220 }, { "epoch": 13.82, "learning_rate": 2.1590998531164255e-06, "loss": 0.7275, "step": 166230 }, { "epoch": 13.82, "learning_rate": 2.1589889975888922e-06, "loss": 0.8354, "step": 166240 }, { "epoch": 13.82, "learning_rate": 2.1588781420613585e-06, "loss": 0.7187, "step": 166250 }, { "epoch": 13.82, "learning_rate": 2.158767286533825e-06, "loss": 0.8257, "step": 166260 }, { "epoch": 13.82, "learning_rate": 2.158656431006291e-06, "loss": 0.8068, "step": 166270 }, { "epoch": 13.82, "learning_rate": 2.158545575478757e-06, "loss": 0.7597, "step": 166280 }, { "epoch": 13.82, "learning_rate": 2.1584347199512237e-06, "loss": 0.7871, "step": 166290 }, { "epoch": 13.82, "learning_rate": 2.1583238644236896e-06, "loss": 0.7989, "step": 166300 }, { "epoch": 13.82, "learning_rate": 2.158213008896156e-06, "loss": 0.8501, "step": 166310 }, { "epoch": 13.82, "learning_rate": 2.158102153368622e-06, "loss": 0.7953, "step": 166320 }, { "epoch": 13.83, "learning_rate": 2.1579912978410885e-06, "loss": 0.7717, "step": 166330 }, { "epoch": 13.83, "learning_rate": 2.1578804423135548e-06, "loss": 0.7802, "step": 166340 }, { "epoch": 13.83, "learning_rate": 2.157769586786021e-06, "loss": 0.7353, "step": 166350 }, { "epoch": 13.83, "learning_rate": 2.157658731258487e-06, "loss": 0.7947, "step": 166360 }, { "epoch": 13.83, "learning_rate": 2.1575478757309537e-06, "loss": 0.7746, "step": 166370 }, { "epoch": 13.83, "learning_rate": 2.15743702020342e-06, "loss": 0.752, "step": 166380 }, { "epoch": 13.83, "learning_rate": 2.157326164675886e-06, "loss": 0.8152, "step": 166390 }, { "epoch": 13.83, "learning_rate": 2.1572153091483525e-06, "loss": 0.743, "step": 166400 }, { "epoch": 13.83, "learning_rate": 2.1571044536208184e-06, "loss": 0.8679, "step": 166410 }, { "epoch": 13.83, "learning_rate": 2.156993598093285e-06, "loss": 0.7463, "step": 166420 }, { "epoch": 13.83, "learning_rate": 2.156882742565751e-06, "loss": 0.7695, "step": 166430 }, { "epoch": 13.83, "learning_rate": 2.1567718870382173e-06, "loss": 0.7605, "step": 166440 }, { "epoch": 13.84, "learning_rate": 2.1566610315106836e-06, "loss": 0.7689, "step": 166450 }, { "epoch": 13.84, "learning_rate": 2.15655017598315e-06, "loss": 0.806, "step": 166460 }, { "epoch": 13.84, "learning_rate": 2.1564393204556158e-06, "loss": 0.7363, "step": 166470 }, { "epoch": 13.84, "learning_rate": 2.1563284649280825e-06, "loss": 0.783, "step": 166480 }, { "epoch": 13.84, "learning_rate": 2.1562176094005484e-06, "loss": 0.7619, "step": 166490 }, { "epoch": 13.84, "learning_rate": 2.156106753873015e-06, "loss": 0.8034, "step": 166500 }, { "epoch": 13.84, "learning_rate": 2.1559958983454814e-06, "loss": 0.8527, "step": 166510 }, { "epoch": 13.84, "learning_rate": 2.1558850428179472e-06, "loss": 0.78, "step": 166520 }, { "epoch": 13.84, "learning_rate": 2.155774187290414e-06, "loss": 0.8099, "step": 166530 }, { "epoch": 13.84, "learning_rate": 2.15566333176288e-06, "loss": 0.7413, "step": 166540 }, { "epoch": 13.84, "learning_rate": 2.155552476235346e-06, "loss": 0.7633, "step": 166550 }, { "epoch": 13.84, "learning_rate": 2.1554416207078124e-06, "loss": 0.8455, "step": 166560 }, { "epoch": 13.85, "learning_rate": 2.1553307651802787e-06, "loss": 0.8285, "step": 166570 }, { "epoch": 13.85, "learning_rate": 2.155219909652745e-06, "loss": 0.8141, "step": 166580 }, { "epoch": 13.85, "learning_rate": 2.1551090541252113e-06, "loss": 0.7253, "step": 166590 }, { "epoch": 13.85, "learning_rate": 2.154998198597677e-06, "loss": 0.752, "step": 166600 }, { "epoch": 13.85, "learning_rate": 2.154887343070144e-06, "loss": 0.797, "step": 166610 }, { "epoch": 13.85, "learning_rate": 2.15477648754261e-06, "loss": 0.7419, "step": 166620 }, { "epoch": 13.85, "learning_rate": 2.154665632015076e-06, "loss": 0.8333, "step": 166630 }, { "epoch": 13.85, "learning_rate": 2.1545547764875428e-06, "loss": 0.8525, "step": 166640 }, { "epoch": 13.85, "learning_rate": 2.1544439209600087e-06, "loss": 0.8318, "step": 166650 }, { "epoch": 13.85, "learning_rate": 2.1543330654324754e-06, "loss": 0.7897, "step": 166660 }, { "epoch": 13.85, "learning_rate": 2.1542222099049413e-06, "loss": 0.7992, "step": 166670 }, { "epoch": 13.85, "learning_rate": 2.1541113543774075e-06, "loss": 0.7556, "step": 166680 }, { "epoch": 13.86, "learning_rate": 2.154000498849874e-06, "loss": 0.7627, "step": 166690 }, { "epoch": 13.86, "learning_rate": 2.15388964332234e-06, "loss": 0.7815, "step": 166700 }, { "epoch": 13.86, "learning_rate": 2.153778787794806e-06, "loss": 0.8016, "step": 166710 }, { "epoch": 13.86, "learning_rate": 2.1536679322672727e-06, "loss": 0.7997, "step": 166720 }, { "epoch": 13.86, "learning_rate": 2.1535570767397386e-06, "loss": 0.7355, "step": 166730 }, { "epoch": 13.86, "learning_rate": 2.153446221212205e-06, "loss": 0.7822, "step": 166740 }, { "epoch": 13.86, "learning_rate": 2.1533353656846716e-06, "loss": 0.7169, "step": 166750 }, { "epoch": 13.86, "learning_rate": 2.1532245101571375e-06, "loss": 0.7905, "step": 166760 }, { "epoch": 13.86, "learning_rate": 2.153113654629604e-06, "loss": 0.7285, "step": 166770 }, { "epoch": 13.86, "learning_rate": 2.15300279910207e-06, "loss": 0.7968, "step": 166780 }, { "epoch": 13.86, "learning_rate": 2.1528919435745364e-06, "loss": 0.7663, "step": 166790 }, { "epoch": 13.86, "learning_rate": 2.1527810880470027e-06, "loss": 0.7053, "step": 166800 }, { "epoch": 13.87, "learning_rate": 2.152670232519469e-06, "loss": 0.831, "step": 166810 }, { "epoch": 13.87, "learning_rate": 2.152559376991935e-06, "loss": 0.701, "step": 166820 }, { "epoch": 13.87, "learning_rate": 2.1524485214644016e-06, "loss": 0.772, "step": 166830 }, { "epoch": 13.87, "learning_rate": 2.1523376659368674e-06, "loss": 0.7799, "step": 166840 }, { "epoch": 13.87, "learning_rate": 2.152226810409334e-06, "loss": 0.7976, "step": 166850 }, { "epoch": 13.87, "learning_rate": 2.1521159548818e-06, "loss": 0.8266, "step": 166860 }, { "epoch": 13.87, "learning_rate": 2.1520050993542663e-06, "loss": 0.7288, "step": 166870 }, { "epoch": 13.87, "learning_rate": 2.151894243826733e-06, "loss": 0.8643, "step": 166880 }, { "epoch": 13.87, "learning_rate": 2.151783388299199e-06, "loss": 0.7993, "step": 166890 }, { "epoch": 13.87, "learning_rate": 2.151672532771665e-06, "loss": 0.7281, "step": 166900 }, { "epoch": 13.87, "learning_rate": 2.1515616772441315e-06, "loss": 0.8205, "step": 166910 }, { "epoch": 13.87, "learning_rate": 2.1514508217165978e-06, "loss": 0.7842, "step": 166920 }, { "epoch": 13.87, "learning_rate": 2.151339966189064e-06, "loss": 0.8143, "step": 166930 }, { "epoch": 13.88, "learning_rate": 2.1512291106615304e-06, "loss": 0.7939, "step": 166940 }, { "epoch": 13.88, "learning_rate": 2.1511182551339962e-06, "loss": 0.7108, "step": 166950 }, { "epoch": 13.88, "learning_rate": 2.151007399606463e-06, "loss": 0.8144, "step": 166960 }, { "epoch": 13.88, "learning_rate": 2.150896544078929e-06, "loss": 0.7255, "step": 166970 }, { "epoch": 13.88, "learning_rate": 2.150785688551395e-06, "loss": 0.7034, "step": 166980 }, { "epoch": 13.88, "learning_rate": 2.150674833023862e-06, "loss": 0.7518, "step": 166990 }, { "epoch": 13.88, "learning_rate": 2.1505639774963277e-06, "loss": 0.8496, "step": 167000 }, { "epoch": 13.88, "learning_rate": 2.1504531219687944e-06, "loss": 0.7796, "step": 167010 }, { "epoch": 13.88, "learning_rate": 2.1503422664412603e-06, "loss": 0.8223, "step": 167020 }, { "epoch": 13.88, "learning_rate": 2.1502314109137266e-06, "loss": 0.7187, "step": 167030 }, { "epoch": 13.88, "learning_rate": 2.150120555386193e-06, "loss": 0.7959, "step": 167040 }, { "epoch": 13.88, "learning_rate": 2.150009699858659e-06, "loss": 0.74, "step": 167050 }, { "epoch": 13.89, "learning_rate": 2.149898844331125e-06, "loss": 0.8213, "step": 167060 }, { "epoch": 13.89, "learning_rate": 2.149787988803592e-06, "loss": 0.815, "step": 167070 }, { "epoch": 13.89, "learning_rate": 2.1496771332760577e-06, "loss": 0.7022, "step": 167080 }, { "epoch": 13.89, "learning_rate": 2.149566277748524e-06, "loss": 0.7383, "step": 167090 }, { "epoch": 13.89, "learning_rate": 2.1494554222209903e-06, "loss": 0.824, "step": 167100 }, { "epoch": 13.89, "learning_rate": 2.1493445666934566e-06, "loss": 0.8761, "step": 167110 }, { "epoch": 13.89, "learning_rate": 2.1492337111659233e-06, "loss": 0.8304, "step": 167120 }, { "epoch": 13.89, "learning_rate": 2.149122855638389e-06, "loss": 0.8052, "step": 167130 }, { "epoch": 13.89, "learning_rate": 2.1490120001108554e-06, "loss": 0.7402, "step": 167140 }, { "epoch": 13.89, "learning_rate": 2.1489011445833217e-06, "loss": 0.7855, "step": 167150 }, { "epoch": 13.89, "learning_rate": 2.148790289055788e-06, "loss": 0.8217, "step": 167160 }, { "epoch": 13.89, "learning_rate": 2.148679433528254e-06, "loss": 0.7666, "step": 167170 }, { "epoch": 13.9, "learning_rate": 2.1485685780007206e-06, "loss": 0.7598, "step": 167180 }, { "epoch": 13.9, "learning_rate": 2.1484577224731865e-06, "loss": 0.7376, "step": 167190 }, { "epoch": 13.9, "learning_rate": 2.148346866945653e-06, "loss": 0.7461, "step": 167200 }, { "epoch": 13.9, "learning_rate": 2.148236011418119e-06, "loss": 0.8034, "step": 167210 }, { "epoch": 13.9, "learning_rate": 2.1481251558905854e-06, "loss": 0.7736, "step": 167220 }, { "epoch": 13.9, "learning_rate": 2.1480143003630517e-06, "loss": 0.8046, "step": 167230 }, { "epoch": 13.9, "learning_rate": 2.147903444835518e-06, "loss": 0.8363, "step": 167240 }, { "epoch": 13.9, "learning_rate": 2.1477925893079843e-06, "loss": 0.7763, "step": 167250 }, { "epoch": 13.9, "learning_rate": 2.1476817337804506e-06, "loss": 0.7879, "step": 167260 }, { "epoch": 13.9, "learning_rate": 2.147570878252917e-06, "loss": 0.7826, "step": 167270 }, { "epoch": 13.9, "learning_rate": 2.147460022725383e-06, "loss": 0.7632, "step": 167280 }, { "epoch": 13.9, "learning_rate": 2.1473491671978494e-06, "loss": 0.7994, "step": 167290 }, { "epoch": 13.91, "learning_rate": 2.1472383116703153e-06, "loss": 0.7997, "step": 167300 }, { "epoch": 13.91, "learning_rate": 2.147127456142782e-06, "loss": 0.7767, "step": 167310 }, { "epoch": 13.91, "learning_rate": 2.147016600615248e-06, "loss": 0.8387, "step": 167320 }, { "epoch": 13.91, "learning_rate": 2.146905745087714e-06, "loss": 0.7636, "step": 167330 }, { "epoch": 13.91, "learning_rate": 2.1467948895601805e-06, "loss": 0.7517, "step": 167340 }, { "epoch": 13.91, "learning_rate": 2.146684034032647e-06, "loss": 0.782, "step": 167350 }, { "epoch": 13.91, "learning_rate": 2.1465731785051135e-06, "loss": 0.804, "step": 167360 }, { "epoch": 13.91, "learning_rate": 2.1464623229775794e-06, "loss": 0.6933, "step": 167370 }, { "epoch": 13.91, "learning_rate": 2.1463514674500457e-06, "loss": 0.7815, "step": 167380 }, { "epoch": 13.91, "learning_rate": 2.146240611922512e-06, "loss": 0.8087, "step": 167390 }, { "epoch": 13.91, "learning_rate": 2.1461297563949783e-06, "loss": 0.7687, "step": 167400 }, { "epoch": 13.91, "learning_rate": 2.146018900867444e-06, "loss": 0.7876, "step": 167410 }, { "epoch": 13.92, "learning_rate": 2.145908045339911e-06, "loss": 0.7915, "step": 167420 }, { "epoch": 13.92, "learning_rate": 2.1457971898123767e-06, "loss": 0.7888, "step": 167430 }, { "epoch": 13.92, "learning_rate": 2.1456863342848435e-06, "loss": 0.7307, "step": 167440 }, { "epoch": 13.92, "learning_rate": 2.1455754787573093e-06, "loss": 0.733, "step": 167450 }, { "epoch": 13.92, "learning_rate": 2.1454646232297756e-06, "loss": 0.7592, "step": 167460 }, { "epoch": 13.92, "learning_rate": 2.145353767702242e-06, "loss": 0.7999, "step": 167470 }, { "epoch": 13.92, "learning_rate": 2.145242912174708e-06, "loss": 0.8348, "step": 167480 }, { "epoch": 13.92, "learning_rate": 2.1451320566471745e-06, "loss": 0.7775, "step": 167490 }, { "epoch": 13.92, "learning_rate": 2.145021201119641e-06, "loss": 0.7208, "step": 167500 }, { "epoch": 13.92, "learning_rate": 2.144910345592107e-06, "loss": 0.8298, "step": 167510 }, { "epoch": 13.92, "learning_rate": 2.144799490064573e-06, "loss": 0.7545, "step": 167520 }, { "epoch": 13.92, "learning_rate": 2.1446886345370397e-06, "loss": 0.7895, "step": 167530 }, { "epoch": 13.93, "learning_rate": 2.1445777790095056e-06, "loss": 0.8047, "step": 167540 }, { "epoch": 13.93, "learning_rate": 2.1444669234819723e-06, "loss": 0.7513, "step": 167550 }, { "epoch": 13.93, "learning_rate": 2.144356067954438e-06, "loss": 0.8025, "step": 167560 }, { "epoch": 13.93, "learning_rate": 2.1442452124269044e-06, "loss": 0.8295, "step": 167570 }, { "epoch": 13.93, "learning_rate": 2.1441343568993707e-06, "loss": 0.7827, "step": 167580 }, { "epoch": 13.93, "learning_rate": 2.144023501371837e-06, "loss": 0.7653, "step": 167590 }, { "epoch": 13.93, "learning_rate": 2.1439126458443033e-06, "loss": 0.7669, "step": 167600 }, { "epoch": 13.93, "learning_rate": 2.1438017903167696e-06, "loss": 0.8447, "step": 167610 }, { "epoch": 13.93, "learning_rate": 2.143690934789236e-06, "loss": 0.814, "step": 167620 }, { "epoch": 13.93, "learning_rate": 2.1435800792617022e-06, "loss": 0.8024, "step": 167630 }, { "epoch": 13.93, "learning_rate": 2.1434692237341685e-06, "loss": 0.8579, "step": 167640 }, { "epoch": 13.93, "learning_rate": 2.1433583682066344e-06, "loss": 0.7147, "step": 167650 }, { "epoch": 13.94, "learning_rate": 2.143247512679101e-06, "loss": 0.8636, "step": 167660 }, { "epoch": 13.94, "learning_rate": 2.143136657151567e-06, "loss": 0.7773, "step": 167670 }, { "epoch": 13.94, "learning_rate": 2.1430258016240333e-06, "loss": 0.882, "step": 167680 }, { "epoch": 13.94, "learning_rate": 2.1429149460964996e-06, "loss": 0.7502, "step": 167690 }, { "epoch": 13.94, "learning_rate": 2.142804090568966e-06, "loss": 0.7469, "step": 167700 }, { "epoch": 13.94, "learning_rate": 2.142693235041432e-06, "loss": 0.8258, "step": 167710 }, { "epoch": 13.94, "learning_rate": 2.1425823795138984e-06, "loss": 0.7582, "step": 167720 }, { "epoch": 13.94, "learning_rate": 2.1424715239863647e-06, "loss": 0.7681, "step": 167730 }, { "epoch": 13.94, "learning_rate": 2.142360668458831e-06, "loss": 0.7492, "step": 167740 }, { "epoch": 13.94, "learning_rate": 2.1422498129312973e-06, "loss": 0.7519, "step": 167750 }, { "epoch": 13.94, "learning_rate": 2.142138957403763e-06, "loss": 0.8333, "step": 167760 }, { "epoch": 13.94, "learning_rate": 2.14202810187623e-06, "loss": 0.7429, "step": 167770 }, { "epoch": 13.95, "learning_rate": 2.141917246348696e-06, "loss": 0.806, "step": 167780 }, { "epoch": 13.95, "learning_rate": 2.1418063908211625e-06, "loss": 0.8022, "step": 167790 }, { "epoch": 13.95, "learning_rate": 2.1416955352936284e-06, "loss": 0.7232, "step": 167800 }, { "epoch": 13.95, "learning_rate": 2.1415846797660947e-06, "loss": 0.8104, "step": 167810 }, { "epoch": 13.95, "learning_rate": 2.141473824238561e-06, "loss": 0.8418, "step": 167820 }, { "epoch": 13.95, "learning_rate": 2.1413629687110273e-06, "loss": 0.7964, "step": 167830 }, { "epoch": 13.95, "learning_rate": 2.141252113183493e-06, "loss": 0.7928, "step": 167840 }, { "epoch": 13.95, "learning_rate": 2.14114125765596e-06, "loss": 0.7944, "step": 167850 }, { "epoch": 13.95, "learning_rate": 2.141030402128426e-06, "loss": 0.8505, "step": 167860 }, { "epoch": 13.95, "learning_rate": 2.1409195466008925e-06, "loss": 0.7472, "step": 167870 }, { "epoch": 13.95, "learning_rate": 2.1408086910733588e-06, "loss": 0.7483, "step": 167880 }, { "epoch": 13.95, "learning_rate": 2.1406978355458246e-06, "loss": 0.8304, "step": 167890 }, { "epoch": 13.96, "learning_rate": 2.1405869800182913e-06, "loss": 0.7198, "step": 167900 }, { "epoch": 13.96, "learning_rate": 2.1404761244907572e-06, "loss": 0.8009, "step": 167910 }, { "epoch": 13.96, "learning_rate": 2.1403652689632235e-06, "loss": 0.7518, "step": 167920 }, { "epoch": 13.96, "learning_rate": 2.14025441343569e-06, "loss": 0.7551, "step": 167930 }, { "epoch": 13.96, "learning_rate": 2.140143557908156e-06, "loss": 0.8027, "step": 167940 }, { "epoch": 13.96, "learning_rate": 2.140032702380622e-06, "loss": 0.8048, "step": 167950 }, { "epoch": 13.96, "learning_rate": 2.1399218468530887e-06, "loss": 0.7973, "step": 167960 }, { "epoch": 13.96, "learning_rate": 2.139810991325555e-06, "loss": 0.8524, "step": 167970 }, { "epoch": 13.96, "learning_rate": 2.1397001357980213e-06, "loss": 0.7447, "step": 167980 }, { "epoch": 13.96, "learning_rate": 2.1395892802704876e-06, "loss": 0.7773, "step": 167990 }, { "epoch": 13.96, "learning_rate": 2.1394784247429534e-06, "loss": 0.8206, "step": 168000 }, { "epoch": 13.96, "learning_rate": 2.13936756921542e-06, "loss": 0.8367, "step": 168010 }, { "epoch": 13.97, "learning_rate": 2.139256713687886e-06, "loss": 0.8061, "step": 168020 }, { "epoch": 13.97, "learning_rate": 2.1391458581603523e-06, "loss": 0.8057, "step": 168030 }, { "epoch": 13.97, "learning_rate": 2.1390350026328186e-06, "loss": 0.7535, "step": 168040 }, { "epoch": 13.97, "learning_rate": 2.138924147105285e-06, "loss": 0.7682, "step": 168050 }, { "epoch": 13.97, "learning_rate": 2.1388132915777512e-06, "loss": 0.7998, "step": 168060 }, { "epoch": 13.97, "learning_rate": 2.1387024360502175e-06, "loss": 0.7529, "step": 168070 }, { "epoch": 13.97, "learning_rate": 2.1385915805226834e-06, "loss": 0.825, "step": 168080 }, { "epoch": 13.97, "learning_rate": 2.13848072499515e-06, "loss": 0.75, "step": 168090 }, { "epoch": 13.97, "learning_rate": 2.1383698694676164e-06, "loss": 0.7825, "step": 168100 }, { "epoch": 13.97, "learning_rate": 2.1382590139400823e-06, "loss": 0.835, "step": 168110 }, { "epoch": 13.97, "learning_rate": 2.138148158412549e-06, "loss": 0.8261, "step": 168120 }, { "epoch": 13.97, "learning_rate": 2.138037302885015e-06, "loss": 0.8483, "step": 168130 }, { "epoch": 13.98, "learning_rate": 2.1379264473574816e-06, "loss": 0.7924, "step": 168140 }, { "epoch": 13.98, "learning_rate": 2.1378155918299475e-06, "loss": 0.7806, "step": 168150 }, { "epoch": 13.98, "learning_rate": 2.1377047363024137e-06, "loss": 0.7897, "step": 168160 }, { "epoch": 13.98, "learning_rate": 2.13759388077488e-06, "loss": 0.7564, "step": 168170 }, { "epoch": 13.98, "learning_rate": 2.1374830252473463e-06, "loss": 0.8007, "step": 168180 }, { "epoch": 13.98, "learning_rate": 2.1373721697198122e-06, "loss": 0.7052, "step": 168190 }, { "epoch": 13.98, "learning_rate": 2.137261314192279e-06, "loss": 0.7816, "step": 168200 }, { "epoch": 13.98, "learning_rate": 2.137150458664745e-06, "loss": 0.8131, "step": 168210 }, { "epoch": 13.98, "learning_rate": 2.1370396031372115e-06, "loss": 0.7216, "step": 168220 }, { "epoch": 13.98, "learning_rate": 2.136928747609678e-06, "loss": 0.7318, "step": 168230 }, { "epoch": 13.98, "learning_rate": 2.1368178920821437e-06, "loss": 0.723, "step": 168240 }, { "epoch": 13.98, "learning_rate": 2.1367070365546104e-06, "loss": 0.7935, "step": 168250 }, { "epoch": 13.99, "learning_rate": 2.1365961810270763e-06, "loss": 0.779, "step": 168260 }, { "epoch": 13.99, "learning_rate": 2.1364853254995426e-06, "loss": 0.7129, "step": 168270 }, { "epoch": 13.99, "learning_rate": 2.136374469972009e-06, "loss": 0.8105, "step": 168280 }, { "epoch": 13.99, "learning_rate": 2.136263614444475e-06, "loss": 0.7502, "step": 168290 }, { "epoch": 13.99, "learning_rate": 2.136152758916941e-06, "loss": 0.7275, "step": 168300 }, { "epoch": 13.99, "learning_rate": 2.1360419033894078e-06, "loss": 0.8464, "step": 168310 }, { "epoch": 13.99, "learning_rate": 2.1359310478618736e-06, "loss": 0.7949, "step": 168320 }, { "epoch": 13.99, "learning_rate": 2.1358201923343403e-06, "loss": 0.7562, "step": 168330 }, { "epoch": 13.99, "learning_rate": 2.1357093368068066e-06, "loss": 0.8031, "step": 168340 }, { "epoch": 13.99, "learning_rate": 2.1355984812792725e-06, "loss": 0.7794, "step": 168350 }, { "epoch": 13.99, "learning_rate": 2.1354876257517392e-06, "loss": 0.8043, "step": 168360 }, { "epoch": 13.99, "learning_rate": 2.135376770224205e-06, "loss": 0.868, "step": 168370 }, { "epoch": 14.0, "learning_rate": 2.1352659146966714e-06, "loss": 0.6712, "step": 168380 }, { "epoch": 14.0, "learning_rate": 2.1351550591691377e-06, "loss": 0.6977, "step": 168390 }, { "epoch": 14.0, "learning_rate": 2.135044203641604e-06, "loss": 0.8392, "step": 168400 }, { "epoch": 14.0, "learning_rate": 2.1349333481140703e-06, "loss": 0.8158, "step": 168410 }, { "epoch": 14.0, "learning_rate": 2.1348224925865366e-06, "loss": 0.818, "step": 168420 }, { "epoch": 14.0, "learning_rate": 2.1347116370590025e-06, "loss": 0.7552, "step": 168430 }, { "epoch": 14.0, "eval_loss": 1.0861937999725342, "eval_runtime": 354.8217, "eval_samples_per_second": 7.536, "eval_steps_per_second": 3.768, "eval_wer": 0.6449171975721961, "step": 168434 }, { "epoch": 14.0, "learning_rate": 2.134600781531469e-06, "loss": 0.7741, "step": 168440 }, { "epoch": 14.0, "learning_rate": 2.134489926003935e-06, "loss": 0.8304, "step": 168450 }, { "epoch": 14.0, "learning_rate": 2.1343790704764013e-06, "loss": 0.7246, "step": 168460 }, { "epoch": 14.0, "learning_rate": 2.134268214948868e-06, "loss": 0.7074, "step": 168470 }, { "epoch": 14.0, "learning_rate": 2.134157359421334e-06, "loss": 0.7872, "step": 168480 }, { "epoch": 14.0, "learning_rate": 2.1340465038938006e-06, "loss": 0.7682, "step": 168490 }, { "epoch": 14.01, "learning_rate": 2.1339356483662665e-06, "loss": 0.7355, "step": 168500 }, { "epoch": 14.01, "learning_rate": 2.133824792838733e-06, "loss": 0.786, "step": 168510 }, { "epoch": 14.01, "learning_rate": 2.133713937311199e-06, "loss": 0.7822, "step": 168520 }, { "epoch": 14.01, "learning_rate": 2.1336030817836654e-06, "loss": 0.7815, "step": 168530 }, { "epoch": 14.01, "learning_rate": 2.1334922262561313e-06, "loss": 0.8281, "step": 168540 }, { "epoch": 14.01, "learning_rate": 2.133381370728598e-06, "loss": 0.8013, "step": 168550 }, { "epoch": 14.01, "learning_rate": 2.133270515201064e-06, "loss": 0.77, "step": 168560 }, { "epoch": 14.01, "learning_rate": 2.1331596596735306e-06, "loss": 0.7147, "step": 168570 }, { "epoch": 14.01, "learning_rate": 2.1330488041459965e-06, "loss": 0.7831, "step": 168580 }, { "epoch": 14.01, "learning_rate": 2.1329379486184628e-06, "loss": 0.8187, "step": 168590 }, { "epoch": 14.01, "learning_rate": 2.1328270930909295e-06, "loss": 0.7589, "step": 168600 }, { "epoch": 14.01, "learning_rate": 2.1327162375633953e-06, "loss": 0.7167, "step": 168610 }, { "epoch": 14.02, "learning_rate": 2.1326053820358616e-06, "loss": 0.7415, "step": 168620 }, { "epoch": 14.02, "learning_rate": 2.132494526508328e-06, "loss": 0.7258, "step": 168630 }, { "epoch": 14.02, "learning_rate": 2.1323836709807942e-06, "loss": 0.8048, "step": 168640 }, { "epoch": 14.02, "learning_rate": 2.1322728154532605e-06, "loss": 0.775, "step": 168650 }, { "epoch": 14.02, "learning_rate": 2.132161959925727e-06, "loss": 0.8066, "step": 168660 }, { "epoch": 14.02, "learning_rate": 2.1320511043981927e-06, "loss": 0.8032, "step": 168670 }, { "epoch": 14.02, "learning_rate": 2.1319402488706594e-06, "loss": 0.7494, "step": 168680 }, { "epoch": 14.02, "learning_rate": 2.1318293933431253e-06, "loss": 0.7667, "step": 168690 }, { "epoch": 14.02, "learning_rate": 2.1317185378155916e-06, "loss": 0.7752, "step": 168700 }, { "epoch": 14.02, "learning_rate": 2.1316076822880583e-06, "loss": 0.7543, "step": 168710 }, { "epoch": 14.02, "learning_rate": 2.131496826760524e-06, "loss": 0.7727, "step": 168720 }, { "epoch": 14.02, "learning_rate": 2.131385971232991e-06, "loss": 0.7518, "step": 168730 }, { "epoch": 14.03, "learning_rate": 2.1312751157054568e-06, "loss": 0.854, "step": 168740 }, { "epoch": 14.03, "learning_rate": 2.131164260177923e-06, "loss": 0.7249, "step": 168750 }, { "epoch": 14.03, "learning_rate": 2.1310534046503894e-06, "loss": 0.8255, "step": 168760 }, { "epoch": 14.03, "learning_rate": 2.1309425491228556e-06, "loss": 0.8074, "step": 168770 }, { "epoch": 14.03, "learning_rate": 2.1308316935953215e-06, "loss": 0.7788, "step": 168780 }, { "epoch": 14.03, "learning_rate": 2.1307208380677882e-06, "loss": 0.7801, "step": 168790 }, { "epoch": 14.03, "learning_rate": 2.130609982540254e-06, "loss": 0.7338, "step": 168800 }, { "epoch": 14.03, "learning_rate": 2.1304991270127204e-06, "loss": 0.787, "step": 168810 }, { "epoch": 14.03, "learning_rate": 2.1303882714851867e-06, "loss": 0.7475, "step": 168820 }, { "epoch": 14.03, "learning_rate": 2.130277415957653e-06, "loss": 0.8003, "step": 168830 }, { "epoch": 14.03, "learning_rate": 2.1301665604301197e-06, "loss": 0.8197, "step": 168840 }, { "epoch": 14.03, "learning_rate": 2.1300557049025856e-06, "loss": 0.7702, "step": 168850 }, { "epoch": 14.04, "learning_rate": 2.129944849375052e-06, "loss": 0.7259, "step": 168860 }, { "epoch": 14.04, "learning_rate": 2.129833993847518e-06, "loss": 0.7555, "step": 168870 }, { "epoch": 14.04, "learning_rate": 2.1297231383199845e-06, "loss": 0.7815, "step": 168880 }, { "epoch": 14.04, "learning_rate": 2.1296122827924503e-06, "loss": 0.8145, "step": 168890 }, { "epoch": 14.04, "learning_rate": 2.129501427264917e-06, "loss": 0.7865, "step": 168900 }, { "epoch": 14.04, "learning_rate": 2.129390571737383e-06, "loss": 0.7902, "step": 168910 }, { "epoch": 14.04, "learning_rate": 2.1292797162098497e-06, "loss": 0.7434, "step": 168920 }, { "epoch": 14.04, "learning_rate": 2.1291688606823155e-06, "loss": 0.8252, "step": 168930 }, { "epoch": 14.04, "learning_rate": 2.129058005154782e-06, "loss": 0.7902, "step": 168940 }, { "epoch": 14.04, "learning_rate": 2.128947149627248e-06, "loss": 0.8185, "step": 168950 }, { "epoch": 14.04, "learning_rate": 2.128847379652468e-06, "loss": 0.8163, "step": 168960 }, { "epoch": 14.04, "learning_rate": 2.128736524124934e-06, "loss": 0.7429, "step": 168970 }, { "epoch": 14.05, "learning_rate": 2.1286256685974002e-06, "loss": 0.7591, "step": 168980 }, { "epoch": 14.05, "learning_rate": 2.1285148130698665e-06, "loss": 0.7796, "step": 168990 }, { "epoch": 14.05, "learning_rate": 2.128403957542333e-06, "loss": 0.82, "step": 169000 }, { "epoch": 14.05, "learning_rate": 2.128293102014799e-06, "loss": 0.7738, "step": 169010 }, { "epoch": 14.05, "learning_rate": 2.1281822464872654e-06, "loss": 0.7907, "step": 169020 }, { "epoch": 14.05, "learning_rate": 2.1280713909597313e-06, "loss": 0.7928, "step": 169030 }, { "epoch": 14.05, "learning_rate": 2.127960535432198e-06, "loss": 0.8095, "step": 169040 }, { "epoch": 14.05, "learning_rate": 2.1278496799046643e-06, "loss": 0.7985, "step": 169050 }, { "epoch": 14.05, "learning_rate": 2.12773882437713e-06, "loss": 0.7481, "step": 169060 }, { "epoch": 14.05, "learning_rate": 2.127627968849597e-06, "loss": 0.7773, "step": 169070 }, { "epoch": 14.05, "learning_rate": 2.1275171133220628e-06, "loss": 0.7572, "step": 169080 }, { "epoch": 14.05, "learning_rate": 2.1274062577945295e-06, "loss": 0.7808, "step": 169090 }, { "epoch": 14.06, "learning_rate": 2.1272954022669954e-06, "loss": 0.7793, "step": 169100 }, { "epoch": 14.06, "learning_rate": 2.1271845467394617e-06, "loss": 0.7525, "step": 169110 }, { "epoch": 14.06, "learning_rate": 2.127073691211928e-06, "loss": 0.7397, "step": 169120 }, { "epoch": 14.06, "learning_rate": 2.1269628356843943e-06, "loss": 0.8162, "step": 169130 }, { "epoch": 14.06, "learning_rate": 2.12685198015686e-06, "loss": 0.8008, "step": 169140 }, { "epoch": 14.06, "learning_rate": 2.126741124629327e-06, "loss": 0.7215, "step": 169150 }, { "epoch": 14.06, "learning_rate": 2.1266302691017927e-06, "loss": 0.7811, "step": 169160 }, { "epoch": 14.06, "learning_rate": 2.1265194135742594e-06, "loss": 0.7423, "step": 169170 }, { "epoch": 14.06, "learning_rate": 2.1264085580467257e-06, "loss": 0.7667, "step": 169180 }, { "epoch": 14.06, "learning_rate": 2.1262977025191916e-06, "loss": 0.8285, "step": 169190 }, { "epoch": 14.06, "learning_rate": 2.1261868469916583e-06, "loss": 0.8754, "step": 169200 }, { "epoch": 14.06, "learning_rate": 2.126075991464124e-06, "loss": 0.7312, "step": 169210 }, { "epoch": 14.07, "learning_rate": 2.1259651359365905e-06, "loss": 0.7474, "step": 169220 }, { "epoch": 14.07, "learning_rate": 2.1258542804090568e-06, "loss": 0.7833, "step": 169230 }, { "epoch": 14.07, "learning_rate": 2.125743424881523e-06, "loss": 0.8067, "step": 169240 }, { "epoch": 14.07, "learning_rate": 2.125632569353989e-06, "loss": 0.8175, "step": 169250 }, { "epoch": 14.07, "learning_rate": 2.1255217138264557e-06, "loss": 0.8177, "step": 169260 }, { "epoch": 14.07, "learning_rate": 2.1254108582989215e-06, "loss": 0.7652, "step": 169270 }, { "epoch": 14.07, "learning_rate": 2.1253000027713883e-06, "loss": 0.7642, "step": 169280 }, { "epoch": 14.07, "learning_rate": 2.1251891472438546e-06, "loss": 0.8177, "step": 169290 }, { "epoch": 14.07, "learning_rate": 2.1250782917163204e-06, "loss": 0.8186, "step": 169300 }, { "epoch": 14.07, "learning_rate": 2.124967436188787e-06, "loss": 0.7999, "step": 169310 }, { "epoch": 14.07, "learning_rate": 2.124856580661253e-06, "loss": 0.7376, "step": 169320 }, { "epoch": 14.07, "learning_rate": 2.1247457251337193e-06, "loss": 0.8161, "step": 169330 }, { "epoch": 14.08, "learning_rate": 2.1246348696061856e-06, "loss": 0.7399, "step": 169340 }, { "epoch": 14.08, "learning_rate": 2.124524014078652e-06, "loss": 0.7418, "step": 169350 }, { "epoch": 14.08, "learning_rate": 2.124413158551118e-06, "loss": 0.8096, "step": 169360 }, { "epoch": 14.08, "learning_rate": 2.1243023030235845e-06, "loss": 0.7468, "step": 169370 }, { "epoch": 14.08, "learning_rate": 2.1241914474960504e-06, "loss": 0.7476, "step": 169380 }, { "epoch": 14.08, "learning_rate": 2.124080591968517e-06, "loss": 0.8411, "step": 169390 }, { "epoch": 14.08, "learning_rate": 2.123969736440983e-06, "loss": 0.8379, "step": 169400 }, { "epoch": 14.08, "learning_rate": 2.1238588809134493e-06, "loss": 0.8203, "step": 169410 }, { "epoch": 14.08, "learning_rate": 2.123748025385916e-06, "loss": 0.7559, "step": 169420 }, { "epoch": 14.08, "learning_rate": 2.123637169858382e-06, "loss": 0.7128, "step": 169430 }, { "epoch": 14.08, "learning_rate": 2.1235263143308486e-06, "loss": 0.8229, "step": 169440 }, { "epoch": 14.08, "learning_rate": 2.1234154588033144e-06, "loss": 0.7577, "step": 169450 }, { "epoch": 14.09, "learning_rate": 2.1233046032757807e-06, "loss": 0.7278, "step": 169460 }, { "epoch": 14.09, "learning_rate": 2.123193747748247e-06, "loss": 0.7712, "step": 169470 }, { "epoch": 14.09, "learning_rate": 2.1230828922207133e-06, "loss": 0.7885, "step": 169480 }, { "epoch": 14.09, "learning_rate": 2.122972036693179e-06, "loss": 0.8205, "step": 169490 }, { "epoch": 14.09, "learning_rate": 2.122861181165646e-06, "loss": 0.7415, "step": 169500 }, { "epoch": 14.09, "learning_rate": 2.1227503256381118e-06, "loss": 0.8006, "step": 169510 }, { "epoch": 14.09, "learning_rate": 2.1226394701105785e-06, "loss": 0.7324, "step": 169520 }, { "epoch": 14.09, "learning_rate": 2.1225286145830444e-06, "loss": 0.7217, "step": 169530 }, { "epoch": 14.09, "learning_rate": 2.1224177590555107e-06, "loss": 0.8149, "step": 169540 }, { "epoch": 14.09, "learning_rate": 2.1223069035279774e-06, "loss": 0.8512, "step": 169550 }, { "epoch": 14.09, "learning_rate": 2.1221960480004433e-06, "loss": 0.7422, "step": 169560 }, { "epoch": 14.09, "learning_rate": 2.1220851924729096e-06, "loss": 0.8363, "step": 169570 }, { "epoch": 14.1, "learning_rate": 2.121974336945376e-06, "loss": 0.8242, "step": 169580 }, { "epoch": 14.1, "learning_rate": 2.121863481417842e-06, "loss": 0.8068, "step": 169590 }, { "epoch": 14.1, "learning_rate": 2.1217526258903084e-06, "loss": 0.7742, "step": 169600 }, { "epoch": 14.1, "learning_rate": 2.1216417703627747e-06, "loss": 0.7296, "step": 169610 }, { "epoch": 14.1, "learning_rate": 2.1215309148352406e-06, "loss": 0.7879, "step": 169620 }, { "epoch": 14.1, "learning_rate": 2.1214200593077073e-06, "loss": 0.7839, "step": 169630 }, { "epoch": 14.1, "learning_rate": 2.121309203780173e-06, "loss": 0.802, "step": 169640 }, { "epoch": 14.1, "learning_rate": 2.1211983482526395e-06, "loss": 0.8085, "step": 169650 }, { "epoch": 14.1, "learning_rate": 2.121087492725106e-06, "loss": 0.7944, "step": 169660 }, { "epoch": 14.1, "learning_rate": 2.120976637197572e-06, "loss": 0.7859, "step": 169670 }, { "epoch": 14.1, "learning_rate": 2.120865781670039e-06, "loss": 0.8343, "step": 169680 }, { "epoch": 14.1, "learning_rate": 2.1207549261425047e-06, "loss": 0.8209, "step": 169690 }, { "epoch": 14.11, "learning_rate": 2.120644070614971e-06, "loss": 0.7848, "step": 169700 }, { "epoch": 14.11, "learning_rate": 2.1205332150874373e-06, "loss": 0.8115, "step": 169710 }, { "epoch": 14.11, "learning_rate": 2.1204223595599036e-06, "loss": 0.7567, "step": 169720 }, { "epoch": 14.11, "learning_rate": 2.1203115040323694e-06, "loss": 0.7507, "step": 169730 }, { "epoch": 14.11, "learning_rate": 2.120200648504836e-06, "loss": 0.8337, "step": 169740 }, { "epoch": 14.11, "learning_rate": 2.120089792977302e-06, "loss": 0.7887, "step": 169750 }, { "epoch": 14.11, "learning_rate": 2.1199789374497683e-06, "loss": 0.8236, "step": 169760 }, { "epoch": 14.11, "learning_rate": 2.1198680819222346e-06, "loss": 0.7731, "step": 169770 }, { "epoch": 14.11, "learning_rate": 2.119757226394701e-06, "loss": 0.767, "step": 169780 }, { "epoch": 14.11, "learning_rate": 2.1196463708671676e-06, "loss": 0.7758, "step": 169790 }, { "epoch": 14.11, "learning_rate": 2.1195355153396335e-06, "loss": 0.7477, "step": 169800 }, { "epoch": 14.11, "learning_rate": 2.1194246598121e-06, "loss": 0.7392, "step": 169810 }, { "epoch": 14.12, "learning_rate": 2.119313804284566e-06, "loss": 0.7686, "step": 169820 }, { "epoch": 14.12, "learning_rate": 2.1192029487570324e-06, "loss": 0.8092, "step": 169830 }, { "epoch": 14.12, "learning_rate": 2.1190920932294983e-06, "loss": 0.8165, "step": 169840 }, { "epoch": 14.12, "learning_rate": 2.118981237701965e-06, "loss": 0.7545, "step": 169850 }, { "epoch": 14.12, "learning_rate": 2.118870382174431e-06, "loss": 0.8123, "step": 169860 }, { "epoch": 14.12, "learning_rate": 2.1187595266468976e-06, "loss": 0.7936, "step": 169870 }, { "epoch": 14.12, "learning_rate": 2.1186486711193634e-06, "loss": 0.7214, "step": 169880 }, { "epoch": 14.12, "learning_rate": 2.1185378155918297e-06, "loss": 0.8032, "step": 169890 }, { "epoch": 14.12, "learning_rate": 2.1184269600642965e-06, "loss": 0.7722, "step": 169900 }, { "epoch": 14.12, "learning_rate": 2.1183161045367623e-06, "loss": 0.728, "step": 169910 }, { "epoch": 14.12, "learning_rate": 2.1182052490092286e-06, "loss": 0.6961, "step": 169920 }, { "epoch": 14.12, "learning_rate": 2.118094393481695e-06, "loss": 0.782, "step": 169930 }, { "epoch": 14.13, "learning_rate": 2.117983537954161e-06, "loss": 0.837, "step": 169940 }, { "epoch": 14.13, "learning_rate": 2.1178726824266275e-06, "loss": 0.7152, "step": 169950 }, { "epoch": 14.13, "learning_rate": 2.117761826899094e-06, "loss": 0.746, "step": 169960 }, { "epoch": 14.13, "learning_rate": 2.1176509713715597e-06, "loss": 0.768, "step": 169970 }, { "epoch": 14.13, "learning_rate": 2.1175401158440264e-06, "loss": 0.697, "step": 169980 }, { "epoch": 14.13, "learning_rate": 2.1174292603164923e-06, "loss": 0.8641, "step": 169990 }, { "epoch": 14.13, "learning_rate": 2.1173184047889586e-06, "loss": 0.8427, "step": 170000 }, { "epoch": 14.13, "learning_rate": 2.117207549261425e-06, "loss": 0.8313, "step": 170010 }, { "epoch": 14.13, "learning_rate": 2.117096693733891e-06, "loss": 0.7601, "step": 170020 }, { "epoch": 14.13, "learning_rate": 2.116985838206358e-06, "loss": 0.8213, "step": 170030 }, { "epoch": 14.13, "learning_rate": 2.1168749826788237e-06, "loss": 0.8463, "step": 170040 }, { "epoch": 14.13, "learning_rate": 2.11676412715129e-06, "loss": 0.8155, "step": 170050 }, { "epoch": 14.14, "learning_rate": 2.1166532716237563e-06, "loss": 0.7917, "step": 170060 }, { "epoch": 14.14, "learning_rate": 2.1165424160962226e-06, "loss": 0.7984, "step": 170070 }, { "epoch": 14.14, "learning_rate": 2.1164315605686885e-06, "loss": 0.7484, "step": 170080 }, { "epoch": 14.14, "learning_rate": 2.1163207050411552e-06, "loss": 0.8436, "step": 170090 }, { "epoch": 14.14, "learning_rate": 2.116209849513621e-06, "loss": 0.7918, "step": 170100 }, { "epoch": 14.14, "learning_rate": 2.116098993986088e-06, "loss": 0.8452, "step": 170110 }, { "epoch": 14.14, "learning_rate": 2.1159881384585537e-06, "loss": 0.8389, "step": 170120 }, { "epoch": 14.14, "learning_rate": 2.11587728293102e-06, "loss": 0.7529, "step": 170130 }, { "epoch": 14.14, "learning_rate": 2.1157664274034863e-06, "loss": 0.8176, "step": 170140 }, { "epoch": 14.14, "learning_rate": 2.1156555718759526e-06, "loss": 0.8367, "step": 170150 }, { "epoch": 14.14, "learning_rate": 2.115544716348419e-06, "loss": 0.7703, "step": 170160 }, { "epoch": 14.14, "learning_rate": 2.115433860820885e-06, "loss": 0.776, "step": 170170 }, { "epoch": 14.15, "learning_rate": 2.1153230052933515e-06, "loss": 0.8395, "step": 170180 }, { "epoch": 14.15, "learning_rate": 2.1152121497658173e-06, "loss": 0.825, "step": 170190 }, { "epoch": 14.15, "learning_rate": 2.115101294238284e-06, "loss": 0.788, "step": 170200 }, { "epoch": 14.15, "learning_rate": 2.11499043871075e-06, "loss": 0.8255, "step": 170210 }, { "epoch": 14.15, "learning_rate": 2.1148795831832166e-06, "loss": 0.7419, "step": 170220 }, { "epoch": 14.15, "learning_rate": 2.1147687276556825e-06, "loss": 0.7069, "step": 170230 }, { "epoch": 14.15, "learning_rate": 2.114657872128149e-06, "loss": 0.7753, "step": 170240 }, { "epoch": 14.15, "learning_rate": 2.114547016600615e-06, "loss": 0.8037, "step": 170250 }, { "epoch": 14.15, "learning_rate": 2.1144361610730814e-06, "loss": 0.8515, "step": 170260 }, { "epoch": 14.15, "learning_rate": 2.1143253055455477e-06, "loss": 0.7297, "step": 170270 }, { "epoch": 14.15, "learning_rate": 2.114214450018014e-06, "loss": 0.7655, "step": 170280 }, { "epoch": 14.15, "learning_rate": 2.1141035944904803e-06, "loss": 0.7972, "step": 170290 }, { "epoch": 14.16, "learning_rate": 2.1139927389629466e-06, "loss": 0.7852, "step": 170300 }, { "epoch": 14.16, "learning_rate": 2.113881883435413e-06, "loss": 0.7577, "step": 170310 }, { "epoch": 14.16, "learning_rate": 2.1137710279078787e-06, "loss": 0.6924, "step": 170320 }, { "epoch": 14.16, "learning_rate": 2.1136601723803455e-06, "loss": 0.7849, "step": 170330 }, { "epoch": 14.16, "learning_rate": 2.1135493168528113e-06, "loss": 0.7665, "step": 170340 }, { "epoch": 14.16, "learning_rate": 2.1134384613252776e-06, "loss": 0.8521, "step": 170350 }, { "epoch": 14.16, "learning_rate": 2.113327605797744e-06, "loss": 0.8022, "step": 170360 }, { "epoch": 14.16, "learning_rate": 2.1132167502702102e-06, "loss": 0.8126, "step": 170370 }, { "epoch": 14.16, "learning_rate": 2.1131058947426765e-06, "loss": 0.7891, "step": 170380 }, { "epoch": 14.16, "learning_rate": 2.112995039215143e-06, "loss": 0.8155, "step": 170390 }, { "epoch": 14.16, "learning_rate": 2.112884183687609e-06, "loss": 0.7266, "step": 170400 }, { "epoch": 14.16, "learning_rate": 2.1127733281600754e-06, "loss": 0.8174, "step": 170410 }, { "epoch": 14.17, "learning_rate": 2.1126624726325417e-06, "loss": 0.7623, "step": 170420 }, { "epoch": 14.17, "learning_rate": 2.1125516171050076e-06, "loss": 0.8099, "step": 170430 }, { "epoch": 14.17, "learning_rate": 2.1124407615774743e-06, "loss": 0.8112, "step": 170440 }, { "epoch": 14.17, "learning_rate": 2.11232990604994e-06, "loss": 0.7926, "step": 170450 }, { "epoch": 14.17, "learning_rate": 2.112219050522407e-06, "loss": 0.7952, "step": 170460 }, { "epoch": 14.17, "learning_rate": 2.1121081949948727e-06, "loss": 0.7999, "step": 170470 }, { "epoch": 14.17, "learning_rate": 2.111997339467339e-06, "loss": 0.7399, "step": 170480 }, { "epoch": 14.17, "learning_rate": 2.1118864839398053e-06, "loss": 0.8074, "step": 170490 }, { "epoch": 14.17, "learning_rate": 2.1117756284122716e-06, "loss": 0.7883, "step": 170500 }, { "epoch": 14.17, "learning_rate": 2.1116647728847375e-06, "loss": 0.8086, "step": 170510 }, { "epoch": 14.17, "learning_rate": 2.1115539173572042e-06, "loss": 0.7647, "step": 170520 }, { "epoch": 14.17, "learning_rate": 2.1114430618296705e-06, "loss": 0.7913, "step": 170530 }, { "epoch": 14.18, "learning_rate": 2.1113322063021364e-06, "loss": 0.8354, "step": 170540 }, { "epoch": 14.18, "learning_rate": 2.111221350774603e-06, "loss": 0.778, "step": 170550 }, { "epoch": 14.18, "learning_rate": 2.111110495247069e-06, "loss": 0.7437, "step": 170560 }, { "epoch": 14.18, "learning_rate": 2.1109996397195357e-06, "loss": 0.7457, "step": 170570 }, { "epoch": 14.18, "learning_rate": 2.1108887841920016e-06, "loss": 0.7282, "step": 170580 }, { "epoch": 14.18, "learning_rate": 2.110777928664468e-06, "loss": 0.8306, "step": 170590 }, { "epoch": 14.18, "learning_rate": 2.110667073136934e-06, "loss": 0.751, "step": 170600 }, { "epoch": 14.18, "learning_rate": 2.1105562176094005e-06, "loss": 0.78, "step": 170610 }, { "epoch": 14.18, "learning_rate": 2.1104453620818663e-06, "loss": 0.8112, "step": 170620 }, { "epoch": 14.18, "learning_rate": 2.110334506554333e-06, "loss": 0.8231, "step": 170630 }, { "epoch": 14.18, "learning_rate": 2.1102236510267993e-06, "loss": 0.7387, "step": 170640 }, { "epoch": 14.18, "learning_rate": 2.1101127954992656e-06, "loss": 0.7368, "step": 170650 }, { "epoch": 14.19, "learning_rate": 2.110001939971732e-06, "loss": 0.7228, "step": 170660 }, { "epoch": 14.19, "learning_rate": 2.109891084444198e-06, "loss": 0.785, "step": 170670 }, { "epoch": 14.19, "learning_rate": 2.1097802289166645e-06, "loss": 0.7478, "step": 170680 }, { "epoch": 14.19, "learning_rate": 2.1096693733891304e-06, "loss": 0.8287, "step": 170690 }, { "epoch": 14.19, "learning_rate": 2.1095585178615967e-06, "loss": 0.749, "step": 170700 }, { "epoch": 14.19, "learning_rate": 2.109447662334063e-06, "loss": 0.779, "step": 170710 }, { "epoch": 14.19, "learning_rate": 2.1093368068065293e-06, "loss": 0.7451, "step": 170720 }, { "epoch": 14.19, "learning_rate": 2.1092259512789956e-06, "loss": 0.7803, "step": 170730 }, { "epoch": 14.19, "learning_rate": 2.109115095751462e-06, "loss": 0.7943, "step": 170740 }, { "epoch": 14.19, "learning_rate": 2.1090042402239277e-06, "loss": 0.7864, "step": 170750 }, { "epoch": 14.19, "learning_rate": 2.1088933846963945e-06, "loss": 0.7677, "step": 170760 }, { "epoch": 14.19, "learning_rate": 2.1087825291688608e-06, "loss": 0.7255, "step": 170770 }, { "epoch": 14.19, "learning_rate": 2.1086716736413266e-06, "loss": 0.7817, "step": 170780 }, { "epoch": 14.2, "learning_rate": 2.1085608181137933e-06, "loss": 0.7691, "step": 170790 }, { "epoch": 14.2, "learning_rate": 2.1084499625862592e-06, "loss": 0.7738, "step": 170800 }, { "epoch": 14.2, "learning_rate": 2.108339107058726e-06, "loss": 0.7236, "step": 170810 }, { "epoch": 14.2, "learning_rate": 2.108228251531192e-06, "loss": 0.7783, "step": 170820 }, { "epoch": 14.2, "learning_rate": 2.108117396003658e-06, "loss": 0.7462, "step": 170830 }, { "epoch": 14.2, "learning_rate": 2.1080065404761244e-06, "loss": 0.7744, "step": 170840 }, { "epoch": 14.2, "learning_rate": 2.1078956849485907e-06, "loss": 0.7223, "step": 170850 }, { "epoch": 14.2, "learning_rate": 2.1077848294210566e-06, "loss": 0.7325, "step": 170860 }, { "epoch": 14.2, "learning_rate": 2.1076739738935233e-06, "loss": 0.9001, "step": 170870 }, { "epoch": 14.2, "learning_rate": 2.107563118365989e-06, "loss": 0.8472, "step": 170880 }, { "epoch": 14.2, "learning_rate": 2.107452262838456e-06, "loss": 0.7581, "step": 170890 }, { "epoch": 14.2, "learning_rate": 2.107341407310922e-06, "loss": 0.797, "step": 170900 }, { "epoch": 14.21, "learning_rate": 2.107230551783388e-06, "loss": 0.7522, "step": 170910 }, { "epoch": 14.21, "learning_rate": 2.1071196962558548e-06, "loss": 0.7438, "step": 170920 }, { "epoch": 14.21, "learning_rate": 2.1070088407283206e-06, "loss": 0.7401, "step": 170930 }, { "epoch": 14.21, "learning_rate": 2.106897985200787e-06, "loss": 0.8042, "step": 170940 }, { "epoch": 14.21, "learning_rate": 2.1067871296732532e-06, "loss": 0.8383, "step": 170950 }, { "epoch": 14.21, "learning_rate": 2.1066762741457195e-06, "loss": 0.7493, "step": 170960 }, { "epoch": 14.21, "learning_rate": 2.1065654186181854e-06, "loss": 0.772, "step": 170970 }, { "epoch": 14.21, "learning_rate": 2.106454563090652e-06, "loss": 0.7638, "step": 170980 }, { "epoch": 14.21, "learning_rate": 2.106343707563118e-06, "loss": 0.798, "step": 170990 }, { "epoch": 14.21, "learning_rate": 2.1062328520355847e-06, "loss": 0.7706, "step": 171000 }, { "epoch": 14.21, "learning_rate": 2.106121996508051e-06, "loss": 0.7449, "step": 171010 }, { "epoch": 14.21, "learning_rate": 2.106011140980517e-06, "loss": 0.8467, "step": 171020 }, { "epoch": 14.22, "learning_rate": 2.1059002854529836e-06, "loss": 0.7327, "step": 171030 }, { "epoch": 14.22, "learning_rate": 2.1057894299254495e-06, "loss": 0.8233, "step": 171040 }, { "epoch": 14.22, "learning_rate": 2.1056785743979158e-06, "loss": 0.7626, "step": 171050 }, { "epoch": 14.22, "learning_rate": 2.105567718870382e-06, "loss": 0.7278, "step": 171060 }, { "epoch": 14.22, "learning_rate": 2.1054568633428483e-06, "loss": 0.7548, "step": 171070 }, { "epoch": 14.22, "learning_rate": 2.1053460078153146e-06, "loss": 0.8121, "step": 171080 }, { "epoch": 14.22, "learning_rate": 2.105235152287781e-06, "loss": 0.7946, "step": 171090 }, { "epoch": 14.22, "learning_rate": 2.105124296760247e-06, "loss": 0.8507, "step": 171100 }, { "epoch": 14.22, "learning_rate": 2.1050134412327135e-06, "loss": 0.8045, "step": 171110 }, { "epoch": 14.22, "learning_rate": 2.1049025857051794e-06, "loss": 0.8061, "step": 171120 }, { "epoch": 14.22, "learning_rate": 2.1047917301776457e-06, "loss": 0.6903, "step": 171130 }, { "epoch": 14.22, "learning_rate": 2.1046808746501124e-06, "loss": 0.8899, "step": 171140 }, { "epoch": 14.23, "learning_rate": 2.1045700191225783e-06, "loss": 0.8111, "step": 171150 }, { "epoch": 14.23, "learning_rate": 2.104459163595045e-06, "loss": 0.7647, "step": 171160 }, { "epoch": 14.23, "learning_rate": 2.104348308067511e-06, "loss": 0.7524, "step": 171170 }, { "epoch": 14.23, "learning_rate": 2.104237452539977e-06, "loss": 0.7768, "step": 171180 }, { "epoch": 14.23, "learning_rate": 2.1041265970124435e-06, "loss": 0.814, "step": 171190 }, { "epoch": 14.23, "learning_rate": 2.1040157414849098e-06, "loss": 0.8356, "step": 171200 }, { "epoch": 14.23, "learning_rate": 2.1039048859573756e-06, "loss": 0.7598, "step": 171210 }, { "epoch": 14.23, "learning_rate": 2.1037940304298424e-06, "loss": 0.7492, "step": 171220 }, { "epoch": 14.23, "learning_rate": 2.1036831749023082e-06, "loss": 0.7334, "step": 171230 }, { "epoch": 14.23, "learning_rate": 2.103572319374775e-06, "loss": 0.7985, "step": 171240 }, { "epoch": 14.23, "learning_rate": 2.103461463847241e-06, "loss": 0.7322, "step": 171250 }, { "epoch": 14.23, "learning_rate": 2.103350608319707e-06, "loss": 0.8186, "step": 171260 }, { "epoch": 14.24, "learning_rate": 2.103239752792174e-06, "loss": 0.7554, "step": 171270 }, { "epoch": 14.24, "learning_rate": 2.1031288972646397e-06, "loss": 0.7733, "step": 171280 }, { "epoch": 14.24, "learning_rate": 2.103018041737106e-06, "loss": 0.8655, "step": 171290 }, { "epoch": 14.24, "learning_rate": 2.1029071862095723e-06, "loss": 0.8139, "step": 171300 }, { "epoch": 14.24, "learning_rate": 2.1027963306820386e-06, "loss": 0.7908, "step": 171310 }, { "epoch": 14.24, "learning_rate": 2.1026854751545045e-06, "loss": 0.8163, "step": 171320 }, { "epoch": 14.24, "learning_rate": 2.102574619626971e-06, "loss": 0.7708, "step": 171330 }, { "epoch": 14.24, "learning_rate": 2.102463764099437e-06, "loss": 0.7625, "step": 171340 }, { "epoch": 14.24, "learning_rate": 2.1023529085719038e-06, "loss": 0.7425, "step": 171350 }, { "epoch": 14.24, "learning_rate": 2.1022420530443696e-06, "loss": 0.7529, "step": 171360 }, { "epoch": 14.24, "learning_rate": 2.102131197516836e-06, "loss": 0.7121, "step": 171370 }, { "epoch": 14.24, "learning_rate": 2.1020203419893027e-06, "loss": 0.8376, "step": 171380 }, { "epoch": 14.25, "learning_rate": 2.1019094864617685e-06, "loss": 0.8135, "step": 171390 }, { "epoch": 14.25, "learning_rate": 2.1017986309342352e-06, "loss": 0.7889, "step": 171400 }, { "epoch": 14.25, "learning_rate": 2.101687775406701e-06, "loss": 0.7633, "step": 171410 }, { "epoch": 14.25, "learning_rate": 2.1015769198791674e-06, "loss": 0.7281, "step": 171420 }, { "epoch": 14.25, "learning_rate": 2.1014660643516337e-06, "loss": 0.7089, "step": 171430 }, { "epoch": 14.25, "learning_rate": 2.1013552088241e-06, "loss": 0.8497, "step": 171440 }, { "epoch": 14.25, "learning_rate": 2.101244353296566e-06, "loss": 0.7742, "step": 171450 }, { "epoch": 14.25, "learning_rate": 2.1011334977690326e-06, "loss": 0.7457, "step": 171460 }, { "epoch": 14.25, "learning_rate": 2.1010226422414985e-06, "loss": 0.7937, "step": 171470 }, { "epoch": 14.25, "learning_rate": 2.1009117867139648e-06, "loss": 0.7937, "step": 171480 }, { "epoch": 14.25, "learning_rate": 2.100800931186431e-06, "loss": 0.8625, "step": 171490 }, { "epoch": 14.25, "learning_rate": 2.1006900756588974e-06, "loss": 0.7974, "step": 171500 }, { "epoch": 14.26, "learning_rate": 2.100579220131364e-06, "loss": 0.7957, "step": 171510 }, { "epoch": 14.26, "learning_rate": 2.10046836460383e-06, "loss": 0.7787, "step": 171520 }, { "epoch": 14.26, "learning_rate": 2.1003575090762962e-06, "loss": 0.8021, "step": 171530 }, { "epoch": 14.26, "learning_rate": 2.1002466535487625e-06, "loss": 0.7807, "step": 171540 }, { "epoch": 14.26, "learning_rate": 2.100135798021229e-06, "loss": 0.7652, "step": 171550 }, { "epoch": 14.26, "learning_rate": 2.1000249424936947e-06, "loss": 0.7599, "step": 171560 }, { "epoch": 14.26, "learning_rate": 2.0999140869661614e-06, "loss": 0.8012, "step": 171570 }, { "epoch": 14.26, "learning_rate": 2.0998032314386273e-06, "loss": 0.8291, "step": 171580 }, { "epoch": 14.26, "learning_rate": 2.099692375911094e-06, "loss": 0.7962, "step": 171590 }, { "epoch": 14.26, "learning_rate": 2.09958152038356e-06, "loss": 0.7052, "step": 171600 }, { "epoch": 14.26, "learning_rate": 2.099470664856026e-06, "loss": 0.7365, "step": 171610 }, { "epoch": 14.26, "learning_rate": 2.0993598093284925e-06, "loss": 0.7794, "step": 171620 }, { "epoch": 14.27, "learning_rate": 2.0992600393537124e-06, "loss": 0.8108, "step": 171630 }, { "epoch": 14.27, "learning_rate": 2.0991491838261783e-06, "loss": 0.7786, "step": 171640 }, { "epoch": 14.27, "learning_rate": 2.0990383282986446e-06, "loss": 0.7425, "step": 171650 }, { "epoch": 14.27, "learning_rate": 2.098927472771111e-06, "loss": 0.7549, "step": 171660 }, { "epoch": 14.27, "learning_rate": 2.098816617243577e-06, "loss": 0.7787, "step": 171670 }, { "epoch": 14.27, "learning_rate": 2.0987057617160435e-06, "loss": 0.8141, "step": 171680 }, { "epoch": 14.27, "learning_rate": 2.0985949061885098e-06, "loss": 0.8372, "step": 171690 }, { "epoch": 14.27, "learning_rate": 2.0984840506609757e-06, "loss": 0.7885, "step": 171700 }, { "epoch": 14.27, "learning_rate": 2.0983731951334424e-06, "loss": 0.8006, "step": 171710 }, { "epoch": 14.27, "learning_rate": 2.0982623396059087e-06, "loss": 0.8134, "step": 171720 }, { "epoch": 14.27, "learning_rate": 2.0981514840783745e-06, "loss": 0.8045, "step": 171730 }, { "epoch": 14.27, "learning_rate": 2.0980406285508413e-06, "loss": 0.7702, "step": 171740 }, { "epoch": 14.28, "learning_rate": 2.097929773023307e-06, "loss": 0.7375, "step": 171750 }, { "epoch": 14.28, "learning_rate": 2.097818917495774e-06, "loss": 0.7748, "step": 171760 }, { "epoch": 14.28, "learning_rate": 2.0977080619682397e-06, "loss": 0.7758, "step": 171770 }, { "epoch": 14.28, "learning_rate": 2.097597206440706e-06, "loss": 0.7511, "step": 171780 }, { "epoch": 14.28, "learning_rate": 2.0974863509131723e-06, "loss": 0.8263, "step": 171790 }, { "epoch": 14.28, "learning_rate": 2.0973754953856386e-06, "loss": 0.8984, "step": 171800 }, { "epoch": 14.28, "learning_rate": 2.0972646398581045e-06, "loss": 0.7978, "step": 171810 }, { "epoch": 14.28, "learning_rate": 2.097153784330571e-06, "loss": 0.7969, "step": 171820 }, { "epoch": 14.28, "learning_rate": 2.097042928803037e-06, "loss": 0.8009, "step": 171830 }, { "epoch": 14.28, "learning_rate": 2.096932073275504e-06, "loss": 0.7823, "step": 171840 }, { "epoch": 14.28, "learning_rate": 2.09682121774797e-06, "loss": 0.7525, "step": 171850 }, { "epoch": 14.28, "learning_rate": 2.096710362220436e-06, "loss": 0.7826, "step": 171860 }, { "epoch": 14.29, "learning_rate": 2.0965995066929027e-06, "loss": 0.6935, "step": 171870 }, { "epoch": 14.29, "learning_rate": 2.0964886511653685e-06, "loss": 0.7986, "step": 171880 }, { "epoch": 14.29, "learning_rate": 2.096377795637835e-06, "loss": 0.7904, "step": 171890 }, { "epoch": 14.29, "learning_rate": 2.096266940110301e-06, "loss": 0.8054, "step": 171900 }, { "epoch": 14.29, "learning_rate": 2.0961560845827674e-06, "loss": 0.7676, "step": 171910 }, { "epoch": 14.29, "learning_rate": 2.0960452290552333e-06, "loss": 0.81, "step": 171920 }, { "epoch": 14.29, "learning_rate": 2.0959343735277e-06, "loss": 0.8015, "step": 171930 }, { "epoch": 14.29, "learning_rate": 2.095823518000166e-06, "loss": 0.855, "step": 171940 }, { "epoch": 14.29, "learning_rate": 2.0957126624726326e-06, "loss": 0.7757, "step": 171950 }, { "epoch": 14.29, "learning_rate": 2.095601806945099e-06, "loss": 0.7715, "step": 171960 }, { "epoch": 14.29, "learning_rate": 2.0954909514175648e-06, "loss": 0.7784, "step": 171970 }, { "epoch": 14.29, "learning_rate": 2.0953800958900315e-06, "loss": 0.78, "step": 171980 }, { "epoch": 14.3, "learning_rate": 2.0952692403624974e-06, "loss": 0.7689, "step": 171990 }, { "epoch": 14.3, "learning_rate": 2.0951583848349637e-06, "loss": 0.7937, "step": 172000 }, { "epoch": 14.3, "learning_rate": 2.09504752930743e-06, "loss": 0.8098, "step": 172010 }, { "epoch": 14.3, "learning_rate": 2.0949366737798963e-06, "loss": 0.7673, "step": 172020 }, { "epoch": 14.3, "learning_rate": 2.0948258182523626e-06, "loss": 0.7286, "step": 172030 }, { "epoch": 14.3, "learning_rate": 2.094714962724829e-06, "loss": 0.8527, "step": 172040 }, { "epoch": 14.3, "learning_rate": 2.0946041071972947e-06, "loss": 0.7659, "step": 172050 }, { "epoch": 14.3, "learning_rate": 2.0944932516697614e-06, "loss": 0.7969, "step": 172060 }, { "epoch": 14.3, "learning_rate": 2.0943823961422273e-06, "loss": 0.8016, "step": 172070 }, { "epoch": 14.3, "learning_rate": 2.0942715406146936e-06, "loss": 0.7938, "step": 172080 }, { "epoch": 14.3, "learning_rate": 2.0941606850871603e-06, "loss": 0.8067, "step": 172090 }, { "epoch": 14.3, "learning_rate": 2.094049829559626e-06, "loss": 0.7522, "step": 172100 }, { "epoch": 14.31, "learning_rate": 2.093938974032093e-06, "loss": 0.7732, "step": 172110 }, { "epoch": 14.31, "learning_rate": 2.093828118504559e-06, "loss": 0.7817, "step": 172120 }, { "epoch": 14.31, "learning_rate": 2.093717262977025e-06, "loss": 0.7006, "step": 172130 }, { "epoch": 14.31, "learning_rate": 2.0936064074494914e-06, "loss": 0.8225, "step": 172140 }, { "epoch": 14.31, "learning_rate": 2.0934955519219577e-06, "loss": 0.7997, "step": 172150 }, { "epoch": 14.31, "learning_rate": 2.0933846963944235e-06, "loss": 0.7405, "step": 172160 }, { "epoch": 14.31, "learning_rate": 2.0932738408668903e-06, "loss": 0.7915, "step": 172170 }, { "epoch": 14.31, "learning_rate": 2.093162985339356e-06, "loss": 0.7422, "step": 172180 }, { "epoch": 14.31, "learning_rate": 2.093052129811823e-06, "loss": 0.8319, "step": 172190 }, { "epoch": 14.31, "learning_rate": 2.092941274284289e-06, "loss": 0.7607, "step": 172200 }, { "epoch": 14.31, "learning_rate": 2.092830418756755e-06, "loss": 0.7672, "step": 172210 }, { "epoch": 14.31, "learning_rate": 2.0927195632292217e-06, "loss": 0.7339, "step": 172220 }, { "epoch": 14.32, "learning_rate": 2.0926087077016876e-06, "loss": 0.761, "step": 172230 }, { "epoch": 14.32, "learning_rate": 2.092497852174154e-06, "loss": 0.8752, "step": 172240 }, { "epoch": 14.32, "learning_rate": 2.09238699664662e-06, "loss": 0.7987, "step": 172250 }, { "epoch": 14.32, "learning_rate": 2.0922761411190865e-06, "loss": 0.8531, "step": 172260 }, { "epoch": 14.32, "learning_rate": 2.092165285591553e-06, "loss": 0.7836, "step": 172270 }, { "epoch": 14.32, "learning_rate": 2.092054430064019e-06, "loss": 0.7394, "step": 172280 }, { "epoch": 14.32, "learning_rate": 2.091943574536485e-06, "loss": 0.825, "step": 172290 }, { "epoch": 14.32, "learning_rate": 2.0918327190089517e-06, "loss": 0.7467, "step": 172300 }, { "epoch": 14.32, "learning_rate": 2.0917218634814176e-06, "loss": 0.7692, "step": 172310 }, { "epoch": 14.32, "learning_rate": 2.091611007953884e-06, "loss": 0.7527, "step": 172320 }, { "epoch": 14.32, "learning_rate": 2.0915001524263506e-06, "loss": 0.7221, "step": 172330 }, { "epoch": 14.32, "learning_rate": 2.0913892968988164e-06, "loss": 0.8354, "step": 172340 }, { "epoch": 14.33, "learning_rate": 2.091278441371283e-06, "loss": 0.8416, "step": 172350 }, { "epoch": 14.33, "learning_rate": 2.091167585843749e-06, "loss": 0.7058, "step": 172360 }, { "epoch": 14.33, "learning_rate": 2.0910567303162153e-06, "loss": 0.7719, "step": 172370 }, { "epoch": 14.33, "learning_rate": 2.0909458747886816e-06, "loss": 0.7473, "step": 172380 }, { "epoch": 14.33, "learning_rate": 2.090835019261148e-06, "loss": 0.8029, "step": 172390 }, { "epoch": 14.33, "learning_rate": 2.090724163733614e-06, "loss": 0.8269, "step": 172400 }, { "epoch": 14.33, "learning_rate": 2.0906133082060805e-06, "loss": 0.7304, "step": 172410 }, { "epoch": 14.33, "learning_rate": 2.0905024526785464e-06, "loss": 0.7712, "step": 172420 }, { "epoch": 14.33, "learning_rate": 2.0903915971510127e-06, "loss": 0.8358, "step": 172430 }, { "epoch": 14.33, "learning_rate": 2.090280741623479e-06, "loss": 0.8896, "step": 172440 }, { "epoch": 14.33, "learning_rate": 2.0901698860959453e-06, "loss": 0.7094, "step": 172450 }, { "epoch": 14.33, "learning_rate": 2.090059030568412e-06, "loss": 0.8142, "step": 172460 }, { "epoch": 14.34, "learning_rate": 2.089948175040878e-06, "loss": 0.7668, "step": 172470 }, { "epoch": 14.34, "learning_rate": 2.089837319513344e-06, "loss": 0.814, "step": 172480 }, { "epoch": 14.34, "learning_rate": 2.0897264639858104e-06, "loss": 0.8016, "step": 172490 }, { "epoch": 14.34, "learning_rate": 2.0896156084582767e-06, "loss": 0.7914, "step": 172500 }, { "epoch": 14.34, "learning_rate": 2.0895047529307426e-06, "loss": 0.7617, "step": 172510 }, { "epoch": 14.34, "learning_rate": 2.0893938974032093e-06, "loss": 0.7605, "step": 172520 }, { "epoch": 14.34, "learning_rate": 2.089283041875675e-06, "loss": 0.7387, "step": 172530 }, { "epoch": 14.34, "learning_rate": 2.089172186348142e-06, "loss": 0.7793, "step": 172540 }, { "epoch": 14.34, "learning_rate": 2.089061330820608e-06, "loss": 0.7833, "step": 172550 }, { "epoch": 14.34, "learning_rate": 2.088950475293074e-06, "loss": 0.7635, "step": 172560 }, { "epoch": 14.34, "learning_rate": 2.088839619765541e-06, "loss": 0.7398, "step": 172570 }, { "epoch": 14.34, "learning_rate": 2.0887287642380067e-06, "loss": 0.8628, "step": 172580 }, { "epoch": 14.35, "learning_rate": 2.088617908710473e-06, "loss": 0.7624, "step": 172590 }, { "epoch": 14.35, "learning_rate": 2.0885070531829393e-06, "loss": 0.7819, "step": 172600 }, { "epoch": 14.35, "learning_rate": 2.0883961976554056e-06, "loss": 0.7283, "step": 172610 }, { "epoch": 14.35, "learning_rate": 2.088285342127872e-06, "loss": 0.8117, "step": 172620 }, { "epoch": 14.35, "learning_rate": 2.088174486600338e-06, "loss": 0.7234, "step": 172630 }, { "epoch": 14.35, "learning_rate": 2.088063631072804e-06, "loss": 0.7913, "step": 172640 }, { "epoch": 14.35, "learning_rate": 2.0879527755452707e-06, "loss": 0.7461, "step": 172650 }, { "epoch": 14.35, "learning_rate": 2.0878419200177366e-06, "loss": 0.7742, "step": 172660 }, { "epoch": 14.35, "learning_rate": 2.087731064490203e-06, "loss": 0.7896, "step": 172670 }, { "epoch": 14.35, "learning_rate": 2.0876202089626692e-06, "loss": 0.7835, "step": 172680 }, { "epoch": 14.35, "learning_rate": 2.0875093534351355e-06, "loss": 0.7747, "step": 172690 }, { "epoch": 14.35, "learning_rate": 2.0873984979076022e-06, "loss": 0.785, "step": 172700 }, { "epoch": 14.36, "learning_rate": 2.087287642380068e-06, "loss": 0.7535, "step": 172710 }, { "epoch": 14.36, "learning_rate": 2.0871767868525344e-06, "loss": 0.7694, "step": 172720 }, { "epoch": 14.36, "learning_rate": 2.0870659313250007e-06, "loss": 0.7632, "step": 172730 }, { "epoch": 14.36, "learning_rate": 2.086955075797467e-06, "loss": 0.7988, "step": 172740 }, { "epoch": 14.36, "learning_rate": 2.086844220269933e-06, "loss": 0.8088, "step": 172750 }, { "epoch": 14.36, "learning_rate": 2.0867333647423996e-06, "loss": 0.7488, "step": 172760 }, { "epoch": 14.36, "learning_rate": 2.0866225092148654e-06, "loss": 0.8488, "step": 172770 }, { "epoch": 14.36, "learning_rate": 2.0865116536873317e-06, "loss": 0.7458, "step": 172780 }, { "epoch": 14.36, "learning_rate": 2.086400798159798e-06, "loss": 0.8845, "step": 172790 }, { "epoch": 14.36, "learning_rate": 2.0862899426322643e-06, "loss": 0.7949, "step": 172800 }, { "epoch": 14.36, "learning_rate": 2.0861790871047306e-06, "loss": 0.7531, "step": 172810 }, { "epoch": 14.36, "learning_rate": 2.086068231577197e-06, "loss": 0.7884, "step": 172820 }, { "epoch": 14.37, "learning_rate": 2.0859573760496632e-06, "loss": 0.7434, "step": 172830 }, { "epoch": 14.37, "learning_rate": 2.0858465205221295e-06, "loss": 0.8239, "step": 172840 }, { "epoch": 14.37, "learning_rate": 2.085735664994596e-06, "loss": 0.8092, "step": 172850 }, { "epoch": 14.37, "learning_rate": 2.0856248094670617e-06, "loss": 0.8483, "step": 172860 }, { "epoch": 14.37, "learning_rate": 2.0855139539395284e-06, "loss": 0.7288, "step": 172870 }, { "epoch": 14.37, "learning_rate": 2.0854030984119943e-06, "loss": 0.7691, "step": 172880 }, { "epoch": 14.37, "learning_rate": 2.085292242884461e-06, "loss": 0.7661, "step": 172890 }, { "epoch": 14.37, "learning_rate": 2.085181387356927e-06, "loss": 0.7975, "step": 172900 }, { "epoch": 14.37, "learning_rate": 2.085070531829393e-06, "loss": 0.8125, "step": 172910 }, { "epoch": 14.37, "learning_rate": 2.0849596763018595e-06, "loss": 0.7804, "step": 172920 }, { "epoch": 14.37, "learning_rate": 2.0848488207743257e-06, "loss": 0.7607, "step": 172930 }, { "epoch": 14.37, "learning_rate": 2.084737965246792e-06, "loss": 0.8199, "step": 172940 }, { "epoch": 14.38, "learning_rate": 2.0846271097192583e-06, "loss": 0.7709, "step": 172950 }, { "epoch": 14.38, "learning_rate": 2.0845162541917246e-06, "loss": 0.812, "step": 172960 }, { "epoch": 14.38, "learning_rate": 2.084405398664191e-06, "loss": 0.7399, "step": 172970 }, { "epoch": 14.38, "learning_rate": 2.0842945431366572e-06, "loss": 0.7619, "step": 172980 }, { "epoch": 14.38, "learning_rate": 2.084183687609123e-06, "loss": 0.8071, "step": 172990 }, { "epoch": 14.38, "learning_rate": 2.08407283208159e-06, "loss": 0.7543, "step": 173000 }, { "epoch": 14.38, "learning_rate": 2.0839619765540557e-06, "loss": 0.7184, "step": 173010 }, { "epoch": 14.38, "learning_rate": 2.083851121026522e-06, "loss": 0.7541, "step": 173020 }, { "epoch": 14.38, "learning_rate": 2.0837402654989883e-06, "loss": 0.7979, "step": 173030 }, { "epoch": 14.38, "learning_rate": 2.0836294099714546e-06, "loss": 0.7851, "step": 173040 }, { "epoch": 14.38, "learning_rate": 2.083518554443921e-06, "loss": 0.8358, "step": 173050 }, { "epoch": 14.38, "learning_rate": 2.083407698916387e-06, "loss": 0.8198, "step": 173060 }, { "epoch": 14.39, "learning_rate": 2.0832968433888535e-06, "loss": 0.787, "step": 173070 }, { "epoch": 14.39, "learning_rate": 2.0831859878613198e-06, "loss": 0.8067, "step": 173080 }, { "epoch": 14.39, "learning_rate": 2.083075132333786e-06, "loss": 0.7833, "step": 173090 }, { "epoch": 14.39, "learning_rate": 2.082964276806252e-06, "loss": 0.7638, "step": 173100 }, { "epoch": 14.39, "learning_rate": 2.0828534212787186e-06, "loss": 0.7901, "step": 173110 }, { "epoch": 14.39, "learning_rate": 2.0827425657511845e-06, "loss": 0.7902, "step": 173120 }, { "epoch": 14.39, "learning_rate": 2.0826317102236512e-06, "loss": 0.7457, "step": 173130 }, { "epoch": 14.39, "learning_rate": 2.082520854696117e-06, "loss": 0.7821, "step": 173140 }, { "epoch": 14.39, "learning_rate": 2.0824099991685834e-06, "loss": 0.779, "step": 173150 }, { "epoch": 14.39, "learning_rate": 2.0822991436410497e-06, "loss": 0.7105, "step": 173160 }, { "epoch": 14.39, "learning_rate": 2.082188288113516e-06, "loss": 0.7072, "step": 173170 }, { "epoch": 14.39, "learning_rate": 2.082077432585982e-06, "loss": 0.7621, "step": 173180 }, { "epoch": 14.4, "learning_rate": 2.0819665770584486e-06, "loss": 0.7979, "step": 173190 }, { "epoch": 14.4, "learning_rate": 2.081855721530915e-06, "loss": 0.8084, "step": 173200 }, { "epoch": 14.4, "learning_rate": 2.0817448660033807e-06, "loss": 0.7879, "step": 173210 }, { "epoch": 14.4, "learning_rate": 2.0816340104758475e-06, "loss": 0.7082, "step": 173220 }, { "epoch": 14.4, "learning_rate": 2.0815231549483133e-06, "loss": 0.7976, "step": 173230 }, { "epoch": 14.4, "learning_rate": 2.08141229942078e-06, "loss": 0.8029, "step": 173240 }, { "epoch": 14.4, "learning_rate": 2.081301443893246e-06, "loss": 0.7843, "step": 173250 }, { "epoch": 14.4, "learning_rate": 2.0811905883657122e-06, "loss": 0.8332, "step": 173260 }, { "epoch": 14.4, "learning_rate": 2.0810797328381785e-06, "loss": 0.8242, "step": 173270 }, { "epoch": 14.4, "learning_rate": 2.080968877310645e-06, "loss": 0.7746, "step": 173280 }, { "epoch": 14.4, "learning_rate": 2.0808580217831107e-06, "loss": 0.7894, "step": 173290 }, { "epoch": 14.4, "learning_rate": 2.0807471662555774e-06, "loss": 0.7879, "step": 173300 }, { "epoch": 14.41, "learning_rate": 2.0806363107280437e-06, "loss": 0.7971, "step": 173310 }, { "epoch": 14.41, "learning_rate": 2.08052545520051e-06, "loss": 0.7309, "step": 173320 }, { "epoch": 14.41, "learning_rate": 2.0804145996729763e-06, "loss": 0.7874, "step": 173330 }, { "epoch": 14.41, "learning_rate": 2.080303744145442e-06, "loss": 0.7736, "step": 173340 }, { "epoch": 14.41, "learning_rate": 2.080192888617909e-06, "loss": 0.751, "step": 173350 }, { "epoch": 14.41, "learning_rate": 2.0800820330903748e-06, "loss": 0.7689, "step": 173360 }, { "epoch": 14.41, "learning_rate": 2.079971177562841e-06, "loss": 0.7635, "step": 173370 }, { "epoch": 14.41, "learning_rate": 2.0798603220353073e-06, "loss": 0.7687, "step": 173380 }, { "epoch": 14.41, "learning_rate": 2.0797494665077736e-06, "loss": 0.8344, "step": 173390 }, { "epoch": 14.41, "learning_rate": 2.07963861098024e-06, "loss": 0.7173, "step": 173400 }, { "epoch": 14.41, "learning_rate": 2.0795277554527062e-06, "loss": 0.8165, "step": 173410 }, { "epoch": 14.41, "learning_rate": 2.079416899925172e-06, "loss": 0.7771, "step": 173420 }, { "epoch": 14.42, "learning_rate": 2.079306044397639e-06, "loss": 0.7463, "step": 173430 }, { "epoch": 14.42, "learning_rate": 2.079195188870105e-06, "loss": 0.7604, "step": 173440 }, { "epoch": 14.42, "learning_rate": 2.079084333342571e-06, "loss": 0.7023, "step": 173450 }, { "epoch": 14.42, "learning_rate": 2.0789734778150377e-06, "loss": 0.7979, "step": 173460 }, { "epoch": 14.42, "learning_rate": 2.0788626222875036e-06, "loss": 0.7572, "step": 173470 }, { "epoch": 14.42, "learning_rate": 2.0787517667599703e-06, "loss": 0.7926, "step": 173480 }, { "epoch": 14.42, "learning_rate": 2.078640911232436e-06, "loss": 0.8484, "step": 173490 }, { "epoch": 14.42, "learning_rate": 2.0785300557049025e-06, "loss": 0.8338, "step": 173500 }, { "epoch": 14.42, "learning_rate": 2.0784192001773688e-06, "loss": 0.7871, "step": 173510 }, { "epoch": 14.42, "learning_rate": 2.078308344649835e-06, "loss": 0.8005, "step": 173520 }, { "epoch": 14.42, "learning_rate": 2.078197489122301e-06, "loss": 0.8179, "step": 173530 }, { "epoch": 14.42, "learning_rate": 2.0780866335947676e-06, "loss": 0.8232, "step": 173540 }, { "epoch": 14.43, "learning_rate": 2.0779757780672335e-06, "loss": 0.7924, "step": 173550 }, { "epoch": 14.43, "learning_rate": 2.0778649225397002e-06, "loss": 0.8484, "step": 173560 }, { "epoch": 14.43, "learning_rate": 2.0777540670121665e-06, "loss": 0.7595, "step": 173570 }, { "epoch": 14.43, "learning_rate": 2.0776432114846324e-06, "loss": 0.7757, "step": 173580 }, { "epoch": 14.43, "learning_rate": 2.077532355957099e-06, "loss": 0.857, "step": 173590 }, { "epoch": 14.43, "learning_rate": 2.077421500429565e-06, "loss": 0.7924, "step": 173600 }, { "epoch": 14.43, "learning_rate": 2.0773106449020313e-06, "loss": 0.7478, "step": 173610 }, { "epoch": 14.43, "learning_rate": 2.0771997893744976e-06, "loss": 0.7643, "step": 173620 }, { "epoch": 14.43, "learning_rate": 2.077088933846964e-06, "loss": 0.771, "step": 173630 }, { "epoch": 14.43, "learning_rate": 2.0769780783194298e-06, "loss": 0.8116, "step": 173640 }, { "epoch": 14.43, "learning_rate": 2.0768672227918965e-06, "loss": 0.7454, "step": 173650 }, { "epoch": 14.43, "learning_rate": 2.0767563672643623e-06, "loss": 0.732, "step": 173660 }, { "epoch": 14.44, "learning_rate": 2.076645511736829e-06, "loss": 0.8236, "step": 173670 }, { "epoch": 14.44, "learning_rate": 2.0765346562092954e-06, "loss": 0.8409, "step": 173680 }, { "epoch": 14.44, "learning_rate": 2.076434886234515e-06, "loss": 0.8264, "step": 173690 }, { "epoch": 14.44, "learning_rate": 2.0763240307069808e-06, "loss": 0.7501, "step": 173700 }, { "epoch": 14.44, "learning_rate": 2.0762131751794475e-06, "loss": 0.7845, "step": 173710 }, { "epoch": 14.44, "learning_rate": 2.0761023196519134e-06, "loss": 0.771, "step": 173720 }, { "epoch": 14.44, "learning_rate": 2.0759914641243797e-06, "loss": 0.799, "step": 173730 }, { "epoch": 14.44, "learning_rate": 2.075880608596846e-06, "loss": 0.8152, "step": 173740 }, { "epoch": 14.44, "learning_rate": 2.0757697530693122e-06, "loss": 0.7237, "step": 173750 }, { "epoch": 14.44, "learning_rate": 2.0756588975417785e-06, "loss": 0.7881, "step": 173760 }, { "epoch": 14.44, "learning_rate": 2.075548042014245e-06, "loss": 0.7435, "step": 173770 }, { "epoch": 14.44, "learning_rate": 2.075437186486711e-06, "loss": 0.7994, "step": 173780 }, { "epoch": 14.45, "learning_rate": 2.0753263309591774e-06, "loss": 0.8329, "step": 173790 }, { "epoch": 14.45, "learning_rate": 2.0752154754316437e-06, "loss": 0.8137, "step": 173800 }, { "epoch": 14.45, "learning_rate": 2.0751046199041096e-06, "loss": 0.7569, "step": 173810 }, { "epoch": 14.45, "learning_rate": 2.0749937643765763e-06, "loss": 0.8401, "step": 173820 }, { "epoch": 14.45, "learning_rate": 2.074882908849042e-06, "loss": 0.711, "step": 173830 }, { "epoch": 14.45, "learning_rate": 2.074772053321509e-06, "loss": 0.7922, "step": 173840 }, { "epoch": 14.45, "learning_rate": 2.0746611977939748e-06, "loss": 0.7697, "step": 173850 }, { "epoch": 14.45, "learning_rate": 2.074550342266441e-06, "loss": 0.7364, "step": 173860 }, { "epoch": 14.45, "learning_rate": 2.0744394867389074e-06, "loss": 0.752, "step": 173870 }, { "epoch": 14.45, "learning_rate": 2.0743286312113737e-06, "loss": 0.8035, "step": 173880 }, { "epoch": 14.45, "learning_rate": 2.07421777568384e-06, "loss": 0.804, "step": 173890 }, { "epoch": 14.45, "learning_rate": 2.0741069201563063e-06, "loss": 0.801, "step": 173900 }, { "epoch": 14.46, "learning_rate": 2.0739960646287725e-06, "loss": 0.6792, "step": 173910 }, { "epoch": 14.46, "learning_rate": 2.073885209101239e-06, "loss": 0.7506, "step": 173920 }, { "epoch": 14.46, "learning_rate": 2.073774353573705e-06, "loss": 0.7153, "step": 173930 }, { "epoch": 14.46, "learning_rate": 2.073663498046171e-06, "loss": 0.8332, "step": 173940 }, { "epoch": 14.46, "learning_rate": 2.0735526425186377e-06, "loss": 0.7966, "step": 173950 }, { "epoch": 14.46, "learning_rate": 2.0734417869911036e-06, "loss": 0.7062, "step": 173960 }, { "epoch": 14.46, "learning_rate": 2.07333093146357e-06, "loss": 0.8524, "step": 173970 }, { "epoch": 14.46, "learning_rate": 2.073220075936036e-06, "loss": 0.7597, "step": 173980 }, { "epoch": 14.46, "learning_rate": 2.0731092204085025e-06, "loss": 0.8644, "step": 173990 }, { "epoch": 14.46, "learning_rate": 2.0729983648809688e-06, "loss": 0.7825, "step": 174000 }, { "epoch": 14.46, "learning_rate": 2.072887509353435e-06, "loss": 0.7666, "step": 174010 }, { "epoch": 14.46, "learning_rate": 2.0727766538259014e-06, "loss": 0.7863, "step": 174020 }, { "epoch": 14.47, "learning_rate": 2.0726657982983677e-06, "loss": 0.7897, "step": 174030 }, { "epoch": 14.47, "learning_rate": 2.072554942770834e-06, "loss": 0.8667, "step": 174040 }, { "epoch": 14.47, "learning_rate": 2.0724440872433e-06, "loss": 0.7964, "step": 174050 }, { "epoch": 14.47, "learning_rate": 2.0723332317157666e-06, "loss": 0.7992, "step": 174060 }, { "epoch": 14.47, "learning_rate": 2.0722223761882324e-06, "loss": 0.825, "step": 174070 }, { "epoch": 14.47, "learning_rate": 2.072111520660699e-06, "loss": 0.7748, "step": 174080 }, { "epoch": 14.47, "learning_rate": 2.072000665133165e-06, "loss": 0.766, "step": 174090 }, { "epoch": 14.47, "learning_rate": 2.0718898096056313e-06, "loss": 0.7771, "step": 174100 }, { "epoch": 14.47, "learning_rate": 2.0717789540780976e-06, "loss": 0.7768, "step": 174110 }, { "epoch": 14.47, "learning_rate": 2.071668098550564e-06, "loss": 0.7412, "step": 174120 }, { "epoch": 14.47, "learning_rate": 2.0715572430230298e-06, "loss": 0.7041, "step": 174130 }, { "epoch": 14.47, "learning_rate": 2.0714463874954965e-06, "loss": 0.7545, "step": 174140 }, { "epoch": 14.48, "learning_rate": 2.0713355319679628e-06, "loss": 0.7759, "step": 174150 }, { "epoch": 14.48, "learning_rate": 2.0712246764404287e-06, "loss": 0.7457, "step": 174160 }, { "epoch": 14.48, "learning_rate": 2.0711138209128954e-06, "loss": 0.7563, "step": 174170 }, { "epoch": 14.48, "learning_rate": 2.0710029653853613e-06, "loss": 0.8354, "step": 174180 }, { "epoch": 14.48, "learning_rate": 2.070892109857828e-06, "loss": 0.7659, "step": 174190 }, { "epoch": 14.48, "learning_rate": 2.070781254330294e-06, "loss": 0.7451, "step": 174200 }, { "epoch": 14.48, "learning_rate": 2.07067039880276e-06, "loss": 0.8132, "step": 174210 }, { "epoch": 14.48, "learning_rate": 2.0705595432752264e-06, "loss": 0.735, "step": 174220 }, { "epoch": 14.48, "learning_rate": 2.0704486877476927e-06, "loss": 0.7415, "step": 174230 }, { "epoch": 14.48, "learning_rate": 2.0703378322201586e-06, "loss": 0.7999, "step": 174240 }, { "epoch": 14.48, "learning_rate": 2.0702269766926253e-06, "loss": 0.7308, "step": 174250 }, { "epoch": 14.48, "learning_rate": 2.0701161211650916e-06, "loss": 0.789, "step": 174260 }, { "epoch": 14.49, "learning_rate": 2.070005265637558e-06, "loss": 0.7438, "step": 174270 }, { "epoch": 14.49, "learning_rate": 2.069894410110024e-06, "loss": 0.7638, "step": 174280 }, { "epoch": 14.49, "learning_rate": 2.06978355458249e-06, "loss": 0.799, "step": 174290 }, { "epoch": 14.49, "learning_rate": 2.069672699054957e-06, "loss": 0.834, "step": 174300 }, { "epoch": 14.49, "learning_rate": 2.0695618435274227e-06, "loss": 0.7628, "step": 174310 }, { "epoch": 14.49, "learning_rate": 2.069450987999889e-06, "loss": 0.7818, "step": 174320 }, { "epoch": 14.49, "learning_rate": 2.0693401324723553e-06, "loss": 0.7957, "step": 174330 }, { "epoch": 14.49, "learning_rate": 2.0692292769448216e-06, "loss": 0.8153, "step": 174340 }, { "epoch": 14.49, "learning_rate": 2.069118421417288e-06, "loss": 0.7832, "step": 174350 }, { "epoch": 14.49, "learning_rate": 2.069007565889754e-06, "loss": 0.7569, "step": 174360 }, { "epoch": 14.49, "learning_rate": 2.06889671036222e-06, "loss": 0.7254, "step": 174370 }, { "epoch": 14.49, "learning_rate": 2.0687858548346867e-06, "loss": 0.7857, "step": 174380 }, { "epoch": 14.5, "learning_rate": 2.068674999307153e-06, "loss": 0.8116, "step": 174390 }, { "epoch": 14.5, "learning_rate": 2.068564143779619e-06, "loss": 0.8179, "step": 174400 }, { "epoch": 14.5, "learning_rate": 2.0684532882520856e-06, "loss": 0.7872, "step": 174410 }, { "epoch": 14.5, "learning_rate": 2.0683424327245515e-06, "loss": 0.8353, "step": 174420 }, { "epoch": 14.5, "learning_rate": 2.068231577197018e-06, "loss": 0.7378, "step": 174430 }, { "epoch": 14.5, "learning_rate": 2.068120721669484e-06, "loss": 0.8268, "step": 174440 }, { "epoch": 14.5, "learning_rate": 2.0680098661419504e-06, "loss": 0.7617, "step": 174450 }, { "epoch": 14.5, "learning_rate": 2.0678990106144167e-06, "loss": 0.787, "step": 174460 }, { "epoch": 14.5, "learning_rate": 2.067788155086883e-06, "loss": 0.7169, "step": 174470 }, { "epoch": 14.5, "learning_rate": 2.067677299559349e-06, "loss": 0.8113, "step": 174480 }, { "epoch": 14.5, "learning_rate": 2.0675664440318156e-06, "loss": 0.8353, "step": 174490 }, { "epoch": 14.5, "learning_rate": 2.067455588504282e-06, "loss": 0.7869, "step": 174500 }, { "epoch": 14.51, "learning_rate": 2.067344732976748e-06, "loss": 0.843, "step": 174510 }, { "epoch": 14.51, "learning_rate": 2.0672338774492144e-06, "loss": 0.7489, "step": 174520 }, { "epoch": 14.51, "learning_rate": 2.0671230219216803e-06, "loss": 0.7468, "step": 174530 }, { "epoch": 14.51, "learning_rate": 2.067012166394147e-06, "loss": 0.8164, "step": 174540 }, { "epoch": 14.51, "learning_rate": 2.066901310866613e-06, "loss": 0.7564, "step": 174550 }, { "epoch": 14.51, "learning_rate": 2.066790455339079e-06, "loss": 0.8257, "step": 174560 }, { "epoch": 14.51, "learning_rate": 2.0666795998115455e-06, "loss": 0.7929, "step": 174570 }, { "epoch": 14.51, "learning_rate": 2.066568744284012e-06, "loss": 0.8101, "step": 174580 }, { "epoch": 14.51, "learning_rate": 2.0664578887564777e-06, "loss": 0.8249, "step": 174590 }, { "epoch": 14.51, "learning_rate": 2.0663470332289444e-06, "loss": 0.8059, "step": 174600 }, { "epoch": 14.51, "learning_rate": 2.0662361777014103e-06, "loss": 0.7694, "step": 174610 }, { "epoch": 14.51, "learning_rate": 2.066125322173877e-06, "loss": 0.7242, "step": 174620 }, { "epoch": 14.52, "learning_rate": 2.0660144666463433e-06, "loss": 0.7661, "step": 174630 }, { "epoch": 14.52, "learning_rate": 2.065903611118809e-06, "loss": 0.8048, "step": 174640 }, { "epoch": 14.52, "learning_rate": 2.065792755591276e-06, "loss": 0.7304, "step": 174650 }, { "epoch": 14.52, "learning_rate": 2.0656819000637417e-06, "loss": 0.7403, "step": 174660 }, { "epoch": 14.52, "learning_rate": 2.065571044536208e-06, "loss": 0.7918, "step": 174670 }, { "epoch": 14.52, "learning_rate": 2.0654601890086743e-06, "loss": 0.7343, "step": 174680 }, { "epoch": 14.52, "learning_rate": 2.0653493334811406e-06, "loss": 0.763, "step": 174690 }, { "epoch": 14.52, "learning_rate": 2.065238477953607e-06, "loss": 0.7472, "step": 174700 }, { "epoch": 14.52, "learning_rate": 2.065127622426073e-06, "loss": 0.8315, "step": 174710 }, { "epoch": 14.52, "learning_rate": 2.065016766898539e-06, "loss": 0.8174, "step": 174720 }, { "epoch": 14.52, "learning_rate": 2.064905911371006e-06, "loss": 0.7504, "step": 174730 }, { "epoch": 14.52, "learning_rate": 2.0647950558434717e-06, "loss": 0.8101, "step": 174740 }, { "epoch": 14.52, "learning_rate": 2.064684200315938e-06, "loss": 0.7358, "step": 174750 }, { "epoch": 14.53, "learning_rate": 2.0645733447884047e-06, "loss": 0.7421, "step": 174760 }, { "epoch": 14.53, "learning_rate": 2.0644624892608706e-06, "loss": 0.7906, "step": 174770 }, { "epoch": 14.53, "learning_rate": 2.0643516337333373e-06, "loss": 0.7645, "step": 174780 }, { "epoch": 14.53, "learning_rate": 2.064240778205803e-06, "loss": 0.8343, "step": 174790 }, { "epoch": 14.53, "learning_rate": 2.0641299226782694e-06, "loss": 0.83, "step": 174800 }, { "epoch": 14.53, "learning_rate": 2.0640190671507357e-06, "loss": 0.7381, "step": 174810 }, { "epoch": 14.53, "learning_rate": 2.063908211623202e-06, "loss": 0.7181, "step": 174820 }, { "epoch": 14.53, "learning_rate": 2.063797356095668e-06, "loss": 0.7942, "step": 174830 }, { "epoch": 14.53, "learning_rate": 2.0636865005681346e-06, "loss": 0.8141, "step": 174840 }, { "epoch": 14.53, "learning_rate": 2.0635756450406005e-06, "loss": 0.7811, "step": 174850 }, { "epoch": 14.53, "learning_rate": 2.0634647895130672e-06, "loss": 0.701, "step": 174860 }, { "epoch": 14.53, "learning_rate": 2.0633539339855335e-06, "loss": 0.7998, "step": 174870 }, { "epoch": 14.54, "learning_rate": 2.0632430784579994e-06, "loss": 0.7959, "step": 174880 }, { "epoch": 14.54, "learning_rate": 2.063132222930466e-06, "loss": 0.8472, "step": 174890 }, { "epoch": 14.54, "learning_rate": 2.063021367402932e-06, "loss": 0.8362, "step": 174900 }, { "epoch": 14.54, "learning_rate": 2.0629105118753983e-06, "loss": 0.7295, "step": 174910 }, { "epoch": 14.54, "learning_rate": 2.0627996563478646e-06, "loss": 0.7898, "step": 174920 }, { "epoch": 14.54, "learning_rate": 2.062688800820331e-06, "loss": 0.737, "step": 174930 }, { "epoch": 14.54, "learning_rate": 2.0625779452927967e-06, "loss": 0.7913, "step": 174940 }, { "epoch": 14.54, "learning_rate": 2.0624670897652635e-06, "loss": 0.708, "step": 174950 }, { "epoch": 14.54, "learning_rate": 2.0623562342377293e-06, "loss": 0.7081, "step": 174960 }, { "epoch": 14.54, "learning_rate": 2.062245378710196e-06, "loss": 0.735, "step": 174970 }, { "epoch": 14.54, "learning_rate": 2.062134523182662e-06, "loss": 0.8824, "step": 174980 }, { "epoch": 14.54, "learning_rate": 2.062023667655128e-06, "loss": 0.793, "step": 174990 }, { "epoch": 14.55, "learning_rate": 2.061912812127595e-06, "loss": 0.7452, "step": 175000 }, { "epoch": 14.55, "learning_rate": 2.061801956600061e-06, "loss": 0.7876, "step": 175010 }, { "epoch": 14.55, "learning_rate": 2.061691101072527e-06, "loss": 0.7327, "step": 175020 }, { "epoch": 14.55, "learning_rate": 2.0615802455449934e-06, "loss": 0.7778, "step": 175030 }, { "epoch": 14.55, "learning_rate": 2.0614693900174597e-06, "loss": 0.8198, "step": 175040 }, { "epoch": 14.55, "learning_rate": 2.061358534489926e-06, "loss": 0.7245, "step": 175050 }, { "epoch": 14.55, "learning_rate": 2.0612476789623923e-06, "loss": 0.8124, "step": 175060 }, { "epoch": 14.55, "learning_rate": 2.061136823434858e-06, "loss": 0.735, "step": 175070 }, { "epoch": 14.55, "learning_rate": 2.061025967907325e-06, "loss": 0.7472, "step": 175080 }, { "epoch": 14.55, "learning_rate": 2.0609151123797907e-06, "loss": 0.766, "step": 175090 }, { "epoch": 14.55, "learning_rate": 2.060804256852257e-06, "loss": 0.823, "step": 175100 }, { "epoch": 14.55, "learning_rate": 2.0606934013247233e-06, "loss": 0.8197, "step": 175110 }, { "epoch": 14.56, "learning_rate": 2.0605825457971896e-06, "loss": 0.7288, "step": 175120 }, { "epoch": 14.56, "learning_rate": 2.0604716902696563e-06, "loss": 0.741, "step": 175130 }, { "epoch": 14.56, "learning_rate": 2.0603608347421222e-06, "loss": 0.8078, "step": 175140 }, { "epoch": 14.56, "learning_rate": 2.0602499792145885e-06, "loss": 0.7662, "step": 175150 }, { "epoch": 14.56, "learning_rate": 2.060139123687055e-06, "loss": 0.7383, "step": 175160 }, { "epoch": 14.56, "learning_rate": 2.060028268159521e-06, "loss": 0.8485, "step": 175170 }, { "epoch": 14.56, "learning_rate": 2.059917412631987e-06, "loss": 0.766, "step": 175180 }, { "epoch": 14.56, "learning_rate": 2.0598065571044537e-06, "loss": 0.8538, "step": 175190 }, { "epoch": 14.56, "learning_rate": 2.0596957015769196e-06, "loss": 0.7441, "step": 175200 }, { "epoch": 14.56, "learning_rate": 2.0595848460493863e-06, "loss": 0.8085, "step": 175210 }, { "epoch": 14.56, "learning_rate": 2.059473990521852e-06, "loss": 0.7824, "step": 175220 }, { "epoch": 14.56, "learning_rate": 2.0593631349943184e-06, "loss": 0.7891, "step": 175230 }, { "epoch": 14.57, "learning_rate": 2.059252279466785e-06, "loss": 0.8385, "step": 175240 }, { "epoch": 14.57, "learning_rate": 2.059141423939251e-06, "loss": 0.7458, "step": 175250 }, { "epoch": 14.57, "learning_rate": 2.0590305684117173e-06, "loss": 0.7203, "step": 175260 }, { "epoch": 14.57, "learning_rate": 2.0589197128841836e-06, "loss": 0.7289, "step": 175270 }, { "epoch": 14.57, "learning_rate": 2.05880885735665e-06, "loss": 0.7592, "step": 175280 }, { "epoch": 14.57, "learning_rate": 2.0586980018291162e-06, "loss": 0.8036, "step": 175290 }, { "epoch": 14.57, "learning_rate": 2.0585871463015825e-06, "loss": 0.8048, "step": 175300 }, { "epoch": 14.57, "learning_rate": 2.0584762907740484e-06, "loss": 0.7632, "step": 175310 }, { "epoch": 14.57, "learning_rate": 2.058365435246515e-06, "loss": 0.7292, "step": 175320 }, { "epoch": 14.57, "learning_rate": 2.058254579718981e-06, "loss": 0.742, "step": 175330 }, { "epoch": 14.57, "learning_rate": 2.0581437241914473e-06, "loss": 0.8412, "step": 175340 }, { "epoch": 14.57, "learning_rate": 2.0580328686639136e-06, "loss": 0.8449, "step": 175350 }, { "epoch": 14.58, "learning_rate": 2.05792201313638e-06, "loss": 0.8244, "step": 175360 }, { "epoch": 14.58, "learning_rate": 2.0578111576088466e-06, "loss": 0.7914, "step": 175370 }, { "epoch": 14.58, "learning_rate": 2.0577003020813125e-06, "loss": 0.7423, "step": 175380 }, { "epoch": 14.58, "learning_rate": 2.0575894465537788e-06, "loss": 0.7613, "step": 175390 }, { "epoch": 14.58, "learning_rate": 2.057478591026245e-06, "loss": 0.8105, "step": 175400 }, { "epoch": 14.58, "learning_rate": 2.0573677354987113e-06, "loss": 0.7829, "step": 175410 }, { "epoch": 14.58, "learning_rate": 2.0572568799711772e-06, "loss": 0.7919, "step": 175420 }, { "epoch": 14.58, "learning_rate": 2.057146024443644e-06, "loss": 0.7809, "step": 175430 }, { "epoch": 14.58, "learning_rate": 2.05703516891611e-06, "loss": 0.7979, "step": 175440 }, { "epoch": 14.58, "learning_rate": 2.056924313388576e-06, "loss": 0.7729, "step": 175450 }, { "epoch": 14.58, "learning_rate": 2.0568134578610424e-06, "loss": 0.7717, "step": 175460 }, { "epoch": 14.58, "learning_rate": 2.0567026023335087e-06, "loss": 0.7628, "step": 175470 }, { "epoch": 14.59, "learning_rate": 2.056591746805975e-06, "loss": 0.8026, "step": 175480 }, { "epoch": 14.59, "learning_rate": 2.0564808912784413e-06, "loss": 0.8132, "step": 175490 }, { "epoch": 14.59, "learning_rate": 2.0563700357509076e-06, "loss": 0.7548, "step": 175500 }, { "epoch": 14.59, "learning_rate": 2.056259180223374e-06, "loss": 0.7927, "step": 175510 }, { "epoch": 14.59, "learning_rate": 2.05614832469584e-06, "loss": 0.7567, "step": 175520 }, { "epoch": 14.59, "learning_rate": 2.056037469168306e-06, "loss": 0.7998, "step": 175530 }, { "epoch": 14.59, "learning_rate": 2.0559266136407728e-06, "loss": 0.7449, "step": 175540 }, { "epoch": 14.59, "learning_rate": 2.0558157581132386e-06, "loss": 0.7726, "step": 175550 }, { "epoch": 14.59, "learning_rate": 2.0557049025857053e-06, "loss": 0.8176, "step": 175560 }, { "epoch": 14.59, "learning_rate": 2.0555940470581712e-06, "loss": 0.7626, "step": 175570 }, { "epoch": 14.59, "learning_rate": 2.0554831915306375e-06, "loss": 0.8081, "step": 175580 }, { "epoch": 14.59, "learning_rate": 2.055372336003104e-06, "loss": 0.8595, "step": 175590 }, { "epoch": 14.6, "learning_rate": 2.05526148047557e-06, "loss": 0.7292, "step": 175600 }, { "epoch": 14.6, "learning_rate": 2.0551506249480364e-06, "loss": 0.8034, "step": 175610 }, { "epoch": 14.6, "learning_rate": 2.0550397694205027e-06, "loss": 0.8246, "step": 175620 }, { "epoch": 14.6, "learning_rate": 2.054928913892969e-06, "loss": 0.7492, "step": 175630 }, { "epoch": 14.6, "learning_rate": 2.0548180583654353e-06, "loss": 0.8713, "step": 175640 }, { "epoch": 14.6, "learning_rate": 2.0547072028379016e-06, "loss": 0.7796, "step": 175650 }, { "epoch": 14.6, "learning_rate": 2.0545963473103675e-06, "loss": 0.7307, "step": 175660 }, { "epoch": 14.6, "learning_rate": 2.054485491782834e-06, "loss": 0.7062, "step": 175670 }, { "epoch": 14.6, "learning_rate": 2.0543746362553e-06, "loss": 0.8353, "step": 175680 }, { "epoch": 14.6, "learning_rate": 2.0542637807277663e-06, "loss": 0.7611, "step": 175690 }, { "epoch": 14.6, "learning_rate": 2.0541529252002326e-06, "loss": 0.8048, "step": 175700 }, { "epoch": 14.6, "learning_rate": 2.054042069672699e-06, "loss": 0.8239, "step": 175710 }, { "epoch": 14.61, "learning_rate": 2.053931214145165e-06, "loss": 0.7781, "step": 175720 }, { "epoch": 14.61, "learning_rate": 2.0538203586176315e-06, "loss": 0.773, "step": 175730 }, { "epoch": 14.61, "learning_rate": 2.053709503090098e-06, "loss": 0.7702, "step": 175740 }, { "epoch": 14.61, "learning_rate": 2.053598647562564e-06, "loss": 0.7725, "step": 175750 }, { "epoch": 14.61, "learning_rate": 2.0534877920350304e-06, "loss": 0.7704, "step": 175760 }, { "epoch": 14.61, "learning_rate": 2.0533769365074963e-06, "loss": 0.8124, "step": 175770 }, { "epoch": 14.61, "learning_rate": 2.053266080979963e-06, "loss": 0.7471, "step": 175780 }, { "epoch": 14.61, "learning_rate": 2.053155225452429e-06, "loss": 0.8023, "step": 175790 }, { "epoch": 14.61, "learning_rate": 2.0530443699248956e-06, "loss": 0.7435, "step": 175800 }, { "epoch": 14.61, "learning_rate": 2.0529335143973615e-06, "loss": 0.7749, "step": 175810 }, { "epoch": 14.61, "learning_rate": 2.0528226588698278e-06, "loss": 0.7891, "step": 175820 }, { "epoch": 14.61, "learning_rate": 2.052711803342294e-06, "loss": 0.7359, "step": 175830 }, { "epoch": 14.62, "learning_rate": 2.0526009478147603e-06, "loss": 0.846, "step": 175840 }, { "epoch": 14.62, "learning_rate": 2.0524900922872262e-06, "loss": 0.745, "step": 175850 }, { "epoch": 14.62, "learning_rate": 2.052379236759693e-06, "loss": 0.7869, "step": 175860 }, { "epoch": 14.62, "learning_rate": 2.0522683812321592e-06, "loss": 0.7426, "step": 175870 }, { "epoch": 14.62, "learning_rate": 2.052157525704625e-06, "loss": 0.7861, "step": 175880 }, { "epoch": 14.62, "learning_rate": 2.052046670177092e-06, "loss": 0.8049, "step": 175890 }, { "epoch": 14.62, "learning_rate": 2.0519358146495577e-06, "loss": 0.7709, "step": 175900 }, { "epoch": 14.62, "learning_rate": 2.0518249591220244e-06, "loss": 0.77, "step": 175910 }, { "epoch": 14.62, "learning_rate": 2.0517141035944903e-06, "loss": 0.7726, "step": 175920 }, { "epoch": 14.62, "learning_rate": 2.0516032480669566e-06, "loss": 0.7995, "step": 175930 }, { "epoch": 14.62, "learning_rate": 2.051492392539423e-06, "loss": 0.8227, "step": 175940 }, { "epoch": 14.62, "learning_rate": 2.051381537011889e-06, "loss": 0.8394, "step": 175950 }, { "epoch": 14.63, "learning_rate": 2.051270681484355e-06, "loss": 0.7479, "step": 175960 }, { "epoch": 14.63, "learning_rate": 2.0511598259568218e-06, "loss": 0.8163, "step": 175970 }, { "epoch": 14.63, "learning_rate": 2.051048970429288e-06, "loss": 0.8051, "step": 175980 }, { "epoch": 14.63, "learning_rate": 2.0509381149017544e-06, "loss": 0.7464, "step": 175990 }, { "epoch": 14.63, "learning_rate": 2.0508272593742206e-06, "loss": 0.7619, "step": 176000 }, { "epoch": 14.63, "learning_rate": 2.0507164038466865e-06, "loss": 0.7502, "step": 176010 }, { "epoch": 14.63, "learning_rate": 2.0506055483191532e-06, "loss": 0.7684, "step": 176020 }, { "epoch": 14.63, "learning_rate": 2.050494692791619e-06, "loss": 0.791, "step": 176030 }, { "epoch": 14.63, "learning_rate": 2.0503838372640854e-06, "loss": 0.7829, "step": 176040 }, { "epoch": 14.63, "learning_rate": 2.0502729817365517e-06, "loss": 0.7613, "step": 176050 }, { "epoch": 14.63, "learning_rate": 2.050162126209018e-06, "loss": 0.7856, "step": 176060 }, { "epoch": 14.63, "learning_rate": 2.0500512706814843e-06, "loss": 0.7796, "step": 176070 }, { "epoch": 14.64, "learning_rate": 2.0499404151539506e-06, "loss": 0.7919, "step": 176080 }, { "epoch": 14.64, "learning_rate": 2.0498295596264165e-06, "loss": 0.7981, "step": 176090 }, { "epoch": 14.64, "learning_rate": 2.049718704098883e-06, "loss": 0.7581, "step": 176100 }, { "epoch": 14.64, "learning_rate": 2.0496078485713495e-06, "loss": 0.8062, "step": 176110 }, { "epoch": 14.64, "learning_rate": 2.0494969930438153e-06, "loss": 0.7108, "step": 176120 }, { "epoch": 14.64, "learning_rate": 2.049386137516282e-06, "loss": 0.7929, "step": 176130 }, { "epoch": 14.64, "learning_rate": 2.049275281988748e-06, "loss": 0.7972, "step": 176140 }, { "epoch": 14.64, "learning_rate": 2.0491644264612147e-06, "loss": 0.8413, "step": 176150 }, { "epoch": 14.64, "learning_rate": 2.0490535709336805e-06, "loss": 0.7947, "step": 176160 }, { "epoch": 14.64, "learning_rate": 2.048942715406147e-06, "loss": 0.7966, "step": 176170 }, { "epoch": 14.64, "learning_rate": 2.048831859878613e-06, "loss": 0.7401, "step": 176180 }, { "epoch": 14.64, "learning_rate": 2.0487210043510794e-06, "loss": 0.8005, "step": 176190 }, { "epoch": 14.65, "learning_rate": 2.0486101488235453e-06, "loss": 0.6816, "step": 176200 }, { "epoch": 14.65, "learning_rate": 2.048499293296012e-06, "loss": 0.7224, "step": 176210 }, { "epoch": 14.65, "learning_rate": 2.048388437768478e-06, "loss": 0.7752, "step": 176220 }, { "epoch": 14.65, "learning_rate": 2.048277582240944e-06, "loss": 0.7664, "step": 176230 }, { "epoch": 14.65, "learning_rate": 2.048166726713411e-06, "loss": 0.8241, "step": 176240 }, { "epoch": 14.65, "learning_rate": 2.0480558711858768e-06, "loss": 0.8808, "step": 176250 }, { "epoch": 14.65, "learning_rate": 2.0479450156583435e-06, "loss": 0.8037, "step": 176260 }, { "epoch": 14.65, "learning_rate": 2.0478341601308094e-06, "loss": 0.7857, "step": 176270 }, { "epoch": 14.65, "learning_rate": 2.0477233046032756e-06, "loss": 0.8107, "step": 176280 }, { "epoch": 14.65, "learning_rate": 2.047612449075742e-06, "loss": 0.8523, "step": 176290 }, { "epoch": 14.65, "learning_rate": 2.0475015935482082e-06, "loss": 0.8598, "step": 176300 }, { "epoch": 14.65, "learning_rate": 2.047390738020674e-06, "loss": 0.8085, "step": 176310 }, { "epoch": 14.66, "learning_rate": 2.047279882493141e-06, "loss": 0.796, "step": 176320 }, { "epoch": 14.66, "learning_rate": 2.0471690269656067e-06, "loss": 0.8419, "step": 176330 }, { "epoch": 14.66, "learning_rate": 2.0470581714380734e-06, "loss": 0.841, "step": 176340 }, { "epoch": 14.66, "learning_rate": 2.0469473159105397e-06, "loss": 0.7768, "step": 176350 }, { "epoch": 14.66, "learning_rate": 2.0468475459357593e-06, "loss": 0.7502, "step": 176360 }, { "epoch": 14.66, "learning_rate": 2.046736690408225e-06, "loss": 0.8508, "step": 176370 }, { "epoch": 14.66, "learning_rate": 2.046625834880692e-06, "loss": 0.8161, "step": 176380 }, { "epoch": 14.66, "learning_rate": 2.0465149793531577e-06, "loss": 0.8324, "step": 176390 }, { "epoch": 14.66, "learning_rate": 2.046404123825624e-06, "loss": 0.7782, "step": 176400 }, { "epoch": 14.66, "learning_rate": 2.0462932682980903e-06, "loss": 0.7486, "step": 176410 }, { "epoch": 14.66, "learning_rate": 2.0461824127705566e-06, "loss": 0.7967, "step": 176420 }, { "epoch": 14.66, "learning_rate": 2.046071557243023e-06, "loss": 0.7795, "step": 176430 }, { "epoch": 14.67, "learning_rate": 2.045960701715489e-06, "loss": 0.7955, "step": 176440 }, { "epoch": 14.67, "learning_rate": 2.0458498461879555e-06, "loss": 0.769, "step": 176450 }, { "epoch": 14.67, "learning_rate": 2.0457389906604218e-06, "loss": 0.7789, "step": 176460 }, { "epoch": 14.67, "learning_rate": 2.045628135132888e-06, "loss": 0.7684, "step": 176470 }, { "epoch": 14.67, "learning_rate": 2.045517279605354e-06, "loss": 0.8086, "step": 176480 }, { "epoch": 14.67, "learning_rate": 2.0454064240778207e-06, "loss": 0.8262, "step": 176490 }, { "epoch": 14.67, "learning_rate": 2.0452955685502865e-06, "loss": 0.8279, "step": 176500 }, { "epoch": 14.67, "learning_rate": 2.0451847130227533e-06, "loss": 0.7916, "step": 176510 }, { "epoch": 14.67, "learning_rate": 2.045073857495219e-06, "loss": 0.7445, "step": 176520 }, { "epoch": 14.67, "learning_rate": 2.0449630019676854e-06, "loss": 0.7973, "step": 176530 }, { "epoch": 14.67, "learning_rate": 2.0448521464401517e-06, "loss": 0.8194, "step": 176540 }, { "epoch": 14.67, "learning_rate": 2.044741290912618e-06, "loss": 0.797, "step": 176550 }, { "epoch": 14.68, "learning_rate": 2.0446304353850843e-06, "loss": 0.8285, "step": 176560 }, { "epoch": 14.68, "learning_rate": 2.0445195798575506e-06, "loss": 0.6953, "step": 176570 }, { "epoch": 14.68, "learning_rate": 2.044408724330017e-06, "loss": 0.7833, "step": 176580 }, { "epoch": 14.68, "learning_rate": 2.044297868802483e-06, "loss": 0.8206, "step": 176590 }, { "epoch": 14.68, "learning_rate": 2.0441870132749495e-06, "loss": 0.7562, "step": 176600 }, { "epoch": 14.68, "learning_rate": 2.0440761577474154e-06, "loss": 0.801, "step": 176610 }, { "epoch": 14.68, "learning_rate": 2.043965302219882e-06, "loss": 0.724, "step": 176620 }, { "epoch": 14.68, "learning_rate": 2.043854446692348e-06, "loss": 0.721, "step": 176630 }, { "epoch": 14.68, "learning_rate": 2.0437435911648143e-06, "loss": 0.7788, "step": 176640 }, { "epoch": 14.68, "learning_rate": 2.0436327356372805e-06, "loss": 0.8392, "step": 176650 }, { "epoch": 14.68, "learning_rate": 2.043521880109747e-06, "loss": 0.7535, "step": 176660 }, { "epoch": 14.68, "learning_rate": 2.043411024582213e-06, "loss": 0.8437, "step": 176670 }, { "epoch": 14.69, "learning_rate": 2.0433001690546794e-06, "loss": 0.8531, "step": 176680 }, { "epoch": 14.69, "learning_rate": 2.0431893135271457e-06, "loss": 0.7975, "step": 176690 }, { "epoch": 14.69, "learning_rate": 2.043078457999612e-06, "loss": 0.8216, "step": 176700 }, { "epoch": 14.69, "learning_rate": 2.0429676024720783e-06, "loss": 0.7403, "step": 176710 }, { "epoch": 14.69, "learning_rate": 2.042856746944544e-06, "loss": 0.7269, "step": 176720 }, { "epoch": 14.69, "learning_rate": 2.042745891417011e-06, "loss": 0.7767, "step": 176730 }, { "epoch": 14.69, "learning_rate": 2.0426350358894768e-06, "loss": 0.785, "step": 176740 }, { "epoch": 14.69, "learning_rate": 2.0425241803619435e-06, "loss": 0.7127, "step": 176750 }, { "epoch": 14.69, "learning_rate": 2.0424133248344094e-06, "loss": 0.8189, "step": 176760 }, { "epoch": 14.69, "learning_rate": 2.0423024693068757e-06, "loss": 0.7822, "step": 176770 }, { "epoch": 14.69, "learning_rate": 2.042191613779342e-06, "loss": 0.7606, "step": 176780 }, { "epoch": 14.69, "learning_rate": 2.0420807582518083e-06, "loss": 0.7643, "step": 176790 }, { "epoch": 14.7, "learning_rate": 2.0419699027242746e-06, "loss": 0.7775, "step": 176800 }, { "epoch": 14.7, "learning_rate": 2.041859047196741e-06, "loss": 0.842, "step": 176810 }, { "epoch": 14.7, "learning_rate": 2.041748191669207e-06, "loss": 0.8131, "step": 176820 }, { "epoch": 14.7, "learning_rate": 2.041637336141673e-06, "loss": 0.7844, "step": 176830 }, { "epoch": 14.7, "learning_rate": 2.0415264806141397e-06, "loss": 0.8084, "step": 176840 }, { "epoch": 14.7, "learning_rate": 2.0414156250866056e-06, "loss": 0.7946, "step": 176850 }, { "epoch": 14.7, "learning_rate": 2.0413047695590723e-06, "loss": 0.7099, "step": 176860 }, { "epoch": 14.7, "learning_rate": 2.041193914031538e-06, "loss": 0.7657, "step": 176870 }, { "epoch": 14.7, "learning_rate": 2.0410830585040045e-06, "loss": 0.7937, "step": 176880 }, { "epoch": 14.7, "learning_rate": 2.040972202976471e-06, "loss": 0.7513, "step": 176890 }, { "epoch": 14.7, "learning_rate": 2.040861347448937e-06, "loss": 0.8381, "step": 176900 }, { "epoch": 14.7, "learning_rate": 2.040750491921403e-06, "loss": 0.7305, "step": 176910 }, { "epoch": 14.71, "learning_rate": 2.0406396363938697e-06, "loss": 0.8374, "step": 176920 }, { "epoch": 14.71, "learning_rate": 2.040528780866336e-06, "loss": 0.7293, "step": 176930 }, { "epoch": 14.71, "learning_rate": 2.0404179253388023e-06, "loss": 0.8041, "step": 176940 }, { "epoch": 14.71, "learning_rate": 2.0403070698112686e-06, "loss": 0.812, "step": 176950 }, { "epoch": 14.71, "learning_rate": 2.0401962142837344e-06, "loss": 0.7742, "step": 176960 }, { "epoch": 14.71, "learning_rate": 2.040085358756201e-06, "loss": 0.7689, "step": 176970 }, { "epoch": 14.71, "learning_rate": 2.039974503228667e-06, "loss": 0.7399, "step": 176980 }, { "epoch": 14.71, "learning_rate": 2.0398636477011333e-06, "loss": 0.7976, "step": 176990 }, { "epoch": 14.71, "learning_rate": 2.0397527921735996e-06, "loss": 0.7384, "step": 177000 }, { "epoch": 14.71, "learning_rate": 2.039641936646066e-06, "loss": 0.7481, "step": 177010 }, { "epoch": 14.71, "learning_rate": 2.039531081118532e-06, "loss": 0.751, "step": 177020 }, { "epoch": 14.71, "learning_rate": 2.0394202255909985e-06, "loss": 0.7577, "step": 177030 }, { "epoch": 14.72, "learning_rate": 2.0393093700634644e-06, "loss": 0.7851, "step": 177040 }, { "epoch": 14.72, "learning_rate": 2.039198514535931e-06, "loss": 0.8014, "step": 177050 }, { "epoch": 14.72, "learning_rate": 2.0390876590083974e-06, "loss": 0.7478, "step": 177060 }, { "epoch": 14.72, "learning_rate": 2.0389768034808633e-06, "loss": 0.7477, "step": 177070 }, { "epoch": 14.72, "learning_rate": 2.03886594795333e-06, "loss": 0.7471, "step": 177080 }, { "epoch": 14.72, "learning_rate": 2.038755092425796e-06, "loss": 0.82, "step": 177090 }, { "epoch": 14.72, "learning_rate": 2.0386442368982626e-06, "loss": 0.757, "step": 177100 }, { "epoch": 14.72, "learning_rate": 2.0385333813707284e-06, "loss": 0.7015, "step": 177110 }, { "epoch": 14.72, "learning_rate": 2.0384225258431947e-06, "loss": 0.7481, "step": 177120 }, { "epoch": 14.72, "learning_rate": 2.038311670315661e-06, "loss": 0.7379, "step": 177130 }, { "epoch": 14.72, "learning_rate": 2.0382008147881273e-06, "loss": 0.8365, "step": 177140 }, { "epoch": 14.72, "learning_rate": 2.038089959260593e-06, "loss": 0.7984, "step": 177150 }, { "epoch": 14.73, "learning_rate": 2.03797910373306e-06, "loss": 0.8493, "step": 177160 }, { "epoch": 14.73, "learning_rate": 2.0378682482055262e-06, "loss": 0.8086, "step": 177170 }, { "epoch": 14.73, "learning_rate": 2.037757392677992e-06, "loss": 0.8211, "step": 177180 }, { "epoch": 14.73, "learning_rate": 2.037646537150459e-06, "loss": 0.78, "step": 177190 }, { "epoch": 14.73, "learning_rate": 2.0375356816229247e-06, "loss": 0.7674, "step": 177200 }, { "epoch": 14.73, "learning_rate": 2.0374248260953914e-06, "loss": 0.7451, "step": 177210 }, { "epoch": 14.73, "learning_rate": 2.0373139705678573e-06, "loss": 0.7468, "step": 177220 }, { "epoch": 14.73, "learning_rate": 2.0372031150403236e-06, "loss": 0.8075, "step": 177230 }, { "epoch": 14.73, "learning_rate": 2.03709225951279e-06, "loss": 0.8077, "step": 177240 }, { "epoch": 14.73, "learning_rate": 2.036981403985256e-06, "loss": 0.7812, "step": 177250 }, { "epoch": 14.73, "learning_rate": 2.036870548457722e-06, "loss": 0.7328, "step": 177260 }, { "epoch": 14.73, "learning_rate": 2.0367596929301887e-06, "loss": 0.765, "step": 177270 }, { "epoch": 14.74, "learning_rate": 2.0366488374026546e-06, "loss": 0.7884, "step": 177280 }, { "epoch": 14.74, "learning_rate": 2.0365379818751213e-06, "loss": 0.8466, "step": 177290 }, { "epoch": 14.74, "learning_rate": 2.0364271263475876e-06, "loss": 0.7387, "step": 177300 }, { "epoch": 14.74, "learning_rate": 2.0363162708200535e-06, "loss": 0.8314, "step": 177310 }, { "epoch": 14.74, "learning_rate": 2.0362054152925202e-06, "loss": 0.7241, "step": 177320 }, { "epoch": 14.74, "learning_rate": 2.036094559764986e-06, "loss": 0.7404, "step": 177330 }, { "epoch": 14.74, "learning_rate": 2.0359837042374524e-06, "loss": 0.8397, "step": 177340 }, { "epoch": 14.74, "learning_rate": 2.0358728487099187e-06, "loss": 0.8789, "step": 177350 }, { "epoch": 14.74, "learning_rate": 2.035761993182385e-06, "loss": 0.8631, "step": 177360 }, { "epoch": 14.74, "learning_rate": 2.0356511376548513e-06, "loss": 0.7637, "step": 177370 }, { "epoch": 14.74, "learning_rate": 2.0355402821273176e-06, "loss": 0.7286, "step": 177380 }, { "epoch": 14.74, "learning_rate": 2.0354294265997834e-06, "loss": 0.8321, "step": 177390 }, { "epoch": 14.75, "learning_rate": 2.03531857107225e-06, "loss": 0.8285, "step": 177400 }, { "epoch": 14.75, "learning_rate": 2.035207715544716e-06, "loss": 0.819, "step": 177410 }, { "epoch": 14.75, "learning_rate": 2.0350968600171823e-06, "loss": 0.7422, "step": 177420 }, { "epoch": 14.75, "learning_rate": 2.034986004489649e-06, "loss": 0.7843, "step": 177430 }, { "epoch": 14.75, "learning_rate": 2.034875148962115e-06, "loss": 0.8135, "step": 177440 }, { "epoch": 14.75, "learning_rate": 2.0347642934345816e-06, "loss": 0.7599, "step": 177450 }, { "epoch": 14.75, "learning_rate": 2.0346534379070475e-06, "loss": 0.7477, "step": 177460 }, { "epoch": 14.75, "learning_rate": 2.034542582379514e-06, "loss": 0.7672, "step": 177470 }, { "epoch": 14.75, "learning_rate": 2.03443172685198e-06, "loss": 0.7831, "step": 177480 }, { "epoch": 14.75, "learning_rate": 2.0343208713244464e-06, "loss": 0.8267, "step": 177490 }, { "epoch": 14.75, "learning_rate": 2.0342100157969123e-06, "loss": 0.7886, "step": 177500 }, { "epoch": 14.75, "learning_rate": 2.034099160269379e-06, "loss": 0.7494, "step": 177510 }, { "epoch": 14.76, "learning_rate": 2.033988304741845e-06, "loss": 0.7424, "step": 177520 }, { "epoch": 14.76, "learning_rate": 2.0338774492143116e-06, "loss": 0.7873, "step": 177530 }, { "epoch": 14.76, "learning_rate": 2.033766593686778e-06, "loss": 0.856, "step": 177540 }, { "epoch": 14.76, "learning_rate": 2.0336557381592437e-06, "loss": 0.7462, "step": 177550 }, { "epoch": 14.76, "learning_rate": 2.0335448826317105e-06, "loss": 0.7536, "step": 177560 }, { "epoch": 14.76, "learning_rate": 2.0334340271041763e-06, "loss": 0.7686, "step": 177570 }, { "epoch": 14.76, "learning_rate": 2.0333231715766426e-06, "loss": 0.7381, "step": 177580 }, { "epoch": 14.76, "learning_rate": 2.033212316049109e-06, "loss": 0.8467, "step": 177590 }, { "epoch": 14.76, "learning_rate": 2.0331014605215752e-06, "loss": 0.7998, "step": 177600 }, { "epoch": 14.76, "learning_rate": 2.032990604994041e-06, "loss": 0.768, "step": 177610 }, { "epoch": 14.76, "learning_rate": 2.032879749466508e-06, "loss": 0.7999, "step": 177620 }, { "epoch": 14.76, "learning_rate": 2.0327688939389737e-06, "loss": 0.7472, "step": 177630 }, { "epoch": 14.77, "learning_rate": 2.0326580384114404e-06, "loss": 0.8086, "step": 177640 }, { "epoch": 14.77, "learning_rate": 2.0325471828839063e-06, "loss": 0.8315, "step": 177650 }, { "epoch": 14.77, "learning_rate": 2.0324363273563726e-06, "loss": 0.7722, "step": 177660 }, { "epoch": 14.77, "learning_rate": 2.0323254718288393e-06, "loss": 0.6664, "step": 177670 }, { "epoch": 14.77, "learning_rate": 2.032214616301305e-06, "loss": 0.8307, "step": 177680 }, { "epoch": 14.77, "learning_rate": 2.0321037607737715e-06, "loss": 0.7405, "step": 177690 }, { "epoch": 14.77, "learning_rate": 2.0319929052462377e-06, "loss": 0.791, "step": 177700 }, { "epoch": 14.77, "learning_rate": 2.031882049718704e-06, "loss": 0.7508, "step": 177710 }, { "epoch": 14.77, "learning_rate": 2.0317711941911703e-06, "loss": 0.7653, "step": 177720 }, { "epoch": 14.77, "learning_rate": 2.0316603386636366e-06, "loss": 0.794, "step": 177730 }, { "epoch": 14.77, "learning_rate": 2.0315494831361025e-06, "loss": 0.8415, "step": 177740 }, { "epoch": 14.77, "learning_rate": 2.0314386276085692e-06, "loss": 0.8171, "step": 177750 }, { "epoch": 14.78, "learning_rate": 2.031327772081035e-06, "loss": 0.7901, "step": 177760 }, { "epoch": 14.78, "learning_rate": 2.0312169165535014e-06, "loss": 0.757, "step": 177770 }, { "epoch": 14.78, "learning_rate": 2.0311060610259677e-06, "loss": 0.7937, "step": 177780 }, { "epoch": 14.78, "learning_rate": 2.030995205498434e-06, "loss": 0.8508, "step": 177790 }, { "epoch": 14.78, "learning_rate": 2.0308843499709007e-06, "loss": 0.7555, "step": 177800 }, { "epoch": 14.78, "learning_rate": 2.0307734944433666e-06, "loss": 0.6732, "step": 177810 }, { "epoch": 14.78, "learning_rate": 2.030662638915833e-06, "loss": 0.7984, "step": 177820 }, { "epoch": 14.78, "learning_rate": 2.030551783388299e-06, "loss": 0.7289, "step": 177830 }, { "epoch": 14.78, "learning_rate": 2.0304409278607655e-06, "loss": 0.8473, "step": 177840 }, { "epoch": 14.78, "learning_rate": 2.0303300723332313e-06, "loss": 0.7492, "step": 177850 }, { "epoch": 14.78, "learning_rate": 2.030219216805698e-06, "loss": 0.764, "step": 177860 }, { "epoch": 14.78, "learning_rate": 2.030108361278164e-06, "loss": 0.8259, "step": 177870 }, { "epoch": 14.79, "learning_rate": 2.0299975057506306e-06, "loss": 0.7721, "step": 177880 }, { "epoch": 14.79, "learning_rate": 2.0298866502230965e-06, "loss": 0.8105, "step": 177890 }, { "epoch": 14.79, "learning_rate": 2.029775794695563e-06, "loss": 0.7824, "step": 177900 }, { "epoch": 14.79, "learning_rate": 2.0296649391680295e-06, "loss": 0.6839, "step": 177910 }, { "epoch": 14.79, "learning_rate": 2.0295540836404954e-06, "loss": 0.7829, "step": 177920 }, { "epoch": 14.79, "learning_rate": 2.0294432281129617e-06, "loss": 0.7655, "step": 177930 }, { "epoch": 14.79, "learning_rate": 2.029332372585428e-06, "loss": 0.771, "step": 177940 }, { "epoch": 14.79, "learning_rate": 2.0292215170578943e-06, "loss": 0.7834, "step": 177950 }, { "epoch": 14.79, "learning_rate": 2.0291106615303606e-06, "loss": 0.7777, "step": 177960 }, { "epoch": 14.79, "learning_rate": 2.028999806002827e-06, "loss": 0.8624, "step": 177970 }, { "epoch": 14.79, "learning_rate": 2.0288889504752927e-06, "loss": 0.7072, "step": 177980 }, { "epoch": 14.79, "learning_rate": 2.0287780949477595e-06, "loss": 0.8582, "step": 177990 }, { "epoch": 14.8, "learning_rate": 2.0286672394202253e-06, "loss": 0.7602, "step": 178000 }, { "epoch": 14.8, "learning_rate": 2.0285563838926916e-06, "loss": 0.7813, "step": 178010 }, { "epoch": 14.8, "learning_rate": 2.028445528365158e-06, "loss": 0.756, "step": 178020 }, { "epoch": 14.8, "learning_rate": 2.0283346728376242e-06, "loss": 0.7713, "step": 178030 }, { "epoch": 14.8, "learning_rate": 2.028223817310091e-06, "loss": 0.836, "step": 178040 }, { "epoch": 14.8, "learning_rate": 2.028112961782557e-06, "loss": 0.7329, "step": 178050 }, { "epoch": 14.8, "learning_rate": 2.028002106255023e-06, "loss": 0.7934, "step": 178060 }, { "epoch": 14.8, "learning_rate": 2.0278912507274894e-06, "loss": 0.7823, "step": 178070 }, { "epoch": 14.8, "learning_rate": 2.0277803951999557e-06, "loss": 0.825, "step": 178080 }, { "epoch": 14.8, "learning_rate": 2.0276695396724216e-06, "loss": 0.7913, "step": 178090 }, { "epoch": 14.8, "learning_rate": 2.0275586841448883e-06, "loss": 0.7689, "step": 178100 }, { "epoch": 14.8, "learning_rate": 2.027447828617354e-06, "loss": 0.8026, "step": 178110 }, { "epoch": 14.81, "learning_rate": 2.0273369730898205e-06, "loss": 0.7966, "step": 178120 }, { "epoch": 14.81, "learning_rate": 2.0272261175622868e-06, "loss": 0.7404, "step": 178130 }, { "epoch": 14.81, "learning_rate": 2.027115262034753e-06, "loss": 0.815, "step": 178140 }, { "epoch": 14.81, "learning_rate": 2.0270044065072193e-06, "loss": 0.7293, "step": 178150 }, { "epoch": 14.81, "learning_rate": 2.0268935509796856e-06, "loss": 0.8005, "step": 178160 }, { "epoch": 14.81, "learning_rate": 2.026782695452152e-06, "loss": 0.7464, "step": 178170 }, { "epoch": 14.81, "learning_rate": 2.0266718399246182e-06, "loss": 0.7775, "step": 178180 }, { "epoch": 14.81, "learning_rate": 2.0265609843970845e-06, "loss": 0.8092, "step": 178190 }, { "epoch": 14.81, "learning_rate": 2.0264501288695504e-06, "loss": 0.7928, "step": 178200 }, { "epoch": 14.81, "learning_rate": 2.026339273342017e-06, "loss": 0.7412, "step": 178210 }, { "epoch": 14.81, "learning_rate": 2.026228417814483e-06, "loss": 0.7988, "step": 178220 }, { "epoch": 14.81, "learning_rate": 2.0261175622869497e-06, "loss": 0.7818, "step": 178230 }, { "epoch": 14.82, "learning_rate": 2.0260067067594156e-06, "loss": 0.7602, "step": 178240 }, { "epoch": 14.82, "learning_rate": 2.025895851231882e-06, "loss": 0.7907, "step": 178250 }, { "epoch": 14.82, "learning_rate": 2.025784995704348e-06, "loss": 0.7501, "step": 178260 }, { "epoch": 14.82, "learning_rate": 2.0256741401768145e-06, "loss": 0.7659, "step": 178270 }, { "epoch": 14.82, "learning_rate": 2.0255632846492808e-06, "loss": 0.7562, "step": 178280 }, { "epoch": 14.82, "learning_rate": 2.025452429121747e-06, "loss": 0.8142, "step": 178290 }, { "epoch": 14.82, "learning_rate": 2.0253415735942134e-06, "loss": 0.8073, "step": 178300 }, { "epoch": 14.82, "learning_rate": 2.0252307180666796e-06, "loss": 0.7658, "step": 178310 }, { "epoch": 14.82, "learning_rate": 2.025119862539146e-06, "loss": 0.7566, "step": 178320 }, { "epoch": 14.82, "learning_rate": 2.025009007011612e-06, "loss": 0.7948, "step": 178330 }, { "epoch": 14.82, "learning_rate": 2.0248981514840785e-06, "loss": 0.8624, "step": 178340 }, { "epoch": 14.82, "learning_rate": 2.0247872959565444e-06, "loss": 0.7687, "step": 178350 }, { "epoch": 14.83, "learning_rate": 2.0246764404290107e-06, "loss": 0.7795, "step": 178360 }, { "epoch": 14.83, "learning_rate": 2.024565584901477e-06, "loss": 0.7218, "step": 178370 }, { "epoch": 14.83, "learning_rate": 2.0244547293739433e-06, "loss": 0.7797, "step": 178380 }, { "epoch": 14.83, "learning_rate": 2.024343873846409e-06, "loss": 0.7686, "step": 178390 }, { "epoch": 14.83, "learning_rate": 2.024233018318876e-06, "loss": 0.7667, "step": 178400 }, { "epoch": 14.83, "learning_rate": 2.024122162791342e-06, "loss": 0.7934, "step": 178410 }, { "epoch": 14.83, "learning_rate": 2.0240113072638085e-06, "loss": 0.8063, "step": 178420 }, { "epoch": 14.83, "learning_rate": 2.0239004517362748e-06, "loss": 0.7428, "step": 178430 }, { "epoch": 14.83, "learning_rate": 2.0237895962087406e-06, "loss": 0.8128, "step": 178440 }, { "epoch": 14.83, "learning_rate": 2.0236787406812074e-06, "loss": 0.7701, "step": 178450 }, { "epoch": 14.83, "learning_rate": 2.0235678851536732e-06, "loss": 0.8081, "step": 178460 }, { "epoch": 14.83, "learning_rate": 2.0234570296261395e-06, "loss": 0.8007, "step": 178470 }, { "epoch": 14.84, "learning_rate": 2.023346174098606e-06, "loss": 0.7408, "step": 178480 }, { "epoch": 14.84, "learning_rate": 2.023235318571072e-06, "loss": 0.7939, "step": 178490 }, { "epoch": 14.84, "learning_rate": 2.0231244630435384e-06, "loss": 0.7918, "step": 178500 }, { "epoch": 14.84, "learning_rate": 2.0230136075160047e-06, "loss": 0.8323, "step": 178510 }, { "epoch": 14.84, "learning_rate": 2.0229027519884706e-06, "loss": 0.7845, "step": 178520 }, { "epoch": 14.84, "learning_rate": 2.0227918964609373e-06, "loss": 0.778, "step": 178530 }, { "epoch": 14.84, "learning_rate": 2.0226810409334036e-06, "loss": 0.6851, "step": 178540 }, { "epoch": 14.84, "learning_rate": 2.0225701854058695e-06, "loss": 0.753, "step": 178550 }, { "epoch": 14.84, "learning_rate": 2.022459329878336e-06, "loss": 0.797, "step": 178560 }, { "epoch": 14.84, "learning_rate": 2.022348474350802e-06, "loss": 0.7934, "step": 178570 }, { "epoch": 14.84, "learning_rate": 2.0222376188232688e-06, "loss": 0.8199, "step": 178580 }, { "epoch": 14.84, "learning_rate": 2.0221267632957346e-06, "loss": 0.8352, "step": 178590 }, { "epoch": 14.84, "learning_rate": 2.022015907768201e-06, "loss": 0.8025, "step": 178600 }, { "epoch": 14.85, "learning_rate": 2.0219050522406672e-06, "loss": 0.7958, "step": 178610 }, { "epoch": 14.85, "learning_rate": 2.0217941967131335e-06, "loss": 0.765, "step": 178620 }, { "epoch": 14.85, "learning_rate": 2.0216833411855994e-06, "loss": 0.7352, "step": 178630 }, { "epoch": 14.85, "learning_rate": 2.021572485658066e-06, "loss": 0.7633, "step": 178640 }, { "epoch": 14.85, "learning_rate": 2.0214616301305324e-06, "loss": 0.7911, "step": 178650 }, { "epoch": 14.85, "learning_rate": 2.0213507746029987e-06, "loss": 0.73, "step": 178660 }, { "epoch": 14.85, "learning_rate": 2.021239919075465e-06, "loss": 0.7951, "step": 178670 }, { "epoch": 14.85, "learning_rate": 2.021129063547931e-06, "loss": 0.7618, "step": 178680 }, { "epoch": 14.85, "learning_rate": 2.0210182080203976e-06, "loss": 0.7998, "step": 178690 }, { "epoch": 14.85, "learning_rate": 2.0209073524928635e-06, "loss": 0.8752, "step": 178700 }, { "epoch": 14.85, "learning_rate": 2.0207964969653298e-06, "loss": 0.7566, "step": 178710 }, { "epoch": 14.85, "learning_rate": 2.0206967269905493e-06, "loss": 0.7801, "step": 178720 }, { "epoch": 14.86, "learning_rate": 2.0205858714630156e-06, "loss": 0.7301, "step": 178730 }, { "epoch": 14.86, "learning_rate": 2.020475015935482e-06, "loss": 0.8702, "step": 178740 }, { "epoch": 14.86, "learning_rate": 2.0203641604079486e-06, "loss": 0.8239, "step": 178750 }, { "epoch": 14.86, "learning_rate": 2.0202533048804145e-06, "loss": 0.7895, "step": 178760 }, { "epoch": 14.86, "learning_rate": 2.0201424493528808e-06, "loss": 0.7515, "step": 178770 }, { "epoch": 14.86, "learning_rate": 2.020031593825347e-06, "loss": 0.7644, "step": 178780 }, { "epoch": 14.86, "learning_rate": 2.0199207382978134e-06, "loss": 0.7572, "step": 178790 }, { "epoch": 14.86, "learning_rate": 2.0198098827702792e-06, "loss": 0.7826, "step": 178800 }, { "epoch": 14.86, "learning_rate": 2.019699027242746e-06, "loss": 0.7444, "step": 178810 }, { "epoch": 14.86, "learning_rate": 2.019588171715212e-06, "loss": 0.7737, "step": 178820 }, { "epoch": 14.86, "learning_rate": 2.0194773161876786e-06, "loss": 0.7333, "step": 178830 }, { "epoch": 14.86, "learning_rate": 2.0193664606601444e-06, "loss": 0.793, "step": 178840 }, { "epoch": 14.87, "learning_rate": 2.0192556051326107e-06, "loss": 0.7626, "step": 178850 }, { "epoch": 14.87, "learning_rate": 2.0191447496050774e-06, "loss": 0.7473, "step": 178860 }, { "epoch": 14.87, "learning_rate": 2.0190338940775433e-06, "loss": 0.7686, "step": 178870 }, { "epoch": 14.87, "learning_rate": 2.0189230385500096e-06, "loss": 0.7269, "step": 178880 }, { "epoch": 14.87, "learning_rate": 2.018812183022476e-06, "loss": 0.8184, "step": 178890 }, { "epoch": 14.87, "learning_rate": 2.018701327494942e-06, "loss": 0.7067, "step": 178900 }, { "epoch": 14.87, "learning_rate": 2.0185904719674085e-06, "loss": 0.7236, "step": 178910 }, { "epoch": 14.87, "learning_rate": 2.0184796164398748e-06, "loss": 0.745, "step": 178920 }, { "epoch": 14.87, "learning_rate": 2.0183687609123407e-06, "loss": 0.7617, "step": 178930 }, { "epoch": 14.87, "learning_rate": 2.0182579053848074e-06, "loss": 0.8023, "step": 178940 }, { "epoch": 14.87, "learning_rate": 2.0181470498572732e-06, "loss": 0.8237, "step": 178950 }, { "epoch": 14.87, "learning_rate": 2.0180361943297395e-06, "loss": 0.778, "step": 178960 }, { "epoch": 14.88, "learning_rate": 2.017925338802206e-06, "loss": 0.7704, "step": 178970 }, { "epoch": 14.88, "learning_rate": 2.017814483274672e-06, "loss": 0.7725, "step": 178980 }, { "epoch": 14.88, "learning_rate": 2.017703627747139e-06, "loss": 0.8051, "step": 178990 }, { "epoch": 14.88, "learning_rate": 2.0175927722196047e-06, "loss": 0.7288, "step": 179000 }, { "epoch": 14.88, "learning_rate": 2.017481916692071e-06, "loss": 0.747, "step": 179010 }, { "epoch": 14.88, "learning_rate": 2.0173710611645373e-06, "loss": 0.7207, "step": 179020 }, { "epoch": 14.88, "learning_rate": 2.0172602056370036e-06, "loss": 0.7458, "step": 179030 }, { "epoch": 14.88, "learning_rate": 2.0171493501094695e-06, "loss": 0.8056, "step": 179040 }, { "epoch": 14.88, "learning_rate": 2.017038494581936e-06, "loss": 0.8147, "step": 179050 }, { "epoch": 14.88, "learning_rate": 2.016927639054402e-06, "loss": 0.7479, "step": 179060 }, { "epoch": 14.88, "learning_rate": 2.0168167835268684e-06, "loss": 0.7297, "step": 179070 }, { "epoch": 14.88, "learning_rate": 2.0167059279993347e-06, "loss": 0.7756, "step": 179080 }, { "epoch": 14.89, "learning_rate": 2.016595072471801e-06, "loss": 0.811, "step": 179090 }, { "epoch": 14.89, "learning_rate": 2.0164842169442677e-06, "loss": 0.7626, "step": 179100 }, { "epoch": 14.89, "learning_rate": 2.0163733614167336e-06, "loss": 0.7551, "step": 179110 }, { "epoch": 14.89, "learning_rate": 2.0162625058892e-06, "loss": 0.7748, "step": 179120 }, { "epoch": 14.89, "learning_rate": 2.016151650361666e-06, "loss": 0.7768, "step": 179130 }, { "epoch": 14.89, "learning_rate": 2.0160407948341324e-06, "loss": 0.846, "step": 179140 }, { "epoch": 14.89, "learning_rate": 2.0159299393065983e-06, "loss": 0.7855, "step": 179150 }, { "epoch": 14.89, "learning_rate": 2.015819083779065e-06, "loss": 0.7735, "step": 179160 }, { "epoch": 14.89, "learning_rate": 2.015708228251531e-06, "loss": 0.7947, "step": 179170 }, { "epoch": 14.89, "learning_rate": 2.0155973727239976e-06, "loss": 0.7969, "step": 179180 }, { "epoch": 14.89, "learning_rate": 2.0154865171964635e-06, "loss": 0.7819, "step": 179190 }, { "epoch": 14.89, "learning_rate": 2.0153756616689298e-06, "loss": 0.773, "step": 179200 }, { "epoch": 14.9, "learning_rate": 2.015264806141396e-06, "loss": 0.7957, "step": 179210 }, { "epoch": 14.9, "learning_rate": 2.0151539506138624e-06, "loss": 0.7243, "step": 179220 }, { "epoch": 14.9, "learning_rate": 2.0150430950863287e-06, "loss": 0.6895, "step": 179230 }, { "epoch": 14.9, "learning_rate": 2.014932239558795e-06, "loss": 0.8579, "step": 179240 }, { "epoch": 14.9, "learning_rate": 2.0148213840312613e-06, "loss": 0.7221, "step": 179250 }, { "epoch": 14.9, "learning_rate": 2.0147105285037276e-06, "loss": 0.7944, "step": 179260 }, { "epoch": 14.9, "learning_rate": 2.014599672976194e-06, "loss": 0.7494, "step": 179270 }, { "epoch": 14.9, "learning_rate": 2.0144888174486597e-06, "loss": 0.7699, "step": 179280 }, { "epoch": 14.9, "learning_rate": 2.0143779619211264e-06, "loss": 0.8161, "step": 179290 }, { "epoch": 14.9, "learning_rate": 2.0142671063935923e-06, "loss": 0.7792, "step": 179300 }, { "epoch": 14.9, "learning_rate": 2.0141562508660586e-06, "loss": 0.7832, "step": 179310 }, { "epoch": 14.9, "learning_rate": 2.014045395338525e-06, "loss": 0.7547, "step": 179320 }, { "epoch": 14.91, "learning_rate": 2.013934539810991e-06, "loss": 0.8056, "step": 179330 }, { "epoch": 14.91, "learning_rate": 2.0138347698362107e-06, "loss": 0.8188, "step": 179340 }, { "epoch": 14.91, "learning_rate": 2.0137239143086775e-06, "loss": 0.673, "step": 179350 }, { "epoch": 14.91, "learning_rate": 2.0136130587811433e-06, "loss": 0.8051, "step": 179360 }, { "epoch": 14.91, "learning_rate": 2.0135022032536096e-06, "loss": 0.7641, "step": 179370 }, { "epoch": 14.91, "learning_rate": 2.013391347726076e-06, "loss": 0.8131, "step": 179380 }, { "epoch": 14.91, "learning_rate": 2.0132804921985422e-06, "loss": 0.7497, "step": 179390 }, { "epoch": 14.91, "learning_rate": 2.013169636671008e-06, "loss": 0.7572, "step": 179400 }, { "epoch": 14.91, "learning_rate": 2.013058781143475e-06, "loss": 0.7419, "step": 179410 }, { "epoch": 14.91, "learning_rate": 2.0129479256159407e-06, "loss": 0.7672, "step": 179420 }, { "epoch": 14.91, "learning_rate": 2.0128370700884074e-06, "loss": 0.7619, "step": 179430 }, { "epoch": 14.91, "learning_rate": 2.0127262145608737e-06, "loss": 0.867, "step": 179440 }, { "epoch": 14.92, "learning_rate": 2.0126153590333396e-06, "loss": 0.764, "step": 179450 }, { "epoch": 14.92, "learning_rate": 2.0125045035058063e-06, "loss": 0.7346, "step": 179460 }, { "epoch": 14.92, "learning_rate": 2.012393647978272e-06, "loss": 0.7416, "step": 179470 }, { "epoch": 14.92, "learning_rate": 2.0122827924507385e-06, "loss": 0.8136, "step": 179480 }, { "epoch": 14.92, "learning_rate": 2.0121719369232047e-06, "loss": 0.8242, "step": 179490 }, { "epoch": 14.92, "learning_rate": 2.012061081395671e-06, "loss": 0.799, "step": 179500 }, { "epoch": 14.92, "learning_rate": 2.011950225868137e-06, "loss": 0.7197, "step": 179510 }, { "epoch": 14.92, "learning_rate": 2.0118393703406036e-06, "loss": 0.7017, "step": 179520 }, { "epoch": 14.92, "learning_rate": 2.0117285148130695e-06, "loss": 0.8819, "step": 179530 }, { "epoch": 14.92, "learning_rate": 2.0116176592855362e-06, "loss": 0.8187, "step": 179540 }, { "epoch": 14.92, "learning_rate": 2.011506803758002e-06, "loss": 0.7572, "step": 179550 }, { "epoch": 14.92, "learning_rate": 2.0113959482304684e-06, "loss": 0.736, "step": 179560 }, { "epoch": 14.93, "learning_rate": 2.011285092702935e-06, "loss": 0.7024, "step": 179570 }, { "epoch": 14.93, "learning_rate": 2.011174237175401e-06, "loss": 0.7063, "step": 179580 }, { "epoch": 14.93, "learning_rate": 2.0110633816478673e-06, "loss": 0.7885, "step": 179590 }, { "epoch": 14.93, "learning_rate": 2.0109525261203336e-06, "loss": 0.7736, "step": 179600 }, { "epoch": 14.93, "learning_rate": 2.0108416705928e-06, "loss": 0.8454, "step": 179610 }, { "epoch": 14.93, "learning_rate": 2.010730815065266e-06, "loss": 0.77, "step": 179620 }, { "epoch": 14.93, "learning_rate": 2.0106199595377325e-06, "loss": 0.8085, "step": 179630 }, { "epoch": 14.93, "learning_rate": 2.0105091040101983e-06, "loss": 0.8096, "step": 179640 }, { "epoch": 14.93, "learning_rate": 2.010398248482665e-06, "loss": 0.8053, "step": 179650 }, { "epoch": 14.93, "learning_rate": 2.010287392955131e-06, "loss": 0.7247, "step": 179660 }, { "epoch": 14.93, "learning_rate": 2.0101765374275972e-06, "loss": 0.7946, "step": 179670 }, { "epoch": 14.93, "learning_rate": 2.010065681900064e-06, "loss": 0.736, "step": 179680 }, { "epoch": 14.94, "learning_rate": 2.00995482637253e-06, "loss": 0.7879, "step": 179690 }, { "epoch": 14.94, "learning_rate": 2.0098439708449965e-06, "loss": 0.7899, "step": 179700 }, { "epoch": 14.94, "learning_rate": 2.0097331153174624e-06, "loss": 0.7678, "step": 179710 }, { "epoch": 14.94, "learning_rate": 2.0096222597899287e-06, "loss": 0.7178, "step": 179720 }, { "epoch": 14.94, "learning_rate": 2.009511404262395e-06, "loss": 0.7551, "step": 179730 }, { "epoch": 14.94, "learning_rate": 2.0094005487348613e-06, "loss": 0.8753, "step": 179740 }, { "epoch": 14.94, "learning_rate": 2.009289693207327e-06, "loss": 0.7704, "step": 179750 }, { "epoch": 14.94, "learning_rate": 2.009178837679794e-06, "loss": 0.8409, "step": 179760 }, { "epoch": 14.94, "learning_rate": 2.0090679821522597e-06, "loss": 0.7742, "step": 179770 }, { "epoch": 14.94, "learning_rate": 2.0089571266247265e-06, "loss": 0.7903, "step": 179780 }, { "epoch": 14.94, "learning_rate": 2.0088462710971923e-06, "loss": 0.7568, "step": 179790 }, { "epoch": 14.94, "learning_rate": 2.0087354155696586e-06, "loss": 0.7877, "step": 179800 }, { "epoch": 14.95, "learning_rate": 2.0086245600421254e-06, "loss": 0.6565, "step": 179810 }, { "epoch": 14.95, "learning_rate": 2.0085137045145912e-06, "loss": 0.8451, "step": 179820 }, { "epoch": 14.95, "learning_rate": 2.0084028489870575e-06, "loss": 0.7415, "step": 179830 }, { "epoch": 14.95, "learning_rate": 2.008291993459524e-06, "loss": 0.7897, "step": 179840 }, { "epoch": 14.95, "learning_rate": 2.00818113793199e-06, "loss": 0.7327, "step": 179850 }, { "epoch": 14.95, "learning_rate": 2.0080702824044564e-06, "loss": 0.7935, "step": 179860 }, { "epoch": 14.95, "learning_rate": 2.0079594268769227e-06, "loss": 0.7583, "step": 179870 }, { "epoch": 14.95, "learning_rate": 2.0078485713493886e-06, "loss": 0.736, "step": 179880 }, { "epoch": 14.95, "learning_rate": 2.0077377158218553e-06, "loss": 0.7733, "step": 179890 }, { "epoch": 14.95, "learning_rate": 2.007626860294321e-06, "loss": 0.7836, "step": 179900 }, { "epoch": 14.95, "learning_rate": 2.0075160047667875e-06, "loss": 0.7905, "step": 179910 }, { "epoch": 14.95, "learning_rate": 2.0074051492392538e-06, "loss": 0.8206, "step": 179920 }, { "epoch": 14.96, "learning_rate": 2.00729429371172e-06, "loss": 0.8078, "step": 179930 }, { "epoch": 14.96, "learning_rate": 2.0071834381841868e-06, "loss": 0.7472, "step": 179940 }, { "epoch": 14.96, "learning_rate": 2.0070725826566526e-06, "loss": 0.7751, "step": 179950 }, { "epoch": 14.96, "learning_rate": 2.006961727129119e-06, "loss": 0.7876, "step": 179960 }, { "epoch": 14.96, "learning_rate": 2.0068508716015852e-06, "loss": 0.7259, "step": 179970 }, { "epoch": 14.96, "learning_rate": 2.0067400160740515e-06, "loss": 0.8204, "step": 179980 }, { "epoch": 14.96, "learning_rate": 2.0066291605465174e-06, "loss": 0.7431, "step": 179990 }, { "epoch": 14.96, "learning_rate": 2.006518305018984e-06, "loss": 0.7826, "step": 180000 }, { "epoch": 14.96, "learning_rate": 2.00640744949145e-06, "loss": 0.7924, "step": 180010 }, { "epoch": 14.96, "learning_rate": 2.0062965939639163e-06, "loss": 0.8086, "step": 180020 }, { "epoch": 14.96, "learning_rate": 2.0061857384363826e-06, "loss": 0.7516, "step": 180030 }, { "epoch": 14.96, "learning_rate": 2.006074882908849e-06, "loss": 0.8175, "step": 180040 }, { "epoch": 14.97, "learning_rate": 2.0059640273813156e-06, "loss": 0.794, "step": 180050 }, { "epoch": 14.97, "learning_rate": 2.0058531718537815e-06, "loss": 0.8304, "step": 180060 }, { "epoch": 14.97, "learning_rate": 2.0057423163262478e-06, "loss": 0.7068, "step": 180070 }, { "epoch": 14.97, "learning_rate": 2.005631460798714e-06, "loss": 0.805, "step": 180080 }, { "epoch": 14.97, "learning_rate": 2.0055206052711803e-06, "loss": 0.8661, "step": 180090 }, { "epoch": 14.97, "learning_rate": 2.0054097497436462e-06, "loss": 0.7728, "step": 180100 }, { "epoch": 14.97, "learning_rate": 2.005298894216113e-06, "loss": 0.8169, "step": 180110 }, { "epoch": 14.97, "learning_rate": 2.005188038688579e-06, "loss": 0.7357, "step": 180120 }, { "epoch": 14.97, "learning_rate": 2.0050771831610455e-06, "loss": 0.7559, "step": 180130 }, { "epoch": 14.97, "learning_rate": 2.0049663276335114e-06, "loss": 0.8075, "step": 180140 }, { "epoch": 14.97, "learning_rate": 2.0048554721059777e-06, "loss": 0.8249, "step": 180150 }, { "epoch": 14.97, "learning_rate": 2.004744616578444e-06, "loss": 0.8253, "step": 180160 }, { "epoch": 14.98, "learning_rate": 2.0046337610509103e-06, "loss": 0.8144, "step": 180170 }, { "epoch": 14.98, "learning_rate": 2.0045229055233766e-06, "loss": 0.8361, "step": 180180 }, { "epoch": 14.98, "learning_rate": 2.004412049995843e-06, "loss": 0.8263, "step": 180190 }, { "epoch": 14.98, "learning_rate": 2.004301194468309e-06, "loss": 0.8278, "step": 180200 }, { "epoch": 14.98, "learning_rate": 2.0041903389407755e-06, "loss": 0.7576, "step": 180210 }, { "epoch": 14.98, "learning_rate": 2.0040794834132418e-06, "loss": 0.7058, "step": 180220 }, { "epoch": 14.98, "learning_rate": 2.0039686278857076e-06, "loss": 0.7964, "step": 180230 }, { "epoch": 14.98, "learning_rate": 2.0038577723581744e-06, "loss": 0.8441, "step": 180240 }, { "epoch": 14.98, "learning_rate": 2.0037469168306402e-06, "loss": 0.7805, "step": 180250 }, { "epoch": 14.98, "learning_rate": 2.0036360613031065e-06, "loss": 0.7143, "step": 180260 }, { "epoch": 14.98, "learning_rate": 2.003525205775573e-06, "loss": 0.7655, "step": 180270 }, { "epoch": 14.98, "learning_rate": 2.003414350248039e-06, "loss": 0.7299, "step": 180280 }, { "epoch": 14.99, "learning_rate": 2.003303494720505e-06, "loss": 0.7294, "step": 180290 }, { "epoch": 14.99, "learning_rate": 2.0031926391929717e-06, "loss": 0.7959, "step": 180300 }, { "epoch": 14.99, "learning_rate": 2.003081783665438e-06, "loss": 0.7385, "step": 180310 }, { "epoch": 14.99, "learning_rate": 2.0029709281379043e-06, "loss": 0.777, "step": 180320 }, { "epoch": 14.99, "learning_rate": 2.0028600726103706e-06, "loss": 0.7576, "step": 180330 }, { "epoch": 14.99, "learning_rate": 2.0027492170828365e-06, "loss": 0.7931, "step": 180340 }, { "epoch": 14.99, "learning_rate": 2.002638361555303e-06, "loss": 0.7904, "step": 180350 }, { "epoch": 14.99, "learning_rate": 2.002527506027769e-06, "loss": 0.7549, "step": 180360 }, { "epoch": 14.99, "learning_rate": 2.0024166505002353e-06, "loss": 0.8072, "step": 180370 }, { "epoch": 14.99, "learning_rate": 2.0023057949727016e-06, "loss": 0.805, "step": 180380 }, { "epoch": 14.99, "learning_rate": 2.002194939445168e-06, "loss": 0.803, "step": 180390 }, { "epoch": 14.99, "learning_rate": 2.0020840839176342e-06, "loss": 0.7609, "step": 180400 }, { "epoch": 15.0, "learning_rate": 2.0019732283901005e-06, "loss": 0.7836, "step": 180410 }, { "epoch": 15.0, "learning_rate": 2.001862372862567e-06, "loss": 0.7444, "step": 180420 }, { "epoch": 15.0, "learning_rate": 2.001751517335033e-06, "loss": 0.7475, "step": 180430 }, { "epoch": 15.0, "learning_rate": 2.0016406618074994e-06, "loss": 0.793, "step": 180440 }, { "epoch": 15.0, "learning_rate": 2.0015298062799653e-06, "loss": 0.74, "step": 180450 }, { "epoch": 15.0, "learning_rate": 2.001418950752432e-06, "loss": 0.8279, "step": 180460 }, { "epoch": 15.0, "eval_loss": 1.1162251234054565, "eval_runtime": 354.1231, "eval_samples_per_second": 7.551, "eval_steps_per_second": 3.776, "eval_wer": 0.646122623874033, "step": 180465 }, { "epoch": 15.0, "learning_rate": 2.001308095224898e-06, "loss": 0.7801, "step": 180470 }, { "epoch": 15.0, "learning_rate": 2.0011972396973646e-06, "loss": 0.7794, "step": 180480 }, { "epoch": 15.0, "learning_rate": 2.0010863841698305e-06, "loss": 0.8483, "step": 180490 }, { "epoch": 15.0, "learning_rate": 2.0009755286422968e-06, "loss": 0.7976, "step": 180500 }, { "epoch": 15.0, "learning_rate": 2.000864673114763e-06, "loss": 0.7541, "step": 180510 }, { "epoch": 15.0, "learning_rate": 2.0007538175872294e-06, "loss": 0.8075, "step": 180520 }, { "epoch": 15.01, "learning_rate": 2.0006429620596952e-06, "loss": 0.8064, "step": 180530 }, { "epoch": 15.01, "learning_rate": 2.000532106532162e-06, "loss": 0.7427, "step": 180540 }, { "epoch": 15.01, "learning_rate": 2.0004212510046282e-06, "loss": 0.7653, "step": 180550 }, { "epoch": 15.01, "learning_rate": 2.0003103954770945e-06, "loss": 0.7732, "step": 180560 }, { "epoch": 15.01, "learning_rate": 2.000199539949561e-06, "loss": 0.7665, "step": 180570 }, { "epoch": 15.01, "learning_rate": 2.0000886844220267e-06, "loss": 0.8564, "step": 180580 }, { "epoch": 15.01, "learning_rate": 1.999977828894493e-06, "loss": 0.8003, "step": 180590 }, { "epoch": 15.01, "learning_rate": 1.9998669733669593e-06, "loss": 0.8331, "step": 180600 }, { "epoch": 15.01, "learning_rate": 1.9997561178394256e-06, "loss": 0.7574, "step": 180610 }, { "epoch": 15.01, "learning_rate": 1.999645262311892e-06, "loss": 0.7926, "step": 180620 }, { "epoch": 15.01, "learning_rate": 1.999534406784358e-06, "loss": 0.7711, "step": 180630 }, { "epoch": 15.01, "learning_rate": 1.9994235512568245e-06, "loss": 0.7557, "step": 180640 }, { "epoch": 15.02, "learning_rate": 1.9993126957292908e-06, "loss": 0.7759, "step": 180650 }, { "epoch": 15.02, "learning_rate": 1.999201840201757e-06, "loss": 0.7905, "step": 180660 }, { "epoch": 15.02, "learning_rate": 1.9990909846742234e-06, "loss": 0.7799, "step": 180670 }, { "epoch": 15.02, "learning_rate": 1.9989801291466897e-06, "loss": 0.7427, "step": 180680 }, { "epoch": 15.02, "learning_rate": 1.9988692736191555e-06, "loss": 0.7841, "step": 180690 }, { "epoch": 15.02, "learning_rate": 1.998758418091622e-06, "loss": 0.793, "step": 180700 }, { "epoch": 15.02, "learning_rate": 1.998647562564088e-06, "loss": 0.8078, "step": 180710 }, { "epoch": 15.02, "learning_rate": 1.9985367070365544e-06, "loss": 0.8169, "step": 180720 }, { "epoch": 15.02, "learning_rate": 1.9984258515090207e-06, "loss": 0.802, "step": 180730 }, { "epoch": 15.02, "learning_rate": 1.998314995981487e-06, "loss": 0.7442, "step": 180740 }, { "epoch": 15.02, "learning_rate": 1.9982041404539533e-06, "loss": 0.7623, "step": 180750 }, { "epoch": 15.02, "learning_rate": 1.9980932849264196e-06, "loss": 0.8404, "step": 180760 }, { "epoch": 15.03, "learning_rate": 1.997982429398886e-06, "loss": 0.7608, "step": 180770 }, { "epoch": 15.03, "learning_rate": 1.997871573871352e-06, "loss": 0.8349, "step": 180780 }, { "epoch": 15.03, "learning_rate": 1.9977607183438185e-06, "loss": 0.7704, "step": 180790 }, { "epoch": 15.03, "learning_rate": 1.9976498628162844e-06, "loss": 0.6932, "step": 180800 }, { "epoch": 15.03, "learning_rate": 1.9975390072887506e-06, "loss": 0.805, "step": 180810 }, { "epoch": 15.03, "learning_rate": 1.997428151761217e-06, "loss": 0.733, "step": 180820 }, { "epoch": 15.03, "learning_rate": 1.9973172962336832e-06, "loss": 0.7357, "step": 180830 }, { "epoch": 15.03, "learning_rate": 1.9972064407061495e-06, "loss": 0.7597, "step": 180840 }, { "epoch": 15.03, "learning_rate": 1.997095585178616e-06, "loss": 0.7589, "step": 180850 }, { "epoch": 15.03, "learning_rate": 1.996984729651082e-06, "loss": 0.7768, "step": 180860 }, { "epoch": 15.03, "learning_rate": 1.9968738741235484e-06, "loss": 0.7702, "step": 180870 }, { "epoch": 15.03, "learning_rate": 1.9967630185960147e-06, "loss": 0.7975, "step": 180880 }, { "epoch": 15.04, "learning_rate": 1.996652163068481e-06, "loss": 0.8139, "step": 180890 }, { "epoch": 15.04, "learning_rate": 1.9965413075409473e-06, "loss": 0.7794, "step": 180900 }, { "epoch": 15.04, "learning_rate": 1.9964304520134136e-06, "loss": 0.7268, "step": 180910 }, { "epoch": 15.04, "learning_rate": 1.9963195964858795e-06, "loss": 0.7565, "step": 180920 }, { "epoch": 15.04, "learning_rate": 1.9962087409583458e-06, "loss": 0.7717, "step": 180930 }, { "epoch": 15.04, "learning_rate": 1.996097885430812e-06, "loss": 0.81, "step": 180940 }, { "epoch": 15.04, "learning_rate": 1.9959870299032784e-06, "loss": 0.7701, "step": 180950 }, { "epoch": 15.04, "learning_rate": 1.9958761743757447e-06, "loss": 0.7524, "step": 180960 }, { "epoch": 15.04, "learning_rate": 1.995765318848211e-06, "loss": 0.843, "step": 180970 }, { "epoch": 15.04, "learning_rate": 1.9956544633206772e-06, "loss": 0.7742, "step": 180980 }, { "epoch": 15.04, "learning_rate": 1.9955436077931435e-06, "loss": 0.7212, "step": 180990 }, { "epoch": 15.04, "learning_rate": 1.99543275226561e-06, "loss": 0.7935, "step": 181000 }, { "epoch": 15.05, "learning_rate": 1.995321896738076e-06, "loss": 0.8264, "step": 181010 }, { "epoch": 15.05, "learning_rate": 1.9952110412105424e-06, "loss": 0.7575, "step": 181020 }, { "epoch": 15.05, "learning_rate": 1.9951001856830087e-06, "loss": 0.7448, "step": 181030 }, { "epoch": 15.05, "learning_rate": 1.9949893301554746e-06, "loss": 0.7156, "step": 181040 }, { "epoch": 15.05, "learning_rate": 1.994878474627941e-06, "loss": 0.7363, "step": 181050 }, { "epoch": 15.05, "learning_rate": 1.994767619100407e-06, "loss": 0.8405, "step": 181060 }, { "epoch": 15.05, "learning_rate": 1.9946567635728735e-06, "loss": 0.778, "step": 181070 }, { "epoch": 15.05, "learning_rate": 1.9945459080453398e-06, "loss": 0.7694, "step": 181080 }, { "epoch": 15.05, "learning_rate": 1.994435052517806e-06, "loss": 0.7655, "step": 181090 }, { "epoch": 15.05, "learning_rate": 1.9943241969902724e-06, "loss": 0.7376, "step": 181100 }, { "epoch": 15.05, "learning_rate": 1.9942133414627387e-06, "loss": 0.8084, "step": 181110 }, { "epoch": 15.05, "learning_rate": 1.994102485935205e-06, "loss": 0.7964, "step": 181120 }, { "epoch": 15.06, "learning_rate": 1.9939916304076713e-06, "loss": 0.7634, "step": 181130 }, { "epoch": 15.06, "learning_rate": 1.9938807748801375e-06, "loss": 0.8041, "step": 181140 }, { "epoch": 15.06, "learning_rate": 1.993769919352604e-06, "loss": 0.7995, "step": 181150 }, { "epoch": 15.06, "learning_rate": 1.9936590638250697e-06, "loss": 0.7081, "step": 181160 }, { "epoch": 15.06, "learning_rate": 1.993548208297536e-06, "loss": 0.8304, "step": 181170 }, { "epoch": 15.06, "learning_rate": 1.9934373527700023e-06, "loss": 0.8446, "step": 181180 }, { "epoch": 15.06, "learning_rate": 1.9933264972424686e-06, "loss": 0.7924, "step": 181190 }, { "epoch": 15.06, "learning_rate": 1.993215641714935e-06, "loss": 0.7554, "step": 181200 }, { "epoch": 15.06, "learning_rate": 1.993104786187401e-06, "loss": 0.7076, "step": 181210 }, { "epoch": 15.06, "learning_rate": 1.9929939306598675e-06, "loss": 0.7533, "step": 181220 }, { "epoch": 15.06, "learning_rate": 1.9928830751323338e-06, "loss": 0.8018, "step": 181230 }, { "epoch": 15.06, "learning_rate": 1.9927722196048e-06, "loss": 0.7221, "step": 181240 }, { "epoch": 15.07, "learning_rate": 1.9926613640772664e-06, "loss": 0.8001, "step": 181250 }, { "epoch": 15.07, "learning_rate": 1.9925505085497327e-06, "loss": 0.7627, "step": 181260 }, { "epoch": 15.07, "learning_rate": 1.9924396530221985e-06, "loss": 0.8393, "step": 181270 }, { "epoch": 15.07, "learning_rate": 1.992328797494665e-06, "loss": 0.7607, "step": 181280 }, { "epoch": 15.07, "learning_rate": 1.992217941967131e-06, "loss": 0.7539, "step": 181290 }, { "epoch": 15.07, "learning_rate": 1.9921070864395974e-06, "loss": 0.7674, "step": 181300 }, { "epoch": 15.07, "learning_rate": 1.9919962309120637e-06, "loss": 0.8125, "step": 181310 }, { "epoch": 15.07, "learning_rate": 1.99188537538453e-06, "loss": 0.8034, "step": 181320 }, { "epoch": 15.07, "learning_rate": 1.9917745198569963e-06, "loss": 0.813, "step": 181330 }, { "epoch": 15.07, "learning_rate": 1.9916636643294626e-06, "loss": 0.764, "step": 181340 }, { "epoch": 15.07, "learning_rate": 1.991552808801929e-06, "loss": 0.7417, "step": 181350 }, { "epoch": 15.07, "learning_rate": 1.991441953274395e-06, "loss": 0.7712, "step": 181360 }, { "epoch": 15.08, "learning_rate": 1.9913310977468615e-06, "loss": 0.7688, "step": 181370 }, { "epoch": 15.08, "learning_rate": 1.991220242219328e-06, "loss": 0.8201, "step": 181380 }, { "epoch": 15.08, "learning_rate": 1.9911093866917937e-06, "loss": 0.7705, "step": 181390 }, { "epoch": 15.08, "learning_rate": 1.99099853116426e-06, "loss": 0.7522, "step": 181400 }, { "epoch": 15.08, "learning_rate": 1.9908876756367263e-06, "loss": 0.8019, "step": 181410 }, { "epoch": 15.08, "learning_rate": 1.9907768201091925e-06, "loss": 0.784, "step": 181420 }, { "epoch": 15.08, "learning_rate": 1.990665964581659e-06, "loss": 0.7539, "step": 181430 }, { "epoch": 15.08, "learning_rate": 1.990555109054125e-06, "loss": 0.7711, "step": 181440 }, { "epoch": 15.08, "learning_rate": 1.9904442535265914e-06, "loss": 0.7737, "step": 181450 }, { "epoch": 15.08, "learning_rate": 1.9903333979990577e-06, "loss": 0.7971, "step": 181460 }, { "epoch": 15.08, "learning_rate": 1.990222542471524e-06, "loss": 0.7603, "step": 181470 }, { "epoch": 15.08, "learning_rate": 1.9901116869439903e-06, "loss": 0.8785, "step": 181480 }, { "epoch": 15.09, "learning_rate": 1.9900008314164566e-06, "loss": 0.778, "step": 181490 }, { "epoch": 15.09, "learning_rate": 1.989889975888923e-06, "loss": 0.8086, "step": 181500 }, { "epoch": 15.09, "learning_rate": 1.9897791203613888e-06, "loss": 0.78, "step": 181510 }, { "epoch": 15.09, "learning_rate": 1.989668264833855e-06, "loss": 0.8369, "step": 181520 }, { "epoch": 15.09, "learning_rate": 1.9895574093063214e-06, "loss": 0.7633, "step": 181530 }, { "epoch": 15.09, "learning_rate": 1.9894465537787877e-06, "loss": 0.8052, "step": 181540 }, { "epoch": 15.09, "learning_rate": 1.989335698251254e-06, "loss": 0.7601, "step": 181550 }, { "epoch": 15.09, "learning_rate": 1.9892248427237203e-06, "loss": 0.7763, "step": 181560 }, { "epoch": 15.09, "learning_rate": 1.9891139871961866e-06, "loss": 0.8081, "step": 181570 }, { "epoch": 15.09, "learning_rate": 1.9890031316686524e-06, "loss": 0.7767, "step": 181580 }, { "epoch": 15.09, "learning_rate": 1.988892276141119e-06, "loss": 0.7491, "step": 181590 }, { "epoch": 15.09, "learning_rate": 1.9887814206135854e-06, "loss": 0.7886, "step": 181600 }, { "epoch": 15.1, "learning_rate": 1.9886705650860517e-06, "loss": 0.8496, "step": 181610 }, { "epoch": 15.1, "learning_rate": 1.9885597095585176e-06, "loss": 0.7875, "step": 181620 }, { "epoch": 15.1, "learning_rate": 1.988448854030984e-06, "loss": 0.8814, "step": 181630 }, { "epoch": 15.1, "learning_rate": 1.98833799850345e-06, "loss": 0.7579, "step": 181640 }, { "epoch": 15.1, "learning_rate": 1.9882271429759165e-06, "loss": 0.7428, "step": 181650 }, { "epoch": 15.1, "learning_rate": 1.988116287448383e-06, "loss": 0.7018, "step": 181660 }, { "epoch": 15.1, "learning_rate": 1.988005431920849e-06, "loss": 0.758, "step": 181670 }, { "epoch": 15.1, "learning_rate": 1.9878945763933154e-06, "loss": 0.7447, "step": 181680 }, { "epoch": 15.1, "learning_rate": 1.9877837208657817e-06, "loss": 0.786, "step": 181690 }, { "epoch": 15.1, "learning_rate": 1.9876728653382475e-06, "loss": 0.7744, "step": 181700 }, { "epoch": 15.1, "learning_rate": 1.9875620098107143e-06, "loss": 0.7618, "step": 181710 }, { "epoch": 15.1, "learning_rate": 1.9874511542831806e-06, "loss": 0.8233, "step": 181720 }, { "epoch": 15.11, "learning_rate": 1.987340298755647e-06, "loss": 0.8167, "step": 181730 }, { "epoch": 15.11, "learning_rate": 1.9872294432281127e-06, "loss": 0.8588, "step": 181740 }, { "epoch": 15.11, "learning_rate": 1.987118587700579e-06, "loss": 0.7635, "step": 181750 }, { "epoch": 15.11, "learning_rate": 1.9870077321730453e-06, "loss": 0.7782, "step": 181760 }, { "epoch": 15.11, "learning_rate": 1.9868968766455116e-06, "loss": 0.7441, "step": 181770 }, { "epoch": 15.11, "learning_rate": 1.986786021117978e-06, "loss": 0.7841, "step": 181780 }, { "epoch": 15.11, "learning_rate": 1.986675165590444e-06, "loss": 0.7874, "step": 181790 }, { "epoch": 15.11, "learning_rate": 1.9865643100629105e-06, "loss": 0.7416, "step": 181800 }, { "epoch": 15.11, "learning_rate": 1.986453454535377e-06, "loss": 0.7902, "step": 181810 }, { "epoch": 15.11, "learning_rate": 1.9863425990078427e-06, "loss": 0.8123, "step": 181820 }, { "epoch": 15.11, "learning_rate": 1.9862317434803094e-06, "loss": 0.7385, "step": 181830 }, { "epoch": 15.11, "learning_rate": 1.9861208879527757e-06, "loss": 0.7469, "step": 181840 }, { "epoch": 15.12, "learning_rate": 1.986010032425242e-06, "loss": 0.7866, "step": 181850 }, { "epoch": 15.12, "learning_rate": 1.985899176897708e-06, "loss": 0.7197, "step": 181860 }, { "epoch": 15.12, "learning_rate": 1.985788321370174e-06, "loss": 0.8412, "step": 181870 }, { "epoch": 15.12, "learning_rate": 1.9856774658426404e-06, "loss": 0.8028, "step": 181880 }, { "epoch": 15.12, "learning_rate": 1.9855666103151067e-06, "loss": 0.7581, "step": 181890 }, { "epoch": 15.12, "learning_rate": 1.985455754787573e-06, "loss": 0.7446, "step": 181900 }, { "epoch": 15.12, "learning_rate": 1.9853448992600393e-06, "loss": 0.754, "step": 181910 }, { "epoch": 15.12, "learning_rate": 1.9852340437325056e-06, "loss": 0.786, "step": 181920 }, { "epoch": 15.12, "learning_rate": 1.985123188204972e-06, "loss": 0.8352, "step": 181930 }, { "epoch": 15.12, "learning_rate": 1.9850123326774378e-06, "loss": 0.7601, "step": 181940 }, { "epoch": 15.12, "learning_rate": 1.984901477149904e-06, "loss": 0.8042, "step": 181950 }, { "epoch": 15.12, "learning_rate": 1.984790621622371e-06, "loss": 0.7399, "step": 181960 }, { "epoch": 15.13, "learning_rate": 1.984679766094837e-06, "loss": 0.8122, "step": 181970 }, { "epoch": 15.13, "learning_rate": 1.984568910567303e-06, "loss": 0.7706, "step": 181980 }, { "epoch": 15.13, "learning_rate": 1.9844580550397693e-06, "loss": 0.6612, "step": 181990 }, { "epoch": 15.13, "learning_rate": 1.9843471995122356e-06, "loss": 0.7961, "step": 182000 }, { "epoch": 15.13, "learning_rate": 1.984236343984702e-06, "loss": 0.8068, "step": 182010 }, { "epoch": 15.13, "learning_rate": 1.984125488457168e-06, "loss": 0.8018, "step": 182020 }, { "epoch": 15.13, "learning_rate": 1.9840146329296344e-06, "loss": 0.7604, "step": 182030 }, { "epoch": 15.13, "learning_rate": 1.9839037774021007e-06, "loss": 0.7649, "step": 182040 }, { "epoch": 15.13, "learning_rate": 1.9837929218745666e-06, "loss": 0.7258, "step": 182050 }, { "epoch": 15.13, "learning_rate": 1.983682066347033e-06, "loss": 0.7721, "step": 182060 }, { "epoch": 15.13, "learning_rate": 1.983571210819499e-06, "loss": 0.8199, "step": 182070 }, { "epoch": 15.13, "learning_rate": 1.983460355291966e-06, "loss": 0.8069, "step": 182080 }, { "epoch": 15.14, "learning_rate": 1.983349499764432e-06, "loss": 0.7863, "step": 182090 }, { "epoch": 15.14, "learning_rate": 1.983238644236898e-06, "loss": 0.7877, "step": 182100 }, { "epoch": 15.14, "learning_rate": 1.9831277887093644e-06, "loss": 0.7492, "step": 182110 }, { "epoch": 15.14, "learning_rate": 1.9830169331818307e-06, "loss": 0.7754, "step": 182120 }, { "epoch": 15.14, "learning_rate": 1.982906077654297e-06, "loss": 0.7529, "step": 182130 }, { "epoch": 15.14, "learning_rate": 1.9827952221267633e-06, "loss": 0.745, "step": 182140 }, { "epoch": 15.14, "learning_rate": 1.9826843665992296e-06, "loss": 0.7467, "step": 182150 }, { "epoch": 15.14, "learning_rate": 1.982573511071696e-06, "loss": 0.7821, "step": 182160 }, { "epoch": 15.14, "learning_rate": 1.9824626555441617e-06, "loss": 0.7784, "step": 182170 }, { "epoch": 15.14, "learning_rate": 1.982351800016628e-06, "loss": 0.7751, "step": 182180 }, { "epoch": 15.14, "learning_rate": 1.9822409444890943e-06, "loss": 0.742, "step": 182190 }, { "epoch": 15.14, "learning_rate": 1.982130088961561e-06, "loss": 0.7529, "step": 182200 }, { "epoch": 15.15, "learning_rate": 1.982019233434027e-06, "loss": 0.7574, "step": 182210 }, { "epoch": 15.15, "learning_rate": 1.981908377906493e-06, "loss": 0.7416, "step": 182220 }, { "epoch": 15.15, "learning_rate": 1.9817975223789595e-06, "loss": 0.7816, "step": 182230 }, { "epoch": 15.15, "learning_rate": 1.981686666851426e-06, "loss": 0.7968, "step": 182240 }, { "epoch": 15.15, "learning_rate": 1.981575811323892e-06, "loss": 0.7812, "step": 182250 }, { "epoch": 15.15, "learning_rate": 1.9814649557963584e-06, "loss": 0.6596, "step": 182260 }, { "epoch": 15.15, "learning_rate": 1.9813541002688247e-06, "loss": 0.8453, "step": 182270 }, { "epoch": 15.15, "learning_rate": 1.981243244741291e-06, "loss": 0.7875, "step": 182280 }, { "epoch": 15.15, "learning_rate": 1.981132389213757e-06, "loss": 0.6969, "step": 182290 }, { "epoch": 15.15, "learning_rate": 1.981021533686223e-06, "loss": 0.7491, "step": 182300 }, { "epoch": 15.15, "learning_rate": 1.9809106781586894e-06, "loss": 0.8404, "step": 182310 }, { "epoch": 15.15, "learning_rate": 1.9807998226311557e-06, "loss": 0.7678, "step": 182320 }, { "epoch": 15.16, "learning_rate": 1.980688967103622e-06, "loss": 0.7762, "step": 182330 }, { "epoch": 15.16, "learning_rate": 1.9805781115760883e-06, "loss": 0.7619, "step": 182340 }, { "epoch": 15.16, "learning_rate": 1.9804672560485546e-06, "loss": 0.7443, "step": 182350 }, { "epoch": 15.16, "learning_rate": 1.980356400521021e-06, "loss": 0.7844, "step": 182360 }, { "epoch": 15.16, "learning_rate": 1.9802455449934872e-06, "loss": 0.7627, "step": 182370 }, { "epoch": 15.16, "learning_rate": 1.9801346894659535e-06, "loss": 0.7983, "step": 182380 }, { "epoch": 15.16, "learning_rate": 1.98002383393842e-06, "loss": 0.7426, "step": 182390 }, { "epoch": 15.16, "learning_rate": 1.979912978410886e-06, "loss": 0.7726, "step": 182400 }, { "epoch": 15.16, "learning_rate": 1.979802122883352e-06, "loss": 0.779, "step": 182410 }, { "epoch": 15.16, "learning_rate": 1.9796912673558183e-06, "loss": 0.7399, "step": 182420 }, { "epoch": 15.16, "learning_rate": 1.9795804118282846e-06, "loss": 0.8484, "step": 182430 }, { "epoch": 15.16, "learning_rate": 1.979469556300751e-06, "loss": 0.7477, "step": 182440 }, { "epoch": 15.16, "learning_rate": 1.979358700773217e-06, "loss": 0.7223, "step": 182450 }, { "epoch": 15.17, "learning_rate": 1.9792478452456835e-06, "loss": 0.77, "step": 182460 }, { "epoch": 15.17, "learning_rate": 1.9791369897181497e-06, "loss": 0.749, "step": 182470 }, { "epoch": 15.17, "learning_rate": 1.979026134190616e-06, "loss": 0.8304, "step": 182480 }, { "epoch": 15.17, "learning_rate": 1.9789152786630823e-06, "loss": 0.7781, "step": 182490 }, { "epoch": 15.17, "learning_rate": 1.9788044231355486e-06, "loss": 0.8402, "step": 182500 }, { "epoch": 15.17, "learning_rate": 1.978693567608015e-06, "loss": 0.8012, "step": 182510 }, { "epoch": 15.17, "learning_rate": 1.978582712080481e-06, "loss": 0.8438, "step": 182520 }, { "epoch": 15.17, "learning_rate": 1.978471856552947e-06, "loss": 0.7509, "step": 182530 }, { "epoch": 15.17, "learning_rate": 1.9783610010254134e-06, "loss": 0.7224, "step": 182540 }, { "epoch": 15.17, "learning_rate": 1.9782501454978797e-06, "loss": 0.7773, "step": 182550 }, { "epoch": 15.17, "learning_rate": 1.978139289970346e-06, "loss": 0.7571, "step": 182560 }, { "epoch": 15.17, "learning_rate": 1.9780284344428123e-06, "loss": 0.7633, "step": 182570 }, { "epoch": 15.18, "learning_rate": 1.9779175789152786e-06, "loss": 0.813, "step": 182580 }, { "epoch": 15.18, "learning_rate": 1.977806723387745e-06, "loss": 0.776, "step": 182590 }, { "epoch": 15.18, "learning_rate": 1.977695867860211e-06, "loss": 0.7373, "step": 182600 }, { "epoch": 15.18, "learning_rate": 1.9775850123326775e-06, "loss": 0.735, "step": 182610 }, { "epoch": 15.18, "learning_rate": 1.9774741568051438e-06, "loss": 0.8016, "step": 182620 }, { "epoch": 15.18, "learning_rate": 1.97736330127761e-06, "loss": 0.7725, "step": 182630 }, { "epoch": 15.18, "learning_rate": 1.977252445750076e-06, "loss": 0.7732, "step": 182640 }, { "epoch": 15.18, "learning_rate": 1.9771415902225422e-06, "loss": 0.7858, "step": 182650 }, { "epoch": 15.18, "learning_rate": 1.9770307346950085e-06, "loss": 0.7518, "step": 182660 }, { "epoch": 15.18, "learning_rate": 1.976919879167475e-06, "loss": 0.812, "step": 182670 }, { "epoch": 15.18, "learning_rate": 1.976809023639941e-06, "loss": 0.7759, "step": 182680 }, { "epoch": 15.18, "learning_rate": 1.9766981681124074e-06, "loss": 0.8386, "step": 182690 }, { "epoch": 15.19, "learning_rate": 1.9765873125848737e-06, "loss": 0.7712, "step": 182700 }, { "epoch": 15.19, "learning_rate": 1.97647645705734e-06, "loss": 0.7267, "step": 182710 }, { "epoch": 15.19, "learning_rate": 1.9763656015298063e-06, "loss": 0.7943, "step": 182720 }, { "epoch": 15.19, "learning_rate": 1.9762547460022726e-06, "loss": 0.8781, "step": 182730 }, { "epoch": 15.19, "learning_rate": 1.976143890474739e-06, "loss": 0.7791, "step": 182740 }, { "epoch": 15.19, "learning_rate": 1.976033034947205e-06, "loss": 0.7608, "step": 182750 }, { "epoch": 15.19, "learning_rate": 1.975922179419671e-06, "loss": 0.7273, "step": 182760 }, { "epoch": 15.19, "learning_rate": 1.9758113238921373e-06, "loss": 0.8015, "step": 182770 }, { "epoch": 15.19, "learning_rate": 1.9757004683646036e-06, "loss": 0.8185, "step": 182780 }, { "epoch": 15.19, "learning_rate": 1.97558961283707e-06, "loss": 0.7637, "step": 182790 }, { "epoch": 15.19, "learning_rate": 1.9754787573095362e-06, "loss": 0.7524, "step": 182800 }, { "epoch": 15.19, "learning_rate": 1.9753679017820025e-06, "loss": 0.7391, "step": 182810 }, { "epoch": 15.2, "learning_rate": 1.975257046254469e-06, "loss": 0.7266, "step": 182820 }, { "epoch": 15.2, "learning_rate": 1.975146190726935e-06, "loss": 0.7806, "step": 182830 }, { "epoch": 15.2, "learning_rate": 1.9750353351994014e-06, "loss": 0.7702, "step": 182840 }, { "epoch": 15.2, "learning_rate": 1.9749244796718677e-06, "loss": 0.7338, "step": 182850 }, { "epoch": 15.2, "learning_rate": 1.974813624144334e-06, "loss": 0.7566, "step": 182860 }, { "epoch": 15.2, "learning_rate": 1.9747027686168e-06, "loss": 0.789, "step": 182870 }, { "epoch": 15.2, "learning_rate": 1.974591913089266e-06, "loss": 0.7637, "step": 182880 }, { "epoch": 15.2, "learning_rate": 1.9744810575617325e-06, "loss": 0.7771, "step": 182890 }, { "epoch": 15.2, "learning_rate": 1.9743702020341988e-06, "loss": 0.8008, "step": 182900 }, { "epoch": 15.2, "learning_rate": 1.974259346506665e-06, "loss": 0.7881, "step": 182910 }, { "epoch": 15.2, "learning_rate": 1.9741484909791313e-06, "loss": 0.7851, "step": 182920 }, { "epoch": 15.2, "learning_rate": 1.9740376354515976e-06, "loss": 0.7408, "step": 182930 }, { "epoch": 15.21, "learning_rate": 1.973926779924064e-06, "loss": 0.7445, "step": 182940 }, { "epoch": 15.21, "learning_rate": 1.9738159243965302e-06, "loss": 0.7481, "step": 182950 }, { "epoch": 15.21, "learning_rate": 1.9737050688689965e-06, "loss": 0.8137, "step": 182960 }, { "epoch": 15.21, "learning_rate": 1.973594213341463e-06, "loss": 0.8418, "step": 182970 }, { "epoch": 15.21, "learning_rate": 1.973483357813929e-06, "loss": 0.7639, "step": 182980 }, { "epoch": 15.21, "learning_rate": 1.973372502286395e-06, "loss": 0.7747, "step": 182990 }, { "epoch": 15.21, "learning_rate": 1.9732616467588613e-06, "loss": 0.784, "step": 183000 }, { "epoch": 15.21, "learning_rate": 1.9731507912313276e-06, "loss": 0.7582, "step": 183010 }, { "epoch": 15.21, "learning_rate": 1.973039935703794e-06, "loss": 0.8134, "step": 183020 }, { "epoch": 15.21, "learning_rate": 1.97292908017626e-06, "loss": 0.8037, "step": 183030 }, { "epoch": 15.21, "learning_rate": 1.9728182246487265e-06, "loss": 0.7317, "step": 183040 }, { "epoch": 15.21, "learning_rate": 1.9727073691211928e-06, "loss": 0.8157, "step": 183050 }, { "epoch": 15.22, "learning_rate": 1.972596513593659e-06, "loss": 0.7742, "step": 183060 }, { "epoch": 15.22, "learning_rate": 1.9724856580661253e-06, "loss": 0.8168, "step": 183070 }, { "epoch": 15.22, "learning_rate": 1.9723748025385916e-06, "loss": 0.7441, "step": 183080 }, { "epoch": 15.22, "learning_rate": 1.972263947011058e-06, "loss": 0.7193, "step": 183090 }, { "epoch": 15.22, "learning_rate": 1.9721530914835242e-06, "loss": 0.8009, "step": 183100 }, { "epoch": 15.22, "learning_rate": 1.97204223595599e-06, "loss": 0.8111, "step": 183110 }, { "epoch": 15.22, "learning_rate": 1.9719313804284564e-06, "loss": 0.8305, "step": 183120 }, { "epoch": 15.22, "learning_rate": 1.9718205249009227e-06, "loss": 0.8071, "step": 183130 }, { "epoch": 15.22, "learning_rate": 1.971709669373389e-06, "loss": 0.7503, "step": 183140 }, { "epoch": 15.22, "learning_rate": 1.9715988138458553e-06, "loss": 0.8052, "step": 183150 }, { "epoch": 15.22, "learning_rate": 1.9714879583183216e-06, "loss": 0.7132, "step": 183160 }, { "epoch": 15.22, "learning_rate": 1.971377102790788e-06, "loss": 0.8156, "step": 183170 }, { "epoch": 15.23, "learning_rate": 1.971266247263254e-06, "loss": 0.7664, "step": 183180 }, { "epoch": 15.23, "learning_rate": 1.9711553917357205e-06, "loss": 0.8562, "step": 183190 }, { "epoch": 15.23, "learning_rate": 1.9710445362081868e-06, "loss": 0.7109, "step": 183200 }, { "epoch": 15.23, "learning_rate": 1.970933680680653e-06, "loss": 0.7379, "step": 183210 }, { "epoch": 15.23, "learning_rate": 1.9708228251531194e-06, "loss": 0.8112, "step": 183220 }, { "epoch": 15.23, "learning_rate": 1.9707119696255852e-06, "loss": 0.8063, "step": 183230 }, { "epoch": 15.23, "learning_rate": 1.9706011140980515e-06, "loss": 0.7895, "step": 183240 }, { "epoch": 15.23, "learning_rate": 1.970490258570518e-06, "loss": 0.6964, "step": 183250 }, { "epoch": 15.23, "learning_rate": 1.970379403042984e-06, "loss": 0.677, "step": 183260 }, { "epoch": 15.23, "learning_rate": 1.9702685475154504e-06, "loss": 0.829, "step": 183270 }, { "epoch": 15.23, "learning_rate": 1.9701576919879167e-06, "loss": 0.7482, "step": 183280 }, { "epoch": 15.23, "learning_rate": 1.970046836460383e-06, "loss": 0.8029, "step": 183290 }, { "epoch": 15.24, "learning_rate": 1.969935980932849e-06, "loss": 0.803, "step": 183300 }, { "epoch": 15.24, "learning_rate": 1.9698251254053156e-06, "loss": 0.7964, "step": 183310 }, { "epoch": 15.24, "learning_rate": 1.969714269877782e-06, "loss": 0.8411, "step": 183320 }, { "epoch": 15.24, "learning_rate": 1.969603414350248e-06, "loss": 0.7355, "step": 183330 }, { "epoch": 15.24, "learning_rate": 1.969492558822714e-06, "loss": 0.7612, "step": 183340 }, { "epoch": 15.24, "learning_rate": 1.9693817032951803e-06, "loss": 0.8417, "step": 183350 }, { "epoch": 15.24, "learning_rate": 1.9692708477676466e-06, "loss": 0.7392, "step": 183360 }, { "epoch": 15.24, "learning_rate": 1.969159992240113e-06, "loss": 0.8356, "step": 183370 }, { "epoch": 15.24, "learning_rate": 1.9690491367125792e-06, "loss": 0.7613, "step": 183380 }, { "epoch": 15.24, "learning_rate": 1.9689382811850455e-06, "loss": 0.7921, "step": 183390 }, { "epoch": 15.24, "learning_rate": 1.968827425657512e-06, "loss": 0.8257, "step": 183400 }, { "epoch": 15.24, "learning_rate": 1.968716570129978e-06, "loss": 0.8276, "step": 183410 }, { "epoch": 15.25, "learning_rate": 1.968605714602444e-06, "loss": 0.7871, "step": 183420 }, { "epoch": 15.25, "learning_rate": 1.9684948590749107e-06, "loss": 0.838, "step": 183430 }, { "epoch": 15.25, "learning_rate": 1.968384003547377e-06, "loss": 0.7604, "step": 183440 }, { "epoch": 15.25, "learning_rate": 1.9682731480198433e-06, "loss": 0.7548, "step": 183450 }, { "epoch": 15.25, "learning_rate": 1.968162292492309e-06, "loss": 0.7624, "step": 183460 }, { "epoch": 15.25, "learning_rate": 1.9680514369647755e-06, "loss": 0.7878, "step": 183470 }, { "epoch": 15.25, "learning_rate": 1.9679405814372418e-06, "loss": 0.903, "step": 183480 }, { "epoch": 15.25, "learning_rate": 1.967829725909708e-06, "loss": 0.7577, "step": 183490 }, { "epoch": 15.25, "learning_rate": 1.9677188703821744e-06, "loss": 0.7127, "step": 183500 }, { "epoch": 15.25, "learning_rate": 1.9676080148546406e-06, "loss": 0.7496, "step": 183510 }, { "epoch": 15.25, "learning_rate": 1.967497159327107e-06, "loss": 0.8272, "step": 183520 }, { "epoch": 15.25, "learning_rate": 1.9673863037995732e-06, "loss": 0.776, "step": 183530 }, { "epoch": 15.26, "learning_rate": 1.967275448272039e-06, "loss": 0.7328, "step": 183540 }, { "epoch": 15.26, "learning_rate": 1.9671645927445054e-06, "loss": 0.7454, "step": 183550 }, { "epoch": 15.26, "learning_rate": 1.967053737216972e-06, "loss": 0.7642, "step": 183560 }, { "epoch": 15.26, "learning_rate": 1.9669428816894384e-06, "loss": 0.8192, "step": 183570 }, { "epoch": 15.26, "learning_rate": 1.9668320261619043e-06, "loss": 0.7744, "step": 183580 }, { "epoch": 15.26, "learning_rate": 1.9667211706343706e-06, "loss": 0.717, "step": 183590 }, { "epoch": 15.26, "learning_rate": 1.966610315106837e-06, "loss": 0.7601, "step": 183600 }, { "epoch": 15.26, "learning_rate": 1.966499459579303e-06, "loss": 0.8018, "step": 183610 }, { "epoch": 15.26, "learning_rate": 1.9663886040517695e-06, "loss": 0.7999, "step": 183620 }, { "epoch": 15.26, "learning_rate": 1.9662777485242358e-06, "loss": 0.7082, "step": 183630 }, { "epoch": 15.26, "learning_rate": 1.966166892996702e-06, "loss": 0.7664, "step": 183640 }, { "epoch": 15.26, "learning_rate": 1.9660560374691684e-06, "loss": 0.7448, "step": 183650 }, { "epoch": 15.27, "learning_rate": 1.9659451819416342e-06, "loss": 0.7752, "step": 183660 }, { "epoch": 15.27, "learning_rate": 1.9658343264141005e-06, "loss": 0.7741, "step": 183670 }, { "epoch": 15.27, "learning_rate": 1.9657234708865672e-06, "loss": 0.7522, "step": 183680 }, { "epoch": 15.27, "learning_rate": 1.9656126153590335e-06, "loss": 0.7289, "step": 183690 }, { "epoch": 15.27, "learning_rate": 1.9655017598314994e-06, "loss": 0.8166, "step": 183700 }, { "epoch": 15.27, "learning_rate": 1.9653909043039657e-06, "loss": 0.7658, "step": 183710 }, { "epoch": 15.27, "learning_rate": 1.965280048776432e-06, "loss": 0.8076, "step": 183720 }, { "epoch": 15.27, "learning_rate": 1.9651691932488983e-06, "loss": 0.7704, "step": 183730 }, { "epoch": 15.27, "learning_rate": 1.9650583377213646e-06, "loss": 0.7568, "step": 183740 }, { "epoch": 15.27, "learning_rate": 1.964947482193831e-06, "loss": 0.71, "step": 183750 }, { "epoch": 15.27, "learning_rate": 1.964836626666297e-06, "loss": 0.7683, "step": 183760 }, { "epoch": 15.27, "learning_rate": 1.964725771138763e-06, "loss": 0.7794, "step": 183770 }, { "epoch": 15.28, "learning_rate": 1.9646149156112294e-06, "loss": 0.7787, "step": 183780 }, { "epoch": 15.28, "learning_rate": 1.9645040600836956e-06, "loss": 0.8122, "step": 183790 }, { "epoch": 15.28, "learning_rate": 1.9643932045561624e-06, "loss": 0.7881, "step": 183800 }, { "epoch": 15.28, "learning_rate": 1.9642823490286282e-06, "loss": 0.769, "step": 183810 }, { "epoch": 15.28, "learning_rate": 1.9641714935010945e-06, "loss": 0.8016, "step": 183820 }, { "epoch": 15.28, "learning_rate": 1.964060637973561e-06, "loss": 0.8432, "step": 183830 }, { "epoch": 15.28, "learning_rate": 1.963949782446027e-06, "loss": 0.7621, "step": 183840 }, { "epoch": 15.28, "learning_rate": 1.9638389269184934e-06, "loss": 0.7482, "step": 183850 }, { "epoch": 15.28, "learning_rate": 1.9637280713909597e-06, "loss": 0.7599, "step": 183860 }, { "epoch": 15.28, "learning_rate": 1.963617215863426e-06, "loss": 0.8518, "step": 183870 }, { "epoch": 15.28, "learning_rate": 1.9635063603358923e-06, "loss": 0.7862, "step": 183880 }, { "epoch": 15.28, "learning_rate": 1.963395504808358e-06, "loss": 0.8142, "step": 183890 }, { "epoch": 15.29, "learning_rate": 1.9632846492808245e-06, "loss": 0.7164, "step": 183900 }, { "epoch": 15.29, "learning_rate": 1.9631737937532908e-06, "loss": 0.7195, "step": 183910 }, { "epoch": 15.29, "learning_rate": 1.9630629382257575e-06, "loss": 0.8287, "step": 183920 }, { "epoch": 15.29, "learning_rate": 1.9629520826982234e-06, "loss": 0.8369, "step": 183930 }, { "epoch": 15.29, "learning_rate": 1.9628412271706897e-06, "loss": 0.7833, "step": 183940 }, { "epoch": 15.29, "learning_rate": 1.962730371643156e-06, "loss": 0.8051, "step": 183950 }, { "epoch": 15.29, "learning_rate": 1.9626195161156222e-06, "loss": 0.6944, "step": 183960 }, { "epoch": 15.29, "learning_rate": 1.9625086605880885e-06, "loss": 0.834, "step": 183970 }, { "epoch": 15.29, "learning_rate": 1.962397805060555e-06, "loss": 0.7761, "step": 183980 }, { "epoch": 15.29, "learning_rate": 1.962286949533021e-06, "loss": 0.7092, "step": 183990 }, { "epoch": 15.29, "learning_rate": 1.9621760940054874e-06, "loss": 0.7385, "step": 184000 }, { "epoch": 15.29, "learning_rate": 1.9620652384779533e-06, "loss": 0.7485, "step": 184010 }, { "epoch": 15.3, "learning_rate": 1.9619543829504196e-06, "loss": 0.7835, "step": 184020 }, { "epoch": 15.3, "learning_rate": 1.961843527422886e-06, "loss": 0.7194, "step": 184030 }, { "epoch": 15.3, "learning_rate": 1.961732671895352e-06, "loss": 0.6965, "step": 184040 }, { "epoch": 15.3, "learning_rate": 1.9616218163678185e-06, "loss": 0.7502, "step": 184050 }, { "epoch": 15.3, "learning_rate": 1.9615109608402848e-06, "loss": 0.7984, "step": 184060 }, { "epoch": 15.3, "learning_rate": 1.961400105312751e-06, "loss": 0.7848, "step": 184070 }, { "epoch": 15.3, "learning_rate": 1.9612892497852174e-06, "loss": 0.7718, "step": 184080 }, { "epoch": 15.3, "learning_rate": 1.9611783942576837e-06, "loss": 0.7881, "step": 184090 }, { "epoch": 15.3, "learning_rate": 1.96106753873015e-06, "loss": 0.7829, "step": 184100 }, { "epoch": 15.3, "learning_rate": 1.9609566832026163e-06, "loss": 0.7956, "step": 184110 }, { "epoch": 15.3, "learning_rate": 1.960845827675082e-06, "loss": 0.8625, "step": 184120 }, { "epoch": 15.3, "learning_rate": 1.9607349721475484e-06, "loss": 0.7731, "step": 184130 }, { "epoch": 15.31, "learning_rate": 1.9606241166200147e-06, "loss": 0.8323, "step": 184140 }, { "epoch": 15.31, "learning_rate": 1.960513261092481e-06, "loss": 0.7579, "step": 184150 }, { "epoch": 15.31, "learning_rate": 1.9604024055649473e-06, "loss": 0.7839, "step": 184160 }, { "epoch": 15.31, "learning_rate": 1.9602915500374136e-06, "loss": 0.7721, "step": 184170 }, { "epoch": 15.31, "learning_rate": 1.96018069450988e-06, "loss": 0.77, "step": 184180 }, { "epoch": 15.31, "learning_rate": 1.960069838982346e-06, "loss": 0.7747, "step": 184190 }, { "epoch": 15.31, "learning_rate": 1.9599589834548125e-06, "loss": 0.8339, "step": 184200 }, { "epoch": 15.31, "learning_rate": 1.9598481279272788e-06, "loss": 0.7269, "step": 184210 }, { "epoch": 15.31, "learning_rate": 1.959737272399745e-06, "loss": 0.7594, "step": 184220 }, { "epoch": 15.31, "learning_rate": 1.9596264168722114e-06, "loss": 0.7255, "step": 184230 }, { "epoch": 15.31, "learning_rate": 1.9595155613446772e-06, "loss": 0.8415, "step": 184240 }, { "epoch": 15.31, "learning_rate": 1.9594047058171435e-06, "loss": 0.7537, "step": 184250 }, { "epoch": 15.32, "learning_rate": 1.95929385028961e-06, "loss": 0.764, "step": 184260 }, { "epoch": 15.32, "learning_rate": 1.959182994762076e-06, "loss": 0.8136, "step": 184270 }, { "epoch": 15.32, "learning_rate": 1.9590721392345424e-06, "loss": 0.7583, "step": 184280 }, { "epoch": 15.32, "learning_rate": 1.9589612837070087e-06, "loss": 0.7171, "step": 184290 }, { "epoch": 15.32, "learning_rate": 1.958850428179475e-06, "loss": 0.7436, "step": 184300 }, { "epoch": 15.32, "learning_rate": 1.9587395726519413e-06, "loss": 0.7795, "step": 184310 }, { "epoch": 15.32, "learning_rate": 1.9586287171244076e-06, "loss": 0.7909, "step": 184320 }, { "epoch": 15.32, "learning_rate": 1.958517861596874e-06, "loss": 0.7136, "step": 184330 }, { "epoch": 15.32, "learning_rate": 1.95840700606934e-06, "loss": 0.7809, "step": 184340 }, { "epoch": 15.32, "learning_rate": 1.9582961505418065e-06, "loss": 0.7105, "step": 184350 }, { "epoch": 15.32, "learning_rate": 1.958196380567026e-06, "loss": 0.7922, "step": 184360 }, { "epoch": 15.32, "learning_rate": 1.958085525039492e-06, "loss": 0.845, "step": 184370 }, { "epoch": 15.33, "learning_rate": 1.9579746695119586e-06, "loss": 0.7448, "step": 184380 }, { "epoch": 15.33, "learning_rate": 1.957863813984425e-06, "loss": 0.7364, "step": 184390 }, { "epoch": 15.33, "learning_rate": 1.9577529584568912e-06, "loss": 0.7465, "step": 184400 }, { "epoch": 15.33, "learning_rate": 1.957642102929357e-06, "loss": 0.737, "step": 184410 }, { "epoch": 15.33, "learning_rate": 1.9575312474018234e-06, "loss": 0.8114, "step": 184420 }, { "epoch": 15.33, "learning_rate": 1.9574203918742897e-06, "loss": 0.7618, "step": 184430 }, { "epoch": 15.33, "learning_rate": 1.957309536346756e-06, "loss": 0.8087, "step": 184440 }, { "epoch": 15.33, "learning_rate": 1.9571986808192223e-06, "loss": 0.7925, "step": 184450 }, { "epoch": 15.33, "learning_rate": 1.9570878252916886e-06, "loss": 0.7428, "step": 184460 }, { "epoch": 15.33, "learning_rate": 1.956976969764155e-06, "loss": 0.8374, "step": 184470 }, { "epoch": 15.33, "learning_rate": 1.956866114236621e-06, "loss": 0.8094, "step": 184480 }, { "epoch": 15.33, "learning_rate": 1.956755258709087e-06, "loss": 0.7854, "step": 184490 }, { "epoch": 15.34, "learning_rate": 1.9566444031815537e-06, "loss": 0.8008, "step": 184500 }, { "epoch": 15.34, "learning_rate": 1.95653354765402e-06, "loss": 0.7571, "step": 184510 }, { "epoch": 15.34, "learning_rate": 1.9564226921264863e-06, "loss": 0.8666, "step": 184520 }, { "epoch": 15.34, "learning_rate": 1.956311836598952e-06, "loss": 0.7017, "step": 184530 }, { "epoch": 15.34, "learning_rate": 1.9562009810714185e-06, "loss": 0.7118, "step": 184540 }, { "epoch": 15.34, "learning_rate": 1.956090125543885e-06, "loss": 0.7796, "step": 184550 }, { "epoch": 15.34, "learning_rate": 1.955979270016351e-06, "loss": 0.8317, "step": 184560 }, { "epoch": 15.34, "learning_rate": 1.9558684144888174e-06, "loss": 0.8606, "step": 184570 }, { "epoch": 15.34, "learning_rate": 1.9557575589612837e-06, "loss": 0.7844, "step": 184580 }, { "epoch": 15.34, "learning_rate": 1.95564670343375e-06, "loss": 0.7106, "step": 184590 }, { "epoch": 15.34, "learning_rate": 1.9555358479062163e-06, "loss": 0.7898, "step": 184600 }, { "epoch": 15.34, "learning_rate": 1.955424992378682e-06, "loss": 0.7259, "step": 184610 }, { "epoch": 15.35, "learning_rate": 1.9553141368511484e-06, "loss": 0.8233, "step": 184620 }, { "epoch": 15.35, "learning_rate": 1.955203281323615e-06, "loss": 0.798, "step": 184630 }, { "epoch": 15.35, "learning_rate": 1.9550924257960815e-06, "loss": 0.7424, "step": 184640 }, { "epoch": 15.35, "learning_rate": 1.9549815702685473e-06, "loss": 0.7562, "step": 184650 }, { "epoch": 15.35, "learning_rate": 1.9548707147410136e-06, "loss": 0.756, "step": 184660 }, { "epoch": 15.35, "learning_rate": 1.95475985921348e-06, "loss": 0.7373, "step": 184670 }, { "epoch": 15.35, "learning_rate": 1.9546490036859462e-06, "loss": 0.8331, "step": 184680 }, { "epoch": 15.35, "learning_rate": 1.9545381481584125e-06, "loss": 0.7666, "step": 184690 }, { "epoch": 15.35, "learning_rate": 1.954427292630879e-06, "loss": 0.8051, "step": 184700 }, { "epoch": 15.35, "learning_rate": 1.954316437103345e-06, "loss": 0.7679, "step": 184710 }, { "epoch": 15.35, "learning_rate": 1.954205581575811e-06, "loss": 0.7963, "step": 184720 }, { "epoch": 15.35, "learning_rate": 1.9540947260482773e-06, "loss": 0.8098, "step": 184730 }, { "epoch": 15.36, "learning_rate": 1.9539838705207436e-06, "loss": 0.7108, "step": 184740 }, { "epoch": 15.36, "learning_rate": 1.9538730149932103e-06, "loss": 0.7973, "step": 184750 }, { "epoch": 15.36, "learning_rate": 1.953762159465676e-06, "loss": 0.7647, "step": 184760 }, { "epoch": 15.36, "learning_rate": 1.9536513039381424e-06, "loss": 0.8112, "step": 184770 }, { "epoch": 15.36, "learning_rate": 1.9535404484106087e-06, "loss": 0.7774, "step": 184780 }, { "epoch": 15.36, "learning_rate": 1.953429592883075e-06, "loss": 0.8014, "step": 184790 }, { "epoch": 15.36, "learning_rate": 1.9533187373555413e-06, "loss": 0.8178, "step": 184800 }, { "epoch": 15.36, "learning_rate": 1.9532078818280076e-06, "loss": 0.7285, "step": 184810 }, { "epoch": 15.36, "learning_rate": 1.953097026300474e-06, "loss": 0.7221, "step": 184820 }, { "epoch": 15.36, "learning_rate": 1.9529861707729402e-06, "loss": 0.7554, "step": 184830 }, { "epoch": 15.36, "learning_rate": 1.952875315245406e-06, "loss": 0.7349, "step": 184840 }, { "epoch": 15.36, "learning_rate": 1.9527644597178724e-06, "loss": 0.7615, "step": 184850 }, { "epoch": 15.37, "learning_rate": 1.9526536041903387e-06, "loss": 0.7618, "step": 184860 }, { "epoch": 15.37, "learning_rate": 1.9525427486628054e-06, "loss": 0.8164, "step": 184870 }, { "epoch": 15.37, "learning_rate": 1.9524318931352713e-06, "loss": 0.7579, "step": 184880 }, { "epoch": 15.37, "learning_rate": 1.9523210376077376e-06, "loss": 0.797, "step": 184890 }, { "epoch": 15.37, "learning_rate": 1.952210182080204e-06, "loss": 0.8069, "step": 184900 }, { "epoch": 15.37, "learning_rate": 1.95209932655267e-06, "loss": 0.7051, "step": 184910 }, { "epoch": 15.37, "learning_rate": 1.9519884710251365e-06, "loss": 0.8156, "step": 184920 }, { "epoch": 15.37, "learning_rate": 1.9518776154976027e-06, "loss": 0.7025, "step": 184930 }, { "epoch": 15.37, "learning_rate": 1.951766759970069e-06, "loss": 0.7633, "step": 184940 }, { "epoch": 15.37, "learning_rate": 1.9516559044425353e-06, "loss": 0.7437, "step": 184950 }, { "epoch": 15.37, "learning_rate": 1.951545048915001e-06, "loss": 0.7505, "step": 184960 }, { "epoch": 15.37, "learning_rate": 1.9514341933874675e-06, "loss": 0.7969, "step": 184970 }, { "epoch": 15.38, "learning_rate": 1.951323337859934e-06, "loss": 0.7979, "step": 184980 }, { "epoch": 15.38, "learning_rate": 1.9512124823324e-06, "loss": 0.7464, "step": 184990 }, { "epoch": 15.38, "learning_rate": 1.9511016268048664e-06, "loss": 0.7467, "step": 185000 }, { "epoch": 15.38, "learning_rate": 1.9509907712773327e-06, "loss": 0.7947, "step": 185010 }, { "epoch": 15.38, "learning_rate": 1.950879915749799e-06, "loss": 0.7888, "step": 185020 }, { "epoch": 15.38, "learning_rate": 1.9507690602222653e-06, "loss": 0.8591, "step": 185030 }, { "epoch": 15.38, "learning_rate": 1.9506582046947316e-06, "loss": 0.767, "step": 185040 }, { "epoch": 15.38, "learning_rate": 1.950547349167198e-06, "loss": 0.817, "step": 185050 }, { "epoch": 15.38, "learning_rate": 1.950436493639664e-06, "loss": 0.7643, "step": 185060 }, { "epoch": 15.38, "learning_rate": 1.95032563811213e-06, "loss": 0.7917, "step": 185070 }, { "epoch": 15.38, "learning_rate": 1.9502147825845963e-06, "loss": 0.7678, "step": 185080 }, { "epoch": 15.38, "learning_rate": 1.9501039270570626e-06, "loss": 0.8038, "step": 185090 }, { "epoch": 15.39, "learning_rate": 1.949993071529529e-06, "loss": 0.7074, "step": 185100 }, { "epoch": 15.39, "learning_rate": 1.9498822160019952e-06, "loss": 0.7579, "step": 185110 }, { "epoch": 15.39, "learning_rate": 1.9497713604744615e-06, "loss": 0.7964, "step": 185120 }, { "epoch": 15.39, "learning_rate": 1.949660504946928e-06, "loss": 0.8007, "step": 185130 }, { "epoch": 15.39, "learning_rate": 1.949549649419394e-06, "loss": 0.7809, "step": 185140 }, { "epoch": 15.39, "learning_rate": 1.9494387938918604e-06, "loss": 0.7705, "step": 185150 }, { "epoch": 15.39, "learning_rate": 1.9493279383643267e-06, "loss": 0.7959, "step": 185160 }, { "epoch": 15.39, "learning_rate": 1.949217082836793e-06, "loss": 0.8272, "step": 185170 }, { "epoch": 15.39, "learning_rate": 1.9491062273092593e-06, "loss": 0.752, "step": 185180 }, { "epoch": 15.39, "learning_rate": 1.948995371781725e-06, "loss": 0.6985, "step": 185190 }, { "epoch": 15.39, "learning_rate": 1.9488845162541915e-06, "loss": 0.7203, "step": 185200 }, { "epoch": 15.39, "learning_rate": 1.9487736607266577e-06, "loss": 0.7911, "step": 185210 }, { "epoch": 15.4, "learning_rate": 1.948662805199124e-06, "loss": 0.792, "step": 185220 }, { "epoch": 15.4, "learning_rate": 1.9485519496715903e-06, "loss": 0.8301, "step": 185230 }, { "epoch": 15.4, "learning_rate": 1.9484410941440566e-06, "loss": 0.8074, "step": 185240 }, { "epoch": 15.4, "learning_rate": 1.948330238616523e-06, "loss": 0.7556, "step": 185250 }, { "epoch": 15.4, "learning_rate": 1.9482193830889892e-06, "loss": 0.7902, "step": 185260 }, { "epoch": 15.4, "learning_rate": 1.9481085275614555e-06, "loss": 0.8023, "step": 185270 }, { "epoch": 15.4, "learning_rate": 1.947997672033922e-06, "loss": 0.8226, "step": 185280 }, { "epoch": 15.4, "learning_rate": 1.947886816506388e-06, "loss": 0.8243, "step": 185290 }, { "epoch": 15.4, "learning_rate": 1.9477759609788544e-06, "loss": 0.7809, "step": 185300 }, { "epoch": 15.4, "learning_rate": 1.9476651054513203e-06, "loss": 0.771, "step": 185310 }, { "epoch": 15.4, "learning_rate": 1.9475542499237866e-06, "loss": 0.7851, "step": 185320 }, { "epoch": 15.4, "learning_rate": 1.947443394396253e-06, "loss": 0.7827, "step": 185330 }, { "epoch": 15.41, "learning_rate": 1.947332538868719e-06, "loss": 0.8143, "step": 185340 }, { "epoch": 15.41, "learning_rate": 1.9472216833411855e-06, "loss": 0.7423, "step": 185350 }, { "epoch": 15.41, "learning_rate": 1.9471108278136518e-06, "loss": 0.8045, "step": 185360 }, { "epoch": 15.41, "learning_rate": 1.946999972286118e-06, "loss": 0.7998, "step": 185370 }, { "epoch": 15.41, "learning_rate": 1.9468891167585843e-06, "loss": 0.7691, "step": 185380 }, { "epoch": 15.41, "learning_rate": 1.9467782612310506e-06, "loss": 0.7681, "step": 185390 }, { "epoch": 15.41, "learning_rate": 1.946667405703517e-06, "loss": 0.8119, "step": 185400 }, { "epoch": 15.41, "learning_rate": 1.9465565501759832e-06, "loss": 0.7167, "step": 185410 }, { "epoch": 15.41, "learning_rate": 1.9464456946484495e-06, "loss": 0.7651, "step": 185420 }, { "epoch": 15.41, "learning_rate": 1.9463348391209154e-06, "loss": 0.722, "step": 185430 }, { "epoch": 15.41, "learning_rate": 1.9462239835933817e-06, "loss": 0.7916, "step": 185440 }, { "epoch": 15.41, "learning_rate": 1.946113128065848e-06, "loss": 0.7809, "step": 185450 }, { "epoch": 15.42, "learning_rate": 1.9460022725383143e-06, "loss": 0.7868, "step": 185460 }, { "epoch": 15.42, "learning_rate": 1.9458914170107806e-06, "loss": 0.7911, "step": 185470 }, { "epoch": 15.42, "learning_rate": 1.945780561483247e-06, "loss": 0.7452, "step": 185480 }, { "epoch": 15.42, "learning_rate": 1.945669705955713e-06, "loss": 0.7442, "step": 185490 }, { "epoch": 15.42, "learning_rate": 1.9455588504281795e-06, "loss": 0.7545, "step": 185500 }, { "epoch": 15.42, "learning_rate": 1.9454479949006458e-06, "loss": 0.8091, "step": 185510 }, { "epoch": 15.42, "learning_rate": 1.945337139373112e-06, "loss": 0.8759, "step": 185520 }, { "epoch": 15.42, "learning_rate": 1.9452262838455784e-06, "loss": 0.698, "step": 185530 }, { "epoch": 15.42, "learning_rate": 1.9451154283180442e-06, "loss": 0.7232, "step": 185540 }, { "epoch": 15.42, "learning_rate": 1.9450045727905105e-06, "loss": 0.764, "step": 185550 }, { "epoch": 15.42, "learning_rate": 1.944893717262977e-06, "loss": 0.8268, "step": 185560 }, { "epoch": 15.42, "learning_rate": 1.944782861735443e-06, "loss": 0.8, "step": 185570 }, { "epoch": 15.43, "learning_rate": 1.9446720062079094e-06, "loss": 0.7566, "step": 185580 }, { "epoch": 15.43, "learning_rate": 1.9445611506803757e-06, "loss": 0.7204, "step": 185590 }, { "epoch": 15.43, "learning_rate": 1.944450295152842e-06, "loss": 0.7498, "step": 185600 }, { "epoch": 15.43, "learning_rate": 1.9443394396253083e-06, "loss": 0.7759, "step": 185610 }, { "epoch": 15.43, "learning_rate": 1.9442285840977746e-06, "loss": 0.7906, "step": 185620 }, { "epoch": 15.43, "learning_rate": 1.944117728570241e-06, "loss": 0.8019, "step": 185630 }, { "epoch": 15.43, "learning_rate": 1.944006873042707e-06, "loss": 0.7476, "step": 185640 }, { "epoch": 15.43, "learning_rate": 1.9438960175151735e-06, "loss": 0.8197, "step": 185650 }, { "epoch": 15.43, "learning_rate": 1.9437851619876393e-06, "loss": 0.7214, "step": 185660 }, { "epoch": 15.43, "learning_rate": 1.9436743064601056e-06, "loss": 0.8358, "step": 185670 }, { "epoch": 15.43, "learning_rate": 1.943563450932572e-06, "loss": 0.8388, "step": 185680 }, { "epoch": 15.43, "learning_rate": 1.9434525954050382e-06, "loss": 0.7693, "step": 185690 }, { "epoch": 15.44, "learning_rate": 1.9433417398775045e-06, "loss": 0.7602, "step": 185700 }, { "epoch": 15.44, "learning_rate": 1.943230884349971e-06, "loss": 0.8323, "step": 185710 }, { "epoch": 15.44, "learning_rate": 1.943120028822437e-06, "loss": 0.7224, "step": 185720 }, { "epoch": 15.44, "learning_rate": 1.9430091732949034e-06, "loss": 0.7614, "step": 185730 }, { "epoch": 15.44, "learning_rate": 1.9428983177673697e-06, "loss": 0.8023, "step": 185740 }, { "epoch": 15.44, "learning_rate": 1.942787462239836e-06, "loss": 0.7692, "step": 185750 }, { "epoch": 15.44, "learning_rate": 1.9426766067123023e-06, "loss": 0.7989, "step": 185760 }, { "epoch": 15.44, "learning_rate": 1.9425657511847686e-06, "loss": 0.8275, "step": 185770 }, { "epoch": 15.44, "learning_rate": 1.9424548956572345e-06, "loss": 0.7917, "step": 185780 }, { "epoch": 15.44, "learning_rate": 1.9423440401297008e-06, "loss": 0.788, "step": 185790 }, { "epoch": 15.44, "learning_rate": 1.942233184602167e-06, "loss": 0.7498, "step": 185800 }, { "epoch": 15.44, "learning_rate": 1.9421223290746334e-06, "loss": 0.7428, "step": 185810 }, { "epoch": 15.45, "learning_rate": 1.9420114735470996e-06, "loss": 0.8085, "step": 185820 }, { "epoch": 15.45, "learning_rate": 1.941900618019566e-06, "loss": 0.779, "step": 185830 }, { "epoch": 15.45, "learning_rate": 1.9417897624920322e-06, "loss": 0.7192, "step": 185840 }, { "epoch": 15.45, "learning_rate": 1.941678906964498e-06, "loss": 0.7764, "step": 185850 }, { "epoch": 15.45, "learning_rate": 1.941568051436965e-06, "loss": 0.8021, "step": 185860 }, { "epoch": 15.45, "learning_rate": 1.941457195909431e-06, "loss": 0.8019, "step": 185870 }, { "epoch": 15.45, "learning_rate": 1.9413463403818974e-06, "loss": 0.7175, "step": 185880 }, { "epoch": 15.45, "learning_rate": 1.9412354848543637e-06, "loss": 0.8094, "step": 185890 }, { "epoch": 15.45, "learning_rate": 1.9411246293268296e-06, "loss": 0.7945, "step": 185900 }, { "epoch": 15.45, "learning_rate": 1.941013773799296e-06, "loss": 0.7305, "step": 185910 }, { "epoch": 15.45, "learning_rate": 1.940902918271762e-06, "loss": 0.8369, "step": 185920 }, { "epoch": 15.45, "learning_rate": 1.9407920627442285e-06, "loss": 0.8282, "step": 185930 }, { "epoch": 15.46, "learning_rate": 1.9406812072166948e-06, "loss": 0.7517, "step": 185940 }, { "epoch": 15.46, "learning_rate": 1.940570351689161e-06, "loss": 0.7951, "step": 185950 }, { "epoch": 15.46, "learning_rate": 1.9404594961616274e-06, "loss": 0.7631, "step": 185960 }, { "epoch": 15.46, "learning_rate": 1.9403486406340932e-06, "loss": 0.8465, "step": 185970 }, { "epoch": 15.46, "learning_rate": 1.94023778510656e-06, "loss": 0.8265, "step": 185980 }, { "epoch": 15.46, "learning_rate": 1.9401269295790262e-06, "loss": 0.7359, "step": 185990 }, { "epoch": 15.46, "learning_rate": 1.9400160740514925e-06, "loss": 0.7659, "step": 186000 }, { "epoch": 15.46, "learning_rate": 1.9399052185239584e-06, "loss": 0.7459, "step": 186010 }, { "epoch": 15.46, "learning_rate": 1.9397943629964247e-06, "loss": 0.7971, "step": 186020 }, { "epoch": 15.46, "learning_rate": 1.939683507468891e-06, "loss": 0.7371, "step": 186030 }, { "epoch": 15.46, "learning_rate": 1.9395726519413573e-06, "loss": 0.7631, "step": 186040 }, { "epoch": 15.46, "learning_rate": 1.9394617964138236e-06, "loss": 0.7657, "step": 186050 }, { "epoch": 15.47, "learning_rate": 1.93935094088629e-06, "loss": 0.7375, "step": 186060 }, { "epoch": 15.47, "learning_rate": 1.939240085358756e-06, "loss": 0.7585, "step": 186070 }, { "epoch": 15.47, "learning_rate": 1.9391292298312225e-06, "loss": 0.8484, "step": 186080 }, { "epoch": 15.47, "learning_rate": 1.9390183743036883e-06, "loss": 0.7605, "step": 186090 }, { "epoch": 15.47, "learning_rate": 1.938907518776155e-06, "loss": 0.7158, "step": 186100 }, { "epoch": 15.47, "learning_rate": 1.9387966632486214e-06, "loss": 0.7838, "step": 186110 }, { "epoch": 15.47, "learning_rate": 1.9386858077210877e-06, "loss": 0.7615, "step": 186120 }, { "epoch": 15.47, "learning_rate": 1.9385749521935535e-06, "loss": 0.7904, "step": 186130 }, { "epoch": 15.47, "learning_rate": 1.93846409666602e-06, "loss": 0.7953, "step": 186140 }, { "epoch": 15.47, "learning_rate": 1.938353241138486e-06, "loss": 0.7419, "step": 186150 }, { "epoch": 15.47, "learning_rate": 1.9382423856109524e-06, "loss": 0.7614, "step": 186160 }, { "epoch": 15.47, "learning_rate": 1.9381315300834187e-06, "loss": 0.7959, "step": 186170 }, { "epoch": 15.48, "learning_rate": 1.938020674555885e-06, "loss": 0.7964, "step": 186180 }, { "epoch": 15.48, "learning_rate": 1.9379098190283513e-06, "loss": 0.7917, "step": 186190 }, { "epoch": 15.48, "learning_rate": 1.9377989635008176e-06, "loss": 0.7752, "step": 186200 }, { "epoch": 15.48, "learning_rate": 1.9376881079732835e-06, "loss": 0.7662, "step": 186210 }, { "epoch": 15.48, "learning_rate": 1.93757725244575e-06, "loss": 0.8226, "step": 186220 }, { "epoch": 15.48, "learning_rate": 1.9374663969182165e-06, "loss": 0.8025, "step": 186230 }, { "epoch": 15.48, "learning_rate": 1.9373555413906828e-06, "loss": 0.7497, "step": 186240 }, { "epoch": 15.48, "learning_rate": 1.9372446858631487e-06, "loss": 0.7455, "step": 186250 }, { "epoch": 15.48, "learning_rate": 1.937133830335615e-06, "loss": 0.7415, "step": 186260 }, { "epoch": 15.48, "learning_rate": 1.9370229748080812e-06, "loss": 0.816, "step": 186270 }, { "epoch": 15.48, "learning_rate": 1.9369121192805475e-06, "loss": 0.6911, "step": 186280 }, { "epoch": 15.48, "learning_rate": 1.936801263753014e-06, "loss": 0.7105, "step": 186290 }, { "epoch": 15.48, "learning_rate": 1.93669040822548e-06, "loss": 0.7582, "step": 186300 }, { "epoch": 15.49, "learning_rate": 1.9365795526979464e-06, "loss": 0.7885, "step": 186310 }, { "epoch": 15.49, "learning_rate": 1.9364686971704123e-06, "loss": 0.8284, "step": 186320 }, { "epoch": 15.49, "learning_rate": 1.9363578416428786e-06, "loss": 0.7827, "step": 186330 }, { "epoch": 15.49, "learning_rate": 1.936246986115345e-06, "loss": 0.7957, "step": 186340 }, { "epoch": 15.49, "learning_rate": 1.9361361305878116e-06, "loss": 0.769, "step": 186350 }, { "epoch": 15.49, "learning_rate": 1.9360252750602775e-06, "loss": 0.737, "step": 186360 }, { "epoch": 15.49, "learning_rate": 1.9359144195327438e-06, "loss": 0.7454, "step": 186370 }, { "epoch": 15.49, "learning_rate": 1.93580356400521e-06, "loss": 0.7632, "step": 186380 }, { "epoch": 15.49, "learning_rate": 1.9356927084776764e-06, "loss": 0.7351, "step": 186390 }, { "epoch": 15.49, "learning_rate": 1.9355818529501427e-06, "loss": 0.7386, "step": 186400 }, { "epoch": 15.49, "learning_rate": 1.935470997422609e-06, "loss": 0.7252, "step": 186410 }, { "epoch": 15.49, "learning_rate": 1.9353601418950752e-06, "loss": 0.7567, "step": 186420 }, { "epoch": 15.5, "learning_rate": 1.9352492863675415e-06, "loss": 0.789, "step": 186430 }, { "epoch": 15.5, "learning_rate": 1.9351384308400074e-06, "loss": 0.7316, "step": 186440 }, { "epoch": 15.5, "learning_rate": 1.9350275753124737e-06, "loss": 0.7062, "step": 186450 }, { "epoch": 15.5, "learning_rate": 1.93491671978494e-06, "loss": 0.7691, "step": 186460 }, { "epoch": 15.5, "learning_rate": 1.9348058642574067e-06, "loss": 0.8004, "step": 186470 }, { "epoch": 15.5, "learning_rate": 1.9346950087298726e-06, "loss": 0.8185, "step": 186480 }, { "epoch": 15.5, "learning_rate": 1.934584153202339e-06, "loss": 0.7363, "step": 186490 }, { "epoch": 15.5, "learning_rate": 1.934473297674805e-06, "loss": 0.7591, "step": 186500 }, { "epoch": 15.5, "learning_rate": 1.9343624421472715e-06, "loss": 0.8034, "step": 186510 }, { "epoch": 15.5, "learning_rate": 1.9342515866197378e-06, "loss": 0.7912, "step": 186520 }, { "epoch": 15.5, "learning_rate": 1.934140731092204e-06, "loss": 0.7804, "step": 186530 }, { "epoch": 15.5, "learning_rate": 1.9340298755646704e-06, "loss": 0.7078, "step": 186540 }, { "epoch": 15.51, "learning_rate": 1.9339190200371367e-06, "loss": 0.6884, "step": 186550 }, { "epoch": 15.51, "learning_rate": 1.9338081645096025e-06, "loss": 0.7581, "step": 186560 }, { "epoch": 15.51, "learning_rate": 1.933697308982069e-06, "loss": 0.8304, "step": 186570 }, { "epoch": 15.51, "learning_rate": 1.933586453454535e-06, "loss": 0.7735, "step": 186580 }, { "epoch": 15.51, "learning_rate": 1.933475597927002e-06, "loss": 0.7664, "step": 186590 }, { "epoch": 15.51, "learning_rate": 1.9333647423994677e-06, "loss": 0.7229, "step": 186600 }, { "epoch": 15.51, "learning_rate": 1.933253886871934e-06, "loss": 0.7286, "step": 186610 }, { "epoch": 15.51, "learning_rate": 1.9331430313444003e-06, "loss": 0.8448, "step": 186620 }, { "epoch": 15.51, "learning_rate": 1.9330321758168666e-06, "loss": 0.7775, "step": 186630 }, { "epoch": 15.51, "learning_rate": 1.932921320289333e-06, "loss": 0.7231, "step": 186640 }, { "epoch": 15.51, "learning_rate": 1.932810464761799e-06, "loss": 0.7406, "step": 186650 }, { "epoch": 15.51, "learning_rate": 1.9326996092342655e-06, "loss": 0.7829, "step": 186660 }, { "epoch": 15.52, "learning_rate": 1.9325887537067318e-06, "loss": 0.8644, "step": 186670 }, { "epoch": 15.52, "learning_rate": 1.9324778981791977e-06, "loss": 0.7555, "step": 186680 }, { "epoch": 15.52, "learning_rate": 1.932367042651664e-06, "loss": 0.7511, "step": 186690 }, { "epoch": 15.52, "learning_rate": 1.9322561871241302e-06, "loss": 0.7694, "step": 186700 }, { "epoch": 15.52, "learning_rate": 1.93215641714935e-06, "loss": 0.7551, "step": 186710 }, { "epoch": 15.52, "learning_rate": 1.9320455616218165e-06, "loss": 0.7761, "step": 186720 }, { "epoch": 15.52, "learning_rate": 1.9319347060942824e-06, "loss": 0.7512, "step": 186730 }, { "epoch": 15.52, "learning_rate": 1.9318238505667487e-06, "loss": 0.7151, "step": 186740 }, { "epoch": 15.52, "learning_rate": 1.931712995039215e-06, "loss": 0.7909, "step": 186750 }, { "epoch": 15.52, "learning_rate": 1.9316021395116813e-06, "loss": 0.7514, "step": 186760 }, { "epoch": 15.52, "learning_rate": 1.9314912839841476e-06, "loss": 0.7366, "step": 186770 }, { "epoch": 15.52, "learning_rate": 1.931380428456614e-06, "loss": 0.7933, "step": 186780 }, { "epoch": 15.53, "learning_rate": 1.93126957292908e-06, "loss": 0.7241, "step": 186790 }, { "epoch": 15.53, "learning_rate": 1.9311587174015464e-06, "loss": 0.7453, "step": 186800 }, { "epoch": 15.53, "learning_rate": 1.9310478618740127e-06, "loss": 0.7955, "step": 186810 }, { "epoch": 15.53, "learning_rate": 1.930937006346479e-06, "loss": 0.8674, "step": 186820 }, { "epoch": 15.53, "learning_rate": 1.9308261508189453e-06, "loss": 0.8421, "step": 186830 }, { "epoch": 15.53, "learning_rate": 1.9307152952914116e-06, "loss": 0.7695, "step": 186840 }, { "epoch": 15.53, "learning_rate": 1.9306044397638775e-06, "loss": 0.8023, "step": 186850 }, { "epoch": 15.53, "learning_rate": 1.930493584236344e-06, "loss": 0.7026, "step": 186860 }, { "epoch": 15.53, "learning_rate": 1.93038272870881e-06, "loss": 0.7531, "step": 186870 }, { "epoch": 15.53, "learning_rate": 1.9302718731812764e-06, "loss": 0.8141, "step": 186880 }, { "epoch": 15.53, "learning_rate": 1.9301610176537427e-06, "loss": 0.7769, "step": 186890 }, { "epoch": 15.53, "learning_rate": 1.930050162126209e-06, "loss": 0.7736, "step": 186900 }, { "epoch": 15.54, "learning_rate": 1.9299393065986753e-06, "loss": 0.8353, "step": 186910 }, { "epoch": 15.54, "learning_rate": 1.929828451071141e-06, "loss": 0.8221, "step": 186920 }, { "epoch": 15.54, "learning_rate": 1.929717595543608e-06, "loss": 0.794, "step": 186930 }, { "epoch": 15.54, "learning_rate": 1.929606740016074e-06, "loss": 0.7695, "step": 186940 }, { "epoch": 15.54, "learning_rate": 1.9294958844885405e-06, "loss": 0.8162, "step": 186950 }, { "epoch": 15.54, "learning_rate": 1.9293850289610063e-06, "loss": 0.7483, "step": 186960 }, { "epoch": 15.54, "learning_rate": 1.9292741734334726e-06, "loss": 0.7657, "step": 186970 }, { "epoch": 15.54, "learning_rate": 1.929163317905939e-06, "loss": 0.7991, "step": 186980 }, { "epoch": 15.54, "learning_rate": 1.929052462378405e-06, "loss": 0.7479, "step": 186990 }, { "epoch": 15.54, "learning_rate": 1.9289416068508715e-06, "loss": 0.7678, "step": 187000 }, { "epoch": 15.54, "learning_rate": 1.928830751323338e-06, "loss": 0.8398, "step": 187010 }, { "epoch": 15.54, "learning_rate": 1.928719895795804e-06, "loss": 0.7899, "step": 187020 }, { "epoch": 15.55, "learning_rate": 1.9286090402682704e-06, "loss": 0.7677, "step": 187030 }, { "epoch": 15.55, "learning_rate": 1.9284981847407363e-06, "loss": 0.7085, "step": 187040 }, { "epoch": 15.55, "learning_rate": 1.928387329213203e-06, "loss": 0.7281, "step": 187050 }, { "epoch": 15.55, "learning_rate": 1.9282764736856693e-06, "loss": 0.712, "step": 187060 }, { "epoch": 15.55, "learning_rate": 1.9281656181581356e-06, "loss": 0.8315, "step": 187070 }, { "epoch": 15.55, "learning_rate": 1.9280547626306014e-06, "loss": 0.7776, "step": 187080 }, { "epoch": 15.55, "learning_rate": 1.9279439071030677e-06, "loss": 0.7349, "step": 187090 }, { "epoch": 15.55, "learning_rate": 1.927833051575534e-06, "loss": 0.7325, "step": 187100 }, { "epoch": 15.55, "learning_rate": 1.9277221960480003e-06, "loss": 0.7167, "step": 187110 }, { "epoch": 15.55, "learning_rate": 1.9276113405204666e-06, "loss": 0.7978, "step": 187120 }, { "epoch": 15.55, "learning_rate": 1.927500484992933e-06, "loss": 0.8261, "step": 187130 }, { "epoch": 15.55, "learning_rate": 1.9273896294653992e-06, "loss": 0.7532, "step": 187140 }, { "epoch": 15.56, "learning_rate": 1.9272787739378655e-06, "loss": 0.7427, "step": 187150 }, { "epoch": 15.56, "learning_rate": 1.9271679184103314e-06, "loss": 0.7925, "step": 187160 }, { "epoch": 15.56, "learning_rate": 1.927057062882798e-06, "loss": 0.8072, "step": 187170 }, { "epoch": 15.56, "learning_rate": 1.9269462073552644e-06, "loss": 0.8302, "step": 187180 }, { "epoch": 15.56, "learning_rate": 1.9268353518277307e-06, "loss": 0.7808, "step": 187190 }, { "epoch": 15.56, "learning_rate": 1.9267244963001966e-06, "loss": 0.7614, "step": 187200 }, { "epoch": 15.56, "learning_rate": 1.926613640772663e-06, "loss": 0.7099, "step": 187210 }, { "epoch": 15.56, "learning_rate": 1.926502785245129e-06, "loss": 0.8225, "step": 187220 }, { "epoch": 15.56, "learning_rate": 1.9263919297175954e-06, "loss": 0.808, "step": 187230 }, { "epoch": 15.56, "learning_rate": 1.9262810741900617e-06, "loss": 0.8143, "step": 187240 }, { "epoch": 15.56, "learning_rate": 1.926170218662528e-06, "loss": 0.7801, "step": 187250 }, { "epoch": 15.56, "learning_rate": 1.9260593631349943e-06, "loss": 0.8361, "step": 187260 }, { "epoch": 15.57, "learning_rate": 1.92594850760746e-06, "loss": 0.7709, "step": 187270 }, { "epoch": 15.57, "learning_rate": 1.9258376520799265e-06, "loss": 0.8315, "step": 187280 }, { "epoch": 15.57, "learning_rate": 1.925726796552393e-06, "loss": 0.7407, "step": 187290 }, { "epoch": 15.57, "learning_rate": 1.9256159410248595e-06, "loss": 0.7842, "step": 187300 }, { "epoch": 15.57, "learning_rate": 1.9255050854973254e-06, "loss": 0.7635, "step": 187310 }, { "epoch": 15.57, "learning_rate": 1.9253942299697917e-06, "loss": 0.7688, "step": 187320 }, { "epoch": 15.57, "learning_rate": 1.925283374442258e-06, "loss": 0.7735, "step": 187330 }, { "epoch": 15.57, "learning_rate": 1.9251725189147243e-06, "loss": 0.7479, "step": 187340 }, { "epoch": 15.57, "learning_rate": 1.9250616633871906e-06, "loss": 0.7426, "step": 187350 }, { "epoch": 15.57, "learning_rate": 1.924950807859657e-06, "loss": 0.7564, "step": 187360 }, { "epoch": 15.57, "learning_rate": 1.924839952332123e-06, "loss": 0.7906, "step": 187370 }, { "epoch": 15.57, "learning_rate": 1.9247290968045895e-06, "loss": 0.8283, "step": 187380 }, { "epoch": 15.58, "learning_rate": 1.9246182412770553e-06, "loss": 0.7895, "step": 187390 }, { "epoch": 15.58, "learning_rate": 1.9245073857495216e-06, "loss": 0.7462, "step": 187400 }, { "epoch": 15.58, "learning_rate": 1.924396530221988e-06, "loss": 0.7398, "step": 187410 }, { "epoch": 15.58, "learning_rate": 1.9242856746944546e-06, "loss": 0.7903, "step": 187420 }, { "epoch": 15.58, "learning_rate": 1.9241748191669205e-06, "loss": 0.7856, "step": 187430 }, { "epoch": 15.58, "learning_rate": 1.924063963639387e-06, "loss": 0.7733, "step": 187440 }, { "epoch": 15.58, "learning_rate": 1.923953108111853e-06, "loss": 0.8301, "step": 187450 }, { "epoch": 15.58, "learning_rate": 1.9238422525843194e-06, "loss": 0.7839, "step": 187460 }, { "epoch": 15.58, "learning_rate": 1.9237313970567857e-06, "loss": 0.8388, "step": 187470 }, { "epoch": 15.58, "learning_rate": 1.923620541529252e-06, "loss": 0.8082, "step": 187480 }, { "epoch": 15.58, "learning_rate": 1.9235096860017183e-06, "loss": 0.7537, "step": 187490 }, { "epoch": 15.58, "learning_rate": 1.9233988304741846e-06, "loss": 0.7359, "step": 187500 }, { "epoch": 15.59, "learning_rate": 1.9232879749466504e-06, "loss": 0.8108, "step": 187510 }, { "epoch": 15.59, "learning_rate": 1.9231771194191167e-06, "loss": 0.7534, "step": 187520 }, { "epoch": 15.59, "learning_rate": 1.923066263891583e-06, "loss": 0.8098, "step": 187530 }, { "epoch": 15.59, "learning_rate": 1.9229554083640498e-06, "loss": 0.7571, "step": 187540 }, { "epoch": 15.59, "learning_rate": 1.9228445528365156e-06, "loss": 0.7395, "step": 187550 }, { "epoch": 15.59, "learning_rate": 1.922733697308982e-06, "loss": 0.7906, "step": 187560 }, { "epoch": 15.59, "learning_rate": 1.9226228417814482e-06, "loss": 0.7573, "step": 187570 }, { "epoch": 15.59, "learning_rate": 1.9225119862539145e-06, "loss": 0.7875, "step": 187580 }, { "epoch": 15.59, "learning_rate": 1.922401130726381e-06, "loss": 0.7359, "step": 187590 }, { "epoch": 15.59, "learning_rate": 1.922290275198847e-06, "loss": 0.7212, "step": 187600 }, { "epoch": 15.59, "learning_rate": 1.9221794196713134e-06, "loss": 0.784, "step": 187610 }, { "epoch": 15.59, "learning_rate": 1.9220685641437797e-06, "loss": 0.7955, "step": 187620 }, { "epoch": 15.6, "learning_rate": 1.9219577086162456e-06, "loss": 0.7898, "step": 187630 }, { "epoch": 15.6, "learning_rate": 1.921846853088712e-06, "loss": 0.7967, "step": 187640 }, { "epoch": 15.6, "learning_rate": 1.921735997561178e-06, "loss": 0.7867, "step": 187650 }, { "epoch": 15.6, "learning_rate": 1.921625142033645e-06, "loss": 0.7967, "step": 187660 }, { "epoch": 15.6, "learning_rate": 1.9215142865061108e-06, "loss": 0.8474, "step": 187670 }, { "epoch": 15.6, "learning_rate": 1.921403430978577e-06, "loss": 0.7906, "step": 187680 }, { "epoch": 15.6, "learning_rate": 1.9212925754510433e-06, "loss": 0.7773, "step": 187690 }, { "epoch": 15.6, "learning_rate": 1.9211817199235096e-06, "loss": 0.7426, "step": 187700 }, { "epoch": 15.6, "learning_rate": 1.921070864395976e-06, "loss": 0.7594, "step": 187710 }, { "epoch": 15.6, "learning_rate": 1.9209600088684422e-06, "loss": 0.8071, "step": 187720 }, { "epoch": 15.6, "learning_rate": 1.9208491533409085e-06, "loss": 0.7811, "step": 187730 }, { "epoch": 15.6, "learning_rate": 1.9207382978133744e-06, "loss": 0.8273, "step": 187740 }, { "epoch": 15.61, "learning_rate": 1.9206274422858407e-06, "loss": 0.759, "step": 187750 }, { "epoch": 15.61, "learning_rate": 1.920516586758307e-06, "loss": 0.8207, "step": 187760 }, { "epoch": 15.61, "learning_rate": 1.9204057312307733e-06, "loss": 0.803, "step": 187770 }, { "epoch": 15.61, "learning_rate": 1.9202948757032396e-06, "loss": 0.7809, "step": 187780 }, { "epoch": 15.61, "learning_rate": 1.920184020175706e-06, "loss": 0.7488, "step": 187790 }, { "epoch": 15.61, "learning_rate": 1.920073164648172e-06, "loss": 0.7493, "step": 187800 }, { "epoch": 15.61, "learning_rate": 1.9199623091206385e-06, "loss": 0.7562, "step": 187810 }, { "epoch": 15.61, "learning_rate": 1.9198514535931048e-06, "loss": 0.8016, "step": 187820 }, { "epoch": 15.61, "learning_rate": 1.919740598065571e-06, "loss": 0.7629, "step": 187830 }, { "epoch": 15.61, "learning_rate": 1.9196297425380373e-06, "loss": 0.7661, "step": 187840 }, { "epoch": 15.61, "learning_rate": 1.9195188870105036e-06, "loss": 0.8128, "step": 187850 }, { "epoch": 15.61, "learning_rate": 1.9194080314829695e-06, "loss": 0.7823, "step": 187860 }, { "epoch": 15.62, "learning_rate": 1.919297175955436e-06, "loss": 0.7406, "step": 187870 }, { "epoch": 15.62, "learning_rate": 1.919186320427902e-06, "loss": 0.8278, "step": 187880 }, { "epoch": 15.62, "learning_rate": 1.9190754649003684e-06, "loss": 0.7773, "step": 187890 }, { "epoch": 15.62, "learning_rate": 1.9189646093728347e-06, "loss": 0.7358, "step": 187900 }, { "epoch": 15.62, "learning_rate": 1.918853753845301e-06, "loss": 0.7186, "step": 187910 }, { "epoch": 15.62, "learning_rate": 1.9187428983177673e-06, "loss": 0.8266, "step": 187920 }, { "epoch": 15.62, "learning_rate": 1.9186320427902336e-06, "loss": 0.7781, "step": 187930 }, { "epoch": 15.62, "learning_rate": 1.9185211872627e-06, "loss": 0.8101, "step": 187940 }, { "epoch": 15.62, "learning_rate": 1.918410331735166e-06, "loss": 0.7756, "step": 187950 }, { "epoch": 15.62, "learning_rate": 1.9182994762076325e-06, "loss": 0.7409, "step": 187960 }, { "epoch": 15.62, "learning_rate": 1.9181886206800988e-06, "loss": 0.7578, "step": 187970 }, { "epoch": 15.62, "learning_rate": 1.9180777651525646e-06, "loss": 0.8089, "step": 187980 }, { "epoch": 15.63, "learning_rate": 1.917966909625031e-06, "loss": 0.7499, "step": 187990 }, { "epoch": 15.63, "learning_rate": 1.9178560540974972e-06, "loss": 0.7852, "step": 188000 }, { "epoch": 15.63, "learning_rate": 1.9177451985699635e-06, "loss": 0.7513, "step": 188010 }, { "epoch": 15.63, "learning_rate": 1.91763434304243e-06, "loss": 0.827, "step": 188020 }, { "epoch": 15.63, "learning_rate": 1.917523487514896e-06, "loss": 0.8346, "step": 188030 }, { "epoch": 15.63, "learning_rate": 1.9174126319873624e-06, "loss": 0.7307, "step": 188040 }, { "epoch": 15.63, "learning_rate": 1.9173017764598287e-06, "loss": 0.8032, "step": 188050 }, { "epoch": 15.63, "learning_rate": 1.917190920932295e-06, "loss": 0.7858, "step": 188060 }, { "epoch": 15.63, "learning_rate": 1.9170800654047613e-06, "loss": 0.7838, "step": 188070 }, { "epoch": 15.63, "learning_rate": 1.9169692098772276e-06, "loss": 0.7083, "step": 188080 }, { "epoch": 15.63, "learning_rate": 1.916858354349694e-06, "loss": 0.7379, "step": 188090 }, { "epoch": 15.63, "learning_rate": 1.9167474988221598e-06, "loss": 0.786, "step": 188100 }, { "epoch": 15.64, "learning_rate": 1.916636643294626e-06, "loss": 0.7128, "step": 188110 }, { "epoch": 15.64, "learning_rate": 1.9165257877670923e-06, "loss": 0.8452, "step": 188120 }, { "epoch": 15.64, "learning_rate": 1.9164149322395586e-06, "loss": 0.8886, "step": 188130 }, { "epoch": 15.64, "learning_rate": 1.916304076712025e-06, "loss": 0.778, "step": 188140 }, { "epoch": 15.64, "learning_rate": 1.9161932211844912e-06, "loss": 0.7595, "step": 188150 }, { "epoch": 15.64, "learning_rate": 1.9160823656569575e-06, "loss": 0.7961, "step": 188160 }, { "epoch": 15.64, "learning_rate": 1.915971510129424e-06, "loss": 0.8102, "step": 188170 }, { "epoch": 15.64, "learning_rate": 1.91586065460189e-06, "loss": 0.7961, "step": 188180 }, { "epoch": 15.64, "learning_rate": 1.9157497990743564e-06, "loss": 0.7196, "step": 188190 }, { "epoch": 15.64, "learning_rate": 1.9156389435468227e-06, "loss": 0.7613, "step": 188200 }, { "epoch": 15.64, "learning_rate": 1.9155280880192886e-06, "loss": 0.747, "step": 188210 }, { "epoch": 15.64, "learning_rate": 1.915417232491755e-06, "loss": 0.82, "step": 188220 }, { "epoch": 15.65, "learning_rate": 1.915306376964221e-06, "loss": 0.7483, "step": 188230 }, { "epoch": 15.65, "learning_rate": 1.9151955214366875e-06, "loss": 0.7413, "step": 188240 }, { "epoch": 15.65, "learning_rate": 1.9150846659091538e-06, "loss": 0.722, "step": 188250 }, { "epoch": 15.65, "learning_rate": 1.91497381038162e-06, "loss": 0.7611, "step": 188260 }, { "epoch": 15.65, "learning_rate": 1.9148629548540864e-06, "loss": 0.7739, "step": 188270 }, { "epoch": 15.65, "learning_rate": 1.9147520993265526e-06, "loss": 0.8708, "step": 188280 }, { "epoch": 15.65, "learning_rate": 1.914641243799019e-06, "loss": 0.72, "step": 188290 }, { "epoch": 15.65, "learning_rate": 1.9145303882714852e-06, "loss": 0.7852, "step": 188300 }, { "epoch": 15.65, "learning_rate": 1.9144195327439515e-06, "loss": 0.7842, "step": 188310 }, { "epoch": 15.65, "learning_rate": 1.914308677216418e-06, "loss": 0.7885, "step": 188320 }, { "epoch": 15.65, "learning_rate": 1.9141978216888837e-06, "loss": 0.7363, "step": 188330 }, { "epoch": 15.65, "learning_rate": 1.91408696616135e-06, "loss": 0.7327, "step": 188340 }, { "epoch": 15.66, "learning_rate": 1.9139761106338163e-06, "loss": 0.742, "step": 188350 }, { "epoch": 15.66, "learning_rate": 1.9138652551062826e-06, "loss": 0.7449, "step": 188360 }, { "epoch": 15.66, "learning_rate": 1.913754399578749e-06, "loss": 0.7657, "step": 188370 }, { "epoch": 15.66, "learning_rate": 1.913643544051215e-06, "loss": 0.762, "step": 188380 }, { "epoch": 15.66, "learning_rate": 1.9135326885236815e-06, "loss": 0.7797, "step": 188390 }, { "epoch": 15.66, "learning_rate": 1.9134218329961478e-06, "loss": 0.7886, "step": 188400 }, { "epoch": 15.66, "learning_rate": 1.913310977468614e-06, "loss": 0.7522, "step": 188410 }, { "epoch": 15.66, "learning_rate": 1.9132001219410804e-06, "loss": 0.81, "step": 188420 }, { "epoch": 15.66, "learning_rate": 1.9130892664135467e-06, "loss": 0.8065, "step": 188430 }, { "epoch": 15.66, "learning_rate": 1.912978410886013e-06, "loss": 0.8158, "step": 188440 }, { "epoch": 15.66, "learning_rate": 1.912867555358479e-06, "loss": 0.7525, "step": 188450 }, { "epoch": 15.66, "learning_rate": 1.912756699830945e-06, "loss": 0.7799, "step": 188460 }, { "epoch": 15.67, "learning_rate": 1.9126458443034114e-06, "loss": 0.8094, "step": 188470 }, { "epoch": 15.67, "learning_rate": 1.9125349887758777e-06, "loss": 0.8028, "step": 188480 }, { "epoch": 15.67, "learning_rate": 1.912424133248344e-06, "loss": 0.7734, "step": 188490 }, { "epoch": 15.67, "learning_rate": 1.9123243632735635e-06, "loss": 0.6963, "step": 188500 }, { "epoch": 15.67, "learning_rate": 1.91221350774603e-06, "loss": 0.7368, "step": 188510 }, { "epoch": 15.67, "learning_rate": 1.912102652218496e-06, "loss": 0.8101, "step": 188520 }, { "epoch": 15.67, "learning_rate": 1.9119917966909624e-06, "loss": 0.7406, "step": 188530 }, { "epoch": 15.67, "learning_rate": 1.9118809411634287e-06, "loss": 0.7518, "step": 188540 }, { "epoch": 15.67, "learning_rate": 1.911770085635895e-06, "loss": 0.8469, "step": 188550 }, { "epoch": 15.67, "learning_rate": 1.9116592301083613e-06, "loss": 0.7961, "step": 188560 }, { "epoch": 15.67, "learning_rate": 1.9115483745808276e-06, "loss": 0.8567, "step": 188570 }, { "epoch": 15.67, "learning_rate": 1.9114375190532935e-06, "loss": 0.7384, "step": 188580 }, { "epoch": 15.68, "learning_rate": 1.9113266635257598e-06, "loss": 0.7413, "step": 188590 }, { "epoch": 15.68, "learning_rate": 1.911215807998226e-06, "loss": 0.7815, "step": 188600 }, { "epoch": 15.68, "learning_rate": 1.911104952470693e-06, "loss": 0.7673, "step": 188610 }, { "epoch": 15.68, "learning_rate": 1.9109940969431587e-06, "loss": 0.8072, "step": 188620 }, { "epoch": 15.68, "learning_rate": 1.910883241415625e-06, "loss": 0.7172, "step": 188630 }, { "epoch": 15.68, "learning_rate": 1.9107723858880913e-06, "loss": 0.7936, "step": 188640 }, { "epoch": 15.68, "learning_rate": 1.9106615303605575e-06, "loss": 0.7472, "step": 188650 }, { "epoch": 15.68, "learning_rate": 1.910550674833024e-06, "loss": 0.7407, "step": 188660 }, { "epoch": 15.68, "learning_rate": 1.91043981930549e-06, "loss": 0.8149, "step": 188670 }, { "epoch": 15.68, "learning_rate": 1.9103289637779564e-06, "loss": 0.8069, "step": 188680 }, { "epoch": 15.68, "learning_rate": 1.9102181082504223e-06, "loss": 0.7166, "step": 188690 }, { "epoch": 15.68, "learning_rate": 1.9101072527228886e-06, "loss": 0.7621, "step": 188700 }, { "epoch": 15.69, "learning_rate": 1.909996397195355e-06, "loss": 0.7658, "step": 188710 }, { "epoch": 15.69, "learning_rate": 1.909885541667821e-06, "loss": 0.8321, "step": 188720 }, { "epoch": 15.69, "learning_rate": 1.9097746861402875e-06, "loss": 0.7917, "step": 188730 }, { "epoch": 15.69, "learning_rate": 1.9096638306127538e-06, "loss": 0.7516, "step": 188740 }, { "epoch": 15.69, "learning_rate": 1.90955297508522e-06, "loss": 0.7797, "step": 188750 }, { "epoch": 15.69, "learning_rate": 1.9094421195576864e-06, "loss": 0.7859, "step": 188760 }, { "epoch": 15.69, "learning_rate": 1.9093312640301527e-06, "loss": 0.8461, "step": 188770 }, { "epoch": 15.69, "learning_rate": 1.909220408502619e-06, "loss": 0.7916, "step": 188780 }, { "epoch": 15.69, "learning_rate": 1.9091095529750853e-06, "loss": 0.7848, "step": 188790 }, { "epoch": 15.69, "learning_rate": 1.9089986974475516e-06, "loss": 0.8123, "step": 188800 }, { "epoch": 15.69, "learning_rate": 1.9088878419200174e-06, "loss": 0.766, "step": 188810 }, { "epoch": 15.69, "learning_rate": 1.9087769863924837e-06, "loss": 0.8023, "step": 188820 }, { "epoch": 15.7, "learning_rate": 1.90866613086495e-06, "loss": 0.7911, "step": 188830 }, { "epoch": 15.7, "learning_rate": 1.9085552753374163e-06, "loss": 0.7529, "step": 188840 }, { "epoch": 15.7, "learning_rate": 1.9084444198098826e-06, "loss": 0.741, "step": 188850 }, { "epoch": 15.7, "learning_rate": 1.908333564282349e-06, "loss": 0.7574, "step": 188860 }, { "epoch": 15.7, "learning_rate": 1.908222708754815e-06, "loss": 0.7489, "step": 188870 }, { "epoch": 15.7, "learning_rate": 1.9081118532272815e-06, "loss": 0.7647, "step": 188880 }, { "epoch": 15.7, "learning_rate": 1.908000997699748e-06, "loss": 0.7209, "step": 188890 }, { "epoch": 15.7, "learning_rate": 1.907890142172214e-06, "loss": 0.7656, "step": 188900 }, { "epoch": 15.7, "learning_rate": 1.9077792866446804e-06, "loss": 0.776, "step": 188910 }, { "epoch": 15.7, "learning_rate": 1.9076684311171467e-06, "loss": 0.8229, "step": 188920 }, { "epoch": 15.7, "learning_rate": 1.9075575755896125e-06, "loss": 0.7926, "step": 188930 }, { "epoch": 15.7, "learning_rate": 1.907446720062079e-06, "loss": 0.7477, "step": 188940 }, { "epoch": 15.71, "learning_rate": 1.9073358645345451e-06, "loss": 0.7617, "step": 188950 }, { "epoch": 15.71, "learning_rate": 1.9072250090070114e-06, "loss": 0.6954, "step": 188960 }, { "epoch": 15.71, "learning_rate": 1.9071141534794777e-06, "loss": 0.8428, "step": 188970 }, { "epoch": 15.71, "learning_rate": 1.9070032979519442e-06, "loss": 0.8198, "step": 188980 }, { "epoch": 15.71, "learning_rate": 1.9068924424244103e-06, "loss": 0.8011, "step": 188990 }, { "epoch": 15.71, "learning_rate": 1.9067815868968766e-06, "loss": 0.7977, "step": 189000 }, { "epoch": 15.71, "learning_rate": 1.906670731369343e-06, "loss": 0.7437, "step": 189010 }, { "epoch": 15.71, "learning_rate": 1.9065598758418092e-06, "loss": 0.8015, "step": 189020 }, { "epoch": 15.71, "learning_rate": 1.9064490203142753e-06, "loss": 0.7358, "step": 189030 }, { "epoch": 15.71, "learning_rate": 1.9063381647867416e-06, "loss": 0.781, "step": 189040 }, { "epoch": 15.71, "learning_rate": 1.9062273092592079e-06, "loss": 0.7673, "step": 189050 }, { "epoch": 15.71, "learning_rate": 1.906116453731674e-06, "loss": 0.8192, "step": 189060 }, { "epoch": 15.72, "learning_rate": 1.9060055982041403e-06, "loss": 0.7713, "step": 189070 }, { "epoch": 15.72, "learning_rate": 1.9058947426766066e-06, "loss": 0.7926, "step": 189080 }, { "epoch": 15.72, "learning_rate": 1.9057838871490728e-06, "loss": 0.7396, "step": 189090 }, { "epoch": 15.72, "learning_rate": 1.9056730316215391e-06, "loss": 0.8016, "step": 189100 }, { "epoch": 15.72, "learning_rate": 1.9055621760940054e-06, "loss": 0.7993, "step": 189110 }, { "epoch": 15.72, "learning_rate": 1.9054513205664717e-06, "loss": 0.7705, "step": 189120 }, { "epoch": 15.72, "learning_rate": 1.905340465038938e-06, "loss": 0.8558, "step": 189130 }, { "epoch": 15.72, "learning_rate": 1.9052296095114041e-06, "loss": 0.7584, "step": 189140 }, { "epoch": 15.72, "learning_rate": 1.9051187539838704e-06, "loss": 0.7584, "step": 189150 }, { "epoch": 15.72, "learning_rate": 1.9050078984563367e-06, "loss": 0.7564, "step": 189160 }, { "epoch": 15.72, "learning_rate": 1.904897042928803e-06, "loss": 0.8131, "step": 189170 }, { "epoch": 15.72, "learning_rate": 1.904786187401269e-06, "loss": 0.8272, "step": 189180 }, { "epoch": 15.73, "learning_rate": 1.9046753318737354e-06, "loss": 0.7717, "step": 189190 }, { "epoch": 15.73, "learning_rate": 1.9045644763462017e-06, "loss": 0.7928, "step": 189200 }, { "epoch": 15.73, "learning_rate": 1.904453620818668e-06, "loss": 0.7446, "step": 189210 }, { "epoch": 15.73, "learning_rate": 1.904342765291134e-06, "loss": 0.7767, "step": 189220 }, { "epoch": 15.73, "learning_rate": 1.9042319097636006e-06, "loss": 0.7687, "step": 189230 }, { "epoch": 15.73, "learning_rate": 1.9041210542360669e-06, "loss": 0.7787, "step": 189240 }, { "epoch": 15.73, "learning_rate": 1.9040101987085332e-06, "loss": 0.8117, "step": 189250 }, { "epoch": 15.73, "learning_rate": 1.9038993431809992e-06, "loss": 0.7608, "step": 189260 }, { "epoch": 15.73, "learning_rate": 1.9037884876534655e-06, "loss": 0.8027, "step": 189270 }, { "epoch": 15.73, "learning_rate": 1.9036776321259318e-06, "loss": 0.7868, "step": 189280 }, { "epoch": 15.73, "learning_rate": 1.9035667765983981e-06, "loss": 0.741, "step": 189290 }, { "epoch": 15.73, "learning_rate": 1.9034559210708642e-06, "loss": 0.7679, "step": 189300 }, { "epoch": 15.74, "learning_rate": 1.9033450655433305e-06, "loss": 0.7364, "step": 189310 }, { "epoch": 15.74, "learning_rate": 1.9032342100157968e-06, "loss": 0.7737, "step": 189320 }, { "epoch": 15.74, "learning_rate": 1.903123354488263e-06, "loss": 0.8567, "step": 189330 }, { "epoch": 15.74, "learning_rate": 1.9030124989607292e-06, "loss": 0.7299, "step": 189340 }, { "epoch": 15.74, "learning_rate": 1.9029016434331957e-06, "loss": 0.7216, "step": 189350 }, { "epoch": 15.74, "learning_rate": 1.902790787905662e-06, "loss": 0.7561, "step": 189360 }, { "epoch": 15.74, "learning_rate": 1.9026799323781283e-06, "loss": 0.7936, "step": 189370 }, { "epoch": 15.74, "learning_rate": 1.9025690768505944e-06, "loss": 0.7853, "step": 189380 }, { "epoch": 15.74, "learning_rate": 1.9024582213230607e-06, "loss": 0.7175, "step": 189390 }, { "epoch": 15.74, "learning_rate": 1.902347365795527e-06, "loss": 0.7739, "step": 189400 }, { "epoch": 15.74, "learning_rate": 1.9022365102679932e-06, "loss": 0.8042, "step": 189410 }, { "epoch": 15.74, "learning_rate": 1.9021256547404593e-06, "loss": 0.8088, "step": 189420 }, { "epoch": 15.75, "learning_rate": 1.9020147992129256e-06, "loss": 0.7539, "step": 189430 }, { "epoch": 15.75, "learning_rate": 1.901903943685392e-06, "loss": 0.7622, "step": 189440 }, { "epoch": 15.75, "learning_rate": 1.901793088157858e-06, "loss": 0.7783, "step": 189450 }, { "epoch": 15.75, "learning_rate": 1.9016822326303243e-06, "loss": 0.759, "step": 189460 }, { "epoch": 15.75, "learning_rate": 1.9015713771027908e-06, "loss": 0.8448, "step": 189470 }, { "epoch": 15.75, "learning_rate": 1.901460521575257e-06, "loss": 0.7357, "step": 189480 }, { "epoch": 15.75, "learning_rate": 1.9013496660477234e-06, "loss": 0.718, "step": 189490 }, { "epoch": 15.75, "learning_rate": 1.9012388105201895e-06, "loss": 0.8425, "step": 189500 }, { "epoch": 15.75, "learning_rate": 1.9011279549926558e-06, "loss": 0.7912, "step": 189510 }, { "epoch": 15.75, "learning_rate": 1.901017099465122e-06, "loss": 0.7963, "step": 189520 }, { "epoch": 15.75, "learning_rate": 1.9009062439375882e-06, "loss": 0.7676, "step": 189530 }, { "epoch": 15.75, "learning_rate": 1.9007953884100544e-06, "loss": 0.8102, "step": 189540 }, { "epoch": 15.76, "learning_rate": 1.9006845328825207e-06, "loss": 0.7343, "step": 189550 }, { "epoch": 15.76, "learning_rate": 1.900573677354987e-06, "loss": 0.7492, "step": 189560 }, { "epoch": 15.76, "learning_rate": 1.9004628218274531e-06, "loss": 0.7848, "step": 189570 }, { "epoch": 15.76, "learning_rate": 1.9003519662999194e-06, "loss": 0.73, "step": 189580 }, { "epoch": 15.76, "learning_rate": 1.9002411107723857e-06, "loss": 0.7768, "step": 189590 }, { "epoch": 15.76, "learning_rate": 1.9001302552448522e-06, "loss": 0.7464, "step": 189600 }, { "epoch": 15.76, "learning_rate": 1.9000193997173183e-06, "loss": 0.7915, "step": 189610 }, { "epoch": 15.76, "learning_rate": 1.8999085441897846e-06, "loss": 0.6994, "step": 189620 }, { "epoch": 15.76, "learning_rate": 1.8997976886622509e-06, "loss": 0.759, "step": 189630 }, { "epoch": 15.76, "learning_rate": 1.8996868331347172e-06, "loss": 0.7645, "step": 189640 }, { "epoch": 15.76, "learning_rate": 1.8995759776071833e-06, "loss": 0.8264, "step": 189650 }, { "epoch": 15.76, "learning_rate": 1.8994651220796496e-06, "loss": 0.7775, "step": 189660 }, { "epoch": 15.77, "learning_rate": 1.8993542665521159e-06, "loss": 0.7363, "step": 189670 }, { "epoch": 15.77, "learning_rate": 1.8992434110245822e-06, "loss": 0.7936, "step": 189680 }, { "epoch": 15.77, "learning_rate": 1.8991325554970482e-06, "loss": 0.7395, "step": 189690 }, { "epoch": 15.77, "learning_rate": 1.8990216999695145e-06, "loss": 0.7729, "step": 189700 }, { "epoch": 15.77, "learning_rate": 1.8989108444419808e-06, "loss": 0.7448, "step": 189710 }, { "epoch": 15.77, "learning_rate": 1.8987999889144473e-06, "loss": 0.7961, "step": 189720 }, { "epoch": 15.77, "learning_rate": 1.8986891333869134e-06, "loss": 0.7732, "step": 189730 }, { "epoch": 15.77, "learning_rate": 1.8985782778593797e-06, "loss": 0.7132, "step": 189740 }, { "epoch": 15.77, "learning_rate": 1.898467422331846e-06, "loss": 0.7613, "step": 189750 }, { "epoch": 15.77, "learning_rate": 1.8983565668043123e-06, "loss": 0.7557, "step": 189760 }, { "epoch": 15.77, "learning_rate": 1.8982457112767784e-06, "loss": 0.7878, "step": 189770 }, { "epoch": 15.77, "learning_rate": 1.8981348557492447e-06, "loss": 0.7677, "step": 189780 }, { "epoch": 15.78, "learning_rate": 1.898024000221711e-06, "loss": 0.8212, "step": 189790 }, { "epoch": 15.78, "learning_rate": 1.8979131446941773e-06, "loss": 0.7698, "step": 189800 }, { "epoch": 15.78, "learning_rate": 1.8978022891666434e-06, "loss": 0.7241, "step": 189810 }, { "epoch": 15.78, "learning_rate": 1.8976914336391097e-06, "loss": 0.8468, "step": 189820 }, { "epoch": 15.78, "learning_rate": 1.897580578111576e-06, "loss": 0.8275, "step": 189830 }, { "epoch": 15.78, "learning_rate": 1.8974697225840425e-06, "loss": 0.8046, "step": 189840 }, { "epoch": 15.78, "learning_rate": 1.8973588670565085e-06, "loss": 0.7576, "step": 189850 }, { "epoch": 15.78, "learning_rate": 1.8972480115289748e-06, "loss": 0.7637, "step": 189860 }, { "epoch": 15.78, "learning_rate": 1.8971371560014411e-06, "loss": 0.8027, "step": 189870 }, { "epoch": 15.78, "learning_rate": 1.8970263004739074e-06, "loss": 0.7761, "step": 189880 }, { "epoch": 15.78, "learning_rate": 1.8969154449463735e-06, "loss": 0.7737, "step": 189890 }, { "epoch": 15.78, "learning_rate": 1.8968045894188398e-06, "loss": 0.8036, "step": 189900 }, { "epoch": 15.79, "learning_rate": 1.896693733891306e-06, "loss": 0.8066, "step": 189910 }, { "epoch": 15.79, "learning_rate": 1.8965828783637722e-06, "loss": 0.8507, "step": 189920 }, { "epoch": 15.79, "learning_rate": 1.8964720228362385e-06, "loss": 0.7982, "step": 189930 }, { "epoch": 15.79, "learning_rate": 1.8963611673087048e-06, "loss": 0.7327, "step": 189940 }, { "epoch": 15.79, "learning_rate": 1.896250311781171e-06, "loss": 0.8256, "step": 189950 }, { "epoch": 15.79, "learning_rate": 1.8961394562536374e-06, "loss": 0.8007, "step": 189960 }, { "epoch": 15.79, "learning_rate": 1.8960286007261037e-06, "loss": 0.8106, "step": 189970 }, { "epoch": 15.79, "learning_rate": 1.89591774519857e-06, "loss": 0.7138, "step": 189980 }, { "epoch": 15.79, "learning_rate": 1.8958068896710363e-06, "loss": 0.7735, "step": 189990 }, { "epoch": 15.79, "learning_rate": 1.8956960341435023e-06, "loss": 0.7209, "step": 190000 }, { "epoch": 15.79, "learning_rate": 1.8955851786159686e-06, "loss": 0.7239, "step": 190010 }, { "epoch": 15.79, "learning_rate": 1.895474323088435e-06, "loss": 0.7979, "step": 190020 }, { "epoch": 15.8, "learning_rate": 1.8953634675609012e-06, "loss": 0.792, "step": 190030 }, { "epoch": 15.8, "learning_rate": 1.8952526120333673e-06, "loss": 0.734, "step": 190040 }, { "epoch": 15.8, "learning_rate": 1.8951417565058336e-06, "loss": 0.8238, "step": 190050 }, { "epoch": 15.8, "learning_rate": 1.8950309009783e-06, "loss": 0.7476, "step": 190060 }, { "epoch": 15.8, "learning_rate": 1.8949200454507662e-06, "loss": 0.8162, "step": 190070 }, { "epoch": 15.8, "learning_rate": 1.8948091899232323e-06, "loss": 0.7016, "step": 190080 }, { "epoch": 15.8, "learning_rate": 1.8946983343956988e-06, "loss": 0.7838, "step": 190090 }, { "epoch": 15.8, "learning_rate": 1.894587478868165e-06, "loss": 0.7986, "step": 190100 }, { "epoch": 15.8, "learning_rate": 1.8944766233406314e-06, "loss": 0.776, "step": 190110 }, { "epoch": 15.8, "learning_rate": 1.8943657678130975e-06, "loss": 0.7894, "step": 190120 }, { "epoch": 15.8, "learning_rate": 1.8942549122855638e-06, "loss": 0.8175, "step": 190130 }, { "epoch": 15.8, "learning_rate": 1.89414405675803e-06, "loss": 0.7688, "step": 190140 }, { "epoch": 15.81, "learning_rate": 1.8940332012304963e-06, "loss": 0.835, "step": 190150 }, { "epoch": 15.81, "learning_rate": 1.8939223457029624e-06, "loss": 0.8398, "step": 190160 }, { "epoch": 15.81, "learning_rate": 1.8938114901754287e-06, "loss": 0.7528, "step": 190170 }, { "epoch": 15.81, "learning_rate": 1.893700634647895e-06, "loss": 0.7743, "step": 190180 }, { "epoch": 15.81, "learning_rate": 1.8935897791203613e-06, "loss": 0.7521, "step": 190190 }, { "epoch": 15.81, "learning_rate": 1.8934789235928274e-06, "loss": 0.7077, "step": 190200 }, { "epoch": 15.81, "learning_rate": 1.893368068065294e-06, "loss": 0.7433, "step": 190210 }, { "epoch": 15.81, "learning_rate": 1.8932572125377602e-06, "loss": 0.7836, "step": 190220 }, { "epoch": 15.81, "learning_rate": 1.8931463570102265e-06, "loss": 0.7678, "step": 190230 }, { "epoch": 15.81, "learning_rate": 1.8930355014826926e-06, "loss": 0.7873, "step": 190240 }, { "epoch": 15.81, "learning_rate": 1.8929246459551589e-06, "loss": 0.7808, "step": 190250 }, { "epoch": 15.81, "learning_rate": 1.8928137904276252e-06, "loss": 0.7924, "step": 190260 }, { "epoch": 15.81, "learning_rate": 1.8927029349000915e-06, "loss": 0.8322, "step": 190270 }, { "epoch": 15.82, "learning_rate": 1.8925920793725575e-06, "loss": 0.7585, "step": 190280 }, { "epoch": 15.82, "learning_rate": 1.8924812238450238e-06, "loss": 0.7861, "step": 190290 }, { "epoch": 15.82, "learning_rate": 1.8923703683174901e-06, "loss": 0.7529, "step": 190300 }, { "epoch": 15.82, "learning_rate": 1.8922595127899562e-06, "loss": 0.7668, "step": 190310 }, { "epoch": 15.82, "learning_rate": 1.8921486572624225e-06, "loss": 0.8062, "step": 190320 }, { "epoch": 15.82, "learning_rate": 1.892037801734889e-06, "loss": 0.7926, "step": 190330 }, { "epoch": 15.82, "learning_rate": 1.8919269462073553e-06, "loss": 0.7915, "step": 190340 }, { "epoch": 15.82, "learning_rate": 1.8918160906798214e-06, "loss": 0.7555, "step": 190350 }, { "epoch": 15.82, "learning_rate": 1.8917052351522877e-06, "loss": 0.7291, "step": 190360 }, { "epoch": 15.82, "learning_rate": 1.891594379624754e-06, "loss": 0.8054, "step": 190370 }, { "epoch": 15.82, "learning_rate": 1.8914835240972203e-06, "loss": 0.7889, "step": 190380 }, { "epoch": 15.82, "learning_rate": 1.8913726685696864e-06, "loss": 0.7785, "step": 190390 }, { "epoch": 15.83, "learning_rate": 1.8912618130421527e-06, "loss": 0.8218, "step": 190400 }, { "epoch": 15.83, "learning_rate": 1.891150957514619e-06, "loss": 0.7474, "step": 190410 }, { "epoch": 15.83, "learning_rate": 1.8910401019870853e-06, "loss": 0.7716, "step": 190420 }, { "epoch": 15.83, "learning_rate": 1.8909292464595513e-06, "loss": 0.7235, "step": 190430 }, { "epoch": 15.83, "learning_rate": 1.8908183909320176e-06, "loss": 0.706, "step": 190440 }, { "epoch": 15.83, "learning_rate": 1.890707535404484e-06, "loss": 0.76, "step": 190450 }, { "epoch": 15.83, "learning_rate": 1.8905966798769504e-06, "loss": 0.7725, "step": 190460 }, { "epoch": 15.83, "learning_rate": 1.8904858243494165e-06, "loss": 0.7968, "step": 190470 }, { "epoch": 15.83, "learning_rate": 1.8903749688218828e-06, "loss": 0.8304, "step": 190480 }, { "epoch": 15.83, "learning_rate": 1.8902641132943491e-06, "loss": 0.6979, "step": 190490 }, { "epoch": 15.83, "learning_rate": 1.8901532577668154e-06, "loss": 0.744, "step": 190500 }, { "epoch": 15.83, "learning_rate": 1.8900424022392815e-06, "loss": 0.7829, "step": 190510 }, { "epoch": 15.84, "learning_rate": 1.8899315467117478e-06, "loss": 0.8227, "step": 190520 }, { "epoch": 15.84, "learning_rate": 1.889820691184214e-06, "loss": 0.8101, "step": 190530 }, { "epoch": 15.84, "learning_rate": 1.8897098356566804e-06, "loss": 0.8029, "step": 190540 }, { "epoch": 15.84, "learning_rate": 1.8895989801291465e-06, "loss": 0.782, "step": 190550 }, { "epoch": 15.84, "learning_rate": 1.8894881246016128e-06, "loss": 0.7152, "step": 190560 }, { "epoch": 15.84, "learning_rate": 1.889377269074079e-06, "loss": 0.7455, "step": 190570 }, { "epoch": 15.84, "learning_rate": 1.8892664135465456e-06, "loss": 0.7363, "step": 190580 }, { "epoch": 15.84, "learning_rate": 1.8891555580190116e-06, "loss": 0.7983, "step": 190590 }, { "epoch": 15.84, "learning_rate": 1.889044702491478e-06, "loss": 0.7409, "step": 190600 }, { "epoch": 15.84, "learning_rate": 1.8889338469639442e-06, "loss": 0.7832, "step": 190610 }, { "epoch": 15.84, "learning_rate": 1.8888229914364105e-06, "loss": 0.8085, "step": 190620 }, { "epoch": 15.84, "learning_rate": 1.8887121359088766e-06, "loss": 0.8076, "step": 190630 }, { "epoch": 15.85, "learning_rate": 1.888601280381343e-06, "loss": 0.7594, "step": 190640 }, { "epoch": 15.85, "learning_rate": 1.8884904248538092e-06, "loss": 0.6889, "step": 190650 }, { "epoch": 15.85, "learning_rate": 1.8883795693262755e-06, "loss": 0.853, "step": 190660 }, { "epoch": 15.85, "learning_rate": 1.8882687137987416e-06, "loss": 0.7969, "step": 190670 }, { "epoch": 15.85, "learning_rate": 1.8881578582712079e-06, "loss": 0.8505, "step": 190680 }, { "epoch": 15.85, "learning_rate": 1.8880470027436742e-06, "loss": 0.7591, "step": 190690 }, { "epoch": 15.85, "learning_rate": 1.8879361472161407e-06, "loss": 0.8286, "step": 190700 }, { "epoch": 15.85, "learning_rate": 1.8878252916886068e-06, "loss": 0.7833, "step": 190710 }, { "epoch": 15.85, "learning_rate": 1.887714436161073e-06, "loss": 0.8494, "step": 190720 }, { "epoch": 15.85, "learning_rate": 1.8876035806335394e-06, "loss": 0.7847, "step": 190730 }, { "epoch": 15.85, "learning_rate": 1.8874927251060054e-06, "loss": 0.7624, "step": 190740 }, { "epoch": 15.85, "learning_rate": 1.8873818695784717e-06, "loss": 0.7566, "step": 190750 }, { "epoch": 15.86, "learning_rate": 1.887271014050938e-06, "loss": 0.7211, "step": 190760 }, { "epoch": 15.86, "learning_rate": 1.8871601585234043e-06, "loss": 0.7804, "step": 190770 }, { "epoch": 15.86, "learning_rate": 1.8870493029958704e-06, "loss": 0.799, "step": 190780 }, { "epoch": 15.86, "learning_rate": 1.8869384474683367e-06, "loss": 0.8113, "step": 190790 }, { "epoch": 15.86, "learning_rate": 1.886827591940803e-06, "loss": 0.764, "step": 190800 }, { "epoch": 15.86, "learning_rate": 1.8867167364132693e-06, "loss": 0.7166, "step": 190810 }, { "epoch": 15.86, "learning_rate": 1.8866058808857356e-06, "loss": 0.7805, "step": 190820 }, { "epoch": 15.86, "learning_rate": 1.8864950253582019e-06, "loss": 0.7545, "step": 190830 }, { "epoch": 15.86, "learning_rate": 1.8863841698306682e-06, "loss": 0.739, "step": 190840 }, { "epoch": 15.86, "learning_rate": 1.8862733143031345e-06, "loss": 0.7568, "step": 190850 }, { "epoch": 15.86, "learning_rate": 1.8861624587756006e-06, "loss": 0.7097, "step": 190860 }, { "epoch": 15.86, "learning_rate": 1.8860516032480669e-06, "loss": 0.8347, "step": 190870 }, { "epoch": 15.87, "learning_rate": 1.8859407477205332e-06, "loss": 0.7557, "step": 190880 }, { "epoch": 15.87, "learning_rate": 1.8858298921929994e-06, "loss": 0.7772, "step": 190890 }, { "epoch": 15.87, "learning_rate": 1.8857190366654655e-06, "loss": 0.7051, "step": 190900 }, { "epoch": 15.87, "learning_rate": 1.8856081811379318e-06, "loss": 0.7414, "step": 190910 }, { "epoch": 15.87, "learning_rate": 1.8854973256103981e-06, "loss": 0.7553, "step": 190920 }, { "epoch": 15.87, "learning_rate": 1.8853864700828644e-06, "loss": 0.7662, "step": 190930 }, { "epoch": 15.87, "learning_rate": 1.8852756145553305e-06, "loss": 0.6944, "step": 190940 }, { "epoch": 15.87, "learning_rate": 1.8851758445805503e-06, "loss": 0.7815, "step": 190950 }, { "epoch": 15.87, "learning_rate": 1.8850649890530165e-06, "loss": 0.7645, "step": 190960 }, { "epoch": 15.87, "learning_rate": 1.8849541335254828e-06, "loss": 0.7786, "step": 190970 }, { "epoch": 15.87, "learning_rate": 1.8848432779979491e-06, "loss": 0.7667, "step": 190980 }, { "epoch": 15.87, "learning_rate": 1.8847324224704152e-06, "loss": 0.736, "step": 190990 }, { "epoch": 15.88, "learning_rate": 1.8846215669428815e-06, "loss": 0.7871, "step": 191000 }, { "epoch": 15.88, "learning_rate": 1.8845107114153478e-06, "loss": 0.7161, "step": 191010 }, { "epoch": 15.88, "learning_rate": 1.884399855887814e-06, "loss": 0.8483, "step": 191020 }, { "epoch": 15.88, "learning_rate": 1.8842890003602804e-06, "loss": 0.7433, "step": 191030 }, { "epoch": 15.88, "learning_rate": 1.8841781448327467e-06, "loss": 0.7857, "step": 191040 }, { "epoch": 15.88, "learning_rate": 1.884067289305213e-06, "loss": 0.7448, "step": 191050 }, { "epoch": 15.88, "learning_rate": 1.8839564337776793e-06, "loss": 0.737, "step": 191060 }, { "epoch": 15.88, "learning_rate": 1.8838455782501454e-06, "loss": 0.8074, "step": 191070 }, { "epoch": 15.88, "learning_rate": 1.8837347227226117e-06, "loss": 0.8074, "step": 191080 }, { "epoch": 15.88, "learning_rate": 1.883623867195078e-06, "loss": 0.8018, "step": 191090 }, { "epoch": 15.88, "learning_rate": 1.8835130116675443e-06, "loss": 0.8445, "step": 191100 }, { "epoch": 15.88, "learning_rate": 1.8834021561400103e-06, "loss": 0.7744, "step": 191110 }, { "epoch": 15.89, "learning_rate": 1.8832913006124766e-06, "loss": 0.8088, "step": 191120 }, { "epoch": 15.89, "learning_rate": 1.883180445084943e-06, "loss": 0.7478, "step": 191130 }, { "epoch": 15.89, "learning_rate": 1.8830695895574092e-06, "loss": 0.7842, "step": 191140 }, { "epoch": 15.89, "learning_rate": 1.8829587340298753e-06, "loss": 0.7865, "step": 191150 }, { "epoch": 15.89, "learning_rate": 1.8828478785023418e-06, "loss": 0.7671, "step": 191160 }, { "epoch": 15.89, "learning_rate": 1.8827370229748081e-06, "loss": 0.8145, "step": 191170 }, { "epoch": 15.89, "learning_rate": 1.8826261674472744e-06, "loss": 0.8079, "step": 191180 }, { "epoch": 15.89, "learning_rate": 1.8825153119197405e-06, "loss": 0.7512, "step": 191190 }, { "epoch": 15.89, "learning_rate": 1.8824044563922068e-06, "loss": 0.7918, "step": 191200 }, { "epoch": 15.89, "learning_rate": 1.882293600864673e-06, "loss": 0.8051, "step": 191210 }, { "epoch": 15.89, "learning_rate": 1.8821827453371394e-06, "loss": 0.8404, "step": 191220 }, { "epoch": 15.89, "learning_rate": 1.8820718898096055e-06, "loss": 0.802, "step": 191230 }, { "epoch": 15.9, "learning_rate": 1.8819610342820718e-06, "loss": 0.7256, "step": 191240 }, { "epoch": 15.9, "learning_rate": 1.881850178754538e-06, "loss": 0.8081, "step": 191250 }, { "epoch": 15.9, "learning_rate": 1.8817393232270041e-06, "loss": 0.7985, "step": 191260 }, { "epoch": 15.9, "learning_rate": 1.8816284676994704e-06, "loss": 0.8089, "step": 191270 }, { "epoch": 15.9, "learning_rate": 1.881517612171937e-06, "loss": 0.8211, "step": 191280 }, { "epoch": 15.9, "learning_rate": 1.8814067566444032e-06, "loss": 0.7717, "step": 191290 }, { "epoch": 15.9, "learning_rate": 1.8812959011168693e-06, "loss": 0.8118, "step": 191300 }, { "epoch": 15.9, "learning_rate": 1.8811850455893356e-06, "loss": 0.7453, "step": 191310 }, { "epoch": 15.9, "learning_rate": 1.881074190061802e-06, "loss": 0.8134, "step": 191320 }, { "epoch": 15.9, "learning_rate": 1.8809633345342682e-06, "loss": 0.8211, "step": 191330 }, { "epoch": 15.9, "learning_rate": 1.8808524790067343e-06, "loss": 0.7475, "step": 191340 }, { "epoch": 15.9, "learning_rate": 1.8807416234792006e-06, "loss": 0.7621, "step": 191350 }, { "epoch": 15.91, "learning_rate": 1.8806307679516669e-06, "loss": 0.8272, "step": 191360 }, { "epoch": 15.91, "learning_rate": 1.8805199124241332e-06, "loss": 0.8655, "step": 191370 }, { "epoch": 15.91, "learning_rate": 1.8804090568965993e-06, "loss": 0.8288, "step": 191380 }, { "epoch": 15.91, "learning_rate": 1.8802982013690656e-06, "loss": 0.7096, "step": 191390 }, { "epoch": 15.91, "learning_rate": 1.880187345841532e-06, "loss": 0.785, "step": 191400 }, { "epoch": 15.91, "learning_rate": 1.8800764903139984e-06, "loss": 0.767, "step": 191410 }, { "epoch": 15.91, "learning_rate": 1.8799656347864644e-06, "loss": 0.7657, "step": 191420 }, { "epoch": 15.91, "learning_rate": 1.8798547792589307e-06, "loss": 0.7778, "step": 191430 }, { "epoch": 15.91, "learning_rate": 1.879743923731397e-06, "loss": 0.7178, "step": 191440 }, { "epoch": 15.91, "learning_rate": 1.8796330682038633e-06, "loss": 0.777, "step": 191450 }, { "epoch": 15.91, "learning_rate": 1.8795222126763294e-06, "loss": 0.736, "step": 191460 }, { "epoch": 15.91, "learning_rate": 1.8794113571487957e-06, "loss": 0.8648, "step": 191470 }, { "epoch": 15.92, "learning_rate": 1.879300501621262e-06, "loss": 0.8305, "step": 191480 }, { "epoch": 15.92, "learning_rate": 1.8791896460937283e-06, "loss": 0.7708, "step": 191490 }, { "epoch": 15.92, "learning_rate": 1.8790787905661944e-06, "loss": 0.7893, "step": 191500 }, { "epoch": 15.92, "learning_rate": 1.8789679350386607e-06, "loss": 0.8064, "step": 191510 }, { "epoch": 15.92, "learning_rate": 1.878857079511127e-06, "loss": 0.8028, "step": 191520 }, { "epoch": 15.92, "learning_rate": 1.8787462239835935e-06, "loss": 0.7944, "step": 191530 }, { "epoch": 15.92, "learning_rate": 1.8786353684560596e-06, "loss": 0.759, "step": 191540 }, { "epoch": 15.92, "learning_rate": 1.8785245129285259e-06, "loss": 0.7942, "step": 191550 }, { "epoch": 15.92, "learning_rate": 1.8784136574009921e-06, "loss": 0.8098, "step": 191560 }, { "epoch": 15.92, "learning_rate": 1.8783028018734584e-06, "loss": 0.7605, "step": 191570 }, { "epoch": 15.92, "learning_rate": 1.8781919463459245e-06, "loss": 0.7388, "step": 191580 }, { "epoch": 15.92, "learning_rate": 1.8780810908183908e-06, "loss": 0.7815, "step": 191590 }, { "epoch": 15.93, "learning_rate": 1.8779702352908571e-06, "loss": 0.8067, "step": 191600 }, { "epoch": 15.93, "learning_rate": 1.8778593797633234e-06, "loss": 0.734, "step": 191610 }, { "epoch": 15.93, "learning_rate": 1.8777485242357895e-06, "loss": 0.7797, "step": 191620 }, { "epoch": 15.93, "learning_rate": 1.8776376687082558e-06, "loss": 0.7377, "step": 191630 }, { "epoch": 15.93, "learning_rate": 1.877526813180722e-06, "loss": 0.7945, "step": 191640 }, { "epoch": 15.93, "learning_rate": 1.8774159576531886e-06, "loss": 0.7322, "step": 191650 }, { "epoch": 15.93, "learning_rate": 1.8773051021256547e-06, "loss": 0.7593, "step": 191660 }, { "epoch": 15.93, "learning_rate": 1.877194246598121e-06, "loss": 0.7528, "step": 191670 }, { "epoch": 15.93, "learning_rate": 1.8770833910705873e-06, "loss": 0.7573, "step": 191680 }, { "epoch": 15.93, "learning_rate": 1.8769725355430536e-06, "loss": 0.7877, "step": 191690 }, { "epoch": 15.93, "learning_rate": 1.8768616800155196e-06, "loss": 0.7679, "step": 191700 }, { "epoch": 15.93, "learning_rate": 1.876750824487986e-06, "loss": 0.7737, "step": 191710 }, { "epoch": 15.94, "learning_rate": 1.8766399689604522e-06, "loss": 0.8574, "step": 191720 }, { "epoch": 15.94, "learning_rate": 1.8765291134329183e-06, "loss": 0.7992, "step": 191730 }, { "epoch": 15.94, "learning_rate": 1.8764182579053846e-06, "loss": 0.7462, "step": 191740 }, { "epoch": 15.94, "learning_rate": 1.876307402377851e-06, "loss": 0.7453, "step": 191750 }, { "epoch": 15.94, "learning_rate": 1.8761965468503172e-06, "loss": 0.8567, "step": 191760 }, { "epoch": 15.94, "learning_rate": 1.8760856913227835e-06, "loss": 0.7736, "step": 191770 }, { "epoch": 15.94, "learning_rate": 1.8759748357952498e-06, "loss": 0.7203, "step": 191780 }, { "epoch": 15.94, "learning_rate": 1.875863980267716e-06, "loss": 0.7737, "step": 191790 }, { "epoch": 15.94, "learning_rate": 1.8757531247401824e-06, "loss": 0.7746, "step": 191800 }, { "epoch": 15.94, "learning_rate": 1.8756422692126485e-06, "loss": 0.7522, "step": 191810 }, { "epoch": 15.94, "learning_rate": 1.8755314136851148e-06, "loss": 0.8176, "step": 191820 }, { "epoch": 15.94, "learning_rate": 1.875420558157581e-06, "loss": 0.7685, "step": 191830 }, { "epoch": 15.95, "learning_rate": 1.8753097026300474e-06, "loss": 0.7366, "step": 191840 }, { "epoch": 15.95, "learning_rate": 1.8751988471025134e-06, "loss": 0.8041, "step": 191850 }, { "epoch": 15.95, "learning_rate": 1.8750879915749797e-06, "loss": 0.756, "step": 191860 }, { "epoch": 15.95, "learning_rate": 1.874977136047446e-06, "loss": 0.8112, "step": 191870 }, { "epoch": 15.95, "learning_rate": 1.8748662805199123e-06, "loss": 0.8393, "step": 191880 }, { "epoch": 15.95, "learning_rate": 1.8747554249923784e-06, "loss": 0.7426, "step": 191890 }, { "epoch": 15.95, "learning_rate": 1.874644569464845e-06, "loss": 0.8391, "step": 191900 }, { "epoch": 15.95, "learning_rate": 1.8745337139373112e-06, "loss": 0.8045, "step": 191910 }, { "epoch": 15.95, "learning_rate": 1.8744228584097775e-06, "loss": 0.7999, "step": 191920 }, { "epoch": 15.95, "learning_rate": 1.8743120028822436e-06, "loss": 0.7879, "step": 191930 }, { "epoch": 15.95, "learning_rate": 1.8742011473547099e-06, "loss": 0.7441, "step": 191940 }, { "epoch": 15.95, "learning_rate": 1.8740902918271762e-06, "loss": 0.7895, "step": 191950 }, { "epoch": 15.96, "learning_rate": 1.8739794362996425e-06, "loss": 0.7768, "step": 191960 }, { "epoch": 15.96, "learning_rate": 1.8738685807721086e-06, "loss": 0.8062, "step": 191970 }, { "epoch": 15.96, "learning_rate": 1.8737577252445749e-06, "loss": 0.7638, "step": 191980 }, { "epoch": 15.96, "learning_rate": 1.8736468697170412e-06, "loss": 0.734, "step": 191990 }, { "epoch": 15.96, "learning_rate": 1.8735360141895074e-06, "loss": 0.7909, "step": 192000 }, { "epoch": 15.96, "learning_rate": 1.8734251586619735e-06, "loss": 0.7673, "step": 192010 }, { "epoch": 15.96, "learning_rate": 1.87331430313444e-06, "loss": 0.8061, "step": 192020 }, { "epoch": 15.96, "learning_rate": 1.8732034476069063e-06, "loss": 0.8063, "step": 192030 }, { "epoch": 15.96, "learning_rate": 1.8730925920793726e-06, "loss": 0.7684, "step": 192040 }, { "epoch": 15.96, "learning_rate": 1.8729817365518387e-06, "loss": 0.7628, "step": 192050 }, { "epoch": 15.96, "learning_rate": 1.872870881024305e-06, "loss": 0.7431, "step": 192060 }, { "epoch": 15.96, "learning_rate": 1.8727600254967713e-06, "loss": 0.7952, "step": 192070 }, { "epoch": 15.97, "learning_rate": 1.8726491699692376e-06, "loss": 0.7629, "step": 192080 }, { "epoch": 15.97, "learning_rate": 1.8725383144417037e-06, "loss": 0.8144, "step": 192090 }, { "epoch": 15.97, "learning_rate": 1.87242745891417e-06, "loss": 0.7453, "step": 192100 }, { "epoch": 15.97, "learning_rate": 1.8723166033866363e-06, "loss": 0.7328, "step": 192110 }, { "epoch": 15.97, "learning_rate": 1.8722057478591024e-06, "loss": 0.7717, "step": 192120 }, { "epoch": 15.97, "learning_rate": 1.8720948923315687e-06, "loss": 0.7774, "step": 192130 }, { "epoch": 15.97, "learning_rate": 1.8719840368040352e-06, "loss": 0.7354, "step": 192140 }, { "epoch": 15.97, "learning_rate": 1.8718731812765015e-06, "loss": 0.7978, "step": 192150 }, { "epoch": 15.97, "learning_rate": 1.8717623257489675e-06, "loss": 0.7882, "step": 192160 }, { "epoch": 15.97, "learning_rate": 1.8716514702214338e-06, "loss": 0.846, "step": 192170 }, { "epoch": 15.97, "learning_rate": 1.8715406146939001e-06, "loss": 0.814, "step": 192180 }, { "epoch": 15.97, "learning_rate": 1.8714297591663664e-06, "loss": 0.7722, "step": 192190 }, { "epoch": 15.98, "learning_rate": 1.8713189036388325e-06, "loss": 0.7637, "step": 192200 }, { "epoch": 15.98, "learning_rate": 1.8712080481112988e-06, "loss": 0.7346, "step": 192210 }, { "epoch": 15.98, "learning_rate": 1.871097192583765e-06, "loss": 0.8188, "step": 192220 }, { "epoch": 15.98, "learning_rate": 1.8709863370562314e-06, "loss": 0.7602, "step": 192230 }, { "epoch": 15.98, "learning_rate": 1.8708754815286975e-06, "loss": 0.7639, "step": 192240 }, { "epoch": 15.98, "learning_rate": 1.8707646260011638e-06, "loss": 0.7759, "step": 192250 }, { "epoch": 15.98, "learning_rate": 1.8706537704736303e-06, "loss": 0.7747, "step": 192260 }, { "epoch": 15.98, "learning_rate": 1.8705429149460966e-06, "loss": 0.8376, "step": 192270 }, { "epoch": 15.98, "learning_rate": 1.8704320594185627e-06, "loss": 0.7512, "step": 192280 }, { "epoch": 15.98, "learning_rate": 1.870321203891029e-06, "loss": 0.7077, "step": 192290 }, { "epoch": 15.98, "learning_rate": 1.8702103483634953e-06, "loss": 0.8002, "step": 192300 }, { "epoch": 15.98, "learning_rate": 1.8700994928359615e-06, "loss": 0.7688, "step": 192310 }, { "epoch": 15.99, "learning_rate": 1.8699886373084276e-06, "loss": 0.771, "step": 192320 }, { "epoch": 15.99, "learning_rate": 1.869877781780894e-06, "loss": 0.8089, "step": 192330 }, { "epoch": 15.99, "learning_rate": 1.8697669262533602e-06, "loss": 0.7641, "step": 192340 }, { "epoch": 15.99, "learning_rate": 1.8696560707258265e-06, "loss": 0.7742, "step": 192350 }, { "epoch": 15.99, "learning_rate": 1.8695452151982926e-06, "loss": 0.7184, "step": 192360 }, { "epoch": 15.99, "learning_rate": 1.8694343596707589e-06, "loss": 0.8162, "step": 192370 }, { "epoch": 15.99, "learning_rate": 1.8693235041432252e-06, "loss": 0.786, "step": 192380 }, { "epoch": 15.99, "learning_rate": 1.8692126486156917e-06, "loss": 0.7911, "step": 192390 }, { "epoch": 15.99, "learning_rate": 1.8691017930881578e-06, "loss": 0.758, "step": 192400 }, { "epoch": 15.99, "learning_rate": 1.868990937560624e-06, "loss": 0.7545, "step": 192410 }, { "epoch": 15.99, "learning_rate": 1.8688800820330904e-06, "loss": 0.7373, "step": 192420 }, { "epoch": 15.99, "learning_rate": 1.8687692265055567e-06, "loss": 0.7634, "step": 192430 }, { "epoch": 16.0, "learning_rate": 1.8686583709780227e-06, "loss": 0.7238, "step": 192440 }, { "epoch": 16.0, "learning_rate": 1.868547515450489e-06, "loss": 0.7981, "step": 192450 }, { "epoch": 16.0, "learning_rate": 1.8684366599229553e-06, "loss": 0.7882, "step": 192460 }, { "epoch": 16.0, "learning_rate": 1.8683258043954216e-06, "loss": 0.8058, "step": 192470 }, { "epoch": 16.0, "learning_rate": 1.8682149488678877e-06, "loss": 0.7561, "step": 192480 }, { "epoch": 16.0, "learning_rate": 1.868104093340354e-06, "loss": 0.7769, "step": 192490 }, { "epoch": 16.0, "eval_loss": 1.102294921875, "eval_runtime": 355.3703, "eval_samples_per_second": 7.525, "eval_steps_per_second": 3.762, "eval_wer": 0.641955427479011, "step": 192496 }, { "epoch": 16.0, "learning_rate": 1.8679932378128203e-06, "loss": 0.7836, "step": 192500 }, { "epoch": 16.0, "learning_rate": 1.8678823822852868e-06, "loss": 0.8097, "step": 192510 }, { "epoch": 16.0, "learning_rate": 1.867771526757753e-06, "loss": 0.7637, "step": 192520 }, { "epoch": 16.0, "learning_rate": 1.8676606712302192e-06, "loss": 0.7263, "step": 192530 }, { "epoch": 16.0, "learning_rate": 1.8675498157026855e-06, "loss": 0.6822, "step": 192540 }, { "epoch": 16.0, "learning_rate": 1.8674389601751516e-06, "loss": 0.7886, "step": 192550 }, { "epoch": 16.01, "learning_rate": 1.8673281046476179e-06, "loss": 0.8003, "step": 192560 }, { "epoch": 16.01, "learning_rate": 1.8672172491200842e-06, "loss": 0.7746, "step": 192570 }, { "epoch": 16.01, "learning_rate": 1.8671063935925505e-06, "loss": 0.7318, "step": 192580 }, { "epoch": 16.01, "learning_rate": 1.8669955380650165e-06, "loss": 0.8275, "step": 192590 }, { "epoch": 16.01, "learning_rate": 1.8668846825374828e-06, "loss": 0.8129, "step": 192600 }, { "epoch": 16.01, "learning_rate": 1.8667738270099491e-06, "loss": 0.7694, "step": 192610 }, { "epoch": 16.01, "learning_rate": 1.8666629714824154e-06, "loss": 0.8403, "step": 192620 }, { "epoch": 16.01, "learning_rate": 1.8665521159548817e-06, "loss": 0.8014, "step": 192630 }, { "epoch": 16.01, "learning_rate": 1.866441260427348e-06, "loss": 0.7738, "step": 192640 }, { "epoch": 16.01, "learning_rate": 1.8663304048998143e-06, "loss": 0.8598, "step": 192650 }, { "epoch": 16.01, "learning_rate": 1.8662195493722806e-06, "loss": 0.8268, "step": 192660 }, { "epoch": 16.01, "learning_rate": 1.8661086938447467e-06, "loss": 0.739, "step": 192670 }, { "epoch": 16.02, "learning_rate": 1.865997838317213e-06, "loss": 0.7119, "step": 192680 }, { "epoch": 16.02, "learning_rate": 1.8658869827896793e-06, "loss": 0.7238, "step": 192690 }, { "epoch": 16.02, "learning_rate": 1.8657761272621456e-06, "loss": 0.8071, "step": 192700 }, { "epoch": 16.02, "learning_rate": 1.8656652717346117e-06, "loss": 0.7547, "step": 192710 }, { "epoch": 16.02, "learning_rate": 1.865554416207078e-06, "loss": 0.7318, "step": 192720 }, { "epoch": 16.02, "learning_rate": 1.8654435606795443e-06, "loss": 0.744, "step": 192730 }, { "epoch": 16.02, "learning_rate": 1.8653327051520106e-06, "loss": 0.7688, "step": 192740 }, { "epoch": 16.02, "learning_rate": 1.8652218496244766e-06, "loss": 0.7857, "step": 192750 }, { "epoch": 16.02, "learning_rate": 1.8651109940969431e-06, "loss": 0.7674, "step": 192760 }, { "epoch": 16.02, "learning_rate": 1.8650001385694094e-06, "loss": 0.7463, "step": 192770 }, { "epoch": 16.02, "learning_rate": 1.8648892830418757e-06, "loss": 0.7823, "step": 192780 }, { "epoch": 16.02, "learning_rate": 1.8647784275143418e-06, "loss": 0.864, "step": 192790 }, { "epoch": 16.03, "learning_rate": 1.8646675719868081e-06, "loss": 0.855, "step": 192800 }, { "epoch": 16.03, "learning_rate": 1.8645567164592744e-06, "loss": 0.7441, "step": 192810 }, { "epoch": 16.03, "learning_rate": 1.8644458609317407e-06, "loss": 0.7401, "step": 192820 }, { "epoch": 16.03, "learning_rate": 1.8643350054042068e-06, "loss": 0.7208, "step": 192830 }, { "epoch": 16.03, "learning_rate": 1.864224149876673e-06, "loss": 0.7454, "step": 192840 }, { "epoch": 16.03, "learning_rate": 1.8641132943491394e-06, "loss": 0.7988, "step": 192850 }, { "epoch": 16.03, "learning_rate": 1.8640024388216057e-06, "loss": 0.7805, "step": 192860 }, { "epoch": 16.03, "learning_rate": 1.8638915832940718e-06, "loss": 0.6929, "step": 192870 }, { "epoch": 16.03, "learning_rate": 1.8637807277665383e-06, "loss": 0.8214, "step": 192880 }, { "epoch": 16.03, "learning_rate": 1.8636698722390046e-06, "loss": 0.7635, "step": 192890 }, { "epoch": 16.03, "learning_rate": 1.8635590167114709e-06, "loss": 0.7979, "step": 192900 }, { "epoch": 16.03, "learning_rate": 1.863448161183937e-06, "loss": 0.7839, "step": 192910 }, { "epoch": 16.04, "learning_rate": 1.8633373056564032e-06, "loss": 0.7397, "step": 192920 }, { "epoch": 16.04, "learning_rate": 1.8632264501288695e-06, "loss": 0.7262, "step": 192930 }, { "epoch": 16.04, "learning_rate": 1.8631155946013356e-06, "loss": 0.807, "step": 192940 }, { "epoch": 16.04, "learning_rate": 1.863004739073802e-06, "loss": 0.7989, "step": 192950 }, { "epoch": 16.04, "learning_rate": 1.8628938835462682e-06, "loss": 0.8282, "step": 192960 }, { "epoch": 16.04, "learning_rate": 1.8627830280187345e-06, "loss": 0.7312, "step": 192970 }, { "epoch": 16.04, "learning_rate": 1.8626721724912006e-06, "loss": 0.7178, "step": 192980 }, { "epoch": 16.04, "learning_rate": 1.8625613169636669e-06, "loss": 0.7855, "step": 192990 }, { "epoch": 16.04, "learning_rate": 1.8624504614361334e-06, "loss": 0.7785, "step": 193000 }, { "epoch": 16.04, "learning_rate": 1.8623396059085997e-06, "loss": 0.7882, "step": 193010 }, { "epoch": 16.04, "learning_rate": 1.8622287503810658e-06, "loss": 0.7581, "step": 193020 }, { "epoch": 16.04, "learning_rate": 1.862117894853532e-06, "loss": 0.7778, "step": 193030 }, { "epoch": 16.05, "learning_rate": 1.8620070393259984e-06, "loss": 0.732, "step": 193040 }, { "epoch": 16.05, "learning_rate": 1.8618961837984646e-06, "loss": 0.8232, "step": 193050 }, { "epoch": 16.05, "learning_rate": 1.8617853282709307e-06, "loss": 0.8067, "step": 193060 }, { "epoch": 16.05, "learning_rate": 1.861674472743397e-06, "loss": 0.8183, "step": 193070 }, { "epoch": 16.05, "learning_rate": 1.8615636172158633e-06, "loss": 0.7686, "step": 193080 }, { "epoch": 16.05, "learning_rate": 1.8614527616883296e-06, "loss": 0.7969, "step": 193090 }, { "epoch": 16.05, "learning_rate": 1.8613419061607957e-06, "loss": 0.7563, "step": 193100 }, { "epoch": 16.05, "learning_rate": 1.861231050633262e-06, "loss": 0.761, "step": 193110 }, { "epoch": 16.05, "learning_rate": 1.8611201951057285e-06, "loss": 0.7287, "step": 193120 }, { "epoch": 16.05, "learning_rate": 1.8610093395781948e-06, "loss": 0.7348, "step": 193130 }, { "epoch": 16.05, "learning_rate": 1.8608984840506609e-06, "loss": 0.8106, "step": 193140 }, { "epoch": 16.05, "learning_rate": 1.8607876285231272e-06, "loss": 0.7527, "step": 193150 }, { "epoch": 16.06, "learning_rate": 1.8606767729955935e-06, "loss": 0.7517, "step": 193160 }, { "epoch": 16.06, "learning_rate": 1.8605659174680598e-06, "loss": 0.8243, "step": 193170 }, { "epoch": 16.06, "learning_rate": 1.8604550619405259e-06, "loss": 0.7886, "step": 193180 }, { "epoch": 16.06, "learning_rate": 1.8603442064129921e-06, "loss": 0.7853, "step": 193190 }, { "epoch": 16.06, "learning_rate": 1.8602333508854584e-06, "loss": 0.6967, "step": 193200 }, { "epoch": 16.06, "learning_rate": 1.8601224953579247e-06, "loss": 0.8069, "step": 193210 }, { "epoch": 16.06, "learning_rate": 1.8600116398303908e-06, "loss": 0.7552, "step": 193220 }, { "epoch": 16.06, "learning_rate": 1.8599007843028571e-06, "loss": 0.7229, "step": 193230 }, { "epoch": 16.06, "learning_rate": 1.8597899287753234e-06, "loss": 0.7557, "step": 193240 }, { "epoch": 16.06, "learning_rate": 1.85967907324779e-06, "loss": 0.7616, "step": 193250 }, { "epoch": 16.06, "learning_rate": 1.859568217720256e-06, "loss": 0.7824, "step": 193260 }, { "epoch": 16.06, "learning_rate": 1.8594573621927223e-06, "loss": 0.7845, "step": 193270 }, { "epoch": 16.07, "learning_rate": 1.8593465066651886e-06, "loss": 0.7882, "step": 193280 }, { "epoch": 16.07, "learning_rate": 1.8592356511376549e-06, "loss": 0.8077, "step": 193290 }, { "epoch": 16.07, "learning_rate": 1.859124795610121e-06, "loss": 0.8479, "step": 193300 }, { "epoch": 16.07, "learning_rate": 1.8590139400825873e-06, "loss": 0.7792, "step": 193310 }, { "epoch": 16.07, "learning_rate": 1.8589030845550536e-06, "loss": 0.7288, "step": 193320 }, { "epoch": 16.07, "learning_rate": 1.8587922290275199e-06, "loss": 0.7481, "step": 193330 }, { "epoch": 16.07, "learning_rate": 1.858681373499986e-06, "loss": 0.7573, "step": 193340 }, { "epoch": 16.07, "learning_rate": 1.8585705179724522e-06, "loss": 0.7807, "step": 193350 }, { "epoch": 16.07, "learning_rate": 1.8584596624449185e-06, "loss": 0.8664, "step": 193360 }, { "epoch": 16.07, "learning_rate": 1.858348806917385e-06, "loss": 0.7898, "step": 193370 }, { "epoch": 16.07, "learning_rate": 1.8582379513898511e-06, "loss": 0.7349, "step": 193380 }, { "epoch": 16.07, "learning_rate": 1.8581270958623174e-06, "loss": 0.7867, "step": 193390 }, { "epoch": 16.08, "learning_rate": 1.8580162403347837e-06, "loss": 0.8305, "step": 193400 }, { "epoch": 16.08, "learning_rate": 1.8579053848072498e-06, "loss": 0.8098, "step": 193410 }, { "epoch": 16.08, "learning_rate": 1.857794529279716e-06, "loss": 0.7309, "step": 193420 }, { "epoch": 16.08, "learning_rate": 1.8576836737521824e-06, "loss": 0.8112, "step": 193430 }, { "epoch": 16.08, "learning_rate": 1.8575728182246487e-06, "loss": 0.7265, "step": 193440 }, { "epoch": 16.08, "learning_rate": 1.8574619626971148e-06, "loss": 0.7793, "step": 193450 }, { "epoch": 16.08, "learning_rate": 1.857351107169581e-06, "loss": 0.838, "step": 193460 }, { "epoch": 16.08, "learning_rate": 1.8572402516420474e-06, "loss": 0.7682, "step": 193470 }, { "epoch": 16.08, "learning_rate": 1.8571293961145137e-06, "loss": 0.7815, "step": 193480 }, { "epoch": 16.08, "learning_rate": 1.85701854058698e-06, "loss": 0.7851, "step": 193490 }, { "epoch": 16.08, "learning_rate": 1.8569076850594462e-06, "loss": 0.8249, "step": 193500 }, { "epoch": 16.08, "learning_rate": 1.8567968295319125e-06, "loss": 0.8, "step": 193510 }, { "epoch": 16.09, "learning_rate": 1.8566859740043788e-06, "loss": 0.8236, "step": 193520 }, { "epoch": 16.09, "learning_rate": 1.856575118476845e-06, "loss": 0.7656, "step": 193530 }, { "epoch": 16.09, "learning_rate": 1.8564642629493112e-06, "loss": 0.7662, "step": 193540 }, { "epoch": 16.09, "learning_rate": 1.8563534074217775e-06, "loss": 0.7759, "step": 193550 }, { "epoch": 16.09, "learning_rate": 1.8562425518942438e-06, "loss": 0.81, "step": 193560 }, { "epoch": 16.09, "learning_rate": 1.8561316963667099e-06, "loss": 0.781, "step": 193570 }, { "epoch": 16.09, "learning_rate": 1.8560208408391762e-06, "loss": 0.7265, "step": 193580 }, { "epoch": 16.09, "learning_rate": 1.8559099853116425e-06, "loss": 0.7921, "step": 193590 }, { "epoch": 16.09, "learning_rate": 1.8557991297841088e-06, "loss": 0.8182, "step": 193600 }, { "epoch": 16.09, "learning_rate": 1.8556882742565749e-06, "loss": 0.8109, "step": 193610 }, { "epoch": 16.09, "learning_rate": 1.8555774187290414e-06, "loss": 0.8308, "step": 193620 }, { "epoch": 16.09, "learning_rate": 1.8554665632015077e-06, "loss": 0.7277, "step": 193630 }, { "epoch": 16.1, "learning_rate": 1.855355707673974e-06, "loss": 0.7332, "step": 193640 }, { "epoch": 16.1, "learning_rate": 1.85524485214644e-06, "loss": 0.7518, "step": 193650 }, { "epoch": 16.1, "learning_rate": 1.8551339966189063e-06, "loss": 0.7768, "step": 193660 }, { "epoch": 16.1, "learning_rate": 1.8550231410913726e-06, "loss": 0.7138, "step": 193670 }, { "epoch": 16.1, "learning_rate": 1.854912285563839e-06, "loss": 0.8052, "step": 193680 }, { "epoch": 16.1, "learning_rate": 1.854801430036305e-06, "loss": 0.7258, "step": 193690 }, { "epoch": 16.1, "learning_rate": 1.8546905745087713e-06, "loss": 0.7994, "step": 193700 }, { "epoch": 16.1, "learning_rate": 1.8545797189812376e-06, "loss": 0.8667, "step": 193710 }, { "epoch": 16.1, "learning_rate": 1.854468863453704e-06, "loss": 0.7415, "step": 193720 }, { "epoch": 16.1, "learning_rate": 1.85435800792617e-06, "loss": 0.739, "step": 193730 }, { "epoch": 16.1, "learning_rate": 1.8542471523986365e-06, "loss": 0.7808, "step": 193740 }, { "epoch": 16.1, "learning_rate": 1.8541362968711028e-06, "loss": 0.7339, "step": 193750 }, { "epoch": 16.11, "learning_rate": 1.854025441343569e-06, "loss": 0.7412, "step": 193760 }, { "epoch": 16.11, "learning_rate": 1.8539145858160352e-06, "loss": 0.7149, "step": 193770 }, { "epoch": 16.11, "learning_rate": 1.8538037302885015e-06, "loss": 0.7695, "step": 193780 }, { "epoch": 16.11, "learning_rate": 1.8536928747609677e-06, "loss": 0.764, "step": 193790 }, { "epoch": 16.11, "learning_rate": 1.8535820192334338e-06, "loss": 0.8112, "step": 193800 }, { "epoch": 16.11, "learning_rate": 1.8534711637059001e-06, "loss": 0.8368, "step": 193810 }, { "epoch": 16.11, "learning_rate": 1.8533603081783664e-06, "loss": 0.7908, "step": 193820 }, { "epoch": 16.11, "learning_rate": 1.8532494526508327e-06, "loss": 0.7336, "step": 193830 }, { "epoch": 16.11, "learning_rate": 1.8531385971232988e-06, "loss": 0.7528, "step": 193840 }, { "epoch": 16.11, "learning_rate": 1.853027741595765e-06, "loss": 0.8369, "step": 193850 }, { "epoch": 16.11, "learning_rate": 1.8529168860682316e-06, "loss": 0.7562, "step": 193860 }, { "epoch": 16.11, "learning_rate": 1.852806030540698e-06, "loss": 0.7492, "step": 193870 }, { "epoch": 16.12, "learning_rate": 1.852695175013164e-06, "loss": 0.8103, "step": 193880 }, { "epoch": 16.12, "learning_rate": 1.8525843194856303e-06, "loss": 0.7428, "step": 193890 }, { "epoch": 16.12, "learning_rate": 1.8524734639580966e-06, "loss": 0.7718, "step": 193900 }, { "epoch": 16.12, "learning_rate": 1.8523626084305629e-06, "loss": 0.7682, "step": 193910 }, { "epoch": 16.12, "learning_rate": 1.852251752903029e-06, "loss": 0.7005, "step": 193920 }, { "epoch": 16.12, "learning_rate": 1.8521408973754952e-06, "loss": 0.759, "step": 193930 }, { "epoch": 16.12, "learning_rate": 1.8520300418479615e-06, "loss": 0.7763, "step": 193940 }, { "epoch": 16.12, "learning_rate": 1.8519191863204278e-06, "loss": 0.8003, "step": 193950 }, { "epoch": 16.12, "learning_rate": 1.851808330792894e-06, "loss": 0.8401, "step": 193960 }, { "epoch": 16.12, "learning_rate": 1.8516974752653602e-06, "loss": 0.7081, "step": 193970 }, { "epoch": 16.12, "learning_rate": 1.8515866197378265e-06, "loss": 0.8211, "step": 193980 }, { "epoch": 16.12, "learning_rate": 1.851475764210293e-06, "loss": 0.7855, "step": 193990 }, { "epoch": 16.13, "learning_rate": 1.851364908682759e-06, "loss": 0.7878, "step": 194000 }, { "epoch": 16.13, "learning_rate": 1.8512540531552254e-06, "loss": 0.8455, "step": 194010 }, { "epoch": 16.13, "learning_rate": 1.8511431976276917e-06, "loss": 0.8001, "step": 194020 }, { "epoch": 16.13, "learning_rate": 1.851032342100158e-06, "loss": 0.7665, "step": 194030 }, { "epoch": 16.13, "learning_rate": 1.850921486572624e-06, "loss": 0.7432, "step": 194040 }, { "epoch": 16.13, "learning_rate": 1.8508106310450904e-06, "loss": 0.7742, "step": 194050 }, { "epoch": 16.13, "learning_rate": 1.8506997755175567e-06, "loss": 0.7921, "step": 194060 }, { "epoch": 16.13, "learning_rate": 1.850588919990023e-06, "loss": 0.7588, "step": 194070 }, { "epoch": 16.13, "learning_rate": 1.850478064462489e-06, "loss": 0.7316, "step": 194080 }, { "epoch": 16.13, "learning_rate": 1.8503672089349553e-06, "loss": 0.7615, "step": 194090 }, { "epoch": 16.13, "learning_rate": 1.8502563534074216e-06, "loss": 0.8208, "step": 194100 }, { "epoch": 16.13, "learning_rate": 1.8501454978798881e-06, "loss": 0.7877, "step": 194110 }, { "epoch": 16.13, "learning_rate": 1.8500346423523542e-06, "loss": 0.7267, "step": 194120 }, { "epoch": 16.14, "learning_rate": 1.8499237868248205e-06, "loss": 0.7665, "step": 194130 }, { "epoch": 16.14, "learning_rate": 1.8498129312972868e-06, "loss": 0.74, "step": 194140 }, { "epoch": 16.14, "learning_rate": 1.8497020757697531e-06, "loss": 0.7708, "step": 194150 }, { "epoch": 16.14, "learning_rate": 1.8495912202422192e-06, "loss": 0.7923, "step": 194160 }, { "epoch": 16.14, "learning_rate": 1.8494803647146855e-06, "loss": 0.7132, "step": 194170 }, { "epoch": 16.14, "learning_rate": 1.8493695091871518e-06, "loss": 0.7845, "step": 194180 }, { "epoch": 16.14, "learning_rate": 1.8492586536596179e-06, "loss": 0.7733, "step": 194190 }, { "epoch": 16.14, "learning_rate": 1.8491477981320842e-06, "loss": 0.809, "step": 194200 }, { "epoch": 16.14, "learning_rate": 1.8490369426045505e-06, "loss": 0.7864, "step": 194210 }, { "epoch": 16.14, "learning_rate": 1.8489260870770168e-06, "loss": 0.8006, "step": 194220 }, { "epoch": 16.14, "learning_rate": 1.848815231549483e-06, "loss": 0.7774, "step": 194230 }, { "epoch": 16.14, "learning_rate": 1.8487043760219493e-06, "loss": 0.7369, "step": 194240 }, { "epoch": 16.15, "learning_rate": 1.8485935204944156e-06, "loss": 0.7479, "step": 194250 }, { "epoch": 16.15, "learning_rate": 1.848482664966882e-06, "loss": 0.8157, "step": 194260 }, { "epoch": 16.15, "learning_rate": 1.848371809439348e-06, "loss": 0.6996, "step": 194270 }, { "epoch": 16.15, "learning_rate": 1.8482609539118143e-06, "loss": 0.7907, "step": 194280 }, { "epoch": 16.15, "learning_rate": 1.8481500983842806e-06, "loss": 0.6776, "step": 194290 }, { "epoch": 16.15, "learning_rate": 1.848039242856747e-06, "loss": 0.8049, "step": 194300 }, { "epoch": 16.15, "learning_rate": 1.847928387329213e-06, "loss": 0.8053, "step": 194310 }, { "epoch": 16.15, "learning_rate": 1.8478175318016793e-06, "loss": 0.762, "step": 194320 }, { "epoch": 16.15, "learning_rate": 1.8477066762741456e-06, "loss": 0.7024, "step": 194330 }, { "epoch": 16.15, "learning_rate": 1.8475958207466119e-06, "loss": 0.8399, "step": 194340 }, { "epoch": 16.15, "learning_rate": 1.8474849652190782e-06, "loss": 0.7402, "step": 194350 }, { "epoch": 16.15, "learning_rate": 1.8473741096915445e-06, "loss": 0.7402, "step": 194360 }, { "epoch": 16.16, "learning_rate": 1.8472632541640108e-06, "loss": 0.8042, "step": 194370 }, { "epoch": 16.16, "learning_rate": 1.847152398636477e-06, "loss": 0.8, "step": 194380 }, { "epoch": 16.16, "learning_rate": 1.8470415431089431e-06, "loss": 0.7807, "step": 194390 }, { "epoch": 16.16, "learning_rate": 1.8469306875814094e-06, "loss": 0.7749, "step": 194400 }, { "epoch": 16.16, "learning_rate": 1.8468198320538757e-06, "loss": 0.7979, "step": 194410 }, { "epoch": 16.16, "learning_rate": 1.846708976526342e-06, "loss": 0.8028, "step": 194420 }, { "epoch": 16.16, "learning_rate": 1.8465981209988081e-06, "loss": 0.747, "step": 194430 }, { "epoch": 16.16, "learning_rate": 1.8464872654712744e-06, "loss": 0.7705, "step": 194440 }, { "epoch": 16.16, "learning_rate": 1.8463764099437407e-06, "loss": 0.7891, "step": 194450 }, { "epoch": 16.16, "learning_rate": 1.846265554416207e-06, "loss": 0.7666, "step": 194460 }, { "epoch": 16.16, "learning_rate": 1.846154698888673e-06, "loss": 0.741, "step": 194470 }, { "epoch": 16.16, "learning_rate": 1.8460438433611396e-06, "loss": 0.7557, "step": 194480 }, { "epoch": 16.17, "learning_rate": 1.8459329878336059e-06, "loss": 0.7746, "step": 194490 }, { "epoch": 16.17, "learning_rate": 1.8458221323060722e-06, "loss": 0.7557, "step": 194500 }, { "epoch": 16.17, "learning_rate": 1.8457112767785383e-06, "loss": 0.7966, "step": 194510 }, { "epoch": 16.17, "learning_rate": 1.8456004212510046e-06, "loss": 0.7308, "step": 194520 }, { "epoch": 16.17, "learning_rate": 1.8454895657234709e-06, "loss": 0.7758, "step": 194530 }, { "epoch": 16.17, "learning_rate": 1.8453787101959371e-06, "loss": 0.7689, "step": 194540 }, { "epoch": 16.17, "learning_rate": 1.8452678546684032e-06, "loss": 0.8129, "step": 194550 }, { "epoch": 16.17, "learning_rate": 1.8451569991408695e-06, "loss": 0.7591, "step": 194560 }, { "epoch": 16.17, "learning_rate": 1.8450461436133358e-06, "loss": 0.7789, "step": 194570 }, { "epoch": 16.17, "learning_rate": 1.844935288085802e-06, "loss": 0.725, "step": 194580 }, { "epoch": 16.17, "learning_rate": 1.8448244325582682e-06, "loss": 0.7424, "step": 194590 }, { "epoch": 16.17, "learning_rate": 1.8447135770307347e-06, "loss": 0.8347, "step": 194600 }, { "epoch": 16.18, "learning_rate": 1.844602721503201e-06, "loss": 0.7553, "step": 194610 }, { "epoch": 16.18, "learning_rate": 1.8444918659756673e-06, "loss": 0.7765, "step": 194620 }, { "epoch": 16.18, "learning_rate": 1.8443810104481334e-06, "loss": 0.7545, "step": 194630 }, { "epoch": 16.18, "learning_rate": 1.8442701549205997e-06, "loss": 0.7864, "step": 194640 }, { "epoch": 16.18, "learning_rate": 1.844159299393066e-06, "loss": 0.7832, "step": 194650 }, { "epoch": 16.18, "learning_rate": 1.844048443865532e-06, "loss": 0.8007, "step": 194660 }, { "epoch": 16.18, "learning_rate": 1.8439375883379984e-06, "loss": 0.7549, "step": 194670 }, { "epoch": 16.18, "learning_rate": 1.8438267328104646e-06, "loss": 0.7723, "step": 194680 }, { "epoch": 16.18, "learning_rate": 1.843715877282931e-06, "loss": 0.7602, "step": 194690 }, { "epoch": 16.18, "learning_rate": 1.843605021755397e-06, "loss": 0.8043, "step": 194700 }, { "epoch": 16.18, "learning_rate": 1.8434941662278633e-06, "loss": 0.8558, "step": 194710 }, { "epoch": 16.18, "learning_rate": 1.8433833107003298e-06, "loss": 0.6664, "step": 194720 }, { "epoch": 16.19, "learning_rate": 1.8432724551727961e-06, "loss": 0.7092, "step": 194730 }, { "epoch": 16.19, "learning_rate": 1.8431615996452622e-06, "loss": 0.7967, "step": 194740 }, { "epoch": 16.19, "learning_rate": 1.8430507441177285e-06, "loss": 0.8093, "step": 194750 }, { "epoch": 16.19, "learning_rate": 1.8429398885901948e-06, "loss": 0.716, "step": 194760 }, { "epoch": 16.19, "learning_rate": 1.842829033062661e-06, "loss": 0.8057, "step": 194770 }, { "epoch": 16.19, "learning_rate": 1.8427181775351272e-06, "loss": 0.7268, "step": 194780 }, { "epoch": 16.19, "learning_rate": 1.8426073220075935e-06, "loss": 0.6823, "step": 194790 }, { "epoch": 16.19, "learning_rate": 1.8424964664800598e-06, "loss": 0.7258, "step": 194800 }, { "epoch": 16.19, "learning_rate": 1.842385610952526e-06, "loss": 0.7953, "step": 194810 }, { "epoch": 16.19, "learning_rate": 1.8422747554249921e-06, "loss": 0.7581, "step": 194820 }, { "epoch": 16.19, "learning_rate": 1.8421638998974584e-06, "loss": 0.7491, "step": 194830 }, { "epoch": 16.19, "learning_rate": 1.8420530443699247e-06, "loss": 0.7766, "step": 194840 }, { "epoch": 16.2, "learning_rate": 1.8419421888423912e-06, "loss": 0.7909, "step": 194850 }, { "epoch": 16.2, "learning_rate": 1.8418313333148573e-06, "loss": 0.7515, "step": 194860 }, { "epoch": 16.2, "learning_rate": 1.8417204777873236e-06, "loss": 0.8055, "step": 194870 }, { "epoch": 16.2, "learning_rate": 1.84160962225979e-06, "loss": 0.7281, "step": 194880 }, { "epoch": 16.2, "learning_rate": 1.8414987667322562e-06, "loss": 0.7964, "step": 194890 }, { "epoch": 16.2, "learning_rate": 1.8413879112047223e-06, "loss": 0.7584, "step": 194900 }, { "epoch": 16.2, "learning_rate": 1.8412770556771886e-06, "loss": 0.8157, "step": 194910 }, { "epoch": 16.2, "learning_rate": 1.8411662001496549e-06, "loss": 0.7562, "step": 194920 }, { "epoch": 16.2, "learning_rate": 1.8410553446221212e-06, "loss": 0.7838, "step": 194930 }, { "epoch": 16.2, "learning_rate": 1.8409444890945873e-06, "loss": 0.7657, "step": 194940 }, { "epoch": 16.2, "learning_rate": 1.8408336335670536e-06, "loss": 0.7654, "step": 194950 }, { "epoch": 16.2, "learning_rate": 1.8407227780395199e-06, "loss": 0.7931, "step": 194960 }, { "epoch": 16.21, "learning_rate": 1.8406119225119864e-06, "loss": 0.744, "step": 194970 }, { "epoch": 16.21, "learning_rate": 1.8405010669844524e-06, "loss": 0.7962, "step": 194980 }, { "epoch": 16.21, "learning_rate": 1.8403902114569187e-06, "loss": 0.7431, "step": 194990 }, { "epoch": 16.21, "learning_rate": 1.840279355929385e-06, "loss": 0.8413, "step": 195000 }, { "epoch": 16.21, "learning_rate": 1.8401685004018513e-06, "loss": 0.7624, "step": 195010 }, { "epoch": 16.21, "learning_rate": 1.8400576448743174e-06, "loss": 0.7442, "step": 195020 }, { "epoch": 16.21, "learning_rate": 1.8399467893467837e-06, "loss": 0.8068, "step": 195030 }, { "epoch": 16.21, "learning_rate": 1.83983593381925e-06, "loss": 0.781, "step": 195040 }, { "epoch": 16.21, "learning_rate": 1.839725078291716e-06, "loss": 0.7779, "step": 195050 }, { "epoch": 16.21, "learning_rate": 1.8396142227641824e-06, "loss": 0.7664, "step": 195060 }, { "epoch": 16.21, "learning_rate": 1.8395033672366487e-06, "loss": 0.7075, "step": 195070 }, { "epoch": 16.21, "learning_rate": 1.839392511709115e-06, "loss": 0.739, "step": 195080 }, { "epoch": 16.22, "learning_rate": 1.8392816561815813e-06, "loss": 0.7658, "step": 195090 }, { "epoch": 16.22, "learning_rate": 1.8391708006540476e-06, "loss": 0.7902, "step": 195100 }, { "epoch": 16.22, "learning_rate": 1.8390599451265139e-06, "loss": 0.7418, "step": 195110 }, { "epoch": 16.22, "learning_rate": 1.8389490895989802e-06, "loss": 0.786, "step": 195120 }, { "epoch": 16.22, "learning_rate": 1.8388382340714462e-06, "loss": 0.781, "step": 195130 }, { "epoch": 16.22, "learning_rate": 1.8387273785439125e-06, "loss": 0.7321, "step": 195140 }, { "epoch": 16.22, "learning_rate": 1.8386165230163788e-06, "loss": 0.7884, "step": 195150 }, { "epoch": 16.22, "learning_rate": 1.8385056674888451e-06, "loss": 0.7694, "step": 195160 }, { "epoch": 16.22, "learning_rate": 1.8383948119613112e-06, "loss": 0.8141, "step": 195170 }, { "epoch": 16.22, "learning_rate": 1.8382839564337775e-06, "loss": 0.7851, "step": 195180 }, { "epoch": 16.22, "learning_rate": 1.8381731009062438e-06, "loss": 0.7546, "step": 195190 }, { "epoch": 16.22, "learning_rate": 1.83806224537871e-06, "loss": 0.7415, "step": 195200 }, { "epoch": 16.23, "learning_rate": 1.8379513898511764e-06, "loss": 0.8141, "step": 195210 }, { "epoch": 16.23, "learning_rate": 1.8378405343236427e-06, "loss": 0.7832, "step": 195220 }, { "epoch": 16.23, "learning_rate": 1.837729678796109e-06, "loss": 0.7964, "step": 195230 }, { "epoch": 16.23, "learning_rate": 1.8376188232685753e-06, "loss": 0.707, "step": 195240 }, { "epoch": 16.23, "learning_rate": 1.8375079677410414e-06, "loss": 0.8494, "step": 195250 }, { "epoch": 16.23, "learning_rate": 1.8373971122135077e-06, "loss": 0.7699, "step": 195260 }, { "epoch": 16.23, "learning_rate": 1.837286256685974e-06, "loss": 0.7362, "step": 195270 }, { "epoch": 16.23, "learning_rate": 1.8371754011584402e-06, "loss": 0.7805, "step": 195280 }, { "epoch": 16.23, "learning_rate": 1.8370645456309063e-06, "loss": 0.7553, "step": 195290 }, { "epoch": 16.23, "learning_rate": 1.8369536901033726e-06, "loss": 0.8034, "step": 195300 }, { "epoch": 16.23, "learning_rate": 1.836842834575839e-06, "loss": 0.8148, "step": 195310 }, { "epoch": 16.23, "learning_rate": 1.8367319790483052e-06, "loss": 0.7978, "step": 195320 }, { "epoch": 16.24, "learning_rate": 1.8366211235207713e-06, "loss": 0.7525, "step": 195330 }, { "epoch": 16.24, "learning_rate": 1.8365102679932378e-06, "loss": 0.765, "step": 195340 }, { "epoch": 16.24, "learning_rate": 1.836399412465704e-06, "loss": 0.8206, "step": 195350 }, { "epoch": 16.24, "learning_rate": 1.8362885569381704e-06, "loss": 0.7839, "step": 195360 }, { "epoch": 16.24, "learning_rate": 1.8361777014106365e-06, "loss": 0.8557, "step": 195370 }, { "epoch": 16.24, "learning_rate": 1.8360668458831028e-06, "loss": 0.8585, "step": 195380 }, { "epoch": 16.24, "learning_rate": 1.835955990355569e-06, "loss": 0.7464, "step": 195390 }, { "epoch": 16.24, "learning_rate": 1.8358451348280354e-06, "loss": 0.7702, "step": 195400 }, { "epoch": 16.24, "learning_rate": 1.8357342793005015e-06, "loss": 0.8215, "step": 195410 }, { "epoch": 16.24, "learning_rate": 1.8356234237729677e-06, "loss": 0.7646, "step": 195420 }, { "epoch": 16.24, "learning_rate": 1.835512568245434e-06, "loss": 0.7274, "step": 195430 }, { "epoch": 16.24, "learning_rate": 1.8354017127179001e-06, "loss": 0.6922, "step": 195440 }, { "epoch": 16.25, "learning_rate": 1.8352908571903664e-06, "loss": 0.8529, "step": 195450 }, { "epoch": 16.25, "learning_rate": 1.835180001662833e-06, "loss": 0.7996, "step": 195460 }, { "epoch": 16.25, "learning_rate": 1.8350691461352992e-06, "loss": 0.755, "step": 195470 }, { "epoch": 16.25, "learning_rate": 1.8349582906077653e-06, "loss": 0.7072, "step": 195480 }, { "epoch": 16.25, "learning_rate": 1.8348474350802316e-06, "loss": 0.8303, "step": 195490 }, { "epoch": 16.25, "learning_rate": 1.834736579552698e-06, "loss": 0.7668, "step": 195500 }, { "epoch": 16.25, "learning_rate": 1.8346257240251642e-06, "loss": 0.7596, "step": 195510 }, { "epoch": 16.25, "learning_rate": 1.8345148684976303e-06, "loss": 0.7263, "step": 195520 }, { "epoch": 16.25, "learning_rate": 1.8344040129700966e-06, "loss": 0.7842, "step": 195530 }, { "epoch": 16.25, "learning_rate": 1.8342931574425629e-06, "loss": 0.6926, "step": 195540 }, { "epoch": 16.25, "learning_rate": 1.8341823019150292e-06, "loss": 0.766, "step": 195550 }, { "epoch": 16.25, "learning_rate": 1.8340714463874952e-06, "loss": 0.7429, "step": 195560 }, { "epoch": 16.26, "learning_rate": 1.8339605908599615e-06, "loss": 0.7977, "step": 195570 }, { "epoch": 16.26, "learning_rate": 1.833849735332428e-06, "loss": 0.8297, "step": 195580 }, { "epoch": 16.26, "learning_rate": 1.8337388798048943e-06, "loss": 0.7119, "step": 195590 }, { "epoch": 16.26, "learning_rate": 1.8336280242773604e-06, "loss": 0.7494, "step": 195600 }, { "epoch": 16.26, "learning_rate": 1.8335171687498267e-06, "loss": 0.7765, "step": 195610 }, { "epoch": 16.26, "learning_rate": 1.833406313222293e-06, "loss": 0.8036, "step": 195620 }, { "epoch": 16.26, "learning_rate": 1.8332954576947593e-06, "loss": 0.7042, "step": 195630 }, { "epoch": 16.26, "learning_rate": 1.8331846021672254e-06, "loss": 0.7942, "step": 195640 }, { "epoch": 16.26, "learning_rate": 1.8330737466396917e-06, "loss": 0.7547, "step": 195650 }, { "epoch": 16.26, "learning_rate": 1.8329739766649112e-06, "loss": 0.8219, "step": 195660 }, { "epoch": 16.26, "learning_rate": 1.8328631211373777e-06, "loss": 0.75, "step": 195670 }, { "epoch": 16.26, "learning_rate": 1.832752265609844e-06, "loss": 0.7654, "step": 195680 }, { "epoch": 16.27, "learning_rate": 1.8326414100823101e-06, "loss": 0.7756, "step": 195690 }, { "epoch": 16.27, "learning_rate": 1.8325305545547764e-06, "loss": 0.779, "step": 195700 }, { "epoch": 16.27, "learning_rate": 1.8324196990272427e-06, "loss": 0.8054, "step": 195710 }, { "epoch": 16.27, "learning_rate": 1.832308843499709e-06, "loss": 0.7987, "step": 195720 }, { "epoch": 16.27, "learning_rate": 1.832197987972175e-06, "loss": 0.7989, "step": 195730 }, { "epoch": 16.27, "learning_rate": 1.8320871324446414e-06, "loss": 0.7518, "step": 195740 }, { "epoch": 16.27, "learning_rate": 1.8319762769171077e-06, "loss": 0.784, "step": 195750 }, { "epoch": 16.27, "learning_rate": 1.831865421389574e-06, "loss": 0.8272, "step": 195760 }, { "epoch": 16.27, "learning_rate": 1.83175456586204e-06, "loss": 0.7877, "step": 195770 }, { "epoch": 16.27, "learning_rate": 1.8316437103345064e-06, "loss": 0.8294, "step": 195780 }, { "epoch": 16.27, "learning_rate": 1.8315328548069729e-06, "loss": 0.7743, "step": 195790 }, { "epoch": 16.27, "learning_rate": 1.8314219992794392e-06, "loss": 0.8083, "step": 195800 }, { "epoch": 16.28, "learning_rate": 1.8313111437519052e-06, "loss": 0.7299, "step": 195810 }, { "epoch": 16.28, "learning_rate": 1.8312002882243715e-06, "loss": 0.7106, "step": 195820 }, { "epoch": 16.28, "learning_rate": 1.8310894326968378e-06, "loss": 0.755, "step": 195830 }, { "epoch": 16.28, "learning_rate": 1.8309785771693041e-06, "loss": 0.7619, "step": 195840 }, { "epoch": 16.28, "learning_rate": 1.8308677216417702e-06, "loss": 0.738, "step": 195850 }, { "epoch": 16.28, "learning_rate": 1.8307568661142365e-06, "loss": 0.721, "step": 195860 }, { "epoch": 16.28, "learning_rate": 1.8306460105867028e-06, "loss": 0.7483, "step": 195870 }, { "epoch": 16.28, "learning_rate": 1.830535155059169e-06, "loss": 0.7465, "step": 195880 }, { "epoch": 16.28, "learning_rate": 1.8304242995316352e-06, "loss": 0.6995, "step": 195890 }, { "epoch": 16.28, "learning_rate": 1.8303134440041015e-06, "loss": 0.8169, "step": 195900 }, { "epoch": 16.28, "learning_rate": 1.8302025884765678e-06, "loss": 0.7534, "step": 195910 }, { "epoch": 16.28, "learning_rate": 1.8300917329490343e-06, "loss": 0.7694, "step": 195920 }, { "epoch": 16.29, "learning_rate": 1.8299808774215004e-06, "loss": 0.7871, "step": 195930 }, { "epoch": 16.29, "learning_rate": 1.8298700218939667e-06, "loss": 0.7544, "step": 195940 }, { "epoch": 16.29, "learning_rate": 1.829759166366433e-06, "loss": 0.7926, "step": 195950 }, { "epoch": 16.29, "learning_rate": 1.8296483108388992e-06, "loss": 0.8269, "step": 195960 }, { "epoch": 16.29, "learning_rate": 1.8295374553113653e-06, "loss": 0.6732, "step": 195970 }, { "epoch": 16.29, "learning_rate": 1.8294265997838316e-06, "loss": 0.7439, "step": 195980 }, { "epoch": 16.29, "learning_rate": 1.829315744256298e-06, "loss": 0.7288, "step": 195990 }, { "epoch": 16.29, "learning_rate": 1.829204888728764e-06, "loss": 0.8294, "step": 196000 }, { "epoch": 16.29, "learning_rate": 1.8290940332012303e-06, "loss": 0.738, "step": 196010 }, { "epoch": 16.29, "learning_rate": 1.8289831776736966e-06, "loss": 0.7753, "step": 196020 }, { "epoch": 16.29, "learning_rate": 1.8288723221461629e-06, "loss": 0.763, "step": 196030 }, { "epoch": 16.29, "learning_rate": 1.8287614666186292e-06, "loss": 0.8018, "step": 196040 }, { "epoch": 16.3, "learning_rate": 1.8286506110910955e-06, "loss": 0.7053, "step": 196050 }, { "epoch": 16.3, "learning_rate": 1.8285397555635618e-06, "loss": 0.7511, "step": 196060 }, { "epoch": 16.3, "learning_rate": 1.828428900036028e-06, "loss": 0.7632, "step": 196070 }, { "epoch": 16.3, "learning_rate": 1.8283180445084942e-06, "loss": 0.7791, "step": 196080 }, { "epoch": 16.3, "learning_rate": 1.8282071889809605e-06, "loss": 0.8211, "step": 196090 }, { "epoch": 16.3, "learning_rate": 1.8280963334534267e-06, "loss": 0.7883, "step": 196100 }, { "epoch": 16.3, "learning_rate": 1.827985477925893e-06, "loss": 0.8006, "step": 196110 }, { "epoch": 16.3, "learning_rate": 1.8278746223983591e-06, "loss": 0.7465, "step": 196120 }, { "epoch": 16.3, "learning_rate": 1.8277637668708254e-06, "loss": 0.7631, "step": 196130 }, { "epoch": 16.3, "learning_rate": 1.8276529113432917e-06, "loss": 0.769, "step": 196140 }, { "epoch": 16.3, "learning_rate": 1.827542055815758e-06, "loss": 0.7766, "step": 196150 }, { "epoch": 16.3, "learning_rate": 1.8274312002882243e-06, "loss": 0.7815, "step": 196160 }, { "epoch": 16.31, "learning_rate": 1.8273203447606906e-06, "loss": 0.7661, "step": 196170 }, { "epoch": 16.31, "learning_rate": 1.827209489233157e-06, "loss": 0.7208, "step": 196180 }, { "epoch": 16.31, "learning_rate": 1.8270986337056232e-06, "loss": 0.7874, "step": 196190 }, { "epoch": 16.31, "learning_rate": 1.8269877781780893e-06, "loss": 0.7404, "step": 196200 }, { "epoch": 16.31, "learning_rate": 1.8268769226505556e-06, "loss": 0.8109, "step": 196210 }, { "epoch": 16.31, "learning_rate": 1.8267660671230219e-06, "loss": 0.7687, "step": 196220 }, { "epoch": 16.31, "learning_rate": 1.8266552115954882e-06, "loss": 0.773, "step": 196230 }, { "epoch": 16.31, "learning_rate": 1.8265443560679542e-06, "loss": 0.7094, "step": 196240 }, { "epoch": 16.31, "learning_rate": 1.8264335005404205e-06, "loss": 0.8581, "step": 196250 }, { "epoch": 16.31, "learning_rate": 1.8263226450128868e-06, "loss": 0.7987, "step": 196260 }, { "epoch": 16.31, "learning_rate": 1.8262117894853531e-06, "loss": 0.7311, "step": 196270 }, { "epoch": 16.31, "learning_rate": 1.8261009339578192e-06, "loss": 0.7113, "step": 196280 }, { "epoch": 16.32, "learning_rate": 1.8259900784302857e-06, "loss": 0.7538, "step": 196290 }, { "epoch": 16.32, "learning_rate": 1.825879222902752e-06, "loss": 0.7524, "step": 196300 }, { "epoch": 16.32, "learning_rate": 1.8257683673752183e-06, "loss": 0.71, "step": 196310 }, { "epoch": 16.32, "learning_rate": 1.8256575118476844e-06, "loss": 0.7312, "step": 196320 }, { "epoch": 16.32, "learning_rate": 1.8255466563201507e-06, "loss": 0.7134, "step": 196330 }, { "epoch": 16.32, "learning_rate": 1.825435800792617e-06, "loss": 0.8044, "step": 196340 }, { "epoch": 16.32, "learning_rate": 1.8253249452650833e-06, "loss": 0.7712, "step": 196350 }, { "epoch": 16.32, "learning_rate": 1.8252140897375494e-06, "loss": 0.8108, "step": 196360 }, { "epoch": 16.32, "learning_rate": 1.8251032342100157e-06, "loss": 0.771, "step": 196370 }, { "epoch": 16.32, "learning_rate": 1.824992378682482e-06, "loss": 0.7074, "step": 196380 }, { "epoch": 16.32, "learning_rate": 1.824881523154948e-06, "loss": 0.8336, "step": 196390 }, { "epoch": 16.32, "learning_rate": 1.8247706676274143e-06, "loss": 0.74, "step": 196400 }, { "epoch": 16.33, "learning_rate": 1.8246598120998808e-06, "loss": 0.8097, "step": 196410 }, { "epoch": 16.33, "learning_rate": 1.8245489565723471e-06, "loss": 0.7881, "step": 196420 }, { "epoch": 16.33, "learning_rate": 1.8244381010448132e-06, "loss": 0.7959, "step": 196430 }, { "epoch": 16.33, "learning_rate": 1.8243272455172795e-06, "loss": 0.7712, "step": 196440 }, { "epoch": 16.33, "learning_rate": 1.8242163899897458e-06, "loss": 0.7438, "step": 196450 }, { "epoch": 16.33, "learning_rate": 1.8241055344622121e-06, "loss": 0.7462, "step": 196460 }, { "epoch": 16.33, "learning_rate": 1.8239946789346782e-06, "loss": 0.7761, "step": 196470 }, { "epoch": 16.33, "learning_rate": 1.8238838234071445e-06, "loss": 0.7235, "step": 196480 }, { "epoch": 16.33, "learning_rate": 1.8237729678796108e-06, "loss": 0.7425, "step": 196490 }, { "epoch": 16.33, "learning_rate": 1.823662112352077e-06, "loss": 0.7799, "step": 196500 }, { "epoch": 16.33, "learning_rate": 1.8235512568245432e-06, "loss": 0.764, "step": 196510 }, { "epoch": 16.33, "learning_rate": 1.8234404012970095e-06, "loss": 0.7192, "step": 196520 }, { "epoch": 16.34, "learning_rate": 1.823329545769476e-06, "loss": 0.7477, "step": 196530 }, { "epoch": 16.34, "learning_rate": 1.8232186902419423e-06, "loss": 0.7447, "step": 196540 }, { "epoch": 16.34, "learning_rate": 1.8231078347144083e-06, "loss": 0.7566, "step": 196550 }, { "epoch": 16.34, "learning_rate": 1.8229969791868746e-06, "loss": 0.7998, "step": 196560 }, { "epoch": 16.34, "learning_rate": 1.822886123659341e-06, "loss": 0.818, "step": 196570 }, { "epoch": 16.34, "learning_rate": 1.8227752681318072e-06, "loss": 0.7617, "step": 196580 }, { "epoch": 16.34, "learning_rate": 1.8226644126042733e-06, "loss": 0.8323, "step": 196590 }, { "epoch": 16.34, "learning_rate": 1.8225535570767396e-06, "loss": 0.7749, "step": 196600 }, { "epoch": 16.34, "learning_rate": 1.822442701549206e-06, "loss": 0.761, "step": 196610 }, { "epoch": 16.34, "learning_rate": 1.8223318460216722e-06, "loss": 0.7688, "step": 196620 }, { "epoch": 16.34, "learning_rate": 1.8222209904941383e-06, "loss": 0.7961, "step": 196630 }, { "epoch": 16.34, "learning_rate": 1.8221101349666046e-06, "loss": 0.7861, "step": 196640 }, { "epoch": 16.35, "learning_rate": 1.821999279439071e-06, "loss": 0.7604, "step": 196650 }, { "epoch": 16.35, "learning_rate": 1.8218884239115374e-06, "loss": 0.7981, "step": 196660 }, { "epoch": 16.35, "learning_rate": 1.8217775683840035e-06, "loss": 0.7293, "step": 196670 }, { "epoch": 16.35, "learning_rate": 1.8216667128564698e-06, "loss": 0.769, "step": 196680 }, { "epoch": 16.35, "learning_rate": 1.821555857328936e-06, "loss": 0.6881, "step": 196690 }, { "epoch": 16.35, "learning_rate": 1.8214450018014023e-06, "loss": 0.7745, "step": 196700 }, { "epoch": 16.35, "learning_rate": 1.8213341462738684e-06, "loss": 0.792, "step": 196710 }, { "epoch": 16.35, "learning_rate": 1.8212232907463347e-06, "loss": 0.8283, "step": 196720 }, { "epoch": 16.35, "learning_rate": 1.821112435218801e-06, "loss": 0.8003, "step": 196730 }, { "epoch": 16.35, "learning_rate": 1.8210015796912673e-06, "loss": 0.7671, "step": 196740 }, { "epoch": 16.35, "learning_rate": 1.8208907241637334e-06, "loss": 0.7916, "step": 196750 }, { "epoch": 16.35, "learning_rate": 1.8207798686361997e-06, "loss": 0.7783, "step": 196760 }, { "epoch": 16.36, "learning_rate": 1.820669013108666e-06, "loss": 0.7829, "step": 196770 }, { "epoch": 16.36, "learning_rate": 1.8205581575811325e-06, "loss": 0.7031, "step": 196780 }, { "epoch": 16.36, "learning_rate": 1.8204473020535986e-06, "loss": 0.7188, "step": 196790 }, { "epoch": 16.36, "learning_rate": 1.8203364465260649e-06, "loss": 0.7822, "step": 196800 }, { "epoch": 16.36, "learning_rate": 1.8202255909985312e-06, "loss": 0.7955, "step": 196810 }, { "epoch": 16.36, "learning_rate": 1.8201147354709975e-06, "loss": 0.8352, "step": 196820 }, { "epoch": 16.36, "learning_rate": 1.8200038799434636e-06, "loss": 0.7828, "step": 196830 }, { "epoch": 16.36, "learning_rate": 1.8198930244159298e-06, "loss": 0.7866, "step": 196840 }, { "epoch": 16.36, "learning_rate": 1.8197821688883961e-06, "loss": 0.8006, "step": 196850 }, { "epoch": 16.36, "learning_rate": 1.8196713133608622e-06, "loss": 0.764, "step": 196860 }, { "epoch": 16.36, "learning_rate": 1.8195604578333285e-06, "loss": 0.7126, "step": 196870 }, { "epoch": 16.36, "learning_rate": 1.8194496023057948e-06, "loss": 0.8722, "step": 196880 }, { "epoch": 16.37, "learning_rate": 1.8193387467782611e-06, "loss": 0.7654, "step": 196890 }, { "epoch": 16.37, "learning_rate": 1.8192278912507274e-06, "loss": 0.7979, "step": 196900 }, { "epoch": 16.37, "learning_rate": 1.8191170357231937e-06, "loss": 0.7737, "step": 196910 }, { "epoch": 16.37, "learning_rate": 1.81900618019566e-06, "loss": 0.7225, "step": 196920 }, { "epoch": 16.37, "learning_rate": 1.8188953246681263e-06, "loss": 0.7897, "step": 196930 }, { "epoch": 16.37, "learning_rate": 1.8187844691405924e-06, "loss": 0.7196, "step": 196940 }, { "epoch": 16.37, "learning_rate": 1.8186736136130587e-06, "loss": 0.7465, "step": 196950 }, { "epoch": 16.37, "learning_rate": 1.818562758085525e-06, "loss": 0.7979, "step": 196960 }, { "epoch": 16.37, "learning_rate": 1.8184519025579913e-06, "loss": 0.8319, "step": 196970 }, { "epoch": 16.37, "learning_rate": 1.8183410470304573e-06, "loss": 0.7793, "step": 196980 }, { "epoch": 16.37, "learning_rate": 1.8182301915029236e-06, "loss": 0.7514, "step": 196990 }, { "epoch": 16.37, "learning_rate": 1.81811933597539e-06, "loss": 0.8064, "step": 197000 }, { "epoch": 16.38, "learning_rate": 1.8180084804478562e-06, "loss": 0.7979, "step": 197010 }, { "epoch": 16.38, "learning_rate": 1.8178976249203225e-06, "loss": 0.8194, "step": 197020 }, { "epoch": 16.38, "learning_rate": 1.8177867693927888e-06, "loss": 0.7725, "step": 197030 }, { "epoch": 16.38, "learning_rate": 1.8176759138652551e-06, "loss": 0.7839, "step": 197040 }, { "epoch": 16.38, "learning_rate": 1.8175650583377214e-06, "loss": 0.7576, "step": 197050 }, { "epoch": 16.38, "learning_rate": 1.8174542028101875e-06, "loss": 0.8255, "step": 197060 }, { "epoch": 16.38, "learning_rate": 1.8173433472826538e-06, "loss": 0.724, "step": 197070 }, { "epoch": 16.38, "learning_rate": 1.81723249175512e-06, "loss": 0.7455, "step": 197080 }, { "epoch": 16.38, "learning_rate": 1.8171216362275864e-06, "loss": 0.7141, "step": 197090 }, { "epoch": 16.38, "learning_rate": 1.817021866252806e-06, "loss": 0.7946, "step": 197100 }, { "epoch": 16.38, "learning_rate": 1.8169110107252722e-06, "loss": 0.7268, "step": 197110 }, { "epoch": 16.38, "learning_rate": 1.8168001551977385e-06, "loss": 0.7602, "step": 197120 }, { "epoch": 16.39, "learning_rate": 1.8166892996702048e-06, "loss": 0.801, "step": 197130 }, { "epoch": 16.39, "learning_rate": 1.816578444142671e-06, "loss": 0.7434, "step": 197140 }, { "epoch": 16.39, "learning_rate": 1.8164675886151372e-06, "loss": 0.7332, "step": 197150 }, { "epoch": 16.39, "learning_rate": 1.8163567330876035e-06, "loss": 0.7778, "step": 197160 }, { "epoch": 16.39, "learning_rate": 1.8162458775600698e-06, "loss": 0.7453, "step": 197170 }, { "epoch": 16.39, "learning_rate": 1.816135022032536e-06, "loss": 0.7931, "step": 197180 }, { "epoch": 16.39, "learning_rate": 1.8160241665050022e-06, "loss": 0.6953, "step": 197190 }, { "epoch": 16.39, "learning_rate": 1.8159133109774685e-06, "loss": 0.8125, "step": 197200 }, { "epoch": 16.39, "learning_rate": 1.8158024554499347e-06, "loss": 0.78, "step": 197210 }, { "epoch": 16.39, "learning_rate": 1.815691599922401e-06, "loss": 0.7758, "step": 197220 }, { "epoch": 16.39, "learning_rate": 1.8155807443948673e-06, "loss": 0.7609, "step": 197230 }, { "epoch": 16.39, "learning_rate": 1.8154698888673336e-06, "loss": 0.7642, "step": 197240 }, { "epoch": 16.4, "learning_rate": 1.8153590333398e-06, "loss": 0.8187, "step": 197250 }, { "epoch": 16.4, "learning_rate": 1.8152481778122662e-06, "loss": 0.8299, "step": 197260 }, { "epoch": 16.4, "learning_rate": 1.8151373222847323e-06, "loss": 0.8021, "step": 197270 }, { "epoch": 16.4, "learning_rate": 1.8150264667571986e-06, "loss": 0.7522, "step": 197280 }, { "epoch": 16.4, "learning_rate": 1.814915611229665e-06, "loss": 0.7397, "step": 197290 }, { "epoch": 16.4, "learning_rate": 1.8148047557021312e-06, "loss": 0.8641, "step": 197300 }, { "epoch": 16.4, "learning_rate": 1.8146939001745973e-06, "loss": 0.7737, "step": 197310 }, { "epoch": 16.4, "learning_rate": 1.8145830446470636e-06, "loss": 0.743, "step": 197320 }, { "epoch": 16.4, "learning_rate": 1.8144721891195299e-06, "loss": 0.7644, "step": 197330 }, { "epoch": 16.4, "learning_rate": 1.814361333591996e-06, "loss": 0.7766, "step": 197340 }, { "epoch": 16.4, "learning_rate": 1.8142504780644622e-06, "loss": 0.7601, "step": 197350 }, { "epoch": 16.4, "learning_rate": 1.8141396225369288e-06, "loss": 0.8105, "step": 197360 }, { "epoch": 16.41, "learning_rate": 1.814028767009395e-06, "loss": 0.738, "step": 197370 }, { "epoch": 16.41, "learning_rate": 1.8139179114818613e-06, "loss": 0.7446, "step": 197380 }, { "epoch": 16.41, "learning_rate": 1.8138070559543274e-06, "loss": 0.8369, "step": 197390 }, { "epoch": 16.41, "learning_rate": 1.8136962004267937e-06, "loss": 0.7909, "step": 197400 }, { "epoch": 16.41, "learning_rate": 1.81358534489926e-06, "loss": 0.7869, "step": 197410 }, { "epoch": 16.41, "learning_rate": 1.813474489371726e-06, "loss": 0.7484, "step": 197420 }, { "epoch": 16.41, "learning_rate": 1.8133636338441924e-06, "loss": 0.7823, "step": 197430 }, { "epoch": 16.41, "learning_rate": 1.8132527783166587e-06, "loss": 0.7266, "step": 197440 }, { "epoch": 16.41, "learning_rate": 1.813141922789125e-06, "loss": 0.8006, "step": 197450 }, { "epoch": 16.41, "learning_rate": 1.813031067261591e-06, "loss": 0.7876, "step": 197460 }, { "epoch": 16.41, "learning_rate": 1.8129202117340574e-06, "loss": 0.7873, "step": 197470 }, { "epoch": 16.41, "learning_rate": 1.8128093562065239e-06, "loss": 0.7187, "step": 197480 }, { "epoch": 16.42, "learning_rate": 1.8126985006789902e-06, "loss": 0.8083, "step": 197490 }, { "epoch": 16.42, "learning_rate": 1.8125876451514563e-06, "loss": 0.814, "step": 197500 }, { "epoch": 16.42, "learning_rate": 1.8124767896239225e-06, "loss": 0.8391, "step": 197510 }, { "epoch": 16.42, "learning_rate": 1.8123659340963888e-06, "loss": 0.7152, "step": 197520 }, { "epoch": 16.42, "learning_rate": 1.8122550785688551e-06, "loss": 0.7924, "step": 197530 }, { "epoch": 16.42, "learning_rate": 1.8121442230413212e-06, "loss": 0.7328, "step": 197540 }, { "epoch": 16.42, "learning_rate": 1.8120333675137875e-06, "loss": 0.7959, "step": 197550 }, { "epoch": 16.42, "learning_rate": 1.8119225119862538e-06, "loss": 0.7381, "step": 197560 }, { "epoch": 16.42, "learning_rate": 1.8118116564587201e-06, "loss": 0.7089, "step": 197570 }, { "epoch": 16.42, "learning_rate": 1.8117008009311862e-06, "loss": 0.7496, "step": 197580 }, { "epoch": 16.42, "learning_rate": 1.8115899454036525e-06, "loss": 0.8067, "step": 197590 }, { "epoch": 16.42, "learning_rate": 1.811479089876119e-06, "loss": 0.7873, "step": 197600 }, { "epoch": 16.43, "learning_rate": 1.8113682343485853e-06, "loss": 0.8058, "step": 197610 }, { "epoch": 16.43, "learning_rate": 1.8112573788210514e-06, "loss": 0.738, "step": 197620 }, { "epoch": 16.43, "learning_rate": 1.8111465232935177e-06, "loss": 0.7834, "step": 197630 }, { "epoch": 16.43, "learning_rate": 1.811035667765984e-06, "loss": 0.7688, "step": 197640 }, { "epoch": 16.43, "learning_rate": 1.8109248122384503e-06, "loss": 0.8031, "step": 197650 }, { "epoch": 16.43, "learning_rate": 1.8108139567109163e-06, "loss": 0.7658, "step": 197660 }, { "epoch": 16.43, "learning_rate": 1.8107031011833826e-06, "loss": 0.7104, "step": 197670 }, { "epoch": 16.43, "learning_rate": 1.810592245655849e-06, "loss": 0.7069, "step": 197680 }, { "epoch": 16.43, "learning_rate": 1.8104813901283152e-06, "loss": 0.7474, "step": 197690 }, { "epoch": 16.43, "learning_rate": 1.8103705346007813e-06, "loss": 0.7909, "step": 197700 }, { "epoch": 16.43, "learning_rate": 1.8102596790732476e-06, "loss": 0.7862, "step": 197710 }, { "epoch": 16.43, "learning_rate": 1.8101488235457141e-06, "loss": 0.7323, "step": 197720 }, { "epoch": 16.44, "learning_rate": 1.8100379680181804e-06, "loss": 0.7498, "step": 197730 }, { "epoch": 16.44, "learning_rate": 1.8099271124906465e-06, "loss": 0.8119, "step": 197740 }, { "epoch": 16.44, "learning_rate": 1.8098162569631128e-06, "loss": 0.7719, "step": 197750 }, { "epoch": 16.44, "learning_rate": 1.809705401435579e-06, "loss": 0.7278, "step": 197760 }, { "epoch": 16.44, "learning_rate": 1.8095945459080454e-06, "loss": 0.7625, "step": 197770 }, { "epoch": 16.44, "learning_rate": 1.8094836903805115e-06, "loss": 0.7549, "step": 197780 }, { "epoch": 16.44, "learning_rate": 1.8093728348529778e-06, "loss": 0.7105, "step": 197790 }, { "epoch": 16.44, "learning_rate": 1.809261979325444e-06, "loss": 0.8101, "step": 197800 }, { "epoch": 16.44, "learning_rate": 1.8091511237979101e-06, "loss": 0.8033, "step": 197810 }, { "epoch": 16.44, "learning_rate": 1.8090402682703764e-06, "loss": 0.7422, "step": 197820 }, { "epoch": 16.44, "learning_rate": 1.8089294127428427e-06, "loss": 0.8272, "step": 197830 }, { "epoch": 16.44, "learning_rate": 1.808818557215309e-06, "loss": 0.7409, "step": 197840 }, { "epoch": 16.45, "learning_rate": 1.8087077016877753e-06, "loss": 0.7898, "step": 197850 }, { "epoch": 16.45, "learning_rate": 1.8085968461602416e-06, "loss": 0.8146, "step": 197860 }, { "epoch": 16.45, "learning_rate": 1.808485990632708e-06, "loss": 0.7274, "step": 197870 }, { "epoch": 16.45, "learning_rate": 1.8083751351051742e-06, "loss": 0.8033, "step": 197880 }, { "epoch": 16.45, "learning_rate": 1.8082642795776403e-06, "loss": 0.7859, "step": 197890 }, { "epoch": 16.45, "learning_rate": 1.8081534240501066e-06, "loss": 0.7887, "step": 197900 }, { "epoch": 16.45, "learning_rate": 1.8080425685225729e-06, "loss": 0.8102, "step": 197910 }, { "epoch": 16.45, "learning_rate": 1.8079317129950392e-06, "loss": 0.7568, "step": 197920 }, { "epoch": 16.45, "learning_rate": 1.8078208574675053e-06, "loss": 0.7818, "step": 197930 }, { "epoch": 16.45, "learning_rate": 1.8077100019399716e-06, "loss": 0.7942, "step": 197940 }, { "epoch": 16.45, "learning_rate": 1.8075991464124379e-06, "loss": 0.7983, "step": 197950 }, { "epoch": 16.45, "learning_rate": 1.8074882908849041e-06, "loss": 0.7645, "step": 197960 }, { "epoch": 16.45, "learning_rate": 1.8073774353573704e-06, "loss": 0.747, "step": 197970 }, { "epoch": 16.46, "learning_rate": 1.8072665798298367e-06, "loss": 0.7653, "step": 197980 }, { "epoch": 16.46, "learning_rate": 1.807155724302303e-06, "loss": 0.7491, "step": 197990 }, { "epoch": 16.46, "learning_rate": 1.8070448687747693e-06, "loss": 0.8282, "step": 198000 }, { "epoch": 16.46, "learning_rate": 1.8069340132472354e-06, "loss": 0.785, "step": 198010 }, { "epoch": 16.46, "learning_rate": 1.8068231577197017e-06, "loss": 0.7147, "step": 198020 }, { "epoch": 16.46, "learning_rate": 1.806712302192168e-06, "loss": 0.7912, "step": 198030 }, { "epoch": 16.46, "learning_rate": 1.8066014466646343e-06, "loss": 0.7331, "step": 198040 }, { "epoch": 16.46, "learning_rate": 1.8064905911371004e-06, "loss": 0.7236, "step": 198050 }, { "epoch": 16.46, "learning_rate": 1.8063797356095667e-06, "loss": 0.8122, "step": 198060 }, { "epoch": 16.46, "learning_rate": 1.806268880082033e-06, "loss": 0.7856, "step": 198070 }, { "epoch": 16.46, "learning_rate": 1.8061580245544993e-06, "loss": 0.7223, "step": 198080 }, { "epoch": 16.46, "learning_rate": 1.8060471690269656e-06, "loss": 0.8253, "step": 198090 }, { "epoch": 16.47, "learning_rate": 1.8059363134994319e-06, "loss": 0.7644, "step": 198100 }, { "epoch": 16.47, "learning_rate": 1.8058254579718982e-06, "loss": 0.7688, "step": 198110 }, { "epoch": 16.47, "learning_rate": 1.8057146024443644e-06, "loss": 0.7431, "step": 198120 }, { "epoch": 16.47, "learning_rate": 1.8056037469168305e-06, "loss": 0.7244, "step": 198130 }, { "epoch": 16.47, "learning_rate": 1.8054928913892968e-06, "loss": 0.7896, "step": 198140 }, { "epoch": 16.47, "learning_rate": 1.8053820358617631e-06, "loss": 0.7613, "step": 198150 }, { "epoch": 16.47, "learning_rate": 1.8052711803342294e-06, "loss": 0.7658, "step": 198160 }, { "epoch": 16.47, "learning_rate": 1.8051603248066955e-06, "loss": 0.7987, "step": 198170 }, { "epoch": 16.47, "learning_rate": 1.8050494692791618e-06, "loss": 0.7075, "step": 198180 }, { "epoch": 16.47, "learning_rate": 1.804938613751628e-06, "loss": 0.8245, "step": 198190 }, { "epoch": 16.47, "learning_rate": 1.8048277582240942e-06, "loss": 0.837, "step": 198200 }, { "epoch": 16.47, "learning_rate": 1.8047169026965605e-06, "loss": 0.7614, "step": 198210 }, { "epoch": 16.48, "learning_rate": 1.804606047169027e-06, "loss": 0.7108, "step": 198220 }, { "epoch": 16.48, "learning_rate": 1.8044951916414933e-06, "loss": 0.821, "step": 198230 }, { "epoch": 16.48, "learning_rate": 1.8043843361139594e-06, "loss": 0.7794, "step": 198240 }, { "epoch": 16.48, "learning_rate": 1.8042734805864257e-06, "loss": 0.783, "step": 198250 }, { "epoch": 16.48, "learning_rate": 1.804162625058892e-06, "loss": 0.7847, "step": 198260 }, { "epoch": 16.48, "learning_rate": 1.8040517695313582e-06, "loss": 0.7533, "step": 198270 }, { "epoch": 16.48, "learning_rate": 1.8039409140038243e-06, "loss": 0.8058, "step": 198280 }, { "epoch": 16.48, "learning_rate": 1.8038300584762906e-06, "loss": 0.7565, "step": 198290 }, { "epoch": 16.48, "learning_rate": 1.803719202948757e-06, "loss": 0.7781, "step": 198300 }, { "epoch": 16.48, "learning_rate": 1.8036083474212232e-06, "loss": 0.8023, "step": 198310 }, { "epoch": 16.48, "learning_rate": 1.8034974918936893e-06, "loss": 0.8364, "step": 198320 }, { "epoch": 16.48, "learning_rate": 1.8033866363661556e-06, "loss": 0.7707, "step": 198330 }, { "epoch": 16.49, "learning_rate": 1.803275780838622e-06, "loss": 0.7622, "step": 198340 }, { "epoch": 16.49, "learning_rate": 1.8031649253110884e-06, "loss": 0.8035, "step": 198350 }, { "epoch": 16.49, "learning_rate": 1.8030540697835545e-06, "loss": 0.756, "step": 198360 }, { "epoch": 16.49, "learning_rate": 1.8029432142560208e-06, "loss": 0.7929, "step": 198370 }, { "epoch": 16.49, "learning_rate": 1.802832358728487e-06, "loss": 0.7226, "step": 198380 }, { "epoch": 16.49, "learning_rate": 1.8027215032009534e-06, "loss": 0.8128, "step": 198390 }, { "epoch": 16.49, "learning_rate": 1.8026106476734194e-06, "loss": 0.7668, "step": 198400 }, { "epoch": 16.49, "learning_rate": 1.8024997921458857e-06, "loss": 0.7909, "step": 198410 }, { "epoch": 16.49, "learning_rate": 1.802388936618352e-06, "loss": 0.7762, "step": 198420 }, { "epoch": 16.49, "learning_rate": 1.8022780810908183e-06, "loss": 0.7337, "step": 198430 }, { "epoch": 16.49, "learning_rate": 1.8021672255632844e-06, "loss": 0.7962, "step": 198440 }, { "epoch": 16.49, "learning_rate": 1.8020563700357507e-06, "loss": 0.7505, "step": 198450 }, { "epoch": 16.5, "learning_rate": 1.8019455145082172e-06, "loss": 0.8018, "step": 198460 }, { "epoch": 16.5, "learning_rate": 1.8018346589806835e-06, "loss": 0.7726, "step": 198470 }, { "epoch": 16.5, "learning_rate": 1.8017238034531496e-06, "loss": 0.7683, "step": 198480 }, { "epoch": 16.5, "learning_rate": 1.8016129479256159e-06, "loss": 0.7815, "step": 198490 }, { "epoch": 16.5, "learning_rate": 1.8015020923980822e-06, "loss": 0.835, "step": 198500 }, { "epoch": 16.5, "learning_rate": 1.8013912368705485e-06, "loss": 0.682, "step": 198510 }, { "epoch": 16.5, "learning_rate": 1.8012803813430146e-06, "loss": 0.7886, "step": 198520 }, { "epoch": 16.5, "learning_rate": 1.8011695258154809e-06, "loss": 0.7585, "step": 198530 }, { "epoch": 16.5, "learning_rate": 1.8010586702879472e-06, "loss": 0.7702, "step": 198540 }, { "epoch": 16.5, "learning_rate": 1.8009478147604135e-06, "loss": 0.8207, "step": 198550 }, { "epoch": 16.5, "learning_rate": 1.8008369592328795e-06, "loss": 0.8207, "step": 198560 }, { "epoch": 16.5, "learning_rate": 1.8007261037053458e-06, "loss": 0.7794, "step": 198570 }, { "epoch": 16.51, "learning_rate": 1.8006152481778121e-06, "loss": 0.7248, "step": 198580 }, { "epoch": 16.51, "learning_rate": 1.8005043926502786e-06, "loss": 0.7512, "step": 198590 }, { "epoch": 16.51, "learning_rate": 1.8003935371227447e-06, "loss": 0.816, "step": 198600 }, { "epoch": 16.51, "learning_rate": 1.800282681595211e-06, "loss": 0.8414, "step": 198610 }, { "epoch": 16.51, "learning_rate": 1.8001718260676773e-06, "loss": 0.774, "step": 198620 }, { "epoch": 16.51, "learning_rate": 1.8000609705401434e-06, "loss": 0.7846, "step": 198630 }, { "epoch": 16.51, "learning_rate": 1.7999501150126097e-06, "loss": 0.7749, "step": 198640 }, { "epoch": 16.51, "learning_rate": 1.799839259485076e-06, "loss": 0.8535, "step": 198650 }, { "epoch": 16.51, "learning_rate": 1.7997284039575423e-06, "loss": 0.7947, "step": 198660 }, { "epoch": 16.51, "learning_rate": 1.7996175484300084e-06, "loss": 0.72, "step": 198670 }, { "epoch": 16.51, "learning_rate": 1.7995066929024747e-06, "loss": 0.7303, "step": 198680 }, { "epoch": 16.51, "learning_rate": 1.799395837374941e-06, "loss": 0.7045, "step": 198690 }, { "epoch": 16.52, "learning_rate": 1.7992849818474072e-06, "loss": 0.7718, "step": 198700 }, { "epoch": 16.52, "learning_rate": 1.7991741263198735e-06, "loss": 0.8232, "step": 198710 }, { "epoch": 16.52, "learning_rate": 1.7990632707923398e-06, "loss": 0.7322, "step": 198720 }, { "epoch": 16.52, "learning_rate": 1.7989524152648061e-06, "loss": 0.7809, "step": 198730 }, { "epoch": 16.52, "learning_rate": 1.7988415597372724e-06, "loss": 0.7686, "step": 198740 }, { "epoch": 16.52, "learning_rate": 1.7987307042097385e-06, "loss": 0.8218, "step": 198750 }, { "epoch": 16.52, "learning_rate": 1.7986198486822048e-06, "loss": 0.7509, "step": 198760 }, { "epoch": 16.52, "learning_rate": 1.798508993154671e-06, "loss": 0.701, "step": 198770 }, { "epoch": 16.52, "learning_rate": 1.7983981376271374e-06, "loss": 0.7329, "step": 198780 }, { "epoch": 16.52, "learning_rate": 1.7982872820996035e-06, "loss": 0.805, "step": 198790 }, { "epoch": 16.52, "learning_rate": 1.7981764265720698e-06, "loss": 0.7978, "step": 198800 }, { "epoch": 16.52, "learning_rate": 1.798065571044536e-06, "loss": 0.7324, "step": 198810 }, { "epoch": 16.53, "learning_rate": 1.7979547155170024e-06, "loss": 0.7815, "step": 198820 }, { "epoch": 16.53, "learning_rate": 1.7978438599894687e-06, "loss": 0.6989, "step": 198830 }, { "epoch": 16.53, "learning_rate": 1.797733004461935e-06, "loss": 0.8155, "step": 198840 }, { "epoch": 16.53, "learning_rate": 1.7976221489344013e-06, "loss": 0.7644, "step": 198850 }, { "epoch": 16.53, "learning_rate": 1.7975112934068676e-06, "loss": 0.7928, "step": 198860 }, { "epoch": 16.53, "learning_rate": 1.7974004378793336e-06, "loss": 0.7737, "step": 198870 }, { "epoch": 16.53, "learning_rate": 1.7972895823518e-06, "loss": 0.7916, "step": 198880 }, { "epoch": 16.53, "learning_rate": 1.7971787268242662e-06, "loss": 0.8079, "step": 198890 }, { "epoch": 16.53, "learning_rate": 1.7970678712967325e-06, "loss": 0.8089, "step": 198900 }, { "epoch": 16.53, "learning_rate": 1.7969570157691986e-06, "loss": 0.7803, "step": 198910 }, { "epoch": 16.53, "learning_rate": 1.796846160241665e-06, "loss": 0.7253, "step": 198920 }, { "epoch": 16.53, "learning_rate": 1.7967353047141312e-06, "loss": 0.7616, "step": 198930 }, { "epoch": 16.54, "learning_rate": 1.7966244491865975e-06, "loss": 0.7704, "step": 198940 }, { "epoch": 16.54, "learning_rate": 1.7965135936590638e-06, "loss": 0.8108, "step": 198950 }, { "epoch": 16.54, "learning_rate": 1.79640273813153e-06, "loss": 0.7868, "step": 198960 }, { "epoch": 16.54, "learning_rate": 1.7962918826039964e-06, "loss": 0.7027, "step": 198970 }, { "epoch": 16.54, "learning_rate": 1.7961810270764627e-06, "loss": 0.7344, "step": 198980 }, { "epoch": 16.54, "learning_rate": 1.7960701715489288e-06, "loss": 0.7609, "step": 198990 }, { "epoch": 16.54, "learning_rate": 1.795959316021395e-06, "loss": 0.7529, "step": 199000 }, { "epoch": 16.54, "learning_rate": 1.7958484604938613e-06, "loss": 0.7658, "step": 199010 }, { "epoch": 16.54, "learning_rate": 1.7957376049663276e-06, "loss": 0.7675, "step": 199020 }, { "epoch": 16.54, "learning_rate": 1.7956267494387937e-06, "loss": 0.7644, "step": 199030 }, { "epoch": 16.54, "learning_rate": 1.79551589391126e-06, "loss": 0.759, "step": 199040 }, { "epoch": 16.54, "learning_rate": 1.7954050383837263e-06, "loss": 0.7774, "step": 199050 }, { "epoch": 16.55, "learning_rate": 1.7952941828561924e-06, "loss": 0.7648, "step": 199060 }, { "epoch": 16.55, "learning_rate": 1.7951833273286587e-06, "loss": 0.7718, "step": 199070 }, { "epoch": 16.55, "learning_rate": 1.7950724718011252e-06, "loss": 0.7513, "step": 199080 }, { "epoch": 16.55, "learning_rate": 1.7949616162735915e-06, "loss": 0.8034, "step": 199090 }, { "epoch": 16.55, "learning_rate": 1.7948507607460576e-06, "loss": 0.8123, "step": 199100 }, { "epoch": 16.55, "learning_rate": 1.7947399052185239e-06, "loss": 0.7933, "step": 199110 }, { "epoch": 16.55, "learning_rate": 1.7946290496909902e-06, "loss": 0.7542, "step": 199120 }, { "epoch": 16.55, "learning_rate": 1.7945181941634565e-06, "loss": 0.7395, "step": 199130 }, { "epoch": 16.55, "learning_rate": 1.7944073386359225e-06, "loss": 0.7278, "step": 199140 }, { "epoch": 16.55, "learning_rate": 1.7942964831083888e-06, "loss": 0.7498, "step": 199150 }, { "epoch": 16.55, "learning_rate": 1.7941856275808551e-06, "loss": 0.7762, "step": 199160 }, { "epoch": 16.55, "learning_rate": 1.7940747720533214e-06, "loss": 0.7156, "step": 199170 }, { "epoch": 16.56, "learning_rate": 1.7939639165257875e-06, "loss": 0.7011, "step": 199180 }, { "epoch": 16.56, "learning_rate": 1.7938530609982538e-06, "loss": 0.7696, "step": 199190 }, { "epoch": 16.56, "learning_rate": 1.7937422054707203e-06, "loss": 0.8538, "step": 199200 }, { "epoch": 16.56, "learning_rate": 1.7936313499431866e-06, "loss": 0.7834, "step": 199210 }, { "epoch": 16.56, "learning_rate": 1.7935204944156527e-06, "loss": 0.756, "step": 199220 }, { "epoch": 16.56, "learning_rate": 1.793409638888119e-06, "loss": 0.7515, "step": 199230 }, { "epoch": 16.56, "learning_rate": 1.7932987833605853e-06, "loss": 0.7912, "step": 199240 }, { "epoch": 16.56, "learning_rate": 1.7931879278330516e-06, "loss": 0.7328, "step": 199250 }, { "epoch": 16.56, "learning_rate": 1.7930770723055177e-06, "loss": 0.7757, "step": 199260 }, { "epoch": 16.56, "learning_rate": 1.792966216777984e-06, "loss": 0.7722, "step": 199270 }, { "epoch": 16.56, "learning_rate": 1.7928553612504503e-06, "loss": 0.7549, "step": 199280 }, { "epoch": 16.56, "learning_rate": 1.7927445057229166e-06, "loss": 0.7523, "step": 199290 }, { "epoch": 16.57, "learning_rate": 1.7926336501953826e-06, "loss": 0.7727, "step": 199300 }, { "epoch": 16.57, "learning_rate": 1.792522794667849e-06, "loss": 0.8341, "step": 199310 }, { "epoch": 16.57, "learning_rate": 1.7924119391403154e-06, "loss": 0.7414, "step": 199320 }, { "epoch": 16.57, "learning_rate": 1.7923010836127817e-06, "loss": 0.7667, "step": 199330 }, { "epoch": 16.57, "learning_rate": 1.7921902280852478e-06, "loss": 0.7619, "step": 199340 }, { "epoch": 16.57, "learning_rate": 1.7920793725577141e-06, "loss": 0.7664, "step": 199350 }, { "epoch": 16.57, "learning_rate": 1.7919685170301804e-06, "loss": 0.7485, "step": 199360 }, { "epoch": 16.57, "learning_rate": 1.7918576615026467e-06, "loss": 0.7398, "step": 199370 }, { "epoch": 16.57, "learning_rate": 1.7917468059751128e-06, "loss": 0.7998, "step": 199380 }, { "epoch": 16.57, "learning_rate": 1.791635950447579e-06, "loss": 0.7845, "step": 199390 }, { "epoch": 16.57, "learning_rate": 1.7915250949200454e-06, "loss": 0.7812, "step": 199400 }, { "epoch": 16.57, "learning_rate": 1.7914142393925117e-06, "loss": 0.7865, "step": 199410 }, { "epoch": 16.58, "learning_rate": 1.7913033838649778e-06, "loss": 0.7528, "step": 199420 }, { "epoch": 16.58, "learning_rate": 1.791192528337444e-06, "loss": 0.6942, "step": 199430 }, { "epoch": 16.58, "learning_rate": 1.7910816728099104e-06, "loss": 0.8136, "step": 199440 }, { "epoch": 16.58, "learning_rate": 1.7909708172823769e-06, "loss": 0.6886, "step": 199450 }, { "epoch": 16.58, "learning_rate": 1.790859961754843e-06, "loss": 0.7212, "step": 199460 }, { "epoch": 16.58, "learning_rate": 1.7907491062273092e-06, "loss": 0.6931, "step": 199470 }, { "epoch": 16.58, "learning_rate": 1.7906382506997755e-06, "loss": 0.7695, "step": 199480 }, { "epoch": 16.58, "learning_rate": 1.7905273951722416e-06, "loss": 0.6676, "step": 199490 }, { "epoch": 16.58, "learning_rate": 1.790416539644708e-06, "loss": 0.7951, "step": 199500 }, { "epoch": 16.58, "learning_rate": 1.7903056841171742e-06, "loss": 0.8212, "step": 199510 }, { "epoch": 16.58, "learning_rate": 1.7901948285896405e-06, "loss": 0.8264, "step": 199520 }, { "epoch": 16.58, "learning_rate": 1.7900839730621066e-06, "loss": 0.7956, "step": 199530 }, { "epoch": 16.59, "learning_rate": 1.7899731175345729e-06, "loss": 0.8169, "step": 199540 }, { "epoch": 16.59, "learning_rate": 1.7898622620070392e-06, "loss": 0.7521, "step": 199550 }, { "epoch": 16.59, "learning_rate": 1.7897514064795055e-06, "loss": 0.7907, "step": 199560 }, { "epoch": 16.59, "learning_rate": 1.7896405509519718e-06, "loss": 0.7962, "step": 199570 }, { "epoch": 16.59, "learning_rate": 1.789529695424438e-06, "loss": 0.7583, "step": 199580 }, { "epoch": 16.59, "learning_rate": 1.7894188398969044e-06, "loss": 0.71, "step": 199590 }, { "epoch": 16.59, "learning_rate": 1.7893079843693707e-06, "loss": 0.7646, "step": 199600 }, { "epoch": 16.59, "learning_rate": 1.7891971288418367e-06, "loss": 0.8165, "step": 199610 }, { "epoch": 16.59, "learning_rate": 1.789086273314303e-06, "loss": 0.7924, "step": 199620 }, { "epoch": 16.59, "learning_rate": 1.7889754177867693e-06, "loss": 0.7854, "step": 199630 }, { "epoch": 16.59, "learning_rate": 1.7888645622592356e-06, "loss": 0.745, "step": 199640 }, { "epoch": 16.59, "learning_rate": 1.7887537067317017e-06, "loss": 0.7457, "step": 199650 }, { "epoch": 16.6, "learning_rate": 1.788642851204168e-06, "loss": 0.8145, "step": 199660 }, { "epoch": 16.6, "learning_rate": 1.7885319956766343e-06, "loss": 0.7472, "step": 199670 }, { "epoch": 16.6, "learning_rate": 1.7884211401491006e-06, "loss": 0.7829, "step": 199680 }, { "epoch": 16.6, "learning_rate": 1.7883102846215669e-06, "loss": 0.7441, "step": 199690 }, { "epoch": 16.6, "learning_rate": 1.7881994290940332e-06, "loss": 0.8041, "step": 199700 }, { "epoch": 16.6, "learning_rate": 1.7880885735664995e-06, "loss": 0.7678, "step": 199710 }, { "epoch": 16.6, "learning_rate": 1.7879777180389658e-06, "loss": 0.7731, "step": 199720 }, { "epoch": 16.6, "learning_rate": 1.7878668625114319e-06, "loss": 0.7585, "step": 199730 }, { "epoch": 16.6, "learning_rate": 1.7877560069838982e-06, "loss": 0.7851, "step": 199740 }, { "epoch": 16.6, "learning_rate": 1.7876451514563644e-06, "loss": 0.8132, "step": 199750 }, { "epoch": 16.6, "learning_rate": 1.7875342959288307e-06, "loss": 0.7561, "step": 199760 }, { "epoch": 16.6, "learning_rate": 1.7874234404012968e-06, "loss": 0.7818, "step": 199770 }, { "epoch": 16.61, "learning_rate": 1.7873125848737631e-06, "loss": 0.7514, "step": 199780 }, { "epoch": 16.61, "learning_rate": 1.7872017293462294e-06, "loss": 0.7282, "step": 199790 }, { "epoch": 16.61, "learning_rate": 1.7870908738186957e-06, "loss": 0.7668, "step": 199800 }, { "epoch": 16.61, "learning_rate": 1.786980018291162e-06, "loss": 0.7691, "step": 199810 }, { "epoch": 16.61, "learning_rate": 1.7868691627636283e-06, "loss": 0.7696, "step": 199820 }, { "epoch": 16.61, "learning_rate": 1.7867583072360946e-06, "loss": 0.8052, "step": 199830 }, { "epoch": 16.61, "learning_rate": 1.7866474517085609e-06, "loss": 0.7732, "step": 199840 }, { "epoch": 16.61, "learning_rate": 1.786536596181027e-06, "loss": 0.7935, "step": 199850 }, { "epoch": 16.61, "learning_rate": 1.7864257406534933e-06, "loss": 0.775, "step": 199860 }, { "epoch": 16.61, "learning_rate": 1.7863148851259596e-06, "loss": 0.7838, "step": 199870 }, { "epoch": 16.61, "learning_rate": 1.7862040295984257e-06, "loss": 0.7658, "step": 199880 }, { "epoch": 16.61, "learning_rate": 1.786093174070892e-06, "loss": 0.7519, "step": 199890 }, { "epoch": 16.62, "learning_rate": 1.7859823185433582e-06, "loss": 0.7509, "step": 199900 }, { "epoch": 16.62, "learning_rate": 1.7858714630158245e-06, "loss": 0.7987, "step": 199910 }, { "epoch": 16.62, "learning_rate": 1.7857606074882906e-06, "loss": 0.8011, "step": 199920 }, { "epoch": 16.62, "learning_rate": 1.785649751960757e-06, "loss": 0.8068, "step": 199930 }, { "epoch": 16.62, "learning_rate": 1.7855388964332234e-06, "loss": 0.7948, "step": 199940 }, { "epoch": 16.62, "learning_rate": 1.7854280409056897e-06, "loss": 0.7684, "step": 199950 }, { "epoch": 16.62, "learning_rate": 1.7853171853781558e-06, "loss": 0.8503, "step": 199960 }, { "epoch": 16.62, "learning_rate": 1.785206329850622e-06, "loss": 0.8157, "step": 199970 }, { "epoch": 16.62, "learning_rate": 1.7850954743230884e-06, "loss": 0.7966, "step": 199980 }, { "epoch": 16.62, "learning_rate": 1.7849846187955547e-06, "loss": 0.785, "step": 199990 }, { "epoch": 16.62, "learning_rate": 1.7848737632680208e-06, "loss": 0.8318, "step": 200000 }, { "epoch": 16.62, "learning_rate": 1.784762907740487e-06, "loss": 0.7661, "step": 200010 }, { "epoch": 16.63, "learning_rate": 1.7846520522129534e-06, "loss": 0.728, "step": 200020 }, { "epoch": 16.63, "learning_rate": 1.7845411966854197e-06, "loss": 0.8027, "step": 200030 }, { "epoch": 16.63, "learning_rate": 1.7844303411578857e-06, "loss": 0.7801, "step": 200040 }, { "epoch": 16.63, "learning_rate": 1.784319485630352e-06, "loss": 0.8409, "step": 200050 }, { "epoch": 16.63, "learning_rate": 1.7842086301028185e-06, "loss": 0.8225, "step": 200060 }, { "epoch": 16.63, "learning_rate": 1.7840977745752848e-06, "loss": 0.7177, "step": 200070 }, { "epoch": 16.63, "learning_rate": 1.783986919047751e-06, "loss": 0.7423, "step": 200080 }, { "epoch": 16.63, "learning_rate": 1.7838760635202172e-06, "loss": 0.7021, "step": 200090 }, { "epoch": 16.63, "learning_rate": 1.7837652079926835e-06, "loss": 0.8004, "step": 200100 }, { "epoch": 16.63, "learning_rate": 1.7836543524651498e-06, "loss": 0.818, "step": 200110 }, { "epoch": 16.63, "learning_rate": 1.7835434969376159e-06, "loss": 0.7489, "step": 200120 }, { "epoch": 16.63, "learning_rate": 1.7834326414100822e-06, "loss": 0.7789, "step": 200130 }, { "epoch": 16.64, "learning_rate": 1.7833217858825485e-06, "loss": 0.8077, "step": 200140 }, { "epoch": 16.64, "learning_rate": 1.7832109303550148e-06, "loss": 0.8249, "step": 200150 }, { "epoch": 16.64, "learning_rate": 1.7831000748274809e-06, "loss": 0.7498, "step": 200160 }, { "epoch": 16.64, "learning_rate": 1.7829892192999472e-06, "loss": 0.8217, "step": 200170 }, { "epoch": 16.64, "learning_rate": 1.7828783637724137e-06, "loss": 0.8408, "step": 200180 }, { "epoch": 16.64, "learning_rate": 1.78276750824488e-06, "loss": 0.7464, "step": 200190 }, { "epoch": 16.64, "learning_rate": 1.782656652717346e-06, "loss": 0.7601, "step": 200200 }, { "epoch": 16.64, "learning_rate": 1.7825457971898123e-06, "loss": 0.7915, "step": 200210 }, { "epoch": 16.64, "learning_rate": 1.7824349416622786e-06, "loss": 0.833, "step": 200220 }, { "epoch": 16.64, "learning_rate": 1.782324086134745e-06, "loss": 0.7737, "step": 200230 }, { "epoch": 16.64, "learning_rate": 1.782213230607211e-06, "loss": 0.7223, "step": 200240 }, { "epoch": 16.64, "learning_rate": 1.7821023750796773e-06, "loss": 0.7416, "step": 200250 }, { "epoch": 16.65, "learning_rate": 1.7819915195521436e-06, "loss": 0.7567, "step": 200260 }, { "epoch": 16.65, "learning_rate": 1.7818806640246097e-06, "loss": 0.7992, "step": 200270 }, { "epoch": 16.65, "learning_rate": 1.781769808497076e-06, "loss": 0.7845, "step": 200280 }, { "epoch": 16.65, "learning_rate": 1.7816589529695423e-06, "loss": 0.7158, "step": 200290 }, { "epoch": 16.65, "learning_rate": 1.7815480974420086e-06, "loss": 0.784, "step": 200300 }, { "epoch": 16.65, "learning_rate": 1.781437241914475e-06, "loss": 0.745, "step": 200310 }, { "epoch": 16.65, "learning_rate": 1.7813263863869412e-06, "loss": 0.7718, "step": 200320 }, { "epoch": 16.65, "learning_rate": 1.7812155308594075e-06, "loss": 0.7868, "step": 200330 }, { "epoch": 16.65, "learning_rate": 1.7811046753318738e-06, "loss": 0.7276, "step": 200340 }, { "epoch": 16.65, "learning_rate": 1.7809938198043398e-06, "loss": 0.7725, "step": 200350 }, { "epoch": 16.65, "learning_rate": 1.7808829642768061e-06, "loss": 0.7441, "step": 200360 }, { "epoch": 16.65, "learning_rate": 1.7807721087492724e-06, "loss": 0.809, "step": 200370 }, { "epoch": 16.66, "learning_rate": 1.7806612532217387e-06, "loss": 0.7352, "step": 200380 }, { "epoch": 16.66, "learning_rate": 1.7805503976942048e-06, "loss": 0.7418, "step": 200390 }, { "epoch": 16.66, "learning_rate": 1.780439542166671e-06, "loss": 0.7896, "step": 200400 }, { "epoch": 16.66, "learning_rate": 1.7803286866391374e-06, "loss": 0.8084, "step": 200410 }, { "epoch": 16.66, "learning_rate": 1.7802178311116037e-06, "loss": 0.7358, "step": 200420 }, { "epoch": 16.66, "learning_rate": 1.78010697558407e-06, "loss": 0.7237, "step": 200430 }, { "epoch": 16.66, "learning_rate": 1.7799961200565363e-06, "loss": 0.7624, "step": 200440 }, { "epoch": 16.66, "learning_rate": 1.7798852645290026e-06, "loss": 0.8184, "step": 200450 }, { "epoch": 16.66, "learning_rate": 1.7797744090014689e-06, "loss": 0.8197, "step": 200460 }, { "epoch": 16.66, "learning_rate": 1.779663553473935e-06, "loss": 0.765, "step": 200470 }, { "epoch": 16.66, "learning_rate": 1.7795526979464013e-06, "loss": 0.7782, "step": 200480 }, { "epoch": 16.66, "learning_rate": 1.7794418424188675e-06, "loss": 0.7299, "step": 200490 }, { "epoch": 16.67, "learning_rate": 1.7793309868913338e-06, "loss": 0.793, "step": 200500 }, { "epoch": 16.67, "learning_rate": 1.7792201313638e-06, "loss": 0.7501, "step": 200510 }, { "epoch": 16.67, "learning_rate": 1.7791092758362662e-06, "loss": 0.7813, "step": 200520 }, { "epoch": 16.67, "learning_rate": 1.7789984203087325e-06, "loss": 0.7737, "step": 200530 }, { "epoch": 16.67, "learning_rate": 1.7788875647811988e-06, "loss": 0.7407, "step": 200540 }, { "epoch": 16.67, "learning_rate": 1.7787767092536651e-06, "loss": 0.7942, "step": 200550 }, { "epoch": 16.67, "learning_rate": 1.7786658537261314e-06, "loss": 0.7511, "step": 200560 }, { "epoch": 16.67, "learning_rate": 1.7785549981985977e-06, "loss": 0.7268, "step": 200570 }, { "epoch": 16.67, "learning_rate": 1.778444142671064e-06, "loss": 0.72, "step": 200580 }, { "epoch": 16.67, "learning_rate": 1.77833328714353e-06, "loss": 0.8416, "step": 200590 }, { "epoch": 16.67, "learning_rate": 1.7782224316159964e-06, "loss": 0.7734, "step": 200600 }, { "epoch": 16.67, "learning_rate": 1.7781115760884627e-06, "loss": 0.8043, "step": 200610 }, { "epoch": 16.68, "learning_rate": 1.778000720560929e-06, "loss": 0.7578, "step": 200620 }, { "epoch": 16.68, "learning_rate": 1.777889865033395e-06, "loss": 0.8388, "step": 200630 }, { "epoch": 16.68, "learning_rate": 1.7777790095058613e-06, "loss": 0.7314, "step": 200640 }, { "epoch": 16.68, "learning_rate": 1.7776681539783276e-06, "loss": 0.7605, "step": 200650 }, { "epoch": 16.68, "learning_rate": 1.777557298450794e-06, "loss": 0.8311, "step": 200660 }, { "epoch": 16.68, "learning_rate": 1.77744644292326e-06, "loss": 0.7448, "step": 200670 }, { "epoch": 16.68, "learning_rate": 1.7773355873957265e-06, "loss": 0.7694, "step": 200680 }, { "epoch": 16.68, "learning_rate": 1.7772247318681928e-06, "loss": 0.7992, "step": 200690 }, { "epoch": 16.68, "learning_rate": 1.7771138763406591e-06, "loss": 0.7695, "step": 200700 }, { "epoch": 16.68, "learning_rate": 1.7770030208131252e-06, "loss": 0.8521, "step": 200710 }, { "epoch": 16.68, "learning_rate": 1.7768921652855915e-06, "loss": 0.7099, "step": 200720 }, { "epoch": 16.68, "learning_rate": 1.7767813097580578e-06, "loss": 0.7467, "step": 200730 }, { "epoch": 16.69, "learning_rate": 1.7766704542305239e-06, "loss": 0.754, "step": 200740 }, { "epoch": 16.69, "learning_rate": 1.7765595987029902e-06, "loss": 0.7396, "step": 200750 }, { "epoch": 16.69, "learning_rate": 1.7764487431754565e-06, "loss": 0.7481, "step": 200760 }, { "epoch": 16.69, "learning_rate": 1.7763378876479228e-06, "loss": 0.7969, "step": 200770 }, { "epoch": 16.69, "learning_rate": 1.7762270321203888e-06, "loss": 0.7439, "step": 200780 }, { "epoch": 16.69, "learning_rate": 1.7761161765928551e-06, "loss": 0.8148, "step": 200790 }, { "epoch": 16.69, "learning_rate": 1.7760053210653216e-06, "loss": 0.8548, "step": 200800 }, { "epoch": 16.69, "learning_rate": 1.775894465537788e-06, "loss": 0.7612, "step": 200810 }, { "epoch": 16.69, "learning_rate": 1.775783610010254e-06, "loss": 0.7869, "step": 200820 }, { "epoch": 16.69, "learning_rate": 1.7756727544827203e-06, "loss": 0.7491, "step": 200830 }, { "epoch": 16.69, "learning_rate": 1.7755618989551866e-06, "loss": 0.7127, "step": 200840 }, { "epoch": 16.69, "learning_rate": 1.775451043427653e-06, "loss": 0.7531, "step": 200850 }, { "epoch": 16.7, "learning_rate": 1.775340187900119e-06, "loss": 0.848, "step": 200860 }, { "epoch": 16.7, "learning_rate": 1.7752293323725853e-06, "loss": 0.7487, "step": 200870 }, { "epoch": 16.7, "learning_rate": 1.7751184768450516e-06, "loss": 0.7435, "step": 200880 }, { "epoch": 16.7, "learning_rate": 1.7750076213175179e-06, "loss": 0.7826, "step": 200890 }, { "epoch": 16.7, "learning_rate": 1.774896765789984e-06, "loss": 0.7997, "step": 200900 }, { "epoch": 16.7, "learning_rate": 1.7747859102624503e-06, "loss": 0.7761, "step": 200910 }, { "epoch": 16.7, "learning_rate": 1.7746750547349168e-06, "loss": 0.8265, "step": 200920 }, { "epoch": 16.7, "learning_rate": 1.774564199207383e-06, "loss": 0.754, "step": 200930 }, { "epoch": 16.7, "learning_rate": 1.7744533436798491e-06, "loss": 0.7339, "step": 200940 }, { "epoch": 16.7, "learning_rate": 1.7743424881523154e-06, "loss": 0.725, "step": 200950 }, { "epoch": 16.7, "learning_rate": 1.7742316326247817e-06, "loss": 0.778, "step": 200960 }, { "epoch": 16.7, "learning_rate": 1.774120777097248e-06, "loss": 0.7574, "step": 200970 }, { "epoch": 16.71, "learning_rate": 1.7740099215697141e-06, "loss": 0.7412, "step": 200980 }, { "epoch": 16.71, "learning_rate": 1.7738990660421804e-06, "loss": 0.712, "step": 200990 }, { "epoch": 16.71, "learning_rate": 1.7737882105146467e-06, "loss": 0.8258, "step": 201000 }, { "epoch": 16.71, "learning_rate": 1.773677354987113e-06, "loss": 0.7534, "step": 201010 }, { "epoch": 16.71, "learning_rate": 1.773566499459579e-06, "loss": 0.7453, "step": 201020 }, { "epoch": 16.71, "learning_rate": 1.7734556439320454e-06, "loss": 0.76, "step": 201030 }, { "epoch": 16.71, "learning_rate": 1.7733447884045119e-06, "loss": 0.7542, "step": 201040 }, { "epoch": 16.71, "learning_rate": 1.7732339328769782e-06, "loss": 0.7898, "step": 201050 }, { "epoch": 16.71, "learning_rate": 1.7731230773494443e-06, "loss": 0.7924, "step": 201060 }, { "epoch": 16.71, "learning_rate": 1.7730122218219106e-06, "loss": 0.7742, "step": 201070 }, { "epoch": 16.71, "learning_rate": 1.7729013662943769e-06, "loss": 0.7475, "step": 201080 }, { "epoch": 16.71, "learning_rate": 1.7727905107668432e-06, "loss": 0.7578, "step": 201090 }, { "epoch": 16.72, "learning_rate": 1.7726796552393092e-06, "loss": 0.8497, "step": 201100 }, { "epoch": 16.72, "learning_rate": 1.7725687997117755e-06, "loss": 0.7716, "step": 201110 }, { "epoch": 16.72, "learning_rate": 1.7724579441842418e-06, "loss": 0.7226, "step": 201120 }, { "epoch": 16.72, "learning_rate": 1.772347088656708e-06, "loss": 0.713, "step": 201130 }, { "epoch": 16.72, "learning_rate": 1.7722362331291742e-06, "loss": 0.7876, "step": 201140 }, { "epoch": 16.72, "learning_rate": 1.7721253776016405e-06, "loss": 0.7928, "step": 201150 }, { "epoch": 16.72, "learning_rate": 1.7720145220741068e-06, "loss": 0.8556, "step": 201160 }, { "epoch": 16.72, "learning_rate": 1.771903666546573e-06, "loss": 0.7587, "step": 201170 }, { "epoch": 16.72, "learning_rate": 1.7717928110190394e-06, "loss": 0.7629, "step": 201180 }, { "epoch": 16.72, "learning_rate": 1.7716819554915057e-06, "loss": 0.7795, "step": 201190 }, { "epoch": 16.72, "learning_rate": 1.771571099963972e-06, "loss": 0.7223, "step": 201200 }, { "epoch": 16.72, "learning_rate": 1.771460244436438e-06, "loss": 0.7879, "step": 201210 }, { "epoch": 16.73, "learning_rate": 1.7713493889089044e-06, "loss": 0.7648, "step": 201220 }, { "epoch": 16.73, "learning_rate": 1.7712385333813707e-06, "loss": 0.7739, "step": 201230 }, { "epoch": 16.73, "learning_rate": 1.771127677853837e-06, "loss": 0.696, "step": 201240 }, { "epoch": 16.73, "learning_rate": 1.771016822326303e-06, "loss": 0.7619, "step": 201250 }, { "epoch": 16.73, "learning_rate": 1.7709059667987693e-06, "loss": 0.8218, "step": 201260 }, { "epoch": 16.73, "learning_rate": 1.7707951112712356e-06, "loss": 0.778, "step": 201270 }, { "epoch": 16.73, "learning_rate": 1.770684255743702e-06, "loss": 0.8272, "step": 201280 }, { "epoch": 16.73, "learning_rate": 1.7705844857689217e-06, "loss": 0.7482, "step": 201290 }, { "epoch": 16.73, "learning_rate": 1.7704736302413878e-06, "loss": 0.829, "step": 201300 }, { "epoch": 16.73, "learning_rate": 1.770362774713854e-06, "loss": 0.7513, "step": 201310 }, { "epoch": 16.73, "learning_rate": 1.7702519191863203e-06, "loss": 0.7831, "step": 201320 }, { "epoch": 16.73, "learning_rate": 1.7701410636587866e-06, "loss": 0.728, "step": 201330 }, { "epoch": 16.74, "learning_rate": 1.7700302081312527e-06, "loss": 0.7726, "step": 201340 }, { "epoch": 16.74, "learning_rate": 1.769919352603719e-06, "loss": 0.7849, "step": 201350 }, { "epoch": 16.74, "learning_rate": 1.7698084970761853e-06, "loss": 0.7923, "step": 201360 }, { "epoch": 16.74, "learning_rate": 1.7696976415486516e-06, "loss": 0.7529, "step": 201370 }, { "epoch": 16.74, "learning_rate": 1.769586786021118e-06, "loss": 0.7924, "step": 201380 }, { "epoch": 16.74, "learning_rate": 1.7694759304935842e-06, "loss": 0.7416, "step": 201390 }, { "epoch": 16.74, "learning_rate": 1.7693650749660505e-06, "loss": 0.8069, "step": 201400 }, { "epoch": 16.74, "learning_rate": 1.7692542194385168e-06, "loss": 0.7512, "step": 201410 }, { "epoch": 16.74, "learning_rate": 1.7691433639109829e-06, "loss": 0.7401, "step": 201420 }, { "epoch": 16.74, "learning_rate": 1.7690325083834492e-06, "loss": 0.7466, "step": 201430 }, { "epoch": 16.74, "learning_rate": 1.7689216528559155e-06, "loss": 0.7412, "step": 201440 }, { "epoch": 16.74, "learning_rate": 1.7688107973283818e-06, "loss": 0.8275, "step": 201450 }, { "epoch": 16.75, "learning_rate": 1.7686999418008478e-06, "loss": 0.7547, "step": 201460 }, { "epoch": 16.75, "learning_rate": 1.7685890862733141e-06, "loss": 0.7979, "step": 201470 }, { "epoch": 16.75, "learning_rate": 1.7684782307457804e-06, "loss": 0.7462, "step": 201480 }, { "epoch": 16.75, "learning_rate": 1.7683673752182467e-06, "loss": 0.7757, "step": 201490 }, { "epoch": 16.75, "learning_rate": 1.768256519690713e-06, "loss": 0.7711, "step": 201500 }, { "epoch": 16.75, "learning_rate": 1.7681456641631793e-06, "loss": 0.7641, "step": 201510 }, { "epoch": 16.75, "learning_rate": 1.7680348086356456e-06, "loss": 0.7897, "step": 201520 }, { "epoch": 16.75, "learning_rate": 1.767923953108112e-06, "loss": 0.7712, "step": 201530 }, { "epoch": 16.75, "learning_rate": 1.767813097580578e-06, "loss": 0.7, "step": 201540 }, { "epoch": 16.75, "learning_rate": 1.7677022420530443e-06, "loss": 0.7606, "step": 201550 }, { "epoch": 16.75, "learning_rate": 1.7675913865255106e-06, "loss": 0.7846, "step": 201560 }, { "epoch": 16.75, "learning_rate": 1.7674805309979769e-06, "loss": 0.7263, "step": 201570 }, { "epoch": 16.76, "learning_rate": 1.767369675470443e-06, "loss": 0.7373, "step": 201580 }, { "epoch": 16.76, "learning_rate": 1.7672588199429093e-06, "loss": 0.839, "step": 201590 }, { "epoch": 16.76, "learning_rate": 1.7671479644153756e-06, "loss": 0.8137, "step": 201600 }, { "epoch": 16.76, "learning_rate": 1.7670371088878418e-06, "loss": 0.792, "step": 201610 }, { "epoch": 16.76, "learning_rate": 1.7669262533603081e-06, "loss": 0.7712, "step": 201620 }, { "epoch": 16.76, "learning_rate": 1.7668153978327744e-06, "loss": 0.7413, "step": 201630 }, { "epoch": 16.76, "learning_rate": 1.7667045423052407e-06, "loss": 0.7294, "step": 201640 }, { "epoch": 16.76, "learning_rate": 1.766593686777707e-06, "loss": 0.7677, "step": 201650 }, { "epoch": 16.76, "learning_rate": 1.7664828312501731e-06, "loss": 0.7964, "step": 201660 }, { "epoch": 16.76, "learning_rate": 1.7663719757226394e-06, "loss": 0.7357, "step": 201670 }, { "epoch": 16.76, "learning_rate": 1.7662611201951057e-06, "loss": 0.7985, "step": 201680 }, { "epoch": 16.76, "learning_rate": 1.7661502646675718e-06, "loss": 0.7742, "step": 201690 }, { "epoch": 16.77, "learning_rate": 1.766039409140038e-06, "loss": 0.7807, "step": 201700 }, { "epoch": 16.77, "learning_rate": 1.7659285536125044e-06, "loss": 0.7465, "step": 201710 }, { "epoch": 16.77, "learning_rate": 1.7658176980849707e-06, "loss": 0.7732, "step": 201720 }, { "epoch": 16.77, "learning_rate": 1.7657068425574368e-06, "loss": 0.7802, "step": 201730 }, { "epoch": 16.77, "learning_rate": 1.765595987029903e-06, "loss": 0.7948, "step": 201740 }, { "epoch": 16.77, "learning_rate": 1.7654851315023696e-06, "loss": 0.7418, "step": 201750 }, { "epoch": 16.77, "learning_rate": 1.7653742759748359e-06, "loss": 0.743, "step": 201760 }, { "epoch": 16.77, "learning_rate": 1.765263420447302e-06, "loss": 0.7736, "step": 201770 }, { "epoch": 16.77, "learning_rate": 1.7651525649197682e-06, "loss": 0.8247, "step": 201780 }, { "epoch": 16.77, "learning_rate": 1.7650417093922345e-06, "loss": 0.8147, "step": 201790 }, { "epoch": 16.77, "learning_rate": 1.7649308538647008e-06, "loss": 0.7416, "step": 201800 }, { "epoch": 16.77, "learning_rate": 1.764819998337167e-06, "loss": 0.7863, "step": 201810 }, { "epoch": 16.77, "learning_rate": 1.7647091428096332e-06, "loss": 0.7472, "step": 201820 }, { "epoch": 16.78, "learning_rate": 1.7645982872820995e-06, "loss": 0.7783, "step": 201830 }, { "epoch": 16.78, "learning_rate": 1.7644874317545658e-06, "loss": 0.7729, "step": 201840 }, { "epoch": 16.78, "learning_rate": 1.7643765762270319e-06, "loss": 0.7045, "step": 201850 }, { "epoch": 16.78, "learning_rate": 1.7642657206994982e-06, "loss": 0.7857, "step": 201860 }, { "epoch": 16.78, "learning_rate": 1.7641548651719647e-06, "loss": 0.7876, "step": 201870 }, { "epoch": 16.78, "learning_rate": 1.764044009644431e-06, "loss": 0.7784, "step": 201880 }, { "epoch": 16.78, "learning_rate": 1.763933154116897e-06, "loss": 0.7578, "step": 201890 }, { "epoch": 16.78, "learning_rate": 1.7638222985893634e-06, "loss": 0.7736, "step": 201900 }, { "epoch": 16.78, "learning_rate": 1.7637114430618296e-06, "loss": 0.8317, "step": 201910 }, { "epoch": 16.78, "learning_rate": 1.763600587534296e-06, "loss": 0.7878, "step": 201920 }, { "epoch": 16.78, "learning_rate": 1.763489732006762e-06, "loss": 0.773, "step": 201930 }, { "epoch": 16.78, "learning_rate": 1.7633788764792283e-06, "loss": 0.7325, "step": 201940 }, { "epoch": 16.79, "learning_rate": 1.7632680209516946e-06, "loss": 0.7896, "step": 201950 }, { "epoch": 16.79, "learning_rate": 1.763157165424161e-06, "loss": 0.7841, "step": 201960 }, { "epoch": 16.79, "learning_rate": 1.763046309896627e-06, "loss": 0.7815, "step": 201970 }, { "epoch": 16.79, "learning_rate": 1.7629354543690933e-06, "loss": 0.7647, "step": 201980 }, { "epoch": 16.79, "learning_rate": 1.7628245988415598e-06, "loss": 0.7533, "step": 201990 }, { "epoch": 16.79, "learning_rate": 1.762713743314026e-06, "loss": 0.7849, "step": 202000 }, { "epoch": 16.79, "learning_rate": 1.7626028877864922e-06, "loss": 0.7677, "step": 202010 }, { "epoch": 16.79, "learning_rate": 1.7624920322589585e-06, "loss": 0.7871, "step": 202020 }, { "epoch": 16.79, "learning_rate": 1.7623811767314248e-06, "loss": 0.7493, "step": 202030 }, { "epoch": 16.79, "learning_rate": 1.762270321203891e-06, "loss": 0.7624, "step": 202040 }, { "epoch": 16.79, "learning_rate": 1.7621594656763571e-06, "loss": 0.8361, "step": 202050 }, { "epoch": 16.79, "learning_rate": 1.7620486101488234e-06, "loss": 0.8187, "step": 202060 }, { "epoch": 16.8, "learning_rate": 1.7619377546212897e-06, "loss": 0.8348, "step": 202070 }, { "epoch": 16.8, "learning_rate": 1.7618268990937558e-06, "loss": 0.7453, "step": 202080 }, { "epoch": 16.8, "learning_rate": 1.7617160435662221e-06, "loss": 0.7798, "step": 202090 }, { "epoch": 16.8, "learning_rate": 1.7616051880386884e-06, "loss": 0.7856, "step": 202100 }, { "epoch": 16.8, "learning_rate": 1.761494332511155e-06, "loss": 0.7056, "step": 202110 }, { "epoch": 16.8, "learning_rate": 1.761383476983621e-06, "loss": 0.6796, "step": 202120 }, { "epoch": 16.8, "learning_rate": 1.7612726214560873e-06, "loss": 0.7501, "step": 202130 }, { "epoch": 16.8, "learning_rate": 1.7611617659285536e-06, "loss": 0.7964, "step": 202140 }, { "epoch": 16.8, "learning_rate": 1.7610509104010199e-06, "loss": 0.8072, "step": 202150 }, { "epoch": 16.8, "learning_rate": 1.760940054873486e-06, "loss": 0.7753, "step": 202160 }, { "epoch": 16.8, "learning_rate": 1.7608291993459523e-06, "loss": 0.7303, "step": 202170 }, { "epoch": 16.8, "learning_rate": 1.7607183438184186e-06, "loss": 0.8065, "step": 202180 }, { "epoch": 16.81, "learning_rate": 1.7606074882908849e-06, "loss": 0.7403, "step": 202190 }, { "epoch": 16.81, "learning_rate": 1.760496632763351e-06, "loss": 0.7546, "step": 202200 }, { "epoch": 16.81, "learning_rate": 1.7603857772358172e-06, "loss": 0.8246, "step": 202210 }, { "epoch": 16.81, "learning_rate": 1.7602749217082835e-06, "loss": 0.7299, "step": 202220 }, { "epoch": 16.81, "learning_rate": 1.7601640661807498e-06, "loss": 0.7393, "step": 202230 }, { "epoch": 16.81, "learning_rate": 1.7600532106532161e-06, "loss": 0.6928, "step": 202240 }, { "epoch": 16.81, "learning_rate": 1.7599423551256824e-06, "loss": 0.8596, "step": 202250 }, { "epoch": 16.81, "learning_rate": 1.7598314995981487e-06, "loss": 0.8346, "step": 202260 }, { "epoch": 16.81, "learning_rate": 1.759720644070615e-06, "loss": 0.6889, "step": 202270 }, { "epoch": 16.81, "learning_rate": 1.759609788543081e-06, "loss": 0.7816, "step": 202280 }, { "epoch": 16.81, "learning_rate": 1.7594989330155474e-06, "loss": 0.8413, "step": 202290 }, { "epoch": 16.81, "learning_rate": 1.7593880774880137e-06, "loss": 0.8085, "step": 202300 }, { "epoch": 16.82, "learning_rate": 1.75927722196048e-06, "loss": 0.7914, "step": 202310 }, { "epoch": 16.82, "learning_rate": 1.759166366432946e-06, "loss": 0.8337, "step": 202320 }, { "epoch": 16.82, "learning_rate": 1.7590555109054124e-06, "loss": 0.7207, "step": 202330 }, { "epoch": 16.82, "learning_rate": 1.7589446553778787e-06, "loss": 0.8092, "step": 202340 }, { "epoch": 16.82, "learning_rate": 1.758833799850345e-06, "loss": 0.7784, "step": 202350 }, { "epoch": 16.82, "learning_rate": 1.7587229443228112e-06, "loss": 0.795, "step": 202360 }, { "epoch": 16.82, "learning_rate": 1.7586120887952775e-06, "loss": 0.7259, "step": 202370 }, { "epoch": 16.82, "learning_rate": 1.7585012332677438e-06, "loss": 0.7872, "step": 202380 }, { "epoch": 16.82, "learning_rate": 1.7583903777402101e-06, "loss": 0.8096, "step": 202390 }, { "epoch": 16.82, "learning_rate": 1.7582795222126762e-06, "loss": 0.8108, "step": 202400 }, { "epoch": 16.82, "learning_rate": 1.7581686666851425e-06, "loss": 0.7919, "step": 202410 }, { "epoch": 16.82, "learning_rate": 1.7580578111576088e-06, "loss": 0.7588, "step": 202420 }, { "epoch": 16.83, "learning_rate": 1.757946955630075e-06, "loss": 0.778, "step": 202430 }, { "epoch": 16.83, "learning_rate": 1.7578361001025412e-06, "loss": 0.7069, "step": 202440 }, { "epoch": 16.83, "learning_rate": 1.7577252445750075e-06, "loss": 0.8237, "step": 202450 }, { "epoch": 16.83, "learning_rate": 1.7576143890474738e-06, "loss": 0.817, "step": 202460 }, { "epoch": 16.83, "learning_rate": 1.7575035335199399e-06, "loss": 0.7493, "step": 202470 }, { "epoch": 16.83, "learning_rate": 1.7573926779924064e-06, "loss": 0.7794, "step": 202480 }, { "epoch": 16.83, "learning_rate": 1.7572818224648727e-06, "loss": 0.8282, "step": 202490 }, { "epoch": 16.83, "learning_rate": 1.757170966937339e-06, "loss": 0.7637, "step": 202500 }, { "epoch": 16.83, "learning_rate": 1.7570601114098053e-06, "loss": 0.8121, "step": 202510 }, { "epoch": 16.83, "learning_rate": 1.7569492558822713e-06, "loss": 0.8201, "step": 202520 }, { "epoch": 16.83, "learning_rate": 1.7568384003547376e-06, "loss": 0.8208, "step": 202530 }, { "epoch": 16.83, "learning_rate": 1.756727544827204e-06, "loss": 0.7625, "step": 202540 }, { "epoch": 16.84, "learning_rate": 1.75661668929967e-06, "loss": 0.7653, "step": 202550 }, { "epoch": 16.84, "learning_rate": 1.7565058337721363e-06, "loss": 0.758, "step": 202560 }, { "epoch": 16.84, "learning_rate": 1.7563949782446026e-06, "loss": 0.7406, "step": 202570 }, { "epoch": 16.84, "learning_rate": 1.756284122717069e-06, "loss": 0.7478, "step": 202580 }, { "epoch": 16.84, "learning_rate": 1.756173267189535e-06, "loss": 0.755, "step": 202590 }, { "epoch": 16.84, "learning_rate": 1.7560624116620013e-06, "loss": 0.7437, "step": 202600 }, { "epoch": 16.84, "learning_rate": 1.7559515561344678e-06, "loss": 0.8406, "step": 202610 }, { "epoch": 16.84, "learning_rate": 1.755840700606934e-06, "loss": 0.7559, "step": 202620 }, { "epoch": 16.84, "learning_rate": 1.7557298450794002e-06, "loss": 0.6949, "step": 202630 }, { "epoch": 16.84, "learning_rate": 1.7556189895518665e-06, "loss": 0.7887, "step": 202640 }, { "epoch": 16.84, "learning_rate": 1.7555081340243328e-06, "loss": 0.7799, "step": 202650 }, { "epoch": 16.84, "learning_rate": 1.755397278496799e-06, "loss": 0.7208, "step": 202660 }, { "epoch": 16.85, "learning_rate": 1.7552864229692651e-06, "loss": 0.8428, "step": 202670 }, { "epoch": 16.85, "learning_rate": 1.7551755674417314e-06, "loss": 0.7943, "step": 202680 }, { "epoch": 16.85, "learning_rate": 1.7550647119141977e-06, "loss": 0.8109, "step": 202690 }, { "epoch": 16.85, "learning_rate": 1.754953856386664e-06, "loss": 0.7877, "step": 202700 }, { "epoch": 16.85, "learning_rate": 1.75484300085913e-06, "loss": 0.7774, "step": 202710 }, { "epoch": 16.85, "learning_rate": 1.7547321453315964e-06, "loss": 0.8274, "step": 202720 }, { "epoch": 16.85, "learning_rate": 1.754621289804063e-06, "loss": 0.8171, "step": 202730 }, { "epoch": 16.85, "learning_rate": 1.7545104342765292e-06, "loss": 0.7775, "step": 202740 }, { "epoch": 16.85, "learning_rate": 1.7543995787489953e-06, "loss": 0.7804, "step": 202750 }, { "epoch": 16.85, "learning_rate": 1.7542887232214616e-06, "loss": 0.7818, "step": 202760 }, { "epoch": 16.85, "learning_rate": 1.7541778676939279e-06, "loss": 0.7836, "step": 202770 }, { "epoch": 16.85, "learning_rate": 1.7540670121663942e-06, "loss": 0.7455, "step": 202780 }, { "epoch": 16.86, "learning_rate": 1.7539561566388603e-06, "loss": 0.7455, "step": 202790 }, { "epoch": 16.86, "learning_rate": 1.7538453011113265e-06, "loss": 0.6942, "step": 202800 }, { "epoch": 16.86, "learning_rate": 1.7537344455837928e-06, "loss": 0.8373, "step": 202810 }, { "epoch": 16.86, "learning_rate": 1.7536235900562591e-06, "loss": 0.7852, "step": 202820 }, { "epoch": 16.86, "learning_rate": 1.7535127345287252e-06, "loss": 0.7563, "step": 202830 }, { "epoch": 16.86, "learning_rate": 1.7534018790011915e-06, "loss": 0.7547, "step": 202840 }, { "epoch": 16.86, "learning_rate": 1.753291023473658e-06, "loss": 0.8058, "step": 202850 }, { "epoch": 16.86, "learning_rate": 1.7531801679461243e-06, "loss": 0.81, "step": 202860 }, { "epoch": 16.86, "learning_rate": 1.7530693124185904e-06, "loss": 0.7695, "step": 202870 }, { "epoch": 16.86, "learning_rate": 1.7529584568910567e-06, "loss": 0.8067, "step": 202880 }, { "epoch": 16.86, "learning_rate": 1.752847601363523e-06, "loss": 0.76, "step": 202890 }, { "epoch": 16.86, "learning_rate": 1.7527367458359893e-06, "loss": 0.7582, "step": 202900 }, { "epoch": 16.87, "learning_rate": 1.7526258903084554e-06, "loss": 0.791, "step": 202910 }, { "epoch": 16.87, "learning_rate": 1.7525150347809217e-06, "loss": 0.7274, "step": 202920 }, { "epoch": 16.87, "learning_rate": 1.752404179253388e-06, "loss": 0.7491, "step": 202930 }, { "epoch": 16.87, "learning_rate": 1.752293323725854e-06, "loss": 0.7699, "step": 202940 }, { "epoch": 16.87, "learning_rate": 1.7521824681983203e-06, "loss": 0.7379, "step": 202950 }, { "epoch": 16.87, "learning_rate": 1.7520716126707866e-06, "loss": 0.8254, "step": 202960 }, { "epoch": 16.87, "learning_rate": 1.751960757143253e-06, "loss": 0.6964, "step": 202970 }, { "epoch": 16.87, "learning_rate": 1.7518499016157192e-06, "loss": 0.7914, "step": 202980 }, { "epoch": 16.87, "learning_rate": 1.7517390460881855e-06, "loss": 0.7505, "step": 202990 }, { "epoch": 16.87, "learning_rate": 1.7516281905606518e-06, "loss": 0.7661, "step": 203000 }, { "epoch": 16.87, "learning_rate": 1.7515173350331181e-06, "loss": 0.7773, "step": 203010 }, { "epoch": 16.87, "learning_rate": 1.7514064795055842e-06, "loss": 0.7222, "step": 203020 }, { "epoch": 16.88, "learning_rate": 1.7512956239780505e-06, "loss": 0.8069, "step": 203030 }, { "epoch": 16.88, "learning_rate": 1.7511847684505168e-06, "loss": 0.7611, "step": 203040 }, { "epoch": 16.88, "learning_rate": 1.751073912922983e-06, "loss": 0.8333, "step": 203050 }, { "epoch": 16.88, "learning_rate": 1.7509630573954492e-06, "loss": 0.7405, "step": 203060 }, { "epoch": 16.88, "learning_rate": 1.7508522018679155e-06, "loss": 0.7941, "step": 203070 }, { "epoch": 16.88, "learning_rate": 1.7507413463403818e-06, "loss": 0.6898, "step": 203080 }, { "epoch": 16.88, "learning_rate": 1.750630490812848e-06, "loss": 0.8142, "step": 203090 }, { "epoch": 16.88, "learning_rate": 1.7505196352853143e-06, "loss": 0.7385, "step": 203100 }, { "epoch": 16.88, "learning_rate": 1.7504087797577806e-06, "loss": 0.7909, "step": 203110 }, { "epoch": 16.88, "learning_rate": 1.750297924230247e-06, "loss": 0.7895, "step": 203120 }, { "epoch": 16.88, "learning_rate": 1.7501870687027132e-06, "loss": 0.7705, "step": 203130 }, { "epoch": 16.88, "learning_rate": 1.7500762131751793e-06, "loss": 0.7401, "step": 203140 }, { "epoch": 16.89, "learning_rate": 1.7499653576476456e-06, "loss": 0.8141, "step": 203150 }, { "epoch": 16.89, "learning_rate": 1.749854502120112e-06, "loss": 0.757, "step": 203160 }, { "epoch": 16.89, "learning_rate": 1.7497436465925782e-06, "loss": 0.722, "step": 203170 }, { "epoch": 16.89, "learning_rate": 1.7496327910650443e-06, "loss": 0.7262, "step": 203180 }, { "epoch": 16.89, "learning_rate": 1.7495219355375106e-06, "loss": 0.7885, "step": 203190 }, { "epoch": 16.89, "learning_rate": 1.7494110800099769e-06, "loss": 0.8004, "step": 203200 }, { "epoch": 16.89, "learning_rate": 1.7493002244824432e-06, "loss": 0.7781, "step": 203210 }, { "epoch": 16.89, "learning_rate": 1.7491893689549095e-06, "loss": 0.7412, "step": 203220 }, { "epoch": 16.89, "learning_rate": 1.7490785134273758e-06, "loss": 0.737, "step": 203230 }, { "epoch": 16.89, "learning_rate": 1.748967657899842e-06, "loss": 0.7224, "step": 203240 }, { "epoch": 16.89, "learning_rate": 1.7488568023723084e-06, "loss": 0.8431, "step": 203250 }, { "epoch": 16.89, "learning_rate": 1.7487459468447744e-06, "loss": 0.7737, "step": 203260 }, { "epoch": 16.9, "learning_rate": 1.7486350913172407e-06, "loss": 0.7619, "step": 203270 }, { "epoch": 16.9, "learning_rate": 1.748524235789707e-06, "loss": 0.7545, "step": 203280 }, { "epoch": 16.9, "learning_rate": 1.7484133802621733e-06, "loss": 0.7851, "step": 203290 }, { "epoch": 16.9, "learning_rate": 1.7483025247346394e-06, "loss": 0.7558, "step": 203300 }, { "epoch": 16.9, "learning_rate": 1.7481916692071057e-06, "loss": 0.7169, "step": 203310 }, { "epoch": 16.9, "learning_rate": 1.748080813679572e-06, "loss": 0.7621, "step": 203320 }, { "epoch": 16.9, "learning_rate": 1.747969958152038e-06, "loss": 0.7845, "step": 203330 }, { "epoch": 16.9, "learning_rate": 1.7478591026245046e-06, "loss": 0.8025, "step": 203340 }, { "epoch": 16.9, "learning_rate": 1.7477482470969709e-06, "loss": 0.8292, "step": 203350 }, { "epoch": 16.9, "learning_rate": 1.7476373915694372e-06, "loss": 0.74, "step": 203360 }, { "epoch": 16.9, "learning_rate": 1.7475265360419033e-06, "loss": 0.7376, "step": 203370 }, { "epoch": 16.9, "learning_rate": 1.7474156805143696e-06, "loss": 0.7635, "step": 203380 }, { "epoch": 16.91, "learning_rate": 1.7473048249868359e-06, "loss": 0.7398, "step": 203390 }, { "epoch": 16.91, "learning_rate": 1.7471939694593021e-06, "loss": 0.7524, "step": 203400 }, { "epoch": 16.91, "learning_rate": 1.7470831139317682e-06, "loss": 0.7764, "step": 203410 }, { "epoch": 16.91, "learning_rate": 1.7469722584042345e-06, "loss": 0.7096, "step": 203420 }, { "epoch": 16.91, "learning_rate": 1.7468614028767008e-06, "loss": 0.7555, "step": 203430 }, { "epoch": 16.91, "learning_rate": 1.7467505473491671e-06, "loss": 0.7497, "step": 203440 }, { "epoch": 16.91, "learning_rate": 1.7466396918216332e-06, "loss": 0.7733, "step": 203450 }, { "epoch": 16.91, "learning_rate": 1.7465288362940995e-06, "loss": 0.7964, "step": 203460 }, { "epoch": 16.91, "learning_rate": 1.746417980766566e-06, "loss": 0.7408, "step": 203470 }, { "epoch": 16.91, "learning_rate": 1.7463071252390323e-06, "loss": 0.7548, "step": 203480 }, { "epoch": 16.91, "learning_rate": 1.7461962697114984e-06, "loss": 0.7046, "step": 203490 }, { "epoch": 16.91, "learning_rate": 1.7460854141839647e-06, "loss": 0.7687, "step": 203500 }, { "epoch": 16.92, "learning_rate": 1.745974558656431e-06, "loss": 0.8408, "step": 203510 }, { "epoch": 16.92, "learning_rate": 1.7458637031288973e-06, "loss": 0.6688, "step": 203520 }, { "epoch": 16.92, "learning_rate": 1.7457528476013634e-06, "loss": 0.802, "step": 203530 }, { "epoch": 16.92, "learning_rate": 1.7456419920738296e-06, "loss": 0.7837, "step": 203540 }, { "epoch": 16.92, "learning_rate": 1.745531136546296e-06, "loss": 0.796, "step": 203550 }, { "epoch": 16.92, "learning_rate": 1.7454202810187622e-06, "loss": 0.7886, "step": 203560 }, { "epoch": 16.92, "learning_rate": 1.7453094254912283e-06, "loss": 0.8125, "step": 203570 }, { "epoch": 16.92, "learning_rate": 1.7451985699636946e-06, "loss": 0.7396, "step": 203580 }, { "epoch": 16.92, "learning_rate": 1.7450877144361611e-06, "loss": 0.7984, "step": 203590 }, { "epoch": 16.92, "learning_rate": 1.7449768589086274e-06, "loss": 0.7758, "step": 203600 }, { "epoch": 16.92, "learning_rate": 1.7448660033810935e-06, "loss": 0.798, "step": 203610 }, { "epoch": 16.92, "learning_rate": 1.7447551478535598e-06, "loss": 0.7494, "step": 203620 }, { "epoch": 16.93, "learning_rate": 1.744644292326026e-06, "loss": 0.8212, "step": 203630 }, { "epoch": 16.93, "learning_rate": 1.7445334367984924e-06, "loss": 0.7488, "step": 203640 }, { "epoch": 16.93, "learning_rate": 1.7444225812709585e-06, "loss": 0.7842, "step": 203650 }, { "epoch": 16.93, "learning_rate": 1.7443117257434248e-06, "loss": 0.7915, "step": 203660 }, { "epoch": 16.93, "learning_rate": 1.744200870215891e-06, "loss": 0.8126, "step": 203670 }, { "epoch": 16.93, "learning_rate": 1.7440900146883574e-06, "loss": 0.7421, "step": 203680 }, { "epoch": 16.93, "learning_rate": 1.7439791591608234e-06, "loss": 0.7538, "step": 203690 }, { "epoch": 16.93, "learning_rate": 1.7438683036332897e-06, "loss": 0.7489, "step": 203700 }, { "epoch": 16.93, "learning_rate": 1.7437574481057562e-06, "loss": 0.7528, "step": 203710 }, { "epoch": 16.93, "learning_rate": 1.7436465925782225e-06, "loss": 0.8004, "step": 203720 }, { "epoch": 16.93, "learning_rate": 1.7435357370506886e-06, "loss": 0.6911, "step": 203730 }, { "epoch": 16.93, "learning_rate": 1.743424881523155e-06, "loss": 0.7443, "step": 203740 }, { "epoch": 16.94, "learning_rate": 1.7433140259956212e-06, "loss": 0.7998, "step": 203750 }, { "epoch": 16.94, "learning_rate": 1.7432031704680873e-06, "loss": 0.7682, "step": 203760 }, { "epoch": 16.94, "learning_rate": 1.7430923149405536e-06, "loss": 0.7638, "step": 203770 }, { "epoch": 16.94, "learning_rate": 1.7429814594130199e-06, "loss": 0.7187, "step": 203780 }, { "epoch": 16.94, "learning_rate": 1.7428706038854862e-06, "loss": 0.7718, "step": 203790 }, { "epoch": 16.94, "learning_rate": 1.7427597483579523e-06, "loss": 0.8795, "step": 203800 }, { "epoch": 16.94, "learning_rate": 1.7426488928304186e-06, "loss": 0.7761, "step": 203810 }, { "epoch": 16.94, "learning_rate": 1.7425380373028849e-06, "loss": 0.7759, "step": 203820 }, { "epoch": 16.94, "learning_rate": 1.7424271817753512e-06, "loss": 0.7512, "step": 203830 }, { "epoch": 16.94, "learning_rate": 1.7423163262478174e-06, "loss": 0.7765, "step": 203840 }, { "epoch": 16.94, "learning_rate": 1.7422054707202837e-06, "loss": 0.7784, "step": 203850 }, { "epoch": 16.94, "learning_rate": 1.74209461519275e-06, "loss": 0.7757, "step": 203860 }, { "epoch": 16.95, "learning_rate": 1.7419837596652163e-06, "loss": 0.8493, "step": 203870 }, { "epoch": 16.95, "learning_rate": 1.7418729041376824e-06, "loss": 0.8294, "step": 203880 }, { "epoch": 16.95, "learning_rate": 1.7417620486101487e-06, "loss": 0.7402, "step": 203890 }, { "epoch": 16.95, "learning_rate": 1.741651193082615e-06, "loss": 0.7619, "step": 203900 }, { "epoch": 16.95, "learning_rate": 1.7415403375550813e-06, "loss": 0.7675, "step": 203910 }, { "epoch": 16.95, "learning_rate": 1.7414294820275474e-06, "loss": 0.74, "step": 203920 }, { "epoch": 16.95, "learning_rate": 1.7413186265000137e-06, "loss": 0.7217, "step": 203930 }, { "epoch": 16.95, "learning_rate": 1.74120777097248e-06, "loss": 0.777, "step": 203940 }, { "epoch": 16.95, "learning_rate": 1.7410969154449463e-06, "loss": 0.7468, "step": 203950 }, { "epoch": 16.95, "learning_rate": 1.7409860599174126e-06, "loss": 0.7524, "step": 203960 }, { "epoch": 16.95, "learning_rate": 1.7408752043898789e-06, "loss": 0.8501, "step": 203970 }, { "epoch": 16.95, "learning_rate": 1.7407643488623452e-06, "loss": 0.7806, "step": 203980 }, { "epoch": 16.96, "learning_rate": 1.7406534933348115e-06, "loss": 0.7604, "step": 203990 }, { "epoch": 16.96, "learning_rate": 1.7405426378072775e-06, "loss": 0.8633, "step": 204000 }, { "epoch": 16.96, "learning_rate": 1.7404317822797438e-06, "loss": 0.7933, "step": 204010 }, { "epoch": 16.96, "learning_rate": 1.7403209267522101e-06, "loss": 0.7561, "step": 204020 }, { "epoch": 16.96, "learning_rate": 1.7402100712246764e-06, "loss": 0.7422, "step": 204030 }, { "epoch": 16.96, "learning_rate": 1.7400992156971425e-06, "loss": 0.7275, "step": 204040 }, { "epoch": 16.96, "learning_rate": 1.7399883601696088e-06, "loss": 0.7737, "step": 204050 }, { "epoch": 16.96, "learning_rate": 1.739877504642075e-06, "loss": 0.8058, "step": 204060 }, { "epoch": 16.96, "learning_rate": 1.7397666491145414e-06, "loss": 0.7354, "step": 204070 }, { "epoch": 16.96, "learning_rate": 1.7396557935870077e-06, "loss": 0.784, "step": 204080 }, { "epoch": 16.96, "learning_rate": 1.739544938059474e-06, "loss": 0.7508, "step": 204090 }, { "epoch": 16.96, "learning_rate": 1.7394340825319403e-06, "loss": 0.83, "step": 204100 }, { "epoch": 16.97, "learning_rate": 1.7393232270044066e-06, "loss": 0.7801, "step": 204110 }, { "epoch": 16.97, "learning_rate": 1.7392123714768727e-06, "loss": 0.7616, "step": 204120 }, { "epoch": 16.97, "learning_rate": 1.739101515949339e-06, "loss": 0.7673, "step": 204130 }, { "epoch": 16.97, "learning_rate": 1.7389906604218053e-06, "loss": 0.7174, "step": 204140 }, { "epoch": 16.97, "learning_rate": 1.7388798048942715e-06, "loss": 0.8049, "step": 204150 }, { "epoch": 16.97, "learning_rate": 1.7387689493667376e-06, "loss": 0.7262, "step": 204160 }, { "epoch": 16.97, "learning_rate": 1.738658093839204e-06, "loss": 0.7819, "step": 204170 }, { "epoch": 16.97, "learning_rate": 1.7385472383116702e-06, "loss": 0.7696, "step": 204180 }, { "epoch": 16.97, "learning_rate": 1.7384363827841363e-06, "loss": 0.7968, "step": 204190 }, { "epoch": 16.97, "learning_rate": 1.7383255272566028e-06, "loss": 0.8218, "step": 204200 }, { "epoch": 16.97, "learning_rate": 1.738214671729069e-06, "loss": 0.7265, "step": 204210 }, { "epoch": 16.97, "learning_rate": 1.7381038162015354e-06, "loss": 0.7835, "step": 204220 }, { "epoch": 16.98, "learning_rate": 1.7379929606740015e-06, "loss": 0.7632, "step": 204230 }, { "epoch": 16.98, "learning_rate": 1.7378821051464678e-06, "loss": 0.8301, "step": 204240 }, { "epoch": 16.98, "learning_rate": 1.737771249618934e-06, "loss": 0.8313, "step": 204250 }, { "epoch": 16.98, "learning_rate": 1.7376603940914004e-06, "loss": 0.7968, "step": 204260 }, { "epoch": 16.98, "learning_rate": 1.7375495385638665e-06, "loss": 0.7555, "step": 204270 }, { "epoch": 16.98, "learning_rate": 1.7374386830363327e-06, "loss": 0.7915, "step": 204280 }, { "epoch": 16.98, "learning_rate": 1.737327827508799e-06, "loss": 0.8185, "step": 204290 }, { "epoch": 16.98, "learning_rate": 1.7372169719812653e-06, "loss": 0.8062, "step": 204300 }, { "epoch": 16.98, "learning_rate": 1.7371061164537314e-06, "loss": 0.7714, "step": 204310 }, { "epoch": 16.98, "learning_rate": 1.7369952609261977e-06, "loss": 0.8101, "step": 204320 }, { "epoch": 16.98, "learning_rate": 1.7368844053986642e-06, "loss": 0.7592, "step": 204330 }, { "epoch": 16.98, "learning_rate": 1.7367735498711305e-06, "loss": 0.7266, "step": 204340 }, { "epoch": 16.99, "learning_rate": 1.7366626943435966e-06, "loss": 0.854, "step": 204350 }, { "epoch": 16.99, "learning_rate": 1.736551838816063e-06, "loss": 0.8282, "step": 204360 }, { "epoch": 16.99, "learning_rate": 1.7364409832885292e-06, "loss": 0.7471, "step": 204370 }, { "epoch": 16.99, "learning_rate": 1.7363301277609955e-06, "loss": 0.7245, "step": 204380 }, { "epoch": 16.99, "learning_rate": 1.7362192722334616e-06, "loss": 0.8079, "step": 204390 }, { "epoch": 16.99, "learning_rate": 1.7361084167059279e-06, "loss": 0.7563, "step": 204400 }, { "epoch": 16.99, "learning_rate": 1.7359975611783942e-06, "loss": 0.8641, "step": 204410 }, { "epoch": 16.99, "learning_rate": 1.7358867056508605e-06, "loss": 0.7561, "step": 204420 }, { "epoch": 16.99, "learning_rate": 1.7357758501233265e-06, "loss": 0.7338, "step": 204430 }, { "epoch": 16.99, "learning_rate": 1.7356649945957928e-06, "loss": 0.7293, "step": 204440 }, { "epoch": 16.99, "learning_rate": 1.7355541390682593e-06, "loss": 0.822, "step": 204450 }, { "epoch": 16.99, "learning_rate": 1.7354543690934789e-06, "loss": 0.7799, "step": 204460 }, { "epoch": 17.0, "learning_rate": 1.7353435135659452e-06, "loss": 0.7432, "step": 204470 }, { "epoch": 17.0, "learning_rate": 1.7352326580384113e-06, "loss": 0.712, "step": 204480 }, { "epoch": 17.0, "learning_rate": 1.7351218025108776e-06, "loss": 0.7517, "step": 204490 }, { "epoch": 17.0, "learning_rate": 1.7350109469833439e-06, "loss": 0.8196, "step": 204500 }, { "epoch": 17.0, "learning_rate": 1.7349000914558102e-06, "loss": 0.7993, "step": 204510 }, { "epoch": 17.0, "learning_rate": 1.7347892359282762e-06, "loss": 0.7918, "step": 204520 }, { "epoch": 17.0, "eval_loss": 1.1085423231124878, "eval_runtime": 354.6106, "eval_samples_per_second": 7.541, "eval_steps_per_second": 3.77, "eval_wer": 0.645557580295047, "step": 204527 }, { "epoch": 17.0, "learning_rate": 1.7346783804007425e-06, "loss": 0.7499, "step": 204530 }, { "epoch": 17.0, "learning_rate": 1.734567524873209e-06, "loss": 0.7099, "step": 204540 }, { "epoch": 17.0, "learning_rate": 1.7344566693456753e-06, "loss": 0.7672, "step": 204550 }, { "epoch": 17.0, "learning_rate": 1.7343458138181414e-06, "loss": 0.764, "step": 204560 }, { "epoch": 17.0, "learning_rate": 1.7342349582906077e-06, "loss": 0.7545, "step": 204570 }, { "epoch": 17.0, "learning_rate": 1.734124102763074e-06, "loss": 0.8296, "step": 204580 }, { "epoch": 17.01, "learning_rate": 1.7340132472355403e-06, "loss": 0.7815, "step": 204590 }, { "epoch": 17.01, "learning_rate": 1.7339023917080064e-06, "loss": 0.7164, "step": 204600 }, { "epoch": 17.01, "learning_rate": 1.7337915361804727e-06, "loss": 0.7397, "step": 204610 }, { "epoch": 17.01, "learning_rate": 1.733680680652939e-06, "loss": 0.781, "step": 204620 }, { "epoch": 17.01, "learning_rate": 1.7335698251254053e-06, "loss": 0.8382, "step": 204630 }, { "epoch": 17.01, "learning_rate": 1.7334589695978714e-06, "loss": 0.7742, "step": 204640 }, { "epoch": 17.01, "learning_rate": 1.7333481140703377e-06, "loss": 0.774, "step": 204650 }, { "epoch": 17.01, "learning_rate": 1.7332372585428042e-06, "loss": 0.7791, "step": 204660 }, { "epoch": 17.01, "learning_rate": 1.7331264030152705e-06, "loss": 0.7194, "step": 204670 }, { "epoch": 17.01, "learning_rate": 1.7330155474877365e-06, "loss": 0.7497, "step": 204680 }, { "epoch": 17.01, "learning_rate": 1.7329046919602028e-06, "loss": 0.8187, "step": 204690 }, { "epoch": 17.01, "learning_rate": 1.7327938364326691e-06, "loss": 0.7698, "step": 204700 }, { "epoch": 17.02, "learning_rate": 1.7326829809051354e-06, "loss": 0.7599, "step": 204710 }, { "epoch": 17.02, "learning_rate": 1.7325721253776015e-06, "loss": 0.8064, "step": 204720 }, { "epoch": 17.02, "learning_rate": 1.732472355402821e-06, "loss": 0.7697, "step": 204730 }, { "epoch": 17.02, "learning_rate": 1.7323614998752873e-06, "loss": 0.7456, "step": 204740 }, { "epoch": 17.02, "learning_rate": 1.7322506443477538e-06, "loss": 0.7271, "step": 204750 }, { "epoch": 17.02, "learning_rate": 1.7321397888202201e-06, "loss": 0.7802, "step": 204760 }, { "epoch": 17.02, "learning_rate": 1.7320289332926862e-06, "loss": 0.7493, "step": 204770 }, { "epoch": 17.02, "learning_rate": 1.7319180777651525e-06, "loss": 0.7677, "step": 204780 }, { "epoch": 17.02, "learning_rate": 1.7318072222376188e-06, "loss": 0.7793, "step": 204790 }, { "epoch": 17.02, "learning_rate": 1.7316963667100851e-06, "loss": 0.7334, "step": 204800 }, { "epoch": 17.02, "learning_rate": 1.7315855111825512e-06, "loss": 0.7639, "step": 204810 }, { "epoch": 17.02, "learning_rate": 1.7314746556550175e-06, "loss": 0.7713, "step": 204820 }, { "epoch": 17.03, "learning_rate": 1.7313638001274838e-06, "loss": 0.7998, "step": 204830 }, { "epoch": 17.03, "learning_rate": 1.7312529445999499e-06, "loss": 0.8076, "step": 204840 }, { "epoch": 17.03, "learning_rate": 1.7311420890724162e-06, "loss": 0.7138, "step": 204850 }, { "epoch": 17.03, "learning_rate": 1.7310312335448825e-06, "loss": 0.8227, "step": 204860 }, { "epoch": 17.03, "learning_rate": 1.730920378017349e-06, "loss": 0.7717, "step": 204870 }, { "epoch": 17.03, "learning_rate": 1.730809522489815e-06, "loss": 0.7178, "step": 204880 }, { "epoch": 17.03, "learning_rate": 1.7306986669622813e-06, "loss": 0.7856, "step": 204890 }, { "epoch": 17.03, "learning_rate": 1.7305878114347476e-06, "loss": 0.7663, "step": 204900 }, { "epoch": 17.03, "learning_rate": 1.730476955907214e-06, "loss": 0.8378, "step": 204910 }, { "epoch": 17.03, "learning_rate": 1.73036610037968e-06, "loss": 0.7492, "step": 204920 }, { "epoch": 17.03, "learning_rate": 1.7302552448521463e-06, "loss": 0.7843, "step": 204930 }, { "epoch": 17.03, "learning_rate": 1.7301443893246126e-06, "loss": 0.8151, "step": 204940 }, { "epoch": 17.04, "learning_rate": 1.730033533797079e-06, "loss": 0.7469, "step": 204950 }, { "epoch": 17.04, "learning_rate": 1.729922678269545e-06, "loss": 0.7465, "step": 204960 }, { "epoch": 17.04, "learning_rate": 1.7298118227420113e-06, "loss": 0.8124, "step": 204970 }, { "epoch": 17.04, "learning_rate": 1.7297009672144776e-06, "loss": 0.7449, "step": 204980 }, { "epoch": 17.04, "learning_rate": 1.729590111686944e-06, "loss": 0.8322, "step": 204990 }, { "epoch": 17.04, "learning_rate": 1.7294792561594102e-06, "loss": 0.7867, "step": 205000 }, { "epoch": 17.04, "learning_rate": 1.7293684006318765e-06, "loss": 0.7345, "step": 205010 }, { "epoch": 17.04, "learning_rate": 1.7292575451043428e-06, "loss": 0.7541, "step": 205020 }, { "epoch": 17.04, "learning_rate": 1.729146689576809e-06, "loss": 0.8049, "step": 205030 }, { "epoch": 17.04, "learning_rate": 1.7290358340492751e-06, "loss": 0.8398, "step": 205040 }, { "epoch": 17.04, "learning_rate": 1.7289249785217414e-06, "loss": 0.8066, "step": 205050 }, { "epoch": 17.04, "learning_rate": 1.7288141229942077e-06, "loss": 0.7635, "step": 205060 }, { "epoch": 17.05, "learning_rate": 1.728703267466674e-06, "loss": 0.7683, "step": 205070 }, { "epoch": 17.05, "learning_rate": 1.7285924119391401e-06, "loss": 0.7958, "step": 205080 }, { "epoch": 17.05, "learning_rate": 1.7284815564116064e-06, "loss": 0.7644, "step": 205090 }, { "epoch": 17.05, "learning_rate": 1.7283707008840727e-06, "loss": 0.8182, "step": 205100 }, { "epoch": 17.05, "learning_rate": 1.728259845356539e-06, "loss": 0.7426, "step": 205110 }, { "epoch": 17.05, "learning_rate": 1.7281489898290053e-06, "loss": 0.7996, "step": 205120 }, { "epoch": 17.05, "learning_rate": 1.7280381343014716e-06, "loss": 0.7384, "step": 205130 }, { "epoch": 17.05, "learning_rate": 1.7279272787739379e-06, "loss": 0.7961, "step": 205140 }, { "epoch": 17.05, "learning_rate": 1.7278164232464042e-06, "loss": 0.7954, "step": 205150 }, { "epoch": 17.05, "learning_rate": 1.7277055677188703e-06, "loss": 0.7817, "step": 205160 }, { "epoch": 17.05, "learning_rate": 1.7275947121913366e-06, "loss": 0.7132, "step": 205170 }, { "epoch": 17.05, "learning_rate": 1.7274838566638029e-06, "loss": 0.7348, "step": 205180 }, { "epoch": 17.06, "learning_rate": 1.7273730011362691e-06, "loss": 0.7881, "step": 205190 }, { "epoch": 17.06, "learning_rate": 1.7272621456087352e-06, "loss": 0.752, "step": 205200 }, { "epoch": 17.06, "learning_rate": 1.7271512900812015e-06, "loss": 0.8111, "step": 205210 }, { "epoch": 17.06, "learning_rate": 1.7270404345536678e-06, "loss": 0.8472, "step": 205220 }, { "epoch": 17.06, "learning_rate": 1.726929579026134e-06, "loss": 0.7331, "step": 205230 }, { "epoch": 17.06, "learning_rate": 1.7268187234986004e-06, "loss": 0.7854, "step": 205240 }, { "epoch": 17.06, "learning_rate": 1.7267078679710667e-06, "loss": 0.7731, "step": 205250 }, { "epoch": 17.06, "learning_rate": 1.726597012443533e-06, "loss": 0.7976, "step": 205260 }, { "epoch": 17.06, "learning_rate": 1.726486156915999e-06, "loss": 0.7432, "step": 205270 }, { "epoch": 17.06, "learning_rate": 1.7263753013884654e-06, "loss": 0.7878, "step": 205280 }, { "epoch": 17.06, "learning_rate": 1.7262644458609317e-06, "loss": 0.7841, "step": 205290 }, { "epoch": 17.06, "learning_rate": 1.726153590333398e-06, "loss": 0.754, "step": 205300 }, { "epoch": 17.07, "learning_rate": 1.726042734805864e-06, "loss": 0.7322, "step": 205310 }, { "epoch": 17.07, "learning_rate": 1.7259318792783304e-06, "loss": 0.7231, "step": 205320 }, { "epoch": 17.07, "learning_rate": 1.7258210237507966e-06, "loss": 0.7497, "step": 205330 }, { "epoch": 17.07, "learning_rate": 1.725710168223263e-06, "loss": 0.7064, "step": 205340 }, { "epoch": 17.07, "learning_rate": 1.725599312695729e-06, "loss": 0.7339, "step": 205350 }, { "epoch": 17.07, "learning_rate": 1.7254884571681955e-06, "loss": 0.7856, "step": 205360 }, { "epoch": 17.07, "learning_rate": 1.7253776016406618e-06, "loss": 0.7552, "step": 205370 }, { "epoch": 17.07, "learning_rate": 1.7252667461131281e-06, "loss": 0.7666, "step": 205380 }, { "epoch": 17.07, "learning_rate": 1.7251558905855942e-06, "loss": 0.8057, "step": 205390 }, { "epoch": 17.07, "learning_rate": 1.7250450350580605e-06, "loss": 0.7671, "step": 205400 }, { "epoch": 17.07, "learning_rate": 1.7249341795305268e-06, "loss": 0.7365, "step": 205410 }, { "epoch": 17.07, "learning_rate": 1.724823324002993e-06, "loss": 0.7153, "step": 205420 }, { "epoch": 17.08, "learning_rate": 1.7247124684754592e-06, "loss": 0.7767, "step": 205430 }, { "epoch": 17.08, "learning_rate": 1.7246016129479255e-06, "loss": 0.7381, "step": 205440 }, { "epoch": 17.08, "learning_rate": 1.7244907574203918e-06, "loss": 0.7109, "step": 205450 }, { "epoch": 17.08, "learning_rate": 1.724379901892858e-06, "loss": 0.7158, "step": 205460 }, { "epoch": 17.08, "learning_rate": 1.7242690463653241e-06, "loss": 0.6969, "step": 205470 }, { "epoch": 17.08, "learning_rate": 1.7241581908377904e-06, "loss": 0.8084, "step": 205480 }, { "epoch": 17.08, "learning_rate": 1.724047335310257e-06, "loss": 0.7484, "step": 205490 }, { "epoch": 17.08, "learning_rate": 1.7239364797827232e-06, "loss": 0.7029, "step": 205500 }, { "epoch": 17.08, "learning_rate": 1.7238256242551893e-06, "loss": 0.7819, "step": 205510 }, { "epoch": 17.08, "learning_rate": 1.7237147687276556e-06, "loss": 0.7499, "step": 205520 }, { "epoch": 17.08, "learning_rate": 1.723603913200122e-06, "loss": 0.7047, "step": 205530 }, { "epoch": 17.08, "learning_rate": 1.7234930576725882e-06, "loss": 0.8004, "step": 205540 }, { "epoch": 17.09, "learning_rate": 1.7233822021450543e-06, "loss": 0.7723, "step": 205550 }, { "epoch": 17.09, "learning_rate": 1.7232713466175206e-06, "loss": 0.8084, "step": 205560 }, { "epoch": 17.09, "learning_rate": 1.7231604910899869e-06, "loss": 0.7537, "step": 205570 }, { "epoch": 17.09, "learning_rate": 1.7230496355624532e-06, "loss": 0.8455, "step": 205580 }, { "epoch": 17.09, "learning_rate": 1.7229387800349193e-06, "loss": 0.8174, "step": 205590 }, { "epoch": 17.09, "learning_rate": 1.7228279245073856e-06, "loss": 0.7379, "step": 205600 }, { "epoch": 17.09, "learning_rate": 1.722717068979852e-06, "loss": 0.7727, "step": 205610 }, { "epoch": 17.09, "learning_rate": 1.7226062134523184e-06, "loss": 0.7603, "step": 205620 }, { "epoch": 17.09, "learning_rate": 1.7224953579247844e-06, "loss": 0.7628, "step": 205630 }, { "epoch": 17.09, "learning_rate": 1.7223845023972507e-06, "loss": 0.8389, "step": 205640 }, { "epoch": 17.09, "learning_rate": 1.722273646869717e-06, "loss": 0.7498, "step": 205650 }, { "epoch": 17.09, "learning_rate": 1.7221627913421833e-06, "loss": 0.7745, "step": 205660 }, { "epoch": 17.1, "learning_rate": 1.7220519358146494e-06, "loss": 0.723, "step": 205670 }, { "epoch": 17.1, "learning_rate": 1.7219410802871157e-06, "loss": 0.7669, "step": 205680 }, { "epoch": 17.1, "learning_rate": 1.721830224759582e-06, "loss": 0.7729, "step": 205690 }, { "epoch": 17.1, "learning_rate": 1.721719369232048e-06, "loss": 0.7589, "step": 205700 }, { "epoch": 17.1, "learning_rate": 1.7216085137045144e-06, "loss": 0.7304, "step": 205710 }, { "epoch": 17.1, "learning_rate": 1.7214976581769807e-06, "loss": 0.7526, "step": 205720 }, { "epoch": 17.1, "learning_rate": 1.7213868026494472e-06, "loss": 0.7164, "step": 205730 }, { "epoch": 17.1, "learning_rate": 1.7212759471219133e-06, "loss": 0.7921, "step": 205740 }, { "epoch": 17.1, "learning_rate": 1.7211650915943796e-06, "loss": 0.8398, "step": 205750 }, { "epoch": 17.1, "learning_rate": 1.7210542360668459e-06, "loss": 0.7505, "step": 205760 }, { "epoch": 17.1, "learning_rate": 1.7209433805393122e-06, "loss": 0.7017, "step": 205770 }, { "epoch": 17.1, "learning_rate": 1.7208325250117782e-06, "loss": 0.744, "step": 205780 }, { "epoch": 17.1, "learning_rate": 1.7207216694842445e-06, "loss": 0.8434, "step": 205790 }, { "epoch": 17.11, "learning_rate": 1.7206108139567108e-06, "loss": 0.7863, "step": 205800 }, { "epoch": 17.11, "learning_rate": 1.7204999584291771e-06, "loss": 0.7217, "step": 205810 }, { "epoch": 17.11, "learning_rate": 1.7203891029016432e-06, "loss": 0.7945, "step": 205820 }, { "epoch": 17.11, "learning_rate": 1.7202782473741095e-06, "loss": 0.7509, "step": 205830 }, { "epoch": 17.11, "learning_rate": 1.7201673918465758e-06, "loss": 0.7507, "step": 205840 }, { "epoch": 17.11, "learning_rate": 1.7200565363190423e-06, "loss": 0.7691, "step": 205850 }, { "epoch": 17.11, "learning_rate": 1.7199456807915084e-06, "loss": 0.7244, "step": 205860 }, { "epoch": 17.11, "learning_rate": 1.7198348252639747e-06, "loss": 0.7932, "step": 205870 }, { "epoch": 17.11, "learning_rate": 1.719723969736441e-06, "loss": 0.7205, "step": 205880 }, { "epoch": 17.11, "learning_rate": 1.7196131142089073e-06, "loss": 0.8863, "step": 205890 }, { "epoch": 17.11, "learning_rate": 1.7195022586813734e-06, "loss": 0.7826, "step": 205900 }, { "epoch": 17.11, "learning_rate": 1.7193914031538397e-06, "loss": 0.7637, "step": 205910 }, { "epoch": 17.12, "learning_rate": 1.719280547626306e-06, "loss": 0.7645, "step": 205920 }, { "epoch": 17.12, "learning_rate": 1.7191696920987722e-06, "loss": 0.7278, "step": 205930 }, { "epoch": 17.12, "learning_rate": 1.7190588365712383e-06, "loss": 0.8251, "step": 205940 }, { "epoch": 17.12, "learning_rate": 1.7189479810437046e-06, "loss": 0.7334, "step": 205950 }, { "epoch": 17.12, "learning_rate": 1.718837125516171e-06, "loss": 0.8202, "step": 205960 }, { "epoch": 17.12, "learning_rate": 1.7187262699886372e-06, "loss": 0.7833, "step": 205970 }, { "epoch": 17.12, "learning_rate": 1.7186154144611035e-06, "loss": 0.7967, "step": 205980 }, { "epoch": 17.12, "learning_rate": 1.7185045589335698e-06, "loss": 0.8114, "step": 205990 }, { "epoch": 17.12, "learning_rate": 1.718393703406036e-06, "loss": 0.7427, "step": 206000 }, { "epoch": 17.12, "learning_rate": 1.7182828478785024e-06, "loss": 0.7303, "step": 206010 }, { "epoch": 17.12, "learning_rate": 1.7181719923509685e-06, "loss": 0.7114, "step": 206020 }, { "epoch": 17.12, "learning_rate": 1.7180611368234348e-06, "loss": 0.7391, "step": 206030 }, { "epoch": 17.13, "learning_rate": 1.717950281295901e-06, "loss": 0.728, "step": 206040 }, { "epoch": 17.13, "learning_rate": 1.7178394257683674e-06, "loss": 0.8063, "step": 206050 }, { "epoch": 17.13, "learning_rate": 1.7177285702408335e-06, "loss": 0.7405, "step": 206060 }, { "epoch": 17.13, "learning_rate": 1.7176177147132997e-06, "loss": 0.8058, "step": 206070 }, { "epoch": 17.13, "learning_rate": 1.717506859185766e-06, "loss": 0.7141, "step": 206080 }, { "epoch": 17.13, "learning_rate": 1.7173960036582321e-06, "loss": 0.8118, "step": 206090 }, { "epoch": 17.13, "learning_rate": 1.7172851481306986e-06, "loss": 0.6981, "step": 206100 }, { "epoch": 17.13, "learning_rate": 1.717174292603165e-06, "loss": 0.7661, "step": 206110 }, { "epoch": 17.13, "learning_rate": 1.7170634370756312e-06, "loss": 0.7352, "step": 206120 }, { "epoch": 17.13, "learning_rate": 1.7169525815480973e-06, "loss": 0.8472, "step": 206130 }, { "epoch": 17.13, "learning_rate": 1.7168417260205636e-06, "loss": 0.791, "step": 206140 }, { "epoch": 17.13, "learning_rate": 1.71673087049303e-06, "loss": 0.7553, "step": 206150 }, { "epoch": 17.14, "learning_rate": 1.7166200149654962e-06, "loss": 0.7512, "step": 206160 }, { "epoch": 17.14, "learning_rate": 1.7165091594379623e-06, "loss": 0.8158, "step": 206170 }, { "epoch": 17.14, "learning_rate": 1.7163983039104286e-06, "loss": 0.8165, "step": 206180 }, { "epoch": 17.14, "learning_rate": 1.7162874483828949e-06, "loss": 0.7953, "step": 206190 }, { "epoch": 17.14, "learning_rate": 1.7161765928553612e-06, "loss": 0.764, "step": 206200 }, { "epoch": 17.14, "learning_rate": 1.7160657373278272e-06, "loss": 0.7772, "step": 206210 }, { "epoch": 17.14, "learning_rate": 1.7159548818002938e-06, "loss": 0.7677, "step": 206220 }, { "epoch": 17.14, "learning_rate": 1.71584402627276e-06, "loss": 0.7555, "step": 206230 }, { "epoch": 17.14, "learning_rate": 1.7157331707452263e-06, "loss": 0.7613, "step": 206240 }, { "epoch": 17.14, "learning_rate": 1.7156223152176924e-06, "loss": 0.7109, "step": 206250 }, { "epoch": 17.14, "learning_rate": 1.7155114596901587e-06, "loss": 0.7735, "step": 206260 }, { "epoch": 17.14, "learning_rate": 1.715400604162625e-06, "loss": 0.7337, "step": 206270 }, { "epoch": 17.15, "learning_rate": 1.7152897486350913e-06, "loss": 0.7866, "step": 206280 }, { "epoch": 17.15, "learning_rate": 1.7151788931075574e-06, "loss": 0.7386, "step": 206290 }, { "epoch": 17.15, "learning_rate": 1.7150680375800237e-06, "loss": 0.7129, "step": 206300 }, { "epoch": 17.15, "learning_rate": 1.71495718205249e-06, "loss": 0.7654, "step": 206310 }, { "epoch": 17.15, "learning_rate": 1.7148463265249563e-06, "loss": 0.7819, "step": 206320 }, { "epoch": 17.15, "learning_rate": 1.7147354709974224e-06, "loss": 0.7358, "step": 206330 }, { "epoch": 17.15, "learning_rate": 1.7146246154698887e-06, "loss": 0.8148, "step": 206340 }, { "epoch": 17.15, "learning_rate": 1.7145137599423552e-06, "loss": 0.7953, "step": 206350 }, { "epoch": 17.15, "learning_rate": 1.7144029044148215e-06, "loss": 0.7365, "step": 206360 }, { "epoch": 17.15, "learning_rate": 1.7142920488872876e-06, "loss": 0.7886, "step": 206370 }, { "epoch": 17.15, "learning_rate": 1.7141811933597538e-06, "loss": 0.8022, "step": 206380 }, { "epoch": 17.15, "learning_rate": 1.7140703378322201e-06, "loss": 0.825, "step": 206390 }, { "epoch": 17.16, "learning_rate": 1.7139594823046864e-06, "loss": 0.7283, "step": 206400 }, { "epoch": 17.16, "learning_rate": 1.7138486267771525e-06, "loss": 0.7124, "step": 206410 }, { "epoch": 17.16, "learning_rate": 1.7137377712496188e-06, "loss": 0.744, "step": 206420 }, { "epoch": 17.16, "learning_rate": 1.7136269157220851e-06, "loss": 0.8439, "step": 206430 }, { "epoch": 17.16, "learning_rate": 1.7135160601945514e-06, "loss": 0.8073, "step": 206440 }, { "epoch": 17.16, "learning_rate": 1.7134052046670175e-06, "loss": 0.8226, "step": 206450 }, { "epoch": 17.16, "learning_rate": 1.7132943491394838e-06, "loss": 0.7205, "step": 206460 }, { "epoch": 17.16, "learning_rate": 1.7131834936119503e-06, "loss": 0.8094, "step": 206470 }, { "epoch": 17.16, "learning_rate": 1.7130726380844166e-06, "loss": 0.7902, "step": 206480 }, { "epoch": 17.16, "learning_rate": 1.7129617825568827e-06, "loss": 0.7872, "step": 206490 }, { "epoch": 17.16, "learning_rate": 1.712850927029349e-06, "loss": 0.7242, "step": 206500 }, { "epoch": 17.16, "learning_rate": 1.7127400715018153e-06, "loss": 0.7527, "step": 206510 }, { "epoch": 17.17, "learning_rate": 1.7126292159742813e-06, "loss": 0.7312, "step": 206520 }, { "epoch": 17.17, "learning_rate": 1.7125183604467476e-06, "loss": 0.8478, "step": 206530 }, { "epoch": 17.17, "learning_rate": 1.712407504919214e-06, "loss": 0.7727, "step": 206540 }, { "epoch": 17.17, "learning_rate": 1.7122966493916802e-06, "loss": 0.748, "step": 206550 }, { "epoch": 17.17, "learning_rate": 1.7121857938641463e-06, "loss": 0.7765, "step": 206560 }, { "epoch": 17.17, "learning_rate": 1.7120749383366126e-06, "loss": 0.7597, "step": 206570 }, { "epoch": 17.17, "learning_rate": 1.711964082809079e-06, "loss": 0.8649, "step": 206580 }, { "epoch": 17.17, "learning_rate": 1.7118532272815454e-06, "loss": 0.7445, "step": 206590 }, { "epoch": 17.17, "learning_rate": 1.7117423717540115e-06, "loss": 0.7862, "step": 206600 }, { "epoch": 17.17, "learning_rate": 1.7116315162264778e-06, "loss": 0.7495, "step": 206610 }, { "epoch": 17.17, "learning_rate": 1.711520660698944e-06, "loss": 0.787, "step": 206620 }, { "epoch": 17.17, "learning_rate": 1.7114098051714104e-06, "loss": 0.7613, "step": 206630 }, { "epoch": 17.18, "learning_rate": 1.7112989496438765e-06, "loss": 0.7774, "step": 206640 }, { "epoch": 17.18, "learning_rate": 1.7111880941163428e-06, "loss": 0.7517, "step": 206650 }, { "epoch": 17.18, "learning_rate": 1.711077238588809e-06, "loss": 0.7116, "step": 206660 }, { "epoch": 17.18, "learning_rate": 1.7109663830612754e-06, "loss": 0.7683, "step": 206670 }, { "epoch": 17.18, "learning_rate": 1.7108555275337414e-06, "loss": 0.7947, "step": 206680 }, { "epoch": 17.18, "learning_rate": 1.7107446720062077e-06, "loss": 0.7435, "step": 206690 }, { "epoch": 17.18, "learning_rate": 1.710633816478674e-06, "loss": 0.7596, "step": 206700 }, { "epoch": 17.18, "learning_rate": 1.7105229609511405e-06, "loss": 0.7641, "step": 206710 }, { "epoch": 17.18, "learning_rate": 1.7104121054236066e-06, "loss": 0.7944, "step": 206720 }, { "epoch": 17.18, "learning_rate": 1.710301249896073e-06, "loss": 0.7649, "step": 206730 }, { "epoch": 17.18, "learning_rate": 1.7101903943685392e-06, "loss": 0.8033, "step": 206740 }, { "epoch": 17.18, "learning_rate": 1.7100795388410055e-06, "loss": 0.7237, "step": 206750 }, { "epoch": 17.19, "learning_rate": 1.7099686833134716e-06, "loss": 0.7901, "step": 206760 }, { "epoch": 17.19, "learning_rate": 1.7098578277859379e-06, "loss": 0.787, "step": 206770 }, { "epoch": 17.19, "learning_rate": 1.7097469722584042e-06, "loss": 0.7799, "step": 206780 }, { "epoch": 17.19, "learning_rate": 1.7096361167308705e-06, "loss": 0.8094, "step": 206790 }, { "epoch": 17.19, "learning_rate": 1.7095252612033366e-06, "loss": 0.7381, "step": 206800 }, { "epoch": 17.19, "learning_rate": 1.7094144056758029e-06, "loss": 0.7633, "step": 206810 }, { "epoch": 17.19, "learning_rate": 1.7093035501482691e-06, "loss": 0.7851, "step": 206820 }, { "epoch": 17.19, "learning_rate": 1.7091926946207354e-06, "loss": 0.7399, "step": 206830 }, { "epoch": 17.19, "learning_rate": 1.7090818390932017e-06, "loss": 0.8358, "step": 206840 }, { "epoch": 17.19, "learning_rate": 1.708970983565668e-06, "loss": 0.7842, "step": 206850 }, { "epoch": 17.19, "learning_rate": 1.7088601280381343e-06, "loss": 0.6867, "step": 206860 }, { "epoch": 17.19, "learning_rate": 1.7087492725106006e-06, "loss": 0.7828, "step": 206870 }, { "epoch": 17.2, "learning_rate": 1.7086384169830667e-06, "loss": 0.8115, "step": 206880 }, { "epoch": 17.2, "learning_rate": 1.708527561455533e-06, "loss": 0.7881, "step": 206890 }, { "epoch": 17.2, "learning_rate": 1.7084167059279993e-06, "loss": 0.7714, "step": 206900 }, { "epoch": 17.2, "learning_rate": 1.7083058504004654e-06, "loss": 0.7741, "step": 206910 }, { "epoch": 17.2, "learning_rate": 1.7081949948729317e-06, "loss": 0.7603, "step": 206920 }, { "epoch": 17.2, "learning_rate": 1.708084139345398e-06, "loss": 0.7669, "step": 206930 }, { "epoch": 17.2, "learning_rate": 1.7079732838178643e-06, "loss": 0.7938, "step": 206940 }, { "epoch": 17.2, "learning_rate": 1.7078624282903304e-06, "loss": 0.7687, "step": 206950 }, { "epoch": 17.2, "learning_rate": 1.7077515727627969e-06, "loss": 0.7258, "step": 206960 }, { "epoch": 17.2, "learning_rate": 1.7076407172352632e-06, "loss": 0.7927, "step": 206970 }, { "epoch": 17.2, "learning_rate": 1.7075298617077294e-06, "loss": 0.7449, "step": 206980 }, { "epoch": 17.2, "learning_rate": 1.7074190061801955e-06, "loss": 0.8008, "step": 206990 }, { "epoch": 17.21, "learning_rate": 1.7073081506526618e-06, "loss": 0.7541, "step": 207000 }, { "epoch": 17.21, "learning_rate": 1.7071972951251281e-06, "loss": 0.7815, "step": 207010 }, { "epoch": 17.21, "learning_rate": 1.7070864395975944e-06, "loss": 0.7362, "step": 207020 }, { "epoch": 17.21, "learning_rate": 1.7069755840700605e-06, "loss": 0.7597, "step": 207030 }, { "epoch": 17.21, "learning_rate": 1.7068647285425268e-06, "loss": 0.7987, "step": 207040 }, { "epoch": 17.21, "learning_rate": 1.706753873014993e-06, "loss": 0.7325, "step": 207050 }, { "epoch": 17.21, "learning_rate": 1.7066430174874594e-06, "loss": 0.7107, "step": 207060 }, { "epoch": 17.21, "learning_rate": 1.7065321619599255e-06, "loss": 0.8102, "step": 207070 }, { "epoch": 17.21, "learning_rate": 1.706421306432392e-06, "loss": 0.7336, "step": 207080 }, { "epoch": 17.21, "learning_rate": 1.7063104509048583e-06, "loss": 0.8286, "step": 207090 }, { "epoch": 17.21, "learning_rate": 1.7061995953773246e-06, "loss": 0.7991, "step": 207100 }, { "epoch": 17.21, "learning_rate": 1.7060887398497907e-06, "loss": 0.7407, "step": 207110 }, { "epoch": 17.22, "learning_rate": 1.705977884322257e-06, "loss": 0.761, "step": 207120 }, { "epoch": 17.22, "learning_rate": 1.7058670287947232e-06, "loss": 0.7803, "step": 207130 }, { "epoch": 17.22, "learning_rate": 1.7057561732671895e-06, "loss": 0.7839, "step": 207140 }, { "epoch": 17.22, "learning_rate": 1.7056453177396556e-06, "loss": 0.776, "step": 207150 }, { "epoch": 17.22, "learning_rate": 1.705534462212122e-06, "loss": 0.7447, "step": 207160 }, { "epoch": 17.22, "learning_rate": 1.7054236066845882e-06, "loss": 0.7566, "step": 207170 }, { "epoch": 17.22, "learning_rate": 1.7053127511570545e-06, "loss": 0.8186, "step": 207180 }, { "epoch": 17.22, "learning_rate": 1.7052018956295206e-06, "loss": 0.7438, "step": 207190 }, { "epoch": 17.22, "learning_rate": 1.7050910401019869e-06, "loss": 0.804, "step": 207200 }, { "epoch": 17.22, "learning_rate": 1.7049801845744534e-06, "loss": 0.7495, "step": 207210 }, { "epoch": 17.22, "learning_rate": 1.7048693290469197e-06, "loss": 0.7149, "step": 207220 }, { "epoch": 17.22, "learning_rate": 1.7047584735193858e-06, "loss": 0.7395, "step": 207230 }, { "epoch": 17.23, "learning_rate": 1.704647617991852e-06, "loss": 0.7854, "step": 207240 }, { "epoch": 17.23, "learning_rate": 1.7045367624643184e-06, "loss": 0.8054, "step": 207250 }, { "epoch": 17.23, "learning_rate": 1.7044259069367847e-06, "loss": 0.8137, "step": 207260 }, { "epoch": 17.23, "learning_rate": 1.7043150514092507e-06, "loss": 0.7688, "step": 207270 }, { "epoch": 17.23, "learning_rate": 1.704204195881717e-06, "loss": 0.8178, "step": 207280 }, { "epoch": 17.23, "learning_rate": 1.7040933403541833e-06, "loss": 0.8072, "step": 207290 }, { "epoch": 17.23, "learning_rate": 1.7039824848266496e-06, "loss": 0.7189, "step": 207300 }, { "epoch": 17.23, "learning_rate": 1.7038716292991157e-06, "loss": 0.8037, "step": 207310 }, { "epoch": 17.23, "learning_rate": 1.703760773771582e-06, "loss": 0.7397, "step": 207320 }, { "epoch": 17.23, "learning_rate": 1.7036499182440485e-06, "loss": 0.8262, "step": 207330 }, { "epoch": 17.23, "learning_rate": 1.7035390627165148e-06, "loss": 0.7697, "step": 207340 }, { "epoch": 17.23, "learning_rate": 1.7034282071889809e-06, "loss": 0.7409, "step": 207350 }, { "epoch": 17.24, "learning_rate": 1.7033173516614472e-06, "loss": 0.743, "step": 207360 }, { "epoch": 17.24, "learning_rate": 1.7032064961339135e-06, "loss": 0.7728, "step": 207370 }, { "epoch": 17.24, "learning_rate": 1.7030956406063796e-06, "loss": 0.7706, "step": 207380 }, { "epoch": 17.24, "learning_rate": 1.7029847850788459e-06, "loss": 0.7826, "step": 207390 }, { "epoch": 17.24, "learning_rate": 1.7028739295513122e-06, "loss": 0.7071, "step": 207400 }, { "epoch": 17.24, "learning_rate": 1.7027630740237785e-06, "loss": 0.7396, "step": 207410 }, { "epoch": 17.24, "learning_rate": 1.7026522184962445e-06, "loss": 0.7444, "step": 207420 }, { "epoch": 17.24, "learning_rate": 1.7025413629687108e-06, "loss": 0.7867, "step": 207430 }, { "epoch": 17.24, "learning_rate": 1.7024305074411771e-06, "loss": 0.8446, "step": 207440 }, { "epoch": 17.24, "learning_rate": 1.7023196519136436e-06, "loss": 0.7443, "step": 207450 }, { "epoch": 17.24, "learning_rate": 1.7022087963861097e-06, "loss": 0.7319, "step": 207460 }, { "epoch": 17.24, "learning_rate": 1.702097940858576e-06, "loss": 0.7322, "step": 207470 }, { "epoch": 17.25, "learning_rate": 1.7019870853310423e-06, "loss": 0.7336, "step": 207480 }, { "epoch": 17.25, "learning_rate": 1.7018762298035086e-06, "loss": 0.7367, "step": 207490 }, { "epoch": 17.25, "learning_rate": 1.7017653742759747e-06, "loss": 0.7514, "step": 207500 }, { "epoch": 17.25, "learning_rate": 1.701654518748441e-06, "loss": 0.7935, "step": 207510 }, { "epoch": 17.25, "learning_rate": 1.7015436632209073e-06, "loss": 0.6857, "step": 207520 }, { "epoch": 17.25, "learning_rate": 1.7014328076933736e-06, "loss": 0.8019, "step": 207530 }, { "epoch": 17.25, "learning_rate": 1.7013219521658397e-06, "loss": 0.7895, "step": 207540 }, { "epoch": 17.25, "learning_rate": 1.701211096638306e-06, "loss": 0.7992, "step": 207550 }, { "epoch": 17.25, "learning_rate": 1.7011002411107722e-06, "loss": 0.7306, "step": 207560 }, { "epoch": 17.25, "learning_rate": 1.7009893855832385e-06, "loss": 0.7946, "step": 207570 }, { "epoch": 17.25, "learning_rate": 1.7008785300557048e-06, "loss": 0.7163, "step": 207580 }, { "epoch": 17.25, "learning_rate": 1.7007676745281711e-06, "loss": 0.7796, "step": 207590 }, { "epoch": 17.26, "learning_rate": 1.7006568190006374e-06, "loss": 0.7615, "step": 207600 }, { "epoch": 17.26, "learning_rate": 1.7005459634731037e-06, "loss": 0.7192, "step": 207610 }, { "epoch": 17.26, "learning_rate": 1.7004351079455698e-06, "loss": 0.7534, "step": 207620 }, { "epoch": 17.26, "learning_rate": 1.700324252418036e-06, "loss": 0.8108, "step": 207630 }, { "epoch": 17.26, "learning_rate": 1.7002133968905024e-06, "loss": 0.7641, "step": 207640 }, { "epoch": 17.26, "learning_rate": 1.7001025413629687e-06, "loss": 0.7643, "step": 207650 }, { "epoch": 17.26, "learning_rate": 1.6999916858354348e-06, "loss": 0.8118, "step": 207660 }, { "epoch": 17.26, "learning_rate": 1.699880830307901e-06, "loss": 0.7364, "step": 207670 }, { "epoch": 17.26, "learning_rate": 1.6997699747803674e-06, "loss": 0.7442, "step": 207680 }, { "epoch": 17.26, "learning_rate": 1.6996591192528337e-06, "loss": 0.7477, "step": 207690 }, { "epoch": 17.26, "learning_rate": 1.6995482637253e-06, "loss": 0.8301, "step": 207700 }, { "epoch": 17.26, "learning_rate": 1.6994374081977663e-06, "loss": 0.7488, "step": 207710 }, { "epoch": 17.27, "learning_rate": 1.6993265526702326e-06, "loss": 0.754, "step": 207720 }, { "epoch": 17.27, "learning_rate": 1.6992156971426988e-06, "loss": 0.7274, "step": 207730 }, { "epoch": 17.27, "learning_rate": 1.699104841615165e-06, "loss": 0.7842, "step": 207740 }, { "epoch": 17.27, "learning_rate": 1.6989939860876312e-06, "loss": 0.7623, "step": 207750 }, { "epoch": 17.27, "learning_rate": 1.6988831305600975e-06, "loss": 0.8049, "step": 207760 }, { "epoch": 17.27, "learning_rate": 1.6987722750325636e-06, "loss": 0.7899, "step": 207770 }, { "epoch": 17.27, "learning_rate": 1.69866141950503e-06, "loss": 0.8143, "step": 207780 }, { "epoch": 17.27, "learning_rate": 1.6985505639774962e-06, "loss": 0.7502, "step": 207790 }, { "epoch": 17.27, "learning_rate": 1.6984397084499625e-06, "loss": 0.7257, "step": 207800 }, { "epoch": 17.27, "learning_rate": 1.6983288529224286e-06, "loss": 0.7962, "step": 207810 }, { "epoch": 17.27, "learning_rate": 1.698217997394895e-06, "loss": 0.7922, "step": 207820 }, { "epoch": 17.27, "learning_rate": 1.6981071418673614e-06, "loss": 0.7363, "step": 207830 }, { "epoch": 17.28, "learning_rate": 1.6979962863398277e-06, "loss": 0.8061, "step": 207840 }, { "epoch": 17.28, "learning_rate": 1.6978854308122938e-06, "loss": 0.7436, "step": 207850 }, { "epoch": 17.28, "learning_rate": 1.69777457528476e-06, "loss": 0.751, "step": 207860 }, { "epoch": 17.28, "learning_rate": 1.6976637197572263e-06, "loss": 0.7485, "step": 207870 }, { "epoch": 17.28, "learning_rate": 1.6975528642296926e-06, "loss": 0.7954, "step": 207880 }, { "epoch": 17.28, "learning_rate": 1.6974420087021587e-06, "loss": 0.7998, "step": 207890 }, { "epoch": 17.28, "learning_rate": 1.697331153174625e-06, "loss": 0.7105, "step": 207900 }, { "epoch": 17.28, "learning_rate": 1.6972202976470913e-06, "loss": 0.7273, "step": 207910 }, { "epoch": 17.28, "learning_rate": 1.6971094421195576e-06, "loss": 0.7278, "step": 207920 }, { "epoch": 17.28, "learning_rate": 1.6969985865920237e-06, "loss": 0.8043, "step": 207930 }, { "epoch": 17.28, "learning_rate": 1.6968877310644902e-06, "loss": 0.8148, "step": 207940 }, { "epoch": 17.28, "learning_rate": 1.6967768755369565e-06, "loss": 0.7832, "step": 207950 }, { "epoch": 17.29, "learning_rate": 1.6966660200094228e-06, "loss": 0.7819, "step": 207960 }, { "epoch": 17.29, "learning_rate": 1.6965551644818889e-06, "loss": 0.7221, "step": 207970 }, { "epoch": 17.29, "learning_rate": 1.6964443089543552e-06, "loss": 0.8149, "step": 207980 }, { "epoch": 17.29, "learning_rate": 1.6963334534268215e-06, "loss": 0.7878, "step": 207990 }, { "epoch": 17.29, "learning_rate": 1.6962225978992878e-06, "loss": 0.7626, "step": 208000 }, { "epoch": 17.29, "learning_rate": 1.6961117423717538e-06, "loss": 0.7408, "step": 208010 }, { "epoch": 17.29, "learning_rate": 1.6960008868442201e-06, "loss": 0.7705, "step": 208020 }, { "epoch": 17.29, "learning_rate": 1.6958900313166864e-06, "loss": 0.7787, "step": 208030 }, { "epoch": 17.29, "learning_rate": 1.6957791757891527e-06, "loss": 0.7197, "step": 208040 }, { "epoch": 17.29, "learning_rate": 1.6956683202616188e-06, "loss": 0.761, "step": 208050 }, { "epoch": 17.29, "learning_rate": 1.6955574647340851e-06, "loss": 0.7825, "step": 208060 }, { "epoch": 17.29, "learning_rate": 1.6954466092065516e-06, "loss": 0.7689, "step": 208070 }, { "epoch": 17.3, "learning_rate": 1.695335753679018e-06, "loss": 0.7734, "step": 208080 }, { "epoch": 17.3, "learning_rate": 1.695224898151484e-06, "loss": 0.7378, "step": 208090 }, { "epoch": 17.3, "learning_rate": 1.6951140426239503e-06, "loss": 0.7096, "step": 208100 }, { "epoch": 17.3, "learning_rate": 1.6950031870964166e-06, "loss": 0.7554, "step": 208110 }, { "epoch": 17.3, "learning_rate": 1.6948923315688829e-06, "loss": 0.711, "step": 208120 }, { "epoch": 17.3, "learning_rate": 1.694781476041349e-06, "loss": 0.7956, "step": 208130 }, { "epoch": 17.3, "learning_rate": 1.6946706205138153e-06, "loss": 0.7449, "step": 208140 }, { "epoch": 17.3, "learning_rate": 1.6945597649862816e-06, "loss": 0.7303, "step": 208150 }, { "epoch": 17.3, "learning_rate": 1.6944489094587476e-06, "loss": 0.7671, "step": 208160 }, { "epoch": 17.3, "learning_rate": 1.694338053931214e-06, "loss": 0.7366, "step": 208170 }, { "epoch": 17.3, "learning_rate": 1.6942271984036802e-06, "loss": 0.7691, "step": 208180 }, { "epoch": 17.3, "learning_rate": 1.6941163428761467e-06, "loss": 0.7526, "step": 208190 }, { "epoch": 17.31, "learning_rate": 1.694005487348613e-06, "loss": 0.7578, "step": 208200 }, { "epoch": 17.31, "learning_rate": 1.6938946318210791e-06, "loss": 0.7961, "step": 208210 }, { "epoch": 17.31, "learning_rate": 1.6937837762935454e-06, "loss": 0.747, "step": 208220 }, { "epoch": 17.31, "learning_rate": 1.6936729207660117e-06, "loss": 0.7979, "step": 208230 }, { "epoch": 17.31, "learning_rate": 1.6935620652384778e-06, "loss": 0.7337, "step": 208240 }, { "epoch": 17.31, "learning_rate": 1.693451209710944e-06, "loss": 0.7603, "step": 208250 }, { "epoch": 17.31, "learning_rate": 1.6933403541834104e-06, "loss": 0.7973, "step": 208260 }, { "epoch": 17.31, "learning_rate": 1.6932294986558767e-06, "loss": 0.7529, "step": 208270 }, { "epoch": 17.31, "learning_rate": 1.6931186431283428e-06, "loss": 0.7774, "step": 208280 }, { "epoch": 17.31, "learning_rate": 1.693007787600809e-06, "loss": 0.8703, "step": 208290 }, { "epoch": 17.31, "learning_rate": 1.6928969320732754e-06, "loss": 0.8072, "step": 208300 }, { "epoch": 17.31, "learning_rate": 1.6927860765457419e-06, "loss": 0.7781, "step": 208310 }, { "epoch": 17.32, "learning_rate": 1.692675221018208e-06, "loss": 0.8185, "step": 208320 }, { "epoch": 17.32, "learning_rate": 1.6925643654906742e-06, "loss": 0.7924, "step": 208330 }, { "epoch": 17.32, "learning_rate": 1.6924535099631405e-06, "loss": 0.7903, "step": 208340 }, { "epoch": 17.32, "learning_rate": 1.6923426544356068e-06, "loss": 0.8045, "step": 208350 }, { "epoch": 17.32, "learning_rate": 1.692231798908073e-06, "loss": 0.7517, "step": 208360 }, { "epoch": 17.32, "learning_rate": 1.6921209433805392e-06, "loss": 0.7395, "step": 208370 }, { "epoch": 17.32, "learning_rate": 1.6920100878530055e-06, "loss": 0.7998, "step": 208380 }, { "epoch": 17.32, "learning_rate": 1.6918992323254718e-06, "loss": 0.746, "step": 208390 }, { "epoch": 17.32, "learning_rate": 1.6917883767979379e-06, "loss": 0.741, "step": 208400 }, { "epoch": 17.32, "learning_rate": 1.6916775212704042e-06, "loss": 0.7076, "step": 208410 }, { "epoch": 17.32, "learning_rate": 1.6915666657428705e-06, "loss": 0.8126, "step": 208420 }, { "epoch": 17.32, "learning_rate": 1.6914558102153368e-06, "loss": 0.8148, "step": 208430 }, { "epoch": 17.33, "learning_rate": 1.691344954687803e-06, "loss": 0.8144, "step": 208440 }, { "epoch": 17.33, "learning_rate": 1.6912340991602694e-06, "loss": 0.6998, "step": 208450 }, { "epoch": 17.33, "learning_rate": 1.6911232436327357e-06, "loss": 0.7095, "step": 208460 }, { "epoch": 17.33, "learning_rate": 1.691012388105202e-06, "loss": 0.7491, "step": 208470 }, { "epoch": 17.33, "learning_rate": 1.690901532577668e-06, "loss": 0.824, "step": 208480 }, { "epoch": 17.33, "learning_rate": 1.6907906770501343e-06, "loss": 0.7632, "step": 208490 }, { "epoch": 17.33, "learning_rate": 1.6906798215226006e-06, "loss": 0.7139, "step": 208500 }, { "epoch": 17.33, "learning_rate": 1.690568965995067e-06, "loss": 0.744, "step": 208510 }, { "epoch": 17.33, "learning_rate": 1.690458110467533e-06, "loss": 0.6864, "step": 208520 }, { "epoch": 17.33, "learning_rate": 1.6903472549399993e-06, "loss": 0.7393, "step": 208530 }, { "epoch": 17.33, "learning_rate": 1.6902363994124656e-06, "loss": 0.8482, "step": 208540 }, { "epoch": 17.33, "learning_rate": 1.6901255438849317e-06, "loss": 0.7444, "step": 208550 }, { "epoch": 17.34, "learning_rate": 1.6900146883573982e-06, "loss": 0.7296, "step": 208560 }, { "epoch": 17.34, "learning_rate": 1.6899038328298645e-06, "loss": 0.7715, "step": 208570 }, { "epoch": 17.34, "learning_rate": 1.6897929773023308e-06, "loss": 0.8124, "step": 208580 }, { "epoch": 17.34, "learning_rate": 1.689682121774797e-06, "loss": 0.7712, "step": 208590 }, { "epoch": 17.34, "learning_rate": 1.6895712662472632e-06, "loss": 0.7766, "step": 208600 }, { "epoch": 17.34, "learning_rate": 1.6894604107197294e-06, "loss": 0.8204, "step": 208610 }, { "epoch": 17.34, "learning_rate": 1.6893495551921957e-06, "loss": 0.7647, "step": 208620 }, { "epoch": 17.34, "learning_rate": 1.6892386996646618e-06, "loss": 0.7739, "step": 208630 }, { "epoch": 17.34, "learning_rate": 1.6891278441371281e-06, "loss": 0.7663, "step": 208640 }, { "epoch": 17.34, "learning_rate": 1.6890169886095944e-06, "loss": 0.788, "step": 208650 }, { "epoch": 17.34, "learning_rate": 1.6889061330820607e-06, "loss": 0.7599, "step": 208660 }, { "epoch": 17.34, "learning_rate": 1.6887952775545268e-06, "loss": 0.7711, "step": 208670 }, { "epoch": 17.35, "learning_rate": 1.6886844220269933e-06, "loss": 0.817, "step": 208680 }, { "epoch": 17.35, "learning_rate": 1.6885735664994596e-06, "loss": 0.7896, "step": 208690 }, { "epoch": 17.35, "learning_rate": 1.6884627109719259e-06, "loss": 0.7458, "step": 208700 }, { "epoch": 17.35, "learning_rate": 1.688351855444392e-06, "loss": 0.7566, "step": 208710 }, { "epoch": 17.35, "learning_rate": 1.6882409999168583e-06, "loss": 0.8103, "step": 208720 }, { "epoch": 17.35, "learning_rate": 1.6881301443893246e-06, "loss": 0.7932, "step": 208730 }, { "epoch": 17.35, "learning_rate": 1.6880192888617909e-06, "loss": 0.7786, "step": 208740 }, { "epoch": 17.35, "learning_rate": 1.687908433334257e-06, "loss": 0.7582, "step": 208750 }, { "epoch": 17.35, "learning_rate": 1.6877975778067232e-06, "loss": 0.7287, "step": 208760 }, { "epoch": 17.35, "learning_rate": 1.6876867222791895e-06, "loss": 0.7822, "step": 208770 }, { "epoch": 17.35, "learning_rate": 1.6875758667516558e-06, "loss": 0.7785, "step": 208780 }, { "epoch": 17.35, "learning_rate": 1.687465011224122e-06, "loss": 0.7846, "step": 208790 }, { "epoch": 17.36, "learning_rate": 1.6873541556965884e-06, "loss": 0.7456, "step": 208800 }, { "epoch": 17.36, "learning_rate": 1.6872433001690547e-06, "loss": 0.7797, "step": 208810 }, { "epoch": 17.36, "learning_rate": 1.687132444641521e-06, "loss": 0.7468, "step": 208820 }, { "epoch": 17.36, "learning_rate": 1.687021589113987e-06, "loss": 0.791, "step": 208830 }, { "epoch": 17.36, "learning_rate": 1.6869107335864534e-06, "loss": 0.785, "step": 208840 }, { "epoch": 17.36, "learning_rate": 1.6867998780589197e-06, "loss": 0.7561, "step": 208850 }, { "epoch": 17.36, "learning_rate": 1.686689022531386e-06, "loss": 0.7208, "step": 208860 }, { "epoch": 17.36, "learning_rate": 1.686578167003852e-06, "loss": 0.7035, "step": 208870 }, { "epoch": 17.36, "learning_rate": 1.6864673114763184e-06, "loss": 0.7691, "step": 208880 }, { "epoch": 17.36, "learning_rate": 1.6863564559487847e-06, "loss": 0.7542, "step": 208890 }, { "epoch": 17.36, "learning_rate": 1.686245600421251e-06, "loss": 0.7234, "step": 208900 }, { "epoch": 17.36, "learning_rate": 1.686134744893717e-06, "loss": 0.7933, "step": 208910 }, { "epoch": 17.37, "learning_rate": 1.6860238893661833e-06, "loss": 0.7815, "step": 208920 }, { "epoch": 17.37, "learning_rate": 1.6859130338386498e-06, "loss": 0.7634, "step": 208930 }, { "epoch": 17.37, "learning_rate": 1.6858021783111161e-06, "loss": 0.7598, "step": 208940 }, { "epoch": 17.37, "learning_rate": 1.6856913227835822e-06, "loss": 0.7322, "step": 208950 }, { "epoch": 17.37, "learning_rate": 1.6855804672560485e-06, "loss": 0.7009, "step": 208960 }, { "epoch": 17.37, "learning_rate": 1.6854696117285148e-06, "loss": 0.7091, "step": 208970 }, { "epoch": 17.37, "learning_rate": 1.685358756200981e-06, "loss": 0.836, "step": 208980 }, { "epoch": 17.37, "learning_rate": 1.6852479006734472e-06, "loss": 0.8061, "step": 208990 }, { "epoch": 17.37, "learning_rate": 1.6851370451459135e-06, "loss": 0.7919, "step": 209000 }, { "epoch": 17.37, "learning_rate": 1.6850261896183798e-06, "loss": 0.6905, "step": 209010 }, { "epoch": 17.37, "learning_rate": 1.6849153340908459e-06, "loss": 0.7766, "step": 209020 }, { "epoch": 17.37, "learning_rate": 1.6848044785633122e-06, "loss": 0.8333, "step": 209030 }, { "epoch": 17.38, "learning_rate": 1.6846936230357785e-06, "loss": 0.7988, "step": 209040 }, { "epoch": 17.38, "learning_rate": 1.684582767508245e-06, "loss": 0.7273, "step": 209050 }, { "epoch": 17.38, "learning_rate": 1.684471911980711e-06, "loss": 0.8379, "step": 209060 }, { "epoch": 17.38, "learning_rate": 1.6843610564531773e-06, "loss": 0.7847, "step": 209070 }, { "epoch": 17.38, "learning_rate": 1.6842502009256436e-06, "loss": 0.7829, "step": 209080 }, { "epoch": 17.38, "learning_rate": 1.6841504309508632e-06, "loss": 0.7755, "step": 209090 }, { "epoch": 17.38, "learning_rate": 1.6840395754233295e-06, "loss": 0.7315, "step": 209100 }, { "epoch": 17.38, "learning_rate": 1.6839287198957956e-06, "loss": 0.8302, "step": 209110 }, { "epoch": 17.38, "learning_rate": 1.6838178643682618e-06, "loss": 0.7814, "step": 209120 }, { "epoch": 17.38, "learning_rate": 1.6837070088407281e-06, "loss": 0.7691, "step": 209130 }, { "epoch": 17.38, "learning_rate": 1.6835961533131946e-06, "loss": 0.7726, "step": 209140 }, { "epoch": 17.38, "learning_rate": 1.683485297785661e-06, "loss": 0.7568, "step": 209150 }, { "epoch": 17.39, "learning_rate": 1.683374442258127e-06, "loss": 0.7813, "step": 209160 }, { "epoch": 17.39, "learning_rate": 1.6832635867305933e-06, "loss": 0.7745, "step": 209170 }, { "epoch": 17.39, "learning_rate": 1.6831527312030596e-06, "loss": 0.7851, "step": 209180 }, { "epoch": 17.39, "learning_rate": 1.6830418756755257e-06, "loss": 0.8218, "step": 209190 }, { "epoch": 17.39, "learning_rate": 1.682931020147992e-06, "loss": 0.7863, "step": 209200 }, { "epoch": 17.39, "learning_rate": 1.6828201646204583e-06, "loss": 0.7927, "step": 209210 }, { "epoch": 17.39, "learning_rate": 1.6827093090929246e-06, "loss": 0.7593, "step": 209220 }, { "epoch": 17.39, "learning_rate": 1.6825984535653907e-06, "loss": 0.761, "step": 209230 }, { "epoch": 17.39, "learning_rate": 1.682487598037857e-06, "loss": 0.7469, "step": 209240 }, { "epoch": 17.39, "learning_rate": 1.6823767425103233e-06, "loss": 0.748, "step": 209250 }, { "epoch": 17.39, "learning_rate": 1.6822658869827898e-06, "loss": 0.7462, "step": 209260 }, { "epoch": 17.39, "learning_rate": 1.6821550314552559e-06, "loss": 0.7018, "step": 209270 }, { "epoch": 17.4, "learning_rate": 1.6820441759277221e-06, "loss": 0.7815, "step": 209280 }, { "epoch": 17.4, "learning_rate": 1.6819333204001884e-06, "loss": 0.7438, "step": 209290 }, { "epoch": 17.4, "learning_rate": 1.6818224648726547e-06, "loss": 0.7631, "step": 209300 }, { "epoch": 17.4, "learning_rate": 1.6817116093451208e-06, "loss": 0.7137, "step": 209310 }, { "epoch": 17.4, "learning_rate": 1.6816007538175871e-06, "loss": 0.734, "step": 209320 }, { "epoch": 17.4, "learning_rate": 1.6814898982900534e-06, "loss": 0.7724, "step": 209330 }, { "epoch": 17.4, "learning_rate": 1.6813790427625197e-06, "loss": 0.7986, "step": 209340 }, { "epoch": 17.4, "learning_rate": 1.6812681872349858e-06, "loss": 0.7694, "step": 209350 }, { "epoch": 17.4, "learning_rate": 1.681157331707452e-06, "loss": 0.7957, "step": 209360 }, { "epoch": 17.4, "learning_rate": 1.6810464761799184e-06, "loss": 0.7755, "step": 209370 }, { "epoch": 17.4, "learning_rate": 1.6809356206523849e-06, "loss": 0.7712, "step": 209380 }, { "epoch": 17.4, "learning_rate": 1.680824765124851e-06, "loss": 0.8098, "step": 209390 }, { "epoch": 17.41, "learning_rate": 1.6807139095973173e-06, "loss": 0.7825, "step": 209400 }, { "epoch": 17.41, "learning_rate": 1.6806030540697836e-06, "loss": 0.7015, "step": 209410 }, { "epoch": 17.41, "learning_rate": 1.6804921985422499e-06, "loss": 0.7891, "step": 209420 }, { "epoch": 17.41, "learning_rate": 1.680381343014716e-06, "loss": 0.7273, "step": 209430 }, { "epoch": 17.41, "learning_rate": 1.6802704874871822e-06, "loss": 0.7693, "step": 209440 }, { "epoch": 17.41, "learning_rate": 1.6801596319596485e-06, "loss": 0.7464, "step": 209450 }, { "epoch": 17.41, "learning_rate": 1.6800487764321148e-06, "loss": 0.7706, "step": 209460 }, { "epoch": 17.41, "learning_rate": 1.679937920904581e-06, "loss": 0.7561, "step": 209470 }, { "epoch": 17.41, "learning_rate": 1.6798270653770472e-06, "loss": 0.7782, "step": 209480 }, { "epoch": 17.41, "learning_rate": 1.6797162098495135e-06, "loss": 0.7621, "step": 209490 }, { "epoch": 17.41, "learning_rate": 1.6796053543219798e-06, "loss": 0.7704, "step": 209500 }, { "epoch": 17.41, "learning_rate": 1.679494498794446e-06, "loss": 0.8378, "step": 209510 }, { "epoch": 17.42, "learning_rate": 1.6793836432669124e-06, "loss": 0.7094, "step": 209520 }, { "epoch": 17.42, "learning_rate": 1.6792727877393787e-06, "loss": 0.7953, "step": 209530 }, { "epoch": 17.42, "learning_rate": 1.679161932211845e-06, "loss": 0.8017, "step": 209540 }, { "epoch": 17.42, "learning_rate": 1.679051076684311e-06, "loss": 0.7682, "step": 209550 }, { "epoch": 17.42, "learning_rate": 1.6789402211567774e-06, "loss": 0.797, "step": 209560 }, { "epoch": 17.42, "learning_rate": 1.6788293656292437e-06, "loss": 0.7545, "step": 209570 }, { "epoch": 17.42, "learning_rate": 1.6787185101017097e-06, "loss": 0.7711, "step": 209580 }, { "epoch": 17.42, "learning_rate": 1.678607654574176e-06, "loss": 0.7769, "step": 209590 }, { "epoch": 17.42, "learning_rate": 1.6784967990466423e-06, "loss": 0.7834, "step": 209600 }, { "epoch": 17.42, "learning_rate": 1.6783859435191086e-06, "loss": 0.7396, "step": 209610 }, { "epoch": 17.42, "learning_rate": 1.6782750879915747e-06, "loss": 0.8132, "step": 209620 }, { "epoch": 17.42, "learning_rate": 1.6781642324640412e-06, "loss": 0.7763, "step": 209630 }, { "epoch": 17.42, "learning_rate": 1.6780533769365075e-06, "loss": 0.7513, "step": 209640 }, { "epoch": 17.43, "learning_rate": 1.6779425214089738e-06, "loss": 0.7355, "step": 209650 }, { "epoch": 17.43, "learning_rate": 1.6778316658814399e-06, "loss": 0.7644, "step": 209660 }, { "epoch": 17.43, "learning_rate": 1.6777208103539062e-06, "loss": 0.7783, "step": 209670 }, { "epoch": 17.43, "learning_rate": 1.6776099548263725e-06, "loss": 0.779, "step": 209680 }, { "epoch": 17.43, "learning_rate": 1.6774990992988388e-06, "loss": 0.7862, "step": 209690 }, { "epoch": 17.43, "learning_rate": 1.6773882437713049e-06, "loss": 0.7063, "step": 209700 }, { "epoch": 17.43, "learning_rate": 1.6772773882437712e-06, "loss": 0.7788, "step": 209710 }, { "epoch": 17.43, "learning_rate": 1.6771665327162375e-06, "loss": 0.7176, "step": 209720 }, { "epoch": 17.43, "learning_rate": 1.6770556771887037e-06, "loss": 0.7731, "step": 209730 }, { "epoch": 17.43, "learning_rate": 1.6769448216611698e-06, "loss": 0.8013, "step": 209740 }, { "epoch": 17.43, "learning_rate": 1.6768339661336363e-06, "loss": 0.7621, "step": 209750 }, { "epoch": 17.43, "learning_rate": 1.6767231106061026e-06, "loss": 0.7806, "step": 209760 }, { "epoch": 17.44, "learning_rate": 1.676612255078569e-06, "loss": 0.7694, "step": 209770 }, { "epoch": 17.44, "learning_rate": 1.676501399551035e-06, "loss": 0.7655, "step": 209780 }, { "epoch": 17.44, "learning_rate": 1.6763905440235013e-06, "loss": 0.7665, "step": 209790 }, { "epoch": 17.44, "learning_rate": 1.6762796884959676e-06, "loss": 0.7951, "step": 209800 }, { "epoch": 17.44, "learning_rate": 1.676168832968434e-06, "loss": 0.7935, "step": 209810 }, { "epoch": 17.44, "learning_rate": 1.6760579774409e-06, "loss": 0.8253, "step": 209820 }, { "epoch": 17.44, "learning_rate": 1.6759471219133663e-06, "loss": 0.7825, "step": 209830 }, { "epoch": 17.44, "learning_rate": 1.6758362663858326e-06, "loss": 0.7776, "step": 209840 }, { "epoch": 17.44, "learning_rate": 1.6757254108582989e-06, "loss": 0.731, "step": 209850 }, { "epoch": 17.44, "learning_rate": 1.675614555330765e-06, "loss": 0.7443, "step": 209860 }, { "epoch": 17.44, "learning_rate": 1.6755036998032312e-06, "loss": 0.7605, "step": 209870 }, { "epoch": 17.44, "learning_rate": 1.6753928442756978e-06, "loss": 0.7567, "step": 209880 }, { "epoch": 17.45, "learning_rate": 1.675281988748164e-06, "loss": 0.7598, "step": 209890 }, { "epoch": 17.45, "learning_rate": 1.6751711332206301e-06, "loss": 0.7598, "step": 209900 }, { "epoch": 17.45, "learning_rate": 1.6750602776930964e-06, "loss": 0.7707, "step": 209910 }, { "epoch": 17.45, "learning_rate": 1.6749494221655627e-06, "loss": 0.7379, "step": 209920 }, { "epoch": 17.45, "learning_rate": 1.674838566638029e-06, "loss": 0.7617, "step": 209930 }, { "epoch": 17.45, "learning_rate": 1.674727711110495e-06, "loss": 0.7685, "step": 209940 }, { "epoch": 17.45, "learning_rate": 1.6746168555829614e-06, "loss": 0.7646, "step": 209950 }, { "epoch": 17.45, "learning_rate": 1.6745060000554277e-06, "loss": 0.776, "step": 209960 }, { "epoch": 17.45, "learning_rate": 1.6743951445278938e-06, "loss": 0.8366, "step": 209970 }, { "epoch": 17.45, "learning_rate": 1.67428428900036e-06, "loss": 0.7775, "step": 209980 }, { "epoch": 17.45, "learning_rate": 1.6741734334728264e-06, "loss": 0.7449, "step": 209990 }, { "epoch": 17.45, "learning_rate": 1.6740625779452929e-06, "loss": 0.7584, "step": 210000 }, { "epoch": 17.46, "learning_rate": 1.673951722417759e-06, "loss": 0.7484, "step": 210010 }, { "epoch": 17.46, "learning_rate": 1.6738408668902253e-06, "loss": 0.782, "step": 210020 }, { "epoch": 17.46, "learning_rate": 1.6737300113626915e-06, "loss": 0.7966, "step": 210030 }, { "epoch": 17.46, "learning_rate": 1.6736191558351578e-06, "loss": 0.7618, "step": 210040 }, { "epoch": 17.46, "learning_rate": 1.673508300307624e-06, "loss": 0.8102, "step": 210050 }, { "epoch": 17.46, "learning_rate": 1.6733974447800902e-06, "loss": 0.7573, "step": 210060 }, { "epoch": 17.46, "learning_rate": 1.6732865892525565e-06, "loss": 0.8012, "step": 210070 }, { "epoch": 17.46, "learning_rate": 1.6731757337250228e-06, "loss": 0.7498, "step": 210080 }, { "epoch": 17.46, "learning_rate": 1.673064878197489e-06, "loss": 0.7801, "step": 210090 }, { "epoch": 17.46, "learning_rate": 1.6729540226699552e-06, "loss": 0.7375, "step": 210100 }, { "epoch": 17.46, "learning_rate": 1.6728431671424215e-06, "loss": 0.7349, "step": 210110 }, { "epoch": 17.46, "learning_rate": 1.672732311614888e-06, "loss": 0.8012, "step": 210120 }, { "epoch": 17.47, "learning_rate": 1.672621456087354e-06, "loss": 0.7662, "step": 210130 }, { "epoch": 17.47, "learning_rate": 1.6725106005598204e-06, "loss": 0.7679, "step": 210140 }, { "epoch": 17.47, "learning_rate": 1.6723997450322867e-06, "loss": 0.7368, "step": 210150 }, { "epoch": 17.47, "learning_rate": 1.672288889504753e-06, "loss": 0.8113, "step": 210160 }, { "epoch": 17.47, "learning_rate": 1.672178033977219e-06, "loss": 0.749, "step": 210170 }, { "epoch": 17.47, "learning_rate": 1.6720671784496853e-06, "loss": 0.7886, "step": 210180 }, { "epoch": 17.47, "learning_rate": 1.6719563229221516e-06, "loss": 0.7919, "step": 210190 }, { "epoch": 17.47, "learning_rate": 1.671845467394618e-06, "loss": 0.7327, "step": 210200 }, { "epoch": 17.47, "learning_rate": 1.671734611867084e-06, "loss": 0.7106, "step": 210210 }, { "epoch": 17.47, "learning_rate": 1.6716237563395503e-06, "loss": 0.6718, "step": 210220 }, { "epoch": 17.47, "learning_rate": 1.6715129008120166e-06, "loss": 0.7114, "step": 210230 }, { "epoch": 17.47, "learning_rate": 1.6714020452844831e-06, "loss": 0.817, "step": 210240 }, { "epoch": 17.48, "learning_rate": 1.6712911897569492e-06, "loss": 0.6604, "step": 210250 }, { "epoch": 17.48, "learning_rate": 1.6711803342294155e-06, "loss": 0.7508, "step": 210260 }, { "epoch": 17.48, "learning_rate": 1.6710694787018818e-06, "loss": 0.7782, "step": 210270 }, { "epoch": 17.48, "learning_rate": 1.670958623174348e-06, "loss": 0.8269, "step": 210280 }, { "epoch": 17.48, "learning_rate": 1.6708477676468142e-06, "loss": 0.8181, "step": 210290 }, { "epoch": 17.48, "learning_rate": 1.6707369121192805e-06, "loss": 0.7994, "step": 210300 }, { "epoch": 17.48, "learning_rate": 1.6706260565917468e-06, "loss": 0.8106, "step": 210310 }, { "epoch": 17.48, "learning_rate": 1.670515201064213e-06, "loss": 0.8109, "step": 210320 }, { "epoch": 17.48, "learning_rate": 1.6704043455366791e-06, "loss": 0.7811, "step": 210330 }, { "epoch": 17.48, "learning_rate": 1.6702934900091454e-06, "loss": 0.7837, "step": 210340 }, { "epoch": 17.48, "learning_rate": 1.6701826344816117e-06, "loss": 0.7142, "step": 210350 }, { "epoch": 17.48, "learning_rate": 1.6700717789540778e-06, "loss": 0.7869, "step": 210360 }, { "epoch": 17.49, "learning_rate": 1.6699609234265443e-06, "loss": 0.7377, "step": 210370 }, { "epoch": 17.49, "learning_rate": 1.6698500678990106e-06, "loss": 0.8057, "step": 210380 }, { "epoch": 17.49, "learning_rate": 1.669739212371477e-06, "loss": 0.7843, "step": 210390 }, { "epoch": 17.49, "learning_rate": 1.669628356843943e-06, "loss": 0.7438, "step": 210400 }, { "epoch": 17.49, "learning_rate": 1.6695175013164093e-06, "loss": 0.7699, "step": 210410 }, { "epoch": 17.49, "learning_rate": 1.6694066457888756e-06, "loss": 0.7761, "step": 210420 }, { "epoch": 17.49, "learning_rate": 1.6692957902613419e-06, "loss": 0.8027, "step": 210430 }, { "epoch": 17.49, "learning_rate": 1.669184934733808e-06, "loss": 0.7401, "step": 210440 }, { "epoch": 17.49, "learning_rate": 1.6690740792062743e-06, "loss": 0.8184, "step": 210450 }, { "epoch": 17.49, "learning_rate": 1.6689632236787406e-06, "loss": 0.742, "step": 210460 }, { "epoch": 17.49, "learning_rate": 1.6688523681512068e-06, "loss": 0.7181, "step": 210470 }, { "epoch": 17.49, "learning_rate": 1.668741512623673e-06, "loss": 0.803, "step": 210480 }, { "epoch": 17.5, "learning_rate": 1.6686306570961394e-06, "loss": 0.7789, "step": 210490 }, { "epoch": 17.5, "learning_rate": 1.6685198015686057e-06, "loss": 0.7239, "step": 210500 }, { "epoch": 17.5, "learning_rate": 1.668408946041072e-06, "loss": 0.762, "step": 210510 }, { "epoch": 17.5, "learning_rate": 1.6682980905135381e-06, "loss": 0.7602, "step": 210520 }, { "epoch": 17.5, "learning_rate": 1.6681872349860044e-06, "loss": 0.7633, "step": 210530 }, { "epoch": 17.5, "learning_rate": 1.6680763794584707e-06, "loss": 0.8128, "step": 210540 }, { "epoch": 17.5, "learning_rate": 1.667965523930937e-06, "loss": 0.6798, "step": 210550 }, { "epoch": 17.5, "learning_rate": 1.667854668403403e-06, "loss": 0.6989, "step": 210560 }, { "epoch": 17.5, "learning_rate": 1.6677438128758694e-06, "loss": 0.8059, "step": 210570 }, { "epoch": 17.5, "learning_rate": 1.6676329573483357e-06, "loss": 0.7999, "step": 210580 }, { "epoch": 17.5, "learning_rate": 1.667522101820802e-06, "loss": 0.7511, "step": 210590 }, { "epoch": 17.5, "learning_rate": 1.667411246293268e-06, "loss": 0.7465, "step": 210600 }, { "epoch": 17.51, "learning_rate": 1.6673003907657346e-06, "loss": 0.7778, "step": 210610 }, { "epoch": 17.51, "learning_rate": 1.6671895352382009e-06, "loss": 0.8028, "step": 210620 }, { "epoch": 17.51, "learning_rate": 1.6670786797106671e-06, "loss": 0.6707, "step": 210630 }, { "epoch": 17.51, "learning_rate": 1.6669678241831332e-06, "loss": 0.7432, "step": 210640 }, { "epoch": 17.51, "learning_rate": 1.6668569686555995e-06, "loss": 0.7572, "step": 210650 }, { "epoch": 17.51, "learning_rate": 1.6667461131280658e-06, "loss": 0.736, "step": 210660 }, { "epoch": 17.51, "learning_rate": 1.6666352576005321e-06, "loss": 0.783, "step": 210670 }, { "epoch": 17.51, "learning_rate": 1.6665244020729982e-06, "loss": 0.8074, "step": 210680 }, { "epoch": 17.51, "learning_rate": 1.6664135465454645e-06, "loss": 0.7316, "step": 210690 }, { "epoch": 17.51, "learning_rate": 1.6663026910179308e-06, "loss": 0.7944, "step": 210700 }, { "epoch": 17.51, "learning_rate": 1.666191835490397e-06, "loss": 0.7362, "step": 210710 }, { "epoch": 17.51, "learning_rate": 1.6660809799628632e-06, "loss": 0.7379, "step": 210720 }, { "epoch": 17.52, "learning_rate": 1.6659701244353295e-06, "loss": 0.7728, "step": 210730 }, { "epoch": 17.52, "learning_rate": 1.665859268907796e-06, "loss": 0.8516, "step": 210740 }, { "epoch": 17.52, "learning_rate": 1.6657484133802623e-06, "loss": 0.8066, "step": 210750 }, { "epoch": 17.52, "learning_rate": 1.6656375578527284e-06, "loss": 0.7639, "step": 210760 }, { "epoch": 17.52, "learning_rate": 1.6655267023251946e-06, "loss": 0.7679, "step": 210770 }, { "epoch": 17.52, "learning_rate": 1.665415846797661e-06, "loss": 0.7596, "step": 210780 }, { "epoch": 17.52, "learning_rate": 1.6653049912701272e-06, "loss": 0.7838, "step": 210790 }, { "epoch": 17.52, "learning_rate": 1.6651941357425933e-06, "loss": 0.7347, "step": 210800 }, { "epoch": 17.52, "learning_rate": 1.6650832802150596e-06, "loss": 0.7543, "step": 210810 }, { "epoch": 17.52, "learning_rate": 1.664972424687526e-06, "loss": 0.766, "step": 210820 }, { "epoch": 17.52, "learning_rate": 1.664861569159992e-06, "loss": 0.761, "step": 210830 }, { "epoch": 17.52, "learning_rate": 1.6647507136324583e-06, "loss": 0.7943, "step": 210840 }, { "epoch": 17.53, "learning_rate": 1.6646398581049246e-06, "loss": 0.7986, "step": 210850 }, { "epoch": 17.53, "learning_rate": 1.664529002577391e-06, "loss": 0.7405, "step": 210860 }, { "epoch": 17.53, "learning_rate": 1.6644181470498572e-06, "loss": 0.7109, "step": 210870 }, { "epoch": 17.53, "learning_rate": 1.6643072915223235e-06, "loss": 0.8193, "step": 210880 }, { "epoch": 17.53, "learning_rate": 1.6641964359947898e-06, "loss": 0.749, "step": 210890 }, { "epoch": 17.53, "learning_rate": 1.664085580467256e-06, "loss": 0.8093, "step": 210900 }, { "epoch": 17.53, "learning_rate": 1.6639747249397221e-06, "loss": 0.7705, "step": 210910 }, { "epoch": 17.53, "learning_rate": 1.6638638694121884e-06, "loss": 0.8191, "step": 210920 }, { "epoch": 17.53, "learning_rate": 1.6637530138846547e-06, "loss": 0.767, "step": 210930 }, { "epoch": 17.53, "learning_rate": 1.663642158357121e-06, "loss": 0.8503, "step": 210940 }, { "epoch": 17.53, "learning_rate": 1.6635313028295871e-06, "loss": 0.794, "step": 210950 }, { "epoch": 17.53, "learning_rate": 1.6634204473020534e-06, "loss": 0.784, "step": 210960 }, { "epoch": 17.54, "learning_rate": 1.6633095917745197e-06, "loss": 0.7347, "step": 210970 }, { "epoch": 17.54, "learning_rate": 1.6631987362469862e-06, "loss": 0.7767, "step": 210980 }, { "epoch": 17.54, "learning_rate": 1.6630878807194523e-06, "loss": 0.7936, "step": 210990 }, { "epoch": 17.54, "learning_rate": 1.6629770251919186e-06, "loss": 0.7413, "step": 211000 }, { "epoch": 17.54, "learning_rate": 1.6628661696643849e-06, "loss": 0.7962, "step": 211010 }, { "epoch": 17.54, "learning_rate": 1.6627553141368512e-06, "loss": 0.6985, "step": 211020 }, { "epoch": 17.54, "learning_rate": 1.6626444586093173e-06, "loss": 0.7761, "step": 211030 }, { "epoch": 17.54, "learning_rate": 1.6625336030817836e-06, "loss": 0.7629, "step": 211040 }, { "epoch": 17.54, "learning_rate": 1.6624227475542499e-06, "loss": 0.8177, "step": 211050 }, { "epoch": 17.54, "learning_rate": 1.6623118920267162e-06, "loss": 0.7665, "step": 211060 }, { "epoch": 17.54, "learning_rate": 1.6622010364991822e-06, "loss": 0.6968, "step": 211070 }, { "epoch": 17.54, "learning_rate": 1.6620901809716485e-06, "loss": 0.7783, "step": 211080 }, { "epoch": 17.55, "learning_rate": 1.6619793254441148e-06, "loss": 0.7826, "step": 211090 }, { "epoch": 17.55, "learning_rate": 1.6618684699165813e-06, "loss": 0.7807, "step": 211100 }, { "epoch": 17.55, "learning_rate": 1.6617576143890474e-06, "loss": 0.7367, "step": 211110 }, { "epoch": 17.55, "learning_rate": 1.6616467588615137e-06, "loss": 0.7373, "step": 211120 }, { "epoch": 17.55, "learning_rate": 1.66153590333398e-06, "loss": 0.7151, "step": 211130 }, { "epoch": 17.55, "learning_rate": 1.6614250478064463e-06, "loss": 0.7768, "step": 211140 }, { "epoch": 17.55, "learning_rate": 1.6613141922789124e-06, "loss": 0.7253, "step": 211150 }, { "epoch": 17.55, "learning_rate": 1.6612033367513787e-06, "loss": 0.7613, "step": 211160 }, { "epoch": 17.55, "learning_rate": 1.661092481223845e-06, "loss": 0.7322, "step": 211170 }, { "epoch": 17.55, "learning_rate": 1.6609816256963113e-06, "loss": 0.7995, "step": 211180 }, { "epoch": 17.55, "learning_rate": 1.6608707701687774e-06, "loss": 0.8291, "step": 211190 }, { "epoch": 17.55, "learning_rate": 1.6607599146412437e-06, "loss": 0.7495, "step": 211200 }, { "epoch": 17.56, "learning_rate": 1.66064905911371e-06, "loss": 0.7492, "step": 211210 }, { "epoch": 17.56, "learning_rate": 1.660538203586176e-06, "loss": 0.6719, "step": 211220 }, { "epoch": 17.56, "learning_rate": 1.6604273480586425e-06, "loss": 0.7781, "step": 211230 }, { "epoch": 17.56, "learning_rate": 1.6603164925311088e-06, "loss": 0.7443, "step": 211240 }, { "epoch": 17.56, "learning_rate": 1.6602056370035751e-06, "loss": 0.7204, "step": 211250 }, { "epoch": 17.56, "learning_rate": 1.6600947814760412e-06, "loss": 0.7105, "step": 211260 }, { "epoch": 17.56, "learning_rate": 1.6599839259485075e-06, "loss": 0.7838, "step": 211270 }, { "epoch": 17.56, "learning_rate": 1.6598730704209738e-06, "loss": 0.8007, "step": 211280 }, { "epoch": 17.56, "learning_rate": 1.65976221489344e-06, "loss": 0.773, "step": 211290 }, { "epoch": 17.56, "learning_rate": 1.6596513593659062e-06, "loss": 0.7669, "step": 211300 }, { "epoch": 17.56, "learning_rate": 1.6595405038383725e-06, "loss": 0.702, "step": 211310 }, { "epoch": 17.56, "learning_rate": 1.6594296483108388e-06, "loss": 0.7544, "step": 211320 }, { "epoch": 17.57, "learning_rate": 1.659318792783305e-06, "loss": 0.7935, "step": 211330 }, { "epoch": 17.57, "learning_rate": 1.6592079372557712e-06, "loss": 0.7047, "step": 211340 }, { "epoch": 17.57, "learning_rate": 1.6590970817282377e-06, "loss": 0.717, "step": 211350 }, { "epoch": 17.57, "learning_rate": 1.6589973117534572e-06, "loss": 0.7661, "step": 211360 }, { "epoch": 17.57, "learning_rate": 1.6588864562259235e-06, "loss": 0.7346, "step": 211370 }, { "epoch": 17.57, "learning_rate": 1.6587756006983898e-06, "loss": 0.7444, "step": 211380 }, { "epoch": 17.57, "learning_rate": 1.6586647451708559e-06, "loss": 0.771, "step": 211390 }, { "epoch": 17.57, "learning_rate": 1.6585538896433222e-06, "loss": 0.7066, "step": 211400 }, { "epoch": 17.57, "learning_rate": 1.6584430341157885e-06, "loss": 0.7402, "step": 211410 }, { "epoch": 17.57, "learning_rate": 1.6583321785882548e-06, "loss": 0.753, "step": 211420 }, { "epoch": 17.57, "learning_rate": 1.6582213230607208e-06, "loss": 0.8027, "step": 211430 }, { "epoch": 17.57, "learning_rate": 1.6581104675331874e-06, "loss": 0.8165, "step": 211440 }, { "epoch": 17.58, "learning_rate": 1.6579996120056536e-06, "loss": 0.7934, "step": 211450 }, { "epoch": 17.58, "learning_rate": 1.65788875647812e-06, "loss": 0.7799, "step": 211460 }, { "epoch": 17.58, "learning_rate": 1.657777900950586e-06, "loss": 0.7642, "step": 211470 }, { "epoch": 17.58, "learning_rate": 1.6576670454230523e-06, "loss": 0.8084, "step": 211480 }, { "epoch": 17.58, "learning_rate": 1.6575561898955186e-06, "loss": 0.7819, "step": 211490 }, { "epoch": 17.58, "learning_rate": 1.657445334367985e-06, "loss": 0.7473, "step": 211500 }, { "epoch": 17.58, "learning_rate": 1.657334478840451e-06, "loss": 0.7887, "step": 211510 }, { "epoch": 17.58, "learning_rate": 1.6572236233129173e-06, "loss": 0.7548, "step": 211520 }, { "epoch": 17.58, "learning_rate": 1.6571127677853836e-06, "loss": 0.7669, "step": 211530 }, { "epoch": 17.58, "learning_rate": 1.6570019122578499e-06, "loss": 0.8053, "step": 211540 }, { "epoch": 17.58, "learning_rate": 1.656891056730316e-06, "loss": 0.7892, "step": 211550 }, { "epoch": 17.58, "learning_rate": 1.6567802012027825e-06, "loss": 0.7795, "step": 211560 }, { "epoch": 17.59, "learning_rate": 1.6566693456752488e-06, "loss": 0.7786, "step": 211570 }, { "epoch": 17.59, "learning_rate": 1.656558490147715e-06, "loss": 0.8023, "step": 211580 }, { "epoch": 17.59, "learning_rate": 1.6564476346201811e-06, "loss": 0.7967, "step": 211590 }, { "epoch": 17.59, "learning_rate": 1.6563367790926474e-06, "loss": 0.7709, "step": 211600 }, { "epoch": 17.59, "learning_rate": 1.6562259235651137e-06, "loss": 0.7644, "step": 211610 }, { "epoch": 17.59, "learning_rate": 1.65611506803758e-06, "loss": 0.8024, "step": 211620 }, { "epoch": 17.59, "learning_rate": 1.6560042125100461e-06, "loss": 0.7815, "step": 211630 }, { "epoch": 17.59, "learning_rate": 1.6558933569825124e-06, "loss": 0.7213, "step": 211640 }, { "epoch": 17.59, "learning_rate": 1.6557825014549787e-06, "loss": 0.7664, "step": 211650 }, { "epoch": 17.59, "learning_rate": 1.655671645927445e-06, "loss": 0.7328, "step": 211660 }, { "epoch": 17.59, "learning_rate": 1.655560790399911e-06, "loss": 0.6873, "step": 211670 }, { "epoch": 17.59, "learning_rate": 1.6554499348723776e-06, "loss": 0.7878, "step": 211680 }, { "epoch": 17.6, "learning_rate": 1.6553390793448439e-06, "loss": 0.7976, "step": 211690 }, { "epoch": 17.6, "learning_rate": 1.6552282238173102e-06, "loss": 0.7767, "step": 211700 }, { "epoch": 17.6, "learning_rate": 1.6551173682897763e-06, "loss": 0.7726, "step": 211710 }, { "epoch": 17.6, "learning_rate": 1.6550065127622426e-06, "loss": 0.7703, "step": 211720 }, { "epoch": 17.6, "learning_rate": 1.6548956572347089e-06, "loss": 0.7637, "step": 211730 }, { "epoch": 17.6, "learning_rate": 1.6547848017071752e-06, "loss": 0.7265, "step": 211740 }, { "epoch": 17.6, "learning_rate": 1.6546739461796412e-06, "loss": 0.7359, "step": 211750 }, { "epoch": 17.6, "learning_rate": 1.6545630906521075e-06, "loss": 0.7886, "step": 211760 }, { "epoch": 17.6, "learning_rate": 1.6544522351245738e-06, "loss": 0.7669, "step": 211770 }, { "epoch": 17.6, "learning_rate": 1.65434137959704e-06, "loss": 0.7772, "step": 211780 }, { "epoch": 17.6, "learning_rate": 1.6542305240695062e-06, "loss": 0.8027, "step": 211790 }, { "epoch": 17.6, "learning_rate": 1.6541196685419725e-06, "loss": 0.775, "step": 211800 }, { "epoch": 17.61, "learning_rate": 1.654008813014439e-06, "loss": 0.8032, "step": 211810 }, { "epoch": 17.61, "learning_rate": 1.653897957486905e-06, "loss": 0.7641, "step": 211820 }, { "epoch": 17.61, "learning_rate": 1.6537871019593714e-06, "loss": 0.8051, "step": 211830 }, { "epoch": 17.61, "learning_rate": 1.6536762464318377e-06, "loss": 0.8023, "step": 211840 }, { "epoch": 17.61, "learning_rate": 1.653565390904304e-06, "loss": 0.7538, "step": 211850 }, { "epoch": 17.61, "learning_rate": 1.65345453537677e-06, "loss": 0.81, "step": 211860 }, { "epoch": 17.61, "learning_rate": 1.6533436798492364e-06, "loss": 0.7541, "step": 211870 }, { "epoch": 17.61, "learning_rate": 1.6532328243217027e-06, "loss": 0.792, "step": 211880 }, { "epoch": 17.61, "learning_rate": 1.653121968794169e-06, "loss": 0.72, "step": 211890 }, { "epoch": 17.61, "learning_rate": 1.653011113266635e-06, "loss": 0.76, "step": 211900 }, { "epoch": 17.61, "learning_rate": 1.6529002577391013e-06, "loss": 0.818, "step": 211910 }, { "epoch": 17.61, "learning_rate": 1.6527894022115676e-06, "loss": 0.7438, "step": 211920 }, { "epoch": 17.62, "learning_rate": 1.6526785466840341e-06, "loss": 0.8307, "step": 211930 }, { "epoch": 17.62, "learning_rate": 1.6525676911565002e-06, "loss": 0.8005, "step": 211940 }, { "epoch": 17.62, "learning_rate": 1.6524568356289665e-06, "loss": 0.7838, "step": 211950 }, { "epoch": 17.62, "learning_rate": 1.6523459801014328e-06, "loss": 0.7562, "step": 211960 }, { "epoch": 17.62, "learning_rate": 1.652235124573899e-06, "loss": 0.7895, "step": 211970 }, { "epoch": 17.62, "learning_rate": 1.6521242690463652e-06, "loss": 0.8202, "step": 211980 }, { "epoch": 17.62, "learning_rate": 1.6520134135188315e-06, "loss": 0.7949, "step": 211990 }, { "epoch": 17.62, "learning_rate": 1.6519025579912978e-06, "loss": 0.7419, "step": 212000 }, { "epoch": 17.62, "learning_rate": 1.651791702463764e-06, "loss": 0.8037, "step": 212010 }, { "epoch": 17.62, "learning_rate": 1.6516808469362302e-06, "loss": 0.8574, "step": 212020 }, { "epoch": 17.62, "learning_rate": 1.6515699914086964e-06, "loss": 0.7705, "step": 212030 }, { "epoch": 17.62, "learning_rate": 1.6514591358811627e-06, "loss": 0.8474, "step": 212040 }, { "epoch": 17.63, "learning_rate": 1.6513482803536292e-06, "loss": 0.7559, "step": 212050 }, { "epoch": 17.63, "learning_rate": 1.6512374248260953e-06, "loss": 0.7264, "step": 212060 }, { "epoch": 17.63, "learning_rate": 1.6511265692985616e-06, "loss": 0.785, "step": 212070 }, { "epoch": 17.63, "learning_rate": 1.651015713771028e-06, "loss": 0.7606, "step": 212080 }, { "epoch": 17.63, "learning_rate": 1.6509048582434942e-06, "loss": 0.8249, "step": 212090 }, { "epoch": 17.63, "learning_rate": 1.6507940027159603e-06, "loss": 0.7037, "step": 212100 }, { "epoch": 17.63, "learning_rate": 1.6506831471884266e-06, "loss": 0.7861, "step": 212110 }, { "epoch": 17.63, "learning_rate": 1.6505722916608929e-06, "loss": 0.6628, "step": 212120 }, { "epoch": 17.63, "learning_rate": 1.6504614361333592e-06, "loss": 0.7978, "step": 212130 }, { "epoch": 17.63, "learning_rate": 1.6503505806058253e-06, "loss": 0.8048, "step": 212140 }, { "epoch": 17.63, "learning_rate": 1.6502397250782916e-06, "loss": 0.7661, "step": 212150 }, { "epoch": 17.63, "learning_rate": 1.6501288695507579e-06, "loss": 0.7448, "step": 212160 }, { "epoch": 17.64, "learning_rate": 1.650018014023224e-06, "loss": 0.7888, "step": 212170 }, { "epoch": 17.64, "learning_rate": 1.6499071584956905e-06, "loss": 0.7422, "step": 212180 }, { "epoch": 17.64, "learning_rate": 1.6497963029681567e-06, "loss": 0.7454, "step": 212190 }, { "epoch": 17.64, "learning_rate": 1.649685447440623e-06, "loss": 0.7711, "step": 212200 }, { "epoch": 17.64, "learning_rate": 1.6495745919130891e-06, "loss": 0.7851, "step": 212210 }, { "epoch": 17.64, "learning_rate": 1.6494637363855554e-06, "loss": 0.822, "step": 212220 }, { "epoch": 17.64, "learning_rate": 1.6493528808580217e-06, "loss": 0.8174, "step": 212230 }, { "epoch": 17.64, "learning_rate": 1.649242025330488e-06, "loss": 0.7662, "step": 212240 }, { "epoch": 17.64, "learning_rate": 1.649131169802954e-06, "loss": 0.7751, "step": 212250 }, { "epoch": 17.64, "learning_rate": 1.6490203142754204e-06, "loss": 0.758, "step": 212260 }, { "epoch": 17.64, "learning_rate": 1.6489094587478867e-06, "loss": 0.7819, "step": 212270 }, { "epoch": 17.64, "learning_rate": 1.648798603220353e-06, "loss": 0.702, "step": 212280 }, { "epoch": 17.65, "learning_rate": 1.648687747692819e-06, "loss": 0.7796, "step": 212290 }, { "epoch": 17.65, "learning_rate": 1.6485768921652856e-06, "loss": 0.7494, "step": 212300 }, { "epoch": 17.65, "learning_rate": 1.6484660366377519e-06, "loss": 0.7649, "step": 212310 }, { "epoch": 17.65, "learning_rate": 1.6483551811102182e-06, "loss": 0.7612, "step": 212320 }, { "epoch": 17.65, "learning_rate": 1.6482443255826842e-06, "loss": 0.7907, "step": 212330 }, { "epoch": 17.65, "learning_rate": 1.6481334700551505e-06, "loss": 0.8388, "step": 212340 }, { "epoch": 17.65, "learning_rate": 1.6480226145276168e-06, "loss": 0.7433, "step": 212350 }, { "epoch": 17.65, "learning_rate": 1.6479117590000831e-06, "loss": 0.7867, "step": 212360 }, { "epoch": 17.65, "learning_rate": 1.6478009034725492e-06, "loss": 0.7672, "step": 212370 }, { "epoch": 17.65, "learning_rate": 1.6476900479450155e-06, "loss": 0.7504, "step": 212380 }, { "epoch": 17.65, "learning_rate": 1.6475791924174818e-06, "loss": 0.7227, "step": 212390 }, { "epoch": 17.65, "learning_rate": 1.647468336889948e-06, "loss": 0.7962, "step": 212400 }, { "epoch": 17.66, "learning_rate": 1.6473574813624142e-06, "loss": 0.7296, "step": 212410 }, { "epoch": 17.66, "learning_rate": 1.6472466258348807e-06, "loss": 0.7363, "step": 212420 }, { "epoch": 17.66, "learning_rate": 1.647135770307347e-06, "loss": 0.7983, "step": 212430 }, { "epoch": 17.66, "learning_rate": 1.6470249147798133e-06, "loss": 0.8318, "step": 212440 }, { "epoch": 17.66, "learning_rate": 1.6469140592522794e-06, "loss": 0.7382, "step": 212450 }, { "epoch": 17.66, "learning_rate": 1.6468032037247457e-06, "loss": 0.7903, "step": 212460 }, { "epoch": 17.66, "learning_rate": 1.646692348197212e-06, "loss": 0.7788, "step": 212470 }, { "epoch": 17.66, "learning_rate": 1.6465814926696783e-06, "loss": 0.7493, "step": 212480 }, { "epoch": 17.66, "learning_rate": 1.6464706371421443e-06, "loss": 0.7792, "step": 212490 }, { "epoch": 17.66, "learning_rate": 1.6463597816146106e-06, "loss": 0.8301, "step": 212500 }, { "epoch": 17.66, "learning_rate": 1.646248926087077e-06, "loss": 0.8311, "step": 212510 }, { "epoch": 17.66, "learning_rate": 1.6461380705595432e-06, "loss": 0.7459, "step": 212520 }, { "epoch": 17.67, "learning_rate": 1.6460272150320093e-06, "loss": 0.799, "step": 212530 }, { "epoch": 17.67, "learning_rate": 1.6459163595044758e-06, "loss": 0.7848, "step": 212540 }, { "epoch": 17.67, "learning_rate": 1.6458055039769421e-06, "loss": 0.7294, "step": 212550 }, { "epoch": 17.67, "learning_rate": 1.6456946484494084e-06, "loss": 0.7584, "step": 212560 }, { "epoch": 17.67, "learning_rate": 1.6455837929218745e-06, "loss": 0.7208, "step": 212570 }, { "epoch": 17.67, "learning_rate": 1.6454729373943408e-06, "loss": 0.7525, "step": 212580 }, { "epoch": 17.67, "learning_rate": 1.645362081866807e-06, "loss": 0.8514, "step": 212590 }, { "epoch": 17.67, "learning_rate": 1.6452512263392732e-06, "loss": 0.7205, "step": 212600 }, { "epoch": 17.67, "learning_rate": 1.6451403708117395e-06, "loss": 0.75, "step": 212610 }, { "epoch": 17.67, "learning_rate": 1.6450295152842058e-06, "loss": 0.7244, "step": 212620 }, { "epoch": 17.67, "learning_rate": 1.644918659756672e-06, "loss": 0.8275, "step": 212630 }, { "epoch": 17.67, "learning_rate": 1.6448078042291381e-06, "loss": 0.7833, "step": 212640 }, { "epoch": 17.68, "learning_rate": 1.6446969487016044e-06, "loss": 0.7207, "step": 212650 }, { "epoch": 17.68, "learning_rate": 1.6445860931740707e-06, "loss": 0.7907, "step": 212660 }, { "epoch": 17.68, "learning_rate": 1.6444752376465372e-06, "loss": 0.7903, "step": 212670 }, { "epoch": 17.68, "learning_rate": 1.6443643821190033e-06, "loss": 0.7924, "step": 212680 }, { "epoch": 17.68, "learning_rate": 1.6442535265914696e-06, "loss": 0.8301, "step": 212690 }, { "epoch": 17.68, "learning_rate": 1.644142671063936e-06, "loss": 0.7433, "step": 212700 }, { "epoch": 17.68, "learning_rate": 1.6440318155364022e-06, "loss": 0.8307, "step": 212710 }, { "epoch": 17.68, "learning_rate": 1.6439209600088683e-06, "loss": 0.7171, "step": 212720 }, { "epoch": 17.68, "learning_rate": 1.6438101044813346e-06, "loss": 0.7897, "step": 212730 }, { "epoch": 17.68, "learning_rate": 1.6436992489538009e-06, "loss": 0.7229, "step": 212740 }, { "epoch": 17.68, "learning_rate": 1.6435883934262672e-06, "loss": 0.6905, "step": 212750 }, { "epoch": 17.68, "learning_rate": 1.6434775378987333e-06, "loss": 0.7922, "step": 212760 }, { "epoch": 17.69, "learning_rate": 1.6433666823711995e-06, "loss": 0.7442, "step": 212770 }, { "epoch": 17.69, "learning_rate": 1.6432558268436658e-06, "loss": 0.797, "step": 212780 }, { "epoch": 17.69, "learning_rate": 1.6431449713161324e-06, "loss": 0.8083, "step": 212790 }, { "epoch": 17.69, "learning_rate": 1.6430341157885984e-06, "loss": 0.7413, "step": 212800 }, { "epoch": 17.69, "learning_rate": 1.6429232602610647e-06, "loss": 0.7465, "step": 212810 }, { "epoch": 17.69, "learning_rate": 1.642812404733531e-06, "loss": 0.7971, "step": 212820 }, { "epoch": 17.69, "learning_rate": 1.6427015492059973e-06, "loss": 0.7718, "step": 212830 }, { "epoch": 17.69, "learning_rate": 1.6425906936784634e-06, "loss": 0.751, "step": 212840 }, { "epoch": 17.69, "learning_rate": 1.6424798381509297e-06, "loss": 0.7358, "step": 212850 }, { "epoch": 17.69, "learning_rate": 1.642368982623396e-06, "loss": 0.7739, "step": 212860 }, { "epoch": 17.69, "learning_rate": 1.6422581270958623e-06, "loss": 0.7495, "step": 212870 }, { "epoch": 17.69, "learning_rate": 1.6421472715683284e-06, "loss": 0.8142, "step": 212880 }, { "epoch": 17.7, "learning_rate": 1.6420364160407947e-06, "loss": 0.7081, "step": 212890 }, { "epoch": 17.7, "learning_rate": 1.641925560513261e-06, "loss": 0.7212, "step": 212900 }, { "epoch": 17.7, "learning_rate": 1.6418147049857275e-06, "loss": 0.7426, "step": 212910 }, { "epoch": 17.7, "learning_rate": 1.6417038494581936e-06, "loss": 0.7617, "step": 212920 }, { "epoch": 17.7, "learning_rate": 1.6415929939306599e-06, "loss": 0.7571, "step": 212930 }, { "epoch": 17.7, "learning_rate": 1.6414821384031261e-06, "loss": 0.8513, "step": 212940 }, { "epoch": 17.7, "learning_rate": 1.6413712828755924e-06, "loss": 0.7561, "step": 212950 }, { "epoch": 17.7, "learning_rate": 1.6412604273480585e-06, "loss": 0.7564, "step": 212960 }, { "epoch": 17.7, "learning_rate": 1.6411495718205248e-06, "loss": 0.7471, "step": 212970 }, { "epoch": 17.7, "learning_rate": 1.6410387162929911e-06, "loss": 0.7681, "step": 212980 }, { "epoch": 17.7, "learning_rate": 1.6409278607654574e-06, "loss": 0.6857, "step": 212990 }, { "epoch": 17.7, "learning_rate": 1.6408170052379235e-06, "loss": 0.7491, "step": 213000 }, { "epoch": 17.71, "learning_rate": 1.6407061497103898e-06, "loss": 0.7546, "step": 213010 }, { "epoch": 17.71, "learning_rate": 1.640595294182856e-06, "loss": 0.7346, "step": 213020 }, { "epoch": 17.71, "learning_rate": 1.6404844386553222e-06, "loss": 0.7961, "step": 213030 }, { "epoch": 17.71, "learning_rate": 1.6403735831277887e-06, "loss": 0.8432, "step": 213040 }, { "epoch": 17.71, "learning_rate": 1.640262727600255e-06, "loss": 0.7805, "step": 213050 }, { "epoch": 17.71, "learning_rate": 1.6401518720727213e-06, "loss": 0.746, "step": 213060 }, { "epoch": 17.71, "learning_rate": 1.6400410165451873e-06, "loss": 0.7537, "step": 213070 }, { "epoch": 17.71, "learning_rate": 1.6399301610176536e-06, "loss": 0.7532, "step": 213080 }, { "epoch": 17.71, "learning_rate": 1.63981930549012e-06, "loss": 0.818, "step": 213090 }, { "epoch": 17.71, "learning_rate": 1.6397084499625862e-06, "loss": 0.7962, "step": 213100 }, { "epoch": 17.71, "learning_rate": 1.6395975944350523e-06, "loss": 0.7984, "step": 213110 }, { "epoch": 17.71, "learning_rate": 1.6394867389075186e-06, "loss": 0.7117, "step": 213120 }, { "epoch": 17.72, "learning_rate": 1.639375883379985e-06, "loss": 0.8149, "step": 213130 }, { "epoch": 17.72, "learning_rate": 1.6392650278524512e-06, "loss": 0.8208, "step": 213140 }, { "epoch": 17.72, "learning_rate": 1.6391541723249173e-06, "loss": 0.7796, "step": 213150 }, { "epoch": 17.72, "learning_rate": 1.6390433167973838e-06, "loss": 0.7469, "step": 213160 }, { "epoch": 17.72, "learning_rate": 1.63893246126985e-06, "loss": 0.7187, "step": 213170 }, { "epoch": 17.72, "learning_rate": 1.6388216057423164e-06, "loss": 0.7425, "step": 213180 }, { "epoch": 17.72, "learning_rate": 1.6387107502147825e-06, "loss": 0.7559, "step": 213190 }, { "epoch": 17.72, "learning_rate": 1.6385998946872488e-06, "loss": 0.7375, "step": 213200 }, { "epoch": 17.72, "learning_rate": 1.638489039159715e-06, "loss": 0.7476, "step": 213210 }, { "epoch": 17.72, "learning_rate": 1.6383781836321814e-06, "loss": 0.7238, "step": 213220 }, { "epoch": 17.72, "learning_rate": 1.6382673281046474e-06, "loss": 0.8266, "step": 213230 }, { "epoch": 17.72, "learning_rate": 1.6381564725771137e-06, "loss": 0.7969, "step": 213240 }, { "epoch": 17.73, "learning_rate": 1.63804561704958e-06, "loss": 0.8287, "step": 213250 }, { "epoch": 17.73, "learning_rate": 1.6379347615220463e-06, "loss": 0.792, "step": 213260 }, { "epoch": 17.73, "learning_rate": 1.6378239059945124e-06, "loss": 0.7569, "step": 213270 }, { "epoch": 17.73, "learning_rate": 1.637713050466979e-06, "loss": 0.7839, "step": 213280 }, { "epoch": 17.73, "learning_rate": 1.6376021949394452e-06, "loss": 0.7702, "step": 213290 }, { "epoch": 17.73, "learning_rate": 1.6374913394119115e-06, "loss": 0.7343, "step": 213300 }, { "epoch": 17.73, "learning_rate": 1.6373804838843776e-06, "loss": 0.8142, "step": 213310 }, { "epoch": 17.73, "learning_rate": 1.6372696283568439e-06, "loss": 0.7191, "step": 213320 }, { "epoch": 17.73, "learning_rate": 1.6371587728293102e-06, "loss": 0.7931, "step": 213330 }, { "epoch": 17.73, "learning_rate": 1.6370479173017765e-06, "loss": 0.8085, "step": 213340 }, { "epoch": 17.73, "learning_rate": 1.6369370617742426e-06, "loss": 0.8082, "step": 213350 }, { "epoch": 17.73, "learning_rate": 1.6368262062467089e-06, "loss": 0.7901, "step": 213360 }, { "epoch": 17.74, "learning_rate": 1.6367153507191752e-06, "loss": 0.7606, "step": 213370 }, { "epoch": 17.74, "learning_rate": 1.6366044951916414e-06, "loss": 0.7363, "step": 213380 }, { "epoch": 17.74, "learning_rate": 1.6364936396641075e-06, "loss": 0.8038, "step": 213390 }, { "epoch": 17.74, "learning_rate": 1.636382784136574e-06, "loss": 0.7322, "step": 213400 }, { "epoch": 17.74, "learning_rate": 1.6362719286090403e-06, "loss": 0.7326, "step": 213410 }, { "epoch": 17.74, "learning_rate": 1.6361610730815066e-06, "loss": 0.762, "step": 213420 }, { "epoch": 17.74, "learning_rate": 1.6360502175539727e-06, "loss": 0.7936, "step": 213430 }, { "epoch": 17.74, "learning_rate": 1.635939362026439e-06, "loss": 0.8394, "step": 213440 }, { "epoch": 17.74, "learning_rate": 1.6358285064989053e-06, "loss": 0.7921, "step": 213450 }, { "epoch": 17.74, "learning_rate": 1.6357176509713714e-06, "loss": 0.7455, "step": 213460 }, { "epoch": 17.74, "learning_rate": 1.6356067954438377e-06, "loss": 0.7942, "step": 213470 }, { "epoch": 17.74, "learning_rate": 1.635495939916304e-06, "loss": 0.7492, "step": 213480 }, { "epoch": 17.74, "learning_rate": 1.6353850843887703e-06, "loss": 0.8588, "step": 213490 }, { "epoch": 17.75, "learning_rate": 1.6352742288612364e-06, "loss": 0.7384, "step": 213500 }, { "epoch": 17.75, "learning_rate": 1.6351633733337027e-06, "loss": 0.7261, "step": 213510 }, { "epoch": 17.75, "learning_rate": 1.635052517806169e-06, "loss": 0.741, "step": 213520 }, { "epoch": 17.75, "learning_rate": 1.6349416622786355e-06, "loss": 0.7414, "step": 213530 }, { "epoch": 17.75, "learning_rate": 1.6348308067511015e-06, "loss": 0.7636, "step": 213540 }, { "epoch": 17.75, "learning_rate": 1.6347199512235678e-06, "loss": 0.7559, "step": 213550 }, { "epoch": 17.75, "learning_rate": 1.6346090956960341e-06, "loss": 0.7408, "step": 213560 }, { "epoch": 17.75, "learning_rate": 1.6344982401685004e-06, "loss": 0.7956, "step": 213570 }, { "epoch": 17.75, "learning_rate": 1.6343873846409665e-06, "loss": 0.7501, "step": 213580 }, { "epoch": 17.75, "learning_rate": 1.6342765291134328e-06, "loss": 0.7467, "step": 213590 }, { "epoch": 17.75, "learning_rate": 1.634165673585899e-06, "loss": 0.7266, "step": 213600 }, { "epoch": 17.75, "learning_rate": 1.6340548180583654e-06, "loss": 0.7898, "step": 213610 }, { "epoch": 17.76, "learning_rate": 1.6339439625308315e-06, "loss": 0.7915, "step": 213620 }, { "epoch": 17.76, "learning_rate": 1.6338331070032978e-06, "loss": 0.7081, "step": 213630 }, { "epoch": 17.76, "learning_rate": 1.633722251475764e-06, "loss": 0.7923, "step": 213640 }, { "epoch": 17.76, "learning_rate": 1.6336113959482306e-06, "loss": 0.8112, "step": 213650 }, { "epoch": 17.76, "learning_rate": 1.6335005404206967e-06, "loss": 0.7302, "step": 213660 }, { "epoch": 17.76, "learning_rate": 1.633389684893163e-06, "loss": 0.7853, "step": 213670 }, { "epoch": 17.76, "learning_rate": 1.6332788293656292e-06, "loss": 0.743, "step": 213680 }, { "epoch": 17.76, "learning_rate": 1.6331679738380955e-06, "loss": 0.7492, "step": 213690 }, { "epoch": 17.76, "learning_rate": 1.6330571183105616e-06, "loss": 0.7465, "step": 213700 }, { "epoch": 17.76, "learning_rate": 1.632946262783028e-06, "loss": 0.7653, "step": 213710 }, { "epoch": 17.76, "learning_rate": 1.6328354072554942e-06, "loss": 0.7559, "step": 213720 }, { "epoch": 17.76, "learning_rate": 1.6327245517279605e-06, "loss": 0.7585, "step": 213730 }, { "epoch": 17.77, "learning_rate": 1.6326136962004266e-06, "loss": 0.7911, "step": 213740 }, { "epoch": 17.77, "learning_rate": 1.6325028406728929e-06, "loss": 0.7152, "step": 213750 }, { "epoch": 17.77, "learning_rate": 1.6323919851453592e-06, "loss": 0.7322, "step": 213760 }, { "epoch": 17.77, "learning_rate": 1.6322811296178257e-06, "loss": 0.811, "step": 213770 }, { "epoch": 17.77, "learning_rate": 1.6321702740902918e-06, "loss": 0.788, "step": 213780 }, { "epoch": 17.77, "learning_rate": 1.632059418562758e-06, "loss": 0.8833, "step": 213790 }, { "epoch": 17.77, "learning_rate": 1.6319485630352244e-06, "loss": 0.743, "step": 213800 }, { "epoch": 17.77, "learning_rate": 1.6318377075076907e-06, "loss": 0.7809, "step": 213810 }, { "epoch": 17.77, "learning_rate": 1.6317268519801567e-06, "loss": 0.7584, "step": 213820 }, { "epoch": 17.77, "learning_rate": 1.631615996452623e-06, "loss": 0.8221, "step": 213830 }, { "epoch": 17.77, "learning_rate": 1.6315051409250893e-06, "loss": 0.7815, "step": 213840 }, { "epoch": 17.77, "learning_rate": 1.6313942853975554e-06, "loss": 0.7603, "step": 213850 }, { "epoch": 17.78, "learning_rate": 1.6312834298700217e-06, "loss": 0.8357, "step": 213860 }, { "epoch": 17.78, "learning_rate": 1.631172574342488e-06, "loss": 0.7486, "step": 213870 }, { "epoch": 17.78, "learning_rate": 1.6310617188149543e-06, "loss": 0.795, "step": 213880 }, { "epoch": 17.78, "learning_rate": 1.6309508632874204e-06, "loss": 0.7441, "step": 213890 }, { "epoch": 17.78, "learning_rate": 1.630840007759887e-06, "loss": 0.78, "step": 213900 }, { "epoch": 17.78, "learning_rate": 1.6307291522323532e-06, "loss": 0.7516, "step": 213910 }, { "epoch": 17.78, "learning_rate": 1.6306182967048195e-06, "loss": 0.7446, "step": 213920 }, { "epoch": 17.78, "learning_rate": 1.6305074411772856e-06, "loss": 0.7759, "step": 213930 }, { "epoch": 17.78, "learning_rate": 1.6303965856497519e-06, "loss": 0.8169, "step": 213940 }, { "epoch": 17.78, "learning_rate": 1.6302857301222182e-06, "loss": 0.7829, "step": 213950 }, { "epoch": 17.78, "learning_rate": 1.6301748745946845e-06, "loss": 0.7174, "step": 213960 }, { "epoch": 17.78, "learning_rate": 1.6300640190671505e-06, "loss": 0.7458, "step": 213970 }, { "epoch": 17.79, "learning_rate": 1.6299531635396168e-06, "loss": 0.7542, "step": 213980 }, { "epoch": 17.79, "learning_rate": 1.6298423080120831e-06, "loss": 0.8272, "step": 213990 }, { "epoch": 17.79, "learning_rate": 1.6297314524845494e-06, "loss": 0.75, "step": 214000 }, { "epoch": 17.79, "learning_rate": 1.6296205969570155e-06, "loss": 0.7735, "step": 214010 }, { "epoch": 17.79, "learning_rate": 1.629509741429482e-06, "loss": 0.7516, "step": 214020 }, { "epoch": 17.79, "learning_rate": 1.6293988859019483e-06, "loss": 0.8052, "step": 214030 }, { "epoch": 17.79, "learning_rate": 1.6292880303744146e-06, "loss": 0.8306, "step": 214040 }, { "epoch": 17.79, "learning_rate": 1.6291771748468807e-06, "loss": 0.8, "step": 214050 }, { "epoch": 17.79, "learning_rate": 1.629066319319347e-06, "loss": 0.7994, "step": 214060 }, { "epoch": 17.79, "learning_rate": 1.6289554637918133e-06, "loss": 0.7331, "step": 214070 }, { "epoch": 17.79, "learning_rate": 1.6288446082642796e-06, "loss": 0.8262, "step": 214080 }, { "epoch": 17.79, "learning_rate": 1.6287337527367457e-06, "loss": 0.7782, "step": 214090 }, { "epoch": 17.8, "learning_rate": 1.628622897209212e-06, "loss": 0.7209, "step": 214100 }, { "epoch": 17.8, "learning_rate": 1.6285120416816783e-06, "loss": 0.7066, "step": 214110 }, { "epoch": 17.8, "learning_rate": 1.6284011861541445e-06, "loss": 0.7882, "step": 214120 }, { "epoch": 17.8, "learning_rate": 1.6282903306266106e-06, "loss": 0.7602, "step": 214130 }, { "epoch": 17.8, "learning_rate": 1.6281794750990771e-06, "loss": 0.7483, "step": 214140 }, { "epoch": 17.8, "learning_rate": 1.6280686195715434e-06, "loss": 0.8234, "step": 214150 }, { "epoch": 17.8, "learning_rate": 1.6279577640440097e-06, "loss": 0.7525, "step": 214160 }, { "epoch": 17.8, "learning_rate": 1.6278469085164758e-06, "loss": 0.7631, "step": 214170 }, { "epoch": 17.8, "learning_rate": 1.6277360529889421e-06, "loss": 0.7894, "step": 214180 }, { "epoch": 17.8, "learning_rate": 1.6276251974614084e-06, "loss": 0.737, "step": 214190 }, { "epoch": 17.8, "learning_rate": 1.6275143419338747e-06, "loss": 0.7245, "step": 214200 }, { "epoch": 17.8, "learning_rate": 1.6274034864063408e-06, "loss": 0.7557, "step": 214210 }, { "epoch": 17.81, "learning_rate": 1.627292630878807e-06, "loss": 0.717, "step": 214220 }, { "epoch": 17.81, "learning_rate": 1.6271817753512734e-06, "loss": 0.7073, "step": 214230 }, { "epoch": 17.81, "learning_rate": 1.6270709198237395e-06, "loss": 0.8148, "step": 214240 }, { "epoch": 17.81, "learning_rate": 1.6269600642962058e-06, "loss": 0.7679, "step": 214250 }, { "epoch": 17.81, "learning_rate": 1.626849208768672e-06, "loss": 0.763, "step": 214260 }, { "epoch": 17.81, "learning_rate": 1.6267383532411386e-06, "loss": 0.7875, "step": 214270 }, { "epoch": 17.81, "learning_rate": 1.6266274977136049e-06, "loss": 0.7526, "step": 214280 }, { "epoch": 17.81, "learning_rate": 1.626516642186071e-06, "loss": 0.7834, "step": 214290 }, { "epoch": 17.81, "learning_rate": 1.6264057866585372e-06, "loss": 0.7934, "step": 214300 }, { "epoch": 17.81, "learning_rate": 1.6262949311310035e-06, "loss": 0.7647, "step": 214310 }, { "epoch": 17.81, "learning_rate": 1.6261840756034696e-06, "loss": 0.742, "step": 214320 }, { "epoch": 17.81, "learning_rate": 1.626073220075936e-06, "loss": 0.7782, "step": 214330 }, { "epoch": 17.82, "learning_rate": 1.6259623645484022e-06, "loss": 0.8201, "step": 214340 }, { "epoch": 17.82, "learning_rate": 1.6258515090208685e-06, "loss": 0.7199, "step": 214350 }, { "epoch": 17.82, "learning_rate": 1.6257406534933346e-06, "loss": 0.7554, "step": 214360 }, { "epoch": 17.82, "learning_rate": 1.6256297979658009e-06, "loss": 0.72, "step": 214370 }, { "epoch": 17.82, "learning_rate": 1.6255189424382672e-06, "loss": 0.7636, "step": 214380 }, { "epoch": 17.82, "learning_rate": 1.625419172463487e-06, "loss": 0.7699, "step": 214390 }, { "epoch": 17.82, "learning_rate": 1.6253083169359532e-06, "loss": 0.7084, "step": 214400 }, { "epoch": 17.82, "learning_rate": 1.6251974614084193e-06, "loss": 0.7372, "step": 214410 }, { "epoch": 17.82, "learning_rate": 1.6250866058808856e-06, "loss": 0.8137, "step": 214420 }, { "epoch": 17.82, "learning_rate": 1.6249757503533519e-06, "loss": 0.7876, "step": 214430 }, { "epoch": 17.82, "learning_rate": 1.6248648948258182e-06, "loss": 0.7907, "step": 214440 }, { "epoch": 17.82, "learning_rate": 1.6247540392982843e-06, "loss": 0.7307, "step": 214450 }, { "epoch": 17.83, "learning_rate": 1.6246431837707506e-06, "loss": 0.799, "step": 214460 }, { "epoch": 17.83, "learning_rate": 1.6245323282432169e-06, "loss": 0.7387, "step": 214470 }, { "epoch": 17.83, "learning_rate": 1.6244214727156834e-06, "loss": 0.7692, "step": 214480 }, { "epoch": 17.83, "learning_rate": 1.6243106171881494e-06, "loss": 0.769, "step": 214490 }, { "epoch": 17.83, "learning_rate": 1.6241997616606157e-06, "loss": 0.7542, "step": 214500 }, { "epoch": 17.83, "learning_rate": 1.624088906133082e-06, "loss": 0.7336, "step": 214510 }, { "epoch": 17.83, "learning_rate": 1.6239780506055483e-06, "loss": 0.7456, "step": 214520 }, { "epoch": 17.83, "learning_rate": 1.6238671950780144e-06, "loss": 0.783, "step": 214530 }, { "epoch": 17.83, "learning_rate": 1.6237563395504807e-06, "loss": 0.7909, "step": 214540 }, { "epoch": 17.83, "learning_rate": 1.623645484022947e-06, "loss": 0.7526, "step": 214550 }, { "epoch": 17.83, "learning_rate": 1.6235346284954133e-06, "loss": 0.8317, "step": 214560 }, { "epoch": 17.83, "learning_rate": 1.6234237729678794e-06, "loss": 0.7756, "step": 214570 }, { "epoch": 17.84, "learning_rate": 1.6233129174403457e-06, "loss": 0.7527, "step": 214580 }, { "epoch": 17.84, "learning_rate": 1.623202061912812e-06, "loss": 0.7769, "step": 214590 }, { "epoch": 17.84, "learning_rate": 1.6230912063852785e-06, "loss": 0.7873, "step": 214600 }, { "epoch": 17.84, "learning_rate": 1.6229803508577446e-06, "loss": 0.7705, "step": 214610 }, { "epoch": 17.84, "learning_rate": 1.6228694953302109e-06, "loss": 0.8269, "step": 214620 }, { "epoch": 17.84, "learning_rate": 1.6227586398026772e-06, "loss": 0.7286, "step": 214630 }, { "epoch": 17.84, "learning_rate": 1.6226477842751435e-06, "loss": 0.7554, "step": 214640 }, { "epoch": 17.84, "learning_rate": 1.6225369287476095e-06, "loss": 0.7475, "step": 214650 }, { "epoch": 17.84, "learning_rate": 1.6224260732200758e-06, "loss": 0.6991, "step": 214660 }, { "epoch": 17.84, "learning_rate": 1.6223152176925421e-06, "loss": 0.7636, "step": 214670 }, { "epoch": 17.84, "learning_rate": 1.6222043621650084e-06, "loss": 0.7841, "step": 214680 }, { "epoch": 17.84, "learning_rate": 1.6220935066374745e-06, "loss": 0.7517, "step": 214690 }, { "epoch": 17.85, "learning_rate": 1.6219826511099408e-06, "loss": 0.772, "step": 214700 }, { "epoch": 17.85, "learning_rate": 1.621871795582407e-06, "loss": 0.7482, "step": 214710 }, { "epoch": 17.85, "learning_rate": 1.6217609400548736e-06, "loss": 0.7737, "step": 214720 }, { "epoch": 17.85, "learning_rate": 1.6216500845273397e-06, "loss": 0.7731, "step": 214730 }, { "epoch": 17.85, "learning_rate": 1.621539228999806e-06, "loss": 0.7824, "step": 214740 }, { "epoch": 17.85, "learning_rate": 1.6214283734722723e-06, "loss": 0.7285, "step": 214750 }, { "epoch": 17.85, "learning_rate": 1.6213175179447386e-06, "loss": 0.7941, "step": 214760 }, { "epoch": 17.85, "learning_rate": 1.6212066624172047e-06, "loss": 0.7754, "step": 214770 }, { "epoch": 17.85, "learning_rate": 1.621095806889671e-06, "loss": 0.7233, "step": 214780 }, { "epoch": 17.85, "learning_rate": 1.6209849513621373e-06, "loss": 0.7755, "step": 214790 }, { "epoch": 17.85, "learning_rate": 1.6208740958346033e-06, "loss": 0.787, "step": 214800 }, { "epoch": 17.85, "learning_rate": 1.6207632403070696e-06, "loss": 0.7395, "step": 214810 }, { "epoch": 17.86, "learning_rate": 1.620652384779536e-06, "loss": 0.7487, "step": 214820 }, { "epoch": 17.86, "learning_rate": 1.6205415292520022e-06, "loss": 0.7569, "step": 214830 }, { "epoch": 17.86, "learning_rate": 1.6204306737244687e-06, "loss": 0.7478, "step": 214840 }, { "epoch": 17.86, "learning_rate": 1.6203198181969348e-06, "loss": 0.7432, "step": 214850 }, { "epoch": 17.86, "learning_rate": 1.6202089626694011e-06, "loss": 0.7491, "step": 214860 }, { "epoch": 17.86, "learning_rate": 1.6200981071418674e-06, "loss": 0.7523, "step": 214870 }, { "epoch": 17.86, "learning_rate": 1.6199872516143335e-06, "loss": 0.7636, "step": 214880 }, { "epoch": 17.86, "learning_rate": 1.6198763960867998e-06, "loss": 0.8463, "step": 214890 }, { "epoch": 17.86, "learning_rate": 1.619765540559266e-06, "loss": 0.7756, "step": 214900 }, { "epoch": 17.86, "learning_rate": 1.6196546850317324e-06, "loss": 0.7681, "step": 214910 }, { "epoch": 17.86, "learning_rate": 1.6195438295041985e-06, "loss": 0.7674, "step": 214920 }, { "epoch": 17.86, "learning_rate": 1.6194329739766647e-06, "loss": 0.7247, "step": 214930 }, { "epoch": 17.87, "learning_rate": 1.619322118449131e-06, "loss": 0.8149, "step": 214940 }, { "epoch": 17.87, "learning_rate": 1.6192112629215973e-06, "loss": 0.7474, "step": 214950 }, { "epoch": 17.87, "learning_rate": 1.6191004073940634e-06, "loss": 0.736, "step": 214960 }, { "epoch": 17.87, "learning_rate": 1.61898955186653e-06, "loss": 0.7888, "step": 214970 }, { "epoch": 17.87, "learning_rate": 1.6188786963389962e-06, "loss": 0.7254, "step": 214980 }, { "epoch": 17.87, "learning_rate": 1.6187678408114625e-06, "loss": 0.7837, "step": 214990 }, { "epoch": 17.87, "learning_rate": 1.6186569852839286e-06, "loss": 0.7305, "step": 215000 }, { "epoch": 17.87, "learning_rate": 1.618546129756395e-06, "loss": 0.7104, "step": 215010 }, { "epoch": 17.87, "learning_rate": 1.6184352742288612e-06, "loss": 0.7812, "step": 215020 }, { "epoch": 17.87, "learning_rate": 1.6183244187013275e-06, "loss": 0.8024, "step": 215030 }, { "epoch": 17.87, "learning_rate": 1.6182135631737936e-06, "loss": 0.7946, "step": 215040 }, { "epoch": 17.87, "learning_rate": 1.6181027076462599e-06, "loss": 0.726, "step": 215050 }, { "epoch": 17.88, "learning_rate": 1.6179918521187262e-06, "loss": 0.7513, "step": 215060 }, { "epoch": 17.88, "learning_rate": 1.6178809965911925e-06, "loss": 0.7401, "step": 215070 }, { "epoch": 17.88, "learning_rate": 1.6177701410636585e-06, "loss": 0.7531, "step": 215080 }, { "epoch": 17.88, "learning_rate": 1.617659285536125e-06, "loss": 0.8063, "step": 215090 }, { "epoch": 17.88, "learning_rate": 1.6175484300085913e-06, "loss": 0.7759, "step": 215100 }, { "epoch": 17.88, "learning_rate": 1.6174375744810576e-06, "loss": 0.7417, "step": 215110 }, { "epoch": 17.88, "learning_rate": 1.6173267189535237e-06, "loss": 0.7768, "step": 215120 }, { "epoch": 17.88, "learning_rate": 1.61721586342599e-06, "loss": 0.7634, "step": 215130 }, { "epoch": 17.88, "learning_rate": 1.6171050078984563e-06, "loss": 0.7677, "step": 215140 }, { "epoch": 17.88, "learning_rate": 1.6169941523709226e-06, "loss": 0.7728, "step": 215150 }, { "epoch": 17.88, "learning_rate": 1.6168832968433887e-06, "loss": 0.7211, "step": 215160 }, { "epoch": 17.88, "learning_rate": 1.616772441315855e-06, "loss": 0.7864, "step": 215170 }, { "epoch": 17.89, "learning_rate": 1.6166615857883213e-06, "loss": 0.7721, "step": 215180 }, { "epoch": 17.89, "learning_rate": 1.6165507302607876e-06, "loss": 0.7833, "step": 215190 }, { "epoch": 17.89, "learning_rate": 1.6164398747332537e-06, "loss": 0.7318, "step": 215200 }, { "epoch": 17.89, "learning_rate": 1.6163290192057202e-06, "loss": 0.7543, "step": 215210 }, { "epoch": 17.89, "learning_rate": 1.6162181636781865e-06, "loss": 0.7368, "step": 215220 }, { "epoch": 17.89, "learning_rate": 1.6161073081506528e-06, "loss": 0.729, "step": 215230 }, { "epoch": 17.89, "learning_rate": 1.6159964526231188e-06, "loss": 0.8165, "step": 215240 }, { "epoch": 17.89, "learning_rate": 1.6158855970955851e-06, "loss": 0.7806, "step": 215250 }, { "epoch": 17.89, "learning_rate": 1.6157747415680514e-06, "loss": 0.7569, "step": 215260 }, { "epoch": 17.89, "learning_rate": 1.6156638860405175e-06, "loss": 0.7745, "step": 215270 }, { "epoch": 17.89, "learning_rate": 1.6155530305129838e-06, "loss": 0.7876, "step": 215280 }, { "epoch": 17.89, "learning_rate": 1.6154421749854501e-06, "loss": 0.7651, "step": 215290 }, { "epoch": 17.9, "learning_rate": 1.6153313194579164e-06, "loss": 0.744, "step": 215300 }, { "epoch": 17.9, "learning_rate": 1.6152204639303825e-06, "loss": 0.7716, "step": 215310 }, { "epoch": 17.9, "learning_rate": 1.6151096084028488e-06, "loss": 0.7461, "step": 215320 }, { "epoch": 17.9, "learning_rate": 1.614998752875315e-06, "loss": 0.7925, "step": 215330 }, { "epoch": 17.9, "learning_rate": 1.6148878973477816e-06, "loss": 0.8022, "step": 215340 }, { "epoch": 17.9, "learning_rate": 1.6147770418202477e-06, "loss": 0.7729, "step": 215350 }, { "epoch": 17.9, "learning_rate": 1.614666186292714e-06, "loss": 0.7514, "step": 215360 }, { "epoch": 17.9, "learning_rate": 1.6145553307651803e-06, "loss": 0.7568, "step": 215370 }, { "epoch": 17.9, "learning_rate": 1.6144444752376466e-06, "loss": 0.7383, "step": 215380 }, { "epoch": 17.9, "learning_rate": 1.6143336197101126e-06, "loss": 0.877, "step": 215390 }, { "epoch": 17.9, "learning_rate": 1.614222764182579e-06, "loss": 0.7136, "step": 215400 }, { "epoch": 17.9, "learning_rate": 1.6141119086550452e-06, "loss": 0.7456, "step": 215410 }, { "epoch": 17.91, "learning_rate": 1.6140010531275115e-06, "loss": 0.7273, "step": 215420 }, { "epoch": 17.91, "learning_rate": 1.6138901975999776e-06, "loss": 0.7505, "step": 215430 }, { "epoch": 17.91, "learning_rate": 1.613779342072444e-06, "loss": 0.8571, "step": 215440 }, { "epoch": 17.91, "learning_rate": 1.6136684865449102e-06, "loss": 0.6688, "step": 215450 }, { "epoch": 17.91, "learning_rate": 1.6135576310173767e-06, "loss": 0.739, "step": 215460 }, { "epoch": 17.91, "learning_rate": 1.6134467754898428e-06, "loss": 0.7816, "step": 215470 }, { "epoch": 17.91, "learning_rate": 1.613335919962309e-06, "loss": 0.8038, "step": 215480 }, { "epoch": 17.91, "learning_rate": 1.6132250644347754e-06, "loss": 0.7585, "step": 215490 }, { "epoch": 17.91, "learning_rate": 1.6131142089072417e-06, "loss": 0.765, "step": 215500 }, { "epoch": 17.91, "learning_rate": 1.6130033533797078e-06, "loss": 0.7744, "step": 215510 }, { "epoch": 17.91, "learning_rate": 1.612892497852174e-06, "loss": 0.7629, "step": 215520 }, { "epoch": 17.91, "learning_rate": 1.6127816423246404e-06, "loss": 0.8158, "step": 215530 }, { "epoch": 17.92, "learning_rate": 1.6126707867971066e-06, "loss": 0.729, "step": 215540 }, { "epoch": 17.92, "learning_rate": 1.6125599312695727e-06, "loss": 0.7655, "step": 215550 }, { "epoch": 17.92, "learning_rate": 1.612449075742039e-06, "loss": 0.755, "step": 215560 }, { "epoch": 17.92, "learning_rate": 1.6123382202145053e-06, "loss": 0.7682, "step": 215570 }, { "epoch": 17.92, "learning_rate": 1.6122273646869718e-06, "loss": 0.7641, "step": 215580 }, { "epoch": 17.92, "learning_rate": 1.612116509159438e-06, "loss": 0.777, "step": 215590 }, { "epoch": 17.92, "learning_rate": 1.6120056536319042e-06, "loss": 0.7222, "step": 215600 }, { "epoch": 17.92, "learning_rate": 1.6118947981043705e-06, "loss": 0.7544, "step": 215610 }, { "epoch": 17.92, "learning_rate": 1.6117839425768368e-06, "loss": 0.7474, "step": 215620 }, { "epoch": 17.92, "learning_rate": 1.6116730870493029e-06, "loss": 0.7883, "step": 215630 }, { "epoch": 17.92, "learning_rate": 1.6115622315217692e-06, "loss": 0.7648, "step": 215640 }, { "epoch": 17.92, "learning_rate": 1.6114513759942355e-06, "loss": 0.7437, "step": 215650 }, { "epoch": 17.93, "learning_rate": 1.6113405204667016e-06, "loss": 0.7408, "step": 215660 }, { "epoch": 17.93, "learning_rate": 1.6112296649391679e-06, "loss": 0.783, "step": 215670 }, { "epoch": 17.93, "learning_rate": 1.6111188094116341e-06, "loss": 0.7437, "step": 215680 }, { "epoch": 17.93, "learning_rate": 1.6110079538841004e-06, "loss": 0.8016, "step": 215690 }, { "epoch": 17.93, "learning_rate": 1.6108970983565667e-06, "loss": 0.7423, "step": 215700 }, { "epoch": 17.93, "learning_rate": 1.610786242829033e-06, "loss": 0.8197, "step": 215710 }, { "epoch": 17.93, "learning_rate": 1.6106753873014993e-06, "loss": 0.7539, "step": 215720 }, { "epoch": 17.93, "learning_rate": 1.6105645317739656e-06, "loss": 0.7903, "step": 215730 }, { "epoch": 17.93, "learning_rate": 1.6104536762464317e-06, "loss": 0.7805, "step": 215740 }, { "epoch": 17.93, "learning_rate": 1.610342820718898e-06, "loss": 0.7642, "step": 215750 }, { "epoch": 17.93, "learning_rate": 1.6102319651913643e-06, "loss": 0.7243, "step": 215760 }, { "epoch": 17.93, "learning_rate": 1.6101211096638306e-06, "loss": 0.7345, "step": 215770 }, { "epoch": 17.94, "learning_rate": 1.6100102541362967e-06, "loss": 0.7822, "step": 215780 }, { "epoch": 17.94, "learning_rate": 1.609899398608763e-06, "loss": 0.7912, "step": 215790 }, { "epoch": 17.94, "learning_rate": 1.6097885430812293e-06, "loss": 0.8322, "step": 215800 }, { "epoch": 17.94, "learning_rate": 1.6096776875536956e-06, "loss": 0.7461, "step": 215810 }, { "epoch": 17.94, "learning_rate": 1.6095668320261616e-06, "loss": 0.7919, "step": 215820 }, { "epoch": 17.94, "learning_rate": 1.6094559764986282e-06, "loss": 0.7648, "step": 215830 }, { "epoch": 17.94, "learning_rate": 1.6093451209710944e-06, "loss": 0.833, "step": 215840 }, { "epoch": 17.94, "learning_rate": 1.6092342654435607e-06, "loss": 0.7401, "step": 215850 }, { "epoch": 17.94, "learning_rate": 1.6091234099160268e-06, "loss": 0.7518, "step": 215860 }, { "epoch": 17.94, "learning_rate": 1.6090125543884931e-06, "loss": 0.7595, "step": 215870 }, { "epoch": 17.94, "learning_rate": 1.6089016988609594e-06, "loss": 0.8055, "step": 215880 }, { "epoch": 17.94, "learning_rate": 1.6087908433334257e-06, "loss": 0.8072, "step": 215890 }, { "epoch": 17.95, "learning_rate": 1.6086799878058918e-06, "loss": 0.8181, "step": 215900 }, { "epoch": 17.95, "learning_rate": 1.608569132278358e-06, "loss": 0.7455, "step": 215910 }, { "epoch": 17.95, "learning_rate": 1.6084582767508244e-06, "loss": 0.7251, "step": 215920 }, { "epoch": 17.95, "learning_rate": 1.6083474212232907e-06, "loss": 0.8296, "step": 215930 }, { "epoch": 17.95, "learning_rate": 1.6082365656957568e-06, "loss": 0.7645, "step": 215940 }, { "epoch": 17.95, "learning_rate": 1.6081257101682233e-06, "loss": 0.7931, "step": 215950 }, { "epoch": 17.95, "learning_rate": 1.6080148546406896e-06, "loss": 0.7579, "step": 215960 }, { "epoch": 17.95, "learning_rate": 1.6079039991131559e-06, "loss": 0.7482, "step": 215970 }, { "epoch": 17.95, "learning_rate": 1.607793143585622e-06, "loss": 0.8025, "step": 215980 }, { "epoch": 17.95, "learning_rate": 1.6076822880580882e-06, "loss": 0.7545, "step": 215990 }, { "epoch": 17.95, "learning_rate": 1.6075714325305545e-06, "loss": 0.7122, "step": 216000 }, { "epoch": 17.95, "learning_rate": 1.6074605770030208e-06, "loss": 0.8244, "step": 216010 }, { "epoch": 17.96, "learning_rate": 1.607349721475487e-06, "loss": 0.7446, "step": 216020 }, { "epoch": 17.96, "learning_rate": 1.6072388659479532e-06, "loss": 0.7836, "step": 216030 }, { "epoch": 17.96, "learning_rate": 1.6071280104204195e-06, "loss": 0.7909, "step": 216040 }, { "epoch": 17.96, "learning_rate": 1.6070171548928856e-06, "loss": 0.7695, "step": 216050 }, { "epoch": 17.96, "learning_rate": 1.6069062993653519e-06, "loss": 0.8123, "step": 216060 }, { "epoch": 17.96, "learning_rate": 1.6067954438378184e-06, "loss": 0.7618, "step": 216070 }, { "epoch": 17.96, "learning_rate": 1.6066845883102847e-06, "loss": 0.7335, "step": 216080 }, { "epoch": 17.96, "learning_rate": 1.6065737327827508e-06, "loss": 0.7656, "step": 216090 }, { "epoch": 17.96, "learning_rate": 1.606462877255217e-06, "loss": 0.7396, "step": 216100 }, { "epoch": 17.96, "learning_rate": 1.6063520217276834e-06, "loss": 0.7472, "step": 216110 }, { "epoch": 17.96, "learning_rate": 1.6062411662001497e-06, "loss": 0.7788, "step": 216120 }, { "epoch": 17.96, "learning_rate": 1.6061303106726157e-06, "loss": 0.7775, "step": 216130 }, { "epoch": 17.97, "learning_rate": 1.606019455145082e-06, "loss": 0.8581, "step": 216140 }, { "epoch": 17.97, "learning_rate": 1.6059085996175483e-06, "loss": 0.7448, "step": 216150 }, { "epoch": 17.97, "learning_rate": 1.6057977440900146e-06, "loss": 0.7112, "step": 216160 }, { "epoch": 17.97, "learning_rate": 1.6056868885624807e-06, "loss": 0.8085, "step": 216170 }, { "epoch": 17.97, "learning_rate": 1.605576033034947e-06, "loss": 0.7876, "step": 216180 }, { "epoch": 17.97, "learning_rate": 1.6054651775074133e-06, "loss": 0.7745, "step": 216190 }, { "epoch": 17.97, "learning_rate": 1.6053543219798798e-06, "loss": 0.7976, "step": 216200 }, { "epoch": 17.97, "learning_rate": 1.605243466452346e-06, "loss": 0.7389, "step": 216210 }, { "epoch": 17.97, "learning_rate": 1.6051326109248122e-06, "loss": 0.728, "step": 216220 }, { "epoch": 17.97, "learning_rate": 1.6050217553972785e-06, "loss": 0.7322, "step": 216230 }, { "epoch": 17.97, "learning_rate": 1.6049108998697448e-06, "loss": 0.7546, "step": 216240 }, { "epoch": 17.97, "learning_rate": 1.6048000443422109e-06, "loss": 0.7218, "step": 216250 }, { "epoch": 17.98, "learning_rate": 1.6046891888146772e-06, "loss": 0.7499, "step": 216260 }, { "epoch": 17.98, "learning_rate": 1.6045783332871435e-06, "loss": 0.7543, "step": 216270 }, { "epoch": 17.98, "learning_rate": 1.6044674777596098e-06, "loss": 0.8042, "step": 216280 }, { "epoch": 17.98, "learning_rate": 1.6043566222320758e-06, "loss": 0.7811, "step": 216290 }, { "epoch": 17.98, "learning_rate": 1.6042457667045421e-06, "loss": 0.7643, "step": 216300 }, { "epoch": 17.98, "learning_rate": 1.6041349111770084e-06, "loss": 0.7799, "step": 216310 }, { "epoch": 17.98, "learning_rate": 1.604024055649475e-06, "loss": 0.7741, "step": 216320 }, { "epoch": 17.98, "learning_rate": 1.603913200121941e-06, "loss": 0.721, "step": 216330 }, { "epoch": 17.98, "learning_rate": 1.6038023445944073e-06, "loss": 0.8524, "step": 216340 }, { "epoch": 17.98, "learning_rate": 1.6036914890668736e-06, "loss": 0.7284, "step": 216350 }, { "epoch": 17.98, "learning_rate": 1.60358063353934e-06, "loss": 0.7674, "step": 216360 }, { "epoch": 17.98, "learning_rate": 1.603469778011806e-06, "loss": 0.7093, "step": 216370 }, { "epoch": 17.99, "learning_rate": 1.6033589224842723e-06, "loss": 0.7666, "step": 216380 }, { "epoch": 17.99, "learning_rate": 1.6032480669567386e-06, "loss": 0.8039, "step": 216390 }, { "epoch": 17.99, "learning_rate": 1.6031372114292049e-06, "loss": 0.804, "step": 216400 }, { "epoch": 17.99, "learning_rate": 1.603026355901671e-06, "loss": 0.7373, "step": 216410 }, { "epoch": 17.99, "learning_rate": 1.6029155003741372e-06, "loss": 0.7677, "step": 216420 }, { "epoch": 17.99, "learning_rate": 1.6028046448466035e-06, "loss": 0.7824, "step": 216430 }, { "epoch": 17.99, "learning_rate": 1.60269378931907e-06, "loss": 0.8082, "step": 216440 }, { "epoch": 17.99, "learning_rate": 1.6025829337915361e-06, "loss": 0.6858, "step": 216450 }, { "epoch": 17.99, "learning_rate": 1.6024720782640024e-06, "loss": 0.8092, "step": 216460 }, { "epoch": 17.99, "learning_rate": 1.6023612227364687e-06, "loss": 0.7488, "step": 216470 }, { "epoch": 17.99, "learning_rate": 1.602250367208935e-06, "loss": 0.7883, "step": 216480 }, { "epoch": 17.99, "learning_rate": 1.602139511681401e-06, "loss": 0.833, "step": 216490 }, { "epoch": 18.0, "learning_rate": 1.6020286561538674e-06, "loss": 0.7346, "step": 216500 }, { "epoch": 18.0, "learning_rate": 1.6019178006263337e-06, "loss": 0.7272, "step": 216510 }, { "epoch": 18.0, "learning_rate": 1.6018069450987998e-06, "loss": 0.7793, "step": 216520 }, { "epoch": 18.0, "learning_rate": 1.601696089571266e-06, "loss": 0.7497, "step": 216530 }, { "epoch": 18.0, "learning_rate": 1.6015852340437324e-06, "loss": 0.7939, "step": 216540 }, { "epoch": 18.0, "learning_rate": 1.6014743785161987e-06, "loss": 0.6941, "step": 216550 }, { "epoch": 18.0, "eval_loss": 1.1138843297958374, "eval_runtime": 353.9604, "eval_samples_per_second": 7.555, "eval_steps_per_second": 3.777, "eval_wer": 0.6416634882965349, "step": 216558 }, { "epoch": 18.0, "learning_rate": 1.6013635229886647e-06, "loss": 0.7852, "step": 216560 }, { "epoch": 18.0, "learning_rate": 1.6012526674611313e-06, "loss": 0.8102, "step": 216570 }, { "epoch": 18.0, "learning_rate": 1.6011418119335976e-06, "loss": 0.7824, "step": 216580 }, { "epoch": 18.0, "learning_rate": 1.6010309564060638e-06, "loss": 0.69, "step": 216590 }, { "epoch": 18.0, "learning_rate": 1.60092010087853e-06, "loss": 0.821, "step": 216600 }, { "epoch": 18.0, "learning_rate": 1.6008092453509962e-06, "loss": 0.7288, "step": 216610 }, { "epoch": 18.01, "learning_rate": 1.6006983898234625e-06, "loss": 0.8384, "step": 216620 }, { "epoch": 18.01, "learning_rate": 1.6005875342959288e-06, "loss": 0.7371, "step": 216630 }, { "epoch": 18.01, "learning_rate": 1.600476678768395e-06, "loss": 0.7666, "step": 216640 }, { "epoch": 18.01, "learning_rate": 1.6003658232408612e-06, "loss": 0.7535, "step": 216650 }, { "epoch": 18.01, "learning_rate": 1.6002549677133275e-06, "loss": 0.7769, "step": 216660 }, { "epoch": 18.01, "learning_rate": 1.6001441121857938e-06, "loss": 0.776, "step": 216670 }, { "epoch": 18.01, "learning_rate": 1.6000332566582599e-06, "loss": 0.819, "step": 216680 }, { "epoch": 18.01, "learning_rate": 1.5999224011307264e-06, "loss": 0.7654, "step": 216690 }, { "epoch": 18.01, "learning_rate": 1.5998115456031927e-06, "loss": 0.7274, "step": 216700 }, { "epoch": 18.01, "learning_rate": 1.599700690075659e-06, "loss": 0.8034, "step": 216710 }, { "epoch": 18.01, "learning_rate": 1.599589834548125e-06, "loss": 0.8017, "step": 216720 }, { "epoch": 18.01, "learning_rate": 1.5994789790205913e-06, "loss": 0.7252, "step": 216730 }, { "epoch": 18.02, "learning_rate": 1.5993681234930576e-06, "loss": 0.7354, "step": 216740 }, { "epoch": 18.02, "learning_rate": 1.599257267965524e-06, "loss": 0.7875, "step": 216750 }, { "epoch": 18.02, "learning_rate": 1.59914641243799e-06, "loss": 0.7972, "step": 216760 }, { "epoch": 18.02, "learning_rate": 1.5990355569104563e-06, "loss": 0.8071, "step": 216770 }, { "epoch": 18.02, "learning_rate": 1.5989247013829226e-06, "loss": 0.7825, "step": 216780 }, { "epoch": 18.02, "learning_rate": 1.598813845855389e-06, "loss": 0.7662, "step": 216790 }, { "epoch": 18.02, "learning_rate": 1.598702990327855e-06, "loss": 0.7144, "step": 216800 }, { "epoch": 18.02, "learning_rate": 1.5985921348003215e-06, "loss": 0.7574, "step": 216810 }, { "epoch": 18.02, "learning_rate": 1.5984812792727878e-06, "loss": 0.7677, "step": 216820 }, { "epoch": 18.02, "learning_rate": 1.598370423745254e-06, "loss": 0.7597, "step": 216830 }, { "epoch": 18.02, "learning_rate": 1.5982595682177202e-06, "loss": 0.7251, "step": 216840 }, { "epoch": 18.02, "learning_rate": 1.5981487126901865e-06, "loss": 0.7372, "step": 216850 }, { "epoch": 18.03, "learning_rate": 1.5980378571626528e-06, "loss": 0.7947, "step": 216860 }, { "epoch": 18.03, "learning_rate": 1.597927001635119e-06, "loss": 0.8195, "step": 216870 }, { "epoch": 18.03, "learning_rate": 1.5978161461075851e-06, "loss": 0.745, "step": 216880 }, { "epoch": 18.03, "learning_rate": 1.5977052905800514e-06, "loss": 0.7362, "step": 216890 }, { "epoch": 18.03, "learning_rate": 1.5975944350525177e-06, "loss": 0.7445, "step": 216900 }, { "epoch": 18.03, "learning_rate": 1.5974835795249838e-06, "loss": 0.7472, "step": 216910 }, { "epoch": 18.03, "learning_rate": 1.5973727239974501e-06, "loss": 0.7559, "step": 216920 }, { "epoch": 18.03, "learning_rate": 1.5972618684699166e-06, "loss": 0.7333, "step": 216930 }, { "epoch": 18.03, "learning_rate": 1.597151012942383e-06, "loss": 0.6774, "step": 216940 }, { "epoch": 18.03, "learning_rate": 1.597040157414849e-06, "loss": 0.8128, "step": 216950 }, { "epoch": 18.03, "learning_rate": 1.5969293018873153e-06, "loss": 0.7497, "step": 216960 }, { "epoch": 18.03, "learning_rate": 1.5968184463597816e-06, "loss": 0.8237, "step": 216970 }, { "epoch": 18.04, "learning_rate": 1.5967075908322479e-06, "loss": 0.7786, "step": 216980 }, { "epoch": 18.04, "learning_rate": 1.596596735304714e-06, "loss": 0.7043, "step": 216990 }, { "epoch": 18.04, "learning_rate": 1.5964858797771803e-06, "loss": 0.8025, "step": 217000 }, { "epoch": 18.04, "learning_rate": 1.5963750242496466e-06, "loss": 0.7588, "step": 217010 }, { "epoch": 18.04, "learning_rate": 1.5962641687221129e-06, "loss": 0.7707, "step": 217020 }, { "epoch": 18.04, "learning_rate": 1.596153313194579e-06, "loss": 0.7543, "step": 217030 }, { "epoch": 18.04, "learning_rate": 1.5960424576670452e-06, "loss": 0.8073, "step": 217040 }, { "epoch": 18.04, "learning_rate": 1.5959316021395115e-06, "loss": 0.7851, "step": 217050 }, { "epoch": 18.04, "learning_rate": 1.595820746611978e-06, "loss": 0.6985, "step": 217060 }, { "epoch": 18.04, "learning_rate": 1.5957209766371976e-06, "loss": 0.7825, "step": 217070 }, { "epoch": 18.04, "learning_rate": 1.5956101211096637e-06, "loss": 0.696, "step": 217080 }, { "epoch": 18.04, "learning_rate": 1.59549926558213e-06, "loss": 0.7227, "step": 217090 }, { "epoch": 18.05, "learning_rate": 1.5953884100545962e-06, "loss": 0.7586, "step": 217100 }, { "epoch": 18.05, "learning_rate": 1.5952775545270625e-06, "loss": 0.7632, "step": 217110 }, { "epoch": 18.05, "learning_rate": 1.5951666989995286e-06, "loss": 0.7721, "step": 217120 }, { "epoch": 18.05, "learning_rate": 1.595055843471995e-06, "loss": 0.6934, "step": 217130 }, { "epoch": 18.05, "learning_rate": 1.5949449879444614e-06, "loss": 0.7937, "step": 217140 }, { "epoch": 18.05, "learning_rate": 1.5948341324169277e-06, "loss": 0.7915, "step": 217150 }, { "epoch": 18.05, "learning_rate": 1.5947232768893938e-06, "loss": 0.7534, "step": 217160 }, { "epoch": 18.05, "learning_rate": 1.59461242136186e-06, "loss": 0.8051, "step": 217170 }, { "epoch": 18.05, "learning_rate": 1.5945015658343264e-06, "loss": 0.7734, "step": 217180 }, { "epoch": 18.05, "learning_rate": 1.5943907103067927e-06, "loss": 0.7547, "step": 217190 }, { "epoch": 18.05, "learning_rate": 1.5942798547792588e-06, "loss": 0.77, "step": 217200 }, { "epoch": 18.05, "learning_rate": 1.594168999251725e-06, "loss": 0.7158, "step": 217210 }, { "epoch": 18.06, "learning_rate": 1.5940581437241914e-06, "loss": 0.7652, "step": 217220 }, { "epoch": 18.06, "learning_rate": 1.5939472881966577e-06, "loss": 0.7649, "step": 217230 }, { "epoch": 18.06, "learning_rate": 1.5938364326691237e-06, "loss": 0.8098, "step": 217240 }, { "epoch": 18.06, "learning_rate": 1.59372557714159e-06, "loss": 0.7155, "step": 217250 }, { "epoch": 18.06, "learning_rate": 1.5936147216140563e-06, "loss": 0.8521, "step": 217260 }, { "epoch": 18.06, "learning_rate": 1.5935038660865228e-06, "loss": 0.7423, "step": 217270 }, { "epoch": 18.06, "learning_rate": 1.593393010558989e-06, "loss": 0.7766, "step": 217280 }, { "epoch": 18.06, "learning_rate": 1.5932821550314552e-06, "loss": 0.6842, "step": 217290 }, { "epoch": 18.06, "learning_rate": 1.5931712995039215e-06, "loss": 0.7697, "step": 217300 }, { "epoch": 18.06, "learning_rate": 1.5930604439763878e-06, "loss": 0.78, "step": 217310 }, { "epoch": 18.06, "learning_rate": 1.592949588448854e-06, "loss": 0.7893, "step": 217320 }, { "epoch": 18.06, "learning_rate": 1.5928387329213202e-06, "loss": 0.7401, "step": 217330 }, { "epoch": 18.06, "learning_rate": 1.5927278773937865e-06, "loss": 0.7189, "step": 217340 }, { "epoch": 18.07, "learning_rate": 1.5926170218662528e-06, "loss": 0.7569, "step": 217350 }, { "epoch": 18.07, "learning_rate": 1.5925061663387189e-06, "loss": 0.7612, "step": 217360 }, { "epoch": 18.07, "learning_rate": 1.5923953108111852e-06, "loss": 0.7544, "step": 217370 }, { "epoch": 18.07, "learning_rate": 1.5922844552836515e-06, "loss": 0.7623, "step": 217380 }, { "epoch": 18.07, "learning_rate": 1.592173599756118e-06, "loss": 0.7202, "step": 217390 }, { "epoch": 18.07, "learning_rate": 1.592062744228584e-06, "loss": 0.7819, "step": 217400 }, { "epoch": 18.07, "learning_rate": 1.5919518887010503e-06, "loss": 0.7824, "step": 217410 }, { "epoch": 18.07, "learning_rate": 1.5918410331735166e-06, "loss": 0.7491, "step": 217420 }, { "epoch": 18.07, "learning_rate": 1.591730177645983e-06, "loss": 0.7102, "step": 217430 }, { "epoch": 18.07, "learning_rate": 1.591619322118449e-06, "loss": 0.7738, "step": 217440 }, { "epoch": 18.07, "learning_rate": 1.5915084665909153e-06, "loss": 0.7366, "step": 217450 }, { "epoch": 18.07, "learning_rate": 1.5913976110633816e-06, "loss": 0.7461, "step": 217460 }, { "epoch": 18.08, "learning_rate": 1.5912867555358477e-06, "loss": 0.7461, "step": 217470 }, { "epoch": 18.08, "learning_rate": 1.591175900008314e-06, "loss": 0.7135, "step": 217480 }, { "epoch": 18.08, "learning_rate": 1.5910650444807803e-06, "loss": 0.781, "step": 217490 }, { "epoch": 18.08, "learning_rate": 1.5909541889532466e-06, "loss": 0.7117, "step": 217500 }, { "epoch": 18.08, "learning_rate": 1.5908433334257129e-06, "loss": 0.7277, "step": 217510 }, { "epoch": 18.08, "learning_rate": 1.5907324778981792e-06, "loss": 0.8222, "step": 217520 }, { "epoch": 18.08, "learning_rate": 1.5906216223706455e-06, "loss": 0.7998, "step": 217530 }, { "epoch": 18.08, "learning_rate": 1.5905107668431118e-06, "loss": 0.7818, "step": 217540 }, { "epoch": 18.08, "learning_rate": 1.5903999113155778e-06, "loss": 0.7337, "step": 217550 }, { "epoch": 18.08, "learning_rate": 1.5902890557880441e-06, "loss": 0.7831, "step": 217560 }, { "epoch": 18.08, "learning_rate": 1.5901782002605104e-06, "loss": 0.7583, "step": 217570 }, { "epoch": 18.08, "learning_rate": 1.5900673447329767e-06, "loss": 0.7411, "step": 217580 }, { "epoch": 18.09, "learning_rate": 1.5899564892054428e-06, "loss": 0.7261, "step": 217590 }, { "epoch": 18.09, "learning_rate": 1.5898456336779091e-06, "loss": 0.8272, "step": 217600 }, { "epoch": 18.09, "learning_rate": 1.5897347781503754e-06, "loss": 0.8139, "step": 217610 }, { "epoch": 18.09, "learning_rate": 1.5896239226228417e-06, "loss": 0.7388, "step": 217620 }, { "epoch": 18.09, "learning_rate": 1.5895130670953078e-06, "loss": 0.7479, "step": 217630 }, { "epoch": 18.09, "learning_rate": 1.5894022115677743e-06, "loss": 0.7209, "step": 217640 }, { "epoch": 18.09, "learning_rate": 1.5892913560402406e-06, "loss": 0.809, "step": 217650 }, { "epoch": 18.09, "learning_rate": 1.5891805005127069e-06, "loss": 0.7926, "step": 217660 }, { "epoch": 18.09, "learning_rate": 1.589069644985173e-06, "loss": 0.8092, "step": 217670 }, { "epoch": 18.09, "learning_rate": 1.5889587894576393e-06, "loss": 0.7794, "step": 217680 }, { "epoch": 18.09, "learning_rate": 1.5888479339301056e-06, "loss": 0.6698, "step": 217690 }, { "epoch": 18.09, "learning_rate": 1.5887370784025718e-06, "loss": 0.7624, "step": 217700 }, { "epoch": 18.1, "learning_rate": 1.588626222875038e-06, "loss": 0.7953, "step": 217710 }, { "epoch": 18.1, "learning_rate": 1.5885153673475042e-06, "loss": 0.8089, "step": 217720 }, { "epoch": 18.1, "learning_rate": 1.5884045118199705e-06, "loss": 0.7169, "step": 217730 }, { "epoch": 18.1, "learning_rate": 1.5882936562924368e-06, "loss": 0.7547, "step": 217740 }, { "epoch": 18.1, "learning_rate": 1.588182800764903e-06, "loss": 0.7706, "step": 217750 }, { "epoch": 18.1, "learning_rate": 1.5880719452373694e-06, "loss": 0.7612, "step": 217760 }, { "epoch": 18.1, "learning_rate": 1.5879610897098357e-06, "loss": 0.8252, "step": 217770 }, { "epoch": 18.1, "learning_rate": 1.587850234182302e-06, "loss": 0.7951, "step": 217780 }, { "epoch": 18.1, "learning_rate": 1.587739378654768e-06, "loss": 0.7925, "step": 217790 }, { "epoch": 18.1, "learning_rate": 1.5876285231272344e-06, "loss": 0.7485, "step": 217800 }, { "epoch": 18.1, "learning_rate": 1.5875176675997007e-06, "loss": 0.7321, "step": 217810 }, { "epoch": 18.1, "learning_rate": 1.587406812072167e-06, "loss": 0.7516, "step": 217820 }, { "epoch": 18.11, "learning_rate": 1.587295956544633e-06, "loss": 0.7344, "step": 217830 }, { "epoch": 18.11, "learning_rate": 1.5871851010170993e-06, "loss": 0.7734, "step": 217840 }, { "epoch": 18.11, "learning_rate": 1.5870742454895656e-06, "loss": 0.7745, "step": 217850 }, { "epoch": 18.11, "learning_rate": 1.5869633899620317e-06, "loss": 0.7655, "step": 217860 }, { "epoch": 18.11, "learning_rate": 1.586852534434498e-06, "loss": 0.751, "step": 217870 }, { "epoch": 18.11, "learning_rate": 1.5867416789069645e-06, "loss": 0.7362, "step": 217880 }, { "epoch": 18.11, "learning_rate": 1.5866308233794308e-06, "loss": 0.7519, "step": 217890 }, { "epoch": 18.11, "learning_rate": 1.586519967851897e-06, "loss": 0.7805, "step": 217900 }, { "epoch": 18.11, "learning_rate": 1.5864091123243632e-06, "loss": 0.7095, "step": 217910 }, { "epoch": 18.11, "learning_rate": 1.5862982567968295e-06, "loss": 0.7476, "step": 217920 }, { "epoch": 18.11, "learning_rate": 1.5861874012692958e-06, "loss": 0.7802, "step": 217930 }, { "epoch": 18.11, "learning_rate": 1.5860765457417619e-06, "loss": 0.7488, "step": 217940 }, { "epoch": 18.12, "learning_rate": 1.5859656902142282e-06, "loss": 0.7273, "step": 217950 }, { "epoch": 18.12, "learning_rate": 1.5858548346866945e-06, "loss": 0.7546, "step": 217960 }, { "epoch": 18.12, "learning_rate": 1.5857439791591608e-06, "loss": 0.7405, "step": 217970 }, { "epoch": 18.12, "learning_rate": 1.5856331236316268e-06, "loss": 0.7591, "step": 217980 }, { "epoch": 18.12, "learning_rate": 1.5855222681040931e-06, "loss": 0.7692, "step": 217990 }, { "epoch": 18.12, "learning_rate": 1.5854114125765597e-06, "loss": 0.7618, "step": 218000 }, { "epoch": 18.12, "learning_rate": 1.585300557049026e-06, "loss": 0.7694, "step": 218010 }, { "epoch": 18.12, "learning_rate": 1.585189701521492e-06, "loss": 0.7835, "step": 218020 }, { "epoch": 18.12, "learning_rate": 1.5850788459939583e-06, "loss": 0.7845, "step": 218030 }, { "epoch": 18.12, "learning_rate": 1.5849679904664246e-06, "loss": 0.7655, "step": 218040 }, { "epoch": 18.12, "learning_rate": 1.584857134938891e-06, "loss": 0.7625, "step": 218050 }, { "epoch": 18.12, "learning_rate": 1.584746279411357e-06, "loss": 0.7766, "step": 218060 }, { "epoch": 18.13, "learning_rate": 1.5846354238838233e-06, "loss": 0.831, "step": 218070 }, { "epoch": 18.13, "learning_rate": 1.5845245683562896e-06, "loss": 0.7613, "step": 218080 }, { "epoch": 18.13, "learning_rate": 1.5844137128287559e-06, "loss": 0.745, "step": 218090 }, { "epoch": 18.13, "learning_rate": 1.584302857301222e-06, "loss": 0.7681, "step": 218100 }, { "epoch": 18.13, "learning_rate": 1.5841920017736883e-06, "loss": 0.7658, "step": 218110 }, { "epoch": 18.13, "learning_rate": 1.5840811462461546e-06, "loss": 0.7474, "step": 218120 }, { "epoch": 18.13, "learning_rate": 1.583970290718621e-06, "loss": 0.752, "step": 218130 }, { "epoch": 18.13, "learning_rate": 1.5838594351910872e-06, "loss": 0.7075, "step": 218140 }, { "epoch": 18.13, "learning_rate": 1.5837485796635534e-06, "loss": 0.73, "step": 218150 }, { "epoch": 18.13, "learning_rate": 1.5836377241360197e-06, "loss": 0.7835, "step": 218160 }, { "epoch": 18.13, "learning_rate": 1.583526868608486e-06, "loss": 0.8073, "step": 218170 }, { "epoch": 18.13, "learning_rate": 1.5834160130809521e-06, "loss": 0.7985, "step": 218180 }, { "epoch": 18.14, "learning_rate": 1.5833051575534184e-06, "loss": 0.7499, "step": 218190 }, { "epoch": 18.14, "learning_rate": 1.5831943020258847e-06, "loss": 0.7246, "step": 218200 }, { "epoch": 18.14, "learning_rate": 1.583083446498351e-06, "loss": 0.735, "step": 218210 }, { "epoch": 18.14, "learning_rate": 1.582972590970817e-06, "loss": 0.8412, "step": 218220 }, { "epoch": 18.14, "learning_rate": 1.5828617354432834e-06, "loss": 0.7459, "step": 218230 }, { "epoch": 18.14, "learning_rate": 1.5827508799157497e-06, "loss": 0.7849, "step": 218240 }, { "epoch": 18.14, "learning_rate": 1.5826400243882162e-06, "loss": 0.7695, "step": 218250 }, { "epoch": 18.14, "learning_rate": 1.5825291688606823e-06, "loss": 0.767, "step": 218260 }, { "epoch": 18.14, "learning_rate": 1.5824183133331486e-06, "loss": 0.8558, "step": 218270 }, { "epoch": 18.14, "learning_rate": 1.5823074578056149e-06, "loss": 0.7371, "step": 218280 }, { "epoch": 18.14, "learning_rate": 1.582196602278081e-06, "loss": 0.7647, "step": 218290 }, { "epoch": 18.14, "learning_rate": 1.5820857467505472e-06, "loss": 0.772, "step": 218300 }, { "epoch": 18.15, "learning_rate": 1.5819748912230135e-06, "loss": 0.8387, "step": 218310 }, { "epoch": 18.15, "learning_rate": 1.5818640356954798e-06, "loss": 0.722, "step": 218320 }, { "epoch": 18.15, "learning_rate": 1.581753180167946e-06, "loss": 0.739, "step": 218330 }, { "epoch": 18.15, "learning_rate": 1.5816423246404122e-06, "loss": 0.7406, "step": 218340 }, { "epoch": 18.15, "learning_rate": 1.5815314691128785e-06, "loss": 0.759, "step": 218350 }, { "epoch": 18.15, "learning_rate": 1.5814206135853448e-06, "loss": 0.7522, "step": 218360 }, { "epoch": 18.15, "learning_rate": 1.581309758057811e-06, "loss": 0.7876, "step": 218370 }, { "epoch": 18.15, "learning_rate": 1.5811989025302774e-06, "loss": 0.8253, "step": 218380 }, { "epoch": 18.15, "learning_rate": 1.5810880470027437e-06, "loss": 0.7311, "step": 218390 }, { "epoch": 18.15, "learning_rate": 1.58097719147521e-06, "loss": 0.7308, "step": 218400 }, { "epoch": 18.15, "learning_rate": 1.580866335947676e-06, "loss": 0.8172, "step": 218410 }, { "epoch": 18.15, "learning_rate": 1.5807554804201424e-06, "loss": 0.7775, "step": 218420 }, { "epoch": 18.16, "learning_rate": 1.5806446248926087e-06, "loss": 0.7733, "step": 218430 }, { "epoch": 18.16, "learning_rate": 1.580533769365075e-06, "loss": 0.6953, "step": 218440 }, { "epoch": 18.16, "learning_rate": 1.580422913837541e-06, "loss": 0.7409, "step": 218450 }, { "epoch": 18.16, "learning_rate": 1.5803120583100073e-06, "loss": 0.7404, "step": 218460 }, { "epoch": 18.16, "learning_rate": 1.5802012027824736e-06, "loss": 0.768, "step": 218470 }, { "epoch": 18.16, "learning_rate": 1.58009034725494e-06, "loss": 0.8051, "step": 218480 }, { "epoch": 18.16, "learning_rate": 1.579979491727406e-06, "loss": 0.7793, "step": 218490 }, { "epoch": 18.16, "learning_rate": 1.5798686361998725e-06, "loss": 0.824, "step": 218500 }, { "epoch": 18.16, "learning_rate": 1.5797577806723388e-06, "loss": 0.8047, "step": 218510 }, { "epoch": 18.16, "learning_rate": 1.579646925144805e-06, "loss": 0.7905, "step": 218520 }, { "epoch": 18.16, "learning_rate": 1.5795360696172712e-06, "loss": 0.7763, "step": 218530 }, { "epoch": 18.16, "learning_rate": 1.5794252140897375e-06, "loss": 0.7709, "step": 218540 }, { "epoch": 18.17, "learning_rate": 1.5793143585622038e-06, "loss": 0.7521, "step": 218550 }, { "epoch": 18.17, "learning_rate": 1.57920350303467e-06, "loss": 0.8069, "step": 218560 }, { "epoch": 18.17, "learning_rate": 1.5790926475071362e-06, "loss": 0.8065, "step": 218570 }, { "epoch": 18.17, "learning_rate": 1.5789817919796025e-06, "loss": 0.7937, "step": 218580 }, { "epoch": 18.17, "learning_rate": 1.5788709364520687e-06, "loss": 0.7274, "step": 218590 }, { "epoch": 18.17, "learning_rate": 1.578760080924535e-06, "loss": 0.764, "step": 218600 }, { "epoch": 18.17, "learning_rate": 1.5786492253970011e-06, "loss": 0.8614, "step": 218610 }, { "epoch": 18.17, "learning_rate": 1.5785383698694676e-06, "loss": 0.7364, "step": 218620 }, { "epoch": 18.17, "learning_rate": 1.5784385998946872e-06, "loss": 0.775, "step": 218630 }, { "epoch": 18.17, "learning_rate": 1.5783277443671535e-06, "loss": 0.6707, "step": 218640 }, { "epoch": 18.17, "learning_rate": 1.5782168888396198e-06, "loss": 0.7262, "step": 218650 }, { "epoch": 18.17, "learning_rate": 1.5781060333120858e-06, "loss": 0.8155, "step": 218660 }, { "epoch": 18.18, "learning_rate": 1.5779951777845521e-06, "loss": 0.8001, "step": 218670 }, { "epoch": 18.18, "learning_rate": 1.5778843222570184e-06, "loss": 0.7327, "step": 218680 }, { "epoch": 18.18, "learning_rate": 1.5777734667294847e-06, "loss": 0.7787, "step": 218690 }, { "epoch": 18.18, "learning_rate": 1.5776626112019508e-06, "loss": 0.8054, "step": 218700 }, { "epoch": 18.18, "learning_rate": 1.5775517556744173e-06, "loss": 0.7356, "step": 218710 }, { "epoch": 18.18, "learning_rate": 1.5774409001468836e-06, "loss": 0.805, "step": 218720 }, { "epoch": 18.18, "learning_rate": 1.57733004461935e-06, "loss": 0.7189, "step": 218730 }, { "epoch": 18.18, "learning_rate": 1.577219189091816e-06, "loss": 0.7228, "step": 218740 }, { "epoch": 18.18, "learning_rate": 1.5771083335642823e-06, "loss": 0.7454, "step": 218750 }, { "epoch": 18.18, "learning_rate": 1.5769974780367486e-06, "loss": 0.7464, "step": 218760 }, { "epoch": 18.18, "learning_rate": 1.5768866225092149e-06, "loss": 0.8329, "step": 218770 }, { "epoch": 18.18, "learning_rate": 1.576775766981681e-06, "loss": 0.7968, "step": 218780 }, { "epoch": 18.19, "learning_rate": 1.5766649114541473e-06, "loss": 0.7706, "step": 218790 }, { "epoch": 18.19, "learning_rate": 1.5765540559266136e-06, "loss": 0.7577, "step": 218800 }, { "epoch": 18.19, "learning_rate": 1.5764432003990796e-06, "loss": 0.7594, "step": 218810 }, { "epoch": 18.19, "learning_rate": 1.576332344871546e-06, "loss": 0.8547, "step": 218820 }, { "epoch": 18.19, "learning_rate": 1.5762214893440124e-06, "loss": 0.7455, "step": 218830 }, { "epoch": 18.19, "learning_rate": 1.5761106338164787e-06, "loss": 0.7577, "step": 218840 }, { "epoch": 18.19, "learning_rate": 1.5759997782889448e-06, "loss": 0.6763, "step": 218850 }, { "epoch": 18.19, "learning_rate": 1.5758889227614111e-06, "loss": 0.7535, "step": 218860 }, { "epoch": 18.19, "learning_rate": 1.5757780672338774e-06, "loss": 0.7941, "step": 218870 }, { "epoch": 18.19, "learning_rate": 1.5756672117063437e-06, "loss": 0.7434, "step": 218880 }, { "epoch": 18.19, "learning_rate": 1.5755563561788098e-06, "loss": 0.7199, "step": 218890 }, { "epoch": 18.19, "learning_rate": 1.575445500651276e-06, "loss": 0.8005, "step": 218900 }, { "epoch": 18.2, "learning_rate": 1.5753346451237424e-06, "loss": 0.7919, "step": 218910 }, { "epoch": 18.2, "learning_rate": 1.5752237895962087e-06, "loss": 0.8054, "step": 218920 }, { "epoch": 18.2, "learning_rate": 1.5751129340686748e-06, "loss": 0.6484, "step": 218930 }, { "epoch": 18.2, "learning_rate": 1.575002078541141e-06, "loss": 0.7506, "step": 218940 }, { "epoch": 18.2, "learning_rate": 1.5748912230136076e-06, "loss": 0.7288, "step": 218950 }, { "epoch": 18.2, "learning_rate": 1.5747803674860739e-06, "loss": 0.75, "step": 218960 }, { "epoch": 18.2, "learning_rate": 1.57466951195854e-06, "loss": 0.7877, "step": 218970 }, { "epoch": 18.2, "learning_rate": 1.5745586564310062e-06, "loss": 0.7382, "step": 218980 }, { "epoch": 18.2, "learning_rate": 1.5744478009034725e-06, "loss": 0.7586, "step": 218990 }, { "epoch": 18.2, "learning_rate": 1.5743369453759388e-06, "loss": 0.7844, "step": 219000 }, { "epoch": 18.2, "learning_rate": 1.574226089848405e-06, "loss": 0.8053, "step": 219010 }, { "epoch": 18.2, "learning_rate": 1.5741152343208712e-06, "loss": 0.8123, "step": 219020 }, { "epoch": 18.21, "learning_rate": 1.5740043787933375e-06, "loss": 0.7936, "step": 219030 }, { "epoch": 18.21, "learning_rate": 1.5738935232658038e-06, "loss": 0.762, "step": 219040 }, { "epoch": 18.21, "learning_rate": 1.5737826677382699e-06, "loss": 0.7447, "step": 219050 }, { "epoch": 18.21, "learning_rate": 1.5736718122107362e-06, "loss": 0.759, "step": 219060 }, { "epoch": 18.21, "learning_rate": 1.5735609566832025e-06, "loss": 0.832, "step": 219070 }, { "epoch": 18.21, "learning_rate": 1.573450101155669e-06, "loss": 0.7828, "step": 219080 }, { "epoch": 18.21, "learning_rate": 1.573339245628135e-06, "loss": 0.7418, "step": 219090 }, { "epoch": 18.21, "learning_rate": 1.5732283901006014e-06, "loss": 0.7433, "step": 219100 }, { "epoch": 18.21, "learning_rate": 1.5731175345730677e-06, "loss": 0.8081, "step": 219110 }, { "epoch": 18.21, "learning_rate": 1.573006679045534e-06, "loss": 0.7883, "step": 219120 }, { "epoch": 18.21, "learning_rate": 1.572895823518e-06, "loss": 0.756, "step": 219130 }, { "epoch": 18.21, "learning_rate": 1.5727849679904663e-06, "loss": 0.8045, "step": 219140 }, { "epoch": 18.22, "learning_rate": 1.5726741124629326e-06, "loss": 0.7252, "step": 219150 }, { "epoch": 18.22, "learning_rate": 1.572563256935399e-06, "loss": 0.7789, "step": 219160 }, { "epoch": 18.22, "learning_rate": 1.572452401407865e-06, "loss": 0.7591, "step": 219170 }, { "epoch": 18.22, "learning_rate": 1.5723415458803313e-06, "loss": 0.7415, "step": 219180 }, { "epoch": 18.22, "learning_rate": 1.5722306903527976e-06, "loss": 0.6997, "step": 219190 }, { "epoch": 18.22, "learning_rate": 1.572119834825264e-06, "loss": 0.7126, "step": 219200 }, { "epoch": 18.22, "learning_rate": 1.5720089792977302e-06, "loss": 0.724, "step": 219210 }, { "epoch": 18.22, "learning_rate": 1.5718981237701965e-06, "loss": 0.7821, "step": 219220 }, { "epoch": 18.22, "learning_rate": 1.5717872682426628e-06, "loss": 0.7531, "step": 219230 }, { "epoch": 18.22, "learning_rate": 1.5716764127151289e-06, "loss": 0.7736, "step": 219240 }, { "epoch": 18.22, "learning_rate": 1.5715655571875952e-06, "loss": 0.7627, "step": 219250 }, { "epoch": 18.22, "learning_rate": 1.5714547016600614e-06, "loss": 0.8079, "step": 219260 }, { "epoch": 18.23, "learning_rate": 1.5713438461325277e-06, "loss": 0.7854, "step": 219270 }, { "epoch": 18.23, "learning_rate": 1.5712329906049938e-06, "loss": 0.7968, "step": 219280 }, { "epoch": 18.23, "learning_rate": 1.5711221350774601e-06, "loss": 0.7605, "step": 219290 }, { "epoch": 18.23, "learning_rate": 1.5710112795499264e-06, "loss": 0.7331, "step": 219300 }, { "epoch": 18.23, "learning_rate": 1.5709004240223927e-06, "loss": 0.7731, "step": 219310 }, { "epoch": 18.23, "learning_rate": 1.570789568494859e-06, "loss": 0.8137, "step": 219320 }, { "epoch": 18.23, "learning_rate": 1.5706787129673253e-06, "loss": 0.764, "step": 219330 }, { "epoch": 18.23, "learning_rate": 1.5705678574397916e-06, "loss": 0.7415, "step": 219340 }, { "epoch": 18.23, "learning_rate": 1.570457001912258e-06, "loss": 0.7863, "step": 219350 }, { "epoch": 18.23, "learning_rate": 1.570346146384724e-06, "loss": 0.7291, "step": 219360 }, { "epoch": 18.23, "learning_rate": 1.5702352908571903e-06, "loss": 0.7786, "step": 219370 }, { "epoch": 18.23, "learning_rate": 1.5701244353296566e-06, "loss": 0.7299, "step": 219380 }, { "epoch": 18.24, "learning_rate": 1.5700135798021229e-06, "loss": 0.8096, "step": 219390 }, { "epoch": 18.24, "learning_rate": 1.569902724274589e-06, "loss": 0.72, "step": 219400 }, { "epoch": 18.24, "learning_rate": 1.5697918687470552e-06, "loss": 0.7574, "step": 219410 }, { "epoch": 18.24, "learning_rate": 1.5696810132195215e-06, "loss": 0.7986, "step": 219420 }, { "epoch": 18.24, "learning_rate": 1.5695701576919878e-06, "loss": 0.8207, "step": 219430 }, { "epoch": 18.24, "learning_rate": 1.5694593021644541e-06, "loss": 0.7592, "step": 219440 }, { "epoch": 18.24, "learning_rate": 1.5693484466369204e-06, "loss": 0.74, "step": 219450 }, { "epoch": 18.24, "learning_rate": 1.5692375911093867e-06, "loss": 0.7242, "step": 219460 }, { "epoch": 18.24, "learning_rate": 1.569126735581853e-06, "loss": 0.7845, "step": 219470 }, { "epoch": 18.24, "learning_rate": 1.569015880054319e-06, "loss": 0.7411, "step": 219480 }, { "epoch": 18.24, "learning_rate": 1.5689050245267854e-06, "loss": 0.7369, "step": 219490 }, { "epoch": 18.24, "learning_rate": 1.5687941689992517e-06, "loss": 0.7347, "step": 219500 }, { "epoch": 18.25, "learning_rate": 1.568683313471718e-06, "loss": 0.7506, "step": 219510 }, { "epoch": 18.25, "learning_rate": 1.568572457944184e-06, "loss": 0.7634, "step": 219520 }, { "epoch": 18.25, "learning_rate": 1.5684616024166504e-06, "loss": 0.727, "step": 219530 }, { "epoch": 18.25, "learning_rate": 1.5683507468891167e-06, "loss": 0.8153, "step": 219540 }, { "epoch": 18.25, "learning_rate": 1.568239891361583e-06, "loss": 0.7068, "step": 219550 }, { "epoch": 18.25, "learning_rate": 1.568129035834049e-06, "loss": 0.7662, "step": 219560 }, { "epoch": 18.25, "learning_rate": 1.5680181803065155e-06, "loss": 0.8444, "step": 219570 }, { "epoch": 18.25, "learning_rate": 1.5679073247789818e-06, "loss": 0.7748, "step": 219580 }, { "epoch": 18.25, "learning_rate": 1.5677964692514481e-06, "loss": 0.7167, "step": 219590 }, { "epoch": 18.25, "learning_rate": 1.5676856137239142e-06, "loss": 0.6905, "step": 219600 }, { "epoch": 18.25, "learning_rate": 1.5675747581963805e-06, "loss": 0.7568, "step": 219610 }, { "epoch": 18.25, "learning_rate": 1.5674639026688468e-06, "loss": 0.7585, "step": 219620 }, { "epoch": 18.26, "learning_rate": 1.567353047141313e-06, "loss": 0.7071, "step": 219630 }, { "epoch": 18.26, "learning_rate": 1.5672421916137792e-06, "loss": 0.7839, "step": 219640 }, { "epoch": 18.26, "learning_rate": 1.5671313360862455e-06, "loss": 0.7392, "step": 219650 }, { "epoch": 18.26, "learning_rate": 1.5670204805587118e-06, "loss": 0.802, "step": 219660 }, { "epoch": 18.26, "learning_rate": 1.5669096250311779e-06, "loss": 0.7684, "step": 219670 }, { "epoch": 18.26, "learning_rate": 1.5667987695036442e-06, "loss": 0.7453, "step": 219680 }, { "epoch": 18.26, "learning_rate": 1.5666879139761107e-06, "loss": 0.7384, "step": 219690 }, { "epoch": 18.26, "learning_rate": 1.566577058448577e-06, "loss": 0.6852, "step": 219700 }, { "epoch": 18.26, "learning_rate": 1.566466202921043e-06, "loss": 0.7184, "step": 219710 }, { "epoch": 18.26, "learning_rate": 1.5663553473935093e-06, "loss": 0.7473, "step": 219720 }, { "epoch": 18.26, "learning_rate": 1.5662444918659756e-06, "loss": 0.7417, "step": 219730 }, { "epoch": 18.26, "learning_rate": 1.566133636338442e-06, "loss": 0.7127, "step": 219740 }, { "epoch": 18.27, "learning_rate": 1.566022780810908e-06, "loss": 0.7276, "step": 219750 }, { "epoch": 18.27, "learning_rate": 1.5659119252833743e-06, "loss": 0.7826, "step": 219760 }, { "epoch": 18.27, "learning_rate": 1.5658010697558406e-06, "loss": 0.7652, "step": 219770 }, { "epoch": 18.27, "learning_rate": 1.565690214228307e-06, "loss": 0.7883, "step": 219780 }, { "epoch": 18.27, "learning_rate": 1.565579358700773e-06, "loss": 0.7137, "step": 219790 }, { "epoch": 18.27, "learning_rate": 1.5654685031732393e-06, "loss": 0.7412, "step": 219800 }, { "epoch": 18.27, "learning_rate": 1.5653576476457058e-06, "loss": 0.7276, "step": 219810 }, { "epoch": 18.27, "learning_rate": 1.565246792118172e-06, "loss": 0.8092, "step": 219820 }, { "epoch": 18.27, "learning_rate": 1.5651359365906382e-06, "loss": 0.7605, "step": 219830 }, { "epoch": 18.27, "learning_rate": 1.5650250810631045e-06, "loss": 0.7985, "step": 219840 }, { "epoch": 18.27, "learning_rate": 1.5649142255355708e-06, "loss": 0.7252, "step": 219850 }, { "epoch": 18.27, "learning_rate": 1.564803370008037e-06, "loss": 0.7615, "step": 219860 }, { "epoch": 18.28, "learning_rate": 1.5646925144805031e-06, "loss": 0.7633, "step": 219870 }, { "epoch": 18.28, "learning_rate": 1.5645816589529694e-06, "loss": 0.7961, "step": 219880 }, { "epoch": 18.28, "learning_rate": 1.5644708034254357e-06, "loss": 0.783, "step": 219890 }, { "epoch": 18.28, "learning_rate": 1.564359947897902e-06, "loss": 0.7584, "step": 219900 }, { "epoch": 18.28, "learning_rate": 1.564249092370368e-06, "loss": 0.787, "step": 219910 }, { "epoch": 18.28, "learning_rate": 1.5641382368428344e-06, "loss": 0.8294, "step": 219920 }, { "epoch": 18.28, "learning_rate": 1.5640273813153007e-06, "loss": 0.7613, "step": 219930 }, { "epoch": 18.28, "learning_rate": 1.5639165257877672e-06, "loss": 0.8002, "step": 219940 }, { "epoch": 18.28, "learning_rate": 1.5638056702602333e-06, "loss": 0.6697, "step": 219950 }, { "epoch": 18.28, "learning_rate": 1.5636948147326996e-06, "loss": 0.7889, "step": 219960 }, { "epoch": 18.28, "learning_rate": 1.5635839592051659e-06, "loss": 0.8357, "step": 219970 }, { "epoch": 18.28, "learning_rate": 1.5634731036776322e-06, "loss": 0.7291, "step": 219980 }, { "epoch": 18.29, "learning_rate": 1.5633622481500983e-06, "loss": 0.7425, "step": 219990 }, { "epoch": 18.29, "learning_rate": 1.5632513926225646e-06, "loss": 0.769, "step": 220000 }, { "epoch": 18.29, "learning_rate": 1.5631405370950308e-06, "loss": 0.7833, "step": 220010 }, { "epoch": 18.29, "learning_rate": 1.5630296815674971e-06, "loss": 0.7698, "step": 220020 }, { "epoch": 18.29, "learning_rate": 1.5629188260399632e-06, "loss": 0.7985, "step": 220030 }, { "epoch": 18.29, "learning_rate": 1.5628079705124295e-06, "loss": 0.7688, "step": 220040 }, { "epoch": 18.29, "learning_rate": 1.5626971149848958e-06, "loss": 0.7642, "step": 220050 }, { "epoch": 18.29, "learning_rate": 1.5625862594573623e-06, "loss": 0.7654, "step": 220060 }, { "epoch": 18.29, "learning_rate": 1.5624754039298284e-06, "loss": 0.8113, "step": 220070 }, { "epoch": 18.29, "learning_rate": 1.5623645484022947e-06, "loss": 0.701, "step": 220080 }, { "epoch": 18.29, "learning_rate": 1.562253692874761e-06, "loss": 0.7523, "step": 220090 }, { "epoch": 18.29, "learning_rate": 1.562142837347227e-06, "loss": 0.7706, "step": 220100 }, { "epoch": 18.3, "learning_rate": 1.5620319818196934e-06, "loss": 0.7678, "step": 220110 }, { "epoch": 18.3, "learning_rate": 1.5619211262921597e-06, "loss": 0.7561, "step": 220120 }, { "epoch": 18.3, "learning_rate": 1.561810270764626e-06, "loss": 0.739, "step": 220130 }, { "epoch": 18.3, "learning_rate": 1.561699415237092e-06, "loss": 0.7198, "step": 220140 }, { "epoch": 18.3, "learning_rate": 1.5615885597095583e-06, "loss": 0.6828, "step": 220150 }, { "epoch": 18.3, "learning_rate": 1.5614777041820246e-06, "loss": 0.7875, "step": 220160 }, { "epoch": 18.3, "learning_rate": 1.561366848654491e-06, "loss": 0.7406, "step": 220170 }, { "epoch": 18.3, "learning_rate": 1.5612559931269572e-06, "loss": 0.8235, "step": 220180 }, { "epoch": 18.3, "learning_rate": 1.5611451375994235e-06, "loss": 0.7305, "step": 220190 }, { "epoch": 18.3, "learning_rate": 1.5610342820718898e-06, "loss": 0.7588, "step": 220200 }, { "epoch": 18.3, "learning_rate": 1.5609234265443561e-06, "loss": 0.789, "step": 220210 }, { "epoch": 18.3, "learning_rate": 1.5608125710168222e-06, "loss": 0.8329, "step": 220220 }, { "epoch": 18.31, "learning_rate": 1.5607017154892885e-06, "loss": 0.7582, "step": 220230 }, { "epoch": 18.31, "learning_rate": 1.5605908599617548e-06, "loss": 0.7527, "step": 220240 }, { "epoch": 18.31, "learning_rate": 1.560480004434221e-06, "loss": 0.7365, "step": 220250 }, { "epoch": 18.31, "learning_rate": 1.5603691489066872e-06, "loss": 0.8114, "step": 220260 }, { "epoch": 18.31, "learning_rate": 1.5602582933791535e-06, "loss": 0.7729, "step": 220270 }, { "epoch": 18.31, "learning_rate": 1.5601474378516198e-06, "loss": 0.7994, "step": 220280 }, { "epoch": 18.31, "learning_rate": 1.560036582324086e-06, "loss": 0.8229, "step": 220290 }, { "epoch": 18.31, "learning_rate": 1.5599257267965524e-06, "loss": 0.7365, "step": 220300 }, { "epoch": 18.31, "learning_rate": 1.5598148712690186e-06, "loss": 0.782, "step": 220310 }, { "epoch": 18.31, "learning_rate": 1.559704015741485e-06, "loss": 0.7417, "step": 220320 }, { "epoch": 18.31, "learning_rate": 1.5595931602139512e-06, "loss": 0.7698, "step": 220330 }, { "epoch": 18.31, "learning_rate": 1.5594823046864173e-06, "loss": 0.7072, "step": 220340 }, { "epoch": 18.32, "learning_rate": 1.5593714491588836e-06, "loss": 0.7395, "step": 220350 }, { "epoch": 18.32, "learning_rate": 1.55926059363135e-06, "loss": 0.8232, "step": 220360 }, { "epoch": 18.32, "learning_rate": 1.5591497381038162e-06, "loss": 0.8355, "step": 220370 }, { "epoch": 18.32, "learning_rate": 1.5590388825762823e-06, "loss": 0.7071, "step": 220380 }, { "epoch": 18.32, "learning_rate": 1.5589280270487486e-06, "loss": 0.7806, "step": 220390 }, { "epoch": 18.32, "learning_rate": 1.5588171715212149e-06, "loss": 0.7884, "step": 220400 }, { "epoch": 18.32, "learning_rate": 1.5587063159936812e-06, "loss": 0.7569, "step": 220410 }, { "epoch": 18.32, "learning_rate": 1.5585954604661473e-06, "loss": 0.7542, "step": 220420 }, { "epoch": 18.32, "learning_rate": 1.5584846049386138e-06, "loss": 0.7496, "step": 220430 }, { "epoch": 18.32, "learning_rate": 1.55837374941108e-06, "loss": 0.7379, "step": 220440 }, { "epoch": 18.32, "learning_rate": 1.5582628938835464e-06, "loss": 0.7573, "step": 220450 }, { "epoch": 18.32, "learning_rate": 1.5581520383560124e-06, "loss": 0.8312, "step": 220460 }, { "epoch": 18.33, "learning_rate": 1.5580411828284787e-06, "loss": 0.7831, "step": 220470 }, { "epoch": 18.33, "learning_rate": 1.557930327300945e-06, "loss": 0.7061, "step": 220480 }, { "epoch": 18.33, "learning_rate": 1.5578194717734111e-06, "loss": 0.7498, "step": 220490 }, { "epoch": 18.33, "learning_rate": 1.5577086162458774e-06, "loss": 0.7219, "step": 220500 }, { "epoch": 18.33, "learning_rate": 1.5575977607183437e-06, "loss": 0.7687, "step": 220510 }, { "epoch": 18.33, "learning_rate": 1.55748690519081e-06, "loss": 0.6735, "step": 220520 }, { "epoch": 18.33, "learning_rate": 1.557376049663276e-06, "loss": 0.7408, "step": 220530 }, { "epoch": 18.33, "learning_rate": 1.5572651941357424e-06, "loss": 0.768, "step": 220540 }, { "epoch": 18.33, "learning_rate": 1.5571543386082089e-06, "loss": 0.7629, "step": 220550 }, { "epoch": 18.33, "learning_rate": 1.5570434830806752e-06, "loss": 0.7603, "step": 220560 }, { "epoch": 18.33, "learning_rate": 1.5569326275531413e-06, "loss": 0.7686, "step": 220570 }, { "epoch": 18.33, "learning_rate": 1.5568217720256076e-06, "loss": 0.7217, "step": 220580 }, { "epoch": 18.34, "learning_rate": 1.5567109164980739e-06, "loss": 0.7523, "step": 220590 }, { "epoch": 18.34, "learning_rate": 1.5566000609705402e-06, "loss": 0.7698, "step": 220600 }, { "epoch": 18.34, "learning_rate": 1.5564892054430062e-06, "loss": 0.7859, "step": 220610 }, { "epoch": 18.34, "learning_rate": 1.5563783499154725e-06, "loss": 0.8032, "step": 220620 }, { "epoch": 18.34, "learning_rate": 1.5562674943879388e-06, "loss": 0.7791, "step": 220630 }, { "epoch": 18.34, "learning_rate": 1.5561566388604051e-06, "loss": 0.7316, "step": 220640 }, { "epoch": 18.34, "learning_rate": 1.5560457833328712e-06, "loss": 0.7565, "step": 220650 }, { "epoch": 18.34, "learning_rate": 1.5559349278053375e-06, "loss": 0.7486, "step": 220660 }, { "epoch": 18.34, "learning_rate": 1.555824072277804e-06, "loss": 0.7996, "step": 220670 }, { "epoch": 18.34, "learning_rate": 1.5557132167502703e-06, "loss": 0.7862, "step": 220680 }, { "epoch": 18.34, "learning_rate": 1.5556023612227364e-06, "loss": 0.7286, "step": 220690 }, { "epoch": 18.34, "learning_rate": 1.5554915056952027e-06, "loss": 0.7497, "step": 220700 }, { "epoch": 18.35, "learning_rate": 1.555380650167669e-06, "loss": 0.7729, "step": 220710 }, { "epoch": 18.35, "learning_rate": 1.5552697946401353e-06, "loss": 0.8098, "step": 220720 }, { "epoch": 18.35, "learning_rate": 1.5551589391126014e-06, "loss": 0.7574, "step": 220730 }, { "epoch": 18.35, "learning_rate": 1.5550480835850677e-06, "loss": 0.8203, "step": 220740 }, { "epoch": 18.35, "learning_rate": 1.554937228057534e-06, "loss": 0.6976, "step": 220750 }, { "epoch": 18.35, "learning_rate": 1.5548263725300002e-06, "loss": 0.8138, "step": 220760 }, { "epoch": 18.35, "learning_rate": 1.5547155170024663e-06, "loss": 0.7063, "step": 220770 }, { "epoch": 18.35, "learning_rate": 1.5546046614749326e-06, "loss": 0.7459, "step": 220780 }, { "epoch": 18.35, "learning_rate": 1.554493805947399e-06, "loss": 0.7657, "step": 220790 }, { "epoch": 18.35, "learning_rate": 1.5543829504198654e-06, "loss": 0.7254, "step": 220800 }, { "epoch": 18.35, "learning_rate": 1.5542720948923315e-06, "loss": 0.7486, "step": 220810 }, { "epoch": 18.35, "learning_rate": 1.5541612393647978e-06, "loss": 0.7974, "step": 220820 }, { "epoch": 18.36, "learning_rate": 1.554050383837264e-06, "loss": 0.7502, "step": 220830 }, { "epoch": 18.36, "learning_rate": 1.5539395283097304e-06, "loss": 0.7812, "step": 220840 }, { "epoch": 18.36, "learning_rate": 1.5538286727821965e-06, "loss": 0.7408, "step": 220850 }, { "epoch": 18.36, "learning_rate": 1.5537178172546628e-06, "loss": 0.7619, "step": 220860 }, { "epoch": 18.36, "learning_rate": 1.553606961727129e-06, "loss": 0.7801, "step": 220870 }, { "epoch": 18.36, "learning_rate": 1.5534961061995954e-06, "loss": 0.7961, "step": 220880 }, { "epoch": 18.36, "learning_rate": 1.5533852506720614e-06, "loss": 0.7263, "step": 220890 }, { "epoch": 18.36, "learning_rate": 1.5532743951445277e-06, "loss": 0.729, "step": 220900 }, { "epoch": 18.36, "learning_rate": 1.553163539616994e-06, "loss": 0.7689, "step": 220910 }, { "epoch": 18.36, "learning_rate": 1.5530526840894605e-06, "loss": 0.7025, "step": 220920 }, { "epoch": 18.36, "learning_rate": 1.5529418285619266e-06, "loss": 0.7537, "step": 220930 }, { "epoch": 18.36, "learning_rate": 1.552830973034393e-06, "loss": 0.7592, "step": 220940 }, { "epoch": 18.37, "learning_rate": 1.5527201175068592e-06, "loss": 0.772, "step": 220950 }, { "epoch": 18.37, "learning_rate": 1.5526092619793253e-06, "loss": 0.8208, "step": 220960 }, { "epoch": 18.37, "learning_rate": 1.5524984064517916e-06, "loss": 0.784, "step": 220970 }, { "epoch": 18.37, "learning_rate": 1.5523875509242579e-06, "loss": 0.8003, "step": 220980 }, { "epoch": 18.37, "learning_rate": 1.5522766953967242e-06, "loss": 0.7266, "step": 220990 }, { "epoch": 18.37, "learning_rate": 1.5521658398691903e-06, "loss": 0.7736, "step": 221000 }, { "epoch": 18.37, "learning_rate": 1.5520549843416566e-06, "loss": 0.7586, "step": 221010 }, { "epoch": 18.37, "learning_rate": 1.5519441288141229e-06, "loss": 0.8107, "step": 221020 }, { "epoch": 18.37, "learning_rate": 1.5518443588393426e-06, "loss": 0.726, "step": 221030 }, { "epoch": 18.37, "learning_rate": 1.551733503311809e-06, "loss": 0.7509, "step": 221040 }, { "epoch": 18.37, "learning_rate": 1.551622647784275e-06, "loss": 0.7432, "step": 221050 }, { "epoch": 18.37, "learning_rate": 1.5515117922567413e-06, "loss": 0.7432, "step": 221060 }, { "epoch": 18.38, "learning_rate": 1.5514009367292076e-06, "loss": 0.825, "step": 221070 }, { "epoch": 18.38, "learning_rate": 1.5512900812016739e-06, "loss": 0.8063, "step": 221080 }, { "epoch": 18.38, "learning_rate": 1.55117922567414e-06, "loss": 0.7269, "step": 221090 }, { "epoch": 18.38, "learning_rate": 1.5510683701466063e-06, "loss": 0.7584, "step": 221100 }, { "epoch": 18.38, "learning_rate": 1.5509575146190726e-06, "loss": 0.7184, "step": 221110 }, { "epoch": 18.38, "learning_rate": 1.5508466590915388e-06, "loss": 0.7257, "step": 221120 }, { "epoch": 18.38, "learning_rate": 1.5507358035640051e-06, "loss": 0.7884, "step": 221130 }, { "epoch": 18.38, "learning_rate": 1.5506249480364714e-06, "loss": 0.7966, "step": 221140 }, { "epoch": 18.38, "learning_rate": 1.5505140925089377e-06, "loss": 0.7547, "step": 221150 }, { "epoch": 18.38, "learning_rate": 1.550403236981404e-06, "loss": 0.7491, "step": 221160 }, { "epoch": 18.38, "learning_rate": 1.5502923814538701e-06, "loss": 0.7805, "step": 221170 }, { "epoch": 18.38, "learning_rate": 1.5501815259263364e-06, "loss": 0.7869, "step": 221180 }, { "epoch": 18.39, "learning_rate": 1.5500706703988027e-06, "loss": 0.7154, "step": 221190 }, { "epoch": 18.39, "learning_rate": 1.549959814871269e-06, "loss": 0.8038, "step": 221200 }, { "epoch": 18.39, "learning_rate": 1.549848959343735e-06, "loss": 0.791, "step": 221210 }, { "epoch": 18.39, "learning_rate": 1.5497381038162014e-06, "loss": 0.7713, "step": 221220 }, { "epoch": 18.39, "learning_rate": 1.5496272482886677e-06, "loss": 0.8035, "step": 221230 }, { "epoch": 18.39, "learning_rate": 1.549516392761134e-06, "loss": 0.7708, "step": 221240 }, { "epoch": 18.39, "learning_rate": 1.5494055372336003e-06, "loss": 0.754, "step": 221250 }, { "epoch": 18.39, "learning_rate": 1.5492946817060666e-06, "loss": 0.8146, "step": 221260 }, { "epoch": 18.39, "learning_rate": 1.5491838261785329e-06, "loss": 0.813, "step": 221270 }, { "epoch": 18.39, "learning_rate": 1.5490729706509991e-06, "loss": 0.7311, "step": 221280 }, { "epoch": 18.39, "learning_rate": 1.5489621151234652e-06, "loss": 0.6766, "step": 221290 }, { "epoch": 18.39, "learning_rate": 1.5488512595959315e-06, "loss": 0.7626, "step": 221300 }, { "epoch": 18.39, "learning_rate": 1.5487404040683978e-06, "loss": 0.772, "step": 221310 }, { "epoch": 18.4, "learning_rate": 1.5486295485408641e-06, "loss": 0.8164, "step": 221320 }, { "epoch": 18.4, "learning_rate": 1.5485186930133302e-06, "loss": 0.8097, "step": 221330 }, { "epoch": 18.4, "learning_rate": 1.5484078374857965e-06, "loss": 0.7468, "step": 221340 }, { "epoch": 18.4, "learning_rate": 1.5482969819582628e-06, "loss": 0.7489, "step": 221350 }, { "epoch": 18.4, "learning_rate": 1.548186126430729e-06, "loss": 0.8003, "step": 221360 }, { "epoch": 18.4, "learning_rate": 1.5480752709031952e-06, "loss": 0.776, "step": 221370 }, { "epoch": 18.4, "learning_rate": 1.5479644153756617e-06, "loss": 0.7578, "step": 221380 }, { "epoch": 18.4, "learning_rate": 1.547853559848128e-06, "loss": 0.7725, "step": 221390 }, { "epoch": 18.4, "learning_rate": 1.5477427043205943e-06, "loss": 0.7485, "step": 221400 }, { "epoch": 18.4, "learning_rate": 1.5476318487930604e-06, "loss": 0.745, "step": 221410 }, { "epoch": 18.4, "learning_rate": 1.5475209932655266e-06, "loss": 0.7966, "step": 221420 }, { "epoch": 18.4, "learning_rate": 1.547410137737993e-06, "loss": 0.7942, "step": 221430 }, { "epoch": 18.41, "learning_rate": 1.547299282210459e-06, "loss": 0.751, "step": 221440 }, { "epoch": 18.41, "learning_rate": 1.5471884266829253e-06, "loss": 0.7807, "step": 221450 }, { "epoch": 18.41, "learning_rate": 1.5470775711553916e-06, "loss": 0.7525, "step": 221460 }, { "epoch": 18.41, "learning_rate": 1.546966715627858e-06, "loss": 0.7502, "step": 221470 }, { "epoch": 18.41, "learning_rate": 1.546855860100324e-06, "loss": 0.7973, "step": 221480 }, { "epoch": 18.41, "learning_rate": 1.5467450045727903e-06, "loss": 0.7397, "step": 221490 }, { "epoch": 18.41, "learning_rate": 1.5466341490452568e-06, "loss": 0.7046, "step": 221500 }, { "epoch": 18.41, "learning_rate": 1.546523293517723e-06, "loss": 0.8016, "step": 221510 }, { "epoch": 18.41, "learning_rate": 1.5464124379901892e-06, "loss": 0.785, "step": 221520 }, { "epoch": 18.41, "learning_rate": 1.5463015824626555e-06, "loss": 0.7204, "step": 221530 }, { "epoch": 18.41, "learning_rate": 1.5461907269351218e-06, "loss": 0.7756, "step": 221540 }, { "epoch": 18.41, "learning_rate": 1.546079871407588e-06, "loss": 0.7386, "step": 221550 }, { "epoch": 18.42, "learning_rate": 1.5459690158800541e-06, "loss": 0.7602, "step": 221560 }, { "epoch": 18.42, "learning_rate": 1.5458581603525204e-06, "loss": 0.7759, "step": 221570 }, { "epoch": 18.42, "learning_rate": 1.5457473048249867e-06, "loss": 0.7444, "step": 221580 }, { "epoch": 18.42, "learning_rate": 1.545636449297453e-06, "loss": 0.7329, "step": 221590 }, { "epoch": 18.42, "learning_rate": 1.5455255937699191e-06, "loss": 0.7898, "step": 221600 }, { "epoch": 18.42, "learning_rate": 1.5454147382423854e-06, "loss": 0.8277, "step": 221610 }, { "epoch": 18.42, "learning_rate": 1.545303882714852e-06, "loss": 0.7964, "step": 221620 }, { "epoch": 18.42, "learning_rate": 1.5451930271873182e-06, "loss": 0.7157, "step": 221630 }, { "epoch": 18.42, "learning_rate": 1.5450821716597843e-06, "loss": 0.7854, "step": 221640 }, { "epoch": 18.42, "learning_rate": 1.5449713161322506e-06, "loss": 0.7025, "step": 221650 }, { "epoch": 18.42, "learning_rate": 1.5448604606047169e-06, "loss": 0.7759, "step": 221660 }, { "epoch": 18.42, "learning_rate": 1.5447496050771832e-06, "loss": 0.7982, "step": 221670 }, { "epoch": 18.43, "learning_rate": 1.5446387495496493e-06, "loss": 0.6975, "step": 221680 }, { "epoch": 18.43, "learning_rate": 1.5445278940221156e-06, "loss": 0.7883, "step": 221690 }, { "epoch": 18.43, "learning_rate": 1.5444170384945819e-06, "loss": 0.7662, "step": 221700 }, { "epoch": 18.43, "learning_rate": 1.5443061829670482e-06, "loss": 0.7498, "step": 221710 }, { "epoch": 18.43, "learning_rate": 1.5441953274395142e-06, "loss": 0.8338, "step": 221720 }, { "epoch": 18.43, "learning_rate": 1.5440844719119805e-06, "loss": 0.7883, "step": 221730 }, { "epoch": 18.43, "learning_rate": 1.543973616384447e-06, "loss": 0.7461, "step": 221740 }, { "epoch": 18.43, "learning_rate": 1.5438627608569133e-06, "loss": 0.7871, "step": 221750 }, { "epoch": 18.43, "learning_rate": 1.5437519053293794e-06, "loss": 0.7615, "step": 221760 }, { "epoch": 18.43, "learning_rate": 1.5436410498018457e-06, "loss": 0.7854, "step": 221770 }, { "epoch": 18.43, "learning_rate": 1.543530194274312e-06, "loss": 0.8054, "step": 221780 }, { "epoch": 18.43, "learning_rate": 1.5434193387467783e-06, "loss": 0.7737, "step": 221790 }, { "epoch": 18.44, "learning_rate": 1.5433084832192444e-06, "loss": 0.7118, "step": 221800 }, { "epoch": 18.44, "learning_rate": 1.5431976276917107e-06, "loss": 0.8231, "step": 221810 }, { "epoch": 18.44, "learning_rate": 1.543086772164177e-06, "loss": 0.7994, "step": 221820 }, { "epoch": 18.44, "learning_rate": 1.5429759166366433e-06, "loss": 0.7234, "step": 221830 }, { "epoch": 18.44, "learning_rate": 1.5428650611091094e-06, "loss": 0.7848, "step": 221840 }, { "epoch": 18.44, "learning_rate": 1.5427542055815757e-06, "loss": 0.7528, "step": 221850 }, { "epoch": 18.44, "learning_rate": 1.542643350054042e-06, "loss": 0.7772, "step": 221860 }, { "epoch": 18.44, "learning_rate": 1.5425324945265085e-06, "loss": 0.8069, "step": 221870 }, { "epoch": 18.44, "learning_rate": 1.5424216389989745e-06, "loss": 0.7525, "step": 221880 }, { "epoch": 18.44, "learning_rate": 1.5423107834714408e-06, "loss": 0.7639, "step": 221890 }, { "epoch": 18.44, "learning_rate": 1.5421999279439071e-06, "loss": 0.7613, "step": 221900 }, { "epoch": 18.44, "learning_rate": 1.5420890724163732e-06, "loss": 0.7451, "step": 221910 }, { "epoch": 18.45, "learning_rate": 1.5419782168888395e-06, "loss": 0.8083, "step": 221920 }, { "epoch": 18.45, "learning_rate": 1.5418673613613058e-06, "loss": 0.7082, "step": 221930 }, { "epoch": 18.45, "learning_rate": 1.541756505833772e-06, "loss": 0.744, "step": 221940 }, { "epoch": 18.45, "learning_rate": 1.5416456503062382e-06, "loss": 0.7307, "step": 221950 }, { "epoch": 18.45, "learning_rate": 1.5415347947787045e-06, "loss": 0.7959, "step": 221960 }, { "epoch": 18.45, "learning_rate": 1.5414239392511708e-06, "loss": 0.7728, "step": 221970 }, { "epoch": 18.45, "learning_rate": 1.541313083723637e-06, "loss": 0.7947, "step": 221980 }, { "epoch": 18.45, "learning_rate": 1.5412022281961034e-06, "loss": 0.736, "step": 221990 }, { "epoch": 18.45, "learning_rate": 1.5410913726685697e-06, "loss": 0.7484, "step": 222000 }, { "epoch": 18.45, "learning_rate": 1.540980517141036e-06, "loss": 0.8197, "step": 222010 }, { "epoch": 18.45, "learning_rate": 1.5408696616135023e-06, "loss": 0.7865, "step": 222020 }, { "epoch": 18.45, "learning_rate": 1.5407588060859683e-06, "loss": 0.7932, "step": 222030 }, { "epoch": 18.46, "learning_rate": 1.5406479505584346e-06, "loss": 0.7565, "step": 222040 }, { "epoch": 18.46, "learning_rate": 1.540537095030901e-06, "loss": 0.7971, "step": 222050 }, { "epoch": 18.46, "learning_rate": 1.5404262395033672e-06, "loss": 0.7748, "step": 222060 }, { "epoch": 18.46, "learning_rate": 1.5403153839758333e-06, "loss": 0.7532, "step": 222070 }, { "epoch": 18.46, "learning_rate": 1.5402045284482996e-06, "loss": 0.7493, "step": 222080 }, { "epoch": 18.46, "learning_rate": 1.540093672920766e-06, "loss": 0.7435, "step": 222090 }, { "epoch": 18.46, "learning_rate": 1.5399828173932322e-06, "loss": 0.7651, "step": 222100 }, { "epoch": 18.46, "learning_rate": 1.5398719618656985e-06, "loss": 0.7385, "step": 222110 }, { "epoch": 18.46, "learning_rate": 1.5397611063381648e-06, "loss": 0.8196, "step": 222120 }, { "epoch": 18.46, "learning_rate": 1.539650250810631e-06, "loss": 0.7098, "step": 222130 }, { "epoch": 18.46, "learning_rate": 1.5395393952830974e-06, "loss": 0.7669, "step": 222140 }, { "epoch": 18.46, "learning_rate": 1.539439625308317e-06, "loss": 0.7023, "step": 222150 }, { "epoch": 18.47, "learning_rate": 1.539328769780783e-06, "loss": 0.7503, "step": 222160 }, { "epoch": 18.47, "learning_rate": 1.5392179142532493e-06, "loss": 0.7916, "step": 222170 }, { "epoch": 18.47, "learning_rate": 1.5391070587257156e-06, "loss": 0.6719, "step": 222180 }, { "epoch": 18.47, "learning_rate": 1.5389962031981819e-06, "loss": 0.8216, "step": 222190 }, { "epoch": 18.47, "learning_rate": 1.5388853476706482e-06, "loss": 0.7909, "step": 222200 }, { "epoch": 18.47, "learning_rate": 1.5387744921431145e-06, "loss": 0.7772, "step": 222210 }, { "epoch": 18.47, "learning_rate": 1.5386636366155808e-06, "loss": 0.805, "step": 222220 }, { "epoch": 18.47, "learning_rate": 1.538552781088047e-06, "loss": 0.7092, "step": 222230 }, { "epoch": 18.47, "learning_rate": 1.5384419255605131e-06, "loss": 0.8126, "step": 222240 }, { "epoch": 18.47, "learning_rate": 1.5383310700329794e-06, "loss": 0.7657, "step": 222250 }, { "epoch": 18.47, "learning_rate": 1.5382202145054457e-06, "loss": 0.7755, "step": 222260 }, { "epoch": 18.47, "learning_rate": 1.538109358977912e-06, "loss": 0.8201, "step": 222270 }, { "epoch": 18.48, "learning_rate": 1.5379985034503781e-06, "loss": 0.7282, "step": 222280 }, { "epoch": 18.48, "learning_rate": 1.5378876479228444e-06, "loss": 0.6629, "step": 222290 }, { "epoch": 18.48, "learning_rate": 1.5377767923953107e-06, "loss": 0.7855, "step": 222300 }, { "epoch": 18.48, "learning_rate": 1.537665936867777e-06, "loss": 0.7465, "step": 222310 }, { "epoch": 18.48, "learning_rate": 1.5375550813402433e-06, "loss": 0.8413, "step": 222320 }, { "epoch": 18.48, "learning_rate": 1.5374442258127096e-06, "loss": 0.7757, "step": 222330 }, { "epoch": 18.48, "learning_rate": 1.5373333702851759e-06, "loss": 0.7403, "step": 222340 }, { "epoch": 18.48, "learning_rate": 1.5372225147576422e-06, "loss": 0.72, "step": 222350 }, { "epoch": 18.48, "learning_rate": 1.5371116592301083e-06, "loss": 0.7841, "step": 222360 }, { "epoch": 18.48, "learning_rate": 1.5370008037025746e-06, "loss": 0.7991, "step": 222370 }, { "epoch": 18.48, "learning_rate": 1.5368899481750409e-06, "loss": 0.7269, "step": 222380 }, { "epoch": 18.48, "learning_rate": 1.5367790926475072e-06, "loss": 0.7954, "step": 222390 }, { "epoch": 18.49, "learning_rate": 1.5366682371199732e-06, "loss": 0.7605, "step": 222400 }, { "epoch": 18.49, "learning_rate": 1.5365573815924395e-06, "loss": 0.7532, "step": 222410 }, { "epoch": 18.49, "learning_rate": 1.5364465260649058e-06, "loss": 0.8305, "step": 222420 }, { "epoch": 18.49, "learning_rate": 1.536335670537372e-06, "loss": 0.7578, "step": 222430 }, { "epoch": 18.49, "learning_rate": 1.5362248150098382e-06, "loss": 0.7196, "step": 222440 }, { "epoch": 18.49, "learning_rate": 1.5361139594823047e-06, "loss": 0.7966, "step": 222450 }, { "epoch": 18.49, "learning_rate": 1.536003103954771e-06, "loss": 0.7649, "step": 222460 }, { "epoch": 18.49, "learning_rate": 1.535892248427237e-06, "loss": 0.7996, "step": 222470 }, { "epoch": 18.49, "learning_rate": 1.5357813928997034e-06, "loss": 0.7595, "step": 222480 }, { "epoch": 18.49, "learning_rate": 1.5356705373721697e-06, "loss": 0.6865, "step": 222490 }, { "epoch": 18.49, "learning_rate": 1.535559681844636e-06, "loss": 0.7474, "step": 222500 }, { "epoch": 18.49, "learning_rate": 1.535448826317102e-06, "loss": 0.7173, "step": 222510 }, { "epoch": 18.5, "learning_rate": 1.5353379707895684e-06, "loss": 0.7279, "step": 222520 }, { "epoch": 18.5, "learning_rate": 1.5352271152620347e-06, "loss": 0.77, "step": 222530 }, { "epoch": 18.5, "learning_rate": 1.535116259734501e-06, "loss": 0.738, "step": 222540 }, { "epoch": 18.5, "learning_rate": 1.535005404206967e-06, "loss": 0.7464, "step": 222550 }, { "epoch": 18.5, "learning_rate": 1.5348945486794333e-06, "loss": 0.764, "step": 222560 }, { "epoch": 18.5, "learning_rate": 1.5347836931518998e-06, "loss": 0.7383, "step": 222570 }, { "epoch": 18.5, "learning_rate": 1.5346728376243661e-06, "loss": 0.7481, "step": 222580 }, { "epoch": 18.5, "learning_rate": 1.5345619820968322e-06, "loss": 0.7618, "step": 222590 }, { "epoch": 18.5, "learning_rate": 1.5344511265692985e-06, "loss": 0.725, "step": 222600 }, { "epoch": 18.5, "learning_rate": 1.5343402710417648e-06, "loss": 0.771, "step": 222610 }, { "epoch": 18.5, "learning_rate": 1.534229415514231e-06, "loss": 0.8282, "step": 222620 }, { "epoch": 18.5, "learning_rate": 1.5341185599866972e-06, "loss": 0.7533, "step": 222630 }, { "epoch": 18.51, "learning_rate": 1.5340077044591635e-06, "loss": 0.7539, "step": 222640 }, { "epoch": 18.51, "learning_rate": 1.5338968489316298e-06, "loss": 0.7389, "step": 222650 }, { "epoch": 18.51, "learning_rate": 1.533785993404096e-06, "loss": 0.8045, "step": 222660 }, { "epoch": 18.51, "learning_rate": 1.5336751378765622e-06, "loss": 0.7531, "step": 222670 }, { "epoch": 18.51, "learning_rate": 1.5335642823490284e-06, "loss": 0.7193, "step": 222680 }, { "epoch": 18.51, "learning_rate": 1.533453426821495e-06, "loss": 0.7125, "step": 222690 }, { "epoch": 18.51, "learning_rate": 1.5333425712939612e-06, "loss": 0.7883, "step": 222700 }, { "epoch": 18.51, "learning_rate": 1.5332317157664273e-06, "loss": 0.7846, "step": 222710 }, { "epoch": 18.51, "learning_rate": 1.5331208602388936e-06, "loss": 0.7058, "step": 222720 }, { "epoch": 18.51, "learning_rate": 1.53301000471136e-06, "loss": 0.7343, "step": 222730 }, { "epoch": 18.51, "learning_rate": 1.5328991491838262e-06, "loss": 0.7183, "step": 222740 }, { "epoch": 18.51, "learning_rate": 1.5327882936562923e-06, "loss": 0.7573, "step": 222750 }, { "epoch": 18.52, "learning_rate": 1.5326774381287586e-06, "loss": 0.7226, "step": 222760 }, { "epoch": 18.52, "learning_rate": 1.5325665826012249e-06, "loss": 0.8032, "step": 222770 }, { "epoch": 18.52, "learning_rate": 1.5324557270736912e-06, "loss": 0.7378, "step": 222780 }, { "epoch": 18.52, "learning_rate": 1.5323448715461573e-06, "loss": 0.7537, "step": 222790 }, { "epoch": 18.52, "learning_rate": 1.5322340160186236e-06, "loss": 0.7525, "step": 222800 }, { "epoch": 18.52, "learning_rate": 1.53212316049109e-06, "loss": 0.8184, "step": 222810 }, { "epoch": 18.52, "learning_rate": 1.5320123049635564e-06, "loss": 0.7572, "step": 222820 }, { "epoch": 18.52, "learning_rate": 1.5319014494360225e-06, "loss": 0.7089, "step": 222830 }, { "epoch": 18.52, "learning_rate": 1.5317905939084887e-06, "loss": 0.741, "step": 222840 }, { "epoch": 18.52, "learning_rate": 1.531679738380955e-06, "loss": 0.7605, "step": 222850 }, { "epoch": 18.52, "learning_rate": 1.5315688828534211e-06, "loss": 0.726, "step": 222860 }, { "epoch": 18.52, "learning_rate": 1.5314580273258874e-06, "loss": 0.7411, "step": 222870 }, { "epoch": 18.53, "learning_rate": 1.5313471717983537e-06, "loss": 0.8151, "step": 222880 }, { "epoch": 18.53, "learning_rate": 1.53123631627082e-06, "loss": 0.8004, "step": 222890 }, { "epoch": 18.53, "learning_rate": 1.531125460743286e-06, "loss": 0.7696, "step": 222900 }, { "epoch": 18.53, "learning_rate": 1.5310146052157524e-06, "loss": 0.7658, "step": 222910 }, { "epoch": 18.53, "learning_rate": 1.5309037496882187e-06, "loss": 0.8217, "step": 222920 }, { "epoch": 18.53, "learning_rate": 1.530792894160685e-06, "loss": 0.8193, "step": 222930 }, { "epoch": 18.53, "learning_rate": 1.5306820386331513e-06, "loss": 0.7685, "step": 222940 }, { "epoch": 18.53, "learning_rate": 1.5305711831056176e-06, "loss": 0.7587, "step": 222950 }, { "epoch": 18.53, "learning_rate": 1.5304603275780839e-06, "loss": 0.7981, "step": 222960 }, { "epoch": 18.53, "learning_rate": 1.5303494720505502e-06, "loss": 0.8378, "step": 222970 }, { "epoch": 18.53, "learning_rate": 1.5302386165230162e-06, "loss": 0.6969, "step": 222980 }, { "epoch": 18.53, "learning_rate": 1.5301277609954825e-06, "loss": 0.7542, "step": 222990 }, { "epoch": 18.54, "learning_rate": 1.5300169054679488e-06, "loss": 0.7289, "step": 223000 }, { "epoch": 18.54, "learning_rate": 1.5299060499404151e-06, "loss": 0.7802, "step": 223010 }, { "epoch": 18.54, "learning_rate": 1.5297951944128812e-06, "loss": 0.7411, "step": 223020 }, { "epoch": 18.54, "learning_rate": 1.5296843388853475e-06, "loss": 0.7194, "step": 223030 }, { "epoch": 18.54, "learning_rate": 1.5295734833578138e-06, "loss": 0.7991, "step": 223040 }, { "epoch": 18.54, "learning_rate": 1.52946262783028e-06, "loss": 0.7954, "step": 223050 }, { "epoch": 18.54, "learning_rate": 1.5293517723027464e-06, "loss": 0.7534, "step": 223060 }, { "epoch": 18.54, "learning_rate": 1.5292409167752127e-06, "loss": 0.7645, "step": 223070 }, { "epoch": 18.54, "learning_rate": 1.529130061247679e-06, "loss": 0.7741, "step": 223080 }, { "epoch": 18.54, "learning_rate": 1.5290192057201453e-06, "loss": 0.7204, "step": 223090 }, { "epoch": 18.54, "learning_rate": 1.5289083501926114e-06, "loss": 0.7327, "step": 223100 }, { "epoch": 18.54, "learning_rate": 1.5287974946650777e-06, "loss": 0.7969, "step": 223110 }, { "epoch": 18.55, "learning_rate": 1.528686639137544e-06, "loss": 0.7763, "step": 223120 }, { "epoch": 18.55, "learning_rate": 1.5285757836100103e-06, "loss": 0.7685, "step": 223130 }, { "epoch": 18.55, "learning_rate": 1.5284649280824763e-06, "loss": 0.81, "step": 223140 }, { "epoch": 18.55, "learning_rate": 1.5283540725549426e-06, "loss": 0.7186, "step": 223150 }, { "epoch": 18.55, "learning_rate": 1.528243217027409e-06, "loss": 0.8361, "step": 223160 }, { "epoch": 18.55, "learning_rate": 1.5281323614998752e-06, "loss": 0.789, "step": 223170 }, { "epoch": 18.55, "learning_rate": 1.5280215059723415e-06, "loss": 0.7698, "step": 223180 }, { "epoch": 18.55, "learning_rate": 1.5279106504448078e-06, "loss": 0.783, "step": 223190 }, { "epoch": 18.55, "learning_rate": 1.5277997949172741e-06, "loss": 0.7942, "step": 223200 }, { "epoch": 18.55, "learning_rate": 1.5276889393897404e-06, "loss": 0.7802, "step": 223210 }, { "epoch": 18.55, "learning_rate": 1.5275780838622065e-06, "loss": 0.7836, "step": 223220 }, { "epoch": 18.55, "learning_rate": 1.5274672283346728e-06, "loss": 0.7601, "step": 223230 }, { "epoch": 18.56, "learning_rate": 1.527356372807139e-06, "loss": 0.6781, "step": 223240 }, { "epoch": 18.56, "learning_rate": 1.5272455172796052e-06, "loss": 0.7915, "step": 223250 }, { "epoch": 18.56, "learning_rate": 1.5271346617520715e-06, "loss": 0.7385, "step": 223260 }, { "epoch": 18.56, "learning_rate": 1.5270238062245378e-06, "loss": 0.8575, "step": 223270 }, { "epoch": 18.56, "learning_rate": 1.526912950697004e-06, "loss": 0.7267, "step": 223280 }, { "epoch": 18.56, "learning_rate": 1.5268020951694701e-06, "loss": 0.7212, "step": 223290 }, { "epoch": 18.56, "learning_rate": 1.5266912396419364e-06, "loss": 0.7987, "step": 223300 }, { "epoch": 18.56, "learning_rate": 1.526580384114403e-06, "loss": 0.8448, "step": 223310 }, { "epoch": 18.56, "learning_rate": 1.5264695285868692e-06, "loss": 0.7474, "step": 223320 }, { "epoch": 18.56, "learning_rate": 1.5263586730593353e-06, "loss": 0.7539, "step": 223330 }, { "epoch": 18.56, "learning_rate": 1.5262478175318016e-06, "loss": 0.7668, "step": 223340 }, { "epoch": 18.56, "learning_rate": 1.526136962004268e-06, "loss": 0.767, "step": 223350 }, { "epoch": 18.57, "learning_rate": 1.5260261064767342e-06, "loss": 0.8023, "step": 223360 }, { "epoch": 18.57, "learning_rate": 1.5259152509492003e-06, "loss": 0.7594, "step": 223370 }, { "epoch": 18.57, "learning_rate": 1.5258043954216666e-06, "loss": 0.7785, "step": 223380 }, { "epoch": 18.57, "learning_rate": 1.5256935398941329e-06, "loss": 0.7706, "step": 223390 }, { "epoch": 18.57, "learning_rate": 1.5255826843665992e-06, "loss": 0.7653, "step": 223400 }, { "epoch": 18.57, "learning_rate": 1.5254718288390653e-06, "loss": 0.7331, "step": 223410 }, { "epoch": 18.57, "learning_rate": 1.5253609733115315e-06, "loss": 0.8371, "step": 223420 }, { "epoch": 18.57, "learning_rate": 1.525250117783998e-06, "loss": 0.7974, "step": 223430 }, { "epoch": 18.57, "learning_rate": 1.5251392622564644e-06, "loss": 0.7619, "step": 223440 }, { "epoch": 18.57, "learning_rate": 1.5250284067289304e-06, "loss": 0.7619, "step": 223450 }, { "epoch": 18.57, "learning_rate": 1.5249175512013967e-06, "loss": 0.7672, "step": 223460 }, { "epoch": 18.57, "learning_rate": 1.524806695673863e-06, "loss": 0.8447, "step": 223470 }, { "epoch": 18.58, "learning_rate": 1.5246958401463293e-06, "loss": 0.8119, "step": 223480 }, { "epoch": 18.58, "learning_rate": 1.5245849846187954e-06, "loss": 0.6999, "step": 223490 }, { "epoch": 18.58, "learning_rate": 1.5244741290912617e-06, "loss": 0.7565, "step": 223500 }, { "epoch": 18.58, "learning_rate": 1.524363273563728e-06, "loss": 0.735, "step": 223510 }, { "epoch": 18.58, "learning_rate": 1.5242524180361943e-06, "loss": 0.7602, "step": 223520 }, { "epoch": 18.58, "learning_rate": 1.5241415625086604e-06, "loss": 0.7335, "step": 223530 }, { "epoch": 18.58, "learning_rate": 1.5240307069811267e-06, "loss": 0.7628, "step": 223540 }, { "epoch": 18.58, "learning_rate": 1.5239198514535932e-06, "loss": 0.7889, "step": 223550 }, { "epoch": 18.58, "learning_rate": 1.5238089959260595e-06, "loss": 0.7494, "step": 223560 }, { "epoch": 18.58, "learning_rate": 1.5236981403985256e-06, "loss": 0.8206, "step": 223570 }, { "epoch": 18.58, "learning_rate": 1.5235872848709919e-06, "loss": 0.7536, "step": 223580 }, { "epoch": 18.58, "learning_rate": 1.5234764293434581e-06, "loss": 0.8166, "step": 223590 }, { "epoch": 18.59, "learning_rate": 1.5233655738159244e-06, "loss": 0.7839, "step": 223600 }, { "epoch": 18.59, "learning_rate": 1.5232547182883905e-06, "loss": 0.757, "step": 223610 }, { "epoch": 18.59, "learning_rate": 1.5231438627608568e-06, "loss": 0.7513, "step": 223620 }, { "epoch": 18.59, "learning_rate": 1.5230330072333231e-06, "loss": 0.7919, "step": 223630 }, { "epoch": 18.59, "learning_rate": 1.5229221517057892e-06, "loss": 0.7602, "step": 223640 }, { "epoch": 18.59, "learning_rate": 1.5228112961782555e-06, "loss": 0.7756, "step": 223650 }, { "epoch": 18.59, "learning_rate": 1.5227004406507218e-06, "loss": 0.7816, "step": 223660 }, { "epoch": 18.59, "learning_rate": 1.522589585123188e-06, "loss": 0.7742, "step": 223670 }, { "epoch": 18.59, "learning_rate": 1.5224787295956546e-06, "loss": 0.7681, "step": 223680 }, { "epoch": 18.59, "learning_rate": 1.5223678740681207e-06, "loss": 0.7362, "step": 223690 }, { "epoch": 18.59, "learning_rate": 1.522257018540587e-06, "loss": 0.7916, "step": 223700 }, { "epoch": 18.59, "learning_rate": 1.5221461630130533e-06, "loss": 0.773, "step": 223710 }, { "epoch": 18.6, "learning_rate": 1.5220353074855194e-06, "loss": 0.7395, "step": 223720 }, { "epoch": 18.6, "learning_rate": 1.5219244519579856e-06, "loss": 0.7568, "step": 223730 }, { "epoch": 18.6, "learning_rate": 1.521813596430452e-06, "loss": 0.7814, "step": 223740 }, { "epoch": 18.6, "learning_rate": 1.5217027409029182e-06, "loss": 0.7773, "step": 223750 }, { "epoch": 18.6, "learning_rate": 1.5215918853753843e-06, "loss": 0.7404, "step": 223760 }, { "epoch": 18.6, "learning_rate": 1.5214810298478506e-06, "loss": 0.7817, "step": 223770 }, { "epoch": 18.6, "learning_rate": 1.521370174320317e-06, "loss": 0.7126, "step": 223780 }, { "epoch": 18.6, "learning_rate": 1.5212593187927832e-06, "loss": 0.6877, "step": 223790 }, { "epoch": 18.6, "learning_rate": 1.5211484632652495e-06, "loss": 0.8371, "step": 223800 }, { "epoch": 18.6, "learning_rate": 1.5210376077377158e-06, "loss": 0.7281, "step": 223810 }, { "epoch": 18.6, "learning_rate": 1.520926752210182e-06, "loss": 0.805, "step": 223820 }, { "epoch": 18.6, "learning_rate": 1.5208158966826484e-06, "loss": 0.7478, "step": 223830 }, { "epoch": 18.61, "learning_rate": 1.5207050411551145e-06, "loss": 0.7624, "step": 223840 }, { "epoch": 18.61, "learning_rate": 1.5205941856275808e-06, "loss": 0.7547, "step": 223850 }, { "epoch": 18.61, "learning_rate": 1.520483330100047e-06, "loss": 0.764, "step": 223860 }, { "epoch": 18.61, "learning_rate": 1.5203724745725134e-06, "loss": 0.7646, "step": 223870 }, { "epoch": 18.61, "learning_rate": 1.5202616190449794e-06, "loss": 0.7767, "step": 223880 }, { "epoch": 18.61, "learning_rate": 1.5201507635174457e-06, "loss": 0.7244, "step": 223890 }, { "epoch": 18.61, "learning_rate": 1.520039907989912e-06, "loss": 0.7311, "step": 223900 }, { "epoch": 18.61, "learning_rate": 1.5199290524623783e-06, "loss": 0.754, "step": 223910 }, { "epoch": 18.61, "learning_rate": 1.5198181969348446e-06, "loss": 0.7864, "step": 223920 }, { "epoch": 18.61, "learning_rate": 1.519707341407311e-06, "loss": 0.7931, "step": 223930 }, { "epoch": 18.61, "learning_rate": 1.5195964858797772e-06, "loss": 0.7502, "step": 223940 }, { "epoch": 18.61, "learning_rate": 1.5194856303522435e-06, "loss": 0.7483, "step": 223950 }, { "epoch": 18.62, "learning_rate": 1.5193747748247096e-06, "loss": 0.6979, "step": 223960 }, { "epoch": 18.62, "learning_rate": 1.5192639192971759e-06, "loss": 0.8107, "step": 223970 }, { "epoch": 18.62, "learning_rate": 1.5191530637696422e-06, "loss": 0.6956, "step": 223980 }, { "epoch": 18.62, "learning_rate": 1.5190422082421085e-06, "loss": 0.7159, "step": 223990 }, { "epoch": 18.62, "learning_rate": 1.5189313527145746e-06, "loss": 0.7832, "step": 224000 }, { "epoch": 18.62, "learning_rate": 1.5188204971870409e-06, "loss": 0.7804, "step": 224010 }, { "epoch": 18.62, "learning_rate": 1.5187096416595072e-06, "loss": 0.8043, "step": 224020 }, { "epoch": 18.62, "learning_rate": 1.5185987861319734e-06, "loss": 0.7162, "step": 224030 }, { "epoch": 18.62, "learning_rate": 1.5184879306044397e-06, "loss": 0.6863, "step": 224040 }, { "epoch": 18.62, "learning_rate": 1.518377075076906e-06, "loss": 0.7458, "step": 224050 }, { "epoch": 18.62, "learning_rate": 1.5182662195493723e-06, "loss": 0.8275, "step": 224060 }, { "epoch": 18.62, "learning_rate": 1.5181553640218386e-06, "loss": 0.7726, "step": 224070 }, { "epoch": 18.63, "learning_rate": 1.5180445084943047e-06, "loss": 0.7595, "step": 224080 }, { "epoch": 18.63, "learning_rate": 1.517933652966771e-06, "loss": 0.8634, "step": 224090 }, { "epoch": 18.63, "learning_rate": 1.5178227974392373e-06, "loss": 0.7555, "step": 224100 }, { "epoch": 18.63, "learning_rate": 1.5177119419117034e-06, "loss": 0.7558, "step": 224110 }, { "epoch": 18.63, "learning_rate": 1.5176010863841697e-06, "loss": 0.8055, "step": 224120 }, { "epoch": 18.63, "learning_rate": 1.517490230856636e-06, "loss": 0.7086, "step": 224130 }, { "epoch": 18.63, "learning_rate": 1.5173793753291023e-06, "loss": 0.7617, "step": 224140 }, { "epoch": 18.63, "learning_rate": 1.5172685198015684e-06, "loss": 0.7853, "step": 224150 }, { "epoch": 18.63, "learning_rate": 1.5171576642740347e-06, "loss": 0.7551, "step": 224160 }, { "epoch": 18.63, "learning_rate": 1.5170468087465012e-06, "loss": 0.7791, "step": 224170 }, { "epoch": 18.63, "learning_rate": 1.5169359532189675e-06, "loss": 0.7812, "step": 224180 }, { "epoch": 18.63, "learning_rate": 1.5168250976914335e-06, "loss": 0.7073, "step": 224190 }, { "epoch": 18.64, "learning_rate": 1.5167142421638998e-06, "loss": 0.7634, "step": 224200 }, { "epoch": 18.64, "learning_rate": 1.5166033866363661e-06, "loss": 0.7419, "step": 224210 }, { "epoch": 18.64, "learning_rate": 1.5164925311088324e-06, "loss": 0.7606, "step": 224220 }, { "epoch": 18.64, "learning_rate": 1.5163816755812985e-06, "loss": 0.7429, "step": 224230 }, { "epoch": 18.64, "learning_rate": 1.5162708200537648e-06, "loss": 0.8355, "step": 224240 }, { "epoch": 18.64, "learning_rate": 1.516159964526231e-06, "loss": 0.7187, "step": 224250 }, { "epoch": 18.64, "learning_rate": 1.5160491089986974e-06, "loss": 0.8204, "step": 224260 }, { "epoch": 18.64, "learning_rate": 1.5159382534711635e-06, "loss": 0.8308, "step": 224270 }, { "epoch": 18.64, "learning_rate": 1.5158273979436298e-06, "loss": 0.83, "step": 224280 }, { "epoch": 18.64, "learning_rate": 1.5157165424160963e-06, "loss": 0.7294, "step": 224290 }, { "epoch": 18.64, "learning_rate": 1.5156056868885626e-06, "loss": 0.7859, "step": 224300 }, { "epoch": 18.64, "learning_rate": 1.5154948313610287e-06, "loss": 0.792, "step": 224310 }, { "epoch": 18.65, "learning_rate": 1.515383975833495e-06, "loss": 0.8552, "step": 224320 }, { "epoch": 18.65, "learning_rate": 1.5152731203059612e-06, "loss": 0.7051, "step": 224330 }, { "epoch": 18.65, "learning_rate": 1.5151622647784275e-06, "loss": 0.7267, "step": 224340 }, { "epoch": 18.65, "learning_rate": 1.5150514092508936e-06, "loss": 0.7395, "step": 224350 }, { "epoch": 18.65, "learning_rate": 1.51494055372336e-06, "loss": 0.731, "step": 224360 }, { "epoch": 18.65, "learning_rate": 1.5148296981958262e-06, "loss": 0.7917, "step": 224370 }, { "epoch": 18.65, "learning_rate": 1.5147188426682925e-06, "loss": 0.8, "step": 224380 }, { "epoch": 18.65, "learning_rate": 1.5146079871407586e-06, "loss": 0.7863, "step": 224390 }, { "epoch": 18.65, "learning_rate": 1.5144971316132249e-06, "loss": 0.7529, "step": 224400 }, { "epoch": 18.65, "learning_rate": 1.5143862760856914e-06, "loss": 0.7756, "step": 224410 }, { "epoch": 18.65, "learning_rate": 1.5142754205581577e-06, "loss": 0.7947, "step": 224420 }, { "epoch": 18.65, "learning_rate": 1.5141645650306238e-06, "loss": 0.7567, "step": 224430 }, { "epoch": 18.66, "learning_rate": 1.51405370950309e-06, "loss": 0.7834, "step": 224440 }, { "epoch": 18.66, "learning_rate": 1.5139428539755564e-06, "loss": 0.7347, "step": 224450 }, { "epoch": 18.66, "learning_rate": 1.5138319984480227e-06, "loss": 0.783, "step": 224460 }, { "epoch": 18.66, "learning_rate": 1.5137211429204887e-06, "loss": 0.8283, "step": 224470 }, { "epoch": 18.66, "learning_rate": 1.513610287392955e-06, "loss": 0.7696, "step": 224480 }, { "epoch": 18.66, "learning_rate": 1.5134994318654213e-06, "loss": 0.734, "step": 224490 }, { "epoch": 18.66, "learning_rate": 1.5133885763378874e-06, "loss": 0.7177, "step": 224500 }, { "epoch": 18.66, "learning_rate": 1.5132777208103537e-06, "loss": 0.7176, "step": 224510 }, { "epoch": 18.66, "learning_rate": 1.51316686528282e-06, "loss": 0.7862, "step": 224520 }, { "epoch": 18.66, "learning_rate": 1.5130560097552863e-06, "loss": 0.7849, "step": 224530 }, { "epoch": 18.66, "learning_rate": 1.5129451542277526e-06, "loss": 0.7526, "step": 224540 }, { "epoch": 18.66, "learning_rate": 1.512834298700219e-06, "loss": 0.8151, "step": 224550 }, { "epoch": 18.67, "learning_rate": 1.5127234431726852e-06, "loss": 0.7722, "step": 224560 }, { "epoch": 18.67, "learning_rate": 1.5126125876451515e-06, "loss": 0.7885, "step": 224570 }, { "epoch": 18.67, "learning_rate": 1.5125017321176176e-06, "loss": 0.7012, "step": 224580 }, { "epoch": 18.67, "learning_rate": 1.5123908765900839e-06, "loss": 0.7677, "step": 224590 }, { "epoch": 18.67, "learning_rate": 1.5122800210625502e-06, "loss": 0.8235, "step": 224600 }, { "epoch": 18.67, "learning_rate": 1.5121691655350165e-06, "loss": 0.8271, "step": 224610 }, { "epoch": 18.67, "learning_rate": 1.5120583100074825e-06, "loss": 0.8015, "step": 224620 }, { "epoch": 18.67, "learning_rate": 1.5119474544799488e-06, "loss": 0.7852, "step": 224630 }, { "epoch": 18.67, "learning_rate": 1.5118365989524151e-06, "loss": 0.7523, "step": 224640 }, { "epoch": 18.67, "learning_rate": 1.5117257434248814e-06, "loss": 0.7159, "step": 224650 }, { "epoch": 18.67, "learning_rate": 1.5116148878973477e-06, "loss": 0.7725, "step": 224660 }, { "epoch": 18.67, "learning_rate": 1.511504032369814e-06, "loss": 0.8222, "step": 224670 }, { "epoch": 18.68, "learning_rate": 1.5113931768422803e-06, "loss": 0.7758, "step": 224680 }, { "epoch": 18.68, "learning_rate": 1.5112823213147466e-06, "loss": 0.7536, "step": 224690 }, { "epoch": 18.68, "learning_rate": 1.5111714657872127e-06, "loss": 0.7348, "step": 224700 }, { "epoch": 18.68, "learning_rate": 1.511060610259679e-06, "loss": 0.7745, "step": 224710 }, { "epoch": 18.68, "learning_rate": 1.5109497547321453e-06, "loss": 0.7935, "step": 224720 }, { "epoch": 18.68, "learning_rate": 1.5108388992046116e-06, "loss": 0.7517, "step": 224730 }, { "epoch": 18.68, "learning_rate": 1.5107280436770777e-06, "loss": 0.7645, "step": 224740 }, { "epoch": 18.68, "learning_rate": 1.510617188149544e-06, "loss": 0.7281, "step": 224750 }, { "epoch": 18.68, "learning_rate": 1.5105063326220103e-06, "loss": 0.7571, "step": 224760 }, { "epoch": 18.68, "learning_rate": 1.5103954770944765e-06, "loss": 0.813, "step": 224770 }, { "epoch": 18.68, "learning_rate": 1.5102846215669428e-06, "loss": 0.7351, "step": 224780 }, { "epoch": 18.68, "learning_rate": 1.5101737660394091e-06, "loss": 0.7427, "step": 224790 }, { "epoch": 18.69, "learning_rate": 1.5100629105118754e-06, "loss": 0.7108, "step": 224800 }, { "epoch": 18.69, "learning_rate": 1.5099520549843417e-06, "loss": 0.7531, "step": 224810 }, { "epoch": 18.69, "learning_rate": 1.5098411994568078e-06, "loss": 0.7288, "step": 224820 }, { "epoch": 18.69, "learning_rate": 1.5097303439292741e-06, "loss": 0.7142, "step": 224830 }, { "epoch": 18.69, "learning_rate": 1.5096194884017404e-06, "loss": 0.7368, "step": 224840 }, { "epoch": 18.69, "learning_rate": 1.5095086328742067e-06, "loss": 0.7024, "step": 224850 }, { "epoch": 18.69, "learning_rate": 1.5093977773466728e-06, "loss": 0.8175, "step": 224860 }, { "epoch": 18.69, "learning_rate": 1.509286921819139e-06, "loss": 0.7871, "step": 224870 }, { "epoch": 18.69, "learning_rate": 1.5091760662916054e-06, "loss": 0.8502, "step": 224880 }, { "epoch": 18.69, "learning_rate": 1.5090652107640715e-06, "loss": 0.7528, "step": 224890 }, { "epoch": 18.69, "learning_rate": 1.508954355236538e-06, "loss": 0.6805, "step": 224900 }, { "epoch": 18.69, "learning_rate": 1.5088434997090043e-06, "loss": 0.7501, "step": 224910 }, { "epoch": 18.7, "learning_rate": 1.5087326441814706e-06, "loss": 0.8271, "step": 224920 }, { "epoch": 18.7, "learning_rate": 1.5086217886539366e-06, "loss": 0.7764, "step": 224930 }, { "epoch": 18.7, "learning_rate": 1.508510933126403e-06, "loss": 0.7499, "step": 224940 }, { "epoch": 18.7, "learning_rate": 1.5084000775988692e-06, "loss": 0.8036, "step": 224950 }, { "epoch": 18.7, "learning_rate": 1.5082892220713355e-06, "loss": 0.7513, "step": 224960 }, { "epoch": 18.7, "learning_rate": 1.5081783665438016e-06, "loss": 0.7692, "step": 224970 }, { "epoch": 18.7, "learning_rate": 1.508067511016268e-06, "loss": 0.7476, "step": 224980 }, { "epoch": 18.7, "learning_rate": 1.5079566554887342e-06, "loss": 0.7815, "step": 224990 }, { "epoch": 18.7, "learning_rate": 1.5078457999612005e-06, "loss": 0.7799, "step": 225000 }, { "epoch": 18.7, "learning_rate": 1.5077349444336666e-06, "loss": 0.762, "step": 225010 }, { "epoch": 18.7, "learning_rate": 1.5076240889061329e-06, "loss": 0.8272, "step": 225020 }, { "epoch": 18.7, "learning_rate": 1.5075132333785994e-06, "loss": 0.7857, "step": 225030 }, { "epoch": 18.71, "learning_rate": 1.5074023778510657e-06, "loss": 0.7903, "step": 225040 }, { "epoch": 18.71, "learning_rate": 1.5072915223235318e-06, "loss": 0.738, "step": 225050 }, { "epoch": 18.71, "learning_rate": 1.507180666795998e-06, "loss": 0.7378, "step": 225060 }, { "epoch": 18.71, "learning_rate": 1.5070698112684644e-06, "loss": 0.8256, "step": 225070 }, { "epoch": 18.71, "learning_rate": 1.5069589557409306e-06, "loss": 0.7901, "step": 225080 }, { "epoch": 18.71, "learning_rate": 1.5068481002133967e-06, "loss": 0.7299, "step": 225090 }, { "epoch": 18.71, "learning_rate": 1.506737244685863e-06, "loss": 0.6748, "step": 225100 }, { "epoch": 18.71, "learning_rate": 1.5066263891583293e-06, "loss": 0.7866, "step": 225110 }, { "epoch": 18.71, "learning_rate": 1.5065155336307956e-06, "loss": 0.821, "step": 225120 }, { "epoch": 18.71, "learning_rate": 1.5064046781032617e-06, "loss": 0.7277, "step": 225130 }, { "epoch": 18.71, "learning_rate": 1.506293822575728e-06, "loss": 0.7714, "step": 225140 }, { "epoch": 18.71, "learning_rate": 1.5061829670481945e-06, "loss": 0.7335, "step": 225150 }, { "epoch": 18.71, "learning_rate": 1.5060721115206608e-06, "loss": 0.781, "step": 225160 }, { "epoch": 18.72, "learning_rate": 1.5059612559931269e-06, "loss": 0.7548, "step": 225170 }, { "epoch": 18.72, "learning_rate": 1.5058504004655932e-06, "loss": 0.7749, "step": 225180 }, { "epoch": 18.72, "learning_rate": 1.5057395449380595e-06, "loss": 0.7362, "step": 225190 }, { "epoch": 18.72, "learning_rate": 1.5056286894105258e-06, "loss": 0.6729, "step": 225200 }, { "epoch": 18.72, "learning_rate": 1.5055178338829918e-06, "loss": 0.7128, "step": 225210 }, { "epoch": 18.72, "learning_rate": 1.5054069783554581e-06, "loss": 0.8046, "step": 225220 }, { "epoch": 18.72, "learning_rate": 1.5052961228279244e-06, "loss": 0.8043, "step": 225230 }, { "epoch": 18.72, "learning_rate": 1.5051852673003907e-06, "loss": 0.7155, "step": 225240 }, { "epoch": 18.72, "learning_rate": 1.5050744117728568e-06, "loss": 0.758, "step": 225250 }, { "epoch": 18.72, "learning_rate": 1.5049635562453231e-06, "loss": 0.7347, "step": 225260 }, { "epoch": 18.72, "learning_rate": 1.5048527007177896e-06, "loss": 0.791, "step": 225270 }, { "epoch": 18.72, "learning_rate": 1.504741845190256e-06, "loss": 0.7449, "step": 225280 }, { "epoch": 18.73, "learning_rate": 1.504630989662722e-06, "loss": 0.6927, "step": 225290 }, { "epoch": 18.73, "learning_rate": 1.5045201341351883e-06, "loss": 0.7502, "step": 225300 }, { "epoch": 18.73, "learning_rate": 1.5044092786076546e-06, "loss": 0.7958, "step": 225310 }, { "epoch": 18.73, "learning_rate": 1.5042984230801209e-06, "loss": 0.8118, "step": 225320 }, { "epoch": 18.73, "learning_rate": 1.504187567552587e-06, "loss": 0.6523, "step": 225330 }, { "epoch": 18.73, "learning_rate": 1.5040767120250533e-06, "loss": 0.7212, "step": 225340 }, { "epoch": 18.73, "learning_rate": 1.5039658564975196e-06, "loss": 0.7998, "step": 225350 }, { "epoch": 18.73, "learning_rate": 1.5038550009699856e-06, "loss": 0.6761, "step": 225360 }, { "epoch": 18.73, "learning_rate": 1.503744145442452e-06, "loss": 0.7956, "step": 225370 }, { "epoch": 18.73, "learning_rate": 1.5036332899149182e-06, "loss": 0.75, "step": 225380 }, { "epoch": 18.73, "learning_rate": 1.5035224343873845e-06, "loss": 0.8116, "step": 225390 }, { "epoch": 18.73, "learning_rate": 1.5034115788598508e-06, "loss": 0.8069, "step": 225400 }, { "epoch": 18.74, "learning_rate": 1.5033007233323171e-06, "loss": 0.7557, "step": 225410 }, { "epoch": 18.74, "learning_rate": 1.5031898678047834e-06, "loss": 0.7795, "step": 225420 }, { "epoch": 18.74, "learning_rate": 1.5030790122772497e-06, "loss": 0.7226, "step": 225430 }, { "epoch": 18.74, "learning_rate": 1.5029681567497158e-06, "loss": 0.7324, "step": 225440 }, { "epoch": 18.74, "learning_rate": 1.502857301222182e-06, "loss": 0.7677, "step": 225450 }, { "epoch": 18.74, "learning_rate": 1.5027464456946484e-06, "loss": 0.7597, "step": 225460 }, { "epoch": 18.74, "learning_rate": 1.5026355901671147e-06, "loss": 0.769, "step": 225470 }, { "epoch": 18.74, "learning_rate": 1.5025247346395808e-06, "loss": 0.7794, "step": 225480 }, { "epoch": 18.74, "learning_rate": 1.502413879112047e-06, "loss": 0.6963, "step": 225490 }, { "epoch": 18.74, "learning_rate": 1.5023030235845134e-06, "loss": 0.7327, "step": 225500 }, { "epoch": 18.74, "learning_rate": 1.5021921680569797e-06, "loss": 0.8099, "step": 225510 }, { "epoch": 18.74, "learning_rate": 1.502081312529446e-06, "loss": 0.7406, "step": 225520 }, { "epoch": 18.75, "learning_rate": 1.5019704570019122e-06, "loss": 0.7789, "step": 225530 }, { "epoch": 18.75, "learning_rate": 1.5018596014743785e-06, "loss": 0.7106, "step": 225540 }, { "epoch": 18.75, "learning_rate": 1.5017487459468448e-06, "loss": 0.7381, "step": 225550 }, { "epoch": 18.75, "learning_rate": 1.501637890419311e-06, "loss": 0.7938, "step": 225560 }, { "epoch": 18.75, "learning_rate": 1.5015270348917772e-06, "loss": 0.8128, "step": 225570 }, { "epoch": 18.75, "learning_rate": 1.5014161793642435e-06, "loss": 0.8059, "step": 225580 }, { "epoch": 18.75, "learning_rate": 1.5013053238367098e-06, "loss": 0.8048, "step": 225590 }, { "epoch": 18.75, "learning_rate": 1.5011944683091759e-06, "loss": 0.775, "step": 225600 }, { "epoch": 18.75, "learning_rate": 1.5010836127816422e-06, "loss": 0.7522, "step": 225610 }, { "epoch": 18.75, "learning_rate": 1.5009727572541085e-06, "loss": 0.7967, "step": 225620 }, { "epoch": 18.75, "learning_rate": 1.5008619017265748e-06, "loss": 0.6814, "step": 225630 }, { "epoch": 18.75, "learning_rate": 1.500751046199041e-06, "loss": 0.7372, "step": 225640 }, { "epoch": 18.76, "learning_rate": 1.5006401906715074e-06, "loss": 0.7107, "step": 225650 }, { "epoch": 18.76, "learning_rate": 1.5005293351439737e-06, "loss": 0.759, "step": 225660 }, { "epoch": 18.76, "learning_rate": 1.50041847961644e-06, "loss": 0.7595, "step": 225670 }, { "epoch": 18.76, "learning_rate": 1.500307624088906e-06, "loss": 0.7833, "step": 225680 }, { "epoch": 18.76, "learning_rate": 1.5001967685613723e-06, "loss": 0.7556, "step": 225690 }, { "epoch": 18.76, "learning_rate": 1.5000859130338386e-06, "loss": 0.7328, "step": 225700 }, { "epoch": 18.76, "learning_rate": 1.499975057506305e-06, "loss": 0.7727, "step": 225710 }, { "epoch": 18.76, "learning_rate": 1.499864201978771e-06, "loss": 0.8356, "step": 225720 }, { "epoch": 18.76, "learning_rate": 1.4997533464512373e-06, "loss": 0.693, "step": 225730 }, { "epoch": 18.76, "learning_rate": 1.4996424909237036e-06, "loss": 0.7679, "step": 225740 }, { "epoch": 18.76, "learning_rate": 1.4995316353961697e-06, "loss": 0.7282, "step": 225750 }, { "epoch": 18.76, "learning_rate": 1.4994207798686362e-06, "loss": 0.7481, "step": 225760 }, { "epoch": 18.77, "learning_rate": 1.4993099243411025e-06, "loss": 0.7654, "step": 225770 }, { "epoch": 18.77, "learning_rate": 1.4991990688135688e-06, "loss": 0.7465, "step": 225780 }, { "epoch": 18.77, "learning_rate": 1.4990882132860349e-06, "loss": 0.7928, "step": 225790 }, { "epoch": 18.77, "learning_rate": 1.4989773577585012e-06, "loss": 0.7297, "step": 225800 }, { "epoch": 18.77, "learning_rate": 1.4988665022309675e-06, "loss": 0.7326, "step": 225810 }, { "epoch": 18.77, "learning_rate": 1.4987556467034337e-06, "loss": 0.8081, "step": 225820 }, { "epoch": 18.77, "learning_rate": 1.4986447911758998e-06, "loss": 0.7896, "step": 225830 }, { "epoch": 18.77, "learning_rate": 1.4985339356483661e-06, "loss": 0.8134, "step": 225840 }, { "epoch": 18.77, "learning_rate": 1.4984230801208324e-06, "loss": 0.781, "step": 225850 }, { "epoch": 18.77, "learning_rate": 1.4983122245932987e-06, "loss": 0.6888, "step": 225860 }, { "epoch": 18.77, "learning_rate": 1.4982013690657648e-06, "loss": 0.7919, "step": 225870 }, { "epoch": 18.77, "learning_rate": 1.498090513538231e-06, "loss": 0.7576, "step": 225880 }, { "epoch": 18.78, "learning_rate": 1.4979796580106976e-06, "loss": 0.7652, "step": 225890 }, { "epoch": 18.78, "learning_rate": 1.497868802483164e-06, "loss": 0.7053, "step": 225900 }, { "epoch": 18.78, "learning_rate": 1.49775794695563e-06, "loss": 0.7722, "step": 225910 }, { "epoch": 18.78, "learning_rate": 1.4976470914280963e-06, "loss": 0.7232, "step": 225920 }, { "epoch": 18.78, "learning_rate": 1.4975362359005626e-06, "loss": 0.7596, "step": 225930 }, { "epoch": 18.78, "learning_rate": 1.4974253803730289e-06, "loss": 0.7239, "step": 225940 }, { "epoch": 18.78, "learning_rate": 1.497314524845495e-06, "loss": 0.8286, "step": 225950 }, { "epoch": 18.78, "learning_rate": 1.4972036693179612e-06, "loss": 0.7129, "step": 225960 }, { "epoch": 18.78, "learning_rate": 1.4970928137904275e-06, "loss": 0.8358, "step": 225970 }, { "epoch": 18.78, "learning_rate": 1.4969819582628938e-06, "loss": 0.7452, "step": 225980 }, { "epoch": 18.78, "learning_rate": 1.49687110273536e-06, "loss": 0.6736, "step": 225990 }, { "epoch": 18.78, "learning_rate": 1.4967602472078262e-06, "loss": 0.7406, "step": 226000 }, { "epoch": 18.79, "learning_rate": 1.4966493916802927e-06, "loss": 0.746, "step": 226010 }, { "epoch": 18.79, "learning_rate": 1.496538536152759e-06, "loss": 0.803, "step": 226020 }, { "epoch": 18.79, "learning_rate": 1.496427680625225e-06, "loss": 0.7816, "step": 226030 }, { "epoch": 18.79, "learning_rate": 1.4963168250976914e-06, "loss": 0.6909, "step": 226040 }, { "epoch": 18.79, "learning_rate": 1.4962059695701577e-06, "loss": 0.698, "step": 226050 }, { "epoch": 18.79, "learning_rate": 1.496095114042624e-06, "loss": 0.7372, "step": 226060 }, { "epoch": 18.79, "learning_rate": 1.49598425851509e-06, "loss": 0.7983, "step": 226070 }, { "epoch": 18.79, "learning_rate": 1.4958734029875564e-06, "loss": 0.7279, "step": 226080 }, { "epoch": 18.79, "learning_rate": 1.4957625474600227e-06, "loss": 0.7872, "step": 226090 }, { "epoch": 18.79, "learning_rate": 1.495651691932489e-06, "loss": 0.8087, "step": 226100 }, { "epoch": 18.79, "learning_rate": 1.495540836404955e-06, "loss": 0.7614, "step": 226110 }, { "epoch": 18.79, "learning_rate": 1.4954299808774213e-06, "loss": 0.8154, "step": 226120 }, { "epoch": 18.8, "learning_rate": 1.4953191253498878e-06, "loss": 0.7846, "step": 226130 }, { "epoch": 18.8, "learning_rate": 1.4952082698223541e-06, "loss": 0.7318, "step": 226140 }, { "epoch": 18.8, "learning_rate": 1.4950974142948202e-06, "loss": 0.7606, "step": 226150 }, { "epoch": 18.8, "learning_rate": 1.4949865587672865e-06, "loss": 0.7479, "step": 226160 }, { "epoch": 18.8, "learning_rate": 1.4948757032397528e-06, "loss": 0.7869, "step": 226170 }, { "epoch": 18.8, "learning_rate": 1.494764847712219e-06, "loss": 0.7996, "step": 226180 }, { "epoch": 18.8, "learning_rate": 1.4946539921846852e-06, "loss": 0.7199, "step": 226190 }, { "epoch": 18.8, "learning_rate": 1.4945431366571515e-06, "loss": 0.7116, "step": 226200 }, { "epoch": 18.8, "learning_rate": 1.4944322811296178e-06, "loss": 0.7994, "step": 226210 }, { "epoch": 18.8, "learning_rate": 1.4943214256020839e-06, "loss": 0.7793, "step": 226220 }, { "epoch": 18.8, "learning_rate": 1.4942105700745502e-06, "loss": 0.7794, "step": 226230 }, { "epoch": 18.8, "learning_rate": 1.4940997145470165e-06, "loss": 0.7466, "step": 226240 }, { "epoch": 18.81, "learning_rate": 1.4939888590194828e-06, "loss": 0.7479, "step": 226250 }, { "epoch": 18.81, "learning_rate": 1.493878003491949e-06, "loss": 0.7654, "step": 226260 }, { "epoch": 18.81, "learning_rate": 1.4937671479644153e-06, "loss": 0.8186, "step": 226270 }, { "epoch": 18.81, "learning_rate": 1.4936562924368816e-06, "loss": 0.7651, "step": 226280 }, { "epoch": 18.81, "learning_rate": 1.493545436909348e-06, "loss": 0.827, "step": 226290 }, { "epoch": 18.81, "learning_rate": 1.493434581381814e-06, "loss": 0.7489, "step": 226300 }, { "epoch": 18.81, "learning_rate": 1.4933237258542803e-06, "loss": 0.7516, "step": 226310 }, { "epoch": 18.81, "learning_rate": 1.4932128703267466e-06, "loss": 0.8293, "step": 226320 }, { "epoch": 18.81, "learning_rate": 1.493102014799213e-06, "loss": 0.7612, "step": 226330 }, { "epoch": 18.81, "learning_rate": 1.492991159271679e-06, "loss": 0.7927, "step": 226340 }, { "epoch": 18.81, "learning_rate": 1.4928803037441453e-06, "loss": 0.7821, "step": 226350 }, { "epoch": 18.81, "learning_rate": 1.4927694482166116e-06, "loss": 0.7457, "step": 226360 }, { "epoch": 18.82, "learning_rate": 1.4926585926890779e-06, "loss": 0.7973, "step": 226370 }, { "epoch": 18.82, "learning_rate": 1.4925477371615442e-06, "loss": 0.7656, "step": 226380 }, { "epoch": 18.82, "learning_rate": 1.4924368816340105e-06, "loss": 0.7313, "step": 226390 }, { "epoch": 18.82, "learning_rate": 1.4923260261064768e-06, "loss": 0.7493, "step": 226400 }, { "epoch": 18.82, "learning_rate": 1.492215170578943e-06, "loss": 0.7434, "step": 226410 }, { "epoch": 18.82, "learning_rate": 1.4921043150514091e-06, "loss": 0.8026, "step": 226420 }, { "epoch": 18.82, "learning_rate": 1.4919934595238754e-06, "loss": 0.719, "step": 226430 }, { "epoch": 18.82, "learning_rate": 1.4918826039963417e-06, "loss": 0.7382, "step": 226440 }, { "epoch": 18.82, "learning_rate": 1.491771748468808e-06, "loss": 0.7386, "step": 226450 }, { "epoch": 18.82, "learning_rate": 1.4916608929412741e-06, "loss": 0.7388, "step": 226460 }, { "epoch": 18.82, "learning_rate": 1.4915500374137404e-06, "loss": 0.8072, "step": 226470 }, { "epoch": 18.82, "learning_rate": 1.4914391818862067e-06, "loss": 0.7399, "step": 226480 }, { "epoch": 18.83, "learning_rate": 1.491328326358673e-06, "loss": 0.7349, "step": 226490 }, { "epoch": 18.83, "learning_rate": 1.4912174708311393e-06, "loss": 0.7358, "step": 226500 }, { "epoch": 18.83, "learning_rate": 1.4911066153036056e-06, "loss": 0.774, "step": 226510 }, { "epoch": 18.83, "learning_rate": 1.4909957597760719e-06, "loss": 0.7713, "step": 226520 }, { "epoch": 18.83, "learning_rate": 1.4908849042485382e-06, "loss": 0.7892, "step": 226530 }, { "epoch": 18.83, "learning_rate": 1.4907740487210043e-06, "loss": 0.7032, "step": 226540 }, { "epoch": 18.83, "learning_rate": 1.4906631931934706e-06, "loss": 0.7436, "step": 226550 }, { "epoch": 18.83, "learning_rate": 1.4905523376659369e-06, "loss": 0.7125, "step": 226560 }, { "epoch": 18.83, "learning_rate": 1.490441482138403e-06, "loss": 0.765, "step": 226570 }, { "epoch": 18.83, "learning_rate": 1.4903306266108692e-06, "loss": 0.7007, "step": 226580 }, { "epoch": 18.83, "learning_rate": 1.4902197710833355e-06, "loss": 0.7546, "step": 226590 }, { "epoch": 18.83, "learning_rate": 1.4901089155558018e-06, "loss": 0.8128, "step": 226600 }, { "epoch": 18.84, "learning_rate": 1.489998060028268e-06, "loss": 0.7713, "step": 226610 }, { "epoch": 18.84, "learning_rate": 1.4898872045007342e-06, "loss": 0.7915, "step": 226620 }, { "epoch": 18.84, "learning_rate": 1.4897763489732007e-06, "loss": 0.8293, "step": 226630 }, { "epoch": 18.84, "learning_rate": 1.489665493445667e-06, "loss": 0.7425, "step": 226640 }, { "epoch": 18.84, "learning_rate": 1.489554637918133e-06, "loss": 0.7523, "step": 226650 }, { "epoch": 18.84, "learning_rate": 1.4894437823905994e-06, "loss": 0.7596, "step": 226660 }, { "epoch": 18.84, "learning_rate": 1.4893329268630657e-06, "loss": 0.7941, "step": 226670 }, { "epoch": 18.84, "learning_rate": 1.489222071335532e-06, "loss": 0.7429, "step": 226680 }, { "epoch": 18.84, "learning_rate": 1.489111215807998e-06, "loss": 0.6603, "step": 226690 }, { "epoch": 18.84, "learning_rate": 1.4890003602804643e-06, "loss": 0.7956, "step": 226700 }, { "epoch": 18.84, "learning_rate": 1.4888895047529306e-06, "loss": 0.7668, "step": 226710 }, { "epoch": 18.84, "learning_rate": 1.488778649225397e-06, "loss": 0.7849, "step": 226720 }, { "epoch": 18.85, "learning_rate": 1.488667793697863e-06, "loss": 0.7461, "step": 226730 }, { "epoch": 18.85, "learning_rate": 1.4885569381703293e-06, "loss": 0.8239, "step": 226740 }, { "epoch": 18.85, "learning_rate": 1.4884460826427958e-06, "loss": 0.7587, "step": 226750 }, { "epoch": 18.85, "learning_rate": 1.4883352271152621e-06, "loss": 0.7936, "step": 226760 }, { "epoch": 18.85, "learning_rate": 1.4882243715877282e-06, "loss": 0.8366, "step": 226770 }, { "epoch": 18.85, "learning_rate": 1.4881135160601945e-06, "loss": 0.7319, "step": 226780 }, { "epoch": 18.85, "learning_rate": 1.4880026605326608e-06, "loss": 0.7287, "step": 226790 }, { "epoch": 18.85, "learning_rate": 1.487891805005127e-06, "loss": 0.7733, "step": 226800 }, { "epoch": 18.85, "learning_rate": 1.4877809494775932e-06, "loss": 0.7882, "step": 226810 }, { "epoch": 18.85, "learning_rate": 1.4876700939500595e-06, "loss": 0.7579, "step": 226820 }, { "epoch": 18.85, "learning_rate": 1.4875592384225258e-06, "loss": 0.7537, "step": 226830 }, { "epoch": 18.85, "learning_rate": 1.487448382894992e-06, "loss": 0.7938, "step": 226840 }, { "epoch": 18.86, "learning_rate": 1.4873375273674581e-06, "loss": 0.8227, "step": 226850 }, { "epoch": 18.86, "learning_rate": 1.4872266718399244e-06, "loss": 0.8157, "step": 226860 }, { "epoch": 18.86, "learning_rate": 1.487115816312391e-06, "loss": 0.7558, "step": 226870 }, { "epoch": 18.86, "learning_rate": 1.4870049607848572e-06, "loss": 0.7686, "step": 226880 }, { "epoch": 18.86, "learning_rate": 1.4868941052573233e-06, "loss": 0.6942, "step": 226890 }, { "epoch": 18.86, "learning_rate": 1.4867832497297896e-06, "loss": 0.7074, "step": 226900 }, { "epoch": 18.86, "learning_rate": 1.486672394202256e-06, "loss": 0.7751, "step": 226910 }, { "epoch": 18.86, "learning_rate": 1.4865615386747222e-06, "loss": 0.7862, "step": 226920 }, { "epoch": 18.86, "learning_rate": 1.4864506831471883e-06, "loss": 0.7989, "step": 226930 }, { "epoch": 18.86, "learning_rate": 1.4863398276196546e-06, "loss": 0.7053, "step": 226940 }, { "epoch": 18.86, "learning_rate": 1.4862289720921209e-06, "loss": 0.7403, "step": 226950 }, { "epoch": 18.86, "learning_rate": 1.4861181165645872e-06, "loss": 0.7599, "step": 226960 }, { "epoch": 18.87, "learning_rate": 1.4860072610370533e-06, "loss": 0.7924, "step": 226970 }, { "epoch": 18.87, "learning_rate": 1.4858964055095196e-06, "loss": 0.6902, "step": 226980 }, { "epoch": 18.87, "learning_rate": 1.485785549981986e-06, "loss": 0.6965, "step": 226990 }, { "epoch": 18.87, "learning_rate": 1.4856746944544524e-06, "loss": 0.7701, "step": 227000 }, { "epoch": 18.87, "learning_rate": 1.4855638389269184e-06, "loss": 0.7681, "step": 227010 }, { "epoch": 18.87, "learning_rate": 1.4854529833993847e-06, "loss": 0.8104, "step": 227020 }, { "epoch": 18.87, "learning_rate": 1.485342127871851e-06, "loss": 0.755, "step": 227030 }, { "epoch": 18.87, "learning_rate": 1.4852312723443171e-06, "loss": 0.8046, "step": 227040 }, { "epoch": 18.87, "learning_rate": 1.4851204168167834e-06, "loss": 0.8426, "step": 227050 }, { "epoch": 18.87, "learning_rate": 1.4850095612892497e-06, "loss": 0.7427, "step": 227060 }, { "epoch": 18.87, "learning_rate": 1.484898705761716e-06, "loss": 0.7786, "step": 227070 }, { "epoch": 18.87, "learning_rate": 1.484787850234182e-06, "loss": 0.8258, "step": 227080 }, { "epoch": 18.88, "learning_rate": 1.4846769947066484e-06, "loss": 0.7559, "step": 227090 }, { "epoch": 18.88, "learning_rate": 1.4845661391791147e-06, "loss": 0.7259, "step": 227100 }, { "epoch": 18.88, "learning_rate": 1.484455283651581e-06, "loss": 0.7829, "step": 227110 }, { "epoch": 18.88, "learning_rate": 1.4843444281240473e-06, "loss": 0.7592, "step": 227120 }, { "epoch": 18.88, "learning_rate": 1.4842335725965136e-06, "loss": 0.7948, "step": 227130 }, { "epoch": 18.88, "learning_rate": 1.4841227170689799e-06, "loss": 0.7405, "step": 227140 }, { "epoch": 18.88, "learning_rate": 1.4840118615414462e-06, "loss": 0.7754, "step": 227150 }, { "epoch": 18.88, "learning_rate": 1.4839010060139122e-06, "loss": 0.7513, "step": 227160 }, { "epoch": 18.88, "learning_rate": 1.4837901504863785e-06, "loss": 0.7579, "step": 227170 }, { "epoch": 18.88, "learning_rate": 1.4836792949588448e-06, "loss": 0.7298, "step": 227180 }, { "epoch": 18.88, "learning_rate": 1.4835684394313111e-06, "loss": 0.7393, "step": 227190 }, { "epoch": 18.88, "learning_rate": 1.4834575839037772e-06, "loss": 0.8206, "step": 227200 }, { "epoch": 18.89, "learning_rate": 1.4833467283762435e-06, "loss": 0.7733, "step": 227210 }, { "epoch": 18.89, "learning_rate": 1.4832358728487098e-06, "loss": 0.8192, "step": 227220 }, { "epoch": 18.89, "learning_rate": 1.483125017321176e-06, "loss": 0.7902, "step": 227230 }, { "epoch": 18.89, "learning_rate": 1.4830141617936424e-06, "loss": 0.71, "step": 227240 }, { "epoch": 18.89, "learning_rate": 1.4829033062661087e-06, "loss": 0.761, "step": 227250 }, { "epoch": 18.89, "learning_rate": 1.482792450738575e-06, "loss": 0.7681, "step": 227260 }, { "epoch": 18.89, "learning_rate": 1.4826815952110413e-06, "loss": 0.77, "step": 227270 }, { "epoch": 18.89, "learning_rate": 1.4825707396835074e-06, "loss": 0.7717, "step": 227280 }, { "epoch": 18.89, "learning_rate": 1.4824598841559737e-06, "loss": 0.8106, "step": 227290 }, { "epoch": 18.89, "learning_rate": 1.48234902862844e-06, "loss": 0.777, "step": 227300 }, { "epoch": 18.89, "learning_rate": 1.4822381731009062e-06, "loss": 0.7589, "step": 227310 }, { "epoch": 18.89, "learning_rate": 1.4821273175733723e-06, "loss": 0.7785, "step": 227320 }, { "epoch": 18.9, "learning_rate": 1.4820164620458386e-06, "loss": 0.8122, "step": 227330 }, { "epoch": 18.9, "learning_rate": 1.481905606518305e-06, "loss": 0.7449, "step": 227340 }, { "epoch": 18.9, "learning_rate": 1.4817947509907712e-06, "loss": 0.7635, "step": 227350 }, { "epoch": 18.9, "learning_rate": 1.4816838954632375e-06, "loss": 0.7961, "step": 227360 }, { "epoch": 18.9, "learning_rate": 1.4815730399357038e-06, "loss": 0.8078, "step": 227370 }, { "epoch": 18.9, "learning_rate": 1.48146218440817e-06, "loss": 0.6983, "step": 227380 }, { "epoch": 18.9, "learning_rate": 1.4813513288806364e-06, "loss": 0.7522, "step": 227390 }, { "epoch": 18.9, "learning_rate": 1.4812404733531025e-06, "loss": 0.7969, "step": 227400 }, { "epoch": 18.9, "learning_rate": 1.4811296178255688e-06, "loss": 0.8254, "step": 227410 }, { "epoch": 18.9, "learning_rate": 1.481018762298035e-06, "loss": 0.7607, "step": 227420 }, { "epoch": 18.9, "learning_rate": 1.4809079067705012e-06, "loss": 0.7241, "step": 227430 }, { "epoch": 18.9, "learning_rate": 1.4807970512429675e-06, "loss": 0.8011, "step": 227440 }, { "epoch": 18.91, "learning_rate": 1.4806861957154337e-06, "loss": 0.7802, "step": 227450 }, { "epoch": 18.91, "learning_rate": 1.4805753401879e-06, "loss": 0.752, "step": 227460 }, { "epoch": 18.91, "learning_rate": 1.4804644846603661e-06, "loss": 0.7634, "step": 227470 }, { "epoch": 18.91, "learning_rate": 1.4803536291328324e-06, "loss": 0.8077, "step": 227480 }, { "epoch": 18.91, "learning_rate": 1.480242773605299e-06, "loss": 0.7748, "step": 227490 }, { "epoch": 18.91, "learning_rate": 1.4801319180777652e-06, "loss": 0.7595, "step": 227500 }, { "epoch": 18.91, "learning_rate": 1.4800210625502313e-06, "loss": 0.795, "step": 227510 }, { "epoch": 18.91, "learning_rate": 1.4799102070226976e-06, "loss": 0.7869, "step": 227520 }, { "epoch": 18.91, "learning_rate": 1.479799351495164e-06, "loss": 0.7268, "step": 227530 }, { "epoch": 18.91, "learning_rate": 1.4796884959676302e-06, "loss": 0.7737, "step": 227540 }, { "epoch": 18.91, "learning_rate": 1.4795776404400963e-06, "loss": 0.7822, "step": 227550 }, { "epoch": 18.91, "learning_rate": 1.4794667849125626e-06, "loss": 0.8014, "step": 227560 }, { "epoch": 18.92, "learning_rate": 1.4793559293850289e-06, "loss": 0.8579, "step": 227570 }, { "epoch": 18.92, "learning_rate": 1.4792450738574952e-06, "loss": 0.7572, "step": 227580 }, { "epoch": 18.92, "learning_rate": 1.4791342183299612e-06, "loss": 0.72, "step": 227590 }, { "epoch": 18.92, "learning_rate": 1.4790233628024275e-06, "loss": 0.7425, "step": 227600 }, { "epoch": 18.92, "learning_rate": 1.478912507274894e-06, "loss": 0.7797, "step": 227610 }, { "epoch": 18.92, "learning_rate": 1.4788016517473603e-06, "loss": 0.7969, "step": 227620 }, { "epoch": 18.92, "learning_rate": 1.4786907962198264e-06, "loss": 0.7355, "step": 227630 }, { "epoch": 18.92, "learning_rate": 1.4785799406922927e-06, "loss": 0.7276, "step": 227640 }, { "epoch": 18.92, "learning_rate": 1.478469085164759e-06, "loss": 0.76, "step": 227650 }, { "epoch": 18.92, "learning_rate": 1.4783582296372253e-06, "loss": 0.7349, "step": 227660 }, { "epoch": 18.92, "learning_rate": 1.4782473741096914e-06, "loss": 0.8474, "step": 227670 }, { "epoch": 18.92, "learning_rate": 1.4781365185821577e-06, "loss": 0.7849, "step": 227680 }, { "epoch": 18.93, "learning_rate": 1.478025663054624e-06, "loss": 0.7576, "step": 227690 }, { "epoch": 18.93, "learning_rate": 1.4779148075270903e-06, "loss": 0.7678, "step": 227700 }, { "epoch": 18.93, "learning_rate": 1.4778039519995564e-06, "loss": 0.7309, "step": 227710 }, { "epoch": 18.93, "learning_rate": 1.4776930964720227e-06, "loss": 0.801, "step": 227720 }, { "epoch": 18.93, "learning_rate": 1.4775822409444892e-06, "loss": 0.7981, "step": 227730 }, { "epoch": 18.93, "learning_rate": 1.4774713854169555e-06, "loss": 0.7667, "step": 227740 }, { "epoch": 18.93, "learning_rate": 1.4773605298894215e-06, "loss": 0.7166, "step": 227750 }, { "epoch": 18.93, "learning_rate": 1.4772496743618878e-06, "loss": 0.7454, "step": 227760 }, { "epoch": 18.93, "learning_rate": 1.4771388188343541e-06, "loss": 0.7801, "step": 227770 }, { "epoch": 18.93, "learning_rate": 1.4770279633068204e-06, "loss": 0.7549, "step": 227780 }, { "epoch": 18.93, "learning_rate": 1.4769171077792865e-06, "loss": 0.7761, "step": 227790 }, { "epoch": 18.93, "learning_rate": 1.4768062522517528e-06, "loss": 0.7888, "step": 227800 }, { "epoch": 18.94, "learning_rate": 1.4766953967242191e-06, "loss": 0.8056, "step": 227810 }, { "epoch": 18.94, "learning_rate": 1.4765845411966852e-06, "loss": 0.8018, "step": 227820 }, { "epoch": 18.94, "learning_rate": 1.4764736856691515e-06, "loss": 0.7288, "step": 227830 }, { "epoch": 18.94, "learning_rate": 1.4763628301416178e-06, "loss": 0.7549, "step": 227840 }, { "epoch": 18.94, "learning_rate": 1.4762519746140843e-06, "loss": 0.751, "step": 227850 }, { "epoch": 18.94, "learning_rate": 1.4761411190865504e-06, "loss": 0.7649, "step": 227860 }, { "epoch": 18.94, "learning_rate": 1.4760302635590167e-06, "loss": 0.7549, "step": 227870 }, { "epoch": 18.94, "learning_rate": 1.475919408031483e-06, "loss": 0.7218, "step": 227880 }, { "epoch": 18.94, "learning_rate": 1.4758085525039493e-06, "loss": 0.6837, "step": 227890 }, { "epoch": 18.94, "learning_rate": 1.4756976969764153e-06, "loss": 0.7366, "step": 227900 }, { "epoch": 18.94, "learning_rate": 1.4755868414488816e-06, "loss": 0.7773, "step": 227910 }, { "epoch": 18.94, "learning_rate": 1.475475985921348e-06, "loss": 0.8009, "step": 227920 }, { "epoch": 18.95, "learning_rate": 1.4753651303938142e-06, "loss": 0.755, "step": 227930 }, { "epoch": 18.95, "learning_rate": 1.4752542748662803e-06, "loss": 0.7379, "step": 227940 }, { "epoch": 18.95, "learning_rate": 1.4751434193387466e-06, "loss": 0.6955, "step": 227950 }, { "epoch": 18.95, "learning_rate": 1.475032563811213e-06, "loss": 0.7671, "step": 227960 }, { "epoch": 18.95, "learning_rate": 1.4749217082836792e-06, "loss": 0.7867, "step": 227970 }, { "epoch": 18.95, "learning_rate": 1.4748108527561455e-06, "loss": 0.7543, "step": 227980 }, { "epoch": 18.95, "learning_rate": 1.4746999972286118e-06, "loss": 0.772, "step": 227990 }, { "epoch": 18.95, "learning_rate": 1.474589141701078e-06, "loss": 0.7553, "step": 228000 }, { "epoch": 18.95, "learning_rate": 1.4744782861735444e-06, "loss": 0.8015, "step": 228010 }, { "epoch": 18.95, "learning_rate": 1.4743674306460105e-06, "loss": 0.7681, "step": 228020 }, { "epoch": 18.95, "learning_rate": 1.4742565751184768e-06, "loss": 0.7468, "step": 228030 }, { "epoch": 18.95, "learning_rate": 1.474145719590943e-06, "loss": 0.7479, "step": 228040 }, { "epoch": 18.96, "learning_rate": 1.4740348640634093e-06, "loss": 0.7265, "step": 228050 }, { "epoch": 18.96, "learning_rate": 1.4739240085358754e-06, "loss": 0.7023, "step": 228060 }, { "epoch": 18.96, "learning_rate": 1.4738131530083417e-06, "loss": 0.7654, "step": 228070 }, { "epoch": 18.96, "learning_rate": 1.473702297480808e-06, "loss": 0.7583, "step": 228080 }, { "epoch": 18.96, "learning_rate": 1.4735914419532743e-06, "loss": 0.7602, "step": 228090 }, { "epoch": 18.96, "learning_rate": 1.4734805864257406e-06, "loss": 0.7492, "step": 228100 }, { "epoch": 18.96, "learning_rate": 1.473369730898207e-06, "loss": 0.7105, "step": 228110 }, { "epoch": 18.96, "learning_rate": 1.4732588753706732e-06, "loss": 0.8484, "step": 228120 }, { "epoch": 18.96, "learning_rate": 1.4731480198431395e-06, "loss": 0.73, "step": 228130 }, { "epoch": 18.96, "learning_rate": 1.4730371643156056e-06, "loss": 0.7678, "step": 228140 }, { "epoch": 18.96, "learning_rate": 1.4729263087880719e-06, "loss": 0.7431, "step": 228150 }, { "epoch": 18.96, "learning_rate": 1.4728154532605382e-06, "loss": 0.7789, "step": 228160 }, { "epoch": 18.97, "learning_rate": 1.4727045977330045e-06, "loss": 0.8459, "step": 228170 }, { "epoch": 18.97, "learning_rate": 1.4725937422054706e-06, "loss": 0.805, "step": 228180 }, { "epoch": 18.97, "learning_rate": 1.4724828866779368e-06, "loss": 0.7595, "step": 228190 }, { "epoch": 18.97, "learning_rate": 1.4723720311504031e-06, "loss": 0.6998, "step": 228200 }, { "epoch": 18.97, "learning_rate": 1.4722611756228692e-06, "loss": 0.7639, "step": 228210 }, { "epoch": 18.97, "learning_rate": 1.4721503200953357e-06, "loss": 0.8275, "step": 228220 }, { "epoch": 18.97, "learning_rate": 1.472039464567802e-06, "loss": 0.7998, "step": 228230 }, { "epoch": 18.97, "learning_rate": 1.4719286090402683e-06, "loss": 0.7706, "step": 228240 }, { "epoch": 18.97, "learning_rate": 1.4718177535127346e-06, "loss": 0.7532, "step": 228250 }, { "epoch": 18.97, "learning_rate": 1.4717068979852007e-06, "loss": 0.7271, "step": 228260 }, { "epoch": 18.97, "learning_rate": 1.471596042457667e-06, "loss": 0.7832, "step": 228270 }, { "epoch": 18.97, "learning_rate": 1.4714851869301333e-06, "loss": 0.7173, "step": 228280 }, { "epoch": 18.98, "learning_rate": 1.4713743314025994e-06, "loss": 0.7285, "step": 228290 }, { "epoch": 18.98, "learning_rate": 1.4712634758750657e-06, "loss": 0.7745, "step": 228300 }, { "epoch": 18.98, "learning_rate": 1.471152620347532e-06, "loss": 0.7302, "step": 228310 }, { "epoch": 18.98, "learning_rate": 1.4710417648199983e-06, "loss": 0.7693, "step": 228320 }, { "epoch": 18.98, "learning_rate": 1.4709309092924643e-06, "loss": 0.7084, "step": 228330 }, { "epoch": 18.98, "learning_rate": 1.4708200537649306e-06, "loss": 0.7504, "step": 228340 }, { "epoch": 18.98, "learning_rate": 1.4707091982373972e-06, "loss": 0.7365, "step": 228350 }, { "epoch": 18.98, "learning_rate": 1.4705983427098634e-06, "loss": 0.7421, "step": 228360 }, { "epoch": 18.98, "learning_rate": 1.4704874871823295e-06, "loss": 0.7902, "step": 228370 }, { "epoch": 18.98, "learning_rate": 1.4703766316547958e-06, "loss": 0.6583, "step": 228380 }, { "epoch": 18.98, "learning_rate": 1.4702657761272621e-06, "loss": 0.7677, "step": 228390 }, { "epoch": 18.98, "learning_rate": 1.4701549205997284e-06, "loss": 0.7545, "step": 228400 }, { "epoch": 18.99, "learning_rate": 1.4700440650721945e-06, "loss": 0.7492, "step": 228410 }, { "epoch": 18.99, "learning_rate": 1.4699332095446608e-06, "loss": 0.7699, "step": 228420 }, { "epoch": 18.99, "learning_rate": 1.469822354017127e-06, "loss": 0.7589, "step": 228430 }, { "epoch": 18.99, "learning_rate": 1.4697114984895934e-06, "loss": 0.7705, "step": 228440 }, { "epoch": 18.99, "learning_rate": 1.4696006429620595e-06, "loss": 0.818, "step": 228450 }, { "epoch": 18.99, "learning_rate": 1.4694897874345258e-06, "loss": 0.7804, "step": 228460 }, { "epoch": 18.99, "learning_rate": 1.4693789319069923e-06, "loss": 0.8677, "step": 228470 }, { "epoch": 18.99, "learning_rate": 1.4692680763794586e-06, "loss": 0.7599, "step": 228480 }, { "epoch": 18.99, "learning_rate": 1.4691572208519247e-06, "loss": 0.797, "step": 228490 }, { "epoch": 18.99, "learning_rate": 1.469046365324391e-06, "loss": 0.7436, "step": 228500 }, { "epoch": 18.99, "learning_rate": 1.4689355097968572e-06, "loss": 0.8199, "step": 228510 }, { "epoch": 18.99, "learning_rate": 1.4688246542693235e-06, "loss": 0.8025, "step": 228520 }, { "epoch": 19.0, "learning_rate": 1.4687137987417896e-06, "loss": 0.7038, "step": 228530 }, { "epoch": 19.0, "learning_rate": 1.468602943214256e-06, "loss": 0.7169, "step": 228540 }, { "epoch": 19.0, "learning_rate": 1.4684920876867222e-06, "loss": 0.7764, "step": 228550 }, { "epoch": 19.0, "learning_rate": 1.4683812321591885e-06, "loss": 0.742, "step": 228560 }, { "epoch": 19.0, "learning_rate": 1.4682703766316546e-06, "loss": 0.717, "step": 228570 }, { "epoch": 19.0, "learning_rate": 1.4681595211041209e-06, "loss": 0.7379, "step": 228580 }, { "epoch": 19.0, "eval_loss": 1.1125543117523193, "eval_runtime": 356.1094, "eval_samples_per_second": 7.509, "eval_steps_per_second": 3.754, "eval_wer": 0.6409948533947347, "step": 228589 }, { "epoch": 19.0, "learning_rate": 1.4680486655765874e-06, "loss": 0.786, "step": 228590 }, { "epoch": 19.0, "learning_rate": 1.467948895601807e-06, "loss": 0.8122, "step": 228600 }, { "epoch": 19.0, "learning_rate": 1.4678380400742732e-06, "loss": 0.7316, "step": 228610 }, { "epoch": 19.0, "learning_rate": 1.4677271845467393e-06, "loss": 0.7921, "step": 228620 }, { "epoch": 19.0, "learning_rate": 1.4676163290192056e-06, "loss": 0.7264, "step": 228630 }, { "epoch": 19.0, "learning_rate": 1.467505473491672e-06, "loss": 0.7081, "step": 228640 }, { "epoch": 19.01, "learning_rate": 1.4673946179641382e-06, "loss": 0.7968, "step": 228650 }, { "epoch": 19.01, "learning_rate": 1.4672837624366043e-06, "loss": 0.7466, "step": 228660 }, { "epoch": 19.01, "learning_rate": 1.4671729069090706e-06, "loss": 0.7826, "step": 228670 }, { "epoch": 19.01, "learning_rate": 1.467062051381537e-06, "loss": 0.79, "step": 228680 }, { "epoch": 19.01, "learning_rate": 1.4669511958540034e-06, "loss": 0.7454, "step": 228690 }, { "epoch": 19.01, "learning_rate": 1.4668403403264695e-06, "loss": 0.7765, "step": 228700 }, { "epoch": 19.01, "learning_rate": 1.4667294847989358e-06, "loss": 0.8218, "step": 228710 }, { "epoch": 19.01, "learning_rate": 1.466618629271402e-06, "loss": 0.7896, "step": 228720 }, { "epoch": 19.01, "learning_rate": 1.4665077737438683e-06, "loss": 0.7299, "step": 228730 }, { "epoch": 19.01, "learning_rate": 1.4663969182163344e-06, "loss": 0.7521, "step": 228740 }, { "epoch": 19.01, "learning_rate": 1.4662860626888007e-06, "loss": 0.8004, "step": 228750 }, { "epoch": 19.01, "learning_rate": 1.466175207161267e-06, "loss": 0.7031, "step": 228760 }, { "epoch": 19.02, "learning_rate": 1.466064351633733e-06, "loss": 0.7705, "step": 228770 }, { "epoch": 19.02, "learning_rate": 1.4659534961061994e-06, "loss": 0.7159, "step": 228780 }, { "epoch": 19.02, "learning_rate": 1.4658426405786657e-06, "loss": 0.7598, "step": 228790 }, { "epoch": 19.02, "learning_rate": 1.4657317850511322e-06, "loss": 0.8057, "step": 228800 }, { "epoch": 19.02, "learning_rate": 1.4656209295235985e-06, "loss": 0.7506, "step": 228810 }, { "epoch": 19.02, "learning_rate": 1.4655100739960646e-06, "loss": 0.7249, "step": 228820 }, { "epoch": 19.02, "learning_rate": 1.4653992184685309e-06, "loss": 0.7862, "step": 228830 }, { "epoch": 19.02, "learning_rate": 1.4652883629409972e-06, "loss": 0.7354, "step": 228840 }, { "epoch": 19.02, "learning_rate": 1.4651775074134633e-06, "loss": 0.7416, "step": 228850 }, { "epoch": 19.02, "learning_rate": 1.4650666518859296e-06, "loss": 0.7142, "step": 228860 }, { "epoch": 19.02, "learning_rate": 1.4649557963583958e-06, "loss": 0.7196, "step": 228870 }, { "epoch": 19.02, "learning_rate": 1.4648449408308621e-06, "loss": 0.8343, "step": 228880 }, { "epoch": 19.03, "learning_rate": 1.4647340853033282e-06, "loss": 0.7061, "step": 228890 }, { "epoch": 19.03, "learning_rate": 1.4646232297757945e-06, "loss": 0.7765, "step": 228900 }, { "epoch": 19.03, "learning_rate": 1.4645123742482608e-06, "loss": 0.7217, "step": 228910 }, { "epoch": 19.03, "learning_rate": 1.4644015187207271e-06, "loss": 0.7587, "step": 228920 }, { "epoch": 19.03, "learning_rate": 1.4642906631931934e-06, "loss": 0.7646, "step": 228930 }, { "epoch": 19.03, "learning_rate": 1.4641798076656597e-06, "loss": 0.7606, "step": 228940 }, { "epoch": 19.03, "learning_rate": 1.464068952138126e-06, "loss": 0.7954, "step": 228950 }, { "epoch": 19.03, "learning_rate": 1.4639580966105923e-06, "loss": 0.7512, "step": 228960 }, { "epoch": 19.03, "learning_rate": 1.4638472410830584e-06, "loss": 0.8265, "step": 228970 }, { "epoch": 19.03, "learning_rate": 1.4637363855555247e-06, "loss": 0.8249, "step": 228980 }, { "epoch": 19.03, "learning_rate": 1.463625530027991e-06, "loss": 0.7731, "step": 228990 }, { "epoch": 19.03, "learning_rate": 1.4635146745004573e-06, "loss": 0.7407, "step": 229000 }, { "epoch": 19.03, "learning_rate": 1.4634038189729233e-06, "loss": 0.7831, "step": 229010 }, { "epoch": 19.04, "learning_rate": 1.4632929634453896e-06, "loss": 0.7184, "step": 229020 }, { "epoch": 19.04, "learning_rate": 1.463182107917856e-06, "loss": 0.7706, "step": 229030 }, { "epoch": 19.04, "learning_rate": 1.4630712523903222e-06, "loss": 0.7928, "step": 229040 }, { "epoch": 19.04, "learning_rate": 1.4629603968627885e-06, "loss": 0.7359, "step": 229050 }, { "epoch": 19.04, "learning_rate": 1.4628495413352548e-06, "loss": 0.7203, "step": 229060 }, { "epoch": 19.04, "learning_rate": 1.4627386858077211e-06, "loss": 0.7466, "step": 229070 }, { "epoch": 19.04, "learning_rate": 1.4626278302801874e-06, "loss": 0.7508, "step": 229080 }, { "epoch": 19.04, "learning_rate": 1.4625169747526535e-06, "loss": 0.7338, "step": 229090 }, { "epoch": 19.04, "learning_rate": 1.4624061192251198e-06, "loss": 0.7225, "step": 229100 }, { "epoch": 19.04, "learning_rate": 1.462295263697586e-06, "loss": 0.7749, "step": 229110 }, { "epoch": 19.04, "learning_rate": 1.4621844081700524e-06, "loss": 0.7546, "step": 229120 }, { "epoch": 19.04, "learning_rate": 1.4620735526425185e-06, "loss": 0.6912, "step": 229130 }, { "epoch": 19.05, "learning_rate": 1.4619626971149848e-06, "loss": 0.7617, "step": 229140 }, { "epoch": 19.05, "learning_rate": 1.461851841587451e-06, "loss": 0.7995, "step": 229150 }, { "epoch": 19.05, "learning_rate": 1.4617409860599174e-06, "loss": 0.7078, "step": 229160 }, { "epoch": 19.05, "learning_rate": 1.4616301305323836e-06, "loss": 0.7707, "step": 229170 }, { "epoch": 19.05, "learning_rate": 1.46151927500485e-06, "loss": 0.7616, "step": 229180 }, { "epoch": 19.05, "learning_rate": 1.4614084194773162e-06, "loss": 0.7479, "step": 229190 }, { "epoch": 19.05, "learning_rate": 1.4612975639497825e-06, "loss": 0.8204, "step": 229200 }, { "epoch": 19.05, "learning_rate": 1.4611867084222486e-06, "loss": 0.7574, "step": 229210 }, { "epoch": 19.05, "learning_rate": 1.461075852894715e-06, "loss": 0.7679, "step": 229220 }, { "epoch": 19.05, "learning_rate": 1.4609649973671812e-06, "loss": 0.7633, "step": 229230 }, { "epoch": 19.05, "learning_rate": 1.4608541418396473e-06, "loss": 0.744, "step": 229240 }, { "epoch": 19.05, "learning_rate": 1.4607432863121136e-06, "loss": 0.807, "step": 229250 }, { "epoch": 19.06, "learning_rate": 1.4606324307845799e-06, "loss": 0.7914, "step": 229260 }, { "epoch": 19.06, "learning_rate": 1.4605215752570462e-06, "loss": 0.7759, "step": 229270 }, { "epoch": 19.06, "learning_rate": 1.4604107197295123e-06, "loss": 0.769, "step": 229280 }, { "epoch": 19.06, "learning_rate": 1.4602998642019788e-06, "loss": 0.654, "step": 229290 }, { "epoch": 19.06, "learning_rate": 1.460189008674445e-06, "loss": 0.7562, "step": 229300 }, { "epoch": 19.06, "learning_rate": 1.4600781531469114e-06, "loss": 0.7526, "step": 229310 }, { "epoch": 19.06, "learning_rate": 1.4599672976193774e-06, "loss": 0.7523, "step": 229320 }, { "epoch": 19.06, "learning_rate": 1.4598564420918437e-06, "loss": 0.7743, "step": 229330 }, { "epoch": 19.06, "learning_rate": 1.45974558656431e-06, "loss": 0.7662, "step": 229340 }, { "epoch": 19.06, "learning_rate": 1.4596347310367763e-06, "loss": 0.7842, "step": 229350 }, { "epoch": 19.06, "learning_rate": 1.4595238755092424e-06, "loss": 0.7625, "step": 229360 }, { "epoch": 19.06, "learning_rate": 1.4594130199817087e-06, "loss": 0.78, "step": 229370 }, { "epoch": 19.07, "learning_rate": 1.459302164454175e-06, "loss": 0.75, "step": 229380 }, { "epoch": 19.07, "learning_rate": 1.4591913089266413e-06, "loss": 0.6993, "step": 229390 }, { "epoch": 19.07, "learning_rate": 1.4590804533991074e-06, "loss": 0.7536, "step": 229400 }, { "epoch": 19.07, "learning_rate": 1.4589695978715737e-06, "loss": 0.7786, "step": 229410 }, { "epoch": 19.07, "learning_rate": 1.4588587423440402e-06, "loss": 0.7381, "step": 229420 }, { "epoch": 19.07, "learning_rate": 1.4587478868165065e-06, "loss": 0.7674, "step": 229430 }, { "epoch": 19.07, "learning_rate": 1.4586370312889726e-06, "loss": 0.7614, "step": 229440 }, { "epoch": 19.07, "learning_rate": 1.4585261757614389e-06, "loss": 0.7983, "step": 229450 }, { "epoch": 19.07, "learning_rate": 1.4584153202339052e-06, "loss": 0.7448, "step": 229460 }, { "epoch": 19.07, "learning_rate": 1.4583044647063714e-06, "loss": 0.7331, "step": 229470 }, { "epoch": 19.07, "learning_rate": 1.4581936091788375e-06, "loss": 0.722, "step": 229480 }, { "epoch": 19.07, "learning_rate": 1.4580827536513038e-06, "loss": 0.7277, "step": 229490 }, { "epoch": 19.08, "learning_rate": 1.4579718981237701e-06, "loss": 0.8207, "step": 229500 }, { "epoch": 19.08, "learning_rate": 1.4578610425962364e-06, "loss": 0.8059, "step": 229510 }, { "epoch": 19.08, "learning_rate": 1.4577501870687025e-06, "loss": 0.8072, "step": 229520 }, { "epoch": 19.08, "learning_rate": 1.4576393315411688e-06, "loss": 0.76, "step": 229530 }, { "epoch": 19.08, "learning_rate": 1.4575284760136353e-06, "loss": 0.7767, "step": 229540 }, { "epoch": 19.08, "learning_rate": 1.4574176204861016e-06, "loss": 0.7961, "step": 229550 }, { "epoch": 19.08, "learning_rate": 1.4573067649585677e-06, "loss": 0.7249, "step": 229560 }, { "epoch": 19.08, "learning_rate": 1.457195909431034e-06, "loss": 0.7514, "step": 229570 }, { "epoch": 19.08, "learning_rate": 1.4570850539035003e-06, "loss": 0.7389, "step": 229580 }, { "epoch": 19.08, "learning_rate": 1.4569741983759666e-06, "loss": 0.7227, "step": 229590 }, { "epoch": 19.08, "learning_rate": 1.4568633428484327e-06, "loss": 0.8211, "step": 229600 }, { "epoch": 19.08, "learning_rate": 1.456752487320899e-06, "loss": 0.7295, "step": 229610 }, { "epoch": 19.09, "learning_rate": 1.4566416317933652e-06, "loss": 0.7605, "step": 229620 }, { "epoch": 19.09, "learning_rate": 1.4565307762658313e-06, "loss": 0.7538, "step": 229630 }, { "epoch": 19.09, "learning_rate": 1.4564199207382976e-06, "loss": 0.7358, "step": 229640 }, { "epoch": 19.09, "learning_rate": 1.456309065210764e-06, "loss": 0.8133, "step": 229650 }, { "epoch": 19.09, "learning_rate": 1.4561982096832304e-06, "loss": 0.7363, "step": 229660 }, { "epoch": 19.09, "learning_rate": 1.4560873541556965e-06, "loss": 0.7458, "step": 229670 }, { "epoch": 19.09, "learning_rate": 1.4559764986281628e-06, "loss": 0.7928, "step": 229680 }, { "epoch": 19.09, "learning_rate": 1.455865643100629e-06, "loss": 0.8468, "step": 229690 }, { "epoch": 19.09, "learning_rate": 1.4557547875730954e-06, "loss": 0.7851, "step": 229700 }, { "epoch": 19.09, "learning_rate": 1.4556439320455615e-06, "loss": 0.7019, "step": 229710 }, { "epoch": 19.09, "learning_rate": 1.4555330765180278e-06, "loss": 0.7385, "step": 229720 }, { "epoch": 19.09, "learning_rate": 1.455422220990494e-06, "loss": 0.7723, "step": 229730 }, { "epoch": 19.1, "learning_rate": 1.4553113654629604e-06, "loss": 0.7564, "step": 229740 }, { "epoch": 19.1, "learning_rate": 1.4552005099354264e-06, "loss": 0.7525, "step": 229750 }, { "epoch": 19.1, "learning_rate": 1.4550896544078927e-06, "loss": 0.7613, "step": 229760 }, { "epoch": 19.1, "learning_rate": 1.454978798880359e-06, "loss": 0.7753, "step": 229770 }, { "epoch": 19.1, "learning_rate": 1.4548679433528253e-06, "loss": 0.7655, "step": 229780 }, { "epoch": 19.1, "learning_rate": 1.4547570878252916e-06, "loss": 0.7931, "step": 229790 }, { "epoch": 19.1, "learning_rate": 1.454646232297758e-06, "loss": 0.8041, "step": 229800 }, { "epoch": 19.1, "learning_rate": 1.4545353767702242e-06, "loss": 0.7843, "step": 229810 }, { "epoch": 19.1, "learning_rate": 1.4544245212426905e-06, "loss": 0.7564, "step": 229820 }, { "epoch": 19.1, "learning_rate": 1.4543136657151566e-06, "loss": 0.7725, "step": 229830 }, { "epoch": 19.1, "learning_rate": 1.4542028101876229e-06, "loss": 0.7475, "step": 229840 }, { "epoch": 19.1, "learning_rate": 1.4540919546600892e-06, "loss": 0.719, "step": 229850 }, { "epoch": 19.11, "learning_rate": 1.4539810991325555e-06, "loss": 0.7691, "step": 229860 }, { "epoch": 19.11, "learning_rate": 1.4538702436050216e-06, "loss": 0.7334, "step": 229870 }, { "epoch": 19.11, "learning_rate": 1.4537593880774879e-06, "loss": 0.7442, "step": 229880 }, { "epoch": 19.11, "learning_rate": 1.4536485325499542e-06, "loss": 0.7863, "step": 229890 }, { "epoch": 19.11, "learning_rate": 1.4535376770224205e-06, "loss": 0.795, "step": 229900 }, { "epoch": 19.11, "learning_rate": 1.4534268214948867e-06, "loss": 0.7134, "step": 229910 }, { "epoch": 19.11, "learning_rate": 1.453315965967353e-06, "loss": 0.7498, "step": 229920 }, { "epoch": 19.11, "learning_rate": 1.4532051104398193e-06, "loss": 0.7567, "step": 229930 }, { "epoch": 19.11, "learning_rate": 1.4530942549122856e-06, "loss": 0.7778, "step": 229940 }, { "epoch": 19.11, "learning_rate": 1.4529833993847517e-06, "loss": 0.8197, "step": 229950 }, { "epoch": 19.11, "learning_rate": 1.452872543857218e-06, "loss": 0.796, "step": 229960 }, { "epoch": 19.11, "learning_rate": 1.4527616883296843e-06, "loss": 0.7885, "step": 229970 }, { "epoch": 19.12, "learning_rate": 1.4526508328021506e-06, "loss": 0.7696, "step": 229980 }, { "epoch": 19.12, "learning_rate": 1.4525399772746167e-06, "loss": 0.7911, "step": 229990 }, { "epoch": 19.12, "learning_rate": 1.452429121747083e-06, "loss": 0.7527, "step": 230000 }, { "epoch": 19.12, "learning_rate": 1.4523182662195493e-06, "loss": 0.7388, "step": 230010 }, { "epoch": 19.12, "learning_rate": 1.4522074106920154e-06, "loss": 0.7724, "step": 230020 }, { "epoch": 19.12, "learning_rate": 1.4520965551644819e-06, "loss": 0.789, "step": 230030 }, { "epoch": 19.12, "learning_rate": 1.4519856996369482e-06, "loss": 0.7469, "step": 230040 }, { "epoch": 19.12, "learning_rate": 1.4518748441094145e-06, "loss": 0.8031, "step": 230050 }, { "epoch": 19.12, "learning_rate": 1.4517639885818805e-06, "loss": 0.7485, "step": 230060 }, { "epoch": 19.12, "learning_rate": 1.4516531330543468e-06, "loss": 0.7046, "step": 230070 }, { "epoch": 19.12, "learning_rate": 1.4515422775268131e-06, "loss": 0.7884, "step": 230080 }, { "epoch": 19.12, "learning_rate": 1.4514314219992794e-06, "loss": 0.7667, "step": 230090 }, { "epoch": 19.13, "learning_rate": 1.4513205664717455e-06, "loss": 0.7856, "step": 230100 }, { "epoch": 19.13, "learning_rate": 1.4512097109442118e-06, "loss": 0.705, "step": 230110 }, { "epoch": 19.13, "learning_rate": 1.451098855416678e-06, "loss": 0.7438, "step": 230120 }, { "epoch": 19.13, "learning_rate": 1.4509879998891444e-06, "loss": 0.732, "step": 230130 }, { "epoch": 19.13, "learning_rate": 1.4508771443616105e-06, "loss": 0.7295, "step": 230140 }, { "epoch": 19.13, "learning_rate": 1.450766288834077e-06, "loss": 0.7787, "step": 230150 }, { "epoch": 19.13, "learning_rate": 1.4506554333065433e-06, "loss": 0.7136, "step": 230160 }, { "epoch": 19.13, "learning_rate": 1.4505445777790096e-06, "loss": 0.7499, "step": 230170 }, { "epoch": 19.13, "learning_rate": 1.4504337222514757e-06, "loss": 0.7264, "step": 230180 }, { "epoch": 19.13, "learning_rate": 1.450322866723942e-06, "loss": 0.7629, "step": 230190 }, { "epoch": 19.13, "learning_rate": 1.4502120111964083e-06, "loss": 0.7554, "step": 230200 }, { "epoch": 19.13, "learning_rate": 1.4501011556688746e-06, "loss": 0.753, "step": 230210 }, { "epoch": 19.14, "learning_rate": 1.4499903001413406e-06, "loss": 0.7255, "step": 230220 }, { "epoch": 19.14, "learning_rate": 1.449879444613807e-06, "loss": 0.7279, "step": 230230 }, { "epoch": 19.14, "learning_rate": 1.4497685890862732e-06, "loss": 0.7824, "step": 230240 }, { "epoch": 19.14, "learning_rate": 1.4496577335587395e-06, "loss": 0.8, "step": 230250 }, { "epoch": 19.14, "learning_rate": 1.4495468780312056e-06, "loss": 0.7584, "step": 230260 }, { "epoch": 19.14, "learning_rate": 1.449436022503672e-06, "loss": 0.7746, "step": 230270 }, { "epoch": 19.14, "learning_rate": 1.4493251669761384e-06, "loss": 0.7111, "step": 230280 }, { "epoch": 19.14, "learning_rate": 1.4492143114486047e-06, "loss": 0.7634, "step": 230290 }, { "epoch": 19.14, "learning_rate": 1.4491034559210708e-06, "loss": 0.759, "step": 230300 }, { "epoch": 19.14, "learning_rate": 1.448992600393537e-06, "loss": 0.7465, "step": 230310 }, { "epoch": 19.14, "learning_rate": 1.4488817448660034e-06, "loss": 0.7626, "step": 230320 }, { "epoch": 19.14, "learning_rate": 1.4487708893384697e-06, "loss": 0.7156, "step": 230330 }, { "epoch": 19.15, "learning_rate": 1.4486600338109358e-06, "loss": 0.7287, "step": 230340 }, { "epoch": 19.15, "learning_rate": 1.448549178283402e-06, "loss": 0.7784, "step": 230350 }, { "epoch": 19.15, "learning_rate": 1.4484383227558683e-06, "loss": 0.7631, "step": 230360 }, { "epoch": 19.15, "learning_rate": 1.4483274672283346e-06, "loss": 0.7616, "step": 230370 }, { "epoch": 19.15, "learning_rate": 1.4482166117008007e-06, "loss": 0.7798, "step": 230380 }, { "epoch": 19.15, "learning_rate": 1.448105756173267e-06, "loss": 0.7469, "step": 230390 }, { "epoch": 19.15, "learning_rate": 1.4479949006457335e-06, "loss": 0.7481, "step": 230400 }, { "epoch": 19.15, "learning_rate": 1.4478840451181998e-06, "loss": 0.7579, "step": 230410 }, { "epoch": 19.15, "learning_rate": 1.447773189590666e-06, "loss": 0.7228, "step": 230420 }, { "epoch": 19.15, "learning_rate": 1.4476623340631322e-06, "loss": 0.7345, "step": 230430 }, { "epoch": 19.15, "learning_rate": 1.4475514785355985e-06, "loss": 0.7094, "step": 230440 }, { "epoch": 19.15, "learning_rate": 1.4474406230080648e-06, "loss": 0.7817, "step": 230450 }, { "epoch": 19.16, "learning_rate": 1.4473297674805309e-06, "loss": 0.71, "step": 230460 }, { "epoch": 19.16, "learning_rate": 1.4472189119529972e-06, "loss": 0.7375, "step": 230470 }, { "epoch": 19.16, "learning_rate": 1.4471080564254635e-06, "loss": 0.7605, "step": 230480 }, { "epoch": 19.16, "learning_rate": 1.4469972008979295e-06, "loss": 0.7372, "step": 230490 }, { "epoch": 19.16, "learning_rate": 1.4468863453703958e-06, "loss": 0.7805, "step": 230500 }, { "epoch": 19.16, "learning_rate": 1.4467754898428621e-06, "loss": 0.726, "step": 230510 }, { "epoch": 19.16, "learning_rate": 1.4466646343153286e-06, "loss": 0.7433, "step": 230520 }, { "epoch": 19.16, "learning_rate": 1.4465537787877947e-06, "loss": 0.6891, "step": 230530 }, { "epoch": 19.16, "learning_rate": 1.446442923260261e-06, "loss": 0.7775, "step": 230540 }, { "epoch": 19.16, "learning_rate": 1.4463320677327273e-06, "loss": 0.8092, "step": 230550 }, { "epoch": 19.16, "learning_rate": 1.4462212122051936e-06, "loss": 0.7604, "step": 230560 }, { "epoch": 19.16, "learning_rate": 1.4461103566776597e-06, "loss": 0.6742, "step": 230570 }, { "epoch": 19.17, "learning_rate": 1.445999501150126e-06, "loss": 0.7864, "step": 230580 }, { "epoch": 19.17, "learning_rate": 1.4458886456225923e-06, "loss": 0.7712, "step": 230590 }, { "epoch": 19.17, "learning_rate": 1.4457777900950586e-06, "loss": 0.8181, "step": 230600 }, { "epoch": 19.17, "learning_rate": 1.4456669345675247e-06, "loss": 0.7661, "step": 230610 }, { "epoch": 19.17, "learning_rate": 1.445556079039991e-06, "loss": 0.8276, "step": 230620 }, { "epoch": 19.17, "learning_rate": 1.4454452235124573e-06, "loss": 0.8001, "step": 230630 }, { "epoch": 19.17, "learning_rate": 1.4453343679849236e-06, "loss": 0.7287, "step": 230640 }, { "epoch": 19.17, "learning_rate": 1.4452235124573899e-06, "loss": 0.7067, "step": 230650 }, { "epoch": 19.17, "learning_rate": 1.4451126569298561e-06, "loss": 0.7876, "step": 230660 }, { "epoch": 19.17, "learning_rate": 1.4450018014023224e-06, "loss": 0.76, "step": 230670 }, { "epoch": 19.17, "learning_rate": 1.4448909458747887e-06, "loss": 0.7308, "step": 230680 }, { "epoch": 19.17, "learning_rate": 1.4447800903472548e-06, "loss": 0.7619, "step": 230690 }, { "epoch": 19.18, "learning_rate": 1.4446692348197211e-06, "loss": 0.8443, "step": 230700 }, { "epoch": 19.18, "learning_rate": 1.4445583792921874e-06, "loss": 0.7704, "step": 230710 }, { "epoch": 19.18, "learning_rate": 1.4444475237646537e-06, "loss": 0.7546, "step": 230720 }, { "epoch": 19.18, "learning_rate": 1.4443366682371198e-06, "loss": 0.7416, "step": 230730 }, { "epoch": 19.18, "learning_rate": 1.444225812709586e-06, "loss": 0.7564, "step": 230740 }, { "epoch": 19.18, "learning_rate": 1.4441149571820524e-06, "loss": 0.8026, "step": 230750 }, { "epoch": 19.18, "learning_rate": 1.4440041016545187e-06, "loss": 0.7569, "step": 230760 }, { "epoch": 19.18, "learning_rate": 1.443893246126985e-06, "loss": 0.7635, "step": 230770 }, { "epoch": 19.18, "learning_rate": 1.4437823905994513e-06, "loss": 0.7722, "step": 230780 }, { "epoch": 19.18, "learning_rate": 1.4436715350719176e-06, "loss": 0.7666, "step": 230790 }, { "epoch": 19.18, "learning_rate": 1.4435606795443839e-06, "loss": 0.7878, "step": 230800 }, { "epoch": 19.18, "learning_rate": 1.44344982401685e-06, "loss": 0.7316, "step": 230810 }, { "epoch": 19.19, "learning_rate": 1.4433389684893162e-06, "loss": 0.7227, "step": 230820 }, { "epoch": 19.19, "learning_rate": 1.4432281129617825e-06, "loss": 0.7572, "step": 230830 }, { "epoch": 19.19, "learning_rate": 1.4431172574342488e-06, "loss": 0.7484, "step": 230840 }, { "epoch": 19.19, "learning_rate": 1.443006401906715e-06, "loss": 0.7774, "step": 230850 }, { "epoch": 19.19, "learning_rate": 1.4428955463791812e-06, "loss": 0.786, "step": 230860 }, { "epoch": 19.19, "learning_rate": 1.4427846908516475e-06, "loss": 0.7644, "step": 230870 }, { "epoch": 19.19, "learning_rate": 1.4426738353241136e-06, "loss": 0.7158, "step": 230880 }, { "epoch": 19.19, "learning_rate": 1.44256297979658e-06, "loss": 0.6988, "step": 230890 }, { "epoch": 19.19, "learning_rate": 1.4424521242690464e-06, "loss": 0.8374, "step": 230900 }, { "epoch": 19.19, "learning_rate": 1.4423412687415127e-06, "loss": 0.7166, "step": 230910 }, { "epoch": 19.19, "learning_rate": 1.4422304132139788e-06, "loss": 0.6806, "step": 230920 }, { "epoch": 19.19, "learning_rate": 1.442119557686445e-06, "loss": 0.7273, "step": 230930 }, { "epoch": 19.2, "learning_rate": 1.4420087021589114e-06, "loss": 0.7626, "step": 230940 }, { "epoch": 19.2, "learning_rate": 1.4418978466313777e-06, "loss": 0.8093, "step": 230950 }, { "epoch": 19.2, "learning_rate": 1.4417869911038437e-06, "loss": 0.7563, "step": 230960 }, { "epoch": 19.2, "learning_rate": 1.44167613557631e-06, "loss": 0.7094, "step": 230970 }, { "epoch": 19.2, "learning_rate": 1.4415652800487763e-06, "loss": 0.7879, "step": 230980 }, { "epoch": 19.2, "learning_rate": 1.4414544245212426e-06, "loss": 0.7564, "step": 230990 }, { "epoch": 19.2, "learning_rate": 1.4413435689937087e-06, "loss": 0.7816, "step": 231000 }, { "epoch": 19.2, "learning_rate": 1.441232713466175e-06, "loss": 0.7561, "step": 231010 }, { "epoch": 19.2, "learning_rate": 1.4411218579386415e-06, "loss": 0.7162, "step": 231020 }, { "epoch": 19.2, "learning_rate": 1.4410110024111078e-06, "loss": 0.7156, "step": 231030 }, { "epoch": 19.2, "learning_rate": 1.4409001468835739e-06, "loss": 0.7541, "step": 231040 }, { "epoch": 19.2, "learning_rate": 1.4407892913560402e-06, "loss": 0.8226, "step": 231050 }, { "epoch": 19.21, "learning_rate": 1.4406784358285065e-06, "loss": 0.8103, "step": 231060 }, { "epoch": 19.21, "learning_rate": 1.4405675803009728e-06, "loss": 0.7854, "step": 231070 }, { "epoch": 19.21, "learning_rate": 1.4404567247734389e-06, "loss": 0.7495, "step": 231080 }, { "epoch": 19.21, "learning_rate": 1.4403458692459052e-06, "loss": 0.7713, "step": 231090 }, { "epoch": 19.21, "learning_rate": 1.4402350137183714e-06, "loss": 0.815, "step": 231100 }, { "epoch": 19.21, "learning_rate": 1.4401241581908377e-06, "loss": 0.776, "step": 231110 }, { "epoch": 19.21, "learning_rate": 1.4400133026633038e-06, "loss": 0.7416, "step": 231120 }, { "epoch": 19.21, "learning_rate": 1.4399024471357701e-06, "loss": 0.7612, "step": 231130 }, { "epoch": 19.21, "learning_rate": 1.4398026771609899e-06, "loss": 0.701, "step": 231140 }, { "epoch": 19.21, "learning_rate": 1.4396918216334562e-06, "loss": 0.7925, "step": 231150 }, { "epoch": 19.21, "learning_rate": 1.4395809661059225e-06, "loss": 0.7641, "step": 231160 }, { "epoch": 19.21, "learning_rate": 1.4394701105783885e-06, "loss": 0.7071, "step": 231170 }, { "epoch": 19.22, "learning_rate": 1.4393592550508548e-06, "loss": 0.7547, "step": 231180 }, { "epoch": 19.22, "learning_rate": 1.4392483995233211e-06, "loss": 0.7152, "step": 231190 }, { "epoch": 19.22, "learning_rate": 1.4391375439957874e-06, "loss": 0.8434, "step": 231200 }, { "epoch": 19.22, "learning_rate": 1.4390266884682535e-06, "loss": 0.7742, "step": 231210 }, { "epoch": 19.22, "learning_rate": 1.4389158329407198e-06, "loss": 0.7733, "step": 231220 }, { "epoch": 19.22, "learning_rate": 1.4388049774131863e-06, "loss": 0.7721, "step": 231230 }, { "epoch": 19.22, "learning_rate": 1.4386941218856526e-06, "loss": 0.7358, "step": 231240 }, { "epoch": 19.22, "learning_rate": 1.4385832663581187e-06, "loss": 0.7705, "step": 231250 }, { "epoch": 19.22, "learning_rate": 1.438472410830585e-06, "loss": 0.7168, "step": 231260 }, { "epoch": 19.22, "learning_rate": 1.4383615553030513e-06, "loss": 0.7258, "step": 231270 }, { "epoch": 19.22, "learning_rate": 1.4382506997755176e-06, "loss": 0.7324, "step": 231280 }, { "epoch": 19.22, "learning_rate": 1.4381398442479837e-06, "loss": 0.7809, "step": 231290 }, { "epoch": 19.23, "learning_rate": 1.43802898872045e-06, "loss": 0.8, "step": 231300 }, { "epoch": 19.23, "learning_rate": 1.4379181331929163e-06, "loss": 0.7289, "step": 231310 }, { "epoch": 19.23, "learning_rate": 1.4378072776653826e-06, "loss": 0.7379, "step": 231320 }, { "epoch": 19.23, "learning_rate": 1.4376964221378486e-06, "loss": 0.7857, "step": 231330 }, { "epoch": 19.23, "learning_rate": 1.437585566610315e-06, "loss": 0.7417, "step": 231340 }, { "epoch": 19.23, "learning_rate": 1.4374747110827814e-06, "loss": 0.8237, "step": 231350 }, { "epoch": 19.23, "learning_rate": 1.4373638555552477e-06, "loss": 0.7551, "step": 231360 }, { "epoch": 19.23, "learning_rate": 1.4372530000277138e-06, "loss": 0.7446, "step": 231370 }, { "epoch": 19.23, "learning_rate": 1.4371421445001801e-06, "loss": 0.6979, "step": 231380 }, { "epoch": 19.23, "learning_rate": 1.4370312889726464e-06, "loss": 0.7695, "step": 231390 }, { "epoch": 19.23, "learning_rate": 1.4369204334451127e-06, "loss": 0.8779, "step": 231400 }, { "epoch": 19.23, "learning_rate": 1.4368095779175788e-06, "loss": 0.7292, "step": 231410 }, { "epoch": 19.24, "learning_rate": 1.436698722390045e-06, "loss": 0.7508, "step": 231420 }, { "epoch": 19.24, "learning_rate": 1.4365878668625114e-06, "loss": 0.8037, "step": 231430 }, { "epoch": 19.24, "learning_rate": 1.4364770113349775e-06, "loss": 0.7502, "step": 231440 }, { "epoch": 19.24, "learning_rate": 1.4363661558074438e-06, "loss": 0.8205, "step": 231450 }, { "epoch": 19.24, "learning_rate": 1.43625530027991e-06, "loss": 0.7441, "step": 231460 }, { "epoch": 19.24, "learning_rate": 1.4361444447523766e-06, "loss": 0.7109, "step": 231470 }, { "epoch": 19.24, "learning_rate": 1.4360335892248426e-06, "loss": 0.7436, "step": 231480 }, { "epoch": 19.24, "learning_rate": 1.435922733697309e-06, "loss": 0.786, "step": 231490 }, { "epoch": 19.24, "learning_rate": 1.4358118781697752e-06, "loss": 0.7735, "step": 231500 }, { "epoch": 19.24, "learning_rate": 1.4357010226422415e-06, "loss": 0.7779, "step": 231510 }, { "epoch": 19.24, "learning_rate": 1.4355901671147076e-06, "loss": 0.7008, "step": 231520 }, { "epoch": 19.24, "learning_rate": 1.435479311587174e-06, "loss": 0.7744, "step": 231530 }, { "epoch": 19.25, "learning_rate": 1.4353684560596402e-06, "loss": 0.771, "step": 231540 }, { "epoch": 19.25, "learning_rate": 1.4352576005321065e-06, "loss": 0.8796, "step": 231550 }, { "epoch": 19.25, "learning_rate": 1.4351467450045726e-06, "loss": 0.6972, "step": 231560 }, { "epoch": 19.25, "learning_rate": 1.4350358894770389e-06, "loss": 0.7839, "step": 231570 }, { "epoch": 19.25, "learning_rate": 1.4349250339495052e-06, "loss": 0.7273, "step": 231580 }, { "epoch": 19.25, "learning_rate": 1.4348141784219717e-06, "loss": 0.7722, "step": 231590 }, { "epoch": 19.25, "learning_rate": 1.4347033228944378e-06, "loss": 0.7919, "step": 231600 }, { "epoch": 19.25, "learning_rate": 1.434592467366904e-06, "loss": 0.7657, "step": 231610 }, { "epoch": 19.25, "learning_rate": 1.4344816118393704e-06, "loss": 0.7421, "step": 231620 }, { "epoch": 19.25, "learning_rate": 1.4343707563118367e-06, "loss": 0.803, "step": 231630 }, { "epoch": 19.25, "learning_rate": 1.4342599007843027e-06, "loss": 0.7368, "step": 231640 }, { "epoch": 19.25, "learning_rate": 1.434149045256769e-06, "loss": 0.803, "step": 231650 }, { "epoch": 19.26, "learning_rate": 1.4340381897292353e-06, "loss": 0.7365, "step": 231660 }, { "epoch": 19.26, "learning_rate": 1.4339273342017016e-06, "loss": 0.7552, "step": 231670 }, { "epoch": 19.26, "learning_rate": 1.4338164786741677e-06, "loss": 0.7903, "step": 231680 }, { "epoch": 19.26, "learning_rate": 1.433705623146634e-06, "loss": 0.8016, "step": 231690 }, { "epoch": 19.26, "learning_rate": 1.4335947676191003e-06, "loss": 0.853, "step": 231700 }, { "epoch": 19.26, "learning_rate": 1.4334839120915666e-06, "loss": 0.8134, "step": 231710 }, { "epoch": 19.26, "learning_rate": 1.4333730565640329e-06, "loss": 0.8062, "step": 231720 }, { "epoch": 19.26, "learning_rate": 1.4332622010364992e-06, "loss": 0.7947, "step": 231730 }, { "epoch": 19.26, "learning_rate": 1.4331513455089655e-06, "loss": 0.7741, "step": 231740 }, { "epoch": 19.26, "learning_rate": 1.4330404899814318e-06, "loss": 0.7749, "step": 231750 }, { "epoch": 19.26, "learning_rate": 1.4329296344538979e-06, "loss": 0.7591, "step": 231760 }, { "epoch": 19.26, "learning_rate": 1.4328187789263641e-06, "loss": 0.7459, "step": 231770 }, { "epoch": 19.27, "learning_rate": 1.4327079233988304e-06, "loss": 0.7373, "step": 231780 }, { "epoch": 19.27, "learning_rate": 1.4325970678712967e-06, "loss": 0.7092, "step": 231790 }, { "epoch": 19.27, "learning_rate": 1.4324862123437628e-06, "loss": 0.7386, "step": 231800 }, { "epoch": 19.27, "learning_rate": 1.4323753568162291e-06, "loss": 0.7835, "step": 231810 }, { "epoch": 19.27, "learning_rate": 1.4322645012886954e-06, "loss": 0.7742, "step": 231820 }, { "epoch": 19.27, "learning_rate": 1.4321536457611615e-06, "loss": 0.7538, "step": 231830 }, { "epoch": 19.27, "learning_rate": 1.432042790233628e-06, "loss": 0.7188, "step": 231840 }, { "epoch": 19.27, "learning_rate": 1.4319319347060943e-06, "loss": 0.7968, "step": 231850 }, { "epoch": 19.27, "learning_rate": 1.4318210791785606e-06, "loss": 0.72, "step": 231860 }, { "epoch": 19.27, "learning_rate": 1.4317102236510267e-06, "loss": 0.7461, "step": 231870 }, { "epoch": 19.27, "learning_rate": 1.431599368123493e-06, "loss": 0.7459, "step": 231880 }, { "epoch": 19.27, "learning_rate": 1.4314885125959593e-06, "loss": 0.6896, "step": 231890 }, { "epoch": 19.28, "learning_rate": 1.4313776570684256e-06, "loss": 0.8045, "step": 231900 }, { "epoch": 19.28, "learning_rate": 1.4312668015408916e-06, "loss": 0.7687, "step": 231910 }, { "epoch": 19.28, "learning_rate": 1.431155946013358e-06, "loss": 0.677, "step": 231920 }, { "epoch": 19.28, "learning_rate": 1.4310450904858242e-06, "loss": 0.7641, "step": 231930 }, { "epoch": 19.28, "learning_rate": 1.4309342349582905e-06, "loss": 0.8363, "step": 231940 }, { "epoch": 19.28, "learning_rate": 1.4308233794307566e-06, "loss": 0.8192, "step": 231950 }, { "epoch": 19.28, "learning_rate": 1.4307125239032231e-06, "loss": 0.7622, "step": 231960 }, { "epoch": 19.28, "learning_rate": 1.4306016683756894e-06, "loss": 0.7567, "step": 231970 }, { "epoch": 19.28, "learning_rate": 1.4304908128481557e-06, "loss": 0.7755, "step": 231980 }, { "epoch": 19.28, "learning_rate": 1.4303799573206218e-06, "loss": 0.7574, "step": 231990 }, { "epoch": 19.28, "learning_rate": 1.430269101793088e-06, "loss": 0.7858, "step": 232000 }, { "epoch": 19.28, "learning_rate": 1.4301582462655544e-06, "loss": 0.7145, "step": 232010 }, { "epoch": 19.29, "learning_rate": 1.4300473907380207e-06, "loss": 0.7976, "step": 232020 }, { "epoch": 19.29, "learning_rate": 1.4299365352104868e-06, "loss": 0.7506, "step": 232030 }, { "epoch": 19.29, "learning_rate": 1.429825679682953e-06, "loss": 0.7725, "step": 232040 }, { "epoch": 19.29, "learning_rate": 1.4297148241554194e-06, "loss": 0.8127, "step": 232050 }, { "epoch": 19.29, "learning_rate": 1.4296039686278857e-06, "loss": 0.7549, "step": 232060 }, { "epoch": 19.29, "learning_rate": 1.4294931131003517e-06, "loss": 0.759, "step": 232070 }, { "epoch": 19.29, "learning_rate": 1.429382257572818e-06, "loss": 0.7356, "step": 232080 }, { "epoch": 19.29, "learning_rate": 1.4292714020452845e-06, "loss": 0.7681, "step": 232090 }, { "epoch": 19.29, "learning_rate": 1.4291605465177508e-06, "loss": 0.8218, "step": 232100 }, { "epoch": 19.29, "learning_rate": 1.429049690990217e-06, "loss": 0.7684, "step": 232110 }, { "epoch": 19.29, "learning_rate": 1.4289388354626832e-06, "loss": 0.7847, "step": 232120 }, { "epoch": 19.29, "learning_rate": 1.4288279799351495e-06, "loss": 0.7583, "step": 232130 }, { "epoch": 19.3, "learning_rate": 1.4287171244076158e-06, "loss": 0.7687, "step": 232140 }, { "epoch": 19.3, "learning_rate": 1.4286062688800819e-06, "loss": 0.8183, "step": 232150 }, { "epoch": 19.3, "learning_rate": 1.4284954133525482e-06, "loss": 0.7, "step": 232160 }, { "epoch": 19.3, "learning_rate": 1.4283845578250145e-06, "loss": 0.7759, "step": 232170 }, { "epoch": 19.3, "learning_rate": 1.4282737022974808e-06, "loss": 0.7586, "step": 232180 }, { "epoch": 19.3, "learning_rate": 1.4281628467699469e-06, "loss": 0.7338, "step": 232190 }, { "epoch": 19.3, "learning_rate": 1.4280519912424132e-06, "loss": 0.7865, "step": 232200 }, { "epoch": 19.3, "learning_rate": 1.4279411357148797e-06, "loss": 0.7064, "step": 232210 }, { "epoch": 19.3, "learning_rate": 1.427830280187346e-06, "loss": 0.763, "step": 232220 }, { "epoch": 19.3, "learning_rate": 1.427719424659812e-06, "loss": 0.6865, "step": 232230 }, { "epoch": 19.3, "learning_rate": 1.4276085691322783e-06, "loss": 0.7361, "step": 232240 }, { "epoch": 19.3, "learning_rate": 1.4274977136047446e-06, "loss": 0.8294, "step": 232250 }, { "epoch": 19.31, "learning_rate": 1.4273868580772107e-06, "loss": 0.7307, "step": 232260 }, { "epoch": 19.31, "learning_rate": 1.427276002549677e-06, "loss": 0.7272, "step": 232270 }, { "epoch": 19.31, "learning_rate": 1.4271651470221433e-06, "loss": 0.8041, "step": 232280 }, { "epoch": 19.31, "learning_rate": 1.4270542914946096e-06, "loss": 0.7357, "step": 232290 }, { "epoch": 19.31, "learning_rate": 1.4269434359670757e-06, "loss": 0.8071, "step": 232300 }, { "epoch": 19.31, "learning_rate": 1.426832580439542e-06, "loss": 0.7379, "step": 232310 }, { "epoch": 19.31, "learning_rate": 1.4267217249120083e-06, "loss": 0.6878, "step": 232320 }, { "epoch": 19.31, "learning_rate": 1.4266108693844748e-06, "loss": 0.8101, "step": 232330 }, { "epoch": 19.31, "learning_rate": 1.4265000138569409e-06, "loss": 0.777, "step": 232340 }, { "epoch": 19.31, "learning_rate": 1.4263891583294072e-06, "loss": 0.8025, "step": 232350 }, { "epoch": 19.31, "learning_rate": 1.4262783028018735e-06, "loss": 0.6676, "step": 232360 }, { "epoch": 19.31, "learning_rate": 1.4261674472743398e-06, "loss": 0.805, "step": 232370 }, { "epoch": 19.32, "learning_rate": 1.4260565917468058e-06, "loss": 0.7587, "step": 232380 }, { "epoch": 19.32, "learning_rate": 1.4259457362192721e-06, "loss": 0.7971, "step": 232390 }, { "epoch": 19.32, "learning_rate": 1.4258348806917384e-06, "loss": 0.7898, "step": 232400 }, { "epoch": 19.32, "learning_rate": 1.4257240251642047e-06, "loss": 0.775, "step": 232410 }, { "epoch": 19.32, "learning_rate": 1.4256131696366708e-06, "loss": 0.7748, "step": 232420 }, { "epoch": 19.32, "learning_rate": 1.425502314109137e-06, "loss": 0.7358, "step": 232430 }, { "epoch": 19.32, "learning_rate": 1.4253914585816034e-06, "loss": 0.8368, "step": 232440 }, { "epoch": 19.32, "learning_rate": 1.42528060305407e-06, "loss": 0.8053, "step": 232450 }, { "epoch": 19.32, "learning_rate": 1.425169747526536e-06, "loss": 0.7138, "step": 232460 }, { "epoch": 19.32, "learning_rate": 1.4250588919990023e-06, "loss": 0.742, "step": 232470 }, { "epoch": 19.32, "learning_rate": 1.4249480364714686e-06, "loss": 0.7525, "step": 232480 }, { "epoch": 19.32, "learning_rate": 1.4248371809439349e-06, "loss": 0.7208, "step": 232490 }, { "epoch": 19.33, "learning_rate": 1.424726325416401e-06, "loss": 0.8047, "step": 232500 }, { "epoch": 19.33, "learning_rate": 1.4246154698888673e-06, "loss": 0.7156, "step": 232510 }, { "epoch": 19.33, "learning_rate": 1.4245046143613335e-06, "loss": 0.7383, "step": 232520 }, { "epoch": 19.33, "learning_rate": 1.4243937588337998e-06, "loss": 0.7157, "step": 232530 }, { "epoch": 19.33, "learning_rate": 1.424282903306266e-06, "loss": 0.7874, "step": 232540 }, { "epoch": 19.33, "learning_rate": 1.4241720477787322e-06, "loss": 0.7815, "step": 232550 }, { "epoch": 19.33, "learning_rate": 1.4240611922511985e-06, "loss": 0.7175, "step": 232560 }, { "epoch": 19.33, "learning_rate": 1.4239503367236648e-06, "loss": 0.73, "step": 232570 }, { "epoch": 19.33, "learning_rate": 1.4238394811961311e-06, "loss": 0.7075, "step": 232580 }, { "epoch": 19.33, "learning_rate": 1.4237286256685974e-06, "loss": 0.7752, "step": 232590 }, { "epoch": 19.33, "learning_rate": 1.4236177701410637e-06, "loss": 0.7616, "step": 232600 }, { "epoch": 19.33, "learning_rate": 1.42350691461353e-06, "loss": 0.7235, "step": 232610 }, { "epoch": 19.34, "learning_rate": 1.423396059085996e-06, "loss": 0.7378, "step": 232620 }, { "epoch": 19.34, "learning_rate": 1.4232852035584624e-06, "loss": 0.7651, "step": 232630 }, { "epoch": 19.34, "learning_rate": 1.4231743480309287e-06, "loss": 0.7848, "step": 232640 }, { "epoch": 19.34, "learning_rate": 1.423063492503395e-06, "loss": 0.7783, "step": 232650 }, { "epoch": 19.34, "learning_rate": 1.422952636975861e-06, "loss": 0.7832, "step": 232660 }, { "epoch": 19.34, "learning_rate": 1.4228417814483273e-06, "loss": 0.7547, "step": 232670 }, { "epoch": 19.34, "learning_rate": 1.4227309259207936e-06, "loss": 0.7403, "step": 232680 }, { "epoch": 19.34, "learning_rate": 1.4226200703932597e-06, "loss": 0.7135, "step": 232690 }, { "epoch": 19.34, "learning_rate": 1.4225092148657262e-06, "loss": 0.8444, "step": 232700 }, { "epoch": 19.34, "learning_rate": 1.4223983593381925e-06, "loss": 0.7786, "step": 232710 }, { "epoch": 19.34, "learning_rate": 1.4222875038106588e-06, "loss": 0.709, "step": 232720 }, { "epoch": 19.34, "learning_rate": 1.422176648283125e-06, "loss": 0.7632, "step": 232730 }, { "epoch": 19.35, "learning_rate": 1.4220657927555912e-06, "loss": 0.7599, "step": 232740 }, { "epoch": 19.35, "learning_rate": 1.4219549372280575e-06, "loss": 0.8205, "step": 232750 }, { "epoch": 19.35, "learning_rate": 1.4218440817005238e-06, "loss": 0.7321, "step": 232760 }, { "epoch": 19.35, "learning_rate": 1.4217332261729899e-06, "loss": 0.7424, "step": 232770 }, { "epoch": 19.35, "learning_rate": 1.4216223706454562e-06, "loss": 0.6863, "step": 232780 }, { "epoch": 19.35, "learning_rate": 1.4215115151179225e-06, "loss": 0.7928, "step": 232790 }, { "epoch": 19.35, "learning_rate": 1.4214006595903888e-06, "loss": 0.7975, "step": 232800 }, { "epoch": 19.35, "learning_rate": 1.4212898040628548e-06, "loss": 0.731, "step": 232810 }, { "epoch": 19.35, "learning_rate": 1.4211789485353213e-06, "loss": 0.7805, "step": 232820 }, { "epoch": 19.35, "learning_rate": 1.4210680930077876e-06, "loss": 0.7234, "step": 232830 }, { "epoch": 19.35, "learning_rate": 1.420957237480254e-06, "loss": 0.8022, "step": 232840 }, { "epoch": 19.35, "learning_rate": 1.42084638195272e-06, "loss": 0.8015, "step": 232850 }, { "epoch": 19.35, "learning_rate": 1.4207355264251863e-06, "loss": 0.7106, "step": 232860 }, { "epoch": 19.36, "learning_rate": 1.4206246708976526e-06, "loss": 0.7453, "step": 232870 }, { "epoch": 19.36, "learning_rate": 1.420513815370119e-06, "loss": 0.7292, "step": 232880 }, { "epoch": 19.36, "learning_rate": 1.420402959842585e-06, "loss": 0.6797, "step": 232890 }, { "epoch": 19.36, "learning_rate": 1.4202921043150513e-06, "loss": 0.7693, "step": 232900 }, { "epoch": 19.36, "learning_rate": 1.4201812487875176e-06, "loss": 0.8242, "step": 232910 }, { "epoch": 19.36, "learning_rate": 1.4200703932599839e-06, "loss": 0.7595, "step": 232920 }, { "epoch": 19.36, "learning_rate": 1.41995953773245e-06, "loss": 0.7647, "step": 232930 }, { "epoch": 19.36, "learning_rate": 1.4198486822049163e-06, "loss": 0.7758, "step": 232940 }, { "epoch": 19.36, "learning_rate": 1.4197378266773828e-06, "loss": 0.8147, "step": 232950 }, { "epoch": 19.36, "learning_rate": 1.419626971149849e-06, "loss": 0.681, "step": 232960 }, { "epoch": 19.36, "learning_rate": 1.4195161156223151e-06, "loss": 0.6977, "step": 232970 }, { "epoch": 19.36, "learning_rate": 1.4194052600947814e-06, "loss": 0.776, "step": 232980 }, { "epoch": 19.37, "learning_rate": 1.4192944045672477e-06, "loss": 0.7512, "step": 232990 }, { "epoch": 19.37, "learning_rate": 1.419183549039714e-06, "loss": 0.7675, "step": 233000 }, { "epoch": 19.37, "learning_rate": 1.4190726935121801e-06, "loss": 0.7361, "step": 233010 }, { "epoch": 19.37, "learning_rate": 1.4189618379846464e-06, "loss": 0.763, "step": 233020 }, { "epoch": 19.37, "learning_rate": 1.4188509824571127e-06, "loss": 0.7593, "step": 233030 }, { "epoch": 19.37, "learning_rate": 1.418740126929579e-06, "loss": 0.7423, "step": 233040 }, { "epoch": 19.37, "learning_rate": 1.418629271402045e-06, "loss": 0.7843, "step": 233050 }, { "epoch": 19.37, "learning_rate": 1.4185184158745114e-06, "loss": 0.7613, "step": 233060 }, { "epoch": 19.37, "learning_rate": 1.4184075603469779e-06, "loss": 0.7273, "step": 233070 }, { "epoch": 19.37, "learning_rate": 1.4182967048194442e-06, "loss": 0.7233, "step": 233080 }, { "epoch": 19.37, "learning_rate": 1.4181858492919103e-06, "loss": 0.7889, "step": 233090 }, { "epoch": 19.37, "learning_rate": 1.4180749937643766e-06, "loss": 0.7357, "step": 233100 }, { "epoch": 19.38, "learning_rate": 1.4179641382368429e-06, "loss": 0.8094, "step": 233110 }, { "epoch": 19.38, "learning_rate": 1.417853282709309e-06, "loss": 0.8104, "step": 233120 }, { "epoch": 19.38, "learning_rate": 1.4177424271817752e-06, "loss": 0.7574, "step": 233130 }, { "epoch": 19.38, "learning_rate": 1.4176315716542415e-06, "loss": 0.8577, "step": 233140 }, { "epoch": 19.38, "learning_rate": 1.4175207161267078e-06, "loss": 0.8376, "step": 233150 }, { "epoch": 19.38, "learning_rate": 1.417409860599174e-06, "loss": 0.7736, "step": 233160 }, { "epoch": 19.38, "learning_rate": 1.4172990050716402e-06, "loss": 0.7458, "step": 233170 }, { "epoch": 19.38, "learning_rate": 1.4171881495441065e-06, "loss": 0.7495, "step": 233180 }, { "epoch": 19.38, "learning_rate": 1.417077294016573e-06, "loss": 0.7783, "step": 233190 }, { "epoch": 19.38, "learning_rate": 1.416966438489039e-06, "loss": 0.8193, "step": 233200 }, { "epoch": 19.38, "learning_rate": 1.4168555829615054e-06, "loss": 0.7758, "step": 233210 }, { "epoch": 19.38, "learning_rate": 1.4167447274339717e-06, "loss": 0.7242, "step": 233220 }, { "epoch": 19.39, "learning_rate": 1.416633871906438e-06, "loss": 0.7716, "step": 233230 }, { "epoch": 19.39, "learning_rate": 1.416523016378904e-06, "loss": 0.7305, "step": 233240 }, { "epoch": 19.39, "learning_rate": 1.4164121608513704e-06, "loss": 0.7498, "step": 233250 }, { "epoch": 19.39, "learning_rate": 1.4163013053238366e-06, "loss": 0.7422, "step": 233260 }, { "epoch": 19.39, "learning_rate": 1.416190449796303e-06, "loss": 0.7519, "step": 233270 }, { "epoch": 19.39, "learning_rate": 1.416079594268769e-06, "loss": 0.7734, "step": 233280 }, { "epoch": 19.39, "learning_rate": 1.4159687387412353e-06, "loss": 0.7792, "step": 233290 }, { "epoch": 19.39, "learning_rate": 1.4158578832137016e-06, "loss": 0.7957, "step": 233300 }, { "epoch": 19.39, "learning_rate": 1.415747027686168e-06, "loss": 0.7861, "step": 233310 }, { "epoch": 19.39, "learning_rate": 1.4156361721586342e-06, "loss": 0.7299, "step": 233320 }, { "epoch": 19.39, "learning_rate": 1.4155253166311005e-06, "loss": 0.7536, "step": 233330 }, { "epoch": 19.39, "learning_rate": 1.4154144611035668e-06, "loss": 0.755, "step": 233340 }, { "epoch": 19.4, "learning_rate": 1.415303605576033e-06, "loss": 0.7871, "step": 233350 }, { "epoch": 19.4, "learning_rate": 1.4151927500484992e-06, "loss": 0.7971, "step": 233360 }, { "epoch": 19.4, "learning_rate": 1.4150818945209655e-06, "loss": 0.7471, "step": 233370 }, { "epoch": 19.4, "learning_rate": 1.4149710389934318e-06, "loss": 0.7845, "step": 233380 }, { "epoch": 19.4, "learning_rate": 1.414860183465898e-06, "loss": 0.7697, "step": 233390 }, { "epoch": 19.4, "learning_rate": 1.4147493279383641e-06, "loss": 0.7898, "step": 233400 }, { "epoch": 19.4, "learning_rate": 1.4146384724108304e-06, "loss": 0.739, "step": 233410 }, { "epoch": 19.4, "learning_rate": 1.4145276168832967e-06, "loss": 0.7109, "step": 233420 }, { "epoch": 19.4, "learning_rate": 1.414416761355763e-06, "loss": 0.7713, "step": 233430 }, { "epoch": 19.4, "learning_rate": 1.4143059058282293e-06, "loss": 0.7835, "step": 233440 }, { "epoch": 19.4, "learning_rate": 1.4141950503006956e-06, "loss": 0.7175, "step": 233450 }, { "epoch": 19.4, "learning_rate": 1.414084194773162e-06, "loss": 0.7333, "step": 233460 }, { "epoch": 19.41, "learning_rate": 1.4139733392456282e-06, "loss": 0.7259, "step": 233470 }, { "epoch": 19.41, "learning_rate": 1.4138624837180943e-06, "loss": 0.8214, "step": 233480 }, { "epoch": 19.41, "learning_rate": 1.4137516281905606e-06, "loss": 0.7406, "step": 233490 }, { "epoch": 19.41, "learning_rate": 1.4136407726630269e-06, "loss": 0.796, "step": 233500 }, { "epoch": 19.41, "learning_rate": 1.413529917135493e-06, "loss": 0.788, "step": 233510 }, { "epoch": 19.41, "learning_rate": 1.4134190616079593e-06, "loss": 0.7297, "step": 233520 }, { "epoch": 19.41, "learning_rate": 1.4133082060804256e-06, "loss": 0.7771, "step": 233530 }, { "epoch": 19.41, "learning_rate": 1.4131973505528919e-06, "loss": 0.7306, "step": 233540 }, { "epoch": 19.41, "learning_rate": 1.413086495025358e-06, "loss": 0.8003, "step": 233550 }, { "epoch": 19.41, "learning_rate": 1.4129756394978245e-06, "loss": 0.6994, "step": 233560 }, { "epoch": 19.41, "learning_rate": 1.4128647839702907e-06, "loss": 0.8158, "step": 233570 }, { "epoch": 19.41, "learning_rate": 1.412753928442757e-06, "loss": 0.8223, "step": 233580 }, { "epoch": 19.42, "learning_rate": 1.4126430729152231e-06, "loss": 0.8469, "step": 233590 }, { "epoch": 19.42, "learning_rate": 1.4125322173876894e-06, "loss": 0.731, "step": 233600 }, { "epoch": 19.42, "learning_rate": 1.4124213618601557e-06, "loss": 0.7243, "step": 233610 }, { "epoch": 19.42, "learning_rate": 1.412310506332622e-06, "loss": 0.7766, "step": 233620 }, { "epoch": 19.42, "learning_rate": 1.412199650805088e-06, "loss": 0.7984, "step": 233630 }, { "epoch": 19.42, "learning_rate": 1.4120887952775544e-06, "loss": 0.732, "step": 233640 }, { "epoch": 19.42, "learning_rate": 1.4119779397500207e-06, "loss": 0.7648, "step": 233650 }, { "epoch": 19.42, "learning_rate": 1.411867084222487e-06, "loss": 0.7402, "step": 233660 }, { "epoch": 19.42, "learning_rate": 1.411756228694953e-06, "loss": 0.7237, "step": 233670 }, { "epoch": 19.42, "learning_rate": 1.4116453731674196e-06, "loss": 0.8018, "step": 233680 }, { "epoch": 19.42, "learning_rate": 1.4115345176398859e-06, "loss": 0.8113, "step": 233690 }, { "epoch": 19.42, "learning_rate": 1.4114236621123522e-06, "loss": 0.8236, "step": 233700 }, { "epoch": 19.43, "learning_rate": 1.4113128065848182e-06, "loss": 0.7401, "step": 233710 }, { "epoch": 19.43, "learning_rate": 1.4112019510572845e-06, "loss": 0.7261, "step": 233720 }, { "epoch": 19.43, "learning_rate": 1.4110910955297508e-06, "loss": 0.7643, "step": 233730 }, { "epoch": 19.43, "learning_rate": 1.4109802400022171e-06, "loss": 0.6949, "step": 233740 }, { "epoch": 19.43, "learning_rate": 1.4108693844746832e-06, "loss": 0.7859, "step": 233750 }, { "epoch": 19.43, "learning_rate": 1.4107585289471495e-06, "loss": 0.7227, "step": 233760 }, { "epoch": 19.43, "learning_rate": 1.4106476734196158e-06, "loss": 0.8028, "step": 233770 }, { "epoch": 19.43, "learning_rate": 1.410536817892082e-06, "loss": 0.731, "step": 233780 }, { "epoch": 19.43, "learning_rate": 1.4104259623645482e-06, "loss": 0.8071, "step": 233790 }, { "epoch": 19.43, "learning_rate": 1.4103151068370145e-06, "loss": 0.7898, "step": 233800 }, { "epoch": 19.43, "learning_rate": 1.410204251309481e-06, "loss": 0.729, "step": 233810 }, { "epoch": 19.43, "learning_rate": 1.4100933957819473e-06, "loss": 0.7091, "step": 233820 }, { "epoch": 19.44, "learning_rate": 1.4099936258071668e-06, "loss": 0.6833, "step": 233830 }, { "epoch": 19.44, "learning_rate": 1.409882770279633e-06, "loss": 0.7897, "step": 233840 }, { "epoch": 19.44, "learning_rate": 1.4097719147520992e-06, "loss": 0.8401, "step": 233850 }, { "epoch": 19.44, "learning_rate": 1.4096610592245655e-06, "loss": 0.7887, "step": 233860 }, { "epoch": 19.44, "learning_rate": 1.4095502036970318e-06, "loss": 0.7424, "step": 233870 }, { "epoch": 19.44, "learning_rate": 1.4094393481694979e-06, "loss": 0.752, "step": 233880 }, { "epoch": 19.44, "learning_rate": 1.4093284926419644e-06, "loss": 0.7615, "step": 233890 }, { "epoch": 19.44, "learning_rate": 1.4092176371144307e-06, "loss": 0.7925, "step": 233900 }, { "epoch": 19.44, "learning_rate": 1.409106781586897e-06, "loss": 0.72, "step": 233910 }, { "epoch": 19.44, "learning_rate": 1.408995926059363e-06, "loss": 0.8038, "step": 233920 }, { "epoch": 19.44, "learning_rate": 1.4088850705318294e-06, "loss": 0.7529, "step": 233930 }, { "epoch": 19.44, "learning_rate": 1.4087742150042956e-06, "loss": 0.7511, "step": 233940 }, { "epoch": 19.45, "learning_rate": 1.408663359476762e-06, "loss": 0.7361, "step": 233950 }, { "epoch": 19.45, "learning_rate": 1.408552503949228e-06, "loss": 0.7868, "step": 233960 }, { "epoch": 19.45, "learning_rate": 1.4084416484216943e-06, "loss": 0.701, "step": 233970 }, { "epoch": 19.45, "learning_rate": 1.4083307928941606e-06, "loss": 0.7344, "step": 233980 }, { "epoch": 19.45, "learning_rate": 1.408219937366627e-06, "loss": 0.7645, "step": 233990 }, { "epoch": 19.45, "learning_rate": 1.408109081839093e-06, "loss": 0.7892, "step": 234000 }, { "epoch": 19.45, "learning_rate": 1.4079982263115593e-06, "loss": 0.6827, "step": 234010 }, { "epoch": 19.45, "learning_rate": 1.4078873707840258e-06, "loss": 0.7614, "step": 234020 }, { "epoch": 19.45, "learning_rate": 1.407776515256492e-06, "loss": 0.7173, "step": 234030 }, { "epoch": 19.45, "learning_rate": 1.4076656597289582e-06, "loss": 0.784, "step": 234040 }, { "epoch": 19.45, "learning_rate": 1.4075548042014245e-06, "loss": 0.7959, "step": 234050 }, { "epoch": 19.45, "learning_rate": 1.4074439486738908e-06, "loss": 0.7707, "step": 234060 }, { "epoch": 19.46, "learning_rate": 1.4073330931463569e-06, "loss": 0.7344, "step": 234070 }, { "epoch": 19.46, "learning_rate": 1.4072222376188231e-06, "loss": 0.7628, "step": 234080 }, { "epoch": 19.46, "learning_rate": 1.4071113820912894e-06, "loss": 0.7681, "step": 234090 }, { "epoch": 19.46, "learning_rate": 1.4070005265637557e-06, "loss": 0.8323, "step": 234100 }, { "epoch": 19.46, "learning_rate": 1.4068896710362218e-06, "loss": 0.7206, "step": 234110 }, { "epoch": 19.46, "learning_rate": 1.4067788155086881e-06, "loss": 0.7482, "step": 234120 }, { "epoch": 19.46, "learning_rate": 1.4066679599811544e-06, "loss": 0.7658, "step": 234130 }, { "epoch": 19.46, "learning_rate": 1.406557104453621e-06, "loss": 0.7937, "step": 234140 }, { "epoch": 19.46, "learning_rate": 1.406446248926087e-06, "loss": 0.8315, "step": 234150 }, { "epoch": 19.46, "learning_rate": 1.4063353933985533e-06, "loss": 0.7756, "step": 234160 }, { "epoch": 19.46, "learning_rate": 1.4062245378710196e-06, "loss": 0.7736, "step": 234170 }, { "epoch": 19.46, "learning_rate": 1.4061136823434859e-06, "loss": 0.7053, "step": 234180 }, { "epoch": 19.47, "learning_rate": 1.406002826815952e-06, "loss": 0.7419, "step": 234190 }, { "epoch": 19.47, "learning_rate": 1.4058919712884183e-06, "loss": 0.78, "step": 234200 }, { "epoch": 19.47, "learning_rate": 1.4057811157608846e-06, "loss": 0.7641, "step": 234210 }, { "epoch": 19.47, "learning_rate": 1.4056702602333509e-06, "loss": 0.7343, "step": 234220 }, { "epoch": 19.47, "learning_rate": 1.405559404705817e-06, "loss": 0.7984, "step": 234230 }, { "epoch": 19.47, "learning_rate": 1.4054485491782832e-06, "loss": 0.7824, "step": 234240 }, { "epoch": 19.47, "learning_rate": 1.4053376936507495e-06, "loss": 0.8385, "step": 234250 }, { "epoch": 19.47, "learning_rate": 1.405226838123216e-06, "loss": 0.7304, "step": 234260 }, { "epoch": 19.47, "learning_rate": 1.4051159825956821e-06, "loss": 0.6753, "step": 234270 }, { "epoch": 19.47, "learning_rate": 1.4050051270681484e-06, "loss": 0.7276, "step": 234280 }, { "epoch": 19.47, "learning_rate": 1.4048942715406147e-06, "loss": 0.7571, "step": 234290 }, { "epoch": 19.47, "learning_rate": 1.404783416013081e-06, "loss": 0.7629, "step": 234300 }, { "epoch": 19.48, "learning_rate": 1.404672560485547e-06, "loss": 0.8036, "step": 234310 }, { "epoch": 19.48, "learning_rate": 1.4045617049580134e-06, "loss": 0.7275, "step": 234320 }, { "epoch": 19.48, "learning_rate": 1.4044508494304797e-06, "loss": 0.7177, "step": 234330 }, { "epoch": 19.48, "learning_rate": 1.404339993902946e-06, "loss": 0.7271, "step": 234340 }, { "epoch": 19.48, "learning_rate": 1.404229138375412e-06, "loss": 0.8268, "step": 234350 }, { "epoch": 19.48, "learning_rate": 1.4041182828478784e-06, "loss": 0.8332, "step": 234360 }, { "epoch": 19.48, "learning_rate": 1.4040074273203447e-06, "loss": 0.7092, "step": 234370 }, { "epoch": 19.48, "learning_rate": 1.403896571792811e-06, "loss": 0.7515, "step": 234380 }, { "epoch": 19.48, "learning_rate": 1.4037857162652772e-06, "loss": 0.711, "step": 234390 }, { "epoch": 19.48, "learning_rate": 1.4036748607377435e-06, "loss": 0.8139, "step": 234400 }, { "epoch": 19.48, "learning_rate": 1.4035640052102098e-06, "loss": 0.7918, "step": 234410 }, { "epoch": 19.48, "learning_rate": 1.4034531496826761e-06, "loss": 0.6972, "step": 234420 }, { "epoch": 19.49, "learning_rate": 1.4033422941551422e-06, "loss": 0.7527, "step": 234430 }, { "epoch": 19.49, "learning_rate": 1.4032314386276085e-06, "loss": 0.734, "step": 234440 }, { "epoch": 19.49, "learning_rate": 1.4031205831000748e-06, "loss": 0.7939, "step": 234450 }, { "epoch": 19.49, "learning_rate": 1.4030097275725409e-06, "loss": 0.7318, "step": 234460 }, { "epoch": 19.49, "learning_rate": 1.4028988720450072e-06, "loss": 0.7547, "step": 234470 }, { "epoch": 19.49, "learning_rate": 1.4027880165174735e-06, "loss": 0.8332, "step": 234480 }, { "epoch": 19.49, "learning_rate": 1.4026771609899398e-06, "loss": 0.7559, "step": 234490 }, { "epoch": 19.49, "learning_rate": 1.4025663054624059e-06, "loss": 0.8632, "step": 234500 }, { "epoch": 19.49, "learning_rate": 1.4024554499348724e-06, "loss": 0.7626, "step": 234510 }, { "epoch": 19.49, "learning_rate": 1.4023445944073387e-06, "loss": 0.7489, "step": 234520 }, { "epoch": 19.49, "learning_rate": 1.402233738879805e-06, "loss": 0.7012, "step": 234530 }, { "epoch": 19.49, "learning_rate": 1.402122883352271e-06, "loss": 0.8193, "step": 234540 }, { "epoch": 19.5, "learning_rate": 1.4020120278247373e-06, "loss": 0.8276, "step": 234550 }, { "epoch": 19.5, "learning_rate": 1.4019011722972036e-06, "loss": 0.7627, "step": 234560 }, { "epoch": 19.5, "learning_rate": 1.40179031676967e-06, "loss": 0.6999, "step": 234570 }, { "epoch": 19.5, "learning_rate": 1.401679461242136e-06, "loss": 0.7483, "step": 234580 }, { "epoch": 19.5, "learning_rate": 1.4015686057146023e-06, "loss": 0.7068, "step": 234590 }, { "epoch": 19.5, "learning_rate": 1.4014577501870686e-06, "loss": 0.8296, "step": 234600 }, { "epoch": 19.5, "learning_rate": 1.4013468946595349e-06, "loss": 0.7733, "step": 234610 }, { "epoch": 19.5, "learning_rate": 1.401236039132001e-06, "loss": 0.7474, "step": 234620 }, { "epoch": 19.5, "learning_rate": 1.4011251836044675e-06, "loss": 0.6823, "step": 234630 }, { "epoch": 19.5, "learning_rate": 1.4010143280769338e-06, "loss": 0.7219, "step": 234640 }, { "epoch": 19.5, "learning_rate": 1.4009034725494e-06, "loss": 0.8406, "step": 234650 }, { "epoch": 19.5, "learning_rate": 1.4007926170218662e-06, "loss": 0.7378, "step": 234660 }, { "epoch": 19.51, "learning_rate": 1.4006817614943325e-06, "loss": 0.7242, "step": 234670 }, { "epoch": 19.51, "learning_rate": 1.4005709059667987e-06, "loss": 0.7488, "step": 234680 }, { "epoch": 19.51, "learning_rate": 1.400460050439265e-06, "loss": 0.7815, "step": 234690 }, { "epoch": 19.51, "learning_rate": 1.4003491949117311e-06, "loss": 0.7178, "step": 234700 }, { "epoch": 19.51, "learning_rate": 1.4002383393841974e-06, "loss": 0.7988, "step": 234710 }, { "epoch": 19.51, "learning_rate": 1.4001274838566637e-06, "loss": 0.7374, "step": 234720 }, { "epoch": 19.51, "learning_rate": 1.40001662832913e-06, "loss": 0.7453, "step": 234730 }, { "epoch": 19.51, "learning_rate": 1.399905772801596e-06, "loss": 0.6691, "step": 234740 }, { "epoch": 19.51, "learning_rate": 1.3997949172740626e-06, "loss": 0.7741, "step": 234750 }, { "epoch": 19.51, "learning_rate": 1.399684061746529e-06, "loss": 0.791, "step": 234760 }, { "epoch": 19.51, "learning_rate": 1.3995732062189952e-06, "loss": 0.7629, "step": 234770 }, { "epoch": 19.51, "learning_rate": 1.3994623506914613e-06, "loss": 0.7407, "step": 234780 }, { "epoch": 19.52, "learning_rate": 1.3993514951639276e-06, "loss": 0.7658, "step": 234790 }, { "epoch": 19.52, "learning_rate": 1.3992406396363939e-06, "loss": 0.81, "step": 234800 }, { "epoch": 19.52, "learning_rate": 1.3991297841088602e-06, "loss": 0.7896, "step": 234810 }, { "epoch": 19.52, "learning_rate": 1.3990189285813262e-06, "loss": 0.6589, "step": 234820 }, { "epoch": 19.52, "learning_rate": 1.3989080730537925e-06, "loss": 0.6958, "step": 234830 }, { "epoch": 19.52, "learning_rate": 1.3987972175262588e-06, "loss": 0.7904, "step": 234840 }, { "epoch": 19.52, "learning_rate": 1.3986863619987251e-06, "loss": 0.8238, "step": 234850 }, { "epoch": 19.52, "learning_rate": 1.3985755064711912e-06, "loss": 0.7621, "step": 234860 }, { "epoch": 19.52, "learning_rate": 1.3984646509436575e-06, "loss": 0.7567, "step": 234870 }, { "epoch": 19.52, "learning_rate": 1.398353795416124e-06, "loss": 0.7864, "step": 234880 }, { "epoch": 19.52, "learning_rate": 1.3982429398885903e-06, "loss": 0.7318, "step": 234890 }, { "epoch": 19.52, "learning_rate": 1.3981320843610564e-06, "loss": 0.833, "step": 234900 }, { "epoch": 19.53, "learning_rate": 1.3980212288335227e-06, "loss": 0.8578, "step": 234910 }, { "epoch": 19.53, "learning_rate": 1.397910373305989e-06, "loss": 0.7877, "step": 234920 }, { "epoch": 19.53, "learning_rate": 1.397799517778455e-06, "loss": 0.7332, "step": 234930 }, { "epoch": 19.53, "learning_rate": 1.3976886622509214e-06, "loss": 0.6959, "step": 234940 }, { "epoch": 19.53, "learning_rate": 1.3975778067233877e-06, "loss": 0.8032, "step": 234950 }, { "epoch": 19.53, "learning_rate": 1.397466951195854e-06, "loss": 0.7007, "step": 234960 }, { "epoch": 19.53, "learning_rate": 1.39735609566832e-06, "loss": 0.7442, "step": 234970 }, { "epoch": 19.53, "learning_rate": 1.3972452401407863e-06, "loss": 0.722, "step": 234980 }, { "epoch": 19.53, "learning_rate": 1.3971343846132526e-06, "loss": 0.7321, "step": 234990 }, { "epoch": 19.53, "learning_rate": 1.3970235290857191e-06, "loss": 0.7667, "step": 235000 }, { "epoch": 19.53, "learning_rate": 1.3969126735581852e-06, "loss": 0.7663, "step": 235010 }, { "epoch": 19.53, "learning_rate": 1.3968018180306515e-06, "loss": 0.7943, "step": 235020 }, { "epoch": 19.54, "learning_rate": 1.3966909625031178e-06, "loss": 0.792, "step": 235030 }, { "epoch": 19.54, "learning_rate": 1.3965801069755841e-06, "loss": 0.7324, "step": 235040 }, { "epoch": 19.54, "learning_rate": 1.3964692514480502e-06, "loss": 0.7743, "step": 235050 }, { "epoch": 19.54, "learning_rate": 1.3963583959205165e-06, "loss": 0.742, "step": 235060 }, { "epoch": 19.54, "learning_rate": 1.3962475403929828e-06, "loss": 0.7882, "step": 235070 }, { "epoch": 19.54, "learning_rate": 1.396136684865449e-06, "loss": 0.7799, "step": 235080 }, { "epoch": 19.54, "learning_rate": 1.3960258293379152e-06, "loss": 0.7872, "step": 235090 }, { "epoch": 19.54, "learning_rate": 1.3959149738103815e-06, "loss": 0.7917, "step": 235100 }, { "epoch": 19.54, "learning_rate": 1.3958041182828478e-06, "loss": 0.6995, "step": 235110 }, { "epoch": 19.54, "learning_rate": 1.3956932627553143e-06, "loss": 0.7706, "step": 235120 }, { "epoch": 19.54, "learning_rate": 1.3955824072277803e-06, "loss": 0.8309, "step": 235130 }, { "epoch": 19.54, "learning_rate": 1.3954715517002466e-06, "loss": 0.7675, "step": 235140 }, { "epoch": 19.55, "learning_rate": 1.395360696172713e-06, "loss": 0.7848, "step": 235150 }, { "epoch": 19.55, "learning_rate": 1.3952498406451792e-06, "loss": 0.77, "step": 235160 }, { "epoch": 19.55, "learning_rate": 1.3951389851176453e-06, "loss": 0.73, "step": 235170 }, { "epoch": 19.55, "learning_rate": 1.3950281295901116e-06, "loss": 0.7648, "step": 235180 }, { "epoch": 19.55, "learning_rate": 1.394917274062578e-06, "loss": 0.7721, "step": 235190 }, { "epoch": 19.55, "learning_rate": 1.3948064185350442e-06, "loss": 0.8171, "step": 235200 }, { "epoch": 19.55, "learning_rate": 1.3946955630075103e-06, "loss": 0.7619, "step": 235210 }, { "epoch": 19.55, "learning_rate": 1.3945847074799766e-06, "loss": 0.7094, "step": 235220 }, { "epoch": 19.55, "learning_rate": 1.3944738519524429e-06, "loss": 0.7956, "step": 235230 }, { "epoch": 19.55, "learning_rate": 1.3943629964249092e-06, "loss": 0.7897, "step": 235240 }, { "epoch": 19.55, "learning_rate": 1.3942521408973755e-06, "loss": 0.7619, "step": 235250 }, { "epoch": 19.55, "learning_rate": 1.3941412853698418e-06, "loss": 0.8047, "step": 235260 }, { "epoch": 19.56, "learning_rate": 1.394030429842308e-06, "loss": 0.7218, "step": 235270 }, { "epoch": 19.56, "learning_rate": 1.3939195743147744e-06, "loss": 0.7207, "step": 235280 }, { "epoch": 19.56, "learning_rate": 1.3938087187872404e-06, "loss": 0.7885, "step": 235290 }, { "epoch": 19.56, "learning_rate": 1.3936978632597067e-06, "loss": 0.7321, "step": 235300 }, { "epoch": 19.56, "learning_rate": 1.393587007732173e-06, "loss": 0.7534, "step": 235310 }, { "epoch": 19.56, "learning_rate": 1.3934761522046391e-06, "loss": 0.7676, "step": 235320 }, { "epoch": 19.56, "learning_rate": 1.3933652966771054e-06, "loss": 0.7603, "step": 235330 }, { "epoch": 19.56, "learning_rate": 1.3932544411495717e-06, "loss": 0.7616, "step": 235340 }, { "epoch": 19.56, "learning_rate": 1.393143585622038e-06, "loss": 0.7895, "step": 235350 }, { "epoch": 19.56, "learning_rate": 1.393032730094504e-06, "loss": 0.7771, "step": 235360 }, { "epoch": 19.56, "learning_rate": 1.3929218745669706e-06, "loss": 0.6921, "step": 235370 }, { "epoch": 19.56, "learning_rate": 1.3928110190394369e-06, "loss": 0.6941, "step": 235380 }, { "epoch": 19.57, "learning_rate": 1.3927001635119032e-06, "loss": 0.7717, "step": 235390 }, { "epoch": 19.57, "learning_rate": 1.3925893079843693e-06, "loss": 0.7704, "step": 235400 }, { "epoch": 19.57, "learning_rate": 1.3924784524568356e-06, "loss": 0.7331, "step": 235410 }, { "epoch": 19.57, "learning_rate": 1.3923675969293019e-06, "loss": 0.7735, "step": 235420 }, { "epoch": 19.57, "learning_rate": 1.3922567414017681e-06, "loss": 0.7616, "step": 235430 }, { "epoch": 19.57, "learning_rate": 1.3921458858742342e-06, "loss": 0.7638, "step": 235440 }, { "epoch": 19.57, "learning_rate": 1.3920350303467005e-06, "loss": 0.7895, "step": 235450 }, { "epoch": 19.57, "learning_rate": 1.3919241748191668e-06, "loss": 0.7817, "step": 235460 }, { "epoch": 19.57, "learning_rate": 1.3918133192916331e-06, "loss": 0.7408, "step": 235470 }, { "epoch": 19.57, "learning_rate": 1.3917024637640992e-06, "loss": 0.7676, "step": 235480 }, { "epoch": 19.57, "learning_rate": 1.3915916082365657e-06, "loss": 0.7461, "step": 235490 }, { "epoch": 19.57, "learning_rate": 1.391480752709032e-06, "loss": 0.7608, "step": 235500 }, { "epoch": 19.58, "learning_rate": 1.3913698971814983e-06, "loss": 0.7535, "step": 235510 }, { "epoch": 19.58, "learning_rate": 1.3912590416539644e-06, "loss": 0.743, "step": 235520 }, { "epoch": 19.58, "learning_rate": 1.3911481861264307e-06, "loss": 0.7815, "step": 235530 }, { "epoch": 19.58, "learning_rate": 1.391037330598897e-06, "loss": 0.7942, "step": 235540 }, { "epoch": 19.58, "learning_rate": 1.3909264750713633e-06, "loss": 0.7852, "step": 235550 }, { "epoch": 19.58, "learning_rate": 1.3908156195438294e-06, "loss": 0.7325, "step": 235560 }, { "epoch": 19.58, "learning_rate": 1.3907047640162956e-06, "loss": 0.8027, "step": 235570 }, { "epoch": 19.58, "learning_rate": 1.390593908488762e-06, "loss": 0.7267, "step": 235580 }, { "epoch": 19.58, "learning_rate": 1.3904830529612282e-06, "loss": 0.7387, "step": 235590 }, { "epoch": 19.58, "learning_rate": 1.3903721974336943e-06, "loss": 0.7459, "step": 235600 }, { "epoch": 19.58, "learning_rate": 1.3902613419061606e-06, "loss": 0.7766, "step": 235610 }, { "epoch": 19.58, "learning_rate": 1.3901504863786271e-06, "loss": 0.7241, "step": 235620 }, { "epoch": 19.59, "learning_rate": 1.3900396308510934e-06, "loss": 0.6885, "step": 235630 }, { "epoch": 19.59, "learning_rate": 1.3899287753235595e-06, "loss": 0.7303, "step": 235640 }, { "epoch": 19.59, "learning_rate": 1.3898179197960258e-06, "loss": 0.8215, "step": 235650 }, { "epoch": 19.59, "learning_rate": 1.389707064268492e-06, "loss": 0.7534, "step": 235660 }, { "epoch": 19.59, "learning_rate": 1.3895962087409584e-06, "loss": 0.7378, "step": 235670 }, { "epoch": 19.59, "learning_rate": 1.3894853532134245e-06, "loss": 0.7701, "step": 235680 }, { "epoch": 19.59, "learning_rate": 1.3893744976858908e-06, "loss": 0.7567, "step": 235690 }, { "epoch": 19.59, "learning_rate": 1.389263642158357e-06, "loss": 0.8121, "step": 235700 }, { "epoch": 19.59, "learning_rate": 1.3891527866308231e-06, "loss": 0.7262, "step": 235710 }, { "epoch": 19.59, "learning_rate": 1.3890419311032894e-06, "loss": 0.7471, "step": 235720 }, { "epoch": 19.59, "learning_rate": 1.3889310755757557e-06, "loss": 0.7067, "step": 235730 }, { "epoch": 19.59, "learning_rate": 1.3888202200482222e-06, "loss": 0.7705, "step": 235740 }, { "epoch": 19.6, "learning_rate": 1.3887093645206883e-06, "loss": 0.802, "step": 235750 }, { "epoch": 19.6, "learning_rate": 1.3885985089931546e-06, "loss": 0.78, "step": 235760 }, { "epoch": 19.6, "learning_rate": 1.388487653465621e-06, "loss": 0.6749, "step": 235770 }, { "epoch": 19.6, "learning_rate": 1.3883767979380872e-06, "loss": 0.7235, "step": 235780 }, { "epoch": 19.6, "learning_rate": 1.3882659424105533e-06, "loss": 0.7106, "step": 235790 }, { "epoch": 19.6, "learning_rate": 1.3881550868830196e-06, "loss": 0.7948, "step": 235800 }, { "epoch": 19.6, "learning_rate": 1.3880442313554859e-06, "loss": 0.7378, "step": 235810 }, { "epoch": 19.6, "learning_rate": 1.3879333758279522e-06, "loss": 0.6954, "step": 235820 }, { "epoch": 19.6, "learning_rate": 1.3878225203004183e-06, "loss": 0.7553, "step": 235830 }, { "epoch": 19.6, "learning_rate": 1.3877116647728846e-06, "loss": 0.7711, "step": 235840 }, { "epoch": 19.6, "learning_rate": 1.3876008092453509e-06, "loss": 0.848, "step": 235850 }, { "epoch": 19.6, "learning_rate": 1.3874899537178174e-06, "loss": 0.6997, "step": 235860 }, { "epoch": 19.61, "learning_rate": 1.3873790981902834e-06, "loss": 0.7834, "step": 235870 }, { "epoch": 19.61, "learning_rate": 1.387279328215503e-06, "loss": 0.7783, "step": 235880 }, { "epoch": 19.61, "learning_rate": 1.3871684726879693e-06, "loss": 0.7198, "step": 235890 }, { "epoch": 19.61, "learning_rate": 1.3870576171604356e-06, "loss": 0.8194, "step": 235900 }, { "epoch": 19.61, "learning_rate": 1.3869467616329019e-06, "loss": 0.767, "step": 235910 }, { "epoch": 19.61, "learning_rate": 1.386835906105368e-06, "loss": 0.7314, "step": 235920 }, { "epoch": 19.61, "learning_rate": 1.3867250505778343e-06, "loss": 0.7351, "step": 235930 }, { "epoch": 19.61, "learning_rate": 1.3866141950503005e-06, "loss": 0.7009, "step": 235940 }, { "epoch": 19.61, "learning_rate": 1.386503339522767e-06, "loss": 0.8093, "step": 235950 }, { "epoch": 19.61, "learning_rate": 1.3863924839952331e-06, "loss": 0.7219, "step": 235960 }, { "epoch": 19.61, "learning_rate": 1.3862816284676994e-06, "loss": 0.7166, "step": 235970 }, { "epoch": 19.61, "learning_rate": 1.3861707729401657e-06, "loss": 0.714, "step": 235980 }, { "epoch": 19.62, "learning_rate": 1.386059917412632e-06, "loss": 0.8279, "step": 235990 }, { "epoch": 19.62, "learning_rate": 1.3859490618850981e-06, "loss": 0.8597, "step": 236000 }, { "epoch": 19.62, "learning_rate": 1.3858382063575644e-06, "loss": 0.8026, "step": 236010 }, { "epoch": 19.62, "learning_rate": 1.3857273508300307e-06, "loss": 0.723, "step": 236020 }, { "epoch": 19.62, "learning_rate": 1.385616495302497e-06, "loss": 0.7722, "step": 236030 }, { "epoch": 19.62, "learning_rate": 1.385505639774963e-06, "loss": 0.7219, "step": 236040 }, { "epoch": 19.62, "learning_rate": 1.3853947842474294e-06, "loss": 0.7732, "step": 236050 }, { "epoch": 19.62, "learning_rate": 1.3852839287198957e-06, "loss": 0.773, "step": 236060 }, { "epoch": 19.62, "learning_rate": 1.3851730731923622e-06, "loss": 0.728, "step": 236070 }, { "epoch": 19.62, "learning_rate": 1.3850622176648283e-06, "loss": 0.7691, "step": 236080 }, { "epoch": 19.62, "learning_rate": 1.3849513621372946e-06, "loss": 0.7655, "step": 236090 }, { "epoch": 19.62, "learning_rate": 1.3848405066097608e-06, "loss": 0.798, "step": 236100 }, { "epoch": 19.63, "learning_rate": 1.3847296510822271e-06, "loss": 0.8161, "step": 236110 }, { "epoch": 19.63, "learning_rate": 1.3846187955546932e-06, "loss": 0.7856, "step": 236120 }, { "epoch": 19.63, "learning_rate": 1.3845079400271595e-06, "loss": 0.7198, "step": 236130 }, { "epoch": 19.63, "learning_rate": 1.3843970844996258e-06, "loss": 0.7413, "step": 236140 }, { "epoch": 19.63, "learning_rate": 1.3842862289720921e-06, "loss": 0.7937, "step": 236150 }, { "epoch": 19.63, "learning_rate": 1.3841753734445582e-06, "loss": 0.7449, "step": 236160 }, { "epoch": 19.63, "learning_rate": 1.3840645179170245e-06, "loss": 0.7574, "step": 236170 }, { "epoch": 19.63, "learning_rate": 1.3839536623894908e-06, "loss": 0.7392, "step": 236180 }, { "epoch": 19.63, "learning_rate": 1.3838428068619573e-06, "loss": 0.719, "step": 236190 }, { "epoch": 19.63, "learning_rate": 1.3837319513344234e-06, "loss": 0.7703, "step": 236200 }, { "epoch": 19.63, "learning_rate": 1.3836210958068897e-06, "loss": 0.7725, "step": 236210 }, { "epoch": 19.63, "learning_rate": 1.383510240279356e-06, "loss": 0.7325, "step": 236220 }, { "epoch": 19.64, "learning_rate": 1.3833993847518223e-06, "loss": 0.7735, "step": 236230 }, { "epoch": 19.64, "learning_rate": 1.3832885292242883e-06, "loss": 0.7117, "step": 236240 }, { "epoch": 19.64, "learning_rate": 1.3831776736967546e-06, "loss": 0.7912, "step": 236250 }, { "epoch": 19.64, "learning_rate": 1.383066818169221e-06, "loss": 0.7369, "step": 236260 }, { "epoch": 19.64, "learning_rate": 1.382955962641687e-06, "loss": 0.7401, "step": 236270 }, { "epoch": 19.64, "learning_rate": 1.3828451071141533e-06, "loss": 0.7699, "step": 236280 }, { "epoch": 19.64, "learning_rate": 1.3827342515866196e-06, "loss": 0.7862, "step": 236290 }, { "epoch": 19.64, "learning_rate": 1.382623396059086e-06, "loss": 0.8104, "step": 236300 }, { "epoch": 19.64, "learning_rate": 1.382512540531552e-06, "loss": 0.8142, "step": 236310 }, { "epoch": 19.64, "learning_rate": 1.3824016850040185e-06, "loss": 0.7744, "step": 236320 }, { "epoch": 19.64, "learning_rate": 1.3822908294764848e-06, "loss": 0.8371, "step": 236330 }, { "epoch": 19.64, "learning_rate": 1.382179973948951e-06, "loss": 0.6983, "step": 236340 }, { "epoch": 19.65, "learning_rate": 1.3820691184214172e-06, "loss": 0.7948, "step": 236350 }, { "epoch": 19.65, "learning_rate": 1.3819582628938835e-06, "loss": 0.7891, "step": 236360 }, { "epoch": 19.65, "learning_rate": 1.3818474073663498e-06, "loss": 0.6512, "step": 236370 }, { "epoch": 19.65, "learning_rate": 1.381736551838816e-06, "loss": 0.6884, "step": 236380 }, { "epoch": 19.65, "learning_rate": 1.3816256963112821e-06, "loss": 0.7459, "step": 236390 }, { "epoch": 19.65, "learning_rate": 1.3815148407837484e-06, "loss": 0.8347, "step": 236400 }, { "epoch": 19.65, "learning_rate": 1.3814039852562147e-06, "loss": 0.7279, "step": 236410 }, { "epoch": 19.65, "learning_rate": 1.381293129728681e-06, "loss": 0.7303, "step": 236420 }, { "epoch": 19.65, "learning_rate": 1.3811822742011471e-06, "loss": 0.779, "step": 236430 }, { "epoch": 19.65, "learning_rate": 1.3810714186736136e-06, "loss": 0.7544, "step": 236440 }, { "epoch": 19.65, "learning_rate": 1.38096056314608e-06, "loss": 0.8403, "step": 236450 }, { "epoch": 19.65, "learning_rate": 1.3808497076185462e-06, "loss": 0.7728, "step": 236460 }, { "epoch": 19.66, "learning_rate": 1.3807388520910123e-06, "loss": 0.7221, "step": 236470 }, { "epoch": 19.66, "learning_rate": 1.3806279965634786e-06, "loss": 0.781, "step": 236480 }, { "epoch": 19.66, "learning_rate": 1.3805171410359449e-06, "loss": 0.768, "step": 236490 }, { "epoch": 19.66, "learning_rate": 1.3804062855084112e-06, "loss": 0.7681, "step": 236500 }, { "epoch": 19.66, "learning_rate": 1.3802954299808773e-06, "loss": 0.686, "step": 236510 }, { "epoch": 19.66, "learning_rate": 1.3801845744533436e-06, "loss": 0.7139, "step": 236520 }, { "epoch": 19.66, "learning_rate": 1.3800737189258099e-06, "loss": 0.6914, "step": 236530 }, { "epoch": 19.66, "learning_rate": 1.3799628633982761e-06, "loss": 0.776, "step": 236540 }, { "epoch": 19.66, "learning_rate": 1.3798520078707422e-06, "loss": 0.812, "step": 236550 }, { "epoch": 19.66, "learning_rate": 1.3797411523432087e-06, "loss": 0.6999, "step": 236560 }, { "epoch": 19.66, "learning_rate": 1.379630296815675e-06, "loss": 0.7997, "step": 236570 }, { "epoch": 19.66, "learning_rate": 1.3795194412881413e-06, "loss": 0.7474, "step": 236580 }, { "epoch": 19.67, "learning_rate": 1.3794085857606074e-06, "loss": 0.7962, "step": 236590 }, { "epoch": 19.67, "learning_rate": 1.3792977302330737e-06, "loss": 0.7963, "step": 236600 }, { "epoch": 19.67, "learning_rate": 1.37918687470554e-06, "loss": 0.7421, "step": 236610 }, { "epoch": 19.67, "learning_rate": 1.3790760191780063e-06, "loss": 0.7008, "step": 236620 }, { "epoch": 19.67, "learning_rate": 1.3789651636504724e-06, "loss": 0.7692, "step": 236630 }, { "epoch": 19.67, "learning_rate": 1.3788543081229387e-06, "loss": 0.7441, "step": 236640 }, { "epoch": 19.67, "learning_rate": 1.378743452595405e-06, "loss": 0.7799, "step": 236650 }, { "epoch": 19.67, "learning_rate": 1.378632597067871e-06, "loss": 0.7886, "step": 236660 }, { "epoch": 19.67, "learning_rate": 1.3785217415403374e-06, "loss": 0.7226, "step": 236670 }, { "epoch": 19.67, "learning_rate": 1.3784108860128036e-06, "loss": 0.7057, "step": 236680 }, { "epoch": 19.67, "learning_rate": 1.3783000304852702e-06, "loss": 0.7367, "step": 236690 }, { "epoch": 19.67, "learning_rate": 1.3781891749577365e-06, "loss": 0.7654, "step": 236700 }, { "epoch": 19.68, "learning_rate": 1.3780783194302025e-06, "loss": 0.7608, "step": 236710 }, { "epoch": 19.68, "learning_rate": 1.3779674639026688e-06, "loss": 0.7481, "step": 236720 }, { "epoch": 19.68, "learning_rate": 1.3778566083751351e-06, "loss": 0.7634, "step": 236730 }, { "epoch": 19.68, "learning_rate": 1.3777457528476012e-06, "loss": 0.7143, "step": 236740 }, { "epoch": 19.68, "learning_rate": 1.3776348973200675e-06, "loss": 0.7412, "step": 236750 }, { "epoch": 19.68, "learning_rate": 1.3775240417925338e-06, "loss": 0.8182, "step": 236760 }, { "epoch": 19.68, "learning_rate": 1.377413186265e-06, "loss": 0.7808, "step": 236770 }, { "epoch": 19.68, "learning_rate": 1.3773023307374662e-06, "loss": 0.7322, "step": 236780 }, { "epoch": 19.68, "learning_rate": 1.3771914752099325e-06, "loss": 0.7814, "step": 236790 }, { "epoch": 19.68, "learning_rate": 1.3770806196823988e-06, "loss": 0.8017, "step": 236800 }, { "epoch": 19.68, "learning_rate": 1.3769697641548653e-06, "loss": 0.7704, "step": 236810 }, { "epoch": 19.68, "learning_rate": 1.3768589086273314e-06, "loss": 0.8406, "step": 236820 }, { "epoch": 19.68, "learning_rate": 1.3767480530997977e-06, "loss": 0.7212, "step": 236830 }, { "epoch": 19.69, "learning_rate": 1.376637197572264e-06, "loss": 0.7262, "step": 236840 }, { "epoch": 19.69, "learning_rate": 1.3765263420447302e-06, "loss": 0.7572, "step": 236850 }, { "epoch": 19.69, "learning_rate": 1.3764154865171963e-06, "loss": 0.7398, "step": 236860 }, { "epoch": 19.69, "learning_rate": 1.3763046309896626e-06, "loss": 0.7098, "step": 236870 }, { "epoch": 19.69, "learning_rate": 1.376193775462129e-06, "loss": 0.8179, "step": 236880 }, { "epoch": 19.69, "learning_rate": 1.3760829199345952e-06, "loss": 0.7569, "step": 236890 }, { "epoch": 19.69, "learning_rate": 1.3759720644070613e-06, "loss": 0.737, "step": 236900 }, { "epoch": 19.69, "learning_rate": 1.3758612088795276e-06, "loss": 0.7405, "step": 236910 }, { "epoch": 19.69, "learning_rate": 1.3757503533519939e-06, "loss": 0.7909, "step": 236920 }, { "epoch": 19.69, "learning_rate": 1.3756394978244604e-06, "loss": 0.7596, "step": 236930 }, { "epoch": 19.69, "learning_rate": 1.3755286422969265e-06, "loss": 0.7447, "step": 236940 }, { "epoch": 19.69, "learning_rate": 1.3754177867693928e-06, "loss": 0.8032, "step": 236950 }, { "epoch": 19.7, "learning_rate": 1.375306931241859e-06, "loss": 0.7527, "step": 236960 }, { "epoch": 19.7, "learning_rate": 1.3751960757143254e-06, "loss": 0.7748, "step": 236970 }, { "epoch": 19.7, "learning_rate": 1.3750852201867914e-06, "loss": 0.77, "step": 236980 }, { "epoch": 19.7, "learning_rate": 1.3749743646592577e-06, "loss": 0.7964, "step": 236990 }, { "epoch": 19.7, "learning_rate": 1.374863509131724e-06, "loss": 0.7951, "step": 237000 }, { "epoch": 19.7, "learning_rate": 1.3747526536041903e-06, "loss": 0.8079, "step": 237010 }, { "epoch": 19.7, "learning_rate": 1.3746417980766564e-06, "loss": 0.7573, "step": 237020 }, { "epoch": 19.7, "learning_rate": 1.3745309425491227e-06, "loss": 0.7709, "step": 237030 }, { "epoch": 19.7, "learning_rate": 1.374420087021589e-06, "loss": 0.8714, "step": 237040 }, { "epoch": 19.7, "learning_rate": 1.3743092314940555e-06, "loss": 0.7746, "step": 237050 }, { "epoch": 19.7, "learning_rate": 1.3741983759665216e-06, "loss": 0.7675, "step": 237060 }, { "epoch": 19.7, "learning_rate": 1.374087520438988e-06, "loss": 0.7404, "step": 237070 }, { "epoch": 19.71, "learning_rate": 1.3739766649114542e-06, "loss": 0.7541, "step": 237080 }, { "epoch": 19.71, "learning_rate": 1.3738658093839205e-06, "loss": 0.745, "step": 237090 }, { "epoch": 19.71, "learning_rate": 1.3737549538563866e-06, "loss": 0.764, "step": 237100 }, { "epoch": 19.71, "learning_rate": 1.3736440983288529e-06, "loss": 0.7762, "step": 237110 }, { "epoch": 19.71, "learning_rate": 1.3735332428013192e-06, "loss": 0.7137, "step": 237120 }, { "epoch": 19.71, "learning_rate": 1.3734223872737852e-06, "loss": 0.8125, "step": 237130 }, { "epoch": 19.71, "learning_rate": 1.3733115317462515e-06, "loss": 0.7505, "step": 237140 }, { "epoch": 19.71, "learning_rate": 1.3732006762187178e-06, "loss": 0.8637, "step": 237150 }, { "epoch": 19.71, "learning_rate": 1.3730898206911841e-06, "loss": 0.7319, "step": 237160 }, { "epoch": 19.71, "learning_rate": 1.3729789651636502e-06, "loss": 0.775, "step": 237170 }, { "epoch": 19.71, "learning_rate": 1.3728681096361167e-06, "loss": 0.7275, "step": 237180 }, { "epoch": 19.71, "learning_rate": 1.372757254108583e-06, "loss": 0.79, "step": 237190 }, { "epoch": 19.72, "learning_rate": 1.3726463985810493e-06, "loss": 0.771, "step": 237200 }, { "epoch": 19.72, "learning_rate": 1.3725355430535154e-06, "loss": 0.7843, "step": 237210 }, { "epoch": 19.72, "learning_rate": 1.3724246875259817e-06, "loss": 0.7547, "step": 237220 }, { "epoch": 19.72, "learning_rate": 1.372313831998448e-06, "loss": 0.7833, "step": 237230 }, { "epoch": 19.72, "learning_rate": 1.3722029764709143e-06, "loss": 0.779, "step": 237240 }, { "epoch": 19.72, "learning_rate": 1.3720921209433804e-06, "loss": 0.8093, "step": 237250 }, { "epoch": 19.72, "learning_rate": 1.3719812654158467e-06, "loss": 0.7358, "step": 237260 }, { "epoch": 19.72, "learning_rate": 1.371870409888313e-06, "loss": 0.7712, "step": 237270 }, { "epoch": 19.72, "learning_rate": 1.3717595543607793e-06, "loss": 0.7583, "step": 237280 }, { "epoch": 19.72, "learning_rate": 1.3716486988332453e-06, "loss": 0.7505, "step": 237290 }, { "epoch": 19.72, "learning_rate": 1.3715378433057118e-06, "loss": 0.7709, "step": 237300 }, { "epoch": 19.72, "learning_rate": 1.3714269877781781e-06, "loss": 0.7599, "step": 237310 }, { "epoch": 19.73, "learning_rate": 1.3713161322506444e-06, "loss": 0.781, "step": 237320 }, { "epoch": 19.73, "learning_rate": 1.3712052767231105e-06, "loss": 0.7375, "step": 237330 }, { "epoch": 19.73, "learning_rate": 1.3710944211955768e-06, "loss": 0.7212, "step": 237340 }, { "epoch": 19.73, "learning_rate": 1.3709835656680431e-06, "loss": 0.7963, "step": 237350 }, { "epoch": 19.73, "learning_rate": 1.3708727101405094e-06, "loss": 0.7609, "step": 237360 }, { "epoch": 19.73, "learning_rate": 1.3707618546129755e-06, "loss": 0.7631, "step": 237370 }, { "epoch": 19.73, "learning_rate": 1.3706509990854418e-06, "loss": 0.7691, "step": 237380 }, { "epoch": 19.73, "learning_rate": 1.370540143557908e-06, "loss": 0.7744, "step": 237390 }, { "epoch": 19.73, "learning_rate": 1.3704292880303744e-06, "loss": 0.7496, "step": 237400 }, { "epoch": 19.73, "learning_rate": 1.3703184325028405e-06, "loss": 0.7486, "step": 237410 }, { "epoch": 19.73, "learning_rate": 1.370207576975307e-06, "loss": 0.7274, "step": 237420 }, { "epoch": 19.73, "learning_rate": 1.3700967214477733e-06, "loss": 0.7503, "step": 237430 }, { "epoch": 19.74, "learning_rate": 1.3699858659202396e-06, "loss": 0.7819, "step": 237440 }, { "epoch": 19.74, "learning_rate": 1.3698750103927056e-06, "loss": 0.8568, "step": 237450 }, { "epoch": 19.74, "learning_rate": 1.369764154865172e-06, "loss": 0.7682, "step": 237460 }, { "epoch": 19.74, "learning_rate": 1.3696532993376382e-06, "loss": 0.6748, "step": 237470 }, { "epoch": 19.74, "learning_rate": 1.3695424438101045e-06, "loss": 0.759, "step": 237480 }, { "epoch": 19.74, "learning_rate": 1.3694315882825706e-06, "loss": 0.7635, "step": 237490 }, { "epoch": 19.74, "learning_rate": 1.369320732755037e-06, "loss": 0.8006, "step": 237500 }, { "epoch": 19.74, "learning_rate": 1.3692098772275032e-06, "loss": 0.7217, "step": 237510 }, { "epoch": 19.74, "learning_rate": 1.3690990216999693e-06, "loss": 0.7313, "step": 237520 }, { "epoch": 19.74, "learning_rate": 1.3689881661724356e-06, "loss": 0.7996, "step": 237530 }, { "epoch": 19.74, "learning_rate": 1.3688773106449019e-06, "loss": 0.7365, "step": 237540 }, { "epoch": 19.74, "learning_rate": 1.3687664551173684e-06, "loss": 0.7851, "step": 237550 }, { "epoch": 19.75, "learning_rate": 1.3686555995898345e-06, "loss": 0.7215, "step": 237560 }, { "epoch": 19.75, "learning_rate": 1.3685447440623008e-06, "loss": 0.7586, "step": 237570 }, { "epoch": 19.75, "learning_rate": 1.368433888534767e-06, "loss": 0.7744, "step": 237580 }, { "epoch": 19.75, "learning_rate": 1.3683230330072333e-06, "loss": 0.7791, "step": 237590 }, { "epoch": 19.75, "learning_rate": 1.3682121774796994e-06, "loss": 0.8216, "step": 237600 }, { "epoch": 19.75, "learning_rate": 1.3681013219521657e-06, "loss": 0.7333, "step": 237610 }, { "epoch": 19.75, "learning_rate": 1.367990466424632e-06, "loss": 0.7132, "step": 237620 }, { "epoch": 19.75, "learning_rate": 1.3678796108970983e-06, "loss": 0.746, "step": 237630 }, { "epoch": 19.75, "learning_rate": 1.3677687553695644e-06, "loss": 0.7398, "step": 237640 }, { "epoch": 19.75, "learning_rate": 1.3676578998420307e-06, "loss": 0.8441, "step": 237650 }, { "epoch": 19.75, "learning_rate": 1.367547044314497e-06, "loss": 0.7617, "step": 237660 }, { "epoch": 19.75, "learning_rate": 1.3674361887869635e-06, "loss": 0.7211, "step": 237670 }, { "epoch": 19.76, "learning_rate": 1.3673253332594296e-06, "loss": 0.7598, "step": 237680 }, { "epoch": 19.76, "learning_rate": 1.3672144777318959e-06, "loss": 0.7354, "step": 237690 }, { "epoch": 19.76, "learning_rate": 1.3671036222043622e-06, "loss": 0.7834, "step": 237700 }, { "epoch": 19.76, "learning_rate": 1.3669927666768285e-06, "loss": 0.7405, "step": 237710 }, { "epoch": 19.76, "learning_rate": 1.3668819111492946e-06, "loss": 0.7746, "step": 237720 }, { "epoch": 19.76, "learning_rate": 1.3667710556217608e-06, "loss": 0.755, "step": 237730 }, { "epoch": 19.76, "learning_rate": 1.3666602000942271e-06, "loss": 0.7781, "step": 237740 }, { "epoch": 19.76, "learning_rate": 1.3665493445666934e-06, "loss": 0.8171, "step": 237750 }, { "epoch": 19.76, "learning_rate": 1.3664384890391595e-06, "loss": 0.7735, "step": 237760 }, { "epoch": 19.76, "learning_rate": 1.3663276335116258e-06, "loss": 0.7935, "step": 237770 }, { "epoch": 19.76, "learning_rate": 1.3662167779840921e-06, "loss": 0.74, "step": 237780 }, { "epoch": 19.76, "learning_rate": 1.3661059224565586e-06, "loss": 0.7002, "step": 237790 }, { "epoch": 19.77, "learning_rate": 1.3659950669290247e-06, "loss": 0.8009, "step": 237800 }, { "epoch": 19.77, "learning_rate": 1.365884211401491e-06, "loss": 0.7523, "step": 237810 }, { "epoch": 19.77, "learning_rate": 1.3657733558739573e-06, "loss": 0.7751, "step": 237820 }, { "epoch": 19.77, "learning_rate": 1.3656625003464236e-06, "loss": 0.7122, "step": 237830 }, { "epoch": 19.77, "learning_rate": 1.3655516448188897e-06, "loss": 0.7541, "step": 237840 }, { "epoch": 19.77, "learning_rate": 1.365440789291356e-06, "loss": 0.7108, "step": 237850 }, { "epoch": 19.77, "learning_rate": 1.3653299337638223e-06, "loss": 0.7775, "step": 237860 }, { "epoch": 19.77, "learning_rate": 1.3652190782362886e-06, "loss": 0.7689, "step": 237870 }, { "epoch": 19.77, "learning_rate": 1.3651082227087546e-06, "loss": 0.7672, "step": 237880 }, { "epoch": 19.77, "learning_rate": 1.364997367181221e-06, "loss": 0.7807, "step": 237890 }, { "epoch": 19.77, "learning_rate": 1.3648865116536872e-06, "loss": 0.7597, "step": 237900 }, { "epoch": 19.77, "learning_rate": 1.3647756561261533e-06, "loss": 0.7279, "step": 237910 }, { "epoch": 19.78, "learning_rate": 1.3646648005986198e-06, "loss": 0.7954, "step": 237920 }, { "epoch": 19.78, "learning_rate": 1.3645539450710861e-06, "loss": 0.7141, "step": 237930 }, { "epoch": 19.78, "learning_rate": 1.3644430895435524e-06, "loss": 0.835, "step": 237940 }, { "epoch": 19.78, "learning_rate": 1.3643322340160185e-06, "loss": 0.7371, "step": 237950 }, { "epoch": 19.78, "learning_rate": 1.3642213784884848e-06, "loss": 0.7785, "step": 237960 }, { "epoch": 19.78, "learning_rate": 1.364110522960951e-06, "loss": 0.7451, "step": 237970 }, { "epoch": 19.78, "learning_rate": 1.3639996674334174e-06, "loss": 0.7648, "step": 237980 }, { "epoch": 19.78, "learning_rate": 1.3638888119058835e-06, "loss": 0.7329, "step": 237990 }, { "epoch": 19.78, "learning_rate": 1.3637779563783498e-06, "loss": 0.727, "step": 238000 }, { "epoch": 19.78, "learning_rate": 1.363667100850816e-06, "loss": 0.7235, "step": 238010 }, { "epoch": 19.78, "learning_rate": 1.3635562453232824e-06, "loss": 0.7669, "step": 238020 }, { "epoch": 19.78, "learning_rate": 1.3634453897957484e-06, "loss": 0.7918, "step": 238030 }, { "epoch": 19.79, "learning_rate": 1.363334534268215e-06, "loss": 0.7966, "step": 238040 }, { "epoch": 19.79, "learning_rate": 1.3632236787406812e-06, "loss": 0.8023, "step": 238050 }, { "epoch": 19.79, "learning_rate": 1.3631128232131475e-06, "loss": 0.8103, "step": 238060 }, { "epoch": 19.79, "learning_rate": 1.3630019676856136e-06, "loss": 0.7535, "step": 238070 }, { "epoch": 19.79, "learning_rate": 1.36289111215808e-06, "loss": 0.7852, "step": 238080 }, { "epoch": 19.79, "learning_rate": 1.3627802566305462e-06, "loss": 0.7647, "step": 238090 }, { "epoch": 19.79, "learning_rate": 1.3626694011030125e-06, "loss": 0.8033, "step": 238100 }, { "epoch": 19.79, "learning_rate": 1.3625585455754786e-06, "loss": 0.7191, "step": 238110 }, { "epoch": 19.79, "learning_rate": 1.3624476900479449e-06, "loss": 0.7718, "step": 238120 }, { "epoch": 19.79, "learning_rate": 1.3623368345204112e-06, "loss": 0.7295, "step": 238130 }, { "epoch": 19.79, "learning_rate": 1.3622259789928775e-06, "loss": 0.7389, "step": 238140 }, { "epoch": 19.79, "learning_rate": 1.3621151234653436e-06, "loss": 0.8319, "step": 238150 }, { "epoch": 19.8, "learning_rate": 1.36200426793781e-06, "loss": 0.7403, "step": 238160 }, { "epoch": 19.8, "learning_rate": 1.3618934124102764e-06, "loss": 0.8304, "step": 238170 }, { "epoch": 19.8, "learning_rate": 1.3617825568827427e-06, "loss": 0.7871, "step": 238180 }, { "epoch": 19.8, "learning_rate": 1.3616717013552087e-06, "loss": 0.7923, "step": 238190 }, { "epoch": 19.8, "learning_rate": 1.361560845827675e-06, "loss": 0.8268, "step": 238200 }, { "epoch": 19.8, "learning_rate": 1.3614499903001413e-06, "loss": 0.727, "step": 238210 }, { "epoch": 19.8, "learning_rate": 1.3613391347726076e-06, "loss": 0.7657, "step": 238220 }, { "epoch": 19.8, "learning_rate": 1.3612282792450737e-06, "loss": 0.7567, "step": 238230 }, { "epoch": 19.8, "learning_rate": 1.36111742371754e-06, "loss": 0.7221, "step": 238240 }, { "epoch": 19.8, "learning_rate": 1.3610065681900063e-06, "loss": 0.788, "step": 238250 }, { "epoch": 19.8, "learning_rate": 1.3608957126624726e-06, "loss": 0.7509, "step": 238260 }, { "epoch": 19.8, "learning_rate": 1.3607848571349387e-06, "loss": 0.7497, "step": 238270 }, { "epoch": 19.81, "learning_rate": 1.3606850871601584e-06, "loss": 0.7626, "step": 238280 }, { "epoch": 19.81, "learning_rate": 1.3605742316326247e-06, "loss": 0.7822, "step": 238290 }, { "epoch": 19.81, "learning_rate": 1.360463376105091e-06, "loss": 0.8157, "step": 238300 }, { "epoch": 19.81, "learning_rate": 1.3603525205775573e-06, "loss": 0.713, "step": 238310 }, { "epoch": 19.81, "learning_rate": 1.3602416650500234e-06, "loss": 0.7462, "step": 238320 }, { "epoch": 19.81, "learning_rate": 1.3601308095224897e-06, "loss": 0.7193, "step": 238330 }, { "epoch": 19.81, "learning_rate": 1.360019953994956e-06, "loss": 0.7779, "step": 238340 }, { "epoch": 19.81, "learning_rate": 1.3599090984674223e-06, "loss": 0.7175, "step": 238350 }, { "epoch": 19.81, "learning_rate": 1.3597982429398884e-06, "loss": 0.7941, "step": 238360 }, { "epoch": 19.81, "learning_rate": 1.3596873874123549e-06, "loss": 0.7425, "step": 238370 }, { "epoch": 19.81, "learning_rate": 1.3595765318848212e-06, "loss": 0.7616, "step": 238380 }, { "epoch": 19.81, "learning_rate": 1.3594656763572875e-06, "loss": 0.7635, "step": 238390 }, { "epoch": 19.82, "learning_rate": 1.3593548208297535e-06, "loss": 0.8413, "step": 238400 }, { "epoch": 19.82, "learning_rate": 1.3592439653022198e-06, "loss": 0.7985, "step": 238410 }, { "epoch": 19.82, "learning_rate": 1.3591331097746861e-06, "loss": 0.7343, "step": 238420 }, { "epoch": 19.82, "learning_rate": 1.3590222542471524e-06, "loss": 0.7597, "step": 238430 }, { "epoch": 19.82, "learning_rate": 1.3589113987196185e-06, "loss": 0.738, "step": 238440 }, { "epoch": 19.82, "learning_rate": 1.3588005431920848e-06, "loss": 0.7853, "step": 238450 }, { "epoch": 19.82, "learning_rate": 1.3586896876645511e-06, "loss": 0.7302, "step": 238460 }, { "epoch": 19.82, "learning_rate": 1.3585788321370172e-06, "loss": 0.7195, "step": 238470 }, { "epoch": 19.82, "learning_rate": 1.3584679766094835e-06, "loss": 0.7894, "step": 238480 }, { "epoch": 19.82, "learning_rate": 1.35835712108195e-06, "loss": 0.7571, "step": 238490 }, { "epoch": 19.82, "learning_rate": 1.3582462655544163e-06, "loss": 0.8265, "step": 238500 }, { "epoch": 19.82, "learning_rate": 1.3581354100268824e-06, "loss": 0.7591, "step": 238510 }, { "epoch": 19.83, "learning_rate": 1.3580245544993487e-06, "loss": 0.7739, "step": 238520 }, { "epoch": 19.83, "learning_rate": 1.357913698971815e-06, "loss": 0.7432, "step": 238530 }, { "epoch": 19.83, "learning_rate": 1.3578028434442813e-06, "loss": 0.7392, "step": 238540 }, { "epoch": 19.83, "learning_rate": 1.3576919879167473e-06, "loss": 0.7848, "step": 238550 }, { "epoch": 19.83, "learning_rate": 1.3575811323892136e-06, "loss": 0.727, "step": 238560 }, { "epoch": 19.83, "learning_rate": 1.35747027686168e-06, "loss": 0.7842, "step": 238570 }, { "epoch": 19.83, "learning_rate": 1.3573594213341462e-06, "loss": 0.7724, "step": 238580 }, { "epoch": 19.83, "learning_rate": 1.3572485658066123e-06, "loss": 0.8022, "step": 238590 }, { "epoch": 19.83, "learning_rate": 1.3571377102790786e-06, "loss": 0.7397, "step": 238600 }, { "epoch": 19.83, "learning_rate": 1.357026854751545e-06, "loss": 0.7034, "step": 238610 }, { "epoch": 19.83, "learning_rate": 1.3569159992240114e-06, "loss": 0.7875, "step": 238620 }, { "epoch": 19.83, "learning_rate": 1.3568051436964775e-06, "loss": 0.7315, "step": 238630 }, { "epoch": 19.84, "learning_rate": 1.3566942881689438e-06, "loss": 0.7263, "step": 238640 }, { "epoch": 19.84, "learning_rate": 1.35658343264141e-06, "loss": 0.8052, "step": 238650 }, { "epoch": 19.84, "learning_rate": 1.3564725771138764e-06, "loss": 0.7489, "step": 238660 }, { "epoch": 19.84, "learning_rate": 1.3563617215863425e-06, "loss": 0.7312, "step": 238670 }, { "epoch": 19.84, "learning_rate": 1.3562508660588088e-06, "loss": 0.775, "step": 238680 }, { "epoch": 19.84, "learning_rate": 1.356140010531275e-06, "loss": 0.7128, "step": 238690 }, { "epoch": 19.84, "learning_rate": 1.3560291550037413e-06, "loss": 0.7589, "step": 238700 }, { "epoch": 19.84, "learning_rate": 1.3559182994762074e-06, "loss": 0.8051, "step": 238710 }, { "epoch": 19.84, "learning_rate": 1.3558074439486737e-06, "loss": 0.791, "step": 238720 }, { "epoch": 19.84, "learning_rate": 1.35569658842114e-06, "loss": 0.6896, "step": 238730 }, { "epoch": 19.84, "learning_rate": 1.3555857328936065e-06, "loss": 0.7617, "step": 238740 }, { "epoch": 19.84, "learning_rate": 1.3554748773660726e-06, "loss": 0.8272, "step": 238750 }, { "epoch": 19.85, "learning_rate": 1.355364021838539e-06, "loss": 0.7804, "step": 238760 }, { "epoch": 19.85, "learning_rate": 1.3552531663110052e-06, "loss": 0.7729, "step": 238770 }, { "epoch": 19.85, "learning_rate": 1.3551423107834715e-06, "loss": 0.7221, "step": 238780 }, { "epoch": 19.85, "learning_rate": 1.3550314552559376e-06, "loss": 0.8095, "step": 238790 }, { "epoch": 19.85, "learning_rate": 1.3549205997284039e-06, "loss": 0.8098, "step": 238800 }, { "epoch": 19.85, "learning_rate": 1.3548097442008702e-06, "loss": 0.7468, "step": 238810 }, { "epoch": 19.85, "learning_rate": 1.3546988886733365e-06, "loss": 0.7558, "step": 238820 }, { "epoch": 19.85, "learning_rate": 1.3545880331458026e-06, "loss": 0.7073, "step": 238830 }, { "epoch": 19.85, "learning_rate": 1.3544771776182688e-06, "loss": 0.8243, "step": 238840 }, { "epoch": 19.85, "learning_rate": 1.3543663220907351e-06, "loss": 0.7585, "step": 238850 }, { "epoch": 19.85, "learning_rate": 1.3542554665632017e-06, "loss": 0.7718, "step": 238860 }, { "epoch": 19.85, "learning_rate": 1.3541446110356677e-06, "loss": 0.6558, "step": 238870 }, { "epoch": 19.86, "learning_rate": 1.354033755508134e-06, "loss": 0.7375, "step": 238880 }, { "epoch": 19.86, "learning_rate": 1.3539228999806003e-06, "loss": 0.8176, "step": 238890 }, { "epoch": 19.86, "learning_rate": 1.3538120444530664e-06, "loss": 0.7722, "step": 238900 }, { "epoch": 19.86, "learning_rate": 1.3537011889255327e-06, "loss": 0.8079, "step": 238910 }, { "epoch": 19.86, "learning_rate": 1.353590333397999e-06, "loss": 0.7277, "step": 238920 }, { "epoch": 19.86, "learning_rate": 1.3534794778704653e-06, "loss": 0.7304, "step": 238930 }, { "epoch": 19.86, "learning_rate": 1.3533686223429314e-06, "loss": 0.7463, "step": 238940 }, { "epoch": 19.86, "learning_rate": 1.3532577668153977e-06, "loss": 0.7604, "step": 238950 }, { "epoch": 19.86, "learning_rate": 1.353146911287864e-06, "loss": 0.7264, "step": 238960 }, { "epoch": 19.86, "learning_rate": 1.3530360557603303e-06, "loss": 0.7869, "step": 238970 }, { "epoch": 19.86, "learning_rate": 1.3529252002327963e-06, "loss": 0.7277, "step": 238980 }, { "epoch": 19.86, "learning_rate": 1.3528143447052629e-06, "loss": 0.7739, "step": 238990 }, { "epoch": 19.87, "learning_rate": 1.3527034891777292e-06, "loss": 0.8405, "step": 239000 }, { "epoch": 19.87, "learning_rate": 1.3525926336501954e-06, "loss": 0.7476, "step": 239010 }, { "epoch": 19.87, "learning_rate": 1.3524817781226615e-06, "loss": 0.7963, "step": 239020 }, { "epoch": 19.87, "learning_rate": 1.3523709225951278e-06, "loss": 0.6824, "step": 239030 }, { "epoch": 19.87, "learning_rate": 1.3522600670675941e-06, "loss": 0.7883, "step": 239040 }, { "epoch": 19.87, "learning_rate": 1.3521492115400604e-06, "loss": 0.7654, "step": 239050 }, { "epoch": 19.87, "learning_rate": 1.3520383560125265e-06, "loss": 0.7542, "step": 239060 }, { "epoch": 19.87, "learning_rate": 1.3519275004849928e-06, "loss": 0.7739, "step": 239070 }, { "epoch": 19.87, "learning_rate": 1.351816644957459e-06, "loss": 0.6816, "step": 239080 }, { "epoch": 19.87, "learning_rate": 1.3517057894299254e-06, "loss": 0.7509, "step": 239090 }, { "epoch": 19.87, "learning_rate": 1.3515949339023915e-06, "loss": 0.7249, "step": 239100 }, { "epoch": 19.87, "learning_rate": 1.351484078374858e-06, "loss": 0.7264, "step": 239110 }, { "epoch": 19.88, "learning_rate": 1.3513732228473243e-06, "loss": 0.7943, "step": 239120 }, { "epoch": 19.88, "learning_rate": 1.3512623673197906e-06, "loss": 0.7248, "step": 239130 }, { "epoch": 19.88, "learning_rate": 1.3511515117922567e-06, "loss": 0.7607, "step": 239140 }, { "epoch": 19.88, "learning_rate": 1.351040656264723e-06, "loss": 0.7942, "step": 239150 }, { "epoch": 19.88, "learning_rate": 1.3509298007371892e-06, "loss": 0.7193, "step": 239160 }, { "epoch": 19.88, "learning_rate": 1.3508189452096555e-06, "loss": 0.7518, "step": 239170 }, { "epoch": 19.88, "learning_rate": 1.3507080896821216e-06, "loss": 0.7365, "step": 239180 }, { "epoch": 19.88, "learning_rate": 1.350597234154588e-06, "loss": 0.7072, "step": 239190 }, { "epoch": 19.88, "learning_rate": 1.3504863786270542e-06, "loss": 0.8187, "step": 239200 }, { "epoch": 19.88, "learning_rate": 1.3503755230995205e-06, "loss": 0.7636, "step": 239210 }, { "epoch": 19.88, "learning_rate": 1.3502646675719866e-06, "loss": 0.7062, "step": 239220 }, { "epoch": 19.88, "learning_rate": 1.350153812044453e-06, "loss": 0.7165, "step": 239230 }, { "epoch": 19.89, "learning_rate": 1.3500429565169194e-06, "loss": 0.7101, "step": 239240 }, { "epoch": 19.89, "learning_rate": 1.3499321009893857e-06, "loss": 0.7817, "step": 239250 }, { "epoch": 19.89, "learning_rate": 1.3498212454618518e-06, "loss": 0.708, "step": 239260 }, { "epoch": 19.89, "learning_rate": 1.349710389934318e-06, "loss": 0.7709, "step": 239270 }, { "epoch": 19.89, "learning_rate": 1.3495995344067844e-06, "loss": 0.7185, "step": 239280 }, { "epoch": 19.89, "learning_rate": 1.3494886788792507e-06, "loss": 0.753, "step": 239290 }, { "epoch": 19.89, "learning_rate": 1.3493778233517167e-06, "loss": 0.8414, "step": 239300 }, { "epoch": 19.89, "learning_rate": 1.349266967824183e-06, "loss": 0.7136, "step": 239310 }, { "epoch": 19.89, "learning_rate": 1.3491561122966493e-06, "loss": 0.7255, "step": 239320 }, { "epoch": 19.89, "learning_rate": 1.3490452567691154e-06, "loss": 0.7828, "step": 239330 }, { "epoch": 19.89, "learning_rate": 1.3489344012415817e-06, "loss": 0.714, "step": 239340 }, { "epoch": 19.89, "learning_rate": 1.3488235457140482e-06, "loss": 0.8249, "step": 239350 }, { "epoch": 19.9, "learning_rate": 1.3487126901865145e-06, "loss": 0.717, "step": 239360 }, { "epoch": 19.9, "learning_rate": 1.3486018346589806e-06, "loss": 0.7559, "step": 239370 }, { "epoch": 19.9, "learning_rate": 1.3484909791314469e-06, "loss": 0.7102, "step": 239380 }, { "epoch": 19.9, "learning_rate": 1.3483801236039132e-06, "loss": 0.7845, "step": 239390 }, { "epoch": 19.9, "learning_rate": 1.3482692680763795e-06, "loss": 0.8081, "step": 239400 }, { "epoch": 19.9, "learning_rate": 1.3481584125488456e-06, "loss": 0.7782, "step": 239410 }, { "epoch": 19.9, "learning_rate": 1.3480475570213119e-06, "loss": 0.7637, "step": 239420 }, { "epoch": 19.9, "learning_rate": 1.3479367014937782e-06, "loss": 0.7264, "step": 239430 }, { "epoch": 19.9, "learning_rate": 1.3478258459662445e-06, "loss": 0.7786, "step": 239440 }, { "epoch": 19.9, "learning_rate": 1.3477149904387105e-06, "loss": 0.8221, "step": 239450 }, { "epoch": 19.9, "learning_rate": 1.3476041349111768e-06, "loss": 0.7613, "step": 239460 }, { "epoch": 19.9, "learning_rate": 1.3474932793836431e-06, "loss": 0.7782, "step": 239470 }, { "epoch": 19.91, "learning_rate": 1.3473824238561096e-06, "loss": 0.7433, "step": 239480 }, { "epoch": 19.91, "learning_rate": 1.3472715683285757e-06, "loss": 0.7506, "step": 239490 }, { "epoch": 19.91, "learning_rate": 1.347160712801042e-06, "loss": 0.7622, "step": 239500 }, { "epoch": 19.91, "learning_rate": 1.3470498572735083e-06, "loss": 0.7881, "step": 239510 }, { "epoch": 19.91, "learning_rate": 1.3469390017459746e-06, "loss": 0.7805, "step": 239520 }, { "epoch": 19.91, "learning_rate": 1.3468281462184407e-06, "loss": 0.7985, "step": 239530 }, { "epoch": 19.91, "learning_rate": 1.346717290690907e-06, "loss": 0.7251, "step": 239540 }, { "epoch": 19.91, "learning_rate": 1.3466064351633733e-06, "loss": 0.7353, "step": 239550 }, { "epoch": 19.91, "learning_rate": 1.3464955796358396e-06, "loss": 0.7477, "step": 239560 }, { "epoch": 19.91, "learning_rate": 1.3463847241083057e-06, "loss": 0.7799, "step": 239570 }, { "epoch": 19.91, "learning_rate": 1.346273868580772e-06, "loss": 0.7726, "step": 239580 }, { "epoch": 19.91, "learning_rate": 1.3461630130532382e-06, "loss": 0.7292, "step": 239590 }, { "epoch": 19.92, "learning_rate": 1.3460521575257048e-06, "loss": 0.7594, "step": 239600 }, { "epoch": 19.92, "learning_rate": 1.3459413019981708e-06, "loss": 0.7121, "step": 239610 }, { "epoch": 19.92, "learning_rate": 1.3458304464706371e-06, "loss": 0.7679, "step": 239620 }, { "epoch": 19.92, "learning_rate": 1.3457195909431034e-06, "loss": 0.7155, "step": 239630 }, { "epoch": 19.92, "learning_rate": 1.3456087354155697e-06, "loss": 0.7673, "step": 239640 }, { "epoch": 19.92, "learning_rate": 1.3454978798880358e-06, "loss": 0.8224, "step": 239650 }, { "epoch": 19.92, "learning_rate": 1.345387024360502e-06, "loss": 0.73, "step": 239660 }, { "epoch": 19.92, "learning_rate": 1.3452761688329684e-06, "loss": 0.7413, "step": 239670 }, { "epoch": 19.92, "learning_rate": 1.3451653133054347e-06, "loss": 0.7389, "step": 239680 }, { "epoch": 19.92, "learning_rate": 1.3450544577779008e-06, "loss": 0.7544, "step": 239690 }, { "epoch": 19.92, "learning_rate": 1.344943602250367e-06, "loss": 0.8016, "step": 239700 }, { "epoch": 19.92, "learning_rate": 1.3448327467228334e-06, "loss": 0.7925, "step": 239710 }, { "epoch": 19.93, "learning_rate": 1.3447218911952999e-06, "loss": 0.7143, "step": 239720 }, { "epoch": 19.93, "learning_rate": 1.344611035667766e-06, "loss": 0.7751, "step": 239730 }, { "epoch": 19.93, "learning_rate": 1.3445001801402323e-06, "loss": 0.7024, "step": 239740 }, { "epoch": 19.93, "learning_rate": 1.3443893246126985e-06, "loss": 0.8051, "step": 239750 }, { "epoch": 19.93, "learning_rate": 1.3442784690851646e-06, "loss": 0.8164, "step": 239760 }, { "epoch": 19.93, "learning_rate": 1.344167613557631e-06, "loss": 0.7619, "step": 239770 }, { "epoch": 19.93, "learning_rate": 1.3440567580300972e-06, "loss": 0.7392, "step": 239780 }, { "epoch": 19.93, "learning_rate": 1.3439459025025635e-06, "loss": 0.7313, "step": 239790 }, { "epoch": 19.93, "learning_rate": 1.3438350469750296e-06, "loss": 0.7539, "step": 239800 }, { "epoch": 19.93, "learning_rate": 1.343724191447496e-06, "loss": 0.7844, "step": 239810 }, { "epoch": 19.93, "learning_rate": 1.3436133359199622e-06, "loss": 0.7553, "step": 239820 }, { "epoch": 19.93, "learning_rate": 1.3435024803924285e-06, "loss": 0.7649, "step": 239830 }, { "epoch": 19.94, "learning_rate": 1.3433916248648946e-06, "loss": 0.6987, "step": 239840 }, { "epoch": 19.94, "learning_rate": 1.343280769337361e-06, "loss": 0.7772, "step": 239850 }, { "epoch": 19.94, "learning_rate": 1.3431699138098274e-06, "loss": 0.7222, "step": 239860 }, { "epoch": 19.94, "learning_rate": 1.3430590582822937e-06, "loss": 0.6912, "step": 239870 }, { "epoch": 19.94, "learning_rate": 1.3429482027547598e-06, "loss": 0.706, "step": 239880 }, { "epoch": 19.94, "learning_rate": 1.342837347227226e-06, "loss": 0.7489, "step": 239890 }, { "epoch": 19.94, "learning_rate": 1.3427264916996923e-06, "loss": 0.7229, "step": 239900 }, { "epoch": 19.94, "learning_rate": 1.3426156361721586e-06, "loss": 0.7215, "step": 239910 }, { "epoch": 19.94, "learning_rate": 1.3425047806446247e-06, "loss": 0.6857, "step": 239920 }, { "epoch": 19.94, "learning_rate": 1.342393925117091e-06, "loss": 0.7555, "step": 239930 }, { "epoch": 19.94, "learning_rate": 1.3422830695895573e-06, "loss": 0.7991, "step": 239940 }, { "epoch": 19.94, "learning_rate": 1.3421722140620236e-06, "loss": 0.7826, "step": 239950 }, { "epoch": 19.95, "learning_rate": 1.3420613585344897e-06, "loss": 0.7385, "step": 239960 }, { "epoch": 19.95, "learning_rate": 1.3419505030069562e-06, "loss": 0.7636, "step": 239970 }, { "epoch": 19.95, "learning_rate": 1.3418396474794225e-06, "loss": 0.6804, "step": 239980 }, { "epoch": 19.95, "learning_rate": 1.3417287919518888e-06, "loss": 0.748, "step": 239990 }, { "epoch": 19.95, "learning_rate": 1.3416179364243549e-06, "loss": 0.8446, "step": 240000 }, { "epoch": 19.95, "learning_rate": 1.3415070808968212e-06, "loss": 0.7162, "step": 240010 }, { "epoch": 19.95, "learning_rate": 1.3413962253692875e-06, "loss": 0.7318, "step": 240020 }, { "epoch": 19.95, "learning_rate": 1.3412853698417538e-06, "loss": 0.8231, "step": 240030 }, { "epoch": 19.95, "learning_rate": 1.3411745143142198e-06, "loss": 0.743, "step": 240040 }, { "epoch": 19.95, "learning_rate": 1.3410636587866861e-06, "loss": 0.7418, "step": 240050 }, { "epoch": 19.95, "learning_rate": 1.3409528032591524e-06, "loss": 0.6924, "step": 240060 }, { "epoch": 19.95, "learning_rate": 1.3408419477316187e-06, "loss": 0.7136, "step": 240070 }, { "epoch": 19.96, "learning_rate": 1.3407310922040848e-06, "loss": 0.7103, "step": 240080 }, { "epoch": 19.96, "learning_rate": 1.3406202366765513e-06, "loss": 0.7773, "step": 240090 }, { "epoch": 19.96, "learning_rate": 1.3405093811490176e-06, "loss": 0.8151, "step": 240100 }, { "epoch": 19.96, "learning_rate": 1.340398525621484e-06, "loss": 0.718, "step": 240110 }, { "epoch": 19.96, "learning_rate": 1.34028767009395e-06, "loss": 0.7221, "step": 240120 }, { "epoch": 19.96, "learning_rate": 1.3401768145664163e-06, "loss": 0.73, "step": 240130 }, { "epoch": 19.96, "learning_rate": 1.3400659590388826e-06, "loss": 0.7215, "step": 240140 }, { "epoch": 19.96, "learning_rate": 1.3399551035113487e-06, "loss": 0.8513, "step": 240150 }, { "epoch": 19.96, "learning_rate": 1.339844247983815e-06, "loss": 0.7215, "step": 240160 }, { "epoch": 19.96, "learning_rate": 1.3397333924562813e-06, "loss": 0.678, "step": 240170 }, { "epoch": 19.96, "learning_rate": 1.3396225369287476e-06, "loss": 0.7432, "step": 240180 }, { "epoch": 19.96, "learning_rate": 1.3395116814012136e-06, "loss": 0.7683, "step": 240190 }, { "epoch": 19.97, "learning_rate": 1.33940082587368e-06, "loss": 0.7762, "step": 240200 }, { "epoch": 19.97, "learning_rate": 1.3392899703461462e-06, "loss": 0.7416, "step": 240210 }, { "epoch": 19.97, "learning_rate": 1.3391791148186127e-06, "loss": 0.7228, "step": 240220 }, { "epoch": 19.97, "learning_rate": 1.3390682592910788e-06, "loss": 0.7604, "step": 240230 }, { "epoch": 19.97, "learning_rate": 1.3389574037635451e-06, "loss": 0.7488, "step": 240240 }, { "epoch": 19.97, "learning_rate": 1.3388465482360114e-06, "loss": 0.847, "step": 240250 }, { "epoch": 19.97, "learning_rate": 1.3387356927084777e-06, "loss": 0.7487, "step": 240260 }, { "epoch": 19.97, "learning_rate": 1.3386248371809438e-06, "loss": 0.7274, "step": 240270 }, { "epoch": 19.97, "learning_rate": 1.33851398165341e-06, "loss": 0.733, "step": 240280 }, { "epoch": 19.97, "learning_rate": 1.3384031261258764e-06, "loss": 0.7397, "step": 240290 }, { "epoch": 19.97, "learning_rate": 1.3382922705983427e-06, "loss": 0.8709, "step": 240300 }, { "epoch": 19.97, "learning_rate": 1.3381814150708088e-06, "loss": 0.7565, "step": 240310 }, { "epoch": 19.98, "learning_rate": 1.338070559543275e-06, "loss": 0.7484, "step": 240320 }, { "epoch": 19.98, "learning_rate": 1.3379597040157413e-06, "loss": 0.7994, "step": 240330 }, { "epoch": 19.98, "learning_rate": 1.3378488484882079e-06, "loss": 0.7737, "step": 240340 }, { "epoch": 19.98, "learning_rate": 1.337737992960674e-06, "loss": 0.8218, "step": 240350 }, { "epoch": 19.98, "learning_rate": 1.3376271374331402e-06, "loss": 0.7144, "step": 240360 }, { "epoch": 19.98, "learning_rate": 1.3375273674583598e-06, "loss": 0.7662, "step": 240370 }, { "epoch": 19.98, "learning_rate": 1.337416511930826e-06, "loss": 0.7489, "step": 240380 }, { "epoch": 19.98, "learning_rate": 1.3373056564032924e-06, "loss": 0.776, "step": 240390 }, { "epoch": 19.98, "learning_rate": 1.3371948008757584e-06, "loss": 0.7305, "step": 240400 }, { "epoch": 19.98, "learning_rate": 1.3370839453482247e-06, "loss": 0.7331, "step": 240410 }, { "epoch": 19.98, "learning_rate": 1.336973089820691e-06, "loss": 0.6955, "step": 240420 }, { "epoch": 19.98, "learning_rate": 1.3368622342931575e-06, "loss": 0.7187, "step": 240430 }, { "epoch": 19.99, "learning_rate": 1.3367513787656236e-06, "loss": 0.8065, "step": 240440 }, { "epoch": 19.99, "learning_rate": 1.33664052323809e-06, "loss": 0.7732, "step": 240450 }, { "epoch": 19.99, "learning_rate": 1.3365296677105562e-06, "loss": 0.7006, "step": 240460 }, { "epoch": 19.99, "learning_rate": 1.3364188121830225e-06, "loss": 0.7446, "step": 240470 }, { "epoch": 19.99, "learning_rate": 1.3363079566554886e-06, "loss": 0.7755, "step": 240480 }, { "epoch": 19.99, "learning_rate": 1.336197101127955e-06, "loss": 0.827, "step": 240490 }, { "epoch": 19.99, "learning_rate": 1.3360862456004212e-06, "loss": 0.7498, "step": 240500 }, { "epoch": 19.99, "learning_rate": 1.3359753900728875e-06, "loss": 0.731, "step": 240510 }, { "epoch": 19.99, "learning_rate": 1.3358645345453536e-06, "loss": 0.7824, "step": 240520 }, { "epoch": 19.99, "learning_rate": 1.3357536790178199e-06, "loss": 0.6959, "step": 240530 }, { "epoch": 19.99, "learning_rate": 1.3356428234902862e-06, "loss": 0.7531, "step": 240540 }, { "epoch": 19.99, "learning_rate": 1.3355319679627527e-06, "loss": 0.7724, "step": 240550 }, { "epoch": 20.0, "learning_rate": 1.3354211124352187e-06, "loss": 0.7903, "step": 240560 }, { "epoch": 20.0, "learning_rate": 1.335310256907685e-06, "loss": 0.788, "step": 240570 }, { "epoch": 20.0, "learning_rate": 1.3351994013801513e-06, "loss": 0.7222, "step": 240580 }, { "epoch": 20.0, "learning_rate": 1.3350885458526176e-06, "loss": 0.7351, "step": 240590 }, { "epoch": 20.0, "learning_rate": 1.3349776903250837e-06, "loss": 0.7844, "step": 240600 }, { "epoch": 20.0, "learning_rate": 1.33486683479755e-06, "loss": 0.7558, "step": 240610 }, { "epoch": 20.0, "learning_rate": 1.3347559792700163e-06, "loss": 0.7467, "step": 240620 }, { "epoch": 20.0, "eval_loss": 1.1102163791656494, "eval_runtime": 358.5047, "eval_samples_per_second": 7.459, "eval_steps_per_second": 3.729, "eval_wer": 0.6368606178751536, "step": 240620 }, { "epoch": 20.0, "learning_rate": 1.3346451237424826e-06, "loss": 0.8255, "step": 240630 }, { "epoch": 20.0, "learning_rate": 1.3345342682149487e-06, "loss": 0.742, "step": 240640 }, { "epoch": 20.0, "learning_rate": 1.334423412687415e-06, "loss": 0.7168, "step": 240650 }, { "epoch": 20.0, "learning_rate": 1.3343125571598813e-06, "loss": 0.7149, "step": 240660 }, { "epoch": 20.0, "learning_rate": 1.3342017016323478e-06, "loss": 0.7502, "step": 240670 }, { "epoch": 20.0, "learning_rate": 1.3340908461048139e-06, "loss": 0.8407, "step": 240680 }, { "epoch": 20.01, "learning_rate": 1.3339799905772802e-06, "loss": 0.6873, "step": 240690 }, { "epoch": 20.01, "learning_rate": 1.3338691350497465e-06, "loss": 0.754, "step": 240700 }, { "epoch": 20.01, "learning_rate": 1.3337582795222125e-06, "loss": 0.7547, "step": 240710 }, { "epoch": 20.01, "learning_rate": 1.3336474239946788e-06, "loss": 0.7606, "step": 240720 }, { "epoch": 20.01, "learning_rate": 1.3335365684671451e-06, "loss": 0.7771, "step": 240730 }, { "epoch": 20.01, "learning_rate": 1.3334257129396114e-06, "loss": 0.7362, "step": 240740 }, { "epoch": 20.01, "learning_rate": 1.3333148574120775e-06, "loss": 0.7833, "step": 240750 }, { "epoch": 20.01, "learning_rate": 1.3332040018845438e-06, "loss": 0.7726, "step": 240760 }, { "epoch": 20.01, "learning_rate": 1.33309314635701e-06, "loss": 0.7654, "step": 240770 }, { "epoch": 20.01, "learning_rate": 1.3329822908294764e-06, "loss": 0.7909, "step": 240780 }, { "epoch": 20.01, "learning_rate": 1.3328714353019427e-06, "loss": 0.7334, "step": 240790 }, { "epoch": 20.01, "learning_rate": 1.332760579774409e-06, "loss": 0.7276, "step": 240800 }, { "epoch": 20.02, "learning_rate": 1.3326497242468753e-06, "loss": 0.7458, "step": 240810 }, { "epoch": 20.02, "learning_rate": 1.3325388687193416e-06, "loss": 0.7848, "step": 240820 }, { "epoch": 20.02, "learning_rate": 1.3324280131918077e-06, "loss": 0.7697, "step": 240830 }, { "epoch": 20.02, "learning_rate": 1.332317157664274e-06, "loss": 0.6945, "step": 240840 }, { "epoch": 20.02, "learning_rate": 1.3322063021367403e-06, "loss": 0.7659, "step": 240850 }, { "epoch": 20.02, "learning_rate": 1.3320954466092066e-06, "loss": 0.7316, "step": 240860 }, { "epoch": 20.02, "learning_rate": 1.3319845910816726e-06, "loss": 0.7822, "step": 240870 }, { "epoch": 20.02, "learning_rate": 1.331873735554139e-06, "loss": 0.7482, "step": 240880 }, { "epoch": 20.02, "learning_rate": 1.3317628800266052e-06, "loss": 0.7463, "step": 240890 }, { "epoch": 20.02, "learning_rate": 1.3316520244990715e-06, "loss": 0.726, "step": 240900 }, { "epoch": 20.02, "learning_rate": 1.3315411689715376e-06, "loss": 0.742, "step": 240910 }, { "epoch": 20.02, "learning_rate": 1.3314303134440041e-06, "loss": 0.7219, "step": 240920 }, { "epoch": 20.03, "learning_rate": 1.3313194579164704e-06, "loss": 0.8773, "step": 240930 }, { "epoch": 20.03, "learning_rate": 1.3312086023889367e-06, "loss": 0.7717, "step": 240940 }, { "epoch": 20.03, "learning_rate": 1.3310977468614028e-06, "loss": 0.7068, "step": 240950 }, { "epoch": 20.03, "learning_rate": 1.330986891333869e-06, "loss": 0.7844, "step": 240960 }, { "epoch": 20.03, "learning_rate": 1.3308760358063354e-06, "loss": 0.7497, "step": 240970 }, { "epoch": 20.03, "learning_rate": 1.3307651802788017e-06, "loss": 0.8325, "step": 240980 }, { "epoch": 20.03, "learning_rate": 1.3306543247512678e-06, "loss": 0.7799, "step": 240990 }, { "epoch": 20.03, "learning_rate": 1.330543469223734e-06, "loss": 0.7294, "step": 241000 }, { "epoch": 20.03, "learning_rate": 1.3304326136962003e-06, "loss": 0.7761, "step": 241010 }, { "epoch": 20.03, "learning_rate": 1.3303217581686666e-06, "loss": 0.7378, "step": 241020 }, { "epoch": 20.03, "learning_rate": 1.3302109026411327e-06, "loss": 0.7648, "step": 241030 }, { "epoch": 20.03, "learning_rate": 1.3301000471135992e-06, "loss": 0.7439, "step": 241040 }, { "epoch": 20.04, "learning_rate": 1.3299891915860655e-06, "loss": 0.743, "step": 241050 }, { "epoch": 20.04, "learning_rate": 1.3298783360585318e-06, "loss": 0.749, "step": 241060 }, { "epoch": 20.04, "learning_rate": 1.329767480530998e-06, "loss": 0.7621, "step": 241070 }, { "epoch": 20.04, "learning_rate": 1.3296566250034642e-06, "loss": 0.8074, "step": 241080 }, { "epoch": 20.04, "learning_rate": 1.3295457694759305e-06, "loss": 0.7033, "step": 241090 }, { "epoch": 20.04, "learning_rate": 1.3294349139483966e-06, "loss": 0.8222, "step": 241100 }, { "epoch": 20.04, "learning_rate": 1.3293240584208629e-06, "loss": 0.7746, "step": 241110 }, { "epoch": 20.04, "learning_rate": 1.3292132028933292e-06, "loss": 0.7741, "step": 241120 }, { "epoch": 20.04, "learning_rate": 1.3291023473657955e-06, "loss": 0.8086, "step": 241130 }, { "epoch": 20.04, "learning_rate": 1.3289914918382616e-06, "loss": 0.6592, "step": 241140 }, { "epoch": 20.04, "learning_rate": 1.3288806363107278e-06, "loss": 0.7776, "step": 241150 }, { "epoch": 20.04, "learning_rate": 1.3287697807831944e-06, "loss": 0.7101, "step": 241160 }, { "epoch": 20.05, "learning_rate": 1.3286589252556606e-06, "loss": 0.8121, "step": 241170 }, { "epoch": 20.05, "learning_rate": 1.3285480697281267e-06, "loss": 0.8338, "step": 241180 }, { "epoch": 20.05, "learning_rate": 1.328437214200593e-06, "loss": 0.7464, "step": 241190 }, { "epoch": 20.05, "learning_rate": 1.3283263586730593e-06, "loss": 0.7582, "step": 241200 }, { "epoch": 20.05, "learning_rate": 1.3282155031455256e-06, "loss": 0.7814, "step": 241210 }, { "epoch": 20.05, "learning_rate": 1.3281046476179917e-06, "loss": 0.7354, "step": 241220 }, { "epoch": 20.05, "learning_rate": 1.327993792090458e-06, "loss": 0.8177, "step": 241230 }, { "epoch": 20.05, "learning_rate": 1.3278829365629243e-06, "loss": 0.7652, "step": 241240 }, { "epoch": 20.05, "learning_rate": 1.3277720810353906e-06, "loss": 0.7286, "step": 241250 }, { "epoch": 20.05, "learning_rate": 1.3276612255078567e-06, "loss": 0.7028, "step": 241260 }, { "epoch": 20.05, "learning_rate": 1.327550369980323e-06, "loss": 0.7973, "step": 241270 }, { "epoch": 20.05, "learning_rate": 1.3274395144527893e-06, "loss": 0.7681, "step": 241280 }, { "epoch": 20.06, "learning_rate": 1.3273286589252558e-06, "loss": 0.769, "step": 241290 }, { "epoch": 20.06, "learning_rate": 1.3272178033977219e-06, "loss": 0.7313, "step": 241300 }, { "epoch": 20.06, "learning_rate": 1.3271069478701881e-06, "loss": 0.7598, "step": 241310 }, { "epoch": 20.06, "learning_rate": 1.3269960923426544e-06, "loss": 0.7041, "step": 241320 }, { "epoch": 20.06, "learning_rate": 1.3268852368151207e-06, "loss": 0.7994, "step": 241330 }, { "epoch": 20.06, "learning_rate": 1.3267743812875868e-06, "loss": 0.7498, "step": 241340 }, { "epoch": 20.06, "learning_rate": 1.3266635257600531e-06, "loss": 0.7773, "step": 241350 }, { "epoch": 20.06, "learning_rate": 1.3265526702325194e-06, "loss": 0.6776, "step": 241360 }, { "epoch": 20.06, "learning_rate": 1.3264529002577392e-06, "loss": 0.7061, "step": 241370 }, { "epoch": 20.06, "learning_rate": 1.3263420447302055e-06, "loss": 0.8096, "step": 241380 }, { "epoch": 20.06, "learning_rate": 1.3262311892026715e-06, "loss": 0.6843, "step": 241390 }, { "epoch": 20.06, "learning_rate": 1.3261203336751378e-06, "loss": 0.7009, "step": 241400 }, { "epoch": 20.07, "learning_rate": 1.3260094781476041e-06, "loss": 0.729, "step": 241410 }, { "epoch": 20.07, "learning_rate": 1.3258986226200704e-06, "loss": 0.7727, "step": 241420 }, { "epoch": 20.07, "learning_rate": 1.3257877670925365e-06, "loss": 0.7734, "step": 241430 }, { "epoch": 20.07, "learning_rate": 1.3256769115650028e-06, "loss": 0.7181, "step": 241440 }, { "epoch": 20.07, "learning_rate": 1.325566056037469e-06, "loss": 0.721, "step": 241450 }, { "epoch": 20.07, "learning_rate": 1.3254552005099354e-06, "loss": 0.7289, "step": 241460 }, { "epoch": 20.07, "learning_rate": 1.3253443449824015e-06, "loss": 0.7006, "step": 241470 }, { "epoch": 20.07, "learning_rate": 1.3252334894548678e-06, "loss": 0.7901, "step": 241480 }, { "epoch": 20.07, "learning_rate": 1.325122633927334e-06, "loss": 0.7625, "step": 241490 }, { "epoch": 20.07, "learning_rate": 1.3250117783998006e-06, "loss": 0.7596, "step": 241500 }, { "epoch": 20.07, "learning_rate": 1.3249009228722667e-06, "loss": 0.7257, "step": 241510 }, { "epoch": 20.07, "learning_rate": 1.324790067344733e-06, "loss": 0.6926, "step": 241520 }, { "epoch": 20.08, "learning_rate": 1.3246792118171993e-06, "loss": 0.7116, "step": 241530 }, { "epoch": 20.08, "learning_rate": 1.3245683562896655e-06, "loss": 0.7236, "step": 241540 }, { "epoch": 20.08, "learning_rate": 1.3244575007621316e-06, "loss": 0.7869, "step": 241550 }, { "epoch": 20.08, "learning_rate": 1.324346645234598e-06, "loss": 0.7771, "step": 241560 }, { "epoch": 20.08, "learning_rate": 1.3242357897070642e-06, "loss": 0.7013, "step": 241570 }, { "epoch": 20.08, "learning_rate": 1.3241249341795305e-06, "loss": 0.8556, "step": 241580 }, { "epoch": 20.08, "learning_rate": 1.3240140786519966e-06, "loss": 0.7625, "step": 241590 }, { "epoch": 20.08, "learning_rate": 1.323903223124463e-06, "loss": 0.7902, "step": 241600 }, { "epoch": 20.08, "learning_rate": 1.3237923675969292e-06, "loss": 0.6617, "step": 241610 }, { "epoch": 20.08, "learning_rate": 1.3236815120693957e-06, "loss": 0.7545, "step": 241620 }, { "epoch": 20.08, "learning_rate": 1.3235706565418618e-06, "loss": 0.8356, "step": 241630 }, { "epoch": 20.08, "learning_rate": 1.323459801014328e-06, "loss": 0.7286, "step": 241640 }, { "epoch": 20.09, "learning_rate": 1.3233489454867944e-06, "loss": 0.6986, "step": 241650 }, { "epoch": 20.09, "learning_rate": 1.3232380899592605e-06, "loss": 0.767, "step": 241660 }, { "epoch": 20.09, "learning_rate": 1.3231272344317268e-06, "loss": 0.7491, "step": 241670 }, { "epoch": 20.09, "learning_rate": 1.323016378904193e-06, "loss": 0.7835, "step": 241680 }, { "epoch": 20.09, "learning_rate": 1.3229055233766593e-06, "loss": 0.7325, "step": 241690 }, { "epoch": 20.09, "learning_rate": 1.3227946678491254e-06, "loss": 0.7631, "step": 241700 }, { "epoch": 20.09, "learning_rate": 1.3226838123215917e-06, "loss": 0.736, "step": 241710 }, { "epoch": 20.09, "learning_rate": 1.322572956794058e-06, "loss": 0.8041, "step": 241720 }, { "epoch": 20.09, "learning_rate": 1.3224621012665243e-06, "loss": 0.813, "step": 241730 }, { "epoch": 20.09, "learning_rate": 1.3223512457389906e-06, "loss": 0.7179, "step": 241740 }, { "epoch": 20.09, "learning_rate": 1.322240390211457e-06, "loss": 0.76, "step": 241750 }, { "epoch": 20.09, "learning_rate": 1.3221295346839232e-06, "loss": 0.7426, "step": 241760 }, { "epoch": 20.1, "learning_rate": 1.3220186791563895e-06, "loss": 0.7457, "step": 241770 }, { "epoch": 20.1, "learning_rate": 1.3219078236288556e-06, "loss": 0.8273, "step": 241780 }, { "epoch": 20.1, "learning_rate": 1.3217969681013219e-06, "loss": 0.7308, "step": 241790 }, { "epoch": 20.1, "learning_rate": 1.3216861125737882e-06, "loss": 0.7821, "step": 241800 }, { "epoch": 20.1, "learning_rate": 1.3215752570462545e-06, "loss": 0.7138, "step": 241810 }, { "epoch": 20.1, "learning_rate": 1.3214644015187205e-06, "loss": 0.7659, "step": 241820 }, { "epoch": 20.1, "learning_rate": 1.3213535459911868e-06, "loss": 0.7876, "step": 241830 }, { "epoch": 20.1, "learning_rate": 1.3212426904636531e-06, "loss": 0.7639, "step": 241840 }, { "epoch": 20.1, "learning_rate": 1.3211318349361194e-06, "loss": 0.6736, "step": 241850 }, { "epoch": 20.1, "learning_rate": 1.3210209794085857e-06, "loss": 0.722, "step": 241860 }, { "epoch": 20.1, "learning_rate": 1.320910123881052e-06, "loss": 0.716, "step": 241870 }, { "epoch": 20.1, "learning_rate": 1.3207992683535183e-06, "loss": 0.7958, "step": 241880 }, { "epoch": 20.11, "learning_rate": 1.3206884128259846e-06, "loss": 0.8057, "step": 241890 }, { "epoch": 20.11, "learning_rate": 1.3205775572984507e-06, "loss": 0.7138, "step": 241900 }, { "epoch": 20.11, "learning_rate": 1.320466701770917e-06, "loss": 0.7197, "step": 241910 }, { "epoch": 20.11, "learning_rate": 1.3203558462433833e-06, "loss": 0.7678, "step": 241920 }, { "epoch": 20.11, "learning_rate": 1.3202449907158496e-06, "loss": 0.8031, "step": 241930 }, { "epoch": 20.11, "learning_rate": 1.3201341351883157e-06, "loss": 0.8029, "step": 241940 }, { "epoch": 20.11, "learning_rate": 1.320023279660782e-06, "loss": 0.7868, "step": 241950 }, { "epoch": 20.11, "learning_rate": 1.3199124241332483e-06, "loss": 0.7661, "step": 241960 }, { "epoch": 20.11, "learning_rate": 1.3198015686057146e-06, "loss": 0.7823, "step": 241970 }, { "epoch": 20.11, "learning_rate": 1.3196907130781806e-06, "loss": 0.8162, "step": 241980 }, { "epoch": 20.11, "learning_rate": 1.3195798575506471e-06, "loss": 0.7315, "step": 241990 }, { "epoch": 20.11, "learning_rate": 1.3194690020231134e-06, "loss": 0.7414, "step": 242000 }, { "epoch": 20.12, "learning_rate": 1.3193581464955797e-06, "loss": 0.7023, "step": 242010 }, { "epoch": 20.12, "learning_rate": 1.3192472909680458e-06, "loss": 0.7094, "step": 242020 }, { "epoch": 20.12, "learning_rate": 1.3191364354405121e-06, "loss": 0.7712, "step": 242030 }, { "epoch": 20.12, "learning_rate": 1.3190255799129784e-06, "loss": 0.7707, "step": 242040 }, { "epoch": 20.12, "learning_rate": 1.3189147243854447e-06, "loss": 0.6967, "step": 242050 }, { "epoch": 20.12, "learning_rate": 1.3188038688579108e-06, "loss": 0.7711, "step": 242060 }, { "epoch": 20.12, "learning_rate": 1.318693013330377e-06, "loss": 0.748, "step": 242070 }, { "epoch": 20.12, "learning_rate": 1.3185821578028434e-06, "loss": 0.8015, "step": 242080 }, { "epoch": 20.12, "learning_rate": 1.3184713022753095e-06, "loss": 0.7989, "step": 242090 }, { "epoch": 20.12, "learning_rate": 1.3183604467477758e-06, "loss": 0.7302, "step": 242100 }, { "epoch": 20.12, "learning_rate": 1.3182495912202423e-06, "loss": 0.7877, "step": 242110 }, { "epoch": 20.12, "learning_rate": 1.3181387356927086e-06, "loss": 0.751, "step": 242120 }, { "epoch": 20.13, "learning_rate": 1.3180278801651746e-06, "loss": 0.7586, "step": 242130 }, { "epoch": 20.13, "learning_rate": 1.317917024637641e-06, "loss": 0.7439, "step": 242140 }, { "epoch": 20.13, "learning_rate": 1.3178061691101072e-06, "loss": 0.7854, "step": 242150 }, { "epoch": 20.13, "learning_rate": 1.3176953135825735e-06, "loss": 0.7329, "step": 242160 }, { "epoch": 20.13, "learning_rate": 1.3175844580550396e-06, "loss": 0.7503, "step": 242170 }, { "epoch": 20.13, "learning_rate": 1.317473602527506e-06, "loss": 0.8057, "step": 242180 }, { "epoch": 20.13, "learning_rate": 1.3173627469999722e-06, "loss": 0.7349, "step": 242190 }, { "epoch": 20.13, "learning_rate": 1.3172518914724385e-06, "loss": 0.7887, "step": 242200 }, { "epoch": 20.13, "learning_rate": 1.3171410359449046e-06, "loss": 0.7476, "step": 242210 }, { "epoch": 20.13, "learning_rate": 1.3170301804173709e-06, "loss": 0.7301, "step": 242220 }, { "epoch": 20.13, "learning_rate": 1.3169193248898374e-06, "loss": 0.7109, "step": 242230 }, { "epoch": 20.13, "learning_rate": 1.3168084693623037e-06, "loss": 0.784, "step": 242240 }, { "epoch": 20.14, "learning_rate": 1.3166976138347698e-06, "loss": 0.735, "step": 242250 }, { "epoch": 20.14, "learning_rate": 1.316586758307236e-06, "loss": 0.7887, "step": 242260 }, { "epoch": 20.14, "learning_rate": 1.3164759027797024e-06, "loss": 0.7438, "step": 242270 }, { "epoch": 20.14, "learning_rate": 1.3163650472521687e-06, "loss": 0.7757, "step": 242280 }, { "epoch": 20.14, "learning_rate": 1.3162541917246347e-06, "loss": 0.7385, "step": 242290 }, { "epoch": 20.14, "learning_rate": 1.316143336197101e-06, "loss": 0.8321, "step": 242300 }, { "epoch": 20.14, "learning_rate": 1.3160324806695673e-06, "loss": 0.7502, "step": 242310 }, { "epoch": 20.14, "learning_rate": 1.3159216251420336e-06, "loss": 0.7264, "step": 242320 }, { "epoch": 20.14, "learning_rate": 1.3158107696144997e-06, "loss": 0.8012, "step": 242330 }, { "epoch": 20.14, "learning_rate": 1.315699914086966e-06, "loss": 0.7154, "step": 242340 }, { "epoch": 20.14, "learning_rate": 1.3155890585594323e-06, "loss": 0.7485, "step": 242350 }, { "epoch": 20.14, "learning_rate": 1.3154782030318988e-06, "loss": 0.7253, "step": 242360 }, { "epoch": 20.15, "learning_rate": 1.3153673475043649e-06, "loss": 0.7781, "step": 242370 }, { "epoch": 20.15, "learning_rate": 1.3152564919768312e-06, "loss": 0.7381, "step": 242380 }, { "epoch": 20.15, "learning_rate": 1.3151456364492975e-06, "loss": 0.8355, "step": 242390 }, { "epoch": 20.15, "learning_rate": 1.3150347809217638e-06, "loss": 0.7096, "step": 242400 }, { "epoch": 20.15, "learning_rate": 1.3149239253942299e-06, "loss": 0.7245, "step": 242410 }, { "epoch": 20.15, "learning_rate": 1.3148130698666962e-06, "loss": 0.7659, "step": 242420 }, { "epoch": 20.15, "learning_rate": 1.3147022143391624e-06, "loss": 0.8556, "step": 242430 }, { "epoch": 20.15, "learning_rate": 1.3145913588116287e-06, "loss": 0.7622, "step": 242440 }, { "epoch": 20.15, "learning_rate": 1.3144805032840948e-06, "loss": 0.7518, "step": 242450 }, { "epoch": 20.15, "learning_rate": 1.3143696477565611e-06, "loss": 0.7578, "step": 242460 }, { "epoch": 20.15, "learning_rate": 1.3142587922290274e-06, "loss": 0.7664, "step": 242470 }, { "epoch": 20.15, "learning_rate": 1.314147936701494e-06, "loss": 0.7756, "step": 242480 }, { "epoch": 20.16, "learning_rate": 1.31403708117396e-06, "loss": 0.8166, "step": 242490 }, { "epoch": 20.16, "learning_rate": 1.3139262256464263e-06, "loss": 0.7382, "step": 242500 }, { "epoch": 20.16, "learning_rate": 1.3138153701188926e-06, "loss": 0.7295, "step": 242510 }, { "epoch": 20.16, "learning_rate": 1.3137045145913587e-06, "loss": 0.7865, "step": 242520 }, { "epoch": 20.16, "learning_rate": 1.313593659063825e-06, "loss": 0.8678, "step": 242530 }, { "epoch": 20.16, "learning_rate": 1.3134828035362913e-06, "loss": 0.7467, "step": 242540 }, { "epoch": 20.16, "learning_rate": 1.3133719480087576e-06, "loss": 0.7258, "step": 242550 }, { "epoch": 20.16, "learning_rate": 1.3132610924812236e-06, "loss": 0.7489, "step": 242560 }, { "epoch": 20.16, "learning_rate": 1.31315023695369e-06, "loss": 0.7095, "step": 242570 }, { "epoch": 20.16, "learning_rate": 1.3130393814261562e-06, "loss": 0.9038, "step": 242580 }, { "epoch": 20.16, "learning_rate": 1.3129285258986225e-06, "loss": 0.7578, "step": 242590 }, { "epoch": 20.16, "learning_rate": 1.3128176703710888e-06, "loss": 0.7568, "step": 242600 }, { "epoch": 20.17, "learning_rate": 1.3127068148435551e-06, "loss": 0.8083, "step": 242610 }, { "epoch": 20.17, "learning_rate": 1.3125959593160214e-06, "loss": 0.7045, "step": 242620 }, { "epoch": 20.17, "learning_rate": 1.3124851037884877e-06, "loss": 0.7761, "step": 242630 }, { "epoch": 20.17, "learning_rate": 1.3123742482609538e-06, "loss": 0.7253, "step": 242640 }, { "epoch": 20.17, "learning_rate": 1.31226339273342e-06, "loss": 0.746, "step": 242650 }, { "epoch": 20.17, "learning_rate": 1.3121525372058864e-06, "loss": 0.7631, "step": 242660 }, { "epoch": 20.17, "learning_rate": 1.3120416816783527e-06, "loss": 0.7405, "step": 242670 }, { "epoch": 20.17, "learning_rate": 1.3119308261508188e-06, "loss": 0.8137, "step": 242680 }, { "epoch": 20.17, "learning_rate": 1.311819970623285e-06, "loss": 0.7217, "step": 242690 }, { "epoch": 20.17, "learning_rate": 1.3117091150957514e-06, "loss": 0.7372, "step": 242700 }, { "epoch": 20.17, "learning_rate": 1.3115982595682177e-06, "loss": 0.7161, "step": 242710 }, { "epoch": 20.17, "learning_rate": 1.3114874040406837e-06, "loss": 0.7311, "step": 242720 }, { "epoch": 20.18, "learning_rate": 1.3113765485131502e-06, "loss": 0.794, "step": 242730 }, { "epoch": 20.18, "learning_rate": 1.3112656929856165e-06, "loss": 0.7184, "step": 242740 }, { "epoch": 20.18, "learning_rate": 1.3111548374580828e-06, "loss": 0.7276, "step": 242750 }, { "epoch": 20.18, "learning_rate": 1.311043981930549e-06, "loss": 0.7507, "step": 242760 }, { "epoch": 20.18, "learning_rate": 1.3109331264030152e-06, "loss": 0.7062, "step": 242770 }, { "epoch": 20.18, "learning_rate": 1.3108222708754815e-06, "loss": 0.744, "step": 242780 }, { "epoch": 20.18, "learning_rate": 1.3107114153479478e-06, "loss": 0.7757, "step": 242790 }, { "epoch": 20.18, "learning_rate": 1.3106005598204139e-06, "loss": 0.7614, "step": 242800 }, { "epoch": 20.18, "learning_rate": 1.3104897042928802e-06, "loss": 0.6902, "step": 242810 }, { "epoch": 20.18, "learning_rate": 1.3103788487653465e-06, "loss": 0.7828, "step": 242820 }, { "epoch": 20.18, "learning_rate": 1.3102679932378128e-06, "loss": 0.8595, "step": 242830 }, { "epoch": 20.18, "learning_rate": 1.3101571377102789e-06, "loss": 0.7654, "step": 242840 }, { "epoch": 20.19, "learning_rate": 1.3100462821827454e-06, "loss": 0.7726, "step": 242850 }, { "epoch": 20.19, "learning_rate": 1.3099354266552117e-06, "loss": 0.7414, "step": 242860 }, { "epoch": 20.19, "learning_rate": 1.309824571127678e-06, "loss": 0.7911, "step": 242870 }, { "epoch": 20.19, "learning_rate": 1.309713715600144e-06, "loss": 0.7864, "step": 242880 }, { "epoch": 20.19, "learning_rate": 1.3096028600726103e-06, "loss": 0.7163, "step": 242890 }, { "epoch": 20.19, "learning_rate": 1.3094920045450766e-06, "loss": 0.7489, "step": 242900 }, { "epoch": 20.19, "learning_rate": 1.3093811490175427e-06, "loss": 0.6945, "step": 242910 }, { "epoch": 20.19, "learning_rate": 1.309270293490009e-06, "loss": 0.7035, "step": 242920 }, { "epoch": 20.19, "learning_rate": 1.3091594379624753e-06, "loss": 0.7393, "step": 242930 }, { "epoch": 20.19, "learning_rate": 1.3090485824349416e-06, "loss": 0.7527, "step": 242940 }, { "epoch": 20.19, "learning_rate": 1.3089377269074077e-06, "loss": 0.7888, "step": 242950 }, { "epoch": 20.19, "learning_rate": 1.308826871379874e-06, "loss": 0.7601, "step": 242960 }, { "epoch": 20.2, "learning_rate": 1.3087160158523405e-06, "loss": 0.7445, "step": 242970 }, { "epoch": 20.2, "learning_rate": 1.3086051603248068e-06, "loss": 0.8346, "step": 242980 }, { "epoch": 20.2, "learning_rate": 1.3084943047972729e-06, "loss": 0.7253, "step": 242990 }, { "epoch": 20.2, "learning_rate": 1.3083834492697392e-06, "loss": 0.7122, "step": 243000 }, { "epoch": 20.2, "learning_rate": 1.3082725937422055e-06, "loss": 0.7591, "step": 243010 }, { "epoch": 20.2, "learning_rate": 1.3081617382146718e-06, "loss": 0.7863, "step": 243020 }, { "epoch": 20.2, "learning_rate": 1.3080508826871378e-06, "loss": 0.7594, "step": 243030 }, { "epoch": 20.2, "learning_rate": 1.3079400271596041e-06, "loss": 0.728, "step": 243040 }, { "epoch": 20.2, "learning_rate": 1.3078291716320704e-06, "loss": 0.7541, "step": 243050 }, { "epoch": 20.2, "learning_rate": 1.3077183161045367e-06, "loss": 0.7263, "step": 243060 }, { "epoch": 20.2, "learning_rate": 1.3076074605770028e-06, "loss": 0.807, "step": 243070 }, { "epoch": 20.2, "learning_rate": 1.307496605049469e-06, "loss": 0.759, "step": 243080 }, { "epoch": 20.21, "learning_rate": 1.3073857495219356e-06, "loss": 0.7686, "step": 243090 }, { "epoch": 20.21, "learning_rate": 1.307274893994402e-06, "loss": 0.6884, "step": 243100 }, { "epoch": 20.21, "learning_rate": 1.307164038466868e-06, "loss": 0.7866, "step": 243110 }, { "epoch": 20.21, "learning_rate": 1.3070531829393343e-06, "loss": 0.6394, "step": 243120 }, { "epoch": 20.21, "learning_rate": 1.3069423274118006e-06, "loss": 0.7912, "step": 243130 }, { "epoch": 20.21, "learning_rate": 1.3068314718842669e-06, "loss": 0.7207, "step": 243140 }, { "epoch": 20.21, "learning_rate": 1.306720616356733e-06, "loss": 0.7158, "step": 243150 }, { "epoch": 20.21, "learning_rate": 1.3066097608291993e-06, "loss": 0.7672, "step": 243160 }, { "epoch": 20.21, "learning_rate": 1.3064989053016655e-06, "loss": 0.8118, "step": 243170 }, { "epoch": 20.21, "learning_rate": 1.3063880497741318e-06, "loss": 0.7206, "step": 243180 }, { "epoch": 20.21, "learning_rate": 1.306277194246598e-06, "loss": 0.7316, "step": 243190 }, { "epoch": 20.21, "learning_rate": 1.3061663387190642e-06, "loss": 0.7651, "step": 243200 }, { "epoch": 20.22, "learning_rate": 1.3060554831915305e-06, "loss": 0.7989, "step": 243210 }, { "epoch": 20.22, "learning_rate": 1.305944627663997e-06, "loss": 0.7759, "step": 243220 }, { "epoch": 20.22, "learning_rate": 1.3058337721364631e-06, "loss": 0.808, "step": 243230 }, { "epoch": 20.22, "learning_rate": 1.3057229166089294e-06, "loss": 0.7106, "step": 243240 }, { "epoch": 20.22, "learning_rate": 1.3056120610813957e-06, "loss": 0.7554, "step": 243250 }, { "epoch": 20.22, "learning_rate": 1.305501205553862e-06, "loss": 0.8237, "step": 243260 }, { "epoch": 20.22, "learning_rate": 1.305390350026328e-06, "loss": 0.6979, "step": 243270 }, { "epoch": 20.22, "learning_rate": 1.3052794944987944e-06, "loss": 0.7838, "step": 243280 }, { "epoch": 20.22, "learning_rate": 1.3051686389712607e-06, "loss": 0.7325, "step": 243290 }, { "epoch": 20.22, "learning_rate": 1.3050577834437268e-06, "loss": 0.7332, "step": 243300 }, { "epoch": 20.22, "learning_rate": 1.304946927916193e-06, "loss": 0.6862, "step": 243310 }, { "epoch": 20.22, "learning_rate": 1.3048360723886593e-06, "loss": 0.6858, "step": 243320 }, { "epoch": 20.23, "learning_rate": 1.3047252168611256e-06, "loss": 0.8352, "step": 243330 }, { "epoch": 20.23, "learning_rate": 1.3046143613335921e-06, "loss": 0.7586, "step": 243340 }, { "epoch": 20.23, "learning_rate": 1.3045035058060582e-06, "loss": 0.7788, "step": 243350 }, { "epoch": 20.23, "learning_rate": 1.3043926502785245e-06, "loss": 0.7609, "step": 243360 }, { "epoch": 20.23, "learning_rate": 1.3042817947509908e-06, "loss": 0.7313, "step": 243370 }, { "epoch": 20.23, "learning_rate": 1.304170939223457e-06, "loss": 0.7997, "step": 243380 }, { "epoch": 20.23, "learning_rate": 1.3040600836959232e-06, "loss": 0.6915, "step": 243390 }, { "epoch": 20.23, "learning_rate": 1.3039492281683895e-06, "loss": 0.7243, "step": 243400 }, { "epoch": 20.23, "learning_rate": 1.3038383726408558e-06, "loss": 0.7225, "step": 243410 }, { "epoch": 20.23, "learning_rate": 1.3037275171133219e-06, "loss": 0.765, "step": 243420 }, { "epoch": 20.23, "learning_rate": 1.3036166615857882e-06, "loss": 0.8162, "step": 243430 }, { "epoch": 20.23, "learning_rate": 1.3035058060582545e-06, "loss": 0.7672, "step": 243440 }, { "epoch": 20.24, "learning_rate": 1.3033949505307208e-06, "loss": 0.6989, "step": 243450 }, { "epoch": 20.24, "learning_rate": 1.303284095003187e-06, "loss": 0.7335, "step": 243460 }, { "epoch": 20.24, "learning_rate": 1.3031732394756533e-06, "loss": 0.8059, "step": 243470 }, { "epoch": 20.24, "learning_rate": 1.3030623839481196e-06, "loss": 0.7952, "step": 243480 }, { "epoch": 20.24, "learning_rate": 1.302951528420586e-06, "loss": 0.7477, "step": 243490 }, { "epoch": 20.24, "learning_rate": 1.302840672893052e-06, "loss": 0.7543, "step": 243500 }, { "epoch": 20.24, "learning_rate": 1.3027298173655183e-06, "loss": 0.7233, "step": 243510 }, { "epoch": 20.24, "learning_rate": 1.3026189618379846e-06, "loss": 0.7385, "step": 243520 }, { "epoch": 20.24, "learning_rate": 1.302508106310451e-06, "loss": 0.7657, "step": 243530 }, { "epoch": 20.24, "learning_rate": 1.302397250782917e-06, "loss": 0.6978, "step": 243540 }, { "epoch": 20.24, "learning_rate": 1.3022863952553833e-06, "loss": 0.7234, "step": 243550 }, { "epoch": 20.24, "learning_rate": 1.3021755397278496e-06, "loss": 0.7309, "step": 243560 }, { "epoch": 20.25, "learning_rate": 1.3020646842003159e-06, "loss": 0.7526, "step": 243570 }, { "epoch": 20.25, "learning_rate": 1.301953828672782e-06, "loss": 0.7629, "step": 243580 }, { "epoch": 20.25, "learning_rate": 1.3018429731452485e-06, "loss": 0.808, "step": 243590 }, { "epoch": 20.25, "learning_rate": 1.3017321176177148e-06, "loss": 0.7262, "step": 243600 }, { "epoch": 20.25, "learning_rate": 1.301621262090181e-06, "loss": 0.7504, "step": 243610 }, { "epoch": 20.25, "learning_rate": 1.3015104065626471e-06, "loss": 0.7441, "step": 243620 }, { "epoch": 20.25, "learning_rate": 1.3013995510351134e-06, "loss": 0.7555, "step": 243630 }, { "epoch": 20.25, "learning_rate": 1.3012886955075797e-06, "loss": 0.8028, "step": 243640 }, { "epoch": 20.25, "learning_rate": 1.301177839980046e-06, "loss": 0.7494, "step": 243650 }, { "epoch": 20.25, "learning_rate": 1.3010669844525121e-06, "loss": 0.7982, "step": 243660 }, { "epoch": 20.25, "learning_rate": 1.3009561289249784e-06, "loss": 0.6945, "step": 243670 }, { "epoch": 20.25, "learning_rate": 1.3008452733974447e-06, "loss": 0.7228, "step": 243680 }, { "epoch": 20.26, "learning_rate": 1.300734417869911e-06, "loss": 0.7631, "step": 243690 }, { "epoch": 20.26, "learning_rate": 1.300623562342377e-06, "loss": 0.761, "step": 243700 }, { "epoch": 20.26, "learning_rate": 1.3005127068148436e-06, "loss": 0.7309, "step": 243710 }, { "epoch": 20.26, "learning_rate": 1.3004018512873099e-06, "loss": 0.7515, "step": 243720 }, { "epoch": 20.26, "learning_rate": 1.3002909957597762e-06, "loss": 0.7526, "step": 243730 }, { "epoch": 20.26, "learning_rate": 1.3001801402322423e-06, "loss": 0.7074, "step": 243740 }, { "epoch": 20.26, "learning_rate": 1.3000692847047086e-06, "loss": 0.718, "step": 243750 }, { "epoch": 20.26, "learning_rate": 1.2999584291771749e-06, "loss": 0.8096, "step": 243760 }, { "epoch": 20.26, "learning_rate": 1.299847573649641e-06, "loss": 0.7173, "step": 243770 }, { "epoch": 20.26, "learning_rate": 1.2997367181221072e-06, "loss": 0.7598, "step": 243780 }, { "epoch": 20.26, "learning_rate": 1.2996258625945735e-06, "loss": 0.7615, "step": 243790 }, { "epoch": 20.26, "learning_rate": 1.2995150070670398e-06, "loss": 0.7365, "step": 243800 }, { "epoch": 20.27, "learning_rate": 1.299404151539506e-06, "loss": 0.7425, "step": 243810 }, { "epoch": 20.27, "learning_rate": 1.2992932960119722e-06, "loss": 0.7241, "step": 243820 }, { "epoch": 20.27, "learning_rate": 1.2991824404844387e-06, "loss": 0.8232, "step": 243830 }, { "epoch": 20.27, "learning_rate": 1.299071584956905e-06, "loss": 0.7263, "step": 243840 }, { "epoch": 20.27, "learning_rate": 1.298960729429371e-06, "loss": 0.7395, "step": 243850 }, { "epoch": 20.27, "learning_rate": 1.2988498739018374e-06, "loss": 0.6883, "step": 243860 }, { "epoch": 20.27, "learning_rate": 1.2987390183743037e-06, "loss": 0.7791, "step": 243870 }, { "epoch": 20.27, "learning_rate": 1.29862816284677e-06, "loss": 0.8247, "step": 243880 }, { "epoch": 20.27, "learning_rate": 1.298517307319236e-06, "loss": 0.7853, "step": 243890 }, { "epoch": 20.27, "learning_rate": 1.2984064517917024e-06, "loss": 0.7588, "step": 243900 }, { "epoch": 20.27, "learning_rate": 1.2982955962641686e-06, "loss": 0.7396, "step": 243910 }, { "epoch": 20.27, "learning_rate": 1.298184740736635e-06, "loss": 0.759, "step": 243920 }, { "epoch": 20.28, "learning_rate": 1.298073885209101e-06, "loss": 0.8008, "step": 243930 }, { "epoch": 20.28, "learning_rate": 1.2979630296815673e-06, "loss": 0.6904, "step": 243940 }, { "epoch": 20.28, "learning_rate": 1.2978521741540338e-06, "loss": 0.7071, "step": 243950 }, { "epoch": 20.28, "learning_rate": 1.2977413186265001e-06, "loss": 0.7132, "step": 243960 }, { "epoch": 20.28, "learning_rate": 1.2976304630989662e-06, "loss": 0.7753, "step": 243970 }, { "epoch": 20.28, "learning_rate": 1.2975196075714325e-06, "loss": 0.7292, "step": 243980 }, { "epoch": 20.28, "learning_rate": 1.2974087520438988e-06, "loss": 0.7279, "step": 243990 }, { "epoch": 20.28, "learning_rate": 1.297297896516365e-06, "loss": 0.7154, "step": 244000 }, { "epoch": 20.28, "learning_rate": 1.2971870409888312e-06, "loss": 0.7542, "step": 244010 }, { "epoch": 20.28, "learning_rate": 1.2970761854612975e-06, "loss": 0.7377, "step": 244020 }, { "epoch": 20.28, "learning_rate": 1.2969653299337638e-06, "loss": 0.832, "step": 244030 }, { "epoch": 20.28, "learning_rate": 1.29685447440623e-06, "loss": 0.8001, "step": 244040 }, { "epoch": 20.29, "learning_rate": 1.2967436188786961e-06, "loss": 0.7617, "step": 244050 }, { "epoch": 20.29, "learning_rate": 1.2966327633511624e-06, "loss": 0.77, "step": 244060 }, { "epoch": 20.29, "learning_rate": 1.2965219078236287e-06, "loss": 0.7259, "step": 244070 }, { "epoch": 20.29, "learning_rate": 1.2964110522960952e-06, "loss": 0.7752, "step": 244080 }, { "epoch": 20.29, "learning_rate": 1.2963001967685613e-06, "loss": 0.7638, "step": 244090 }, { "epoch": 20.29, "learning_rate": 1.2961893412410276e-06, "loss": 0.761, "step": 244100 }, { "epoch": 20.29, "learning_rate": 1.296078485713494e-06, "loss": 0.7567, "step": 244110 }, { "epoch": 20.29, "learning_rate": 1.2959676301859602e-06, "loss": 0.7061, "step": 244120 }, { "epoch": 20.29, "learning_rate": 1.2958567746584263e-06, "loss": 0.8072, "step": 244130 }, { "epoch": 20.29, "learning_rate": 1.2957459191308926e-06, "loss": 0.6797, "step": 244140 }, { "epoch": 20.29, "learning_rate": 1.2956350636033589e-06, "loss": 0.7515, "step": 244150 }, { "epoch": 20.29, "learning_rate": 1.295524208075825e-06, "loss": 0.7673, "step": 244160 }, { "epoch": 20.3, "learning_rate": 1.2954133525482913e-06, "loss": 0.7475, "step": 244170 }, { "epoch": 20.3, "learning_rate": 1.2953024970207576e-06, "loss": 0.783, "step": 244180 }, { "epoch": 20.3, "learning_rate": 1.2951916414932239e-06, "loss": 0.7639, "step": 244190 }, { "epoch": 20.3, "learning_rate": 1.2950807859656902e-06, "loss": 0.8025, "step": 244200 }, { "epoch": 20.3, "learning_rate": 1.2949699304381565e-06, "loss": 0.7628, "step": 244210 }, { "epoch": 20.3, "learning_rate": 1.2948590749106227e-06, "loss": 0.7465, "step": 244220 }, { "epoch": 20.3, "learning_rate": 1.294748219383089e-06, "loss": 0.8177, "step": 244230 }, { "epoch": 20.3, "learning_rate": 1.2946373638555551e-06, "loss": 0.7689, "step": 244240 }, { "epoch": 20.3, "learning_rate": 1.2945265083280214e-06, "loss": 0.7774, "step": 244250 }, { "epoch": 20.3, "learning_rate": 1.2944156528004877e-06, "loss": 0.7543, "step": 244260 }, { "epoch": 20.3, "learning_rate": 1.294304797272954e-06, "loss": 0.7169, "step": 244270 }, { "epoch": 20.3, "learning_rate": 1.29419394174542e-06, "loss": 0.8191, "step": 244280 }, { "epoch": 20.31, "learning_rate": 1.2940830862178864e-06, "loss": 0.7962, "step": 244290 }, { "epoch": 20.31, "learning_rate": 1.2939722306903527e-06, "loss": 0.7329, "step": 244300 }, { "epoch": 20.31, "learning_rate": 1.293861375162819e-06, "loss": 0.6393, "step": 244310 }, { "epoch": 20.31, "learning_rate": 1.2937505196352853e-06, "loss": 0.7133, "step": 244320 }, { "epoch": 20.31, "learning_rate": 1.2936396641077516e-06, "loss": 0.7485, "step": 244330 }, { "epoch": 20.31, "learning_rate": 1.2935288085802179e-06, "loss": 0.6853, "step": 244340 }, { "epoch": 20.31, "learning_rate": 1.2934179530526842e-06, "loss": 0.7284, "step": 244350 }, { "epoch": 20.31, "learning_rate": 1.2933070975251502e-06, "loss": 0.8432, "step": 244360 }, { "epoch": 20.31, "learning_rate": 1.2931962419976165e-06, "loss": 0.7063, "step": 244370 }, { "epoch": 20.31, "learning_rate": 1.2930853864700828e-06, "loss": 0.8041, "step": 244380 }, { "epoch": 20.31, "learning_rate": 1.2929745309425491e-06, "loss": 0.7578, "step": 244390 }, { "epoch": 20.31, "learning_rate": 1.2928636754150152e-06, "loss": 0.7951, "step": 244400 }, { "epoch": 20.32, "learning_rate": 1.2927528198874815e-06, "loss": 0.7529, "step": 244410 }, { "epoch": 20.32, "learning_rate": 1.2926419643599478e-06, "loss": 0.8258, "step": 244420 }, { "epoch": 20.32, "learning_rate": 1.292531108832414e-06, "loss": 0.7734, "step": 244430 }, { "epoch": 20.32, "learning_rate": 1.2924202533048802e-06, "loss": 0.7836, "step": 244440 }, { "epoch": 20.32, "learning_rate": 1.2923093977773467e-06, "loss": 0.6877, "step": 244450 }, { "epoch": 20.32, "learning_rate": 1.292198542249813e-06, "loss": 0.7697, "step": 244460 }, { "epoch": 20.32, "learning_rate": 1.2920876867222793e-06, "loss": 0.7617, "step": 244470 }, { "epoch": 20.32, "learning_rate": 1.2919768311947454e-06, "loss": 0.7964, "step": 244480 }, { "epoch": 20.32, "learning_rate": 1.2918659756672117e-06, "loss": 0.7574, "step": 244490 }, { "epoch": 20.32, "learning_rate": 1.291755120139678e-06, "loss": 0.8411, "step": 244500 }, { "epoch": 20.32, "learning_rate": 1.2916442646121443e-06, "loss": 0.7457, "step": 244510 }, { "epoch": 20.32, "learning_rate": 1.2915334090846103e-06, "loss": 0.7551, "step": 244520 }, { "epoch": 20.32, "learning_rate": 1.2914225535570766e-06, "loss": 0.7623, "step": 244530 }, { "epoch": 20.33, "learning_rate": 1.291311698029543e-06, "loss": 0.749, "step": 244540 }, { "epoch": 20.33, "learning_rate": 1.291200842502009e-06, "loss": 0.7347, "step": 244550 }, { "epoch": 20.33, "learning_rate": 1.2910899869744753e-06, "loss": 0.8128, "step": 244560 }, { "epoch": 20.33, "learning_rate": 1.2909791314469418e-06, "loss": 0.7607, "step": 244570 }, { "epoch": 20.33, "learning_rate": 1.2908682759194081e-06, "loss": 0.824, "step": 244580 }, { "epoch": 20.33, "learning_rate": 1.2907574203918742e-06, "loss": 0.7279, "step": 244590 }, { "epoch": 20.33, "learning_rate": 1.2906465648643405e-06, "loss": 0.7612, "step": 244600 }, { "epoch": 20.33, "learning_rate": 1.2905357093368068e-06, "loss": 0.6789, "step": 244610 }, { "epoch": 20.33, "learning_rate": 1.290424853809273e-06, "loss": 0.7634, "step": 244620 }, { "epoch": 20.33, "learning_rate": 1.2903139982817392e-06, "loss": 0.7733, "step": 244630 }, { "epoch": 20.33, "learning_rate": 1.2902031427542055e-06, "loss": 0.7529, "step": 244640 }, { "epoch": 20.33, "learning_rate": 1.2900922872266718e-06, "loss": 0.7235, "step": 244650 }, { "epoch": 20.34, "learning_rate": 1.289981431699138e-06, "loss": 0.7721, "step": 244660 }, { "epoch": 20.34, "learning_rate": 1.2898705761716041e-06, "loss": 0.7328, "step": 244670 }, { "epoch": 20.34, "learning_rate": 1.2897597206440704e-06, "loss": 0.8206, "step": 244680 }, { "epoch": 20.34, "learning_rate": 1.289648865116537e-06, "loss": 0.7366, "step": 244690 }, { "epoch": 20.34, "learning_rate": 1.2895380095890032e-06, "loss": 0.683, "step": 244700 }, { "epoch": 20.34, "learning_rate": 1.2894271540614693e-06, "loss": 0.7292, "step": 244710 }, { "epoch": 20.34, "learning_rate": 1.2893162985339356e-06, "loss": 0.7689, "step": 244720 }, { "epoch": 20.34, "learning_rate": 1.289205443006402e-06, "loss": 0.8047, "step": 244730 }, { "epoch": 20.34, "learning_rate": 1.2890945874788682e-06, "loss": 0.7616, "step": 244740 }, { "epoch": 20.34, "learning_rate": 1.2889837319513343e-06, "loss": 0.6907, "step": 244750 }, { "epoch": 20.34, "learning_rate": 1.2888728764238006e-06, "loss": 0.8129, "step": 244760 }, { "epoch": 20.34, "learning_rate": 1.2887620208962669e-06, "loss": 0.7319, "step": 244770 }, { "epoch": 20.35, "learning_rate": 1.2886511653687332e-06, "loss": 0.8057, "step": 244780 }, { "epoch": 20.35, "learning_rate": 1.2885403098411993e-06, "loss": 0.7669, "step": 244790 }, { "epoch": 20.35, "learning_rate": 1.2884294543136655e-06, "loss": 0.7537, "step": 244800 }, { "epoch": 20.35, "learning_rate": 1.2883185987861318e-06, "loss": 0.7378, "step": 244810 }, { "epoch": 20.35, "learning_rate": 1.2882077432585983e-06, "loss": 0.7025, "step": 244820 }, { "epoch": 20.35, "learning_rate": 1.2880968877310644e-06, "loss": 0.796, "step": 244830 }, { "epoch": 20.35, "learning_rate": 1.2879860322035307e-06, "loss": 0.7755, "step": 244840 }, { "epoch": 20.35, "learning_rate": 1.287875176675997e-06, "loss": 0.7454, "step": 244850 }, { "epoch": 20.35, "learning_rate": 1.2877643211484633e-06, "loss": 0.7199, "step": 244860 }, { "epoch": 20.35, "learning_rate": 1.2876534656209294e-06, "loss": 0.6947, "step": 244870 }, { "epoch": 20.35, "learning_rate": 1.2875426100933957e-06, "loss": 0.8425, "step": 244880 }, { "epoch": 20.35, "learning_rate": 1.287431754565862e-06, "loss": 0.7136, "step": 244890 }, { "epoch": 20.36, "learning_rate": 1.2873208990383283e-06, "loss": 0.7499, "step": 244900 }, { "epoch": 20.36, "learning_rate": 1.2872100435107944e-06, "loss": 0.7341, "step": 244910 }, { "epoch": 20.36, "learning_rate": 1.2870991879832607e-06, "loss": 0.7994, "step": 244920 }, { "epoch": 20.36, "learning_rate": 1.286988332455727e-06, "loss": 0.7867, "step": 244930 }, { "epoch": 20.36, "learning_rate": 1.2868774769281935e-06, "loss": 0.7368, "step": 244940 }, { "epoch": 20.36, "learning_rate": 1.2867666214006596e-06, "loss": 0.6993, "step": 244950 }, { "epoch": 20.36, "learning_rate": 1.2866557658731258e-06, "loss": 0.6983, "step": 244960 }, { "epoch": 20.36, "learning_rate": 1.2865449103455921e-06, "loss": 0.7942, "step": 244970 }, { "epoch": 20.36, "learning_rate": 1.2864340548180584e-06, "loss": 0.7535, "step": 244980 }, { "epoch": 20.36, "learning_rate": 1.2863231992905245e-06, "loss": 0.7555, "step": 244990 }, { "epoch": 20.36, "learning_rate": 1.2862123437629908e-06, "loss": 0.7796, "step": 245000 }, { "epoch": 20.36, "learning_rate": 1.2861014882354571e-06, "loss": 0.7036, "step": 245010 }, { "epoch": 20.37, "learning_rate": 1.2859906327079232e-06, "loss": 0.6992, "step": 245020 }, { "epoch": 20.37, "learning_rate": 1.2858797771803895e-06, "loss": 0.8001, "step": 245030 }, { "epoch": 20.37, "learning_rate": 1.2857689216528558e-06, "loss": 0.7624, "step": 245040 }, { "epoch": 20.37, "learning_rate": 1.285658066125322e-06, "loss": 0.7796, "step": 245050 }, { "epoch": 20.37, "learning_rate": 1.2855472105977884e-06, "loss": 0.7705, "step": 245060 }, { "epoch": 20.37, "learning_rate": 1.2854363550702547e-06, "loss": 0.7244, "step": 245070 }, { "epoch": 20.37, "learning_rate": 1.285325499542721e-06, "loss": 0.8197, "step": 245080 }, { "epoch": 20.37, "learning_rate": 1.2852146440151873e-06, "loss": 0.7813, "step": 245090 }, { "epoch": 20.37, "learning_rate": 1.2851037884876533e-06, "loss": 0.7896, "step": 245100 }, { "epoch": 20.37, "learning_rate": 1.2849929329601196e-06, "loss": 0.7433, "step": 245110 }, { "epoch": 20.37, "learning_rate": 1.284882077432586e-06, "loss": 0.8027, "step": 245120 }, { "epoch": 20.37, "learning_rate": 1.2847712219050522e-06, "loss": 0.781, "step": 245130 }, { "epoch": 20.38, "learning_rate": 1.2846603663775183e-06, "loss": 0.7288, "step": 245140 }, { "epoch": 20.38, "learning_rate": 1.2845495108499846e-06, "loss": 0.7846, "step": 245150 }, { "epoch": 20.38, "learning_rate": 1.284438655322451e-06, "loss": 0.7692, "step": 245160 }, { "epoch": 20.38, "learning_rate": 1.2843277997949172e-06, "loss": 0.762, "step": 245170 }, { "epoch": 20.38, "learning_rate": 1.2842169442673835e-06, "loss": 0.8191, "step": 245180 }, { "epoch": 20.38, "learning_rate": 1.2841060887398498e-06, "loss": 0.7904, "step": 245190 }, { "epoch": 20.38, "learning_rate": 1.283995233212316e-06, "loss": 0.743, "step": 245200 }, { "epoch": 20.38, "learning_rate": 1.2838843776847824e-06, "loss": 0.7786, "step": 245210 }, { "epoch": 20.38, "learning_rate": 1.2837735221572485e-06, "loss": 0.781, "step": 245220 }, { "epoch": 20.38, "learning_rate": 1.2836626666297148e-06, "loss": 0.7451, "step": 245230 }, { "epoch": 20.38, "learning_rate": 1.283551811102181e-06, "loss": 0.7744, "step": 245240 }, { "epoch": 20.38, "learning_rate": 1.2834409555746474e-06, "loss": 0.7684, "step": 245250 }, { "epoch": 20.39, "learning_rate": 1.2833301000471134e-06, "loss": 0.7665, "step": 245260 }, { "epoch": 20.39, "learning_rate": 1.2832192445195797e-06, "loss": 0.7662, "step": 245270 }, { "epoch": 20.39, "learning_rate": 1.283108388992046e-06, "loss": 0.7982, "step": 245280 }, { "epoch": 20.39, "learning_rate": 1.2829975334645123e-06, "loss": 0.7386, "step": 245290 }, { "epoch": 20.39, "learning_rate": 1.2828866779369784e-06, "loss": 0.8076, "step": 245300 }, { "epoch": 20.39, "learning_rate": 1.282775822409445e-06, "loss": 0.7704, "step": 245310 }, { "epoch": 20.39, "learning_rate": 1.2826649668819112e-06, "loss": 0.6856, "step": 245320 }, { "epoch": 20.39, "learning_rate": 1.2825541113543775e-06, "loss": 0.8223, "step": 245330 }, { "epoch": 20.39, "learning_rate": 1.2824432558268436e-06, "loss": 0.7538, "step": 245340 }, { "epoch": 20.39, "learning_rate": 1.2823324002993099e-06, "loss": 0.7473, "step": 245350 }, { "epoch": 20.39, "learning_rate": 1.2822215447717762e-06, "loss": 0.6925, "step": 245360 }, { "epoch": 20.39, "learning_rate": 1.2821106892442425e-06, "loss": 0.7173, "step": 245370 }, { "epoch": 20.4, "learning_rate": 1.2819998337167086e-06, "loss": 0.7511, "step": 245380 }, { "epoch": 20.4, "learning_rate": 1.2818889781891749e-06, "loss": 0.7894, "step": 245390 }, { "epoch": 20.4, "learning_rate": 1.2817781226616411e-06, "loss": 0.7785, "step": 245400 }, { "epoch": 20.4, "learning_rate": 1.2816672671341072e-06, "loss": 0.7576, "step": 245410 }, { "epoch": 20.4, "learning_rate": 1.2815564116065735e-06, "loss": 0.7806, "step": 245420 }, { "epoch": 20.4, "learning_rate": 1.28144555607904e-06, "loss": 0.8463, "step": 245430 }, { "epoch": 20.4, "learning_rate": 1.2813347005515063e-06, "loss": 0.768, "step": 245440 }, { "epoch": 20.4, "learning_rate": 1.2812238450239724e-06, "loss": 0.7567, "step": 245450 }, { "epoch": 20.4, "learning_rate": 1.2811129894964387e-06, "loss": 0.7096, "step": 245460 }, { "epoch": 20.4, "learning_rate": 1.281002133968905e-06, "loss": 0.8031, "step": 245470 }, { "epoch": 20.4, "learning_rate": 1.2808912784413713e-06, "loss": 0.7728, "step": 245480 }, { "epoch": 20.4, "learning_rate": 1.2807804229138374e-06, "loss": 0.7373, "step": 245490 }, { "epoch": 20.41, "learning_rate": 1.2806695673863037e-06, "loss": 0.7049, "step": 245500 }, { "epoch": 20.41, "learning_rate": 1.28055871185877e-06, "loss": 0.7537, "step": 245510 }, { "epoch": 20.41, "learning_rate": 1.2804478563312363e-06, "loss": 0.7589, "step": 245520 }, { "epoch": 20.41, "learning_rate": 1.2803370008037024e-06, "loss": 0.7995, "step": 245530 }, { "epoch": 20.41, "learning_rate": 1.2802261452761686e-06, "loss": 0.7908, "step": 245540 }, { "epoch": 20.41, "learning_rate": 1.2801152897486352e-06, "loss": 0.7517, "step": 245550 }, { "epoch": 20.41, "learning_rate": 1.2800044342211015e-06, "loss": 0.7127, "step": 245560 }, { "epoch": 20.41, "learning_rate": 1.2798935786935675e-06, "loss": 0.6602, "step": 245570 }, { "epoch": 20.41, "learning_rate": 1.2797827231660338e-06, "loss": 0.8432, "step": 245580 }, { "epoch": 20.41, "learning_rate": 1.2796718676385001e-06, "loss": 0.6713, "step": 245590 }, { "epoch": 20.41, "learning_rate": 1.2795610121109664e-06, "loss": 0.7406, "step": 245600 }, { "epoch": 20.41, "learning_rate": 1.2794501565834325e-06, "loss": 0.8052, "step": 245610 }, { "epoch": 20.42, "learning_rate": 1.2793393010558988e-06, "loss": 0.7693, "step": 245620 }, { "epoch": 20.42, "learning_rate": 1.279228445528365e-06, "loss": 0.8047, "step": 245630 }, { "epoch": 20.42, "learning_rate": 1.2791175900008314e-06, "loss": 0.7423, "step": 245640 }, { "epoch": 20.42, "learning_rate": 1.2790067344732975e-06, "loss": 0.7673, "step": 245650 }, { "epoch": 20.42, "learning_rate": 1.2788958789457638e-06, "loss": 0.7899, "step": 245660 }, { "epoch": 20.42, "learning_rate": 1.27878502341823e-06, "loss": 0.7924, "step": 245670 }, { "epoch": 20.42, "learning_rate": 1.2786741678906966e-06, "loss": 0.7723, "step": 245680 }, { "epoch": 20.42, "learning_rate": 1.2785633123631627e-06, "loss": 0.6979, "step": 245690 }, { "epoch": 20.42, "learning_rate": 1.278452456835629e-06, "loss": 0.7685, "step": 245700 }, { "epoch": 20.42, "learning_rate": 1.2783416013080952e-06, "loss": 0.7153, "step": 245710 }, { "epoch": 20.42, "learning_rate": 1.2782307457805615e-06, "loss": 0.7402, "step": 245720 }, { "epoch": 20.42, "learning_rate": 1.2781198902530276e-06, "loss": 0.7534, "step": 245730 }, { "epoch": 20.43, "learning_rate": 1.278009034725494e-06, "loss": 0.708, "step": 245740 }, { "epoch": 20.43, "learning_rate": 1.2778981791979602e-06, "loss": 0.7266, "step": 245750 }, { "epoch": 20.43, "learning_rate": 1.2777873236704265e-06, "loss": 0.7226, "step": 245760 }, { "epoch": 20.43, "learning_rate": 1.2776764681428926e-06, "loss": 0.7945, "step": 245770 }, { "epoch": 20.43, "learning_rate": 1.2775656126153589e-06, "loss": 0.7692, "step": 245780 }, { "epoch": 20.43, "learning_rate": 1.2774547570878252e-06, "loss": 0.7686, "step": 245790 }, { "epoch": 20.43, "learning_rate": 1.2773439015602917e-06, "loss": 0.7646, "step": 245800 }, { "epoch": 20.43, "learning_rate": 1.2772330460327578e-06, "loss": 0.7844, "step": 245810 }, { "epoch": 20.43, "learning_rate": 1.277122190505224e-06, "loss": 0.7284, "step": 245820 }, { "epoch": 20.43, "learning_rate": 1.2770113349776904e-06, "loss": 0.7598, "step": 245830 }, { "epoch": 20.43, "learning_rate": 1.2769004794501565e-06, "loss": 0.7186, "step": 245840 }, { "epoch": 20.43, "learning_rate": 1.2767896239226227e-06, "loss": 0.7665, "step": 245850 }, { "epoch": 20.44, "learning_rate": 1.276678768395089e-06, "loss": 0.7198, "step": 245860 }, { "epoch": 20.44, "learning_rate": 1.2765679128675553e-06, "loss": 0.7738, "step": 245870 }, { "epoch": 20.44, "learning_rate": 1.2764570573400214e-06, "loss": 0.7822, "step": 245880 }, { "epoch": 20.44, "learning_rate": 1.2763462018124877e-06, "loss": 0.8014, "step": 245890 }, { "epoch": 20.44, "learning_rate": 1.276235346284954e-06, "loss": 0.7273, "step": 245900 }, { "epoch": 20.44, "learning_rate": 1.2761244907574203e-06, "loss": 0.6897, "step": 245910 }, { "epoch": 20.44, "learning_rate": 1.2760136352298866e-06, "loss": 0.7478, "step": 245920 }, { "epoch": 20.44, "learning_rate": 1.275902779702353e-06, "loss": 0.7709, "step": 245930 }, { "epoch": 20.44, "learning_rate": 1.2757919241748192e-06, "loss": 0.7424, "step": 245940 }, { "epoch": 20.44, "learning_rate": 1.2756810686472855e-06, "loss": 0.7618, "step": 245950 }, { "epoch": 20.44, "learning_rate": 1.2755702131197516e-06, "loss": 0.7842, "step": 245960 }, { "epoch": 20.44, "learning_rate": 1.2754593575922179e-06, "loss": 0.766, "step": 245970 }, { "epoch": 20.45, "learning_rate": 1.2753485020646842e-06, "loss": 0.7755, "step": 245980 }, { "epoch": 20.45, "learning_rate": 1.2752376465371505e-06, "loss": 0.7751, "step": 245990 }, { "epoch": 20.45, "learning_rate": 1.2751267910096165e-06, "loss": 0.7128, "step": 246000 }, { "epoch": 20.45, "learning_rate": 1.2750159354820828e-06, "loss": 0.7607, "step": 246010 }, { "epoch": 20.45, "learning_rate": 1.2749050799545491e-06, "loss": 0.6885, "step": 246020 }, { "epoch": 20.45, "learning_rate": 1.2747942244270154e-06, "loss": 0.7674, "step": 246030 }, { "epoch": 20.45, "learning_rate": 1.2746833688994817e-06, "loss": 0.722, "step": 246040 }, { "epoch": 20.45, "learning_rate": 1.274572513371948e-06, "loss": 0.7422, "step": 246050 }, { "epoch": 20.45, "learning_rate": 1.2744616578444143e-06, "loss": 0.7804, "step": 246060 }, { "epoch": 20.45, "learning_rate": 1.2743618878696339e-06, "loss": 0.7678, "step": 246070 }, { "epoch": 20.45, "learning_rate": 1.2742510323421001e-06, "loss": 0.8383, "step": 246080 }, { "epoch": 20.45, "learning_rate": 1.2741401768145662e-06, "loss": 0.7643, "step": 246090 }, { "epoch": 20.46, "learning_rate": 1.2740293212870325e-06, "loss": 0.7255, "step": 246100 }, { "epoch": 20.46, "learning_rate": 1.2739184657594988e-06, "loss": 0.7084, "step": 246110 }, { "epoch": 20.46, "learning_rate": 1.2738076102319651e-06, "loss": 0.6995, "step": 246120 }, { "epoch": 20.46, "learning_rate": 1.2736967547044314e-06, "loss": 0.7993, "step": 246130 }, { "epoch": 20.46, "learning_rate": 1.2735858991768977e-06, "loss": 0.7314, "step": 246140 }, { "epoch": 20.46, "learning_rate": 1.273475043649364e-06, "loss": 0.7593, "step": 246150 }, { "epoch": 20.46, "learning_rate": 1.2733641881218303e-06, "loss": 0.7629, "step": 246160 }, { "epoch": 20.46, "learning_rate": 1.2732533325942964e-06, "loss": 0.7911, "step": 246170 }, { "epoch": 20.46, "learning_rate": 1.2731424770667627e-06, "loss": 0.7987, "step": 246180 }, { "epoch": 20.46, "learning_rate": 1.273031621539229e-06, "loss": 0.7161, "step": 246190 }, { "epoch": 20.46, "learning_rate": 1.2729207660116953e-06, "loss": 0.75, "step": 246200 }, { "epoch": 20.46, "learning_rate": 1.2728099104841614e-06, "loss": 0.7342, "step": 246210 }, { "epoch": 20.47, "learning_rate": 1.2726990549566276e-06, "loss": 0.7104, "step": 246220 }, { "epoch": 20.47, "learning_rate": 1.272588199429094e-06, "loss": 0.8368, "step": 246230 }, { "epoch": 20.47, "learning_rate": 1.2724773439015602e-06, "loss": 0.8123, "step": 246240 }, { "epoch": 20.47, "learning_rate": 1.2723664883740265e-06, "loss": 0.739, "step": 246250 }, { "epoch": 20.47, "learning_rate": 1.2722556328464928e-06, "loss": 0.7443, "step": 246260 }, { "epoch": 20.47, "learning_rate": 1.2721447773189591e-06, "loss": 0.7612, "step": 246270 }, { "epoch": 20.47, "learning_rate": 1.2720339217914254e-06, "loss": 0.7521, "step": 246280 }, { "epoch": 20.47, "learning_rate": 1.2719230662638915e-06, "loss": 0.7534, "step": 246290 }, { "epoch": 20.47, "learning_rate": 1.2718122107363578e-06, "loss": 0.7172, "step": 246300 }, { "epoch": 20.47, "learning_rate": 1.271701355208824e-06, "loss": 0.7661, "step": 246310 }, { "epoch": 20.47, "learning_rate": 1.2715904996812904e-06, "loss": 0.7448, "step": 246320 }, { "epoch": 20.47, "learning_rate": 1.2714796441537565e-06, "loss": 0.7603, "step": 246330 }, { "epoch": 20.48, "learning_rate": 1.2713687886262228e-06, "loss": 0.7504, "step": 246340 }, { "epoch": 20.48, "learning_rate": 1.271257933098689e-06, "loss": 0.7521, "step": 246350 }, { "epoch": 20.48, "learning_rate": 1.2711470775711551e-06, "loss": 0.7475, "step": 246360 }, { "epoch": 20.48, "learning_rate": 1.2710362220436214e-06, "loss": 0.7187, "step": 246370 }, { "epoch": 20.48, "learning_rate": 1.270925366516088e-06, "loss": 0.8342, "step": 246380 }, { "epoch": 20.48, "learning_rate": 1.2708145109885542e-06, "loss": 0.7529, "step": 246390 }, { "epoch": 20.48, "learning_rate": 1.2707036554610203e-06, "loss": 0.6997, "step": 246400 }, { "epoch": 20.48, "learning_rate": 1.2705927999334866e-06, "loss": 0.8067, "step": 246410 }, { "epoch": 20.48, "learning_rate": 1.270481944405953e-06, "loss": 0.7506, "step": 246420 }, { "epoch": 20.48, "learning_rate": 1.2703710888784192e-06, "loss": 0.7332, "step": 246430 }, { "epoch": 20.48, "learning_rate": 1.2702602333508853e-06, "loss": 0.7159, "step": 246440 }, { "epoch": 20.48, "learning_rate": 1.2701493778233516e-06, "loss": 0.725, "step": 246450 }, { "epoch": 20.49, "learning_rate": 1.2700385222958179e-06, "loss": 0.7868, "step": 246460 }, { "epoch": 20.49, "learning_rate": 1.2699276667682842e-06, "loss": 0.6873, "step": 246470 }, { "epoch": 20.49, "learning_rate": 1.2698168112407503e-06, "loss": 0.7805, "step": 246480 }, { "epoch": 20.49, "learning_rate": 1.2697059557132166e-06, "loss": 0.744, "step": 246490 }, { "epoch": 20.49, "learning_rate": 1.269595100185683e-06, "loss": 0.7989, "step": 246500 }, { "epoch": 20.49, "learning_rate": 1.2694842446581494e-06, "loss": 0.7269, "step": 246510 }, { "epoch": 20.49, "learning_rate": 1.2693733891306154e-06, "loss": 0.7743, "step": 246520 }, { "epoch": 20.49, "learning_rate": 1.2692625336030817e-06, "loss": 0.776, "step": 246530 }, { "epoch": 20.49, "learning_rate": 1.269151678075548e-06, "loss": 0.6793, "step": 246540 }, { "epoch": 20.49, "learning_rate": 1.2690408225480143e-06, "loss": 0.754, "step": 246550 }, { "epoch": 20.49, "learning_rate": 1.2689299670204804e-06, "loss": 0.7375, "step": 246560 }, { "epoch": 20.49, "learning_rate": 1.2688191114929467e-06, "loss": 0.7283, "step": 246570 }, { "epoch": 20.5, "learning_rate": 1.268708255965413e-06, "loss": 0.8463, "step": 246580 }, { "epoch": 20.5, "learning_rate": 1.2686084859906328e-06, "loss": 0.7119, "step": 246590 }, { "epoch": 20.5, "learning_rate": 1.268497630463099e-06, "loss": 0.7275, "step": 246600 }, { "epoch": 20.5, "learning_rate": 1.2683867749355651e-06, "loss": 0.7485, "step": 246610 }, { "epoch": 20.5, "learning_rate": 1.2682759194080314e-06, "loss": 0.692, "step": 246620 }, { "epoch": 20.5, "learning_rate": 1.2681650638804977e-06, "loss": 0.8161, "step": 246630 }, { "epoch": 20.5, "learning_rate": 1.268054208352964e-06, "loss": 0.7907, "step": 246640 }, { "epoch": 20.5, "learning_rate": 1.2679433528254301e-06, "loss": 0.7233, "step": 246650 }, { "epoch": 20.5, "learning_rate": 1.2678324972978964e-06, "loss": 0.7487, "step": 246660 }, { "epoch": 20.5, "learning_rate": 1.2677216417703627e-06, "loss": 0.7363, "step": 246670 }, { "epoch": 20.5, "learning_rate": 1.267610786242829e-06, "loss": 0.8081, "step": 246680 }, { "epoch": 20.5, "learning_rate": 1.267499930715295e-06, "loss": 0.8025, "step": 246690 }, { "epoch": 20.51, "learning_rate": 1.2673890751877614e-06, "loss": 0.7261, "step": 246700 }, { "epoch": 20.51, "learning_rate": 1.2672782196602279e-06, "loss": 0.8002, "step": 246710 }, { "epoch": 20.51, "learning_rate": 1.2671673641326942e-06, "loss": 0.7379, "step": 246720 }, { "epoch": 20.51, "learning_rate": 1.2670565086051603e-06, "loss": 0.8226, "step": 246730 }, { "epoch": 20.51, "learning_rate": 1.2669456530776266e-06, "loss": 0.7873, "step": 246740 }, { "epoch": 20.51, "learning_rate": 1.2668347975500928e-06, "loss": 0.7123, "step": 246750 }, { "epoch": 20.51, "learning_rate": 1.2667239420225591e-06, "loss": 0.6837, "step": 246760 }, { "epoch": 20.51, "learning_rate": 1.2666130864950252e-06, "loss": 0.7579, "step": 246770 }, { "epoch": 20.51, "learning_rate": 1.2665022309674915e-06, "loss": 0.8272, "step": 246780 }, { "epoch": 20.51, "learning_rate": 1.2663913754399578e-06, "loss": 0.7936, "step": 246790 }, { "epoch": 20.51, "learning_rate": 1.2662805199124241e-06, "loss": 0.749, "step": 246800 }, { "epoch": 20.51, "learning_rate": 1.2661696643848902e-06, "loss": 0.768, "step": 246810 }, { "epoch": 20.52, "learning_rate": 1.2660588088573565e-06, "loss": 0.7217, "step": 246820 }, { "epoch": 20.52, "learning_rate": 1.265947953329823e-06, "loss": 0.7828, "step": 246830 }, { "epoch": 20.52, "learning_rate": 1.2658370978022893e-06, "loss": 0.7137, "step": 246840 }, { "epoch": 20.52, "learning_rate": 1.2657262422747554e-06, "loss": 0.8035, "step": 246850 }, { "epoch": 20.52, "learning_rate": 1.2656153867472217e-06, "loss": 0.7722, "step": 246860 }, { "epoch": 20.52, "learning_rate": 1.265504531219688e-06, "loss": 0.7704, "step": 246870 }, { "epoch": 20.52, "learning_rate": 1.2653936756921543e-06, "loss": 0.7427, "step": 246880 }, { "epoch": 20.52, "learning_rate": 1.2652828201646203e-06, "loss": 0.7824, "step": 246890 }, { "epoch": 20.52, "learning_rate": 1.2651719646370866e-06, "loss": 0.7676, "step": 246900 }, { "epoch": 20.52, "learning_rate": 1.265061109109553e-06, "loss": 0.7539, "step": 246910 }, { "epoch": 20.52, "learning_rate": 1.264950253582019e-06, "loss": 0.7471, "step": 246920 }, { "epoch": 20.52, "learning_rate": 1.2648393980544853e-06, "loss": 0.7876, "step": 246930 }, { "epoch": 20.53, "learning_rate": 1.2647285425269516e-06, "loss": 0.6673, "step": 246940 }, { "epoch": 20.53, "learning_rate": 1.264617686999418e-06, "loss": 0.7416, "step": 246950 }, { "epoch": 20.53, "learning_rate": 1.2645068314718842e-06, "loss": 0.7127, "step": 246960 }, { "epoch": 20.53, "learning_rate": 1.2643959759443505e-06, "loss": 0.7096, "step": 246970 }, { "epoch": 20.53, "learning_rate": 1.2642851204168168e-06, "loss": 0.8204, "step": 246980 }, { "epoch": 20.53, "learning_rate": 1.264174264889283e-06, "loss": 0.8273, "step": 246990 }, { "epoch": 20.53, "learning_rate": 1.2640634093617492e-06, "loss": 0.7348, "step": 247000 }, { "epoch": 20.53, "learning_rate": 1.2639525538342155e-06, "loss": 0.7531, "step": 247010 }, { "epoch": 20.53, "learning_rate": 1.2638416983066818e-06, "loss": 0.7067, "step": 247020 }, { "epoch": 20.53, "learning_rate": 1.263730842779148e-06, "loss": 0.7846, "step": 247030 }, { "epoch": 20.53, "learning_rate": 1.2636199872516141e-06, "loss": 0.7253, "step": 247040 }, { "epoch": 20.53, "learning_rate": 1.2635091317240804e-06, "loss": 0.7639, "step": 247050 }, { "epoch": 20.54, "learning_rate": 1.2633982761965467e-06, "loss": 0.7602, "step": 247060 }, { "epoch": 20.54, "learning_rate": 1.263287420669013e-06, "loss": 0.7672, "step": 247070 }, { "epoch": 20.54, "learning_rate": 1.2631765651414793e-06, "loss": 0.7172, "step": 247080 }, { "epoch": 20.54, "learning_rate": 1.2630657096139456e-06, "loss": 0.7656, "step": 247090 }, { "epoch": 20.54, "learning_rate": 1.262954854086412e-06, "loss": 0.7722, "step": 247100 }, { "epoch": 20.54, "learning_rate": 1.2628439985588782e-06, "loss": 0.7702, "step": 247110 }, { "epoch": 20.54, "learning_rate": 1.2627331430313443e-06, "loss": 0.6912, "step": 247120 }, { "epoch": 20.54, "learning_rate": 1.2626222875038106e-06, "loss": 0.8318, "step": 247130 }, { "epoch": 20.54, "learning_rate": 1.2625114319762769e-06, "loss": 0.7746, "step": 247140 }, { "epoch": 20.54, "learning_rate": 1.2624005764487432e-06, "loss": 0.7663, "step": 247150 }, { "epoch": 20.54, "learning_rate": 1.2622897209212093e-06, "loss": 0.7977, "step": 247160 }, { "epoch": 20.54, "learning_rate": 1.2621788653936756e-06, "loss": 0.7373, "step": 247170 }, { "epoch": 20.55, "learning_rate": 1.2620680098661419e-06, "loss": 0.809, "step": 247180 }, { "epoch": 20.55, "learning_rate": 1.2619571543386081e-06, "loss": 0.7573, "step": 247190 }, { "epoch": 20.55, "learning_rate": 1.2618462988110744e-06, "loss": 0.7753, "step": 247200 }, { "epoch": 20.55, "learning_rate": 1.2617354432835407e-06, "loss": 0.7497, "step": 247210 }, { "epoch": 20.55, "learning_rate": 1.261624587756007e-06, "loss": 0.7646, "step": 247220 }, { "epoch": 20.55, "learning_rate": 1.2615137322284733e-06, "loss": 0.8586, "step": 247230 }, { "epoch": 20.55, "learning_rate": 1.2614028767009394e-06, "loss": 0.7229, "step": 247240 }, { "epoch": 20.55, "learning_rate": 1.2612920211734057e-06, "loss": 0.7718, "step": 247250 }, { "epoch": 20.55, "learning_rate": 1.261181165645872e-06, "loss": 0.7616, "step": 247260 }, { "epoch": 20.55, "learning_rate": 1.2610703101183383e-06, "loss": 0.806, "step": 247270 }, { "epoch": 20.55, "learning_rate": 1.2609594545908044e-06, "loss": 0.778, "step": 247280 }, { "epoch": 20.55, "learning_rate": 1.2608485990632707e-06, "loss": 0.7199, "step": 247290 }, { "epoch": 20.56, "learning_rate": 1.260737743535737e-06, "loss": 0.7575, "step": 247300 }, { "epoch": 20.56, "learning_rate": 1.260626888008203e-06, "loss": 0.772, "step": 247310 }, { "epoch": 20.56, "learning_rate": 1.2605160324806694e-06, "loss": 0.7549, "step": 247320 }, { "epoch": 20.56, "learning_rate": 1.2604051769531359e-06, "loss": 0.7764, "step": 247330 }, { "epoch": 20.56, "learning_rate": 1.2602943214256022e-06, "loss": 0.6836, "step": 247340 }, { "epoch": 20.56, "learning_rate": 1.2601834658980682e-06, "loss": 0.7461, "step": 247350 }, { "epoch": 20.56, "learning_rate": 1.2600726103705345e-06, "loss": 0.7565, "step": 247360 }, { "epoch": 20.56, "learning_rate": 1.2599617548430008e-06, "loss": 0.7515, "step": 247370 }, { "epoch": 20.56, "learning_rate": 1.2598508993154671e-06, "loss": 0.7975, "step": 247380 }, { "epoch": 20.56, "learning_rate": 1.2597400437879332e-06, "loss": 0.7363, "step": 247390 }, { "epoch": 20.56, "learning_rate": 1.2596291882603995e-06, "loss": 0.7399, "step": 247400 }, { "epoch": 20.56, "learning_rate": 1.2595183327328658e-06, "loss": 0.7384, "step": 247410 }, { "epoch": 20.57, "learning_rate": 1.259407477205332e-06, "loss": 0.7368, "step": 247420 }, { "epoch": 20.57, "learning_rate": 1.2592966216777982e-06, "loss": 0.773, "step": 247430 }, { "epoch": 20.57, "learning_rate": 1.2591857661502645e-06, "loss": 0.7068, "step": 247440 }, { "epoch": 20.57, "learning_rate": 1.259074910622731e-06, "loss": 0.7624, "step": 247450 }, { "epoch": 20.57, "learning_rate": 1.2589640550951973e-06, "loss": 0.6957, "step": 247460 }, { "epoch": 20.57, "learning_rate": 1.2588531995676634e-06, "loss": 0.7007, "step": 247470 }, { "epoch": 20.57, "learning_rate": 1.2587423440401297e-06, "loss": 0.8334, "step": 247480 }, { "epoch": 20.57, "learning_rate": 1.258631488512596e-06, "loss": 0.7738, "step": 247490 }, { "epoch": 20.57, "learning_rate": 1.2585206329850622e-06, "loss": 0.7125, "step": 247500 }, { "epoch": 20.57, "learning_rate": 1.2584097774575283e-06, "loss": 0.7765, "step": 247510 }, { "epoch": 20.57, "learning_rate": 1.2582989219299946e-06, "loss": 0.6953, "step": 247520 }, { "epoch": 20.57, "learning_rate": 1.258188066402461e-06, "loss": 0.8395, "step": 247530 }, { "epoch": 20.58, "learning_rate": 1.2580772108749272e-06, "loss": 0.8041, "step": 247540 }, { "epoch": 20.58, "learning_rate": 1.2579663553473933e-06, "loss": 0.7637, "step": 247550 }, { "epoch": 20.58, "learning_rate": 1.2578554998198596e-06, "loss": 0.7176, "step": 247560 }, { "epoch": 20.58, "learning_rate": 1.257744644292326e-06, "loss": 0.7555, "step": 247570 }, { "epoch": 20.58, "learning_rate": 1.2576337887647924e-06, "loss": 0.8109, "step": 247580 }, { "epoch": 20.58, "learning_rate": 1.2575229332372585e-06, "loss": 0.7507, "step": 247590 }, { "epoch": 20.58, "learning_rate": 1.2574120777097248e-06, "loss": 0.7653, "step": 247600 }, { "epoch": 20.58, "learning_rate": 1.257301222182191e-06, "loss": 0.7537, "step": 247610 }, { "epoch": 20.58, "learning_rate": 1.2571903666546574e-06, "loss": 0.7407, "step": 247620 }, { "epoch": 20.58, "learning_rate": 1.2570795111271234e-06, "loss": 0.7637, "step": 247630 }, { "epoch": 20.58, "learning_rate": 1.2569686555995897e-06, "loss": 0.7018, "step": 247640 }, { "epoch": 20.58, "learning_rate": 1.256857800072056e-06, "loss": 0.7649, "step": 247650 }, { "epoch": 20.59, "learning_rate": 1.2567469445445223e-06, "loss": 0.7795, "step": 247660 }, { "epoch": 20.59, "learning_rate": 1.2566360890169884e-06, "loss": 0.6988, "step": 247670 }, { "epoch": 20.59, "learning_rate": 1.2565252334894547e-06, "loss": 0.756, "step": 247680 }, { "epoch": 20.59, "learning_rate": 1.2564143779619212e-06, "loss": 0.7587, "step": 247690 }, { "epoch": 20.59, "learning_rate": 1.2563035224343875e-06, "loss": 0.7954, "step": 247700 }, { "epoch": 20.59, "learning_rate": 1.2561926669068536e-06, "loss": 0.761, "step": 247710 }, { "epoch": 20.59, "learning_rate": 1.25608181137932e-06, "loss": 0.7528, "step": 247720 }, { "epoch": 20.59, "learning_rate": 1.2559709558517862e-06, "loss": 0.8108, "step": 247730 }, { "epoch": 20.59, "learning_rate": 1.2558601003242523e-06, "loss": 0.7622, "step": 247740 }, { "epoch": 20.59, "learning_rate": 1.2557492447967186e-06, "loss": 0.7204, "step": 247750 }, { "epoch": 20.59, "learning_rate": 1.2556383892691849e-06, "loss": 0.7475, "step": 247760 }, { "epoch": 20.59, "learning_rate": 1.2555275337416512e-06, "loss": 0.7947, "step": 247770 }, { "epoch": 20.6, "learning_rate": 1.2554166782141172e-06, "loss": 0.7883, "step": 247780 }, { "epoch": 20.6, "learning_rate": 1.2553058226865835e-06, "loss": 0.7976, "step": 247790 }, { "epoch": 20.6, "learning_rate": 1.2551949671590498e-06, "loss": 0.6786, "step": 247800 }, { "epoch": 20.6, "learning_rate": 1.2550841116315161e-06, "loss": 0.8406, "step": 247810 }, { "epoch": 20.6, "learning_rate": 1.2549732561039824e-06, "loss": 0.7517, "step": 247820 }, { "epoch": 20.6, "learning_rate": 1.2548624005764487e-06, "loss": 0.7717, "step": 247830 }, { "epoch": 20.6, "learning_rate": 1.254751545048915e-06, "loss": 0.8045, "step": 247840 }, { "epoch": 20.6, "learning_rate": 1.2546406895213813e-06, "loss": 0.748, "step": 247850 }, { "epoch": 20.6, "learning_rate": 1.2545298339938474e-06, "loss": 0.6833, "step": 247860 }, { "epoch": 20.6, "learning_rate": 1.2544189784663137e-06, "loss": 0.6713, "step": 247870 }, { "epoch": 20.6, "learning_rate": 1.25430812293878e-06, "loss": 0.785, "step": 247880 }, { "epoch": 20.6, "learning_rate": 1.2541972674112463e-06, "loss": 0.6933, "step": 247890 }, { "epoch": 20.61, "learning_rate": 1.2540864118837124e-06, "loss": 0.7681, "step": 247900 }, { "epoch": 20.61, "learning_rate": 1.2539755563561787e-06, "loss": 0.7399, "step": 247910 }, { "epoch": 20.61, "learning_rate": 1.253864700828645e-06, "loss": 0.6951, "step": 247920 }, { "epoch": 20.61, "learning_rate": 1.2537538453011113e-06, "loss": 0.8066, "step": 247930 }, { "epoch": 20.61, "learning_rate": 1.2536429897735775e-06, "loss": 0.761, "step": 247940 }, { "epoch": 20.61, "learning_rate": 1.2535321342460438e-06, "loss": 0.7878, "step": 247950 }, { "epoch": 20.61, "learning_rate": 1.2534212787185101e-06, "loss": 0.7363, "step": 247960 }, { "epoch": 20.61, "learning_rate": 1.2533104231909764e-06, "loss": 0.7502, "step": 247970 }, { "epoch": 20.61, "learning_rate": 1.2531995676634425e-06, "loss": 0.7898, "step": 247980 }, { "epoch": 20.61, "learning_rate": 1.2530887121359088e-06, "loss": 0.7407, "step": 247990 }, { "epoch": 20.61, "learning_rate": 1.2529778566083751e-06, "loss": 0.7726, "step": 248000 }, { "epoch": 20.61, "learning_rate": 1.2528670010808414e-06, "loss": 0.6946, "step": 248010 }, { "epoch": 20.62, "learning_rate": 1.2527561455533075e-06, "loss": 0.7451, "step": 248020 }, { "epoch": 20.62, "learning_rate": 1.2526452900257738e-06, "loss": 0.785, "step": 248030 }, { "epoch": 20.62, "learning_rate": 1.25253443449824e-06, "loss": 0.7057, "step": 248040 }, { "epoch": 20.62, "learning_rate": 1.2524235789707064e-06, "loss": 0.8308, "step": 248050 }, { "epoch": 20.62, "learning_rate": 1.2523127234431727e-06, "loss": 0.7693, "step": 248060 }, { "epoch": 20.62, "learning_rate": 1.252201867915639e-06, "loss": 0.7547, "step": 248070 }, { "epoch": 20.62, "learning_rate": 1.2520910123881053e-06, "loss": 0.7519, "step": 248080 }, { "epoch": 20.62, "learning_rate": 1.2519801568605716e-06, "loss": 0.7498, "step": 248090 }, { "epoch": 20.62, "learning_rate": 1.2518693013330376e-06, "loss": 0.7058, "step": 248100 }, { "epoch": 20.62, "learning_rate": 1.251758445805504e-06, "loss": 0.7688, "step": 248110 }, { "epoch": 20.62, "learning_rate": 1.2516475902779702e-06, "loss": 0.7224, "step": 248120 }, { "epoch": 20.62, "learning_rate": 1.2515367347504365e-06, "loss": 0.8232, "step": 248130 }, { "epoch": 20.63, "learning_rate": 1.2514258792229026e-06, "loss": 0.7762, "step": 248140 }, { "epoch": 20.63, "learning_rate": 1.251315023695369e-06, "loss": 0.7447, "step": 248150 }, { "epoch": 20.63, "learning_rate": 1.2512041681678352e-06, "loss": 0.7877, "step": 248160 }, { "epoch": 20.63, "learning_rate": 1.2510933126403013e-06, "loss": 0.7746, "step": 248170 }, { "epoch": 20.63, "learning_rate": 1.2509824571127676e-06, "loss": 0.7702, "step": 248180 }, { "epoch": 20.63, "learning_rate": 1.250871601585234e-06, "loss": 0.673, "step": 248190 }, { "epoch": 20.63, "learning_rate": 1.2507607460577004e-06, "loss": 0.8135, "step": 248200 }, { "epoch": 20.63, "learning_rate": 1.2506498905301665e-06, "loss": 0.8076, "step": 248210 }, { "epoch": 20.63, "learning_rate": 1.2505390350026328e-06, "loss": 0.7658, "step": 248220 }, { "epoch": 20.63, "learning_rate": 1.250428179475099e-06, "loss": 0.7781, "step": 248230 }, { "epoch": 20.63, "learning_rate": 1.2503173239475653e-06, "loss": 0.7606, "step": 248240 }, { "epoch": 20.63, "learning_rate": 1.2502064684200314e-06, "loss": 0.7279, "step": 248250 }, { "epoch": 20.64, "learning_rate": 1.2500956128924977e-06, "loss": 0.7628, "step": 248260 }, { "epoch": 20.64, "learning_rate": 1.249984757364964e-06, "loss": 0.7473, "step": 248270 }, { "epoch": 20.64, "learning_rate": 1.2498739018374303e-06, "loss": 0.7892, "step": 248280 }, { "epoch": 20.64, "learning_rate": 1.2497630463098964e-06, "loss": 0.7924, "step": 248290 }, { "epoch": 20.64, "learning_rate": 1.2496521907823627e-06, "loss": 0.757, "step": 248300 }, { "epoch": 20.64, "learning_rate": 1.2495413352548292e-06, "loss": 0.7803, "step": 248310 }, { "epoch": 20.64, "learning_rate": 1.2494304797272955e-06, "loss": 0.7845, "step": 248320 }, { "epoch": 20.64, "learning_rate": 1.2493196241997616e-06, "loss": 0.8221, "step": 248330 }, { "epoch": 20.64, "learning_rate": 1.2492087686722279e-06, "loss": 0.7213, "step": 248340 }, { "epoch": 20.64, "learning_rate": 1.2490979131446942e-06, "loss": 0.6883, "step": 248350 }, { "epoch": 20.64, "learning_rate": 1.2489870576171605e-06, "loss": 0.8013, "step": 248360 }, { "epoch": 20.64, "learning_rate": 1.2488762020896266e-06, "loss": 0.7686, "step": 248370 }, { "epoch": 20.65, "learning_rate": 1.2487653465620928e-06, "loss": 0.8281, "step": 248380 }, { "epoch": 20.65, "learning_rate": 1.2486544910345591e-06, "loss": 0.7727, "step": 248390 }, { "epoch": 20.65, "learning_rate": 1.2485436355070254e-06, "loss": 0.7619, "step": 248400 }, { "epoch": 20.65, "learning_rate": 1.2484327799794915e-06, "loss": 0.7246, "step": 248410 }, { "epoch": 20.65, "learning_rate": 1.2483219244519578e-06, "loss": 0.7126, "step": 248420 }, { "epoch": 20.65, "learning_rate": 1.2482110689244243e-06, "loss": 0.7889, "step": 248430 }, { "epoch": 20.65, "learning_rate": 1.2481002133968906e-06, "loss": 0.7583, "step": 248440 }, { "epoch": 20.65, "learning_rate": 1.2479893578693567e-06, "loss": 0.7276, "step": 248450 }, { "epoch": 20.65, "learning_rate": 1.247878502341823e-06, "loss": 0.7135, "step": 248460 }, { "epoch": 20.65, "learning_rate": 1.2477676468142893e-06, "loss": 0.7815, "step": 248470 }, { "epoch": 20.65, "learning_rate": 1.2476567912867556e-06, "loss": 0.799, "step": 248480 }, { "epoch": 20.65, "learning_rate": 1.2475459357592217e-06, "loss": 0.7585, "step": 248490 }, { "epoch": 20.65, "learning_rate": 1.247435080231688e-06, "loss": 0.713, "step": 248500 }, { "epoch": 20.66, "learning_rate": 1.2473242247041543e-06, "loss": 0.7451, "step": 248510 }, { "epoch": 20.66, "learning_rate": 1.2472133691766206e-06, "loss": 0.7063, "step": 248520 }, { "epoch": 20.66, "learning_rate": 1.2471025136490866e-06, "loss": 0.8031, "step": 248530 }, { "epoch": 20.66, "learning_rate": 1.246991658121553e-06, "loss": 0.8251, "step": 248540 }, { "epoch": 20.66, "learning_rate": 1.2468808025940194e-06, "loss": 0.7336, "step": 248550 }, { "epoch": 20.66, "learning_rate": 1.2467699470664857e-06, "loss": 0.8051, "step": 248560 }, { "epoch": 20.66, "learning_rate": 1.2466590915389518e-06, "loss": 0.7258, "step": 248570 }, { "epoch": 20.66, "learning_rate": 1.2465482360114181e-06, "loss": 0.7464, "step": 248580 }, { "epoch": 20.66, "learning_rate": 1.2464373804838844e-06, "loss": 0.784, "step": 248590 }, { "epoch": 20.66, "learning_rate": 1.2463265249563505e-06, "loss": 0.7486, "step": 248600 }, { "epoch": 20.66, "learning_rate": 1.2462156694288168e-06, "loss": 0.783, "step": 248610 }, { "epoch": 20.66, "learning_rate": 1.246104813901283e-06, "loss": 0.7208, "step": 248620 }, { "epoch": 20.67, "learning_rate": 1.2459939583737494e-06, "loss": 0.8544, "step": 248630 }, { "epoch": 20.67, "learning_rate": 1.2458831028462155e-06, "loss": 0.7376, "step": 248640 }, { "epoch": 20.67, "learning_rate": 1.2457722473186818e-06, "loss": 0.7073, "step": 248650 }, { "epoch": 20.67, "learning_rate": 1.245661391791148e-06, "loss": 0.7325, "step": 248660 }, { "epoch": 20.67, "learning_rate": 1.2455505362636144e-06, "loss": 0.6669, "step": 248670 }, { "epoch": 20.67, "learning_rate": 1.2454396807360806e-06, "loss": 0.7347, "step": 248680 }, { "epoch": 20.67, "learning_rate": 1.245328825208547e-06, "loss": 0.7937, "step": 248690 }, { "epoch": 20.67, "learning_rate": 1.2452179696810132e-06, "loss": 0.7325, "step": 248700 }, { "epoch": 20.67, "learning_rate": 1.2451071141534795e-06, "loss": 0.7945, "step": 248710 }, { "epoch": 20.67, "learning_rate": 1.2449962586259456e-06, "loss": 0.7499, "step": 248720 }, { "epoch": 20.67, "learning_rate": 1.244885403098412e-06, "loss": 0.7856, "step": 248730 }, { "epoch": 20.67, "learning_rate": 1.2447745475708782e-06, "loss": 0.6795, "step": 248740 }, { "epoch": 20.68, "learning_rate": 1.2446636920433445e-06, "loss": 0.7733, "step": 248750 }, { "epoch": 20.68, "learning_rate": 1.2445528365158106e-06, "loss": 0.6909, "step": 248760 }, { "epoch": 20.68, "learning_rate": 1.2444419809882769e-06, "loss": 0.7538, "step": 248770 }, { "epoch": 20.68, "learning_rate": 1.2443311254607432e-06, "loss": 0.7397, "step": 248780 }, { "epoch": 20.68, "learning_rate": 1.2442202699332095e-06, "loss": 0.7282, "step": 248790 }, { "epoch": 20.68, "learning_rate": 1.2441094144056758e-06, "loss": 0.7247, "step": 248800 }, { "epoch": 20.68, "learning_rate": 1.243998558878142e-06, "loss": 0.7391, "step": 248810 }, { "epoch": 20.68, "learning_rate": 1.2438877033506084e-06, "loss": 0.7619, "step": 248820 }, { "epoch": 20.68, "learning_rate": 1.2437768478230747e-06, "loss": 0.8326, "step": 248830 }, { "epoch": 20.68, "learning_rate": 1.2436659922955407e-06, "loss": 0.7929, "step": 248840 }, { "epoch": 20.68, "learning_rate": 1.243555136768007e-06, "loss": 0.7177, "step": 248850 }, { "epoch": 20.68, "learning_rate": 1.2434442812404733e-06, "loss": 0.7292, "step": 248860 }, { "epoch": 20.69, "learning_rate": 1.2433334257129396e-06, "loss": 0.735, "step": 248870 }, { "epoch": 20.69, "learning_rate": 1.2432225701854057e-06, "loss": 0.8047, "step": 248880 }, { "epoch": 20.69, "learning_rate": 1.243111714657872e-06, "loss": 0.7295, "step": 248890 }, { "epoch": 20.69, "learning_rate": 1.2430008591303383e-06, "loss": 0.7066, "step": 248900 }, { "epoch": 20.69, "learning_rate": 1.2428900036028046e-06, "loss": 0.7576, "step": 248910 }, { "epoch": 20.69, "learning_rate": 1.2427791480752709e-06, "loss": 0.7198, "step": 248920 }, { "epoch": 20.69, "learning_rate": 1.2426682925477372e-06, "loss": 0.7902, "step": 248930 }, { "epoch": 20.69, "learning_rate": 1.2425574370202035e-06, "loss": 0.7895, "step": 248940 }, { "epoch": 20.69, "learning_rate": 1.2424465814926698e-06, "loss": 0.7632, "step": 248950 }, { "epoch": 20.69, "learning_rate": 1.2423357259651359e-06, "loss": 0.7104, "step": 248960 }, { "epoch": 20.69, "learning_rate": 1.2422248704376022e-06, "loss": 0.7003, "step": 248970 }, { "epoch": 20.69, "learning_rate": 1.2421140149100684e-06, "loss": 0.7514, "step": 248980 }, { "epoch": 20.7, "learning_rate": 1.2420031593825345e-06, "loss": 0.7738, "step": 248990 }, { "epoch": 20.7, "learning_rate": 1.2418923038550008e-06, "loss": 0.774, "step": 249000 }, { "epoch": 20.7, "learning_rate": 1.2417814483274671e-06, "loss": 0.7797, "step": 249010 }, { "epoch": 20.7, "learning_rate": 1.2416705927999334e-06, "loss": 0.7131, "step": 249020 }, { "epoch": 20.7, "learning_rate": 1.2415597372723995e-06, "loss": 0.8261, "step": 249030 }, { "epoch": 20.7, "learning_rate": 1.2414488817448658e-06, "loss": 0.8003, "step": 249040 }, { "epoch": 20.7, "learning_rate": 1.2413380262173323e-06, "loss": 0.7126, "step": 249050 }, { "epoch": 20.7, "learning_rate": 1.2412271706897986e-06, "loss": 0.726, "step": 249060 }, { "epoch": 20.7, "learning_rate": 1.2411163151622647e-06, "loss": 0.6668, "step": 249070 }, { "epoch": 20.7, "learning_rate": 1.241005459634731e-06, "loss": 0.7798, "step": 249080 }, { "epoch": 20.7, "learning_rate": 1.2408946041071973e-06, "loss": 0.7658, "step": 249090 }, { "epoch": 20.7, "learning_rate": 1.2407837485796636e-06, "loss": 0.7169, "step": 249100 }, { "epoch": 20.71, "learning_rate": 1.2406728930521297e-06, "loss": 0.7709, "step": 249110 }, { "epoch": 20.71, "learning_rate": 1.240562037524596e-06, "loss": 0.7618, "step": 249120 }, { "epoch": 20.71, "learning_rate": 1.2404511819970622e-06, "loss": 0.7626, "step": 249130 }, { "epoch": 20.71, "learning_rate": 1.2403403264695285e-06, "loss": 0.7298, "step": 249140 }, { "epoch": 20.71, "learning_rate": 1.2402294709419946e-06, "loss": 0.7312, "step": 249150 }, { "epoch": 20.71, "learning_rate": 1.240118615414461e-06, "loss": 0.7555, "step": 249160 }, { "epoch": 20.71, "learning_rate": 1.2400077598869274e-06, "loss": 0.7117, "step": 249170 }, { "epoch": 20.71, "learning_rate": 1.2398969043593937e-06, "loss": 0.7974, "step": 249180 }, { "epoch": 20.71, "learning_rate": 1.2397860488318598e-06, "loss": 0.7277, "step": 249190 }, { "epoch": 20.71, "learning_rate": 1.239675193304326e-06, "loss": 0.7791, "step": 249200 }, { "epoch": 20.71, "learning_rate": 1.2395643377767924e-06, "loss": 0.7352, "step": 249210 }, { "epoch": 20.71, "learning_rate": 1.2394534822492587e-06, "loss": 0.69, "step": 249220 }, { "epoch": 20.72, "learning_rate": 1.2393426267217248e-06, "loss": 0.785, "step": 249230 }, { "epoch": 20.72, "learning_rate": 1.239231771194191e-06, "loss": 0.7271, "step": 249240 }, { "epoch": 20.72, "learning_rate": 1.2391209156666574e-06, "loss": 0.7253, "step": 249250 }, { "epoch": 20.72, "learning_rate": 1.2390100601391237e-06, "loss": 0.7852, "step": 249260 }, { "epoch": 20.72, "learning_rate": 1.2388992046115897e-06, "loss": 0.7623, "step": 249270 }, { "epoch": 20.72, "learning_rate": 1.238788349084056e-06, "loss": 0.7729, "step": 249280 }, { "epoch": 20.72, "learning_rate": 1.2386774935565225e-06, "loss": 0.8047, "step": 249290 }, { "epoch": 20.72, "learning_rate": 1.2385666380289888e-06, "loss": 0.6993, "step": 249300 }, { "epoch": 20.72, "learning_rate": 1.238455782501455e-06, "loss": 0.8053, "step": 249310 }, { "epoch": 20.72, "learning_rate": 1.2383449269739212e-06, "loss": 0.7308, "step": 249320 }, { "epoch": 20.72, "learning_rate": 1.2382340714463875e-06, "loss": 0.7763, "step": 249330 }, { "epoch": 20.72, "learning_rate": 1.2381232159188538e-06, "loss": 0.6641, "step": 249340 }, { "epoch": 20.73, "learning_rate": 1.23801236039132e-06, "loss": 0.7684, "step": 249350 }, { "epoch": 20.73, "learning_rate": 1.2379015048637862e-06, "loss": 0.7798, "step": 249360 }, { "epoch": 20.73, "learning_rate": 1.2377906493362525e-06, "loss": 0.7329, "step": 249370 }, { "epoch": 20.73, "learning_rate": 1.2376797938087186e-06, "loss": 0.7756, "step": 249380 }, { "epoch": 20.73, "learning_rate": 1.2375689382811849e-06, "loss": 0.7046, "step": 249390 }, { "epoch": 20.73, "learning_rate": 1.2374580827536512e-06, "loss": 0.7311, "step": 249400 }, { "epoch": 20.73, "learning_rate": 1.2373472272261175e-06, "loss": 0.7857, "step": 249410 }, { "epoch": 20.73, "learning_rate": 1.237236371698584e-06, "loss": 0.7446, "step": 249420 }, { "epoch": 20.73, "learning_rate": 1.23712551617105e-06, "loss": 0.804, "step": 249430 }, { "epoch": 20.73, "learning_rate": 1.2370146606435163e-06, "loss": 0.733, "step": 249440 }, { "epoch": 20.73, "learning_rate": 1.2369038051159826e-06, "loss": 0.7387, "step": 249450 }, { "epoch": 20.73, "learning_rate": 1.2367929495884487e-06, "loss": 0.7382, "step": 249460 }, { "epoch": 20.74, "learning_rate": 1.236682094060915e-06, "loss": 0.7122, "step": 249470 }, { "epoch": 20.74, "learning_rate": 1.2365712385333813e-06, "loss": 0.7311, "step": 249480 }, { "epoch": 20.74, "learning_rate": 1.2364603830058476e-06, "loss": 0.7503, "step": 249490 }, { "epoch": 20.74, "learning_rate": 1.2363495274783137e-06, "loss": 0.7468, "step": 249500 }, { "epoch": 20.74, "learning_rate": 1.23623867195078e-06, "loss": 0.6959, "step": 249510 }, { "epoch": 20.74, "learning_rate": 1.2361278164232463e-06, "loss": 0.6741, "step": 249520 }, { "epoch": 20.74, "learning_rate": 1.2360169608957126e-06, "loss": 0.7895, "step": 249530 }, { "epoch": 20.74, "learning_rate": 1.2359061053681789e-06, "loss": 0.7317, "step": 249540 }, { "epoch": 20.74, "learning_rate": 1.2357952498406452e-06, "loss": 0.7204, "step": 249550 }, { "epoch": 20.74, "learning_rate": 1.2356843943131115e-06, "loss": 0.7886, "step": 249560 }, { "epoch": 20.74, "learning_rate": 1.2355735387855778e-06, "loss": 0.7489, "step": 249570 }, { "epoch": 20.74, "learning_rate": 1.2354626832580438e-06, "loss": 0.7307, "step": 249580 }, { "epoch": 20.75, "learning_rate": 1.2353518277305101e-06, "loss": 0.7385, "step": 249590 }, { "epoch": 20.75, "learning_rate": 1.2352409722029764e-06, "loss": 0.771, "step": 249600 }, { "epoch": 20.75, "learning_rate": 1.2351301166754427e-06, "loss": 0.8051, "step": 249610 }, { "epoch": 20.75, "learning_rate": 1.2350192611479088e-06, "loss": 0.6659, "step": 249620 }, { "epoch": 20.75, "learning_rate": 1.234908405620375e-06, "loss": 0.786, "step": 249630 }, { "epoch": 20.75, "learning_rate": 1.2347975500928414e-06, "loss": 0.7371, "step": 249640 }, { "epoch": 20.75, "learning_rate": 1.2346866945653077e-06, "loss": 0.7095, "step": 249650 }, { "epoch": 20.75, "learning_rate": 1.234575839037774e-06, "loss": 0.746, "step": 249660 }, { "epoch": 20.75, "learning_rate": 1.2344649835102403e-06, "loss": 0.8007, "step": 249670 }, { "epoch": 20.75, "learning_rate": 1.2343541279827066e-06, "loss": 0.7871, "step": 249680 }, { "epoch": 20.75, "learning_rate": 1.2342432724551729e-06, "loss": 0.7743, "step": 249690 }, { "epoch": 20.75, "learning_rate": 1.234132416927639e-06, "loss": 0.749, "step": 249700 }, { "epoch": 20.76, "learning_rate": 1.2340215614001053e-06, "loss": 0.7218, "step": 249710 }, { "epoch": 20.76, "learning_rate": 1.2339107058725716e-06, "loss": 0.747, "step": 249720 }, { "epoch": 20.76, "learning_rate": 1.2337998503450378e-06, "loss": 0.7575, "step": 249730 }, { "epoch": 20.76, "learning_rate": 1.233688994817504e-06, "loss": 0.7789, "step": 249740 }, { "epoch": 20.76, "learning_rate": 1.2335781392899702e-06, "loss": 0.6698, "step": 249750 }, { "epoch": 20.76, "learning_rate": 1.2334672837624365e-06, "loss": 0.7499, "step": 249760 }, { "epoch": 20.76, "learning_rate": 1.2333564282349028e-06, "loss": 0.7846, "step": 249770 }, { "epoch": 20.76, "learning_rate": 1.2332455727073691e-06, "loss": 0.7992, "step": 249780 }, { "epoch": 20.76, "learning_rate": 1.2331347171798354e-06, "loss": 0.7432, "step": 249790 }, { "epoch": 20.76, "learning_rate": 1.2330238616523017e-06, "loss": 0.7394, "step": 249800 }, { "epoch": 20.76, "learning_rate": 1.232913006124768e-06, "loss": 0.7316, "step": 249810 }, { "epoch": 20.76, "learning_rate": 1.232802150597234e-06, "loss": 0.767, "step": 249820 }, { "epoch": 20.77, "learning_rate": 1.2326912950697004e-06, "loss": 0.8521, "step": 249830 }, { "epoch": 20.77, "learning_rate": 1.2325804395421667e-06, "loss": 0.7403, "step": 249840 }, { "epoch": 20.77, "learning_rate": 1.2324695840146328e-06, "loss": 0.7362, "step": 249850 }, { "epoch": 20.77, "learning_rate": 1.232358728487099e-06, "loss": 0.7197, "step": 249860 }, { "epoch": 20.77, "learning_rate": 1.2322478729595653e-06, "loss": 0.7237, "step": 249870 }, { "epoch": 20.77, "learning_rate": 1.2321370174320316e-06, "loss": 0.771, "step": 249880 }, { "epoch": 20.77, "learning_rate": 1.2320261619044977e-06, "loss": 0.8017, "step": 249890 }, { "epoch": 20.77, "learning_rate": 1.231915306376964e-06, "loss": 0.8169, "step": 249900 }, { "epoch": 20.77, "learning_rate": 1.2318044508494305e-06, "loss": 0.7127, "step": 249910 }, { "epoch": 20.77, "learning_rate": 1.2316935953218968e-06, "loss": 0.748, "step": 249920 }, { "epoch": 20.77, "learning_rate": 1.231582739794363e-06, "loss": 0.8191, "step": 249930 }, { "epoch": 20.77, "learning_rate": 1.2314718842668292e-06, "loss": 0.7803, "step": 249940 }, { "epoch": 20.78, "learning_rate": 1.2313610287392955e-06, "loss": 0.8002, "step": 249950 }, { "epoch": 20.78, "learning_rate": 1.2312501732117618e-06, "loss": 0.7141, "step": 249960 }, { "epoch": 20.78, "learning_rate": 1.2311393176842279e-06, "loss": 0.8133, "step": 249970 }, { "epoch": 20.78, "learning_rate": 1.2310284621566942e-06, "loss": 0.7874, "step": 249980 }, { "epoch": 20.78, "learning_rate": 1.2309176066291605e-06, "loss": 0.7294, "step": 249990 }, { "epoch": 20.78, "learning_rate": 1.2308067511016268e-06, "loss": 0.6822, "step": 250000 }, { "epoch": 20.78, "learning_rate": 1.2306958955740928e-06, "loss": 0.7928, "step": 250010 }, { "epoch": 20.78, "learning_rate": 1.2305850400465591e-06, "loss": 0.7927, "step": 250020 }, { "epoch": 20.78, "learning_rate": 1.2304741845190256e-06, "loss": 0.8171, "step": 250030 }, { "epoch": 20.78, "learning_rate": 1.230363328991492e-06, "loss": 0.7051, "step": 250040 }, { "epoch": 20.78, "learning_rate": 1.230252473463958e-06, "loss": 0.7509, "step": 250050 }, { "epoch": 20.78, "learning_rate": 1.2301416179364243e-06, "loss": 0.7345, "step": 250060 }, { "epoch": 20.79, "learning_rate": 1.2300307624088906e-06, "loss": 0.7818, "step": 250070 }, { "epoch": 20.79, "learning_rate": 1.229919906881357e-06, "loss": 0.8511, "step": 250080 }, { "epoch": 20.79, "learning_rate": 1.229809051353823e-06, "loss": 0.6804, "step": 250090 }, { "epoch": 20.79, "learning_rate": 1.2296981958262893e-06, "loss": 0.7742, "step": 250100 }, { "epoch": 20.79, "learning_rate": 1.2295873402987556e-06, "loss": 0.8037, "step": 250110 }, { "epoch": 20.79, "learning_rate": 1.2294764847712219e-06, "loss": 0.7608, "step": 250120 }, { "epoch": 20.79, "learning_rate": 1.229365629243688e-06, "loss": 0.7928, "step": 250130 }, { "epoch": 20.79, "learning_rate": 1.2292547737161543e-06, "loss": 0.7092, "step": 250140 }, { "epoch": 20.79, "learning_rate": 1.2291439181886208e-06, "loss": 0.7209, "step": 250150 }, { "epoch": 20.79, "learning_rate": 1.229033062661087e-06, "loss": 0.7415, "step": 250160 }, { "epoch": 20.79, "learning_rate": 1.2289222071335531e-06, "loss": 0.7776, "step": 250170 }, { "epoch": 20.79, "learning_rate": 1.2288113516060194e-06, "loss": 0.7834, "step": 250180 }, { "epoch": 20.8, "learning_rate": 1.2287004960784857e-06, "loss": 0.776, "step": 250190 }, { "epoch": 20.8, "learning_rate": 1.228589640550952e-06, "loss": 0.7722, "step": 250200 }, { "epoch": 20.8, "learning_rate": 1.2284787850234181e-06, "loss": 0.7196, "step": 250210 }, { "epoch": 20.8, "learning_rate": 1.2283679294958844e-06, "loss": 0.7368, "step": 250220 }, { "epoch": 20.8, "learning_rate": 1.2282570739683507e-06, "loss": 0.765, "step": 250230 }, { "epoch": 20.8, "learning_rate": 1.2281462184408168e-06, "loss": 0.6841, "step": 250240 }, { "epoch": 20.8, "learning_rate": 1.228035362913283e-06, "loss": 0.7287, "step": 250250 }, { "epoch": 20.8, "learning_rate": 1.2279245073857494e-06, "loss": 0.7231, "step": 250260 }, { "epoch": 20.8, "learning_rate": 1.2278136518582157e-06, "loss": 0.7385, "step": 250270 }, { "epoch": 20.8, "learning_rate": 1.227702796330682e-06, "loss": 0.7789, "step": 250280 }, { "epoch": 20.8, "learning_rate": 1.2275919408031483e-06, "loss": 0.7811, "step": 250290 }, { "epoch": 20.8, "learning_rate": 1.2274810852756146e-06, "loss": 0.7655, "step": 250300 }, { "epoch": 20.81, "learning_rate": 1.2273702297480809e-06, "loss": 0.6992, "step": 250310 }, { "epoch": 20.81, "learning_rate": 1.227259374220547e-06, "loss": 0.7067, "step": 250320 }, { "epoch": 20.81, "learning_rate": 1.2271485186930132e-06, "loss": 0.8177, "step": 250330 }, { "epoch": 20.81, "learning_rate": 1.2270376631654795e-06, "loss": 0.7549, "step": 250340 }, { "epoch": 20.81, "learning_rate": 1.2269268076379458e-06, "loss": 0.7399, "step": 250350 }, { "epoch": 20.81, "learning_rate": 1.226815952110412e-06, "loss": 0.7315, "step": 250360 }, { "epoch": 20.81, "learning_rate": 1.2267050965828782e-06, "loss": 0.7219, "step": 250370 }, { "epoch": 20.81, "learning_rate": 1.2265942410553445e-06, "loss": 0.7878, "step": 250380 }, { "epoch": 20.81, "learning_rate": 1.2264833855278108e-06, "loss": 0.7075, "step": 250390 }, { "epoch": 20.81, "learning_rate": 1.226372530000277e-06, "loss": 0.7883, "step": 250400 }, { "epoch": 20.81, "learning_rate": 1.2262616744727434e-06, "loss": 0.7235, "step": 250410 }, { "epoch": 20.81, "learning_rate": 1.2261508189452097e-06, "loss": 0.6818, "step": 250420 }, { "epoch": 20.82, "learning_rate": 1.226039963417676e-06, "loss": 0.8333, "step": 250430 }, { "epoch": 20.82, "learning_rate": 1.225929107890142e-06, "loss": 0.7717, "step": 250440 }, { "epoch": 20.82, "learning_rate": 1.2258182523626084e-06, "loss": 0.6642, "step": 250450 }, { "epoch": 20.82, "learning_rate": 1.2257073968350747e-06, "loss": 0.7506, "step": 250460 }, { "epoch": 20.82, "learning_rate": 1.225596541307541e-06, "loss": 0.7567, "step": 250470 }, { "epoch": 20.82, "learning_rate": 1.225485685780007e-06, "loss": 0.8391, "step": 250480 }, { "epoch": 20.82, "learning_rate": 1.2253748302524733e-06, "loss": 0.784, "step": 250490 }, { "epoch": 20.82, "learning_rate": 1.2252639747249396e-06, "loss": 0.778, "step": 250500 }, { "epoch": 20.82, "learning_rate": 1.225153119197406e-06, "loss": 0.6791, "step": 250510 }, { "epoch": 20.82, "learning_rate": 1.2250422636698722e-06, "loss": 0.7442, "step": 250520 }, { "epoch": 20.82, "learning_rate": 1.2249314081423385e-06, "loss": 0.7928, "step": 250530 }, { "epoch": 20.82, "learning_rate": 1.2248205526148048e-06, "loss": 0.7603, "step": 250540 }, { "epoch": 20.83, "learning_rate": 1.224709697087271e-06, "loss": 0.6893, "step": 250550 }, { "epoch": 20.83, "learning_rate": 1.2245988415597372e-06, "loss": 0.7287, "step": 250560 }, { "epoch": 20.83, "learning_rate": 1.2244879860322035e-06, "loss": 0.7662, "step": 250570 }, { "epoch": 20.83, "learning_rate": 1.2243771305046698e-06, "loss": 0.7841, "step": 250580 }, { "epoch": 20.83, "learning_rate": 1.224266274977136e-06, "loss": 0.7602, "step": 250590 }, { "epoch": 20.83, "learning_rate": 1.2241554194496022e-06, "loss": 0.7906, "step": 250600 }, { "epoch": 20.83, "learning_rate": 1.2240445639220684e-06, "loss": 0.666, "step": 250610 }, { "epoch": 20.83, "learning_rate": 1.2239337083945347e-06, "loss": 0.7395, "step": 250620 }, { "epoch": 20.83, "learning_rate": 1.2238228528670008e-06, "loss": 0.7298, "step": 250630 }, { "epoch": 20.83, "learning_rate": 1.2237119973394673e-06, "loss": 0.7571, "step": 250640 }, { "epoch": 20.83, "learning_rate": 1.2236011418119336e-06, "loss": 0.7754, "step": 250650 }, { "epoch": 20.83, "learning_rate": 1.2234902862844e-06, "loss": 0.7217, "step": 250660 }, { "epoch": 20.84, "learning_rate": 1.2233794307568662e-06, "loss": 0.7927, "step": 250670 }, { "epoch": 20.84, "learning_rate": 1.2232685752293323e-06, "loss": 0.7959, "step": 250680 }, { "epoch": 20.84, "learning_rate": 1.2231577197017986e-06, "loss": 0.7919, "step": 250690 }, { "epoch": 20.84, "learning_rate": 1.223046864174265e-06, "loss": 0.8041, "step": 250700 }, { "epoch": 20.84, "learning_rate": 1.222936008646731e-06, "loss": 0.7259, "step": 250710 }, { "epoch": 20.84, "learning_rate": 1.2228251531191973e-06, "loss": 0.7514, "step": 250720 }, { "epoch": 20.84, "learning_rate": 1.2227142975916636e-06, "loss": 0.7916, "step": 250730 }, { "epoch": 20.84, "learning_rate": 1.2226034420641299e-06, "loss": 0.7576, "step": 250740 }, { "epoch": 20.84, "learning_rate": 1.222492586536596e-06, "loss": 0.6918, "step": 250750 }, { "epoch": 20.84, "learning_rate": 1.2223817310090622e-06, "loss": 0.8366, "step": 250760 }, { "epoch": 20.84, "learning_rate": 1.2222708754815288e-06, "loss": 0.7275, "step": 250770 }, { "epoch": 20.84, "learning_rate": 1.222160019953995e-06, "loss": 0.7996, "step": 250780 }, { "epoch": 20.85, "learning_rate": 1.2220491644264611e-06, "loss": 0.7326, "step": 250790 }, { "epoch": 20.85, "learning_rate": 1.2219383088989274e-06, "loss": 0.7281, "step": 250800 }, { "epoch": 20.85, "learning_rate": 1.2218274533713937e-06, "loss": 0.7569, "step": 250810 }, { "epoch": 20.85, "learning_rate": 1.22171659784386e-06, "loss": 0.7659, "step": 250820 }, { "epoch": 20.85, "learning_rate": 1.221605742316326e-06, "loss": 0.8048, "step": 250830 }, { "epoch": 20.85, "learning_rate": 1.2214948867887924e-06, "loss": 0.8054, "step": 250840 }, { "epoch": 20.85, "learning_rate": 1.2213840312612587e-06, "loss": 0.7278, "step": 250850 }, { "epoch": 20.85, "learning_rate": 1.221273175733725e-06, "loss": 0.7422, "step": 250860 }, { "epoch": 20.85, "learning_rate": 1.221162320206191e-06, "loss": 0.6656, "step": 250870 }, { "epoch": 20.85, "learning_rate": 1.2210514646786574e-06, "loss": 0.8177, "step": 250880 }, { "epoch": 20.85, "learning_rate": 1.2209406091511239e-06, "loss": 0.705, "step": 250890 }, { "epoch": 20.85, "learning_rate": 1.2208297536235902e-06, "loss": 0.7896, "step": 250900 }, { "epoch": 20.86, "learning_rate": 1.2207188980960563e-06, "loss": 0.7565, "step": 250910 }, { "epoch": 20.86, "learning_rate": 1.2206080425685225e-06, "loss": 0.7946, "step": 250920 }, { "epoch": 20.86, "learning_rate": 1.2204971870409888e-06, "loss": 0.7697, "step": 250930 }, { "epoch": 20.86, "learning_rate": 1.2203863315134551e-06, "loss": 0.7542, "step": 250940 }, { "epoch": 20.86, "learning_rate": 1.2202754759859212e-06, "loss": 0.7627, "step": 250950 }, { "epoch": 20.86, "learning_rate": 1.2201646204583875e-06, "loss": 0.825, "step": 250960 }, { "epoch": 20.86, "learning_rate": 1.2200537649308538e-06, "loss": 0.7839, "step": 250970 }, { "epoch": 20.86, "learning_rate": 1.2199429094033201e-06, "loss": 0.7503, "step": 250980 }, { "epoch": 20.86, "learning_rate": 1.2198320538757862e-06, "loss": 0.7769, "step": 250990 }, { "epoch": 20.86, "learning_rate": 1.2197211983482525e-06, "loss": 0.7474, "step": 251000 }, { "epoch": 20.86, "learning_rate": 1.219610342820719e-06, "loss": 0.7554, "step": 251010 }, { "epoch": 20.86, "learning_rate": 1.2194994872931853e-06, "loss": 0.799, "step": 251020 }, { "epoch": 20.87, "learning_rate": 1.2193886317656514e-06, "loss": 0.7754, "step": 251030 }, { "epoch": 20.87, "learning_rate": 1.2192777762381177e-06, "loss": 0.7394, "step": 251040 }, { "epoch": 20.87, "learning_rate": 1.219166920710584e-06, "loss": 0.7605, "step": 251050 }, { "epoch": 20.87, "learning_rate": 1.2190560651830503e-06, "loss": 0.7265, "step": 251060 }, { "epoch": 20.87, "learning_rate": 1.2189452096555163e-06, "loss": 0.7504, "step": 251070 }, { "epoch": 20.87, "learning_rate": 1.2188343541279826e-06, "loss": 0.7732, "step": 251080 }, { "epoch": 20.87, "learning_rate": 1.218723498600449e-06, "loss": 0.7379, "step": 251090 }, { "epoch": 20.87, "learning_rate": 1.218612643072915e-06, "loss": 0.7592, "step": 251100 }, { "epoch": 20.87, "learning_rate": 1.2185017875453813e-06, "loss": 0.7955, "step": 251110 }, { "epoch": 20.87, "learning_rate": 1.2183909320178476e-06, "loss": 0.7256, "step": 251120 }, { "epoch": 20.87, "learning_rate": 1.218280076490314e-06, "loss": 0.7945, "step": 251130 }, { "epoch": 20.87, "learning_rate": 1.2181692209627802e-06, "loss": 0.7235, "step": 251140 }, { "epoch": 20.88, "learning_rate": 1.2180583654352465e-06, "loss": 0.7691, "step": 251150 }, { "epoch": 20.88, "learning_rate": 1.2179475099077128e-06, "loss": 0.7112, "step": 251160 }, { "epoch": 20.88, "learning_rate": 1.217836654380179e-06, "loss": 0.6572, "step": 251170 }, { "epoch": 20.88, "learning_rate": 1.2177257988526452e-06, "loss": 0.7631, "step": 251180 }, { "epoch": 20.88, "learning_rate": 1.2176149433251115e-06, "loss": 0.7424, "step": 251190 }, { "epoch": 20.88, "learning_rate": 1.2175040877975778e-06, "loss": 0.7233, "step": 251200 }, { "epoch": 20.88, "learning_rate": 1.217393232270044e-06, "loss": 0.7127, "step": 251210 }, { "epoch": 20.88, "learning_rate": 1.2172823767425101e-06, "loss": 0.7325, "step": 251220 }, { "epoch": 20.88, "learning_rate": 1.2171715212149764e-06, "loss": 0.842, "step": 251230 }, { "epoch": 20.88, "learning_rate": 1.2170606656874427e-06, "loss": 0.7573, "step": 251240 }, { "epoch": 20.88, "learning_rate": 1.216949810159909e-06, "loss": 0.7567, "step": 251250 }, { "epoch": 20.88, "learning_rate": 1.2168389546323753e-06, "loss": 0.7774, "step": 251260 }, { "epoch": 20.89, "learning_rate": 1.2167280991048416e-06, "loss": 0.7467, "step": 251270 }, { "epoch": 20.89, "learning_rate": 1.216617243577308e-06, "loss": 0.7566, "step": 251280 }, { "epoch": 20.89, "learning_rate": 1.2165063880497742e-06, "loss": 0.7862, "step": 251290 }, { "epoch": 20.89, "learning_rate": 1.2163955325222403e-06, "loss": 0.7641, "step": 251300 }, { "epoch": 20.89, "learning_rate": 1.2162846769947066e-06, "loss": 0.7649, "step": 251310 }, { "epoch": 20.89, "learning_rate": 1.2161738214671729e-06, "loss": 0.6733, "step": 251320 }, { "epoch": 20.89, "learning_rate": 1.2160629659396392e-06, "loss": 0.8002, "step": 251330 }, { "epoch": 20.89, "learning_rate": 1.2159521104121053e-06, "loss": 0.7474, "step": 251340 }, { "epoch": 20.89, "learning_rate": 1.2158412548845716e-06, "loss": 0.7493, "step": 251350 }, { "epoch": 20.89, "learning_rate": 1.2157303993570378e-06, "loss": 0.7223, "step": 251360 }, { "epoch": 20.89, "learning_rate": 1.2156195438295041e-06, "loss": 0.6864, "step": 251370 }, { "epoch": 20.89, "learning_rate": 1.2155086883019704e-06, "loss": 0.8545, "step": 251380 }, { "epoch": 20.9, "learning_rate": 1.2153978327744367e-06, "loss": 0.7439, "step": 251390 }, { "epoch": 20.9, "learning_rate": 1.215286977246903e-06, "loss": 0.7729, "step": 251400 }, { "epoch": 20.9, "learning_rate": 1.2151761217193693e-06, "loss": 0.7639, "step": 251410 }, { "epoch": 20.9, "learning_rate": 1.2150652661918354e-06, "loss": 0.7247, "step": 251420 }, { "epoch": 20.9, "learning_rate": 1.2149544106643017e-06, "loss": 0.7755, "step": 251430 }, { "epoch": 20.9, "learning_rate": 1.214843555136768e-06, "loss": 0.7315, "step": 251440 }, { "epoch": 20.9, "learning_rate": 1.2147326996092343e-06, "loss": 0.7541, "step": 251450 }, { "epoch": 20.9, "learning_rate": 1.2146218440817004e-06, "loss": 0.7995, "step": 251460 }, { "epoch": 20.9, "learning_rate": 1.2145109885541667e-06, "loss": 0.7934, "step": 251470 }, { "epoch": 20.9, "learning_rate": 1.214400133026633e-06, "loss": 0.8327, "step": 251480 }, { "epoch": 20.9, "learning_rate": 1.214289277499099e-06, "loss": 0.7209, "step": 251490 }, { "epoch": 20.9, "learning_rate": 1.2141784219715653e-06, "loss": 0.726, "step": 251500 }, { "epoch": 20.91, "learning_rate": 1.2140675664440319e-06, "loss": 0.7586, "step": 251510 }, { "epoch": 20.91, "learning_rate": 1.2139567109164981e-06, "loss": 0.7525, "step": 251520 }, { "epoch": 20.91, "learning_rate": 1.2138458553889642e-06, "loss": 0.7766, "step": 251530 }, { "epoch": 20.91, "learning_rate": 1.2137349998614305e-06, "loss": 0.7534, "step": 251540 }, { "epoch": 20.91, "learning_rate": 1.2136241443338968e-06, "loss": 0.7711, "step": 251550 }, { "epoch": 20.91, "learning_rate": 1.2135132888063631e-06, "loss": 0.6659, "step": 251560 }, { "epoch": 20.91, "learning_rate": 1.2134024332788292e-06, "loss": 0.7309, "step": 251570 }, { "epoch": 20.91, "learning_rate": 1.2132915777512955e-06, "loss": 0.8359, "step": 251580 }, { "epoch": 20.91, "learning_rate": 1.2131807222237618e-06, "loss": 0.7397, "step": 251590 }, { "epoch": 20.91, "learning_rate": 1.2130809522489815e-06, "loss": 0.7441, "step": 251600 }, { "epoch": 20.91, "learning_rate": 1.2129700967214478e-06, "loss": 0.7356, "step": 251610 }, { "epoch": 20.91, "learning_rate": 1.2128592411939141e-06, "loss": 0.797, "step": 251620 }, { "epoch": 20.92, "learning_rate": 1.2127483856663802e-06, "loss": 0.7651, "step": 251630 }, { "epoch": 20.92, "learning_rate": 1.2126375301388465e-06, "loss": 0.7432, "step": 251640 }, { "epoch": 20.92, "learning_rate": 1.2125266746113128e-06, "loss": 0.791, "step": 251650 }, { "epoch": 20.92, "learning_rate": 1.2124158190837789e-06, "loss": 0.7187, "step": 251660 }, { "epoch": 20.92, "learning_rate": 1.2123049635562452e-06, "loss": 0.724, "step": 251670 }, { "epoch": 20.92, "learning_rate": 1.2121941080287115e-06, "loss": 0.7997, "step": 251680 }, { "epoch": 20.92, "learning_rate": 1.2120832525011778e-06, "loss": 0.7376, "step": 251690 }, { "epoch": 20.92, "learning_rate": 1.2119723969736439e-06, "loss": 0.7401, "step": 251700 }, { "epoch": 20.92, "learning_rate": 1.2118615414461102e-06, "loss": 0.7735, "step": 251710 }, { "epoch": 20.92, "learning_rate": 1.2117506859185767e-06, "loss": 0.7598, "step": 251720 }, { "epoch": 20.92, "learning_rate": 1.211639830391043e-06, "loss": 0.7675, "step": 251730 }, { "epoch": 20.92, "learning_rate": 1.211528974863509e-06, "loss": 0.8124, "step": 251740 }, { "epoch": 20.93, "learning_rate": 1.2114181193359753e-06, "loss": 0.7035, "step": 251750 }, { "epoch": 20.93, "learning_rate": 1.2113072638084416e-06, "loss": 0.7095, "step": 251760 }, { "epoch": 20.93, "learning_rate": 1.211196408280908e-06, "loss": 0.7405, "step": 251770 }, { "epoch": 20.93, "learning_rate": 1.211085552753374e-06, "loss": 0.8228, "step": 251780 }, { "epoch": 20.93, "learning_rate": 1.2109746972258403e-06, "loss": 0.7341, "step": 251790 }, { "epoch": 20.93, "learning_rate": 1.2108638416983066e-06, "loss": 0.7583, "step": 251800 }, { "epoch": 20.93, "learning_rate": 1.210752986170773e-06, "loss": 0.7653, "step": 251810 }, { "epoch": 20.93, "learning_rate": 1.210642130643239e-06, "loss": 0.7994, "step": 251820 }, { "epoch": 20.93, "learning_rate": 1.2105312751157053e-06, "loss": 0.8042, "step": 251830 }, { "epoch": 20.93, "learning_rate": 1.2104204195881718e-06, "loss": 0.7189, "step": 251840 }, { "epoch": 20.93, "learning_rate": 1.210309564060638e-06, "loss": 0.7055, "step": 251850 }, { "epoch": 20.93, "learning_rate": 1.2101987085331042e-06, "loss": 0.7153, "step": 251860 }, { "epoch": 20.94, "learning_rate": 1.2100878530055705e-06, "loss": 0.7415, "step": 251870 }, { "epoch": 20.94, "learning_rate": 1.2099769974780368e-06, "loss": 0.8005, "step": 251880 }, { "epoch": 20.94, "learning_rate": 1.209866141950503e-06, "loss": 0.7258, "step": 251890 }, { "epoch": 20.94, "learning_rate": 1.2097552864229691e-06, "loss": 0.7333, "step": 251900 }, { "epoch": 20.94, "learning_rate": 1.2096444308954354e-06, "loss": 0.7327, "step": 251910 }, { "epoch": 20.94, "learning_rate": 1.2095335753679017e-06, "loss": 0.8057, "step": 251920 }, { "epoch": 20.94, "learning_rate": 1.209422719840368e-06, "loss": 0.7979, "step": 251930 }, { "epoch": 20.94, "learning_rate": 1.209311864312834e-06, "loss": 0.7675, "step": 251940 }, { "epoch": 20.94, "learning_rate": 1.2092010087853004e-06, "loss": 0.7474, "step": 251950 }, { "epoch": 20.94, "learning_rate": 1.209090153257767e-06, "loss": 0.7312, "step": 251960 }, { "epoch": 20.94, "learning_rate": 1.2089792977302332e-06, "loss": 0.7527, "step": 251970 }, { "epoch": 20.94, "learning_rate": 1.2088684422026993e-06, "loss": 0.781, "step": 251980 }, { "epoch": 20.95, "learning_rate": 1.2087575866751656e-06, "loss": 0.7467, "step": 251990 }, { "epoch": 20.95, "learning_rate": 1.2086467311476319e-06, "loss": 0.7446, "step": 252000 }, { "epoch": 20.95, "learning_rate": 1.2085358756200982e-06, "loss": 0.7826, "step": 252010 }, { "epoch": 20.95, "learning_rate": 1.2084250200925643e-06, "loss": 0.7634, "step": 252020 }, { "epoch": 20.95, "learning_rate": 1.2083141645650305e-06, "loss": 0.7426, "step": 252030 }, { "epoch": 20.95, "learning_rate": 1.2082033090374968e-06, "loss": 0.7319, "step": 252040 }, { "epoch": 20.95, "learning_rate": 1.208092453509963e-06, "loss": 0.7541, "step": 252050 }, { "epoch": 20.95, "learning_rate": 1.2079815979824292e-06, "loss": 0.7229, "step": 252060 }, { "epoch": 20.95, "learning_rate": 1.2078707424548955e-06, "loss": 0.7265, "step": 252070 }, { "epoch": 20.95, "learning_rate": 1.207759886927362e-06, "loss": 0.7822, "step": 252080 }, { "epoch": 20.95, "learning_rate": 1.2076490313998281e-06, "loss": 0.7596, "step": 252090 }, { "epoch": 20.95, "learning_rate": 1.2075381758722944e-06, "loss": 0.826, "step": 252100 }, { "epoch": 20.96, "learning_rate": 1.2074273203447607e-06, "loss": 0.7385, "step": 252110 }, { "epoch": 20.96, "learning_rate": 1.207316464817227e-06, "loss": 0.7472, "step": 252120 }, { "epoch": 20.96, "learning_rate": 1.207205609289693e-06, "loss": 0.7891, "step": 252130 }, { "epoch": 20.96, "learning_rate": 1.2070947537621594e-06, "loss": 0.748, "step": 252140 }, { "epoch": 20.96, "learning_rate": 1.2069838982346257e-06, "loss": 0.787, "step": 252150 }, { "epoch": 20.96, "learning_rate": 1.206873042707092e-06, "loss": 0.7953, "step": 252160 }, { "epoch": 20.96, "learning_rate": 1.206762187179558e-06, "loss": 0.7445, "step": 252170 }, { "epoch": 20.96, "learning_rate": 1.2066513316520243e-06, "loss": 0.8144, "step": 252180 }, { "epoch": 20.96, "learning_rate": 1.2065404761244906e-06, "loss": 0.7604, "step": 252190 }, { "epoch": 20.96, "learning_rate": 1.206429620596957e-06, "loss": 0.7638, "step": 252200 }, { "epoch": 20.96, "learning_rate": 1.2063187650694232e-06, "loss": 0.7299, "step": 252210 }, { "epoch": 20.96, "learning_rate": 1.2062079095418895e-06, "loss": 0.8019, "step": 252220 }, { "epoch": 20.97, "learning_rate": 1.2060970540143558e-06, "loss": 0.8158, "step": 252230 }, { "epoch": 20.97, "learning_rate": 1.2059861984868221e-06, "loss": 0.7252, "step": 252240 }, { "epoch": 20.97, "learning_rate": 1.2058753429592882e-06, "loss": 0.7443, "step": 252250 }, { "epoch": 20.97, "learning_rate": 1.2057644874317545e-06, "loss": 0.7334, "step": 252260 }, { "epoch": 20.97, "learning_rate": 1.2056536319042208e-06, "loss": 0.7812, "step": 252270 }, { "epoch": 20.97, "learning_rate": 1.205542776376687e-06, "loss": 0.8325, "step": 252280 }, { "epoch": 20.97, "learning_rate": 1.2054319208491532e-06, "loss": 0.758, "step": 252290 }, { "epoch": 20.97, "learning_rate": 1.2053210653216195e-06, "loss": 0.7433, "step": 252300 }, { "epoch": 20.97, "learning_rate": 1.2052102097940858e-06, "loss": 0.7898, "step": 252310 }, { "epoch": 20.97, "learning_rate": 1.205099354266552e-06, "loss": 0.8075, "step": 252320 }, { "epoch": 20.97, "learning_rate": 1.2049884987390183e-06, "loss": 0.7804, "step": 252330 }, { "epoch": 20.97, "learning_rate": 1.2048776432114846e-06, "loss": 0.7763, "step": 252340 }, { "epoch": 20.97, "learning_rate": 1.204766787683951e-06, "loss": 0.7513, "step": 252350 }, { "epoch": 20.98, "learning_rate": 1.2046559321564172e-06, "loss": 0.77, "step": 252360 }, { "epoch": 20.98, "learning_rate": 1.2045450766288833e-06, "loss": 0.7153, "step": 252370 }, { "epoch": 20.98, "learning_rate": 1.2044342211013496e-06, "loss": 0.7697, "step": 252380 }, { "epoch": 20.98, "learning_rate": 1.204323365573816e-06, "loss": 0.7458, "step": 252390 }, { "epoch": 20.98, "learning_rate": 1.2042125100462822e-06, "loss": 0.7372, "step": 252400 }, { "epoch": 20.98, "learning_rate": 1.2041016545187483e-06, "loss": 0.7035, "step": 252410 }, { "epoch": 20.98, "learning_rate": 1.2039907989912146e-06, "loss": 0.7786, "step": 252420 }, { "epoch": 20.98, "learning_rate": 1.2038799434636809e-06, "loss": 0.7992, "step": 252430 }, { "epoch": 20.98, "learning_rate": 1.203769087936147e-06, "loss": 0.7111, "step": 252440 }, { "epoch": 20.98, "learning_rate": 1.2036582324086135e-06, "loss": 0.7209, "step": 252450 }, { "epoch": 20.98, "learning_rate": 1.2035473768810798e-06, "loss": 0.7511, "step": 252460 }, { "epoch": 20.98, "learning_rate": 1.203436521353546e-06, "loss": 0.8062, "step": 252470 }, { "epoch": 20.99, "learning_rate": 1.2033256658260121e-06, "loss": 0.7643, "step": 252480 }, { "epoch": 20.99, "learning_rate": 1.2032148102984784e-06, "loss": 0.7825, "step": 252490 }, { "epoch": 20.99, "learning_rate": 1.2031039547709447e-06, "loss": 0.7385, "step": 252500 }, { "epoch": 20.99, "learning_rate": 1.202993099243411e-06, "loss": 0.7274, "step": 252510 }, { "epoch": 20.99, "learning_rate": 1.2028822437158771e-06, "loss": 0.7325, "step": 252520 }, { "epoch": 20.99, "learning_rate": 1.2027713881883434e-06, "loss": 0.7961, "step": 252530 }, { "epoch": 20.99, "learning_rate": 1.2026605326608097e-06, "loss": 0.7598, "step": 252540 }, { "epoch": 20.99, "learning_rate": 1.202549677133276e-06, "loss": 0.718, "step": 252550 }, { "epoch": 20.99, "learning_rate": 1.202438821605742e-06, "loss": 0.7513, "step": 252560 }, { "epoch": 20.99, "learning_rate": 1.2023279660782084e-06, "loss": 0.6866, "step": 252570 }, { "epoch": 20.99, "learning_rate": 1.2022171105506749e-06, "loss": 0.7934, "step": 252580 }, { "epoch": 20.99, "learning_rate": 1.2021062550231412e-06, "loss": 0.75, "step": 252590 }, { "epoch": 21.0, "learning_rate": 1.2019953994956073e-06, "loss": 0.7584, "step": 252600 }, { "epoch": 21.0, "learning_rate": 1.2018845439680736e-06, "loss": 0.7294, "step": 252610 }, { "epoch": 21.0, "learning_rate": 1.2017736884405399e-06, "loss": 0.8184, "step": 252620 }, { "epoch": 21.0, "learning_rate": 1.2016628329130062e-06, "loss": 0.7586, "step": 252630 }, { "epoch": 21.0, "learning_rate": 1.2015519773854722e-06, "loss": 0.7561, "step": 252640 }, { "epoch": 21.0, "learning_rate": 1.2014411218579385e-06, "loss": 0.8045, "step": 252650 }, { "epoch": 21.0, "eval_loss": 1.1190541982650757, "eval_runtime": 354.9243, "eval_samples_per_second": 7.534, "eval_steps_per_second": 3.767, "eval_wer": 0.6376140093138016, "step": 252651 }, { "epoch": 21.0, "learning_rate": 1.2013302663304048e-06, "loss": 0.6952, "step": 252660 }, { "epoch": 21.0, "learning_rate": 1.2012194108028711e-06, "loss": 0.7157, "step": 252670 }, { "epoch": 21.0, "learning_rate": 1.2011085552753372e-06, "loss": 0.7157, "step": 252680 }, { "epoch": 21.0, "learning_rate": 1.2009976997478035e-06, "loss": 0.7612, "step": 252690 }, { "epoch": 21.0, "learning_rate": 1.20088684422027e-06, "loss": 0.697, "step": 252700 }, { "epoch": 21.0, "learning_rate": 1.2007759886927363e-06, "loss": 0.7952, "step": 252710 }, { "epoch": 21.01, "learning_rate": 1.2006651331652024e-06, "loss": 0.7526, "step": 252720 }, { "epoch": 21.01, "learning_rate": 1.2005542776376687e-06, "loss": 0.809, "step": 252730 }, { "epoch": 21.01, "learning_rate": 1.200443422110135e-06, "loss": 0.7801, "step": 252740 }, { "epoch": 21.01, "learning_rate": 1.2003325665826013e-06, "loss": 0.7426, "step": 252750 }, { "epoch": 21.01, "learning_rate": 1.2002217110550674e-06, "loss": 0.8165, "step": 252760 }, { "epoch": 21.01, "learning_rate": 1.2001108555275337e-06, "loss": 0.8182, "step": 252770 }, { "epoch": 21.01, "learning_rate": 1.2e-06, "loss": 0.7511, "step": 252780 }, { "epoch": 21.01, "learning_rate": 1.1998891444724662e-06, "loss": 0.7447, "step": 252790 }, { "epoch": 21.01, "learning_rate": 1.1997782889449323e-06, "loss": 0.7844, "step": 252800 }, { "epoch": 21.01, "learning_rate": 1.1996674334173986e-06, "loss": 0.7633, "step": 252810 }, { "epoch": 21.01, "learning_rate": 1.1995565778898651e-06, "loss": 0.6885, "step": 252820 }, { "epoch": 21.01, "learning_rate": 1.1994457223623314e-06, "loss": 0.7398, "step": 252830 }, { "epoch": 21.02, "learning_rate": 1.1993348668347975e-06, "loss": 0.7333, "step": 252840 }, { "epoch": 21.02, "learning_rate": 1.1992240113072638e-06, "loss": 0.7696, "step": 252850 }, { "epoch": 21.02, "learning_rate": 1.19911315577973e-06, "loss": 0.8162, "step": 252860 }, { "epoch": 21.02, "learning_rate": 1.1990023002521962e-06, "loss": 0.799, "step": 252870 }, { "epoch": 21.02, "learning_rate": 1.1988914447246625e-06, "loss": 0.8762, "step": 252880 }, { "epoch": 21.02, "learning_rate": 1.1987805891971288e-06, "loss": 0.7319, "step": 252890 }, { "epoch": 21.02, "learning_rate": 1.198669733669595e-06, "loss": 0.7074, "step": 252900 }, { "epoch": 21.02, "learning_rate": 1.1985588781420611e-06, "loss": 0.7097, "step": 252910 }, { "epoch": 21.02, "learning_rate": 1.1984480226145274e-06, "loss": 0.7557, "step": 252920 }, { "epoch": 21.02, "learning_rate": 1.1983371670869937e-06, "loss": 0.7758, "step": 252930 }, { "epoch": 21.02, "learning_rate": 1.1982263115594602e-06, "loss": 0.8223, "step": 252940 }, { "epoch": 21.02, "learning_rate": 1.1981154560319263e-06, "loss": 0.7401, "step": 252950 }, { "epoch": 21.03, "learning_rate": 1.1980046005043926e-06, "loss": 0.7853, "step": 252960 }, { "epoch": 21.03, "learning_rate": 1.197893744976859e-06, "loss": 0.7255, "step": 252970 }, { "epoch": 21.03, "learning_rate": 1.1977828894493252e-06, "loss": 0.6917, "step": 252980 }, { "epoch": 21.03, "learning_rate": 1.1976720339217913e-06, "loss": 0.7876, "step": 252990 }, { "epoch": 21.03, "learning_rate": 1.1975611783942576e-06, "loss": 0.7782, "step": 253000 }, { "epoch": 21.03, "learning_rate": 1.1974503228667239e-06, "loss": 0.8017, "step": 253010 }, { "epoch": 21.03, "learning_rate": 1.1973394673391902e-06, "loss": 0.7664, "step": 253020 }, { "epoch": 21.03, "learning_rate": 1.1972286118116563e-06, "loss": 0.8207, "step": 253030 }, { "epoch": 21.03, "learning_rate": 1.1971177562841226e-06, "loss": 0.7308, "step": 253040 }, { "epoch": 21.03, "learning_rate": 1.1970069007565889e-06, "loss": 0.7674, "step": 253050 }, { "epoch": 21.03, "learning_rate": 1.1968960452290552e-06, "loss": 0.8039, "step": 253060 }, { "epoch": 21.03, "learning_rate": 1.1967851897015215e-06, "loss": 0.8165, "step": 253070 }, { "epoch": 21.04, "learning_rate": 1.1966743341739877e-06, "loss": 0.7285, "step": 253080 }, { "epoch": 21.04, "learning_rate": 1.196563478646454e-06, "loss": 0.7944, "step": 253090 }, { "epoch": 21.04, "learning_rate": 1.1964526231189203e-06, "loss": 0.7922, "step": 253100 }, { "epoch": 21.04, "learning_rate": 1.1963417675913864e-06, "loss": 0.7516, "step": 253110 }, { "epoch": 21.04, "learning_rate": 1.1962309120638527e-06, "loss": 0.7397, "step": 253120 }, { "epoch": 21.04, "learning_rate": 1.196120056536319e-06, "loss": 0.8063, "step": 253130 }, { "epoch": 21.04, "learning_rate": 1.1960092010087853e-06, "loss": 0.7526, "step": 253140 }, { "epoch": 21.04, "learning_rate": 1.1958983454812514e-06, "loss": 0.7746, "step": 253150 }, { "epoch": 21.04, "learning_rate": 1.1957874899537177e-06, "loss": 0.7688, "step": 253160 }, { "epoch": 21.04, "learning_rate": 1.195676634426184e-06, "loss": 0.7677, "step": 253170 }, { "epoch": 21.04, "learning_rate": 1.1955657788986503e-06, "loss": 0.7983, "step": 253180 }, { "epoch": 21.04, "learning_rate": 1.1954549233711166e-06, "loss": 0.7135, "step": 253190 }, { "epoch": 21.05, "learning_rate": 1.1953440678435829e-06, "loss": 0.759, "step": 253200 }, { "epoch": 21.05, "learning_rate": 1.1952332123160492e-06, "loss": 0.8052, "step": 253210 }, { "epoch": 21.05, "learning_rate": 1.1951223567885155e-06, "loss": 0.7104, "step": 253220 }, { "epoch": 21.05, "learning_rate": 1.1950115012609815e-06, "loss": 0.7865, "step": 253230 }, { "epoch": 21.05, "learning_rate": 1.1949006457334478e-06, "loss": 0.7405, "step": 253240 }, { "epoch": 21.05, "learning_rate": 1.1947897902059141e-06, "loss": 0.735, "step": 253250 }, { "epoch": 21.05, "learning_rate": 1.1946789346783804e-06, "loss": 0.7969, "step": 253260 }, { "epoch": 21.05, "learning_rate": 1.1945680791508465e-06, "loss": 0.7437, "step": 253270 }, { "epoch": 21.05, "learning_rate": 1.1944572236233128e-06, "loss": 0.819, "step": 253280 }, { "epoch": 21.05, "learning_rate": 1.194346368095779e-06, "loss": 0.7624, "step": 253290 }, { "epoch": 21.05, "learning_rate": 1.1942355125682452e-06, "loss": 0.7559, "step": 253300 }, { "epoch": 21.05, "learning_rate": 1.1941246570407117e-06, "loss": 0.8108, "step": 253310 }, { "epoch": 21.06, "learning_rate": 1.194013801513178e-06, "loss": 0.6635, "step": 253320 }, { "epoch": 21.06, "learning_rate": 1.1939140315383975e-06, "loss": 0.756, "step": 253330 }, { "epoch": 21.06, "learning_rate": 1.1938031760108638e-06, "loss": 0.7453, "step": 253340 }, { "epoch": 21.06, "learning_rate": 1.1936923204833301e-06, "loss": 0.747, "step": 253350 }, { "epoch": 21.06, "learning_rate": 1.1935814649557962e-06, "loss": 0.7999, "step": 253360 }, { "epoch": 21.06, "learning_rate": 1.1934706094282625e-06, "loss": 0.7557, "step": 253370 }, { "epoch": 21.06, "learning_rate": 1.1933597539007288e-06, "loss": 0.7352, "step": 253380 }, { "epoch": 21.06, "learning_rate": 1.1932488983731949e-06, "loss": 0.7625, "step": 253390 }, { "epoch": 21.06, "learning_rate": 1.1931380428456614e-06, "loss": 0.7319, "step": 253400 }, { "epoch": 21.06, "learning_rate": 1.1930271873181277e-06, "loss": 0.772, "step": 253410 }, { "epoch": 21.06, "learning_rate": 1.192916331790594e-06, "loss": 0.7734, "step": 253420 }, { "epoch": 21.06, "learning_rate": 1.19280547626306e-06, "loss": 0.7774, "step": 253430 }, { "epoch": 21.07, "learning_rate": 1.1926946207355264e-06, "loss": 0.8146, "step": 253440 }, { "epoch": 21.07, "learning_rate": 1.1925837652079926e-06, "loss": 0.7317, "step": 253450 }, { "epoch": 21.07, "learning_rate": 1.192472909680459e-06, "loss": 0.7232, "step": 253460 }, { "epoch": 21.07, "learning_rate": 1.192362054152925e-06, "loss": 0.7759, "step": 253470 }, { "epoch": 21.07, "learning_rate": 1.1922511986253913e-06, "loss": 0.7209, "step": 253480 }, { "epoch": 21.07, "learning_rate": 1.1921403430978576e-06, "loss": 0.7845, "step": 253490 }, { "epoch": 21.07, "learning_rate": 1.192029487570324e-06, "loss": 0.7658, "step": 253500 }, { "epoch": 21.07, "learning_rate": 1.19191863204279e-06, "loss": 0.7932, "step": 253510 }, { "epoch": 21.07, "learning_rate": 1.1918077765152565e-06, "loss": 0.7769, "step": 253520 }, { "epoch": 21.07, "learning_rate": 1.1916969209877228e-06, "loss": 0.7173, "step": 253530 }, { "epoch": 21.07, "learning_rate": 1.191586065460189e-06, "loss": 0.6902, "step": 253540 }, { "epoch": 21.07, "learning_rate": 1.1914752099326552e-06, "loss": 0.7376, "step": 253550 }, { "epoch": 21.08, "learning_rate": 1.1913643544051215e-06, "loss": 0.8181, "step": 253560 }, { "epoch": 21.08, "learning_rate": 1.1912534988775878e-06, "loss": 0.7163, "step": 253570 }, { "epoch": 21.08, "learning_rate": 1.191142643350054e-06, "loss": 0.7321, "step": 253580 }, { "epoch": 21.08, "learning_rate": 1.1910317878225201e-06, "loss": 0.6983, "step": 253590 }, { "epoch": 21.08, "learning_rate": 1.1909209322949864e-06, "loss": 0.7449, "step": 253600 }, { "epoch": 21.08, "learning_rate": 1.1908100767674527e-06, "loss": 0.7977, "step": 253610 }, { "epoch": 21.08, "learning_rate": 1.190699221239919e-06, "loss": 0.7653, "step": 253620 }, { "epoch": 21.08, "learning_rate": 1.1905883657123851e-06, "loss": 0.7527, "step": 253630 }, { "epoch": 21.08, "learning_rate": 1.1904775101848514e-06, "loss": 0.7645, "step": 253640 }, { "epoch": 21.08, "learning_rate": 1.190366654657318e-06, "loss": 0.7597, "step": 253650 }, { "epoch": 21.08, "learning_rate": 1.1902557991297842e-06, "loss": 0.808, "step": 253660 }, { "epoch": 21.08, "learning_rate": 1.1901449436022503e-06, "loss": 0.7847, "step": 253670 }, { "epoch": 21.09, "learning_rate": 1.1900340880747166e-06, "loss": 0.774, "step": 253680 }, { "epoch": 21.09, "learning_rate": 1.1899232325471829e-06, "loss": 0.7782, "step": 253690 }, { "epoch": 21.09, "learning_rate": 1.1898123770196492e-06, "loss": 0.6837, "step": 253700 }, { "epoch": 21.09, "learning_rate": 1.1897015214921153e-06, "loss": 0.8133, "step": 253710 }, { "epoch": 21.09, "learning_rate": 1.1895906659645816e-06, "loss": 0.7838, "step": 253720 }, { "epoch": 21.09, "learning_rate": 1.1894798104370479e-06, "loss": 0.735, "step": 253730 }, { "epoch": 21.09, "learning_rate": 1.1893689549095142e-06, "loss": 0.7884, "step": 253740 }, { "epoch": 21.09, "learning_rate": 1.1892580993819802e-06, "loss": 0.7249, "step": 253750 }, { "epoch": 21.09, "learning_rate": 1.1891472438544465e-06, "loss": 0.8044, "step": 253760 }, { "epoch": 21.09, "learning_rate": 1.189036388326913e-06, "loss": 0.7075, "step": 253770 }, { "epoch": 21.09, "learning_rate": 1.1889255327993793e-06, "loss": 0.7108, "step": 253780 }, { "epoch": 21.09, "learning_rate": 1.1888146772718454e-06, "loss": 0.7099, "step": 253790 }, { "epoch": 21.1, "learning_rate": 1.1887038217443117e-06, "loss": 0.7545, "step": 253800 }, { "epoch": 21.1, "learning_rate": 1.188592966216778e-06, "loss": 0.76, "step": 253810 }, { "epoch": 21.1, "learning_rate": 1.1884821106892443e-06, "loss": 0.7409, "step": 253820 }, { "epoch": 21.1, "learning_rate": 1.1883712551617104e-06, "loss": 0.7093, "step": 253830 }, { "epoch": 21.1, "learning_rate": 1.1882603996341767e-06, "loss": 0.7238, "step": 253840 }, { "epoch": 21.1, "learning_rate": 1.188149544106643e-06, "loss": 0.6765, "step": 253850 }, { "epoch": 21.1, "learning_rate": 1.188038688579109e-06, "loss": 0.7829, "step": 253860 }, { "epoch": 21.1, "learning_rate": 1.1879278330515754e-06, "loss": 0.6877, "step": 253870 }, { "epoch": 21.1, "learning_rate": 1.1878169775240417e-06, "loss": 0.7707, "step": 253880 }, { "epoch": 21.1, "learning_rate": 1.1877061219965082e-06, "loss": 0.7136, "step": 253890 }, { "epoch": 21.1, "learning_rate": 1.1875952664689742e-06, "loss": 0.7885, "step": 253900 }, { "epoch": 21.1, "learning_rate": 1.1874844109414405e-06, "loss": 0.8224, "step": 253910 }, { "epoch": 21.11, "learning_rate": 1.1873735554139068e-06, "loss": 0.7925, "step": 253920 }, { "epoch": 21.11, "learning_rate": 1.1872626998863731e-06, "loss": 0.6721, "step": 253930 }, { "epoch": 21.11, "learning_rate": 1.1871518443588392e-06, "loss": 0.6918, "step": 253940 }, { "epoch": 21.11, "learning_rate": 1.1870409888313055e-06, "loss": 0.7495, "step": 253950 }, { "epoch": 21.11, "learning_rate": 1.1869301333037718e-06, "loss": 0.702, "step": 253960 }, { "epoch": 21.11, "learning_rate": 1.186819277776238e-06, "loss": 0.7644, "step": 253970 }, { "epoch": 21.11, "learning_rate": 1.1867084222487042e-06, "loss": 0.7755, "step": 253980 }, { "epoch": 21.11, "learning_rate": 1.1865975667211705e-06, "loss": 0.7751, "step": 253990 }, { "epoch": 21.11, "learning_rate": 1.1864867111936368e-06, "loss": 0.736, "step": 254000 }, { "epoch": 21.11, "learning_rate": 1.186375855666103e-06, "loss": 0.768, "step": 254010 }, { "epoch": 21.11, "learning_rate": 1.1862650001385694e-06, "loss": 0.7663, "step": 254020 }, { "epoch": 21.11, "learning_rate": 1.1861541446110357e-06, "loss": 0.7154, "step": 254030 }, { "epoch": 21.12, "learning_rate": 1.186043289083502e-06, "loss": 0.7557, "step": 254040 }, { "epoch": 21.12, "learning_rate": 1.1859324335559683e-06, "loss": 0.7155, "step": 254050 }, { "epoch": 21.12, "learning_rate": 1.1858215780284343e-06, "loss": 0.7914, "step": 254060 }, { "epoch": 21.12, "learning_rate": 1.1857107225009006e-06, "loss": 0.7568, "step": 254070 }, { "epoch": 21.12, "learning_rate": 1.185599866973367e-06, "loss": 0.7656, "step": 254080 }, { "epoch": 21.12, "learning_rate": 1.1854890114458332e-06, "loss": 0.6662, "step": 254090 }, { "epoch": 21.12, "learning_rate": 1.1853781559182993e-06, "loss": 0.6827, "step": 254100 }, { "epoch": 21.12, "learning_rate": 1.1852673003907656e-06, "loss": 0.7804, "step": 254110 }, { "epoch": 21.12, "learning_rate": 1.1851564448632319e-06, "loss": 0.7301, "step": 254120 }, { "epoch": 21.12, "learning_rate": 1.1850455893356982e-06, "loss": 0.8393, "step": 254130 }, { "epoch": 21.12, "learning_rate": 1.1849347338081645e-06, "loss": 0.7177, "step": 254140 }, { "epoch": 21.12, "learning_rate": 1.1848238782806308e-06, "loss": 0.7224, "step": 254150 }, { "epoch": 21.13, "learning_rate": 1.184713022753097e-06, "loss": 0.8326, "step": 254160 }, { "epoch": 21.13, "learning_rate": 1.1846021672255634e-06, "loss": 0.7257, "step": 254170 }, { "epoch": 21.13, "learning_rate": 1.1844913116980295e-06, "loss": 0.7888, "step": 254180 }, { "epoch": 21.13, "learning_rate": 1.1843804561704957e-06, "loss": 0.7181, "step": 254190 }, { "epoch": 21.13, "learning_rate": 1.184269600642962e-06, "loss": 0.7025, "step": 254200 }, { "epoch": 21.13, "learning_rate": 1.1841587451154283e-06, "loss": 0.8027, "step": 254210 }, { "epoch": 21.13, "learning_rate": 1.1840478895878944e-06, "loss": 0.7557, "step": 254220 }, { "epoch": 21.13, "learning_rate": 1.1839370340603607e-06, "loss": 0.7448, "step": 254230 }, { "epoch": 21.13, "learning_rate": 1.183826178532827e-06, "loss": 0.6638, "step": 254240 }, { "epoch": 21.13, "learning_rate": 1.183715323005293e-06, "loss": 0.7804, "step": 254250 }, { "epoch": 21.13, "learning_rate": 1.1836044674777596e-06, "loss": 0.76, "step": 254260 }, { "epoch": 21.13, "learning_rate": 1.183493611950226e-06, "loss": 0.7401, "step": 254270 }, { "epoch": 21.14, "learning_rate": 1.1833827564226922e-06, "loss": 0.6747, "step": 254280 }, { "epoch": 21.14, "learning_rate": 1.1832719008951583e-06, "loss": 0.6962, "step": 254290 }, { "epoch": 21.14, "learning_rate": 1.1831610453676246e-06, "loss": 0.756, "step": 254300 }, { "epoch": 21.14, "learning_rate": 1.1830501898400909e-06, "loss": 0.7793, "step": 254310 }, { "epoch": 21.14, "learning_rate": 1.1829393343125572e-06, "loss": 0.7541, "step": 254320 }, { "epoch": 21.14, "learning_rate": 1.1828284787850232e-06, "loss": 0.7511, "step": 254330 }, { "epoch": 21.14, "learning_rate": 1.1827176232574895e-06, "loss": 0.7509, "step": 254340 }, { "epoch": 21.14, "learning_rate": 1.1826067677299558e-06, "loss": 0.7224, "step": 254350 }, { "epoch": 21.14, "learning_rate": 1.1824959122024221e-06, "loss": 0.8309, "step": 254360 }, { "epoch": 21.14, "learning_rate": 1.1823850566748882e-06, "loss": 0.7687, "step": 254370 }, { "epoch": 21.14, "learning_rate": 1.1822742011473547e-06, "loss": 0.7249, "step": 254380 }, { "epoch": 21.14, "learning_rate": 1.182163345619821e-06, "loss": 0.6884, "step": 254390 }, { "epoch": 21.15, "learning_rate": 1.1820524900922873e-06, "loss": 0.7206, "step": 254400 }, { "epoch": 21.15, "learning_rate": 1.1819416345647534e-06, "loss": 0.8517, "step": 254410 }, { "epoch": 21.15, "learning_rate": 1.1818307790372197e-06, "loss": 0.739, "step": 254420 }, { "epoch": 21.15, "learning_rate": 1.181719923509686e-06, "loss": 0.6965, "step": 254430 }, { "epoch": 21.15, "learning_rate": 1.1816090679821523e-06, "loss": 0.7362, "step": 254440 }, { "epoch": 21.15, "learning_rate": 1.1814982124546184e-06, "loss": 0.7415, "step": 254450 }, { "epoch": 21.15, "learning_rate": 1.1813873569270847e-06, "loss": 0.7728, "step": 254460 }, { "epoch": 21.15, "learning_rate": 1.181276501399551e-06, "loss": 0.7287, "step": 254470 }, { "epoch": 21.15, "learning_rate": 1.1811656458720173e-06, "loss": 0.7221, "step": 254480 }, { "epoch": 21.15, "learning_rate": 1.1810547903444833e-06, "loss": 0.732, "step": 254490 }, { "epoch": 21.15, "learning_rate": 1.1809439348169496e-06, "loss": 0.7561, "step": 254500 }, { "epoch": 21.15, "learning_rate": 1.1808330792894161e-06, "loss": 0.7684, "step": 254510 }, { "epoch": 21.16, "learning_rate": 1.1807222237618824e-06, "loss": 0.693, "step": 254520 }, { "epoch": 21.16, "learning_rate": 1.1806113682343485e-06, "loss": 0.7552, "step": 254530 }, { "epoch": 21.16, "learning_rate": 1.1805005127068148e-06, "loss": 0.7334, "step": 254540 }, { "epoch": 21.16, "learning_rate": 1.1803896571792811e-06, "loss": 0.801, "step": 254550 }, { "epoch": 21.16, "learning_rate": 1.1802788016517474e-06, "loss": 0.7969, "step": 254560 }, { "epoch": 21.16, "learning_rate": 1.1801679461242135e-06, "loss": 0.7663, "step": 254570 }, { "epoch": 21.16, "learning_rate": 1.1800570905966798e-06, "loss": 0.7653, "step": 254580 }, { "epoch": 21.16, "learning_rate": 1.179946235069146e-06, "loss": 0.767, "step": 254590 }, { "epoch": 21.16, "learning_rate": 1.1798353795416124e-06, "loss": 0.7281, "step": 254600 }, { "epoch": 21.16, "learning_rate": 1.1797245240140785e-06, "loss": 0.7805, "step": 254610 }, { "epoch": 21.16, "learning_rate": 1.1796136684865448e-06, "loss": 0.8126, "step": 254620 }, { "epoch": 21.16, "learning_rate": 1.1795028129590113e-06, "loss": 0.7274, "step": 254630 }, { "epoch": 21.17, "learning_rate": 1.1793919574314776e-06, "loss": 0.7503, "step": 254640 }, { "epoch": 21.17, "learning_rate": 1.1792811019039436e-06, "loss": 0.7293, "step": 254650 }, { "epoch": 21.17, "learning_rate": 1.17917024637641e-06, "loss": 0.7371, "step": 254660 }, { "epoch": 21.17, "learning_rate": 1.1790593908488762e-06, "loss": 0.6952, "step": 254670 }, { "epoch": 21.17, "learning_rate": 1.1789485353213423e-06, "loss": 0.7333, "step": 254680 }, { "epoch": 21.17, "learning_rate": 1.1788376797938086e-06, "loss": 0.7161, "step": 254690 }, { "epoch": 21.17, "learning_rate": 1.178726824266275e-06, "loss": 0.6899, "step": 254700 }, { "epoch": 21.17, "learning_rate": 1.1786159687387412e-06, "loss": 0.7766, "step": 254710 }, { "epoch": 21.17, "learning_rate": 1.1785051132112073e-06, "loss": 0.754, "step": 254720 }, { "epoch": 21.17, "learning_rate": 1.1783942576836736e-06, "loss": 0.7584, "step": 254730 }, { "epoch": 21.17, "learning_rate": 1.1782834021561399e-06, "loss": 0.7725, "step": 254740 }, { "epoch": 21.17, "learning_rate": 1.1781725466286064e-06, "loss": 0.7688, "step": 254750 }, { "epoch": 21.18, "learning_rate": 1.1780616911010725e-06, "loss": 0.7592, "step": 254760 }, { "epoch": 21.18, "learning_rate": 1.1779508355735388e-06, "loss": 0.775, "step": 254770 }, { "epoch": 21.18, "learning_rate": 1.177839980046005e-06, "loss": 0.6874, "step": 254780 }, { "epoch": 21.18, "learning_rate": 1.1777291245184714e-06, "loss": 0.7689, "step": 254790 }, { "epoch": 21.18, "learning_rate": 1.1776182689909374e-06, "loss": 0.7623, "step": 254800 }, { "epoch": 21.18, "learning_rate": 1.1775074134634037e-06, "loss": 0.8259, "step": 254810 }, { "epoch": 21.18, "learning_rate": 1.17739655793587e-06, "loss": 0.735, "step": 254820 }, { "epoch": 21.18, "learning_rate": 1.1772857024083363e-06, "loss": 0.7769, "step": 254830 }, { "epoch": 21.18, "learning_rate": 1.1771748468808024e-06, "loss": 0.7454, "step": 254840 }, { "epoch": 21.18, "learning_rate": 1.1770639913532687e-06, "loss": 0.7456, "step": 254850 }, { "epoch": 21.18, "learning_rate": 1.176953135825735e-06, "loss": 0.7686, "step": 254860 }, { "epoch": 21.18, "learning_rate": 1.1768422802982013e-06, "loss": 0.7094, "step": 254870 }, { "epoch": 21.19, "learning_rate": 1.1767314247706676e-06, "loss": 0.7508, "step": 254880 }, { "epoch": 21.19, "learning_rate": 1.1766205692431339e-06, "loss": 0.745, "step": 254890 }, { "epoch": 21.19, "learning_rate": 1.1765097137156002e-06, "loss": 0.6982, "step": 254900 }, { "epoch": 21.19, "learning_rate": 1.1763988581880665e-06, "loss": 0.7931, "step": 254910 }, { "epoch": 21.19, "learning_rate": 1.1762880026605326e-06, "loss": 0.8327, "step": 254920 }, { "epoch": 21.19, "learning_rate": 1.1761771471329989e-06, "loss": 0.7063, "step": 254930 }, { "epoch": 21.19, "learning_rate": 1.1760662916054651e-06, "loss": 0.7969, "step": 254940 }, { "epoch": 21.19, "learning_rate": 1.1759554360779314e-06, "loss": 0.7872, "step": 254950 }, { "epoch": 21.19, "learning_rate": 1.1758445805503975e-06, "loss": 0.8489, "step": 254960 }, { "epoch": 21.19, "learning_rate": 1.1757337250228638e-06, "loss": 0.7274, "step": 254970 }, { "epoch": 21.19, "learning_rate": 1.1756228694953301e-06, "loss": 0.6889, "step": 254980 }, { "epoch": 21.19, "learning_rate": 1.1755120139677964e-06, "loss": 0.7401, "step": 254990 }, { "epoch": 21.2, "learning_rate": 1.1754011584402627e-06, "loss": 0.7896, "step": 255000 }, { "epoch": 21.2, "learning_rate": 1.175290302912729e-06, "loss": 0.724, "step": 255010 }, { "epoch": 21.2, "learning_rate": 1.1751794473851953e-06, "loss": 0.7612, "step": 255020 }, { "epoch": 21.2, "learning_rate": 1.1750685918576616e-06, "loss": 0.7437, "step": 255030 }, { "epoch": 21.2, "learning_rate": 1.1749577363301277e-06, "loss": 0.6951, "step": 255040 }, { "epoch": 21.2, "learning_rate": 1.174846880802594e-06, "loss": 0.7383, "step": 255050 }, { "epoch": 21.2, "learning_rate": 1.1747360252750603e-06, "loss": 0.8126, "step": 255060 }, { "epoch": 21.2, "learning_rate": 1.1746251697475264e-06, "loss": 0.7636, "step": 255070 }, { "epoch": 21.2, "learning_rate": 1.1745143142199926e-06, "loss": 0.7324, "step": 255080 }, { "epoch": 21.2, "learning_rate": 1.174403458692459e-06, "loss": 0.7263, "step": 255090 }, { "epoch": 21.2, "learning_rate": 1.1742926031649252e-06, "loss": 0.7212, "step": 255100 }, { "epoch": 21.2, "learning_rate": 1.1741817476373913e-06, "loss": 0.8481, "step": 255110 }, { "epoch": 21.21, "learning_rate": 1.1740708921098578e-06, "loss": 0.7564, "step": 255120 }, { "epoch": 21.21, "learning_rate": 1.1739600365823241e-06, "loss": 0.7448, "step": 255130 }, { "epoch": 21.21, "learning_rate": 1.1738491810547904e-06, "loss": 0.7486, "step": 255140 }, { "epoch": 21.21, "learning_rate": 1.1737383255272565e-06, "loss": 0.7262, "step": 255150 }, { "epoch": 21.21, "learning_rate": 1.1736274699997228e-06, "loss": 0.8368, "step": 255160 }, { "epoch": 21.21, "learning_rate": 1.173516614472189e-06, "loss": 0.797, "step": 255170 }, { "epoch": 21.21, "learning_rate": 1.1734057589446554e-06, "loss": 0.7782, "step": 255180 }, { "epoch": 21.21, "learning_rate": 1.1732949034171215e-06, "loss": 0.7387, "step": 255190 }, { "epoch": 21.21, "learning_rate": 1.1731840478895878e-06, "loss": 0.7277, "step": 255200 }, { "epoch": 21.21, "learning_rate": 1.173073192362054e-06, "loss": 0.7826, "step": 255210 }, { "epoch": 21.21, "learning_rate": 1.1729623368345204e-06, "loss": 0.7748, "step": 255220 }, { "epoch": 21.21, "learning_rate": 1.1728514813069864e-06, "loss": 0.7482, "step": 255230 }, { "epoch": 21.22, "learning_rate": 1.172740625779453e-06, "loss": 0.7888, "step": 255240 }, { "epoch": 21.22, "learning_rate": 1.1726297702519192e-06, "loss": 0.7298, "step": 255250 }, { "epoch": 21.22, "learning_rate": 1.1725189147243855e-06, "loss": 0.7201, "step": 255260 }, { "epoch": 21.22, "learning_rate": 1.1724080591968516e-06, "loss": 0.7763, "step": 255270 }, { "epoch": 21.22, "learning_rate": 1.172297203669318e-06, "loss": 0.7257, "step": 255280 }, { "epoch": 21.22, "learning_rate": 1.1721863481417842e-06, "loss": 0.701, "step": 255290 }, { "epoch": 21.22, "learning_rate": 1.1720754926142505e-06, "loss": 0.7508, "step": 255300 }, { "epoch": 21.22, "learning_rate": 1.1719646370867166e-06, "loss": 0.8041, "step": 255310 }, { "epoch": 21.22, "learning_rate": 1.1718537815591829e-06, "loss": 0.8045, "step": 255320 }, { "epoch": 21.22, "learning_rate": 1.1717429260316492e-06, "loss": 0.7162, "step": 255330 }, { "epoch": 21.22, "learning_rate": 1.1716320705041155e-06, "loss": 0.719, "step": 255340 }, { "epoch": 21.22, "learning_rate": 1.1715212149765816e-06, "loss": 0.7603, "step": 255350 }, { "epoch": 21.23, "learning_rate": 1.1714103594490479e-06, "loss": 0.7264, "step": 255360 }, { "epoch": 21.23, "learning_rate": 1.1712995039215144e-06, "loss": 0.7555, "step": 255370 }, { "epoch": 21.23, "learning_rate": 1.1711886483939807e-06, "loss": 0.7749, "step": 255380 }, { "epoch": 21.23, "learning_rate": 1.1710777928664467e-06, "loss": 0.7109, "step": 255390 }, { "epoch": 21.23, "learning_rate": 1.170966937338913e-06, "loss": 0.7178, "step": 255400 }, { "epoch": 21.23, "learning_rate": 1.1708560818113793e-06, "loss": 0.7538, "step": 255410 }, { "epoch": 21.23, "learning_rate": 1.1707452262838456e-06, "loss": 0.6906, "step": 255420 }, { "epoch": 21.23, "learning_rate": 1.1706343707563117e-06, "loss": 0.7151, "step": 255430 }, { "epoch": 21.23, "learning_rate": 1.170523515228778e-06, "loss": 0.7379, "step": 255440 }, { "epoch": 21.23, "learning_rate": 1.1704126597012443e-06, "loss": 0.7561, "step": 255450 }, { "epoch": 21.23, "learning_rate": 1.1703018041737106e-06, "loss": 0.7899, "step": 255460 }, { "epoch": 21.23, "learning_rate": 1.1701909486461767e-06, "loss": 0.683, "step": 255470 }, { "epoch": 21.24, "learning_rate": 1.170080093118643e-06, "loss": 0.7363, "step": 255480 }, { "epoch": 21.24, "learning_rate": 1.1699692375911095e-06, "loss": 0.7338, "step": 255490 }, { "epoch": 21.24, "learning_rate": 1.1698583820635758e-06, "loss": 0.704, "step": 255500 }, { "epoch": 21.24, "learning_rate": 1.1697475265360419e-06, "loss": 0.8148, "step": 255510 }, { "epoch": 21.24, "learning_rate": 1.1696366710085082e-06, "loss": 0.7378, "step": 255520 }, { "epoch": 21.24, "learning_rate": 1.1695258154809745e-06, "loss": 0.7449, "step": 255530 }, { "epoch": 21.24, "learning_rate": 1.1694149599534405e-06, "loss": 0.7732, "step": 255540 }, { "epoch": 21.24, "learning_rate": 1.1693041044259068e-06, "loss": 0.7382, "step": 255550 }, { "epoch": 21.24, "learning_rate": 1.1691932488983731e-06, "loss": 0.7625, "step": 255560 }, { "epoch": 21.24, "learning_rate": 1.1690823933708394e-06, "loss": 0.7086, "step": 255570 }, { "epoch": 21.24, "learning_rate": 1.1689715378433055e-06, "loss": 0.7261, "step": 255580 }, { "epoch": 21.24, "learning_rate": 1.1688606823157718e-06, "loss": 0.6796, "step": 255590 }, { "epoch": 21.25, "learning_rate": 1.168749826788238e-06, "loss": 0.774, "step": 255600 }, { "epoch": 21.25, "learning_rate": 1.1686389712607046e-06, "loss": 0.772, "step": 255610 }, { "epoch": 21.25, "learning_rate": 1.1685281157331707e-06, "loss": 0.7319, "step": 255620 }, { "epoch": 21.25, "learning_rate": 1.168417260205637e-06, "loss": 0.772, "step": 255630 }, { "epoch": 21.25, "learning_rate": 1.1683064046781033e-06, "loss": 0.7306, "step": 255640 }, { "epoch": 21.25, "learning_rate": 1.1681955491505696e-06, "loss": 0.7602, "step": 255650 }, { "epoch": 21.25, "learning_rate": 1.1680846936230357e-06, "loss": 0.7828, "step": 255660 }, { "epoch": 21.25, "learning_rate": 1.167973838095502e-06, "loss": 0.735, "step": 255670 }, { "epoch": 21.25, "learning_rate": 1.1678629825679682e-06, "loss": 0.7424, "step": 255680 }, { "epoch": 21.25, "learning_rate": 1.1677521270404345e-06, "loss": 0.7086, "step": 255690 }, { "epoch": 21.25, "learning_rate": 1.1676412715129006e-06, "loss": 0.7861, "step": 255700 }, { "epoch": 21.25, "learning_rate": 1.167530415985367e-06, "loss": 0.7747, "step": 255710 }, { "epoch": 21.26, "learning_rate": 1.1674195604578332e-06, "loss": 0.7385, "step": 255720 }, { "epoch": 21.26, "learning_rate": 1.1673087049302995e-06, "loss": 0.8016, "step": 255730 }, { "epoch": 21.26, "learning_rate": 1.1671978494027658e-06, "loss": 0.7, "step": 255740 }, { "epoch": 21.26, "learning_rate": 1.167086993875232e-06, "loss": 0.739, "step": 255750 }, { "epoch": 21.26, "learning_rate": 1.1669761383476984e-06, "loss": 0.7587, "step": 255760 }, { "epoch": 21.26, "learning_rate": 1.1668652828201647e-06, "loss": 0.7407, "step": 255770 }, { "epoch": 21.26, "learning_rate": 1.1667544272926308e-06, "loss": 0.7464, "step": 255780 }, { "epoch": 21.26, "learning_rate": 1.166643571765097e-06, "loss": 0.7446, "step": 255790 }, { "epoch": 21.26, "learning_rate": 1.1665327162375634e-06, "loss": 0.7461, "step": 255800 }, { "epoch": 21.26, "learning_rate": 1.1664218607100297e-06, "loss": 0.8106, "step": 255810 }, { "epoch": 21.26, "learning_rate": 1.1663110051824957e-06, "loss": 0.7404, "step": 255820 }, { "epoch": 21.26, "learning_rate": 1.166200149654962e-06, "loss": 0.7418, "step": 255830 }, { "epoch": 21.27, "learning_rate": 1.1660892941274283e-06, "loss": 0.7299, "step": 255840 }, { "epoch": 21.27, "learning_rate": 1.1659784385998946e-06, "loss": 0.7711, "step": 255850 }, { "epoch": 21.27, "learning_rate": 1.165867583072361e-06, "loss": 0.7868, "step": 255860 }, { "epoch": 21.27, "learning_rate": 1.1657567275448272e-06, "loss": 0.7614, "step": 255870 }, { "epoch": 21.27, "learning_rate": 1.1656458720172935e-06, "loss": 0.705, "step": 255880 }, { "epoch": 21.27, "learning_rate": 1.1655350164897598e-06, "loss": 0.7399, "step": 255890 }, { "epoch": 21.27, "learning_rate": 1.165424160962226e-06, "loss": 0.7846, "step": 255900 }, { "epoch": 21.27, "learning_rate": 1.1653133054346922e-06, "loss": 0.7711, "step": 255910 }, { "epoch": 21.27, "learning_rate": 1.1652024499071585e-06, "loss": 0.7394, "step": 255920 }, { "epoch": 21.27, "learning_rate": 1.1650915943796246e-06, "loss": 0.7542, "step": 255930 }, { "epoch": 21.27, "learning_rate": 1.1649807388520909e-06, "loss": 0.7401, "step": 255940 }, { "epoch": 21.27, "learning_rate": 1.1648698833245572e-06, "loss": 0.7074, "step": 255950 }, { "epoch": 21.28, "learning_rate": 1.1647590277970235e-06, "loss": 0.8265, "step": 255960 }, { "epoch": 21.28, "learning_rate": 1.1646481722694895e-06, "loss": 0.7543, "step": 255970 }, { "epoch": 21.28, "learning_rate": 1.164537316741956e-06, "loss": 0.7179, "step": 255980 }, { "epoch": 21.28, "learning_rate": 1.1644264612144223e-06, "loss": 0.7183, "step": 255990 }, { "epoch": 21.28, "learning_rate": 1.1643156056868886e-06, "loss": 0.713, "step": 256000 }, { "epoch": 21.28, "learning_rate": 1.1642047501593547e-06, "loss": 0.8322, "step": 256010 }, { "epoch": 21.28, "learning_rate": 1.164093894631821e-06, "loss": 0.757, "step": 256020 }, { "epoch": 21.28, "learning_rate": 1.1639830391042873e-06, "loss": 0.7906, "step": 256030 }, { "epoch": 21.28, "learning_rate": 1.1638721835767536e-06, "loss": 0.7418, "step": 256040 }, { "epoch": 21.28, "learning_rate": 1.1637613280492197e-06, "loss": 0.7417, "step": 256050 }, { "epoch": 21.28, "learning_rate": 1.163650472521686e-06, "loss": 0.8178, "step": 256060 }, { "epoch": 21.28, "learning_rate": 1.1635396169941523e-06, "loss": 0.7392, "step": 256070 }, { "epoch": 21.29, "learning_rate": 1.1634287614666186e-06, "loss": 0.7352, "step": 256080 }, { "epoch": 21.29, "learning_rate": 1.1633179059390847e-06, "loss": 0.7169, "step": 256090 }, { "epoch": 21.29, "learning_rate": 1.163207050411551e-06, "loss": 0.7381, "step": 256100 }, { "epoch": 21.29, "learning_rate": 1.1630961948840175e-06, "loss": 0.737, "step": 256110 }, { "epoch": 21.29, "learning_rate": 1.1629853393564838e-06, "loss": 0.7253, "step": 256120 }, { "epoch": 21.29, "learning_rate": 1.1628744838289498e-06, "loss": 0.7247, "step": 256130 }, { "epoch": 21.29, "learning_rate": 1.1627636283014161e-06, "loss": 0.6995, "step": 256140 }, { "epoch": 21.29, "learning_rate": 1.1626527727738824e-06, "loss": 0.7604, "step": 256150 }, { "epoch": 21.29, "learning_rate": 1.1625419172463487e-06, "loss": 0.7611, "step": 256160 }, { "epoch": 21.29, "learning_rate": 1.1624310617188148e-06, "loss": 0.7568, "step": 256170 }, { "epoch": 21.29, "learning_rate": 1.1623202061912811e-06, "loss": 0.7971, "step": 256180 }, { "epoch": 21.29, "learning_rate": 1.1622093506637474e-06, "loss": 0.7002, "step": 256190 }, { "epoch": 21.29, "learning_rate": 1.1620984951362137e-06, "loss": 0.7723, "step": 256200 }, { "epoch": 21.3, "learning_rate": 1.1619876396086798e-06, "loss": 0.8255, "step": 256210 }, { "epoch": 21.3, "learning_rate": 1.161876784081146e-06, "loss": 0.7157, "step": 256220 }, { "epoch": 21.3, "learning_rate": 1.1617659285536126e-06, "loss": 0.7483, "step": 256230 }, { "epoch": 21.3, "learning_rate": 1.1616550730260789e-06, "loss": 0.8067, "step": 256240 }, { "epoch": 21.3, "learning_rate": 1.161544217498545e-06, "loss": 0.7427, "step": 256250 }, { "epoch": 21.3, "learning_rate": 1.1614333619710113e-06, "loss": 0.7514, "step": 256260 }, { "epoch": 21.3, "learning_rate": 1.1613225064434776e-06, "loss": 0.7237, "step": 256270 }, { "epoch": 21.3, "learning_rate": 1.1612116509159439e-06, "loss": 0.7323, "step": 256280 }, { "epoch": 21.3, "learning_rate": 1.16110079538841e-06, "loss": 0.717, "step": 256290 }, { "epoch": 21.3, "learning_rate": 1.1609899398608762e-06, "loss": 0.7436, "step": 256300 }, { "epoch": 21.3, "learning_rate": 1.1608790843333425e-06, "loss": 0.7833, "step": 256310 }, { "epoch": 21.3, "learning_rate": 1.1607682288058086e-06, "loss": 0.7048, "step": 256320 }, { "epoch": 21.31, "learning_rate": 1.160657373278275e-06, "loss": 0.7936, "step": 256330 }, { "epoch": 21.31, "learning_rate": 1.1605465177507412e-06, "loss": 0.6962, "step": 256340 }, { "epoch": 21.31, "learning_rate": 1.1604356622232077e-06, "loss": 0.7895, "step": 256350 }, { "epoch": 21.31, "learning_rate": 1.1603248066956738e-06, "loss": 0.7399, "step": 256360 }, { "epoch": 21.31, "learning_rate": 1.16021395116814e-06, "loss": 0.7489, "step": 256370 }, { "epoch": 21.31, "learning_rate": 1.1601030956406064e-06, "loss": 0.7405, "step": 256380 }, { "epoch": 21.31, "learning_rate": 1.1599922401130727e-06, "loss": 0.8385, "step": 256390 }, { "epoch": 21.31, "learning_rate": 1.1598813845855388e-06, "loss": 0.8195, "step": 256400 }, { "epoch": 21.31, "learning_rate": 1.159770529058005e-06, "loss": 0.766, "step": 256410 }, { "epoch": 21.31, "learning_rate": 1.1596596735304714e-06, "loss": 0.722, "step": 256420 }, { "epoch": 21.31, "learning_rate": 1.1595488180029376e-06, "loss": 0.6935, "step": 256430 }, { "epoch": 21.31, "learning_rate": 1.1594379624754037e-06, "loss": 0.7652, "step": 256440 }, { "epoch": 21.32, "learning_rate": 1.15932710694787e-06, "loss": 0.7501, "step": 256450 }, { "epoch": 21.32, "learning_rate": 1.1592162514203363e-06, "loss": 0.7358, "step": 256460 }, { "epoch": 21.32, "learning_rate": 1.1591053958928028e-06, "loss": 0.712, "step": 256470 }, { "epoch": 21.32, "learning_rate": 1.158994540365269e-06, "loss": 0.7751, "step": 256480 }, { "epoch": 21.32, "learning_rate": 1.1588836848377352e-06, "loss": 0.7307, "step": 256490 }, { "epoch": 21.32, "learning_rate": 1.1587728293102015e-06, "loss": 0.7168, "step": 256500 }, { "epoch": 21.32, "learning_rate": 1.1586619737826678e-06, "loss": 0.8073, "step": 256510 }, { "epoch": 21.32, "learning_rate": 1.1585511182551339e-06, "loss": 0.6777, "step": 256520 }, { "epoch": 21.32, "learning_rate": 1.1584402627276002e-06, "loss": 0.7452, "step": 256530 }, { "epoch": 21.32, "learning_rate": 1.1583294072000665e-06, "loss": 0.701, "step": 256540 }, { "epoch": 21.32, "learning_rate": 1.1582185516725328e-06, "loss": 0.7815, "step": 256550 }, { "epoch": 21.32, "learning_rate": 1.1581076961449989e-06, "loss": 0.7857, "step": 256560 }, { "epoch": 21.33, "learning_rate": 1.1579968406174651e-06, "loss": 0.7616, "step": 256570 }, { "epoch": 21.33, "learning_rate": 1.1578859850899314e-06, "loss": 0.7557, "step": 256580 }, { "epoch": 21.33, "learning_rate": 1.1577751295623977e-06, "loss": 0.7037, "step": 256590 }, { "epoch": 21.33, "learning_rate": 1.157664274034864e-06, "loss": 0.6933, "step": 256600 }, { "epoch": 21.33, "learning_rate": 1.1575534185073303e-06, "loss": 0.795, "step": 256610 }, { "epoch": 21.33, "learning_rate": 1.1574425629797966e-06, "loss": 0.7445, "step": 256620 }, { "epoch": 21.33, "learning_rate": 1.157331707452263e-06, "loss": 0.7712, "step": 256630 }, { "epoch": 21.33, "learning_rate": 1.157220851924729e-06, "loss": 0.7888, "step": 256640 }, { "epoch": 21.33, "learning_rate": 1.1571099963971953e-06, "loss": 0.7068, "step": 256650 }, { "epoch": 21.33, "learning_rate": 1.1569991408696616e-06, "loss": 0.8348, "step": 256660 }, { "epoch": 21.33, "learning_rate": 1.1568882853421279e-06, "loss": 0.7225, "step": 256670 }, { "epoch": 21.33, "learning_rate": 1.156777429814594e-06, "loss": 0.7073, "step": 256680 }, { "epoch": 21.34, "learning_rate": 1.1566665742870603e-06, "loss": 0.7216, "step": 256690 }, { "epoch": 21.34, "learning_rate": 1.1565557187595266e-06, "loss": 0.7753, "step": 256700 }, { "epoch": 21.34, "learning_rate": 1.1564448632319926e-06, "loss": 0.8057, "step": 256710 }, { "epoch": 21.34, "learning_rate": 1.1563340077044592e-06, "loss": 0.7599, "step": 256720 }, { "epoch": 21.34, "learning_rate": 1.1562231521769254e-06, "loss": 0.7491, "step": 256730 }, { "epoch": 21.34, "learning_rate": 1.1561122966493917e-06, "loss": 0.7127, "step": 256740 }, { "epoch": 21.34, "learning_rate": 1.156001441121858e-06, "loss": 0.7732, "step": 256750 }, { "epoch": 21.34, "learning_rate": 1.1558905855943241e-06, "loss": 0.7347, "step": 256760 }, { "epoch": 21.34, "learning_rate": 1.1557797300667904e-06, "loss": 0.7194, "step": 256770 }, { "epoch": 21.34, "learning_rate": 1.1556688745392567e-06, "loss": 0.7956, "step": 256780 }, { "epoch": 21.34, "learning_rate": 1.1555580190117228e-06, "loss": 0.7519, "step": 256790 }, { "epoch": 21.34, "learning_rate": 1.155447163484189e-06, "loss": 0.6983, "step": 256800 }, { "epoch": 21.35, "learning_rate": 1.1553363079566554e-06, "loss": 0.761, "step": 256810 }, { "epoch": 21.35, "learning_rate": 1.1552254524291217e-06, "loss": 0.7001, "step": 256820 }, { "epoch": 21.35, "learning_rate": 1.1551145969015878e-06, "loss": 0.743, "step": 256830 }, { "epoch": 21.35, "learning_rate": 1.1550037413740543e-06, "loss": 0.6932, "step": 256840 }, { "epoch": 21.35, "learning_rate": 1.1548928858465206e-06, "loss": 0.778, "step": 256850 }, { "epoch": 21.35, "learning_rate": 1.1547820303189869e-06, "loss": 0.8032, "step": 256860 }, { "epoch": 21.35, "learning_rate": 1.154671174791453e-06, "loss": 0.7317, "step": 256870 }, { "epoch": 21.35, "learning_rate": 1.1545603192639192e-06, "loss": 0.772, "step": 256880 }, { "epoch": 21.35, "learning_rate": 1.1544494637363855e-06, "loss": 0.7133, "step": 256890 }, { "epoch": 21.35, "learning_rate": 1.1543386082088518e-06, "loss": 0.7243, "step": 256900 }, { "epoch": 21.35, "learning_rate": 1.154227752681318e-06, "loss": 0.7639, "step": 256910 }, { "epoch": 21.35, "learning_rate": 1.1541168971537842e-06, "loss": 0.7279, "step": 256920 }, { "epoch": 21.36, "learning_rate": 1.1540060416262505e-06, "loss": 0.6905, "step": 256930 }, { "epoch": 21.36, "learning_rate": 1.1538951860987168e-06, "loss": 0.7324, "step": 256940 }, { "epoch": 21.36, "learning_rate": 1.1537843305711829e-06, "loss": 0.774, "step": 256950 }, { "epoch": 21.36, "learning_rate": 1.1536734750436492e-06, "loss": 0.7892, "step": 256960 }, { "epoch": 21.36, "learning_rate": 1.1535626195161157e-06, "loss": 0.7518, "step": 256970 }, { "epoch": 21.36, "learning_rate": 1.153451763988582e-06, "loss": 0.757, "step": 256980 }, { "epoch": 21.36, "learning_rate": 1.153340908461048e-06, "loss": 0.6744, "step": 256990 }, { "epoch": 21.36, "learning_rate": 1.1532411384862676e-06, "loss": 0.6929, "step": 257000 }, { "epoch": 21.36, "learning_rate": 1.153130282958734e-06, "loss": 0.8141, "step": 257010 }, { "epoch": 21.36, "learning_rate": 1.1530194274312002e-06, "loss": 0.7916, "step": 257020 }, { "epoch": 21.36, "learning_rate": 1.1529085719036665e-06, "loss": 0.8378, "step": 257030 }, { "epoch": 21.36, "learning_rate": 1.1527977163761326e-06, "loss": 0.7825, "step": 257040 }, { "epoch": 21.37, "learning_rate": 1.152686860848599e-06, "loss": 0.7304, "step": 257050 }, { "epoch": 21.37, "learning_rate": 1.1525760053210654e-06, "loss": 0.7532, "step": 257060 }, { "epoch": 21.37, "learning_rate": 1.1524651497935317e-06, "loss": 0.6964, "step": 257070 }, { "epoch": 21.37, "learning_rate": 1.1523542942659978e-06, "loss": 0.7755, "step": 257080 }, { "epoch": 21.37, "learning_rate": 1.152243438738464e-06, "loss": 0.6966, "step": 257090 }, { "epoch": 21.37, "learning_rate": 1.1521325832109303e-06, "loss": 0.7167, "step": 257100 }, { "epoch": 21.37, "learning_rate": 1.1520217276833966e-06, "loss": 0.8177, "step": 257110 }, { "epoch": 21.37, "learning_rate": 1.1519108721558627e-06, "loss": 0.705, "step": 257120 }, { "epoch": 21.37, "learning_rate": 1.151800016628329e-06, "loss": 0.7605, "step": 257130 }, { "epoch": 21.37, "learning_rate": 1.1516891611007953e-06, "loss": 0.7226, "step": 257140 }, { "epoch": 21.37, "learning_rate": 1.1515783055732616e-06, "loss": 0.7505, "step": 257150 }, { "epoch": 21.37, "learning_rate": 1.1514674500457277e-06, "loss": 0.8143, "step": 257160 }, { "epoch": 21.38, "learning_rate": 1.151356594518194e-06, "loss": 0.7182, "step": 257170 }, { "epoch": 21.38, "learning_rate": 1.1512457389906605e-06, "loss": 0.7289, "step": 257180 }, { "epoch": 21.38, "learning_rate": 1.1511348834631268e-06, "loss": 0.7499, "step": 257190 }, { "epoch": 21.38, "learning_rate": 1.1510240279355929e-06, "loss": 0.6856, "step": 257200 }, { "epoch": 21.38, "learning_rate": 1.1509131724080592e-06, "loss": 0.7983, "step": 257210 }, { "epoch": 21.38, "learning_rate": 1.1508023168805255e-06, "loss": 0.752, "step": 257220 }, { "epoch": 21.38, "learning_rate": 1.1506914613529918e-06, "loss": 0.779, "step": 257230 }, { "epoch": 21.38, "learning_rate": 1.1505806058254578e-06, "loss": 0.7036, "step": 257240 }, { "epoch": 21.38, "learning_rate": 1.1504697502979241e-06, "loss": 0.7874, "step": 257250 }, { "epoch": 21.38, "learning_rate": 1.1503588947703904e-06, "loss": 0.8109, "step": 257260 }, { "epoch": 21.38, "learning_rate": 1.1502480392428565e-06, "loss": 0.7656, "step": 257270 }, { "epoch": 21.38, "learning_rate": 1.1501371837153228e-06, "loss": 0.7863, "step": 257280 }, { "epoch": 21.39, "learning_rate": 1.1500263281877891e-06, "loss": 0.7867, "step": 257290 }, { "epoch": 21.39, "learning_rate": 1.1499154726602556e-06, "loss": 0.7473, "step": 257300 }, { "epoch": 21.39, "learning_rate": 1.149804617132722e-06, "loss": 0.7786, "step": 257310 }, { "epoch": 21.39, "learning_rate": 1.149693761605188e-06, "loss": 0.6766, "step": 257320 }, { "epoch": 21.39, "learning_rate": 1.1495829060776543e-06, "loss": 0.7507, "step": 257330 }, { "epoch": 21.39, "learning_rate": 1.1494720505501206e-06, "loss": 0.6971, "step": 257340 }, { "epoch": 21.39, "learning_rate": 1.1493611950225867e-06, "loss": 0.7255, "step": 257350 }, { "epoch": 21.39, "learning_rate": 1.149250339495053e-06, "loss": 0.7494, "step": 257360 }, { "epoch": 21.39, "learning_rate": 1.1491394839675193e-06, "loss": 0.7172, "step": 257370 }, { "epoch": 21.39, "learning_rate": 1.1490286284399856e-06, "loss": 0.772, "step": 257380 }, { "epoch": 21.39, "learning_rate": 1.1489177729124516e-06, "loss": 0.7718, "step": 257390 }, { "epoch": 21.39, "learning_rate": 1.148806917384918e-06, "loss": 0.7312, "step": 257400 }, { "epoch": 21.4, "learning_rate": 1.1486960618573842e-06, "loss": 0.7612, "step": 257410 }, { "epoch": 21.4, "learning_rate": 1.1485852063298507e-06, "loss": 0.7429, "step": 257420 }, { "epoch": 21.4, "learning_rate": 1.1484743508023168e-06, "loss": 0.7746, "step": 257430 }, { "epoch": 21.4, "learning_rate": 1.1483634952747831e-06, "loss": 0.7082, "step": 257440 }, { "epoch": 21.4, "learning_rate": 1.1482526397472494e-06, "loss": 0.7304, "step": 257450 }, { "epoch": 21.4, "learning_rate": 1.1481417842197157e-06, "loss": 0.7836, "step": 257460 }, { "epoch": 21.4, "learning_rate": 1.1480309286921818e-06, "loss": 0.7787, "step": 257470 }, { "epoch": 21.4, "learning_rate": 1.147920073164648e-06, "loss": 0.7816, "step": 257480 }, { "epoch": 21.4, "learning_rate": 1.1478092176371144e-06, "loss": 0.7371, "step": 257490 }, { "epoch": 21.4, "learning_rate": 1.1476983621095807e-06, "loss": 0.7413, "step": 257500 }, { "epoch": 21.4, "learning_rate": 1.1475875065820468e-06, "loss": 0.7858, "step": 257510 }, { "epoch": 21.4, "learning_rate": 1.147476651054513e-06, "loss": 0.7324, "step": 257520 }, { "epoch": 21.41, "learning_rate": 1.1473657955269794e-06, "loss": 0.7964, "step": 257530 }, { "epoch": 21.41, "learning_rate": 1.1472549399994459e-06, "loss": 0.7472, "step": 257540 }, { "epoch": 21.41, "learning_rate": 1.147144084471912e-06, "loss": 0.7666, "step": 257550 }, { "epoch": 21.41, "learning_rate": 1.1470332289443782e-06, "loss": 0.8335, "step": 257560 }, { "epoch": 21.41, "learning_rate": 1.1469223734168445e-06, "loss": 0.7652, "step": 257570 }, { "epoch": 21.41, "learning_rate": 1.1468115178893108e-06, "loss": 0.7179, "step": 257580 }, { "epoch": 21.41, "learning_rate": 1.146700662361777e-06, "loss": 0.728, "step": 257590 }, { "epoch": 21.41, "learning_rate": 1.1465898068342432e-06, "loss": 0.7182, "step": 257600 }, { "epoch": 21.41, "learning_rate": 1.1464789513067095e-06, "loss": 0.7748, "step": 257610 }, { "epoch": 21.41, "learning_rate": 1.1463680957791758e-06, "loss": 0.7442, "step": 257620 }, { "epoch": 21.41, "learning_rate": 1.1462572402516419e-06, "loss": 0.7539, "step": 257630 }, { "epoch": 21.41, "learning_rate": 1.1461463847241082e-06, "loss": 0.8084, "step": 257640 }, { "epoch": 21.42, "learning_rate": 1.1460355291965745e-06, "loss": 0.7713, "step": 257650 }, { "epoch": 21.42, "learning_rate": 1.1459246736690408e-06, "loss": 0.8026, "step": 257660 }, { "epoch": 21.42, "learning_rate": 1.145813818141507e-06, "loss": 0.7252, "step": 257670 }, { "epoch": 21.42, "learning_rate": 1.1457029626139734e-06, "loss": 0.732, "step": 257680 }, { "epoch": 21.42, "learning_rate": 1.1455921070864397e-06, "loss": 0.7138, "step": 257690 }, { "epoch": 21.42, "learning_rate": 1.145481251558906e-06, "loss": 0.8388, "step": 257700 }, { "epoch": 21.42, "learning_rate": 1.145370396031372e-06, "loss": 0.7824, "step": 257710 }, { "epoch": 21.42, "learning_rate": 1.1452595405038383e-06, "loss": 0.7309, "step": 257720 }, { "epoch": 21.42, "learning_rate": 1.1451486849763046e-06, "loss": 0.8023, "step": 257730 }, { "epoch": 21.42, "learning_rate": 1.1450378294487707e-06, "loss": 0.6928, "step": 257740 }, { "epoch": 21.42, "learning_rate": 1.144926973921237e-06, "loss": 0.7532, "step": 257750 }, { "epoch": 21.42, "learning_rate": 1.1448161183937033e-06, "loss": 0.7728, "step": 257760 }, { "epoch": 21.43, "learning_rate": 1.1447052628661696e-06, "loss": 0.7407, "step": 257770 }, { "epoch": 21.43, "learning_rate": 1.1445944073386357e-06, "loss": 0.6915, "step": 257780 }, { "epoch": 21.43, "learning_rate": 1.1444835518111022e-06, "loss": 0.8065, "step": 257790 }, { "epoch": 21.43, "learning_rate": 1.1443726962835685e-06, "loss": 0.7771, "step": 257800 }, { "epoch": 21.43, "learning_rate": 1.1442618407560348e-06, "loss": 0.767, "step": 257810 }, { "epoch": 21.43, "learning_rate": 1.1441509852285009e-06, "loss": 0.7475, "step": 257820 }, { "epoch": 21.43, "learning_rate": 1.1440401297009672e-06, "loss": 0.7272, "step": 257830 }, { "epoch": 21.43, "learning_rate": 1.1439292741734335e-06, "loss": 0.7255, "step": 257840 }, { "epoch": 21.43, "learning_rate": 1.1438184186458997e-06, "loss": 0.6939, "step": 257850 }, { "epoch": 21.43, "learning_rate": 1.1437075631183658e-06, "loss": 0.8033, "step": 257860 }, { "epoch": 21.43, "learning_rate": 1.1435967075908321e-06, "loss": 0.7946, "step": 257870 }, { "epoch": 21.43, "learning_rate": 1.1434858520632984e-06, "loss": 0.7224, "step": 257880 }, { "epoch": 21.44, "learning_rate": 1.1433749965357647e-06, "loss": 0.7079, "step": 257890 }, { "epoch": 21.44, "learning_rate": 1.1432641410082308e-06, "loss": 0.7074, "step": 257900 }, { "epoch": 21.44, "learning_rate": 1.1431532854806973e-06, "loss": 0.7208, "step": 257910 }, { "epoch": 21.44, "learning_rate": 1.1430424299531636e-06, "loss": 0.8155, "step": 257920 }, { "epoch": 21.44, "learning_rate": 1.14293157442563e-06, "loss": 0.758, "step": 257930 }, { "epoch": 21.44, "learning_rate": 1.142820718898096e-06, "loss": 0.7698, "step": 257940 }, { "epoch": 21.44, "learning_rate": 1.1427098633705623e-06, "loss": 0.7682, "step": 257950 }, { "epoch": 21.44, "learning_rate": 1.1425990078430286e-06, "loss": 0.7893, "step": 257960 }, { "epoch": 21.44, "learning_rate": 1.1424881523154949e-06, "loss": 0.7527, "step": 257970 }, { "epoch": 21.44, "learning_rate": 1.142377296787961e-06, "loss": 0.7854, "step": 257980 }, { "epoch": 21.44, "learning_rate": 1.1422664412604272e-06, "loss": 0.8067, "step": 257990 }, { "epoch": 21.44, "learning_rate": 1.1421555857328935e-06, "loss": 0.7054, "step": 258000 }, { "epoch": 21.45, "learning_rate": 1.1420447302053598e-06, "loss": 0.7982, "step": 258010 }, { "epoch": 21.45, "learning_rate": 1.141933874677826e-06, "loss": 0.7661, "step": 258020 }, { "epoch": 21.45, "learning_rate": 1.1418230191502922e-06, "loss": 0.7616, "step": 258030 }, { "epoch": 21.45, "learning_rate": 1.1417121636227587e-06, "loss": 0.7067, "step": 258040 }, { "epoch": 21.45, "learning_rate": 1.141601308095225e-06, "loss": 0.7342, "step": 258050 }, { "epoch": 21.45, "learning_rate": 1.141490452567691e-06, "loss": 0.7836, "step": 258060 }, { "epoch": 21.45, "learning_rate": 1.1413795970401574e-06, "loss": 0.7091, "step": 258070 }, { "epoch": 21.45, "learning_rate": 1.1412687415126237e-06, "loss": 0.7408, "step": 258080 }, { "epoch": 21.45, "learning_rate": 1.14115788598509e-06, "loss": 0.7321, "step": 258090 }, { "epoch": 21.45, "learning_rate": 1.141047030457556e-06, "loss": 0.8286, "step": 258100 }, { "epoch": 21.45, "learning_rate": 1.1409361749300224e-06, "loss": 0.7718, "step": 258110 }, { "epoch": 21.45, "learning_rate": 1.1408253194024887e-06, "loss": 0.7634, "step": 258120 }, { "epoch": 21.46, "learning_rate": 1.1407144638749547e-06, "loss": 0.7381, "step": 258130 }, { "epoch": 21.46, "learning_rate": 1.140603608347421e-06, "loss": 0.7336, "step": 258140 }, { "epoch": 21.46, "learning_rate": 1.1404927528198873e-06, "loss": 0.7609, "step": 258150 }, { "epoch": 21.46, "learning_rate": 1.1403818972923538e-06, "loss": 0.7582, "step": 258160 }, { "epoch": 21.46, "learning_rate": 1.14027104176482e-06, "loss": 0.7464, "step": 258170 }, { "epoch": 21.46, "learning_rate": 1.1401601862372862e-06, "loss": 0.7663, "step": 258180 }, { "epoch": 21.46, "learning_rate": 1.1400493307097525e-06, "loss": 0.6889, "step": 258190 }, { "epoch": 21.46, "learning_rate": 1.1399384751822188e-06, "loss": 0.8098, "step": 258200 }, { "epoch": 21.46, "learning_rate": 1.139827619654685e-06, "loss": 0.7759, "step": 258210 }, { "epoch": 21.46, "learning_rate": 1.1397167641271512e-06, "loss": 0.6907, "step": 258220 }, { "epoch": 21.46, "learning_rate": 1.1396059085996175e-06, "loss": 0.8201, "step": 258230 }, { "epoch": 21.46, "learning_rate": 1.1394950530720838e-06, "loss": 0.7347, "step": 258240 }, { "epoch": 21.47, "learning_rate": 1.1393841975445499e-06, "loss": 0.787, "step": 258250 }, { "epoch": 21.47, "learning_rate": 1.1392733420170162e-06, "loss": 0.7806, "step": 258260 }, { "epoch": 21.47, "learning_rate": 1.1391624864894825e-06, "loss": 0.7768, "step": 258270 }, { "epoch": 21.47, "learning_rate": 1.139051630961949e-06, "loss": 0.7135, "step": 258280 }, { "epoch": 21.47, "learning_rate": 1.138940775434415e-06, "loss": 0.7499, "step": 258290 }, { "epoch": 21.47, "learning_rate": 1.1388299199068813e-06, "loss": 0.7187, "step": 258300 }, { "epoch": 21.47, "learning_rate": 1.1387190643793476e-06, "loss": 0.7867, "step": 258310 }, { "epoch": 21.47, "learning_rate": 1.138608208851814e-06, "loss": 0.7656, "step": 258320 }, { "epoch": 21.47, "learning_rate": 1.13849735332428e-06, "loss": 0.7015, "step": 258330 }, { "epoch": 21.47, "learning_rate": 1.1383864977967463e-06, "loss": 0.7628, "step": 258340 }, { "epoch": 21.47, "learning_rate": 1.1382756422692126e-06, "loss": 0.6848, "step": 258350 }, { "epoch": 21.47, "learning_rate": 1.138164786741679e-06, "loss": 0.7532, "step": 258360 }, { "epoch": 21.48, "learning_rate": 1.138053931214145e-06, "loss": 0.7632, "step": 258370 }, { "epoch": 21.48, "learning_rate": 1.1379430756866113e-06, "loss": 0.733, "step": 258380 }, { "epoch": 21.48, "learning_rate": 1.1378322201590776e-06, "loss": 0.7235, "step": 258390 }, { "epoch": 21.48, "learning_rate": 1.1377213646315439e-06, "loss": 0.754, "step": 258400 }, { "epoch": 21.48, "learning_rate": 1.1376105091040102e-06, "loss": 0.7766, "step": 258410 }, { "epoch": 21.48, "learning_rate": 1.1374996535764765e-06, "loss": 0.8038, "step": 258420 }, { "epoch": 21.48, "learning_rate": 1.1373887980489428e-06, "loss": 0.7143, "step": 258430 }, { "epoch": 21.48, "learning_rate": 1.137277942521409e-06, "loss": 0.7712, "step": 258440 }, { "epoch": 21.48, "learning_rate": 1.1371670869938751e-06, "loss": 0.7684, "step": 258450 }, { "epoch": 21.48, "learning_rate": 1.1370562314663414e-06, "loss": 0.7862, "step": 258460 }, { "epoch": 21.48, "learning_rate": 1.1369453759388077e-06, "loss": 0.726, "step": 258470 }, { "epoch": 21.48, "learning_rate": 1.136834520411274e-06, "loss": 0.7234, "step": 258480 }, { "epoch": 21.49, "learning_rate": 1.1367236648837401e-06, "loss": 0.7033, "step": 258490 }, { "epoch": 21.49, "learning_rate": 1.1366128093562064e-06, "loss": 0.7278, "step": 258500 }, { "epoch": 21.49, "learning_rate": 1.1365019538286727e-06, "loss": 0.8083, "step": 258510 }, { "epoch": 21.49, "learning_rate": 1.1363910983011388e-06, "loss": 0.7294, "step": 258520 }, { "epoch": 21.49, "learning_rate": 1.1362802427736053e-06, "loss": 0.8146, "step": 258530 }, { "epoch": 21.49, "learning_rate": 1.1361693872460716e-06, "loss": 0.7178, "step": 258540 }, { "epoch": 21.49, "learning_rate": 1.1360585317185379e-06, "loss": 0.7048, "step": 258550 }, { "epoch": 21.49, "learning_rate": 1.135947676191004e-06, "loss": 0.7832, "step": 258560 }, { "epoch": 21.49, "learning_rate": 1.1358368206634703e-06, "loss": 0.6891, "step": 258570 }, { "epoch": 21.49, "learning_rate": 1.1357259651359366e-06, "loss": 0.731, "step": 258580 }, { "epoch": 21.49, "learning_rate": 1.1356151096084028e-06, "loss": 0.6859, "step": 258590 }, { "epoch": 21.49, "learning_rate": 1.135504254080869e-06, "loss": 0.7536, "step": 258600 }, { "epoch": 21.5, "learning_rate": 1.1353933985533352e-06, "loss": 0.7965, "step": 258610 }, { "epoch": 21.5, "learning_rate": 1.1352825430258015e-06, "loss": 0.6985, "step": 258620 }, { "epoch": 21.5, "learning_rate": 1.1351716874982678e-06, "loss": 0.7684, "step": 258630 }, { "epoch": 21.5, "learning_rate": 1.135060831970734e-06, "loss": 0.7074, "step": 258640 }, { "epoch": 21.5, "learning_rate": 1.1349499764432004e-06, "loss": 0.7146, "step": 258650 }, { "epoch": 21.5, "learning_rate": 1.1348391209156667e-06, "loss": 0.7674, "step": 258660 }, { "epoch": 21.5, "learning_rate": 1.134728265388133e-06, "loss": 0.7393, "step": 258670 }, { "epoch": 21.5, "learning_rate": 1.134617409860599e-06, "loss": 0.7063, "step": 258680 }, { "epoch": 21.5, "learning_rate": 1.1345065543330654e-06, "loss": 0.723, "step": 258690 }, { "epoch": 21.5, "learning_rate": 1.1343956988055317e-06, "loss": 0.7447, "step": 258700 }, { "epoch": 21.5, "learning_rate": 1.134284843277998e-06, "loss": 0.7338, "step": 258710 }, { "epoch": 21.5, "learning_rate": 1.134173987750464e-06, "loss": 0.7631, "step": 258720 }, { "epoch": 21.51, "learning_rate": 1.1340631322229303e-06, "loss": 0.7924, "step": 258730 }, { "epoch": 21.51, "learning_rate": 1.1339522766953966e-06, "loss": 0.6941, "step": 258740 }, { "epoch": 21.51, "learning_rate": 1.133841421167863e-06, "loss": 0.7496, "step": 258750 }, { "epoch": 21.51, "learning_rate": 1.133730565640329e-06, "loss": 0.7792, "step": 258760 }, { "epoch": 21.51, "learning_rate": 1.1336197101127955e-06, "loss": 0.7306, "step": 258770 }, { "epoch": 21.51, "learning_rate": 1.1335088545852618e-06, "loss": 0.7306, "step": 258780 }, { "epoch": 21.51, "learning_rate": 1.1333979990577281e-06, "loss": 0.7059, "step": 258790 }, { "epoch": 21.51, "learning_rate": 1.1332871435301942e-06, "loss": 0.7433, "step": 258800 }, { "epoch": 21.51, "learning_rate": 1.1331762880026605e-06, "loss": 0.8256, "step": 258810 }, { "epoch": 21.51, "learning_rate": 1.1330654324751268e-06, "loss": 0.7119, "step": 258820 }, { "epoch": 21.51, "learning_rate": 1.132954576947593e-06, "loss": 0.7117, "step": 258830 }, { "epoch": 21.51, "learning_rate": 1.1328437214200592e-06, "loss": 0.7399, "step": 258840 }, { "epoch": 21.52, "learning_rate": 1.1327328658925255e-06, "loss": 0.7891, "step": 258850 }, { "epoch": 21.52, "learning_rate": 1.1326220103649918e-06, "loss": 0.8288, "step": 258860 }, { "epoch": 21.52, "learning_rate": 1.132511154837458e-06, "loss": 0.7073, "step": 258870 }, { "epoch": 21.52, "learning_rate": 1.1324002993099241e-06, "loss": 0.7017, "step": 258880 }, { "epoch": 21.52, "learning_rate": 1.1322894437823904e-06, "loss": 0.7055, "step": 258890 }, { "epoch": 21.52, "learning_rate": 1.132178588254857e-06, "loss": 0.7424, "step": 258900 }, { "epoch": 21.52, "learning_rate": 1.1320677327273232e-06, "loss": 0.7753, "step": 258910 }, { "epoch": 21.52, "learning_rate": 1.1319568771997893e-06, "loss": 0.7127, "step": 258920 }, { "epoch": 21.52, "learning_rate": 1.1318460216722556e-06, "loss": 0.7161, "step": 258930 }, { "epoch": 21.52, "learning_rate": 1.131735166144722e-06, "loss": 0.7668, "step": 258940 }, { "epoch": 21.52, "learning_rate": 1.1316243106171882e-06, "loss": 0.7022, "step": 258950 }, { "epoch": 21.52, "learning_rate": 1.1315134550896543e-06, "loss": 0.8016, "step": 258960 }, { "epoch": 21.53, "learning_rate": 1.1314025995621206e-06, "loss": 0.7678, "step": 258970 }, { "epoch": 21.53, "learning_rate": 1.1312917440345869e-06, "loss": 0.7309, "step": 258980 }, { "epoch": 21.53, "learning_rate": 1.131180888507053e-06, "loss": 0.6999, "step": 258990 }, { "epoch": 21.53, "learning_rate": 1.1310700329795193e-06, "loss": 0.7104, "step": 259000 }, { "epoch": 21.53, "learning_rate": 1.1309591774519856e-06, "loss": 0.8373, "step": 259010 }, { "epoch": 21.53, "learning_rate": 1.130848321924452e-06, "loss": 0.752, "step": 259020 }, { "epoch": 21.53, "learning_rate": 1.1307374663969181e-06, "loss": 0.7472, "step": 259030 }, { "epoch": 21.53, "learning_rate": 1.1306266108693844e-06, "loss": 0.7748, "step": 259040 }, { "epoch": 21.53, "learning_rate": 1.1305157553418507e-06, "loss": 0.7105, "step": 259050 }, { "epoch": 21.53, "learning_rate": 1.130404899814317e-06, "loss": 0.8426, "step": 259060 }, { "epoch": 21.53, "learning_rate": 1.1302940442867831e-06, "loss": 0.7129, "step": 259070 }, { "epoch": 21.53, "learning_rate": 1.1301831887592494e-06, "loss": 0.7783, "step": 259080 }, { "epoch": 21.54, "learning_rate": 1.1300723332317157e-06, "loss": 0.7094, "step": 259090 }, { "epoch": 21.54, "learning_rate": 1.129961477704182e-06, "loss": 0.72, "step": 259100 }, { "epoch": 21.54, "learning_rate": 1.129850622176648e-06, "loss": 0.7722, "step": 259110 }, { "epoch": 21.54, "learning_rate": 1.1297397666491144e-06, "loss": 0.7536, "step": 259120 }, { "epoch": 21.54, "learning_rate": 1.1296289111215807e-06, "loss": 0.7335, "step": 259130 }, { "epoch": 21.54, "learning_rate": 1.1295180555940472e-06, "loss": 0.698, "step": 259140 }, { "epoch": 21.54, "learning_rate": 1.1294072000665133e-06, "loss": 0.726, "step": 259150 }, { "epoch": 21.54, "learning_rate": 1.1292963445389796e-06, "loss": 0.7529, "step": 259160 }, { "epoch": 21.54, "learning_rate": 1.1291854890114459e-06, "loss": 0.7796, "step": 259170 }, { "epoch": 21.54, "learning_rate": 1.1290746334839122e-06, "loss": 0.7784, "step": 259180 }, { "epoch": 21.54, "learning_rate": 1.1289637779563782e-06, "loss": 0.7461, "step": 259190 }, { "epoch": 21.54, "learning_rate": 1.1288529224288445e-06, "loss": 0.7351, "step": 259200 }, { "epoch": 21.55, "learning_rate": 1.1287420669013108e-06, "loss": 0.8018, "step": 259210 }, { "epoch": 21.55, "learning_rate": 1.1286312113737771e-06, "loss": 0.7269, "step": 259220 }, { "epoch": 21.55, "learning_rate": 1.1285203558462432e-06, "loss": 0.7676, "step": 259230 }, { "epoch": 21.55, "learning_rate": 1.1284095003187095e-06, "loss": 0.7732, "step": 259240 }, { "epoch": 21.55, "learning_rate": 1.1282986447911758e-06, "loss": 0.7781, "step": 259250 }, { "epoch": 21.55, "learning_rate": 1.128187789263642e-06, "loss": 0.7457, "step": 259260 }, { "epoch": 21.55, "learning_rate": 1.1280769337361084e-06, "loss": 0.7204, "step": 259270 }, { "epoch": 21.55, "learning_rate": 1.1279660782085747e-06, "loss": 0.7522, "step": 259280 }, { "epoch": 21.55, "learning_rate": 1.127855222681041e-06, "loss": 0.7348, "step": 259290 }, { "epoch": 21.55, "learning_rate": 1.1277443671535073e-06, "loss": 0.7655, "step": 259300 }, { "epoch": 21.55, "learning_rate": 1.1276335116259734e-06, "loss": 0.776, "step": 259310 }, { "epoch": 21.55, "learning_rate": 1.1275226560984397e-06, "loss": 0.7297, "step": 259320 }, { "epoch": 21.56, "learning_rate": 1.127411800570906e-06, "loss": 0.7005, "step": 259330 }, { "epoch": 21.56, "learning_rate": 1.1273009450433722e-06, "loss": 0.7056, "step": 259340 }, { "epoch": 21.56, "learning_rate": 1.1271900895158383e-06, "loss": 0.7649, "step": 259350 }, { "epoch": 21.56, "learning_rate": 1.1270792339883046e-06, "loss": 0.7824, "step": 259360 }, { "epoch": 21.56, "learning_rate": 1.126968378460771e-06, "loss": 0.776, "step": 259370 }, { "epoch": 21.56, "learning_rate": 1.126857522933237e-06, "loss": 0.7837, "step": 259380 }, { "epoch": 21.56, "learning_rate": 1.1267466674057035e-06, "loss": 0.7154, "step": 259390 }, { "epoch": 21.56, "learning_rate": 1.1266358118781698e-06, "loss": 0.7343, "step": 259400 }, { "epoch": 21.56, "learning_rate": 1.126524956350636e-06, "loss": 0.7749, "step": 259410 }, { "epoch": 21.56, "learning_rate": 1.1264141008231022e-06, "loss": 0.7337, "step": 259420 }, { "epoch": 21.56, "learning_rate": 1.1263032452955685e-06, "loss": 0.8096, "step": 259430 }, { "epoch": 21.56, "learning_rate": 1.1261923897680348e-06, "loss": 0.7295, "step": 259440 }, { "epoch": 21.57, "learning_rate": 1.1260926197932543e-06, "loss": 0.7789, "step": 259450 }, { "epoch": 21.57, "learning_rate": 1.1259817642657206e-06, "loss": 0.7615, "step": 259460 }, { "epoch": 21.57, "learning_rate": 1.1258709087381867e-06, "loss": 0.7309, "step": 259470 }, { "epoch": 21.57, "learning_rate": 1.1257600532106532e-06, "loss": 0.6861, "step": 259480 }, { "epoch": 21.57, "learning_rate": 1.1256491976831195e-06, "loss": 0.7465, "step": 259490 }, { "epoch": 21.57, "learning_rate": 1.1255383421555858e-06, "loss": 0.7566, "step": 259500 }, { "epoch": 21.57, "learning_rate": 1.125427486628052e-06, "loss": 0.7832, "step": 259510 }, { "epoch": 21.57, "learning_rate": 1.1253166311005182e-06, "loss": 0.781, "step": 259520 }, { "epoch": 21.57, "learning_rate": 1.1252057755729845e-06, "loss": 0.7172, "step": 259530 }, { "epoch": 21.57, "learning_rate": 1.1250949200454508e-06, "loss": 0.7336, "step": 259540 }, { "epoch": 21.57, "learning_rate": 1.1249840645179168e-06, "loss": 0.7343, "step": 259550 }, { "epoch": 21.57, "learning_rate": 1.1248732089903831e-06, "loss": 0.7925, "step": 259560 }, { "epoch": 21.58, "learning_rate": 1.1247623534628494e-06, "loss": 0.7077, "step": 259570 }, { "epoch": 21.58, "learning_rate": 1.1246514979353157e-06, "loss": 0.7012, "step": 259580 }, { "epoch": 21.58, "learning_rate": 1.1245406424077818e-06, "loss": 0.7759, "step": 259590 }, { "epoch": 21.58, "learning_rate": 1.1244297868802483e-06, "loss": 0.7237, "step": 259600 }, { "epoch": 21.58, "learning_rate": 1.1243189313527146e-06, "loss": 0.7681, "step": 259610 }, { "epoch": 21.58, "learning_rate": 1.124208075825181e-06, "loss": 0.7627, "step": 259620 }, { "epoch": 21.58, "learning_rate": 1.124097220297647e-06, "loss": 0.753, "step": 259630 }, { "epoch": 21.58, "learning_rate": 1.1239863647701133e-06, "loss": 0.7349, "step": 259640 }, { "epoch": 21.58, "learning_rate": 1.1238755092425796e-06, "loss": 0.7891, "step": 259650 }, { "epoch": 21.58, "learning_rate": 1.1237646537150459e-06, "loss": 0.737, "step": 259660 }, { "epoch": 21.58, "learning_rate": 1.123653798187512e-06, "loss": 0.7917, "step": 259670 }, { "epoch": 21.58, "learning_rate": 1.1235429426599783e-06, "loss": 0.7358, "step": 259680 }, { "epoch": 21.59, "learning_rate": 1.1234320871324446e-06, "loss": 0.7099, "step": 259690 }, { "epoch": 21.59, "learning_rate": 1.1233212316049109e-06, "loss": 0.6665, "step": 259700 }, { "epoch": 21.59, "learning_rate": 1.123210376077377e-06, "loss": 0.7986, "step": 259710 }, { "epoch": 21.59, "learning_rate": 1.1230995205498434e-06, "loss": 0.7618, "step": 259720 }, { "epoch": 21.59, "learning_rate": 1.1229886650223097e-06, "loss": 0.7495, "step": 259730 }, { "epoch": 21.59, "learning_rate": 1.122877809494776e-06, "loss": 0.7297, "step": 259740 }, { "epoch": 21.59, "learning_rate": 1.1227669539672421e-06, "loss": 0.7305, "step": 259750 }, { "epoch": 21.59, "learning_rate": 1.1226560984397084e-06, "loss": 0.7863, "step": 259760 }, { "epoch": 21.59, "learning_rate": 1.1225452429121747e-06, "loss": 0.8313, "step": 259770 }, { "epoch": 21.59, "learning_rate": 1.122434387384641e-06, "loss": 0.7461, "step": 259780 }, { "epoch": 21.59, "learning_rate": 1.122323531857107e-06, "loss": 0.7238, "step": 259790 }, { "epoch": 21.59, "learning_rate": 1.1222126763295734e-06, "loss": 0.7462, "step": 259800 }, { "epoch": 21.6, "learning_rate": 1.1221018208020397e-06, "loss": 0.8016, "step": 259810 }, { "epoch": 21.6, "learning_rate": 1.121990965274506e-06, "loss": 0.8063, "step": 259820 }, { "epoch": 21.6, "learning_rate": 1.121880109746972e-06, "loss": 0.7609, "step": 259830 }, { "epoch": 21.6, "learning_rate": 1.1217692542194386e-06, "loss": 0.6923, "step": 259840 }, { "epoch": 21.6, "learning_rate": 1.1216583986919049e-06, "loss": 0.734, "step": 259850 }, { "epoch": 21.6, "learning_rate": 1.1215475431643712e-06, "loss": 0.832, "step": 259860 }, { "epoch": 21.6, "learning_rate": 1.1214366876368372e-06, "loss": 0.7373, "step": 259870 }, { "epoch": 21.6, "learning_rate": 1.1213258321093035e-06, "loss": 0.7053, "step": 259880 }, { "epoch": 21.6, "learning_rate": 1.1212149765817698e-06, "loss": 0.7281, "step": 259890 }, { "epoch": 21.6, "learning_rate": 1.1211041210542361e-06, "loss": 0.7214, "step": 259900 }, { "epoch": 21.6, "learning_rate": 1.1209932655267022e-06, "loss": 0.8481, "step": 259910 }, { "epoch": 21.6, "learning_rate": 1.1208824099991685e-06, "loss": 0.7812, "step": 259920 }, { "epoch": 21.61, "learning_rate": 1.1207715544716348e-06, "loss": 0.7229, "step": 259930 }, { "epoch": 21.61, "learning_rate": 1.1206606989441009e-06, "loss": 0.7399, "step": 259940 }, { "epoch": 21.61, "learning_rate": 1.1205498434165672e-06, "loss": 0.7076, "step": 259950 }, { "epoch": 21.61, "learning_rate": 1.1204389878890335e-06, "loss": 0.7561, "step": 259960 }, { "epoch": 21.61, "learning_rate": 1.1203281323615e-06, "loss": 0.6786, "step": 259970 }, { "epoch": 21.61, "learning_rate": 1.120217276833966e-06, "loss": 0.7363, "step": 259980 }, { "epoch": 21.61, "learning_rate": 1.1201064213064324e-06, "loss": 0.7496, "step": 259990 }, { "epoch": 21.61, "learning_rate": 1.1199955657788987e-06, "loss": 0.7547, "step": 260000 }, { "epoch": 21.61, "learning_rate": 1.119884710251365e-06, "loss": 0.7434, "step": 260010 }, { "epoch": 21.61, "learning_rate": 1.119773854723831e-06, "loss": 0.7367, "step": 260020 }, { "epoch": 21.61, "learning_rate": 1.1196629991962973e-06, "loss": 0.7054, "step": 260030 }, { "epoch": 21.61, "learning_rate": 1.1195521436687636e-06, "loss": 0.7534, "step": 260040 }, { "epoch": 21.61, "learning_rate": 1.11944128814123e-06, "loss": 0.7653, "step": 260050 }, { "epoch": 21.62, "learning_rate": 1.119330432613696e-06, "loss": 0.7566, "step": 260060 }, { "epoch": 21.62, "learning_rate": 1.1192195770861623e-06, "loss": 0.7795, "step": 260070 }, { "epoch": 21.62, "learning_rate": 1.1191087215586286e-06, "loss": 0.738, "step": 260080 }, { "epoch": 21.62, "learning_rate": 1.118997866031095e-06, "loss": 0.7215, "step": 260090 }, { "epoch": 21.62, "learning_rate": 1.1188870105035612e-06, "loss": 0.7066, "step": 260100 }, { "epoch": 21.62, "learning_rate": 1.1187761549760275e-06, "loss": 0.8165, "step": 260110 }, { "epoch": 21.62, "learning_rate": 1.1186652994484938e-06, "loss": 0.7948, "step": 260120 }, { "epoch": 21.62, "learning_rate": 1.11855444392096e-06, "loss": 0.7146, "step": 260130 }, { "epoch": 21.62, "learning_rate": 1.1184435883934262e-06, "loss": 0.7751, "step": 260140 }, { "epoch": 21.62, "learning_rate": 1.1183327328658924e-06, "loss": 0.775, "step": 260150 }, { "epoch": 21.62, "learning_rate": 1.1182218773383587e-06, "loss": 0.7691, "step": 260160 }, { "epoch": 21.62, "learning_rate": 1.118111021810825e-06, "loss": 0.7927, "step": 260170 }, { "epoch": 21.63, "learning_rate": 1.1180001662832911e-06, "loss": 0.7546, "step": 260180 }, { "epoch": 21.63, "learning_rate": 1.1178893107557574e-06, "loss": 0.7118, "step": 260190 }, { "epoch": 21.63, "learning_rate": 1.1177784552282237e-06, "loss": 0.7433, "step": 260200 }, { "epoch": 21.63, "learning_rate": 1.1176675997006902e-06, "loss": 0.7928, "step": 260210 }, { "epoch": 21.63, "learning_rate": 1.1175567441731563e-06, "loss": 0.764, "step": 260220 }, { "epoch": 21.63, "learning_rate": 1.1174458886456226e-06, "loss": 0.7565, "step": 260230 }, { "epoch": 21.63, "learning_rate": 1.1173350331180889e-06, "loss": 0.7461, "step": 260240 }, { "epoch": 21.63, "learning_rate": 1.1172241775905552e-06, "loss": 0.7297, "step": 260250 }, { "epoch": 21.63, "learning_rate": 1.1171133220630213e-06, "loss": 0.7681, "step": 260260 }, { "epoch": 21.63, "learning_rate": 1.1170024665354876e-06, "loss": 0.775, "step": 260270 }, { "epoch": 21.63, "learning_rate": 1.1168916110079539e-06, "loss": 0.727, "step": 260280 }, { "epoch": 21.63, "learning_rate": 1.1167807554804202e-06, "loss": 0.7083, "step": 260290 }, { "epoch": 21.64, "learning_rate": 1.1166698999528862e-06, "loss": 0.7583, "step": 260300 }, { "epoch": 21.64, "learning_rate": 1.1165590444253525e-06, "loss": 0.7938, "step": 260310 }, { "epoch": 21.64, "learning_rate": 1.1164481888978188e-06, "loss": 0.7346, "step": 260320 }, { "epoch": 21.64, "learning_rate": 1.116337333370285e-06, "loss": 0.7052, "step": 260330 }, { "epoch": 21.64, "learning_rate": 1.1162264778427514e-06, "loss": 0.7839, "step": 260340 }, { "epoch": 21.64, "learning_rate": 1.1161156223152177e-06, "loss": 0.7559, "step": 260350 }, { "epoch": 21.64, "learning_rate": 1.116004766787684e-06, "loss": 0.7865, "step": 260360 }, { "epoch": 21.64, "learning_rate": 1.11589391126015e-06, "loss": 0.753, "step": 260370 }, { "epoch": 21.64, "learning_rate": 1.1157830557326164e-06, "loss": 0.7602, "step": 260380 }, { "epoch": 21.64, "learning_rate": 1.1156722002050827e-06, "loss": 0.7713, "step": 260390 }, { "epoch": 21.64, "learning_rate": 1.115561344677549e-06, "loss": 0.7315, "step": 260400 }, { "epoch": 21.64, "learning_rate": 1.115450489150015e-06, "loss": 0.705, "step": 260410 }, { "epoch": 21.65, "learning_rate": 1.1153396336224814e-06, "loss": 0.7075, "step": 260420 }, { "epoch": 21.65, "learning_rate": 1.1152287780949477e-06, "loss": 0.7409, "step": 260430 }, { "epoch": 21.65, "learning_rate": 1.115117922567414e-06, "loss": 0.7098, "step": 260440 }, { "epoch": 21.65, "learning_rate": 1.11500706703988e-06, "loss": 0.6863, "step": 260450 }, { "epoch": 21.65, "learning_rate": 1.1148962115123465e-06, "loss": 0.7588, "step": 260460 }, { "epoch": 21.65, "learning_rate": 1.1147853559848128e-06, "loss": 0.7228, "step": 260470 }, { "epoch": 21.65, "learning_rate": 1.1146745004572791e-06, "loss": 0.7297, "step": 260480 }, { "epoch": 21.65, "learning_rate": 1.1145636449297452e-06, "loss": 0.7961, "step": 260490 }, { "epoch": 21.65, "learning_rate": 1.1144527894022115e-06, "loss": 0.7964, "step": 260500 }, { "epoch": 21.65, "learning_rate": 1.1143419338746778e-06, "loss": 0.778, "step": 260510 }, { "epoch": 21.65, "learning_rate": 1.114231078347144e-06, "loss": 0.735, "step": 260520 }, { "epoch": 21.65, "learning_rate": 1.1141202228196102e-06, "loss": 0.7619, "step": 260530 }, { "epoch": 21.66, "learning_rate": 1.1140093672920765e-06, "loss": 0.6888, "step": 260540 }, { "epoch": 21.66, "learning_rate": 1.1138985117645428e-06, "loss": 0.7654, "step": 260550 }, { "epoch": 21.66, "learning_rate": 1.113787656237009e-06, "loss": 0.824, "step": 260560 }, { "epoch": 21.66, "learning_rate": 1.1136768007094752e-06, "loss": 0.7658, "step": 260570 }, { "epoch": 21.66, "learning_rate": 1.1135659451819417e-06, "loss": 0.814, "step": 260580 }, { "epoch": 21.66, "learning_rate": 1.113455089654408e-06, "loss": 0.7278, "step": 260590 }, { "epoch": 21.66, "learning_rate": 1.1133442341268743e-06, "loss": 0.7766, "step": 260600 }, { "epoch": 21.66, "learning_rate": 1.1132333785993403e-06, "loss": 0.8342, "step": 260610 }, { "epoch": 21.66, "learning_rate": 1.1131225230718066e-06, "loss": 0.7574, "step": 260620 }, { "epoch": 21.66, "learning_rate": 1.113011667544273e-06, "loss": 0.7424, "step": 260630 }, { "epoch": 21.66, "learning_rate": 1.1129008120167392e-06, "loss": 0.7415, "step": 260640 }, { "epoch": 21.66, "learning_rate": 1.1127899564892053e-06, "loss": 0.7981, "step": 260650 }, { "epoch": 21.67, "learning_rate": 1.1126791009616716e-06, "loss": 0.8094, "step": 260660 }, { "epoch": 21.67, "learning_rate": 1.112568245434138e-06, "loss": 0.7485, "step": 260670 }, { "epoch": 21.67, "learning_rate": 1.1124573899066042e-06, "loss": 0.7747, "step": 260680 }, { "epoch": 21.67, "learning_rate": 1.1123465343790703e-06, "loss": 0.7435, "step": 260690 }, { "epoch": 21.67, "learning_rate": 1.1122356788515366e-06, "loss": 0.7125, "step": 260700 }, { "epoch": 21.67, "learning_rate": 1.112124823324003e-06, "loss": 0.7937, "step": 260710 }, { "epoch": 21.67, "learning_rate": 1.1120139677964694e-06, "loss": 0.7852, "step": 260720 }, { "epoch": 21.67, "learning_rate": 1.1119031122689355e-06, "loss": 0.7422, "step": 260730 }, { "epoch": 21.67, "learning_rate": 1.1117922567414018e-06, "loss": 0.7045, "step": 260740 }, { "epoch": 21.67, "learning_rate": 1.111681401213868e-06, "loss": 0.7647, "step": 260750 }, { "epoch": 21.67, "learning_rate": 1.1115705456863341e-06, "loss": 0.7519, "step": 260760 }, { "epoch": 21.67, "learning_rate": 1.1114596901588004e-06, "loss": 0.7512, "step": 260770 }, { "epoch": 21.68, "learning_rate": 1.1113488346312667e-06, "loss": 0.7088, "step": 260780 }, { "epoch": 21.68, "learning_rate": 1.111237979103733e-06, "loss": 0.7958, "step": 260790 }, { "epoch": 21.68, "learning_rate": 1.111127123576199e-06, "loss": 0.7078, "step": 260800 }, { "epoch": 21.68, "learning_rate": 1.1110162680486654e-06, "loss": 0.7687, "step": 260810 }, { "epoch": 21.68, "learning_rate": 1.1109054125211317e-06, "loss": 0.7631, "step": 260820 }, { "epoch": 21.68, "learning_rate": 1.1107945569935982e-06, "loss": 0.7699, "step": 260830 }, { "epoch": 21.68, "learning_rate": 1.1106837014660643e-06, "loss": 0.7959, "step": 260840 }, { "epoch": 21.68, "learning_rate": 1.1105728459385306e-06, "loss": 0.7552, "step": 260850 }, { "epoch": 21.68, "learning_rate": 1.1104619904109969e-06, "loss": 0.7538, "step": 260860 }, { "epoch": 21.68, "learning_rate": 1.1103511348834632e-06, "loss": 0.738, "step": 260870 }, { "epoch": 21.68, "learning_rate": 1.1102402793559293e-06, "loss": 0.681, "step": 260880 }, { "epoch": 21.68, "learning_rate": 1.1101294238283955e-06, "loss": 0.6994, "step": 260890 }, { "epoch": 21.69, "learning_rate": 1.1100185683008618e-06, "loss": 0.7792, "step": 260900 }, { "epoch": 21.69, "learning_rate": 1.1099077127733281e-06, "loss": 0.8226, "step": 260910 }, { "epoch": 21.69, "learning_rate": 1.1097968572457942e-06, "loss": 0.7306, "step": 260920 }, { "epoch": 21.69, "learning_rate": 1.1096860017182605e-06, "loss": 0.7855, "step": 260930 }, { "epoch": 21.69, "learning_rate": 1.1095751461907268e-06, "loss": 0.7682, "step": 260940 }, { "epoch": 21.69, "learning_rate": 1.1094642906631933e-06, "loss": 0.7245, "step": 260950 }, { "epoch": 21.69, "learning_rate": 1.1093534351356594e-06, "loss": 0.7861, "step": 260960 }, { "epoch": 21.69, "learning_rate": 1.1092425796081257e-06, "loss": 0.73, "step": 260970 }, { "epoch": 21.69, "learning_rate": 1.109131724080592e-06, "loss": 0.7637, "step": 260980 }, { "epoch": 21.69, "learning_rate": 1.1090208685530583e-06, "loss": 0.7382, "step": 260990 }, { "epoch": 21.69, "learning_rate": 1.1089100130255244e-06, "loss": 0.7199, "step": 261000 }, { "epoch": 21.69, "learning_rate": 1.1087991574979907e-06, "loss": 0.7273, "step": 261010 }, { "epoch": 21.7, "learning_rate": 1.108688301970457e-06, "loss": 0.7734, "step": 261020 }, { "epoch": 21.7, "learning_rate": 1.1085774464429233e-06, "loss": 0.7385, "step": 261030 }, { "epoch": 21.7, "learning_rate": 1.1084665909153893e-06, "loss": 0.7766, "step": 261040 }, { "epoch": 21.7, "learning_rate": 1.1083557353878556e-06, "loss": 0.7115, "step": 261050 }, { "epoch": 21.7, "learning_rate": 1.108244879860322e-06, "loss": 0.7541, "step": 261060 }, { "epoch": 21.7, "learning_rate": 1.1081340243327884e-06, "loss": 0.7687, "step": 261070 }, { "epoch": 21.7, "learning_rate": 1.1080231688052545e-06, "loss": 0.8147, "step": 261080 }, { "epoch": 21.7, "learning_rate": 1.1079123132777208e-06, "loss": 0.7454, "step": 261090 }, { "epoch": 21.7, "learning_rate": 1.1078014577501871e-06, "loss": 0.6961, "step": 261100 }, { "epoch": 21.7, "learning_rate": 1.1076906022226534e-06, "loss": 0.8068, "step": 261110 }, { "epoch": 21.7, "learning_rate": 1.1075797466951195e-06, "loss": 0.7412, "step": 261120 }, { "epoch": 21.7, "learning_rate": 1.1074688911675858e-06, "loss": 0.7691, "step": 261130 }, { "epoch": 21.71, "learning_rate": 1.107358035640052e-06, "loss": 0.6625, "step": 261140 }, { "epoch": 21.71, "learning_rate": 1.1072471801125184e-06, "loss": 0.7416, "step": 261150 }, { "epoch": 21.71, "learning_rate": 1.1071363245849845e-06, "loss": 0.7997, "step": 261160 }, { "epoch": 21.71, "learning_rate": 1.1070254690574508e-06, "loss": 0.7501, "step": 261170 }, { "epoch": 21.71, "learning_rate": 1.106914613529917e-06, "loss": 0.796, "step": 261180 }, { "epoch": 21.71, "learning_rate": 1.1068037580023831e-06, "loss": 0.7208, "step": 261190 }, { "epoch": 21.71, "learning_rate": 1.1066929024748496e-06, "loss": 0.7611, "step": 261200 }, { "epoch": 21.71, "learning_rate": 1.106582046947316e-06, "loss": 0.7978, "step": 261210 }, { "epoch": 21.71, "learning_rate": 1.1064711914197822e-06, "loss": 0.7199, "step": 261220 }, { "epoch": 21.71, "learning_rate": 1.1063603358922483e-06, "loss": 0.6918, "step": 261230 }, { "epoch": 21.71, "learning_rate": 1.1062494803647146e-06, "loss": 0.728, "step": 261240 }, { "epoch": 21.71, "learning_rate": 1.106138624837181e-06, "loss": 0.7147, "step": 261250 }, { "epoch": 21.72, "learning_rate": 1.1060277693096472e-06, "loss": 0.7755, "step": 261260 }, { "epoch": 21.72, "learning_rate": 1.1059169137821133e-06, "loss": 0.7953, "step": 261270 }, { "epoch": 21.72, "learning_rate": 1.1058060582545796e-06, "loss": 0.6717, "step": 261280 }, { "epoch": 21.72, "learning_rate": 1.1056952027270459e-06, "loss": 0.7561, "step": 261290 }, { "epoch": 21.72, "learning_rate": 1.1055843471995122e-06, "loss": 0.7527, "step": 261300 }, { "epoch": 21.72, "learning_rate": 1.1054734916719783e-06, "loss": 0.7149, "step": 261310 }, { "epoch": 21.72, "learning_rate": 1.1053626361444448e-06, "loss": 0.7347, "step": 261320 }, { "epoch": 21.72, "learning_rate": 1.105251780616911e-06, "loss": 0.7497, "step": 261330 }, { "epoch": 21.72, "learning_rate": 1.1051409250893774e-06, "loss": 0.7546, "step": 261340 }, { "epoch": 21.72, "learning_rate": 1.1050300695618434e-06, "loss": 0.7222, "step": 261350 }, { "epoch": 21.72, "learning_rate": 1.1049192140343097e-06, "loss": 0.8173, "step": 261360 }, { "epoch": 21.72, "learning_rate": 1.104808358506776e-06, "loss": 0.7748, "step": 261370 }, { "epoch": 21.73, "learning_rate": 1.1046975029792423e-06, "loss": 0.7387, "step": 261380 }, { "epoch": 21.73, "learning_rate": 1.1045866474517084e-06, "loss": 0.7669, "step": 261390 }, { "epoch": 21.73, "learning_rate": 1.1044757919241747e-06, "loss": 0.7268, "step": 261400 }, { "epoch": 21.73, "learning_rate": 1.104364936396641e-06, "loss": 0.8173, "step": 261410 }, { "epoch": 21.73, "learning_rate": 1.1042540808691073e-06, "loss": 0.76, "step": 261420 }, { "epoch": 21.73, "learning_rate": 1.1041432253415734e-06, "loss": 0.7236, "step": 261430 }, { "epoch": 21.73, "learning_rate": 1.1040323698140399e-06, "loss": 0.7723, "step": 261440 }, { "epoch": 21.73, "learning_rate": 1.1039215142865062e-06, "loss": 0.7487, "step": 261450 }, { "epoch": 21.73, "learning_rate": 1.1038106587589725e-06, "loss": 0.7937, "step": 261460 }, { "epoch": 21.73, "learning_rate": 1.1036998032314386e-06, "loss": 0.7641, "step": 261470 }, { "epoch": 21.73, "learning_rate": 1.1035889477039049e-06, "loss": 0.7829, "step": 261480 }, { "epoch": 21.73, "learning_rate": 1.1034780921763712e-06, "loss": 0.752, "step": 261490 }, { "epoch": 21.74, "learning_rate": 1.1033672366488374e-06, "loss": 0.7614, "step": 261500 }, { "epoch": 21.74, "learning_rate": 1.1032563811213035e-06, "loss": 0.7887, "step": 261510 }, { "epoch": 21.74, "learning_rate": 1.1031455255937698e-06, "loss": 0.764, "step": 261520 }, { "epoch": 21.74, "learning_rate": 1.1030346700662361e-06, "loss": 0.7615, "step": 261530 }, { "epoch": 21.74, "learning_rate": 1.1029238145387024e-06, "loss": 0.7471, "step": 261540 }, { "epoch": 21.74, "learning_rate": 1.1028129590111685e-06, "loss": 0.7121, "step": 261550 }, { "epoch": 21.74, "learning_rate": 1.1027021034836348e-06, "loss": 0.7741, "step": 261560 }, { "epoch": 21.74, "learning_rate": 1.1026023335088545e-06, "loss": 0.7804, "step": 261570 }, { "epoch": 21.74, "learning_rate": 1.1024914779813208e-06, "loss": 0.7741, "step": 261580 }, { "epoch": 21.74, "learning_rate": 1.1023806224537871e-06, "loss": 0.7587, "step": 261590 }, { "epoch": 21.74, "learning_rate": 1.1022697669262532e-06, "loss": 0.8201, "step": 261600 }, { "epoch": 21.74, "learning_rate": 1.1021589113987195e-06, "loss": 0.7248, "step": 261610 }, { "epoch": 21.75, "learning_rate": 1.1020480558711858e-06, "loss": 0.8184, "step": 261620 }, { "epoch": 21.75, "learning_rate": 1.1019372003436521e-06, "loss": 0.7304, "step": 261630 }, { "epoch": 21.75, "learning_rate": 1.1018263448161182e-06, "loss": 0.7579, "step": 261640 }, { "epoch": 21.75, "learning_rate": 1.1017154892885847e-06, "loss": 0.7288, "step": 261650 }, { "epoch": 21.75, "learning_rate": 1.101604633761051e-06, "loss": 0.764, "step": 261660 }, { "epoch": 21.75, "learning_rate": 1.1014937782335173e-06, "loss": 0.7429, "step": 261670 }, { "epoch": 21.75, "learning_rate": 1.1013829227059834e-06, "loss": 0.7285, "step": 261680 }, { "epoch": 21.75, "learning_rate": 1.1012720671784497e-06, "loss": 0.6968, "step": 261690 }, { "epoch": 21.75, "learning_rate": 1.101161211650916e-06, "loss": 0.7481, "step": 261700 }, { "epoch": 21.75, "learning_rate": 1.1010503561233823e-06, "loss": 0.8111, "step": 261710 }, { "epoch": 21.75, "learning_rate": 1.1009395005958483e-06, "loss": 0.7745, "step": 261720 }, { "epoch": 21.75, "learning_rate": 1.1008286450683146e-06, "loss": 0.7385, "step": 261730 }, { "epoch": 21.76, "learning_rate": 1.100717789540781e-06, "loss": 0.6845, "step": 261740 }, { "epoch": 21.76, "learning_rate": 1.100606934013247e-06, "loss": 0.6769, "step": 261750 }, { "epoch": 21.76, "learning_rate": 1.1004960784857133e-06, "loss": 0.7495, "step": 261760 }, { "epoch": 21.76, "learning_rate": 1.1003852229581796e-06, "loss": 0.7182, "step": 261770 }, { "epoch": 21.76, "learning_rate": 1.1002743674306461e-06, "loss": 0.7823, "step": 261780 }, { "epoch": 21.76, "learning_rate": 1.1001635119031122e-06, "loss": 0.8052, "step": 261790 }, { "epoch": 21.76, "learning_rate": 1.1000526563755785e-06, "loss": 0.7521, "step": 261800 }, { "epoch": 21.76, "learning_rate": 1.0999418008480448e-06, "loss": 0.799, "step": 261810 }, { "epoch": 21.76, "learning_rate": 1.099830945320511e-06, "loss": 0.6952, "step": 261820 }, { "epoch": 21.76, "learning_rate": 1.0997200897929772e-06, "loss": 0.7729, "step": 261830 }, { "epoch": 21.76, "learning_rate": 1.0996092342654435e-06, "loss": 0.7472, "step": 261840 }, { "epoch": 21.76, "learning_rate": 1.0994983787379098e-06, "loss": 0.7656, "step": 261850 }, { "epoch": 21.77, "learning_rate": 1.099387523210376e-06, "loss": 0.7774, "step": 261860 }, { "epoch": 21.77, "learning_rate": 1.0992766676828421e-06, "loss": 0.8073, "step": 261870 }, { "epoch": 21.77, "learning_rate": 1.0991658121553084e-06, "loss": 0.7735, "step": 261880 }, { "epoch": 21.77, "learning_rate": 1.0990549566277747e-06, "loss": 0.7213, "step": 261890 }, { "epoch": 21.77, "learning_rate": 1.0989441011002412e-06, "loss": 0.7217, "step": 261900 }, { "epoch": 21.77, "learning_rate": 1.0988332455727073e-06, "loss": 0.8062, "step": 261910 }, { "epoch": 21.77, "learning_rate": 1.0987223900451736e-06, "loss": 0.7342, "step": 261920 }, { "epoch": 21.77, "learning_rate": 1.09861153451764e-06, "loss": 0.7064, "step": 261930 }, { "epoch": 21.77, "learning_rate": 1.0985006789901062e-06, "loss": 0.7429, "step": 261940 }, { "epoch": 21.77, "learning_rate": 1.0983898234625723e-06, "loss": 0.7455, "step": 261950 }, { "epoch": 21.77, "learning_rate": 1.0982789679350386e-06, "loss": 0.7598, "step": 261960 }, { "epoch": 21.77, "learning_rate": 1.0981681124075049e-06, "loss": 0.7189, "step": 261970 }, { "epoch": 21.78, "learning_rate": 1.0980572568799712e-06, "loss": 0.7362, "step": 261980 }, { "epoch": 21.78, "learning_rate": 1.0979464013524373e-06, "loss": 0.7158, "step": 261990 }, { "epoch": 21.78, "learning_rate": 1.0978355458249036e-06, "loss": 0.7298, "step": 262000 }, { "epoch": 21.78, "learning_rate": 1.0977246902973698e-06, "loss": 0.7537, "step": 262010 }, { "epoch": 21.78, "learning_rate": 1.0976138347698364e-06, "loss": 0.7608, "step": 262020 }, { "epoch": 21.78, "learning_rate": 1.0975029792423024e-06, "loss": 0.6779, "step": 262030 }, { "epoch": 21.78, "learning_rate": 1.0973921237147687e-06, "loss": 0.7204, "step": 262040 }, { "epoch": 21.78, "learning_rate": 1.097281268187235e-06, "loss": 0.7163, "step": 262050 }, { "epoch": 21.78, "learning_rate": 1.0971704126597013e-06, "loss": 0.8094, "step": 262060 }, { "epoch": 21.78, "learning_rate": 1.0970595571321674e-06, "loss": 0.7657, "step": 262070 }, { "epoch": 21.78, "learning_rate": 1.0969487016046337e-06, "loss": 0.7667, "step": 262080 }, { "epoch": 21.78, "learning_rate": 1.0968378460771e-06, "loss": 0.7696, "step": 262090 }, { "epoch": 21.79, "learning_rate": 1.0967269905495663e-06, "loss": 0.7519, "step": 262100 }, { "epoch": 21.79, "learning_rate": 1.0966161350220324e-06, "loss": 0.83, "step": 262110 }, { "epoch": 21.79, "learning_rate": 1.0965052794944987e-06, "loss": 0.6681, "step": 262120 }, { "epoch": 21.79, "learning_rate": 1.096394423966965e-06, "loss": 0.7118, "step": 262130 }, { "epoch": 21.79, "learning_rate": 1.0962835684394315e-06, "loss": 0.7206, "step": 262140 }, { "epoch": 21.79, "learning_rate": 1.0961727129118976e-06, "loss": 0.6587, "step": 262150 }, { "epoch": 21.79, "learning_rate": 1.0960618573843639e-06, "loss": 0.8055, "step": 262160 }, { "epoch": 21.79, "learning_rate": 1.0959510018568301e-06, "loss": 0.783, "step": 262170 }, { "epoch": 21.79, "learning_rate": 1.0958401463292962e-06, "loss": 0.7623, "step": 262180 }, { "epoch": 21.79, "learning_rate": 1.0957292908017625e-06, "loss": 0.7404, "step": 262190 }, { "epoch": 21.79, "learning_rate": 1.0956184352742288e-06, "loss": 0.7805, "step": 262200 }, { "epoch": 21.79, "learning_rate": 1.0955075797466951e-06, "loss": 0.7634, "step": 262210 }, { "epoch": 21.8, "learning_rate": 1.0953967242191612e-06, "loss": 0.749, "step": 262220 }, { "epoch": 21.8, "learning_rate": 1.0952858686916275e-06, "loss": 0.727, "step": 262230 }, { "epoch": 21.8, "learning_rate": 1.0951750131640938e-06, "loss": 0.7711, "step": 262240 }, { "epoch": 21.8, "learning_rate": 1.09506415763656e-06, "loss": 0.7454, "step": 262250 }, { "epoch": 21.8, "learning_rate": 1.0949533021090262e-06, "loss": 0.8551, "step": 262260 }, { "epoch": 21.8, "learning_rate": 1.0948424465814927e-06, "loss": 0.7647, "step": 262270 }, { "epoch": 21.8, "learning_rate": 1.094731591053959e-06, "loss": 0.7913, "step": 262280 }, { "epoch": 21.8, "learning_rate": 1.0946207355264253e-06, "loss": 0.7349, "step": 262290 }, { "epoch": 21.8, "learning_rate": 1.0945098799988914e-06, "loss": 0.6914, "step": 262300 }, { "epoch": 21.8, "learning_rate": 1.0943990244713576e-06, "loss": 0.7639, "step": 262310 }, { "epoch": 21.8, "learning_rate": 1.094288168943824e-06, "loss": 0.7265, "step": 262320 }, { "epoch": 21.8, "learning_rate": 1.0941773134162902e-06, "loss": 0.7239, "step": 262330 }, { "epoch": 21.81, "learning_rate": 1.0940664578887563e-06, "loss": 0.7287, "step": 262340 }, { "epoch": 21.81, "learning_rate": 1.0939556023612226e-06, "loss": 0.7209, "step": 262350 }, { "epoch": 21.81, "learning_rate": 1.093844746833689e-06, "loss": 0.7652, "step": 262360 }, { "epoch": 21.81, "learning_rate": 1.0937338913061552e-06, "loss": 0.7242, "step": 262370 }, { "epoch": 21.81, "learning_rate": 1.0936230357786213e-06, "loss": 0.764, "step": 262380 }, { "epoch": 21.81, "learning_rate": 1.0935121802510878e-06, "loss": 0.7609, "step": 262390 }, { "epoch": 21.81, "learning_rate": 1.093401324723554e-06, "loss": 0.7149, "step": 262400 }, { "epoch": 21.81, "learning_rate": 1.0932904691960204e-06, "loss": 0.7766, "step": 262410 }, { "epoch": 21.81, "learning_rate": 1.0931796136684865e-06, "loss": 0.7318, "step": 262420 }, { "epoch": 21.81, "learning_rate": 1.0930687581409528e-06, "loss": 0.7225, "step": 262430 }, { "epoch": 21.81, "learning_rate": 1.092957902613419e-06, "loss": 0.7681, "step": 262440 }, { "epoch": 21.81, "learning_rate": 1.0928470470858854e-06, "loss": 0.7782, "step": 262450 }, { "epoch": 21.82, "learning_rate": 1.0927361915583514e-06, "loss": 0.7404, "step": 262460 }, { "epoch": 21.82, "learning_rate": 1.0926253360308177e-06, "loss": 0.737, "step": 262470 }, { "epoch": 21.82, "learning_rate": 1.092514480503284e-06, "loss": 0.7025, "step": 262480 }, { "epoch": 21.82, "learning_rate": 1.0924036249757503e-06, "loss": 0.754, "step": 262490 }, { "epoch": 21.82, "learning_rate": 1.0922927694482164e-06, "loss": 0.721, "step": 262500 }, { "epoch": 21.82, "learning_rate": 1.092181913920683e-06, "loss": 0.8054, "step": 262510 }, { "epoch": 21.82, "learning_rate": 1.0920710583931492e-06, "loss": 0.7479, "step": 262520 }, { "epoch": 21.82, "learning_rate": 1.0919602028656155e-06, "loss": 0.7626, "step": 262530 }, { "epoch": 21.82, "learning_rate": 1.0918493473380816e-06, "loss": 0.7903, "step": 262540 }, { "epoch": 21.82, "learning_rate": 1.0917384918105479e-06, "loss": 0.7353, "step": 262550 }, { "epoch": 21.82, "learning_rate": 1.0916276362830142e-06, "loss": 0.7557, "step": 262560 }, { "epoch": 21.82, "learning_rate": 1.0915167807554803e-06, "loss": 0.7218, "step": 262570 }, { "epoch": 21.83, "learning_rate": 1.0914059252279466e-06, "loss": 0.7889, "step": 262580 }, { "epoch": 21.83, "learning_rate": 1.0912950697004129e-06, "loss": 0.774, "step": 262590 }, { "epoch": 21.83, "learning_rate": 1.0911842141728792e-06, "loss": 0.7129, "step": 262600 }, { "epoch": 21.83, "learning_rate": 1.0910733586453452e-06, "loss": 0.7903, "step": 262610 }, { "epoch": 21.83, "learning_rate": 1.0909625031178115e-06, "loss": 0.7617, "step": 262620 }, { "epoch": 21.83, "learning_rate": 1.0908516475902778e-06, "loss": 0.7438, "step": 262630 }, { "epoch": 21.83, "learning_rate": 1.0907407920627443e-06, "loss": 0.7359, "step": 262640 }, { "epoch": 21.83, "learning_rate": 1.0906299365352104e-06, "loss": 0.744, "step": 262650 }, { "epoch": 21.83, "learning_rate": 1.0905190810076767e-06, "loss": 0.7687, "step": 262660 }, { "epoch": 21.83, "learning_rate": 1.090408225480143e-06, "loss": 0.792, "step": 262670 }, { "epoch": 21.83, "learning_rate": 1.0902973699526093e-06, "loss": 0.7325, "step": 262680 }, { "epoch": 21.83, "learning_rate": 1.0901865144250754e-06, "loss": 0.7616, "step": 262690 }, { "epoch": 21.84, "learning_rate": 1.0900756588975417e-06, "loss": 0.7581, "step": 262700 }, { "epoch": 21.84, "learning_rate": 1.089964803370008e-06, "loss": 0.7657, "step": 262710 }, { "epoch": 21.84, "learning_rate": 1.0898539478424743e-06, "loss": 0.7837, "step": 262720 }, { "epoch": 21.84, "learning_rate": 1.0897430923149404e-06, "loss": 0.7563, "step": 262730 }, { "epoch": 21.84, "learning_rate": 1.0896322367874067e-06, "loss": 0.7094, "step": 262740 }, { "epoch": 21.84, "learning_rate": 1.089521381259873e-06, "loss": 0.7649, "step": 262750 }, { "epoch": 21.84, "learning_rate": 1.0894105257323395e-06, "loss": 0.7519, "step": 262760 }, { "epoch": 21.84, "learning_rate": 1.0892996702048055e-06, "loss": 0.7332, "step": 262770 }, { "epoch": 21.84, "learning_rate": 1.0891888146772718e-06, "loss": 0.7608, "step": 262780 }, { "epoch": 21.84, "learning_rate": 1.0890779591497381e-06, "loss": 0.7485, "step": 262790 }, { "epoch": 21.84, "learning_rate": 1.0889671036222044e-06, "loss": 0.7761, "step": 262800 }, { "epoch": 21.84, "learning_rate": 1.0888562480946705e-06, "loss": 0.8182, "step": 262810 }, { "epoch": 21.85, "learning_rate": 1.0887453925671368e-06, "loss": 0.7397, "step": 262820 }, { "epoch": 21.85, "learning_rate": 1.088634537039603e-06, "loss": 0.7278, "step": 262830 }, { "epoch": 21.85, "learning_rate": 1.0885236815120694e-06, "loss": 0.7846, "step": 262840 }, { "epoch": 21.85, "learning_rate": 1.0884128259845355e-06, "loss": 0.7445, "step": 262850 }, { "epoch": 21.85, "learning_rate": 1.0883019704570018e-06, "loss": 0.81, "step": 262860 }, { "epoch": 21.85, "learning_rate": 1.088191114929468e-06, "loss": 0.7367, "step": 262870 }, { "epoch": 21.85, "learning_rate": 1.0880802594019346e-06, "loss": 0.6952, "step": 262880 }, { "epoch": 21.85, "learning_rate": 1.0879694038744007e-06, "loss": 0.7038, "step": 262890 }, { "epoch": 21.85, "learning_rate": 1.087858548346867e-06, "loss": 0.7079, "step": 262900 }, { "epoch": 21.85, "learning_rate": 1.0877476928193333e-06, "loss": 0.78, "step": 262910 }, { "epoch": 21.85, "learning_rate": 1.0876368372917995e-06, "loss": 0.788, "step": 262920 }, { "epoch": 21.85, "learning_rate": 1.0875259817642656e-06, "loss": 0.7134, "step": 262930 }, { "epoch": 21.86, "learning_rate": 1.087415126236732e-06, "loss": 0.7576, "step": 262940 }, { "epoch": 21.86, "learning_rate": 1.0873042707091982e-06, "loss": 0.8475, "step": 262950 }, { "epoch": 21.86, "learning_rate": 1.0871934151816643e-06, "loss": 0.824, "step": 262960 }, { "epoch": 21.86, "learning_rate": 1.0870825596541306e-06, "loss": 0.7625, "step": 262970 }, { "epoch": 21.86, "learning_rate": 1.086971704126597e-06, "loss": 0.7154, "step": 262980 }, { "epoch": 21.86, "learning_rate": 1.0868608485990632e-06, "loss": 0.7624, "step": 262990 }, { "epoch": 21.86, "learning_rate": 1.0867499930715293e-06, "loss": 0.7025, "step": 263000 }, { "epoch": 21.86, "learning_rate": 1.0866391375439958e-06, "loss": 0.7674, "step": 263010 }, { "epoch": 21.86, "learning_rate": 1.086528282016462e-06, "loss": 0.7125, "step": 263020 }, { "epoch": 21.86, "learning_rate": 1.0864174264889284e-06, "loss": 0.7579, "step": 263030 }, { "epoch": 21.86, "learning_rate": 1.0863065709613945e-06, "loss": 0.7363, "step": 263040 }, { "epoch": 21.86, "learning_rate": 1.0861957154338608e-06, "loss": 0.719, "step": 263050 }, { "epoch": 21.87, "learning_rate": 1.086084859906327e-06, "loss": 0.8234, "step": 263060 }, { "epoch": 21.87, "learning_rate": 1.0859740043787933e-06, "loss": 0.6979, "step": 263070 }, { "epoch": 21.87, "learning_rate": 1.0858631488512594e-06, "loss": 0.7346, "step": 263080 }, { "epoch": 21.87, "learning_rate": 1.0857522933237257e-06, "loss": 0.7524, "step": 263090 }, { "epoch": 21.87, "learning_rate": 1.085641437796192e-06, "loss": 0.6757, "step": 263100 }, { "epoch": 21.87, "learning_rate": 1.0855305822686583e-06, "loss": 0.7889, "step": 263110 }, { "epoch": 21.87, "learning_rate": 1.0854197267411244e-06, "loss": 0.7066, "step": 263120 }, { "epoch": 21.87, "learning_rate": 1.085308871213591e-06, "loss": 0.768, "step": 263130 }, { "epoch": 21.87, "learning_rate": 1.0851980156860572e-06, "loss": 0.729, "step": 263140 }, { "epoch": 21.87, "learning_rate": 1.0850871601585235e-06, "loss": 0.7444, "step": 263150 }, { "epoch": 21.87, "learning_rate": 1.0849763046309896e-06, "loss": 0.7962, "step": 263160 }, { "epoch": 21.87, "learning_rate": 1.0848654491034559e-06, "loss": 0.7452, "step": 263170 }, { "epoch": 21.88, "learning_rate": 1.0847545935759222e-06, "loss": 0.7445, "step": 263180 }, { "epoch": 21.88, "learning_rate": 1.0846437380483885e-06, "loss": 0.7042, "step": 263190 }, { "epoch": 21.88, "learning_rate": 1.0845328825208545e-06, "loss": 0.7948, "step": 263200 }, { "epoch": 21.88, "learning_rate": 1.0844220269933208e-06, "loss": 0.7929, "step": 263210 }, { "epoch": 21.88, "learning_rate": 1.0843111714657871e-06, "loss": 0.7623, "step": 263220 }, { "epoch": 21.88, "learning_rate": 1.0842003159382534e-06, "loss": 0.7253, "step": 263230 }, { "epoch": 21.88, "learning_rate": 1.0840894604107195e-06, "loss": 0.7365, "step": 263240 }, { "epoch": 21.88, "learning_rate": 1.083978604883186e-06, "loss": 0.7046, "step": 263250 }, { "epoch": 21.88, "learning_rate": 1.0838677493556523e-06, "loss": 0.8006, "step": 263260 }, { "epoch": 21.88, "learning_rate": 1.0837568938281186e-06, "loss": 0.7784, "step": 263270 }, { "epoch": 21.88, "learning_rate": 1.0836460383005847e-06, "loss": 0.7786, "step": 263280 }, { "epoch": 21.88, "learning_rate": 1.083535182773051e-06, "loss": 0.7022, "step": 263290 }, { "epoch": 21.89, "learning_rate": 1.0834243272455173e-06, "loss": 0.7568, "step": 263300 }, { "epoch": 21.89, "learning_rate": 1.0833134717179836e-06, "loss": 0.7835, "step": 263310 }, { "epoch": 21.89, "learning_rate": 1.0832026161904497e-06, "loss": 0.6946, "step": 263320 }, { "epoch": 21.89, "learning_rate": 1.083091760662916e-06, "loss": 0.7422, "step": 263330 }, { "epoch": 21.89, "learning_rate": 1.0829809051353823e-06, "loss": 0.8084, "step": 263340 }, { "epoch": 21.89, "learning_rate": 1.0828700496078486e-06, "loss": 0.7137, "step": 263350 }, { "epoch": 21.89, "learning_rate": 1.0827591940803146e-06, "loss": 0.7574, "step": 263360 }, { "epoch": 21.89, "learning_rate": 1.0826483385527811e-06, "loss": 0.7536, "step": 263370 }, { "epoch": 21.89, "learning_rate": 1.0825374830252474e-06, "loss": 0.7665, "step": 263380 }, { "epoch": 21.89, "learning_rate": 1.0824266274977137e-06, "loss": 0.7182, "step": 263390 }, { "epoch": 21.89, "learning_rate": 1.0823157719701798e-06, "loss": 0.7458, "step": 263400 }, { "epoch": 21.89, "learning_rate": 1.0822049164426461e-06, "loss": 0.822, "step": 263410 }, { "epoch": 21.9, "learning_rate": 1.0820940609151124e-06, "loss": 0.7641, "step": 263420 }, { "epoch": 21.9, "learning_rate": 1.0819832053875785e-06, "loss": 0.7594, "step": 263430 }, { "epoch": 21.9, "learning_rate": 1.0818723498600448e-06, "loss": 0.7351, "step": 263440 }, { "epoch": 21.9, "learning_rate": 1.081761494332511e-06, "loss": 0.7807, "step": 263450 }, { "epoch": 21.9, "learning_rate": 1.0816506388049774e-06, "loss": 0.7898, "step": 263460 }, { "epoch": 21.9, "learning_rate": 1.0815397832774435e-06, "loss": 0.7457, "step": 263470 }, { "epoch": 21.9, "learning_rate": 1.0814289277499098e-06, "loss": 0.7768, "step": 263480 }, { "epoch": 21.9, "learning_rate": 1.081318072222376e-06, "loss": 0.7394, "step": 263490 }, { "epoch": 21.9, "learning_rate": 1.0812072166948426e-06, "loss": 0.7438, "step": 263500 }, { "epoch": 21.9, "learning_rate": 1.0810963611673086e-06, "loss": 0.7546, "step": 263510 }, { "epoch": 21.9, "learning_rate": 1.080985505639775e-06, "loss": 0.6931, "step": 263520 }, { "epoch": 21.9, "learning_rate": 1.0808746501122412e-06, "loss": 0.7357, "step": 263530 }, { "epoch": 21.91, "learning_rate": 1.0807637945847075e-06, "loss": 0.7267, "step": 263540 }, { "epoch": 21.91, "learning_rate": 1.0806529390571736e-06, "loss": 0.6639, "step": 263550 }, { "epoch": 21.91, "learning_rate": 1.08054208352964e-06, "loss": 0.7664, "step": 263560 }, { "epoch": 21.91, "learning_rate": 1.0804312280021062e-06, "loss": 0.7786, "step": 263570 }, { "epoch": 21.91, "learning_rate": 1.0803203724745725e-06, "loss": 0.7494, "step": 263580 }, { "epoch": 21.91, "learning_rate": 1.0802095169470386e-06, "loss": 0.7883, "step": 263590 }, { "epoch": 21.91, "learning_rate": 1.0800986614195049e-06, "loss": 0.7452, "step": 263600 }, { "epoch": 21.91, "learning_rate": 1.0799878058919712e-06, "loss": 0.764, "step": 263610 }, { "epoch": 21.91, "learning_rate": 1.0798769503644377e-06, "loss": 0.7494, "step": 263620 }, { "epoch": 21.91, "learning_rate": 1.0797660948369038e-06, "loss": 0.7115, "step": 263630 }, { "epoch": 21.91, "learning_rate": 1.07965523930937e-06, "loss": 0.7437, "step": 263640 }, { "epoch": 21.91, "learning_rate": 1.0795443837818364e-06, "loss": 0.7828, "step": 263650 }, { "epoch": 21.92, "learning_rate": 1.0794335282543026e-06, "loss": 0.7927, "step": 263660 }, { "epoch": 21.92, "learning_rate": 1.0793226727267687e-06, "loss": 0.7892, "step": 263670 }, { "epoch": 21.92, "learning_rate": 1.079211817199235e-06, "loss": 0.6865, "step": 263680 }, { "epoch": 21.92, "learning_rate": 1.0791009616717013e-06, "loss": 0.7931, "step": 263690 }, { "epoch": 21.92, "learning_rate": 1.0789901061441676e-06, "loss": 0.8231, "step": 263700 }, { "epoch": 21.92, "learning_rate": 1.0788792506166337e-06, "loss": 0.7926, "step": 263710 }, { "epoch": 21.92, "learning_rate": 1.0787683950891e-06, "loss": 0.6809, "step": 263720 }, { "epoch": 21.92, "learning_rate": 1.0786575395615663e-06, "loss": 0.7592, "step": 263730 }, { "epoch": 21.92, "learning_rate": 1.0785466840340328e-06, "loss": 0.714, "step": 263740 }, { "epoch": 21.92, "learning_rate": 1.0784358285064989e-06, "loss": 0.7162, "step": 263750 }, { "epoch": 21.92, "learning_rate": 1.0783249729789652e-06, "loss": 0.7969, "step": 263760 }, { "epoch": 21.92, "learning_rate": 1.0782141174514315e-06, "loss": 0.694, "step": 263770 }, { "epoch": 21.93, "learning_rate": 1.0781032619238978e-06, "loss": 0.8192, "step": 263780 }, { "epoch": 21.93, "learning_rate": 1.0779924063963639e-06, "loss": 0.798, "step": 263790 }, { "epoch": 21.93, "learning_rate": 1.0778815508688301e-06, "loss": 0.7511, "step": 263800 }, { "epoch": 21.93, "learning_rate": 1.0777706953412964e-06, "loss": 0.8232, "step": 263810 }, { "epoch": 21.93, "learning_rate": 1.0776598398137625e-06, "loss": 0.7657, "step": 263820 }, { "epoch": 21.93, "learning_rate": 1.0775489842862288e-06, "loss": 0.7304, "step": 263830 }, { "epoch": 21.93, "learning_rate": 1.0774381287586951e-06, "loss": 0.6944, "step": 263840 }, { "epoch": 21.93, "learning_rate": 1.0773272732311614e-06, "loss": 0.7195, "step": 263850 }, { "epoch": 21.93, "learning_rate": 1.0772164177036275e-06, "loss": 0.7351, "step": 263860 }, { "epoch": 21.93, "learning_rate": 1.077105562176094e-06, "loss": 0.7397, "step": 263870 }, { "epoch": 21.93, "learning_rate": 1.0769947066485603e-06, "loss": 0.7921, "step": 263880 }, { "epoch": 21.93, "learning_rate": 1.0768838511210266e-06, "loss": 0.7752, "step": 263890 }, { "epoch": 21.94, "learning_rate": 1.0767729955934927e-06, "loss": 0.7183, "step": 263900 }, { "epoch": 21.94, "learning_rate": 1.076662140065959e-06, "loss": 0.7986, "step": 263910 }, { "epoch": 21.94, "learning_rate": 1.0765512845384253e-06, "loss": 0.7213, "step": 263920 }, { "epoch": 21.94, "learning_rate": 1.0764404290108916e-06, "loss": 0.7128, "step": 263930 }, { "epoch": 21.94, "learning_rate": 1.0763295734833576e-06, "loss": 0.7369, "step": 263940 }, { "epoch": 21.94, "learning_rate": 1.076218717955824e-06, "loss": 0.7633, "step": 263950 }, { "epoch": 21.94, "learning_rate": 1.0761078624282902e-06, "loss": 0.8114, "step": 263960 }, { "epoch": 21.94, "learning_rate": 1.0759970069007565e-06, "loss": 0.7186, "step": 263970 }, { "epoch": 21.94, "learning_rate": 1.0758861513732226e-06, "loss": 0.7602, "step": 263980 }, { "epoch": 21.94, "learning_rate": 1.0757752958456891e-06, "loss": 0.72, "step": 263990 }, { "epoch": 21.94, "learning_rate": 1.0756644403181554e-06, "loss": 0.7299, "step": 264000 }, { "epoch": 21.94, "learning_rate": 1.0755535847906217e-06, "loss": 0.7799, "step": 264010 }, { "epoch": 21.94, "learning_rate": 1.0754427292630878e-06, "loss": 0.7764, "step": 264020 }, { "epoch": 21.95, "learning_rate": 1.075331873735554e-06, "loss": 0.7307, "step": 264030 }, { "epoch": 21.95, "learning_rate": 1.0752210182080204e-06, "loss": 0.7116, "step": 264040 }, { "epoch": 21.95, "learning_rate": 1.0751101626804867e-06, "loss": 0.7099, "step": 264050 }, { "epoch": 21.95, "learning_rate": 1.0749993071529528e-06, "loss": 0.7715, "step": 264060 }, { "epoch": 21.95, "learning_rate": 1.074888451625419e-06, "loss": 0.7474, "step": 264070 }, { "epoch": 21.95, "learning_rate": 1.0747775960978854e-06, "loss": 0.795, "step": 264080 }, { "epoch": 21.95, "learning_rate": 1.0746667405703517e-06, "loss": 0.7373, "step": 264090 }, { "epoch": 21.95, "learning_rate": 1.0745558850428177e-06, "loss": 0.6928, "step": 264100 }, { "epoch": 21.95, "learning_rate": 1.0744450295152842e-06, "loss": 0.7767, "step": 264110 }, { "epoch": 21.95, "learning_rate": 1.0743341739877505e-06, "loss": 0.7591, "step": 264120 }, { "epoch": 21.95, "learning_rate": 1.0742233184602168e-06, "loss": 0.7464, "step": 264130 }, { "epoch": 21.95, "learning_rate": 1.074112462932683e-06, "loss": 0.7464, "step": 264140 }, { "epoch": 21.96, "learning_rate": 1.0740016074051492e-06, "loss": 0.7359, "step": 264150 }, { "epoch": 21.96, "learning_rate": 1.0738907518776155e-06, "loss": 0.7935, "step": 264160 }, { "epoch": 21.96, "learning_rate": 1.0737798963500818e-06, "loss": 0.7029, "step": 264170 }, { "epoch": 21.96, "learning_rate": 1.0736690408225479e-06, "loss": 0.746, "step": 264180 }, { "epoch": 21.96, "learning_rate": 1.0735581852950142e-06, "loss": 0.7691, "step": 264190 }, { "epoch": 21.96, "learning_rate": 1.0734473297674805e-06, "loss": 0.7341, "step": 264200 }, { "epoch": 21.96, "learning_rate": 1.0733364742399466e-06, "loss": 0.7642, "step": 264210 }, { "epoch": 21.96, "learning_rate": 1.0732256187124129e-06, "loss": 0.7433, "step": 264220 }, { "epoch": 21.96, "learning_rate": 1.0731147631848794e-06, "loss": 0.8096, "step": 264230 }, { "epoch": 21.96, "learning_rate": 1.0730039076573457e-06, "loss": 0.7648, "step": 264240 }, { "epoch": 21.96, "learning_rate": 1.0728930521298117e-06, "loss": 0.6957, "step": 264250 }, { "epoch": 21.96, "learning_rate": 1.072782196602278e-06, "loss": 0.7587, "step": 264260 }, { "epoch": 21.97, "learning_rate": 1.0726713410747443e-06, "loss": 0.7099, "step": 264270 }, { "epoch": 21.97, "learning_rate": 1.0725604855472106e-06, "loss": 0.7831, "step": 264280 }, { "epoch": 21.97, "learning_rate": 1.0724496300196767e-06, "loss": 0.7959, "step": 264290 }, { "epoch": 21.97, "learning_rate": 1.072338774492143e-06, "loss": 0.8088, "step": 264300 }, { "epoch": 21.97, "learning_rate": 1.0722279189646093e-06, "loss": 0.7716, "step": 264310 }, { "epoch": 21.97, "learning_rate": 1.0721170634370756e-06, "loss": 0.7606, "step": 264320 }, { "epoch": 21.97, "learning_rate": 1.0720062079095417e-06, "loss": 0.7356, "step": 264330 }, { "epoch": 21.97, "learning_rate": 1.071895352382008e-06, "loss": 0.7417, "step": 264340 }, { "epoch": 21.97, "learning_rate": 1.0717844968544743e-06, "loss": 0.7178, "step": 264350 }, { "epoch": 21.97, "learning_rate": 1.0716736413269408e-06, "loss": 0.7774, "step": 264360 }, { "epoch": 21.97, "learning_rate": 1.0715627857994069e-06, "loss": 0.7629, "step": 264370 }, { "epoch": 21.97, "learning_rate": 1.0714519302718732e-06, "loss": 0.7656, "step": 264380 }, { "epoch": 21.98, "learning_rate": 1.0713410747443395e-06, "loss": 0.7432, "step": 264390 }, { "epoch": 21.98, "learning_rate": 1.0712302192168058e-06, "loss": 0.7398, "step": 264400 }, { "epoch": 21.98, "learning_rate": 1.0711193636892718e-06, "loss": 0.7732, "step": 264410 }, { "epoch": 21.98, "learning_rate": 1.0710085081617381e-06, "loss": 0.7329, "step": 264420 }, { "epoch": 21.98, "learning_rate": 1.0708976526342044e-06, "loss": 0.7848, "step": 264430 }, { "epoch": 21.98, "learning_rate": 1.0707867971066707e-06, "loss": 0.7263, "step": 264440 }, { "epoch": 21.98, "learning_rate": 1.0706759415791368e-06, "loss": 0.7308, "step": 264450 }, { "epoch": 21.98, "learning_rate": 1.070565086051603e-06, "loss": 0.8523, "step": 264460 }, { "epoch": 21.98, "learning_rate": 1.0704542305240694e-06, "loss": 0.8189, "step": 264470 }, { "epoch": 21.98, "learning_rate": 1.070343374996536e-06, "loss": 0.7695, "step": 264480 }, { "epoch": 21.98, "learning_rate": 1.070232519469002e-06, "loss": 0.7557, "step": 264490 }, { "epoch": 21.98, "learning_rate": 1.0701216639414683e-06, "loss": 0.7678, "step": 264500 }, { "epoch": 21.99, "learning_rate": 1.0700108084139346e-06, "loss": 0.8068, "step": 264510 }, { "epoch": 21.99, "learning_rate": 1.0698999528864009e-06, "loss": 0.7615, "step": 264520 }, { "epoch": 21.99, "learning_rate": 1.069789097358867e-06, "loss": 0.7547, "step": 264530 }, { "epoch": 21.99, "learning_rate": 1.0696782418313332e-06, "loss": 0.7944, "step": 264540 }, { "epoch": 21.99, "learning_rate": 1.0695673863037995e-06, "loss": 0.7596, "step": 264550 }, { "epoch": 21.99, "learning_rate": 1.0694565307762658e-06, "loss": 0.792, "step": 264560 }, { "epoch": 21.99, "learning_rate": 1.069345675248732e-06, "loss": 0.7913, "step": 264570 }, { "epoch": 21.99, "learning_rate": 1.0692348197211982e-06, "loss": 0.7226, "step": 264580 }, { "epoch": 21.99, "learning_rate": 1.0691239641936645e-06, "loss": 0.7195, "step": 264590 }, { "epoch": 21.99, "learning_rate": 1.069013108666131e-06, "loss": 0.7155, "step": 264600 }, { "epoch": 21.99, "learning_rate": 1.068902253138597e-06, "loss": 0.7752, "step": 264610 }, { "epoch": 21.99, "learning_rate": 1.0687913976110634e-06, "loss": 0.7536, "step": 264620 }, { "epoch": 22.0, "learning_rate": 1.0686805420835297e-06, "loss": 0.747, "step": 264630 }, { "epoch": 22.0, "learning_rate": 1.068569686555996e-06, "loss": 0.7754, "step": 264640 }, { "epoch": 22.0, "learning_rate": 1.068458831028462e-06, "loss": 0.7172, "step": 264650 }, { "epoch": 22.0, "learning_rate": 1.0683479755009284e-06, "loss": 0.7529, "step": 264660 }, { "epoch": 22.0, "learning_rate": 1.0682371199733947e-06, "loss": 0.7327, "step": 264670 }, { "epoch": 22.0, "learning_rate": 1.0681262644458607e-06, "loss": 0.7059, "step": 264680 }, { "epoch": 22.0, "eval_loss": 1.1285432577133179, "eval_runtime": 356.9376, "eval_samples_per_second": 7.492, "eval_steps_per_second": 3.746, "eval_wer": 0.6381084224454144, "step": 264682 }, { "epoch": 22.0, "learning_rate": 1.068015408918327e-06, "loss": 0.7532, "step": 264690 }, { "epoch": 22.0, "learning_rate": 1.0679045533907933e-06, "loss": 0.7205, "step": 264700 }, { "epoch": 22.0, "learning_rate": 1.0677936978632596e-06, "loss": 0.7243, "step": 264710 }, { "epoch": 22.0, "learning_rate": 1.0676828423357257e-06, "loss": 0.6947, "step": 264720 }, { "epoch": 22.0, "learning_rate": 1.0675719868081922e-06, "loss": 0.7737, "step": 264730 }, { "epoch": 22.0, "learning_rate": 1.0674611312806585e-06, "loss": 0.7882, "step": 264740 }, { "epoch": 22.01, "learning_rate": 1.0673502757531248e-06, "loss": 0.7433, "step": 264750 }, { "epoch": 22.01, "learning_rate": 1.067239420225591e-06, "loss": 0.7767, "step": 264760 }, { "epoch": 22.01, "learning_rate": 1.0671285646980572e-06, "loss": 0.7783, "step": 264770 }, { "epoch": 22.01, "learning_rate": 1.0670177091705235e-06, "loss": 0.7602, "step": 264780 }, { "epoch": 22.01, "learning_rate": 1.0669068536429898e-06, "loss": 0.7565, "step": 264790 }, { "epoch": 22.01, "learning_rate": 1.0667959981154559e-06, "loss": 0.7891, "step": 264800 }, { "epoch": 22.01, "learning_rate": 1.0666851425879222e-06, "loss": 0.7931, "step": 264810 }, { "epoch": 22.01, "learning_rate": 1.0665742870603885e-06, "loss": 0.6013, "step": 264820 }, { "epoch": 22.01, "learning_rate": 1.0664634315328548e-06, "loss": 0.755, "step": 264830 }, { "epoch": 22.01, "learning_rate": 1.0663525760053208e-06, "loss": 0.8025, "step": 264840 }, { "epoch": 22.01, "learning_rate": 1.0662417204777873e-06, "loss": 0.8154, "step": 264850 }, { "epoch": 22.01, "learning_rate": 1.0661308649502536e-06, "loss": 0.6866, "step": 264860 }, { "epoch": 22.02, "learning_rate": 1.06602000942272e-06, "loss": 0.7322, "step": 264870 }, { "epoch": 22.02, "learning_rate": 1.065909153895186e-06, "loss": 0.7321, "step": 264880 }, { "epoch": 22.02, "learning_rate": 1.0657982983676523e-06, "loss": 0.795, "step": 264890 }, { "epoch": 22.02, "learning_rate": 1.0656874428401186e-06, "loss": 0.7398, "step": 264900 }, { "epoch": 22.02, "learning_rate": 1.065576587312585e-06, "loss": 0.7556, "step": 264910 }, { "epoch": 22.02, "learning_rate": 1.065465731785051e-06, "loss": 0.7563, "step": 264920 }, { "epoch": 22.02, "learning_rate": 1.0653548762575173e-06, "loss": 0.7026, "step": 264930 }, { "epoch": 22.02, "learning_rate": 1.0652440207299836e-06, "loss": 0.7371, "step": 264940 }, { "epoch": 22.02, "learning_rate": 1.0651331652024499e-06, "loss": 0.7607, "step": 264950 }, { "epoch": 22.02, "learning_rate": 1.065022309674916e-06, "loss": 0.7533, "step": 264960 }, { "epoch": 22.02, "learning_rate": 1.0649114541473825e-06, "loss": 0.767, "step": 264970 }, { "epoch": 22.02, "learning_rate": 1.0648005986198488e-06, "loss": 0.7125, "step": 264980 }, { "epoch": 22.03, "learning_rate": 1.064689743092315e-06, "loss": 0.8039, "step": 264990 }, { "epoch": 22.03, "learning_rate": 1.0645788875647811e-06, "loss": 0.7848, "step": 265000 }, { "epoch": 22.03, "learning_rate": 1.0644680320372474e-06, "loss": 0.771, "step": 265010 }, { "epoch": 22.03, "learning_rate": 1.0643571765097137e-06, "loss": 0.7617, "step": 265020 }, { "epoch": 22.03, "learning_rate": 1.06424632098218e-06, "loss": 0.7238, "step": 265030 }, { "epoch": 22.03, "learning_rate": 1.0641354654546461e-06, "loss": 0.7569, "step": 265040 }, { "epoch": 22.03, "learning_rate": 1.0640246099271124e-06, "loss": 0.7233, "step": 265050 }, { "epoch": 22.03, "learning_rate": 1.0639137543995787e-06, "loss": 0.7646, "step": 265060 }, { "epoch": 22.03, "learning_rate": 1.0638028988720448e-06, "loss": 0.7638, "step": 265070 }, { "epoch": 22.03, "learning_rate": 1.063692043344511e-06, "loss": 0.6762, "step": 265080 }, { "epoch": 22.03, "learning_rate": 1.0635811878169774e-06, "loss": 0.8094, "step": 265090 }, { "epoch": 22.03, "learning_rate": 1.0634703322894439e-06, "loss": 0.7125, "step": 265100 }, { "epoch": 22.04, "learning_rate": 1.06335947676191e-06, "loss": 0.7637, "step": 265110 }, { "epoch": 22.04, "learning_rate": 1.0632486212343763e-06, "loss": 0.757, "step": 265120 }, { "epoch": 22.04, "learning_rate": 1.0631377657068426e-06, "loss": 0.7995, "step": 265130 }, { "epoch": 22.04, "learning_rate": 1.0630269101793089e-06, "loss": 0.7888, "step": 265140 }, { "epoch": 22.04, "learning_rate": 1.062916054651775e-06, "loss": 0.6763, "step": 265150 }, { "epoch": 22.04, "learning_rate": 1.0628051991242412e-06, "loss": 0.8315, "step": 265160 }, { "epoch": 22.04, "learning_rate": 1.0626943435967075e-06, "loss": 0.7603, "step": 265170 }, { "epoch": 22.04, "learning_rate": 1.0625834880691738e-06, "loss": 0.7747, "step": 265180 }, { "epoch": 22.04, "learning_rate": 1.06247263254164e-06, "loss": 0.8166, "step": 265190 }, { "epoch": 22.04, "learning_rate": 1.0623617770141062e-06, "loss": 0.7841, "step": 265200 }, { "epoch": 22.04, "learning_rate": 1.0622509214865725e-06, "loss": 0.7264, "step": 265210 }, { "epoch": 22.04, "learning_rate": 1.062140065959039e-06, "loss": 0.7233, "step": 265220 }, { "epoch": 22.05, "learning_rate": 1.062029210431505e-06, "loss": 0.7615, "step": 265230 }, { "epoch": 22.05, "learning_rate": 1.0619183549039714e-06, "loss": 0.7482, "step": 265240 }, { "epoch": 22.05, "learning_rate": 1.0618074993764377e-06, "loss": 0.7875, "step": 265250 }, { "epoch": 22.05, "learning_rate": 1.061696643848904e-06, "loss": 0.7781, "step": 265260 }, { "epoch": 22.05, "learning_rate": 1.06158578832137e-06, "loss": 0.752, "step": 265270 }, { "epoch": 22.05, "learning_rate": 1.0614749327938364e-06, "loss": 0.7453, "step": 265280 }, { "epoch": 22.05, "learning_rate": 1.0613640772663026e-06, "loss": 0.7676, "step": 265290 }, { "epoch": 22.05, "learning_rate": 1.061253221738769e-06, "loss": 0.7114, "step": 265300 }, { "epoch": 22.05, "learning_rate": 1.061142366211235e-06, "loss": 0.697, "step": 265310 }, { "epoch": 22.05, "learning_rate": 1.0610315106837013e-06, "loss": 0.7433, "step": 265320 }, { "epoch": 22.05, "learning_rate": 1.0609206551561676e-06, "loss": 0.7129, "step": 265330 }, { "epoch": 22.05, "learning_rate": 1.0608097996286341e-06, "loss": 0.8169, "step": 265340 }, { "epoch": 22.06, "learning_rate": 1.0606989441011002e-06, "loss": 0.7056, "step": 265350 }, { "epoch": 22.06, "learning_rate": 1.0605880885735665e-06, "loss": 0.7955, "step": 265360 }, { "epoch": 22.06, "learning_rate": 1.0604772330460328e-06, "loss": 0.7519, "step": 265370 }, { "epoch": 22.06, "learning_rate": 1.060366377518499e-06, "loss": 0.7683, "step": 265380 }, { "epoch": 22.06, "learning_rate": 1.0602555219909652e-06, "loss": 0.8098, "step": 265390 }, { "epoch": 22.06, "learning_rate": 1.0601446664634315e-06, "loss": 0.6839, "step": 265400 }, { "epoch": 22.06, "learning_rate": 1.0600338109358978e-06, "loss": 0.6397, "step": 265410 }, { "epoch": 22.06, "learning_rate": 1.059922955408364e-06, "loss": 0.7357, "step": 265420 }, { "epoch": 22.06, "learning_rate": 1.0598120998808301e-06, "loss": 0.7925, "step": 265430 }, { "epoch": 22.06, "learning_rate": 1.0597012443532964e-06, "loss": 0.7828, "step": 265440 }, { "epoch": 22.06, "learning_rate": 1.0595903888257627e-06, "loss": 0.7105, "step": 265450 }, { "epoch": 22.06, "learning_rate": 1.0594795332982292e-06, "loss": 0.7302, "step": 265460 }, { "epoch": 22.07, "learning_rate": 1.0593686777706953e-06, "loss": 0.7515, "step": 265470 }, { "epoch": 22.07, "learning_rate": 1.0592578222431616e-06, "loss": 0.7737, "step": 265480 }, { "epoch": 22.07, "learning_rate": 1.059146966715628e-06, "loss": 0.8073, "step": 265490 }, { "epoch": 22.07, "learning_rate": 1.059036111188094e-06, "loss": 0.7649, "step": 265500 }, { "epoch": 22.07, "learning_rate": 1.0589252556605603e-06, "loss": 0.7927, "step": 265510 }, { "epoch": 22.07, "learning_rate": 1.0588144001330266e-06, "loss": 0.7493, "step": 265520 }, { "epoch": 22.07, "learning_rate": 1.0587035446054929e-06, "loss": 0.7309, "step": 265530 }, { "epoch": 22.07, "learning_rate": 1.058592689077959e-06, "loss": 0.7109, "step": 265540 }, { "epoch": 22.07, "learning_rate": 1.0584818335504253e-06, "loss": 0.7019, "step": 265550 }, { "epoch": 22.07, "learning_rate": 1.0583709780228916e-06, "loss": 0.7363, "step": 265560 }, { "epoch": 22.07, "learning_rate": 1.0582601224953579e-06, "loss": 0.7758, "step": 265570 }, { "epoch": 22.07, "learning_rate": 1.058149266967824e-06, "loss": 0.7358, "step": 265580 }, { "epoch": 22.08, "learning_rate": 1.0580384114402904e-06, "loss": 0.7848, "step": 265590 }, { "epoch": 22.08, "learning_rate": 1.0579275559127567e-06, "loss": 0.7448, "step": 265600 }, { "epoch": 22.08, "learning_rate": 1.057816700385223e-06, "loss": 0.7464, "step": 265610 }, { "epoch": 22.08, "learning_rate": 1.0577058448576891e-06, "loss": 0.6996, "step": 265620 }, { "epoch": 22.08, "learning_rate": 1.0575949893301554e-06, "loss": 0.7497, "step": 265630 }, { "epoch": 22.08, "learning_rate": 1.0574841338026217e-06, "loss": 0.7736, "step": 265640 }, { "epoch": 22.08, "learning_rate": 1.057373278275088e-06, "loss": 0.7246, "step": 265650 }, { "epoch": 22.08, "learning_rate": 1.057262422747554e-06, "loss": 0.7227, "step": 265660 }, { "epoch": 22.08, "learning_rate": 1.0571515672200204e-06, "loss": 0.7019, "step": 265670 }, { "epoch": 22.08, "learning_rate": 1.0570407116924867e-06, "loss": 0.7929, "step": 265680 }, { "epoch": 22.08, "learning_rate": 1.056929856164953e-06, "loss": 0.7566, "step": 265690 }, { "epoch": 22.08, "learning_rate": 1.0568300861901727e-06, "loss": 0.7189, "step": 265700 }, { "epoch": 22.09, "learning_rate": 1.0567192306626388e-06, "loss": 0.7224, "step": 265710 }, { "epoch": 22.09, "learning_rate": 1.0566083751351051e-06, "loss": 0.7281, "step": 265720 }, { "epoch": 22.09, "learning_rate": 1.0564975196075714e-06, "loss": 0.8135, "step": 265730 }, { "epoch": 22.09, "learning_rate": 1.0563866640800377e-06, "loss": 0.8156, "step": 265740 }, { "epoch": 22.09, "learning_rate": 1.0562758085525038e-06, "loss": 0.6993, "step": 265750 }, { "epoch": 22.09, "learning_rate": 1.05616495302497e-06, "loss": 0.7549, "step": 265760 }, { "epoch": 22.09, "learning_rate": 1.0560540974974364e-06, "loss": 0.7835, "step": 265770 }, { "epoch": 22.09, "learning_rate": 1.0559432419699027e-06, "loss": 0.821, "step": 265780 }, { "epoch": 22.09, "learning_rate": 1.0558323864423688e-06, "loss": 0.8003, "step": 265790 }, { "epoch": 22.09, "learning_rate": 1.0557215309148353e-06, "loss": 0.7518, "step": 265800 }, { "epoch": 22.09, "learning_rate": 1.0556106753873016e-06, "loss": 0.7551, "step": 265810 }, { "epoch": 22.09, "learning_rate": 1.0554998198597678e-06, "loss": 0.7543, "step": 265820 }, { "epoch": 22.1, "learning_rate": 1.055388964332234e-06, "loss": 0.7614, "step": 265830 }, { "epoch": 22.1, "learning_rate": 1.0552781088047002e-06, "loss": 0.7511, "step": 265840 }, { "epoch": 22.1, "learning_rate": 1.0551672532771665e-06, "loss": 0.7292, "step": 265850 }, { "epoch": 22.1, "learning_rate": 1.0550563977496328e-06, "loss": 0.7801, "step": 265860 }, { "epoch": 22.1, "learning_rate": 1.054945542222099e-06, "loss": 0.7021, "step": 265870 }, { "epoch": 22.1, "learning_rate": 1.0548346866945652e-06, "loss": 0.6967, "step": 265880 }, { "epoch": 22.1, "learning_rate": 1.0547238311670315e-06, "loss": 0.8007, "step": 265890 }, { "epoch": 22.1, "learning_rate": 1.0546129756394978e-06, "loss": 0.727, "step": 265900 }, { "epoch": 22.1, "learning_rate": 1.0545021201119639e-06, "loss": 0.774, "step": 265910 }, { "epoch": 22.1, "learning_rate": 1.0543912645844304e-06, "loss": 0.7563, "step": 265920 }, { "epoch": 22.1, "learning_rate": 1.0542804090568967e-06, "loss": 0.7139, "step": 265930 }, { "epoch": 22.1, "learning_rate": 1.054169553529363e-06, "loss": 0.7135, "step": 265940 }, { "epoch": 22.11, "learning_rate": 1.054058698001829e-06, "loss": 0.7329, "step": 265950 }, { "epoch": 22.11, "learning_rate": 1.0539478424742953e-06, "loss": 0.7651, "step": 265960 }, { "epoch": 22.11, "learning_rate": 1.0538369869467616e-06, "loss": 0.6816, "step": 265970 }, { "epoch": 22.11, "learning_rate": 1.053726131419228e-06, "loss": 0.7699, "step": 265980 }, { "epoch": 22.11, "learning_rate": 1.053615275891694e-06, "loss": 0.7689, "step": 265990 }, { "epoch": 22.11, "learning_rate": 1.0535044203641603e-06, "loss": 0.6991, "step": 266000 }, { "epoch": 22.11, "learning_rate": 1.0533935648366266e-06, "loss": 0.7932, "step": 266010 }, { "epoch": 22.11, "learning_rate": 1.0532827093090927e-06, "loss": 0.6615, "step": 266020 }, { "epoch": 22.11, "learning_rate": 1.053171853781559e-06, "loss": 0.783, "step": 266030 }, { "epoch": 22.11, "learning_rate": 1.0530609982540255e-06, "loss": 0.7341, "step": 266040 }, { "epoch": 22.11, "learning_rate": 1.0529501427264918e-06, "loss": 0.7504, "step": 266050 }, { "epoch": 22.11, "learning_rate": 1.0528392871989579e-06, "loss": 0.7511, "step": 266060 }, { "epoch": 22.12, "learning_rate": 1.0527284316714242e-06, "loss": 0.8122, "step": 266070 }, { "epoch": 22.12, "learning_rate": 1.0526175761438905e-06, "loss": 0.7038, "step": 266080 }, { "epoch": 22.12, "learning_rate": 1.0525067206163568e-06, "loss": 0.7085, "step": 266090 }, { "epoch": 22.12, "learning_rate": 1.0523958650888228e-06, "loss": 0.7582, "step": 266100 }, { "epoch": 22.12, "learning_rate": 1.0522850095612891e-06, "loss": 0.7325, "step": 266110 }, { "epoch": 22.12, "learning_rate": 1.0521741540337554e-06, "loss": 0.8067, "step": 266120 }, { "epoch": 22.12, "learning_rate": 1.0520632985062217e-06, "loss": 0.7147, "step": 266130 }, { "epoch": 22.12, "learning_rate": 1.0519524429786878e-06, "loss": 0.789, "step": 266140 }, { "epoch": 22.12, "learning_rate": 1.0518415874511541e-06, "loss": 0.7601, "step": 266150 }, { "epoch": 22.12, "learning_rate": 1.0517307319236204e-06, "loss": 0.7226, "step": 266160 }, { "epoch": 22.12, "learning_rate": 1.051619876396087e-06, "loss": 0.744, "step": 266170 }, { "epoch": 22.12, "learning_rate": 1.051509020868553e-06, "loss": 0.7995, "step": 266180 }, { "epoch": 22.13, "learning_rate": 1.0513981653410193e-06, "loss": 0.7994, "step": 266190 }, { "epoch": 22.13, "learning_rate": 1.0512873098134856e-06, "loss": 0.7395, "step": 266200 }, { "epoch": 22.13, "learning_rate": 1.0511764542859519e-06, "loss": 0.7373, "step": 266210 }, { "epoch": 22.13, "learning_rate": 1.051065598758418e-06, "loss": 0.7295, "step": 266220 }, { "epoch": 22.13, "learning_rate": 1.0509547432308843e-06, "loss": 0.7278, "step": 266230 }, { "epoch": 22.13, "learning_rate": 1.0508438877033506e-06, "loss": 0.7709, "step": 266240 }, { "epoch": 22.13, "learning_rate": 1.0507330321758169e-06, "loss": 0.7518, "step": 266250 }, { "epoch": 22.13, "learning_rate": 1.050622176648283e-06, "loss": 0.7723, "step": 266260 }, { "epoch": 22.13, "learning_rate": 1.0505113211207492e-06, "loss": 0.7233, "step": 266270 }, { "epoch": 22.13, "learning_rate": 1.0504004655932155e-06, "loss": 0.6714, "step": 266280 }, { "epoch": 22.13, "learning_rate": 1.050289610065682e-06, "loss": 0.839, "step": 266290 }, { "epoch": 22.13, "learning_rate": 1.0501787545381481e-06, "loss": 0.7668, "step": 266300 }, { "epoch": 22.14, "learning_rate": 1.0500678990106144e-06, "loss": 0.665, "step": 266310 }, { "epoch": 22.14, "learning_rate": 1.0499570434830807e-06, "loss": 0.783, "step": 266320 }, { "epoch": 22.14, "learning_rate": 1.049846187955547e-06, "loss": 0.7065, "step": 266330 }, { "epoch": 22.14, "learning_rate": 1.049735332428013e-06, "loss": 0.7723, "step": 266340 }, { "epoch": 22.14, "learning_rate": 1.0496244769004794e-06, "loss": 0.7574, "step": 266350 }, { "epoch": 22.14, "learning_rate": 1.0495136213729457e-06, "loss": 0.8386, "step": 266360 }, { "epoch": 22.14, "learning_rate": 1.049402765845412e-06, "loss": 0.7248, "step": 266370 }, { "epoch": 22.14, "learning_rate": 1.049291910317878e-06, "loss": 0.6744, "step": 266380 }, { "epoch": 22.14, "learning_rate": 1.0491810547903444e-06, "loss": 0.7781, "step": 266390 }, { "epoch": 22.14, "learning_rate": 1.0490701992628106e-06, "loss": 0.7603, "step": 266400 }, { "epoch": 22.14, "learning_rate": 1.0489593437352772e-06, "loss": 0.7412, "step": 266410 }, { "epoch": 22.14, "learning_rate": 1.0488484882077432e-06, "loss": 0.7178, "step": 266420 }, { "epoch": 22.15, "learning_rate": 1.0487376326802095e-06, "loss": 0.7333, "step": 266430 }, { "epoch": 22.15, "learning_rate": 1.0486267771526758e-06, "loss": 0.7516, "step": 266440 }, { "epoch": 22.15, "learning_rate": 1.048515921625142e-06, "loss": 0.7265, "step": 266450 }, { "epoch": 22.15, "learning_rate": 1.0484050660976082e-06, "loss": 0.7234, "step": 266460 }, { "epoch": 22.15, "learning_rate": 1.0482942105700745e-06, "loss": 0.7285, "step": 266470 }, { "epoch": 22.15, "learning_rate": 1.0481833550425408e-06, "loss": 0.6715, "step": 266480 }, { "epoch": 22.15, "learning_rate": 1.0480724995150069e-06, "loss": 0.8238, "step": 266490 }, { "epoch": 22.15, "learning_rate": 1.0479616439874732e-06, "loss": 0.7138, "step": 266500 }, { "epoch": 22.15, "learning_rate": 1.0478507884599395e-06, "loss": 0.7364, "step": 266510 }, { "epoch": 22.15, "learning_rate": 1.0477399329324058e-06, "loss": 0.8308, "step": 266520 }, { "epoch": 22.15, "learning_rate": 1.047629077404872e-06, "loss": 0.7111, "step": 266530 }, { "epoch": 22.15, "learning_rate": 1.0475182218773384e-06, "loss": 0.7569, "step": 266540 }, { "epoch": 22.16, "learning_rate": 1.0474073663498047e-06, "loss": 0.7671, "step": 266550 }, { "epoch": 22.16, "learning_rate": 1.047296510822271e-06, "loss": 0.7197, "step": 266560 }, { "epoch": 22.16, "learning_rate": 1.047185655294737e-06, "loss": 0.7404, "step": 266570 }, { "epoch": 22.16, "learning_rate": 1.0470747997672033e-06, "loss": 0.7127, "step": 266580 }, { "epoch": 22.16, "learning_rate": 1.0469639442396696e-06, "loss": 0.7777, "step": 266590 }, { "epoch": 22.16, "learning_rate": 1.046853088712136e-06, "loss": 0.6812, "step": 266600 }, { "epoch": 22.16, "learning_rate": 1.046742233184602e-06, "loss": 0.759, "step": 266610 }, { "epoch": 22.16, "learning_rate": 1.0466313776570683e-06, "loss": 0.678, "step": 266620 }, { "epoch": 22.16, "learning_rate": 1.0465205221295346e-06, "loss": 0.7648, "step": 266630 }, { "epoch": 22.16, "learning_rate": 1.0464096666020009e-06, "loss": 0.8208, "step": 266640 }, { "epoch": 22.16, "learning_rate": 1.046298811074467e-06, "loss": 0.8023, "step": 266650 }, { "epoch": 22.16, "learning_rate": 1.0461879555469335e-06, "loss": 0.7769, "step": 266660 }, { "epoch": 22.17, "learning_rate": 1.0460771000193998e-06, "loss": 0.7078, "step": 266670 }, { "epoch": 22.17, "learning_rate": 1.045966244491866e-06, "loss": 0.6681, "step": 266680 }, { "epoch": 22.17, "learning_rate": 1.0458553889643322e-06, "loss": 0.7537, "step": 266690 }, { "epoch": 22.17, "learning_rate": 1.0457445334367985e-06, "loss": 0.7664, "step": 266700 }, { "epoch": 22.17, "learning_rate": 1.0456336779092647e-06, "loss": 0.7626, "step": 266710 }, { "epoch": 22.17, "learning_rate": 1.045522822381731e-06, "loss": 0.7049, "step": 266720 }, { "epoch": 22.17, "learning_rate": 1.0454119668541971e-06, "loss": 0.7341, "step": 266730 }, { "epoch": 22.17, "learning_rate": 1.0453011113266634e-06, "loss": 0.7638, "step": 266740 }, { "epoch": 22.17, "learning_rate": 1.0451902557991297e-06, "loss": 0.7707, "step": 266750 }, { "epoch": 22.17, "learning_rate": 1.045079400271596e-06, "loss": 0.7532, "step": 266760 }, { "epoch": 22.17, "learning_rate": 1.044968544744062e-06, "loss": 0.7386, "step": 266770 }, { "epoch": 22.17, "learning_rate": 1.0448576892165286e-06, "loss": 0.7867, "step": 266780 }, { "epoch": 22.18, "learning_rate": 1.044746833688995e-06, "loss": 0.8046, "step": 266790 }, { "epoch": 22.18, "learning_rate": 1.0446359781614612e-06, "loss": 0.7732, "step": 266800 }, { "epoch": 22.18, "learning_rate": 1.0445251226339273e-06, "loss": 0.7561, "step": 266810 }, { "epoch": 22.18, "learning_rate": 1.0444142671063936e-06, "loss": 0.7099, "step": 266820 }, { "epoch": 22.18, "learning_rate": 1.0443034115788599e-06, "loss": 0.768, "step": 266830 }, { "epoch": 22.18, "learning_rate": 1.0441925560513262e-06, "loss": 0.7282, "step": 266840 }, { "epoch": 22.18, "learning_rate": 1.0440817005237922e-06, "loss": 0.7978, "step": 266850 }, { "epoch": 22.18, "learning_rate": 1.0439708449962585e-06, "loss": 0.7202, "step": 266860 }, { "epoch": 22.18, "learning_rate": 1.0438599894687248e-06, "loss": 0.778, "step": 266870 }, { "epoch": 22.18, "learning_rate": 1.043749133941191e-06, "loss": 0.7759, "step": 266880 }, { "epoch": 22.18, "learning_rate": 1.0436493639664109e-06, "loss": 0.7994, "step": 266890 }, { "epoch": 22.18, "learning_rate": 1.043538508438877e-06, "loss": 0.7419, "step": 266900 }, { "epoch": 22.19, "learning_rate": 1.0434276529113433e-06, "loss": 0.7201, "step": 266910 }, { "epoch": 22.19, "learning_rate": 1.0433167973838096e-06, "loss": 0.7109, "step": 266920 }, { "epoch": 22.19, "learning_rate": 1.0432059418562759e-06, "loss": 0.7417, "step": 266930 }, { "epoch": 22.19, "learning_rate": 1.043095086328742e-06, "loss": 0.8034, "step": 266940 }, { "epoch": 22.19, "learning_rate": 1.0429842308012082e-06, "loss": 0.6825, "step": 266950 }, { "epoch": 22.19, "learning_rate": 1.0428733752736745e-06, "loss": 0.8244, "step": 266960 }, { "epoch": 22.19, "learning_rate": 1.0427625197461406e-06, "loss": 0.7279, "step": 266970 }, { "epoch": 22.19, "learning_rate": 1.042651664218607e-06, "loss": 0.8141, "step": 266980 }, { "epoch": 22.19, "learning_rate": 1.0425408086910734e-06, "loss": 0.7297, "step": 266990 }, { "epoch": 22.19, "learning_rate": 1.0424299531635397e-06, "loss": 0.7357, "step": 267000 }, { "epoch": 22.19, "learning_rate": 1.0423190976360058e-06, "loss": 0.7242, "step": 267010 }, { "epoch": 22.19, "learning_rate": 1.042208242108472e-06, "loss": 0.7153, "step": 267020 }, { "epoch": 22.2, "learning_rate": 1.0420973865809384e-06, "loss": 0.6668, "step": 267030 }, { "epoch": 22.2, "learning_rate": 1.0419865310534047e-06, "loss": 0.7678, "step": 267040 }, { "epoch": 22.2, "learning_rate": 1.0418756755258708e-06, "loss": 0.7308, "step": 267050 }, { "epoch": 22.2, "learning_rate": 1.041764819998337e-06, "loss": 0.7364, "step": 267060 }, { "epoch": 22.2, "learning_rate": 1.0416539644708034e-06, "loss": 0.7417, "step": 267070 }, { "epoch": 22.2, "learning_rate": 1.0415431089432696e-06, "loss": 0.7368, "step": 267080 }, { "epoch": 22.2, "learning_rate": 1.0414322534157357e-06, "loss": 0.8447, "step": 267090 }, { "epoch": 22.2, "learning_rate": 1.041321397888202e-06, "loss": 0.7204, "step": 267100 }, { "epoch": 22.2, "learning_rate": 1.0412105423606685e-06, "loss": 0.7461, "step": 267110 }, { "epoch": 22.2, "learning_rate": 1.0410996868331348e-06, "loss": 0.7037, "step": 267120 }, { "epoch": 22.2, "learning_rate": 1.040988831305601e-06, "loss": 0.7766, "step": 267130 }, { "epoch": 22.2, "learning_rate": 1.0408779757780672e-06, "loss": 0.769, "step": 267140 }, { "epoch": 22.21, "learning_rate": 1.0407671202505335e-06, "loss": 0.7423, "step": 267150 }, { "epoch": 22.21, "learning_rate": 1.0406562647229998e-06, "loss": 0.734, "step": 267160 }, { "epoch": 22.21, "learning_rate": 1.0405454091954659e-06, "loss": 0.7572, "step": 267170 }, { "epoch": 22.21, "learning_rate": 1.0404345536679322e-06, "loss": 0.7724, "step": 267180 }, { "epoch": 22.21, "learning_rate": 1.0403236981403985e-06, "loss": 0.7164, "step": 267190 }, { "epoch": 22.21, "learning_rate": 1.0402128426128648e-06, "loss": 0.6961, "step": 267200 }, { "epoch": 22.21, "learning_rate": 1.0401019870853309e-06, "loss": 0.7094, "step": 267210 }, { "epoch": 22.21, "learning_rate": 1.0399911315577971e-06, "loss": 0.7478, "step": 267220 }, { "epoch": 22.21, "learning_rate": 1.0398802760302634e-06, "loss": 0.6785, "step": 267230 }, { "epoch": 22.21, "learning_rate": 1.03976942050273e-06, "loss": 0.7722, "step": 267240 }, { "epoch": 22.21, "learning_rate": 1.039658564975196e-06, "loss": 0.7254, "step": 267250 }, { "epoch": 22.21, "learning_rate": 1.0395477094476623e-06, "loss": 0.7157, "step": 267260 }, { "epoch": 22.22, "learning_rate": 1.0394368539201286e-06, "loss": 0.7335, "step": 267270 }, { "epoch": 22.22, "learning_rate": 1.039325998392595e-06, "loss": 0.7572, "step": 267280 }, { "epoch": 22.22, "learning_rate": 1.039215142865061e-06, "loss": 0.7799, "step": 267290 }, { "epoch": 22.22, "learning_rate": 1.0391042873375273e-06, "loss": 0.684, "step": 267300 }, { "epoch": 22.22, "learning_rate": 1.0389934318099936e-06, "loss": 0.7838, "step": 267310 }, { "epoch": 22.22, "learning_rate": 1.0388825762824599e-06, "loss": 0.7167, "step": 267320 }, { "epoch": 22.22, "learning_rate": 1.038771720754926e-06, "loss": 0.6982, "step": 267330 }, { "epoch": 22.22, "learning_rate": 1.0386608652273923e-06, "loss": 0.803, "step": 267340 }, { "epoch": 22.22, "learning_rate": 1.0385500096998586e-06, "loss": 0.7521, "step": 267350 }, { "epoch": 22.22, "learning_rate": 1.038439154172325e-06, "loss": 0.7979, "step": 267360 }, { "epoch": 22.22, "learning_rate": 1.0383282986447912e-06, "loss": 0.7405, "step": 267370 }, { "epoch": 22.22, "learning_rate": 1.0382174431172574e-06, "loss": 0.7402, "step": 267380 }, { "epoch": 22.23, "learning_rate": 1.0381065875897237e-06, "loss": 0.7868, "step": 267390 }, { "epoch": 22.23, "learning_rate": 1.0379957320621898e-06, "loss": 0.6915, "step": 267400 }, { "epoch": 22.23, "learning_rate": 1.0378848765346561e-06, "loss": 0.7379, "step": 267410 }, { "epoch": 22.23, "learning_rate": 1.0377740210071224e-06, "loss": 0.7775, "step": 267420 }, { "epoch": 22.23, "learning_rate": 1.0376631654795887e-06, "loss": 0.7661, "step": 267430 }, { "epoch": 22.23, "learning_rate": 1.0375523099520548e-06, "loss": 0.7944, "step": 267440 }, { "epoch": 22.23, "learning_rate": 1.037441454424521e-06, "loss": 0.8145, "step": 267450 }, { "epoch": 22.23, "learning_rate": 1.0373305988969874e-06, "loss": 0.7606, "step": 267460 }, { "epoch": 22.23, "learning_rate": 1.0372197433694537e-06, "loss": 0.8078, "step": 267470 }, { "epoch": 22.23, "learning_rate": 1.03710888784192e-06, "loss": 0.7395, "step": 267480 }, { "epoch": 22.23, "learning_rate": 1.0369980323143863e-06, "loss": 0.7807, "step": 267490 }, { "epoch": 22.23, "learning_rate": 1.0368871767868526e-06, "loss": 0.7623, "step": 267500 }, { "epoch": 22.24, "learning_rate": 1.0367763212593189e-06, "loss": 0.7363, "step": 267510 }, { "epoch": 22.24, "learning_rate": 1.036665465731785e-06, "loss": 0.7411, "step": 267520 }, { "epoch": 22.24, "learning_rate": 1.0365546102042512e-06, "loss": 0.7572, "step": 267530 }, { "epoch": 22.24, "learning_rate": 1.0364437546767175e-06, "loss": 0.8163, "step": 267540 }, { "epoch": 22.24, "learning_rate": 1.0363328991491838e-06, "loss": 0.7501, "step": 267550 }, { "epoch": 22.24, "learning_rate": 1.03622204362165e-06, "loss": 0.7643, "step": 267560 }, { "epoch": 22.24, "learning_rate": 1.0361111880941162e-06, "loss": 0.7212, "step": 267570 }, { "epoch": 22.24, "learning_rate": 1.0360003325665825e-06, "loss": 0.7851, "step": 267580 }, { "epoch": 22.24, "learning_rate": 1.0358894770390488e-06, "loss": 0.7651, "step": 267590 }, { "epoch": 22.24, "learning_rate": 1.0357786215115149e-06, "loss": 0.7086, "step": 267600 }, { "epoch": 22.24, "learning_rate": 1.0356677659839814e-06, "loss": 0.7214, "step": 267610 }, { "epoch": 22.24, "learning_rate": 1.0355569104564477e-06, "loss": 0.7141, "step": 267620 }, { "epoch": 22.25, "learning_rate": 1.035446054928914e-06, "loss": 0.7294, "step": 267630 }, { "epoch": 22.25, "learning_rate": 1.03533519940138e-06, "loss": 0.7817, "step": 267640 }, { "epoch": 22.25, "learning_rate": 1.0352243438738464e-06, "loss": 0.7759, "step": 267650 }, { "epoch": 22.25, "learning_rate": 1.0351134883463127e-06, "loss": 0.7216, "step": 267660 }, { "epoch": 22.25, "learning_rate": 1.035002632818779e-06, "loss": 0.7163, "step": 267670 }, { "epoch": 22.25, "learning_rate": 1.034891777291245e-06, "loss": 0.736, "step": 267680 }, { "epoch": 22.25, "learning_rate": 1.0347809217637113e-06, "loss": 0.7578, "step": 267690 }, { "epoch": 22.25, "learning_rate": 1.0346700662361776e-06, "loss": 0.7631, "step": 267700 }, { "epoch": 22.25, "learning_rate": 1.034559210708644e-06, "loss": 0.7865, "step": 267710 }, { "epoch": 22.25, "learning_rate": 1.03444835518111e-06, "loss": 0.7904, "step": 267720 }, { "epoch": 22.25, "learning_rate": 1.0343374996535765e-06, "loss": 0.7396, "step": 267730 }, { "epoch": 22.25, "learning_rate": 1.0342266441260428e-06, "loss": 0.8328, "step": 267740 }, { "epoch": 22.26, "learning_rate": 1.034115788598509e-06, "loss": 0.702, "step": 267750 }, { "epoch": 22.26, "learning_rate": 1.0340049330709752e-06, "loss": 0.745, "step": 267760 }, { "epoch": 22.26, "learning_rate": 1.0338940775434415e-06, "loss": 0.7987, "step": 267770 }, { "epoch": 22.26, "learning_rate": 1.0337832220159078e-06, "loss": 0.7579, "step": 267780 }, { "epoch": 22.26, "learning_rate": 1.033672366488374e-06, "loss": 0.8025, "step": 267790 }, { "epoch": 22.26, "learning_rate": 1.0335615109608402e-06, "loss": 0.7435, "step": 267800 }, { "epoch": 22.26, "learning_rate": 1.0334506554333065e-06, "loss": 0.7308, "step": 267810 }, { "epoch": 22.26, "learning_rate": 1.0333397999057727e-06, "loss": 0.6837, "step": 267820 }, { "epoch": 22.26, "learning_rate": 1.0332289443782388e-06, "loss": 0.7975, "step": 267830 }, { "epoch": 22.26, "learning_rate": 1.0331180888507051e-06, "loss": 0.801, "step": 267840 }, { "epoch": 22.26, "learning_rate": 1.0330072333231716e-06, "loss": 0.7692, "step": 267850 }, { "epoch": 22.26, "learning_rate": 1.032896377795638e-06, "loss": 0.7638, "step": 267860 }, { "epoch": 22.26, "learning_rate": 1.032785522268104e-06, "loss": 0.7108, "step": 267870 }, { "epoch": 22.27, "learning_rate": 1.0326746667405703e-06, "loss": 0.7426, "step": 267880 }, { "epoch": 22.27, "learning_rate": 1.0325638112130366e-06, "loss": 0.7948, "step": 267890 }, { "epoch": 22.27, "learning_rate": 1.032452955685503e-06, "loss": 0.7595, "step": 267900 }, { "epoch": 22.27, "learning_rate": 1.032342100157969e-06, "loss": 0.7608, "step": 267910 }, { "epoch": 22.27, "learning_rate": 1.0322312446304353e-06, "loss": 0.7422, "step": 267920 }, { "epoch": 22.27, "learning_rate": 1.0321203891029016e-06, "loss": 0.7882, "step": 267930 }, { "epoch": 22.27, "learning_rate": 1.0320095335753679e-06, "loss": 0.8236, "step": 267940 }, { "epoch": 22.27, "learning_rate": 1.031898678047834e-06, "loss": 0.754, "step": 267950 }, { "epoch": 22.27, "learning_rate": 1.0317878225203002e-06, "loss": 0.7015, "step": 267960 }, { "epoch": 22.27, "learning_rate": 1.0316769669927668e-06, "loss": 0.7344, "step": 267970 }, { "epoch": 22.27, "learning_rate": 1.031566111465233e-06, "loss": 0.7368, "step": 267980 }, { "epoch": 22.27, "learning_rate": 1.0314552559376991e-06, "loss": 0.7632, "step": 267990 }, { "epoch": 22.28, "learning_rate": 1.0313444004101654e-06, "loss": 0.7313, "step": 268000 }, { "epoch": 22.28, "learning_rate": 1.0312335448826317e-06, "loss": 0.7897, "step": 268010 }, { "epoch": 22.28, "learning_rate": 1.031122689355098e-06, "loss": 0.7281, "step": 268020 }, { "epoch": 22.28, "learning_rate": 1.031011833827564e-06, "loss": 0.7658, "step": 268030 }, { "epoch": 22.28, "learning_rate": 1.0309009783000304e-06, "loss": 0.7856, "step": 268040 }, { "epoch": 22.28, "learning_rate": 1.0307901227724967e-06, "loss": 0.7225, "step": 268050 }, { "epoch": 22.28, "learning_rate": 1.030679267244963e-06, "loss": 0.7515, "step": 268060 }, { "epoch": 22.28, "learning_rate": 1.030568411717429e-06, "loss": 0.7474, "step": 268070 }, { "epoch": 22.28, "learning_rate": 1.0304575561898954e-06, "loss": 0.7348, "step": 268080 }, { "epoch": 22.28, "learning_rate": 1.0303467006623617e-06, "loss": 0.7623, "step": 268090 }, { "epoch": 22.28, "learning_rate": 1.0302358451348282e-06, "loss": 0.7242, "step": 268100 }, { "epoch": 22.28, "learning_rate": 1.0301249896072943e-06, "loss": 0.7209, "step": 268110 }, { "epoch": 22.29, "learning_rate": 1.0300141340797606e-06, "loss": 0.7296, "step": 268120 }, { "epoch": 22.29, "learning_rate": 1.0299032785522268e-06, "loss": 0.7603, "step": 268130 }, { "epoch": 22.29, "learning_rate": 1.0297924230246931e-06, "loss": 0.7651, "step": 268140 }, { "epoch": 22.29, "learning_rate": 1.0296815674971592e-06, "loss": 0.744, "step": 268150 }, { "epoch": 22.29, "learning_rate": 1.0295707119696255e-06, "loss": 0.7065, "step": 268160 }, { "epoch": 22.29, "learning_rate": 1.0294598564420918e-06, "loss": 0.7229, "step": 268170 }, { "epoch": 22.29, "learning_rate": 1.0293490009145581e-06, "loss": 0.7737, "step": 268180 }, { "epoch": 22.29, "learning_rate": 1.0292381453870242e-06, "loss": 0.766, "step": 268190 }, { "epoch": 22.29, "learning_rate": 1.0291272898594905e-06, "loss": 0.6762, "step": 268200 }, { "epoch": 22.29, "learning_rate": 1.0290164343319568e-06, "loss": 0.7366, "step": 268210 }, { "epoch": 22.29, "learning_rate": 1.0289055788044233e-06, "loss": 0.7312, "step": 268220 }, { "epoch": 22.29, "learning_rate": 1.0287947232768894e-06, "loss": 0.7385, "step": 268230 }, { "epoch": 22.3, "learning_rate": 1.0286838677493557e-06, "loss": 0.7863, "step": 268240 }, { "epoch": 22.3, "learning_rate": 1.028573012221822e-06, "loss": 0.7762, "step": 268250 }, { "epoch": 22.3, "learning_rate": 1.028462156694288e-06, "loss": 0.7543, "step": 268260 }, { "epoch": 22.3, "learning_rate": 1.0283513011667543e-06, "loss": 0.7399, "step": 268270 }, { "epoch": 22.3, "learning_rate": 1.0282404456392206e-06, "loss": 0.7044, "step": 268280 }, { "epoch": 22.3, "learning_rate": 1.028129590111687e-06, "loss": 0.7852, "step": 268290 }, { "epoch": 22.3, "learning_rate": 1.028018734584153e-06, "loss": 0.7273, "step": 268300 }, { "epoch": 22.3, "learning_rate": 1.0279078790566193e-06, "loss": 0.6928, "step": 268310 }, { "epoch": 22.3, "learning_rate": 1.0277970235290856e-06, "loss": 0.7248, "step": 268320 }, { "epoch": 22.3, "learning_rate": 1.027686168001552e-06, "loss": 0.7672, "step": 268330 }, { "epoch": 22.3, "learning_rate": 1.0275753124740182e-06, "loss": 0.801, "step": 268340 }, { "epoch": 22.3, "learning_rate": 1.0274644569464845e-06, "loss": 0.7075, "step": 268350 }, { "epoch": 22.31, "learning_rate": 1.0273536014189508e-06, "loss": 0.7466, "step": 268360 }, { "epoch": 22.31, "learning_rate": 1.027242745891417e-06, "loss": 0.7466, "step": 268370 }, { "epoch": 22.31, "learning_rate": 1.0271318903638832e-06, "loss": 0.7212, "step": 268380 }, { "epoch": 22.31, "learning_rate": 1.0270210348363495e-06, "loss": 0.7633, "step": 268390 }, { "epoch": 22.31, "learning_rate": 1.0269101793088158e-06, "loss": 0.7485, "step": 268400 }, { "epoch": 22.31, "learning_rate": 1.026799323781282e-06, "loss": 0.7702, "step": 268410 }, { "epoch": 22.31, "learning_rate": 1.0266884682537481e-06, "loss": 0.7241, "step": 268420 }, { "epoch": 22.31, "learning_rate": 1.0265776127262144e-06, "loss": 0.7761, "step": 268430 }, { "epoch": 22.31, "learning_rate": 1.0264667571986807e-06, "loss": 0.7997, "step": 268440 }, { "epoch": 22.31, "learning_rate": 1.026355901671147e-06, "loss": 0.7113, "step": 268450 }, { "epoch": 22.31, "learning_rate": 1.0262450461436131e-06, "loss": 0.6801, "step": 268460 }, { "epoch": 22.31, "learning_rate": 1.0261341906160796e-06, "loss": 0.7057, "step": 268470 }, { "epoch": 22.32, "learning_rate": 1.026023335088546e-06, "loss": 0.748, "step": 268480 }, { "epoch": 22.32, "learning_rate": 1.0259124795610122e-06, "loss": 0.7554, "step": 268490 }, { "epoch": 22.32, "learning_rate": 1.0258016240334783e-06, "loss": 0.7527, "step": 268500 }, { "epoch": 22.32, "learning_rate": 1.0256907685059446e-06, "loss": 0.7464, "step": 268510 }, { "epoch": 22.32, "learning_rate": 1.0255799129784109e-06, "loss": 0.7507, "step": 268520 }, { "epoch": 22.32, "learning_rate": 1.0254690574508772e-06, "loss": 0.7061, "step": 268530 }, { "epoch": 22.32, "learning_rate": 1.0253582019233433e-06, "loss": 0.7242, "step": 268540 }, { "epoch": 22.32, "learning_rate": 1.0252473463958096e-06, "loss": 0.8082, "step": 268550 }, { "epoch": 22.32, "learning_rate": 1.0251364908682759e-06, "loss": 0.7287, "step": 268560 }, { "epoch": 22.32, "learning_rate": 1.0250256353407421e-06, "loss": 0.7072, "step": 268570 }, { "epoch": 22.32, "learning_rate": 1.0249147798132082e-06, "loss": 0.7479, "step": 268580 }, { "epoch": 22.32, "learning_rate": 1.0248039242856747e-06, "loss": 0.7171, "step": 268590 }, { "epoch": 22.33, "learning_rate": 1.024693068758141e-06, "loss": 0.7468, "step": 268600 }, { "epoch": 22.33, "learning_rate": 1.0245822132306073e-06, "loss": 0.7193, "step": 268610 }, { "epoch": 22.33, "learning_rate": 1.0244713577030734e-06, "loss": 0.7358, "step": 268620 }, { "epoch": 22.33, "learning_rate": 1.0243605021755397e-06, "loss": 0.7829, "step": 268630 }, { "epoch": 22.33, "learning_rate": 1.024249646648006e-06, "loss": 0.8076, "step": 268640 }, { "epoch": 22.33, "learning_rate": 1.024138791120472e-06, "loss": 0.7373, "step": 268650 }, { "epoch": 22.33, "learning_rate": 1.0240279355929384e-06, "loss": 0.7419, "step": 268660 }, { "epoch": 22.33, "learning_rate": 1.0239170800654047e-06, "loss": 0.7116, "step": 268670 }, { "epoch": 22.33, "learning_rate": 1.023806224537871e-06, "loss": 0.7625, "step": 268680 }, { "epoch": 22.33, "learning_rate": 1.023695369010337e-06, "loss": 0.8484, "step": 268690 }, { "epoch": 22.33, "learning_rate": 1.0235845134828034e-06, "loss": 0.7042, "step": 268700 }, { "epoch": 22.33, "learning_rate": 1.0234736579552699e-06, "loss": 0.7596, "step": 268710 }, { "epoch": 22.34, "learning_rate": 1.0233628024277362e-06, "loss": 0.7166, "step": 268720 }, { "epoch": 22.34, "learning_rate": 1.0232519469002022e-06, "loss": 0.7555, "step": 268730 }, { "epoch": 22.34, "learning_rate": 1.0231410913726685e-06, "loss": 0.8108, "step": 268740 }, { "epoch": 22.34, "learning_rate": 1.0230302358451348e-06, "loss": 0.701, "step": 268750 }, { "epoch": 22.34, "learning_rate": 1.0229193803176011e-06, "loss": 0.7353, "step": 268760 }, { "epoch": 22.34, "learning_rate": 1.0228085247900672e-06, "loss": 0.7723, "step": 268770 }, { "epoch": 22.34, "learning_rate": 1.0226976692625335e-06, "loss": 0.7889, "step": 268780 }, { "epoch": 22.34, "learning_rate": 1.0225868137349998e-06, "loss": 0.8354, "step": 268790 }, { "epoch": 22.34, "learning_rate": 1.022475958207466e-06, "loss": 0.7231, "step": 268800 }, { "epoch": 22.34, "learning_rate": 1.0223651026799322e-06, "loss": 0.6602, "step": 268810 }, { "epoch": 22.34, "learning_rate": 1.0222542471523985e-06, "loss": 0.7274, "step": 268820 }, { "epoch": 22.34, "learning_rate": 1.022143391624865e-06, "loss": 0.7347, "step": 268830 }, { "epoch": 22.35, "learning_rate": 1.0220325360973313e-06, "loss": 0.8075, "step": 268840 }, { "epoch": 22.35, "learning_rate": 1.0219216805697974e-06, "loss": 0.7285, "step": 268850 }, { "epoch": 22.35, "learning_rate": 1.0218108250422637e-06, "loss": 0.8107, "step": 268860 }, { "epoch": 22.35, "learning_rate": 1.02169996951473e-06, "loss": 0.6958, "step": 268870 }, { "epoch": 22.35, "learning_rate": 1.0215891139871962e-06, "loss": 0.7247, "step": 268880 }, { "epoch": 22.35, "learning_rate": 1.0214782584596623e-06, "loss": 0.7855, "step": 268890 }, { "epoch": 22.35, "learning_rate": 1.0213674029321286e-06, "loss": 0.7113, "step": 268900 }, { "epoch": 22.35, "learning_rate": 1.021256547404595e-06, "loss": 0.7408, "step": 268910 }, { "epoch": 22.35, "learning_rate": 1.0211456918770612e-06, "loss": 0.7588, "step": 268920 }, { "epoch": 22.35, "learning_rate": 1.0210348363495273e-06, "loss": 0.7199, "step": 268930 }, { "epoch": 22.35, "learning_rate": 1.0209239808219936e-06, "loss": 0.8225, "step": 268940 }, { "epoch": 22.35, "learning_rate": 1.0208131252944599e-06, "loss": 0.7459, "step": 268950 }, { "epoch": 22.36, "learning_rate": 1.0207022697669264e-06, "loss": 0.7064, "step": 268960 }, { "epoch": 22.36, "learning_rate": 1.0205914142393925e-06, "loss": 0.6707, "step": 268970 }, { "epoch": 22.36, "learning_rate": 1.0204805587118588e-06, "loss": 0.7972, "step": 268980 }, { "epoch": 22.36, "learning_rate": 1.020369703184325e-06, "loss": 0.7526, "step": 268990 }, { "epoch": 22.36, "learning_rate": 1.0202588476567914e-06, "loss": 0.7323, "step": 269000 }, { "epoch": 22.36, "learning_rate": 1.0201479921292574e-06, "loss": 0.7698, "step": 269010 }, { "epoch": 22.36, "learning_rate": 1.0200371366017237e-06, "loss": 0.7242, "step": 269020 }, { "epoch": 22.36, "learning_rate": 1.01992628107419e-06, "loss": 0.7776, "step": 269030 }, { "epoch": 22.36, "learning_rate": 1.0198154255466561e-06, "loss": 0.7847, "step": 269040 }, { "epoch": 22.36, "learning_rate": 1.0197045700191224e-06, "loss": 0.7316, "step": 269050 }, { "epoch": 22.36, "learning_rate": 1.0195937144915887e-06, "loss": 0.7197, "step": 269060 }, { "epoch": 22.36, "learning_rate": 1.019482858964055e-06, "loss": 0.7243, "step": 269070 }, { "epoch": 22.37, "learning_rate": 1.0193720034365215e-06, "loss": 0.7744, "step": 269080 }, { "epoch": 22.37, "learning_rate": 1.0192611479089876e-06, "loss": 0.8441, "step": 269090 }, { "epoch": 22.37, "learning_rate": 1.0191502923814539e-06, "loss": 0.7245, "step": 269100 }, { "epoch": 22.37, "learning_rate": 1.0190394368539202e-06, "loss": 0.6988, "step": 269110 }, { "epoch": 22.37, "learning_rate": 1.0189285813263863e-06, "loss": 0.7378, "step": 269120 }, { "epoch": 22.37, "learning_rate": 1.0188177257988526e-06, "loss": 0.7347, "step": 269130 }, { "epoch": 22.37, "learning_rate": 1.0187068702713189e-06, "loss": 0.7725, "step": 269140 }, { "epoch": 22.37, "learning_rate": 1.0185960147437852e-06, "loss": 0.7615, "step": 269150 }, { "epoch": 22.37, "learning_rate": 1.0184851592162512e-06, "loss": 0.7902, "step": 269160 }, { "epoch": 22.37, "learning_rate": 1.0183743036887175e-06, "loss": 0.7035, "step": 269170 }, { "epoch": 22.37, "learning_rate": 1.0182634481611838e-06, "loss": 0.7914, "step": 269180 }, { "epoch": 22.37, "learning_rate": 1.0181525926336501e-06, "loss": 0.7283, "step": 269190 }, { "epoch": 22.38, "learning_rate": 1.0180417371061164e-06, "loss": 0.7667, "step": 269200 }, { "epoch": 22.38, "learning_rate": 1.0179308815785827e-06, "loss": 0.7647, "step": 269210 }, { "epoch": 22.38, "learning_rate": 1.017820026051049e-06, "loss": 0.7312, "step": 269220 }, { "epoch": 22.38, "learning_rate": 1.0177091705235153e-06, "loss": 0.7746, "step": 269230 }, { "epoch": 22.38, "learning_rate": 1.0175983149959814e-06, "loss": 0.7922, "step": 269240 }, { "epoch": 22.38, "learning_rate": 1.0174874594684477e-06, "loss": 0.7557, "step": 269250 }, { "epoch": 22.38, "learning_rate": 1.017376603940914e-06, "loss": 0.7691, "step": 269260 }, { "epoch": 22.38, "learning_rate": 1.0172657484133803e-06, "loss": 0.7262, "step": 269270 }, { "epoch": 22.38, "learning_rate": 1.0171659784385998e-06, "loss": 0.7043, "step": 269280 }, { "epoch": 22.38, "learning_rate": 1.0170551229110661e-06, "loss": 0.8057, "step": 269290 }, { "epoch": 22.38, "learning_rate": 1.0169442673835324e-06, "loss": 0.7713, "step": 269300 }, { "epoch": 22.38, "learning_rate": 1.0168334118559987e-06, "loss": 0.7732, "step": 269310 }, { "epoch": 22.39, "learning_rate": 1.016722556328465e-06, "loss": 0.7565, "step": 269320 }, { "epoch": 22.39, "learning_rate": 1.016611700800931e-06, "loss": 0.7278, "step": 269330 }, { "epoch": 22.39, "learning_rate": 1.0165008452733974e-06, "loss": 0.8034, "step": 269340 }, { "epoch": 22.39, "learning_rate": 1.0163899897458637e-06, "loss": 0.8052, "step": 269350 }, { "epoch": 22.39, "learning_rate": 1.01627913421833e-06, "loss": 0.7363, "step": 269360 }, { "epoch": 22.39, "learning_rate": 1.016168278690796e-06, "loss": 0.6949, "step": 269370 }, { "epoch": 22.39, "learning_rate": 1.0160574231632623e-06, "loss": 0.7669, "step": 269380 }, { "epoch": 22.39, "learning_rate": 1.0159465676357286e-06, "loss": 0.8463, "step": 269390 }, { "epoch": 22.39, "learning_rate": 1.015835712108195e-06, "loss": 0.7253, "step": 269400 }, { "epoch": 22.39, "learning_rate": 1.0157248565806612e-06, "loss": 0.7582, "step": 269410 }, { "epoch": 22.39, "learning_rate": 1.0156140010531275e-06, "loss": 0.7406, "step": 269420 }, { "epoch": 22.39, "learning_rate": 1.0155031455255938e-06, "loss": 0.6951, "step": 269430 }, { "epoch": 22.4, "learning_rate": 1.0153922899980601e-06, "loss": 0.7617, "step": 269440 }, { "epoch": 22.4, "learning_rate": 1.0152814344705262e-06, "loss": 0.7628, "step": 269450 }, { "epoch": 22.4, "learning_rate": 1.0151705789429925e-06, "loss": 0.7025, "step": 269460 }, { "epoch": 22.4, "learning_rate": 1.0150597234154588e-06, "loss": 0.7046, "step": 269470 }, { "epoch": 22.4, "learning_rate": 1.014948867887925e-06, "loss": 0.741, "step": 269480 }, { "epoch": 22.4, "learning_rate": 1.0148380123603912e-06, "loss": 0.771, "step": 269490 }, { "epoch": 22.4, "learning_rate": 1.0147271568328575e-06, "loss": 0.7746, "step": 269500 }, { "epoch": 22.4, "learning_rate": 1.0146163013053238e-06, "loss": 0.7323, "step": 269510 }, { "epoch": 22.4, "learning_rate": 1.01450544577779e-06, "loss": 0.7041, "step": 269520 }, { "epoch": 22.4, "learning_rate": 1.0143945902502561e-06, "loss": 0.6512, "step": 269530 }, { "epoch": 22.4, "learning_rate": 1.0142837347227226e-06, "loss": 0.7505, "step": 269540 }, { "epoch": 22.4, "learning_rate": 1.014172879195189e-06, "loss": 0.7397, "step": 269550 }, { "epoch": 22.41, "learning_rate": 1.0140620236676552e-06, "loss": 0.7147, "step": 269560 }, { "epoch": 22.41, "learning_rate": 1.0139511681401213e-06, "loss": 0.7512, "step": 269570 }, { "epoch": 22.41, "learning_rate": 1.0138403126125876e-06, "loss": 0.7155, "step": 269580 }, { "epoch": 22.41, "learning_rate": 1.013729457085054e-06, "loss": 0.7561, "step": 269590 }, { "epoch": 22.41, "learning_rate": 1.01361860155752e-06, "loss": 0.7026, "step": 269600 }, { "epoch": 22.41, "learning_rate": 1.0135077460299863e-06, "loss": 0.7597, "step": 269610 }, { "epoch": 22.41, "learning_rate": 1.0133968905024526e-06, "loss": 0.7331, "step": 269620 }, { "epoch": 22.41, "learning_rate": 1.0132860349749189e-06, "loss": 0.748, "step": 269630 }, { "epoch": 22.41, "learning_rate": 1.013175179447385e-06, "loss": 0.7939, "step": 269640 }, { "epoch": 22.41, "learning_rate": 1.0130643239198513e-06, "loss": 0.7261, "step": 269650 }, { "epoch": 22.41, "learning_rate": 1.0129534683923178e-06, "loss": 0.841, "step": 269660 }, { "epoch": 22.41, "learning_rate": 1.012842612864784e-06, "loss": 0.7502, "step": 269670 }, { "epoch": 22.42, "learning_rate": 1.0127317573372501e-06, "loss": 0.757, "step": 269680 }, { "epoch": 22.42, "learning_rate": 1.0126209018097164e-06, "loss": 0.8402, "step": 269690 }, { "epoch": 22.42, "learning_rate": 1.0125100462821827e-06, "loss": 0.7177, "step": 269700 }, { "epoch": 22.42, "learning_rate": 1.012399190754649e-06, "loss": 0.7365, "step": 269710 }, { "epoch": 22.42, "learning_rate": 1.0122883352271151e-06, "loss": 0.7408, "step": 269720 }, { "epoch": 22.42, "learning_rate": 1.0121774796995814e-06, "loss": 0.7512, "step": 269730 }, { "epoch": 22.42, "learning_rate": 1.0120666241720477e-06, "loss": 0.8041, "step": 269740 }, { "epoch": 22.42, "learning_rate": 1.011955768644514e-06, "loss": 0.7477, "step": 269750 }, { "epoch": 22.42, "learning_rate": 1.01184491311698e-06, "loss": 0.7659, "step": 269760 }, { "epoch": 22.42, "learning_rate": 1.0117340575894464e-06, "loss": 0.7835, "step": 269770 }, { "epoch": 22.42, "learning_rate": 1.0116232020619129e-06, "loss": 0.7408, "step": 269780 }, { "epoch": 22.42, "learning_rate": 1.0115123465343792e-06, "loss": 0.7877, "step": 269790 }, { "epoch": 22.43, "learning_rate": 1.0114014910068453e-06, "loss": 0.7967, "step": 269800 }, { "epoch": 22.43, "learning_rate": 1.0112906354793116e-06, "loss": 0.7458, "step": 269810 }, { "epoch": 22.43, "learning_rate": 1.0111797799517779e-06, "loss": 0.6794, "step": 269820 }, { "epoch": 22.43, "learning_rate": 1.0110689244242442e-06, "loss": 0.7737, "step": 269830 }, { "epoch": 22.43, "learning_rate": 1.0109580688967102e-06, "loss": 0.7476, "step": 269840 }, { "epoch": 22.43, "learning_rate": 1.0108472133691765e-06, "loss": 0.7178, "step": 269850 }, { "epoch": 22.43, "learning_rate": 1.0107363578416428e-06, "loss": 0.772, "step": 269860 }, { "epoch": 22.43, "learning_rate": 1.0106255023141091e-06, "loss": 0.7594, "step": 269870 }, { "epoch": 22.43, "learning_rate": 1.0105146467865752e-06, "loss": 0.7211, "step": 269880 }, { "epoch": 22.43, "learning_rate": 1.0104037912590415e-06, "loss": 0.7689, "step": 269890 }, { "epoch": 22.43, "learning_rate": 1.0102929357315078e-06, "loss": 0.7131, "step": 269900 }, { "epoch": 22.43, "learning_rate": 1.0101820802039743e-06, "loss": 0.7357, "step": 269910 }, { "epoch": 22.44, "learning_rate": 1.0100712246764404e-06, "loss": 0.7821, "step": 269920 }, { "epoch": 22.44, "learning_rate": 1.0099603691489067e-06, "loss": 0.7409, "step": 269930 }, { "epoch": 22.44, "learning_rate": 1.009849513621373e-06, "loss": 0.7717, "step": 269940 }, { "epoch": 22.44, "learning_rate": 1.0097386580938393e-06, "loss": 0.7655, "step": 269950 }, { "epoch": 22.44, "learning_rate": 1.0096278025663054e-06, "loss": 0.7992, "step": 269960 }, { "epoch": 22.44, "learning_rate": 1.0095169470387717e-06, "loss": 0.6819, "step": 269970 }, { "epoch": 22.44, "learning_rate": 1.009406091511238e-06, "loss": 0.7766, "step": 269980 }, { "epoch": 22.44, "learning_rate": 1.0092952359837042e-06, "loss": 0.764, "step": 269990 }, { "epoch": 22.44, "learning_rate": 1.0091843804561703e-06, "loss": 0.7148, "step": 270000 }, { "epoch": 22.44, "learning_rate": 1.0090735249286366e-06, "loss": 0.7583, "step": 270010 }, { "epoch": 22.44, "learning_rate": 1.008962669401103e-06, "loss": 0.7143, "step": 270020 }, { "epoch": 22.44, "learning_rate": 1.0088518138735694e-06, "loss": 0.7506, "step": 270030 }, { "epoch": 22.45, "learning_rate": 1.0087409583460355e-06, "loss": 0.772, "step": 270040 }, { "epoch": 22.45, "learning_rate": 1.0086301028185018e-06, "loss": 0.77, "step": 270050 }, { "epoch": 22.45, "learning_rate": 1.008519247290968e-06, "loss": 0.7977, "step": 270060 }, { "epoch": 22.45, "learning_rate": 1.0084083917634342e-06, "loss": 0.7593, "step": 270070 }, { "epoch": 22.45, "learning_rate": 1.0082975362359005e-06, "loss": 0.7791, "step": 270080 }, { "epoch": 22.45, "learning_rate": 1.0081866807083668e-06, "loss": 0.7468, "step": 270090 }, { "epoch": 22.45, "learning_rate": 1.008075825180833e-06, "loss": 0.7378, "step": 270100 }, { "epoch": 22.45, "learning_rate": 1.0079649696532992e-06, "loss": 0.7501, "step": 270110 }, { "epoch": 22.45, "learning_rate": 1.0078541141257654e-06, "loss": 0.7166, "step": 270120 }, { "epoch": 22.45, "learning_rate": 1.0077432585982317e-06, "loss": 0.7801, "step": 270130 }, { "epoch": 22.45, "learning_rate": 1.007632403070698e-06, "loss": 0.8082, "step": 270140 }, { "epoch": 22.45, "learning_rate": 1.0075215475431643e-06, "loss": 0.7497, "step": 270150 }, { "epoch": 22.46, "learning_rate": 1.0074106920156306e-06, "loss": 0.717, "step": 270160 }, { "epoch": 22.46, "learning_rate": 1.007299836488097e-06, "loss": 0.7016, "step": 270170 }, { "epoch": 22.46, "learning_rate": 1.0071889809605632e-06, "loss": 0.7779, "step": 270180 }, { "epoch": 22.46, "learning_rate": 1.0070781254330293e-06, "loss": 0.8177, "step": 270190 }, { "epoch": 22.46, "learning_rate": 1.0069672699054956e-06, "loss": 0.7404, "step": 270200 }, { "epoch": 22.46, "learning_rate": 1.006856414377962e-06, "loss": 0.6958, "step": 270210 }, { "epoch": 22.46, "learning_rate": 1.0067455588504282e-06, "loss": 0.7658, "step": 270220 }, { "epoch": 22.46, "learning_rate": 1.0066347033228943e-06, "loss": 0.7611, "step": 270230 }, { "epoch": 22.46, "learning_rate": 1.0065238477953606e-06, "loss": 0.7587, "step": 270240 }, { "epoch": 22.46, "learning_rate": 1.0064129922678269e-06, "loss": 0.6981, "step": 270250 }, { "epoch": 22.46, "learning_rate": 1.0063021367402932e-06, "loss": 0.7441, "step": 270260 }, { "epoch": 22.46, "learning_rate": 1.0061912812127595e-06, "loss": 0.7282, "step": 270270 }, { "epoch": 22.47, "learning_rate": 1.0060804256852258e-06, "loss": 0.7259, "step": 270280 }, { "epoch": 22.47, "learning_rate": 1.005969570157692e-06, "loss": 0.7643, "step": 270290 }, { "epoch": 22.47, "learning_rate": 1.0058587146301583e-06, "loss": 0.7962, "step": 270300 }, { "epoch": 22.47, "learning_rate": 1.0057478591026244e-06, "loss": 0.6992, "step": 270310 }, { "epoch": 22.47, "learning_rate": 1.0056370035750907e-06, "loss": 0.7292, "step": 270320 }, { "epoch": 22.47, "learning_rate": 1.005526148047557e-06, "loss": 0.7034, "step": 270330 }, { "epoch": 22.47, "learning_rate": 1.0054152925200233e-06, "loss": 0.7608, "step": 270340 }, { "epoch": 22.47, "learning_rate": 1.0053044369924894e-06, "loss": 0.7477, "step": 270350 }, { "epoch": 22.47, "learning_rate": 1.0051935814649557e-06, "loss": 0.7535, "step": 270360 }, { "epoch": 22.47, "learning_rate": 1.005082725937422e-06, "loss": 0.7035, "step": 270370 }, { "epoch": 22.47, "learning_rate": 1.0049718704098883e-06, "loss": 0.7136, "step": 270380 }, { "epoch": 22.47, "learning_rate": 1.0048610148823544e-06, "loss": 0.7488, "step": 270390 }, { "epoch": 22.48, "learning_rate": 1.0047501593548209e-06, "loss": 0.6853, "step": 270400 }, { "epoch": 22.48, "learning_rate": 1.0046393038272872e-06, "loss": 0.7353, "step": 270410 }, { "epoch": 22.48, "learning_rate": 1.0045284482997535e-06, "loss": 0.7461, "step": 270420 }, { "epoch": 22.48, "learning_rate": 1.0044175927722195e-06, "loss": 0.7862, "step": 270430 }, { "epoch": 22.48, "learning_rate": 1.0043067372446858e-06, "loss": 0.8005, "step": 270440 }, { "epoch": 22.48, "learning_rate": 1.0041958817171521e-06, "loss": 0.753, "step": 270450 }, { "epoch": 22.48, "learning_rate": 1.0040850261896182e-06, "loss": 0.7157, "step": 270460 }, { "epoch": 22.48, "learning_rate": 1.0039741706620845e-06, "loss": 0.7369, "step": 270470 }, { "epoch": 22.48, "learning_rate": 1.0038633151345508e-06, "loss": 0.754, "step": 270480 }, { "epoch": 22.48, "learning_rate": 1.0037524596070171e-06, "loss": 0.7632, "step": 270490 }, { "epoch": 22.48, "learning_rate": 1.0036416040794832e-06, "loss": 0.7257, "step": 270500 }, { "epoch": 22.48, "learning_rate": 1.0035307485519495e-06, "loss": 0.7818, "step": 270510 }, { "epoch": 22.49, "learning_rate": 1.003419893024416e-06, "loss": 0.7279, "step": 270520 }, { "epoch": 22.49, "learning_rate": 1.0033090374968823e-06, "loss": 0.7491, "step": 270530 }, { "epoch": 22.49, "learning_rate": 1.0031981819693484e-06, "loss": 0.7635, "step": 270540 }, { "epoch": 22.49, "learning_rate": 1.0030873264418147e-06, "loss": 0.7546, "step": 270550 }, { "epoch": 22.49, "learning_rate": 1.002976470914281e-06, "loss": 0.6882, "step": 270560 }, { "epoch": 22.49, "learning_rate": 1.0028656153867473e-06, "loss": 0.7416, "step": 270570 }, { "epoch": 22.49, "learning_rate": 1.0027547598592133e-06, "loss": 0.6667, "step": 270580 }, { "epoch": 22.49, "learning_rate": 1.0026439043316796e-06, "loss": 0.8094, "step": 270590 }, { "epoch": 22.49, "learning_rate": 1.002533048804146e-06, "loss": 0.7449, "step": 270600 }, { "epoch": 22.49, "learning_rate": 1.0024221932766122e-06, "loss": 0.7383, "step": 270610 }, { "epoch": 22.49, "learning_rate": 1.0023113377490783e-06, "loss": 0.715, "step": 270620 }, { "epoch": 22.49, "learning_rate": 1.0022004822215446e-06, "loss": 0.7386, "step": 270630 }, { "epoch": 22.5, "learning_rate": 1.0020896266940111e-06, "loss": 0.7474, "step": 270640 }, { "epoch": 22.5, "learning_rate": 1.0019787711664774e-06, "loss": 0.7103, "step": 270650 }, { "epoch": 22.5, "learning_rate": 1.0018679156389435e-06, "loss": 0.7554, "step": 270660 }, { "epoch": 22.5, "learning_rate": 1.0017570601114098e-06, "loss": 0.7177, "step": 270670 }, { "epoch": 22.5, "learning_rate": 1.001646204583876e-06, "loss": 0.7097, "step": 270680 }, { "epoch": 22.5, "learning_rate": 1.0015353490563424e-06, "loss": 0.7836, "step": 270690 }, { "epoch": 22.5, "learning_rate": 1.0014244935288085e-06, "loss": 0.7633, "step": 270700 }, { "epoch": 22.5, "learning_rate": 1.0013136380012748e-06, "loss": 0.7451, "step": 270710 }, { "epoch": 22.5, "learning_rate": 1.001202782473741e-06, "loss": 0.6724, "step": 270720 }, { "epoch": 22.5, "learning_rate": 1.0010919269462073e-06, "loss": 0.7765, "step": 270730 }, { "epoch": 22.5, "learning_rate": 1.0009810714186734e-06, "loss": 0.7933, "step": 270740 }, { "epoch": 22.5, "learning_rate": 1.0008702158911397e-06, "loss": 0.79, "step": 270750 }, { "epoch": 22.51, "learning_rate": 1.000759360363606e-06, "loss": 0.761, "step": 270760 }, { "epoch": 22.51, "learning_rate": 1.0006485048360725e-06, "loss": 0.7561, "step": 270770 }, { "epoch": 22.51, "learning_rate": 1.0005376493085386e-06, "loss": 0.7011, "step": 270780 }, { "epoch": 22.51, "learning_rate": 1.000426793781005e-06, "loss": 0.8247, "step": 270790 }, { "epoch": 22.51, "learning_rate": 1.0003159382534712e-06, "loss": 0.7446, "step": 270800 }, { "epoch": 22.51, "learning_rate": 1.0002050827259375e-06, "loss": 0.7647, "step": 270810 }, { "epoch": 22.51, "learning_rate": 1.0000942271984036e-06, "loss": 0.7171, "step": 270820 }, { "epoch": 22.51, "learning_rate": 9.999833716708699e-07, "loss": 0.7003, "step": 270830 }, { "epoch": 22.51, "learning_rate": 9.998725161433362e-07, "loss": 0.8359, "step": 270840 }, { "epoch": 22.51, "learning_rate": 9.997616606158023e-07, "loss": 0.7032, "step": 270850 }, { "epoch": 22.51, "learning_rate": 9.996508050882688e-07, "loss": 0.7349, "step": 270860 }, { "epoch": 22.51, "learning_rate": 9.995399495607348e-07, "loss": 0.7779, "step": 270870 }, { "epoch": 22.52, "learning_rate": 9.994290940332011e-07, "loss": 0.7376, "step": 270880 }, { "epoch": 22.52, "learning_rate": 9.993182385056674e-07, "loss": 0.8612, "step": 270890 }, { "epoch": 22.52, "learning_rate": 9.992073829781337e-07, "loss": 0.7477, "step": 270900 }, { "epoch": 22.52, "learning_rate": 9.990965274505998e-07, "loss": 0.7033, "step": 270910 }, { "epoch": 22.52, "learning_rate": 9.989856719230663e-07, "loss": 0.7199, "step": 270920 }, { "epoch": 22.52, "learning_rate": 9.988748163955324e-07, "loss": 0.7528, "step": 270930 }, { "epoch": 22.52, "learning_rate": 9.987639608679987e-07, "loss": 0.7871, "step": 270940 }, { "epoch": 22.52, "learning_rate": 9.98653105340465e-07, "loss": 0.8144, "step": 270950 }, { "epoch": 22.52, "learning_rate": 9.985422498129313e-07, "loss": 0.7342, "step": 270960 }, { "epoch": 22.52, "learning_rate": 9.984313942853974e-07, "loss": 0.7364, "step": 270970 }, { "epoch": 22.52, "learning_rate": 9.983205387578639e-07, "loss": 0.7023, "step": 270980 }, { "epoch": 22.52, "learning_rate": 9.9820968323033e-07, "loss": 0.7619, "step": 270990 }, { "epoch": 22.53, "learning_rate": 9.980988277027963e-07, "loss": 0.7509, "step": 271000 }, { "epoch": 22.53, "learning_rate": 9.979879721752626e-07, "loss": 0.7008, "step": 271010 }, { "epoch": 22.53, "learning_rate": 9.978771166477289e-07, "loss": 0.7646, "step": 271020 }, { "epoch": 22.53, "learning_rate": 9.97766261120195e-07, "loss": 0.7097, "step": 271030 }, { "epoch": 22.53, "learning_rate": 9.976554055926614e-07, "loss": 0.8367, "step": 271040 }, { "epoch": 22.53, "learning_rate": 9.975445500651275e-07, "loss": 0.7424, "step": 271050 }, { "epoch": 22.53, "learning_rate": 9.974336945375938e-07, "loss": 0.802, "step": 271060 }, { "epoch": 22.53, "learning_rate": 9.973228390100601e-07, "loss": 0.715, "step": 271070 }, { "epoch": 22.53, "learning_rate": 9.972119834825264e-07, "loss": 0.7559, "step": 271080 }, { "epoch": 22.53, "learning_rate": 9.971011279549925e-07, "loss": 0.7783, "step": 271090 }, { "epoch": 22.53, "learning_rate": 9.96990272427459e-07, "loss": 0.7523, "step": 271100 }, { "epoch": 22.53, "learning_rate": 9.96879416899925e-07, "loss": 0.7468, "step": 271110 }, { "epoch": 22.54, "learning_rate": 9.967685613723914e-07, "loss": 0.7431, "step": 271120 }, { "epoch": 22.54, "learning_rate": 9.966577058448577e-07, "loss": 0.7297, "step": 271130 }, { "epoch": 22.54, "learning_rate": 9.96546850317324e-07, "loss": 0.78, "step": 271140 }, { "epoch": 22.54, "learning_rate": 9.9643599478979e-07, "loss": 0.7851, "step": 271150 }, { "epoch": 22.54, "learning_rate": 9.963251392622564e-07, "loss": 0.7469, "step": 271160 }, { "epoch": 22.54, "learning_rate": 9.962142837347226e-07, "loss": 0.7022, "step": 271170 }, { "epoch": 22.54, "learning_rate": 9.96103428207189e-07, "loss": 0.7547, "step": 271180 }, { "epoch": 22.54, "learning_rate": 9.959925726796552e-07, "loss": 0.7723, "step": 271190 }, { "epoch": 22.54, "learning_rate": 9.958817171521215e-07, "loss": 0.6875, "step": 271200 }, { "epoch": 22.54, "learning_rate": 9.957708616245876e-07, "loss": 0.7573, "step": 271210 }, { "epoch": 22.54, "learning_rate": 9.95660006097054e-07, "loss": 0.6872, "step": 271220 }, { "epoch": 22.54, "learning_rate": 9.955491505695202e-07, "loss": 0.7386, "step": 271230 }, { "epoch": 22.55, "learning_rate": 9.954382950419865e-07, "loss": 0.7817, "step": 271240 }, { "epoch": 22.55, "learning_rate": 9.953274395144528e-07, "loss": 0.7976, "step": 271250 }, { "epoch": 22.55, "learning_rate": 9.95216583986919e-07, "loss": 0.7135, "step": 271260 }, { "epoch": 22.55, "learning_rate": 9.951057284593852e-07, "loss": 0.7731, "step": 271270 }, { "epoch": 22.55, "learning_rate": 9.949948729318515e-07, "loss": 0.7471, "step": 271280 }, { "epoch": 22.55, "learning_rate": 9.948840174043178e-07, "loss": 0.7646, "step": 271290 }, { "epoch": 22.55, "learning_rate": 9.94773161876784e-07, "loss": 0.759, "step": 271300 }, { "epoch": 22.55, "learning_rate": 9.946623063492504e-07, "loss": 0.7844, "step": 271310 }, { "epoch": 22.55, "learning_rate": 9.945514508217164e-07, "loss": 0.8222, "step": 271320 }, { "epoch": 22.55, "learning_rate": 9.944405952941827e-07, "loss": 0.7217, "step": 271330 }, { "epoch": 22.55, "learning_rate": 9.94329739766649e-07, "loss": 0.733, "step": 271340 }, { "epoch": 22.55, "learning_rate": 9.942188842391153e-07, "loss": 0.6914, "step": 271350 }, { "epoch": 22.56, "learning_rate": 9.941080287115816e-07, "loss": 0.7586, "step": 271360 }, { "epoch": 22.56, "learning_rate": 9.93997173184048e-07, "loss": 0.6965, "step": 271370 }, { "epoch": 22.56, "learning_rate": 9.93886317656514e-07, "loss": 0.7819, "step": 271380 }, { "epoch": 22.56, "learning_rate": 9.937754621289803e-07, "loss": 0.7185, "step": 271390 }, { "epoch": 22.56, "learning_rate": 9.936646066014466e-07, "loss": 0.7249, "step": 271400 }, { "epoch": 22.56, "learning_rate": 9.935537510739129e-07, "loss": 0.7641, "step": 271410 }, { "epoch": 22.56, "learning_rate": 9.934428955463792e-07, "loss": 0.7172, "step": 271420 }, { "epoch": 22.56, "learning_rate": 9.933320400188455e-07, "loss": 0.7424, "step": 271430 }, { "epoch": 22.56, "learning_rate": 9.932211844913116e-07, "loss": 0.7868, "step": 271440 }, { "epoch": 22.56, "learning_rate": 9.931103289637779e-07, "loss": 0.7383, "step": 271450 }, { "epoch": 22.56, "learning_rate": 9.929994734362442e-07, "loss": 0.7637, "step": 271460 }, { "epoch": 22.56, "learning_rate": 9.928886179087105e-07, "loss": 0.7512, "step": 271470 }, { "epoch": 22.57, "learning_rate": 9.927777623811767e-07, "loss": 0.7253, "step": 271480 }, { "epoch": 22.57, "learning_rate": 9.92666906853643e-07, "loss": 0.7981, "step": 271490 }, { "epoch": 22.57, "learning_rate": 9.925560513261091e-07, "loss": 0.7454, "step": 271500 }, { "epoch": 22.57, "learning_rate": 9.924451957985754e-07, "loss": 0.7772, "step": 271510 }, { "epoch": 22.57, "learning_rate": 9.923343402710417e-07, "loss": 0.7106, "step": 271520 }, { "epoch": 22.57, "learning_rate": 9.92223484743508e-07, "loss": 0.7103, "step": 271530 }, { "epoch": 22.57, "learning_rate": 9.921126292159743e-07, "loss": 0.7609, "step": 271540 }, { "epoch": 22.57, "learning_rate": 9.920017736884406e-07, "loss": 0.7577, "step": 271550 }, { "epoch": 22.57, "learning_rate": 9.918909181609067e-07, "loss": 0.6879, "step": 271560 }, { "epoch": 22.57, "learning_rate": 9.91780062633373e-07, "loss": 0.7459, "step": 271570 }, { "epoch": 22.57, "learning_rate": 9.916692071058393e-07, "loss": 0.7337, "step": 271580 }, { "epoch": 22.57, "learning_rate": 9.915583515783056e-07, "loss": 0.7448, "step": 271590 }, { "epoch": 22.58, "learning_rate": 9.914474960507719e-07, "loss": 0.7365, "step": 271600 }, { "epoch": 22.58, "learning_rate": 9.913366405232382e-07, "loss": 0.7665, "step": 271610 }, { "epoch": 22.58, "learning_rate": 9.912257849957042e-07, "loss": 0.6925, "step": 271620 }, { "epoch": 22.58, "learning_rate": 9.911149294681705e-07, "loss": 0.6584, "step": 271630 }, { "epoch": 22.58, "learning_rate": 9.910040739406368e-07, "loss": 0.8085, "step": 271640 }, { "epoch": 22.58, "learning_rate": 9.908932184131031e-07, "loss": 0.7163, "step": 271650 }, { "epoch": 22.58, "learning_rate": 9.907823628855694e-07, "loss": 0.7221, "step": 271660 }, { "epoch": 22.58, "learning_rate": 9.906715073580357e-07, "loss": 0.6438, "step": 271670 }, { "epoch": 22.58, "learning_rate": 9.905606518305018e-07, "loss": 0.6935, "step": 271680 }, { "epoch": 22.58, "learning_rate": 9.90449796302968e-07, "loss": 0.7898, "step": 271690 }, { "epoch": 22.58, "learning_rate": 9.903389407754344e-07, "loss": 0.7684, "step": 271700 }, { "epoch": 22.58, "learning_rate": 9.902280852479005e-07, "loss": 0.7184, "step": 271710 }, { "epoch": 22.58, "learning_rate": 9.90117229720367e-07, "loss": 0.708, "step": 271720 }, { "epoch": 22.59, "learning_rate": 9.90006374192833e-07, "loss": 0.7464, "step": 271730 }, { "epoch": 22.59, "learning_rate": 9.898955186652994e-07, "loss": 0.8088, "step": 271740 }, { "epoch": 22.59, "learning_rate": 9.897846631377657e-07, "loss": 0.776, "step": 271750 }, { "epoch": 22.59, "learning_rate": 9.89673807610232e-07, "loss": 0.7059, "step": 271760 }, { "epoch": 22.59, "learning_rate": 9.89562952082698e-07, "loss": 0.7142, "step": 271770 }, { "epoch": 22.59, "learning_rate": 9.894520965551645e-07, "loss": 0.7771, "step": 271780 }, { "epoch": 22.59, "learning_rate": 9.89352326580384e-07, "loss": 0.7471, "step": 271790 }, { "epoch": 22.59, "learning_rate": 9.892414710528502e-07, "loss": 0.7356, "step": 271800 }, { "epoch": 22.59, "learning_rate": 9.891306155253167e-07, "loss": 0.7432, "step": 271810 }, { "epoch": 22.59, "learning_rate": 9.890197599977828e-07, "loss": 0.7687, "step": 271820 }, { "epoch": 22.59, "learning_rate": 9.88908904470249e-07, "loss": 0.7089, "step": 271830 }, { "epoch": 22.59, "learning_rate": 9.887980489427154e-07, "loss": 0.7467, "step": 271840 }, { "epoch": 22.6, "learning_rate": 9.886871934151816e-07, "loss": 0.7756, "step": 271850 }, { "epoch": 22.6, "learning_rate": 9.885763378876477e-07, "loss": 0.7511, "step": 271860 }, { "epoch": 22.6, "learning_rate": 9.884654823601142e-07, "loss": 0.7065, "step": 271870 }, { "epoch": 22.6, "learning_rate": 9.883546268325803e-07, "loss": 0.6954, "step": 271880 }, { "epoch": 22.6, "learning_rate": 9.882437713050466e-07, "loss": 0.6908, "step": 271890 }, { "epoch": 22.6, "learning_rate": 9.88132915777513e-07, "loss": 0.7341, "step": 271900 }, { "epoch": 22.6, "learning_rate": 9.880220602499792e-07, "loss": 0.7508, "step": 271910 }, { "epoch": 22.6, "learning_rate": 9.879112047224453e-07, "loss": 0.7861, "step": 271920 }, { "epoch": 22.6, "learning_rate": 9.878003491949118e-07, "loss": 0.7023, "step": 271930 }, { "epoch": 22.6, "learning_rate": 9.876894936673779e-07, "loss": 0.8233, "step": 271940 }, { "epoch": 22.6, "learning_rate": 9.875786381398442e-07, "loss": 0.7703, "step": 271950 }, { "epoch": 22.6, "learning_rate": 9.874677826123105e-07, "loss": 0.7152, "step": 271960 }, { "epoch": 22.61, "learning_rate": 9.873569270847768e-07, "loss": 0.7385, "step": 271970 }, { "epoch": 22.61, "learning_rate": 9.872460715572428e-07, "loss": 0.7941, "step": 271980 }, { "epoch": 22.61, "learning_rate": 9.871352160297094e-07, "loss": 0.8156, "step": 271990 }, { "epoch": 22.61, "learning_rate": 9.870243605021754e-07, "loss": 0.7419, "step": 272000 }, { "epoch": 22.61, "learning_rate": 9.869135049746417e-07, "loss": 0.6936, "step": 272010 }, { "epoch": 22.61, "learning_rate": 9.86802649447108e-07, "loss": 0.6916, "step": 272020 }, { "epoch": 22.61, "learning_rate": 9.866917939195743e-07, "loss": 0.6973, "step": 272030 }, { "epoch": 22.61, "learning_rate": 9.865809383920404e-07, "loss": 0.8281, "step": 272040 }, { "epoch": 22.61, "learning_rate": 9.86470082864507e-07, "loss": 0.7427, "step": 272050 }, { "epoch": 22.61, "learning_rate": 9.86359227336973e-07, "loss": 0.7091, "step": 272060 }, { "epoch": 22.61, "learning_rate": 9.862483718094393e-07, "loss": 0.7355, "step": 272070 }, { "epoch": 22.61, "learning_rate": 9.861375162819056e-07, "loss": 0.7765, "step": 272080 }, { "epoch": 22.62, "learning_rate": 9.860266607543719e-07, "loss": 0.7649, "step": 272090 }, { "epoch": 22.62, "learning_rate": 9.85915805226838e-07, "loss": 0.807, "step": 272100 }, { "epoch": 22.62, "learning_rate": 9.858049496993045e-07, "loss": 0.761, "step": 272110 }, { "epoch": 22.62, "learning_rate": 9.856940941717706e-07, "loss": 0.7293, "step": 272120 }, { "epoch": 22.62, "learning_rate": 9.855832386442369e-07, "loss": 0.6755, "step": 272130 }, { "epoch": 22.62, "learning_rate": 9.854723831167032e-07, "loss": 0.8149, "step": 272140 }, { "epoch": 22.62, "learning_rate": 9.853615275891694e-07, "loss": 0.7618, "step": 272150 }, { "epoch": 22.62, "learning_rate": 9.852506720616355e-07, "loss": 0.7174, "step": 272160 }, { "epoch": 22.62, "learning_rate": 9.85139816534102e-07, "loss": 0.7546, "step": 272170 }, { "epoch": 22.62, "learning_rate": 9.850289610065681e-07, "loss": 0.7555, "step": 272180 }, { "epoch": 22.62, "learning_rate": 9.849181054790344e-07, "loss": 0.7227, "step": 272190 }, { "epoch": 22.62, "learning_rate": 9.848072499515007e-07, "loss": 0.7284, "step": 272200 }, { "epoch": 22.63, "learning_rate": 9.84696394423967e-07, "loss": 0.7505, "step": 272210 }, { "epoch": 22.63, "learning_rate": 9.84585538896433e-07, "loss": 0.7129, "step": 272220 }, { "epoch": 22.63, "learning_rate": 9.844746833688994e-07, "loss": 0.7359, "step": 272230 }, { "epoch": 22.63, "learning_rate": 9.843638278413657e-07, "loss": 0.7483, "step": 272240 }, { "epoch": 22.63, "learning_rate": 9.84252972313832e-07, "loss": 0.7443, "step": 272250 }, { "epoch": 22.63, "learning_rate": 9.841421167862983e-07, "loss": 0.7848, "step": 272260 }, { "epoch": 22.63, "learning_rate": 9.840312612587644e-07, "loss": 0.731, "step": 272270 }, { "epoch": 22.63, "learning_rate": 9.839204057312307e-07, "loss": 0.7341, "step": 272280 }, { "epoch": 22.63, "learning_rate": 9.83809550203697e-07, "loss": 0.8345, "step": 272290 }, { "epoch": 22.63, "learning_rate": 9.836986946761632e-07, "loss": 0.8037, "step": 272300 }, { "epoch": 22.63, "learning_rate": 9.835878391486295e-07, "loss": 0.7487, "step": 272310 }, { "epoch": 22.63, "learning_rate": 9.834769836210958e-07, "loss": 0.7572, "step": 272320 }, { "epoch": 22.64, "learning_rate": 9.83366128093562e-07, "loss": 0.7659, "step": 272330 }, { "epoch": 22.64, "learning_rate": 9.832552725660282e-07, "loss": 0.7358, "step": 272340 }, { "epoch": 22.64, "learning_rate": 9.831444170384945e-07, "loss": 0.706, "step": 272350 }, { "epoch": 22.64, "learning_rate": 9.830335615109608e-07, "loss": 0.6963, "step": 272360 }, { "epoch": 22.64, "learning_rate": 9.82922705983427e-07, "loss": 0.7556, "step": 272370 }, { "epoch": 22.64, "learning_rate": 9.828118504558934e-07, "loss": 0.7391, "step": 272380 }, { "epoch": 22.64, "learning_rate": 9.827009949283595e-07, "loss": 0.8051, "step": 272390 }, { "epoch": 22.64, "learning_rate": 9.825901394008258e-07, "loss": 0.7134, "step": 272400 }, { "epoch": 22.64, "learning_rate": 9.82479283873292e-07, "loss": 0.7147, "step": 272410 }, { "epoch": 22.64, "learning_rate": 9.823684283457584e-07, "loss": 0.7441, "step": 272420 }, { "epoch": 22.64, "learning_rate": 9.822575728182247e-07, "loss": 0.7372, "step": 272430 }, { "epoch": 22.64, "learning_rate": 9.82146717290691e-07, "loss": 0.7716, "step": 272440 }, { "epoch": 22.65, "learning_rate": 9.82035861763157e-07, "loss": 0.771, "step": 272450 }, { "epoch": 22.65, "learning_rate": 9.819250062356233e-07, "loss": 0.679, "step": 272460 }, { "epoch": 22.65, "learning_rate": 9.818141507080896e-07, "loss": 0.7282, "step": 272470 }, { "epoch": 22.65, "learning_rate": 9.81703295180556e-07, "loss": 0.7192, "step": 272480 }, { "epoch": 22.65, "learning_rate": 9.815924396530222e-07, "loss": 0.762, "step": 272490 }, { "epoch": 22.65, "learning_rate": 9.814815841254885e-07, "loss": 0.8066, "step": 272500 }, { "epoch": 22.65, "learning_rate": 9.813707285979546e-07, "loss": 0.802, "step": 272510 }, { "epoch": 22.65, "learning_rate": 9.812598730704209e-07, "loss": 0.756, "step": 272520 }, { "epoch": 22.65, "learning_rate": 9.811490175428872e-07, "loss": 0.7699, "step": 272530 }, { "epoch": 22.65, "learning_rate": 9.810381620153535e-07, "loss": 0.7241, "step": 272540 }, { "epoch": 22.65, "learning_rate": 9.809273064878198e-07, "loss": 0.7096, "step": 272550 }, { "epoch": 22.65, "learning_rate": 9.80816450960286e-07, "loss": 0.7887, "step": 272560 }, { "epoch": 22.66, "learning_rate": 9.807055954327522e-07, "loss": 0.7487, "step": 272570 }, { "epoch": 22.66, "learning_rate": 9.805947399052185e-07, "loss": 0.6985, "step": 272580 }, { "epoch": 22.66, "learning_rate": 9.804838843776847e-07, "loss": 0.7072, "step": 272590 }, { "epoch": 22.66, "learning_rate": 9.80373028850151e-07, "loss": 0.6917, "step": 272600 }, { "epoch": 22.66, "learning_rate": 9.802621733226173e-07, "loss": 0.7502, "step": 272610 }, { "epoch": 22.66, "learning_rate": 9.801513177950836e-07, "loss": 0.7613, "step": 272620 }, { "epoch": 22.66, "learning_rate": 9.800404622675497e-07, "loss": 0.7201, "step": 272630 }, { "epoch": 22.66, "learning_rate": 9.79929606740016e-07, "loss": 0.8223, "step": 272640 }, { "epoch": 22.66, "learning_rate": 9.798187512124823e-07, "loss": 0.7669, "step": 272650 }, { "epoch": 22.66, "learning_rate": 9.797078956849484e-07, "loss": 0.8049, "step": 272660 }, { "epoch": 22.66, "learning_rate": 9.79597040157415e-07, "loss": 0.7282, "step": 272670 }, { "epoch": 22.66, "learning_rate": 9.79486184629881e-07, "loss": 0.7151, "step": 272680 }, { "epoch": 22.67, "learning_rate": 9.793753291023473e-07, "loss": 0.7702, "step": 272690 }, { "epoch": 22.67, "learning_rate": 9.792644735748136e-07, "loss": 0.7075, "step": 272700 }, { "epoch": 22.67, "learning_rate": 9.791536180472799e-07, "loss": 0.7666, "step": 272710 }, { "epoch": 22.67, "learning_rate": 9.79042762519746e-07, "loss": 0.8189, "step": 272720 }, { "epoch": 22.67, "learning_rate": 9.789319069922125e-07, "loss": 0.7504, "step": 272730 }, { "epoch": 22.67, "learning_rate": 9.788210514646785e-07, "loss": 0.7642, "step": 272740 }, { "epoch": 22.67, "learning_rate": 9.787101959371448e-07, "loss": 0.7611, "step": 272750 }, { "epoch": 22.67, "learning_rate": 9.785993404096111e-07, "loss": 0.7499, "step": 272760 }, { "epoch": 22.67, "learning_rate": 9.784884848820774e-07, "loss": 0.7195, "step": 272770 }, { "epoch": 22.67, "learning_rate": 9.783776293545435e-07, "loss": 0.7426, "step": 272780 }, { "epoch": 22.67, "learning_rate": 9.7826677382701e-07, "loss": 0.7715, "step": 272790 }, { "epoch": 22.67, "learning_rate": 9.78155918299476e-07, "loss": 0.7409, "step": 272800 }, { "epoch": 22.68, "learning_rate": 9.780450627719424e-07, "loss": 0.7174, "step": 272810 }, { "epoch": 22.68, "learning_rate": 9.779342072444087e-07, "loss": 0.7496, "step": 272820 }, { "epoch": 22.68, "learning_rate": 9.77823351716875e-07, "loss": 0.7315, "step": 272830 }, { "epoch": 22.68, "learning_rate": 9.77712496189341e-07, "loss": 0.8573, "step": 272840 }, { "epoch": 22.68, "learning_rate": 9.776016406618076e-07, "loss": 0.7388, "step": 272850 }, { "epoch": 22.68, "learning_rate": 9.774907851342737e-07, "loss": 0.7573, "step": 272860 }, { "epoch": 22.68, "learning_rate": 9.7737992960674e-07, "loss": 0.7168, "step": 272870 }, { "epoch": 22.68, "learning_rate": 9.772690740792063e-07, "loss": 0.7596, "step": 272880 }, { "epoch": 22.68, "learning_rate": 9.771582185516725e-07, "loss": 0.7673, "step": 272890 }, { "epoch": 22.68, "learning_rate": 9.770473630241386e-07, "loss": 0.6885, "step": 272900 }, { "epoch": 22.68, "learning_rate": 9.769365074966051e-07, "loss": 0.7634, "step": 272910 }, { "epoch": 22.68, "learning_rate": 9.768256519690712e-07, "loss": 0.702, "step": 272920 }, { "epoch": 22.69, "learning_rate": 9.767147964415375e-07, "loss": 0.7624, "step": 272930 }, { "epoch": 22.69, "learning_rate": 9.766039409140038e-07, "loss": 0.8103, "step": 272940 }, { "epoch": 22.69, "learning_rate": 9.764930853864701e-07, "loss": 0.7421, "step": 272950 }, { "epoch": 22.69, "learning_rate": 9.763822298589362e-07, "loss": 0.8051, "step": 272960 }, { "epoch": 22.69, "learning_rate": 9.762713743314027e-07, "loss": 0.7321, "step": 272970 }, { "epoch": 22.69, "learning_rate": 9.761605188038688e-07, "loss": 0.7816, "step": 272980 }, { "epoch": 22.69, "learning_rate": 9.76049663276335e-07, "loss": 0.7935, "step": 272990 }, { "epoch": 22.69, "learning_rate": 9.759388077488014e-07, "loss": 0.7186, "step": 273000 }, { "epoch": 22.69, "learning_rate": 9.758279522212677e-07, "loss": 0.6934, "step": 273010 }, { "epoch": 22.69, "learning_rate": 9.757170966937338e-07, "loss": 0.7032, "step": 273020 }, { "epoch": 22.69, "learning_rate": 9.756062411662e-07, "loss": 0.7376, "step": 273030 }, { "epoch": 22.69, "learning_rate": 9.754953856386663e-07, "loss": 0.7672, "step": 273040 }, { "epoch": 22.7, "learning_rate": 9.753845301111326e-07, "loss": 0.7555, "step": 273050 }, { "epoch": 22.7, "learning_rate": 9.75273674583599e-07, "loss": 0.7033, "step": 273060 }, { "epoch": 22.7, "learning_rate": 9.75162819056065e-07, "loss": 0.7379, "step": 273070 }, { "epoch": 22.7, "learning_rate": 9.750519635285313e-07, "loss": 0.7506, "step": 273080 }, { "epoch": 22.7, "learning_rate": 9.749411080009976e-07, "loss": 0.7462, "step": 273090 }, { "epoch": 22.7, "learning_rate": 9.74830252473464e-07, "loss": 0.7149, "step": 273100 }, { "epoch": 22.7, "learning_rate": 9.747193969459302e-07, "loss": 0.7899, "step": 273110 }, { "epoch": 22.7, "learning_rate": 9.746085414183965e-07, "loss": 0.7159, "step": 273120 }, { "epoch": 22.7, "learning_rate": 9.744976858908626e-07, "loss": 0.7, "step": 273130 }, { "epoch": 22.7, "learning_rate": 9.743868303633289e-07, "loss": 0.8123, "step": 273140 }, { "epoch": 22.7, "learning_rate": 9.742759748357952e-07, "loss": 0.7745, "step": 273150 }, { "epoch": 22.7, "learning_rate": 9.741651193082615e-07, "loss": 0.6929, "step": 273160 }, { "epoch": 22.71, "learning_rate": 9.740542637807278e-07, "loss": 0.7662, "step": 273170 }, { "epoch": 22.71, "learning_rate": 9.73943408253194e-07, "loss": 0.7114, "step": 273180 }, { "epoch": 22.71, "learning_rate": 9.738325527256601e-07, "loss": 0.7148, "step": 273190 }, { "epoch": 22.71, "learning_rate": 9.737216971981264e-07, "loss": 0.7119, "step": 273200 }, { "epoch": 22.71, "learning_rate": 9.736108416705927e-07, "loss": 0.692, "step": 273210 }, { "epoch": 22.71, "learning_rate": 9.73499986143059e-07, "loss": 0.7484, "step": 273220 }, { "epoch": 22.71, "learning_rate": 9.733891306155253e-07, "loss": 0.7431, "step": 273230 }, { "epoch": 22.71, "learning_rate": 9.732782750879916e-07, "loss": 0.7472, "step": 273240 }, { "epoch": 22.71, "learning_rate": 9.731674195604577e-07, "loss": 0.7861, "step": 273250 }, { "epoch": 22.71, "learning_rate": 9.73056564032924e-07, "loss": 0.7621, "step": 273260 }, { "epoch": 22.71, "learning_rate": 9.729457085053903e-07, "loss": 0.7815, "step": 273270 }, { "epoch": 22.71, "learning_rate": 9.728348529778566e-07, "loss": 0.7438, "step": 273280 }, { "epoch": 22.72, "learning_rate": 9.727239974503229e-07, "loss": 0.8104, "step": 273290 }, { "epoch": 22.72, "learning_rate": 9.726131419227892e-07, "loss": 0.8084, "step": 273300 }, { "epoch": 22.72, "learning_rate": 9.725022863952553e-07, "loss": 0.721, "step": 273310 }, { "epoch": 22.72, "learning_rate": 9.723914308677216e-07, "loss": 0.7871, "step": 273320 }, { "epoch": 22.72, "learning_rate": 9.722805753401879e-07, "loss": 0.7716, "step": 273330 }, { "epoch": 22.72, "learning_rate": 9.721697198126541e-07, "loss": 0.7908, "step": 273340 }, { "epoch": 22.72, "learning_rate": 9.720588642851204e-07, "loss": 0.6826, "step": 273350 }, { "epoch": 22.72, "learning_rate": 9.719480087575867e-07, "loss": 0.7769, "step": 273360 }, { "epoch": 22.72, "learning_rate": 9.718371532300528e-07, "loss": 0.8175, "step": 273370 }, { "epoch": 22.72, "learning_rate": 9.717262977025191e-07, "loss": 0.7405, "step": 273380 }, { "epoch": 22.72, "learning_rate": 9.716154421749854e-07, "loss": 0.7755, "step": 273390 }, { "epoch": 22.72, "learning_rate": 9.715045866474517e-07, "loss": 0.7587, "step": 273400 }, { "epoch": 22.73, "learning_rate": 9.71393731119918e-07, "loss": 0.7294, "step": 273410 }, { "epoch": 22.73, "learning_rate": 9.712828755923843e-07, "loss": 0.8025, "step": 273420 }, { "epoch": 22.73, "learning_rate": 9.711720200648504e-07, "loss": 0.7415, "step": 273430 }, { "epoch": 22.73, "learning_rate": 9.710611645373167e-07, "loss": 0.799, "step": 273440 }, { "epoch": 22.73, "learning_rate": 9.70950309009783e-07, "loss": 0.7099, "step": 273450 }, { "epoch": 22.73, "learning_rate": 9.70839453482249e-07, "loss": 0.7224, "step": 273460 }, { "epoch": 22.73, "learning_rate": 9.707285979547156e-07, "loss": 0.7731, "step": 273470 }, { "epoch": 22.73, "learning_rate": 9.706177424271819e-07, "loss": 0.7569, "step": 273480 }, { "epoch": 22.73, "learning_rate": 9.70506886899648e-07, "loss": 0.7593, "step": 273490 }, { "epoch": 22.73, "learning_rate": 9.703960313721142e-07, "loss": 0.7509, "step": 273500 }, { "epoch": 22.73, "learning_rate": 9.702851758445805e-07, "loss": 0.7314, "step": 273510 }, { "epoch": 22.73, "learning_rate": 9.701743203170466e-07, "loss": 0.7836, "step": 273520 }, { "epoch": 22.74, "learning_rate": 9.700634647895131e-07, "loss": 0.7337, "step": 273530 }, { "epoch": 22.74, "learning_rate": 9.699526092619792e-07, "loss": 0.7227, "step": 273540 }, { "epoch": 22.74, "learning_rate": 9.698417537344455e-07, "loss": 0.7384, "step": 273550 }, { "epoch": 22.74, "learning_rate": 9.697308982069118e-07, "loss": 0.7911, "step": 273560 }, { "epoch": 22.74, "learning_rate": 9.69620042679378e-07, "loss": 0.7378, "step": 273570 }, { "epoch": 22.74, "learning_rate": 9.695091871518442e-07, "loss": 0.7454, "step": 273580 }, { "epoch": 22.74, "learning_rate": 9.693983316243107e-07, "loss": 0.7925, "step": 273590 }, { "epoch": 22.74, "learning_rate": 9.692874760967768e-07, "loss": 0.7341, "step": 273600 }, { "epoch": 22.74, "learning_rate": 9.69176620569243e-07, "loss": 0.7277, "step": 273610 }, { "epoch": 22.74, "learning_rate": 9.690657650417094e-07, "loss": 0.7348, "step": 273620 }, { "epoch": 22.74, "learning_rate": 9.689549095141757e-07, "loss": 0.7192, "step": 273630 }, { "epoch": 22.74, "learning_rate": 9.688440539866417e-07, "loss": 0.787, "step": 273640 }, { "epoch": 22.75, "learning_rate": 9.687331984591082e-07, "loss": 0.7359, "step": 273650 }, { "epoch": 22.75, "learning_rate": 9.686223429315743e-07, "loss": 0.7573, "step": 273660 }, { "epoch": 22.75, "learning_rate": 9.685114874040406e-07, "loss": 0.7177, "step": 273670 }, { "epoch": 22.75, "learning_rate": 9.68400631876507e-07, "loss": 0.7242, "step": 273680 }, { "epoch": 22.75, "learning_rate": 9.682897763489732e-07, "loss": 0.7717, "step": 273690 }, { "epoch": 22.75, "learning_rate": 9.681789208214393e-07, "loss": 0.7583, "step": 273700 }, { "epoch": 22.75, "learning_rate": 9.680680652939058e-07, "loss": 0.7213, "step": 273710 }, { "epoch": 22.75, "learning_rate": 9.679572097663719e-07, "loss": 0.7824, "step": 273720 }, { "epoch": 22.75, "learning_rate": 9.678463542388382e-07, "loss": 0.7493, "step": 273730 }, { "epoch": 22.75, "learning_rate": 9.677354987113045e-07, "loss": 0.7084, "step": 273740 }, { "epoch": 22.75, "learning_rate": 9.676246431837708e-07, "loss": 0.7364, "step": 273750 }, { "epoch": 22.75, "learning_rate": 9.675137876562369e-07, "loss": 0.7573, "step": 273760 }, { "epoch": 22.76, "learning_rate": 9.674029321287034e-07, "loss": 0.7094, "step": 273770 }, { "epoch": 22.76, "learning_rate": 9.672920766011694e-07, "loss": 0.7859, "step": 273780 }, { "epoch": 22.76, "learning_rate": 9.671812210736357e-07, "loss": 0.794, "step": 273790 }, { "epoch": 22.76, "learning_rate": 9.67070365546102e-07, "loss": 0.7357, "step": 273800 }, { "epoch": 22.76, "learning_rate": 9.669595100185683e-07, "loss": 0.6875, "step": 273810 }, { "epoch": 22.76, "learning_rate": 9.668486544910344e-07, "loss": 0.7766, "step": 273820 }, { "epoch": 22.76, "learning_rate": 9.66737798963501e-07, "loss": 0.7307, "step": 273830 }, { "epoch": 22.76, "learning_rate": 9.66626943435967e-07, "loss": 0.7728, "step": 273840 }, { "epoch": 22.76, "learning_rate": 9.665160879084333e-07, "loss": 0.7446, "step": 273850 }, { "epoch": 22.76, "learning_rate": 9.664052323808996e-07, "loss": 0.6939, "step": 273860 }, { "epoch": 22.76, "learning_rate": 9.662943768533659e-07, "loss": 0.7517, "step": 273870 }, { "epoch": 22.76, "learning_rate": 9.66183521325832e-07, "loss": 0.7412, "step": 273880 }, { "epoch": 22.77, "learning_rate": 9.660726657982983e-07, "loss": 0.7419, "step": 273890 }, { "epoch": 22.77, "learning_rate": 9.659618102707646e-07, "loss": 0.6732, "step": 273900 }, { "epoch": 22.77, "learning_rate": 9.658509547432309e-07, "loss": 0.7428, "step": 273910 }, { "epoch": 22.77, "learning_rate": 9.657400992156972e-07, "loss": 0.6928, "step": 273920 }, { "epoch": 22.77, "learning_rate": 9.656292436881632e-07, "loss": 0.7398, "step": 273930 }, { "epoch": 22.77, "learning_rate": 9.655183881606295e-07, "loss": 0.8085, "step": 273940 }, { "epoch": 22.77, "learning_rate": 9.654075326330958e-07, "loss": 0.758, "step": 273950 }, { "epoch": 22.77, "learning_rate": 9.652966771055621e-07, "loss": 0.7835, "step": 273960 }, { "epoch": 22.77, "learning_rate": 9.651858215780284e-07, "loss": 0.8428, "step": 273970 }, { "epoch": 22.77, "learning_rate": 9.650749660504947e-07, "loss": 0.7485, "step": 273980 }, { "epoch": 22.77, "learning_rate": 9.649641105229608e-07, "loss": 0.7967, "step": 273990 }, { "epoch": 22.77, "learning_rate": 9.64853254995427e-07, "loss": 0.7817, "step": 274000 }, { "epoch": 22.78, "learning_rate": 9.647423994678934e-07, "loss": 0.7257, "step": 274010 }, { "epoch": 22.78, "learning_rate": 9.646315439403597e-07, "loss": 0.7081, "step": 274020 }, { "epoch": 22.78, "learning_rate": 9.64520688412826e-07, "loss": 0.777, "step": 274030 }, { "epoch": 22.78, "learning_rate": 9.644098328852923e-07, "loss": 0.7653, "step": 274040 }, { "epoch": 22.78, "learning_rate": 9.642989773577584e-07, "loss": 0.7412, "step": 274050 }, { "epoch": 22.78, "learning_rate": 9.641881218302247e-07, "loss": 0.8009, "step": 274060 }, { "epoch": 22.78, "learning_rate": 9.64077266302691e-07, "loss": 0.7233, "step": 274070 }, { "epoch": 22.78, "learning_rate": 9.639664107751572e-07, "loss": 0.7389, "step": 274080 }, { "epoch": 22.78, "learning_rate": 9.638555552476235e-07, "loss": 0.7226, "step": 274090 }, { "epoch": 22.78, "learning_rate": 9.637446997200898e-07, "loss": 0.7281, "step": 274100 }, { "epoch": 22.78, "learning_rate": 9.63633844192556e-07, "loss": 0.6809, "step": 274110 }, { "epoch": 22.78, "learning_rate": 9.635229886650222e-07, "loss": 0.7511, "step": 274120 }, { "epoch": 22.79, "learning_rate": 9.634121331374885e-07, "loss": 0.7448, "step": 274130 }, { "epoch": 22.79, "learning_rate": 9.633012776099548e-07, "loss": 0.7888, "step": 274140 }, { "epoch": 22.79, "learning_rate": 9.63190422082421e-07, "loss": 0.7082, "step": 274150 }, { "epoch": 22.79, "learning_rate": 9.630795665548874e-07, "loss": 0.762, "step": 274160 }, { "epoch": 22.79, "learning_rate": 9.629687110273535e-07, "loss": 0.7668, "step": 274170 }, { "epoch": 22.79, "learning_rate": 9.628578554998198e-07, "loss": 0.7618, "step": 274180 }, { "epoch": 22.79, "learning_rate": 9.62746999972286e-07, "loss": 0.8108, "step": 274190 }, { "epoch": 22.79, "learning_rate": 9.626361444447524e-07, "loss": 0.7637, "step": 274200 }, { "epoch": 22.79, "learning_rate": 9.625252889172187e-07, "loss": 0.8202, "step": 274210 }, { "epoch": 22.79, "learning_rate": 9.62414433389685e-07, "loss": 0.7239, "step": 274220 }, { "epoch": 22.79, "learning_rate": 9.62303577862151e-07, "loss": 0.8023, "step": 274230 }, { "epoch": 22.79, "learning_rate": 9.621927223346173e-07, "loss": 0.7713, "step": 274240 }, { "epoch": 22.8, "learning_rate": 9.620818668070836e-07, "loss": 0.779, "step": 274250 }, { "epoch": 22.8, "learning_rate": 9.6197101127955e-07, "loss": 0.785, "step": 274260 }, { "epoch": 22.8, "learning_rate": 9.618601557520162e-07, "loss": 0.7275, "step": 274270 }, { "epoch": 22.8, "learning_rate": 9.617493002244825e-07, "loss": 0.7878, "step": 274280 }, { "epoch": 22.8, "learning_rate": 9.616384446969486e-07, "loss": 0.7799, "step": 274290 }, { "epoch": 22.8, "learning_rate": 9.61527589169415e-07, "loss": 0.7586, "step": 274300 }, { "epoch": 22.8, "learning_rate": 9.614167336418812e-07, "loss": 0.7123, "step": 274310 }, { "epoch": 22.8, "learning_rate": 9.613058781143473e-07, "loss": 0.6951, "step": 274320 }, { "epoch": 22.8, "learning_rate": 9.611950225868138e-07, "loss": 0.7677, "step": 274330 }, { "epoch": 22.8, "learning_rate": 9.610841670592799e-07, "loss": 0.8111, "step": 274340 }, { "epoch": 22.8, "learning_rate": 9.609733115317462e-07, "loss": 0.6879, "step": 274350 }, { "epoch": 22.8, "learning_rate": 9.608624560042125e-07, "loss": 0.7152, "step": 274360 }, { "epoch": 22.81, "learning_rate": 9.607516004766788e-07, "loss": 0.7239, "step": 274370 }, { "epoch": 22.81, "learning_rate": 9.606407449491448e-07, "loss": 0.7443, "step": 274380 }, { "epoch": 22.81, "learning_rate": 9.605298894216113e-07, "loss": 0.816, "step": 274390 }, { "epoch": 22.81, "learning_rate": 9.604190338940774e-07, "loss": 0.7672, "step": 274400 }, { "epoch": 22.81, "learning_rate": 9.603081783665437e-07, "loss": 0.7599, "step": 274410 }, { "epoch": 22.81, "learning_rate": 9.6019732283901e-07, "loss": 0.7802, "step": 274420 }, { "epoch": 22.81, "learning_rate": 9.600864673114763e-07, "loss": 0.719, "step": 274430 }, { "epoch": 22.81, "learning_rate": 9.599756117839424e-07, "loss": 0.7789, "step": 274440 }, { "epoch": 22.81, "learning_rate": 9.59864756256409e-07, "loss": 0.7741, "step": 274450 }, { "epoch": 22.81, "learning_rate": 9.59753900728875e-07, "loss": 0.7316, "step": 274460 }, { "epoch": 22.81, "learning_rate": 9.596430452013413e-07, "loss": 0.7578, "step": 274470 }, { "epoch": 22.81, "learning_rate": 9.595321896738076e-07, "loss": 0.7564, "step": 274480 }, { "epoch": 22.82, "learning_rate": 9.594213341462739e-07, "loss": 0.7514, "step": 274490 }, { "epoch": 22.82, "learning_rate": 9.5931047861874e-07, "loss": 0.7895, "step": 274500 }, { "epoch": 22.82, "learning_rate": 9.591996230912065e-07, "loss": 0.7155, "step": 274510 }, { "epoch": 22.82, "learning_rate": 9.590887675636725e-07, "loss": 0.7223, "step": 274520 }, { "epoch": 22.82, "learning_rate": 9.589779120361388e-07, "loss": 0.7587, "step": 274530 }, { "epoch": 22.82, "learning_rate": 9.588670565086051e-07, "loss": 0.741, "step": 274540 }, { "epoch": 22.82, "learning_rate": 9.587562009810714e-07, "loss": 0.7541, "step": 274550 }, { "epoch": 22.82, "learning_rate": 9.586453454535375e-07, "loss": 0.7195, "step": 274560 }, { "epoch": 22.82, "learning_rate": 9.58534489926004e-07, "loss": 0.7351, "step": 274570 }, { "epoch": 22.82, "learning_rate": 9.584236343984701e-07, "loss": 0.7245, "step": 274580 }, { "epoch": 22.82, "learning_rate": 9.583127788709364e-07, "loss": 0.7571, "step": 274590 }, { "epoch": 22.82, "learning_rate": 9.582019233434027e-07, "loss": 0.7391, "step": 274600 }, { "epoch": 22.83, "learning_rate": 9.58091067815869e-07, "loss": 0.708, "step": 274610 }, { "epoch": 22.83, "learning_rate": 9.57980212288335e-07, "loss": 0.7422, "step": 274620 }, { "epoch": 22.83, "learning_rate": 9.578693567608016e-07, "loss": 0.7263, "step": 274630 }, { "epoch": 22.83, "learning_rate": 9.577585012332677e-07, "loss": 0.77, "step": 274640 }, { "epoch": 22.83, "learning_rate": 9.57647645705734e-07, "loss": 0.7665, "step": 274650 }, { "epoch": 22.83, "learning_rate": 9.575367901782003e-07, "loss": 0.7857, "step": 274660 }, { "epoch": 22.83, "learning_rate": 9.574259346506666e-07, "loss": 0.7543, "step": 274670 }, { "epoch": 22.83, "learning_rate": 9.573150791231326e-07, "loss": 0.744, "step": 274680 }, { "epoch": 22.83, "learning_rate": 9.572042235955991e-07, "loss": 0.7282, "step": 274690 }, { "epoch": 22.83, "learning_rate": 9.570933680680652e-07, "loss": 0.7488, "step": 274700 }, { "epoch": 22.83, "learning_rate": 9.569825125405315e-07, "loss": 0.7282, "step": 274710 }, { "epoch": 22.83, "learning_rate": 9.568716570129978e-07, "loss": 0.7831, "step": 274720 }, { "epoch": 22.84, "learning_rate": 9.56760801485464e-07, "loss": 0.7565, "step": 274730 }, { "epoch": 22.84, "learning_rate": 9.566499459579302e-07, "loss": 0.7706, "step": 274740 }, { "epoch": 22.84, "learning_rate": 9.565390904303965e-07, "loss": 0.726, "step": 274750 }, { "epoch": 22.84, "learning_rate": 9.564282349028628e-07, "loss": 0.7039, "step": 274760 }, { "epoch": 22.84, "learning_rate": 9.56317379375329e-07, "loss": 0.7575, "step": 274770 }, { "epoch": 22.84, "learning_rate": 9.562065238477954e-07, "loss": 0.7332, "step": 274780 }, { "epoch": 22.84, "learning_rate": 9.560956683202615e-07, "loss": 0.7618, "step": 274790 }, { "epoch": 22.84, "learning_rate": 9.559848127927278e-07, "loss": 0.7259, "step": 274800 }, { "epoch": 22.84, "learning_rate": 9.55873957265194e-07, "loss": 0.6883, "step": 274810 }, { "epoch": 22.84, "learning_rate": 9.557631017376603e-07, "loss": 0.727, "step": 274820 }, { "epoch": 22.84, "learning_rate": 9.556522462101266e-07, "loss": 0.7482, "step": 274830 }, { "epoch": 22.84, "learning_rate": 9.55541390682593e-07, "loss": 0.8336, "step": 274840 }, { "epoch": 22.85, "learning_rate": 9.55430535155059e-07, "loss": 0.7163, "step": 274850 }, { "epoch": 22.85, "learning_rate": 9.553196796275253e-07, "loss": 0.6921, "step": 274860 }, { "epoch": 22.85, "learning_rate": 9.552088240999916e-07, "loss": 0.6893, "step": 274870 }, { "epoch": 22.85, "learning_rate": 9.55097968572458e-07, "loss": 0.7098, "step": 274880 }, { "epoch": 22.85, "learning_rate": 9.549871130449242e-07, "loss": 0.8593, "step": 274890 }, { "epoch": 22.85, "learning_rate": 9.548762575173905e-07, "loss": 0.7078, "step": 274900 }, { "epoch": 22.85, "learning_rate": 9.547654019898566e-07, "loss": 0.7194, "step": 274910 }, { "epoch": 22.85, "learning_rate": 9.546545464623229e-07, "loss": 0.7447, "step": 274920 }, { "epoch": 22.85, "learning_rate": 9.545436909347892e-07, "loss": 0.7321, "step": 274930 }, { "epoch": 22.85, "learning_rate": 9.544328354072555e-07, "loss": 0.7995, "step": 274940 }, { "epoch": 22.85, "learning_rate": 9.543219798797218e-07, "loss": 0.7676, "step": 274950 }, { "epoch": 22.85, "learning_rate": 9.54211124352188e-07, "loss": 0.7427, "step": 274960 }, { "epoch": 22.86, "learning_rate": 9.541002688246541e-07, "loss": 0.7638, "step": 274970 }, { "epoch": 22.86, "learning_rate": 9.539894132971204e-07, "loss": 0.7784, "step": 274980 }, { "epoch": 22.86, "learning_rate": 9.538785577695867e-07, "loss": 0.7604, "step": 274990 }, { "epoch": 22.86, "learning_rate": 9.53767702242053e-07, "loss": 0.7408, "step": 275000 }, { "epoch": 22.86, "learning_rate": 9.536568467145193e-07, "loss": 0.7862, "step": 275010 }, { "epoch": 22.86, "learning_rate": 9.535459911869855e-07, "loss": 0.734, "step": 275020 }, { "epoch": 22.86, "learning_rate": 9.534351356594518e-07, "loss": 0.7313, "step": 275030 }, { "epoch": 22.86, "learning_rate": 9.53324280131918e-07, "loss": 0.7508, "step": 275040 }, { "epoch": 22.86, "learning_rate": 9.532134246043843e-07, "loss": 0.7561, "step": 275050 }, { "epoch": 22.86, "learning_rate": 9.531025690768506e-07, "loss": 0.7449, "step": 275060 }, { "epoch": 22.86, "learning_rate": 9.529917135493169e-07, "loss": 0.6988, "step": 275070 }, { "epoch": 22.86, "learning_rate": 9.528808580217831e-07, "loss": 0.7379, "step": 275080 }, { "epoch": 22.87, "learning_rate": 9.527700024942494e-07, "loss": 0.787, "step": 275090 }, { "epoch": 22.87, "learning_rate": 9.526591469667156e-07, "loss": 0.7464, "step": 275100 }, { "epoch": 22.87, "learning_rate": 9.525482914391819e-07, "loss": 0.7664, "step": 275110 }, { "epoch": 22.87, "learning_rate": 9.52437435911648e-07, "loss": 0.7339, "step": 275120 }, { "epoch": 22.87, "learning_rate": 9.523265803841144e-07, "loss": 0.7308, "step": 275130 }, { "epoch": 22.87, "learning_rate": 9.522157248565806e-07, "loss": 0.8191, "step": 275140 }, { "epoch": 22.87, "learning_rate": 9.521048693290468e-07, "loss": 0.6943, "step": 275150 }, { "epoch": 22.87, "learning_rate": 9.519940138015131e-07, "loss": 0.7147, "step": 275160 }, { "epoch": 22.87, "learning_rate": 9.518831582739793e-07, "loss": 0.7576, "step": 275170 }, { "epoch": 22.87, "learning_rate": 9.517833882991991e-07, "loss": 0.7394, "step": 275180 }, { "epoch": 22.87, "learning_rate": 9.516725327716653e-07, "loss": 0.7655, "step": 275190 }, { "epoch": 22.87, "learning_rate": 9.515616772441315e-07, "loss": 0.7727, "step": 275200 }, { "epoch": 22.88, "learning_rate": 9.514508217165978e-07, "loss": 0.7435, "step": 275210 }, { "epoch": 22.88, "learning_rate": 9.513399661890641e-07, "loss": 0.7699, "step": 275220 }, { "epoch": 22.88, "learning_rate": 9.512291106615303e-07, "loss": 0.6666, "step": 275230 }, { "epoch": 22.88, "learning_rate": 9.511182551339966e-07, "loss": 0.7298, "step": 275240 }, { "epoch": 22.88, "learning_rate": 9.510073996064628e-07, "loss": 0.7203, "step": 275250 }, { "epoch": 22.88, "learning_rate": 9.50896544078929e-07, "loss": 0.7477, "step": 275260 }, { "epoch": 22.88, "learning_rate": 9.507856885513954e-07, "loss": 0.7065, "step": 275270 }, { "epoch": 22.88, "learning_rate": 9.506748330238617e-07, "loss": 0.7446, "step": 275280 }, { "epoch": 22.88, "learning_rate": 9.505639774963279e-07, "loss": 0.7854, "step": 275290 }, { "epoch": 22.88, "learning_rate": 9.504531219687941e-07, "loss": 0.7093, "step": 275300 }, { "epoch": 22.88, "learning_rate": 9.503422664412604e-07, "loss": 0.6887, "step": 275310 }, { "epoch": 22.88, "learning_rate": 9.502314109137266e-07, "loss": 0.7841, "step": 275320 }, { "epoch": 22.89, "learning_rate": 9.501205553861929e-07, "loss": 0.7238, "step": 275330 }, { "epoch": 22.89, "learning_rate": 9.500096998586592e-07, "loss": 0.7399, "step": 275340 }, { "epoch": 22.89, "learning_rate": 9.498988443311254e-07, "loss": 0.7585, "step": 275350 }, { "epoch": 22.89, "learning_rate": 9.497879888035916e-07, "loss": 0.7602, "step": 275360 }, { "epoch": 22.89, "learning_rate": 9.496771332760579e-07, "loss": 0.7428, "step": 275370 }, { "epoch": 22.89, "learning_rate": 9.495662777485241e-07, "loss": 0.7643, "step": 275380 }, { "epoch": 22.89, "learning_rate": 9.494554222209904e-07, "loss": 0.8193, "step": 275390 }, { "epoch": 22.89, "learning_rate": 9.493445666934567e-07, "loss": 0.7066, "step": 275400 }, { "epoch": 22.89, "learning_rate": 9.49233711165923e-07, "loss": 0.7144, "step": 275410 }, { "epoch": 22.89, "learning_rate": 9.491228556383892e-07, "loss": 0.7185, "step": 275420 }, { "epoch": 22.89, "learning_rate": 9.490120001108555e-07, "loss": 0.6863, "step": 275430 }, { "epoch": 22.89, "learning_rate": 9.489011445833217e-07, "loss": 0.7683, "step": 275440 }, { "epoch": 22.9, "learning_rate": 9.48790289055788e-07, "loss": 0.7515, "step": 275450 }, { "epoch": 22.9, "learning_rate": 9.486794335282543e-07, "loss": 0.7085, "step": 275460 }, { "epoch": 22.9, "learning_rate": 9.485685780007206e-07, "loss": 0.7369, "step": 275470 }, { "epoch": 22.9, "learning_rate": 9.484577224731868e-07, "loss": 0.7571, "step": 275480 }, { "epoch": 22.9, "learning_rate": 9.48346866945653e-07, "loss": 0.7898, "step": 275490 }, { "epoch": 22.9, "learning_rate": 9.482360114181192e-07, "loss": 0.7206, "step": 275500 }, { "epoch": 22.9, "learning_rate": 9.481251558905855e-07, "loss": 0.7412, "step": 275510 }, { "epoch": 22.9, "learning_rate": 9.480143003630518e-07, "loss": 0.7526, "step": 275520 }, { "epoch": 22.9, "learning_rate": 9.479034448355181e-07, "loss": 0.7721, "step": 275530 }, { "epoch": 22.9, "learning_rate": 9.477925893079843e-07, "loss": 0.7518, "step": 275540 }, { "epoch": 22.9, "learning_rate": 9.476817337804506e-07, "loss": 0.7981, "step": 275550 }, { "epoch": 22.9, "learning_rate": 9.475708782529168e-07, "loss": 0.7096, "step": 275560 }, { "epoch": 22.9, "learning_rate": 9.474600227253831e-07, "loss": 0.7496, "step": 275570 }, { "epoch": 22.91, "learning_rate": 9.473491671978494e-07, "loss": 0.7276, "step": 275580 }, { "epoch": 22.91, "learning_rate": 9.472383116703157e-07, "loss": 0.8237, "step": 275590 }, { "epoch": 22.91, "learning_rate": 9.471274561427819e-07, "loss": 0.7988, "step": 275600 }, { "epoch": 22.91, "learning_rate": 9.470166006152482e-07, "loss": 0.7231, "step": 275610 }, { "epoch": 22.91, "learning_rate": 9.469057450877144e-07, "loss": 0.7979, "step": 275620 }, { "epoch": 22.91, "learning_rate": 9.467948895601807e-07, "loss": 0.7154, "step": 275630 }, { "epoch": 22.91, "learning_rate": 9.46684034032647e-07, "loss": 0.7697, "step": 275640 }, { "epoch": 22.91, "learning_rate": 9.465731785051132e-07, "loss": 0.7802, "step": 275650 }, { "epoch": 22.91, "learning_rate": 9.464623229775794e-07, "loss": 0.7788, "step": 275660 }, { "epoch": 22.91, "learning_rate": 9.463514674500457e-07, "loss": 0.7752, "step": 275670 }, { "epoch": 22.91, "learning_rate": 9.462406119225119e-07, "loss": 0.7072, "step": 275680 }, { "epoch": 22.91, "learning_rate": 9.461297563949781e-07, "loss": 0.791, "step": 275690 }, { "epoch": 22.92, "learning_rate": 9.460189008674445e-07, "loss": 0.7318, "step": 275700 }, { "epoch": 22.92, "learning_rate": 9.459080453399107e-07, "loss": 0.7561, "step": 275710 }, { "epoch": 22.92, "learning_rate": 9.45797189812377e-07, "loss": 0.7035, "step": 275720 }, { "epoch": 22.92, "learning_rate": 9.456863342848432e-07, "loss": 0.6964, "step": 275730 }, { "epoch": 22.92, "learning_rate": 9.455754787573095e-07, "loss": 0.7942, "step": 275740 }, { "epoch": 22.92, "learning_rate": 9.454646232297757e-07, "loss": 0.6779, "step": 275750 }, { "epoch": 22.92, "learning_rate": 9.45353767702242e-07, "loss": 0.7245, "step": 275760 }, { "epoch": 22.92, "learning_rate": 9.452429121747083e-07, "loss": 0.7459, "step": 275770 }, { "epoch": 22.92, "learning_rate": 9.451320566471746e-07, "loss": 0.7401, "step": 275780 }, { "epoch": 22.92, "learning_rate": 9.450212011196407e-07, "loss": 0.7788, "step": 275790 }, { "epoch": 22.92, "learning_rate": 9.44910345592107e-07, "loss": 0.7701, "step": 275800 }, { "epoch": 22.92, "learning_rate": 9.447994900645732e-07, "loss": 0.7235, "step": 275810 }, { "epoch": 22.93, "learning_rate": 9.446886345370395e-07, "loss": 0.7775, "step": 275820 }, { "epoch": 22.93, "learning_rate": 9.445777790095058e-07, "loss": 0.6454, "step": 275830 }, { "epoch": 22.93, "learning_rate": 9.444669234819721e-07, "loss": 0.7705, "step": 275840 }, { "epoch": 22.93, "learning_rate": 9.443560679544383e-07, "loss": 0.8034, "step": 275850 }, { "epoch": 22.93, "learning_rate": 9.442452124269046e-07, "loss": 0.7621, "step": 275860 }, { "epoch": 22.93, "learning_rate": 9.441343568993708e-07, "loss": 0.7149, "step": 275870 }, { "epoch": 22.93, "learning_rate": 9.440235013718371e-07, "loss": 0.7628, "step": 275880 }, { "epoch": 22.93, "learning_rate": 9.439126458443034e-07, "loss": 0.7783, "step": 275890 }, { "epoch": 22.93, "learning_rate": 9.438017903167697e-07, "loss": 0.7432, "step": 275900 }, { "epoch": 22.93, "learning_rate": 9.436909347892359e-07, "loss": 0.7357, "step": 275910 }, { "epoch": 22.93, "learning_rate": 9.435800792617022e-07, "loss": 0.7019, "step": 275920 }, { "epoch": 22.93, "learning_rate": 9.434692237341684e-07, "loss": 0.734, "step": 275930 }, { "epoch": 22.94, "learning_rate": 9.433583682066346e-07, "loss": 0.7892, "step": 275940 }, { "epoch": 22.94, "learning_rate": 9.432475126791009e-07, "loss": 0.747, "step": 275950 }, { "epoch": 22.94, "learning_rate": 9.431366571515672e-07, "loss": 0.7464, "step": 275960 }, { "epoch": 22.94, "learning_rate": 9.430258016240334e-07, "loss": 0.79, "step": 275970 }, { "epoch": 22.94, "learning_rate": 9.429149460964997e-07, "loss": 0.787, "step": 275980 }, { "epoch": 22.94, "learning_rate": 9.428040905689659e-07, "loss": 0.7486, "step": 275990 }, { "epoch": 22.94, "learning_rate": 9.426932350414322e-07, "loss": 0.8183, "step": 276000 }, { "epoch": 22.94, "learning_rate": 9.425823795138985e-07, "loss": 0.706, "step": 276010 }, { "epoch": 22.94, "learning_rate": 9.424715239863648e-07, "loss": 0.7611, "step": 276020 }, { "epoch": 22.94, "learning_rate": 9.42360668458831e-07, "loss": 0.7288, "step": 276030 }, { "epoch": 22.94, "learning_rate": 9.422498129312973e-07, "loss": 0.8448, "step": 276040 }, { "epoch": 22.94, "learning_rate": 9.421389574037635e-07, "loss": 0.7535, "step": 276050 }, { "epoch": 22.95, "learning_rate": 9.420281018762298e-07, "loss": 0.7068, "step": 276060 }, { "epoch": 22.95, "learning_rate": 9.419172463486961e-07, "loss": 0.7118, "step": 276070 }, { "epoch": 22.95, "learning_rate": 9.418063908211624e-07, "loss": 0.7305, "step": 276080 }, { "epoch": 22.95, "learning_rate": 9.416955352936285e-07, "loss": 0.8678, "step": 276090 }, { "epoch": 22.95, "learning_rate": 9.415846797660948e-07, "loss": 0.756, "step": 276100 }, { "epoch": 22.95, "learning_rate": 9.41473824238561e-07, "loss": 0.7532, "step": 276110 }, { "epoch": 22.95, "learning_rate": 9.413629687110272e-07, "loss": 0.7387, "step": 276120 }, { "epoch": 22.95, "learning_rate": 9.412521131834936e-07, "loss": 0.7731, "step": 276130 }, { "epoch": 22.95, "learning_rate": 9.411412576559598e-07, "loss": 0.7603, "step": 276140 }, { "epoch": 22.95, "learning_rate": 9.410304021284261e-07, "loss": 0.7076, "step": 276150 }, { "epoch": 22.95, "learning_rate": 9.409195466008923e-07, "loss": 0.7327, "step": 276160 }, { "epoch": 22.95, "learning_rate": 9.408086910733586e-07, "loss": 0.7538, "step": 276170 }, { "epoch": 22.96, "learning_rate": 9.406978355458248e-07, "loss": 0.7489, "step": 276180 }, { "epoch": 22.96, "learning_rate": 9.405869800182911e-07, "loss": 0.7818, "step": 276190 }, { "epoch": 22.96, "learning_rate": 9.404761244907574e-07, "loss": 0.7614, "step": 276200 }, { "epoch": 22.96, "learning_rate": 9.403652689632237e-07, "loss": 0.7333, "step": 276210 }, { "epoch": 22.96, "learning_rate": 9.402544134356899e-07, "loss": 0.716, "step": 276220 }, { "epoch": 22.96, "learning_rate": 9.401435579081562e-07, "loss": 0.7731, "step": 276230 }, { "epoch": 22.96, "learning_rate": 9.400327023806223e-07, "loss": 0.7179, "step": 276240 }, { "epoch": 22.96, "learning_rate": 9.399218468530886e-07, "loss": 0.7078, "step": 276250 }, { "epoch": 22.96, "learning_rate": 9.398109913255549e-07, "loss": 0.7154, "step": 276260 }, { "epoch": 22.96, "learning_rate": 9.397001357980212e-07, "loss": 0.7625, "step": 276270 }, { "epoch": 22.96, "learning_rate": 9.395892802704874e-07, "loss": 0.7345, "step": 276280 }, { "epoch": 22.96, "learning_rate": 9.394784247429537e-07, "loss": 0.7315, "step": 276290 }, { "epoch": 22.97, "learning_rate": 9.393675692154199e-07, "loss": 0.7858, "step": 276300 }, { "epoch": 22.97, "learning_rate": 9.392567136878862e-07, "loss": 0.6938, "step": 276310 }, { "epoch": 22.97, "learning_rate": 9.391458581603525e-07, "loss": 0.7181, "step": 276320 }, { "epoch": 22.97, "learning_rate": 9.390350026328188e-07, "loss": 0.7035, "step": 276330 }, { "epoch": 22.97, "learning_rate": 9.38924147105285e-07, "loss": 0.8289, "step": 276340 }, { "epoch": 22.97, "learning_rate": 9.388132915777513e-07, "loss": 0.6991, "step": 276350 }, { "epoch": 22.97, "learning_rate": 9.387024360502175e-07, "loss": 0.7753, "step": 276360 }, { "epoch": 22.97, "learning_rate": 9.385915805226838e-07, "loss": 0.7858, "step": 276370 }, { "epoch": 22.97, "learning_rate": 9.384807249951501e-07, "loss": 0.6994, "step": 276380 }, { "epoch": 22.97, "learning_rate": 9.383698694676163e-07, "loss": 0.7283, "step": 276390 }, { "epoch": 22.97, "learning_rate": 9.382590139400825e-07, "loss": 0.6372, "step": 276400 }, { "epoch": 22.97, "learning_rate": 9.381481584125488e-07, "loss": 0.7406, "step": 276410 }, { "epoch": 22.98, "learning_rate": 9.38037302885015e-07, "loss": 0.7597, "step": 276420 }, { "epoch": 22.98, "learning_rate": 9.379264473574813e-07, "loss": 0.7756, "step": 276430 }, { "epoch": 22.98, "learning_rate": 9.378155918299476e-07, "loss": 0.8207, "step": 276440 }, { "epoch": 22.98, "learning_rate": 9.377047363024139e-07, "loss": 0.746, "step": 276450 }, { "epoch": 22.98, "learning_rate": 9.375938807748801e-07, "loss": 0.7163, "step": 276460 }, { "epoch": 22.98, "learning_rate": 9.374830252473464e-07, "loss": 0.6899, "step": 276470 }, { "epoch": 22.98, "learning_rate": 9.373721697198126e-07, "loss": 0.7114, "step": 276480 }, { "epoch": 22.98, "learning_rate": 9.372613141922789e-07, "loss": 0.7775, "step": 276490 }, { "epoch": 22.98, "learning_rate": 9.371504586647452e-07, "loss": 0.7179, "step": 276500 }, { "epoch": 22.98, "learning_rate": 9.370396031372115e-07, "loss": 0.7727, "step": 276510 }, { "epoch": 22.98, "learning_rate": 9.369287476096777e-07, "loss": 0.7154, "step": 276520 }, { "epoch": 22.98, "learning_rate": 9.368178920821438e-07, "loss": 0.7477, "step": 276530 }, { "epoch": 22.99, "learning_rate": 9.367070365546101e-07, "loss": 0.7833, "step": 276540 }, { "epoch": 22.99, "learning_rate": 9.365961810270763e-07, "loss": 0.7458, "step": 276550 }, { "epoch": 22.99, "learning_rate": 9.364853254995427e-07, "loss": 0.7103, "step": 276560 }, { "epoch": 22.99, "learning_rate": 9.363744699720089e-07, "loss": 0.7505, "step": 276570 }, { "epoch": 22.99, "learning_rate": 9.362636144444752e-07, "loss": 0.7756, "step": 276580 }, { "epoch": 22.99, "learning_rate": 9.361527589169414e-07, "loss": 0.7686, "step": 276590 }, { "epoch": 22.99, "learning_rate": 9.360419033894077e-07, "loss": 0.7436, "step": 276600 }, { "epoch": 22.99, "learning_rate": 9.359310478618739e-07, "loss": 0.7607, "step": 276610 }, { "epoch": 22.99, "learning_rate": 9.358201923343402e-07, "loss": 0.7401, "step": 276620 }, { "epoch": 22.99, "learning_rate": 9.357093368068065e-07, "loss": 0.8325, "step": 276630 }, { "epoch": 22.99, "learning_rate": 9.355984812792728e-07, "loss": 0.8248, "step": 276640 }, { "epoch": 22.99, "learning_rate": 9.35487625751739e-07, "loss": 0.7545, "step": 276650 }, { "epoch": 23.0, "learning_rate": 9.353767702242053e-07, "loss": 0.736, "step": 276660 }, { "epoch": 23.0, "learning_rate": 9.352659146966715e-07, "loss": 0.771, "step": 276670 }, { "epoch": 23.0, "learning_rate": 9.351550591691377e-07, "loss": 0.756, "step": 276680 }, { "epoch": 23.0, "learning_rate": 9.35044203641604e-07, "loss": 0.7352, "step": 276690 }, { "epoch": 23.0, "learning_rate": 9.349333481140703e-07, "loss": 0.7104, "step": 276700 }, { "epoch": 23.0, "learning_rate": 9.348224925865365e-07, "loss": 0.7008, "step": 276710 }, { "epoch": 23.0, "eval_loss": 1.1328233480453491, "eval_runtime": 347.2086, "eval_samples_per_second": 7.701, "eval_steps_per_second": 3.851, "eval_wer": 0.6376799310646833, "step": 276713 }, { "epoch": 23.0, "learning_rate": 9.347116370590028e-07, "loss": 0.7671, "step": 276720 }, { "epoch": 23.0, "learning_rate": 9.34600781531469e-07, "loss": 0.697, "step": 276730 }, { "epoch": 23.0, "learning_rate": 9.344899260039353e-07, "loss": 0.7538, "step": 276740 }, { "epoch": 23.0, "learning_rate": 9.343790704764016e-07, "loss": 0.7166, "step": 276750 }, { "epoch": 23.0, "learning_rate": 9.342682149488679e-07, "loss": 0.6985, "step": 276760 }, { "epoch": 23.0, "learning_rate": 9.341573594213341e-07, "loss": 0.8361, "step": 276770 }, { "epoch": 23.01, "learning_rate": 9.340465038938004e-07, "loss": 0.7578, "step": 276780 }, { "epoch": 23.01, "learning_rate": 9.339356483662666e-07, "loss": 0.7235, "step": 276790 }, { "epoch": 23.01, "learning_rate": 9.338247928387329e-07, "loss": 0.7805, "step": 276800 }, { "epoch": 23.01, "learning_rate": 9.337139373111992e-07, "loss": 0.7976, "step": 276810 }, { "epoch": 23.01, "learning_rate": 9.336030817836655e-07, "loss": 0.8016, "step": 276820 }, { "epoch": 23.01, "learning_rate": 9.334922262561317e-07, "loss": 0.8125, "step": 276830 }, { "epoch": 23.01, "learning_rate": 9.333813707285979e-07, "loss": 0.7719, "step": 276840 }, { "epoch": 23.01, "learning_rate": 9.332705152010641e-07, "loss": 0.7691, "step": 276850 }, { "epoch": 23.01, "learning_rate": 9.331596596735304e-07, "loss": 0.6978, "step": 276860 }, { "epoch": 23.01, "learning_rate": 9.330488041459967e-07, "loss": 0.7606, "step": 276870 }, { "epoch": 23.01, "learning_rate": 9.32937948618463e-07, "loss": 0.7843, "step": 276880 }, { "epoch": 23.01, "learning_rate": 9.328270930909292e-07, "loss": 0.7147, "step": 276890 }, { "epoch": 23.02, "learning_rate": 9.327162375633955e-07, "loss": 0.7876, "step": 276900 }, { "epoch": 23.02, "learning_rate": 9.326053820358617e-07, "loss": 0.7791, "step": 276910 }, { "epoch": 23.02, "learning_rate": 9.32494526508328e-07, "loss": 0.7708, "step": 276920 }, { "epoch": 23.02, "learning_rate": 9.323836709807943e-07, "loss": 0.7207, "step": 276930 }, { "epoch": 23.02, "learning_rate": 9.322728154532606e-07, "loss": 0.762, "step": 276940 }, { "epoch": 23.02, "learning_rate": 9.321619599257268e-07, "loss": 0.7302, "step": 276950 }, { "epoch": 23.02, "learning_rate": 9.32051104398193e-07, "loss": 0.7467, "step": 276960 }, { "epoch": 23.02, "learning_rate": 9.319402488706593e-07, "loss": 0.837, "step": 276970 }, { "epoch": 23.02, "learning_rate": 9.318293933431254e-07, "loss": 0.7937, "step": 276980 }, { "epoch": 23.02, "learning_rate": 9.317185378155918e-07, "loss": 0.7274, "step": 276990 }, { "epoch": 23.02, "learning_rate": 9.31607682288058e-07, "loss": 0.8089, "step": 277000 }, { "epoch": 23.02, "learning_rate": 9.314968267605243e-07, "loss": 0.7506, "step": 277010 }, { "epoch": 23.03, "learning_rate": 9.313859712329905e-07, "loss": 0.8431, "step": 277020 }, { "epoch": 23.03, "learning_rate": 9.312751157054568e-07, "loss": 0.759, "step": 277030 }, { "epoch": 23.03, "learning_rate": 9.31164260177923e-07, "loss": 0.7452, "step": 277040 }, { "epoch": 23.03, "learning_rate": 9.310534046503893e-07, "loss": 0.7223, "step": 277050 }, { "epoch": 23.03, "learning_rate": 9.309425491228556e-07, "loss": 0.801, "step": 277060 }, { "epoch": 23.03, "learning_rate": 9.308316935953219e-07, "loss": 0.7608, "step": 277070 }, { "epoch": 23.03, "learning_rate": 9.307208380677881e-07, "loss": 0.7204, "step": 277080 }, { "epoch": 23.03, "learning_rate": 9.306099825402544e-07, "loss": 0.7272, "step": 277090 }, { "epoch": 23.03, "learning_rate": 9.304991270127206e-07, "loss": 0.7438, "step": 277100 }, { "epoch": 23.03, "learning_rate": 9.303882714851869e-07, "loss": 0.7627, "step": 277110 }, { "epoch": 23.03, "learning_rate": 9.302774159576532e-07, "loss": 0.7261, "step": 277120 }, { "epoch": 23.03, "learning_rate": 9.301665604301195e-07, "loss": 0.7358, "step": 277130 }, { "epoch": 23.04, "learning_rate": 9.300557049025856e-07, "loss": 0.7051, "step": 277140 }, { "epoch": 23.04, "learning_rate": 9.299448493750519e-07, "loss": 0.7266, "step": 277150 }, { "epoch": 23.04, "learning_rate": 9.298339938475181e-07, "loss": 0.7413, "step": 277160 }, { "epoch": 23.04, "learning_rate": 9.297231383199844e-07, "loss": 0.7413, "step": 277170 }, { "epoch": 23.04, "learning_rate": 9.296122827924507e-07, "loss": 0.7892, "step": 277180 }, { "epoch": 23.04, "learning_rate": 9.29501427264917e-07, "loss": 0.7562, "step": 277190 }, { "epoch": 23.04, "learning_rate": 9.293905717373832e-07, "loss": 0.7589, "step": 277200 }, { "epoch": 23.04, "learning_rate": 9.292797162098495e-07, "loss": 0.7156, "step": 277210 }, { "epoch": 23.04, "learning_rate": 9.291688606823157e-07, "loss": 0.8214, "step": 277220 }, { "epoch": 23.04, "learning_rate": 9.29058005154782e-07, "loss": 0.7613, "step": 277230 }, { "epoch": 23.04, "learning_rate": 9.289471496272483e-07, "loss": 0.7548, "step": 277240 }, { "epoch": 23.04, "learning_rate": 9.288473796524678e-07, "loss": 0.7102, "step": 277250 }, { "epoch": 23.05, "learning_rate": 9.287365241249341e-07, "loss": 0.7094, "step": 277260 }, { "epoch": 23.05, "learning_rate": 9.286256685974004e-07, "loss": 0.7314, "step": 277270 }, { "epoch": 23.05, "learning_rate": 9.285148130698667e-07, "loss": 0.7285, "step": 277280 }, { "epoch": 23.05, "learning_rate": 9.284039575423329e-07, "loss": 0.7513, "step": 277290 }, { "epoch": 23.05, "learning_rate": 9.282931020147992e-07, "loss": 0.7842, "step": 277300 }, { "epoch": 23.05, "learning_rate": 9.281822464872654e-07, "loss": 0.7436, "step": 277310 }, { "epoch": 23.05, "learning_rate": 9.280713909597317e-07, "loss": 0.7572, "step": 277320 }, { "epoch": 23.05, "learning_rate": 9.27960535432198e-07, "loss": 0.7186, "step": 277330 }, { "epoch": 23.05, "learning_rate": 9.278496799046643e-07, "loss": 0.6945, "step": 277340 }, { "epoch": 23.05, "learning_rate": 9.277388243771305e-07, "loss": 0.7569, "step": 277350 }, { "epoch": 23.05, "learning_rate": 9.276279688495967e-07, "loss": 0.7495, "step": 277360 }, { "epoch": 23.05, "learning_rate": 9.275171133220629e-07, "loss": 0.807, "step": 277370 }, { "epoch": 23.06, "learning_rate": 9.274062577945292e-07, "loss": 0.7128, "step": 277380 }, { "epoch": 23.06, "learning_rate": 9.272954022669955e-07, "loss": 0.7906, "step": 277390 }, { "epoch": 23.06, "learning_rate": 9.271845467394618e-07, "loss": 0.7695, "step": 277400 }, { "epoch": 23.06, "learning_rate": 9.27073691211928e-07, "loss": 0.7103, "step": 277410 }, { "epoch": 23.06, "learning_rate": 9.269628356843943e-07, "loss": 0.8125, "step": 277420 }, { "epoch": 23.06, "learning_rate": 9.268519801568605e-07, "loss": 0.7831, "step": 277430 }, { "epoch": 23.06, "learning_rate": 9.267411246293268e-07, "loss": 0.8062, "step": 277440 }, { "epoch": 23.06, "learning_rate": 9.266302691017931e-07, "loss": 0.7361, "step": 277450 }, { "epoch": 23.06, "learning_rate": 9.265194135742594e-07, "loss": 0.7497, "step": 277460 }, { "epoch": 23.06, "learning_rate": 9.264085580467256e-07, "loss": 0.7668, "step": 277470 }, { "epoch": 23.06, "learning_rate": 9.262977025191919e-07, "loss": 0.7148, "step": 277480 }, { "epoch": 23.06, "learning_rate": 9.261868469916581e-07, "loss": 0.6756, "step": 277490 }, { "epoch": 23.07, "learning_rate": 9.260759914641242e-07, "loss": 0.7327, "step": 277500 }, { "epoch": 23.07, "learning_rate": 9.259651359365906e-07, "loss": 0.7301, "step": 277510 }, { "epoch": 23.07, "learning_rate": 9.258542804090568e-07, "loss": 0.7682, "step": 277520 }, { "epoch": 23.07, "learning_rate": 9.257434248815231e-07, "loss": 0.7384, "step": 277530 }, { "epoch": 23.07, "learning_rate": 9.256325693539893e-07, "loss": 0.7157, "step": 277540 }, { "epoch": 23.07, "learning_rate": 9.255217138264556e-07, "loss": 0.8135, "step": 277550 }, { "epoch": 23.07, "learning_rate": 9.254108582989218e-07, "loss": 0.7497, "step": 277560 }, { "epoch": 23.07, "learning_rate": 9.253000027713882e-07, "loss": 0.7881, "step": 277570 }, { "epoch": 23.07, "learning_rate": 9.251891472438544e-07, "loss": 0.8001, "step": 277580 }, { "epoch": 23.07, "learning_rate": 9.250782917163207e-07, "loss": 0.7091, "step": 277590 }, { "epoch": 23.07, "learning_rate": 9.249674361887869e-07, "loss": 0.7728, "step": 277600 }, { "epoch": 23.07, "learning_rate": 9.248565806612532e-07, "loss": 0.7947, "step": 277610 }, { "epoch": 23.08, "learning_rate": 9.247457251337194e-07, "loss": 0.7852, "step": 277620 }, { "epoch": 23.08, "learning_rate": 9.246348696061857e-07, "loss": 0.7752, "step": 277630 }, { "epoch": 23.08, "learning_rate": 9.24524014078652e-07, "loss": 0.7409, "step": 277640 }, { "epoch": 23.08, "learning_rate": 9.244131585511183e-07, "loss": 0.688, "step": 277650 }, { "epoch": 23.08, "learning_rate": 9.243023030235844e-07, "loss": 0.7602, "step": 277660 }, { "epoch": 23.08, "learning_rate": 9.241914474960507e-07, "loss": 0.7356, "step": 277670 }, { "epoch": 23.08, "learning_rate": 9.240805919685169e-07, "loss": 0.7729, "step": 277680 }, { "epoch": 23.08, "learning_rate": 9.239697364409832e-07, "loss": 0.7172, "step": 277690 }, { "epoch": 23.08, "learning_rate": 9.238588809134495e-07, "loss": 0.7318, "step": 277700 }, { "epoch": 23.08, "learning_rate": 9.237480253859158e-07, "loss": 0.7643, "step": 277710 }, { "epoch": 23.08, "learning_rate": 9.23637169858382e-07, "loss": 0.7373, "step": 277720 }, { "epoch": 23.08, "learning_rate": 9.235263143308483e-07, "loss": 0.7069, "step": 277730 }, { "epoch": 23.09, "learning_rate": 9.234154588033145e-07, "loss": 0.7611, "step": 277740 }, { "epoch": 23.09, "learning_rate": 9.233046032757808e-07, "loss": 0.7441, "step": 277750 }, { "epoch": 23.09, "learning_rate": 9.231937477482471e-07, "loss": 0.7919, "step": 277760 }, { "epoch": 23.09, "learning_rate": 9.230828922207134e-07, "loss": 0.776, "step": 277770 }, { "epoch": 23.09, "learning_rate": 9.229720366931796e-07, "loss": 0.7569, "step": 277780 }, { "epoch": 23.09, "learning_rate": 9.228611811656459e-07, "loss": 0.7073, "step": 277790 }, { "epoch": 23.09, "learning_rate": 9.22750325638112e-07, "loss": 0.7232, "step": 277800 }, { "epoch": 23.09, "learning_rate": 9.226394701105783e-07, "loss": 0.768, "step": 277810 }, { "epoch": 23.09, "learning_rate": 9.225286145830446e-07, "loss": 0.7856, "step": 277820 }, { "epoch": 23.09, "learning_rate": 9.224177590555109e-07, "loss": 0.7586, "step": 277830 }, { "epoch": 23.09, "learning_rate": 9.223069035279771e-07, "loss": 0.7547, "step": 277840 }, { "epoch": 23.09, "learning_rate": 9.221960480004434e-07, "loss": 0.7678, "step": 277850 }, { "epoch": 23.1, "learning_rate": 9.220851924729096e-07, "loss": 0.7377, "step": 277860 }, { "epoch": 23.1, "learning_rate": 9.219743369453759e-07, "loss": 0.702, "step": 277870 }, { "epoch": 23.1, "learning_rate": 9.218634814178422e-07, "loss": 0.7338, "step": 277880 }, { "epoch": 23.1, "learning_rate": 9.217526258903085e-07, "loss": 0.7294, "step": 277890 }, { "epoch": 23.1, "learning_rate": 9.216417703627747e-07, "loss": 0.7507, "step": 277900 }, { "epoch": 23.1, "learning_rate": 9.215309148352409e-07, "loss": 0.7199, "step": 277910 }, { "epoch": 23.1, "learning_rate": 9.214200593077072e-07, "loss": 0.7435, "step": 277920 }, { "epoch": 23.1, "learning_rate": 9.213092037801734e-07, "loss": 0.6521, "step": 277930 }, { "epoch": 23.1, "learning_rate": 9.211983482526398e-07, "loss": 0.7397, "step": 277940 }, { "epoch": 23.1, "learning_rate": 9.21087492725106e-07, "loss": 0.6631, "step": 277950 }, { "epoch": 23.1, "learning_rate": 9.209766371975722e-07, "loss": 0.7407, "step": 277960 }, { "epoch": 23.1, "learning_rate": 9.208657816700384e-07, "loss": 0.7988, "step": 277970 }, { "epoch": 23.11, "learning_rate": 9.207549261425047e-07, "loss": 0.7534, "step": 277980 }, { "epoch": 23.11, "learning_rate": 9.206440706149709e-07, "loss": 0.6613, "step": 277990 }, { "epoch": 23.11, "learning_rate": 9.205332150874373e-07, "loss": 0.7355, "step": 278000 }, { "epoch": 23.11, "learning_rate": 9.204223595599035e-07, "loss": 0.7298, "step": 278010 }, { "epoch": 23.11, "learning_rate": 9.203115040323698e-07, "loss": 0.734, "step": 278020 }, { "epoch": 23.11, "learning_rate": 9.20200648504836e-07, "loss": 0.7176, "step": 278030 }, { "epoch": 23.11, "learning_rate": 9.200897929773023e-07, "loss": 0.7137, "step": 278040 }, { "epoch": 23.11, "learning_rate": 9.199789374497685e-07, "loss": 0.7361, "step": 278050 }, { "epoch": 23.11, "learning_rate": 9.198680819222348e-07, "loss": 0.7115, "step": 278060 }, { "epoch": 23.11, "learning_rate": 9.197572263947011e-07, "loss": 0.7383, "step": 278070 }, { "epoch": 23.11, "learning_rate": 9.196463708671674e-07, "loss": 0.7609, "step": 278080 }, { "epoch": 23.11, "learning_rate": 9.195355153396336e-07, "loss": 0.7518, "step": 278090 }, { "epoch": 23.12, "learning_rate": 9.194246598120998e-07, "loss": 0.6904, "step": 278100 }, { "epoch": 23.12, "learning_rate": 9.19313804284566e-07, "loss": 0.7487, "step": 278110 }, { "epoch": 23.12, "learning_rate": 9.192029487570323e-07, "loss": 0.7726, "step": 278120 }, { "epoch": 23.12, "learning_rate": 9.190920932294986e-07, "loss": 0.722, "step": 278130 }, { "epoch": 23.12, "learning_rate": 9.189812377019649e-07, "loss": 0.726, "step": 278140 }, { "epoch": 23.12, "learning_rate": 9.188703821744311e-07, "loss": 0.7054, "step": 278150 }, { "epoch": 23.12, "learning_rate": 9.187595266468974e-07, "loss": 0.684, "step": 278160 }, { "epoch": 23.12, "learning_rate": 9.186486711193636e-07, "loss": 0.7823, "step": 278170 }, { "epoch": 23.12, "learning_rate": 9.185378155918299e-07, "loss": 0.7583, "step": 278180 }, { "epoch": 23.12, "learning_rate": 9.184269600642962e-07, "loss": 0.7075, "step": 278190 }, { "epoch": 23.12, "learning_rate": 9.183161045367625e-07, "loss": 0.7645, "step": 278200 }, { "epoch": 23.12, "learning_rate": 9.182052490092287e-07, "loss": 0.6624, "step": 278210 }, { "epoch": 23.13, "learning_rate": 9.18094393481695e-07, "loss": 0.803, "step": 278220 }, { "epoch": 23.13, "learning_rate": 9.179835379541612e-07, "loss": 0.7249, "step": 278230 }, { "epoch": 23.13, "learning_rate": 9.178726824266275e-07, "loss": 0.7575, "step": 278240 }, { "epoch": 23.13, "learning_rate": 9.177618268990937e-07, "loss": 0.818, "step": 278250 }, { "epoch": 23.13, "learning_rate": 9.1765097137156e-07, "loss": 0.8038, "step": 278260 }, { "epoch": 23.13, "learning_rate": 9.175401158440262e-07, "loss": 0.7826, "step": 278270 }, { "epoch": 23.13, "learning_rate": 9.174292603164925e-07, "loss": 0.7789, "step": 278280 }, { "epoch": 23.13, "learning_rate": 9.173184047889587e-07, "loss": 0.7121, "step": 278290 }, { "epoch": 23.13, "learning_rate": 9.17207549261425e-07, "loss": 0.7896, "step": 278300 }, { "epoch": 23.13, "learning_rate": 9.170966937338913e-07, "loss": 0.7156, "step": 278310 }, { "epoch": 23.13, "learning_rate": 9.169858382063576e-07, "loss": 0.8364, "step": 278320 }, { "epoch": 23.13, "learning_rate": 9.168749826788238e-07, "loss": 0.7301, "step": 278330 }, { "epoch": 23.14, "learning_rate": 9.1676412715129e-07, "loss": 0.7825, "step": 278340 }, { "epoch": 23.14, "learning_rate": 9.166532716237563e-07, "loss": 0.7637, "step": 278350 }, { "epoch": 23.14, "learning_rate": 9.165424160962225e-07, "loss": 0.7597, "step": 278360 }, { "epoch": 23.14, "learning_rate": 9.164315605686889e-07, "loss": 0.7351, "step": 278370 }, { "epoch": 23.14, "learning_rate": 9.163207050411551e-07, "loss": 0.7447, "step": 278380 }, { "epoch": 23.14, "learning_rate": 9.162098495136214e-07, "loss": 0.726, "step": 278390 }, { "epoch": 23.14, "learning_rate": 9.160989939860875e-07, "loss": 0.7398, "step": 278400 }, { "epoch": 23.14, "learning_rate": 9.159881384585538e-07, "loss": 0.7088, "step": 278410 }, { "epoch": 23.14, "learning_rate": 9.1587728293102e-07, "loss": 0.7622, "step": 278420 }, { "epoch": 23.14, "learning_rate": 9.157664274034864e-07, "loss": 0.7787, "step": 278430 }, { "epoch": 23.14, "learning_rate": 9.156555718759526e-07, "loss": 0.7059, "step": 278440 }, { "epoch": 23.14, "learning_rate": 9.155447163484189e-07, "loss": 0.7182, "step": 278450 }, { "epoch": 23.15, "learning_rate": 9.154338608208851e-07, "loss": 0.7214, "step": 278460 }, { "epoch": 23.15, "learning_rate": 9.153230052933514e-07, "loss": 0.7724, "step": 278470 }, { "epoch": 23.15, "learning_rate": 9.152121497658176e-07, "loss": 0.7259, "step": 278480 }, { "epoch": 23.15, "learning_rate": 9.151012942382839e-07, "loss": 0.7335, "step": 278490 }, { "epoch": 23.15, "learning_rate": 9.149904387107502e-07, "loss": 0.6973, "step": 278500 }, { "epoch": 23.15, "learning_rate": 9.148795831832165e-07, "loss": 0.718, "step": 278510 }, { "epoch": 23.15, "learning_rate": 9.147687276556827e-07, "loss": 0.7894, "step": 278520 }, { "epoch": 23.15, "learning_rate": 9.14657872128149e-07, "loss": 0.7649, "step": 278530 }, { "epoch": 23.15, "learning_rate": 9.145470166006151e-07, "loss": 0.6952, "step": 278540 }, { "epoch": 23.15, "learning_rate": 9.144361610730814e-07, "loss": 0.7621, "step": 278550 }, { "epoch": 23.15, "learning_rate": 9.143253055455477e-07, "loss": 0.7762, "step": 278560 }, { "epoch": 23.15, "learning_rate": 9.14214450018014e-07, "loss": 0.7606, "step": 278570 }, { "epoch": 23.16, "learning_rate": 9.141035944904802e-07, "loss": 0.7519, "step": 278580 }, { "epoch": 23.16, "learning_rate": 9.139927389629465e-07, "loss": 0.7132, "step": 278590 }, { "epoch": 23.16, "learning_rate": 9.138818834354127e-07, "loss": 0.6821, "step": 278600 }, { "epoch": 23.16, "learning_rate": 9.13771027907879e-07, "loss": 0.8365, "step": 278610 }, { "epoch": 23.16, "learning_rate": 9.136601723803453e-07, "loss": 0.7837, "step": 278620 }, { "epoch": 23.16, "learning_rate": 9.135493168528116e-07, "loss": 0.7669, "step": 278630 }, { "epoch": 23.16, "learning_rate": 9.134384613252778e-07, "loss": 0.6875, "step": 278640 }, { "epoch": 23.16, "learning_rate": 9.133276057977441e-07, "loss": 0.7106, "step": 278650 }, { "epoch": 23.16, "learning_rate": 9.132167502702103e-07, "loss": 0.734, "step": 278660 }, { "epoch": 23.16, "learning_rate": 9.131058947426766e-07, "loss": 0.7857, "step": 278670 }, { "epoch": 23.16, "learning_rate": 9.129950392151429e-07, "loss": 0.7362, "step": 278680 }, { "epoch": 23.16, "learning_rate": 9.128841836876092e-07, "loss": 0.7315, "step": 278690 }, { "epoch": 23.17, "learning_rate": 9.127733281600753e-07, "loss": 0.7936, "step": 278700 }, { "epoch": 23.17, "learning_rate": 9.126624726325416e-07, "loss": 0.7406, "step": 278710 }, { "epoch": 23.17, "learning_rate": 9.125516171050078e-07, "loss": 0.8077, "step": 278720 }, { "epoch": 23.17, "learning_rate": 9.12440761577474e-07, "loss": 0.7763, "step": 278730 }, { "epoch": 23.17, "learning_rate": 9.123299060499404e-07, "loss": 0.7368, "step": 278740 }, { "epoch": 23.17, "learning_rate": 9.122190505224066e-07, "loss": 0.6657, "step": 278750 }, { "epoch": 23.17, "learning_rate": 9.121081949948729e-07, "loss": 0.7365, "step": 278760 }, { "epoch": 23.17, "learning_rate": 9.119973394673391e-07, "loss": 0.7624, "step": 278770 }, { "epoch": 23.17, "learning_rate": 9.118864839398054e-07, "loss": 0.7403, "step": 278780 }, { "epoch": 23.17, "learning_rate": 9.117756284122716e-07, "loss": 0.6221, "step": 278790 }, { "epoch": 23.17, "learning_rate": 9.11664772884738e-07, "loss": 0.7392, "step": 278800 }, { "epoch": 23.17, "learning_rate": 9.115539173572042e-07, "loss": 0.7133, "step": 278810 }, { "epoch": 23.18, "learning_rate": 9.114430618296705e-07, "loss": 0.8065, "step": 278820 }, { "epoch": 23.18, "learning_rate": 9.113322063021367e-07, "loss": 0.6976, "step": 278830 }, { "epoch": 23.18, "learning_rate": 9.11221350774603e-07, "loss": 0.8116, "step": 278840 }, { "epoch": 23.18, "learning_rate": 9.111104952470691e-07, "loss": 0.7662, "step": 278850 }, { "epoch": 23.18, "learning_rate": 9.109996397195355e-07, "loss": 0.743, "step": 278860 }, { "epoch": 23.18, "learning_rate": 9.108887841920017e-07, "loss": 0.7374, "step": 278870 }, { "epoch": 23.18, "learning_rate": 9.10777928664468e-07, "loss": 0.7504, "step": 278880 }, { "epoch": 23.18, "learning_rate": 9.106670731369342e-07, "loss": 0.7823, "step": 278890 }, { "epoch": 23.18, "learning_rate": 9.105562176094005e-07, "loss": 0.7405, "step": 278900 }, { "epoch": 23.18, "learning_rate": 9.104453620818667e-07, "loss": 0.7123, "step": 278910 }, { "epoch": 23.18, "learning_rate": 9.10334506554333e-07, "loss": 0.7826, "step": 278920 }, { "epoch": 23.18, "learning_rate": 9.102236510267993e-07, "loss": 0.663, "step": 278930 }, { "epoch": 23.19, "learning_rate": 9.101127954992656e-07, "loss": 0.7275, "step": 278940 }, { "epoch": 23.19, "learning_rate": 9.100019399717318e-07, "loss": 0.7255, "step": 278950 }, { "epoch": 23.19, "learning_rate": 9.098910844441981e-07, "loss": 0.7156, "step": 278960 }, { "epoch": 23.19, "learning_rate": 9.097802289166643e-07, "loss": 0.8203, "step": 278970 }, { "epoch": 23.19, "learning_rate": 9.096693733891306e-07, "loss": 0.7279, "step": 278980 }, { "epoch": 23.19, "learning_rate": 9.095585178615969e-07, "loss": 0.7412, "step": 278990 }, { "epoch": 23.19, "learning_rate": 9.094476623340631e-07, "loss": 0.694, "step": 279000 }, { "epoch": 23.19, "learning_rate": 9.093368068065293e-07, "loss": 0.7847, "step": 279010 }, { "epoch": 23.19, "learning_rate": 9.092259512789956e-07, "loss": 0.7746, "step": 279020 }, { "epoch": 23.19, "learning_rate": 9.091150957514618e-07, "loss": 0.7438, "step": 279030 }, { "epoch": 23.19, "learning_rate": 9.090042402239281e-07, "loss": 0.7206, "step": 279040 }, { "epoch": 23.19, "learning_rate": 9.088933846963944e-07, "loss": 0.7347, "step": 279050 }, { "epoch": 23.2, "learning_rate": 9.087825291688607e-07, "loss": 0.7745, "step": 279060 }, { "epoch": 23.2, "learning_rate": 9.086716736413269e-07, "loss": 0.7787, "step": 279070 }, { "epoch": 23.2, "learning_rate": 9.085608181137932e-07, "loss": 0.7728, "step": 279080 }, { "epoch": 23.2, "learning_rate": 9.084499625862594e-07, "loss": 0.7514, "step": 279090 }, { "epoch": 23.2, "learning_rate": 9.083391070587257e-07, "loss": 0.6835, "step": 279100 }, { "epoch": 23.2, "learning_rate": 9.08228251531192e-07, "loss": 0.6919, "step": 279110 }, { "epoch": 23.2, "learning_rate": 9.081173960036583e-07, "loss": 0.7666, "step": 279120 }, { "epoch": 23.2, "learning_rate": 9.080065404761245e-07, "loss": 0.7804, "step": 279130 }, { "epoch": 23.2, "learning_rate": 9.078956849485908e-07, "loss": 0.7287, "step": 279140 }, { "epoch": 23.2, "learning_rate": 9.077848294210569e-07, "loss": 0.7314, "step": 279150 }, { "epoch": 23.2, "learning_rate": 9.076739738935231e-07, "loss": 0.787, "step": 279160 }, { "epoch": 23.2, "learning_rate": 9.075631183659895e-07, "loss": 0.76, "step": 279170 }, { "epoch": 23.21, "learning_rate": 9.074522628384557e-07, "loss": 0.71, "step": 279180 }, { "epoch": 23.21, "learning_rate": 9.07341407310922e-07, "loss": 0.7312, "step": 279190 }, { "epoch": 23.21, "learning_rate": 9.072305517833882e-07, "loss": 0.7512, "step": 279200 }, { "epoch": 23.21, "learning_rate": 9.071196962558545e-07, "loss": 0.6884, "step": 279210 }, { "epoch": 23.21, "learning_rate": 9.070088407283207e-07, "loss": 0.7556, "step": 279220 }, { "epoch": 23.21, "learning_rate": 9.068979852007871e-07, "loss": 0.741, "step": 279230 }, { "epoch": 23.21, "learning_rate": 9.067871296732533e-07, "loss": 0.7184, "step": 279240 }, { "epoch": 23.21, "learning_rate": 9.066762741457196e-07, "loss": 0.7596, "step": 279250 }, { "epoch": 23.21, "learning_rate": 9.065654186181858e-07, "loss": 0.702, "step": 279260 }, { "epoch": 23.21, "learning_rate": 9.064545630906521e-07, "loss": 0.7599, "step": 279270 }, { "epoch": 23.21, "learning_rate": 9.063437075631183e-07, "loss": 0.6701, "step": 279280 }, { "epoch": 23.21, "learning_rate": 9.062328520355847e-07, "loss": 0.7382, "step": 279290 }, { "epoch": 23.22, "learning_rate": 9.061219965080508e-07, "loss": 0.709, "step": 279300 }, { "epoch": 23.22, "learning_rate": 9.060111409805171e-07, "loss": 0.7105, "step": 279310 }, { "epoch": 23.22, "learning_rate": 9.059002854529833e-07, "loss": 0.7177, "step": 279320 }, { "epoch": 23.22, "learning_rate": 9.057894299254496e-07, "loss": 0.7539, "step": 279330 }, { "epoch": 23.22, "learning_rate": 9.056785743979158e-07, "loss": 0.7182, "step": 279340 }, { "epoch": 23.22, "learning_rate": 9.055677188703821e-07, "loss": 0.745, "step": 279350 }, { "epoch": 23.22, "learning_rate": 9.054568633428484e-07, "loss": 0.7215, "step": 279360 }, { "epoch": 23.22, "learning_rate": 9.053460078153147e-07, "loss": 0.7284, "step": 279370 }, { "epoch": 23.22, "learning_rate": 9.052351522877809e-07, "loss": 0.7538, "step": 279380 }, { "epoch": 23.22, "learning_rate": 9.051242967602472e-07, "loss": 0.7517, "step": 279390 }, { "epoch": 23.22, "learning_rate": 9.050134412327134e-07, "loss": 0.7303, "step": 279400 }, { "epoch": 23.22, "learning_rate": 9.049025857051797e-07, "loss": 0.7213, "step": 279410 }, { "epoch": 23.23, "learning_rate": 9.04791730177646e-07, "loss": 0.7411, "step": 279420 }, { "epoch": 23.23, "learning_rate": 9.046808746501123e-07, "loss": 0.7453, "step": 279430 }, { "epoch": 23.23, "learning_rate": 9.045700191225784e-07, "loss": 0.6986, "step": 279440 }, { "epoch": 23.23, "learning_rate": 9.044591635950447e-07, "loss": 0.7364, "step": 279450 }, { "epoch": 23.23, "learning_rate": 9.043483080675109e-07, "loss": 0.6824, "step": 279460 }, { "epoch": 23.23, "learning_rate": 9.042374525399772e-07, "loss": 0.7619, "step": 279470 }, { "epoch": 23.23, "learning_rate": 9.041265970124435e-07, "loss": 0.723, "step": 279480 }, { "epoch": 23.23, "learning_rate": 9.040157414849098e-07, "loss": 0.7821, "step": 279490 }, { "epoch": 23.23, "learning_rate": 9.03904885957376e-07, "loss": 0.7517, "step": 279500 }, { "epoch": 23.23, "learning_rate": 9.037940304298423e-07, "loss": 0.7803, "step": 279510 }, { "epoch": 23.23, "learning_rate": 9.036831749023085e-07, "loss": 0.7794, "step": 279520 }, { "epoch": 23.23, "learning_rate": 9.035723193747748e-07, "loss": 0.7472, "step": 279530 }, { "epoch": 23.23, "learning_rate": 9.034614638472411e-07, "loss": 0.6936, "step": 279540 }, { "epoch": 23.24, "learning_rate": 9.033506083197074e-07, "loss": 0.7517, "step": 279550 }, { "epoch": 23.24, "learning_rate": 9.032397527921736e-07, "loss": 0.7984, "step": 279560 }, { "epoch": 23.24, "learning_rate": 9.031288972646398e-07, "loss": 0.8076, "step": 279570 }, { "epoch": 23.24, "learning_rate": 9.030180417371061e-07, "loss": 0.7392, "step": 279580 }, { "epoch": 23.24, "learning_rate": 9.029071862095722e-07, "loss": 0.7438, "step": 279590 }, { "epoch": 23.24, "learning_rate": 9.027963306820386e-07, "loss": 0.7016, "step": 279600 }, { "epoch": 23.24, "learning_rate": 9.026854751545048e-07, "loss": 0.6972, "step": 279610 }, { "epoch": 23.24, "learning_rate": 9.025746196269711e-07, "loss": 0.741, "step": 279620 }, { "epoch": 23.24, "learning_rate": 9.024637640994373e-07, "loss": 0.6298, "step": 279630 }, { "epoch": 23.24, "learning_rate": 9.023529085719036e-07, "loss": 0.7608, "step": 279640 }, { "epoch": 23.24, "learning_rate": 9.022420530443698e-07, "loss": 0.7384, "step": 279650 }, { "epoch": 23.24, "learning_rate": 9.021311975168362e-07, "loss": 0.7429, "step": 279660 }, { "epoch": 23.25, "learning_rate": 9.020203419893024e-07, "loss": 0.8098, "step": 279670 }, { "epoch": 23.25, "learning_rate": 9.019094864617687e-07, "loss": 0.738, "step": 279680 }, { "epoch": 23.25, "learning_rate": 9.017986309342349e-07, "loss": 0.72, "step": 279690 }, { "epoch": 23.25, "learning_rate": 9.016877754067012e-07, "loss": 0.7332, "step": 279700 }, { "epoch": 23.25, "learning_rate": 9.015769198791674e-07, "loss": 0.736, "step": 279710 }, { "epoch": 23.25, "learning_rate": 9.014660643516337e-07, "loss": 0.7324, "step": 279720 }, { "epoch": 23.25, "learning_rate": 9.013552088241e-07, "loss": 0.7364, "step": 279730 }, { "epoch": 23.25, "learning_rate": 9.012443532965662e-07, "loss": 0.6783, "step": 279740 }, { "epoch": 23.25, "learning_rate": 9.011334977690324e-07, "loss": 0.745, "step": 279750 }, { "epoch": 23.25, "learning_rate": 9.010226422414987e-07, "loss": 0.7102, "step": 279760 }, { "epoch": 23.25, "learning_rate": 9.009117867139649e-07, "loss": 0.7771, "step": 279770 }, { "epoch": 23.25, "learning_rate": 9.008009311864312e-07, "loss": 0.72, "step": 279780 }, { "epoch": 23.26, "learning_rate": 9.006900756588975e-07, "loss": 0.6955, "step": 279790 }, { "epoch": 23.26, "learning_rate": 9.005792201313638e-07, "loss": 0.7515, "step": 279800 }, { "epoch": 23.26, "learning_rate": 9.0046836460383e-07, "loss": 0.7259, "step": 279810 }, { "epoch": 23.26, "learning_rate": 9.003575090762963e-07, "loss": 0.7419, "step": 279820 }, { "epoch": 23.26, "learning_rate": 9.002466535487625e-07, "loss": 0.769, "step": 279830 }, { "epoch": 23.26, "learning_rate": 9.001357980212288e-07, "loss": 0.7198, "step": 279840 }, { "epoch": 23.26, "learning_rate": 9.000249424936951e-07, "loss": 0.7507, "step": 279850 }, { "epoch": 23.26, "learning_rate": 8.999140869661614e-07, "loss": 0.7619, "step": 279860 }, { "epoch": 23.26, "learning_rate": 8.998032314386276e-07, "loss": 0.8299, "step": 279870 }, { "epoch": 23.26, "learning_rate": 8.996923759110939e-07, "loss": 0.7259, "step": 279880 }, { "epoch": 23.26, "learning_rate": 8.9958152038356e-07, "loss": 0.7601, "step": 279890 }, { "epoch": 23.26, "learning_rate": 8.994706648560263e-07, "loss": 0.7732, "step": 279900 }, { "epoch": 23.27, "learning_rate": 8.993598093284926e-07, "loss": 0.7965, "step": 279910 }, { "epoch": 23.27, "learning_rate": 8.992489538009589e-07, "loss": 0.7563, "step": 279920 }, { "epoch": 23.27, "learning_rate": 8.991491838261785e-07, "loss": 0.7046, "step": 279930 }, { "epoch": 23.27, "learning_rate": 8.990383282986448e-07, "loss": 0.6959, "step": 279940 }, { "epoch": 23.27, "learning_rate": 8.989274727711111e-07, "loss": 0.7622, "step": 279950 }, { "epoch": 23.27, "learning_rate": 8.988166172435772e-07, "loss": 0.666, "step": 279960 }, { "epoch": 23.27, "learning_rate": 8.987057617160435e-07, "loss": 0.77, "step": 279970 }, { "epoch": 23.27, "learning_rate": 8.985949061885097e-07, "loss": 0.7679, "step": 279980 }, { "epoch": 23.27, "learning_rate": 8.98484050660976e-07, "loss": 0.724, "step": 279990 }, { "epoch": 23.27, "learning_rate": 8.983731951334423e-07, "loss": 0.772, "step": 280000 }, { "epoch": 23.27, "learning_rate": 8.982623396059086e-07, "loss": 0.7907, "step": 280010 }, { "epoch": 23.27, "learning_rate": 8.981514840783748e-07, "loss": 0.7503, "step": 280020 }, { "epoch": 23.28, "learning_rate": 8.980406285508411e-07, "loss": 0.7256, "step": 280030 }, { "epoch": 23.28, "learning_rate": 8.979297730233073e-07, "loss": 0.7058, "step": 280040 }, { "epoch": 23.28, "learning_rate": 8.978189174957736e-07, "loss": 0.755, "step": 280050 }, { "epoch": 23.28, "learning_rate": 8.977080619682399e-07, "loss": 0.7251, "step": 280060 }, { "epoch": 23.28, "learning_rate": 8.975972064407062e-07, "loss": 0.7615, "step": 280070 }, { "epoch": 23.28, "learning_rate": 8.974863509131724e-07, "loss": 0.7356, "step": 280080 }, { "epoch": 23.28, "learning_rate": 8.973754953856387e-07, "loss": 0.756, "step": 280090 }, { "epoch": 23.28, "learning_rate": 8.972646398581049e-07, "loss": 0.7053, "step": 280100 }, { "epoch": 23.28, "learning_rate": 8.97153784330571e-07, "loss": 0.7433, "step": 280110 }, { "epoch": 23.28, "learning_rate": 8.970429288030374e-07, "loss": 0.799, "step": 280120 }, { "epoch": 23.28, "learning_rate": 8.969320732755036e-07, "loss": 0.7565, "step": 280130 }, { "epoch": 23.28, "learning_rate": 8.968212177479699e-07, "loss": 0.7317, "step": 280140 }, { "epoch": 23.29, "learning_rate": 8.967103622204361e-07, "loss": 0.7523, "step": 280150 }, { "epoch": 23.29, "learning_rate": 8.965995066929024e-07, "loss": 0.7937, "step": 280160 }, { "epoch": 23.29, "learning_rate": 8.964886511653686e-07, "loss": 0.7924, "step": 280170 }, { "epoch": 23.29, "learning_rate": 8.96377795637835e-07, "loss": 0.7255, "step": 280180 }, { "epoch": 23.29, "learning_rate": 8.962669401103012e-07, "loss": 0.6603, "step": 280190 }, { "epoch": 23.29, "learning_rate": 8.961560845827675e-07, "loss": 0.7578, "step": 280200 }, { "epoch": 23.29, "learning_rate": 8.960452290552337e-07, "loss": 0.788, "step": 280210 }, { "epoch": 23.29, "learning_rate": 8.959343735277e-07, "loss": 0.7756, "step": 280220 }, { "epoch": 23.29, "learning_rate": 8.958235180001662e-07, "loss": 0.7097, "step": 280230 }, { "epoch": 23.29, "learning_rate": 8.957126624726326e-07, "loss": 0.7482, "step": 280240 }, { "epoch": 23.29, "learning_rate": 8.956018069450988e-07, "loss": 0.6261, "step": 280250 }, { "epoch": 23.29, "learning_rate": 8.95490951417565e-07, "loss": 0.7252, "step": 280260 }, { "epoch": 23.3, "learning_rate": 8.953800958900312e-07, "loss": 0.7137, "step": 280270 }, { "epoch": 23.3, "learning_rate": 8.952692403624975e-07, "loss": 0.7409, "step": 280280 }, { "epoch": 23.3, "learning_rate": 8.951583848349637e-07, "loss": 0.6909, "step": 280290 }, { "epoch": 23.3, "learning_rate": 8.950475293074301e-07, "loss": 0.7899, "step": 280300 }, { "epoch": 23.3, "learning_rate": 8.949366737798963e-07, "loss": 0.6859, "step": 280310 }, { "epoch": 23.3, "learning_rate": 8.948258182523626e-07, "loss": 0.7478, "step": 280320 }, { "epoch": 23.3, "learning_rate": 8.947149627248288e-07, "loss": 0.742, "step": 280330 }, { "epoch": 23.3, "learning_rate": 8.946041071972951e-07, "loss": 0.8069, "step": 280340 }, { "epoch": 23.3, "learning_rate": 8.944932516697613e-07, "loss": 0.7589, "step": 280350 }, { "epoch": 23.3, "learning_rate": 8.943823961422276e-07, "loss": 0.7185, "step": 280360 }, { "epoch": 23.3, "learning_rate": 8.942715406146939e-07, "loss": 0.8379, "step": 280370 }, { "epoch": 23.3, "learning_rate": 8.941606850871602e-07, "loss": 0.7294, "step": 280380 }, { "epoch": 23.31, "learning_rate": 8.940498295596264e-07, "loss": 0.7332, "step": 280390 }, { "epoch": 23.31, "learning_rate": 8.939389740320927e-07, "loss": 0.7289, "step": 280400 }, { "epoch": 23.31, "learning_rate": 8.938281185045588e-07, "loss": 0.7048, "step": 280410 }, { "epoch": 23.31, "learning_rate": 8.937172629770251e-07, "loss": 0.763, "step": 280420 }, { "epoch": 23.31, "learning_rate": 8.936064074494914e-07, "loss": 0.7569, "step": 280430 }, { "epoch": 23.31, "learning_rate": 8.934955519219577e-07, "loss": 0.7087, "step": 280440 }, { "epoch": 23.31, "learning_rate": 8.933846963944239e-07, "loss": 0.6742, "step": 280450 }, { "epoch": 23.31, "learning_rate": 8.932738408668902e-07, "loss": 0.6826, "step": 280460 }, { "epoch": 23.31, "learning_rate": 8.931629853393564e-07, "loss": 0.7582, "step": 280470 }, { "epoch": 23.31, "learning_rate": 8.930521298118227e-07, "loss": 0.7816, "step": 280480 }, { "epoch": 23.31, "learning_rate": 8.92941274284289e-07, "loss": 0.6987, "step": 280490 }, { "epoch": 23.31, "learning_rate": 8.928304187567553e-07, "loss": 0.7152, "step": 280500 }, { "epoch": 23.32, "learning_rate": 8.927195632292215e-07, "loss": 0.7365, "step": 280510 }, { "epoch": 23.32, "learning_rate": 8.926087077016878e-07, "loss": 0.7663, "step": 280520 }, { "epoch": 23.32, "learning_rate": 8.92497852174154e-07, "loss": 0.7578, "step": 280530 }, { "epoch": 23.32, "learning_rate": 8.923869966466202e-07, "loss": 0.7329, "step": 280540 }, { "epoch": 23.32, "learning_rate": 8.922761411190866e-07, "loss": 0.7473, "step": 280550 }, { "epoch": 23.32, "learning_rate": 8.921652855915527e-07, "loss": 0.7493, "step": 280560 }, { "epoch": 23.32, "learning_rate": 8.92054430064019e-07, "loss": 0.7889, "step": 280570 }, { "epoch": 23.32, "learning_rate": 8.919435745364852e-07, "loss": 0.7027, "step": 280580 }, { "epoch": 23.32, "learning_rate": 8.918327190089515e-07, "loss": 0.7385, "step": 280590 }, { "epoch": 23.32, "learning_rate": 8.917218634814177e-07, "loss": 0.7436, "step": 280600 }, { "epoch": 23.32, "learning_rate": 8.916110079538841e-07, "loss": 0.7165, "step": 280610 }, { "epoch": 23.32, "learning_rate": 8.915001524263503e-07, "loss": 0.7185, "step": 280620 }, { "epoch": 23.33, "learning_rate": 8.913892968988166e-07, "loss": 0.7056, "step": 280630 }, { "epoch": 23.33, "learning_rate": 8.912784413712828e-07, "loss": 0.7519, "step": 280640 }, { "epoch": 23.33, "learning_rate": 8.911675858437491e-07, "loss": 0.7125, "step": 280650 }, { "epoch": 23.33, "learning_rate": 8.910567303162153e-07, "loss": 0.7345, "step": 280660 }, { "epoch": 23.33, "learning_rate": 8.909458747886817e-07, "loss": 0.7459, "step": 280670 }, { "epoch": 23.33, "learning_rate": 8.908350192611479e-07, "loss": 0.714, "step": 280680 }, { "epoch": 23.33, "learning_rate": 8.907241637336142e-07, "loss": 0.7594, "step": 280690 }, { "epoch": 23.33, "learning_rate": 8.906133082060804e-07, "loss": 0.7438, "step": 280700 }, { "epoch": 23.33, "learning_rate": 8.905024526785466e-07, "loss": 0.7217, "step": 280710 }, { "epoch": 23.33, "learning_rate": 8.903915971510128e-07, "loss": 0.7387, "step": 280720 }, { "epoch": 23.33, "learning_rate": 8.902807416234792e-07, "loss": 0.7824, "step": 280730 }, { "epoch": 23.33, "learning_rate": 8.901698860959454e-07, "loss": 0.7326, "step": 280740 }, { "epoch": 23.34, "learning_rate": 8.900590305684117e-07, "loss": 0.6773, "step": 280750 }, { "epoch": 23.34, "learning_rate": 8.899481750408779e-07, "loss": 0.7425, "step": 280760 }, { "epoch": 23.34, "learning_rate": 8.898373195133442e-07, "loss": 0.7597, "step": 280770 }, { "epoch": 23.34, "learning_rate": 8.897264639858104e-07, "loss": 0.7288, "step": 280780 }, { "epoch": 23.34, "learning_rate": 8.896156084582767e-07, "loss": 0.7117, "step": 280790 }, { "epoch": 23.34, "learning_rate": 8.89504752930743e-07, "loss": 0.7629, "step": 280800 }, { "epoch": 23.34, "learning_rate": 8.893938974032093e-07, "loss": 0.7356, "step": 280810 }, { "epoch": 23.34, "learning_rate": 8.892830418756755e-07, "loss": 0.7972, "step": 280820 }, { "epoch": 23.34, "learning_rate": 8.891721863481418e-07, "loss": 0.7793, "step": 280830 }, { "epoch": 23.34, "learning_rate": 8.89061330820608e-07, "loss": 0.7084, "step": 280840 }, { "epoch": 23.34, "learning_rate": 8.889504752930743e-07, "loss": 0.7343, "step": 280850 }, { "epoch": 23.34, "learning_rate": 8.888396197655405e-07, "loss": 0.7793, "step": 280860 }, { "epoch": 23.35, "learning_rate": 8.887287642380068e-07, "loss": 0.8157, "step": 280870 }, { "epoch": 23.35, "learning_rate": 8.88617908710473e-07, "loss": 0.7341, "step": 280880 }, { "epoch": 23.35, "learning_rate": 8.885070531829393e-07, "loss": 0.7517, "step": 280890 }, { "epoch": 23.35, "learning_rate": 8.883961976554055e-07, "loss": 0.7744, "step": 280900 }, { "epoch": 23.35, "learning_rate": 8.882853421278718e-07, "loss": 0.7171, "step": 280910 }, { "epoch": 23.35, "learning_rate": 8.881744866003381e-07, "loss": 0.7465, "step": 280920 }, { "epoch": 23.35, "learning_rate": 8.880636310728044e-07, "loss": 0.6807, "step": 280930 }, { "epoch": 23.35, "learning_rate": 8.879527755452706e-07, "loss": 0.7555, "step": 280940 }, { "epoch": 23.35, "learning_rate": 8.878419200177368e-07, "loss": 0.7743, "step": 280950 }, { "epoch": 23.35, "learning_rate": 8.877310644902031e-07, "loss": 0.6842, "step": 280960 }, { "epoch": 23.35, "learning_rate": 8.876202089626693e-07, "loss": 0.7527, "step": 280970 }, { "epoch": 23.35, "learning_rate": 8.875093534351357e-07, "loss": 0.7441, "step": 280980 }, { "epoch": 23.36, "learning_rate": 8.873984979076019e-07, "loss": 0.7395, "step": 280990 }, { "epoch": 23.36, "learning_rate": 8.872876423800682e-07, "loss": 0.7441, "step": 281000 }, { "epoch": 23.36, "learning_rate": 8.871767868525343e-07, "loss": 0.7591, "step": 281010 }, { "epoch": 23.36, "learning_rate": 8.870659313250006e-07, "loss": 0.7959, "step": 281020 }, { "epoch": 23.36, "learning_rate": 8.869550757974668e-07, "loss": 0.664, "step": 281030 }, { "epoch": 23.36, "learning_rate": 8.868442202699332e-07, "loss": 0.7129, "step": 281040 }, { "epoch": 23.36, "learning_rate": 8.867333647423994e-07, "loss": 0.7412, "step": 281050 }, { "epoch": 23.36, "learning_rate": 8.866225092148657e-07, "loss": 0.7008, "step": 281060 }, { "epoch": 23.36, "learning_rate": 8.865116536873319e-07, "loss": 0.7834, "step": 281070 }, { "epoch": 23.36, "learning_rate": 8.864007981597982e-07, "loss": 0.7923, "step": 281080 }, { "epoch": 23.36, "learning_rate": 8.862899426322644e-07, "loss": 0.7823, "step": 281090 }, { "epoch": 23.36, "learning_rate": 8.861790871047308e-07, "loss": 0.7418, "step": 281100 }, { "epoch": 23.37, "learning_rate": 8.86068231577197e-07, "loss": 0.697, "step": 281110 }, { "epoch": 23.37, "learning_rate": 8.859573760496633e-07, "loss": 0.7364, "step": 281120 }, { "epoch": 23.37, "learning_rate": 8.858465205221295e-07, "loss": 0.7403, "step": 281130 }, { "epoch": 23.37, "learning_rate": 8.857356649945958e-07, "loss": 0.7706, "step": 281140 }, { "epoch": 23.37, "learning_rate": 8.85624809467062e-07, "loss": 0.744, "step": 281150 }, { "epoch": 23.37, "learning_rate": 8.855139539395283e-07, "loss": 0.7758, "step": 281160 }, { "epoch": 23.37, "learning_rate": 8.854030984119945e-07, "loss": 0.7472, "step": 281170 }, { "epoch": 23.37, "learning_rate": 8.852922428844608e-07, "loss": 0.8092, "step": 281180 }, { "epoch": 23.37, "learning_rate": 8.85181387356927e-07, "loss": 0.7603, "step": 281190 }, { "epoch": 23.37, "learning_rate": 8.850705318293933e-07, "loss": 0.7886, "step": 281200 }, { "epoch": 23.37, "learning_rate": 8.849596763018595e-07, "loss": 0.7174, "step": 281210 }, { "epoch": 23.37, "learning_rate": 8.848488207743258e-07, "loss": 0.7573, "step": 281220 }, { "epoch": 23.38, "learning_rate": 8.847379652467921e-07, "loss": 0.7784, "step": 281230 }, { "epoch": 23.38, "learning_rate": 8.846271097192584e-07, "loss": 0.7544, "step": 281240 }, { "epoch": 23.38, "learning_rate": 8.845162541917246e-07, "loss": 0.7703, "step": 281250 }, { "epoch": 23.38, "learning_rate": 8.844053986641909e-07, "loss": 0.7315, "step": 281260 }, { "epoch": 23.38, "learning_rate": 8.842945431366571e-07, "loss": 0.7414, "step": 281270 }, { "epoch": 23.38, "learning_rate": 8.841836876091234e-07, "loss": 0.7052, "step": 281280 }, { "epoch": 23.38, "learning_rate": 8.840728320815897e-07, "loss": 0.7011, "step": 281290 }, { "epoch": 23.38, "learning_rate": 8.83961976554056e-07, "loss": 0.6989, "step": 281300 }, { "epoch": 23.38, "learning_rate": 8.838511210265221e-07, "loss": 0.6989, "step": 281310 }, { "epoch": 23.38, "learning_rate": 8.837402654989884e-07, "loss": 0.7645, "step": 281320 }, { "epoch": 23.38, "learning_rate": 8.836294099714546e-07, "loss": 0.7614, "step": 281330 }, { "epoch": 23.38, "learning_rate": 8.835185544439209e-07, "loss": 0.7405, "step": 281340 }, { "epoch": 23.39, "learning_rate": 8.834076989163872e-07, "loss": 0.7832, "step": 281350 }, { "epoch": 23.39, "learning_rate": 8.832968433888535e-07, "loss": 0.7866, "step": 281360 }, { "epoch": 23.39, "learning_rate": 8.831859878613197e-07, "loss": 0.7751, "step": 281370 }, { "epoch": 23.39, "learning_rate": 8.830751323337859e-07, "loss": 0.7431, "step": 281380 }, { "epoch": 23.39, "learning_rate": 8.829642768062522e-07, "loss": 0.7401, "step": 281390 }, { "epoch": 23.39, "learning_rate": 8.828534212787184e-07, "loss": 0.7253, "step": 281400 }, { "epoch": 23.39, "learning_rate": 8.827425657511848e-07, "loss": 0.7445, "step": 281410 }, { "epoch": 23.39, "learning_rate": 8.82631710223651e-07, "loss": 0.7689, "step": 281420 }, { "epoch": 23.39, "learning_rate": 8.825208546961173e-07, "loss": 0.7325, "step": 281430 }, { "epoch": 23.39, "learning_rate": 8.824099991685835e-07, "loss": 0.7731, "step": 281440 }, { "epoch": 23.39, "learning_rate": 8.822991436410497e-07, "loss": 0.7313, "step": 281450 }, { "epoch": 23.39, "learning_rate": 8.821882881135159e-07, "loss": 0.7637, "step": 281460 }, { "epoch": 23.4, "learning_rate": 8.820774325859823e-07, "loss": 0.7495, "step": 281470 }, { "epoch": 23.4, "learning_rate": 8.819665770584485e-07, "loss": 0.7392, "step": 281480 }, { "epoch": 23.4, "learning_rate": 8.818557215309148e-07, "loss": 0.788, "step": 281490 }, { "epoch": 23.4, "learning_rate": 8.81744866003381e-07, "loss": 0.7284, "step": 281500 }, { "epoch": 23.4, "learning_rate": 8.816340104758473e-07, "loss": 0.7448, "step": 281510 }, { "epoch": 23.4, "learning_rate": 8.815231549483135e-07, "loss": 0.8047, "step": 281520 }, { "epoch": 23.4, "learning_rate": 8.814122994207799e-07, "loss": 0.7391, "step": 281530 }, { "epoch": 23.4, "learning_rate": 8.813014438932461e-07, "loss": 0.7238, "step": 281540 }, { "epoch": 23.4, "learning_rate": 8.811905883657124e-07, "loss": 0.7637, "step": 281550 }, { "epoch": 23.4, "learning_rate": 8.810797328381786e-07, "loss": 0.688, "step": 281560 }, { "epoch": 23.4, "learning_rate": 8.809688773106449e-07, "loss": 0.7209, "step": 281570 }, { "epoch": 23.4, "learning_rate": 8.808580217831111e-07, "loss": 0.7426, "step": 281580 }, { "epoch": 23.41, "learning_rate": 8.807471662555775e-07, "loss": 0.7546, "step": 281590 }, { "epoch": 23.41, "learning_rate": 8.806363107280436e-07, "loss": 0.7531, "step": 281600 }, { "epoch": 23.41, "learning_rate": 8.805254552005099e-07, "loss": 0.794, "step": 281610 }, { "epoch": 23.41, "learning_rate": 8.804145996729761e-07, "loss": 0.8381, "step": 281620 }, { "epoch": 23.41, "learning_rate": 8.803037441454424e-07, "loss": 0.7379, "step": 281630 }, { "epoch": 23.41, "learning_rate": 8.801928886179086e-07, "loss": 0.7372, "step": 281640 }, { "epoch": 23.41, "learning_rate": 8.800820330903749e-07, "loss": 0.7942, "step": 281650 }, { "epoch": 23.41, "learning_rate": 8.799711775628412e-07, "loss": 0.7192, "step": 281660 }, { "epoch": 23.41, "learning_rate": 8.798603220353075e-07, "loss": 0.779, "step": 281670 }, { "epoch": 23.41, "learning_rate": 8.797494665077737e-07, "loss": 0.7679, "step": 281680 }, { "epoch": 23.41, "learning_rate": 8.7963861098024e-07, "loss": 0.7177, "step": 281690 }, { "epoch": 23.41, "learning_rate": 8.795277554527062e-07, "loss": 0.751, "step": 281700 }, { "epoch": 23.42, "learning_rate": 8.794168999251725e-07, "loss": 0.7267, "step": 281710 }, { "epoch": 23.42, "learning_rate": 8.793060443976388e-07, "loss": 0.7814, "step": 281720 }, { "epoch": 23.42, "learning_rate": 8.791951888701051e-07, "loss": 0.7555, "step": 281730 }, { "epoch": 23.42, "learning_rate": 8.790843333425713e-07, "loss": 0.7443, "step": 281740 }, { "epoch": 23.42, "learning_rate": 8.789734778150376e-07, "loss": 0.7141, "step": 281750 }, { "epoch": 23.42, "learning_rate": 8.788626222875037e-07, "loss": 0.727, "step": 281760 }, { "epoch": 23.42, "learning_rate": 8.787517667599699e-07, "loss": 0.7704, "step": 281770 }, { "epoch": 23.42, "learning_rate": 8.786409112324363e-07, "loss": 0.7409, "step": 281780 }, { "epoch": 23.42, "learning_rate": 8.785300557049026e-07, "loss": 0.6898, "step": 281790 }, { "epoch": 23.42, "learning_rate": 8.784192001773688e-07, "loss": 0.7549, "step": 281800 }, { "epoch": 23.42, "learning_rate": 8.78308344649835e-07, "loss": 0.7013, "step": 281810 }, { "epoch": 23.42, "learning_rate": 8.781974891223013e-07, "loss": 0.7923, "step": 281820 }, { "epoch": 23.43, "learning_rate": 8.780866335947675e-07, "loss": 0.806, "step": 281830 }, { "epoch": 23.43, "learning_rate": 8.779757780672339e-07, "loss": 0.713, "step": 281840 }, { "epoch": 23.43, "learning_rate": 8.778649225397001e-07, "loss": 0.8067, "step": 281850 }, { "epoch": 23.43, "learning_rate": 8.777540670121664e-07, "loss": 0.7551, "step": 281860 }, { "epoch": 23.43, "learning_rate": 8.776432114846326e-07, "loss": 0.7391, "step": 281870 }, { "epoch": 23.43, "learning_rate": 8.775323559570989e-07, "loss": 0.6691, "step": 281880 }, { "epoch": 23.43, "learning_rate": 8.77421500429565e-07, "loss": 0.7349, "step": 281890 }, { "epoch": 23.43, "learning_rate": 8.773106449020315e-07, "loss": 0.7935, "step": 281900 }, { "epoch": 23.43, "learning_rate": 8.771997893744976e-07, "loss": 0.7482, "step": 281910 }, { "epoch": 23.43, "learning_rate": 8.770889338469639e-07, "loss": 0.7955, "step": 281920 }, { "epoch": 23.43, "learning_rate": 8.769780783194301e-07, "loss": 0.7519, "step": 281930 }, { "epoch": 23.43, "learning_rate": 8.768672227918964e-07, "loss": 0.7403, "step": 281940 }, { "epoch": 23.44, "learning_rate": 8.767563672643626e-07, "loss": 0.7523, "step": 281950 }, { "epoch": 23.44, "learning_rate": 8.76645511736829e-07, "loss": 0.7637, "step": 281960 }, { "epoch": 23.44, "learning_rate": 8.765346562092952e-07, "loss": 0.7549, "step": 281970 }, { "epoch": 23.44, "learning_rate": 8.764238006817615e-07, "loss": 0.7893, "step": 281980 }, { "epoch": 23.44, "learning_rate": 8.763129451542277e-07, "loss": 0.7047, "step": 281990 }, { "epoch": 23.44, "learning_rate": 8.76202089626694e-07, "loss": 0.7383, "step": 282000 }, { "epoch": 23.44, "learning_rate": 8.760912340991602e-07, "loss": 0.7428, "step": 282010 }, { "epoch": 23.44, "learning_rate": 8.759803785716265e-07, "loss": 0.7454, "step": 282020 }, { "epoch": 23.44, "learning_rate": 8.758695230440928e-07, "loss": 0.739, "step": 282030 }, { "epoch": 23.44, "learning_rate": 8.757586675165591e-07, "loss": 0.7162, "step": 282040 }, { "epoch": 23.44, "learning_rate": 8.756478119890252e-07, "loss": 0.7354, "step": 282050 }, { "epoch": 23.44, "learning_rate": 8.755369564614915e-07, "loss": 0.7199, "step": 282060 }, { "epoch": 23.45, "learning_rate": 8.754261009339577e-07, "loss": 0.7727, "step": 282070 }, { "epoch": 23.45, "learning_rate": 8.75315245406424e-07, "loss": 0.741, "step": 282080 }, { "epoch": 23.45, "learning_rate": 8.752043898788903e-07, "loss": 0.7099, "step": 282090 }, { "epoch": 23.45, "learning_rate": 8.750935343513566e-07, "loss": 0.721, "step": 282100 }, { "epoch": 23.45, "learning_rate": 8.749826788238228e-07, "loss": 0.6987, "step": 282110 }, { "epoch": 23.45, "learning_rate": 8.748718232962891e-07, "loss": 0.8143, "step": 282120 }, { "epoch": 23.45, "learning_rate": 8.747609677687553e-07, "loss": 0.7295, "step": 282130 }, { "epoch": 23.45, "learning_rate": 8.746501122412216e-07, "loss": 0.6912, "step": 282140 }, { "epoch": 23.45, "learning_rate": 8.745392567136879e-07, "loss": 0.7756, "step": 282150 }, { "epoch": 23.45, "learning_rate": 8.744284011861542e-07, "loss": 0.8277, "step": 282160 }, { "epoch": 23.45, "learning_rate": 8.743175456586204e-07, "loss": 0.7267, "step": 282170 }, { "epoch": 23.45, "learning_rate": 8.742066901310867e-07, "loss": 0.7395, "step": 282180 }, { "epoch": 23.46, "learning_rate": 8.740958346035529e-07, "loss": 0.7248, "step": 282190 }, { "epoch": 23.46, "learning_rate": 8.73984979076019e-07, "loss": 0.7652, "step": 282200 }, { "epoch": 23.46, "learning_rate": 8.738741235484854e-07, "loss": 0.7761, "step": 282210 }, { "epoch": 23.46, "learning_rate": 8.737632680209516e-07, "loss": 0.7787, "step": 282220 }, { "epoch": 23.46, "learning_rate": 8.736524124934179e-07, "loss": 0.738, "step": 282230 }, { "epoch": 23.46, "learning_rate": 8.735415569658841e-07, "loss": 0.7127, "step": 282240 }, { "epoch": 23.46, "learning_rate": 8.734307014383504e-07, "loss": 0.6965, "step": 282250 }, { "epoch": 23.46, "learning_rate": 8.733198459108166e-07, "loss": 0.7404, "step": 282260 }, { "epoch": 23.46, "learning_rate": 8.73208990383283e-07, "loss": 0.7533, "step": 282270 }, { "epoch": 23.46, "learning_rate": 8.730981348557492e-07, "loss": 0.7402, "step": 282280 }, { "epoch": 23.46, "learning_rate": 8.729872793282155e-07, "loss": 0.714, "step": 282290 }, { "epoch": 23.46, "learning_rate": 8.728764238006817e-07, "loss": 0.7385, "step": 282300 }, { "epoch": 23.47, "learning_rate": 8.72765568273148e-07, "loss": 0.7249, "step": 282310 }, { "epoch": 23.47, "learning_rate": 8.726547127456142e-07, "loss": 0.7704, "step": 282320 }, { "epoch": 23.47, "learning_rate": 8.725438572180806e-07, "loss": 0.742, "step": 282330 }, { "epoch": 23.47, "learning_rate": 8.724330016905468e-07, "loss": 0.7011, "step": 282340 }, { "epoch": 23.47, "learning_rate": 8.72322146163013e-07, "loss": 0.7341, "step": 282350 }, { "epoch": 23.47, "learning_rate": 8.722112906354792e-07, "loss": 0.7783, "step": 282360 }, { "epoch": 23.47, "learning_rate": 8.721004351079455e-07, "loss": 0.7798, "step": 282370 }, { "epoch": 23.47, "learning_rate": 8.719895795804117e-07, "loss": 0.7349, "step": 282380 }, { "epoch": 23.47, "learning_rate": 8.718787240528781e-07, "loss": 0.7444, "step": 282390 }, { "epoch": 23.47, "learning_rate": 8.717678685253443e-07, "loss": 0.7691, "step": 282400 }, { "epoch": 23.47, "learning_rate": 8.716570129978106e-07, "loss": 0.7629, "step": 282410 }, { "epoch": 23.47, "learning_rate": 8.715461574702768e-07, "loss": 0.7781, "step": 282420 }, { "epoch": 23.48, "learning_rate": 8.714353019427431e-07, "loss": 0.7308, "step": 282430 }, { "epoch": 23.48, "learning_rate": 8.713244464152093e-07, "loss": 0.8057, "step": 282440 }, { "epoch": 23.48, "learning_rate": 8.712135908876756e-07, "loss": 0.7525, "step": 282450 }, { "epoch": 23.48, "learning_rate": 8.711027353601419e-07, "loss": 0.7941, "step": 282460 }, { "epoch": 23.48, "learning_rate": 8.709918798326082e-07, "loss": 0.7229, "step": 282470 }, { "epoch": 23.48, "learning_rate": 8.708810243050744e-07, "loss": 0.7493, "step": 282480 }, { "epoch": 23.48, "learning_rate": 8.707701687775407e-07, "loss": 0.7779, "step": 282490 }, { "epoch": 23.48, "learning_rate": 8.706593132500068e-07, "loss": 0.7608, "step": 282500 }, { "epoch": 23.48, "learning_rate": 8.705484577224731e-07, "loss": 0.7794, "step": 282510 }, { "epoch": 23.48, "learning_rate": 8.704376021949394e-07, "loss": 0.8133, "step": 282520 }, { "epoch": 23.48, "learning_rate": 8.703267466674057e-07, "loss": 0.6929, "step": 282530 }, { "epoch": 23.48, "learning_rate": 8.702158911398719e-07, "loss": 0.7977, "step": 282540 }, { "epoch": 23.49, "learning_rate": 8.701050356123382e-07, "loss": 0.7223, "step": 282550 }, { "epoch": 23.49, "learning_rate": 8.699941800848044e-07, "loss": 0.7733, "step": 282560 }, { "epoch": 23.49, "learning_rate": 8.698833245572707e-07, "loss": 0.7757, "step": 282570 }, { "epoch": 23.49, "learning_rate": 8.69772469029737e-07, "loss": 0.724, "step": 282580 }, { "epoch": 23.49, "learning_rate": 8.696616135022033e-07, "loss": 0.7527, "step": 282590 }, { "epoch": 23.49, "learning_rate": 8.695507579746695e-07, "loss": 0.7466, "step": 282600 }, { "epoch": 23.49, "learning_rate": 8.694399024471358e-07, "loss": 0.6873, "step": 282610 }, { "epoch": 23.49, "learning_rate": 8.69329046919602e-07, "loss": 0.791, "step": 282620 }, { "epoch": 23.49, "learning_rate": 8.692181913920682e-07, "loss": 0.792, "step": 282630 }, { "epoch": 23.49, "learning_rate": 8.691073358645346e-07, "loss": 0.7573, "step": 282640 }, { "epoch": 23.49, "learning_rate": 8.689964803370007e-07, "loss": 0.6957, "step": 282650 }, { "epoch": 23.49, "learning_rate": 8.68885624809467e-07, "loss": 0.7104, "step": 282660 }, { "epoch": 23.5, "learning_rate": 8.687747692819332e-07, "loss": 0.7488, "step": 282670 }, { "epoch": 23.5, "learning_rate": 8.686639137543995e-07, "loss": 0.7578, "step": 282680 }, { "epoch": 23.5, "learning_rate": 8.685530582268657e-07, "loss": 0.7753, "step": 282690 }, { "epoch": 23.5, "learning_rate": 8.684422026993321e-07, "loss": 0.7317, "step": 282700 }, { "epoch": 23.5, "learning_rate": 8.683313471717983e-07, "loss": 0.7237, "step": 282710 }, { "epoch": 23.5, "learning_rate": 8.682204916442646e-07, "loss": 0.7861, "step": 282720 }, { "epoch": 23.5, "learning_rate": 8.681096361167308e-07, "loss": 0.7457, "step": 282730 }, { "epoch": 23.5, "learning_rate": 8.679987805891971e-07, "loss": 0.7585, "step": 282740 }, { "epoch": 23.5, "learning_rate": 8.678879250616633e-07, "loss": 0.7882, "step": 282750 }, { "epoch": 23.5, "learning_rate": 8.677770695341297e-07, "loss": 0.7273, "step": 282760 }, { "epoch": 23.5, "learning_rate": 8.676662140065959e-07, "loss": 0.786, "step": 282770 }, { "epoch": 23.5, "learning_rate": 8.675553584790622e-07, "loss": 0.7016, "step": 282780 }, { "epoch": 23.51, "learning_rate": 8.674445029515283e-07, "loss": 0.779, "step": 282790 }, { "epoch": 23.51, "learning_rate": 8.673336474239946e-07, "loss": 0.7643, "step": 282800 }, { "epoch": 23.51, "learning_rate": 8.672227918964608e-07, "loss": 0.7297, "step": 282810 }, { "epoch": 23.51, "learning_rate": 8.671230219216805e-07, "loss": 0.7963, "step": 282820 }, { "epoch": 23.51, "learning_rate": 8.670121663941468e-07, "loss": 0.7383, "step": 282830 }, { "epoch": 23.51, "learning_rate": 8.66901310866613e-07, "loss": 0.8313, "step": 282840 }, { "epoch": 23.51, "learning_rate": 8.667904553390794e-07, "loss": 0.6929, "step": 282850 }, { "epoch": 23.51, "learning_rate": 8.666795998115456e-07, "loss": 0.7293, "step": 282860 }, { "epoch": 23.51, "learning_rate": 8.665687442840118e-07, "loss": 0.7516, "step": 282870 }, { "epoch": 23.51, "learning_rate": 8.66457888756478e-07, "loss": 0.7376, "step": 282880 }, { "epoch": 23.51, "learning_rate": 8.663470332289443e-07, "loss": 0.6856, "step": 282890 }, { "epoch": 23.51, "learning_rate": 8.662361777014105e-07, "loss": 0.7152, "step": 282900 }, { "epoch": 23.52, "learning_rate": 8.661253221738769e-07, "loss": 0.7959, "step": 282910 }, { "epoch": 23.52, "learning_rate": 8.660144666463431e-07, "loss": 0.7284, "step": 282920 }, { "epoch": 23.52, "learning_rate": 8.659036111188094e-07, "loss": 0.7468, "step": 282930 }, { "epoch": 23.52, "learning_rate": 8.657927555912756e-07, "loss": 0.7549, "step": 282940 }, { "epoch": 23.52, "learning_rate": 8.656819000637419e-07, "loss": 0.7191, "step": 282950 }, { "epoch": 23.52, "learning_rate": 8.655710445362081e-07, "loss": 0.7674, "step": 282960 }, { "epoch": 23.52, "learning_rate": 8.654601890086745e-07, "loss": 0.8056, "step": 282970 }, { "epoch": 23.52, "learning_rate": 8.653493334811407e-07, "loss": 0.7337, "step": 282980 }, { "epoch": 23.52, "learning_rate": 8.65238477953607e-07, "loss": 0.7224, "step": 282990 }, { "epoch": 23.52, "learning_rate": 8.651276224260732e-07, "loss": 0.7413, "step": 283000 }, { "epoch": 23.52, "learning_rate": 8.650167668985395e-07, "loss": 0.7068, "step": 283010 }, { "epoch": 23.52, "learning_rate": 8.649059113710056e-07, "loss": 0.7731, "step": 283020 }, { "epoch": 23.53, "learning_rate": 8.64795055843472e-07, "loss": 0.696, "step": 283030 }, { "epoch": 23.53, "learning_rate": 8.646842003159382e-07, "loss": 0.806, "step": 283040 }, { "epoch": 23.53, "learning_rate": 8.645733447884045e-07, "loss": 0.7346, "step": 283050 }, { "epoch": 23.53, "learning_rate": 8.644624892608707e-07, "loss": 0.7248, "step": 283060 }, { "epoch": 23.53, "learning_rate": 8.64351633733337e-07, "loss": 0.7603, "step": 283070 }, { "epoch": 23.53, "learning_rate": 8.642407782058032e-07, "loss": 0.8144, "step": 283080 }, { "epoch": 23.53, "learning_rate": 8.641299226782695e-07, "loss": 0.729, "step": 283090 }, { "epoch": 23.53, "learning_rate": 8.640190671507358e-07, "loss": 0.7629, "step": 283100 }, { "epoch": 23.53, "learning_rate": 8.639082116232021e-07, "loss": 0.7139, "step": 283110 }, { "epoch": 23.53, "learning_rate": 8.637973560956683e-07, "loss": 0.7686, "step": 283120 }, { "epoch": 23.53, "learning_rate": 8.636865005681346e-07, "loss": 0.7039, "step": 283130 }, { "epoch": 23.53, "learning_rate": 8.635756450406008e-07, "loss": 0.7641, "step": 283140 }, { "epoch": 23.54, "learning_rate": 8.63464789513067e-07, "loss": 0.6967, "step": 283150 }, { "epoch": 23.54, "learning_rate": 8.633539339855334e-07, "loss": 0.7524, "step": 283160 }, { "epoch": 23.54, "learning_rate": 8.632430784579995e-07, "loss": 0.8406, "step": 283170 }, { "epoch": 23.54, "learning_rate": 8.631322229304658e-07, "loss": 0.7325, "step": 283180 }, { "epoch": 23.54, "learning_rate": 8.63021367402932e-07, "loss": 0.7001, "step": 283190 }, { "epoch": 23.54, "learning_rate": 8.629105118753983e-07, "loss": 0.6817, "step": 283200 }, { "epoch": 23.54, "learning_rate": 8.627996563478645e-07, "loss": 0.7474, "step": 283210 }, { "epoch": 23.54, "learning_rate": 8.626888008203309e-07, "loss": 0.7608, "step": 283220 }, { "epoch": 23.54, "learning_rate": 8.625779452927971e-07, "loss": 0.7464, "step": 283230 }, { "epoch": 23.54, "learning_rate": 8.624670897652634e-07, "loss": 0.7797, "step": 283240 }, { "epoch": 23.54, "learning_rate": 8.623562342377296e-07, "loss": 0.7397, "step": 283250 }, { "epoch": 23.54, "learning_rate": 8.622453787101959e-07, "loss": 0.7229, "step": 283260 }, { "epoch": 23.55, "learning_rate": 8.621345231826621e-07, "loss": 0.8315, "step": 283270 }, { "epoch": 23.55, "learning_rate": 8.620236676551285e-07, "loss": 0.7368, "step": 283280 }, { "epoch": 23.55, "learning_rate": 8.619128121275947e-07, "loss": 0.7089, "step": 283290 }, { "epoch": 23.55, "learning_rate": 8.61801956600061e-07, "loss": 0.7056, "step": 283300 }, { "epoch": 23.55, "learning_rate": 8.616911010725271e-07, "loss": 0.7506, "step": 283310 }, { "epoch": 23.55, "learning_rate": 8.615802455449934e-07, "loss": 0.7919, "step": 283320 }, { "epoch": 23.55, "learning_rate": 8.614693900174596e-07, "loss": 0.7536, "step": 283330 }, { "epoch": 23.55, "learning_rate": 8.61358534489926e-07, "loss": 0.7666, "step": 283340 }, { "epoch": 23.55, "learning_rate": 8.612476789623922e-07, "loss": 0.7406, "step": 283350 }, { "epoch": 23.55, "learning_rate": 8.611368234348585e-07, "loss": 0.7328, "step": 283360 }, { "epoch": 23.55, "learning_rate": 8.610259679073247e-07, "loss": 0.7857, "step": 283370 }, { "epoch": 23.55, "learning_rate": 8.60915112379791e-07, "loss": 0.7261, "step": 283380 }, { "epoch": 23.55, "learning_rate": 8.608042568522572e-07, "loss": 0.7282, "step": 283390 }, { "epoch": 23.56, "learning_rate": 8.606934013247236e-07, "loss": 0.7125, "step": 283400 }, { "epoch": 23.56, "learning_rate": 8.605825457971898e-07, "loss": 0.7429, "step": 283410 }, { "epoch": 23.56, "learning_rate": 8.604716902696561e-07, "loss": 0.7422, "step": 283420 }, { "epoch": 23.56, "learning_rate": 8.603608347421223e-07, "loss": 0.7554, "step": 283430 }, { "epoch": 23.56, "learning_rate": 8.602499792145886e-07, "loss": 0.7953, "step": 283440 }, { "epoch": 23.56, "learning_rate": 8.601391236870548e-07, "loss": 0.74, "step": 283450 }, { "epoch": 23.56, "learning_rate": 8.600282681595212e-07, "loss": 0.7143, "step": 283460 }, { "epoch": 23.56, "learning_rate": 8.599174126319873e-07, "loss": 0.794, "step": 283470 }, { "epoch": 23.56, "learning_rate": 8.598065571044536e-07, "loss": 0.7775, "step": 283480 }, { "epoch": 23.56, "learning_rate": 8.596957015769198e-07, "loss": 0.7482, "step": 283490 }, { "epoch": 23.56, "learning_rate": 8.595848460493861e-07, "loss": 0.7308, "step": 283500 }, { "epoch": 23.56, "learning_rate": 8.594739905218523e-07, "loss": 0.7709, "step": 283510 }, { "epoch": 23.57, "learning_rate": 8.593631349943186e-07, "loss": 0.7815, "step": 283520 }, { "epoch": 23.57, "learning_rate": 8.592522794667849e-07, "loss": 0.8249, "step": 283530 }, { "epoch": 23.57, "learning_rate": 8.591414239392512e-07, "loss": 0.777, "step": 283540 }, { "epoch": 23.57, "learning_rate": 8.590305684117174e-07, "loss": 0.7066, "step": 283550 }, { "epoch": 23.57, "learning_rate": 8.589197128841837e-07, "loss": 0.7395, "step": 283560 }, { "epoch": 23.57, "learning_rate": 8.588088573566499e-07, "loss": 0.7552, "step": 283570 }, { "epoch": 23.57, "learning_rate": 8.586980018291161e-07, "loss": 0.7357, "step": 283580 }, { "epoch": 23.57, "learning_rate": 8.585871463015825e-07, "loss": 0.7327, "step": 283590 }, { "epoch": 23.57, "learning_rate": 8.584762907740487e-07, "loss": 0.7164, "step": 283600 }, { "epoch": 23.57, "learning_rate": 8.58365435246515e-07, "loss": 0.7541, "step": 283610 }, { "epoch": 23.57, "learning_rate": 8.582545797189811e-07, "loss": 0.781, "step": 283620 }, { "epoch": 23.57, "learning_rate": 8.581437241914474e-07, "loss": 0.7338, "step": 283630 }, { "epoch": 23.58, "learning_rate": 8.580328686639136e-07, "loss": 0.7489, "step": 283640 }, { "epoch": 23.58, "learning_rate": 8.5792201313638e-07, "loss": 0.7038, "step": 283650 }, { "epoch": 23.58, "learning_rate": 8.578111576088462e-07, "loss": 0.7315, "step": 283660 }, { "epoch": 23.58, "learning_rate": 8.577003020813125e-07, "loss": 0.7968, "step": 283670 }, { "epoch": 23.58, "learning_rate": 8.575894465537787e-07, "loss": 0.7151, "step": 283680 }, { "epoch": 23.58, "learning_rate": 8.57478591026245e-07, "loss": 0.7575, "step": 283690 }, { "epoch": 23.58, "learning_rate": 8.573677354987112e-07, "loss": 0.7782, "step": 283700 }, { "epoch": 23.58, "learning_rate": 8.572568799711776e-07, "loss": 0.7457, "step": 283710 }, { "epoch": 23.58, "learning_rate": 8.571460244436438e-07, "loss": 0.7962, "step": 283720 }, { "epoch": 23.58, "learning_rate": 8.570351689161101e-07, "loss": 0.7217, "step": 283730 }, { "epoch": 23.58, "learning_rate": 8.569243133885763e-07, "loss": 0.6884, "step": 283740 }, { "epoch": 23.58, "learning_rate": 8.568134578610426e-07, "loss": 0.7463, "step": 283750 }, { "epoch": 23.59, "learning_rate": 8.567026023335087e-07, "loss": 0.7415, "step": 283760 }, { "epoch": 23.59, "learning_rate": 8.565917468059751e-07, "loss": 0.7968, "step": 283770 }, { "epoch": 23.59, "learning_rate": 8.564808912784413e-07, "loss": 0.7199, "step": 283780 }, { "epoch": 23.59, "learning_rate": 8.563700357509076e-07, "loss": 0.7308, "step": 283790 }, { "epoch": 23.59, "learning_rate": 8.562591802233738e-07, "loss": 0.7932, "step": 283800 }, { "epoch": 23.59, "learning_rate": 8.561483246958401e-07, "loss": 0.734, "step": 283810 }, { "epoch": 23.59, "learning_rate": 8.560374691683063e-07, "loss": 0.7738, "step": 283820 }, { "epoch": 23.59, "learning_rate": 8.559266136407727e-07, "loss": 0.7092, "step": 283830 }, { "epoch": 23.59, "learning_rate": 8.558157581132389e-07, "loss": 0.7428, "step": 283840 }, { "epoch": 23.59, "learning_rate": 8.557049025857052e-07, "loss": 0.7233, "step": 283850 }, { "epoch": 23.59, "learning_rate": 8.555940470581714e-07, "loss": 0.7203, "step": 283860 }, { "epoch": 23.59, "learning_rate": 8.554831915306377e-07, "loss": 0.7732, "step": 283870 }, { "epoch": 23.6, "learning_rate": 8.553723360031039e-07, "loss": 0.8267, "step": 283880 }, { "epoch": 23.6, "learning_rate": 8.552614804755703e-07, "loss": 0.7111, "step": 283890 }, { "epoch": 23.6, "learning_rate": 8.551506249480365e-07, "loss": 0.7774, "step": 283900 }, { "epoch": 23.6, "learning_rate": 8.550397694205028e-07, "loss": 0.7378, "step": 283910 }, { "epoch": 23.6, "learning_rate": 8.549289138929689e-07, "loss": 0.7411, "step": 283920 }, { "epoch": 23.6, "learning_rate": 8.548180583654352e-07, "loss": 0.7657, "step": 283930 }, { "epoch": 23.6, "learning_rate": 8.547072028379014e-07, "loss": 0.7113, "step": 283940 }, { "epoch": 23.6, "learning_rate": 8.545963473103677e-07, "loss": 0.7091, "step": 283950 }, { "epoch": 23.6, "learning_rate": 8.54485491782834e-07, "loss": 0.7544, "step": 283960 }, { "epoch": 23.6, "learning_rate": 8.543746362553003e-07, "loss": 0.8032, "step": 283970 }, { "epoch": 23.6, "learning_rate": 8.542637807277665e-07, "loss": 0.7582, "step": 283980 }, { "epoch": 23.6, "learning_rate": 8.541529252002327e-07, "loss": 0.6815, "step": 283990 }, { "epoch": 23.61, "learning_rate": 8.54042069672699e-07, "loss": 0.7803, "step": 284000 }, { "epoch": 23.61, "learning_rate": 8.539312141451652e-07, "loss": 0.7603, "step": 284010 }, { "epoch": 23.61, "learning_rate": 8.538203586176316e-07, "loss": 0.7793, "step": 284020 }, { "epoch": 23.61, "learning_rate": 8.537095030900978e-07, "loss": 0.7425, "step": 284030 }, { "epoch": 23.61, "learning_rate": 8.535986475625641e-07, "loss": 0.7762, "step": 284040 }, { "epoch": 23.61, "learning_rate": 8.534877920350303e-07, "loss": 0.71, "step": 284050 }, { "epoch": 23.61, "learning_rate": 8.533769365074965e-07, "loss": 0.7086, "step": 284060 }, { "epoch": 23.61, "learning_rate": 8.532660809799627e-07, "loss": 0.7275, "step": 284070 }, { "epoch": 23.61, "learning_rate": 8.531552254524291e-07, "loss": 0.8142, "step": 284080 }, { "epoch": 23.61, "learning_rate": 8.530443699248953e-07, "loss": 0.7593, "step": 284090 }, { "epoch": 23.61, "learning_rate": 8.529335143973616e-07, "loss": 0.6994, "step": 284100 }, { "epoch": 23.61, "learning_rate": 8.528226588698278e-07, "loss": 0.7851, "step": 284110 }, { "epoch": 23.62, "learning_rate": 8.527118033422941e-07, "loss": 0.8192, "step": 284120 }, { "epoch": 23.62, "learning_rate": 8.526009478147603e-07, "loss": 0.7395, "step": 284130 }, { "epoch": 23.62, "learning_rate": 8.524900922872267e-07, "loss": 0.7472, "step": 284140 }, { "epoch": 23.62, "learning_rate": 8.523792367596929e-07, "loss": 0.7296, "step": 284150 }, { "epoch": 23.62, "learning_rate": 8.522683812321592e-07, "loss": 0.7825, "step": 284160 }, { "epoch": 23.62, "learning_rate": 8.521575257046254e-07, "loss": 0.7753, "step": 284170 }, { "epoch": 23.62, "learning_rate": 8.520466701770917e-07, "loss": 0.7114, "step": 284180 }, { "epoch": 23.62, "learning_rate": 8.519358146495579e-07, "loss": 0.6915, "step": 284190 }, { "epoch": 23.62, "learning_rate": 8.518249591220243e-07, "loss": 0.7244, "step": 284200 }, { "epoch": 23.62, "learning_rate": 8.517141035944904e-07, "loss": 0.6743, "step": 284210 }, { "epoch": 23.62, "learning_rate": 8.516032480669567e-07, "loss": 0.7734, "step": 284220 }, { "epoch": 23.62, "learning_rate": 8.514923925394229e-07, "loss": 0.7593, "step": 284230 }, { "epoch": 23.63, "learning_rate": 8.513815370118892e-07, "loss": 0.6941, "step": 284240 }, { "epoch": 23.63, "learning_rate": 8.512706814843554e-07, "loss": 0.7866, "step": 284250 }, { "epoch": 23.63, "learning_rate": 8.511598259568218e-07, "loss": 0.7664, "step": 284260 }, { "epoch": 23.63, "learning_rate": 8.51048970429288e-07, "loss": 0.7707, "step": 284270 }, { "epoch": 23.63, "learning_rate": 8.509381149017543e-07, "loss": 0.7397, "step": 284280 }, { "epoch": 23.63, "learning_rate": 8.508272593742205e-07, "loss": 0.7751, "step": 284290 }, { "epoch": 23.63, "learning_rate": 8.507164038466868e-07, "loss": 0.659, "step": 284300 }, { "epoch": 23.63, "learning_rate": 8.50605548319153e-07, "loss": 0.7737, "step": 284310 }, { "epoch": 23.63, "learning_rate": 8.504946927916193e-07, "loss": 0.7631, "step": 284320 }, { "epoch": 23.63, "learning_rate": 8.503838372640856e-07, "loss": 0.7093, "step": 284330 }, { "epoch": 23.63, "learning_rate": 8.502729817365519e-07, "loss": 0.8328, "step": 284340 }, { "epoch": 23.63, "learning_rate": 8.50162126209018e-07, "loss": 0.7174, "step": 284350 }, { "epoch": 23.64, "learning_rate": 8.500512706814843e-07, "loss": 0.7443, "step": 284360 }, { "epoch": 23.64, "learning_rate": 8.499404151539505e-07, "loss": 0.7653, "step": 284370 }, { "epoch": 23.64, "learning_rate": 8.498295596264168e-07, "loss": 0.7634, "step": 284380 }, { "epoch": 23.64, "learning_rate": 8.497187040988831e-07, "loss": 0.6894, "step": 284390 }, { "epoch": 23.64, "learning_rate": 8.496078485713494e-07, "loss": 0.7325, "step": 284400 }, { "epoch": 23.64, "learning_rate": 8.494969930438156e-07, "loss": 0.7066, "step": 284410 }, { "epoch": 23.64, "learning_rate": 8.493861375162818e-07, "loss": 0.7592, "step": 284420 }, { "epoch": 23.64, "learning_rate": 8.492752819887481e-07, "loss": 0.7268, "step": 284430 }, { "epoch": 23.64, "learning_rate": 8.491644264612143e-07, "loss": 0.7384, "step": 284440 }, { "epoch": 23.64, "learning_rate": 8.490535709336807e-07, "loss": 0.7621, "step": 284450 }, { "epoch": 23.64, "learning_rate": 8.489427154061469e-07, "loss": 0.7446, "step": 284460 }, { "epoch": 23.64, "learning_rate": 8.488318598786132e-07, "loss": 0.7947, "step": 284470 }, { "epoch": 23.65, "learning_rate": 8.487210043510794e-07, "loss": 0.7378, "step": 284480 }, { "epoch": 23.65, "learning_rate": 8.486101488235457e-07, "loss": 0.6821, "step": 284490 }, { "epoch": 23.65, "learning_rate": 8.484992932960118e-07, "loss": 0.6903, "step": 284500 }, { "epoch": 23.65, "learning_rate": 8.483884377684782e-07, "loss": 0.791, "step": 284510 }, { "epoch": 23.65, "learning_rate": 8.482775822409444e-07, "loss": 0.7994, "step": 284520 }, { "epoch": 23.65, "learning_rate": 8.481667267134107e-07, "loss": 0.722, "step": 284530 }, { "epoch": 23.65, "learning_rate": 8.480558711858769e-07, "loss": 0.6949, "step": 284540 }, { "epoch": 23.65, "learning_rate": 8.479450156583432e-07, "loss": 0.6982, "step": 284550 }, { "epoch": 23.65, "learning_rate": 8.478341601308094e-07, "loss": 0.7709, "step": 284560 }, { "epoch": 23.65, "learning_rate": 8.477233046032758e-07, "loss": 0.8631, "step": 284570 }, { "epoch": 23.65, "learning_rate": 8.47612449075742e-07, "loss": 0.6691, "step": 284580 }, { "epoch": 23.65, "learning_rate": 8.475015935482083e-07, "loss": 0.7492, "step": 284590 }, { "epoch": 23.66, "learning_rate": 8.473907380206745e-07, "loss": 0.6983, "step": 284600 }, { "epoch": 23.66, "learning_rate": 8.472798824931408e-07, "loss": 0.7066, "step": 284610 }, { "epoch": 23.66, "learning_rate": 8.47169026965607e-07, "loss": 0.7891, "step": 284620 }, { "epoch": 23.66, "learning_rate": 8.470581714380734e-07, "loss": 0.743, "step": 284630 }, { "epoch": 23.66, "learning_rate": 8.469473159105396e-07, "loss": 0.7162, "step": 284640 }, { "epoch": 23.66, "learning_rate": 8.468364603830059e-07, "loss": 0.7675, "step": 284650 }, { "epoch": 23.66, "learning_rate": 8.46725604855472e-07, "loss": 0.7212, "step": 284660 }, { "epoch": 23.66, "learning_rate": 8.466147493279383e-07, "loss": 0.7649, "step": 284670 }, { "epoch": 23.66, "learning_rate": 8.465038938004045e-07, "loss": 0.7493, "step": 284680 }, { "epoch": 23.66, "learning_rate": 8.463930382728709e-07, "loss": 0.7023, "step": 284690 }, { "epoch": 23.66, "learning_rate": 8.462821827453371e-07, "loss": 0.7832, "step": 284700 }, { "epoch": 23.66, "learning_rate": 8.461713272178034e-07, "loss": 0.6929, "step": 284710 }, { "epoch": 23.67, "learning_rate": 8.460604716902696e-07, "loss": 0.8005, "step": 284720 }, { "epoch": 23.67, "learning_rate": 8.459496161627359e-07, "loss": 0.8082, "step": 284730 }, { "epoch": 23.67, "learning_rate": 8.458387606352021e-07, "loss": 0.7284, "step": 284740 }, { "epoch": 23.67, "learning_rate": 8.457279051076684e-07, "loss": 0.6811, "step": 284750 }, { "epoch": 23.67, "learning_rate": 8.456170495801347e-07, "loss": 0.7712, "step": 284760 }, { "epoch": 23.67, "learning_rate": 8.45506194052601e-07, "loss": 0.7877, "step": 284770 }, { "epoch": 23.67, "learning_rate": 8.453953385250672e-07, "loss": 0.7708, "step": 284780 }, { "epoch": 23.67, "learning_rate": 8.452844829975335e-07, "loss": 0.8048, "step": 284790 }, { "epoch": 23.67, "learning_rate": 8.451736274699996e-07, "loss": 0.7431, "step": 284800 }, { "epoch": 23.67, "learning_rate": 8.450627719424658e-07, "loss": 0.7016, "step": 284810 }, { "epoch": 23.67, "learning_rate": 8.449519164149322e-07, "loss": 0.8111, "step": 284820 }, { "epoch": 23.67, "learning_rate": 8.448410608873985e-07, "loss": 0.7482, "step": 284830 }, { "epoch": 23.68, "learning_rate": 8.447412909126182e-07, "loss": 0.6786, "step": 284840 }, { "epoch": 23.68, "learning_rate": 8.446304353850844e-07, "loss": 0.7647, "step": 284850 }, { "epoch": 23.68, "learning_rate": 8.445195798575507e-07, "loss": 0.7314, "step": 284860 }, { "epoch": 23.68, "learning_rate": 8.444087243300169e-07, "loss": 0.7833, "step": 284870 }, { "epoch": 23.68, "learning_rate": 8.442978688024831e-07, "loss": 0.7372, "step": 284880 }, { "epoch": 23.68, "learning_rate": 8.441870132749493e-07, "loss": 0.7512, "step": 284890 }, { "epoch": 23.68, "learning_rate": 8.440761577474157e-07, "loss": 0.6942, "step": 284900 }, { "epoch": 23.68, "learning_rate": 8.439653022198819e-07, "loss": 0.7858, "step": 284910 }, { "epoch": 23.68, "learning_rate": 8.438544466923482e-07, "loss": 0.7545, "step": 284920 }, { "epoch": 23.68, "learning_rate": 8.437435911648144e-07, "loss": 0.7342, "step": 284930 }, { "epoch": 23.68, "learning_rate": 8.436327356372807e-07, "loss": 0.7424, "step": 284940 }, { "epoch": 23.68, "learning_rate": 8.435218801097469e-07, "loss": 0.6951, "step": 284950 }, { "epoch": 23.69, "learning_rate": 8.434110245822131e-07, "loss": 0.7215, "step": 284960 }, { "epoch": 23.69, "learning_rate": 8.433001690546795e-07, "loss": 0.7435, "step": 284970 }, { "epoch": 23.69, "learning_rate": 8.431893135271457e-07, "loss": 0.6982, "step": 284980 }, { "epoch": 23.69, "learning_rate": 8.43078457999612e-07, "loss": 0.77, "step": 284990 }, { "epoch": 23.69, "learning_rate": 8.429676024720782e-07, "loss": 0.7101, "step": 285000 }, { "epoch": 23.69, "learning_rate": 8.428567469445445e-07, "loss": 0.7395, "step": 285010 }, { "epoch": 23.69, "learning_rate": 8.427458914170106e-07, "loss": 0.7767, "step": 285020 }, { "epoch": 23.69, "learning_rate": 8.42635035889477e-07, "loss": 0.7182, "step": 285030 }, { "epoch": 23.69, "learning_rate": 8.425241803619432e-07, "loss": 0.7401, "step": 285040 }, { "epoch": 23.69, "learning_rate": 8.424133248344095e-07, "loss": 0.6825, "step": 285050 }, { "epoch": 23.69, "learning_rate": 8.423024693068757e-07, "loss": 0.7398, "step": 285060 }, { "epoch": 23.69, "learning_rate": 8.42191613779342e-07, "loss": 0.7962, "step": 285070 }, { "epoch": 23.7, "learning_rate": 8.420807582518082e-07, "loss": 0.7446, "step": 285080 }, { "epoch": 23.7, "learning_rate": 8.419699027242746e-07, "loss": 0.7378, "step": 285090 }, { "epoch": 23.7, "learning_rate": 8.418590471967408e-07, "loss": 0.7469, "step": 285100 }, { "epoch": 23.7, "learning_rate": 8.417481916692071e-07, "loss": 0.7866, "step": 285110 }, { "epoch": 23.7, "learning_rate": 8.416373361416733e-07, "loss": 0.7884, "step": 285120 }, { "epoch": 23.7, "learning_rate": 8.415264806141396e-07, "loss": 0.7577, "step": 285130 }, { "epoch": 23.7, "learning_rate": 8.414156250866058e-07, "loss": 0.7399, "step": 285140 }, { "epoch": 23.7, "learning_rate": 8.413047695590722e-07, "loss": 0.7173, "step": 285150 }, { "epoch": 23.7, "learning_rate": 8.411939140315384e-07, "loss": 0.7154, "step": 285160 }, { "epoch": 23.7, "learning_rate": 8.410830585040047e-07, "loss": 0.7076, "step": 285170 }, { "epoch": 23.7, "learning_rate": 8.409722029764708e-07, "loss": 0.7188, "step": 285180 }, { "epoch": 23.7, "learning_rate": 8.408613474489371e-07, "loss": 0.7456, "step": 285190 }, { "epoch": 23.71, "learning_rate": 8.407504919214033e-07, "loss": 0.7431, "step": 285200 }, { "epoch": 23.71, "learning_rate": 8.406396363938697e-07, "loss": 0.6962, "step": 285210 }, { "epoch": 23.71, "learning_rate": 8.405287808663359e-07, "loss": 0.7412, "step": 285220 }, { "epoch": 23.71, "learning_rate": 8.404179253388022e-07, "loss": 0.7608, "step": 285230 }, { "epoch": 23.71, "learning_rate": 8.403070698112684e-07, "loss": 0.7671, "step": 285240 }, { "epoch": 23.71, "learning_rate": 8.401962142837347e-07, "loss": 0.7115, "step": 285250 }, { "epoch": 23.71, "learning_rate": 8.400853587562009e-07, "loss": 0.671, "step": 285260 }, { "epoch": 23.71, "learning_rate": 8.399745032286673e-07, "loss": 0.7376, "step": 285270 }, { "epoch": 23.71, "learning_rate": 8.398636477011335e-07, "loss": 0.72, "step": 285280 }, { "epoch": 23.71, "learning_rate": 8.397527921735998e-07, "loss": 0.7358, "step": 285290 }, { "epoch": 23.71, "learning_rate": 8.39641936646066e-07, "loss": 0.7165, "step": 285300 }, { "epoch": 23.71, "learning_rate": 8.395310811185323e-07, "loss": 0.7111, "step": 285310 }, { "epoch": 23.72, "learning_rate": 8.394202255909984e-07, "loss": 0.7909, "step": 285320 }, { "epoch": 23.72, "learning_rate": 8.393093700634649e-07, "loss": 0.7721, "step": 285330 }, { "epoch": 23.72, "learning_rate": 8.39198514535931e-07, "loss": 0.7473, "step": 285340 }, { "epoch": 23.72, "learning_rate": 8.390876590083973e-07, "loss": 0.6883, "step": 285350 }, { "epoch": 23.72, "learning_rate": 8.389768034808635e-07, "loss": 0.7449, "step": 285360 }, { "epoch": 23.72, "learning_rate": 8.388659479533297e-07, "loss": 0.7717, "step": 285370 }, { "epoch": 23.72, "learning_rate": 8.38755092425796e-07, "loss": 0.7519, "step": 285380 }, { "epoch": 23.72, "learning_rate": 8.386442368982622e-07, "loss": 0.7113, "step": 285390 }, { "epoch": 23.72, "learning_rate": 8.385333813707286e-07, "loss": 0.7328, "step": 285400 }, { "epoch": 23.72, "learning_rate": 8.384225258431948e-07, "loss": 0.6999, "step": 285410 }, { "epoch": 23.72, "learning_rate": 8.383116703156611e-07, "loss": 0.7773, "step": 285420 }, { "epoch": 23.72, "learning_rate": 8.382008147881273e-07, "loss": 0.7367, "step": 285430 }, { "epoch": 23.73, "learning_rate": 8.380899592605936e-07, "loss": 0.724, "step": 285440 }, { "epoch": 23.73, "learning_rate": 8.379791037330598e-07, "loss": 0.7267, "step": 285450 }, { "epoch": 23.73, "learning_rate": 8.378682482055262e-07, "loss": 0.7581, "step": 285460 }, { "epoch": 23.73, "learning_rate": 8.377573926779924e-07, "loss": 0.7729, "step": 285470 }, { "epoch": 23.73, "learning_rate": 8.376465371504586e-07, "loss": 0.7447, "step": 285480 }, { "epoch": 23.73, "learning_rate": 8.375356816229248e-07, "loss": 0.6954, "step": 285490 }, { "epoch": 23.73, "learning_rate": 8.374248260953911e-07, "loss": 0.7677, "step": 285500 }, { "epoch": 23.73, "learning_rate": 8.373139705678573e-07, "loss": 0.7304, "step": 285510 }, { "epoch": 23.73, "learning_rate": 8.372031150403237e-07, "loss": 0.8037, "step": 285520 }, { "epoch": 23.73, "learning_rate": 8.370922595127899e-07, "loss": 0.7654, "step": 285530 }, { "epoch": 23.73, "learning_rate": 8.369814039852562e-07, "loss": 0.7556, "step": 285540 }, { "epoch": 23.73, "learning_rate": 8.368705484577224e-07, "loss": 0.7421, "step": 285550 }, { "epoch": 23.74, "learning_rate": 8.367596929301887e-07, "loss": 0.7707, "step": 285560 }, { "epoch": 23.74, "learning_rate": 8.366488374026549e-07, "loss": 0.7668, "step": 285570 }, { "epoch": 23.74, "learning_rate": 8.365379818751213e-07, "loss": 0.7531, "step": 285580 }, { "epoch": 23.74, "learning_rate": 8.364271263475875e-07, "loss": 0.6957, "step": 285590 }, { "epoch": 23.74, "learning_rate": 8.363162708200538e-07, "loss": 0.8122, "step": 285600 }, { "epoch": 23.74, "learning_rate": 8.3620541529252e-07, "loss": 0.6832, "step": 285610 }, { "epoch": 23.74, "learning_rate": 8.360945597649863e-07, "loss": 0.7746, "step": 285620 }, { "epoch": 23.74, "learning_rate": 8.359837042374524e-07, "loss": 0.7602, "step": 285630 }, { "epoch": 23.74, "learning_rate": 8.358728487099188e-07, "loss": 0.7191, "step": 285640 }, { "epoch": 23.74, "learning_rate": 8.35761993182385e-07, "loss": 0.7957, "step": 285650 }, { "epoch": 23.74, "learning_rate": 8.356511376548513e-07, "loss": 0.7413, "step": 285660 }, { "epoch": 23.74, "learning_rate": 8.355402821273175e-07, "loss": 0.7386, "step": 285670 }, { "epoch": 23.75, "learning_rate": 8.354294265997838e-07, "loss": 0.7476, "step": 285680 }, { "epoch": 23.75, "learning_rate": 8.3531857107225e-07, "loss": 0.7652, "step": 285690 }, { "epoch": 23.75, "learning_rate": 8.352077155447164e-07, "loss": 0.7441, "step": 285700 }, { "epoch": 23.75, "learning_rate": 8.350968600171826e-07, "loss": 0.7445, "step": 285710 }, { "epoch": 23.75, "learning_rate": 8.349860044896489e-07, "loss": 0.7605, "step": 285720 }, { "epoch": 23.75, "learning_rate": 8.348751489621151e-07, "loss": 0.7102, "step": 285730 }, { "epoch": 23.75, "learning_rate": 8.347642934345814e-07, "loss": 0.7303, "step": 285740 }, { "epoch": 23.75, "learning_rate": 8.346534379070476e-07, "loss": 0.7644, "step": 285750 }, { "epoch": 23.75, "learning_rate": 8.34542582379514e-07, "loss": 0.7511, "step": 285760 }, { "epoch": 23.75, "learning_rate": 8.344317268519802e-07, "loss": 0.7888, "step": 285770 }, { "epoch": 23.75, "learning_rate": 8.343208713244464e-07, "loss": 0.76, "step": 285780 }, { "epoch": 23.75, "learning_rate": 8.342100157969126e-07, "loss": 0.7882, "step": 285790 }, { "epoch": 23.76, "learning_rate": 8.340991602693788e-07, "loss": 0.7432, "step": 285800 }, { "epoch": 23.76, "learning_rate": 8.339883047418451e-07, "loss": 0.7294, "step": 285810 }, { "epoch": 23.76, "learning_rate": 8.338774492143113e-07, "loss": 0.7561, "step": 285820 }, { "epoch": 23.76, "learning_rate": 8.337665936867777e-07, "loss": 0.747, "step": 285830 }, { "epoch": 23.76, "learning_rate": 8.336557381592439e-07, "loss": 0.7357, "step": 285840 }, { "epoch": 23.76, "learning_rate": 8.335448826317102e-07, "loss": 0.7452, "step": 285850 }, { "epoch": 23.76, "learning_rate": 8.334340271041764e-07, "loss": 0.7114, "step": 285860 }, { "epoch": 23.76, "learning_rate": 8.333231715766427e-07, "loss": 0.7641, "step": 285870 }, { "epoch": 23.76, "learning_rate": 8.332123160491089e-07, "loss": 0.7548, "step": 285880 }, { "epoch": 23.76, "learning_rate": 8.331014605215753e-07, "loss": 0.7204, "step": 285890 }, { "epoch": 23.76, "learning_rate": 8.329906049940415e-07, "loss": 0.7369, "step": 285900 }, { "epoch": 23.76, "learning_rate": 8.328797494665078e-07, "loss": 0.7563, "step": 285910 }, { "epoch": 23.77, "learning_rate": 8.327688939389739e-07, "loss": 0.7617, "step": 285920 }, { "epoch": 23.77, "learning_rate": 8.326580384114402e-07, "loss": 0.7746, "step": 285930 }, { "epoch": 23.77, "learning_rate": 8.325471828839064e-07, "loss": 0.7866, "step": 285940 }, { "epoch": 23.77, "learning_rate": 8.324363273563728e-07, "loss": 0.7527, "step": 285950 }, { "epoch": 23.77, "learning_rate": 8.32325471828839e-07, "loss": 0.7263, "step": 285960 }, { "epoch": 23.77, "learning_rate": 8.322146163013053e-07, "loss": 0.7791, "step": 285970 }, { "epoch": 23.77, "learning_rate": 8.321037607737715e-07, "loss": 0.6945, "step": 285980 }, { "epoch": 23.77, "learning_rate": 8.319929052462378e-07, "loss": 0.7382, "step": 285990 }, { "epoch": 23.77, "learning_rate": 8.31882049718704e-07, "loss": 0.7943, "step": 286000 }, { "epoch": 23.77, "learning_rate": 8.317711941911704e-07, "loss": 0.7104, "step": 286010 }, { "epoch": 23.77, "learning_rate": 8.316603386636366e-07, "loss": 0.7635, "step": 286020 }, { "epoch": 23.77, "learning_rate": 8.315494831361029e-07, "loss": 0.7727, "step": 286030 }, { "epoch": 23.78, "learning_rate": 8.314386276085691e-07, "loss": 0.7482, "step": 286040 }, { "epoch": 23.78, "learning_rate": 8.313277720810354e-07, "loss": 0.7432, "step": 286050 }, { "epoch": 23.78, "learning_rate": 8.312169165535016e-07, "loss": 0.75, "step": 286060 }, { "epoch": 23.78, "learning_rate": 8.31106061025968e-07, "loss": 0.7988, "step": 286070 }, { "epoch": 23.78, "learning_rate": 8.309952054984341e-07, "loss": 0.6971, "step": 286080 }, { "epoch": 23.78, "learning_rate": 8.308843499709004e-07, "loss": 0.7345, "step": 286090 }, { "epoch": 23.78, "learning_rate": 8.307734944433666e-07, "loss": 0.7165, "step": 286100 }, { "epoch": 23.78, "learning_rate": 8.306626389158329e-07, "loss": 0.6975, "step": 286110 }, { "epoch": 23.78, "learning_rate": 8.305517833882991e-07, "loss": 0.8291, "step": 286120 }, { "epoch": 23.78, "learning_rate": 8.304409278607655e-07, "loss": 0.8005, "step": 286130 }, { "epoch": 23.78, "learning_rate": 8.303300723332317e-07, "loss": 0.7429, "step": 286140 }, { "epoch": 23.78, "learning_rate": 8.30219216805698e-07, "loss": 0.7138, "step": 286150 }, { "epoch": 23.79, "learning_rate": 8.301083612781642e-07, "loss": 0.7826, "step": 286160 }, { "epoch": 23.79, "learning_rate": 8.299975057506305e-07, "loss": 0.7999, "step": 286170 }, { "epoch": 23.79, "learning_rate": 8.298866502230967e-07, "loss": 0.7384, "step": 286180 }, { "epoch": 23.79, "learning_rate": 8.297757946955631e-07, "loss": 0.7767, "step": 286190 }, { "epoch": 23.79, "learning_rate": 8.296649391680293e-07, "loss": 0.7462, "step": 286200 }, { "epoch": 23.79, "learning_rate": 8.295540836404956e-07, "loss": 0.7455, "step": 286210 }, { "epoch": 23.79, "learning_rate": 8.294432281129617e-07, "loss": 0.8058, "step": 286220 }, { "epoch": 23.79, "learning_rate": 8.293323725854279e-07, "loss": 0.7513, "step": 286230 }, { "epoch": 23.79, "learning_rate": 8.292215170578942e-07, "loss": 0.7077, "step": 286240 }, { "epoch": 23.79, "learning_rate": 8.291106615303604e-07, "loss": 0.7431, "step": 286250 }, { "epoch": 23.79, "learning_rate": 8.289998060028268e-07, "loss": 0.7419, "step": 286260 }, { "epoch": 23.79, "learning_rate": 8.28888950475293e-07, "loss": 0.9016, "step": 286270 }, { "epoch": 23.8, "learning_rate": 8.287780949477593e-07, "loss": 0.6837, "step": 286280 }, { "epoch": 23.8, "learning_rate": 8.286672394202255e-07, "loss": 0.7718, "step": 286290 }, { "epoch": 23.8, "learning_rate": 8.285563838926918e-07, "loss": 0.7204, "step": 286300 }, { "epoch": 23.8, "learning_rate": 8.28445528365158e-07, "loss": 0.9238, "step": 286310 }, { "epoch": 23.8, "learning_rate": 8.283346728376244e-07, "loss": 0.7847, "step": 286320 }, { "epoch": 23.8, "learning_rate": 8.282238173100906e-07, "loss": 0.7611, "step": 286330 }, { "epoch": 23.8, "learning_rate": 8.281129617825569e-07, "loss": 0.7369, "step": 286340 }, { "epoch": 23.8, "learning_rate": 8.280021062550231e-07, "loss": 0.7531, "step": 286350 }, { "epoch": 23.8, "learning_rate": 8.278912507274894e-07, "loss": 0.6645, "step": 286360 }, { "epoch": 23.8, "learning_rate": 8.277803951999555e-07, "loss": 0.7428, "step": 286370 }, { "epoch": 23.8, "learning_rate": 8.276695396724219e-07, "loss": 0.6938, "step": 286380 }, { "epoch": 23.8, "learning_rate": 8.275586841448881e-07, "loss": 0.7634, "step": 286390 }, { "epoch": 23.81, "learning_rate": 8.274478286173544e-07, "loss": 0.7625, "step": 286400 }, { "epoch": 23.81, "learning_rate": 8.273369730898206e-07, "loss": 0.7564, "step": 286410 }, { "epoch": 23.81, "learning_rate": 8.272261175622869e-07, "loss": 0.8291, "step": 286420 }, { "epoch": 23.81, "learning_rate": 8.271152620347531e-07, "loss": 0.7613, "step": 286430 }, { "epoch": 23.81, "learning_rate": 8.270044065072195e-07, "loss": 0.7027, "step": 286440 }, { "epoch": 23.81, "learning_rate": 8.268935509796857e-07, "loss": 0.7725, "step": 286450 }, { "epoch": 23.81, "learning_rate": 8.26782695452152e-07, "loss": 0.7621, "step": 286460 }, { "epoch": 23.81, "learning_rate": 8.266718399246182e-07, "loss": 0.7697, "step": 286470 }, { "epoch": 23.81, "learning_rate": 8.265609843970845e-07, "loss": 0.751, "step": 286480 }, { "epoch": 23.81, "learning_rate": 8.264501288695507e-07, "loss": 0.714, "step": 286490 }, { "epoch": 23.81, "learning_rate": 8.263392733420171e-07, "loss": 0.7701, "step": 286500 }, { "epoch": 23.81, "learning_rate": 8.262284178144833e-07, "loss": 0.7066, "step": 286510 }, { "epoch": 23.82, "learning_rate": 8.261175622869495e-07, "loss": 0.8023, "step": 286520 }, { "epoch": 23.82, "learning_rate": 8.260067067594157e-07, "loss": 0.7279, "step": 286530 }, { "epoch": 23.82, "learning_rate": 8.25895851231882e-07, "loss": 0.7297, "step": 286540 }, { "epoch": 23.82, "learning_rate": 8.257849957043482e-07, "loss": 0.7432, "step": 286550 }, { "epoch": 23.82, "learning_rate": 8.256741401768146e-07, "loss": 0.7491, "step": 286560 }, { "epoch": 23.82, "learning_rate": 8.255632846492808e-07, "loss": 0.8106, "step": 286570 }, { "epoch": 23.82, "learning_rate": 8.254524291217471e-07, "loss": 0.7089, "step": 286580 }, { "epoch": 23.82, "learning_rate": 8.253415735942133e-07, "loss": 0.7148, "step": 286590 }, { "epoch": 23.82, "learning_rate": 8.252307180666796e-07, "loss": 0.7274, "step": 286600 }, { "epoch": 23.82, "learning_rate": 8.251198625391458e-07, "loss": 0.7316, "step": 286610 }, { "epoch": 23.82, "learning_rate": 8.25009007011612e-07, "loss": 0.7516, "step": 286620 }, { "epoch": 23.82, "learning_rate": 8.248981514840784e-07, "loss": 0.7076, "step": 286630 }, { "epoch": 23.83, "learning_rate": 8.247872959565446e-07, "loss": 0.748, "step": 286640 }, { "epoch": 23.83, "learning_rate": 8.246764404290109e-07, "loss": 0.7161, "step": 286650 }, { "epoch": 23.83, "learning_rate": 8.24565584901477e-07, "loss": 0.7627, "step": 286660 }, { "epoch": 23.83, "learning_rate": 8.244547293739433e-07, "loss": 0.7488, "step": 286670 }, { "epoch": 23.83, "learning_rate": 8.243438738464095e-07, "loss": 0.7324, "step": 286680 }, { "epoch": 23.83, "learning_rate": 8.242330183188759e-07, "loss": 0.7256, "step": 286690 }, { "epoch": 23.83, "learning_rate": 8.241221627913421e-07, "loss": 0.7323, "step": 286700 }, { "epoch": 23.83, "learning_rate": 8.240113072638084e-07, "loss": 0.7258, "step": 286710 }, { "epoch": 23.83, "learning_rate": 8.239004517362746e-07, "loss": 0.737, "step": 286720 }, { "epoch": 23.83, "learning_rate": 8.237895962087409e-07, "loss": 0.8024, "step": 286730 }, { "epoch": 23.83, "learning_rate": 8.236787406812071e-07, "loss": 0.7356, "step": 286740 }, { "epoch": 23.83, "learning_rate": 8.235678851536735e-07, "loss": 0.7339, "step": 286750 }, { "epoch": 23.84, "learning_rate": 8.234570296261397e-07, "loss": 0.7635, "step": 286760 }, { "epoch": 23.84, "learning_rate": 8.23346174098606e-07, "loss": 0.8185, "step": 286770 }, { "epoch": 23.84, "learning_rate": 8.232353185710722e-07, "loss": 0.7187, "step": 286780 }, { "epoch": 23.84, "learning_rate": 8.231244630435385e-07, "loss": 0.7469, "step": 286790 }, { "epoch": 23.84, "learning_rate": 8.230136075160047e-07, "loss": 0.6974, "step": 286800 }, { "epoch": 23.84, "learning_rate": 8.229027519884711e-07, "loss": 0.7576, "step": 286810 }, { "epoch": 23.84, "learning_rate": 8.227918964609372e-07, "loss": 0.7233, "step": 286820 }, { "epoch": 23.84, "learning_rate": 8.226810409334035e-07, "loss": 0.7509, "step": 286830 }, { "epoch": 23.84, "learning_rate": 8.225701854058697e-07, "loss": 0.7033, "step": 286840 }, { "epoch": 23.84, "learning_rate": 8.22459329878336e-07, "loss": 0.7432, "step": 286850 }, { "epoch": 23.84, "learning_rate": 8.223484743508022e-07, "loss": 0.7334, "step": 286860 }, { "epoch": 23.84, "learning_rate": 8.222376188232686e-07, "loss": 0.7791, "step": 286870 }, { "epoch": 23.85, "learning_rate": 8.221267632957348e-07, "loss": 0.737, "step": 286880 }, { "epoch": 23.85, "learning_rate": 8.220159077682011e-07, "loss": 0.7597, "step": 286890 }, { "epoch": 23.85, "learning_rate": 8.219050522406673e-07, "loss": 0.8089, "step": 286900 }, { "epoch": 23.85, "learning_rate": 8.217941967131336e-07, "loss": 0.7201, "step": 286910 }, { "epoch": 23.85, "learning_rate": 8.216833411855998e-07, "loss": 0.8443, "step": 286920 }, { "epoch": 23.85, "learning_rate": 8.215724856580662e-07, "loss": 0.6742, "step": 286930 }, { "epoch": 23.85, "learning_rate": 8.214616301305324e-07, "loss": 0.7648, "step": 286940 }, { "epoch": 23.85, "learning_rate": 8.213507746029987e-07, "loss": 0.7423, "step": 286950 }, { "epoch": 23.85, "learning_rate": 8.212399190754648e-07, "loss": 0.7499, "step": 286960 }, { "epoch": 23.85, "learning_rate": 8.211290635479311e-07, "loss": 0.7574, "step": 286970 }, { "epoch": 23.85, "learning_rate": 8.210182080203973e-07, "loss": 0.7556, "step": 286980 }, { "epoch": 23.85, "learning_rate": 8.209073524928637e-07, "loss": 0.6935, "step": 286990 }, { "epoch": 23.86, "learning_rate": 8.207964969653299e-07, "loss": 0.7518, "step": 287000 }, { "epoch": 23.86, "learning_rate": 8.206856414377962e-07, "loss": 0.7063, "step": 287010 }, { "epoch": 23.86, "learning_rate": 8.205747859102624e-07, "loss": 0.762, "step": 287020 }, { "epoch": 23.86, "learning_rate": 8.204639303827287e-07, "loss": 0.7484, "step": 287030 }, { "epoch": 23.86, "learning_rate": 8.203530748551949e-07, "loss": 0.7484, "step": 287040 }, { "epoch": 23.86, "learning_rate": 8.202422193276611e-07, "loss": 0.7328, "step": 287050 }, { "epoch": 23.86, "learning_rate": 8.201313638001275e-07, "loss": 0.7147, "step": 287060 }, { "epoch": 23.86, "learning_rate": 8.200205082725937e-07, "loss": 0.7462, "step": 287070 }, { "epoch": 23.86, "learning_rate": 8.1990965274506e-07, "loss": 0.7235, "step": 287080 }, { "epoch": 23.86, "learning_rate": 8.197987972175262e-07, "loss": 0.7623, "step": 287090 }, { "epoch": 23.86, "learning_rate": 8.196879416899925e-07, "loss": 0.7726, "step": 287100 }, { "epoch": 23.86, "learning_rate": 8.195770861624586e-07, "loss": 0.7355, "step": 287110 }, { "epoch": 23.87, "learning_rate": 8.19466230634925e-07, "loss": 0.7579, "step": 287120 }, { "epoch": 23.87, "learning_rate": 8.193553751073912e-07, "loss": 0.6864, "step": 287130 }, { "epoch": 23.87, "learning_rate": 8.192445195798575e-07, "loss": 0.7511, "step": 287140 }, { "epoch": 23.87, "learning_rate": 8.191336640523237e-07, "loss": 0.7645, "step": 287150 }, { "epoch": 23.87, "learning_rate": 8.1902280852479e-07, "loss": 0.7403, "step": 287160 }, { "epoch": 23.87, "learning_rate": 8.189119529972562e-07, "loss": 0.7307, "step": 287170 }, { "epoch": 23.87, "learning_rate": 8.188010974697226e-07, "loss": 0.6961, "step": 287180 }, { "epoch": 23.87, "learning_rate": 8.186902419421888e-07, "loss": 0.676, "step": 287190 }, { "epoch": 23.87, "learning_rate": 8.185793864146551e-07, "loss": 0.7785, "step": 287200 }, { "epoch": 23.87, "learning_rate": 8.184685308871213e-07, "loss": 0.7067, "step": 287210 }, { "epoch": 23.87, "learning_rate": 8.183576753595876e-07, "loss": 0.7877, "step": 287220 }, { "epoch": 23.87, "learning_rate": 8.182468198320538e-07, "loss": 0.7211, "step": 287230 }, { "epoch": 23.87, "learning_rate": 8.181359643045202e-07, "loss": 0.7855, "step": 287240 }, { "epoch": 23.88, "learning_rate": 8.180251087769864e-07, "loss": 0.7197, "step": 287250 }, { "epoch": 23.88, "learning_rate": 8.179142532494527e-07, "loss": 0.7344, "step": 287260 }, { "epoch": 23.88, "learning_rate": 8.178033977219188e-07, "loss": 0.7673, "step": 287270 }, { "epoch": 23.88, "learning_rate": 8.176925421943851e-07, "loss": 0.724, "step": 287280 }, { "epoch": 23.88, "learning_rate": 8.175816866668513e-07, "loss": 0.7417, "step": 287290 }, { "epoch": 23.88, "learning_rate": 8.174708311393177e-07, "loss": 0.7212, "step": 287300 }, { "epoch": 23.88, "learning_rate": 8.173599756117839e-07, "loss": 0.7552, "step": 287310 }, { "epoch": 23.88, "learning_rate": 8.172491200842502e-07, "loss": 0.8116, "step": 287320 }, { "epoch": 23.88, "learning_rate": 8.171382645567164e-07, "loss": 0.7506, "step": 287330 }, { "epoch": 23.88, "learning_rate": 8.170274090291827e-07, "loss": 0.6756, "step": 287340 }, { "epoch": 23.88, "learning_rate": 8.169165535016489e-07, "loss": 0.7246, "step": 287350 }, { "epoch": 23.88, "learning_rate": 8.168056979741153e-07, "loss": 0.7384, "step": 287360 }, { "epoch": 23.89, "learning_rate": 8.166948424465815e-07, "loss": 0.8172, "step": 287370 }, { "epoch": 23.89, "learning_rate": 8.165839869190478e-07, "loss": 0.7469, "step": 287380 }, { "epoch": 23.89, "learning_rate": 8.16473131391514e-07, "loss": 0.6986, "step": 287390 }, { "epoch": 23.89, "learning_rate": 8.163622758639803e-07, "loss": 0.7251, "step": 287400 }, { "epoch": 23.89, "learning_rate": 8.162514203364464e-07, "loss": 0.7272, "step": 287410 }, { "epoch": 23.89, "learning_rate": 8.161405648089128e-07, "loss": 0.7813, "step": 287420 }, { "epoch": 23.89, "learning_rate": 8.16029709281379e-07, "loss": 0.7579, "step": 287430 }, { "epoch": 23.89, "learning_rate": 8.159188537538453e-07, "loss": 0.7158, "step": 287440 }, { "epoch": 23.89, "learning_rate": 8.158079982263115e-07, "loss": 0.7305, "step": 287450 }, { "epoch": 23.89, "learning_rate": 8.156971426987777e-07, "loss": 0.7781, "step": 287460 }, { "epoch": 23.89, "learning_rate": 8.15586287171244e-07, "loss": 0.7368, "step": 287470 }, { "epoch": 23.89, "learning_rate": 8.154754316437102e-07, "loss": 0.8288, "step": 287480 }, { "epoch": 23.9, "learning_rate": 8.153645761161766e-07, "loss": 0.7679, "step": 287490 }, { "epoch": 23.9, "learning_rate": 8.152537205886428e-07, "loss": 0.7727, "step": 287500 }, { "epoch": 23.9, "learning_rate": 8.151428650611091e-07, "loss": 0.7131, "step": 287510 }, { "epoch": 23.9, "learning_rate": 8.150320095335753e-07, "loss": 0.7838, "step": 287520 }, { "epoch": 23.9, "learning_rate": 8.149211540060416e-07, "loss": 0.7732, "step": 287530 }, { "epoch": 23.9, "learning_rate": 8.148102984785078e-07, "loss": 0.7457, "step": 287540 }, { "epoch": 23.9, "learning_rate": 8.146994429509742e-07, "loss": 0.7614, "step": 287550 }, { "epoch": 23.9, "learning_rate": 8.145885874234403e-07, "loss": 0.7256, "step": 287560 }, { "epoch": 23.9, "learning_rate": 8.144777318959066e-07, "loss": 0.739, "step": 287570 }, { "epoch": 23.9, "learning_rate": 8.143668763683728e-07, "loss": 0.7377, "step": 287580 }, { "epoch": 23.9, "learning_rate": 8.142560208408391e-07, "loss": 0.75, "step": 287590 }, { "epoch": 23.9, "learning_rate": 8.141451653133053e-07, "loss": 0.7659, "step": 287600 }, { "epoch": 23.91, "learning_rate": 8.140343097857717e-07, "loss": 0.6889, "step": 287610 }, { "epoch": 23.91, "learning_rate": 8.139234542582379e-07, "loss": 0.8336, "step": 287620 }, { "epoch": 23.91, "learning_rate": 8.138125987307042e-07, "loss": 0.7172, "step": 287630 }, { "epoch": 23.91, "learning_rate": 8.137017432031704e-07, "loss": 0.7697, "step": 287640 }, { "epoch": 23.91, "learning_rate": 8.135908876756367e-07, "loss": 0.6939, "step": 287650 }, { "epoch": 23.91, "learning_rate": 8.134800321481029e-07, "loss": 0.7282, "step": 287660 }, { "epoch": 23.91, "learning_rate": 8.133691766205693e-07, "loss": 0.7873, "step": 287670 }, { "epoch": 23.91, "learning_rate": 8.132583210930355e-07, "loss": 0.7662, "step": 287680 }, { "epoch": 23.91, "learning_rate": 8.131474655655018e-07, "loss": 0.7207, "step": 287690 }, { "epoch": 23.91, "learning_rate": 8.13036610037968e-07, "loss": 0.7381, "step": 287700 }, { "epoch": 23.91, "learning_rate": 8.129257545104342e-07, "loss": 0.6893, "step": 287710 }, { "epoch": 23.91, "learning_rate": 8.128148989829004e-07, "loss": 0.783, "step": 287720 }, { "epoch": 23.92, "learning_rate": 8.127040434553668e-07, "loss": 0.6875, "step": 287730 }, { "epoch": 23.92, "learning_rate": 8.12593187927833e-07, "loss": 0.6884, "step": 287740 }, { "epoch": 23.92, "learning_rate": 8.124823324002993e-07, "loss": 0.7886, "step": 287750 }, { "epoch": 23.92, "learning_rate": 8.123714768727655e-07, "loss": 0.7022, "step": 287760 }, { "epoch": 23.92, "learning_rate": 8.122606213452318e-07, "loss": 0.8023, "step": 287770 }, { "epoch": 23.92, "learning_rate": 8.12149765817698e-07, "loss": 0.7988, "step": 287780 }, { "epoch": 23.92, "learning_rate": 8.120389102901644e-07, "loss": 0.7498, "step": 287790 }, { "epoch": 23.92, "learning_rate": 8.119280547626306e-07, "loss": 0.8088, "step": 287800 }, { "epoch": 23.92, "learning_rate": 8.118171992350969e-07, "loss": 0.6963, "step": 287810 }, { "epoch": 23.92, "learning_rate": 8.117063437075631e-07, "loss": 0.7969, "step": 287820 }, { "epoch": 23.92, "learning_rate": 8.115954881800294e-07, "loss": 0.7333, "step": 287830 }, { "epoch": 23.92, "learning_rate": 8.114846326524956e-07, "loss": 0.7331, "step": 287840 }, { "epoch": 23.93, "learning_rate": 8.11373777124962e-07, "loss": 0.7512, "step": 287850 }, { "epoch": 23.93, "learning_rate": 8.112629215974281e-07, "loss": 0.7413, "step": 287860 }, { "epoch": 23.93, "learning_rate": 8.111520660698944e-07, "loss": 0.7883, "step": 287870 }, { "epoch": 23.93, "learning_rate": 8.110412105423606e-07, "loss": 0.7482, "step": 287880 }, { "epoch": 23.93, "learning_rate": 8.109303550148268e-07, "loss": 0.7509, "step": 287890 }, { "epoch": 23.93, "learning_rate": 8.108194994872931e-07, "loss": 0.7278, "step": 287900 }, { "epoch": 23.93, "learning_rate": 8.107086439597593e-07, "loss": 0.7306, "step": 287910 }, { "epoch": 23.93, "learning_rate": 8.105977884322257e-07, "loss": 0.8199, "step": 287920 }, { "epoch": 23.93, "learning_rate": 8.104869329046919e-07, "loss": 0.7041, "step": 287930 }, { "epoch": 23.93, "learning_rate": 8.103760773771582e-07, "loss": 0.719, "step": 287940 }, { "epoch": 23.93, "learning_rate": 8.102652218496244e-07, "loss": 0.7294, "step": 287950 }, { "epoch": 23.93, "learning_rate": 8.101543663220907e-07, "loss": 0.6996, "step": 287960 }, { "epoch": 23.94, "learning_rate": 8.100435107945569e-07, "loss": 0.7622, "step": 287970 }, { "epoch": 23.94, "learning_rate": 8.099326552670233e-07, "loss": 0.7619, "step": 287980 }, { "epoch": 23.94, "learning_rate": 8.098217997394895e-07, "loss": 0.7065, "step": 287990 }, { "epoch": 23.94, "learning_rate": 8.097109442119558e-07, "loss": 0.7372, "step": 288000 }, { "epoch": 23.94, "learning_rate": 8.096000886844219e-07, "loss": 0.703, "step": 288010 }, { "epoch": 23.94, "learning_rate": 8.094892331568882e-07, "loss": 0.774, "step": 288020 }, { "epoch": 23.94, "learning_rate": 8.093783776293544e-07, "loss": 0.7212, "step": 288030 }, { "epoch": 23.94, "learning_rate": 8.092675221018208e-07, "loss": 0.7534, "step": 288040 }, { "epoch": 23.94, "learning_rate": 8.09156666574287e-07, "loss": 0.7257, "step": 288050 }, { "epoch": 23.94, "learning_rate": 8.090458110467533e-07, "loss": 0.7521, "step": 288060 }, { "epoch": 23.94, "learning_rate": 8.089349555192195e-07, "loss": 0.7447, "step": 288070 }, { "epoch": 23.94, "learning_rate": 8.088240999916858e-07, "loss": 0.7492, "step": 288080 }, { "epoch": 23.95, "learning_rate": 8.08713244464152e-07, "loss": 0.7074, "step": 288090 }, { "epoch": 23.95, "learning_rate": 8.086023889366184e-07, "loss": 0.7615, "step": 288100 }, { "epoch": 23.95, "learning_rate": 8.084915334090846e-07, "loss": 0.6932, "step": 288110 }, { "epoch": 23.95, "learning_rate": 8.083806778815509e-07, "loss": 0.796, "step": 288120 }, { "epoch": 23.95, "learning_rate": 8.082698223540171e-07, "loss": 0.7083, "step": 288130 }, { "epoch": 23.95, "learning_rate": 8.081589668264834e-07, "loss": 0.7388, "step": 288140 }, { "epoch": 23.95, "learning_rate": 8.080481112989495e-07, "loss": 0.7, "step": 288150 }, { "epoch": 23.95, "learning_rate": 8.07937255771416e-07, "loss": 0.7824, "step": 288160 }, { "epoch": 23.95, "learning_rate": 8.078264002438821e-07, "loss": 0.7478, "step": 288170 }, { "epoch": 23.95, "learning_rate": 8.077155447163484e-07, "loss": 0.7734, "step": 288180 }, { "epoch": 23.95, "learning_rate": 8.076046891888146e-07, "loss": 0.7499, "step": 288190 }, { "epoch": 23.95, "learning_rate": 8.074938336612809e-07, "loss": 0.7522, "step": 288200 }, { "epoch": 23.96, "learning_rate": 8.073829781337471e-07, "loss": 0.785, "step": 288210 }, { "epoch": 23.96, "learning_rate": 8.072721226062135e-07, "loss": 0.7252, "step": 288220 }, { "epoch": 23.96, "learning_rate": 8.071612670786797e-07, "loss": 0.7534, "step": 288230 }, { "epoch": 23.96, "learning_rate": 8.07050411551146e-07, "loss": 0.7268, "step": 288240 }, { "epoch": 23.96, "learning_rate": 8.069395560236122e-07, "loss": 0.7051, "step": 288250 }, { "epoch": 23.96, "learning_rate": 8.068287004960785e-07, "loss": 0.6981, "step": 288260 }, { "epoch": 23.96, "learning_rate": 8.067178449685447e-07, "loss": 0.8051, "step": 288270 }, { "epoch": 23.96, "learning_rate": 8.066069894410111e-07, "loss": 0.7473, "step": 288280 }, { "epoch": 23.96, "learning_rate": 8.064961339134773e-07, "loss": 0.7527, "step": 288290 }, { "epoch": 23.96, "learning_rate": 8.063852783859434e-07, "loss": 0.7664, "step": 288300 }, { "epoch": 23.96, "learning_rate": 8.062744228584097e-07, "loss": 0.6994, "step": 288310 }, { "epoch": 23.96, "learning_rate": 8.061635673308759e-07, "loss": 0.8384, "step": 288320 }, { "epoch": 23.97, "learning_rate": 8.060527118033422e-07, "loss": 0.703, "step": 288330 }, { "epoch": 23.97, "learning_rate": 8.059418562758084e-07, "loss": 0.7409, "step": 288340 }, { "epoch": 23.97, "learning_rate": 8.058310007482748e-07, "loss": 0.703, "step": 288350 }, { "epoch": 23.97, "learning_rate": 8.05720145220741e-07, "loss": 0.7279, "step": 288360 }, { "epoch": 23.97, "learning_rate": 8.056092896932073e-07, "loss": 0.7783, "step": 288370 }, { "epoch": 23.97, "learning_rate": 8.054984341656735e-07, "loss": 0.7517, "step": 288380 }, { "epoch": 23.97, "learning_rate": 8.053875786381398e-07, "loss": 0.7626, "step": 288390 }, { "epoch": 23.97, "learning_rate": 8.05276723110606e-07, "loss": 0.7803, "step": 288400 }, { "epoch": 23.97, "learning_rate": 8.051658675830724e-07, "loss": 0.7335, "step": 288410 }, { "epoch": 23.97, "learning_rate": 8.050550120555386e-07, "loss": 0.7922, "step": 288420 }, { "epoch": 23.97, "learning_rate": 8.049441565280049e-07, "loss": 0.7494, "step": 288430 }, { "epoch": 23.97, "learning_rate": 8.048333010004711e-07, "loss": 0.7785, "step": 288440 }, { "epoch": 23.98, "learning_rate": 8.047224454729373e-07, "loss": 0.6821, "step": 288450 }, { "epoch": 23.98, "learning_rate": 8.046115899454035e-07, "loss": 0.7494, "step": 288460 }, { "epoch": 23.98, "learning_rate": 8.045007344178699e-07, "loss": 0.7936, "step": 288470 }, { "epoch": 23.98, "learning_rate": 8.043898788903361e-07, "loss": 0.6865, "step": 288480 }, { "epoch": 23.98, "learning_rate": 8.042790233628024e-07, "loss": 0.7331, "step": 288490 }, { "epoch": 23.98, "learning_rate": 8.041681678352686e-07, "loss": 0.7292, "step": 288500 }, { "epoch": 23.98, "learning_rate": 8.040573123077349e-07, "loss": 0.7635, "step": 288510 }, { "epoch": 23.98, "learning_rate": 8.039464567802011e-07, "loss": 0.7321, "step": 288520 }, { "epoch": 23.98, "learning_rate": 8.038356012526675e-07, "loss": 0.7473, "step": 288530 }, { "epoch": 23.98, "learning_rate": 8.037247457251337e-07, "loss": 0.7276, "step": 288540 }, { "epoch": 23.98, "learning_rate": 8.036138901976e-07, "loss": 0.7359, "step": 288550 }, { "epoch": 23.98, "learning_rate": 8.035030346700662e-07, "loss": 0.8137, "step": 288560 }, { "epoch": 23.99, "learning_rate": 8.033921791425325e-07, "loss": 0.7836, "step": 288570 }, { "epoch": 23.99, "learning_rate": 8.032813236149987e-07, "loss": 0.7266, "step": 288580 }, { "epoch": 23.99, "learning_rate": 8.031704680874651e-07, "loss": 0.7057, "step": 288590 }, { "epoch": 23.99, "learning_rate": 8.030596125599313e-07, "loss": 0.6961, "step": 288600 }, { "epoch": 23.99, "learning_rate": 8.029487570323975e-07, "loss": 0.7298, "step": 288610 }, { "epoch": 23.99, "learning_rate": 8.028379015048637e-07, "loss": 0.8267, "step": 288620 }, { "epoch": 23.99, "learning_rate": 8.0272704597733e-07, "loss": 0.7542, "step": 288630 }, { "epoch": 23.99, "learning_rate": 8.026161904497962e-07, "loss": 0.7562, "step": 288640 }, { "epoch": 23.99, "learning_rate": 8.025053349222626e-07, "loss": 0.807, "step": 288650 }, { "epoch": 23.99, "learning_rate": 8.023944793947288e-07, "loss": 0.7911, "step": 288660 }, { "epoch": 23.99, "learning_rate": 8.022836238671951e-07, "loss": 0.7809, "step": 288670 }, { "epoch": 23.99, "learning_rate": 8.021727683396613e-07, "loss": 0.74, "step": 288680 }, { "epoch": 24.0, "learning_rate": 8.020619128121276e-07, "loss": 0.722, "step": 288690 }, { "epoch": 24.0, "learning_rate": 8.019510572845938e-07, "loss": 0.7349, "step": 288700 }, { "epoch": 24.0, "learning_rate": 8.0184020175706e-07, "loss": 0.7504, "step": 288710 }, { "epoch": 24.0, "learning_rate": 8.017293462295264e-07, "loss": 0.7777, "step": 288720 }, { "epoch": 24.0, "learning_rate": 8.016184907019926e-07, "loss": 0.7385, "step": 288730 }, { "epoch": 24.0, "learning_rate": 8.015076351744589e-07, "loss": 0.7816, "step": 288740 }, { "epoch": 24.0, "eval_loss": 1.1326406002044678, "eval_runtime": 345.1794, "eval_samples_per_second": 7.747, "eval_steps_per_second": 3.873, "eval_wer": 0.6365969308716268, "step": 288744 }, { "epoch": 24.0, "learning_rate": 8.01396779646925e-07, "loss": 0.7119, "step": 288750 }, { "epoch": 24.0, "learning_rate": 8.012859241193913e-07, "loss": 0.712, "step": 288760 }, { "epoch": 24.0, "learning_rate": 8.011750685918575e-07, "loss": 0.7463, "step": 288770 }, { "epoch": 24.0, "learning_rate": 8.010642130643239e-07, "loss": 0.7739, "step": 288780 }, { "epoch": 24.0, "learning_rate": 8.009533575367901e-07, "loss": 0.7115, "step": 288790 }, { "epoch": 24.0, "learning_rate": 8.008425020092564e-07, "loss": 0.8019, "step": 288800 }, { "epoch": 24.01, "learning_rate": 8.007316464817226e-07, "loss": 0.76, "step": 288810 }, { "epoch": 24.01, "learning_rate": 8.006207909541889e-07, "loss": 0.7682, "step": 288820 }, { "epoch": 24.01, "learning_rate": 8.005099354266551e-07, "loss": 0.7515, "step": 288830 }, { "epoch": 24.01, "learning_rate": 8.003990798991215e-07, "loss": 0.7303, "step": 288840 }, { "epoch": 24.01, "learning_rate": 8.002882243715877e-07, "loss": 0.7545, "step": 288850 }, { "epoch": 24.01, "learning_rate": 8.00177368844054e-07, "loss": 0.7343, "step": 288860 }, { "epoch": 24.01, "learning_rate": 8.000665133165202e-07, "loss": 0.6372, "step": 288870 }, { "epoch": 24.01, "learning_rate": 7.999556577889865e-07, "loss": 0.7752, "step": 288880 }, { "epoch": 24.01, "learning_rate": 7.998448022614527e-07, "loss": 0.7711, "step": 288890 }, { "epoch": 24.01, "learning_rate": 7.997450322866723e-07, "loss": 0.763, "step": 288900 }, { "epoch": 24.01, "learning_rate": 7.996341767591386e-07, "loss": 0.7264, "step": 288910 }, { "epoch": 24.01, "learning_rate": 7.995233212316048e-07, "loss": 0.6982, "step": 288920 }, { "epoch": 24.02, "learning_rate": 7.994124657040712e-07, "loss": 0.7082, "step": 288930 }, { "epoch": 24.02, "learning_rate": 7.993016101765374e-07, "loss": 0.7176, "step": 288940 }, { "epoch": 24.02, "learning_rate": 7.991907546490037e-07, "loss": 0.7813, "step": 288950 }, { "epoch": 24.02, "learning_rate": 7.990798991214699e-07, "loss": 0.6884, "step": 288960 }, { "epoch": 24.02, "learning_rate": 7.989690435939362e-07, "loss": 0.732, "step": 288970 }, { "epoch": 24.02, "learning_rate": 7.988581880664023e-07, "loss": 0.7635, "step": 288980 }, { "epoch": 24.02, "learning_rate": 7.987473325388687e-07, "loss": 0.7178, "step": 288990 }, { "epoch": 24.02, "learning_rate": 7.986364770113349e-07, "loss": 0.7164, "step": 289000 }, { "epoch": 24.02, "learning_rate": 7.985256214838012e-07, "loss": 0.6849, "step": 289010 }, { "epoch": 24.02, "learning_rate": 7.984147659562674e-07, "loss": 0.7462, "step": 289020 }, { "epoch": 24.02, "learning_rate": 7.983039104287337e-07, "loss": 0.7094, "step": 289030 }, { "epoch": 24.02, "learning_rate": 7.981930549011999e-07, "loss": 0.7202, "step": 289040 }, { "epoch": 24.03, "learning_rate": 7.980821993736663e-07, "loss": 0.7415, "step": 289050 }, { "epoch": 24.03, "learning_rate": 7.979713438461325e-07, "loss": 0.6961, "step": 289060 }, { "epoch": 24.03, "learning_rate": 7.978604883185988e-07, "loss": 0.718, "step": 289070 }, { "epoch": 24.03, "learning_rate": 7.97749632791065e-07, "loss": 0.719, "step": 289080 }, { "epoch": 24.03, "learning_rate": 7.976387772635313e-07, "loss": 0.7838, "step": 289090 }, { "epoch": 24.03, "learning_rate": 7.975279217359975e-07, "loss": 0.7831, "step": 289100 }, { "epoch": 24.03, "learning_rate": 7.974170662084639e-07, "loss": 0.7781, "step": 289110 }, { "epoch": 24.03, "learning_rate": 7.9730621068093e-07, "loss": 0.6699, "step": 289120 }, { "epoch": 24.03, "learning_rate": 7.971953551533963e-07, "loss": 0.6641, "step": 289130 }, { "epoch": 24.03, "learning_rate": 7.970844996258625e-07, "loss": 0.7026, "step": 289140 }, { "epoch": 24.03, "learning_rate": 7.969736440983288e-07, "loss": 0.7689, "step": 289150 }, { "epoch": 24.03, "learning_rate": 7.96862788570795e-07, "loss": 0.7883, "step": 289160 }, { "epoch": 24.04, "learning_rate": 7.967519330432614e-07, "loss": 0.7397, "step": 289170 }, { "epoch": 24.04, "learning_rate": 7.966410775157276e-07, "loss": 0.7802, "step": 289180 }, { "epoch": 24.04, "learning_rate": 7.965302219881939e-07, "loss": 0.6724, "step": 289190 }, { "epoch": 24.04, "learning_rate": 7.964193664606601e-07, "loss": 0.7521, "step": 289200 }, { "epoch": 24.04, "learning_rate": 7.963085109331264e-07, "loss": 0.7072, "step": 289210 }, { "epoch": 24.04, "learning_rate": 7.961976554055926e-07, "loss": 0.7747, "step": 289220 }, { "epoch": 24.04, "learning_rate": 7.96086799878059e-07, "loss": 0.778, "step": 289230 }, { "epoch": 24.04, "learning_rate": 7.959759443505252e-07, "loss": 0.7768, "step": 289240 }, { "epoch": 24.04, "learning_rate": 7.958650888229915e-07, "loss": 0.7718, "step": 289250 }, { "epoch": 24.04, "learning_rate": 7.957542332954577e-07, "loss": 0.7275, "step": 289260 }, { "epoch": 24.04, "learning_rate": 7.956433777679238e-07, "loss": 0.713, "step": 289270 }, { "epoch": 24.04, "learning_rate": 7.955325222403901e-07, "loss": 0.7216, "step": 289280 }, { "epoch": 24.05, "learning_rate": 7.954216667128564e-07, "loss": 0.7478, "step": 289290 }, { "epoch": 24.05, "learning_rate": 7.953108111853227e-07, "loss": 0.7471, "step": 289300 }, { "epoch": 24.05, "learning_rate": 7.951999556577889e-07, "loss": 0.7258, "step": 289310 }, { "epoch": 24.05, "learning_rate": 7.950891001302552e-07, "loss": 0.7388, "step": 289320 }, { "epoch": 24.05, "learning_rate": 7.949782446027214e-07, "loss": 0.7076, "step": 289330 }, { "epoch": 24.05, "learning_rate": 7.948673890751877e-07, "loss": 0.6914, "step": 289340 }, { "epoch": 24.05, "learning_rate": 7.947565335476539e-07, "loss": 0.729, "step": 289350 }, { "epoch": 24.05, "learning_rate": 7.946456780201203e-07, "loss": 0.7254, "step": 289360 }, { "epoch": 24.05, "learning_rate": 7.945348224925865e-07, "loss": 0.7234, "step": 289370 }, { "epoch": 24.05, "learning_rate": 7.944239669650528e-07, "loss": 0.7695, "step": 289380 }, { "epoch": 24.05, "learning_rate": 7.94313111437519e-07, "loss": 0.7259, "step": 289390 }, { "epoch": 24.05, "learning_rate": 7.942022559099853e-07, "loss": 0.7482, "step": 289400 }, { "epoch": 24.06, "learning_rate": 7.940914003824515e-07, "loss": 0.7756, "step": 289410 }, { "epoch": 24.06, "learning_rate": 7.939805448549179e-07, "loss": 0.7114, "step": 289420 }, { "epoch": 24.06, "learning_rate": 7.93869689327384e-07, "loss": 0.7808, "step": 289430 }, { "epoch": 24.06, "learning_rate": 7.937588337998503e-07, "loss": 0.7544, "step": 289440 }, { "epoch": 24.06, "learning_rate": 7.936479782723165e-07, "loss": 0.7528, "step": 289450 }, { "epoch": 24.06, "learning_rate": 7.935371227447828e-07, "loss": 0.7515, "step": 289460 }, { "epoch": 24.06, "learning_rate": 7.93426267217249e-07, "loss": 0.6847, "step": 289470 }, { "epoch": 24.06, "learning_rate": 7.933154116897154e-07, "loss": 0.7569, "step": 289480 }, { "epoch": 24.06, "learning_rate": 7.932045561621816e-07, "loss": 0.7206, "step": 289490 }, { "epoch": 24.06, "learning_rate": 7.930937006346479e-07, "loss": 0.7445, "step": 289500 }, { "epoch": 24.06, "learning_rate": 7.929828451071141e-07, "loss": 0.7631, "step": 289510 }, { "epoch": 24.06, "learning_rate": 7.928719895795804e-07, "loss": 0.746, "step": 289520 }, { "epoch": 24.07, "learning_rate": 7.927611340520466e-07, "loss": 0.7331, "step": 289530 }, { "epoch": 24.07, "learning_rate": 7.92650278524513e-07, "loss": 0.7482, "step": 289540 }, { "epoch": 24.07, "learning_rate": 7.925394229969792e-07, "loss": 0.7856, "step": 289550 }, { "epoch": 24.07, "learning_rate": 7.924285674694455e-07, "loss": 0.8265, "step": 289560 }, { "epoch": 24.07, "learning_rate": 7.923177119419116e-07, "loss": 0.7453, "step": 289570 }, { "epoch": 24.07, "learning_rate": 7.922068564143779e-07, "loss": 0.7143, "step": 289580 }, { "epoch": 24.07, "learning_rate": 7.920960008868441e-07, "loss": 0.7848, "step": 289590 }, { "epoch": 24.07, "learning_rate": 7.919851453593105e-07, "loss": 0.789, "step": 289600 }, { "epoch": 24.07, "learning_rate": 7.918742898317767e-07, "loss": 0.6729, "step": 289610 }, { "epoch": 24.07, "learning_rate": 7.91763434304243e-07, "loss": 0.7257, "step": 289620 }, { "epoch": 24.07, "learning_rate": 7.916525787767092e-07, "loss": 0.7379, "step": 289630 }, { "epoch": 24.07, "learning_rate": 7.915417232491755e-07, "loss": 0.7458, "step": 289640 }, { "epoch": 24.08, "learning_rate": 7.914308677216417e-07, "loss": 0.7048, "step": 289650 }, { "epoch": 24.08, "learning_rate": 7.913200121941081e-07, "loss": 0.7328, "step": 289660 }, { "epoch": 24.08, "learning_rate": 7.912091566665743e-07, "loss": 0.7799, "step": 289670 }, { "epoch": 24.08, "learning_rate": 7.910983011390405e-07, "loss": 0.7001, "step": 289680 }, { "epoch": 24.08, "learning_rate": 7.909874456115068e-07, "loss": 0.7412, "step": 289690 }, { "epoch": 24.08, "learning_rate": 7.90876590083973e-07, "loss": 0.7531, "step": 289700 }, { "epoch": 24.08, "learning_rate": 7.907657345564393e-07, "loss": 0.7357, "step": 289710 }, { "epoch": 24.08, "learning_rate": 7.906548790289055e-07, "loss": 0.7344, "step": 289720 }, { "epoch": 24.08, "learning_rate": 7.905440235013718e-07, "loss": 0.7563, "step": 289730 }, { "epoch": 24.08, "learning_rate": 7.90433167973838e-07, "loss": 0.7127, "step": 289740 }, { "epoch": 24.08, "learning_rate": 7.903223124463043e-07, "loss": 0.791, "step": 289750 }, { "epoch": 24.08, "learning_rate": 7.902114569187705e-07, "loss": 0.7041, "step": 289760 }, { "epoch": 24.09, "learning_rate": 7.901006013912368e-07, "loss": 0.7546, "step": 289770 }, { "epoch": 24.09, "learning_rate": 7.89989745863703e-07, "loss": 0.7375, "step": 289780 }, { "epoch": 24.09, "learning_rate": 7.898788903361694e-07, "loss": 0.7664, "step": 289790 }, { "epoch": 24.09, "learning_rate": 7.897680348086356e-07, "loss": 0.7466, "step": 289800 }, { "epoch": 24.09, "learning_rate": 7.896571792811019e-07, "loss": 0.7788, "step": 289810 }, { "epoch": 24.09, "learning_rate": 7.895463237535681e-07, "loss": 0.6888, "step": 289820 }, { "epoch": 24.09, "learning_rate": 7.894354682260344e-07, "loss": 0.7338, "step": 289830 }, { "epoch": 24.09, "learning_rate": 7.893246126985006e-07, "loss": 0.7194, "step": 289840 }, { "epoch": 24.09, "learning_rate": 7.89213757170967e-07, "loss": 0.7527, "step": 289850 }, { "epoch": 24.09, "learning_rate": 7.891029016434332e-07, "loss": 0.792, "step": 289860 }, { "epoch": 24.09, "learning_rate": 7.889920461158994e-07, "loss": 0.7326, "step": 289870 }, { "epoch": 24.09, "learning_rate": 7.888811905883656e-07, "loss": 0.7611, "step": 289880 }, { "epoch": 24.1, "learning_rate": 7.887703350608319e-07, "loss": 0.7217, "step": 289890 }, { "epoch": 24.1, "learning_rate": 7.886594795332981e-07, "loss": 0.7553, "step": 289900 }, { "epoch": 24.1, "learning_rate": 7.885486240057645e-07, "loss": 0.7404, "step": 289910 }, { "epoch": 24.1, "learning_rate": 7.884377684782307e-07, "loss": 0.7489, "step": 289920 }, { "epoch": 24.1, "learning_rate": 7.88326912950697e-07, "loss": 0.7859, "step": 289930 }, { "epoch": 24.1, "learning_rate": 7.882160574231632e-07, "loss": 0.7223, "step": 289940 }, { "epoch": 24.1, "learning_rate": 7.881052018956295e-07, "loss": 0.7426, "step": 289950 }, { "epoch": 24.1, "learning_rate": 7.879943463680957e-07, "loss": 0.7355, "step": 289960 }, { "epoch": 24.1, "learning_rate": 7.878834908405621e-07, "loss": 0.6732, "step": 289970 }, { "epoch": 24.1, "learning_rate": 7.877726353130283e-07, "loss": 0.7442, "step": 289980 }, { "epoch": 24.1, "learning_rate": 7.876617797854946e-07, "loss": 0.658, "step": 289990 }, { "epoch": 24.1, "learning_rate": 7.875509242579608e-07, "loss": 0.7227, "step": 290000 }, { "epoch": 24.11, "learning_rate": 7.874400687304271e-07, "loss": 0.7778, "step": 290010 }, { "epoch": 24.11, "learning_rate": 7.873292132028932e-07, "loss": 0.7763, "step": 290020 }, { "epoch": 24.11, "learning_rate": 7.872183576753596e-07, "loss": 0.7657, "step": 290030 }, { "epoch": 24.11, "learning_rate": 7.871075021478258e-07, "loss": 0.7508, "step": 290040 }, { "epoch": 24.11, "learning_rate": 7.869966466202921e-07, "loss": 0.7604, "step": 290050 }, { "epoch": 24.11, "learning_rate": 7.868857910927583e-07, "loss": 0.7312, "step": 290060 }, { "epoch": 24.11, "learning_rate": 7.867749355652246e-07, "loss": 0.7533, "step": 290070 }, { "epoch": 24.11, "learning_rate": 7.866640800376908e-07, "loss": 0.6992, "step": 290080 }, { "epoch": 24.11, "learning_rate": 7.865532245101572e-07, "loss": 0.7974, "step": 290090 }, { "epoch": 24.11, "learning_rate": 7.864423689826234e-07, "loss": 0.7351, "step": 290100 }, { "epoch": 24.11, "learning_rate": 7.863315134550896e-07, "loss": 0.7437, "step": 290110 }, { "epoch": 24.11, "learning_rate": 7.862206579275559e-07, "loss": 0.7177, "step": 290120 }, { "epoch": 24.12, "learning_rate": 7.861098024000221e-07, "loss": 0.7262, "step": 290130 }, { "epoch": 24.12, "learning_rate": 7.859989468724884e-07, "loss": 0.6836, "step": 290140 }, { "epoch": 24.12, "learning_rate": 7.858880913449547e-07, "loss": 0.7533, "step": 290150 }, { "epoch": 24.12, "learning_rate": 7.85777235817421e-07, "loss": 0.7351, "step": 290160 }, { "epoch": 24.12, "learning_rate": 7.856663802898871e-07, "loss": 0.6956, "step": 290170 }, { "epoch": 24.12, "learning_rate": 7.855555247623534e-07, "loss": 0.7743, "step": 290180 }, { "epoch": 24.12, "learning_rate": 7.854446692348196e-07, "loss": 0.8194, "step": 290190 }, { "epoch": 24.12, "learning_rate": 7.853338137072859e-07, "loss": 0.7792, "step": 290200 }, { "epoch": 24.12, "learning_rate": 7.852229581797521e-07, "loss": 0.7878, "step": 290210 }, { "epoch": 24.12, "learning_rate": 7.851121026522185e-07, "loss": 0.7388, "step": 290220 }, { "epoch": 24.12, "learning_rate": 7.850012471246847e-07, "loss": 0.7241, "step": 290230 }, { "epoch": 24.12, "learning_rate": 7.84890391597151e-07, "loss": 0.7512, "step": 290240 }, { "epoch": 24.13, "learning_rate": 7.847795360696172e-07, "loss": 0.7419, "step": 290250 }, { "epoch": 24.13, "learning_rate": 7.846686805420835e-07, "loss": 0.6643, "step": 290260 }, { "epoch": 24.13, "learning_rate": 7.845578250145497e-07, "loss": 0.7051, "step": 290270 }, { "epoch": 24.13, "learning_rate": 7.844469694870161e-07, "loss": 0.7214, "step": 290280 }, { "epoch": 24.13, "learning_rate": 7.843361139594823e-07, "loss": 0.7264, "step": 290290 }, { "epoch": 24.13, "learning_rate": 7.842252584319486e-07, "loss": 0.7391, "step": 290300 }, { "epoch": 24.13, "learning_rate": 7.841144029044147e-07, "loss": 0.7011, "step": 290310 }, { "epoch": 24.13, "learning_rate": 7.84003547376881e-07, "loss": 0.6992, "step": 290320 }, { "epoch": 24.13, "learning_rate": 7.838926918493472e-07, "loss": 0.7693, "step": 290330 }, { "epoch": 24.13, "learning_rate": 7.837818363218136e-07, "loss": 0.751, "step": 290340 }, { "epoch": 24.13, "learning_rate": 7.836709807942798e-07, "loss": 0.7266, "step": 290350 }, { "epoch": 24.13, "learning_rate": 7.835601252667461e-07, "loss": 0.7086, "step": 290360 }, { "epoch": 24.14, "learning_rate": 7.834492697392123e-07, "loss": 0.7019, "step": 290370 }, { "epoch": 24.14, "learning_rate": 7.833384142116786e-07, "loss": 0.7321, "step": 290380 }, { "epoch": 24.14, "learning_rate": 7.832275586841448e-07, "loss": 0.7703, "step": 290390 }, { "epoch": 24.14, "learning_rate": 7.831167031566112e-07, "loss": 0.7866, "step": 290400 }, { "epoch": 24.14, "learning_rate": 7.830058476290774e-07, "loss": 0.834, "step": 290410 }, { "epoch": 24.14, "learning_rate": 7.828949921015437e-07, "loss": 0.7422, "step": 290420 }, { "epoch": 24.14, "learning_rate": 7.827841365740099e-07, "loss": 0.7353, "step": 290430 }, { "epoch": 24.14, "learning_rate": 7.826732810464762e-07, "loss": 0.7305, "step": 290440 }, { "epoch": 24.14, "learning_rate": 7.825624255189424e-07, "loss": 0.7597, "step": 290450 }, { "epoch": 24.14, "learning_rate": 7.824515699914088e-07, "loss": 0.7582, "step": 290460 }, { "epoch": 24.14, "learning_rate": 7.823407144638749e-07, "loss": 0.7772, "step": 290470 }, { "epoch": 24.14, "learning_rate": 7.822298589363412e-07, "loss": 0.7011, "step": 290480 }, { "epoch": 24.15, "learning_rate": 7.821190034088074e-07, "loss": 0.6614, "step": 290490 }, { "epoch": 24.15, "learning_rate": 7.820081478812736e-07, "loss": 0.716, "step": 290500 }, { "epoch": 24.15, "learning_rate": 7.818972923537399e-07, "loss": 0.7635, "step": 290510 }, { "epoch": 24.15, "learning_rate": 7.817864368262063e-07, "loss": 0.747, "step": 290520 }, { "epoch": 24.15, "learning_rate": 7.816755812986725e-07, "loss": 0.6878, "step": 290530 }, { "epoch": 24.15, "learning_rate": 7.815647257711387e-07, "loss": 0.7033, "step": 290540 }, { "epoch": 24.15, "learning_rate": 7.81453870243605e-07, "loss": 0.7356, "step": 290550 }, { "epoch": 24.15, "learning_rate": 7.813430147160712e-07, "loss": 0.7287, "step": 290560 }, { "epoch": 24.15, "learning_rate": 7.812321591885375e-07, "loss": 0.7424, "step": 290570 }, { "epoch": 24.15, "learning_rate": 7.811213036610038e-07, "loss": 0.7612, "step": 290580 }, { "epoch": 24.15, "learning_rate": 7.810104481334701e-07, "loss": 0.7228, "step": 290590 }, { "epoch": 24.15, "learning_rate": 7.808995926059363e-07, "loss": 0.7762, "step": 290600 }, { "epoch": 24.16, "learning_rate": 7.807887370784026e-07, "loss": 0.6934, "step": 290610 }, { "epoch": 24.16, "learning_rate": 7.806778815508687e-07, "loss": 0.7913, "step": 290620 }, { "epoch": 24.16, "learning_rate": 7.80567026023335e-07, "loss": 0.7325, "step": 290630 }, { "epoch": 24.16, "learning_rate": 7.804561704958012e-07, "loss": 0.7587, "step": 290640 }, { "epoch": 24.16, "learning_rate": 7.803453149682676e-07, "loss": 0.7792, "step": 290650 }, { "epoch": 24.16, "learning_rate": 7.802344594407338e-07, "loss": 0.8118, "step": 290660 }, { "epoch": 24.16, "learning_rate": 7.801236039132001e-07, "loss": 0.7977, "step": 290670 }, { "epoch": 24.16, "learning_rate": 7.800127483856663e-07, "loss": 0.7079, "step": 290680 }, { "epoch": 24.16, "learning_rate": 7.799018928581326e-07, "loss": 0.73, "step": 290690 }, { "epoch": 24.16, "learning_rate": 7.797910373305988e-07, "loss": 0.7706, "step": 290700 }, { "epoch": 24.16, "learning_rate": 7.796801818030652e-07, "loss": 0.7539, "step": 290710 }, { "epoch": 24.16, "learning_rate": 7.795693262755314e-07, "loss": 0.7718, "step": 290720 }, { "epoch": 24.17, "learning_rate": 7.794584707479977e-07, "loss": 0.7538, "step": 290730 }, { "epoch": 24.17, "learning_rate": 7.793476152204639e-07, "loss": 0.7648, "step": 290740 }, { "epoch": 24.17, "learning_rate": 7.792367596929302e-07, "loss": 0.7289, "step": 290750 }, { "epoch": 24.17, "learning_rate": 7.791259041653963e-07, "loss": 0.6863, "step": 290760 }, { "epoch": 24.17, "learning_rate": 7.790150486378627e-07, "loss": 0.699, "step": 290770 }, { "epoch": 24.17, "learning_rate": 7.789041931103289e-07, "loss": 0.7895, "step": 290780 }, { "epoch": 24.17, "learning_rate": 7.787933375827952e-07, "loss": 0.6699, "step": 290790 }, { "epoch": 24.17, "learning_rate": 7.786824820552614e-07, "loss": 0.753, "step": 290800 }, { "epoch": 24.17, "learning_rate": 7.785716265277277e-07, "loss": 0.7547, "step": 290810 }, { "epoch": 24.17, "learning_rate": 7.784607710001939e-07, "loss": 0.68, "step": 290820 }, { "epoch": 24.17, "learning_rate": 7.783499154726603e-07, "loss": 0.76, "step": 290830 }, { "epoch": 24.17, "learning_rate": 7.782390599451265e-07, "loss": 0.7514, "step": 290840 }, { "epoch": 24.18, "learning_rate": 7.781282044175928e-07, "loss": 0.7683, "step": 290850 }, { "epoch": 24.18, "learning_rate": 7.78017348890059e-07, "loss": 0.7648, "step": 290860 }, { "epoch": 24.18, "learning_rate": 7.779064933625253e-07, "loss": 0.734, "step": 290870 }, { "epoch": 24.18, "learning_rate": 7.777956378349915e-07, "loss": 0.7081, "step": 290880 }, { "epoch": 24.18, "learning_rate": 7.776847823074579e-07, "loss": 0.7414, "step": 290890 }, { "epoch": 24.18, "learning_rate": 7.775739267799241e-07, "loss": 0.7747, "step": 290900 }, { "epoch": 24.18, "learning_rate": 7.774630712523904e-07, "loss": 0.7567, "step": 290910 }, { "epoch": 24.18, "learning_rate": 7.773522157248565e-07, "loss": 0.8076, "step": 290920 }, { "epoch": 24.18, "learning_rate": 7.772413601973227e-07, "loss": 0.7309, "step": 290930 }, { "epoch": 24.18, "learning_rate": 7.77130504669789e-07, "loss": 0.7534, "step": 290940 }, { "epoch": 24.18, "learning_rate": 7.770196491422553e-07, "loss": 0.7749, "step": 290950 }, { "epoch": 24.18, "learning_rate": 7.769087936147216e-07, "loss": 0.7897, "step": 290960 }, { "epoch": 24.19, "learning_rate": 7.767979380871878e-07, "loss": 0.7586, "step": 290970 }, { "epoch": 24.19, "learning_rate": 7.766870825596541e-07, "loss": 0.6585, "step": 290980 }, { "epoch": 24.19, "learning_rate": 7.765762270321203e-07, "loss": 0.7226, "step": 290990 }, { "epoch": 24.19, "learning_rate": 7.764653715045866e-07, "loss": 0.7597, "step": 291000 }, { "epoch": 24.19, "learning_rate": 7.763545159770528e-07, "loss": 0.7501, "step": 291010 }, { "epoch": 24.19, "learning_rate": 7.762436604495192e-07, "loss": 0.7624, "step": 291020 }, { "epoch": 24.19, "learning_rate": 7.761328049219854e-07, "loss": 0.7642, "step": 291030 }, { "epoch": 24.19, "learning_rate": 7.760219493944517e-07, "loss": 0.7585, "step": 291040 }, { "epoch": 24.19, "learning_rate": 7.759110938669179e-07, "loss": 0.7672, "step": 291050 }, { "epoch": 24.19, "learning_rate": 7.758002383393841e-07, "loss": 0.7117, "step": 291060 }, { "epoch": 24.19, "learning_rate": 7.756893828118503e-07, "loss": 0.7236, "step": 291070 }, { "epoch": 24.19, "learning_rate": 7.755785272843167e-07, "loss": 0.7136, "step": 291080 }, { "epoch": 24.19, "learning_rate": 7.754676717567829e-07, "loss": 0.6982, "step": 291090 }, { "epoch": 24.2, "learning_rate": 7.753568162292492e-07, "loss": 0.7299, "step": 291100 }, { "epoch": 24.2, "learning_rate": 7.752459607017154e-07, "loss": 0.7422, "step": 291110 }, { "epoch": 24.2, "learning_rate": 7.751351051741817e-07, "loss": 0.7363, "step": 291120 }, { "epoch": 24.2, "learning_rate": 7.750242496466479e-07, "loss": 0.7083, "step": 291130 }, { "epoch": 24.2, "learning_rate": 7.749133941191143e-07, "loss": 0.7029, "step": 291140 }, { "epoch": 24.2, "learning_rate": 7.748025385915805e-07, "loss": 0.6993, "step": 291150 }, { "epoch": 24.2, "learning_rate": 7.746916830640468e-07, "loss": 0.7297, "step": 291160 }, { "epoch": 24.2, "learning_rate": 7.74580827536513e-07, "loss": 0.7532, "step": 291170 }, { "epoch": 24.2, "learning_rate": 7.744699720089793e-07, "loss": 0.7208, "step": 291180 }, { "epoch": 24.2, "learning_rate": 7.743591164814455e-07, "loss": 0.7492, "step": 291190 }, { "epoch": 24.2, "learning_rate": 7.742482609539119e-07, "loss": 0.8352, "step": 291200 }, { "epoch": 24.2, "learning_rate": 7.74137405426378e-07, "loss": 0.7767, "step": 291210 }, { "epoch": 24.21, "learning_rate": 7.740265498988443e-07, "loss": 0.7539, "step": 291220 }, { "epoch": 24.21, "learning_rate": 7.739156943713105e-07, "loss": 0.6784, "step": 291230 }, { "epoch": 24.21, "learning_rate": 7.738048388437768e-07, "loss": 0.7332, "step": 291240 }, { "epoch": 24.21, "learning_rate": 7.73693983316243e-07, "loss": 0.7504, "step": 291250 }, { "epoch": 24.21, "learning_rate": 7.735831277887094e-07, "loss": 0.6698, "step": 291260 }, { "epoch": 24.21, "learning_rate": 7.734722722611756e-07, "loss": 0.746, "step": 291270 }, { "epoch": 24.21, "learning_rate": 7.733614167336419e-07, "loss": 0.6615, "step": 291280 }, { "epoch": 24.21, "learning_rate": 7.732505612061081e-07, "loss": 0.7597, "step": 291290 }, { "epoch": 24.21, "learning_rate": 7.731397056785744e-07, "loss": 0.8169, "step": 291300 }, { "epoch": 24.21, "learning_rate": 7.730288501510406e-07, "loss": 0.742, "step": 291310 }, { "epoch": 24.21, "learning_rate": 7.72917994623507e-07, "loss": 0.795, "step": 291320 }, { "epoch": 24.21, "learning_rate": 7.728071390959732e-07, "loss": 0.6791, "step": 291330 }, { "epoch": 24.22, "learning_rate": 7.726962835684395e-07, "loss": 0.7684, "step": 291340 }, { "epoch": 24.22, "learning_rate": 7.725854280409057e-07, "loss": 0.758, "step": 291350 }, { "epoch": 24.22, "learning_rate": 7.724745725133718e-07, "loss": 0.6733, "step": 291360 }, { "epoch": 24.22, "learning_rate": 7.723637169858381e-07, "loss": 0.7078, "step": 291370 }, { "epoch": 24.22, "learning_rate": 7.722528614583044e-07, "loss": 0.7499, "step": 291380 }, { "epoch": 24.22, "learning_rate": 7.721420059307707e-07, "loss": 0.7276, "step": 291390 }, { "epoch": 24.22, "learning_rate": 7.720311504032369e-07, "loss": 0.7933, "step": 291400 }, { "epoch": 24.22, "learning_rate": 7.719202948757032e-07, "loss": 0.6982, "step": 291410 }, { "epoch": 24.22, "learning_rate": 7.718094393481694e-07, "loss": 0.7069, "step": 291420 }, { "epoch": 24.22, "learning_rate": 7.716985838206357e-07, "loss": 0.699, "step": 291430 }, { "epoch": 24.22, "learning_rate": 7.715877282931019e-07, "loss": 0.7177, "step": 291440 }, { "epoch": 24.22, "learning_rate": 7.714768727655683e-07, "loss": 0.7926, "step": 291450 }, { "epoch": 24.23, "learning_rate": 7.713660172380345e-07, "loss": 0.7456, "step": 291460 }, { "epoch": 24.23, "learning_rate": 7.712551617105008e-07, "loss": 0.7659, "step": 291470 }, { "epoch": 24.23, "learning_rate": 7.71144306182967e-07, "loss": 0.7649, "step": 291480 }, { "epoch": 24.23, "learning_rate": 7.710334506554333e-07, "loss": 0.7273, "step": 291490 }, { "epoch": 24.23, "learning_rate": 7.709225951278994e-07, "loss": 0.7409, "step": 291500 }, { "epoch": 24.23, "learning_rate": 7.708117396003658e-07, "loss": 0.7232, "step": 291510 }, { "epoch": 24.23, "learning_rate": 7.70700884072832e-07, "loss": 0.7086, "step": 291520 }, { "epoch": 24.23, "learning_rate": 7.705900285452983e-07, "loss": 0.7822, "step": 291530 }, { "epoch": 24.23, "learning_rate": 7.704791730177645e-07, "loss": 0.7635, "step": 291540 }, { "epoch": 24.23, "learning_rate": 7.703683174902308e-07, "loss": 0.7795, "step": 291550 }, { "epoch": 24.23, "learning_rate": 7.70257461962697e-07, "loss": 0.7214, "step": 291560 }, { "epoch": 24.23, "learning_rate": 7.701466064351634e-07, "loss": 0.7176, "step": 291570 }, { "epoch": 24.24, "learning_rate": 7.700357509076296e-07, "loss": 0.7079, "step": 291580 }, { "epoch": 24.24, "learning_rate": 7.699248953800959e-07, "loss": 0.7271, "step": 291590 }, { "epoch": 24.24, "learning_rate": 7.698140398525621e-07, "loss": 0.755, "step": 291600 }, { "epoch": 24.24, "learning_rate": 7.697142698777817e-07, "loss": 0.8004, "step": 291610 }, { "epoch": 24.24, "learning_rate": 7.69603414350248e-07, "loss": 0.7847, "step": 291620 }, { "epoch": 24.24, "learning_rate": 7.694925588227142e-07, "loss": 0.7274, "step": 291630 }, { "epoch": 24.24, "learning_rate": 7.693817032951805e-07, "loss": 0.7465, "step": 291640 }, { "epoch": 24.24, "learning_rate": 7.692708477676467e-07, "loss": 0.8153, "step": 291650 }, { "epoch": 24.24, "learning_rate": 7.691599922401131e-07, "loss": 0.716, "step": 291660 }, { "epoch": 24.24, "learning_rate": 7.690491367125793e-07, "loss": 0.7241, "step": 291670 }, { "epoch": 24.24, "learning_rate": 7.689382811850456e-07, "loss": 0.7071, "step": 291680 }, { "epoch": 24.24, "learning_rate": 7.688274256575118e-07, "loss": 0.7776, "step": 291690 }, { "epoch": 24.25, "learning_rate": 7.687165701299781e-07, "loss": 0.7589, "step": 291700 }, { "epoch": 24.25, "learning_rate": 7.686057146024443e-07, "loss": 0.6984, "step": 291710 }, { "epoch": 24.25, "learning_rate": 7.684948590749107e-07, "loss": 0.8129, "step": 291720 }, { "epoch": 24.25, "learning_rate": 7.683840035473768e-07, "loss": 0.761, "step": 291730 }, { "epoch": 24.25, "learning_rate": 7.682731480198431e-07, "loss": 0.7612, "step": 291740 }, { "epoch": 24.25, "learning_rate": 7.681622924923093e-07, "loss": 0.7562, "step": 291750 }, { "epoch": 24.25, "learning_rate": 7.680514369647756e-07, "loss": 0.6606, "step": 291760 }, { "epoch": 24.25, "learning_rate": 7.679405814372418e-07, "loss": 0.6786, "step": 291770 }, { "epoch": 24.25, "learning_rate": 7.678297259097082e-07, "loss": 0.7719, "step": 291780 }, { "epoch": 24.25, "learning_rate": 7.677188703821744e-07, "loss": 0.8003, "step": 291790 }, { "epoch": 24.25, "learning_rate": 7.676080148546407e-07, "loss": 0.7408, "step": 291800 }, { "epoch": 24.25, "learning_rate": 7.674971593271069e-07, "loss": 0.785, "step": 291810 }, { "epoch": 24.26, "learning_rate": 7.673863037995732e-07, "loss": 0.752, "step": 291820 }, { "epoch": 24.26, "learning_rate": 7.672754482720394e-07, "loss": 0.7739, "step": 291830 }, { "epoch": 24.26, "learning_rate": 7.671645927445058e-07, "loss": 0.7422, "step": 291840 }, { "epoch": 24.26, "learning_rate": 7.67053737216972e-07, "loss": 0.7661, "step": 291850 }, { "epoch": 24.26, "learning_rate": 7.669428816894383e-07, "loss": 0.8052, "step": 291860 }, { "epoch": 24.26, "learning_rate": 7.668320261619045e-07, "loss": 0.66, "step": 291870 }, { "epoch": 24.26, "learning_rate": 7.667211706343706e-07, "loss": 0.7135, "step": 291880 }, { "epoch": 24.26, "learning_rate": 7.666103151068369e-07, "loss": 0.775, "step": 291890 }, { "epoch": 24.26, "learning_rate": 7.664994595793032e-07, "loss": 0.7514, "step": 291900 }, { "epoch": 24.26, "learning_rate": 7.663886040517695e-07, "loss": 0.7582, "step": 291910 }, { "epoch": 24.26, "learning_rate": 7.662777485242357e-07, "loss": 0.751, "step": 291920 }, { "epoch": 24.26, "learning_rate": 7.66166892996702e-07, "loss": 0.6632, "step": 291930 }, { "epoch": 24.27, "learning_rate": 7.660560374691682e-07, "loss": 0.7352, "step": 291940 }, { "epoch": 24.27, "learning_rate": 7.659451819416345e-07, "loss": 0.7389, "step": 291950 }, { "epoch": 24.27, "learning_rate": 7.658343264141008e-07, "loss": 0.7594, "step": 291960 }, { "epoch": 24.27, "learning_rate": 7.657234708865671e-07, "loss": 0.7722, "step": 291970 }, { "epoch": 24.27, "learning_rate": 7.656126153590333e-07, "loss": 0.7334, "step": 291980 }, { "epoch": 24.27, "learning_rate": 7.655017598314996e-07, "loss": 0.684, "step": 291990 }, { "epoch": 24.27, "learning_rate": 7.653909043039658e-07, "loss": 0.7855, "step": 292000 }, { "epoch": 24.27, "learning_rate": 7.652800487764321e-07, "loss": 0.8116, "step": 292010 }, { "epoch": 24.27, "learning_rate": 7.651691932488984e-07, "loss": 0.7601, "step": 292020 }, { "epoch": 24.27, "learning_rate": 7.650583377213646e-07, "loss": 0.6805, "step": 292030 }, { "epoch": 24.27, "learning_rate": 7.649474821938308e-07, "loss": 0.7004, "step": 292040 }, { "epoch": 24.27, "learning_rate": 7.648366266662971e-07, "loss": 0.7212, "step": 292050 }, { "epoch": 24.28, "learning_rate": 7.647257711387633e-07, "loss": 0.6996, "step": 292060 }, { "epoch": 24.28, "learning_rate": 7.646149156112296e-07, "loss": 0.7137, "step": 292070 }, { "epoch": 24.28, "learning_rate": 7.645040600836958e-07, "loss": 0.7457, "step": 292080 }, { "epoch": 24.28, "learning_rate": 7.643932045561622e-07, "loss": 0.7196, "step": 292090 }, { "epoch": 24.28, "learning_rate": 7.642823490286284e-07, "loss": 0.7182, "step": 292100 }, { "epoch": 24.28, "learning_rate": 7.641714935010947e-07, "loss": 0.7782, "step": 292110 }, { "epoch": 24.28, "learning_rate": 7.640606379735609e-07, "loss": 0.7007, "step": 292120 }, { "epoch": 24.28, "learning_rate": 7.639497824460272e-07, "loss": 0.7722, "step": 292130 }, { "epoch": 24.28, "learning_rate": 7.638389269184934e-07, "loss": 0.7646, "step": 292140 }, { "epoch": 24.28, "learning_rate": 7.637280713909598e-07, "loss": 0.7988, "step": 292150 }, { "epoch": 24.28, "learning_rate": 7.63617215863426e-07, "loss": 0.7481, "step": 292160 }, { "epoch": 24.28, "learning_rate": 7.635063603358923e-07, "loss": 0.7106, "step": 292170 }, { "epoch": 24.29, "learning_rate": 7.633955048083584e-07, "loss": 0.7294, "step": 292180 }, { "epoch": 24.29, "learning_rate": 7.632846492808247e-07, "loss": 0.7098, "step": 292190 }, { "epoch": 24.29, "learning_rate": 7.631737937532909e-07, "loss": 0.7504, "step": 292200 }, { "epoch": 24.29, "learning_rate": 7.630629382257573e-07, "loss": 0.7386, "step": 292210 }, { "epoch": 24.29, "learning_rate": 7.629520826982235e-07, "loss": 0.7738, "step": 292220 }, { "epoch": 24.29, "learning_rate": 7.628412271706898e-07, "loss": 0.7468, "step": 292230 }, { "epoch": 24.29, "learning_rate": 7.62730371643156e-07, "loss": 0.8127, "step": 292240 }, { "epoch": 24.29, "learning_rate": 7.626195161156223e-07, "loss": 0.7589, "step": 292250 }, { "epoch": 24.29, "learning_rate": 7.625086605880885e-07, "loss": 0.7096, "step": 292260 }, { "epoch": 24.29, "learning_rate": 7.623978050605549e-07, "loss": 0.8068, "step": 292270 }, { "epoch": 24.29, "learning_rate": 7.622869495330211e-07, "loss": 0.758, "step": 292280 }, { "epoch": 24.29, "learning_rate": 7.621760940054874e-07, "loss": 0.7432, "step": 292290 }, { "epoch": 24.3, "learning_rate": 7.620652384779536e-07, "loss": 0.7262, "step": 292300 }, { "epoch": 24.3, "learning_rate": 7.619543829504198e-07, "loss": 0.724, "step": 292310 }, { "epoch": 24.3, "learning_rate": 7.61843527422886e-07, "loss": 0.7058, "step": 292320 }, { "epoch": 24.3, "learning_rate": 7.617326718953523e-07, "loss": 0.8212, "step": 292330 }, { "epoch": 24.3, "learning_rate": 7.616218163678186e-07, "loss": 0.6788, "step": 292340 }, { "epoch": 24.3, "learning_rate": 7.615109608402848e-07, "loss": 0.7984, "step": 292350 }, { "epoch": 24.3, "learning_rate": 7.614001053127511e-07, "loss": 0.7455, "step": 292360 }, { "epoch": 24.3, "learning_rate": 7.612892497852173e-07, "loss": 0.7923, "step": 292370 }, { "epoch": 24.3, "learning_rate": 7.611783942576836e-07, "loss": 0.8231, "step": 292380 }, { "epoch": 24.3, "learning_rate": 7.610675387301499e-07, "loss": 0.7498, "step": 292390 }, { "epoch": 24.3, "learning_rate": 7.609566832026162e-07, "loss": 0.7397, "step": 292400 }, { "epoch": 24.3, "learning_rate": 7.608458276750824e-07, "loss": 0.6836, "step": 292410 }, { "epoch": 24.31, "learning_rate": 7.607349721475487e-07, "loss": 0.7452, "step": 292420 }, { "epoch": 24.31, "learning_rate": 7.606241166200149e-07, "loss": 0.7373, "step": 292430 }, { "epoch": 24.31, "learning_rate": 7.605132610924812e-07, "loss": 0.7019, "step": 292440 }, { "epoch": 24.31, "learning_rate": 7.604024055649475e-07, "loss": 0.7225, "step": 292450 }, { "epoch": 24.31, "learning_rate": 7.602915500374138e-07, "loss": 0.7197, "step": 292460 }, { "epoch": 24.31, "learning_rate": 7.6018069450988e-07, "loss": 0.7768, "step": 292470 }, { "epoch": 24.31, "learning_rate": 7.600698389823462e-07, "loss": 0.7491, "step": 292480 }, { "epoch": 24.31, "learning_rate": 7.599589834548124e-07, "loss": 0.7563, "step": 292490 }, { "epoch": 24.31, "learning_rate": 7.598481279272787e-07, "loss": 0.7426, "step": 292500 }, { "epoch": 24.31, "learning_rate": 7.597372723997449e-07, "loss": 0.7553, "step": 292510 }, { "epoch": 24.31, "learning_rate": 7.596264168722113e-07, "loss": 0.7326, "step": 292520 }, { "epoch": 24.31, "learning_rate": 7.595155613446775e-07, "loss": 0.7154, "step": 292530 }, { "epoch": 24.32, "learning_rate": 7.594047058171438e-07, "loss": 0.7862, "step": 292540 }, { "epoch": 24.32, "learning_rate": 7.5929385028961e-07, "loss": 0.741, "step": 292550 }, { "epoch": 24.32, "learning_rate": 7.591829947620763e-07, "loss": 0.7097, "step": 292560 }, { "epoch": 24.32, "learning_rate": 7.590721392345425e-07, "loss": 0.7032, "step": 292570 }, { "epoch": 24.32, "learning_rate": 7.589612837070089e-07, "loss": 0.6682, "step": 292580 }, { "epoch": 24.32, "learning_rate": 7.588504281794751e-07, "loss": 0.6868, "step": 292590 }, { "epoch": 24.32, "learning_rate": 7.587395726519414e-07, "loss": 0.7599, "step": 292600 }, { "epoch": 24.32, "learning_rate": 7.586287171244076e-07, "loss": 0.7982, "step": 292610 }, { "epoch": 24.32, "learning_rate": 7.585178615968739e-07, "loss": 0.7593, "step": 292620 }, { "epoch": 24.32, "learning_rate": 7.5840700606934e-07, "loss": 0.7068, "step": 292630 }, { "epoch": 24.32, "learning_rate": 7.582961505418064e-07, "loss": 0.7322, "step": 292640 }, { "epoch": 24.32, "learning_rate": 7.581852950142726e-07, "loss": 0.7364, "step": 292650 }, { "epoch": 24.33, "learning_rate": 7.580744394867389e-07, "loss": 0.7897, "step": 292660 }, { "epoch": 24.33, "learning_rate": 7.579635839592051e-07, "loss": 0.7365, "step": 292670 }, { "epoch": 24.33, "learning_rate": 7.578527284316714e-07, "loss": 0.7059, "step": 292680 }, { "epoch": 24.33, "learning_rate": 7.577418729041376e-07, "loss": 0.7046, "step": 292690 }, { "epoch": 24.33, "learning_rate": 7.57631017376604e-07, "loss": 0.7424, "step": 292700 }, { "epoch": 24.33, "learning_rate": 7.575201618490702e-07, "loss": 0.7809, "step": 292710 }, { "epoch": 24.33, "learning_rate": 7.574093063215364e-07, "loss": 0.6749, "step": 292720 }, { "epoch": 24.33, "learning_rate": 7.572984507940027e-07, "loss": 0.8044, "step": 292730 }, { "epoch": 24.33, "learning_rate": 7.571875952664689e-07, "loss": 0.7891, "step": 292740 }, { "epoch": 24.33, "learning_rate": 7.570767397389352e-07, "loss": 0.7269, "step": 292750 }, { "epoch": 24.33, "learning_rate": 7.569658842114015e-07, "loss": 0.7216, "step": 292760 }, { "epoch": 24.33, "learning_rate": 7.568550286838678e-07, "loss": 0.75, "step": 292770 }, { "epoch": 24.34, "learning_rate": 7.567441731563339e-07, "loss": 0.7734, "step": 292780 }, { "epoch": 24.34, "learning_rate": 7.566333176288002e-07, "loss": 0.7144, "step": 292790 }, { "epoch": 24.34, "learning_rate": 7.565224621012664e-07, "loss": 0.7701, "step": 292800 }, { "epoch": 24.34, "learning_rate": 7.564116065737327e-07, "loss": 0.7155, "step": 292810 }, { "epoch": 24.34, "learning_rate": 7.56300751046199e-07, "loss": 0.7597, "step": 292820 }, { "epoch": 24.34, "learning_rate": 7.561898955186653e-07, "loss": 0.7179, "step": 292830 }, { "epoch": 24.34, "learning_rate": 7.560790399911315e-07, "loss": 0.7787, "step": 292840 }, { "epoch": 24.34, "learning_rate": 7.559681844635978e-07, "loss": 0.8166, "step": 292850 }, { "epoch": 24.34, "learning_rate": 7.55857328936064e-07, "loss": 0.725, "step": 292860 }, { "epoch": 24.34, "learning_rate": 7.557464734085303e-07, "loss": 0.7803, "step": 292870 }, { "epoch": 24.34, "learning_rate": 7.556356178809966e-07, "loss": 0.6884, "step": 292880 }, { "epoch": 24.34, "learning_rate": 7.555247623534629e-07, "loss": 0.7262, "step": 292890 }, { "epoch": 24.35, "learning_rate": 7.554139068259291e-07, "loss": 0.828, "step": 292900 }, { "epoch": 24.35, "learning_rate": 7.553030512983954e-07, "loss": 0.7368, "step": 292910 }, { "epoch": 24.35, "learning_rate": 7.551921957708615e-07, "loss": 0.6868, "step": 292920 }, { "epoch": 24.35, "learning_rate": 7.550813402433278e-07, "loss": 0.7516, "step": 292930 }, { "epoch": 24.35, "learning_rate": 7.54970484715794e-07, "loss": 0.7307, "step": 292940 }, { "epoch": 24.35, "learning_rate": 7.548596291882604e-07, "loss": 0.8298, "step": 292950 }, { "epoch": 24.35, "learning_rate": 7.547487736607266e-07, "loss": 0.6949, "step": 292960 }, { "epoch": 24.35, "learning_rate": 7.546379181331929e-07, "loss": 0.7163, "step": 292970 }, { "epoch": 24.35, "learning_rate": 7.545270626056591e-07, "loss": 0.7981, "step": 292980 }, { "epoch": 24.35, "learning_rate": 7.544162070781254e-07, "loss": 0.6871, "step": 292990 }, { "epoch": 24.35, "learning_rate": 7.543053515505916e-07, "loss": 0.7731, "step": 293000 }, { "epoch": 24.35, "learning_rate": 7.54194496023058e-07, "loss": 0.7208, "step": 293010 }, { "epoch": 24.36, "learning_rate": 7.540836404955242e-07, "loss": 0.7797, "step": 293020 }, { "epoch": 24.36, "learning_rate": 7.539727849679905e-07, "loss": 0.6842, "step": 293030 }, { "epoch": 24.36, "learning_rate": 7.538619294404567e-07, "loss": 0.7469, "step": 293040 }, { "epoch": 24.36, "learning_rate": 7.53751073912923e-07, "loss": 0.7616, "step": 293050 }, { "epoch": 24.36, "learning_rate": 7.536402183853892e-07, "loss": 0.7615, "step": 293060 }, { "epoch": 24.36, "learning_rate": 7.535293628578556e-07, "loss": 0.7193, "step": 293070 }, { "epoch": 24.36, "learning_rate": 7.534185073303217e-07, "loss": 0.7651, "step": 293080 }, { "epoch": 24.36, "learning_rate": 7.53307651802788e-07, "loss": 0.7758, "step": 293090 }, { "epoch": 24.36, "learning_rate": 7.531967962752542e-07, "loss": 0.7668, "step": 293100 }, { "epoch": 24.36, "learning_rate": 7.530859407477205e-07, "loss": 0.7398, "step": 293110 }, { "epoch": 24.36, "learning_rate": 7.529750852201867e-07, "loss": 0.7454, "step": 293120 }, { "epoch": 24.36, "learning_rate": 7.528642296926531e-07, "loss": 0.7788, "step": 293130 }, { "epoch": 24.37, "learning_rate": 7.527533741651193e-07, "loss": 0.7778, "step": 293140 }, { "epoch": 24.37, "learning_rate": 7.526425186375855e-07, "loss": 0.8199, "step": 293150 }, { "epoch": 24.37, "learning_rate": 7.525316631100518e-07, "loss": 0.7494, "step": 293160 }, { "epoch": 24.37, "learning_rate": 7.52420807582518e-07, "loss": 0.7395, "step": 293170 }, { "epoch": 24.37, "learning_rate": 7.523099520549843e-07, "loss": 0.76, "step": 293180 }, { "epoch": 24.37, "learning_rate": 7.521990965274506e-07, "loss": 0.714, "step": 293190 }, { "epoch": 24.37, "learning_rate": 7.520882409999169e-07, "loss": 0.7417, "step": 293200 }, { "epoch": 24.37, "learning_rate": 7.519773854723831e-07, "loss": 0.7905, "step": 293210 }, { "epoch": 24.37, "learning_rate": 7.518665299448493e-07, "loss": 0.7741, "step": 293220 }, { "epoch": 24.37, "learning_rate": 7.517556744173155e-07, "loss": 0.7627, "step": 293230 }, { "epoch": 24.37, "learning_rate": 7.516448188897818e-07, "loss": 0.6796, "step": 293240 }, { "epoch": 24.37, "learning_rate": 7.515339633622481e-07, "loss": 0.7803, "step": 293250 }, { "epoch": 24.38, "learning_rate": 7.514231078347144e-07, "loss": 0.717, "step": 293260 }, { "epoch": 24.38, "learning_rate": 7.513122523071806e-07, "loss": 0.7567, "step": 293270 }, { "epoch": 24.38, "learning_rate": 7.512013967796469e-07, "loss": 0.7491, "step": 293280 }, { "epoch": 24.38, "learning_rate": 7.510905412521131e-07, "loss": 0.7413, "step": 293290 }, { "epoch": 24.38, "learning_rate": 7.509796857245794e-07, "loss": 0.7642, "step": 293300 }, { "epoch": 24.38, "learning_rate": 7.508688301970456e-07, "loss": 0.7428, "step": 293310 }, { "epoch": 24.38, "learning_rate": 7.50757974669512e-07, "loss": 0.7507, "step": 293320 }, { "epoch": 24.38, "learning_rate": 7.506471191419782e-07, "loss": 0.7412, "step": 293330 }, { "epoch": 24.38, "learning_rate": 7.505362636144445e-07, "loss": 0.722, "step": 293340 }, { "epoch": 24.38, "learning_rate": 7.504254080869107e-07, "loss": 0.7222, "step": 293350 }, { "epoch": 24.38, "learning_rate": 7.50314552559377e-07, "loss": 0.7863, "step": 293360 }, { "epoch": 24.38, "learning_rate": 7.502036970318431e-07, "loss": 0.6871, "step": 293370 }, { "epoch": 24.39, "learning_rate": 7.500928415043095e-07, "loss": 0.737, "step": 293380 }, { "epoch": 24.39, "learning_rate": 7.499819859767757e-07, "loss": 0.7022, "step": 293390 }, { "epoch": 24.39, "learning_rate": 7.49871130449242e-07, "loss": 0.7935, "step": 293400 }, { "epoch": 24.39, "learning_rate": 7.497602749217082e-07, "loss": 0.7464, "step": 293410 }, { "epoch": 24.39, "learning_rate": 7.496494193941745e-07, "loss": 0.7146, "step": 293420 }, { "epoch": 24.39, "learning_rate": 7.495385638666407e-07, "loss": 0.7348, "step": 293430 }, { "epoch": 24.39, "learning_rate": 7.494277083391071e-07, "loss": 0.7337, "step": 293440 }, { "epoch": 24.39, "learning_rate": 7.493168528115733e-07, "loss": 0.7464, "step": 293450 }, { "epoch": 24.39, "learning_rate": 7.492059972840396e-07, "loss": 0.7219, "step": 293460 }, { "epoch": 24.39, "learning_rate": 7.490951417565058e-07, "loss": 0.7067, "step": 293470 }, { "epoch": 24.39, "learning_rate": 7.489842862289721e-07, "loss": 0.7559, "step": 293480 }, { "epoch": 24.39, "learning_rate": 7.488734307014383e-07, "loss": 0.7222, "step": 293490 }, { "epoch": 24.4, "learning_rate": 7.487625751739047e-07, "loss": 0.7871, "step": 293500 }, { "epoch": 24.4, "learning_rate": 7.486517196463709e-07, "loss": 0.7631, "step": 293510 }, { "epoch": 24.4, "learning_rate": 7.485408641188371e-07, "loss": 0.7602, "step": 293520 }, { "epoch": 24.4, "learning_rate": 7.484300085913033e-07, "loss": 0.7593, "step": 293530 }, { "epoch": 24.4, "learning_rate": 7.483191530637696e-07, "loss": 0.7411, "step": 293540 }, { "epoch": 24.4, "learning_rate": 7.482082975362358e-07, "loss": 0.7405, "step": 293550 }, { "epoch": 24.4, "learning_rate": 7.480974420087022e-07, "loss": 0.7686, "step": 293560 }, { "epoch": 24.4, "learning_rate": 7.479865864811684e-07, "loss": 0.7705, "step": 293570 }, { "epoch": 24.4, "learning_rate": 7.478757309536346e-07, "loss": 0.7687, "step": 293580 }, { "epoch": 24.4, "learning_rate": 7.477648754261009e-07, "loss": 0.7181, "step": 293590 }, { "epoch": 24.4, "learning_rate": 7.476540198985671e-07, "loss": 0.7702, "step": 293600 }, { "epoch": 24.4, "learning_rate": 7.475542499237868e-07, "loss": 0.7976, "step": 293610 }, { "epoch": 24.41, "learning_rate": 7.47443394396253e-07, "loss": 0.7271, "step": 293620 }, { "epoch": 24.41, "learning_rate": 7.473325388687193e-07, "loss": 0.7586, "step": 293630 }, { "epoch": 24.41, "learning_rate": 7.472216833411855e-07, "loss": 0.7676, "step": 293640 }, { "epoch": 24.41, "learning_rate": 7.471108278136519e-07, "loss": 0.7589, "step": 293650 }, { "epoch": 24.41, "learning_rate": 7.469999722861181e-07, "loss": 0.813, "step": 293660 }, { "epoch": 24.41, "learning_rate": 7.468891167585844e-07, "loss": 0.768, "step": 293670 }, { "epoch": 24.41, "learning_rate": 7.467782612310506e-07, "loss": 0.7031, "step": 293680 }, { "epoch": 24.41, "learning_rate": 7.466674057035168e-07, "loss": 0.7258, "step": 293690 }, { "epoch": 24.41, "learning_rate": 7.465565501759831e-07, "loss": 0.7599, "step": 293700 }, { "epoch": 24.41, "learning_rate": 7.464456946484494e-07, "loss": 0.7211, "step": 293710 }, { "epoch": 24.41, "learning_rate": 7.463348391209157e-07, "loss": 0.7124, "step": 293720 }, { "epoch": 24.41, "learning_rate": 7.462239835933819e-07, "loss": 0.6986, "step": 293730 }, { "epoch": 24.42, "learning_rate": 7.461131280658481e-07, "loss": 0.7495, "step": 293740 }, { "epoch": 24.42, "learning_rate": 7.460022725383143e-07, "loss": 0.7831, "step": 293750 }, { "epoch": 24.42, "learning_rate": 7.458914170107806e-07, "loss": 0.7977, "step": 293760 }, { "epoch": 24.42, "learning_rate": 7.457805614832469e-07, "loss": 0.7384, "step": 293770 }, { "epoch": 24.42, "learning_rate": 7.456697059557132e-07, "loss": 0.7376, "step": 293780 }, { "epoch": 24.42, "learning_rate": 7.455588504281794e-07, "loss": 0.6994, "step": 293790 }, { "epoch": 24.42, "learning_rate": 7.454479949006457e-07, "loss": 0.7567, "step": 293800 }, { "epoch": 24.42, "learning_rate": 7.453371393731119e-07, "loss": 0.7479, "step": 293810 }, { "epoch": 24.42, "learning_rate": 7.452262838455782e-07, "loss": 0.7054, "step": 293820 }, { "epoch": 24.42, "learning_rate": 7.451154283180445e-07, "loss": 0.775, "step": 293830 }, { "epoch": 24.42, "learning_rate": 7.450045727905108e-07, "loss": 0.7333, "step": 293840 }, { "epoch": 24.42, "learning_rate": 7.44893717262977e-07, "loss": 0.7166, "step": 293850 }, { "epoch": 24.43, "learning_rate": 7.447828617354433e-07, "loss": 0.7544, "step": 293860 }, { "epoch": 24.43, "learning_rate": 7.446720062079095e-07, "loss": 0.6749, "step": 293870 }, { "epoch": 24.43, "learning_rate": 7.445611506803758e-07, "loss": 0.6766, "step": 293880 }, { "epoch": 24.43, "learning_rate": 7.44450295152842e-07, "loss": 0.6801, "step": 293890 }, { "epoch": 24.43, "learning_rate": 7.443394396253083e-07, "loss": 0.7272, "step": 293900 }, { "epoch": 24.43, "learning_rate": 7.442285840977745e-07, "loss": 0.7137, "step": 293910 }, { "epoch": 24.43, "learning_rate": 7.441177285702408e-07, "loss": 0.7447, "step": 293920 }, { "epoch": 24.43, "learning_rate": 7.44006873042707e-07, "loss": 0.7237, "step": 293930 }, { "epoch": 24.43, "learning_rate": 7.438960175151733e-07, "loss": 0.7455, "step": 293940 }, { "epoch": 24.43, "learning_rate": 7.437851619876395e-07, "loss": 0.7643, "step": 293950 }, { "epoch": 24.43, "learning_rate": 7.436743064601059e-07, "loss": 0.7667, "step": 293960 }, { "epoch": 24.43, "learning_rate": 7.435634509325721e-07, "loss": 0.7592, "step": 293970 }, { "epoch": 24.44, "learning_rate": 7.434525954050384e-07, "loss": 0.7423, "step": 293980 }, { "epoch": 24.44, "learning_rate": 7.433417398775046e-07, "loss": 0.7686, "step": 293990 }, { "epoch": 24.44, "learning_rate": 7.432308843499709e-07, "loss": 0.7456, "step": 294000 }, { "epoch": 24.44, "learning_rate": 7.431200288224371e-07, "loss": 0.791, "step": 294010 }, { "epoch": 24.44, "learning_rate": 7.430091732949035e-07, "loss": 0.7495, "step": 294020 }, { "epoch": 24.44, "learning_rate": 7.428983177673697e-07, "loss": 0.7607, "step": 294030 }, { "epoch": 24.44, "learning_rate": 7.42787462239836e-07, "loss": 0.7287, "step": 294040 }, { "epoch": 24.44, "learning_rate": 7.426766067123021e-07, "loss": 0.7803, "step": 294050 }, { "epoch": 24.44, "learning_rate": 7.425657511847684e-07, "loss": 0.7719, "step": 294060 }, { "epoch": 24.44, "learning_rate": 7.424548956572346e-07, "loss": 0.7523, "step": 294070 }, { "epoch": 24.44, "learning_rate": 7.42344040129701e-07, "loss": 0.7798, "step": 294080 }, { "epoch": 24.44, "learning_rate": 7.422331846021672e-07, "loss": 0.7695, "step": 294090 }, { "epoch": 24.45, "learning_rate": 7.421223290746334e-07, "loss": 0.7277, "step": 294100 }, { "epoch": 24.45, "learning_rate": 7.420114735470997e-07, "loss": 0.7416, "step": 294110 }, { "epoch": 24.45, "learning_rate": 7.419006180195659e-07, "loss": 0.7537, "step": 294120 }, { "epoch": 24.45, "learning_rate": 7.417897624920322e-07, "loss": 0.7353, "step": 294130 }, { "epoch": 24.45, "learning_rate": 7.416789069644985e-07, "loss": 0.7735, "step": 294140 }, { "epoch": 24.45, "learning_rate": 7.415680514369648e-07, "loss": 0.748, "step": 294150 }, { "epoch": 24.45, "learning_rate": 7.41457195909431e-07, "loss": 0.7241, "step": 294160 }, { "epoch": 24.45, "learning_rate": 7.413463403818973e-07, "loss": 0.7154, "step": 294170 }, { "epoch": 24.45, "learning_rate": 7.412354848543635e-07, "loss": 0.7567, "step": 294180 }, { "epoch": 24.45, "learning_rate": 7.411246293268297e-07, "loss": 0.7628, "step": 294190 }, { "epoch": 24.45, "learning_rate": 7.41013773799296e-07, "loss": 0.7513, "step": 294200 }, { "epoch": 24.45, "learning_rate": 7.409029182717623e-07, "loss": 0.6919, "step": 294210 }, { "epoch": 24.46, "learning_rate": 7.407920627442285e-07, "loss": 0.6933, "step": 294220 }, { "epoch": 24.46, "learning_rate": 7.406812072166948e-07, "loss": 0.7418, "step": 294230 }, { "epoch": 24.46, "learning_rate": 7.40570351689161e-07, "loss": 0.7577, "step": 294240 }, { "epoch": 24.46, "learning_rate": 7.404594961616273e-07, "loss": 0.7569, "step": 294250 }, { "epoch": 24.46, "learning_rate": 7.403486406340936e-07, "loss": 0.7458, "step": 294260 }, { "epoch": 24.46, "learning_rate": 7.402377851065599e-07, "loss": 0.7346, "step": 294270 }, { "epoch": 24.46, "learning_rate": 7.401269295790261e-07, "loss": 0.7253, "step": 294280 }, { "epoch": 24.46, "learning_rate": 7.400160740514924e-07, "loss": 0.7242, "step": 294290 }, { "epoch": 24.46, "learning_rate": 7.399052185239586e-07, "loss": 0.7845, "step": 294300 }, { "epoch": 24.46, "learning_rate": 7.397943629964249e-07, "loss": 0.7664, "step": 294310 }, { "epoch": 24.46, "learning_rate": 7.396835074688912e-07, "loss": 0.7369, "step": 294320 }, { "epoch": 24.46, "learning_rate": 7.395726519413575e-07, "loss": 0.7604, "step": 294330 }, { "epoch": 24.47, "learning_rate": 7.394617964138236e-07, "loss": 0.7552, "step": 294340 }, { "epoch": 24.47, "learning_rate": 7.393509408862899e-07, "loss": 0.771, "step": 294350 }, { "epoch": 24.47, "learning_rate": 7.392400853587561e-07, "loss": 0.752, "step": 294360 }, { "epoch": 24.47, "learning_rate": 7.391292298312224e-07, "loss": 0.7368, "step": 294370 }, { "epoch": 24.47, "learning_rate": 7.390183743036886e-07, "loss": 0.7389, "step": 294380 }, { "epoch": 24.47, "learning_rate": 7.38907518776155e-07, "loss": 0.7458, "step": 294390 }, { "epoch": 24.47, "learning_rate": 7.387966632486212e-07, "loss": 0.7563, "step": 294400 }, { "epoch": 24.47, "learning_rate": 7.386858077210875e-07, "loss": 0.7454, "step": 294410 }, { "epoch": 24.47, "learning_rate": 7.385749521935537e-07, "loss": 0.7458, "step": 294420 }, { "epoch": 24.47, "learning_rate": 7.3846409666602e-07, "loss": 0.7545, "step": 294430 }, { "epoch": 24.47, "learning_rate": 7.383532411384862e-07, "loss": 0.732, "step": 294440 }, { "epoch": 24.47, "learning_rate": 7.382423856109526e-07, "loss": 0.8067, "step": 294450 }, { "epoch": 24.48, "learning_rate": 7.381315300834188e-07, "loss": 0.7272, "step": 294460 }, { "epoch": 24.48, "learning_rate": 7.380206745558851e-07, "loss": 0.7671, "step": 294470 }, { "epoch": 24.48, "learning_rate": 7.379098190283513e-07, "loss": 0.7439, "step": 294480 }, { "epoch": 24.48, "learning_rate": 7.377989635008175e-07, "loss": 0.7126, "step": 294490 }, { "epoch": 24.48, "learning_rate": 7.376881079732837e-07, "loss": 0.7187, "step": 294500 }, { "epoch": 24.48, "learning_rate": 7.375772524457501e-07, "loss": 0.7588, "step": 294510 }, { "epoch": 24.48, "learning_rate": 7.374663969182163e-07, "loss": 0.6778, "step": 294520 }, { "epoch": 24.48, "learning_rate": 7.373555413906825e-07, "loss": 0.7484, "step": 294530 }, { "epoch": 24.48, "learning_rate": 7.372446858631488e-07, "loss": 0.6597, "step": 294540 }, { "epoch": 24.48, "learning_rate": 7.37133830335615e-07, "loss": 0.8145, "step": 294550 }, { "epoch": 24.48, "learning_rate": 7.370229748080813e-07, "loss": 0.718, "step": 294560 }, { "epoch": 24.48, "learning_rate": 7.369121192805476e-07, "loss": 0.7748, "step": 294570 }, { "epoch": 24.49, "learning_rate": 7.368012637530139e-07, "loss": 0.8508, "step": 294580 }, { "epoch": 24.49, "learning_rate": 7.366904082254801e-07, "loss": 0.7129, "step": 294590 }, { "epoch": 24.49, "learning_rate": 7.365795526979464e-07, "loss": 0.8091, "step": 294600 }, { "epoch": 24.49, "learning_rate": 7.364686971704126e-07, "loss": 0.7626, "step": 294610 }, { "epoch": 24.49, "learning_rate": 7.363578416428789e-07, "loss": 0.7595, "step": 294620 }, { "epoch": 24.49, "learning_rate": 7.362469861153452e-07, "loss": 0.7399, "step": 294630 }, { "epoch": 24.49, "learning_rate": 7.361361305878114e-07, "loss": 0.7252, "step": 294640 }, { "epoch": 24.49, "learning_rate": 7.360252750602776e-07, "loss": 0.7788, "step": 294650 }, { "epoch": 24.49, "learning_rate": 7.359144195327439e-07, "loss": 0.784, "step": 294660 }, { "epoch": 24.49, "learning_rate": 7.358035640052101e-07, "loss": 0.7796, "step": 294670 }, { "epoch": 24.49, "learning_rate": 7.356927084776764e-07, "loss": 0.6792, "step": 294680 }, { "epoch": 24.49, "learning_rate": 7.355818529501427e-07, "loss": 0.811, "step": 294690 }, { "epoch": 24.5, "learning_rate": 7.35470997422609e-07, "loss": 0.7884, "step": 294700 }, { "epoch": 24.5, "learning_rate": 7.353601418950752e-07, "loss": 0.7793, "step": 294710 }, { "epoch": 24.5, "learning_rate": 7.352492863675415e-07, "loss": 0.7563, "step": 294720 }, { "epoch": 24.5, "learning_rate": 7.351384308400077e-07, "loss": 0.7218, "step": 294730 }, { "epoch": 24.5, "learning_rate": 7.35027575312474e-07, "loss": 0.7532, "step": 294740 }, { "epoch": 24.5, "learning_rate": 7.349167197849403e-07, "loss": 0.7302, "step": 294750 }, { "epoch": 24.5, "learning_rate": 7.348169498101598e-07, "loss": 0.7704, "step": 294760 }, { "epoch": 24.5, "learning_rate": 7.347060942826261e-07, "loss": 0.7391, "step": 294770 }, { "epoch": 24.5, "learning_rate": 7.345952387550924e-07, "loss": 0.7032, "step": 294780 }, { "epoch": 24.5, "learning_rate": 7.344843832275587e-07, "loss": 0.7662, "step": 294790 }, { "epoch": 24.5, "learning_rate": 7.343735277000249e-07, "loss": 0.8136, "step": 294800 }, { "epoch": 24.5, "learning_rate": 7.342626721724912e-07, "loss": 0.7464, "step": 294810 }, { "epoch": 24.51, "learning_rate": 7.341518166449574e-07, "loss": 0.7643, "step": 294820 }, { "epoch": 24.51, "learning_rate": 7.340409611174237e-07, "loss": 0.7565, "step": 294830 }, { "epoch": 24.51, "learning_rate": 7.3393010558989e-07, "loss": 0.7042, "step": 294840 }, { "epoch": 24.51, "learning_rate": 7.338192500623563e-07, "loss": 0.815, "step": 294850 }, { "epoch": 24.51, "learning_rate": 7.337083945348224e-07, "loss": 0.747, "step": 294860 }, { "epoch": 24.51, "learning_rate": 7.335975390072887e-07, "loss": 0.7132, "step": 294870 }, { "epoch": 24.51, "learning_rate": 7.334866834797549e-07, "loss": 0.762, "step": 294880 }, { "epoch": 24.51, "learning_rate": 7.333758279522212e-07, "loss": 0.6851, "step": 294890 }, { "epoch": 24.51, "learning_rate": 7.332649724246875e-07, "loss": 0.7791, "step": 294900 }, { "epoch": 24.51, "learning_rate": 7.331541168971538e-07, "loss": 0.7314, "step": 294910 }, { "epoch": 24.51, "learning_rate": 7.3304326136962e-07, "loss": 0.7021, "step": 294920 }, { "epoch": 24.51, "learning_rate": 7.329324058420863e-07, "loss": 0.7201, "step": 294930 }, { "epoch": 24.52, "learning_rate": 7.328215503145525e-07, "loss": 0.7597, "step": 294940 }, { "epoch": 24.52, "learning_rate": 7.327106947870188e-07, "loss": 0.7364, "step": 294950 }, { "epoch": 24.52, "learning_rate": 7.325998392594851e-07, "loss": 0.7712, "step": 294960 }, { "epoch": 24.52, "learning_rate": 7.324889837319514e-07, "loss": 0.7793, "step": 294970 }, { "epoch": 24.52, "learning_rate": 7.323781282044176e-07, "loss": 0.7429, "step": 294980 }, { "epoch": 24.52, "learning_rate": 7.322672726768839e-07, "loss": 0.6886, "step": 294990 }, { "epoch": 24.52, "learning_rate": 7.3215641714935e-07, "loss": 0.7894, "step": 295000 }, { "epoch": 24.52, "learning_rate": 7.320455616218163e-07, "loss": 0.7348, "step": 295010 }, { "epoch": 24.52, "learning_rate": 7.319347060942825e-07, "loss": 0.6919, "step": 295020 }, { "epoch": 24.52, "learning_rate": 7.318238505667489e-07, "loss": 0.7611, "step": 295030 }, { "epoch": 24.52, "learning_rate": 7.317129950392151e-07, "loss": 0.7276, "step": 295040 }, { "epoch": 24.52, "learning_rate": 7.316021395116814e-07, "loss": 0.82, "step": 295050 }, { "epoch": 24.52, "learning_rate": 7.314912839841476e-07, "loss": 0.7757, "step": 295060 }, { "epoch": 24.53, "learning_rate": 7.313804284566138e-07, "loss": 0.6482, "step": 295070 }, { "epoch": 24.53, "learning_rate": 7.312695729290801e-07, "loss": 0.7256, "step": 295080 }, { "epoch": 24.53, "learning_rate": 7.311587174015464e-07, "loss": 0.7056, "step": 295090 }, { "epoch": 24.53, "learning_rate": 7.310478618740127e-07, "loss": 0.7604, "step": 295100 }, { "epoch": 24.53, "learning_rate": 7.309370063464789e-07, "loss": 0.7495, "step": 295110 }, { "epoch": 24.53, "learning_rate": 7.308261508189452e-07, "loss": 0.7344, "step": 295120 }, { "epoch": 24.53, "learning_rate": 7.307152952914114e-07, "loss": 0.7146, "step": 295130 }, { "epoch": 24.53, "learning_rate": 7.306044397638777e-07, "loss": 0.7339, "step": 295140 }, { "epoch": 24.53, "learning_rate": 7.30493584236344e-07, "loss": 0.8177, "step": 295150 }, { "epoch": 24.53, "learning_rate": 7.303827287088102e-07, "loss": 0.7307, "step": 295160 }, { "epoch": 24.53, "learning_rate": 7.302718731812764e-07, "loss": 0.7205, "step": 295170 }, { "epoch": 24.53, "learning_rate": 7.301610176537427e-07, "loss": 0.7413, "step": 295180 }, { "epoch": 24.54, "learning_rate": 7.300501621262089e-07, "loss": 0.6881, "step": 295190 }, { "epoch": 24.54, "learning_rate": 7.299393065986752e-07, "loss": 0.7766, "step": 295200 }, { "epoch": 24.54, "learning_rate": 7.298284510711415e-07, "loss": 0.7162, "step": 295210 }, { "epoch": 24.54, "learning_rate": 7.297175955436078e-07, "loss": 0.7107, "step": 295220 }, { "epoch": 24.54, "learning_rate": 7.29606740016074e-07, "loss": 0.7207, "step": 295230 }, { "epoch": 24.54, "learning_rate": 7.294958844885403e-07, "loss": 0.7043, "step": 295240 }, { "epoch": 24.54, "learning_rate": 7.293850289610065e-07, "loss": 0.7431, "step": 295250 }, { "epoch": 24.54, "learning_rate": 7.292741734334728e-07, "loss": 0.7505, "step": 295260 }, { "epoch": 24.54, "learning_rate": 7.291633179059391e-07, "loss": 0.7019, "step": 295270 }, { "epoch": 24.54, "learning_rate": 7.290524623784054e-07, "loss": 0.754, "step": 295280 }, { "epoch": 24.54, "learning_rate": 7.289416068508716e-07, "loss": 0.7718, "step": 295290 }, { "epoch": 24.54, "learning_rate": 7.288307513233379e-07, "loss": 0.7448, "step": 295300 }, { "epoch": 24.55, "learning_rate": 7.28719895795804e-07, "loss": 0.7395, "step": 295310 }, { "epoch": 24.55, "learning_rate": 7.286090402682703e-07, "loss": 0.7667, "step": 295320 }, { "epoch": 24.55, "learning_rate": 7.284981847407366e-07, "loss": 0.748, "step": 295330 }, { "epoch": 24.55, "learning_rate": 7.283873292132029e-07, "loss": 0.7446, "step": 295340 }, { "epoch": 24.55, "learning_rate": 7.282764736856691e-07, "loss": 0.7601, "step": 295350 }, { "epoch": 24.55, "learning_rate": 7.281656181581354e-07, "loss": 0.7386, "step": 295360 }, { "epoch": 24.55, "learning_rate": 7.280547626306016e-07, "loss": 0.6954, "step": 295370 }, { "epoch": 24.55, "learning_rate": 7.279439071030679e-07, "loss": 0.7714, "step": 295380 }, { "epoch": 24.55, "learning_rate": 7.278330515755342e-07, "loss": 0.7316, "step": 295390 }, { "epoch": 24.55, "learning_rate": 7.277221960480005e-07, "loss": 0.8156, "step": 295400 }, { "epoch": 24.55, "learning_rate": 7.276113405204667e-07, "loss": 0.7431, "step": 295410 }, { "epoch": 24.55, "learning_rate": 7.27500484992933e-07, "loss": 0.7395, "step": 295420 }, { "epoch": 24.56, "learning_rate": 7.273896294653992e-07, "loss": 0.7078, "step": 295430 }, { "epoch": 24.56, "learning_rate": 7.272787739378655e-07, "loss": 0.668, "step": 295440 }, { "epoch": 24.56, "learning_rate": 7.271679184103316e-07, "loss": 0.8171, "step": 295450 }, { "epoch": 24.56, "learning_rate": 7.27057062882798e-07, "loss": 0.7596, "step": 295460 }, { "epoch": 24.56, "learning_rate": 7.269462073552642e-07, "loss": 0.7921, "step": 295470 }, { "epoch": 24.56, "learning_rate": 7.268353518277304e-07, "loss": 0.727, "step": 295480 }, { "epoch": 24.56, "learning_rate": 7.267244963001967e-07, "loss": 0.7783, "step": 295490 }, { "epoch": 24.56, "learning_rate": 7.266136407726629e-07, "loss": 0.7569, "step": 295500 }, { "epoch": 24.56, "learning_rate": 7.265027852451292e-07, "loss": 0.7888, "step": 295510 }, { "epoch": 24.56, "learning_rate": 7.263919297175955e-07, "loss": 0.6899, "step": 295520 }, { "epoch": 24.56, "learning_rate": 7.262810741900618e-07, "loss": 0.7971, "step": 295530 }, { "epoch": 24.56, "learning_rate": 7.26170218662528e-07, "loss": 0.8502, "step": 295540 }, { "epoch": 24.57, "learning_rate": 7.260593631349943e-07, "loss": 0.7666, "step": 295550 }, { "epoch": 24.57, "learning_rate": 7.259485076074605e-07, "loss": 0.742, "step": 295560 }, { "epoch": 24.57, "learning_rate": 7.258376520799268e-07, "loss": 0.7808, "step": 295570 }, { "epoch": 24.57, "learning_rate": 7.257267965523931e-07, "loss": 0.7272, "step": 295580 }, { "epoch": 24.57, "learning_rate": 7.256159410248594e-07, "loss": 0.703, "step": 295590 }, { "epoch": 24.57, "learning_rate": 7.255050854973255e-07, "loss": 0.7245, "step": 295600 }, { "epoch": 24.57, "learning_rate": 7.253942299697918e-07, "loss": 0.702, "step": 295610 }, { "epoch": 24.57, "learning_rate": 7.25283374442258e-07, "loss": 0.7391, "step": 295620 }, { "epoch": 24.57, "learning_rate": 7.251725189147243e-07, "loss": 0.7618, "step": 295630 }, { "epoch": 24.57, "learning_rate": 7.250616633871906e-07, "loss": 0.6635, "step": 295640 }, { "epoch": 24.57, "learning_rate": 7.249508078596569e-07, "loss": 0.7653, "step": 295650 }, { "epoch": 24.57, "learning_rate": 7.248399523321231e-07, "loss": 0.7555, "step": 295660 }, { "epoch": 24.58, "learning_rate": 7.247290968045894e-07, "loss": 0.7403, "step": 295670 }, { "epoch": 24.58, "learning_rate": 7.246182412770556e-07, "loss": 0.7066, "step": 295680 }, { "epoch": 24.58, "learning_rate": 7.245073857495219e-07, "loss": 0.6848, "step": 295690 }, { "epoch": 24.58, "learning_rate": 7.243965302219882e-07, "loss": 0.7373, "step": 295700 }, { "epoch": 24.58, "learning_rate": 7.242856746944545e-07, "loss": 0.7825, "step": 295710 }, { "epoch": 24.58, "learning_rate": 7.241748191669207e-07, "loss": 0.7112, "step": 295720 }, { "epoch": 24.58, "learning_rate": 7.24063963639387e-07, "loss": 0.7671, "step": 295730 }, { "epoch": 24.58, "learning_rate": 7.239531081118532e-07, "loss": 0.7899, "step": 295740 }, { "epoch": 24.58, "learning_rate": 7.238422525843195e-07, "loss": 0.8044, "step": 295750 }, { "epoch": 24.58, "learning_rate": 7.237313970567857e-07, "loss": 0.7398, "step": 295760 }, { "epoch": 24.58, "learning_rate": 7.23620541529252e-07, "loss": 0.7861, "step": 295770 }, { "epoch": 24.58, "learning_rate": 7.235096860017182e-07, "loss": 0.7471, "step": 295780 }, { "epoch": 24.59, "learning_rate": 7.233988304741845e-07, "loss": 0.7421, "step": 295790 }, { "epoch": 24.59, "learning_rate": 7.232879749466507e-07, "loss": 0.7707, "step": 295800 }, { "epoch": 24.59, "learning_rate": 7.23177119419117e-07, "loss": 0.7125, "step": 295810 }, { "epoch": 24.59, "learning_rate": 7.230662638915833e-07, "loss": 0.7053, "step": 295820 }, { "epoch": 24.59, "learning_rate": 7.229554083640496e-07, "loss": 0.721, "step": 295830 }, { "epoch": 24.59, "learning_rate": 7.228445528365158e-07, "loss": 0.7593, "step": 295840 }, { "epoch": 24.59, "learning_rate": 7.227336973089821e-07, "loss": 0.7403, "step": 295850 }, { "epoch": 24.59, "learning_rate": 7.226228417814483e-07, "loss": 0.7456, "step": 295860 }, { "epoch": 24.59, "learning_rate": 7.225119862539146e-07, "loss": 0.7278, "step": 295870 }, { "epoch": 24.59, "learning_rate": 7.224011307263808e-07, "loss": 0.7313, "step": 295880 }, { "epoch": 24.59, "learning_rate": 7.222902751988472e-07, "loss": 0.7538, "step": 295890 }, { "epoch": 24.59, "learning_rate": 7.221794196713134e-07, "loss": 0.7519, "step": 295900 }, { "epoch": 24.6, "learning_rate": 7.220685641437795e-07, "loss": 0.7451, "step": 295910 }, { "epoch": 24.6, "learning_rate": 7.219577086162458e-07, "loss": 0.7456, "step": 295920 }, { "epoch": 24.6, "learning_rate": 7.21846853088712e-07, "loss": 0.7414, "step": 295930 }, { "epoch": 24.6, "learning_rate": 7.217359975611783e-07, "loss": 0.747, "step": 295940 }, { "epoch": 24.6, "learning_rate": 7.216251420336446e-07, "loss": 0.7428, "step": 295950 }, { "epoch": 24.6, "learning_rate": 7.215142865061109e-07, "loss": 0.8006, "step": 295960 }, { "epoch": 24.6, "learning_rate": 7.214034309785771e-07, "loss": 0.7654, "step": 295970 }, { "epoch": 24.6, "learning_rate": 7.212925754510434e-07, "loss": 0.7053, "step": 295980 }, { "epoch": 24.6, "learning_rate": 7.211817199235096e-07, "loss": 0.764, "step": 295990 }, { "epoch": 24.6, "learning_rate": 7.210708643959759e-07, "loss": 0.728, "step": 296000 }, { "epoch": 24.6, "learning_rate": 7.209600088684422e-07, "loss": 0.7066, "step": 296010 }, { "epoch": 24.6, "learning_rate": 7.208491533409085e-07, "loss": 0.7857, "step": 296020 }, { "epoch": 24.61, "learning_rate": 7.207382978133747e-07, "loss": 0.7029, "step": 296030 }, { "epoch": 24.61, "learning_rate": 7.20627442285841e-07, "loss": 0.7286, "step": 296040 }, { "epoch": 24.61, "learning_rate": 7.205165867583071e-07, "loss": 0.7431, "step": 296050 }, { "epoch": 24.61, "learning_rate": 7.204057312307734e-07, "loss": 0.7587, "step": 296060 }, { "epoch": 24.61, "learning_rate": 7.202948757032397e-07, "loss": 0.7107, "step": 296070 }, { "epoch": 24.61, "learning_rate": 7.20184020175706e-07, "loss": 0.6807, "step": 296080 }, { "epoch": 24.61, "learning_rate": 7.200731646481722e-07, "loss": 0.7541, "step": 296090 }, { "epoch": 24.61, "learning_rate": 7.199623091206385e-07, "loss": 0.7686, "step": 296100 }, { "epoch": 24.61, "learning_rate": 7.198514535931047e-07, "loss": 0.7433, "step": 296110 }, { "epoch": 24.61, "learning_rate": 7.19740598065571e-07, "loss": 0.7185, "step": 296120 }, { "epoch": 24.61, "learning_rate": 7.196297425380373e-07, "loss": 0.7459, "step": 296130 }, { "epoch": 24.61, "learning_rate": 7.195188870105036e-07, "loss": 0.7384, "step": 296140 }, { "epoch": 24.62, "learning_rate": 7.194080314829698e-07, "loss": 0.7257, "step": 296150 }, { "epoch": 24.62, "learning_rate": 7.192971759554361e-07, "loss": 0.723, "step": 296160 }, { "epoch": 24.62, "learning_rate": 7.191863204279023e-07, "loss": 0.7167, "step": 296170 }, { "epoch": 24.62, "learning_rate": 7.190754649003686e-07, "loss": 0.7245, "step": 296180 }, { "epoch": 24.62, "learning_rate": 7.189646093728349e-07, "loss": 0.7698, "step": 296190 }, { "epoch": 24.62, "learning_rate": 7.188537538453012e-07, "loss": 0.7463, "step": 296200 }, { "epoch": 24.62, "learning_rate": 7.187428983177673e-07, "loss": 0.6993, "step": 296210 }, { "epoch": 24.62, "learning_rate": 7.186320427902336e-07, "loss": 0.7365, "step": 296220 }, { "epoch": 24.62, "learning_rate": 7.185211872626998e-07, "loss": 0.7328, "step": 296230 }, { "epoch": 24.62, "learning_rate": 7.184103317351661e-07, "loss": 0.7304, "step": 296240 }, { "epoch": 24.62, "learning_rate": 7.182994762076323e-07, "loss": 0.7726, "step": 296250 }, { "epoch": 24.62, "learning_rate": 7.181886206800987e-07, "loss": 0.7815, "step": 296260 }, { "epoch": 24.63, "learning_rate": 7.180777651525649e-07, "loss": 0.781, "step": 296270 }, { "epoch": 24.63, "learning_rate": 7.179669096250312e-07, "loss": 0.6876, "step": 296280 }, { "epoch": 24.63, "learning_rate": 7.178560540974974e-07, "loss": 0.7793, "step": 296290 }, { "epoch": 24.63, "learning_rate": 7.177451985699636e-07, "loss": 0.7754, "step": 296300 }, { "epoch": 24.63, "learning_rate": 7.176343430424299e-07, "loss": 0.7612, "step": 296310 }, { "epoch": 24.63, "learning_rate": 7.175234875148962e-07, "loss": 0.7461, "step": 296320 }, { "epoch": 24.63, "learning_rate": 7.174126319873625e-07, "loss": 0.7203, "step": 296330 }, { "epoch": 24.63, "learning_rate": 7.173017764598287e-07, "loss": 0.7463, "step": 296340 }, { "epoch": 24.63, "learning_rate": 7.171909209322949e-07, "loss": 0.7586, "step": 296350 }, { "epoch": 24.63, "learning_rate": 7.170800654047611e-07, "loss": 0.7215, "step": 296360 }, { "epoch": 24.63, "learning_rate": 7.169692098772274e-07, "loss": 0.782, "step": 296370 }, { "epoch": 24.63, "learning_rate": 7.168583543496937e-07, "loss": 0.7513, "step": 296380 }, { "epoch": 24.64, "learning_rate": 7.1674749882216e-07, "loss": 0.7576, "step": 296390 }, { "epoch": 24.64, "learning_rate": 7.166366432946262e-07, "loss": 0.7688, "step": 296400 }, { "epoch": 24.64, "learning_rate": 7.165257877670925e-07, "loss": 0.7682, "step": 296410 }, { "epoch": 24.64, "learning_rate": 7.164149322395587e-07, "loss": 0.7622, "step": 296420 }, { "epoch": 24.64, "learning_rate": 7.16304076712025e-07, "loss": 0.6353, "step": 296430 }, { "epoch": 24.64, "learning_rate": 7.161932211844913e-07, "loss": 0.8025, "step": 296440 }, { "epoch": 24.64, "learning_rate": 7.160823656569576e-07, "loss": 0.7229, "step": 296450 }, { "epoch": 24.64, "learning_rate": 7.159715101294238e-07, "loss": 0.7965, "step": 296460 }, { "epoch": 24.64, "learning_rate": 7.158606546018901e-07, "loss": 0.6475, "step": 296470 }, { "epoch": 24.64, "learning_rate": 7.157497990743563e-07, "loss": 0.7391, "step": 296480 }, { "epoch": 24.64, "learning_rate": 7.156389435468226e-07, "loss": 0.6896, "step": 296490 }, { "epoch": 24.64, "learning_rate": 7.155280880192888e-07, "loss": 0.7433, "step": 296500 }, { "epoch": 24.65, "learning_rate": 7.154172324917551e-07, "loss": 0.7016, "step": 296510 }, { "epoch": 24.65, "learning_rate": 7.153063769642213e-07, "loss": 0.7155, "step": 296520 }, { "epoch": 24.65, "learning_rate": 7.151955214366876e-07, "loss": 0.7708, "step": 296530 }, { "epoch": 24.65, "learning_rate": 7.150846659091538e-07, "loss": 0.702, "step": 296540 }, { "epoch": 24.65, "learning_rate": 7.149738103816201e-07, "loss": 0.7978, "step": 296550 }, { "epoch": 24.65, "learning_rate": 7.148629548540864e-07, "loss": 0.7162, "step": 296560 }, { "epoch": 24.65, "learning_rate": 7.147520993265527e-07, "loss": 0.7451, "step": 296570 }, { "epoch": 24.65, "learning_rate": 7.146412437990189e-07, "loss": 0.7618, "step": 296580 }, { "epoch": 24.65, "learning_rate": 7.145303882714852e-07, "loss": 0.6976, "step": 296590 }, { "epoch": 24.65, "learning_rate": 7.144195327439514e-07, "loss": 0.7856, "step": 296600 }, { "epoch": 24.65, "learning_rate": 7.143086772164177e-07, "loss": 0.7598, "step": 296610 }, { "epoch": 24.65, "learning_rate": 7.14197821688884e-07, "loss": 0.6967, "step": 296620 }, { "epoch": 24.66, "learning_rate": 7.140869661613503e-07, "loss": 0.7225, "step": 296630 }, { "epoch": 24.66, "learning_rate": 7.139761106338165e-07, "loss": 0.7406, "step": 296640 }, { "epoch": 24.66, "learning_rate": 7.138652551062827e-07, "loss": 0.7356, "step": 296650 }, { "epoch": 24.66, "learning_rate": 7.137543995787489e-07, "loss": 0.7562, "step": 296660 }, { "epoch": 24.66, "learning_rate": 7.136435440512152e-07, "loss": 0.7858, "step": 296670 }, { "epoch": 24.66, "learning_rate": 7.135326885236814e-07, "loss": 0.7853, "step": 296680 }, { "epoch": 24.66, "learning_rate": 7.134218329961478e-07, "loss": 0.6908, "step": 296690 }, { "epoch": 24.66, "learning_rate": 7.13310977468614e-07, "loss": 0.748, "step": 296700 }, { "epoch": 24.66, "learning_rate": 7.132001219410803e-07, "loss": 0.6621, "step": 296710 }, { "epoch": 24.66, "learning_rate": 7.130892664135465e-07, "loss": 0.7088, "step": 296720 }, { "epoch": 24.66, "learning_rate": 7.129784108860127e-07, "loss": 0.6915, "step": 296730 }, { "epoch": 24.66, "learning_rate": 7.12867555358479e-07, "loss": 0.7546, "step": 296740 }, { "epoch": 24.67, "learning_rate": 7.127566998309453e-07, "loss": 0.8276, "step": 296750 }, { "epoch": 24.67, "learning_rate": 7.126458443034116e-07, "loss": 0.7024, "step": 296760 }, { "epoch": 24.67, "learning_rate": 7.125349887758778e-07, "loss": 0.7222, "step": 296770 }, { "epoch": 24.67, "learning_rate": 7.124241332483441e-07, "loss": 0.7274, "step": 296780 }, { "epoch": 24.67, "learning_rate": 7.123132777208102e-07, "loss": 0.7255, "step": 296790 }, { "epoch": 24.67, "learning_rate": 7.122024221932765e-07, "loss": 0.7316, "step": 296800 }, { "epoch": 24.67, "learning_rate": 7.120915666657428e-07, "loss": 0.7338, "step": 296810 }, { "epoch": 24.67, "learning_rate": 7.119807111382091e-07, "loss": 0.6988, "step": 296820 }, { "epoch": 24.67, "learning_rate": 7.118698556106753e-07, "loss": 0.7462, "step": 296830 }, { "epoch": 24.67, "learning_rate": 7.117590000831416e-07, "loss": 0.7, "step": 296840 }, { "epoch": 24.67, "learning_rate": 7.116481445556078e-07, "loss": 0.7646, "step": 296850 }, { "epoch": 24.67, "learning_rate": 7.115372890280741e-07, "loss": 0.7502, "step": 296860 }, { "epoch": 24.68, "learning_rate": 7.114264335005404e-07, "loss": 0.7629, "step": 296870 }, { "epoch": 24.68, "learning_rate": 7.113155779730067e-07, "loss": 0.7339, "step": 296880 }, { "epoch": 24.68, "learning_rate": 7.112047224454729e-07, "loss": 0.7485, "step": 296890 }, { "epoch": 24.68, "learning_rate": 7.110938669179392e-07, "loss": 0.7892, "step": 296900 }, { "epoch": 24.68, "learning_rate": 7.109830113904054e-07, "loss": 0.7526, "step": 296910 }, { "epoch": 24.68, "learning_rate": 7.108721558628717e-07, "loss": 0.7524, "step": 296920 }, { "epoch": 24.68, "learning_rate": 7.10761300335338e-07, "loss": 0.7342, "step": 296930 }, { "epoch": 24.68, "learning_rate": 7.106504448078043e-07, "loss": 0.7318, "step": 296940 }, { "epoch": 24.68, "learning_rate": 7.105395892802704e-07, "loss": 0.7493, "step": 296950 }, { "epoch": 24.68, "learning_rate": 7.104287337527367e-07, "loss": 0.7187, "step": 296960 }, { "epoch": 24.68, "learning_rate": 7.103178782252029e-07, "loss": 0.7304, "step": 296970 }, { "epoch": 24.68, "learning_rate": 7.102070226976692e-07, "loss": 0.7502, "step": 296980 }, { "epoch": 24.69, "learning_rate": 7.100961671701355e-07, "loss": 0.7596, "step": 296990 }, { "epoch": 24.69, "learning_rate": 7.099853116426018e-07, "loss": 0.7784, "step": 297000 }, { "epoch": 24.69, "learning_rate": 7.09874456115068e-07, "loss": 0.7706, "step": 297010 }, { "epoch": 24.69, "learning_rate": 7.097636005875343e-07, "loss": 0.763, "step": 297020 }, { "epoch": 24.69, "learning_rate": 7.096527450600005e-07, "loss": 0.7952, "step": 297030 }, { "epoch": 24.69, "learning_rate": 7.095418895324668e-07, "loss": 0.716, "step": 297040 }, { "epoch": 24.69, "learning_rate": 7.094310340049331e-07, "loss": 0.8099, "step": 297050 }, { "epoch": 24.69, "learning_rate": 7.093201784773994e-07, "loss": 0.7523, "step": 297060 }, { "epoch": 24.69, "learning_rate": 7.092093229498656e-07, "loss": 0.7863, "step": 297070 }, { "epoch": 24.69, "learning_rate": 7.090984674223319e-07, "loss": 0.773, "step": 297080 }, { "epoch": 24.69, "learning_rate": 7.08987611894798e-07, "loss": 0.7155, "step": 297090 }, { "epoch": 24.69, "learning_rate": 7.088767563672643e-07, "loss": 0.7865, "step": 297100 }, { "epoch": 24.7, "learning_rate": 7.087659008397305e-07, "loss": 0.6935, "step": 297110 }, { "epoch": 24.7, "learning_rate": 7.086550453121969e-07, "loss": 0.7303, "step": 297120 }, { "epoch": 24.7, "learning_rate": 7.085441897846631e-07, "loss": 0.6903, "step": 297130 }, { "epoch": 24.7, "learning_rate": 7.084333342571294e-07, "loss": 0.7182, "step": 297140 }, { "epoch": 24.7, "learning_rate": 7.083224787295956e-07, "loss": 0.7309, "step": 297150 }, { "epoch": 24.7, "learning_rate": 7.082116232020618e-07, "loss": 0.7251, "step": 297160 }, { "epoch": 24.7, "learning_rate": 7.081007676745281e-07, "loss": 0.748, "step": 297170 }, { "epoch": 24.7, "learning_rate": 7.079899121469944e-07, "loss": 0.743, "step": 297180 }, { "epoch": 24.7, "learning_rate": 7.078790566194607e-07, "loss": 0.7201, "step": 297190 }, { "epoch": 24.7, "learning_rate": 7.077682010919269e-07, "loss": 0.7631, "step": 297200 }, { "epoch": 24.7, "learning_rate": 7.076573455643932e-07, "loss": 0.766, "step": 297210 }, { "epoch": 24.7, "learning_rate": 7.075464900368594e-07, "loss": 0.7666, "step": 297220 }, { "epoch": 24.71, "learning_rate": 7.074356345093257e-07, "loss": 0.7219, "step": 297230 }, { "epoch": 24.71, "learning_rate": 7.07324778981792e-07, "loss": 0.7599, "step": 297240 }, { "epoch": 24.71, "learning_rate": 7.072139234542582e-07, "loss": 0.7997, "step": 297250 }, { "epoch": 24.71, "learning_rate": 7.071030679267244e-07, "loss": 0.7198, "step": 297260 }, { "epoch": 24.71, "learning_rate": 7.069922123991907e-07, "loss": 0.7025, "step": 297270 }, { "epoch": 24.71, "learning_rate": 7.068813568716569e-07, "loss": 0.7619, "step": 297280 }, { "epoch": 24.71, "learning_rate": 7.067705013441232e-07, "loss": 0.7151, "step": 297290 }, { "epoch": 24.71, "learning_rate": 7.066596458165895e-07, "loss": 0.7822, "step": 297300 }, { "epoch": 24.71, "learning_rate": 7.065487902890558e-07, "loss": 0.7174, "step": 297310 }, { "epoch": 24.71, "learning_rate": 7.06437934761522e-07, "loss": 0.7304, "step": 297320 }, { "epoch": 24.71, "learning_rate": 7.063270792339883e-07, "loss": 0.6963, "step": 297330 }, { "epoch": 24.71, "learning_rate": 7.062162237064545e-07, "loss": 0.7217, "step": 297340 }, { "epoch": 24.72, "learning_rate": 7.061053681789208e-07, "loss": 0.7865, "step": 297350 }, { "epoch": 24.72, "learning_rate": 7.059945126513871e-07, "loss": 0.732, "step": 297360 }, { "epoch": 24.72, "learning_rate": 7.058836571238534e-07, "loss": 0.7828, "step": 297370 }, { "epoch": 24.72, "learning_rate": 7.057728015963196e-07, "loss": 0.7196, "step": 297380 }, { "epoch": 24.72, "learning_rate": 7.056619460687859e-07, "loss": 0.7273, "step": 297390 }, { "epoch": 24.72, "learning_rate": 7.05551090541252e-07, "loss": 0.746, "step": 297400 }, { "epoch": 24.72, "learning_rate": 7.054402350137183e-07, "loss": 0.7466, "step": 297410 }, { "epoch": 24.72, "learning_rate": 7.053293794861846e-07, "loss": 0.7836, "step": 297420 }, { "epoch": 24.72, "learning_rate": 7.052185239586509e-07, "loss": 0.7598, "step": 297430 }, { "epoch": 24.72, "learning_rate": 7.051076684311171e-07, "loss": 0.7409, "step": 297440 }, { "epoch": 24.72, "learning_rate": 7.049968129035834e-07, "loss": 0.829, "step": 297450 }, { "epoch": 24.72, "learning_rate": 7.048859573760496e-07, "loss": 0.7126, "step": 297460 }, { "epoch": 24.73, "learning_rate": 7.047751018485159e-07, "loss": 0.7406, "step": 297470 }, { "epoch": 24.73, "learning_rate": 7.046642463209822e-07, "loss": 0.7096, "step": 297480 }, { "epoch": 24.73, "learning_rate": 7.045533907934485e-07, "loss": 0.7276, "step": 297490 }, { "epoch": 24.73, "learning_rate": 7.044425352659147e-07, "loss": 0.7739, "step": 297500 }, { "epoch": 24.73, "learning_rate": 7.04331679738381e-07, "loss": 0.7324, "step": 297510 }, { "epoch": 24.73, "learning_rate": 7.042208242108472e-07, "loss": 0.7833, "step": 297520 }, { "epoch": 24.73, "learning_rate": 7.041099686833135e-07, "loss": 0.7426, "step": 297530 }, { "epoch": 24.73, "learning_rate": 7.039991131557796e-07, "loss": 0.7803, "step": 297540 }, { "epoch": 24.73, "learning_rate": 7.03888257628246e-07, "loss": 0.7908, "step": 297550 }, { "epoch": 24.73, "learning_rate": 7.037774021007122e-07, "loss": 0.7787, "step": 297560 }, { "epoch": 24.73, "learning_rate": 7.036665465731784e-07, "loss": 0.7706, "step": 297570 }, { "epoch": 24.73, "learning_rate": 7.035556910456447e-07, "loss": 0.6936, "step": 297580 }, { "epoch": 24.74, "learning_rate": 7.034448355181109e-07, "loss": 0.7269, "step": 297590 }, { "epoch": 24.74, "learning_rate": 7.033339799905772e-07, "loss": 0.7766, "step": 297600 }, { "epoch": 24.74, "learning_rate": 7.032231244630435e-07, "loss": 0.7379, "step": 297610 }, { "epoch": 24.74, "learning_rate": 7.031122689355098e-07, "loss": 0.7294, "step": 297620 }, { "epoch": 24.74, "learning_rate": 7.03001413407976e-07, "loss": 0.7336, "step": 297630 }, { "epoch": 24.74, "learning_rate": 7.028905578804423e-07, "loss": 0.6847, "step": 297640 }, { "epoch": 24.74, "learning_rate": 7.027797023529085e-07, "loss": 0.7695, "step": 297650 }, { "epoch": 24.74, "learning_rate": 7.026688468253748e-07, "loss": 0.7073, "step": 297660 }, { "epoch": 24.74, "learning_rate": 7.025579912978411e-07, "loss": 0.6762, "step": 297670 }, { "epoch": 24.74, "learning_rate": 7.024471357703074e-07, "loss": 0.6969, "step": 297680 }, { "epoch": 24.74, "learning_rate": 7.023362802427735e-07, "loss": 0.7315, "step": 297690 }, { "epoch": 24.74, "learning_rate": 7.022254247152398e-07, "loss": 0.747, "step": 297700 }, { "epoch": 24.75, "learning_rate": 7.02114569187706e-07, "loss": 0.7074, "step": 297710 }, { "epoch": 24.75, "learning_rate": 7.020037136601723e-07, "loss": 0.7268, "step": 297720 }, { "epoch": 24.75, "learning_rate": 7.018928581326386e-07, "loss": 0.7144, "step": 297730 }, { "epoch": 24.75, "learning_rate": 7.017820026051049e-07, "loss": 0.7475, "step": 297740 }, { "epoch": 24.75, "learning_rate": 7.016711470775711e-07, "loss": 0.7677, "step": 297750 }, { "epoch": 24.75, "learning_rate": 7.015602915500374e-07, "loss": 0.755, "step": 297760 }, { "epoch": 24.75, "learning_rate": 7.014494360225036e-07, "loss": 0.6822, "step": 297770 }, { "epoch": 24.75, "learning_rate": 7.013385804949699e-07, "loss": 0.738, "step": 297780 }, { "epoch": 24.75, "learning_rate": 7.012277249674362e-07, "loss": 0.7894, "step": 297790 }, { "epoch": 24.75, "learning_rate": 7.011168694399025e-07, "loss": 0.7664, "step": 297800 }, { "epoch": 24.75, "learning_rate": 7.010060139123687e-07, "loss": 0.6871, "step": 297810 }, { "epoch": 24.75, "learning_rate": 7.00895158384835e-07, "loss": 0.7782, "step": 297820 }, { "epoch": 24.76, "learning_rate": 7.007843028573012e-07, "loss": 0.7216, "step": 297830 }, { "epoch": 24.76, "learning_rate": 7.006734473297674e-07, "loss": 0.7352, "step": 297840 }, { "epoch": 24.76, "learning_rate": 7.005625918022337e-07, "loss": 0.7635, "step": 297850 }, { "epoch": 24.76, "learning_rate": 7.004517362747e-07, "loss": 0.7127, "step": 297860 }, { "epoch": 24.76, "learning_rate": 7.003408807471662e-07, "loss": 0.7471, "step": 297870 }, { "epoch": 24.76, "learning_rate": 7.002300252196325e-07, "loss": 0.6717, "step": 297880 }, { "epoch": 24.76, "learning_rate": 7.001191696920987e-07, "loss": 0.7513, "step": 297890 }, { "epoch": 24.76, "learning_rate": 7.00008314164565e-07, "loss": 0.7793, "step": 297900 }, { "epoch": 24.76, "learning_rate": 6.998974586370313e-07, "loss": 0.7619, "step": 297910 }, { "epoch": 24.76, "learning_rate": 6.997866031094976e-07, "loss": 0.7165, "step": 297920 }, { "epoch": 24.76, "learning_rate": 6.996757475819638e-07, "loss": 0.6871, "step": 297930 }, { "epoch": 24.76, "learning_rate": 6.995648920544301e-07, "loss": 0.7228, "step": 297940 }, { "epoch": 24.77, "learning_rate": 6.994540365268963e-07, "loss": 0.7932, "step": 297950 }, { "epoch": 24.77, "learning_rate": 6.993431809993626e-07, "loss": 0.7006, "step": 297960 }, { "epoch": 24.77, "learning_rate": 6.992323254718288e-07, "loss": 0.684, "step": 297970 }, { "epoch": 24.77, "learning_rate": 6.991214699442952e-07, "loss": 0.756, "step": 297980 }, { "epoch": 24.77, "learning_rate": 6.990106144167613e-07, "loss": 0.7133, "step": 297990 }, { "epoch": 24.77, "learning_rate": 6.988997588892275e-07, "loss": 0.7788, "step": 298000 }, { "epoch": 24.77, "learning_rate": 6.987889033616938e-07, "loss": 0.7288, "step": 298010 }, { "epoch": 24.77, "learning_rate": 6.9867804783416e-07, "loss": 0.6587, "step": 298020 }, { "epoch": 24.77, "learning_rate": 6.985671923066263e-07, "loss": 0.6779, "step": 298030 }, { "epoch": 24.77, "learning_rate": 6.984563367790926e-07, "loss": 0.7381, "step": 298040 }, { "epoch": 24.77, "learning_rate": 6.983454812515589e-07, "loss": 0.7671, "step": 298050 }, { "epoch": 24.77, "learning_rate": 6.982346257240251e-07, "loss": 0.754, "step": 298060 }, { "epoch": 24.78, "learning_rate": 6.981237701964914e-07, "loss": 0.7225, "step": 298070 }, { "epoch": 24.78, "learning_rate": 6.980129146689576e-07, "loss": 0.6852, "step": 298080 }, { "epoch": 24.78, "learning_rate": 6.979020591414239e-07, "loss": 0.7127, "step": 298090 }, { "epoch": 24.78, "learning_rate": 6.977912036138902e-07, "loss": 0.8053, "step": 298100 }, { "epoch": 24.78, "learning_rate": 6.976803480863565e-07, "loss": 0.7073, "step": 298110 }, { "epoch": 24.78, "learning_rate": 6.975694925588227e-07, "loss": 0.7357, "step": 298120 }, { "epoch": 24.78, "learning_rate": 6.97458637031289e-07, "loss": 0.7102, "step": 298130 }, { "epoch": 24.78, "learning_rate": 6.973477815037551e-07, "loss": 0.7805, "step": 298140 }, { "epoch": 24.78, "learning_rate": 6.972369259762214e-07, "loss": 0.7918, "step": 298150 }, { "epoch": 24.78, "learning_rate": 6.971260704486877e-07, "loss": 0.7305, "step": 298160 }, { "epoch": 24.78, "learning_rate": 6.97015214921154e-07, "loss": 0.7243, "step": 298170 }, { "epoch": 24.78, "learning_rate": 6.969043593936202e-07, "loss": 0.7602, "step": 298180 }, { "epoch": 24.79, "learning_rate": 6.967935038660865e-07, "loss": 0.7037, "step": 298190 }, { "epoch": 24.79, "learning_rate": 6.966826483385527e-07, "loss": 0.7273, "step": 298200 }, { "epoch": 24.79, "learning_rate": 6.96571792811019e-07, "loss": 0.7036, "step": 298210 }, { "epoch": 24.79, "learning_rate": 6.964609372834853e-07, "loss": 0.7416, "step": 298220 }, { "epoch": 24.79, "learning_rate": 6.963500817559516e-07, "loss": 0.744, "step": 298230 }, { "epoch": 24.79, "learning_rate": 6.962392262284178e-07, "loss": 0.7211, "step": 298240 }, { "epoch": 24.79, "learning_rate": 6.961283707008841e-07, "loss": 0.7476, "step": 298250 }, { "epoch": 24.79, "learning_rate": 6.960175151733503e-07, "loss": 0.7764, "step": 298260 }, { "epoch": 24.79, "learning_rate": 6.959066596458166e-07, "loss": 0.7258, "step": 298270 }, { "epoch": 24.79, "learning_rate": 6.957958041182829e-07, "loss": 0.7152, "step": 298280 }, { "epoch": 24.79, "learning_rate": 6.956849485907491e-07, "loss": 0.7545, "step": 298290 }, { "epoch": 24.79, "learning_rate": 6.955740930632153e-07, "loss": 0.7533, "step": 298300 }, { "epoch": 24.8, "learning_rate": 6.954632375356816e-07, "loss": 0.738, "step": 298310 }, { "epoch": 24.8, "learning_rate": 6.953523820081478e-07, "loss": 0.7323, "step": 298320 }, { "epoch": 24.8, "learning_rate": 6.952415264806141e-07, "loss": 0.7636, "step": 298330 }, { "epoch": 24.8, "learning_rate": 6.951306709530803e-07, "loss": 0.7209, "step": 298340 }, { "epoch": 24.8, "learning_rate": 6.950198154255467e-07, "loss": 0.8012, "step": 298350 }, { "epoch": 24.8, "learning_rate": 6.949089598980129e-07, "loss": 0.7165, "step": 298360 }, { "epoch": 24.8, "learning_rate": 6.947981043704792e-07, "loss": 0.6913, "step": 298370 }, { "epoch": 24.8, "learning_rate": 6.946872488429454e-07, "loss": 0.7088, "step": 298380 }, { "epoch": 24.8, "learning_rate": 6.945763933154116e-07, "loss": 0.795, "step": 298390 }, { "epoch": 24.8, "learning_rate": 6.944655377878779e-07, "loss": 0.7602, "step": 298400 }, { "epoch": 24.8, "learning_rate": 6.943546822603442e-07, "loss": 0.8069, "step": 298410 }, { "epoch": 24.8, "learning_rate": 6.942438267328105e-07, "loss": 0.7492, "step": 298420 }, { "epoch": 24.81, "learning_rate": 6.941329712052766e-07, "loss": 0.708, "step": 298430 }, { "epoch": 24.81, "learning_rate": 6.940221156777429e-07, "loss": 0.7515, "step": 298440 }, { "epoch": 24.81, "learning_rate": 6.939112601502091e-07, "loss": 0.7184, "step": 298450 }, { "epoch": 24.81, "learning_rate": 6.938004046226754e-07, "loss": 0.7586, "step": 298460 }, { "epoch": 24.81, "learning_rate": 6.936895490951417e-07, "loss": 0.7614, "step": 298470 }, { "epoch": 24.81, "learning_rate": 6.93578693567608e-07, "loss": 0.755, "step": 298480 }, { "epoch": 24.81, "learning_rate": 6.934678380400742e-07, "loss": 0.7318, "step": 298490 }, { "epoch": 24.81, "learning_rate": 6.933569825125405e-07, "loss": 0.7854, "step": 298500 }, { "epoch": 24.81, "learning_rate": 6.932461269850067e-07, "loss": 0.7829, "step": 298510 }, { "epoch": 24.81, "learning_rate": 6.93135271457473e-07, "loss": 0.7717, "step": 298520 }, { "epoch": 24.81, "learning_rate": 6.930244159299393e-07, "loss": 0.6995, "step": 298530 }, { "epoch": 24.81, "learning_rate": 6.929135604024056e-07, "loss": 0.765, "step": 298540 }, { "epoch": 24.82, "learning_rate": 6.928027048748718e-07, "loss": 0.8057, "step": 298550 }, { "epoch": 24.82, "learning_rate": 6.926918493473381e-07, "loss": 0.7334, "step": 298560 }, { "epoch": 24.82, "learning_rate": 6.925809938198043e-07, "loss": 0.7192, "step": 298570 }, { "epoch": 24.82, "learning_rate": 6.924701382922705e-07, "loss": 0.6856, "step": 298580 }, { "epoch": 24.82, "learning_rate": 6.923592827647368e-07, "loss": 0.6807, "step": 298590 }, { "epoch": 24.82, "learning_rate": 6.922484272372031e-07, "loss": 0.7939, "step": 298600 }, { "epoch": 24.82, "learning_rate": 6.921375717096693e-07, "loss": 0.6567, "step": 298610 }, { "epoch": 24.82, "learning_rate": 6.920267161821356e-07, "loss": 0.7226, "step": 298620 }, { "epoch": 24.82, "learning_rate": 6.919158606546018e-07, "loss": 0.8198, "step": 298630 }, { "epoch": 24.82, "learning_rate": 6.918050051270681e-07, "loss": 0.7517, "step": 298640 }, { "epoch": 24.82, "learning_rate": 6.916941495995344e-07, "loss": 0.7805, "step": 298650 }, { "epoch": 24.82, "learning_rate": 6.915832940720007e-07, "loss": 0.7731, "step": 298660 }, { "epoch": 24.83, "learning_rate": 6.914724385444669e-07, "loss": 0.7756, "step": 298670 }, { "epoch": 24.83, "learning_rate": 6.913615830169332e-07, "loss": 0.8052, "step": 298680 }, { "epoch": 24.83, "learning_rate": 6.912507274893994e-07, "loss": 0.6805, "step": 298690 }, { "epoch": 24.83, "learning_rate": 6.911398719618657e-07, "loss": 0.7826, "step": 298700 }, { "epoch": 24.83, "learning_rate": 6.91029016434332e-07, "loss": 0.7042, "step": 298710 }, { "epoch": 24.83, "learning_rate": 6.909181609067983e-07, "loss": 0.7444, "step": 298720 }, { "epoch": 24.83, "learning_rate": 6.908073053792644e-07, "loss": 0.7891, "step": 298730 }, { "epoch": 24.83, "learning_rate": 6.906964498517307e-07, "loss": 0.7437, "step": 298740 }, { "epoch": 24.83, "learning_rate": 6.905855943241969e-07, "loss": 0.7307, "step": 298750 }, { "epoch": 24.83, "learning_rate": 6.904747387966632e-07, "loss": 0.7533, "step": 298760 }, { "epoch": 24.83, "learning_rate": 6.903638832691294e-07, "loss": 0.7521, "step": 298770 }, { "epoch": 24.83, "learning_rate": 6.902530277415958e-07, "loss": 0.7596, "step": 298780 }, { "epoch": 24.84, "learning_rate": 6.90142172214062e-07, "loss": 0.7519, "step": 298790 }, { "epoch": 24.84, "learning_rate": 6.900313166865283e-07, "loss": 0.7476, "step": 298800 }, { "epoch": 24.84, "learning_rate": 6.899204611589945e-07, "loss": 0.752, "step": 298810 }, { "epoch": 24.84, "learning_rate": 6.898096056314607e-07, "loss": 0.6551, "step": 298820 }, { "epoch": 24.84, "learning_rate": 6.89698750103927e-07, "loss": 0.7392, "step": 298830 }, { "epoch": 24.84, "learning_rate": 6.895878945763933e-07, "loss": 0.7958, "step": 298840 }, { "epoch": 24.84, "learning_rate": 6.894770390488596e-07, "loss": 0.7483, "step": 298850 }, { "epoch": 24.84, "learning_rate": 6.893661835213258e-07, "loss": 0.7884, "step": 298860 }, { "epoch": 24.84, "learning_rate": 6.892553279937921e-07, "loss": 0.7357, "step": 298870 }, { "epoch": 24.84, "learning_rate": 6.891444724662582e-07, "loss": 0.7226, "step": 298880 }, { "epoch": 24.84, "learning_rate": 6.890336169387245e-07, "loss": 0.7446, "step": 298890 }, { "epoch": 24.84, "learning_rate": 6.889227614111908e-07, "loss": 0.7633, "step": 298900 }, { "epoch": 24.84, "learning_rate": 6.888119058836571e-07, "loss": 0.74, "step": 298910 }, { "epoch": 24.85, "learning_rate": 6.887010503561233e-07, "loss": 0.7281, "step": 298920 }, { "epoch": 24.85, "learning_rate": 6.885901948285896e-07, "loss": 0.7147, "step": 298930 }, { "epoch": 24.85, "learning_rate": 6.884793393010558e-07, "loss": 0.758, "step": 298940 }, { "epoch": 24.85, "learning_rate": 6.883684837735221e-07, "loss": 0.7855, "step": 298950 }, { "epoch": 24.85, "learning_rate": 6.882576282459884e-07, "loss": 0.6913, "step": 298960 }, { "epoch": 24.85, "learning_rate": 6.881467727184547e-07, "loss": 0.7616, "step": 298970 }, { "epoch": 24.85, "learning_rate": 6.880359171909209e-07, "loss": 0.7528, "step": 298980 }, { "epoch": 24.85, "learning_rate": 6.879250616633872e-07, "loss": 0.7021, "step": 298990 }, { "epoch": 24.85, "learning_rate": 6.878142061358534e-07, "loss": 0.7741, "step": 299000 }, { "epoch": 24.85, "learning_rate": 6.877033506083197e-07, "loss": 0.7429, "step": 299010 }, { "epoch": 24.85, "learning_rate": 6.87592495080786e-07, "loss": 0.7102, "step": 299020 }, { "epoch": 24.85, "learning_rate": 6.874816395532523e-07, "loss": 0.7756, "step": 299030 }, { "epoch": 24.86, "learning_rate": 6.873707840257184e-07, "loss": 0.7433, "step": 299040 }, { "epoch": 24.86, "learning_rate": 6.872599284981847e-07, "loss": 0.7929, "step": 299050 }, { "epoch": 24.86, "learning_rate": 6.871490729706509e-07, "loss": 0.7484, "step": 299060 }, { "epoch": 24.86, "learning_rate": 6.870382174431172e-07, "loss": 0.7141, "step": 299070 }, { "epoch": 24.86, "learning_rate": 6.869273619155835e-07, "loss": 0.7024, "step": 299080 }, { "epoch": 24.86, "learning_rate": 6.868165063880498e-07, "loss": 0.7425, "step": 299090 }, { "epoch": 24.86, "learning_rate": 6.86705650860516e-07, "loss": 0.6954, "step": 299100 }, { "epoch": 24.86, "learning_rate": 6.865947953329823e-07, "loss": 0.7008, "step": 299110 }, { "epoch": 24.86, "learning_rate": 6.864839398054485e-07, "loss": 0.7246, "step": 299120 }, { "epoch": 24.86, "learning_rate": 6.863730842779148e-07, "loss": 0.7473, "step": 299130 }, { "epoch": 24.86, "learning_rate": 6.862622287503811e-07, "loss": 0.7762, "step": 299140 }, { "epoch": 24.86, "learning_rate": 6.861513732228474e-07, "loss": 0.7598, "step": 299150 }, { "epoch": 24.87, "learning_rate": 6.860405176953136e-07, "loss": 0.7543, "step": 299160 }, { "epoch": 24.87, "learning_rate": 6.859296621677799e-07, "loss": 0.6658, "step": 299170 }, { "epoch": 24.87, "learning_rate": 6.858298921929995e-07, "loss": 0.6795, "step": 299180 }, { "epoch": 24.87, "learning_rate": 6.857190366654657e-07, "loss": 0.7514, "step": 299190 }, { "epoch": 24.87, "learning_rate": 6.85608181137932e-07, "loss": 0.7733, "step": 299200 }, { "epoch": 24.87, "learning_rate": 6.854973256103982e-07, "loss": 0.7368, "step": 299210 }, { "epoch": 24.87, "learning_rate": 6.853864700828645e-07, "loss": 0.7684, "step": 299220 }, { "epoch": 24.87, "learning_rate": 6.852756145553308e-07, "loss": 0.7267, "step": 299230 }, { "epoch": 24.87, "learning_rate": 6.851647590277971e-07, "loss": 0.6651, "step": 299240 }, { "epoch": 24.87, "learning_rate": 6.850539035002633e-07, "loss": 0.7172, "step": 299250 }, { "epoch": 24.87, "learning_rate": 6.849430479727295e-07, "loss": 0.7684, "step": 299260 }, { "epoch": 24.87, "learning_rate": 6.848321924451957e-07, "loss": 0.7325, "step": 299270 }, { "epoch": 24.88, "learning_rate": 6.84721336917662e-07, "loss": 0.7474, "step": 299280 }, { "epoch": 24.88, "learning_rate": 6.846104813901283e-07, "loss": 0.7142, "step": 299290 }, { "epoch": 24.88, "learning_rate": 6.844996258625946e-07, "loss": 0.7777, "step": 299300 }, { "epoch": 24.88, "learning_rate": 6.843887703350608e-07, "loss": 0.789, "step": 299310 }, { "epoch": 24.88, "learning_rate": 6.842779148075271e-07, "loss": 0.7362, "step": 299320 }, { "epoch": 24.88, "learning_rate": 6.841670592799933e-07, "loss": 0.7265, "step": 299330 }, { "epoch": 24.88, "learning_rate": 6.840562037524595e-07, "loss": 0.7229, "step": 299340 }, { "epoch": 24.88, "learning_rate": 6.839453482249259e-07, "loss": 0.7254, "step": 299350 }, { "epoch": 24.88, "learning_rate": 6.838344926973922e-07, "loss": 0.7309, "step": 299360 }, { "epoch": 24.88, "learning_rate": 6.837236371698584e-07, "loss": 0.7777, "step": 299370 }, { "epoch": 24.88, "learning_rate": 6.836127816423246e-07, "loss": 0.7102, "step": 299380 }, { "epoch": 24.88, "learning_rate": 6.835019261147909e-07, "loss": 0.7563, "step": 299390 }, { "epoch": 24.89, "learning_rate": 6.83391070587257e-07, "loss": 0.8397, "step": 299400 }, { "epoch": 24.89, "learning_rate": 6.832802150597233e-07, "loss": 0.7241, "step": 299410 }, { "epoch": 24.89, "learning_rate": 6.831693595321896e-07, "loss": 0.7085, "step": 299420 }, { "epoch": 24.89, "learning_rate": 6.830585040046559e-07, "loss": 0.7254, "step": 299430 }, { "epoch": 24.89, "learning_rate": 6.829476484771221e-07, "loss": 0.7845, "step": 299440 }, { "epoch": 24.89, "learning_rate": 6.828367929495884e-07, "loss": 0.8227, "step": 299450 }, { "epoch": 24.89, "learning_rate": 6.827259374220546e-07, "loss": 0.7063, "step": 299460 }, { "epoch": 24.89, "learning_rate": 6.826150818945209e-07, "loss": 0.7071, "step": 299470 }, { "epoch": 24.89, "learning_rate": 6.825042263669872e-07, "loss": 0.7004, "step": 299480 }, { "epoch": 24.89, "learning_rate": 6.823933708394535e-07, "loss": 0.6788, "step": 299490 }, { "epoch": 24.89, "learning_rate": 6.822825153119197e-07, "loss": 0.7595, "step": 299500 }, { "epoch": 24.89, "learning_rate": 6.82171659784386e-07, "loss": 0.7206, "step": 299510 }, { "epoch": 24.9, "learning_rate": 6.820608042568522e-07, "loss": 0.7393, "step": 299520 }, { "epoch": 24.9, "learning_rate": 6.819499487293185e-07, "loss": 0.7414, "step": 299530 }, { "epoch": 24.9, "learning_rate": 6.818390932017848e-07, "loss": 0.7171, "step": 299540 }, { "epoch": 24.9, "learning_rate": 6.81728237674251e-07, "loss": 0.7649, "step": 299550 }, { "epoch": 24.9, "learning_rate": 6.816173821467172e-07, "loss": 0.7219, "step": 299560 }, { "epoch": 24.9, "learning_rate": 6.815065266191835e-07, "loss": 0.7261, "step": 299570 }, { "epoch": 24.9, "learning_rate": 6.813956710916497e-07, "loss": 0.7842, "step": 299580 }, { "epoch": 24.9, "learning_rate": 6.81284815564116e-07, "loss": 0.7327, "step": 299590 }, { "epoch": 24.9, "learning_rate": 6.811739600365823e-07, "loss": 0.7691, "step": 299600 }, { "epoch": 24.9, "learning_rate": 6.810631045090486e-07, "loss": 0.7405, "step": 299610 }, { "epoch": 24.9, "learning_rate": 6.809522489815148e-07, "loss": 0.722, "step": 299620 }, { "epoch": 24.9, "learning_rate": 6.808413934539811e-07, "loss": 0.6989, "step": 299630 }, { "epoch": 24.91, "learning_rate": 6.807305379264473e-07, "loss": 0.8049, "step": 299640 }, { "epoch": 24.91, "learning_rate": 6.806196823989136e-07, "loss": 0.7804, "step": 299650 }, { "epoch": 24.91, "learning_rate": 6.805088268713799e-07, "loss": 0.7289, "step": 299660 }, { "epoch": 24.91, "learning_rate": 6.803979713438462e-07, "loss": 0.7127, "step": 299670 }, { "epoch": 24.91, "learning_rate": 6.802871158163124e-07, "loss": 0.7493, "step": 299680 }, { "epoch": 24.91, "learning_rate": 6.801762602887787e-07, "loss": 0.7061, "step": 299690 }, { "epoch": 24.91, "learning_rate": 6.800654047612448e-07, "loss": 0.7124, "step": 299700 }, { "epoch": 24.91, "learning_rate": 6.799545492337111e-07, "loss": 0.7508, "step": 299710 }, { "epoch": 24.91, "learning_rate": 6.798436937061774e-07, "loss": 0.7983, "step": 299720 }, { "epoch": 24.91, "learning_rate": 6.797328381786437e-07, "loss": 0.7163, "step": 299730 }, { "epoch": 24.91, "learning_rate": 6.796219826511099e-07, "loss": 0.7027, "step": 299740 }, { "epoch": 24.91, "learning_rate": 6.795111271235762e-07, "loss": 0.8096, "step": 299750 }, { "epoch": 24.92, "learning_rate": 6.794002715960424e-07, "loss": 0.7722, "step": 299760 }, { "epoch": 24.92, "learning_rate": 6.792894160685086e-07, "loss": 0.7808, "step": 299770 }, { "epoch": 24.92, "learning_rate": 6.79178560540975e-07, "loss": 0.7367, "step": 299780 }, { "epoch": 24.92, "learning_rate": 6.790677050134412e-07, "loss": 0.7204, "step": 299790 }, { "epoch": 24.92, "learning_rate": 6.789568494859075e-07, "loss": 0.7893, "step": 299800 }, { "epoch": 24.92, "learning_rate": 6.788459939583737e-07, "loss": 0.7666, "step": 299810 }, { "epoch": 24.92, "learning_rate": 6.7873513843084e-07, "loss": 0.7152, "step": 299820 }, { "epoch": 24.92, "learning_rate": 6.786242829033062e-07, "loss": 0.6678, "step": 299830 }, { "epoch": 24.92, "learning_rate": 6.785134273757725e-07, "loss": 0.7416, "step": 299840 }, { "epoch": 24.92, "learning_rate": 6.784025718482387e-07, "loss": 0.7589, "step": 299850 }, { "epoch": 24.92, "learning_rate": 6.78291716320705e-07, "loss": 0.7465, "step": 299860 }, { "epoch": 24.92, "learning_rate": 6.781808607931712e-07, "loss": 0.7691, "step": 299870 }, { "epoch": 24.93, "learning_rate": 6.780700052656375e-07, "loss": 0.733, "step": 299880 }, { "epoch": 24.93, "learning_rate": 6.779591497381037e-07, "loss": 0.7744, "step": 299890 }, { "epoch": 24.93, "learning_rate": 6.7784829421057e-07, "loss": 0.7659, "step": 299900 }, { "epoch": 24.93, "learning_rate": 6.777374386830363e-07, "loss": 0.708, "step": 299910 }, { "epoch": 24.93, "learning_rate": 6.776265831555026e-07, "loss": 0.7693, "step": 299920 }, { "epoch": 24.93, "learning_rate": 6.775157276279688e-07, "loss": 0.7811, "step": 299930 }, { "epoch": 24.93, "learning_rate": 6.774048721004351e-07, "loss": 0.7469, "step": 299940 }, { "epoch": 24.93, "learning_rate": 6.772940165729013e-07, "loss": 0.7752, "step": 299950 }, { "epoch": 24.93, "learning_rate": 6.771831610453676e-07, "loss": 0.7277, "step": 299960 }, { "epoch": 24.93, "learning_rate": 6.770723055178339e-07, "loss": 0.7867, "step": 299970 }, { "epoch": 24.93, "learning_rate": 6.769614499903002e-07, "loss": 0.7441, "step": 299980 }, { "epoch": 24.93, "learning_rate": 6.768505944627664e-07, "loss": 0.7225, "step": 299990 }, { "epoch": 24.94, "learning_rate": 6.767397389352326e-07, "loss": 0.7502, "step": 300000 }, { "epoch": 24.94, "learning_rate": 6.766288834076988e-07, "loss": 0.7145, "step": 300010 }, { "epoch": 24.94, "learning_rate": 6.765180278801651e-07, "loss": 0.7442, "step": 300020 }, { "epoch": 24.94, "learning_rate": 6.764071723526314e-07, "loss": 0.6799, "step": 300030 }, { "epoch": 24.94, "learning_rate": 6.762963168250977e-07, "loss": 0.825, "step": 300040 }, { "epoch": 24.94, "learning_rate": 6.761854612975639e-07, "loss": 0.7862, "step": 300050 }, { "epoch": 24.94, "learning_rate": 6.760746057700302e-07, "loss": 0.7263, "step": 300060 }, { "epoch": 24.94, "learning_rate": 6.759637502424964e-07, "loss": 0.7359, "step": 300070 }, { "epoch": 24.94, "learning_rate": 6.758528947149627e-07, "loss": 0.6881, "step": 300080 }, { "epoch": 24.94, "learning_rate": 6.75742039187429e-07, "loss": 0.6813, "step": 300090 }, { "epoch": 24.94, "learning_rate": 6.756311836598953e-07, "loss": 0.8227, "step": 300100 }, { "epoch": 24.94, "learning_rate": 6.755203281323615e-07, "loss": 0.7199, "step": 300110 }, { "epoch": 24.95, "learning_rate": 6.754094726048278e-07, "loss": 0.7969, "step": 300120 }, { "epoch": 24.95, "learning_rate": 6.75298617077294e-07, "loss": 0.785, "step": 300130 }, { "epoch": 24.95, "learning_rate": 6.751877615497603e-07, "loss": 0.729, "step": 300140 }, { "epoch": 24.95, "learning_rate": 6.750769060222265e-07, "loss": 0.7703, "step": 300150 }, { "epoch": 24.95, "learning_rate": 6.749660504946928e-07, "loss": 0.8213, "step": 300160 }, { "epoch": 24.95, "learning_rate": 6.74855194967159e-07, "loss": 0.677, "step": 300170 }, { "epoch": 24.95, "learning_rate": 6.747443394396253e-07, "loss": 0.7062, "step": 300180 }, { "epoch": 24.95, "learning_rate": 6.746334839120915e-07, "loss": 0.7584, "step": 300190 }, { "epoch": 24.95, "learning_rate": 6.745226283845577e-07, "loss": 0.799, "step": 300200 }, { "epoch": 24.95, "learning_rate": 6.744117728570241e-07, "loss": 0.7524, "step": 300210 }, { "epoch": 24.95, "learning_rate": 6.743009173294903e-07, "loss": 0.7586, "step": 300220 }, { "epoch": 24.95, "learning_rate": 6.741900618019566e-07, "loss": 0.7296, "step": 300230 }, { "epoch": 24.96, "learning_rate": 6.740792062744228e-07, "loss": 0.725, "step": 300240 }, { "epoch": 24.96, "learning_rate": 6.739683507468891e-07, "loss": 0.7311, "step": 300250 }, { "epoch": 24.96, "learning_rate": 6.738574952193553e-07, "loss": 0.752, "step": 300260 }, { "epoch": 24.96, "learning_rate": 6.737466396918216e-07, "loss": 0.7152, "step": 300270 }, { "epoch": 24.96, "learning_rate": 6.736357841642879e-07, "loss": 0.741, "step": 300280 }, { "epoch": 24.96, "learning_rate": 6.735249286367542e-07, "loss": 0.7556, "step": 300290 }, { "epoch": 24.96, "learning_rate": 6.734140731092203e-07, "loss": 0.7138, "step": 300300 }, { "epoch": 24.96, "learning_rate": 6.733032175816866e-07, "loss": 0.809, "step": 300310 }, { "epoch": 24.96, "learning_rate": 6.731923620541528e-07, "loss": 0.7154, "step": 300320 }, { "epoch": 24.96, "learning_rate": 6.730815065266191e-07, "loss": 0.6837, "step": 300330 }, { "epoch": 24.96, "learning_rate": 6.729706509990854e-07, "loss": 0.6896, "step": 300340 }, { "epoch": 24.96, "learning_rate": 6.728597954715517e-07, "loss": 0.7881, "step": 300350 }, { "epoch": 24.97, "learning_rate": 6.727489399440179e-07, "loss": 0.7295, "step": 300360 }, { "epoch": 24.97, "learning_rate": 6.726380844164842e-07, "loss": 0.683, "step": 300370 }, { "epoch": 24.97, "learning_rate": 6.725272288889504e-07, "loss": 0.6661, "step": 300380 }, { "epoch": 24.97, "learning_rate": 6.724163733614167e-07, "loss": 0.7901, "step": 300390 }, { "epoch": 24.97, "learning_rate": 6.72305517833883e-07, "loss": 0.7554, "step": 300400 }, { "epoch": 24.97, "learning_rate": 6.721946623063493e-07, "loss": 0.7516, "step": 300410 }, { "epoch": 24.97, "learning_rate": 6.720838067788155e-07, "loss": 0.7698, "step": 300420 }, { "epoch": 24.97, "learning_rate": 6.719729512512818e-07, "loss": 0.7928, "step": 300430 }, { "epoch": 24.97, "learning_rate": 6.71862095723748e-07, "loss": 0.7301, "step": 300440 }, { "epoch": 24.97, "learning_rate": 6.717512401962142e-07, "loss": 0.7594, "step": 300450 }, { "epoch": 24.97, "learning_rate": 6.716403846686805e-07, "loss": 0.7575, "step": 300460 }, { "epoch": 24.97, "learning_rate": 6.715295291411468e-07, "loss": 0.7316, "step": 300470 }, { "epoch": 24.98, "learning_rate": 6.71418673613613e-07, "loss": 0.6919, "step": 300480 }, { "epoch": 24.98, "learning_rate": 6.713078180860793e-07, "loss": 0.7127, "step": 300490 }, { "epoch": 24.98, "learning_rate": 6.711969625585455e-07, "loss": 0.7274, "step": 300500 }, { "epoch": 24.98, "learning_rate": 6.710861070310118e-07, "loss": 0.7063, "step": 300510 }, { "epoch": 24.98, "learning_rate": 6.709752515034781e-07, "loss": 0.7034, "step": 300520 }, { "epoch": 24.98, "learning_rate": 6.708643959759444e-07, "loss": 0.7542, "step": 300530 }, { "epoch": 24.98, "learning_rate": 6.707535404484106e-07, "loss": 0.7237, "step": 300540 }, { "epoch": 24.98, "learning_rate": 6.706426849208769e-07, "loss": 0.7624, "step": 300550 }, { "epoch": 24.98, "learning_rate": 6.705318293933431e-07, "loss": 0.7651, "step": 300560 }, { "epoch": 24.98, "learning_rate": 6.704209738658094e-07, "loss": 0.7165, "step": 300570 }, { "epoch": 24.98, "learning_rate": 6.703101183382757e-07, "loss": 0.7604, "step": 300580 }, { "epoch": 24.98, "learning_rate": 6.70199262810742e-07, "loss": 0.7545, "step": 300590 }, { "epoch": 24.99, "learning_rate": 6.700884072832081e-07, "loss": 0.8094, "step": 300600 }, { "epoch": 24.99, "learning_rate": 6.699775517556743e-07, "loss": 0.7435, "step": 300610 }, { "epoch": 24.99, "learning_rate": 6.698666962281406e-07, "loss": 0.7082, "step": 300620 }, { "epoch": 24.99, "learning_rate": 6.697558407006068e-07, "loss": 0.7468, "step": 300630 }, { "epoch": 24.99, "learning_rate": 6.696449851730731e-07, "loss": 0.7899, "step": 300640 }, { "epoch": 24.99, "learning_rate": 6.695341296455394e-07, "loss": 0.8024, "step": 300650 }, { "epoch": 24.99, "learning_rate": 6.694232741180057e-07, "loss": 0.7602, "step": 300660 }, { "epoch": 24.99, "learning_rate": 6.693124185904719e-07, "loss": 0.7952, "step": 300670 }, { "epoch": 24.99, "learning_rate": 6.692015630629382e-07, "loss": 0.8111, "step": 300680 }, { "epoch": 24.99, "learning_rate": 6.690907075354044e-07, "loss": 0.7651, "step": 300690 }, { "epoch": 24.99, "learning_rate": 6.689798520078707e-07, "loss": 0.7834, "step": 300700 }, { "epoch": 24.99, "learning_rate": 6.68868996480337e-07, "loss": 0.7573, "step": 300710 }, { "epoch": 25.0, "learning_rate": 6.687581409528033e-07, "loss": 0.7636, "step": 300720 }, { "epoch": 25.0, "learning_rate": 6.686472854252695e-07, "loss": 0.6785, "step": 300730 }, { "epoch": 25.0, "learning_rate": 6.685364298977358e-07, "loss": 0.7737, "step": 300740 }, { "epoch": 25.0, "learning_rate": 6.684255743702019e-07, "loss": 0.7792, "step": 300750 }, { "epoch": 25.0, "learning_rate": 6.683147188426682e-07, "loss": 0.7177, "step": 300760 }, { "epoch": 25.0, "learning_rate": 6.682038633151345e-07, "loss": 0.7426, "step": 300770 }, { "epoch": 25.0, "eval_loss": 1.142024278640747, "eval_runtime": 349.7111, "eval_samples_per_second": 7.646, "eval_steps_per_second": 3.823, "eval_wer": 0.6361825655803703, "step": 300775 }, { "epoch": 25.0, "learning_rate": 6.680930077876008e-07, "loss": 0.802, "step": 300780 }, { "epoch": 25.0, "learning_rate": 6.67982152260067e-07, "loss": 0.7327, "step": 300790 }, { "epoch": 25.0, "learning_rate": 6.678712967325333e-07, "loss": 0.7549, "step": 300800 }, { "epoch": 25.0, "learning_rate": 6.677604412049995e-07, "loss": 0.7401, "step": 300810 }, { "epoch": 25.0, "learning_rate": 6.676495856774658e-07, "loss": 0.6857, "step": 300820 }, { "epoch": 25.0, "learning_rate": 6.675387301499321e-07, "loss": 0.7625, "step": 300830 }, { "epoch": 25.01, "learning_rate": 6.674278746223984e-07, "loss": 0.7573, "step": 300840 }, { "epoch": 25.01, "learning_rate": 6.673170190948646e-07, "loss": 0.7073, "step": 300850 }, { "epoch": 25.01, "learning_rate": 6.672061635673309e-07, "loss": 0.7231, "step": 300860 }, { "epoch": 25.01, "learning_rate": 6.670953080397971e-07, "loss": 0.7147, "step": 300870 }, { "epoch": 25.01, "learning_rate": 6.669844525122634e-07, "loss": 0.7583, "step": 300880 }, { "epoch": 25.01, "learning_rate": 6.668735969847297e-07, "loss": 0.7389, "step": 300890 }, { "epoch": 25.01, "learning_rate": 6.667627414571959e-07, "loss": 0.7179, "step": 300900 }, { "epoch": 25.01, "learning_rate": 6.666518859296621e-07, "loss": 0.7014, "step": 300910 }, { "epoch": 25.01, "learning_rate": 6.665410304021284e-07, "loss": 0.7166, "step": 300920 }, { "epoch": 25.01, "learning_rate": 6.664301748745946e-07, "loss": 0.7494, "step": 300930 }, { "epoch": 25.01, "learning_rate": 6.663193193470609e-07, "loss": 0.7456, "step": 300940 }, { "epoch": 25.01, "learning_rate": 6.662084638195272e-07, "loss": 0.6889, "step": 300950 }, { "epoch": 25.02, "learning_rate": 6.660976082919935e-07, "loss": 0.7887, "step": 300960 }, { "epoch": 25.02, "learning_rate": 6.659867527644597e-07, "loss": 0.7081, "step": 300970 }, { "epoch": 25.02, "learning_rate": 6.65875897236926e-07, "loss": 0.7407, "step": 300980 }, { "epoch": 25.02, "learning_rate": 6.657650417093922e-07, "loss": 0.7296, "step": 300990 }, { "epoch": 25.02, "learning_rate": 6.656541861818585e-07, "loss": 0.687, "step": 301000 }, { "epoch": 25.02, "learning_rate": 6.655433306543248e-07, "loss": 0.7566, "step": 301010 }, { "epoch": 25.02, "learning_rate": 6.654324751267911e-07, "loss": 0.7708, "step": 301020 }, { "epoch": 25.02, "learning_rate": 6.653216195992573e-07, "loss": 0.7783, "step": 301030 }, { "epoch": 25.02, "learning_rate": 6.652107640717234e-07, "loss": 0.7592, "step": 301040 }, { "epoch": 25.02, "learning_rate": 6.650999085441897e-07, "loss": 0.7418, "step": 301050 }, { "epoch": 25.02, "learning_rate": 6.649890530166559e-07, "loss": 0.7033, "step": 301060 }, { "epoch": 25.02, "learning_rate": 6.648781974891222e-07, "loss": 0.7991, "step": 301070 }, { "epoch": 25.03, "learning_rate": 6.647673419615885e-07, "loss": 0.7932, "step": 301080 }, { "epoch": 25.03, "learning_rate": 6.646564864340548e-07, "loss": 0.7084, "step": 301090 }, { "epoch": 25.03, "learning_rate": 6.64545630906521e-07, "loss": 0.7337, "step": 301100 }, { "epoch": 25.03, "learning_rate": 6.644347753789873e-07, "loss": 0.7283, "step": 301110 }, { "epoch": 25.03, "learning_rate": 6.643239198514535e-07, "loss": 0.723, "step": 301120 }, { "epoch": 25.03, "learning_rate": 6.642130643239198e-07, "loss": 0.7241, "step": 301130 }, { "epoch": 25.03, "learning_rate": 6.641022087963861e-07, "loss": 0.6774, "step": 301140 }, { "epoch": 25.03, "learning_rate": 6.639913532688524e-07, "loss": 0.6561, "step": 301150 }, { "epoch": 25.03, "learning_rate": 6.638804977413186e-07, "loss": 0.739, "step": 301160 }, { "epoch": 25.03, "learning_rate": 6.637696422137849e-07, "loss": 0.723, "step": 301170 }, { "epoch": 25.03, "learning_rate": 6.63658786686251e-07, "loss": 0.8472, "step": 301180 }, { "epoch": 25.03, "learning_rate": 6.635479311587173e-07, "loss": 0.7529, "step": 301190 }, { "epoch": 25.04, "learning_rate": 6.634370756311836e-07, "loss": 0.7181, "step": 301200 }, { "epoch": 25.04, "learning_rate": 6.633262201036499e-07, "loss": 0.7291, "step": 301210 }, { "epoch": 25.04, "learning_rate": 6.632153645761161e-07, "loss": 0.7266, "step": 301220 }, { "epoch": 25.04, "learning_rate": 6.631045090485824e-07, "loss": 0.8027, "step": 301230 }, { "epoch": 25.04, "learning_rate": 6.629936535210486e-07, "loss": 0.7499, "step": 301240 }, { "epoch": 25.04, "learning_rate": 6.628827979935149e-07, "loss": 0.7728, "step": 301250 }, { "epoch": 25.04, "learning_rate": 6.627719424659812e-07, "loss": 0.7015, "step": 301260 }, { "epoch": 25.04, "learning_rate": 6.626610869384475e-07, "loss": 0.717, "step": 301270 }, { "epoch": 25.04, "learning_rate": 6.62561316963667e-07, "loss": 0.7179, "step": 301280 }, { "epoch": 25.04, "learning_rate": 6.624504614361333e-07, "loss": 0.7377, "step": 301290 }, { "epoch": 25.04, "learning_rate": 6.623396059085996e-07, "loss": 0.7355, "step": 301300 }, { "epoch": 25.04, "learning_rate": 6.622287503810658e-07, "loss": 0.7277, "step": 301310 }, { "epoch": 25.05, "learning_rate": 6.621178948535321e-07, "loss": 0.7118, "step": 301320 }, { "epoch": 25.05, "learning_rate": 6.620070393259983e-07, "loss": 0.7559, "step": 301330 }, { "epoch": 25.05, "learning_rate": 6.618961837984646e-07, "loss": 0.7182, "step": 301340 }, { "epoch": 25.05, "learning_rate": 6.617853282709309e-07, "loss": 0.6892, "step": 301350 }, { "epoch": 25.05, "learning_rate": 6.616744727433972e-07, "loss": 0.7254, "step": 301360 }, { "epoch": 25.05, "learning_rate": 6.615636172158634e-07, "loss": 0.6874, "step": 301370 }, { "epoch": 25.05, "learning_rate": 6.614527616883297e-07, "loss": 0.7937, "step": 301380 }, { "epoch": 25.05, "learning_rate": 6.613419061607959e-07, "loss": 0.7435, "step": 301390 }, { "epoch": 25.05, "learning_rate": 6.612310506332622e-07, "loss": 0.6614, "step": 301400 }, { "epoch": 25.05, "learning_rate": 6.611201951057285e-07, "loss": 0.7259, "step": 301410 }, { "epoch": 25.05, "learning_rate": 6.610093395781947e-07, "loss": 0.7423, "step": 301420 }, { "epoch": 25.05, "learning_rate": 6.608984840506609e-07, "loss": 0.7476, "step": 301430 }, { "epoch": 25.06, "learning_rate": 6.607876285231272e-07, "loss": 0.6979, "step": 301440 }, { "epoch": 25.06, "learning_rate": 6.606767729955934e-07, "loss": 0.7057, "step": 301450 }, { "epoch": 25.06, "learning_rate": 6.605659174680597e-07, "loss": 0.6906, "step": 301460 }, { "epoch": 25.06, "learning_rate": 6.60455061940526e-07, "loss": 0.7131, "step": 301470 }, { "epoch": 25.06, "learning_rate": 6.603442064129923e-07, "loss": 0.741, "step": 301480 }, { "epoch": 25.06, "learning_rate": 6.602333508854585e-07, "loss": 0.7594, "step": 301490 }, { "epoch": 25.06, "learning_rate": 6.601224953579248e-07, "loss": 0.7414, "step": 301500 }, { "epoch": 25.06, "learning_rate": 6.60011639830391e-07, "loss": 0.6972, "step": 301510 }, { "epoch": 25.06, "learning_rate": 6.599007843028573e-07, "loss": 0.7717, "step": 301520 }, { "epoch": 25.06, "learning_rate": 6.597899287753236e-07, "loss": 0.7987, "step": 301530 }, { "epoch": 25.06, "learning_rate": 6.596790732477899e-07, "loss": 0.7387, "step": 301540 }, { "epoch": 25.06, "learning_rate": 6.595682177202561e-07, "loss": 0.7784, "step": 301550 }, { "epoch": 25.07, "learning_rate": 6.594573621927224e-07, "loss": 0.7447, "step": 301560 }, { "epoch": 25.07, "learning_rate": 6.593465066651885e-07, "loss": 0.7631, "step": 301570 }, { "epoch": 25.07, "learning_rate": 6.592356511376547e-07, "loss": 0.7762, "step": 301580 }, { "epoch": 25.07, "learning_rate": 6.591247956101211e-07, "loss": 0.7285, "step": 301590 }, { "epoch": 25.07, "learning_rate": 6.590139400825873e-07, "loss": 0.6935, "step": 301600 }, { "epoch": 25.07, "learning_rate": 6.589030845550536e-07, "loss": 0.6636, "step": 301610 }, { "epoch": 25.07, "learning_rate": 6.587922290275198e-07, "loss": 0.7217, "step": 301620 }, { "epoch": 25.07, "learning_rate": 6.586813734999861e-07, "loss": 0.7512, "step": 301630 }, { "epoch": 25.07, "learning_rate": 6.585705179724523e-07, "loss": 0.8126, "step": 301640 }, { "epoch": 25.07, "learning_rate": 6.584596624449187e-07, "loss": 0.736, "step": 301650 }, { "epoch": 25.07, "learning_rate": 6.583488069173849e-07, "loss": 0.7289, "step": 301660 }, { "epoch": 25.07, "learning_rate": 6.582379513898512e-07, "loss": 0.6908, "step": 301670 }, { "epoch": 25.08, "learning_rate": 6.581270958623174e-07, "loss": 0.795, "step": 301680 }, { "epoch": 25.08, "learning_rate": 6.580162403347837e-07, "loss": 0.7703, "step": 301690 }, { "epoch": 25.08, "learning_rate": 6.579053848072499e-07, "loss": 0.7232, "step": 301700 }, { "epoch": 25.08, "learning_rate": 6.577945292797161e-07, "loss": 0.7278, "step": 301710 }, { "epoch": 25.08, "learning_rate": 6.576836737521824e-07, "loss": 0.6843, "step": 301720 }, { "epoch": 25.08, "learning_rate": 6.575728182246487e-07, "loss": 0.7614, "step": 301730 }, { "epoch": 25.08, "learning_rate": 6.574619626971149e-07, "loss": 0.7177, "step": 301740 }, { "epoch": 25.08, "learning_rate": 6.573511071695812e-07, "loss": 0.7379, "step": 301750 }, { "epoch": 25.08, "learning_rate": 6.572402516420474e-07, "loss": 0.7405, "step": 301760 }, { "epoch": 25.08, "learning_rate": 6.571293961145137e-07, "loss": 0.7123, "step": 301770 }, { "epoch": 25.08, "learning_rate": 6.5701854058698e-07, "loss": 0.7261, "step": 301780 }, { "epoch": 25.08, "learning_rate": 6.569076850594463e-07, "loss": 0.757, "step": 301790 }, { "epoch": 25.09, "learning_rate": 6.567968295319125e-07, "loss": 0.7274, "step": 301800 }, { "epoch": 25.09, "learning_rate": 6.566859740043788e-07, "loss": 0.8061, "step": 301810 }, { "epoch": 25.09, "learning_rate": 6.56575118476845e-07, "loss": 0.6911, "step": 301820 }, { "epoch": 25.09, "learning_rate": 6.564642629493113e-07, "loss": 0.7071, "step": 301830 }, { "epoch": 25.09, "learning_rate": 6.563534074217776e-07, "loss": 0.7671, "step": 301840 }, { "epoch": 25.09, "learning_rate": 6.562425518942439e-07, "loss": 0.6953, "step": 301850 }, { "epoch": 25.09, "learning_rate": 6.5613169636671e-07, "loss": 0.7511, "step": 301860 }, { "epoch": 25.09, "learning_rate": 6.560208408391763e-07, "loss": 0.7538, "step": 301870 }, { "epoch": 25.09, "learning_rate": 6.559099853116425e-07, "loss": 0.7675, "step": 301880 }, { "epoch": 25.09, "learning_rate": 6.557991297841088e-07, "loss": 0.7397, "step": 301890 }, { "epoch": 25.09, "learning_rate": 6.556882742565751e-07, "loss": 0.7278, "step": 301900 }, { "epoch": 25.09, "learning_rate": 6.555774187290414e-07, "loss": 0.7125, "step": 301910 }, { "epoch": 25.1, "learning_rate": 6.554665632015076e-07, "loss": 0.7402, "step": 301920 }, { "epoch": 25.1, "learning_rate": 6.553557076739739e-07, "loss": 0.7475, "step": 301930 }, { "epoch": 25.1, "learning_rate": 6.552448521464401e-07, "loss": 0.7513, "step": 301940 }, { "epoch": 25.1, "learning_rate": 6.551339966189064e-07, "loss": 0.693, "step": 301950 }, { "epoch": 25.1, "learning_rate": 6.550231410913727e-07, "loss": 0.7034, "step": 301960 }, { "epoch": 25.1, "learning_rate": 6.54912285563839e-07, "loss": 0.7736, "step": 301970 }, { "epoch": 25.1, "learning_rate": 6.548014300363052e-07, "loss": 0.7166, "step": 301980 }, { "epoch": 25.1, "learning_rate": 6.546905745087714e-07, "loss": 0.7274, "step": 301990 }, { "epoch": 25.1, "learning_rate": 6.545797189812377e-07, "loss": 0.7449, "step": 302000 }, { "epoch": 25.1, "learning_rate": 6.544688634537038e-07, "loss": 0.751, "step": 302010 }, { "epoch": 25.1, "learning_rate": 6.543580079261702e-07, "loss": 0.7187, "step": 302020 }, { "epoch": 25.1, "learning_rate": 6.542471523986364e-07, "loss": 0.7405, "step": 302030 }, { "epoch": 25.11, "learning_rate": 6.541362968711027e-07, "loss": 0.6994, "step": 302040 }, { "epoch": 25.11, "learning_rate": 6.540254413435689e-07, "loss": 0.7173, "step": 302050 }, { "epoch": 25.11, "learning_rate": 6.539145858160352e-07, "loss": 0.6968, "step": 302060 }, { "epoch": 25.11, "learning_rate": 6.538037302885014e-07, "loss": 0.7877, "step": 302070 }, { "epoch": 25.11, "learning_rate": 6.536928747609678e-07, "loss": 0.7429, "step": 302080 }, { "epoch": 25.11, "learning_rate": 6.53582019233434e-07, "loss": 0.739, "step": 302090 }, { "epoch": 25.11, "learning_rate": 6.534711637059003e-07, "loss": 0.6732, "step": 302100 }, { "epoch": 25.11, "learning_rate": 6.533603081783665e-07, "loss": 0.7306, "step": 302110 }, { "epoch": 25.11, "learning_rate": 6.532494526508328e-07, "loss": 0.7458, "step": 302120 }, { "epoch": 25.11, "learning_rate": 6.53138597123299e-07, "loss": 0.76, "step": 302130 }, { "epoch": 25.11, "learning_rate": 6.530277415957653e-07, "loss": 0.7685, "step": 302140 }, { "epoch": 25.11, "learning_rate": 6.529168860682316e-07, "loss": 0.7593, "step": 302150 }, { "epoch": 25.12, "learning_rate": 6.528060305406978e-07, "loss": 0.7322, "step": 302160 }, { "epoch": 25.12, "learning_rate": 6.52695175013164e-07, "loss": 0.7736, "step": 302170 }, { "epoch": 25.12, "learning_rate": 6.525843194856303e-07, "loss": 0.7683, "step": 302180 }, { "epoch": 25.12, "learning_rate": 6.524734639580965e-07, "loss": 0.7491, "step": 302190 }, { "epoch": 25.12, "learning_rate": 6.523626084305628e-07, "loss": 0.7457, "step": 302200 }, { "epoch": 25.12, "learning_rate": 6.522517529030291e-07, "loss": 0.7566, "step": 302210 }, { "epoch": 25.12, "learning_rate": 6.521408973754954e-07, "loss": 0.7649, "step": 302220 }, { "epoch": 25.12, "learning_rate": 6.520300418479616e-07, "loss": 0.7766, "step": 302230 }, { "epoch": 25.12, "learning_rate": 6.519191863204279e-07, "loss": 0.7485, "step": 302240 }, { "epoch": 25.12, "learning_rate": 6.518083307928941e-07, "loss": 0.687, "step": 302250 }, { "epoch": 25.12, "learning_rate": 6.516974752653604e-07, "loss": 0.7613, "step": 302260 }, { "epoch": 25.12, "learning_rate": 6.515866197378267e-07, "loss": 0.7463, "step": 302270 }, { "epoch": 25.13, "learning_rate": 6.51475764210293e-07, "loss": 0.7406, "step": 302280 }, { "epoch": 25.13, "learning_rate": 6.513649086827592e-07, "loss": 0.7158, "step": 302290 }, { "epoch": 25.13, "learning_rate": 6.512540531552255e-07, "loss": 0.7116, "step": 302300 }, { "epoch": 25.13, "learning_rate": 6.511431976276916e-07, "loss": 0.7786, "step": 302310 }, { "epoch": 25.13, "learning_rate": 6.510323421001579e-07, "loss": 0.7597, "step": 302320 }, { "epoch": 25.13, "learning_rate": 6.509214865726242e-07, "loss": 0.7155, "step": 302330 }, { "epoch": 25.13, "learning_rate": 6.508106310450905e-07, "loss": 0.7449, "step": 302340 }, { "epoch": 25.13, "learning_rate": 6.506997755175567e-07, "loss": 0.7636, "step": 302350 }, { "epoch": 25.13, "learning_rate": 6.50588919990023e-07, "loss": 0.6845, "step": 302360 }, { "epoch": 25.13, "learning_rate": 6.504780644624892e-07, "loss": 0.7105, "step": 302370 }, { "epoch": 25.13, "learning_rate": 6.503672089349555e-07, "loss": 0.7512, "step": 302380 }, { "epoch": 25.13, "learning_rate": 6.502563534074218e-07, "loss": 0.7142, "step": 302390 }, { "epoch": 25.14, "learning_rate": 6.501454978798881e-07, "loss": 0.7567, "step": 302400 }, { "epoch": 25.14, "learning_rate": 6.500346423523543e-07, "loss": 0.7413, "step": 302410 }, { "epoch": 25.14, "learning_rate": 6.499237868248205e-07, "loss": 0.7364, "step": 302420 }, { "epoch": 25.14, "learning_rate": 6.498129312972868e-07, "loss": 0.7461, "step": 302430 }, { "epoch": 25.14, "learning_rate": 6.49702075769753e-07, "loss": 0.7609, "step": 302440 }, { "epoch": 25.14, "learning_rate": 6.495912202422194e-07, "loss": 0.7321, "step": 302450 }, { "epoch": 25.14, "learning_rate": 6.494803647146855e-07, "loss": 0.7128, "step": 302460 }, { "epoch": 25.14, "learning_rate": 6.493695091871518e-07, "loss": 0.6849, "step": 302470 }, { "epoch": 25.14, "learning_rate": 6.49258653659618e-07, "loss": 0.7382, "step": 302480 }, { "epoch": 25.14, "learning_rate": 6.491477981320843e-07, "loss": 0.7666, "step": 302490 }, { "epoch": 25.14, "learning_rate": 6.490369426045505e-07, "loss": 0.7351, "step": 302500 }, { "epoch": 25.14, "learning_rate": 6.489260870770169e-07, "loss": 0.7202, "step": 302510 }, { "epoch": 25.15, "learning_rate": 6.488152315494831e-07, "loss": 0.6947, "step": 302520 }, { "epoch": 25.15, "learning_rate": 6.487043760219494e-07, "loss": 0.743, "step": 302530 }, { "epoch": 25.15, "learning_rate": 6.485935204944156e-07, "loss": 0.7521, "step": 302540 }, { "epoch": 25.15, "learning_rate": 6.484826649668819e-07, "loss": 0.7562, "step": 302550 }, { "epoch": 25.15, "learning_rate": 6.483718094393481e-07, "loss": 0.7388, "step": 302560 }, { "epoch": 25.15, "learning_rate": 6.482609539118144e-07, "loss": 0.7272, "step": 302570 }, { "epoch": 25.15, "learning_rate": 6.481500983842807e-07, "loss": 0.775, "step": 302580 }, { "epoch": 25.15, "learning_rate": 6.48039242856747e-07, "loss": 0.7804, "step": 302590 }, { "epoch": 25.15, "learning_rate": 6.479283873292132e-07, "loss": 0.711, "step": 302600 }, { "epoch": 25.15, "learning_rate": 6.478175318016794e-07, "loss": 0.7335, "step": 302610 }, { "epoch": 25.15, "learning_rate": 6.477066762741456e-07, "loss": 0.7601, "step": 302620 }, { "epoch": 25.15, "learning_rate": 6.475958207466119e-07, "loss": 0.7676, "step": 302630 }, { "epoch": 25.16, "learning_rate": 6.474849652190782e-07, "loss": 0.7476, "step": 302640 }, { "epoch": 25.16, "learning_rate": 6.473741096915445e-07, "loss": 0.7435, "step": 302650 }, { "epoch": 25.16, "learning_rate": 6.472632541640107e-07, "loss": 0.741, "step": 302660 }, { "epoch": 25.16, "learning_rate": 6.47152398636477e-07, "loss": 0.7082, "step": 302670 }, { "epoch": 25.16, "learning_rate": 6.470415431089432e-07, "loss": 0.7659, "step": 302680 }, { "epoch": 25.16, "learning_rate": 6.469306875814095e-07, "loss": 0.752, "step": 302690 }, { "epoch": 25.16, "learning_rate": 6.468198320538758e-07, "loss": 0.7767, "step": 302700 }, { "epoch": 25.16, "learning_rate": 6.467089765263421e-07, "loss": 0.73, "step": 302710 }, { "epoch": 25.16, "learning_rate": 6.465981209988083e-07, "loss": 0.6714, "step": 302720 }, { "epoch": 25.16, "learning_rate": 6.464872654712746e-07, "loss": 0.7362, "step": 302730 }, { "epoch": 25.16, "learning_rate": 6.463764099437408e-07, "loss": 0.7523, "step": 302740 }, { "epoch": 25.16, "learning_rate": 6.46265554416207e-07, "loss": 0.6886, "step": 302750 }, { "epoch": 25.16, "learning_rate": 6.461546988886733e-07, "loss": 0.7348, "step": 302760 }, { "epoch": 25.17, "learning_rate": 6.460438433611396e-07, "loss": 0.7203, "step": 302770 }, { "epoch": 25.17, "learning_rate": 6.459329878336058e-07, "loss": 0.7663, "step": 302780 }, { "epoch": 25.17, "learning_rate": 6.458221323060721e-07, "loss": 0.7293, "step": 302790 }, { "epoch": 25.17, "learning_rate": 6.457112767785383e-07, "loss": 0.776, "step": 302800 }, { "epoch": 25.17, "learning_rate": 6.456004212510045e-07, "loss": 0.7072, "step": 302810 }, { "epoch": 25.17, "learning_rate": 6.454895657234709e-07, "loss": 0.726, "step": 302820 }, { "epoch": 25.17, "learning_rate": 6.453787101959371e-07, "loss": 0.7372, "step": 302830 }, { "epoch": 25.17, "learning_rate": 6.452678546684034e-07, "loss": 0.7107, "step": 302840 }, { "epoch": 25.17, "learning_rate": 6.451569991408696e-07, "loss": 0.6856, "step": 302850 }, { "epoch": 25.17, "learning_rate": 6.450461436133359e-07, "loss": 0.7509, "step": 302860 }, { "epoch": 25.17, "learning_rate": 6.449352880858021e-07, "loss": 0.6781, "step": 302870 }, { "epoch": 25.17, "learning_rate": 6.448244325582685e-07, "loss": 0.7425, "step": 302880 }, { "epoch": 25.18, "learning_rate": 6.447135770307347e-07, "loss": 0.7492, "step": 302890 }, { "epoch": 25.18, "learning_rate": 6.44602721503201e-07, "loss": 0.7307, "step": 302900 }, { "epoch": 25.18, "learning_rate": 6.444918659756671e-07, "loss": 0.7048, "step": 302910 }, { "epoch": 25.18, "learning_rate": 6.443810104481334e-07, "loss": 0.689, "step": 302920 }, { "epoch": 25.18, "learning_rate": 6.442701549205996e-07, "loss": 0.735, "step": 302930 }, { "epoch": 25.18, "learning_rate": 6.441592993930659e-07, "loss": 0.7076, "step": 302940 }, { "epoch": 25.18, "learning_rate": 6.440484438655322e-07, "loss": 0.7597, "step": 302950 }, { "epoch": 25.18, "learning_rate": 6.439375883379985e-07, "loss": 0.6626, "step": 302960 }, { "epoch": 25.18, "learning_rate": 6.438267328104647e-07, "loss": 0.7723, "step": 302970 }, { "epoch": 25.18, "learning_rate": 6.43715877282931e-07, "loss": 0.7571, "step": 302980 }, { "epoch": 25.18, "learning_rate": 6.436050217553972e-07, "loss": 0.7494, "step": 302990 }, { "epoch": 25.18, "learning_rate": 6.434941662278635e-07, "loss": 0.7044, "step": 303000 }, { "epoch": 25.19, "learning_rate": 6.433833107003298e-07, "loss": 0.7387, "step": 303010 }, { "epoch": 25.19, "learning_rate": 6.432724551727961e-07, "loss": 0.7503, "step": 303020 }, { "epoch": 25.19, "learning_rate": 6.431615996452623e-07, "loss": 0.7045, "step": 303030 }, { "epoch": 25.19, "learning_rate": 6.430507441177286e-07, "loss": 0.726, "step": 303040 }, { "epoch": 25.19, "learning_rate": 6.429398885901947e-07, "loss": 0.7419, "step": 303050 }, { "epoch": 25.19, "learning_rate": 6.42829033062661e-07, "loss": 0.715, "step": 303060 }, { "epoch": 25.19, "learning_rate": 6.427181775351273e-07, "loss": 0.7576, "step": 303070 }, { "epoch": 25.19, "learning_rate": 6.426073220075936e-07, "loss": 0.7893, "step": 303080 }, { "epoch": 25.19, "learning_rate": 6.424964664800598e-07, "loss": 0.7229, "step": 303090 }, { "epoch": 25.19, "learning_rate": 6.423856109525261e-07, "loss": 0.7317, "step": 303100 }, { "epoch": 25.19, "learning_rate": 6.422747554249923e-07, "loss": 0.6994, "step": 303110 }, { "epoch": 25.19, "learning_rate": 6.421638998974586e-07, "loss": 0.7629, "step": 303120 }, { "epoch": 25.2, "learning_rate": 6.420530443699249e-07, "loss": 0.75, "step": 303130 }, { "epoch": 25.2, "learning_rate": 6.419421888423912e-07, "loss": 0.6973, "step": 303140 }, { "epoch": 25.2, "learning_rate": 6.418313333148574e-07, "loss": 0.7153, "step": 303150 }, { "epoch": 25.2, "learning_rate": 6.417204777873237e-07, "loss": 0.7377, "step": 303160 }, { "epoch": 25.2, "learning_rate": 6.416096222597899e-07, "loss": 0.7226, "step": 303170 }, { "epoch": 25.2, "learning_rate": 6.414987667322562e-07, "loss": 0.7735, "step": 303180 }, { "epoch": 25.2, "learning_rate": 6.413879112047225e-07, "loss": 0.7228, "step": 303190 }, { "epoch": 25.2, "learning_rate": 6.412770556771888e-07, "loss": 0.7029, "step": 303200 }, { "epoch": 25.2, "learning_rate": 6.411662001496549e-07, "loss": 0.7022, "step": 303210 }, { "epoch": 25.2, "learning_rate": 6.410553446221212e-07, "loss": 0.7448, "step": 303220 }, { "epoch": 25.2, "learning_rate": 6.409444890945874e-07, "loss": 0.7735, "step": 303230 }, { "epoch": 25.2, "learning_rate": 6.408336335670536e-07, "loss": 0.7473, "step": 303240 }, { "epoch": 25.21, "learning_rate": 6.4072277803952e-07, "loss": 0.7499, "step": 303250 }, { "epoch": 25.21, "learning_rate": 6.406119225119862e-07, "loss": 0.7317, "step": 303260 }, { "epoch": 25.21, "learning_rate": 6.405010669844525e-07, "loss": 0.7003, "step": 303270 }, { "epoch": 25.21, "learning_rate": 6.403902114569187e-07, "loss": 0.8258, "step": 303280 }, { "epoch": 25.21, "learning_rate": 6.40279355929385e-07, "loss": 0.7998, "step": 303290 }, { "epoch": 25.21, "learning_rate": 6.401685004018512e-07, "loss": 0.7596, "step": 303300 }, { "epoch": 25.21, "learning_rate": 6.400576448743176e-07, "loss": 0.6635, "step": 303310 }, { "epoch": 25.21, "learning_rate": 6.399467893467838e-07, "loss": 0.7411, "step": 303320 }, { "epoch": 25.21, "learning_rate": 6.398359338192501e-07, "loss": 0.7343, "step": 303330 }, { "epoch": 25.21, "learning_rate": 6.397250782917163e-07, "loss": 0.7761, "step": 303340 }, { "epoch": 25.21, "learning_rate": 6.396142227641825e-07, "loss": 0.7072, "step": 303350 }, { "epoch": 25.21, "learning_rate": 6.395033672366487e-07, "loss": 0.7146, "step": 303360 }, { "epoch": 25.22, "learning_rate": 6.39392511709115e-07, "loss": 0.7457, "step": 303370 }, { "epoch": 25.22, "learning_rate": 6.392816561815813e-07, "loss": 0.7286, "step": 303380 }, { "epoch": 25.22, "learning_rate": 6.391818862068009e-07, "loss": 0.7002, "step": 303390 }, { "epoch": 25.22, "learning_rate": 6.390710306792673e-07, "loss": 0.7189, "step": 303400 }, { "epoch": 25.22, "learning_rate": 6.389601751517335e-07, "loss": 0.7478, "step": 303410 }, { "epoch": 25.22, "learning_rate": 6.388493196241998e-07, "loss": 0.712, "step": 303420 }, { "epoch": 25.22, "learning_rate": 6.387384640966659e-07, "loss": 0.7861, "step": 303430 }, { "epoch": 25.22, "learning_rate": 6.386276085691322e-07, "loss": 0.7505, "step": 303440 }, { "epoch": 25.22, "learning_rate": 6.385167530415984e-07, "loss": 0.7854, "step": 303450 }, { "epoch": 25.22, "learning_rate": 6.384058975140648e-07, "loss": 0.7308, "step": 303460 }, { "epoch": 25.22, "learning_rate": 6.38295041986531e-07, "loss": 0.6882, "step": 303470 }, { "epoch": 25.22, "learning_rate": 6.381841864589973e-07, "loss": 0.7536, "step": 303480 }, { "epoch": 25.23, "learning_rate": 6.380733309314635e-07, "loss": 0.7307, "step": 303490 }, { "epoch": 25.23, "learning_rate": 6.379624754039298e-07, "loss": 0.7522, "step": 303500 }, { "epoch": 25.23, "learning_rate": 6.37851619876396e-07, "loss": 0.7427, "step": 303510 }, { "epoch": 25.23, "learning_rate": 6.377407643488624e-07, "loss": 0.7295, "step": 303520 }, { "epoch": 25.23, "learning_rate": 6.376299088213286e-07, "loss": 0.7422, "step": 303530 }, { "epoch": 25.23, "learning_rate": 6.375190532937949e-07, "loss": 0.714, "step": 303540 }, { "epoch": 25.23, "learning_rate": 6.374081977662611e-07, "loss": 0.7517, "step": 303550 }, { "epoch": 25.23, "learning_rate": 6.372973422387274e-07, "loss": 0.7451, "step": 303560 }, { "epoch": 25.23, "learning_rate": 6.371864867111935e-07, "loss": 0.6829, "step": 303570 }, { "epoch": 25.23, "learning_rate": 6.370756311836598e-07, "loss": 0.7237, "step": 303580 }, { "epoch": 25.23, "learning_rate": 6.369647756561261e-07, "loss": 0.7422, "step": 303590 }, { "epoch": 25.23, "learning_rate": 6.368539201285924e-07, "loss": 0.7426, "step": 303600 }, { "epoch": 25.24, "learning_rate": 6.367430646010586e-07, "loss": 0.7417, "step": 303610 }, { "epoch": 25.24, "learning_rate": 6.366322090735249e-07, "loss": 0.797, "step": 303620 }, { "epoch": 25.24, "learning_rate": 6.365213535459911e-07, "loss": 0.7576, "step": 303630 }, { "epoch": 25.24, "learning_rate": 6.364104980184574e-07, "loss": 0.7078, "step": 303640 }, { "epoch": 25.24, "learning_rate": 6.362996424909237e-07, "loss": 0.7594, "step": 303650 }, { "epoch": 25.24, "learning_rate": 6.3618878696339e-07, "loss": 0.7859, "step": 303660 }, { "epoch": 25.24, "learning_rate": 6.360779314358562e-07, "loss": 0.7246, "step": 303670 }, { "epoch": 25.24, "learning_rate": 6.359670759083225e-07, "loss": 0.7215, "step": 303680 }, { "epoch": 25.24, "learning_rate": 6.358562203807887e-07, "loss": 0.7386, "step": 303690 }, { "epoch": 25.24, "learning_rate": 6.35745364853255e-07, "loss": 0.7487, "step": 303700 }, { "epoch": 25.24, "learning_rate": 6.356345093257213e-07, "loss": 0.6952, "step": 303710 }, { "epoch": 25.24, "learning_rate": 6.355236537981876e-07, "loss": 0.7127, "step": 303720 }, { "epoch": 25.25, "learning_rate": 6.354127982706537e-07, "loss": 0.7625, "step": 303730 }, { "epoch": 25.25, "learning_rate": 6.3530194274312e-07, "loss": 0.7295, "step": 303740 }, { "epoch": 25.25, "learning_rate": 6.351910872155862e-07, "loss": 0.7113, "step": 303750 }, { "epoch": 25.25, "learning_rate": 6.350802316880524e-07, "loss": 0.7052, "step": 303760 }, { "epoch": 25.25, "learning_rate": 6.349693761605188e-07, "loss": 0.7335, "step": 303770 }, { "epoch": 25.25, "learning_rate": 6.348585206329851e-07, "loss": 0.7745, "step": 303780 }, { "epoch": 25.25, "learning_rate": 6.347476651054513e-07, "loss": 0.7438, "step": 303790 }, { "epoch": 25.25, "learning_rate": 6.346368095779175e-07, "loss": 0.7018, "step": 303800 }, { "epoch": 25.25, "learning_rate": 6.345259540503838e-07, "loss": 0.6973, "step": 303810 }, { "epoch": 25.25, "learning_rate": 6.3441509852285e-07, "loss": 0.7323, "step": 303820 }, { "epoch": 25.25, "learning_rate": 6.343042429953164e-07, "loss": 0.7522, "step": 303830 }, { "epoch": 25.25, "learning_rate": 6.341933874677826e-07, "loss": 0.7377, "step": 303840 }, { "epoch": 25.26, "learning_rate": 6.340825319402489e-07, "loss": 0.7451, "step": 303850 }, { "epoch": 25.26, "learning_rate": 6.339716764127151e-07, "loss": 0.7489, "step": 303860 }, { "epoch": 25.26, "learning_rate": 6.338608208851813e-07, "loss": 0.731, "step": 303870 }, { "epoch": 25.26, "learning_rate": 6.337499653576475e-07, "loss": 0.7479, "step": 303880 }, { "epoch": 25.26, "learning_rate": 6.336391098301139e-07, "loss": 0.7818, "step": 303890 }, { "epoch": 25.26, "learning_rate": 6.335282543025801e-07, "loss": 0.7991, "step": 303900 }, { "epoch": 25.26, "learning_rate": 6.334173987750464e-07, "loss": 0.721, "step": 303910 }, { "epoch": 25.26, "learning_rate": 6.333065432475126e-07, "loss": 0.6828, "step": 303920 }, { "epoch": 25.26, "learning_rate": 6.331956877199789e-07, "loss": 0.7738, "step": 303930 }, { "epoch": 25.26, "learning_rate": 6.330848321924451e-07, "loss": 0.7522, "step": 303940 }, { "epoch": 25.26, "learning_rate": 6.329739766649115e-07, "loss": 0.697, "step": 303950 }, { "epoch": 25.26, "learning_rate": 6.328631211373777e-07, "loss": 0.7342, "step": 303960 }, { "epoch": 25.27, "learning_rate": 6.32752265609844e-07, "loss": 0.7614, "step": 303970 }, { "epoch": 25.27, "learning_rate": 6.326414100823102e-07, "loss": 0.7412, "step": 303980 }, { "epoch": 25.27, "learning_rate": 6.325305545547765e-07, "loss": 0.7638, "step": 303990 }, { "epoch": 25.27, "learning_rate": 6.324196990272427e-07, "loss": 0.8001, "step": 304000 }, { "epoch": 25.27, "learning_rate": 6.32308843499709e-07, "loss": 0.7022, "step": 304010 }, { "epoch": 25.27, "learning_rate": 6.321979879721752e-07, "loss": 0.6922, "step": 304020 }, { "epoch": 25.27, "learning_rate": 6.320871324446415e-07, "loss": 0.787, "step": 304030 }, { "epoch": 25.27, "learning_rate": 6.319762769171077e-07, "loss": 0.7203, "step": 304040 }, { "epoch": 25.27, "learning_rate": 6.31865421389574e-07, "loss": 0.7183, "step": 304050 }, { "epoch": 25.27, "learning_rate": 6.317545658620402e-07, "loss": 0.7013, "step": 304060 }, { "epoch": 25.27, "learning_rate": 6.316437103345065e-07, "loss": 0.7249, "step": 304070 }, { "epoch": 25.27, "learning_rate": 6.315328548069728e-07, "loss": 0.7224, "step": 304080 }, { "epoch": 25.28, "learning_rate": 6.314219992794391e-07, "loss": 0.742, "step": 304090 }, { "epoch": 25.28, "learning_rate": 6.313111437519053e-07, "loss": 0.7062, "step": 304100 }, { "epoch": 25.28, "learning_rate": 6.312002882243716e-07, "loss": 0.7339, "step": 304110 }, { "epoch": 25.28, "learning_rate": 6.310894326968378e-07, "loss": 0.7746, "step": 304120 }, { "epoch": 25.28, "learning_rate": 6.309785771693041e-07, "loss": 0.7171, "step": 304130 }, { "epoch": 25.28, "learning_rate": 6.308677216417704e-07, "loss": 0.7059, "step": 304140 }, { "epoch": 25.28, "learning_rate": 6.307568661142367e-07, "loss": 0.6996, "step": 304150 }, { "epoch": 25.28, "learning_rate": 6.306460105867029e-07, "loss": 0.753, "step": 304160 }, { "epoch": 25.28, "learning_rate": 6.305351550591691e-07, "loss": 0.6984, "step": 304170 }, { "epoch": 25.28, "learning_rate": 6.304242995316353e-07, "loss": 0.783, "step": 304180 }, { "epoch": 25.28, "learning_rate": 6.303134440041015e-07, "loss": 0.7282, "step": 304190 }, { "epoch": 25.28, "learning_rate": 6.302025884765679e-07, "loss": 0.7506, "step": 304200 }, { "epoch": 25.29, "learning_rate": 6.300917329490341e-07, "loss": 0.7518, "step": 304210 }, { "epoch": 25.29, "learning_rate": 6.299808774215004e-07, "loss": 0.7094, "step": 304220 }, { "epoch": 25.29, "learning_rate": 6.298700218939666e-07, "loss": 0.7635, "step": 304230 }, { "epoch": 25.29, "learning_rate": 6.297591663664329e-07, "loss": 0.7607, "step": 304240 }, { "epoch": 25.29, "learning_rate": 6.296483108388991e-07, "loss": 0.7424, "step": 304250 }, { "epoch": 25.29, "learning_rate": 6.295374553113655e-07, "loss": 0.714, "step": 304260 }, { "epoch": 25.29, "learning_rate": 6.294265997838317e-07, "loss": 0.752, "step": 304270 }, { "epoch": 25.29, "learning_rate": 6.29315744256298e-07, "loss": 0.7369, "step": 304280 }, { "epoch": 25.29, "learning_rate": 6.292048887287642e-07, "loss": 0.7061, "step": 304290 }, { "epoch": 25.29, "learning_rate": 6.290940332012305e-07, "loss": 0.745, "step": 304300 }, { "epoch": 25.29, "learning_rate": 6.289831776736966e-07, "loss": 0.7871, "step": 304310 }, { "epoch": 25.29, "learning_rate": 6.28872322146163e-07, "loss": 0.7972, "step": 304320 }, { "epoch": 25.3, "learning_rate": 6.287614666186292e-07, "loss": 0.6913, "step": 304330 }, { "epoch": 25.3, "learning_rate": 6.286506110910955e-07, "loss": 0.6935, "step": 304340 }, { "epoch": 25.3, "learning_rate": 6.285397555635617e-07, "loss": 0.6384, "step": 304350 }, { "epoch": 25.3, "learning_rate": 6.28428900036028e-07, "loss": 0.7496, "step": 304360 }, { "epoch": 25.3, "learning_rate": 6.283180445084942e-07, "loss": 0.7041, "step": 304370 }, { "epoch": 25.3, "learning_rate": 6.282071889809606e-07, "loss": 0.7446, "step": 304380 }, { "epoch": 25.3, "learning_rate": 6.280963334534268e-07, "loss": 0.7534, "step": 304390 }, { "epoch": 25.3, "learning_rate": 6.279854779258931e-07, "loss": 0.7928, "step": 304400 }, { "epoch": 25.3, "learning_rate": 6.278746223983593e-07, "loss": 0.7665, "step": 304410 }, { "epoch": 25.3, "learning_rate": 6.277637668708256e-07, "loss": 0.7626, "step": 304420 }, { "epoch": 25.3, "learning_rate": 6.276529113432918e-07, "loss": 0.748, "step": 304430 }, { "epoch": 25.3, "learning_rate": 6.275420558157581e-07, "loss": 0.7112, "step": 304440 }, { "epoch": 25.31, "learning_rate": 6.274312002882244e-07, "loss": 0.7251, "step": 304450 }, { "epoch": 25.31, "learning_rate": 6.273203447606907e-07, "loss": 0.7534, "step": 304460 }, { "epoch": 25.31, "learning_rate": 6.272094892331568e-07, "loss": 0.7094, "step": 304470 }, { "epoch": 25.31, "learning_rate": 6.270986337056231e-07, "loss": 0.8042, "step": 304480 }, { "epoch": 25.31, "learning_rate": 6.269877781780893e-07, "loss": 0.7697, "step": 304490 }, { "epoch": 25.31, "learning_rate": 6.268769226505556e-07, "loss": 0.7394, "step": 304500 }, { "epoch": 25.31, "learning_rate": 6.267660671230219e-07, "loss": 0.7319, "step": 304510 }, { "epoch": 25.31, "learning_rate": 6.266552115954882e-07, "loss": 0.7422, "step": 304520 }, { "epoch": 25.31, "learning_rate": 6.265443560679544e-07, "loss": 0.7454, "step": 304530 }, { "epoch": 25.31, "learning_rate": 6.264335005404207e-07, "loss": 0.7466, "step": 304540 }, { "epoch": 25.31, "learning_rate": 6.263226450128869e-07, "loss": 0.751, "step": 304550 }, { "epoch": 25.31, "learning_rate": 6.262117894853532e-07, "loss": 0.6986, "step": 304560 }, { "epoch": 25.32, "learning_rate": 6.261009339578195e-07, "loss": 0.7438, "step": 304570 }, { "epoch": 25.32, "learning_rate": 6.259900784302858e-07, "loss": 0.8277, "step": 304580 }, { "epoch": 25.32, "learning_rate": 6.25879222902752e-07, "loss": 0.7246, "step": 304590 }, { "epoch": 25.32, "learning_rate": 6.257683673752183e-07, "loss": 0.7091, "step": 304600 }, { "epoch": 25.32, "learning_rate": 6.256575118476845e-07, "loss": 0.7308, "step": 304610 }, { "epoch": 25.32, "learning_rate": 6.255466563201506e-07, "loss": 0.7507, "step": 304620 }, { "epoch": 25.32, "learning_rate": 6.25435800792617e-07, "loss": 0.7419, "step": 304630 }, { "epoch": 25.32, "learning_rate": 6.253249452650832e-07, "loss": 0.6967, "step": 304640 }, { "epoch": 25.32, "learning_rate": 6.252140897375495e-07, "loss": 0.7331, "step": 304650 }, { "epoch": 25.32, "learning_rate": 6.251032342100157e-07, "loss": 0.7232, "step": 304660 }, { "epoch": 25.32, "learning_rate": 6.24992378682482e-07, "loss": 0.6746, "step": 304670 }, { "epoch": 25.32, "learning_rate": 6.248815231549482e-07, "loss": 0.7641, "step": 304680 }, { "epoch": 25.33, "learning_rate": 6.247706676274146e-07, "loss": 0.7924, "step": 304690 }, { "epoch": 25.33, "learning_rate": 6.246598120998808e-07, "loss": 0.7157, "step": 304700 }, { "epoch": 25.33, "learning_rate": 6.245489565723471e-07, "loss": 0.7089, "step": 304710 }, { "epoch": 25.33, "learning_rate": 6.244381010448133e-07, "loss": 0.7306, "step": 304720 }, { "epoch": 25.33, "learning_rate": 6.243272455172796e-07, "loss": 0.7346, "step": 304730 }, { "epoch": 25.33, "learning_rate": 6.242163899897458e-07, "loss": 0.6793, "step": 304740 }, { "epoch": 25.33, "learning_rate": 6.241055344622122e-07, "loss": 0.6873, "step": 304750 }, { "epoch": 25.33, "learning_rate": 6.239946789346784e-07, "loss": 0.8019, "step": 304760 }, { "epoch": 25.33, "learning_rate": 6.238838234071446e-07, "loss": 0.7789, "step": 304770 }, { "epoch": 25.33, "learning_rate": 6.237729678796108e-07, "loss": 0.805, "step": 304780 }, { "epoch": 25.33, "learning_rate": 6.236621123520771e-07, "loss": 0.7313, "step": 304790 }, { "epoch": 25.33, "learning_rate": 6.235512568245433e-07, "loss": 0.6991, "step": 304800 }, { "epoch": 25.34, "learning_rate": 6.234404012970097e-07, "loss": 0.7514, "step": 304810 }, { "epoch": 25.34, "learning_rate": 6.233295457694759e-07, "loss": 0.7357, "step": 304820 }, { "epoch": 25.34, "learning_rate": 6.232186902419422e-07, "loss": 0.7587, "step": 304830 }, { "epoch": 25.34, "learning_rate": 6.231078347144084e-07, "loss": 0.7301, "step": 304840 }, { "epoch": 25.34, "learning_rate": 6.229969791868747e-07, "loss": 0.7624, "step": 304850 }, { "epoch": 25.34, "learning_rate": 6.228861236593409e-07, "loss": 0.7796, "step": 304860 }, { "epoch": 25.34, "learning_rate": 6.227752681318072e-07, "loss": 0.6772, "step": 304870 }, { "epoch": 25.34, "learning_rate": 6.226644126042735e-07, "loss": 0.7142, "step": 304880 }, { "epoch": 25.34, "learning_rate": 6.225535570767398e-07, "loss": 0.7155, "step": 304890 }, { "epoch": 25.34, "learning_rate": 6.22442701549206e-07, "loss": 0.7264, "step": 304900 }, { "epoch": 25.34, "learning_rate": 6.223318460216723e-07, "loss": 0.7304, "step": 304910 }, { "epoch": 25.34, "learning_rate": 6.222209904941384e-07, "loss": 0.7733, "step": 304920 }, { "epoch": 25.35, "learning_rate": 6.221101349666047e-07, "loss": 0.79, "step": 304930 }, { "epoch": 25.35, "learning_rate": 6.21999279439071e-07, "loss": 0.8017, "step": 304940 }, { "epoch": 25.35, "learning_rate": 6.218884239115373e-07, "loss": 0.7483, "step": 304950 }, { "epoch": 25.35, "learning_rate": 6.217775683840035e-07, "loss": 0.785, "step": 304960 }, { "epoch": 25.35, "learning_rate": 6.216667128564698e-07, "loss": 0.7703, "step": 304970 }, { "epoch": 25.35, "learning_rate": 6.21555857328936e-07, "loss": 0.7885, "step": 304980 }, { "epoch": 25.35, "learning_rate": 6.214450018014023e-07, "loss": 0.813, "step": 304990 }, { "epoch": 25.35, "learning_rate": 6.213341462738686e-07, "loss": 0.7467, "step": 305000 }, { "epoch": 25.35, "learning_rate": 6.212232907463349e-07, "loss": 0.7433, "step": 305010 }, { "epoch": 25.35, "learning_rate": 6.211124352188011e-07, "loss": 0.6854, "step": 305020 }, { "epoch": 25.35, "learning_rate": 6.210015796912673e-07, "loss": 0.6995, "step": 305030 }, { "epoch": 25.35, "learning_rate": 6.208907241637336e-07, "loss": 0.7387, "step": 305040 }, { "epoch": 25.36, "learning_rate": 6.207798686361998e-07, "loss": 0.7647, "step": 305050 }, { "epoch": 25.36, "learning_rate": 6.206690131086662e-07, "loss": 0.7359, "step": 305060 }, { "epoch": 25.36, "learning_rate": 6.205581575811323e-07, "loss": 0.6662, "step": 305070 }, { "epoch": 25.36, "learning_rate": 6.204473020535986e-07, "loss": 0.7527, "step": 305080 }, { "epoch": 25.36, "learning_rate": 6.203364465260648e-07, "loss": 0.713, "step": 305090 }, { "epoch": 25.36, "learning_rate": 6.202255909985311e-07, "loss": 0.7393, "step": 305100 }, { "epoch": 25.36, "learning_rate": 6.201147354709973e-07, "loss": 0.7318, "step": 305110 }, { "epoch": 25.36, "learning_rate": 6.200038799434637e-07, "loss": 0.762, "step": 305120 }, { "epoch": 25.36, "learning_rate": 6.198930244159299e-07, "loss": 0.7765, "step": 305130 }, { "epoch": 25.36, "learning_rate": 6.197821688883962e-07, "loss": 0.8082, "step": 305140 }, { "epoch": 25.36, "learning_rate": 6.196713133608624e-07, "loss": 0.8015, "step": 305150 }, { "epoch": 25.36, "learning_rate": 6.195604578333287e-07, "loss": 0.7429, "step": 305160 }, { "epoch": 25.37, "learning_rate": 6.194496023057949e-07, "loss": 0.7328, "step": 305170 }, { "epoch": 25.37, "learning_rate": 6.193387467782613e-07, "loss": 0.7064, "step": 305180 }, { "epoch": 25.37, "learning_rate": 6.192278912507275e-07, "loss": 0.7594, "step": 305190 }, { "epoch": 25.37, "learning_rate": 6.191170357231938e-07, "loss": 0.7252, "step": 305200 }, { "epoch": 25.37, "learning_rate": 6.1900618019566e-07, "loss": 0.8148, "step": 305210 }, { "epoch": 25.37, "learning_rate": 6.188953246681262e-07, "loss": 0.7424, "step": 305220 }, { "epoch": 25.37, "learning_rate": 6.187844691405924e-07, "loss": 0.7534, "step": 305230 }, { "epoch": 25.37, "learning_rate": 6.186736136130587e-07, "loss": 0.7583, "step": 305240 }, { "epoch": 25.37, "learning_rate": 6.18562758085525e-07, "loss": 0.7335, "step": 305250 }, { "epoch": 25.37, "learning_rate": 6.184519025579913e-07, "loss": 0.7126, "step": 305260 }, { "epoch": 25.37, "learning_rate": 6.183410470304575e-07, "loss": 0.7704, "step": 305270 }, { "epoch": 25.37, "learning_rate": 6.182301915029238e-07, "loss": 0.737, "step": 305280 }, { "epoch": 25.38, "learning_rate": 6.1811933597539e-07, "loss": 0.7602, "step": 305290 }, { "epoch": 25.38, "learning_rate": 6.180084804478563e-07, "loss": 0.6976, "step": 305300 }, { "epoch": 25.38, "learning_rate": 6.178976249203226e-07, "loss": 0.695, "step": 305310 }, { "epoch": 25.38, "learning_rate": 6.177867693927889e-07, "loss": 0.7337, "step": 305320 }, { "epoch": 25.38, "learning_rate": 6.176759138652551e-07, "loss": 0.7654, "step": 305330 }, { "epoch": 25.38, "learning_rate": 6.175650583377214e-07, "loss": 0.7762, "step": 305340 }, { "epoch": 25.38, "learning_rate": 6.174542028101876e-07, "loss": 0.8002, "step": 305350 }, { "epoch": 25.38, "learning_rate": 6.173433472826538e-07, "loss": 0.7031, "step": 305360 }, { "epoch": 25.38, "learning_rate": 6.172324917551201e-07, "loss": 0.7547, "step": 305370 }, { "epoch": 25.38, "learning_rate": 6.171216362275864e-07, "loss": 0.6815, "step": 305380 }, { "epoch": 25.38, "learning_rate": 6.170107807000526e-07, "loss": 0.6889, "step": 305390 }, { "epoch": 25.38, "learning_rate": 6.168999251725189e-07, "loss": 0.7441, "step": 305400 }, { "epoch": 25.39, "learning_rate": 6.167890696449851e-07, "loss": 0.7549, "step": 305410 }, { "epoch": 25.39, "learning_rate": 6.166782141174514e-07, "loss": 0.7428, "step": 305420 }, { "epoch": 25.39, "learning_rate": 6.165784441426711e-07, "loss": 0.7621, "step": 305430 }, { "epoch": 25.39, "learning_rate": 6.164675886151372e-07, "loss": 0.6894, "step": 305440 }, { "epoch": 25.39, "learning_rate": 6.163567330876035e-07, "loss": 0.7981, "step": 305450 }, { "epoch": 25.39, "learning_rate": 6.162458775600698e-07, "loss": 0.7215, "step": 305460 }, { "epoch": 25.39, "learning_rate": 6.161350220325361e-07, "loss": 0.7638, "step": 305470 }, { "epoch": 25.39, "learning_rate": 6.160241665050023e-07, "loss": 0.7221, "step": 305480 }, { "epoch": 25.39, "learning_rate": 6.159133109774686e-07, "loss": 0.7679, "step": 305490 }, { "epoch": 25.39, "learning_rate": 6.158024554499348e-07, "loss": 0.7047, "step": 305500 }, { "epoch": 25.39, "learning_rate": 6.156915999224011e-07, "loss": 0.7659, "step": 305510 }, { "epoch": 25.39, "learning_rate": 6.155807443948674e-07, "loss": 0.7263, "step": 305520 }, { "epoch": 25.4, "learning_rate": 6.154698888673337e-07, "loss": 0.7916, "step": 305530 }, { "epoch": 25.4, "learning_rate": 6.153590333397999e-07, "loss": 0.7156, "step": 305540 }, { "epoch": 25.4, "learning_rate": 6.152481778122662e-07, "loss": 0.7383, "step": 305550 }, { "epoch": 25.4, "learning_rate": 6.151373222847324e-07, "loss": 0.702, "step": 305560 }, { "epoch": 25.4, "learning_rate": 6.150264667571986e-07, "loss": 0.7376, "step": 305570 }, { "epoch": 25.4, "learning_rate": 6.14915611229665e-07, "loss": 0.7415, "step": 305580 }, { "epoch": 25.4, "learning_rate": 6.148047557021311e-07, "loss": 0.712, "step": 305590 }, { "epoch": 25.4, "learning_rate": 6.146939001745974e-07, "loss": 0.7459, "step": 305600 }, { "epoch": 25.4, "learning_rate": 6.145830446470636e-07, "loss": 0.7599, "step": 305610 }, { "epoch": 25.4, "learning_rate": 6.144832746722834e-07, "loss": 0.7207, "step": 305620 }, { "epoch": 25.4, "learning_rate": 6.143724191447496e-07, "loss": 0.7765, "step": 305630 }, { "epoch": 25.4, "learning_rate": 6.142615636172159e-07, "loss": 0.7338, "step": 305640 }, { "epoch": 25.41, "learning_rate": 6.14150708089682e-07, "loss": 0.7536, "step": 305650 }, { "epoch": 25.41, "learning_rate": 6.140398525621483e-07, "loss": 0.8129, "step": 305660 }, { "epoch": 25.41, "learning_rate": 6.139289970346146e-07, "loss": 0.7614, "step": 305670 }, { "epoch": 25.41, "learning_rate": 6.138181415070809e-07, "loss": 0.7881, "step": 305680 }, { "epoch": 25.41, "learning_rate": 6.137072859795471e-07, "loss": 0.7653, "step": 305690 }, { "epoch": 25.41, "learning_rate": 6.135964304520133e-07, "loss": 0.7295, "step": 305700 }, { "epoch": 25.41, "learning_rate": 6.134855749244796e-07, "loss": 0.7258, "step": 305710 }, { "epoch": 25.41, "learning_rate": 6.133747193969458e-07, "loss": 0.724, "step": 305720 }, { "epoch": 25.41, "learning_rate": 6.132638638694122e-07, "loss": 0.7383, "step": 305730 }, { "epoch": 25.41, "learning_rate": 6.131530083418784e-07, "loss": 0.7633, "step": 305740 }, { "epoch": 25.41, "learning_rate": 6.130421528143447e-07, "loss": 0.743, "step": 305750 }, { "epoch": 25.41, "learning_rate": 6.129312972868109e-07, "loss": 0.6653, "step": 305760 }, { "epoch": 25.42, "learning_rate": 6.128204417592772e-07, "loss": 0.721, "step": 305770 }, { "epoch": 25.42, "learning_rate": 6.127095862317434e-07, "loss": 0.7651, "step": 305780 }, { "epoch": 25.42, "learning_rate": 6.125987307042098e-07, "loss": 0.8044, "step": 305790 }, { "epoch": 25.42, "learning_rate": 6.12487875176676e-07, "loss": 0.7355, "step": 305800 }, { "epoch": 25.42, "learning_rate": 6.123770196491422e-07, "loss": 0.7237, "step": 305810 }, { "epoch": 25.42, "learning_rate": 6.122661641216084e-07, "loss": 0.7005, "step": 305820 }, { "epoch": 25.42, "learning_rate": 6.121553085940747e-07, "loss": 0.7467, "step": 305830 }, { "epoch": 25.42, "learning_rate": 6.120444530665409e-07, "loss": 0.7279, "step": 305840 }, { "epoch": 25.42, "learning_rate": 6.119335975390073e-07, "loss": 0.7066, "step": 305850 }, { "epoch": 25.42, "learning_rate": 6.118227420114735e-07, "loss": 0.7086, "step": 305860 }, { "epoch": 25.42, "learning_rate": 6.117118864839398e-07, "loss": 0.7223, "step": 305870 }, { "epoch": 25.42, "learning_rate": 6.11601030956406e-07, "loss": 0.7723, "step": 305880 }, { "epoch": 25.43, "learning_rate": 6.114901754288723e-07, "loss": 0.7489, "step": 305890 }, { "epoch": 25.43, "learning_rate": 6.113793199013385e-07, "loss": 0.7657, "step": 305900 }, { "epoch": 25.43, "learning_rate": 6.112684643738049e-07, "loss": 0.7194, "step": 305910 }, { "epoch": 25.43, "learning_rate": 6.111576088462711e-07, "loss": 0.7193, "step": 305920 }, { "epoch": 25.43, "learning_rate": 6.110467533187374e-07, "loss": 0.7466, "step": 305930 }, { "epoch": 25.43, "learning_rate": 6.109358977912036e-07, "loss": 0.706, "step": 305940 }, { "epoch": 25.43, "learning_rate": 6.108250422636699e-07, "loss": 0.7076, "step": 305950 }, { "epoch": 25.43, "learning_rate": 6.10714186736136e-07, "loss": 0.755, "step": 305960 }, { "epoch": 25.43, "learning_rate": 6.106033312086024e-07, "loss": 0.6876, "step": 305970 }, { "epoch": 25.43, "learning_rate": 6.104924756810686e-07, "loss": 0.8117, "step": 305980 }, { "epoch": 25.43, "learning_rate": 6.103816201535349e-07, "loss": 0.7439, "step": 305990 }, { "epoch": 25.43, "learning_rate": 6.102707646260011e-07, "loss": 0.7171, "step": 306000 }, { "epoch": 25.44, "learning_rate": 6.101599090984674e-07, "loss": 0.7507, "step": 306010 }, { "epoch": 25.44, "learning_rate": 6.100490535709336e-07, "loss": 0.784, "step": 306020 }, { "epoch": 25.44, "learning_rate": 6.099381980434e-07, "loss": 0.7729, "step": 306030 }, { "epoch": 25.44, "learning_rate": 6.098273425158662e-07, "loss": 0.7223, "step": 306040 }, { "epoch": 25.44, "learning_rate": 6.097164869883325e-07, "loss": 0.7564, "step": 306050 }, { "epoch": 25.44, "learning_rate": 6.096056314607987e-07, "loss": 0.7112, "step": 306060 }, { "epoch": 25.44, "learning_rate": 6.09494775933265e-07, "loss": 0.7733, "step": 306070 }, { "epoch": 25.44, "learning_rate": 6.093839204057312e-07, "loss": 0.8055, "step": 306080 }, { "epoch": 25.44, "learning_rate": 6.092730648781975e-07, "loss": 0.7558, "step": 306090 }, { "epoch": 25.44, "learning_rate": 6.091622093506638e-07, "loss": 0.7374, "step": 306100 }, { "epoch": 25.44, "learning_rate": 6.0905135382313e-07, "loss": 0.6831, "step": 306110 }, { "epoch": 25.44, "learning_rate": 6.089404982955962e-07, "loss": 0.7307, "step": 306120 }, { "epoch": 25.45, "learning_rate": 6.088296427680624e-07, "loss": 0.7395, "step": 306130 }, { "epoch": 25.45, "learning_rate": 6.087187872405287e-07, "loss": 0.7123, "step": 306140 }, { "epoch": 25.45, "learning_rate": 6.086079317129949e-07, "loss": 0.731, "step": 306150 }, { "epoch": 25.45, "learning_rate": 6.084970761854613e-07, "loss": 0.7159, "step": 306160 }, { "epoch": 25.45, "learning_rate": 6.083862206579275e-07, "loss": 0.8076, "step": 306170 }, { "epoch": 25.45, "learning_rate": 6.082753651303938e-07, "loss": 0.8197, "step": 306180 }, { "epoch": 25.45, "learning_rate": 6.0816450960286e-07, "loss": 0.7632, "step": 306190 }, { "epoch": 25.45, "learning_rate": 6.080536540753263e-07, "loss": 0.7139, "step": 306200 }, { "epoch": 25.45, "learning_rate": 6.079427985477925e-07, "loss": 0.7273, "step": 306210 }, { "epoch": 25.45, "learning_rate": 6.078319430202589e-07, "loss": 0.6836, "step": 306220 }, { "epoch": 25.45, "learning_rate": 6.077210874927251e-07, "loss": 0.7315, "step": 306230 }, { "epoch": 25.45, "learning_rate": 6.076102319651914e-07, "loss": 0.7951, "step": 306240 }, { "epoch": 25.46, "learning_rate": 6.074993764376575e-07, "loss": 0.7226, "step": 306250 }, { "epoch": 25.46, "learning_rate": 6.073885209101238e-07, "loss": 0.69, "step": 306260 }, { "epoch": 25.46, "learning_rate": 6.0727766538259e-07, "loss": 0.708, "step": 306270 }, { "epoch": 25.46, "learning_rate": 6.071668098550564e-07, "loss": 0.7263, "step": 306280 }, { "epoch": 25.46, "learning_rate": 6.070559543275226e-07, "loss": 0.7301, "step": 306290 }, { "epoch": 25.46, "learning_rate": 6.069450987999889e-07, "loss": 0.747, "step": 306300 }, { "epoch": 25.46, "learning_rate": 6.068342432724551e-07, "loss": 0.6881, "step": 306310 }, { "epoch": 25.46, "learning_rate": 6.067233877449214e-07, "loss": 0.7305, "step": 306320 }, { "epoch": 25.46, "learning_rate": 6.066125322173876e-07, "loss": 0.7242, "step": 306330 }, { "epoch": 25.46, "learning_rate": 6.06501676689854e-07, "loss": 0.7326, "step": 306340 }, { "epoch": 25.46, "learning_rate": 6.063908211623202e-07, "loss": 0.7494, "step": 306350 }, { "epoch": 25.46, "learning_rate": 6.062799656347865e-07, "loss": 0.7515, "step": 306360 }, { "epoch": 25.47, "learning_rate": 6.061691101072527e-07, "loss": 0.75, "step": 306370 }, { "epoch": 25.47, "learning_rate": 6.06058254579719e-07, "loss": 0.751, "step": 306380 }, { "epoch": 25.47, "learning_rate": 6.059473990521852e-07, "loss": 0.7195, "step": 306390 }, { "epoch": 25.47, "learning_rate": 6.058365435246516e-07, "loss": 0.6436, "step": 306400 }, { "epoch": 25.47, "learning_rate": 6.057256879971177e-07, "loss": 0.78, "step": 306410 }, { "epoch": 25.47, "learning_rate": 6.05614832469584e-07, "loss": 0.7587, "step": 306420 }, { "epoch": 25.47, "learning_rate": 6.055039769420502e-07, "loss": 0.7291, "step": 306430 }, { "epoch": 25.47, "learning_rate": 6.053931214145165e-07, "loss": 0.7335, "step": 306440 }, { "epoch": 25.47, "learning_rate": 6.052822658869827e-07, "loss": 0.7471, "step": 306450 }, { "epoch": 25.47, "learning_rate": 6.051714103594491e-07, "loss": 0.7745, "step": 306460 }, { "epoch": 25.47, "learning_rate": 6.050605548319153e-07, "loss": 0.7469, "step": 306470 }, { "epoch": 25.47, "learning_rate": 6.049496993043816e-07, "loss": 0.7512, "step": 306480 }, { "epoch": 25.48, "learning_rate": 6.048388437768478e-07, "loss": 0.717, "step": 306490 }, { "epoch": 25.48, "learning_rate": 6.047279882493141e-07, "loss": 0.7329, "step": 306500 }, { "epoch": 25.48, "learning_rate": 6.046171327217803e-07, "loss": 0.7346, "step": 306510 }, { "epoch": 25.48, "learning_rate": 6.045062771942465e-07, "loss": 0.8379, "step": 306520 }, { "epoch": 25.48, "learning_rate": 6.043954216667129e-07, "loss": 0.7624, "step": 306530 }, { "epoch": 25.48, "learning_rate": 6.042845661391791e-07, "loss": 0.782, "step": 306540 }, { "epoch": 25.48, "learning_rate": 6.041737106116454e-07, "loss": 0.7591, "step": 306550 }, { "epoch": 25.48, "learning_rate": 6.040628550841115e-07, "loss": 0.752, "step": 306560 }, { "epoch": 25.48, "learning_rate": 6.039519995565778e-07, "loss": 0.7499, "step": 306570 }, { "epoch": 25.48, "learning_rate": 6.03841144029044e-07, "loss": 0.7895, "step": 306580 }, { "epoch": 25.48, "learning_rate": 6.037302885015104e-07, "loss": 0.7443, "step": 306590 }, { "epoch": 25.48, "learning_rate": 6.036194329739766e-07, "loss": 0.7538, "step": 306600 }, { "epoch": 25.48, "learning_rate": 6.035085774464429e-07, "loss": 0.7468, "step": 306610 }, { "epoch": 25.49, "learning_rate": 6.033977219189091e-07, "loss": 0.7448, "step": 306620 }, { "epoch": 25.49, "learning_rate": 6.032868663913754e-07, "loss": 0.737, "step": 306630 }, { "epoch": 25.49, "learning_rate": 6.031760108638416e-07, "loss": 0.77, "step": 306640 }, { "epoch": 25.49, "learning_rate": 6.03065155336308e-07, "loss": 0.7011, "step": 306650 }, { "epoch": 25.49, "learning_rate": 6.029542998087742e-07, "loss": 0.7275, "step": 306660 }, { "epoch": 25.49, "learning_rate": 6.028434442812405e-07, "loss": 0.7681, "step": 306670 }, { "epoch": 25.49, "learning_rate": 6.027325887537067e-07, "loss": 0.7552, "step": 306680 }, { "epoch": 25.49, "learning_rate": 6.02621733226173e-07, "loss": 0.6939, "step": 306690 }, { "epoch": 25.49, "learning_rate": 6.025108776986391e-07, "loss": 0.7321, "step": 306700 }, { "epoch": 25.49, "learning_rate": 6.024000221711055e-07, "loss": 0.7627, "step": 306710 }, { "epoch": 25.49, "learning_rate": 6.022891666435717e-07, "loss": 0.7921, "step": 306720 }, { "epoch": 25.49, "learning_rate": 6.02178311116038e-07, "loss": 0.7434, "step": 306730 }, { "epoch": 25.5, "learning_rate": 6.020674555885042e-07, "loss": 0.8013, "step": 306740 }, { "epoch": 25.5, "learning_rate": 6.019566000609705e-07, "loss": 0.7032, "step": 306750 }, { "epoch": 25.5, "learning_rate": 6.018457445334367e-07, "loss": 0.6889, "step": 306760 }, { "epoch": 25.5, "learning_rate": 6.017348890059031e-07, "loss": 0.7384, "step": 306770 }, { "epoch": 25.5, "learning_rate": 6.016240334783693e-07, "loss": 0.7145, "step": 306780 }, { "epoch": 25.5, "learning_rate": 6.015131779508356e-07, "loss": 0.8095, "step": 306790 }, { "epoch": 25.5, "learning_rate": 6.014023224233018e-07, "loss": 0.7328, "step": 306800 }, { "epoch": 25.5, "learning_rate": 6.012914668957681e-07, "loss": 0.7664, "step": 306810 }, { "epoch": 25.5, "learning_rate": 6.011806113682343e-07, "loss": 0.7071, "step": 306820 }, { "epoch": 25.5, "learning_rate": 6.010697558407007e-07, "loss": 0.6934, "step": 306830 }, { "epoch": 25.5, "learning_rate": 6.009589003131669e-07, "loss": 0.8032, "step": 306840 }, { "epoch": 25.5, "learning_rate": 6.008480447856332e-07, "loss": 0.7753, "step": 306850 }, { "epoch": 25.51, "learning_rate": 6.007371892580993e-07, "loss": 0.7306, "step": 306860 }, { "epoch": 25.51, "learning_rate": 6.006263337305656e-07, "loss": 0.7795, "step": 306870 }, { "epoch": 25.51, "learning_rate": 6.005154782030318e-07, "loss": 0.7738, "step": 306880 }, { "epoch": 25.51, "learning_rate": 6.004046226754982e-07, "loss": 0.7676, "step": 306890 }, { "epoch": 25.51, "learning_rate": 6.002937671479644e-07, "loss": 0.6665, "step": 306900 }, { "epoch": 25.51, "learning_rate": 6.001829116204307e-07, "loss": 0.7429, "step": 306910 }, { "epoch": 25.51, "learning_rate": 6.000720560928969e-07, "loss": 0.7003, "step": 306920 }, { "epoch": 25.51, "learning_rate": 5.999612005653632e-07, "loss": 0.7827, "step": 306930 }, { "epoch": 25.51, "learning_rate": 5.998503450378294e-07, "loss": 0.7805, "step": 306940 }, { "epoch": 25.51, "learning_rate": 5.997394895102956e-07, "loss": 0.7344, "step": 306950 }, { "epoch": 25.51, "learning_rate": 5.99628633982762e-07, "loss": 0.7719, "step": 306960 }, { "epoch": 25.51, "learning_rate": 5.995177784552282e-07, "loss": 0.7135, "step": 306970 }, { "epoch": 25.52, "learning_rate": 5.994069229276945e-07, "loss": 0.7344, "step": 306980 }, { "epoch": 25.52, "learning_rate": 5.992960674001607e-07, "loss": 0.747, "step": 306990 }, { "epoch": 25.52, "learning_rate": 5.99185211872627e-07, "loss": 0.7126, "step": 307000 }, { "epoch": 25.52, "learning_rate": 5.990743563450931e-07, "loss": 0.7135, "step": 307010 }, { "epoch": 25.52, "learning_rate": 5.989635008175595e-07, "loss": 0.7589, "step": 307020 }, { "epoch": 25.52, "learning_rate": 5.988526452900257e-07, "loss": 0.7179, "step": 307030 }, { "epoch": 25.52, "learning_rate": 5.98741789762492e-07, "loss": 0.6853, "step": 307040 }, { "epoch": 25.52, "learning_rate": 5.986309342349582e-07, "loss": 0.6985, "step": 307050 }, { "epoch": 25.52, "learning_rate": 5.985200787074245e-07, "loss": 0.7065, "step": 307060 }, { "epoch": 25.52, "learning_rate": 5.984092231798907e-07, "loss": 0.7117, "step": 307070 }, { "epoch": 25.52, "learning_rate": 5.982983676523571e-07, "loss": 0.7975, "step": 307080 }, { "epoch": 25.52, "learning_rate": 5.981875121248233e-07, "loss": 0.7668, "step": 307090 }, { "epoch": 25.53, "learning_rate": 5.980766565972896e-07, "loss": 0.7153, "step": 307100 }, { "epoch": 25.53, "learning_rate": 5.979658010697558e-07, "loss": 0.7197, "step": 307110 }, { "epoch": 25.53, "learning_rate": 5.978549455422221e-07, "loss": 0.7539, "step": 307120 }, { "epoch": 25.53, "learning_rate": 5.977440900146883e-07, "loss": 0.8251, "step": 307130 }, { "epoch": 25.53, "learning_rate": 5.976332344871547e-07, "loss": 0.7159, "step": 307140 }, { "epoch": 25.53, "learning_rate": 5.975223789596208e-07, "loss": 0.7006, "step": 307150 }, { "epoch": 25.53, "learning_rate": 5.974115234320871e-07, "loss": 0.7678, "step": 307160 }, { "epoch": 25.53, "learning_rate": 5.973006679045533e-07, "loss": 0.7508, "step": 307170 }, { "epoch": 25.53, "learning_rate": 5.971898123770196e-07, "loss": 0.7312, "step": 307180 }, { "epoch": 25.53, "learning_rate": 5.970789568494858e-07, "loss": 0.7398, "step": 307190 }, { "epoch": 25.53, "learning_rate": 5.969681013219522e-07, "loss": 0.7719, "step": 307200 }, { "epoch": 25.53, "learning_rate": 5.968572457944184e-07, "loss": 0.6999, "step": 307210 }, { "epoch": 25.54, "learning_rate": 5.967463902668847e-07, "loss": 0.6968, "step": 307220 }, { "epoch": 25.54, "learning_rate": 5.966355347393509e-07, "loss": 0.7723, "step": 307230 }, { "epoch": 25.54, "learning_rate": 5.965246792118172e-07, "loss": 0.7464, "step": 307240 }, { "epoch": 25.54, "learning_rate": 5.964138236842834e-07, "loss": 0.7291, "step": 307250 }, { "epoch": 25.54, "learning_rate": 5.963029681567498e-07, "loss": 0.7557, "step": 307260 }, { "epoch": 25.54, "learning_rate": 5.96192112629216e-07, "loss": 0.7769, "step": 307270 }, { "epoch": 25.54, "learning_rate": 5.960812571016823e-07, "loss": 0.7258, "step": 307280 }, { "epoch": 25.54, "learning_rate": 5.959704015741485e-07, "loss": 0.7021, "step": 307290 }, { "epoch": 25.54, "learning_rate": 5.958595460466147e-07, "loss": 0.762, "step": 307300 }, { "epoch": 25.54, "learning_rate": 5.957486905190809e-07, "loss": 0.7137, "step": 307310 }, { "epoch": 25.54, "learning_rate": 5.956378349915473e-07, "loss": 0.7766, "step": 307320 }, { "epoch": 25.54, "learning_rate": 5.955269794640135e-07, "loss": 0.6922, "step": 307330 }, { "epoch": 25.55, "learning_rate": 5.954161239364798e-07, "loss": 0.7382, "step": 307340 }, { "epoch": 25.55, "learning_rate": 5.95305268408946e-07, "loss": 0.7932, "step": 307350 }, { "epoch": 25.55, "learning_rate": 5.951944128814122e-07, "loss": 0.7364, "step": 307360 }, { "epoch": 25.55, "learning_rate": 5.950835573538785e-07, "loss": 0.753, "step": 307370 }, { "epoch": 25.55, "learning_rate": 5.949727018263447e-07, "loss": 0.7812, "step": 307380 }, { "epoch": 25.55, "learning_rate": 5.948618462988111e-07, "loss": 0.803, "step": 307390 }, { "epoch": 25.55, "learning_rate": 5.947509907712773e-07, "loss": 0.7547, "step": 307400 }, { "epoch": 25.55, "learning_rate": 5.946401352437436e-07, "loss": 0.74, "step": 307410 }, { "epoch": 25.55, "learning_rate": 5.945292797162098e-07, "loss": 0.7246, "step": 307420 }, { "epoch": 25.55, "learning_rate": 5.944184241886761e-07, "loss": 0.718, "step": 307430 }, { "epoch": 25.55, "learning_rate": 5.943075686611422e-07, "loss": 0.6965, "step": 307440 }, { "epoch": 25.55, "learning_rate": 5.941967131336086e-07, "loss": 0.69, "step": 307450 }, { "epoch": 25.56, "learning_rate": 5.940858576060748e-07, "loss": 0.728, "step": 307460 }, { "epoch": 25.56, "learning_rate": 5.939750020785411e-07, "loss": 0.7835, "step": 307470 }, { "epoch": 25.56, "learning_rate": 5.938641465510073e-07, "loss": 0.7449, "step": 307480 }, { "epoch": 25.56, "learning_rate": 5.937532910234736e-07, "loss": 0.7453, "step": 307490 }, { "epoch": 25.56, "learning_rate": 5.936424354959398e-07, "loss": 0.7357, "step": 307500 }, { "epoch": 25.56, "learning_rate": 5.935315799684062e-07, "loss": 0.6706, "step": 307510 }, { "epoch": 25.56, "learning_rate": 5.934207244408724e-07, "loss": 0.7764, "step": 307520 }, { "epoch": 25.56, "learning_rate": 5.933098689133387e-07, "loss": 0.7326, "step": 307530 }, { "epoch": 25.56, "learning_rate": 5.931990133858049e-07, "loss": 0.7776, "step": 307540 }, { "epoch": 25.56, "learning_rate": 5.930881578582712e-07, "loss": 0.7912, "step": 307550 }, { "epoch": 25.56, "learning_rate": 5.929773023307374e-07, "loss": 0.7234, "step": 307560 }, { "epoch": 25.56, "learning_rate": 5.928664468032038e-07, "loss": 0.7068, "step": 307570 }, { "epoch": 25.57, "learning_rate": 5.9275559127567e-07, "loss": 0.7562, "step": 307580 }, { "epoch": 25.57, "learning_rate": 5.926447357481363e-07, "loss": 0.7317, "step": 307590 }, { "epoch": 25.57, "learning_rate": 5.925338802206024e-07, "loss": 0.7467, "step": 307600 }, { "epoch": 25.57, "learning_rate": 5.924230246930687e-07, "loss": 0.724, "step": 307610 }, { "epoch": 25.57, "learning_rate": 5.923121691655349e-07, "loss": 0.7687, "step": 307620 }, { "epoch": 25.57, "learning_rate": 5.922013136380013e-07, "loss": 0.833, "step": 307630 }, { "epoch": 25.57, "learning_rate": 5.920904581104675e-07, "loss": 0.762, "step": 307640 }, { "epoch": 25.57, "learning_rate": 5.919796025829338e-07, "loss": 0.7389, "step": 307650 }, { "epoch": 25.57, "learning_rate": 5.918687470554e-07, "loss": 0.7457, "step": 307660 }, { "epoch": 25.57, "learning_rate": 5.917578915278663e-07, "loss": 0.6593, "step": 307670 }, { "epoch": 25.57, "learning_rate": 5.916470360003325e-07, "loss": 0.7692, "step": 307680 }, { "epoch": 25.57, "learning_rate": 5.915361804727989e-07, "loss": 0.7843, "step": 307690 }, { "epoch": 25.58, "learning_rate": 5.914253249452651e-07, "loss": 0.7431, "step": 307700 }, { "epoch": 25.58, "learning_rate": 5.913144694177314e-07, "loss": 0.7685, "step": 307710 }, { "epoch": 25.58, "learning_rate": 5.912036138901976e-07, "loss": 0.7813, "step": 307720 }, { "epoch": 25.58, "learning_rate": 5.910927583626639e-07, "loss": 0.7332, "step": 307730 }, { "epoch": 25.58, "learning_rate": 5.9098190283513e-07, "loss": 0.7409, "step": 307740 }, { "epoch": 25.58, "learning_rate": 5.908710473075963e-07, "loss": 0.7218, "step": 307750 }, { "epoch": 25.58, "learning_rate": 5.907601917800626e-07, "loss": 0.7107, "step": 307760 }, { "epoch": 25.58, "learning_rate": 5.906493362525289e-07, "loss": 0.7346, "step": 307770 }, { "epoch": 25.58, "learning_rate": 5.905384807249951e-07, "loss": 0.7471, "step": 307780 }, { "epoch": 25.58, "learning_rate": 5.904276251974613e-07, "loss": 0.7399, "step": 307790 }, { "epoch": 25.58, "learning_rate": 5.903167696699276e-07, "loss": 0.7444, "step": 307800 }, { "epoch": 25.58, "learning_rate": 5.902059141423938e-07, "loss": 0.6898, "step": 307810 }, { "epoch": 25.59, "learning_rate": 5.900950586148602e-07, "loss": 0.6999, "step": 307820 }, { "epoch": 25.59, "learning_rate": 5.899842030873264e-07, "loss": 0.7624, "step": 307830 }, { "epoch": 25.59, "learning_rate": 5.898733475597927e-07, "loss": 0.6871, "step": 307840 }, { "epoch": 25.59, "learning_rate": 5.897624920322589e-07, "loss": 0.6825, "step": 307850 }, { "epoch": 25.59, "learning_rate": 5.896516365047252e-07, "loss": 0.6792, "step": 307860 }, { "epoch": 25.59, "learning_rate": 5.895407809771914e-07, "loss": 0.7418, "step": 307870 }, { "epoch": 25.59, "learning_rate": 5.894299254496578e-07, "loss": 0.7061, "step": 307880 }, { "epoch": 25.59, "learning_rate": 5.89319069922124e-07, "loss": 0.7814, "step": 307890 }, { "epoch": 25.59, "learning_rate": 5.892082143945902e-07, "loss": 0.7438, "step": 307900 }, { "epoch": 25.59, "learning_rate": 5.890973588670564e-07, "loss": 0.7603, "step": 307910 }, { "epoch": 25.59, "learning_rate": 5.889865033395227e-07, "loss": 0.7789, "step": 307920 }, { "epoch": 25.59, "learning_rate": 5.888756478119889e-07, "loss": 0.7293, "step": 307930 }, { "epoch": 25.6, "learning_rate": 5.887647922844553e-07, "loss": 0.7819, "step": 307940 }, { "epoch": 25.6, "learning_rate": 5.886539367569215e-07, "loss": 0.7197, "step": 307950 }, { "epoch": 25.6, "learning_rate": 5.885430812293878e-07, "loss": 0.7486, "step": 307960 }, { "epoch": 25.6, "learning_rate": 5.88432225701854e-07, "loss": 0.7373, "step": 307970 }, { "epoch": 25.6, "learning_rate": 5.883213701743203e-07, "loss": 0.8047, "step": 307980 }, { "epoch": 25.6, "learning_rate": 5.882105146467865e-07, "loss": 0.7269, "step": 307990 }, { "epoch": 25.6, "learning_rate": 5.881107446720061e-07, "loss": 0.7605, "step": 308000 }, { "epoch": 25.6, "learning_rate": 5.879998891444724e-07, "loss": 0.7488, "step": 308010 }, { "epoch": 25.6, "learning_rate": 5.878890336169386e-07, "loss": 0.7696, "step": 308020 }, { "epoch": 25.6, "learning_rate": 5.87778178089405e-07, "loss": 0.7725, "step": 308030 }, { "epoch": 25.6, "learning_rate": 5.876673225618712e-07, "loss": 0.8479, "step": 308040 }, { "epoch": 25.6, "learning_rate": 5.875564670343375e-07, "loss": 0.7221, "step": 308050 }, { "epoch": 25.61, "learning_rate": 5.874456115068037e-07, "loss": 0.7256, "step": 308060 }, { "epoch": 25.61, "learning_rate": 5.8733475597927e-07, "loss": 0.7354, "step": 308070 }, { "epoch": 25.61, "learning_rate": 5.872239004517362e-07, "loss": 0.7128, "step": 308080 }, { "epoch": 25.61, "learning_rate": 5.871130449242026e-07, "loss": 0.7079, "step": 308090 }, { "epoch": 25.61, "learning_rate": 5.870021893966688e-07, "loss": 0.7194, "step": 308100 }, { "epoch": 25.61, "learning_rate": 5.868913338691351e-07, "loss": 0.7354, "step": 308110 }, { "epoch": 25.61, "learning_rate": 5.867804783416012e-07, "loss": 0.7695, "step": 308120 }, { "epoch": 25.61, "learning_rate": 5.866696228140675e-07, "loss": 0.8202, "step": 308130 }, { "epoch": 25.61, "learning_rate": 5.865587672865337e-07, "loss": 0.8003, "step": 308140 }, { "epoch": 25.61, "learning_rate": 5.864479117590001e-07, "loss": 0.7807, "step": 308150 }, { "epoch": 25.61, "learning_rate": 5.863370562314663e-07, "loss": 0.7029, "step": 308160 }, { "epoch": 25.61, "learning_rate": 5.862262007039326e-07, "loss": 0.7211, "step": 308170 }, { "epoch": 25.62, "learning_rate": 5.861153451763988e-07, "loss": 0.7369, "step": 308180 }, { "epoch": 25.62, "learning_rate": 5.860044896488651e-07, "loss": 0.7286, "step": 308190 }, { "epoch": 25.62, "learning_rate": 5.858936341213313e-07, "loss": 0.7392, "step": 308200 }, { "epoch": 25.62, "learning_rate": 5.857827785937977e-07, "loss": 0.7363, "step": 308210 }, { "epoch": 25.62, "learning_rate": 5.856719230662639e-07, "loss": 0.8047, "step": 308220 }, { "epoch": 25.62, "learning_rate": 5.855610675387302e-07, "loss": 0.779, "step": 308230 }, { "epoch": 25.62, "learning_rate": 5.854502120111964e-07, "loss": 0.7345, "step": 308240 }, { "epoch": 25.62, "learning_rate": 5.853393564836627e-07, "loss": 0.7321, "step": 308250 }, { "epoch": 25.62, "learning_rate": 5.852285009561289e-07, "loss": 0.7308, "step": 308260 }, { "epoch": 25.62, "learning_rate": 5.851176454285953e-07, "loss": 0.7612, "step": 308270 }, { "epoch": 25.62, "learning_rate": 5.850067899010614e-07, "loss": 0.7672, "step": 308280 }, { "epoch": 25.62, "learning_rate": 5.848959343735277e-07, "loss": 0.7714, "step": 308290 }, { "epoch": 25.63, "learning_rate": 5.847850788459939e-07, "loss": 0.7108, "step": 308300 }, { "epoch": 25.63, "learning_rate": 5.846742233184602e-07, "loss": 0.7756, "step": 308310 }, { "epoch": 25.63, "learning_rate": 5.845633677909264e-07, "loss": 0.7398, "step": 308320 }, { "epoch": 25.63, "learning_rate": 5.844525122633928e-07, "loss": 0.7598, "step": 308330 }, { "epoch": 25.63, "learning_rate": 5.84341656735859e-07, "loss": 0.8377, "step": 308340 }, { "epoch": 25.63, "learning_rate": 5.842308012083252e-07, "loss": 0.755, "step": 308350 }, { "epoch": 25.63, "learning_rate": 5.841199456807915e-07, "loss": 0.7394, "step": 308360 }, { "epoch": 25.63, "learning_rate": 5.840090901532577e-07, "loss": 0.7568, "step": 308370 }, { "epoch": 25.63, "learning_rate": 5.83898234625724e-07, "loss": 0.8091, "step": 308380 }, { "epoch": 25.63, "learning_rate": 5.837873790981902e-07, "loss": 0.7762, "step": 308390 }, { "epoch": 25.63, "learning_rate": 5.836765235706566e-07, "loss": 0.7382, "step": 308400 }, { "epoch": 25.63, "learning_rate": 5.835656680431228e-07, "loss": 0.7424, "step": 308410 }, { "epoch": 25.64, "learning_rate": 5.83454812515589e-07, "loss": 0.7767, "step": 308420 }, { "epoch": 25.64, "learning_rate": 5.833439569880552e-07, "loss": 0.8265, "step": 308430 }, { "epoch": 25.64, "learning_rate": 5.832331014605215e-07, "loss": 0.7618, "step": 308440 }, { "epoch": 25.64, "learning_rate": 5.831222459329877e-07, "loss": 0.7209, "step": 308450 }, { "epoch": 25.64, "learning_rate": 5.830113904054541e-07, "loss": 0.6964, "step": 308460 }, { "epoch": 25.64, "learning_rate": 5.829005348779203e-07, "loss": 0.7004, "step": 308470 }, { "epoch": 25.64, "learning_rate": 5.827896793503866e-07, "loss": 0.7088, "step": 308480 }, { "epoch": 25.64, "learning_rate": 5.826788238228528e-07, "loss": 0.7738, "step": 308490 }, { "epoch": 25.64, "learning_rate": 5.825679682953191e-07, "loss": 0.6721, "step": 308500 }, { "epoch": 25.64, "learning_rate": 5.824571127677853e-07, "loss": 0.7271, "step": 308510 }, { "epoch": 25.64, "learning_rate": 5.823462572402517e-07, "loss": 0.7391, "step": 308520 }, { "epoch": 25.64, "learning_rate": 5.822354017127179e-07, "loss": 0.7616, "step": 308530 }, { "epoch": 25.65, "learning_rate": 5.821245461851842e-07, "loss": 0.7847, "step": 308540 }, { "epoch": 25.65, "learning_rate": 5.820136906576504e-07, "loss": 0.7122, "step": 308550 }, { "epoch": 25.65, "learning_rate": 5.819028351301167e-07, "loss": 0.7912, "step": 308560 }, { "epoch": 25.65, "learning_rate": 5.817919796025828e-07, "loss": 0.706, "step": 308570 }, { "epoch": 25.65, "learning_rate": 5.816811240750492e-07, "loss": 0.7684, "step": 308580 }, { "epoch": 25.65, "learning_rate": 5.815702685475154e-07, "loss": 0.7483, "step": 308590 }, { "epoch": 25.65, "learning_rate": 5.814594130199817e-07, "loss": 0.6981, "step": 308600 }, { "epoch": 25.65, "learning_rate": 5.813485574924479e-07, "loss": 0.7359, "step": 308610 }, { "epoch": 25.65, "learning_rate": 5.812377019649142e-07, "loss": 0.7117, "step": 308620 }, { "epoch": 25.65, "learning_rate": 5.811268464373804e-07, "loss": 0.8287, "step": 308630 }, { "epoch": 25.65, "learning_rate": 5.810159909098468e-07, "loss": 0.7453, "step": 308640 }, { "epoch": 25.65, "learning_rate": 5.80905135382313e-07, "loss": 0.7061, "step": 308650 }, { "epoch": 25.66, "learning_rate": 5.807942798547793e-07, "loss": 0.7242, "step": 308660 }, { "epoch": 25.66, "learning_rate": 5.806834243272455e-07, "loss": 0.7488, "step": 308670 }, { "epoch": 25.66, "learning_rate": 5.805725687997118e-07, "loss": 0.7171, "step": 308680 }, { "epoch": 25.66, "learning_rate": 5.80461713272178e-07, "loss": 0.7017, "step": 308690 }, { "epoch": 25.66, "learning_rate": 5.803508577446444e-07, "loss": 0.7809, "step": 308700 }, { "epoch": 25.66, "learning_rate": 5.802400022171106e-07, "loss": 0.7613, "step": 308710 }, { "epoch": 25.66, "learning_rate": 5.801291466895768e-07, "loss": 0.7321, "step": 308720 }, { "epoch": 25.66, "learning_rate": 5.80018291162043e-07, "loss": 0.7452, "step": 308730 }, { "epoch": 25.66, "learning_rate": 5.799074356345092e-07, "loss": 0.6953, "step": 308740 }, { "epoch": 25.66, "learning_rate": 5.797965801069755e-07, "loss": 0.7524, "step": 308750 }, { "epoch": 25.66, "learning_rate": 5.796857245794419e-07, "loss": 0.7601, "step": 308760 }, { "epoch": 25.66, "learning_rate": 5.795748690519081e-07, "loss": 0.704, "step": 308770 }, { "epoch": 25.67, "learning_rate": 5.794640135243743e-07, "loss": 0.721, "step": 308780 }, { "epoch": 25.67, "learning_rate": 5.793531579968406e-07, "loss": 0.7475, "step": 308790 }, { "epoch": 25.67, "learning_rate": 5.792423024693068e-07, "loss": 0.7525, "step": 308800 }, { "epoch": 25.67, "learning_rate": 5.791314469417731e-07, "loss": 0.7672, "step": 308810 }, { "epoch": 25.67, "learning_rate": 5.790205914142393e-07, "loss": 0.7169, "step": 308820 }, { "epoch": 25.67, "learning_rate": 5.789097358867057e-07, "loss": 0.74, "step": 308830 }, { "epoch": 25.67, "learning_rate": 5.787988803591719e-07, "loss": 0.7592, "step": 308840 }, { "epoch": 25.67, "learning_rate": 5.786880248316382e-07, "loss": 0.7175, "step": 308850 }, { "epoch": 25.67, "learning_rate": 5.785771693041043e-07, "loss": 0.749, "step": 308860 }, { "epoch": 25.67, "learning_rate": 5.784663137765706e-07, "loss": 0.7338, "step": 308870 }, { "epoch": 25.67, "learning_rate": 5.783554582490368e-07, "loss": 0.7648, "step": 308880 }, { "epoch": 25.67, "learning_rate": 5.782446027215032e-07, "loss": 0.7219, "step": 308890 }, { "epoch": 25.68, "learning_rate": 5.781337471939694e-07, "loss": 0.7464, "step": 308900 }, { "epoch": 25.68, "learning_rate": 5.780228916664357e-07, "loss": 0.6741, "step": 308910 }, { "epoch": 25.68, "learning_rate": 5.779120361389019e-07, "loss": 0.7168, "step": 308920 }, { "epoch": 25.68, "learning_rate": 5.778011806113682e-07, "loss": 0.7528, "step": 308930 }, { "epoch": 25.68, "learning_rate": 5.776903250838344e-07, "loss": 0.71, "step": 308940 }, { "epoch": 25.68, "learning_rate": 5.775794695563008e-07, "loss": 0.7211, "step": 308950 }, { "epoch": 25.68, "learning_rate": 5.77468614028767e-07, "loss": 0.7454, "step": 308960 }, { "epoch": 25.68, "learning_rate": 5.773577585012333e-07, "loss": 0.7118, "step": 308970 }, { "epoch": 25.68, "learning_rate": 5.772469029736995e-07, "loss": 0.7556, "step": 308980 }, { "epoch": 25.68, "learning_rate": 5.771360474461658e-07, "loss": 0.7221, "step": 308990 }, { "epoch": 25.68, "learning_rate": 5.77025191918632e-07, "loss": 0.7535, "step": 309000 }, { "epoch": 25.68, "learning_rate": 5.769143363910984e-07, "loss": 0.7064, "step": 309010 }, { "epoch": 25.69, "learning_rate": 5.768034808635645e-07, "loss": 0.7404, "step": 309020 }, { "epoch": 25.69, "learning_rate": 5.766926253360308e-07, "loss": 0.7484, "step": 309030 }, { "epoch": 25.69, "learning_rate": 5.76581769808497e-07, "loss": 0.7455, "step": 309040 }, { "epoch": 25.69, "learning_rate": 5.764709142809633e-07, "loss": 0.8022, "step": 309050 }, { "epoch": 25.69, "learning_rate": 5.763600587534295e-07, "loss": 0.7288, "step": 309060 }, { "epoch": 25.69, "learning_rate": 5.762492032258959e-07, "loss": 0.7792, "step": 309070 }, { "epoch": 25.69, "learning_rate": 5.761383476983621e-07, "loss": 0.7255, "step": 309080 }, { "epoch": 25.69, "learning_rate": 5.760274921708284e-07, "loss": 0.7721, "step": 309090 }, { "epoch": 25.69, "learning_rate": 5.759166366432946e-07, "loss": 0.769, "step": 309100 }, { "epoch": 25.69, "learning_rate": 5.758057811157609e-07, "loss": 0.7173, "step": 309110 }, { "epoch": 25.69, "learning_rate": 5.756949255882271e-07, "loss": 0.6758, "step": 309120 }, { "epoch": 25.69, "learning_rate": 5.755840700606935e-07, "loss": 0.7616, "step": 309130 }, { "epoch": 25.7, "learning_rate": 5.754732145331597e-07, "loss": 0.7563, "step": 309140 }, { "epoch": 25.7, "learning_rate": 5.75362359005626e-07, "loss": 0.7495, "step": 309150 }, { "epoch": 25.7, "learning_rate": 5.752515034780921e-07, "loss": 0.7119, "step": 309160 }, { "epoch": 25.7, "learning_rate": 5.751406479505583e-07, "loss": 0.6539, "step": 309170 }, { "epoch": 25.7, "learning_rate": 5.750297924230246e-07, "loss": 0.7341, "step": 309180 }, { "epoch": 25.7, "learning_rate": 5.749189368954909e-07, "loss": 0.7484, "step": 309190 }, { "epoch": 25.7, "learning_rate": 5.748080813679572e-07, "loss": 0.7722, "step": 309200 }, { "epoch": 25.7, "learning_rate": 5.746972258404234e-07, "loss": 0.6835, "step": 309210 }, { "epoch": 25.7, "learning_rate": 5.745863703128897e-07, "loss": 0.6801, "step": 309220 }, { "epoch": 25.7, "learning_rate": 5.744755147853559e-07, "loss": 0.7496, "step": 309230 }, { "epoch": 25.7, "learning_rate": 5.743646592578222e-07, "loss": 0.7077, "step": 309240 }, { "epoch": 25.7, "learning_rate": 5.742538037302884e-07, "loss": 0.7491, "step": 309250 }, { "epoch": 25.71, "learning_rate": 5.741429482027548e-07, "loss": 0.7224, "step": 309260 }, { "epoch": 25.71, "learning_rate": 5.74032092675221e-07, "loss": 0.7426, "step": 309270 }, { "epoch": 25.71, "learning_rate": 5.739212371476873e-07, "loss": 0.7747, "step": 309280 }, { "epoch": 25.71, "learning_rate": 5.738103816201535e-07, "loss": 0.799, "step": 309290 }, { "epoch": 25.71, "learning_rate": 5.736995260926198e-07, "loss": 0.7309, "step": 309300 }, { "epoch": 25.71, "learning_rate": 5.735886705650859e-07, "loss": 0.7496, "step": 309310 }, { "epoch": 25.71, "learning_rate": 5.734778150375523e-07, "loss": 0.7225, "step": 309320 }, { "epoch": 25.71, "learning_rate": 5.733669595100185e-07, "loss": 0.7905, "step": 309330 }, { "epoch": 25.71, "learning_rate": 5.732561039824848e-07, "loss": 0.6915, "step": 309340 }, { "epoch": 25.71, "learning_rate": 5.73145248454951e-07, "loss": 0.675, "step": 309350 }, { "epoch": 25.71, "learning_rate": 5.730343929274173e-07, "loss": 0.7037, "step": 309360 }, { "epoch": 25.71, "learning_rate": 5.729235373998835e-07, "loss": 0.7416, "step": 309370 }, { "epoch": 25.72, "learning_rate": 5.728126818723499e-07, "loss": 0.7647, "step": 309380 }, { "epoch": 25.72, "learning_rate": 5.727018263448161e-07, "loss": 0.797, "step": 309390 }, { "epoch": 25.72, "learning_rate": 5.725909708172824e-07, "loss": 0.7815, "step": 309400 }, { "epoch": 25.72, "learning_rate": 5.724801152897486e-07, "loss": 0.7684, "step": 309410 }, { "epoch": 25.72, "learning_rate": 5.723692597622149e-07, "loss": 0.7011, "step": 309420 }, { "epoch": 25.72, "learning_rate": 5.722584042346811e-07, "loss": 0.7057, "step": 309430 }, { "epoch": 25.72, "learning_rate": 5.721475487071475e-07, "loss": 0.6967, "step": 309440 }, { "epoch": 25.72, "learning_rate": 5.720366931796137e-07, "loss": 0.714, "step": 309450 }, { "epoch": 25.72, "learning_rate": 5.7192583765208e-07, "loss": 0.7243, "step": 309460 }, { "epoch": 25.72, "learning_rate": 5.718149821245461e-07, "loss": 0.7459, "step": 309470 }, { "epoch": 25.72, "learning_rate": 5.717041265970124e-07, "loss": 0.809, "step": 309480 }, { "epoch": 25.72, "learning_rate": 5.715932710694786e-07, "loss": 0.7526, "step": 309490 }, { "epoch": 25.73, "learning_rate": 5.71482415541945e-07, "loss": 0.7286, "step": 309500 }, { "epoch": 25.73, "learning_rate": 5.713715600144112e-07, "loss": 0.7838, "step": 309510 }, { "epoch": 25.73, "learning_rate": 5.712607044868775e-07, "loss": 0.738, "step": 309520 }, { "epoch": 25.73, "learning_rate": 5.711498489593437e-07, "loss": 0.7694, "step": 309530 }, { "epoch": 25.73, "learning_rate": 5.7103899343181e-07, "loss": 0.6927, "step": 309540 }, { "epoch": 25.73, "learning_rate": 5.709281379042762e-07, "loss": 0.762, "step": 309550 }, { "epoch": 25.73, "learning_rate": 5.708172823767426e-07, "loss": 0.7184, "step": 309560 }, { "epoch": 25.73, "learning_rate": 5.707064268492088e-07, "loss": 0.6826, "step": 309570 }, { "epoch": 25.73, "learning_rate": 5.705955713216751e-07, "loss": 0.7941, "step": 309580 }, { "epoch": 25.73, "learning_rate": 5.704847157941413e-07, "loss": 0.7386, "step": 309590 }, { "epoch": 25.73, "learning_rate": 5.703738602666074e-07, "loss": 0.7201, "step": 309600 }, { "epoch": 25.73, "learning_rate": 5.702630047390737e-07, "loss": 0.7435, "step": 309610 }, { "epoch": 25.74, "learning_rate": 5.7015214921154e-07, "loss": 0.7354, "step": 309620 }, { "epoch": 25.74, "learning_rate": 5.700412936840063e-07, "loss": 0.7688, "step": 309630 }, { "epoch": 25.74, "learning_rate": 5.699304381564725e-07, "loss": 0.7506, "step": 309640 }, { "epoch": 25.74, "learning_rate": 5.698195826289388e-07, "loss": 0.7872, "step": 309650 }, { "epoch": 25.74, "learning_rate": 5.69708727101405e-07, "loss": 0.7363, "step": 309660 }, { "epoch": 25.74, "learning_rate": 5.695978715738713e-07, "loss": 0.7714, "step": 309670 }, { "epoch": 25.74, "learning_rate": 5.694870160463375e-07, "loss": 0.8254, "step": 309680 }, { "epoch": 25.74, "learning_rate": 5.693761605188039e-07, "loss": 0.7009, "step": 309690 }, { "epoch": 25.74, "learning_rate": 5.692653049912701e-07, "loss": 0.7474, "step": 309700 }, { "epoch": 25.74, "learning_rate": 5.691544494637364e-07, "loss": 0.6801, "step": 309710 }, { "epoch": 25.74, "learning_rate": 5.690435939362026e-07, "loss": 0.7362, "step": 309720 }, { "epoch": 25.74, "learning_rate": 5.689327384086689e-07, "loss": 0.769, "step": 309730 }, { "epoch": 25.75, "learning_rate": 5.688218828811351e-07, "loss": 0.7306, "step": 309740 }, { "epoch": 25.75, "learning_rate": 5.687110273536015e-07, "loss": 0.7716, "step": 309750 }, { "epoch": 25.75, "learning_rate": 5.686001718260676e-07, "loss": 0.7271, "step": 309760 }, { "epoch": 25.75, "learning_rate": 5.684893162985339e-07, "loss": 0.7474, "step": 309770 }, { "epoch": 25.75, "learning_rate": 5.683784607710001e-07, "loss": 0.7724, "step": 309780 }, { "epoch": 25.75, "learning_rate": 5.682676052434664e-07, "loss": 0.6902, "step": 309790 }, { "epoch": 25.75, "learning_rate": 5.681567497159326e-07, "loss": 0.6815, "step": 309800 }, { "epoch": 25.75, "learning_rate": 5.68045894188399e-07, "loss": 0.8023, "step": 309810 }, { "epoch": 25.75, "learning_rate": 5.679350386608652e-07, "loss": 0.6716, "step": 309820 }, { "epoch": 25.75, "learning_rate": 5.678241831333315e-07, "loss": 0.7769, "step": 309830 }, { "epoch": 25.75, "learning_rate": 5.677133276057977e-07, "loss": 0.6966, "step": 309840 }, { "epoch": 25.75, "learning_rate": 5.67602472078264e-07, "loss": 0.669, "step": 309850 }, { "epoch": 25.76, "learning_rate": 5.674916165507302e-07, "loss": 0.7146, "step": 309860 }, { "epoch": 25.76, "learning_rate": 5.673807610231966e-07, "loss": 0.77, "step": 309870 }, { "epoch": 25.76, "learning_rate": 5.672699054956628e-07, "loss": 0.7474, "step": 309880 }, { "epoch": 25.76, "learning_rate": 5.671590499681291e-07, "loss": 0.7764, "step": 309890 }, { "epoch": 25.76, "learning_rate": 5.670481944405953e-07, "loss": 0.7233, "step": 309900 }, { "epoch": 25.76, "learning_rate": 5.669373389130615e-07, "loss": 0.7845, "step": 309910 }, { "epoch": 25.76, "learning_rate": 5.668264833855277e-07, "loss": 0.7087, "step": 309920 }, { "epoch": 25.76, "learning_rate": 5.667156278579941e-07, "loss": 0.7636, "step": 309930 }, { "epoch": 25.76, "learning_rate": 5.666047723304603e-07, "loss": 0.7483, "step": 309940 }, { "epoch": 25.76, "learning_rate": 5.664939168029266e-07, "loss": 0.7827, "step": 309950 }, { "epoch": 25.76, "learning_rate": 5.663830612753928e-07, "loss": 0.7682, "step": 309960 }, { "epoch": 25.76, "learning_rate": 5.662722057478591e-07, "loss": 0.7703, "step": 309970 }, { "epoch": 25.77, "learning_rate": 5.661613502203253e-07, "loss": 0.7287, "step": 309980 }, { "epoch": 25.77, "learning_rate": 5.660504946927917e-07, "loss": 0.7756, "step": 309990 }, { "epoch": 25.77, "learning_rate": 5.659396391652579e-07, "loss": 0.6922, "step": 310000 }, { "epoch": 25.77, "learning_rate": 5.658287836377241e-07, "loss": 0.716, "step": 310010 }, { "epoch": 25.77, "learning_rate": 5.657179281101904e-07, "loss": 0.7767, "step": 310020 }, { "epoch": 25.77, "learning_rate": 5.656070725826566e-07, "loss": 0.7633, "step": 310030 }, { "epoch": 25.77, "learning_rate": 5.654962170551229e-07, "loss": 0.7376, "step": 310040 }, { "epoch": 25.77, "learning_rate": 5.65385361527589e-07, "loss": 0.7247, "step": 310050 }, { "epoch": 25.77, "learning_rate": 5.652745060000554e-07, "loss": 0.7747, "step": 310060 }, { "epoch": 25.77, "learning_rate": 5.651636504725216e-07, "loss": 0.7465, "step": 310070 }, { "epoch": 25.77, "learning_rate": 5.650527949449879e-07, "loss": 0.8086, "step": 310080 }, { "epoch": 25.77, "learning_rate": 5.649419394174541e-07, "loss": 0.7201, "step": 310090 }, { "epoch": 25.78, "learning_rate": 5.648310838899204e-07, "loss": 0.7527, "step": 310100 }, { "epoch": 25.78, "learning_rate": 5.647202283623866e-07, "loss": 0.7039, "step": 310110 }, { "epoch": 25.78, "learning_rate": 5.64609372834853e-07, "loss": 0.6652, "step": 310120 }, { "epoch": 25.78, "learning_rate": 5.644985173073192e-07, "loss": 0.7618, "step": 310130 }, { "epoch": 25.78, "learning_rate": 5.643876617797855e-07, "loss": 0.7295, "step": 310140 }, { "epoch": 25.78, "learning_rate": 5.642768062522517e-07, "loss": 0.7312, "step": 310150 }, { "epoch": 25.78, "learning_rate": 5.64165950724718e-07, "loss": 0.7172, "step": 310160 }, { "epoch": 25.78, "learning_rate": 5.640550951971842e-07, "loss": 0.7433, "step": 310170 }, { "epoch": 25.78, "learning_rate": 5.639442396696506e-07, "loss": 0.7715, "step": 310180 }, { "epoch": 25.78, "learning_rate": 5.638333841421168e-07, "loss": 0.8322, "step": 310190 }, { "epoch": 25.78, "learning_rate": 5.63722528614583e-07, "loss": 0.8338, "step": 310200 }, { "epoch": 25.78, "learning_rate": 5.636116730870492e-07, "loss": 0.7471, "step": 310210 }, { "epoch": 25.79, "learning_rate": 5.635008175595155e-07, "loss": 0.7425, "step": 310220 }, { "epoch": 25.79, "learning_rate": 5.633899620319817e-07, "loss": 0.7107, "step": 310230 }, { "epoch": 25.79, "learning_rate": 5.632791065044481e-07, "loss": 0.7185, "step": 310240 }, { "epoch": 25.79, "learning_rate": 5.631682509769143e-07, "loss": 0.7551, "step": 310250 }, { "epoch": 25.79, "learning_rate": 5.630573954493806e-07, "loss": 0.6856, "step": 310260 }, { "epoch": 25.79, "learning_rate": 5.629465399218468e-07, "loss": 0.7576, "step": 310270 }, { "epoch": 25.79, "learning_rate": 5.628356843943131e-07, "loss": 0.7316, "step": 310280 }, { "epoch": 25.79, "learning_rate": 5.627248288667793e-07, "loss": 0.7307, "step": 310290 }, { "epoch": 25.79, "learning_rate": 5.626139733392457e-07, "loss": 0.7544, "step": 310300 }, { "epoch": 25.79, "learning_rate": 5.625031178117119e-07, "loss": 0.7241, "step": 310310 }, { "epoch": 25.79, "learning_rate": 5.623922622841782e-07, "loss": 0.7187, "step": 310320 }, { "epoch": 25.79, "learning_rate": 5.622814067566444e-07, "loss": 0.8004, "step": 310330 }, { "epoch": 25.8, "learning_rate": 5.621705512291107e-07, "loss": 0.7447, "step": 310340 }, { "epoch": 25.8, "learning_rate": 5.620596957015768e-07, "loss": 0.6879, "step": 310350 }, { "epoch": 25.8, "learning_rate": 5.619488401740432e-07, "loss": 0.7271, "step": 310360 }, { "epoch": 25.8, "learning_rate": 5.618379846465094e-07, "loss": 0.7317, "step": 310370 }, { "epoch": 25.8, "learning_rate": 5.617271291189757e-07, "loss": 0.7543, "step": 310380 }, { "epoch": 25.8, "learning_rate": 5.616162735914419e-07, "loss": 0.7161, "step": 310390 }, { "epoch": 25.8, "learning_rate": 5.615054180639082e-07, "loss": 0.7351, "step": 310400 }, { "epoch": 25.8, "learning_rate": 5.613945625363744e-07, "loss": 0.7217, "step": 310410 }, { "epoch": 25.8, "learning_rate": 5.612837070088408e-07, "loss": 0.7413, "step": 310420 }, { "epoch": 25.8, "learning_rate": 5.61172851481307e-07, "loss": 0.7686, "step": 310430 }, { "epoch": 25.8, "learning_rate": 5.610619959537732e-07, "loss": 0.7479, "step": 310440 }, { "epoch": 25.8, "learning_rate": 5.609511404262395e-07, "loss": 0.6887, "step": 310450 }, { "epoch": 25.81, "learning_rate": 5.608402848987057e-07, "loss": 0.7655, "step": 310460 }, { "epoch": 25.81, "learning_rate": 5.60729429371172e-07, "loss": 0.734, "step": 310470 }, { "epoch": 25.81, "learning_rate": 5.606185738436382e-07, "loss": 0.7822, "step": 310480 }, { "epoch": 25.81, "learning_rate": 5.605077183161046e-07, "loss": 0.7143, "step": 310490 }, { "epoch": 25.81, "learning_rate": 5.603968627885707e-07, "loss": 0.7141, "step": 310500 }, { "epoch": 25.81, "learning_rate": 5.60286007261037e-07, "loss": 0.7246, "step": 310510 }, { "epoch": 25.81, "learning_rate": 5.601751517335032e-07, "loss": 0.686, "step": 310520 }, { "epoch": 25.81, "learning_rate": 5.600642962059695e-07, "loss": 0.7702, "step": 310530 }, { "epoch": 25.81, "learning_rate": 5.599534406784357e-07, "loss": 0.7228, "step": 310540 }, { "epoch": 25.81, "learning_rate": 5.598425851509021e-07, "loss": 0.6812, "step": 310550 }, { "epoch": 25.81, "learning_rate": 5.597317296233683e-07, "loss": 0.7031, "step": 310560 }, { "epoch": 25.81, "learning_rate": 5.596208740958346e-07, "loss": 0.715, "step": 310570 }, { "epoch": 25.81, "learning_rate": 5.595100185683008e-07, "loss": 0.7794, "step": 310580 }, { "epoch": 25.82, "learning_rate": 5.593991630407671e-07, "loss": 0.7484, "step": 310590 }, { "epoch": 25.82, "learning_rate": 5.592883075132333e-07, "loss": 0.6684, "step": 310600 }, { "epoch": 25.82, "learning_rate": 5.591774519856997e-07, "loss": 0.7195, "step": 310610 }, { "epoch": 25.82, "learning_rate": 5.590665964581659e-07, "loss": 0.7992, "step": 310620 }, { "epoch": 25.82, "learning_rate": 5.589557409306322e-07, "loss": 0.7787, "step": 310630 }, { "epoch": 25.82, "learning_rate": 5.588448854030984e-07, "loss": 0.7576, "step": 310640 }, { "epoch": 25.82, "learning_rate": 5.587340298755646e-07, "loss": 0.7012, "step": 310650 }, { "epoch": 25.82, "learning_rate": 5.586231743480308e-07, "loss": 0.773, "step": 310660 }, { "epoch": 25.82, "learning_rate": 5.585123188204972e-07, "loss": 0.6932, "step": 310670 }, { "epoch": 25.82, "learning_rate": 5.584014632929634e-07, "loss": 0.7071, "step": 310680 }, { "epoch": 25.82, "learning_rate": 5.582906077654297e-07, "loss": 0.7886, "step": 310690 }, { "epoch": 25.82, "learning_rate": 5.581797522378959e-07, "loss": 0.82, "step": 310700 }, { "epoch": 25.83, "learning_rate": 5.580688967103622e-07, "loss": 0.7093, "step": 310710 }, { "epoch": 25.83, "learning_rate": 5.579580411828284e-07, "loss": 0.739, "step": 310720 }, { "epoch": 25.83, "learning_rate": 5.578471856552948e-07, "loss": 0.7486, "step": 310730 }, { "epoch": 25.83, "learning_rate": 5.57736330127761e-07, "loss": 0.7273, "step": 310740 }, { "epoch": 25.83, "learning_rate": 5.576254746002273e-07, "loss": 0.7006, "step": 310750 }, { "epoch": 25.83, "learning_rate": 5.575146190726935e-07, "loss": 0.6924, "step": 310760 }, { "epoch": 25.83, "learning_rate": 5.574037635451598e-07, "loss": 0.6567, "step": 310770 }, { "epoch": 25.83, "learning_rate": 5.57292908017626e-07, "loss": 0.706, "step": 310780 }, { "epoch": 25.83, "learning_rate": 5.571820524900924e-07, "loss": 0.7254, "step": 310790 }, { "epoch": 25.83, "learning_rate": 5.570711969625585e-07, "loss": 0.7031, "step": 310800 }, { "epoch": 25.83, "learning_rate": 5.569603414350248e-07, "loss": 0.7415, "step": 310810 }, { "epoch": 25.83, "learning_rate": 5.56849485907491e-07, "loss": 0.6899, "step": 310820 }, { "epoch": 25.84, "learning_rate": 5.567386303799572e-07, "loss": 0.7284, "step": 310830 }, { "epoch": 25.84, "learning_rate": 5.566277748524235e-07, "loss": 0.7352, "step": 310840 }, { "epoch": 25.84, "learning_rate": 5.565169193248898e-07, "loss": 0.7964, "step": 310850 }, { "epoch": 25.84, "learning_rate": 5.564060637973561e-07, "loss": 0.7204, "step": 310860 }, { "epoch": 25.84, "learning_rate": 5.562952082698223e-07, "loss": 0.7319, "step": 310870 }, { "epoch": 25.84, "learning_rate": 5.561843527422886e-07, "loss": 0.7364, "step": 310880 }, { "epoch": 25.84, "learning_rate": 5.560734972147548e-07, "loss": 0.8105, "step": 310890 }, { "epoch": 25.84, "learning_rate": 5.559626416872211e-07, "loss": 0.7647, "step": 310900 }, { "epoch": 25.84, "learning_rate": 5.558517861596873e-07, "loss": 0.7697, "step": 310910 }, { "epoch": 25.84, "learning_rate": 5.557409306321537e-07, "loss": 0.7135, "step": 310920 }, { "epoch": 25.84, "learning_rate": 5.556300751046199e-07, "loss": 0.7904, "step": 310930 }, { "epoch": 25.84, "learning_rate": 5.555192195770862e-07, "loss": 0.7736, "step": 310940 }, { "epoch": 25.85, "learning_rate": 5.554083640495523e-07, "loss": 0.7511, "step": 310950 }, { "epoch": 25.85, "learning_rate": 5.552975085220186e-07, "loss": 0.762, "step": 310960 }, { "epoch": 25.85, "learning_rate": 5.551866529944848e-07, "loss": 0.7138, "step": 310970 }, { "epoch": 25.85, "learning_rate": 5.550757974669512e-07, "loss": 0.7624, "step": 310980 }, { "epoch": 25.85, "learning_rate": 5.549649419394174e-07, "loss": 0.7588, "step": 310990 }, { "epoch": 25.85, "learning_rate": 5.548540864118837e-07, "loss": 0.7714, "step": 311000 }, { "epoch": 25.85, "learning_rate": 5.547432308843499e-07, "loss": 0.7014, "step": 311010 }, { "epoch": 25.85, "learning_rate": 5.546323753568162e-07, "loss": 0.7585, "step": 311020 }, { "epoch": 25.85, "learning_rate": 5.545215198292824e-07, "loss": 0.7584, "step": 311030 }, { "epoch": 25.85, "learning_rate": 5.544106643017488e-07, "loss": 0.7686, "step": 311040 }, { "epoch": 25.85, "learning_rate": 5.54299808774215e-07, "loss": 0.6782, "step": 311050 }, { "epoch": 25.85, "learning_rate": 5.541889532466813e-07, "loss": 0.7768, "step": 311060 }, { "epoch": 25.86, "learning_rate": 5.540780977191475e-07, "loss": 0.7245, "step": 311070 }, { "epoch": 25.86, "learning_rate": 5.539672421916138e-07, "loss": 0.7693, "step": 311080 }, { "epoch": 25.86, "learning_rate": 5.5385638666408e-07, "loss": 0.7666, "step": 311090 }, { "epoch": 25.86, "learning_rate": 5.537455311365464e-07, "loss": 0.7957, "step": 311100 }, { "epoch": 25.86, "learning_rate": 5.536346756090125e-07, "loss": 0.6734, "step": 311110 }, { "epoch": 25.86, "learning_rate": 5.535238200814788e-07, "loss": 0.7126, "step": 311120 }, { "epoch": 25.86, "learning_rate": 5.53412964553945e-07, "loss": 0.7804, "step": 311130 }, { "epoch": 25.86, "learning_rate": 5.533021090264113e-07, "loss": 0.6844, "step": 311140 }, { "epoch": 25.86, "learning_rate": 5.531912534988775e-07, "loss": 0.7868, "step": 311150 }, { "epoch": 25.86, "learning_rate": 5.530803979713439e-07, "loss": 0.7168, "step": 311160 }, { "epoch": 25.86, "learning_rate": 5.529695424438101e-07, "loss": 0.6563, "step": 311170 }, { "epoch": 25.86, "learning_rate": 5.528586869162764e-07, "loss": 0.7866, "step": 311180 }, { "epoch": 25.87, "learning_rate": 5.527478313887426e-07, "loss": 0.7801, "step": 311190 }, { "epoch": 25.87, "learning_rate": 5.526369758612089e-07, "loss": 0.6898, "step": 311200 }, { "epoch": 25.87, "learning_rate": 5.525261203336751e-07, "loss": 0.7423, "step": 311210 }, { "epoch": 25.87, "learning_rate": 5.524263503588947e-07, "loss": 0.7032, "step": 311220 }, { "epoch": 25.87, "learning_rate": 5.52315494831361e-07, "loss": 0.7778, "step": 311230 }, { "epoch": 25.87, "learning_rate": 5.522046393038272e-07, "loss": 0.7642, "step": 311240 }, { "epoch": 25.87, "learning_rate": 5.520937837762936e-07, "loss": 0.7098, "step": 311250 }, { "epoch": 25.87, "learning_rate": 5.519829282487598e-07, "loss": 0.7592, "step": 311260 }, { "epoch": 25.87, "learning_rate": 5.518720727212261e-07, "loss": 0.7194, "step": 311270 }, { "epoch": 25.87, "learning_rate": 5.517612171936923e-07, "loss": 0.769, "step": 311280 }, { "epoch": 25.87, "learning_rate": 5.516503616661586e-07, "loss": 0.7076, "step": 311290 }, { "epoch": 25.87, "learning_rate": 5.515395061386248e-07, "loss": 0.7213, "step": 311300 }, { "epoch": 25.88, "learning_rate": 5.514286506110912e-07, "loss": 0.6924, "step": 311310 }, { "epoch": 25.88, "learning_rate": 5.513177950835573e-07, "loss": 0.722, "step": 311320 }, { "epoch": 25.88, "learning_rate": 5.512069395560236e-07, "loss": 0.7449, "step": 311330 }, { "epoch": 25.88, "learning_rate": 5.510960840284898e-07, "loss": 0.7493, "step": 311340 }, { "epoch": 25.88, "learning_rate": 5.509852285009561e-07, "loss": 0.6691, "step": 311350 }, { "epoch": 25.88, "learning_rate": 5.508743729734223e-07, "loss": 0.7656, "step": 311360 }, { "epoch": 25.88, "learning_rate": 5.507635174458887e-07, "loss": 0.7266, "step": 311370 }, { "epoch": 25.88, "learning_rate": 5.506526619183549e-07, "loss": 0.8798, "step": 311380 }, { "epoch": 25.88, "learning_rate": 5.505418063908211e-07, "loss": 0.7803, "step": 311390 }, { "epoch": 25.88, "learning_rate": 5.504309508632874e-07, "loss": 0.7889, "step": 311400 }, { "epoch": 25.88, "learning_rate": 5.503200953357536e-07, "loss": 0.7298, "step": 311410 }, { "epoch": 25.88, "learning_rate": 5.502092398082199e-07, "loss": 0.7613, "step": 311420 }, { "epoch": 25.89, "learning_rate": 5.500983842806862e-07, "loss": 0.7424, "step": 311430 }, { "epoch": 25.89, "learning_rate": 5.499875287531525e-07, "loss": 0.7527, "step": 311440 }, { "epoch": 25.89, "learning_rate": 5.498766732256187e-07, "loss": 0.7293, "step": 311450 }, { "epoch": 25.89, "learning_rate": 5.49765817698085e-07, "loss": 0.7246, "step": 311460 }, { "epoch": 25.89, "learning_rate": 5.496549621705511e-07, "loss": 0.7155, "step": 311470 }, { "epoch": 25.89, "learning_rate": 5.495441066430174e-07, "loss": 0.7642, "step": 311480 }, { "epoch": 25.89, "learning_rate": 5.494332511154837e-07, "loss": 0.7542, "step": 311490 }, { "epoch": 25.89, "learning_rate": 5.4932239558795e-07, "loss": 0.7292, "step": 311500 }, { "epoch": 25.89, "learning_rate": 5.492115400604162e-07, "loss": 0.7705, "step": 311510 }, { "epoch": 25.89, "learning_rate": 5.491006845328825e-07, "loss": 0.7618, "step": 311520 }, { "epoch": 25.89, "learning_rate": 5.489898290053487e-07, "loss": 0.7592, "step": 311530 }, { "epoch": 25.89, "learning_rate": 5.48878973477815e-07, "loss": 0.727, "step": 311540 }, { "epoch": 25.9, "learning_rate": 5.487681179502812e-07, "loss": 0.6699, "step": 311550 }, { "epoch": 25.9, "learning_rate": 5.486572624227476e-07, "loss": 0.7214, "step": 311560 }, { "epoch": 25.9, "learning_rate": 5.485464068952138e-07, "loss": 0.7669, "step": 311570 }, { "epoch": 25.9, "learning_rate": 5.484355513676801e-07, "loss": 0.7342, "step": 311580 }, { "epoch": 25.9, "learning_rate": 5.483246958401463e-07, "loss": 0.749, "step": 311590 }, { "epoch": 25.9, "learning_rate": 5.482138403126126e-07, "loss": 0.7091, "step": 311600 }, { "epoch": 25.9, "learning_rate": 5.481029847850787e-07, "loss": 0.7685, "step": 311610 }, { "epoch": 25.9, "learning_rate": 5.479921292575452e-07, "loss": 0.8085, "step": 311620 }, { "epoch": 25.9, "learning_rate": 5.478812737300113e-07, "loss": 0.7493, "step": 311630 }, { "epoch": 25.9, "learning_rate": 5.477704182024776e-07, "loss": 0.7623, "step": 311640 }, { "epoch": 25.9, "learning_rate": 5.476595626749438e-07, "loss": 0.7386, "step": 311650 }, { "epoch": 25.9, "learning_rate": 5.475487071474101e-07, "loss": 0.7041, "step": 311660 }, { "epoch": 25.91, "learning_rate": 5.474378516198763e-07, "loss": 0.7014, "step": 311670 }, { "epoch": 25.91, "learning_rate": 5.473269960923427e-07, "loss": 0.7886, "step": 311680 }, { "epoch": 25.91, "learning_rate": 5.472161405648089e-07, "loss": 0.7202, "step": 311690 }, { "epoch": 25.91, "learning_rate": 5.471052850372752e-07, "loss": 0.733, "step": 311700 }, { "epoch": 25.91, "learning_rate": 5.469944295097414e-07, "loss": 0.7199, "step": 311710 }, { "epoch": 25.91, "learning_rate": 5.468835739822077e-07, "loss": 0.6887, "step": 311720 }, { "epoch": 25.91, "learning_rate": 5.467727184546739e-07, "loss": 0.7202, "step": 311730 }, { "epoch": 25.91, "learning_rate": 5.466618629271403e-07, "loss": 0.755, "step": 311740 }, { "epoch": 25.91, "learning_rate": 5.465510073996065e-07, "loss": 0.7576, "step": 311750 }, { "epoch": 25.91, "learning_rate": 5.464401518720728e-07, "loss": 0.7381, "step": 311760 }, { "epoch": 25.91, "learning_rate": 5.463292963445389e-07, "loss": 0.7006, "step": 311770 }, { "epoch": 25.91, "learning_rate": 5.462184408170051e-07, "loss": 0.819, "step": 311780 }, { "epoch": 25.92, "learning_rate": 5.461075852894714e-07, "loss": 0.7679, "step": 311790 }, { "epoch": 25.92, "learning_rate": 5.459967297619378e-07, "loss": 0.6763, "step": 311800 }, { "epoch": 25.92, "learning_rate": 5.45885874234404e-07, "loss": 0.7242, "step": 311810 }, { "epoch": 25.92, "learning_rate": 5.457750187068702e-07, "loss": 0.7501, "step": 311820 }, { "epoch": 25.92, "learning_rate": 5.456641631793365e-07, "loss": 0.7338, "step": 311830 }, { "epoch": 25.92, "learning_rate": 5.455533076518027e-07, "loss": 0.7715, "step": 311840 }, { "epoch": 25.92, "learning_rate": 5.45442452124269e-07, "loss": 0.7034, "step": 311850 }, { "epoch": 25.92, "learning_rate": 5.453315965967353e-07, "loss": 0.7499, "step": 311860 }, { "epoch": 25.92, "learning_rate": 5.452207410692016e-07, "loss": 0.7225, "step": 311870 }, { "epoch": 25.92, "learning_rate": 5.451098855416678e-07, "loss": 0.7661, "step": 311880 }, { "epoch": 25.92, "learning_rate": 5.449990300141341e-07, "loss": 0.7394, "step": 311890 }, { "epoch": 25.92, "learning_rate": 5.448881744866003e-07, "loss": 0.7145, "step": 311900 }, { "epoch": 25.93, "learning_rate": 5.447773189590666e-07, "loss": 0.7198, "step": 311910 }, { "epoch": 25.93, "learning_rate": 5.446664634315328e-07, "loss": 0.7507, "step": 311920 }, { "epoch": 25.93, "learning_rate": 5.445556079039991e-07, "loss": 0.7415, "step": 311930 }, { "epoch": 25.93, "learning_rate": 5.444447523764653e-07, "loss": 0.7378, "step": 311940 }, { "epoch": 25.93, "learning_rate": 5.443338968489316e-07, "loss": 0.7299, "step": 311950 }, { "epoch": 25.93, "learning_rate": 5.442230413213978e-07, "loss": 0.7539, "step": 311960 }, { "epoch": 25.93, "learning_rate": 5.441121857938641e-07, "loss": 0.7567, "step": 311970 }, { "epoch": 25.93, "learning_rate": 5.440013302663303e-07, "loss": 0.7941, "step": 311980 }, { "epoch": 25.93, "learning_rate": 5.438904747387967e-07, "loss": 0.772, "step": 311990 }, { "epoch": 25.93, "learning_rate": 5.437796192112629e-07, "loss": 0.7325, "step": 312000 }, { "epoch": 25.93, "learning_rate": 5.436687636837292e-07, "loss": 0.7833, "step": 312010 }, { "epoch": 25.93, "learning_rate": 5.435579081561954e-07, "loss": 0.7736, "step": 312020 }, { "epoch": 25.94, "learning_rate": 5.434470526286617e-07, "loss": 0.79, "step": 312030 }, { "epoch": 25.94, "learning_rate": 5.433361971011279e-07, "loss": 0.724, "step": 312040 }, { "epoch": 25.94, "learning_rate": 5.432253415735943e-07, "loss": 0.7439, "step": 312050 }, { "epoch": 25.94, "learning_rate": 5.431144860460605e-07, "loss": 0.7224, "step": 312060 }, { "epoch": 25.94, "learning_rate": 5.430036305185267e-07, "loss": 0.7834, "step": 312070 }, { "epoch": 25.94, "learning_rate": 5.428927749909929e-07, "loss": 0.7816, "step": 312080 }, { "epoch": 25.94, "learning_rate": 5.427819194634592e-07, "loss": 0.7913, "step": 312090 }, { "epoch": 25.94, "learning_rate": 5.426710639359254e-07, "loss": 0.7231, "step": 312100 }, { "epoch": 25.94, "learning_rate": 5.425602084083918e-07, "loss": 0.7354, "step": 312110 }, { "epoch": 25.94, "learning_rate": 5.42449352880858e-07, "loss": 0.7393, "step": 312120 }, { "epoch": 25.94, "learning_rate": 5.423384973533243e-07, "loss": 0.7456, "step": 312130 }, { "epoch": 25.94, "learning_rate": 5.422276418257905e-07, "loss": 0.7135, "step": 312140 }, { "epoch": 25.95, "learning_rate": 5.421167862982568e-07, "loss": 0.8007, "step": 312150 }, { "epoch": 25.95, "learning_rate": 5.42005930770723e-07, "loss": 0.7514, "step": 312160 }, { "epoch": 25.95, "learning_rate": 5.418950752431894e-07, "loss": 0.7635, "step": 312170 }, { "epoch": 25.95, "learning_rate": 5.417842197156556e-07, "loss": 0.7708, "step": 312180 }, { "epoch": 25.95, "learning_rate": 5.416733641881219e-07, "loss": 0.712, "step": 312190 }, { "epoch": 25.95, "learning_rate": 5.415625086605881e-07, "loss": 0.753, "step": 312200 }, { "epoch": 25.95, "learning_rate": 5.414516531330542e-07, "loss": 0.7108, "step": 312210 }, { "epoch": 25.95, "learning_rate": 5.413407976055205e-07, "loss": 0.7399, "step": 312220 }, { "epoch": 25.95, "learning_rate": 5.412299420779868e-07, "loss": 0.7804, "step": 312230 }, { "epoch": 25.95, "learning_rate": 5.411190865504531e-07, "loss": 0.7575, "step": 312240 }, { "epoch": 25.95, "learning_rate": 5.410082310229193e-07, "loss": 0.7005, "step": 312250 }, { "epoch": 25.95, "learning_rate": 5.408973754953856e-07, "loss": 0.7397, "step": 312260 }, { "epoch": 25.96, "learning_rate": 5.407865199678518e-07, "loss": 0.8015, "step": 312270 }, { "epoch": 25.96, "learning_rate": 5.406756644403181e-07, "loss": 0.7471, "step": 312280 }, { "epoch": 25.96, "learning_rate": 5.405648089127844e-07, "loss": 0.6952, "step": 312290 }, { "epoch": 25.96, "learning_rate": 5.404539533852507e-07, "loss": 0.7824, "step": 312300 }, { "epoch": 25.96, "learning_rate": 5.403430978577169e-07, "loss": 0.7278, "step": 312310 }, { "epoch": 25.96, "learning_rate": 5.402322423301832e-07, "loss": 0.7392, "step": 312320 }, { "epoch": 25.96, "learning_rate": 5.401213868026494e-07, "loss": 0.7163, "step": 312330 }, { "epoch": 25.96, "learning_rate": 5.400105312751157e-07, "loss": 0.7059, "step": 312340 }, { "epoch": 25.96, "learning_rate": 5.398996757475819e-07, "loss": 0.7186, "step": 312350 }, { "epoch": 25.96, "learning_rate": 5.397888202200483e-07, "loss": 0.7058, "step": 312360 }, { "epoch": 25.96, "learning_rate": 5.396779646925144e-07, "loss": 0.7452, "step": 312370 }, { "epoch": 25.96, "learning_rate": 5.395671091649807e-07, "loss": 0.7808, "step": 312380 }, { "epoch": 25.97, "learning_rate": 5.394562536374469e-07, "loss": 0.7839, "step": 312390 }, { "epoch": 25.97, "learning_rate": 5.393453981099132e-07, "loss": 0.6693, "step": 312400 }, { "epoch": 25.97, "learning_rate": 5.392345425823794e-07, "loss": 0.6742, "step": 312410 }, { "epoch": 25.97, "learning_rate": 5.391236870548458e-07, "loss": 0.6861, "step": 312420 }, { "epoch": 25.97, "learning_rate": 5.39012831527312e-07, "loss": 0.7618, "step": 312430 }, { "epoch": 25.97, "learning_rate": 5.389019759997783e-07, "loss": 0.7627, "step": 312440 }, { "epoch": 25.97, "learning_rate": 5.387911204722445e-07, "loss": 0.7291, "step": 312450 }, { "epoch": 25.97, "learning_rate": 5.386802649447108e-07, "loss": 0.6914, "step": 312460 }, { "epoch": 25.97, "learning_rate": 5.38569409417177e-07, "loss": 0.7711, "step": 312470 }, { "epoch": 25.97, "learning_rate": 5.384585538896434e-07, "loss": 0.7203, "step": 312480 }, { "epoch": 25.97, "learning_rate": 5.383476983621096e-07, "loss": 0.8074, "step": 312490 }, { "epoch": 25.97, "learning_rate": 5.382368428345759e-07, "loss": 0.7222, "step": 312500 }, { "epoch": 25.98, "learning_rate": 5.38125987307042e-07, "loss": 0.7728, "step": 312510 }, { "epoch": 25.98, "learning_rate": 5.380151317795083e-07, "loss": 0.7301, "step": 312520 }, { "epoch": 25.98, "learning_rate": 5.379042762519745e-07, "loss": 0.7137, "step": 312530 }, { "epoch": 25.98, "learning_rate": 5.377934207244409e-07, "loss": 0.776, "step": 312540 }, { "epoch": 25.98, "learning_rate": 5.376825651969071e-07, "loss": 0.6973, "step": 312550 }, { "epoch": 25.98, "learning_rate": 5.375717096693734e-07, "loss": 0.7117, "step": 312560 }, { "epoch": 25.98, "learning_rate": 5.374608541418396e-07, "loss": 0.7604, "step": 312570 }, { "epoch": 25.98, "learning_rate": 5.373499986143059e-07, "loss": 0.7406, "step": 312580 }, { "epoch": 25.98, "learning_rate": 5.372391430867721e-07, "loss": 0.7091, "step": 312590 }, { "epoch": 25.98, "learning_rate": 5.371282875592385e-07, "loss": 0.7093, "step": 312600 }, { "epoch": 25.98, "learning_rate": 5.370174320317047e-07, "loss": 0.714, "step": 312610 }, { "epoch": 25.98, "learning_rate": 5.36906576504171e-07, "loss": 0.7364, "step": 312620 }, { "epoch": 25.99, "learning_rate": 5.367957209766372e-07, "loss": 0.7779, "step": 312630 }, { "epoch": 25.99, "learning_rate": 5.366848654491034e-07, "loss": 0.7718, "step": 312640 }, { "epoch": 25.99, "learning_rate": 5.365740099215697e-07, "loss": 0.7573, "step": 312650 }, { "epoch": 25.99, "learning_rate": 5.36463154394036e-07, "loss": 0.6926, "step": 312660 }, { "epoch": 25.99, "learning_rate": 5.363522988665022e-07, "loss": 0.7811, "step": 312670 }, { "epoch": 25.99, "learning_rate": 5.362414433389684e-07, "loss": 0.7532, "step": 312680 }, { "epoch": 25.99, "learning_rate": 5.361305878114347e-07, "loss": 0.7034, "step": 312690 }, { "epoch": 25.99, "learning_rate": 5.360197322839009e-07, "loss": 0.7603, "step": 312700 }, { "epoch": 25.99, "learning_rate": 5.359088767563672e-07, "loss": 0.7805, "step": 312710 }, { "epoch": 25.99, "learning_rate": 5.357980212288335e-07, "loss": 0.7117, "step": 312720 }, { "epoch": 25.99, "learning_rate": 5.356871657012998e-07, "loss": 0.7741, "step": 312730 }, { "epoch": 25.99, "learning_rate": 5.35576310173766e-07, "loss": 0.7536, "step": 312740 }, { "epoch": 26.0, "learning_rate": 5.354654546462323e-07, "loss": 0.7749, "step": 312750 }, { "epoch": 26.0, "learning_rate": 5.353545991186985e-07, "loss": 0.7355, "step": 312760 }, { "epoch": 26.0, "learning_rate": 5.352437435911648e-07, "loss": 0.7116, "step": 312770 }, { "epoch": 26.0, "learning_rate": 5.35132888063631e-07, "loss": 0.7277, "step": 312780 }, { "epoch": 26.0, "learning_rate": 5.350220325360974e-07, "loss": 0.7626, "step": 312790 }, { "epoch": 26.0, "learning_rate": 5.349111770085636e-07, "loss": 0.7226, "step": 312800 }, { "epoch": 26.0, "eval_loss": 1.1326377391815186, "eval_runtime": 345.6047, "eval_samples_per_second": 7.737, "eval_steps_per_second": 3.869, "eval_wer": 0.6350336436364321, "step": 312806 }, { "epoch": 26.0, "learning_rate": 5.348003214810298e-07, "loss": 0.7436, "step": 312810 }, { "epoch": 26.0, "learning_rate": 5.34689465953496e-07, "loss": 0.6954, "step": 312820 }, { "epoch": 26.0, "learning_rate": 5.345786104259623e-07, "loss": 0.7317, "step": 312830 }, { "epoch": 26.0, "learning_rate": 5.344677548984285e-07, "loss": 0.6975, "step": 312840 }, { "epoch": 26.0, "learning_rate": 5.343568993708949e-07, "loss": 0.749, "step": 312850 }, { "epoch": 26.0, "learning_rate": 5.342460438433611e-07, "loss": 0.8057, "step": 312860 }, { "epoch": 26.01, "learning_rate": 5.341351883158274e-07, "loss": 0.6947, "step": 312870 }, { "epoch": 26.01, "learning_rate": 5.340243327882936e-07, "loss": 0.7311, "step": 312880 }, { "epoch": 26.01, "learning_rate": 5.339134772607599e-07, "loss": 0.7445, "step": 312890 }, { "epoch": 26.01, "learning_rate": 5.338026217332261e-07, "loss": 0.7096, "step": 312900 }, { "epoch": 26.01, "learning_rate": 5.336917662056925e-07, "loss": 0.7274, "step": 312910 }, { "epoch": 26.01, "learning_rate": 5.335809106781587e-07, "loss": 0.7868, "step": 312920 }, { "epoch": 26.01, "learning_rate": 5.33470055150625e-07, "loss": 0.7281, "step": 312930 }, { "epoch": 26.01, "learning_rate": 5.333591996230912e-07, "loss": 0.7553, "step": 312940 }, { "epoch": 26.01, "learning_rate": 5.332483440955575e-07, "loss": 0.7659, "step": 312950 }, { "epoch": 26.01, "learning_rate": 5.331374885680236e-07, "loss": 0.8059, "step": 312960 }, { "epoch": 26.01, "learning_rate": 5.3302663304049e-07, "loss": 0.6763, "step": 312970 }, { "epoch": 26.01, "learning_rate": 5.329157775129562e-07, "loss": 0.7881, "step": 312980 }, { "epoch": 26.02, "learning_rate": 5.328049219854225e-07, "loss": 0.7112, "step": 312990 }, { "epoch": 26.02, "learning_rate": 5.326940664578887e-07, "loss": 0.7123, "step": 313000 }, { "epoch": 26.02, "learning_rate": 5.32583210930355e-07, "loss": 0.7217, "step": 313010 }, { "epoch": 26.02, "learning_rate": 5.324723554028212e-07, "loss": 0.7737, "step": 313020 }, { "epoch": 26.02, "learning_rate": 5.323614998752876e-07, "loss": 0.7312, "step": 313030 }, { "epoch": 26.02, "learning_rate": 5.322506443477538e-07, "loss": 0.7549, "step": 313040 }, { "epoch": 26.02, "learning_rate": 5.3213978882022e-07, "loss": 0.7412, "step": 313050 }, { "epoch": 26.02, "learning_rate": 5.320289332926863e-07, "loss": 0.7705, "step": 313060 }, { "epoch": 26.02, "learning_rate": 5.319180777651525e-07, "loss": 0.7777, "step": 313070 }, { "epoch": 26.02, "learning_rate": 5.318072222376188e-07, "loss": 0.6764, "step": 313080 }, { "epoch": 26.02, "learning_rate": 5.316963667100851e-07, "loss": 0.7544, "step": 313090 }, { "epoch": 26.02, "learning_rate": 5.315855111825514e-07, "loss": 0.7196, "step": 313100 }, { "epoch": 26.03, "learning_rate": 5.314746556550175e-07, "loss": 0.8137, "step": 313110 }, { "epoch": 26.03, "learning_rate": 5.313638001274838e-07, "loss": 0.7373, "step": 313120 }, { "epoch": 26.03, "learning_rate": 5.3125294459995e-07, "loss": 0.6951, "step": 313130 }, { "epoch": 26.03, "learning_rate": 5.311420890724163e-07, "loss": 0.7548, "step": 313140 }, { "epoch": 26.03, "learning_rate": 5.310312335448826e-07, "loss": 0.7071, "step": 313150 }, { "epoch": 26.03, "learning_rate": 5.309203780173489e-07, "loss": 0.7517, "step": 313160 }, { "epoch": 26.03, "learning_rate": 5.308095224898151e-07, "loss": 0.8005, "step": 313170 }, { "epoch": 26.03, "learning_rate": 5.306986669622814e-07, "loss": 0.7383, "step": 313180 }, { "epoch": 26.03, "learning_rate": 5.305878114347476e-07, "loss": 0.6831, "step": 313190 }, { "epoch": 26.03, "learning_rate": 5.304769559072139e-07, "loss": 0.7477, "step": 313200 }, { "epoch": 26.03, "learning_rate": 5.303661003796801e-07, "loss": 0.7123, "step": 313210 }, { "epoch": 26.03, "learning_rate": 5.302552448521465e-07, "loss": 0.7633, "step": 313220 }, { "epoch": 26.04, "learning_rate": 5.301443893246127e-07, "loss": 0.7146, "step": 313230 }, { "epoch": 26.04, "learning_rate": 5.30033533797079e-07, "loss": 0.6814, "step": 313240 }, { "epoch": 26.04, "learning_rate": 5.299226782695452e-07, "loss": 0.721, "step": 313250 }, { "epoch": 26.04, "learning_rate": 5.298118227420114e-07, "loss": 0.7642, "step": 313260 }, { "epoch": 26.04, "learning_rate": 5.297009672144776e-07, "loss": 0.7453, "step": 313270 }, { "epoch": 26.04, "learning_rate": 5.29590111686944e-07, "loss": 0.7776, "step": 313280 }, { "epoch": 26.04, "learning_rate": 5.294792561594102e-07, "loss": 0.7884, "step": 313290 }, { "epoch": 26.04, "learning_rate": 5.293684006318765e-07, "loss": 0.682, "step": 313300 }, { "epoch": 26.04, "learning_rate": 5.292575451043427e-07, "loss": 0.7759, "step": 313310 }, { "epoch": 26.04, "learning_rate": 5.29146689576809e-07, "loss": 0.7628, "step": 313320 }, { "epoch": 26.04, "learning_rate": 5.290358340492752e-07, "loss": 0.7079, "step": 313330 }, { "epoch": 26.04, "learning_rate": 5.289249785217416e-07, "loss": 0.6746, "step": 313340 }, { "epoch": 26.05, "learning_rate": 5.288141229942078e-07, "loss": 0.665, "step": 313350 }, { "epoch": 26.05, "learning_rate": 5.287032674666741e-07, "loss": 0.8295, "step": 313360 }, { "epoch": 26.05, "learning_rate": 5.285924119391403e-07, "loss": 0.7315, "step": 313370 }, { "epoch": 26.05, "learning_rate": 5.284815564116066e-07, "loss": 0.7012, "step": 313380 }, { "epoch": 26.05, "learning_rate": 5.283707008840728e-07, "loss": 0.7264, "step": 313390 }, { "epoch": 26.05, "learning_rate": 5.282598453565392e-07, "loss": 0.7373, "step": 313400 }, { "epoch": 26.05, "learning_rate": 5.281489898290053e-07, "loss": 0.7711, "step": 313410 }, { "epoch": 26.05, "learning_rate": 5.280381343014716e-07, "loss": 0.6831, "step": 313420 }, { "epoch": 26.05, "learning_rate": 5.279272787739378e-07, "loss": 0.7382, "step": 313430 }, { "epoch": 26.05, "learning_rate": 5.278164232464041e-07, "loss": 0.7819, "step": 313440 }, { "epoch": 26.05, "learning_rate": 5.277055677188703e-07, "loss": 0.6841, "step": 313450 }, { "epoch": 26.05, "learning_rate": 5.275947121913367e-07, "loss": 0.7518, "step": 313460 }, { "epoch": 26.06, "learning_rate": 5.274838566638029e-07, "loss": 0.6969, "step": 313470 }, { "epoch": 26.06, "learning_rate": 5.273730011362691e-07, "loss": 0.6844, "step": 313480 }, { "epoch": 26.06, "learning_rate": 5.272621456087354e-07, "loss": 0.7448, "step": 313490 }, { "epoch": 26.06, "learning_rate": 5.271512900812016e-07, "loss": 0.7378, "step": 313500 }, { "epoch": 26.06, "learning_rate": 5.270404345536679e-07, "loss": 0.7805, "step": 313510 }, { "epoch": 26.06, "learning_rate": 5.269295790261342e-07, "loss": 0.7169, "step": 313520 }, { "epoch": 26.06, "learning_rate": 5.268187234986005e-07, "loss": 0.8033, "step": 313530 }, { "epoch": 26.06, "learning_rate": 5.267078679710667e-07, "loss": 0.7353, "step": 313540 }, { "epoch": 26.06, "learning_rate": 5.26597012443533e-07, "loss": 0.7866, "step": 313550 }, { "epoch": 26.06, "learning_rate": 5.264861569159991e-07, "loss": 0.8049, "step": 313560 }, { "epoch": 26.06, "learning_rate": 5.263753013884654e-07, "loss": 0.7221, "step": 313570 }, { "epoch": 26.06, "learning_rate": 5.262644458609317e-07, "loss": 0.7592, "step": 313580 }, { "epoch": 26.07, "learning_rate": 5.26153590333398e-07, "loss": 0.7084, "step": 313590 }, { "epoch": 26.07, "learning_rate": 5.260427348058642e-07, "loss": 0.7153, "step": 313600 }, { "epoch": 26.07, "learning_rate": 5.259318792783305e-07, "loss": 0.7998, "step": 313610 }, { "epoch": 26.07, "learning_rate": 5.258210237507967e-07, "loss": 0.7338, "step": 313620 }, { "epoch": 26.07, "learning_rate": 5.25710168223263e-07, "loss": 0.7085, "step": 313630 }, { "epoch": 26.07, "learning_rate": 5.255993126957292e-07, "loss": 0.7643, "step": 313640 }, { "epoch": 26.07, "learning_rate": 5.254884571681956e-07, "loss": 0.7123, "step": 313650 }, { "epoch": 26.07, "learning_rate": 5.253776016406618e-07, "loss": 0.7709, "step": 313660 }, { "epoch": 26.07, "learning_rate": 5.252667461131281e-07, "loss": 0.7337, "step": 313670 }, { "epoch": 26.07, "learning_rate": 5.251558905855943e-07, "loss": 0.7279, "step": 313680 }, { "epoch": 26.07, "learning_rate": 5.250450350580606e-07, "loss": 0.7206, "step": 313690 }, { "epoch": 26.07, "learning_rate": 5.249341795305267e-07, "loss": 0.7305, "step": 313700 }, { "epoch": 26.08, "learning_rate": 5.248233240029931e-07, "loss": 0.8054, "step": 313710 }, { "epoch": 26.08, "learning_rate": 5.247124684754593e-07, "loss": 0.7632, "step": 313720 }, { "epoch": 26.08, "learning_rate": 5.246016129479256e-07, "loss": 0.7802, "step": 313730 }, { "epoch": 26.08, "learning_rate": 5.244907574203918e-07, "loss": 0.778, "step": 313740 }, { "epoch": 26.08, "learning_rate": 5.243799018928581e-07, "loss": 0.7121, "step": 313750 }, { "epoch": 26.08, "learning_rate": 5.242690463653243e-07, "loss": 0.7346, "step": 313760 }, { "epoch": 26.08, "learning_rate": 5.241581908377907e-07, "loss": 0.732, "step": 313770 }, { "epoch": 26.08, "learning_rate": 5.240473353102569e-07, "loss": 0.7634, "step": 313780 }, { "epoch": 26.08, "learning_rate": 5.239364797827232e-07, "loss": 0.7568, "step": 313790 }, { "epoch": 26.08, "learning_rate": 5.238256242551894e-07, "loss": 0.7429, "step": 313800 }, { "epoch": 26.08, "learning_rate": 5.237147687276557e-07, "loss": 0.7948, "step": 313810 }, { "epoch": 26.08, "learning_rate": 5.236039132001219e-07, "loss": 0.7047, "step": 313820 }, { "epoch": 26.09, "learning_rate": 5.234930576725883e-07, "loss": 0.7052, "step": 313830 }, { "epoch": 26.09, "learning_rate": 5.233822021450545e-07, "loss": 0.7715, "step": 313840 }, { "epoch": 26.09, "learning_rate": 5.232713466175208e-07, "loss": 0.7697, "step": 313850 }, { "epoch": 26.09, "learning_rate": 5.231604910899869e-07, "loss": 0.7417, "step": 313860 }, { "epoch": 26.09, "learning_rate": 5.230496355624531e-07, "loss": 0.7557, "step": 313870 }, { "epoch": 26.09, "learning_rate": 5.229387800349194e-07, "loss": 0.7328, "step": 313880 }, { "epoch": 26.09, "learning_rate": 5.228279245073858e-07, "loss": 0.7673, "step": 313890 }, { "epoch": 26.09, "learning_rate": 5.22717068979852e-07, "loss": 0.753, "step": 313900 }, { "epoch": 26.09, "learning_rate": 5.226062134523182e-07, "loss": 0.7143, "step": 313910 }, { "epoch": 26.09, "learning_rate": 5.224953579247845e-07, "loss": 0.8285, "step": 313920 }, { "epoch": 26.09, "learning_rate": 5.223845023972507e-07, "loss": 0.7384, "step": 313930 }, { "epoch": 26.09, "learning_rate": 5.22273646869717e-07, "loss": 0.6929, "step": 313940 }, { "epoch": 26.1, "learning_rate": 5.221627913421833e-07, "loss": 0.7428, "step": 313950 }, { "epoch": 26.1, "learning_rate": 5.220519358146496e-07, "loss": 0.7685, "step": 313960 }, { "epoch": 26.1, "learning_rate": 5.219410802871158e-07, "loss": 0.7245, "step": 313970 }, { "epoch": 26.1, "learning_rate": 5.218302247595821e-07, "loss": 0.7688, "step": 313980 }, { "epoch": 26.1, "learning_rate": 5.217193692320483e-07, "loss": 0.7571, "step": 313990 }, { "epoch": 26.1, "learning_rate": 5.216085137045145e-07, "loss": 0.7271, "step": 314000 }, { "epoch": 26.1, "learning_rate": 5.214976581769808e-07, "loss": 0.7443, "step": 314010 }, { "epoch": 26.1, "learning_rate": 5.213868026494471e-07, "loss": 0.736, "step": 314020 }, { "epoch": 26.1, "learning_rate": 5.212759471219133e-07, "loss": 0.7285, "step": 314030 }, { "epoch": 26.1, "learning_rate": 5.211650915943796e-07, "loss": 0.7492, "step": 314040 }, { "epoch": 26.1, "learning_rate": 5.210542360668458e-07, "loss": 0.7271, "step": 314050 }, { "epoch": 26.1, "learning_rate": 5.209433805393121e-07, "loss": 0.8147, "step": 314060 }, { "epoch": 26.11, "learning_rate": 5.208325250117783e-07, "loss": 0.6883, "step": 314070 }, { "epoch": 26.11, "learning_rate": 5.207216694842447e-07, "loss": 0.754, "step": 314080 }, { "epoch": 26.11, "learning_rate": 5.206108139567109e-07, "loss": 0.6769, "step": 314090 }, { "epoch": 26.11, "learning_rate": 5.204999584291772e-07, "loss": 0.7546, "step": 314100 }, { "epoch": 26.11, "learning_rate": 5.203891029016434e-07, "loss": 0.7316, "step": 314110 }, { "epoch": 26.11, "learning_rate": 5.202782473741097e-07, "loss": 0.777, "step": 314120 }, { "epoch": 26.11, "learning_rate": 5.201673918465759e-07, "loss": 0.752, "step": 314130 }, { "epoch": 26.11, "learning_rate": 5.200565363190423e-07, "loss": 0.7517, "step": 314140 }, { "epoch": 26.11, "learning_rate": 5.199456807915084e-07, "loss": 0.7284, "step": 314150 }, { "epoch": 26.11, "learning_rate": 5.198348252639747e-07, "loss": 0.7892, "step": 314160 }, { "epoch": 26.11, "learning_rate": 5.197239697364409e-07, "loss": 0.77, "step": 314170 }, { "epoch": 26.11, "learning_rate": 5.196131142089072e-07, "loss": 0.7633, "step": 314180 }, { "epoch": 26.12, "learning_rate": 5.195022586813734e-07, "loss": 0.7944, "step": 314190 }, { "epoch": 26.12, "learning_rate": 5.193914031538398e-07, "loss": 0.7873, "step": 314200 }, { "epoch": 26.12, "learning_rate": 5.19280547626306e-07, "loss": 0.7494, "step": 314210 }, { "epoch": 26.12, "learning_rate": 5.191696920987723e-07, "loss": 0.7909, "step": 314220 }, { "epoch": 26.12, "learning_rate": 5.190588365712385e-07, "loss": 0.6903, "step": 314230 }, { "epoch": 26.12, "learning_rate": 5.189479810437048e-07, "loss": 0.7659, "step": 314240 }, { "epoch": 26.12, "learning_rate": 5.18837125516171e-07, "loss": 0.7417, "step": 314250 }, { "epoch": 26.12, "learning_rate": 5.187262699886374e-07, "loss": 0.7565, "step": 314260 }, { "epoch": 26.12, "learning_rate": 5.186154144611036e-07, "loss": 0.7873, "step": 314270 }, { "epoch": 26.12, "learning_rate": 5.185045589335699e-07, "loss": 0.742, "step": 314280 }, { "epoch": 26.12, "learning_rate": 5.183937034060361e-07, "loss": 0.7462, "step": 314290 }, { "epoch": 26.12, "learning_rate": 5.182828478785022e-07, "loss": 0.7746, "step": 314300 }, { "epoch": 26.13, "learning_rate": 5.181719923509685e-07, "loss": 0.77, "step": 314310 }, { "epoch": 26.13, "learning_rate": 5.180611368234348e-07, "loss": 0.7545, "step": 314320 }, { "epoch": 26.13, "learning_rate": 5.179502812959011e-07, "loss": 0.6882, "step": 314330 }, { "epoch": 26.13, "learning_rate": 5.178394257683673e-07, "loss": 0.7092, "step": 314340 }, { "epoch": 26.13, "learning_rate": 5.177285702408336e-07, "loss": 0.7541, "step": 314350 }, { "epoch": 26.13, "learning_rate": 5.176177147132998e-07, "loss": 0.7527, "step": 314360 }, { "epoch": 26.13, "learning_rate": 5.175068591857661e-07, "loss": 0.7281, "step": 314370 }, { "epoch": 26.13, "learning_rate": 5.173960036582324e-07, "loss": 0.8035, "step": 314380 }, { "epoch": 26.13, "learning_rate": 5.17296233683452e-07, "loss": 0.7193, "step": 314390 }, { "epoch": 26.13, "learning_rate": 5.171853781559182e-07, "loss": 0.7333, "step": 314400 }, { "epoch": 26.13, "learning_rate": 5.170745226283846e-07, "loss": 0.7282, "step": 314410 }, { "epoch": 26.13, "learning_rate": 5.169636671008508e-07, "loss": 0.7526, "step": 314420 }, { "epoch": 26.13, "learning_rate": 5.16852811573317e-07, "loss": 0.6863, "step": 314430 }, { "epoch": 26.14, "learning_rate": 5.167419560457833e-07, "loss": 0.7426, "step": 314440 }, { "epoch": 26.14, "learning_rate": 5.166311005182495e-07, "loss": 0.7613, "step": 314450 }, { "epoch": 26.14, "learning_rate": 5.165202449907158e-07, "loss": 0.7367, "step": 314460 }, { "epoch": 26.14, "learning_rate": 5.164093894631821e-07, "loss": 0.7314, "step": 314470 }, { "epoch": 26.14, "learning_rate": 5.162985339356484e-07, "loss": 0.703, "step": 314480 }, { "epoch": 26.14, "learning_rate": 5.161876784081146e-07, "loss": 0.6947, "step": 314490 }, { "epoch": 26.14, "learning_rate": 5.160768228805809e-07, "loss": 0.8318, "step": 314500 }, { "epoch": 26.14, "learning_rate": 5.159659673530471e-07, "loss": 0.7397, "step": 314510 }, { "epoch": 26.14, "learning_rate": 5.158551118255133e-07, "loss": 0.7842, "step": 314520 }, { "epoch": 26.14, "learning_rate": 5.157442562979796e-07, "loss": 0.7037, "step": 314530 }, { "epoch": 26.14, "learning_rate": 5.156334007704459e-07, "loss": 0.656, "step": 314540 }, { "epoch": 26.14, "learning_rate": 5.155225452429121e-07, "loss": 0.7649, "step": 314550 }, { "epoch": 26.15, "learning_rate": 5.154116897153784e-07, "loss": 0.7642, "step": 314560 }, { "epoch": 26.15, "learning_rate": 5.153008341878446e-07, "loss": 0.7404, "step": 314570 }, { "epoch": 26.15, "learning_rate": 5.151899786603109e-07, "loss": 0.7778, "step": 314580 }, { "epoch": 26.15, "learning_rate": 5.150791231327772e-07, "loss": 0.7191, "step": 314590 }, { "epoch": 26.15, "learning_rate": 5.149682676052435e-07, "loss": 0.7217, "step": 314600 }, { "epoch": 26.15, "learning_rate": 5.148574120777097e-07, "loss": 0.7083, "step": 314610 }, { "epoch": 26.15, "learning_rate": 5.14746556550176e-07, "loss": 0.8177, "step": 314620 }, { "epoch": 26.15, "learning_rate": 5.146357010226422e-07, "loss": 0.7272, "step": 314630 }, { "epoch": 26.15, "learning_rate": 5.145248454951085e-07, "loss": 0.6685, "step": 314640 }, { "epoch": 26.15, "learning_rate": 5.144139899675747e-07, "loss": 0.7294, "step": 314650 }, { "epoch": 26.15, "learning_rate": 5.143031344400411e-07, "loss": 0.7157, "step": 314660 }, { "epoch": 26.15, "learning_rate": 5.141922789125072e-07, "loss": 0.7417, "step": 314670 }, { "epoch": 26.16, "learning_rate": 5.140814233849735e-07, "loss": 0.6983, "step": 314680 }, { "epoch": 26.16, "learning_rate": 5.139705678574397e-07, "loss": 0.6816, "step": 314690 }, { "epoch": 26.16, "learning_rate": 5.13859712329906e-07, "loss": 0.696, "step": 314700 }, { "epoch": 26.16, "learning_rate": 5.137488568023722e-07, "loss": 0.7662, "step": 314710 }, { "epoch": 26.16, "learning_rate": 5.136380012748386e-07, "loss": 0.8093, "step": 314720 }, { "epoch": 26.16, "learning_rate": 5.135271457473048e-07, "loss": 0.7124, "step": 314730 }, { "epoch": 26.16, "learning_rate": 5.134162902197711e-07, "loss": 0.7301, "step": 314740 }, { "epoch": 26.16, "learning_rate": 5.133054346922373e-07, "loss": 0.7659, "step": 314750 }, { "epoch": 26.16, "learning_rate": 5.131945791647036e-07, "loss": 0.7182, "step": 314760 }, { "epoch": 26.16, "learning_rate": 5.130837236371698e-07, "loss": 0.8131, "step": 314770 }, { "epoch": 26.16, "learning_rate": 5.129728681096362e-07, "loss": 0.7206, "step": 314780 }, { "epoch": 26.16, "learning_rate": 5.128620125821024e-07, "loss": 0.7016, "step": 314790 }, { "epoch": 26.17, "learning_rate": 5.127511570545687e-07, "loss": 0.7655, "step": 314800 }, { "epoch": 26.17, "learning_rate": 5.126403015270349e-07, "loss": 0.7392, "step": 314810 }, { "epoch": 26.17, "learning_rate": 5.125294459995012e-07, "loss": 0.7953, "step": 314820 }, { "epoch": 26.17, "learning_rate": 5.124185904719673e-07, "loss": 0.7112, "step": 314830 }, { "epoch": 26.17, "learning_rate": 5.123077349444337e-07, "loss": 0.7002, "step": 314840 }, { "epoch": 26.17, "learning_rate": 5.121968794168999e-07, "loss": 0.6907, "step": 314850 }, { "epoch": 26.17, "learning_rate": 5.120860238893661e-07, "loss": 0.7649, "step": 314860 }, { "epoch": 26.17, "learning_rate": 5.119751683618324e-07, "loss": 0.7651, "step": 314870 }, { "epoch": 26.17, "learning_rate": 5.118643128342986e-07, "loss": 0.6854, "step": 314880 }, { "epoch": 26.17, "learning_rate": 5.117534573067649e-07, "loss": 0.6902, "step": 314890 }, { "epoch": 26.17, "learning_rate": 5.116426017792312e-07, "loss": 0.7063, "step": 314900 }, { "epoch": 26.17, "learning_rate": 5.115317462516975e-07, "loss": 0.7502, "step": 314910 }, { "epoch": 26.18, "learning_rate": 5.114208907241637e-07, "loss": 0.7353, "step": 314920 }, { "epoch": 26.18, "learning_rate": 5.1131003519663e-07, "loss": 0.6952, "step": 314930 }, { "epoch": 26.18, "learning_rate": 5.111991796690962e-07, "loss": 0.7776, "step": 314940 }, { "epoch": 26.18, "learning_rate": 5.110883241415625e-07, "loss": 0.7751, "step": 314950 }, { "epoch": 26.18, "learning_rate": 5.109774686140288e-07, "loss": 0.7977, "step": 314960 }, { "epoch": 26.18, "learning_rate": 5.10866613086495e-07, "loss": 0.7884, "step": 314970 }, { "epoch": 26.18, "learning_rate": 5.107557575589612e-07, "loss": 0.72, "step": 314980 }, { "epoch": 26.18, "learning_rate": 5.106449020314275e-07, "loss": 0.7434, "step": 314990 }, { "epoch": 26.18, "learning_rate": 5.105340465038937e-07, "loss": 0.7319, "step": 315000 }, { "epoch": 26.18, "learning_rate": 5.1042319097636e-07, "loss": 0.7531, "step": 315010 }, { "epoch": 26.18, "learning_rate": 5.103123354488263e-07, "loss": 0.7655, "step": 315020 }, { "epoch": 26.18, "learning_rate": 5.102014799212926e-07, "loss": 0.6983, "step": 315030 }, { "epoch": 26.19, "learning_rate": 5.100906243937588e-07, "loss": 0.7294, "step": 315040 }, { "epoch": 26.19, "learning_rate": 5.099797688662251e-07, "loss": 0.7111, "step": 315050 }, { "epoch": 26.19, "learning_rate": 5.098689133386913e-07, "loss": 0.7211, "step": 315060 }, { "epoch": 26.19, "learning_rate": 5.097580578111576e-07, "loss": 0.7552, "step": 315070 }, { "epoch": 26.19, "learning_rate": 5.096472022836238e-07, "loss": 0.7415, "step": 315080 }, { "epoch": 26.19, "learning_rate": 5.095363467560902e-07, "loss": 0.7278, "step": 315090 }, { "epoch": 26.19, "learning_rate": 5.094254912285564e-07, "loss": 0.7642, "step": 315100 }, { "epoch": 26.19, "learning_rate": 5.093146357010227e-07, "loss": 0.7526, "step": 315110 }, { "epoch": 26.19, "learning_rate": 5.092037801734888e-07, "loss": 0.7577, "step": 315120 }, { "epoch": 26.19, "learning_rate": 5.090929246459551e-07, "loss": 0.753, "step": 315130 }, { "epoch": 26.19, "learning_rate": 5.089820691184213e-07, "loss": 0.7209, "step": 315140 }, { "epoch": 26.19, "learning_rate": 5.088712135908877e-07, "loss": 0.7841, "step": 315150 }, { "epoch": 26.2, "learning_rate": 5.087603580633539e-07, "loss": 0.8109, "step": 315160 }, { "epoch": 26.2, "learning_rate": 5.086495025358202e-07, "loss": 0.7873, "step": 315170 }, { "epoch": 26.2, "learning_rate": 5.085386470082864e-07, "loss": 0.7269, "step": 315180 }, { "epoch": 26.2, "learning_rate": 5.084277914807527e-07, "loss": 0.7248, "step": 315190 }, { "epoch": 26.2, "learning_rate": 5.083169359532189e-07, "loss": 0.7436, "step": 315200 }, { "epoch": 26.2, "learning_rate": 5.082060804256853e-07, "loss": 0.7539, "step": 315210 }, { "epoch": 26.2, "learning_rate": 5.080952248981515e-07, "loss": 0.7396, "step": 315220 }, { "epoch": 26.2, "learning_rate": 5.079843693706178e-07, "loss": 0.7123, "step": 315230 }, { "epoch": 26.2, "learning_rate": 5.07873513843084e-07, "loss": 0.7528, "step": 315240 }, { "epoch": 26.2, "learning_rate": 5.077626583155502e-07, "loss": 0.733, "step": 315250 }, { "epoch": 26.2, "learning_rate": 5.076518027880165e-07, "loss": 0.7473, "step": 315260 }, { "epoch": 26.2, "learning_rate": 5.075409472604827e-07, "loss": 0.8197, "step": 315270 }, { "epoch": 26.21, "learning_rate": 5.07430091732949e-07, "loss": 0.7937, "step": 315280 }, { "epoch": 26.21, "learning_rate": 5.073192362054152e-07, "loss": 0.7275, "step": 315290 }, { "epoch": 26.21, "learning_rate": 5.072083806778815e-07, "loss": 0.7422, "step": 315300 }, { "epoch": 26.21, "learning_rate": 5.070975251503477e-07, "loss": 0.7073, "step": 315310 }, { "epoch": 26.21, "learning_rate": 5.06986669622814e-07, "loss": 0.7651, "step": 315320 }, { "epoch": 26.21, "learning_rate": 5.068758140952803e-07, "loss": 0.689, "step": 315330 }, { "epoch": 26.21, "learning_rate": 5.067649585677466e-07, "loss": 0.7515, "step": 315340 }, { "epoch": 26.21, "learning_rate": 5.066541030402128e-07, "loss": 0.7018, "step": 315350 }, { "epoch": 26.21, "learning_rate": 5.065432475126791e-07, "loss": 0.7399, "step": 315360 }, { "epoch": 26.21, "learning_rate": 5.064323919851453e-07, "loss": 0.8082, "step": 315370 }, { "epoch": 26.21, "learning_rate": 5.063215364576116e-07, "loss": 0.7945, "step": 315380 }, { "epoch": 26.21, "learning_rate": 5.062106809300779e-07, "loss": 0.7057, "step": 315390 }, { "epoch": 26.22, "learning_rate": 5.060998254025442e-07, "loss": 0.7304, "step": 315400 }, { "epoch": 26.22, "learning_rate": 5.059889698750104e-07, "loss": 0.7448, "step": 315410 }, { "epoch": 26.22, "learning_rate": 5.058781143474766e-07, "loss": 0.7046, "step": 315420 }, { "epoch": 26.22, "learning_rate": 5.057672588199428e-07, "loss": 0.7129, "step": 315430 }, { "epoch": 26.22, "learning_rate": 5.056564032924091e-07, "loss": 0.7356, "step": 315440 }, { "epoch": 26.22, "learning_rate": 5.055455477648754e-07, "loss": 0.7598, "step": 315450 }, { "epoch": 26.22, "learning_rate": 5.054346922373417e-07, "loss": 0.7262, "step": 315460 }, { "epoch": 26.22, "learning_rate": 5.053238367098079e-07, "loss": 0.6927, "step": 315470 }, { "epoch": 26.22, "learning_rate": 5.052129811822742e-07, "loss": 0.7338, "step": 315480 }, { "epoch": 26.22, "learning_rate": 5.051021256547404e-07, "loss": 0.7125, "step": 315490 }, { "epoch": 26.22, "learning_rate": 5.049912701272067e-07, "loss": 0.7437, "step": 315500 }, { "epoch": 26.22, "learning_rate": 5.048804145996729e-07, "loss": 0.8067, "step": 315510 }, { "epoch": 26.23, "learning_rate": 5.047695590721393e-07, "loss": 0.7116, "step": 315520 }, { "epoch": 26.23, "learning_rate": 5.046587035446055e-07, "loss": 0.7365, "step": 315530 }, { "epoch": 26.23, "learning_rate": 5.045478480170718e-07, "loss": 0.7434, "step": 315540 }, { "epoch": 26.23, "learning_rate": 5.04436992489538e-07, "loss": 0.7441, "step": 315550 }, { "epoch": 26.23, "learning_rate": 5.043261369620043e-07, "loss": 0.7567, "step": 315560 }, { "epoch": 26.23, "learning_rate": 5.042152814344704e-07, "loss": 0.7219, "step": 315570 }, { "epoch": 26.23, "learning_rate": 5.041044259069368e-07, "loss": 0.7122, "step": 315580 }, { "epoch": 26.23, "learning_rate": 5.03993570379403e-07, "loss": 0.7409, "step": 315590 }, { "epoch": 26.23, "learning_rate": 5.038827148518693e-07, "loss": 0.7293, "step": 315600 }, { "epoch": 26.23, "learning_rate": 5.037718593243355e-07, "loss": 0.7632, "step": 315610 }, { "epoch": 26.23, "learning_rate": 5.036610037968018e-07, "loss": 0.7663, "step": 315620 }, { "epoch": 26.23, "learning_rate": 5.03550148269268e-07, "loss": 0.7012, "step": 315630 }, { "epoch": 26.24, "learning_rate": 5.034392927417344e-07, "loss": 0.7788, "step": 315640 }, { "epoch": 26.24, "learning_rate": 5.033284372142006e-07, "loss": 0.7482, "step": 315650 }, { "epoch": 26.24, "learning_rate": 5.032175816866669e-07, "loss": 0.7105, "step": 315660 }, { "epoch": 26.24, "learning_rate": 5.031067261591331e-07, "loss": 0.7359, "step": 315670 }, { "epoch": 26.24, "learning_rate": 5.029958706315993e-07, "loss": 0.6787, "step": 315680 }, { "epoch": 26.24, "learning_rate": 5.028850151040656e-07, "loss": 0.7554, "step": 315690 }, { "epoch": 26.24, "learning_rate": 5.027741595765319e-07, "loss": 0.7162, "step": 315700 }, { "epoch": 26.24, "learning_rate": 5.026633040489982e-07, "loss": 0.6834, "step": 315710 }, { "epoch": 26.24, "learning_rate": 5.025524485214643e-07, "loss": 0.7787, "step": 315720 }, { "epoch": 26.24, "learning_rate": 5.024415929939306e-07, "loss": 0.7521, "step": 315730 }, { "epoch": 26.24, "learning_rate": 5.023307374663968e-07, "loss": 0.7711, "step": 315740 }, { "epoch": 26.24, "learning_rate": 5.022198819388631e-07, "loss": 0.7082, "step": 315750 }, { "epoch": 26.25, "learning_rate": 5.021090264113294e-07, "loss": 0.7176, "step": 315760 }, { "epoch": 26.25, "learning_rate": 5.019981708837957e-07, "loss": 0.7679, "step": 315770 }, { "epoch": 26.25, "learning_rate": 5.018873153562619e-07, "loss": 0.7457, "step": 315780 }, { "epoch": 26.25, "learning_rate": 5.017764598287282e-07, "loss": 0.7046, "step": 315790 }, { "epoch": 26.25, "learning_rate": 5.016656043011944e-07, "loss": 0.6998, "step": 315800 }, { "epoch": 26.25, "learning_rate": 5.015547487736607e-07, "loss": 0.7492, "step": 315810 }, { "epoch": 26.25, "learning_rate": 5.01443893246127e-07, "loss": 0.7611, "step": 315820 }, { "epoch": 26.25, "learning_rate": 5.013330377185933e-07, "loss": 0.7354, "step": 315830 }, { "epoch": 26.25, "learning_rate": 5.012221821910595e-07, "loss": 0.7389, "step": 315840 }, { "epoch": 26.25, "learning_rate": 5.011113266635258e-07, "loss": 0.7078, "step": 315850 }, { "epoch": 26.25, "learning_rate": 5.01000471135992e-07, "loss": 0.736, "step": 315860 }, { "epoch": 26.25, "learning_rate": 5.008896156084582e-07, "loss": 0.7006, "step": 315870 }, { "epoch": 26.26, "learning_rate": 5.007787600809245e-07, "loss": 0.6987, "step": 315880 }, { "epoch": 26.26, "learning_rate": 5.006679045533908e-07, "loss": 0.6934, "step": 315890 }, { "epoch": 26.26, "learning_rate": 5.00557049025857e-07, "loss": 0.7003, "step": 315900 }, { "epoch": 26.26, "learning_rate": 5.004461934983233e-07, "loss": 0.7165, "step": 315910 }, { "epoch": 26.26, "learning_rate": 5.003353379707895e-07, "loss": 0.7123, "step": 315920 }, { "epoch": 26.26, "learning_rate": 5.002244824432558e-07, "loss": 0.7659, "step": 315930 }, { "epoch": 26.26, "learning_rate": 5.00113626915722e-07, "loss": 0.7327, "step": 315940 }, { "epoch": 26.26, "learning_rate": 5.000027713881884e-07, "loss": 0.6968, "step": 315950 }, { "epoch": 26.26, "learning_rate": 4.998919158606546e-07, "loss": 0.7755, "step": 315960 }, { "epoch": 26.26, "learning_rate": 4.997810603331209e-07, "loss": 0.7671, "step": 315970 }, { "epoch": 26.26, "learning_rate": 4.996702048055871e-07, "loss": 0.717, "step": 315980 }, { "epoch": 26.26, "learning_rate": 4.995593492780534e-07, "loss": 0.7101, "step": 315990 }, { "epoch": 26.27, "learning_rate": 4.994484937505197e-07, "loss": 0.7379, "step": 316000 }, { "epoch": 26.27, "learning_rate": 4.993376382229858e-07, "loss": 0.7268, "step": 316010 }, { "epoch": 26.27, "learning_rate": 4.992267826954521e-07, "loss": 0.7872, "step": 316020 }, { "epoch": 26.27, "learning_rate": 4.991159271679184e-07, "loss": 0.7457, "step": 316030 }, { "epoch": 26.27, "learning_rate": 4.990050716403846e-07, "loss": 0.6987, "step": 316040 }, { "epoch": 26.27, "learning_rate": 4.988942161128509e-07, "loss": 0.702, "step": 316050 }, { "epoch": 26.27, "learning_rate": 4.987833605853172e-07, "loss": 0.7213, "step": 316060 }, { "epoch": 26.27, "learning_rate": 4.986725050577834e-07, "loss": 0.7516, "step": 316070 }, { "epoch": 26.27, "learning_rate": 4.985616495302497e-07, "loss": 0.6593, "step": 316080 }, { "epoch": 26.27, "learning_rate": 4.984507940027159e-07, "loss": 0.7857, "step": 316090 }, { "epoch": 26.27, "learning_rate": 4.983399384751822e-07, "loss": 0.7548, "step": 316100 }, { "epoch": 26.27, "learning_rate": 4.982290829476484e-07, "loss": 0.7636, "step": 316110 }, { "epoch": 26.28, "learning_rate": 4.981182274201147e-07, "loss": 0.7161, "step": 316120 }, { "epoch": 26.28, "learning_rate": 4.98007371892581e-07, "loss": 0.7261, "step": 316130 }, { "epoch": 26.28, "learning_rate": 4.978965163650472e-07, "loss": 0.709, "step": 316140 }, { "epoch": 26.28, "learning_rate": 4.977856608375135e-07, "loss": 0.7184, "step": 316150 }, { "epoch": 26.28, "learning_rate": 4.976748053099797e-07, "loss": 0.7707, "step": 316160 }, { "epoch": 26.28, "learning_rate": 4.975639497824459e-07, "loss": 0.7609, "step": 316170 }, { "epoch": 26.28, "learning_rate": 4.974530942549122e-07, "loss": 0.7568, "step": 316180 }, { "epoch": 26.28, "learning_rate": 4.973422387273785e-07, "loss": 0.7361, "step": 316190 }, { "epoch": 26.28, "learning_rate": 4.972313831998447e-07, "loss": 0.6912, "step": 316200 }, { "epoch": 26.28, "learning_rate": 4.97120527672311e-07, "loss": 0.7296, "step": 316210 }, { "epoch": 26.28, "learning_rate": 4.970096721447773e-07, "loss": 0.7836, "step": 316220 }, { "epoch": 26.28, "learning_rate": 4.968988166172435e-07, "loss": 0.7854, "step": 316230 }, { "epoch": 26.29, "learning_rate": 4.967879610897098e-07, "loss": 0.7244, "step": 316240 }, { "epoch": 26.29, "learning_rate": 4.966771055621761e-07, "loss": 0.7018, "step": 316250 }, { "epoch": 26.29, "learning_rate": 4.965662500346423e-07, "loss": 0.7293, "step": 316260 }, { "epoch": 26.29, "learning_rate": 4.964553945071086e-07, "loss": 0.7567, "step": 316270 }, { "epoch": 26.29, "learning_rate": 4.963445389795749e-07, "loss": 0.7122, "step": 316280 }, { "epoch": 26.29, "learning_rate": 4.962336834520411e-07, "loss": 0.703, "step": 316290 }, { "epoch": 26.29, "learning_rate": 4.961228279245074e-07, "loss": 0.7314, "step": 316300 }, { "epoch": 26.29, "learning_rate": 4.960119723969736e-07, "loss": 0.7651, "step": 316310 }, { "epoch": 26.29, "learning_rate": 4.959011168694398e-07, "loss": 0.7451, "step": 316320 }, { "epoch": 26.29, "learning_rate": 4.957902613419061e-07, "loss": 0.7466, "step": 316330 }, { "epoch": 26.29, "learning_rate": 4.956794058143724e-07, "loss": 0.6802, "step": 316340 }, { "epoch": 26.29, "learning_rate": 4.955685502868386e-07, "loss": 0.7123, "step": 316350 }, { "epoch": 26.3, "learning_rate": 4.954576947593049e-07, "loss": 0.7602, "step": 316360 }, { "epoch": 26.3, "learning_rate": 4.953468392317712e-07, "loss": 0.7309, "step": 316370 }, { "epoch": 26.3, "learning_rate": 4.952359837042374e-07, "loss": 0.6759, "step": 316380 }, { "epoch": 26.3, "learning_rate": 4.951251281767037e-07, "loss": 0.782, "step": 316390 }, { "epoch": 26.3, "learning_rate": 4.9501427264917e-07, "loss": 0.7151, "step": 316400 }, { "epoch": 26.3, "learning_rate": 4.949034171216362e-07, "loss": 0.7858, "step": 316410 }, { "epoch": 26.3, "learning_rate": 4.947925615941025e-07, "loss": 0.7975, "step": 316420 }, { "epoch": 26.3, "learning_rate": 4.946817060665688e-07, "loss": 0.7567, "step": 316430 }, { "epoch": 26.3, "learning_rate": 4.94570850539035e-07, "loss": 0.7801, "step": 316440 }, { "epoch": 26.3, "learning_rate": 4.944599950115013e-07, "loss": 0.7377, "step": 316450 }, { "epoch": 26.3, "learning_rate": 4.943491394839676e-07, "loss": 0.7349, "step": 316460 }, { "epoch": 26.3, "learning_rate": 4.942382839564337e-07, "loss": 0.7258, "step": 316470 }, { "epoch": 26.31, "learning_rate": 4.941274284289e-07, "loss": 0.7368, "step": 316480 }, { "epoch": 26.31, "learning_rate": 4.940165729013663e-07, "loss": 0.7327, "step": 316490 }, { "epoch": 26.31, "learning_rate": 4.939057173738325e-07, "loss": 0.753, "step": 316500 }, { "epoch": 26.31, "learning_rate": 4.937948618462988e-07, "loss": 0.7254, "step": 316510 }, { "epoch": 26.31, "learning_rate": 4.93684006318765e-07, "loss": 0.7455, "step": 316520 }, { "epoch": 26.31, "learning_rate": 4.935731507912313e-07, "loss": 0.6891, "step": 316530 }, { "epoch": 26.31, "learning_rate": 4.934622952636975e-07, "loss": 0.7593, "step": 316540 }, { "epoch": 26.31, "learning_rate": 4.933514397361638e-07, "loss": 0.7639, "step": 316550 }, { "epoch": 26.31, "learning_rate": 4.932405842086301e-07, "loss": 0.739, "step": 316560 }, { "epoch": 26.31, "learning_rate": 4.931297286810963e-07, "loss": 0.7432, "step": 316570 }, { "epoch": 26.31, "learning_rate": 4.930188731535626e-07, "loss": 0.7138, "step": 316580 }, { "epoch": 26.31, "learning_rate": 4.929080176260289e-07, "loss": 0.7361, "step": 316590 }, { "epoch": 26.32, "learning_rate": 4.92797162098495e-07, "loss": 0.7632, "step": 316600 }, { "epoch": 26.32, "learning_rate": 4.926863065709613e-07, "loss": 0.7938, "step": 316610 }, { "epoch": 26.32, "learning_rate": 4.925754510434276e-07, "loss": 0.7497, "step": 316620 }, { "epoch": 26.32, "learning_rate": 4.924645955158938e-07, "loss": 0.7393, "step": 316630 }, { "epoch": 26.32, "learning_rate": 4.923537399883601e-07, "loss": 0.7039, "step": 316640 }, { "epoch": 26.32, "learning_rate": 4.922428844608264e-07, "loss": 0.7094, "step": 316650 }, { "epoch": 26.32, "learning_rate": 4.921320289332926e-07, "loss": 0.7289, "step": 316660 }, { "epoch": 26.32, "learning_rate": 4.920211734057589e-07, "loss": 0.7448, "step": 316670 }, { "epoch": 26.32, "learning_rate": 4.919103178782252e-07, "loss": 0.726, "step": 316680 }, { "epoch": 26.32, "learning_rate": 4.917994623506914e-07, "loss": 0.7776, "step": 316690 }, { "epoch": 26.32, "learning_rate": 4.916886068231577e-07, "loss": 0.7186, "step": 316700 }, { "epoch": 26.32, "learning_rate": 4.91577751295624e-07, "loss": 0.7467, "step": 316710 }, { "epoch": 26.33, "learning_rate": 4.914668957680902e-07, "loss": 0.6906, "step": 316720 }, { "epoch": 26.33, "learning_rate": 4.913560402405565e-07, "loss": 0.6829, "step": 316730 }, { "epoch": 26.33, "learning_rate": 4.912451847130228e-07, "loss": 0.6711, "step": 316740 }, { "epoch": 26.33, "learning_rate": 4.91134329185489e-07, "loss": 0.6826, "step": 316750 }, { "epoch": 26.33, "learning_rate": 4.910234736579552e-07, "loss": 0.7981, "step": 316760 }, { "epoch": 26.33, "learning_rate": 4.909126181304215e-07, "loss": 0.7452, "step": 316770 }, { "epoch": 26.33, "learning_rate": 4.908017626028877e-07, "loss": 0.7656, "step": 316780 }, { "epoch": 26.33, "learning_rate": 4.90690907075354e-07, "loss": 0.7101, "step": 316790 }, { "epoch": 26.33, "learning_rate": 4.905800515478203e-07, "loss": 0.7259, "step": 316800 }, { "epoch": 26.33, "learning_rate": 4.904691960202865e-07, "loss": 0.7637, "step": 316810 }, { "epoch": 26.33, "learning_rate": 4.903583404927528e-07, "loss": 0.7105, "step": 316820 }, { "epoch": 26.33, "learning_rate": 4.902474849652191e-07, "loss": 0.7496, "step": 316830 }, { "epoch": 26.34, "learning_rate": 4.901366294376853e-07, "loss": 0.7268, "step": 316840 }, { "epoch": 26.34, "learning_rate": 4.900257739101516e-07, "loss": 0.7153, "step": 316850 }, { "epoch": 26.34, "learning_rate": 4.899149183826179e-07, "loss": 0.7383, "step": 316860 }, { "epoch": 26.34, "learning_rate": 4.898040628550841e-07, "loss": 0.7407, "step": 316870 }, { "epoch": 26.34, "learning_rate": 4.896932073275504e-07, "loss": 0.7083, "step": 316880 }, { "epoch": 26.34, "learning_rate": 4.895823518000167e-07, "loss": 0.7567, "step": 316890 }, { "epoch": 26.34, "learning_rate": 4.894714962724829e-07, "loss": 0.7439, "step": 316900 }, { "epoch": 26.34, "learning_rate": 4.893606407449491e-07, "loss": 0.751, "step": 316910 }, { "epoch": 26.34, "learning_rate": 4.892497852174154e-07, "loss": 0.8033, "step": 316920 }, { "epoch": 26.34, "learning_rate": 4.891389296898816e-07, "loss": 0.7887, "step": 316930 }, { "epoch": 26.34, "learning_rate": 4.890280741623479e-07, "loss": 0.7397, "step": 316940 }, { "epoch": 26.34, "learning_rate": 4.889172186348141e-07, "loss": 0.7015, "step": 316950 }, { "epoch": 26.35, "learning_rate": 4.888063631072804e-07, "loss": 0.7926, "step": 316960 }, { "epoch": 26.35, "learning_rate": 4.886955075797466e-07, "loss": 0.7456, "step": 316970 }, { "epoch": 26.35, "learning_rate": 4.885846520522129e-07, "loss": 0.7178, "step": 316980 }, { "epoch": 26.35, "learning_rate": 4.884737965246792e-07, "loss": 0.7332, "step": 316990 }, { "epoch": 26.35, "learning_rate": 4.883629409971454e-07, "loss": 0.7142, "step": 317000 }, { "epoch": 26.35, "learning_rate": 4.882520854696117e-07, "loss": 0.727, "step": 317010 }, { "epoch": 26.35, "learning_rate": 4.88141229942078e-07, "loss": 0.7526, "step": 317020 }, { "epoch": 26.35, "learning_rate": 4.880303744145442e-07, "loss": 0.6864, "step": 317030 }, { "epoch": 26.35, "learning_rate": 4.879195188870105e-07, "loss": 0.7556, "step": 317040 }, { "epoch": 26.35, "learning_rate": 4.878086633594768e-07, "loss": 0.7139, "step": 317050 }, { "epoch": 26.35, "learning_rate": 4.876978078319429e-07, "loss": 0.7624, "step": 317060 }, { "epoch": 26.35, "learning_rate": 4.875869523044092e-07, "loss": 0.7709, "step": 317070 }, { "epoch": 26.36, "learning_rate": 4.874760967768755e-07, "loss": 0.7885, "step": 317080 }, { "epoch": 26.36, "learning_rate": 4.873652412493417e-07, "loss": 0.7505, "step": 317090 }, { "epoch": 26.36, "learning_rate": 4.87254385721808e-07, "loss": 0.7451, "step": 317100 }, { "epoch": 26.36, "learning_rate": 4.871435301942743e-07, "loss": 0.7553, "step": 317110 }, { "epoch": 26.36, "learning_rate": 4.870326746667405e-07, "loss": 0.7307, "step": 317120 }, { "epoch": 26.36, "learning_rate": 4.869218191392068e-07, "loss": 0.7598, "step": 317130 }, { "epoch": 26.36, "learning_rate": 4.868109636116731e-07, "loss": 0.707, "step": 317140 }, { "epoch": 26.36, "learning_rate": 4.867001080841393e-07, "loss": 0.7224, "step": 317150 }, { "epoch": 26.36, "learning_rate": 4.865892525566056e-07, "loss": 0.705, "step": 317160 }, { "epoch": 26.36, "learning_rate": 4.864783970290719e-07, "loss": 0.7813, "step": 317170 }, { "epoch": 26.36, "learning_rate": 4.863675415015381e-07, "loss": 0.7384, "step": 317180 }, { "epoch": 26.36, "learning_rate": 4.862566859740044e-07, "loss": 0.7196, "step": 317190 }, { "epoch": 26.37, "learning_rate": 4.861458304464707e-07, "loss": 0.7504, "step": 317200 }, { "epoch": 26.37, "learning_rate": 4.860349749189368e-07, "loss": 0.7256, "step": 317210 }, { "epoch": 26.37, "learning_rate": 4.859241193914031e-07, "loss": 0.7974, "step": 317220 }, { "epoch": 26.37, "learning_rate": 4.858132638638694e-07, "loss": 0.74, "step": 317230 }, { "epoch": 26.37, "learning_rate": 4.857024083363356e-07, "loss": 0.7411, "step": 317240 }, { "epoch": 26.37, "learning_rate": 4.855915528088019e-07, "loss": 0.7344, "step": 317250 }, { "epoch": 26.37, "learning_rate": 4.854806972812682e-07, "loss": 0.7217, "step": 317260 }, { "epoch": 26.37, "learning_rate": 4.853698417537344e-07, "loss": 0.8263, "step": 317270 }, { "epoch": 26.37, "learning_rate": 4.852589862262007e-07, "loss": 0.6559, "step": 317280 }, { "epoch": 26.37, "learning_rate": 4.85148130698667e-07, "loss": 0.6867, "step": 317290 }, { "epoch": 26.37, "learning_rate": 4.850483607238865e-07, "loss": 0.6929, "step": 317300 }, { "epoch": 26.37, "learning_rate": 4.849375051963528e-07, "loss": 0.7744, "step": 317310 }, { "epoch": 26.38, "learning_rate": 4.848266496688191e-07, "loss": 0.8742, "step": 317320 }, { "epoch": 26.38, "learning_rate": 4.847157941412853e-07, "loss": 0.7391, "step": 317330 }, { "epoch": 26.38, "learning_rate": 4.846049386137516e-07, "loss": 0.7381, "step": 317340 }, { "epoch": 26.38, "learning_rate": 4.844940830862179e-07, "loss": 0.7519, "step": 317350 }, { "epoch": 26.38, "learning_rate": 4.843832275586841e-07, "loss": 0.7623, "step": 317360 }, { "epoch": 26.38, "learning_rate": 4.842723720311504e-07, "loss": 0.7264, "step": 317370 }, { "epoch": 26.38, "learning_rate": 4.841615165036167e-07, "loss": 0.6996, "step": 317380 }, { "epoch": 26.38, "learning_rate": 4.840506609760829e-07, "loss": 0.7312, "step": 317390 }, { "epoch": 26.38, "learning_rate": 4.839398054485492e-07, "loss": 0.7186, "step": 317400 }, { "epoch": 26.38, "learning_rate": 4.838289499210155e-07, "loss": 0.7386, "step": 317410 }, { "epoch": 26.38, "learning_rate": 4.837180943934817e-07, "loss": 0.7311, "step": 317420 }, { "epoch": 26.38, "learning_rate": 4.83607238865948e-07, "loss": 0.8125, "step": 317430 }, { "epoch": 26.39, "learning_rate": 4.834963833384142e-07, "loss": 0.7397, "step": 317440 }, { "epoch": 26.39, "learning_rate": 4.833855278108804e-07, "loss": 0.7475, "step": 317450 }, { "epoch": 26.39, "learning_rate": 4.832746722833467e-07, "loss": 0.77, "step": 317460 }, { "epoch": 26.39, "learning_rate": 4.831638167558129e-07, "loss": 0.7272, "step": 317470 }, { "epoch": 26.39, "learning_rate": 4.830529612282792e-07, "loss": 0.7354, "step": 317480 }, { "epoch": 26.39, "learning_rate": 4.829421057007455e-07, "loss": 0.7108, "step": 317490 }, { "epoch": 26.39, "learning_rate": 4.828312501732117e-07, "loss": 0.7836, "step": 317500 }, { "epoch": 26.39, "learning_rate": 4.82720394645678e-07, "loss": 0.7455, "step": 317510 }, { "epoch": 26.39, "learning_rate": 4.826095391181443e-07, "loss": 0.7807, "step": 317520 }, { "epoch": 26.39, "learning_rate": 4.824986835906105e-07, "loss": 0.7733, "step": 317530 }, { "epoch": 26.39, "learning_rate": 4.823878280630768e-07, "loss": 0.7843, "step": 317540 }, { "epoch": 26.39, "learning_rate": 4.822769725355431e-07, "loss": 0.7241, "step": 317550 }, { "epoch": 26.4, "learning_rate": 4.821661170080093e-07, "loss": 0.7781, "step": 317560 }, { "epoch": 26.4, "learning_rate": 4.820552614804756e-07, "loss": 0.7796, "step": 317570 }, { "epoch": 26.4, "learning_rate": 4.819444059529417e-07, "loss": 0.7316, "step": 317580 }, { "epoch": 26.4, "learning_rate": 4.81833550425408e-07, "loss": 0.7508, "step": 317590 }, { "epoch": 26.4, "learning_rate": 4.817226948978743e-07, "loss": 0.7571, "step": 317600 }, { "epoch": 26.4, "learning_rate": 4.816118393703405e-07, "loss": 0.7699, "step": 317610 }, { "epoch": 26.4, "learning_rate": 4.815009838428068e-07, "loss": 0.712, "step": 317620 }, { "epoch": 26.4, "learning_rate": 4.813901283152731e-07, "loss": 0.7216, "step": 317630 }, { "epoch": 26.4, "learning_rate": 4.812792727877393e-07, "loss": 0.668, "step": 317640 }, { "epoch": 26.4, "learning_rate": 4.811684172602056e-07, "loss": 0.6821, "step": 317650 }, { "epoch": 26.4, "learning_rate": 4.810575617326719e-07, "loss": 0.7613, "step": 317660 }, { "epoch": 26.4, "learning_rate": 4.809467062051381e-07, "loss": 0.7095, "step": 317670 }, { "epoch": 26.41, "learning_rate": 4.808358506776044e-07, "loss": 0.732, "step": 317680 }, { "epoch": 26.41, "learning_rate": 4.807249951500707e-07, "loss": 0.7749, "step": 317690 }, { "epoch": 26.41, "learning_rate": 4.806141396225369e-07, "loss": 0.7069, "step": 317700 }, { "epoch": 26.41, "learning_rate": 4.805032840950032e-07, "loss": 0.7533, "step": 317710 }, { "epoch": 26.41, "learning_rate": 4.803924285674695e-07, "loss": 0.714, "step": 317720 }, { "epoch": 26.41, "learning_rate": 4.802815730399356e-07, "loss": 0.7106, "step": 317730 }, { "epoch": 26.41, "learning_rate": 4.801707175124019e-07, "loss": 0.8072, "step": 317740 }, { "epoch": 26.41, "learning_rate": 4.800598619848682e-07, "loss": 0.6558, "step": 317750 }, { "epoch": 26.41, "learning_rate": 4.799490064573344e-07, "loss": 0.7642, "step": 317760 }, { "epoch": 26.41, "learning_rate": 4.798381509298007e-07, "loss": 0.6979, "step": 317770 }, { "epoch": 26.41, "learning_rate": 4.79727295402267e-07, "loss": 0.7097, "step": 317780 }, { "epoch": 26.41, "learning_rate": 4.796164398747332e-07, "loss": 0.751, "step": 317790 }, { "epoch": 26.42, "learning_rate": 4.795055843471995e-07, "loss": 0.78, "step": 317800 }, { "epoch": 26.42, "learning_rate": 4.793947288196658e-07, "loss": 0.7194, "step": 317810 }, { "epoch": 26.42, "learning_rate": 4.79283873292132e-07, "loss": 0.8041, "step": 317820 }, { "epoch": 26.42, "learning_rate": 4.791730177645983e-07, "loss": 0.7577, "step": 317830 }, { "epoch": 26.42, "learning_rate": 4.790621622370646e-07, "loss": 0.6429, "step": 317840 }, { "epoch": 26.42, "learning_rate": 4.789513067095308e-07, "loss": 0.7342, "step": 317850 }, { "epoch": 26.42, "learning_rate": 4.788404511819971e-07, "loss": 0.7773, "step": 317860 }, { "epoch": 26.42, "learning_rate": 4.787295956544634e-07, "loss": 0.7064, "step": 317870 }, { "epoch": 26.42, "learning_rate": 4.786187401269295e-07, "loss": 0.6839, "step": 317880 }, { "epoch": 26.42, "learning_rate": 4.785078845993958e-07, "loss": 0.7213, "step": 317890 }, { "epoch": 26.42, "learning_rate": 4.78397029071862e-07, "loss": 0.8083, "step": 317900 }, { "epoch": 26.42, "learning_rate": 4.782861735443283e-07, "loss": 0.7604, "step": 317910 }, { "epoch": 26.43, "learning_rate": 4.781753180167946e-07, "loss": 0.7153, "step": 317920 }, { "epoch": 26.43, "learning_rate": 4.780644624892608e-07, "loss": 0.6804, "step": 317930 }, { "epoch": 26.43, "learning_rate": 4.779536069617271e-07, "loss": 0.7392, "step": 317940 }, { "epoch": 26.43, "learning_rate": 4.778427514341934e-07, "loss": 0.7519, "step": 317950 }, { "epoch": 26.43, "learning_rate": 4.777318959066596e-07, "loss": 0.7029, "step": 317960 }, { "epoch": 26.43, "learning_rate": 4.776210403791259e-07, "loss": 0.7719, "step": 317970 }, { "epoch": 26.43, "learning_rate": 4.775101848515922e-07, "loss": 0.6796, "step": 317980 }, { "epoch": 26.43, "learning_rate": 4.773993293240584e-07, "loss": 0.6838, "step": 317990 }, { "epoch": 26.43, "learning_rate": 4.772884737965247e-07, "loss": 0.6849, "step": 318000 }, { "epoch": 26.43, "learning_rate": 4.771776182689909e-07, "loss": 0.7493, "step": 318010 }, { "epoch": 26.43, "learning_rate": 4.770667627414571e-07, "loss": 0.7279, "step": 318020 }, { "epoch": 26.43, "learning_rate": 4.769559072139234e-07, "loss": 0.72, "step": 318030 }, { "epoch": 26.44, "learning_rate": 4.768450516863896e-07, "loss": 0.7072, "step": 318040 }, { "epoch": 26.44, "learning_rate": 4.76734196158856e-07, "loss": 0.8037, "step": 318050 }, { "epoch": 26.44, "learning_rate": 4.766233406313222e-07, "loss": 0.7169, "step": 318060 }, { "epoch": 26.44, "learning_rate": 4.7651248510378847e-07, "loss": 0.7172, "step": 318070 }, { "epoch": 26.44, "learning_rate": 4.7640162957625476e-07, "loss": 0.7552, "step": 318080 }, { "epoch": 26.44, "learning_rate": 4.7629077404872095e-07, "loss": 0.7141, "step": 318090 }, { "epoch": 26.44, "learning_rate": 4.761799185211872e-07, "loss": 0.7409, "step": 318100 }, { "epoch": 26.44, "learning_rate": 4.760690629936535e-07, "loss": 0.7273, "step": 318110 }, { "epoch": 26.44, "learning_rate": 4.7595820746611973e-07, "loss": 0.7833, "step": 318120 }, { "epoch": 26.44, "learning_rate": 4.75847351938586e-07, "loss": 0.6763, "step": 318130 }, { "epoch": 26.44, "learning_rate": 4.7573649641105227e-07, "loss": 0.751, "step": 318140 }, { "epoch": 26.44, "learning_rate": 4.756256408835185e-07, "loss": 0.7393, "step": 318150 }, { "epoch": 26.45, "learning_rate": 4.7551478535598475e-07, "loss": 0.7851, "step": 318160 }, { "epoch": 26.45, "learning_rate": 4.7540392982845105e-07, "loss": 0.7865, "step": 318170 }, { "epoch": 26.45, "learning_rate": 4.752930743009173e-07, "loss": 0.7051, "step": 318180 }, { "epoch": 26.45, "learning_rate": 4.7518221877338353e-07, "loss": 0.7183, "step": 318190 }, { "epoch": 26.45, "learning_rate": 4.7507136324584983e-07, "loss": 0.7259, "step": 318200 }, { "epoch": 26.45, "learning_rate": 4.7496050771831607e-07, "loss": 0.727, "step": 318210 }, { "epoch": 26.45, "learning_rate": 4.748496521907823e-07, "loss": 0.7837, "step": 318220 }, { "epoch": 26.45, "learning_rate": 4.747387966632486e-07, "loss": 0.7482, "step": 318230 }, { "epoch": 26.45, "learning_rate": 4.7462794113571485e-07, "loss": 0.7328, "step": 318240 }, { "epoch": 26.45, "learning_rate": 4.745170856081811e-07, "loss": 0.7001, "step": 318250 }, { "epoch": 26.45, "learning_rate": 4.744062300806474e-07, "loss": 0.7313, "step": 318260 }, { "epoch": 26.45, "learning_rate": 4.7429537455311363e-07, "loss": 0.7088, "step": 318270 }, { "epoch": 26.45, "learning_rate": 4.741845190255799e-07, "loss": 0.7402, "step": 318280 }, { "epoch": 26.46, "learning_rate": 4.7407366349804617e-07, "loss": 0.7196, "step": 318290 }, { "epoch": 26.46, "learning_rate": 4.739628079705124e-07, "loss": 0.6961, "step": 318300 }, { "epoch": 26.46, "learning_rate": 4.7385195244297866e-07, "loss": 0.7187, "step": 318310 }, { "epoch": 26.46, "learning_rate": 4.7374109691544495e-07, "loss": 0.7952, "step": 318320 }, { "epoch": 26.46, "learning_rate": 4.736302413879112e-07, "loss": 0.7145, "step": 318330 }, { "epoch": 26.46, "learning_rate": 4.7351938586037744e-07, "loss": 0.7481, "step": 318340 }, { "epoch": 26.46, "learning_rate": 4.7340853033284373e-07, "loss": 0.7103, "step": 318350 }, { "epoch": 26.46, "learning_rate": 4.7329767480530997e-07, "loss": 0.7352, "step": 318360 }, { "epoch": 26.46, "learning_rate": 4.731868192777762e-07, "loss": 0.7649, "step": 318370 }, { "epoch": 26.46, "learning_rate": 4.730759637502425e-07, "loss": 0.7819, "step": 318380 }, { "epoch": 26.46, "learning_rate": 4.7296510822270875e-07, "loss": 0.7291, "step": 318390 }, { "epoch": 26.46, "learning_rate": 4.72854252695175e-07, "loss": 0.7248, "step": 318400 }, { "epoch": 26.47, "learning_rate": 4.7274339716764124e-07, "loss": 0.7935, "step": 318410 }, { "epoch": 26.47, "learning_rate": 4.7263254164010753e-07, "loss": 0.7579, "step": 318420 }, { "epoch": 26.47, "learning_rate": 4.725216861125738e-07, "loss": 0.7278, "step": 318430 }, { "epoch": 26.47, "learning_rate": 4.7241083058504e-07, "loss": 0.7487, "step": 318440 }, { "epoch": 26.47, "learning_rate": 4.722999750575063e-07, "loss": 0.7177, "step": 318450 }, { "epoch": 26.47, "learning_rate": 4.7218911952997256e-07, "loss": 0.764, "step": 318460 }, { "epoch": 26.47, "learning_rate": 4.720782640024388e-07, "loss": 0.714, "step": 318470 }, { "epoch": 26.47, "learning_rate": 4.719674084749051e-07, "loss": 0.7375, "step": 318480 }, { "epoch": 26.47, "learning_rate": 4.7185655294737134e-07, "loss": 0.7615, "step": 318490 }, { "epoch": 26.47, "learning_rate": 4.717456974198375e-07, "loss": 0.7241, "step": 318500 }, { "epoch": 26.47, "learning_rate": 4.716348418923039e-07, "loss": 0.7236, "step": 318510 }, { "epoch": 26.47, "learning_rate": 4.7152398636477006e-07, "loss": 0.7352, "step": 318520 }, { "epoch": 26.48, "learning_rate": 4.714131308372363e-07, "loss": 0.7133, "step": 318530 }, { "epoch": 26.48, "learning_rate": 4.713022753097026e-07, "loss": 0.7823, "step": 318540 }, { "epoch": 26.48, "learning_rate": 4.7119141978216884e-07, "loss": 0.7517, "step": 318550 }, { "epoch": 26.48, "learning_rate": 4.710805642546351e-07, "loss": 0.7533, "step": 318560 }, { "epoch": 26.48, "learning_rate": 4.709697087271014e-07, "loss": 0.6919, "step": 318570 }, { "epoch": 26.48, "learning_rate": 4.708588531995676e-07, "loss": 0.6912, "step": 318580 }, { "epoch": 26.48, "learning_rate": 4.7074799767203387e-07, "loss": 0.747, "step": 318590 }, { "epoch": 26.48, "learning_rate": 4.7063714214450016e-07, "loss": 0.6968, "step": 318600 }, { "epoch": 26.48, "learning_rate": 4.705262866169664e-07, "loss": 0.665, "step": 318610 }, { "epoch": 26.48, "learning_rate": 4.7041543108943265e-07, "loss": 0.7575, "step": 318620 }, { "epoch": 26.48, "learning_rate": 4.7030457556189894e-07, "loss": 0.7702, "step": 318630 }, { "epoch": 26.48, "learning_rate": 4.701937200343652e-07, "loss": 0.7552, "step": 318640 }, { "epoch": 26.49, "learning_rate": 4.700828645068314e-07, "loss": 0.6514, "step": 318650 }, { "epoch": 26.49, "learning_rate": 4.699720089792977e-07, "loss": 0.7242, "step": 318660 }, { "epoch": 26.49, "learning_rate": 4.6986115345176396e-07, "loss": 0.7293, "step": 318670 }, { "epoch": 26.49, "learning_rate": 4.697502979242302e-07, "loss": 0.7684, "step": 318680 }, { "epoch": 26.49, "learning_rate": 4.696394423966965e-07, "loss": 0.7203, "step": 318690 }, { "epoch": 26.49, "learning_rate": 4.6952858686916274e-07, "loss": 0.7344, "step": 318700 }, { "epoch": 26.49, "learning_rate": 4.69417731341629e-07, "loss": 0.8111, "step": 318710 }, { "epoch": 26.49, "learning_rate": 4.693068758140953e-07, "loss": 0.715, "step": 318720 }, { "epoch": 26.49, "learning_rate": 4.691960202865615e-07, "loss": 0.6691, "step": 318730 }, { "epoch": 26.49, "learning_rate": 4.6908516475902777e-07, "loss": 0.6611, "step": 318740 }, { "epoch": 26.49, "learning_rate": 4.6897430923149406e-07, "loss": 0.7109, "step": 318750 }, { "epoch": 26.49, "learning_rate": 4.688634537039603e-07, "loss": 0.7445, "step": 318760 }, { "epoch": 26.5, "learning_rate": 4.6875259817642655e-07, "loss": 0.7933, "step": 318770 }, { "epoch": 26.5, "learning_rate": 4.6864174264889284e-07, "loss": 0.6774, "step": 318780 }, { "epoch": 26.5, "learning_rate": 4.685308871213591e-07, "loss": 0.7359, "step": 318790 }, { "epoch": 26.5, "learning_rate": 4.6842003159382533e-07, "loss": 0.7049, "step": 318800 }, { "epoch": 26.5, "learning_rate": 4.683091760662916e-07, "loss": 0.7859, "step": 318810 }, { "epoch": 26.5, "learning_rate": 4.6819832053875786e-07, "loss": 0.7329, "step": 318820 }, { "epoch": 26.5, "learning_rate": 4.680874650112241e-07, "loss": 0.6931, "step": 318830 }, { "epoch": 26.5, "learning_rate": 4.6797660948369035e-07, "loss": 0.722, "step": 318840 }, { "epoch": 26.5, "learning_rate": 4.6786575395615664e-07, "loss": 0.6994, "step": 318850 }, { "epoch": 26.5, "learning_rate": 4.677548984286229e-07, "loss": 0.7516, "step": 318860 }, { "epoch": 26.5, "learning_rate": 4.6764404290108913e-07, "loss": 0.7967, "step": 318870 }, { "epoch": 26.5, "learning_rate": 4.675331873735554e-07, "loss": 0.7692, "step": 318880 }, { "epoch": 26.51, "learning_rate": 4.6742233184602167e-07, "loss": 0.7258, "step": 318890 }, { "epoch": 26.51, "learning_rate": 4.673114763184879e-07, "loss": 0.6549, "step": 318900 }, { "epoch": 26.51, "learning_rate": 4.672006207909542e-07, "loss": 0.7849, "step": 318910 }, { "epoch": 26.51, "learning_rate": 4.6708976526342045e-07, "loss": 0.6688, "step": 318920 }, { "epoch": 26.51, "learning_rate": 4.6697890973588664e-07, "loss": 0.7358, "step": 318930 }, { "epoch": 26.51, "learning_rate": 4.6686805420835293e-07, "loss": 0.6561, "step": 318940 }, { "epoch": 26.51, "learning_rate": 4.667571986808192e-07, "loss": 0.7377, "step": 318950 }, { "epoch": 26.51, "learning_rate": 4.666463431532854e-07, "loss": 0.7682, "step": 318960 }, { "epoch": 26.51, "learning_rate": 4.665354876257517e-07, "loss": 0.7546, "step": 318970 }, { "epoch": 26.51, "learning_rate": 4.6642463209821795e-07, "loss": 0.7446, "step": 318980 }, { "epoch": 26.51, "learning_rate": 4.663137765706842e-07, "loss": 0.7358, "step": 318990 }, { "epoch": 26.51, "learning_rate": 4.662029210431505e-07, "loss": 0.7415, "step": 319000 }, { "epoch": 26.52, "learning_rate": 4.6609206551561673e-07, "loss": 0.7628, "step": 319010 }, { "epoch": 26.52, "learning_rate": 4.65981209988083e-07, "loss": 0.7588, "step": 319020 }, { "epoch": 26.52, "learning_rate": 4.6587035446054927e-07, "loss": 0.7363, "step": 319030 }, { "epoch": 26.52, "learning_rate": 4.657594989330155e-07, "loss": 0.7228, "step": 319040 }, { "epoch": 26.52, "learning_rate": 4.6564864340548176e-07, "loss": 0.7256, "step": 319050 }, { "epoch": 26.52, "learning_rate": 4.6553778787794805e-07, "loss": 0.6774, "step": 319060 }, { "epoch": 26.52, "learning_rate": 4.654269323504143e-07, "loss": 0.7748, "step": 319070 }, { "epoch": 26.52, "learning_rate": 4.6531607682288054e-07, "loss": 0.7749, "step": 319080 }, { "epoch": 26.52, "learning_rate": 4.6520522129534683e-07, "loss": 0.7372, "step": 319090 }, { "epoch": 26.52, "learning_rate": 4.650943657678131e-07, "loss": 0.7367, "step": 319100 }, { "epoch": 26.52, "learning_rate": 4.649835102402793e-07, "loss": 0.7862, "step": 319110 }, { "epoch": 26.52, "learning_rate": 4.648726547127456e-07, "loss": 0.6825, "step": 319120 }, { "epoch": 26.53, "learning_rate": 4.6476179918521186e-07, "loss": 0.7082, "step": 319130 }, { "epoch": 26.53, "learning_rate": 4.646509436576781e-07, "loss": 0.7452, "step": 319140 }, { "epoch": 26.53, "learning_rate": 4.645400881301444e-07, "loss": 0.7052, "step": 319150 }, { "epoch": 26.53, "learning_rate": 4.6442923260261064e-07, "loss": 0.7669, "step": 319160 }, { "epoch": 26.53, "learning_rate": 4.643183770750769e-07, "loss": 0.7307, "step": 319170 }, { "epoch": 26.53, "learning_rate": 4.6420752154754317e-07, "loss": 0.7638, "step": 319180 }, { "epoch": 26.53, "learning_rate": 4.640966660200094e-07, "loss": 0.7742, "step": 319190 }, { "epoch": 26.53, "learning_rate": 4.6398581049247566e-07, "loss": 0.7476, "step": 319200 }, { "epoch": 26.53, "learning_rate": 4.6387495496494195e-07, "loss": 0.7479, "step": 319210 }, { "epoch": 26.53, "learning_rate": 4.637640994374082e-07, "loss": 0.7956, "step": 319220 }, { "epoch": 26.53, "learning_rate": 4.6365324390987444e-07, "loss": 0.7087, "step": 319230 }, { "epoch": 26.53, "learning_rate": 4.6354238838234073e-07, "loss": 0.6915, "step": 319240 }, { "epoch": 26.54, "learning_rate": 4.63431532854807e-07, "loss": 0.6862, "step": 319250 }, { "epoch": 26.54, "learning_rate": 4.633206773272732e-07, "loss": 0.7008, "step": 319260 }, { "epoch": 26.54, "learning_rate": 4.6320982179973946e-07, "loss": 0.7621, "step": 319270 }, { "epoch": 26.54, "learning_rate": 4.6309896627220576e-07, "loss": 0.7288, "step": 319280 }, { "epoch": 26.54, "learning_rate": 4.62988110744672e-07, "loss": 0.7306, "step": 319290 }, { "epoch": 26.54, "learning_rate": 4.6287725521713824e-07, "loss": 0.7062, "step": 319300 }, { "epoch": 26.54, "learning_rate": 4.6276639968960454e-07, "loss": 0.7603, "step": 319310 }, { "epoch": 26.54, "learning_rate": 4.626555441620708e-07, "loss": 0.7781, "step": 319320 }, { "epoch": 26.54, "learning_rate": 4.62544688634537e-07, "loss": 0.7206, "step": 319330 }, { "epoch": 26.54, "learning_rate": 4.624338331070033e-07, "loss": 0.6985, "step": 319340 }, { "epoch": 26.54, "learning_rate": 4.623229775794695e-07, "loss": 0.7346, "step": 319350 }, { "epoch": 26.54, "learning_rate": 4.6221212205193575e-07, "loss": 0.8163, "step": 319360 }, { "epoch": 26.55, "learning_rate": 4.6210126652440204e-07, "loss": 0.7907, "step": 319370 }, { "epoch": 26.55, "learning_rate": 4.619904109968683e-07, "loss": 0.7098, "step": 319380 }, { "epoch": 26.55, "learning_rate": 4.6187955546933453e-07, "loss": 0.7042, "step": 319390 }, { "epoch": 26.55, "learning_rate": 4.617686999418008e-07, "loss": 0.7083, "step": 319400 }, { "epoch": 26.55, "learning_rate": 4.6165784441426707e-07, "loss": 0.7074, "step": 319410 }, { "epoch": 26.55, "learning_rate": 4.615469888867333e-07, "loss": 0.7521, "step": 319420 }, { "epoch": 26.55, "learning_rate": 4.614361333591996e-07, "loss": 0.7639, "step": 319430 }, { "epoch": 26.55, "learning_rate": 4.6132527783166585e-07, "loss": 0.7045, "step": 319440 }, { "epoch": 26.55, "learning_rate": 4.612144223041321e-07, "loss": 0.7253, "step": 319450 }, { "epoch": 26.55, "learning_rate": 4.611035667765984e-07, "loss": 0.7799, "step": 319460 }, { "epoch": 26.55, "learning_rate": 4.609927112490646e-07, "loss": 0.7188, "step": 319470 }, { "epoch": 26.55, "learning_rate": 4.6088185572153087e-07, "loss": 0.7195, "step": 319480 }, { "epoch": 26.56, "learning_rate": 4.6077100019399716e-07, "loss": 0.7791, "step": 319490 }, { "epoch": 26.56, "learning_rate": 4.606601446664634e-07, "loss": 0.7059, "step": 319500 }, { "epoch": 26.56, "learning_rate": 4.6054928913892965e-07, "loss": 0.7323, "step": 319510 }, { "epoch": 26.56, "learning_rate": 4.6043843361139594e-07, "loss": 0.753, "step": 319520 }, { "epoch": 26.56, "learning_rate": 4.603275780838622e-07, "loss": 0.7022, "step": 319530 }, { "epoch": 26.56, "learning_rate": 4.6021672255632843e-07, "loss": 0.72, "step": 319540 }, { "epoch": 26.56, "learning_rate": 4.601058670287947e-07, "loss": 0.719, "step": 319550 }, { "epoch": 26.56, "learning_rate": 4.5999501150126097e-07, "loss": 0.7247, "step": 319560 }, { "epoch": 26.56, "learning_rate": 4.598841559737272e-07, "loss": 0.7515, "step": 319570 }, { "epoch": 26.56, "learning_rate": 4.597733004461935e-07, "loss": 0.7159, "step": 319580 }, { "epoch": 26.56, "learning_rate": 4.5966244491865975e-07, "loss": 0.7761, "step": 319590 }, { "epoch": 26.56, "learning_rate": 4.59551589391126e-07, "loss": 0.7559, "step": 319600 }, { "epoch": 26.57, "learning_rate": 4.594407338635923e-07, "loss": 0.6578, "step": 319610 }, { "epoch": 26.57, "learning_rate": 4.5932987833605853e-07, "loss": 0.7562, "step": 319620 }, { "epoch": 26.57, "learning_rate": 4.5921902280852477e-07, "loss": 0.7646, "step": 319630 }, { "epoch": 26.57, "learning_rate": 4.5910816728099106e-07, "loss": 0.7519, "step": 319640 }, { "epoch": 26.57, "learning_rate": 4.589973117534573e-07, "loss": 0.753, "step": 319650 }, { "epoch": 26.57, "learning_rate": 4.5888645622592355e-07, "loss": 0.7461, "step": 319660 }, { "epoch": 26.57, "learning_rate": 4.587756006983898e-07, "loss": 0.8157, "step": 319670 }, { "epoch": 26.57, "learning_rate": 4.586647451708561e-07, "loss": 0.6485, "step": 319680 }, { "epoch": 26.57, "learning_rate": 4.5855388964332233e-07, "loss": 0.7081, "step": 319690 }, { "epoch": 26.57, "learning_rate": 4.5844303411578857e-07, "loss": 0.6882, "step": 319700 }, { "epoch": 26.57, "learning_rate": 4.5833217858825487e-07, "loss": 0.7576, "step": 319710 }, { "epoch": 26.57, "learning_rate": 4.582213230607211e-07, "loss": 0.7526, "step": 319720 }, { "epoch": 26.58, "learning_rate": 4.5811046753318735e-07, "loss": 0.7529, "step": 319730 }, { "epoch": 26.58, "learning_rate": 4.5799961200565365e-07, "loss": 0.6724, "step": 319740 }, { "epoch": 26.58, "learning_rate": 4.578887564781199e-07, "loss": 0.693, "step": 319750 }, { "epoch": 26.58, "learning_rate": 4.577779009505861e-07, "loss": 0.8269, "step": 319760 }, { "epoch": 26.58, "learning_rate": 4.576670454230524e-07, "loss": 0.6999, "step": 319770 }, { "epoch": 26.58, "learning_rate": 4.575561898955186e-07, "loss": 0.708, "step": 319780 }, { "epoch": 26.58, "learning_rate": 4.5744533436798486e-07, "loss": 0.7378, "step": 319790 }, { "epoch": 26.58, "learning_rate": 4.5733447884045115e-07, "loss": 0.7234, "step": 319800 }, { "epoch": 26.58, "learning_rate": 4.572236233129174e-07, "loss": 0.7849, "step": 319810 }, { "epoch": 26.58, "learning_rate": 4.5711276778538364e-07, "loss": 0.7795, "step": 319820 }, { "epoch": 26.58, "learning_rate": 4.5700191225784993e-07, "loss": 0.804, "step": 319830 }, { "epoch": 26.58, "learning_rate": 4.568910567303162e-07, "loss": 0.7453, "step": 319840 }, { "epoch": 26.59, "learning_rate": 4.567802012027824e-07, "loss": 0.7378, "step": 319850 }, { "epoch": 26.59, "learning_rate": 4.566693456752487e-07, "loss": 0.7329, "step": 319860 }, { "epoch": 26.59, "learning_rate": 4.5655849014771496e-07, "loss": 0.7497, "step": 319870 }, { "epoch": 26.59, "learning_rate": 4.564476346201812e-07, "loss": 0.695, "step": 319880 }, { "epoch": 26.59, "learning_rate": 4.563367790926475e-07, "loss": 0.6783, "step": 319890 }, { "epoch": 26.59, "learning_rate": 4.5622592356511374e-07, "loss": 0.7412, "step": 319900 }, { "epoch": 26.59, "learning_rate": 4.5611506803758e-07, "loss": 0.7553, "step": 319910 }, { "epoch": 26.59, "learning_rate": 4.560042125100463e-07, "loss": 0.7799, "step": 319920 }, { "epoch": 26.59, "learning_rate": 4.558933569825125e-07, "loss": 0.7005, "step": 319930 }, { "epoch": 26.59, "learning_rate": 4.5578250145497876e-07, "loss": 0.7242, "step": 319940 }, { "epoch": 26.59, "learning_rate": 4.5567164592744506e-07, "loss": 0.7723, "step": 319950 }, { "epoch": 26.59, "learning_rate": 4.555607903999113e-07, "loss": 0.7448, "step": 319960 }, { "epoch": 26.6, "learning_rate": 4.5544993487237754e-07, "loss": 0.7834, "step": 319970 }, { "epoch": 26.6, "learning_rate": 4.5533907934484384e-07, "loss": 0.72, "step": 319980 }, { "epoch": 26.6, "learning_rate": 4.552282238173101e-07, "loss": 0.7205, "step": 319990 }, { "epoch": 26.6, "learning_rate": 4.551173682897763e-07, "loss": 0.7619, "step": 320000 }, { "epoch": 26.6, "learning_rate": 4.550065127622426e-07, "loss": 0.7258, "step": 320010 }, { "epoch": 26.6, "learning_rate": 4.5489565723470886e-07, "loss": 0.714, "step": 320020 }, { "epoch": 26.6, "learning_rate": 4.547848017071751e-07, "loss": 0.7221, "step": 320030 }, { "epoch": 26.6, "learning_rate": 4.546739461796414e-07, "loss": 0.7403, "step": 320040 }, { "epoch": 26.6, "learning_rate": 4.5456309065210764e-07, "loss": 0.7231, "step": 320050 }, { "epoch": 26.6, "learning_rate": 4.544522351245739e-07, "loss": 0.7462, "step": 320060 }, { "epoch": 26.6, "learning_rate": 4.543413795970402e-07, "loss": 0.6854, "step": 320070 }, { "epoch": 26.6, "learning_rate": 4.542305240695064e-07, "loss": 0.7724, "step": 320080 }, { "epoch": 26.61, "learning_rate": 4.5411966854197266e-07, "loss": 0.8075, "step": 320090 }, { "epoch": 26.61, "learning_rate": 4.540088130144389e-07, "loss": 0.7568, "step": 320100 }, { "epoch": 26.61, "learning_rate": 4.538979574869052e-07, "loss": 0.7876, "step": 320110 }, { "epoch": 26.61, "learning_rate": 4.5378710195937144e-07, "loss": 0.7556, "step": 320120 }, { "epoch": 26.61, "learning_rate": 4.536762464318377e-07, "loss": 0.6739, "step": 320130 }, { "epoch": 26.61, "learning_rate": 4.53565390904304e-07, "loss": 0.719, "step": 320140 }, { "epoch": 26.61, "learning_rate": 4.534545353767702e-07, "loss": 0.7443, "step": 320150 }, { "epoch": 26.61, "learning_rate": 4.5334367984923646e-07, "loss": 0.7096, "step": 320160 }, { "epoch": 26.61, "learning_rate": 4.5323282432170276e-07, "loss": 0.755, "step": 320170 }, { "epoch": 26.61, "learning_rate": 4.5312196879416895e-07, "loss": 0.7303, "step": 320180 }, { "epoch": 26.61, "learning_rate": 4.530111132666352e-07, "loss": 0.6965, "step": 320190 }, { "epoch": 26.61, "learning_rate": 4.529002577391015e-07, "loss": 0.7536, "step": 320200 }, { "epoch": 26.62, "learning_rate": 4.5278940221156773e-07, "loss": 0.7961, "step": 320210 }, { "epoch": 26.62, "learning_rate": 4.5267854668403397e-07, "loss": 0.7411, "step": 320220 }, { "epoch": 26.62, "learning_rate": 4.5256769115650027e-07, "loss": 0.7168, "step": 320230 }, { "epoch": 26.62, "learning_rate": 4.524568356289665e-07, "loss": 0.6843, "step": 320240 }, { "epoch": 26.62, "learning_rate": 4.5234598010143275e-07, "loss": 0.756, "step": 320250 }, { "epoch": 26.62, "learning_rate": 4.5223512457389905e-07, "loss": 0.7589, "step": 320260 }, { "epoch": 26.62, "learning_rate": 4.521242690463653e-07, "loss": 0.7328, "step": 320270 }, { "epoch": 26.62, "learning_rate": 4.5201341351883153e-07, "loss": 0.771, "step": 320280 }, { "epoch": 26.62, "learning_rate": 4.519025579912978e-07, "loss": 0.7115, "step": 320290 }, { "epoch": 26.62, "learning_rate": 4.5179170246376407e-07, "loss": 0.7435, "step": 320300 }, { "epoch": 26.62, "learning_rate": 4.516808469362303e-07, "loss": 0.7199, "step": 320310 }, { "epoch": 26.62, "learning_rate": 4.515699914086966e-07, "loss": 0.7225, "step": 320320 }, { "epoch": 26.63, "learning_rate": 4.5145913588116285e-07, "loss": 0.6944, "step": 320330 }, { "epoch": 26.63, "learning_rate": 4.513482803536291e-07, "loss": 0.6962, "step": 320340 }, { "epoch": 26.63, "learning_rate": 4.512374248260954e-07, "loss": 0.7245, "step": 320350 }, { "epoch": 26.63, "learning_rate": 4.5112656929856163e-07, "loss": 0.792, "step": 320360 }, { "epoch": 26.63, "learning_rate": 4.5101571377102787e-07, "loss": 0.6969, "step": 320370 }, { "epoch": 26.63, "learning_rate": 4.5090485824349417e-07, "loss": 0.7506, "step": 320380 }, { "epoch": 26.63, "learning_rate": 4.507940027159604e-07, "loss": 0.7485, "step": 320390 }, { "epoch": 26.63, "learning_rate": 4.5068314718842665e-07, "loss": 0.7529, "step": 320400 }, { "epoch": 26.63, "learning_rate": 4.5057229166089295e-07, "loss": 0.7521, "step": 320410 }, { "epoch": 26.63, "learning_rate": 4.504614361333592e-07, "loss": 0.7546, "step": 320420 }, { "epoch": 26.63, "learning_rate": 4.5035058060582543e-07, "loss": 0.7181, "step": 320430 }, { "epoch": 26.63, "learning_rate": 4.5023972507829173e-07, "loss": 0.6951, "step": 320440 }, { "epoch": 26.64, "learning_rate": 4.5012886955075797e-07, "loss": 0.747, "step": 320450 }, { "epoch": 26.64, "learning_rate": 4.500180140232242e-07, "loss": 0.7387, "step": 320460 }, { "epoch": 26.64, "learning_rate": 4.499071584956905e-07, "loss": 0.7667, "step": 320470 }, { "epoch": 26.64, "learning_rate": 4.4979630296815675e-07, "loss": 0.6765, "step": 320480 }, { "epoch": 26.64, "learning_rate": 4.49685447440623e-07, "loss": 0.7722, "step": 320490 }, { "epoch": 26.64, "learning_rate": 4.4957459191308923e-07, "loss": 0.7847, "step": 320500 }, { "epoch": 26.64, "learning_rate": 4.4946373638555553e-07, "loss": 0.7698, "step": 320510 }, { "epoch": 26.64, "learning_rate": 4.4935288085802177e-07, "loss": 0.7481, "step": 320520 }, { "epoch": 26.64, "learning_rate": 4.49242025330488e-07, "loss": 0.7031, "step": 320530 }, { "epoch": 26.64, "learning_rate": 4.491311698029543e-07, "loss": 0.7398, "step": 320540 }, { "epoch": 26.64, "learning_rate": 4.4902031427542055e-07, "loss": 0.7574, "step": 320550 }, { "epoch": 26.64, "learning_rate": 4.489094587478868e-07, "loss": 0.7051, "step": 320560 }, { "epoch": 26.65, "learning_rate": 4.487986032203531e-07, "loss": 0.7553, "step": 320570 }, { "epoch": 26.65, "learning_rate": 4.4868774769281933e-07, "loss": 0.7407, "step": 320580 }, { "epoch": 26.65, "learning_rate": 4.485768921652855e-07, "loss": 0.7767, "step": 320590 }, { "epoch": 26.65, "learning_rate": 4.484660366377518e-07, "loss": 0.6849, "step": 320600 }, { "epoch": 26.65, "learning_rate": 4.4835518111021806e-07, "loss": 0.7642, "step": 320610 }, { "epoch": 26.65, "learning_rate": 4.482443255826843e-07, "loss": 0.7255, "step": 320620 }, { "epoch": 26.65, "learning_rate": 4.481334700551506e-07, "loss": 0.7399, "step": 320630 }, { "epoch": 26.65, "learning_rate": 4.4802261452761684e-07, "loss": 0.7144, "step": 320640 }, { "epoch": 26.65, "learning_rate": 4.479117590000831e-07, "loss": 0.6872, "step": 320650 }, { "epoch": 26.65, "learning_rate": 4.478009034725494e-07, "loss": 0.758, "step": 320660 }, { "epoch": 26.65, "learning_rate": 4.476900479450156e-07, "loss": 0.8271, "step": 320670 }, { "epoch": 26.65, "learning_rate": 4.4757919241748186e-07, "loss": 0.7877, "step": 320680 }, { "epoch": 26.66, "learning_rate": 4.4746833688994816e-07, "loss": 0.717, "step": 320690 }, { "epoch": 26.66, "learning_rate": 4.473574813624144e-07, "loss": 0.7103, "step": 320700 }, { "epoch": 26.66, "learning_rate": 4.4724662583488064e-07, "loss": 0.7011, "step": 320710 }, { "epoch": 26.66, "learning_rate": 4.4713577030734694e-07, "loss": 0.7648, "step": 320720 }, { "epoch": 26.66, "learning_rate": 4.470249147798132e-07, "loss": 0.7098, "step": 320730 }, { "epoch": 26.66, "learning_rate": 4.469140592522794e-07, "loss": 0.7471, "step": 320740 }, { "epoch": 26.66, "learning_rate": 4.468032037247457e-07, "loss": 0.7194, "step": 320750 }, { "epoch": 26.66, "learning_rate": 4.4669234819721196e-07, "loss": 0.7921, "step": 320760 }, { "epoch": 26.66, "learning_rate": 4.465814926696782e-07, "loss": 0.7721, "step": 320770 }, { "epoch": 26.66, "learning_rate": 4.464706371421445e-07, "loss": 0.7391, "step": 320780 }, { "epoch": 26.66, "learning_rate": 4.4635978161461074e-07, "loss": 0.6889, "step": 320790 }, { "epoch": 26.66, "learning_rate": 4.46248926087077e-07, "loss": 0.6903, "step": 320800 }, { "epoch": 26.67, "learning_rate": 4.461380705595433e-07, "loss": 0.7269, "step": 320810 }, { "epoch": 26.67, "learning_rate": 4.460272150320095e-07, "loss": 0.674, "step": 320820 }, { "epoch": 26.67, "learning_rate": 4.4591635950447576e-07, "loss": 0.7551, "step": 320830 }, { "epoch": 26.67, "learning_rate": 4.4580550397694206e-07, "loss": 0.6717, "step": 320840 }, { "epoch": 26.67, "learning_rate": 4.456946484494083e-07, "loss": 0.7103, "step": 320850 }, { "epoch": 26.67, "learning_rate": 4.4558379292187454e-07, "loss": 0.7622, "step": 320860 }, { "epoch": 26.67, "learning_rate": 4.4547293739434084e-07, "loss": 0.7399, "step": 320870 }, { "epoch": 26.67, "learning_rate": 4.453620818668071e-07, "loss": 0.6908, "step": 320880 }, { "epoch": 26.67, "learning_rate": 4.452512263392733e-07, "loss": 0.7593, "step": 320890 }, { "epoch": 26.67, "learning_rate": 4.451403708117396e-07, "loss": 0.7326, "step": 320900 }, { "epoch": 26.67, "learning_rate": 4.4502951528420586e-07, "loss": 0.7821, "step": 320910 }, { "epoch": 26.67, "learning_rate": 4.449186597566721e-07, "loss": 0.6907, "step": 320920 }, { "epoch": 26.68, "learning_rate": 4.4480780422913835e-07, "loss": 0.7386, "step": 320930 }, { "epoch": 26.68, "learning_rate": 4.4469694870160464e-07, "loss": 0.7061, "step": 320940 }, { "epoch": 26.68, "learning_rate": 4.445860931740709e-07, "loss": 0.7609, "step": 320950 }, { "epoch": 26.68, "learning_rate": 4.444752376465371e-07, "loss": 0.7042, "step": 320960 }, { "epoch": 26.68, "learning_rate": 4.443643821190034e-07, "loss": 0.7283, "step": 320970 }, { "epoch": 26.68, "learning_rate": 4.4425352659146966e-07, "loss": 0.748, "step": 320980 }, { "epoch": 26.68, "learning_rate": 4.441426710639359e-07, "loss": 0.7138, "step": 320990 }, { "epoch": 26.68, "learning_rate": 4.440318155364022e-07, "loss": 0.7619, "step": 321000 }, { "epoch": 26.68, "learning_rate": 4.439209600088684e-07, "loss": 0.7866, "step": 321010 }, { "epoch": 26.68, "learning_rate": 4.4381010448133463e-07, "loss": 0.7291, "step": 321020 }, { "epoch": 26.68, "learning_rate": 4.4369924895380093e-07, "loss": 0.7203, "step": 321030 }, { "epoch": 26.68, "learning_rate": 4.4358839342626717e-07, "loss": 0.7249, "step": 321040 }, { "epoch": 26.69, "learning_rate": 4.434775378987334e-07, "loss": 0.6723, "step": 321050 }, { "epoch": 26.69, "learning_rate": 4.433666823711997e-07, "loss": 0.7625, "step": 321060 }, { "epoch": 26.69, "learning_rate": 4.4325582684366595e-07, "loss": 0.7239, "step": 321070 }, { "epoch": 26.69, "learning_rate": 4.431449713161322e-07, "loss": 0.7376, "step": 321080 }, { "epoch": 26.69, "learning_rate": 4.430341157885985e-07, "loss": 0.7329, "step": 321090 }, { "epoch": 26.69, "learning_rate": 4.4292326026106473e-07, "loss": 0.6942, "step": 321100 }, { "epoch": 26.69, "learning_rate": 4.42812404733531e-07, "loss": 0.767, "step": 321110 }, { "epoch": 26.69, "learning_rate": 4.4270154920599727e-07, "loss": 0.7343, "step": 321120 }, { "epoch": 26.69, "learning_rate": 4.425906936784635e-07, "loss": 0.7588, "step": 321130 }, { "epoch": 26.69, "learning_rate": 4.4247983815092975e-07, "loss": 0.8115, "step": 321140 }, { "epoch": 26.69, "learning_rate": 4.4236898262339605e-07, "loss": 0.6919, "step": 321150 }, { "epoch": 26.69, "learning_rate": 4.422581270958623e-07, "loss": 0.7588, "step": 321160 }, { "epoch": 26.7, "learning_rate": 4.4214727156832853e-07, "loss": 0.729, "step": 321170 }, { "epoch": 26.7, "learning_rate": 4.4203641604079483e-07, "loss": 0.7574, "step": 321180 }, { "epoch": 26.7, "learning_rate": 4.4192556051326107e-07, "loss": 0.7095, "step": 321190 }, { "epoch": 26.7, "learning_rate": 4.418147049857273e-07, "loss": 0.7398, "step": 321200 }, { "epoch": 26.7, "learning_rate": 4.417038494581936e-07, "loss": 0.7901, "step": 321210 }, { "epoch": 26.7, "learning_rate": 4.4159299393065985e-07, "loss": 0.7482, "step": 321220 }, { "epoch": 26.7, "learning_rate": 4.414821384031261e-07, "loss": 0.6817, "step": 321230 }, { "epoch": 26.7, "learning_rate": 4.413712828755924e-07, "loss": 0.7638, "step": 321240 }, { "epoch": 26.7, "learning_rate": 4.4126042734805863e-07, "loss": 0.7114, "step": 321250 }, { "epoch": 26.7, "learning_rate": 4.411495718205249e-07, "loss": 0.742, "step": 321260 }, { "epoch": 26.7, "learning_rate": 4.4103871629299117e-07, "loss": 0.7518, "step": 321270 }, { "epoch": 26.7, "learning_rate": 4.409278607654574e-07, "loss": 0.7396, "step": 321280 }, { "epoch": 26.71, "learning_rate": 4.4081700523792365e-07, "loss": 0.7238, "step": 321290 }, { "epoch": 26.71, "learning_rate": 4.4070614971038995e-07, "loss": 0.7065, "step": 321300 }, { "epoch": 26.71, "learning_rate": 4.405952941828562e-07, "loss": 0.7395, "step": 321310 }, { "epoch": 26.71, "learning_rate": 4.4048443865532243e-07, "loss": 0.7576, "step": 321320 }, { "epoch": 26.71, "learning_rate": 4.4037358312778873e-07, "loss": 0.7249, "step": 321330 }, { "epoch": 26.71, "learning_rate": 4.4026272760025497e-07, "loss": 0.7224, "step": 321340 }, { "epoch": 26.71, "learning_rate": 4.401518720727212e-07, "loss": 0.6775, "step": 321350 }, { "epoch": 26.71, "learning_rate": 4.4004101654518746e-07, "loss": 0.7677, "step": 321360 }, { "epoch": 26.71, "learning_rate": 4.399412465704071e-07, "loss": 0.7688, "step": 321370 }, { "epoch": 26.71, "learning_rate": 4.3983039104287334e-07, "loss": 0.7469, "step": 321380 }, { "epoch": 26.71, "learning_rate": 4.3971953551533964e-07, "loss": 0.776, "step": 321390 }, { "epoch": 26.71, "learning_rate": 4.396086799878059e-07, "loss": 0.7368, "step": 321400 }, { "epoch": 26.72, "learning_rate": 4.394978244602721e-07, "loss": 0.7395, "step": 321410 }, { "epoch": 26.72, "learning_rate": 4.393869689327384e-07, "loss": 0.7517, "step": 321420 }, { "epoch": 26.72, "learning_rate": 4.3927611340520466e-07, "loss": 0.7377, "step": 321430 }, { "epoch": 26.72, "learning_rate": 4.391652578776709e-07, "loss": 0.746, "step": 321440 }, { "epoch": 26.72, "learning_rate": 4.390544023501372e-07, "loss": 0.7325, "step": 321450 }, { "epoch": 26.72, "learning_rate": 4.3894354682260344e-07, "loss": 0.7358, "step": 321460 }, { "epoch": 26.72, "learning_rate": 4.388326912950697e-07, "loss": 0.7699, "step": 321470 }, { "epoch": 26.72, "learning_rate": 4.38721835767536e-07, "loss": 0.7925, "step": 321480 }, { "epoch": 26.72, "learning_rate": 4.386109802400022e-07, "loss": 0.6797, "step": 321490 }, { "epoch": 26.72, "learning_rate": 4.3850012471246846e-07, "loss": 0.6871, "step": 321500 }, { "epoch": 26.72, "learning_rate": 4.3838926918493476e-07, "loss": 0.7184, "step": 321510 }, { "epoch": 26.72, "learning_rate": 4.38278413657401e-07, "loss": 0.7255, "step": 321520 }, { "epoch": 26.73, "learning_rate": 4.3816755812986724e-07, "loss": 0.7644, "step": 321530 }, { "epoch": 26.73, "learning_rate": 4.3805670260233354e-07, "loss": 0.7171, "step": 321540 }, { "epoch": 26.73, "learning_rate": 4.379458470747998e-07, "loss": 0.7101, "step": 321550 }, { "epoch": 26.73, "learning_rate": 4.3783499154726597e-07, "loss": 0.7453, "step": 321560 }, { "epoch": 26.73, "learning_rate": 4.377241360197322e-07, "loss": 0.7444, "step": 321570 }, { "epoch": 26.73, "learning_rate": 4.376132804921985e-07, "loss": 0.7661, "step": 321580 }, { "epoch": 26.73, "learning_rate": 4.3750242496466475e-07, "loss": 0.7316, "step": 321590 }, { "epoch": 26.73, "learning_rate": 4.37391569437131e-07, "loss": 0.755, "step": 321600 }, { "epoch": 26.73, "learning_rate": 4.372807139095973e-07, "loss": 0.7458, "step": 321610 }, { "epoch": 26.73, "learning_rate": 4.3716985838206353e-07, "loss": 0.7771, "step": 321620 }, { "epoch": 26.73, "learning_rate": 4.370590028545298e-07, "loss": 0.7462, "step": 321630 }, { "epoch": 26.73, "learning_rate": 4.3694814732699607e-07, "loss": 0.7415, "step": 321640 }, { "epoch": 26.74, "learning_rate": 4.368372917994623e-07, "loss": 0.7486, "step": 321650 }, { "epoch": 26.74, "learning_rate": 4.3672643627192855e-07, "loss": 0.7211, "step": 321660 }, { "epoch": 26.74, "learning_rate": 4.3661558074439485e-07, "loss": 0.6977, "step": 321670 }, { "epoch": 26.74, "learning_rate": 4.365047252168611e-07, "loss": 0.73, "step": 321680 }, { "epoch": 26.74, "learning_rate": 4.3639386968932734e-07, "loss": 0.7004, "step": 321690 }, { "epoch": 26.74, "learning_rate": 4.3628301416179363e-07, "loss": 0.7452, "step": 321700 }, { "epoch": 26.74, "learning_rate": 4.3617215863425987e-07, "loss": 0.806, "step": 321710 }, { "epoch": 26.74, "learning_rate": 4.360613031067261e-07, "loss": 0.731, "step": 321720 }, { "epoch": 26.74, "learning_rate": 4.359504475791924e-07, "loss": 0.7144, "step": 321730 }, { "epoch": 26.74, "learning_rate": 4.3583959205165865e-07, "loss": 0.7288, "step": 321740 }, { "epoch": 26.74, "learning_rate": 4.357287365241249e-07, "loss": 0.7545, "step": 321750 }, { "epoch": 26.74, "learning_rate": 4.356178809965912e-07, "loss": 0.7808, "step": 321760 }, { "epoch": 26.75, "learning_rate": 4.3550702546905743e-07, "loss": 0.7381, "step": 321770 }, { "epoch": 26.75, "learning_rate": 4.353961699415237e-07, "loss": 0.6871, "step": 321780 }, { "epoch": 26.75, "learning_rate": 4.3528531441398997e-07, "loss": 0.7406, "step": 321790 }, { "epoch": 26.75, "learning_rate": 4.351744588864562e-07, "loss": 0.6903, "step": 321800 }, { "epoch": 26.75, "learning_rate": 4.3506360335892246e-07, "loss": 0.7704, "step": 321810 }, { "epoch": 26.75, "learning_rate": 4.3495274783138875e-07, "loss": 0.7385, "step": 321820 }, { "epoch": 26.75, "learning_rate": 4.34841892303855e-07, "loss": 0.7766, "step": 321830 }, { "epoch": 26.75, "learning_rate": 4.3473103677632124e-07, "loss": 0.7176, "step": 321840 }, { "epoch": 26.75, "learning_rate": 4.3462018124878753e-07, "loss": 0.7106, "step": 321850 }, { "epoch": 26.75, "learning_rate": 4.3450932572125377e-07, "loss": 0.7655, "step": 321860 }, { "epoch": 26.75, "learning_rate": 4.3439847019372e-07, "loss": 0.7328, "step": 321870 }, { "epoch": 26.75, "learning_rate": 4.342876146661863e-07, "loss": 0.6543, "step": 321880 }, { "epoch": 26.76, "learning_rate": 4.3417675913865255e-07, "loss": 0.7715, "step": 321890 }, { "epoch": 26.76, "learning_rate": 4.340659036111188e-07, "loss": 0.7377, "step": 321900 }, { "epoch": 26.76, "learning_rate": 4.339550480835851e-07, "loss": 0.7589, "step": 321910 }, { "epoch": 26.76, "learning_rate": 4.3384419255605133e-07, "loss": 0.6849, "step": 321920 }, { "epoch": 26.76, "learning_rate": 4.337333370285176e-07, "loss": 0.6931, "step": 321930 }, { "epoch": 26.76, "learning_rate": 4.3362248150098387e-07, "loss": 0.7067, "step": 321940 }, { "epoch": 26.76, "learning_rate": 4.335116259734501e-07, "loss": 0.7549, "step": 321950 }, { "epoch": 26.76, "learning_rate": 4.3340077044591636e-07, "loss": 0.7493, "step": 321960 }, { "epoch": 26.76, "learning_rate": 4.3328991491838255e-07, "loss": 0.7143, "step": 321970 }, { "epoch": 26.76, "learning_rate": 4.3317905939084884e-07, "loss": 0.7131, "step": 321980 }, { "epoch": 26.76, "learning_rate": 4.330682038633151e-07, "loss": 0.7525, "step": 321990 }, { "epoch": 26.76, "learning_rate": 4.329573483357813e-07, "loss": 0.6883, "step": 322000 }, { "epoch": 26.77, "learning_rate": 4.328464928082476e-07, "loss": 0.7548, "step": 322010 }, { "epoch": 26.77, "learning_rate": 4.3273563728071386e-07, "loss": 0.7317, "step": 322020 }, { "epoch": 26.77, "learning_rate": 4.326247817531801e-07, "loss": 0.6804, "step": 322030 }, { "epoch": 26.77, "learning_rate": 4.325250117783998e-07, "loss": 0.7246, "step": 322040 }, { "epoch": 26.77, "learning_rate": 4.3241415625086605e-07, "loss": 0.7574, "step": 322050 }, { "epoch": 26.77, "learning_rate": 4.3230330072333234e-07, "loss": 0.7804, "step": 322060 }, { "epoch": 26.77, "learning_rate": 4.321924451957986e-07, "loss": 0.7426, "step": 322070 }, { "epoch": 26.77, "learning_rate": 4.320815896682648e-07, "loss": 0.7903, "step": 322080 }, { "epoch": 26.77, "learning_rate": 4.319707341407311e-07, "loss": 0.735, "step": 322090 }, { "epoch": 26.77, "learning_rate": 4.318598786131973e-07, "loss": 0.766, "step": 322100 }, { "epoch": 26.77, "learning_rate": 4.3174902308566355e-07, "loss": 0.7391, "step": 322110 }, { "epoch": 26.77, "learning_rate": 4.3163816755812985e-07, "loss": 0.6822, "step": 322120 }, { "epoch": 26.77, "learning_rate": 4.315273120305961e-07, "loss": 0.7926, "step": 322130 }, { "epoch": 26.78, "learning_rate": 4.3141645650306233e-07, "loss": 0.6761, "step": 322140 }, { "epoch": 26.78, "learning_rate": 4.3130560097552863e-07, "loss": 0.8134, "step": 322150 }, { "epoch": 26.78, "learning_rate": 4.3119474544799487e-07, "loss": 0.7587, "step": 322160 }, { "epoch": 26.78, "learning_rate": 4.310838899204611e-07, "loss": 0.7229, "step": 322170 }, { "epoch": 26.78, "learning_rate": 4.3097303439292736e-07, "loss": 0.7213, "step": 322180 }, { "epoch": 26.78, "learning_rate": 4.3086217886539365e-07, "loss": 0.7139, "step": 322190 }, { "epoch": 26.78, "learning_rate": 4.307513233378599e-07, "loss": 0.7512, "step": 322200 }, { "epoch": 26.78, "learning_rate": 4.3064046781032614e-07, "loss": 0.7599, "step": 322210 }, { "epoch": 26.78, "learning_rate": 4.3052961228279243e-07, "loss": 0.7704, "step": 322220 }, { "epoch": 26.78, "learning_rate": 4.304187567552587e-07, "loss": 0.7381, "step": 322230 }, { "epoch": 26.78, "learning_rate": 4.303079012277249e-07, "loss": 0.7544, "step": 322240 }, { "epoch": 26.78, "learning_rate": 4.301970457001912e-07, "loss": 0.7175, "step": 322250 }, { "epoch": 26.79, "learning_rate": 4.3008619017265745e-07, "loss": 0.7589, "step": 322260 }, { "epoch": 26.79, "learning_rate": 4.299753346451237e-07, "loss": 0.7345, "step": 322270 }, { "epoch": 26.79, "learning_rate": 4.2986447911759e-07, "loss": 0.6931, "step": 322280 }, { "epoch": 26.79, "learning_rate": 4.2975362359005623e-07, "loss": 0.7242, "step": 322290 }, { "epoch": 26.79, "learning_rate": 4.296427680625225e-07, "loss": 0.6956, "step": 322300 }, { "epoch": 26.79, "learning_rate": 4.2953191253498877e-07, "loss": 0.7163, "step": 322310 }, { "epoch": 26.79, "learning_rate": 4.29421057007455e-07, "loss": 0.7823, "step": 322320 }, { "epoch": 26.79, "learning_rate": 4.2931020147992126e-07, "loss": 0.7338, "step": 322330 }, { "epoch": 26.79, "learning_rate": 4.2919934595238755e-07, "loss": 0.7299, "step": 322340 }, { "epoch": 26.79, "learning_rate": 4.290884904248538e-07, "loss": 0.7276, "step": 322350 }, { "epoch": 26.79, "learning_rate": 4.2897763489732004e-07, "loss": 0.7249, "step": 322360 }, { "epoch": 26.79, "learning_rate": 4.2886677936978633e-07, "loss": 0.7214, "step": 322370 }, { "epoch": 26.8, "learning_rate": 4.287559238422526e-07, "loss": 0.7565, "step": 322380 }, { "epoch": 26.8, "learning_rate": 4.286450683147188e-07, "loss": 0.7245, "step": 322390 }, { "epoch": 26.8, "learning_rate": 4.285342127871851e-07, "loss": 0.7029, "step": 322400 }, { "epoch": 26.8, "learning_rate": 4.2842335725965135e-07, "loss": 0.7432, "step": 322410 }, { "epoch": 26.8, "learning_rate": 4.283125017321176e-07, "loss": 0.7588, "step": 322420 }, { "epoch": 26.8, "learning_rate": 4.282016462045839e-07, "loss": 0.7505, "step": 322430 }, { "epoch": 26.8, "learning_rate": 4.2809079067705013e-07, "loss": 0.7016, "step": 322440 }, { "epoch": 26.8, "learning_rate": 4.279799351495164e-07, "loss": 0.7256, "step": 322450 }, { "epoch": 26.8, "learning_rate": 4.2786907962198267e-07, "loss": 0.79, "step": 322460 }, { "epoch": 26.8, "learning_rate": 4.277582240944489e-07, "loss": 0.7574, "step": 322470 }, { "epoch": 26.8, "learning_rate": 4.2764736856691516e-07, "loss": 0.7704, "step": 322480 }, { "epoch": 26.8, "learning_rate": 4.2753651303938145e-07, "loss": 0.7395, "step": 322490 }, { "epoch": 26.81, "learning_rate": 4.274256575118477e-07, "loss": 0.7378, "step": 322500 }, { "epoch": 26.81, "learning_rate": 4.273148019843139e-07, "loss": 0.7577, "step": 322510 }, { "epoch": 26.81, "learning_rate": 4.2720394645678023e-07, "loss": 0.7286, "step": 322520 }, { "epoch": 26.81, "learning_rate": 4.270930909292464e-07, "loss": 0.7002, "step": 322530 }, { "epoch": 26.81, "learning_rate": 4.2698223540171266e-07, "loss": 0.7102, "step": 322540 }, { "epoch": 26.81, "learning_rate": 4.2687137987417896e-07, "loss": 0.7363, "step": 322550 }, { "epoch": 26.81, "learning_rate": 4.267605243466452e-07, "loss": 0.7798, "step": 322560 }, { "epoch": 26.81, "learning_rate": 4.2664966881911144e-07, "loss": 0.7172, "step": 322570 }, { "epoch": 26.81, "learning_rate": 4.2653881329157774e-07, "loss": 0.8001, "step": 322580 }, { "epoch": 26.81, "learning_rate": 4.26427957764044e-07, "loss": 0.7386, "step": 322590 }, { "epoch": 26.81, "learning_rate": 4.263171022365102e-07, "loss": 0.7018, "step": 322600 }, { "epoch": 26.81, "learning_rate": 4.2620624670897647e-07, "loss": 0.7553, "step": 322610 }, { "epoch": 26.82, "learning_rate": 4.2609539118144276e-07, "loss": 0.7735, "step": 322620 }, { "epoch": 26.82, "learning_rate": 4.25984535653909e-07, "loss": 0.7154, "step": 322630 }, { "epoch": 26.82, "learning_rate": 4.2587368012637525e-07, "loss": 0.7336, "step": 322640 }, { "epoch": 26.82, "learning_rate": 4.2576282459884154e-07, "loss": 0.7451, "step": 322650 }, { "epoch": 26.82, "learning_rate": 4.256519690713078e-07, "loss": 0.7054, "step": 322660 }, { "epoch": 26.82, "learning_rate": 4.2554111354377403e-07, "loss": 0.7107, "step": 322670 }, { "epoch": 26.82, "learning_rate": 4.254302580162403e-07, "loss": 0.7137, "step": 322680 }, { "epoch": 26.82, "learning_rate": 4.2531940248870657e-07, "loss": 0.7386, "step": 322690 }, { "epoch": 26.82, "learning_rate": 4.252085469611728e-07, "loss": 0.7526, "step": 322700 }, { "epoch": 26.82, "learning_rate": 4.250976914336391e-07, "loss": 0.7357, "step": 322710 }, { "epoch": 26.82, "learning_rate": 4.2498683590610535e-07, "loss": 0.7029, "step": 322720 }, { "epoch": 26.82, "learning_rate": 4.248759803785716e-07, "loss": 0.6852, "step": 322730 }, { "epoch": 26.83, "learning_rate": 4.247651248510379e-07, "loss": 0.7609, "step": 322740 }, { "epoch": 26.83, "learning_rate": 4.246542693235041e-07, "loss": 0.7124, "step": 322750 }, { "epoch": 26.83, "learning_rate": 4.2454341379597037e-07, "loss": 0.7616, "step": 322760 }, { "epoch": 26.83, "learning_rate": 4.2443255826843666e-07, "loss": 0.7253, "step": 322770 }, { "epoch": 26.83, "learning_rate": 4.243217027409029e-07, "loss": 0.7359, "step": 322780 }, { "epoch": 26.83, "learning_rate": 4.2421084721336915e-07, "loss": 0.7435, "step": 322790 }, { "epoch": 26.83, "learning_rate": 4.2409999168583544e-07, "loss": 0.7589, "step": 322800 }, { "epoch": 26.83, "learning_rate": 4.239891361583017e-07, "loss": 0.7426, "step": 322810 }, { "epoch": 26.83, "learning_rate": 4.2387828063076793e-07, "loss": 0.7216, "step": 322820 }, { "epoch": 26.83, "learning_rate": 4.237674251032342e-07, "loss": 0.7635, "step": 322830 }, { "epoch": 26.83, "learning_rate": 4.2365656957570047e-07, "loss": 0.6902, "step": 322840 }, { "epoch": 26.83, "learning_rate": 4.235457140481667e-07, "loss": 0.7575, "step": 322850 }, { "epoch": 26.84, "learning_rate": 4.23434858520633e-07, "loss": 0.7732, "step": 322860 }, { "epoch": 26.84, "learning_rate": 4.2332400299309925e-07, "loss": 0.6902, "step": 322870 }, { "epoch": 26.84, "learning_rate": 4.232131474655655e-07, "loss": 0.7606, "step": 322880 }, { "epoch": 26.84, "learning_rate": 4.231022919380318e-07, "loss": 0.7769, "step": 322890 }, { "epoch": 26.84, "learning_rate": 4.22991436410498e-07, "loss": 0.6814, "step": 322900 }, { "epoch": 26.84, "learning_rate": 4.2288058088296427e-07, "loss": 0.768, "step": 322910 }, { "epoch": 26.84, "learning_rate": 4.2276972535543056e-07, "loss": 0.7466, "step": 322920 }, { "epoch": 26.84, "learning_rate": 4.226588698278968e-07, "loss": 0.6865, "step": 322930 }, { "epoch": 26.84, "learning_rate": 4.22548014300363e-07, "loss": 0.7042, "step": 322940 }, { "epoch": 26.84, "learning_rate": 4.224371587728293e-07, "loss": 0.7392, "step": 322950 }, { "epoch": 26.84, "learning_rate": 4.2232630324529553e-07, "loss": 0.7504, "step": 322960 }, { "epoch": 26.84, "learning_rate": 4.222154477177618e-07, "loss": 0.741, "step": 322970 }, { "epoch": 26.85, "learning_rate": 4.2210459219022807e-07, "loss": 0.7241, "step": 322980 }, { "epoch": 26.85, "learning_rate": 4.219937366626943e-07, "loss": 0.712, "step": 322990 }, { "epoch": 26.85, "learning_rate": 4.2188288113516056e-07, "loss": 0.6968, "step": 323000 }, { "epoch": 26.85, "learning_rate": 4.217720256076268e-07, "loss": 0.7779, "step": 323010 }, { "epoch": 26.85, "learning_rate": 4.216611700800931e-07, "loss": 0.759, "step": 323020 }, { "epoch": 26.85, "learning_rate": 4.2155031455255934e-07, "loss": 0.6901, "step": 323030 }, { "epoch": 26.85, "learning_rate": 4.214394590250256e-07, "loss": 0.7078, "step": 323040 }, { "epoch": 26.85, "learning_rate": 4.213286034974919e-07, "loss": 0.731, "step": 323050 }, { "epoch": 26.85, "learning_rate": 4.212177479699581e-07, "loss": 0.7727, "step": 323060 }, { "epoch": 26.85, "learning_rate": 4.2110689244242436e-07, "loss": 0.7917, "step": 323070 }, { "epoch": 26.85, "learning_rate": 4.2099603691489065e-07, "loss": 0.7206, "step": 323080 }, { "epoch": 26.85, "learning_rate": 4.208851813873569e-07, "loss": 0.7399, "step": 323090 }, { "epoch": 26.86, "learning_rate": 4.2077432585982314e-07, "loss": 0.7807, "step": 323100 }, { "epoch": 26.86, "learning_rate": 4.2066347033228943e-07, "loss": 0.7535, "step": 323110 }, { "epoch": 26.86, "learning_rate": 4.205526148047557e-07, "loss": 0.7265, "step": 323120 }, { "epoch": 26.86, "learning_rate": 4.204417592772219e-07, "loss": 0.7095, "step": 323130 }, { "epoch": 26.86, "learning_rate": 4.203309037496882e-07, "loss": 0.7412, "step": 323140 }, { "epoch": 26.86, "learning_rate": 4.2022004822215446e-07, "loss": 0.7416, "step": 323150 }, { "epoch": 26.86, "learning_rate": 4.201091926946207e-07, "loss": 0.7843, "step": 323160 }, { "epoch": 26.86, "learning_rate": 4.19998337167087e-07, "loss": 0.8187, "step": 323170 }, { "epoch": 26.86, "learning_rate": 4.1988748163955324e-07, "loss": 0.7912, "step": 323180 }, { "epoch": 26.86, "learning_rate": 4.197766261120195e-07, "loss": 0.781, "step": 323190 }, { "epoch": 26.86, "learning_rate": 4.196657705844858e-07, "loss": 0.6999, "step": 323200 }, { "epoch": 26.86, "learning_rate": 4.19554915056952e-07, "loss": 0.7216, "step": 323210 }, { "epoch": 26.87, "learning_rate": 4.1944405952941826e-07, "loss": 0.7691, "step": 323220 }, { "epoch": 26.87, "learning_rate": 4.1933320400188455e-07, "loss": 0.7637, "step": 323230 }, { "epoch": 26.87, "learning_rate": 4.192223484743508e-07, "loss": 0.7401, "step": 323240 }, { "epoch": 26.87, "learning_rate": 4.1911149294681704e-07, "loss": 0.6965, "step": 323250 }, { "epoch": 26.87, "learning_rate": 4.1900063741928333e-07, "loss": 0.733, "step": 323260 }, { "epoch": 26.87, "learning_rate": 4.188897818917496e-07, "loss": 0.7384, "step": 323270 }, { "epoch": 26.87, "learning_rate": 4.187789263642158e-07, "loss": 0.7436, "step": 323280 }, { "epoch": 26.87, "learning_rate": 4.186680708366821e-07, "loss": 0.7536, "step": 323290 }, { "epoch": 26.87, "learning_rate": 4.1855721530914836e-07, "loss": 0.7728, "step": 323300 }, { "epoch": 26.87, "learning_rate": 4.184463597816146e-07, "loss": 0.7505, "step": 323310 }, { "epoch": 26.87, "learning_rate": 4.183355042540809e-07, "loss": 0.7297, "step": 323320 }, { "epoch": 26.87, "learning_rate": 4.1822464872654714e-07, "loss": 0.7244, "step": 323330 }, { "epoch": 26.88, "learning_rate": 4.181137931990134e-07, "loss": 0.6951, "step": 323340 }, { "epoch": 26.88, "learning_rate": 4.180029376714797e-07, "loss": 0.7311, "step": 323350 }, { "epoch": 26.88, "learning_rate": 4.1789208214394586e-07, "loss": 0.7143, "step": 323360 }, { "epoch": 26.88, "learning_rate": 4.177812266164121e-07, "loss": 0.7618, "step": 323370 }, { "epoch": 26.88, "learning_rate": 4.176703710888784e-07, "loss": 0.751, "step": 323380 }, { "epoch": 26.88, "learning_rate": 4.1755951556134464e-07, "loss": 0.7853, "step": 323390 }, { "epoch": 26.88, "learning_rate": 4.174486600338109e-07, "loss": 0.696, "step": 323400 }, { "epoch": 26.88, "learning_rate": 4.173378045062772e-07, "loss": 0.7211, "step": 323410 }, { "epoch": 26.88, "learning_rate": 4.172269489787434e-07, "loss": 0.7427, "step": 323420 }, { "epoch": 26.88, "learning_rate": 4.1711609345120967e-07, "loss": 0.7847, "step": 323430 }, { "epoch": 26.88, "learning_rate": 4.170052379236759e-07, "loss": 0.6698, "step": 323440 }, { "epoch": 26.88, "learning_rate": 4.168943823961422e-07, "loss": 0.7646, "step": 323450 }, { "epoch": 26.89, "learning_rate": 4.1678352686860845e-07, "loss": 0.7582, "step": 323460 }, { "epoch": 26.89, "learning_rate": 4.166726713410747e-07, "loss": 0.775, "step": 323470 }, { "epoch": 26.89, "learning_rate": 4.16561815813541e-07, "loss": 0.7371, "step": 323480 }, { "epoch": 26.89, "learning_rate": 4.1645096028600723e-07, "loss": 0.6928, "step": 323490 }, { "epoch": 26.89, "learning_rate": 4.1634010475847347e-07, "loss": 0.7515, "step": 323500 }, { "epoch": 26.89, "learning_rate": 4.1622924923093977e-07, "loss": 0.7044, "step": 323510 }, { "epoch": 26.89, "learning_rate": 4.16118393703406e-07, "loss": 0.7798, "step": 323520 }, { "epoch": 26.89, "learning_rate": 4.1600753817587225e-07, "loss": 0.6982, "step": 323530 }, { "epoch": 26.89, "learning_rate": 4.1589668264833855e-07, "loss": 0.763, "step": 323540 }, { "epoch": 26.89, "learning_rate": 4.157858271208048e-07, "loss": 0.7486, "step": 323550 }, { "epoch": 26.89, "learning_rate": 4.1567497159327103e-07, "loss": 0.6883, "step": 323560 }, { "epoch": 26.89, "learning_rate": 4.155641160657373e-07, "loss": 0.729, "step": 323570 }, { "epoch": 26.9, "learning_rate": 4.1545326053820357e-07, "loss": 0.6872, "step": 323580 }, { "epoch": 26.9, "learning_rate": 4.153424050106698e-07, "loss": 0.7392, "step": 323590 }, { "epoch": 26.9, "learning_rate": 4.152315494831361e-07, "loss": 0.6996, "step": 323600 }, { "epoch": 26.9, "learning_rate": 4.1512069395560235e-07, "loss": 0.7267, "step": 323610 }, { "epoch": 26.9, "learning_rate": 4.150098384280686e-07, "loss": 0.7237, "step": 323620 }, { "epoch": 26.9, "learning_rate": 4.148989829005349e-07, "loss": 0.7614, "step": 323630 }, { "epoch": 26.9, "learning_rate": 4.1478812737300113e-07, "loss": 0.771, "step": 323640 }, { "epoch": 26.9, "learning_rate": 4.1467727184546737e-07, "loss": 0.7009, "step": 323650 }, { "epoch": 26.9, "learning_rate": 4.1456641631793367e-07, "loss": 0.7977, "step": 323660 }, { "epoch": 26.9, "learning_rate": 4.144555607903999e-07, "loss": 0.7251, "step": 323670 }, { "epoch": 26.9, "learning_rate": 4.1434470526286615e-07, "loss": 0.7295, "step": 323680 }, { "epoch": 26.9, "learning_rate": 4.1423384973533245e-07, "loss": 0.7412, "step": 323690 }, { "epoch": 26.91, "learning_rate": 4.141229942077987e-07, "loss": 0.759, "step": 323700 }, { "epoch": 26.91, "learning_rate": 4.1401213868026493e-07, "loss": 0.7109, "step": 323710 }, { "epoch": 26.91, "learning_rate": 4.139012831527312e-07, "loss": 0.7919, "step": 323720 }, { "epoch": 26.91, "learning_rate": 4.1379042762519747e-07, "loss": 0.7261, "step": 323730 }, { "epoch": 26.91, "learning_rate": 4.136795720976637e-07, "loss": 0.7693, "step": 323740 }, { "epoch": 26.91, "learning_rate": 4.1356871657013e-07, "loss": 0.678, "step": 323750 }, { "epoch": 26.91, "learning_rate": 4.1345786104259625e-07, "loss": 0.762, "step": 323760 }, { "epoch": 26.91, "learning_rate": 4.1334700551506244e-07, "loss": 0.785, "step": 323770 }, { "epoch": 26.91, "learning_rate": 4.1323614998752873e-07, "loss": 0.7304, "step": 323780 }, { "epoch": 26.91, "learning_rate": 4.13125294459995e-07, "loss": 0.727, "step": 323790 }, { "epoch": 26.91, "learning_rate": 4.130144389324612e-07, "loss": 0.7318, "step": 323800 }, { "epoch": 26.91, "learning_rate": 4.129035834049275e-07, "loss": 0.7572, "step": 323810 }, { "epoch": 26.92, "learning_rate": 4.1279272787739376e-07, "loss": 0.7674, "step": 323820 }, { "epoch": 26.92, "learning_rate": 4.1268187234986e-07, "loss": 0.7429, "step": 323830 }, { "epoch": 26.92, "learning_rate": 4.125710168223263e-07, "loss": 0.7718, "step": 323840 }, { "epoch": 26.92, "learning_rate": 4.1246016129479254e-07, "loss": 0.7861, "step": 323850 }, { "epoch": 26.92, "learning_rate": 4.123493057672588e-07, "loss": 0.7715, "step": 323860 }, { "epoch": 26.92, "learning_rate": 4.12238450239725e-07, "loss": 0.6929, "step": 323870 }, { "epoch": 26.92, "learning_rate": 4.121275947121913e-07, "loss": 0.7382, "step": 323880 }, { "epoch": 26.92, "learning_rate": 4.1201673918465756e-07, "loss": 0.7392, "step": 323890 }, { "epoch": 26.92, "learning_rate": 4.119058836571238e-07, "loss": 0.7734, "step": 323900 }, { "epoch": 26.92, "learning_rate": 4.117950281295901e-07, "loss": 0.7201, "step": 323910 }, { "epoch": 26.92, "learning_rate": 4.1168417260205634e-07, "loss": 0.6818, "step": 323920 }, { "epoch": 26.92, "learning_rate": 4.115733170745226e-07, "loss": 0.7008, "step": 323930 }, { "epoch": 26.93, "learning_rate": 4.114624615469889e-07, "loss": 0.7844, "step": 323940 }, { "epoch": 26.93, "learning_rate": 4.113516060194551e-07, "loss": 0.7422, "step": 323950 }, { "epoch": 26.93, "learning_rate": 4.1124075049192136e-07, "loss": 0.7256, "step": 323960 }, { "epoch": 26.93, "learning_rate": 4.1112989496438766e-07, "loss": 0.7803, "step": 323970 }, { "epoch": 26.93, "learning_rate": 4.110190394368539e-07, "loss": 0.6838, "step": 323980 }, { "epoch": 26.93, "learning_rate": 4.1090818390932014e-07, "loss": 0.7293, "step": 323990 }, { "epoch": 26.93, "learning_rate": 4.1079732838178644e-07, "loss": 0.677, "step": 324000 }, { "epoch": 26.93, "learning_rate": 4.106864728542527e-07, "loss": 0.7809, "step": 324010 }, { "epoch": 26.93, "learning_rate": 4.105756173267189e-07, "loss": 0.7811, "step": 324020 }, { "epoch": 26.93, "learning_rate": 4.104647617991852e-07, "loss": 0.7588, "step": 324030 }, { "epoch": 26.93, "learning_rate": 4.1035390627165146e-07, "loss": 0.7165, "step": 324040 }, { "epoch": 26.93, "learning_rate": 4.102430507441177e-07, "loss": 0.7128, "step": 324050 }, { "epoch": 26.94, "learning_rate": 4.10132195216584e-07, "loss": 0.7035, "step": 324060 }, { "epoch": 26.94, "learning_rate": 4.1002133968905024e-07, "loss": 0.7916, "step": 324070 }, { "epoch": 26.94, "learning_rate": 4.099104841615165e-07, "loss": 0.6923, "step": 324080 }, { "epoch": 26.94, "learning_rate": 4.097996286339828e-07, "loss": 0.7037, "step": 324090 }, { "epoch": 26.94, "learning_rate": 4.09688773106449e-07, "loss": 0.709, "step": 324100 }, { "epoch": 26.94, "learning_rate": 4.0957791757891526e-07, "loss": 0.7546, "step": 324110 }, { "epoch": 26.94, "learning_rate": 4.0946706205138156e-07, "loss": 0.7994, "step": 324120 }, { "epoch": 26.94, "learning_rate": 4.093562065238478e-07, "loss": 0.6885, "step": 324130 }, { "epoch": 26.94, "learning_rate": 4.0924535099631404e-07, "loss": 0.6987, "step": 324140 }, { "epoch": 26.94, "learning_rate": 4.0913449546878034e-07, "loss": 0.7264, "step": 324150 }, { "epoch": 26.94, "learning_rate": 4.090236399412466e-07, "loss": 0.7384, "step": 324160 }, { "epoch": 26.94, "learning_rate": 4.089127844137128e-07, "loss": 0.7223, "step": 324170 }, { "epoch": 26.95, "learning_rate": 4.088019288861791e-07, "loss": 0.7717, "step": 324180 }, { "epoch": 26.95, "learning_rate": 4.086910733586453e-07, "loss": 0.73, "step": 324190 }, { "epoch": 26.95, "learning_rate": 4.0858021783111155e-07, "loss": 0.7206, "step": 324200 }, { "epoch": 26.95, "learning_rate": 4.0846936230357785e-07, "loss": 0.7549, "step": 324210 }, { "epoch": 26.95, "learning_rate": 4.083585067760441e-07, "loss": 0.8016, "step": 324220 }, { "epoch": 26.95, "learning_rate": 4.0824765124851033e-07, "loss": 0.7224, "step": 324230 }, { "epoch": 26.95, "learning_rate": 4.081367957209766e-07, "loss": 0.7563, "step": 324240 }, { "epoch": 26.95, "learning_rate": 4.0802594019344287e-07, "loss": 0.7759, "step": 324250 }, { "epoch": 26.95, "learning_rate": 4.079150846659091e-07, "loss": 0.749, "step": 324260 }, { "epoch": 26.95, "learning_rate": 4.0780422913837535e-07, "loss": 0.7639, "step": 324270 }, { "epoch": 26.95, "learning_rate": 4.0769337361084165e-07, "loss": 0.7768, "step": 324280 }, { "epoch": 26.95, "learning_rate": 4.075825180833079e-07, "loss": 0.7088, "step": 324290 }, { "epoch": 26.96, "learning_rate": 4.0747166255577413e-07, "loss": 0.7465, "step": 324300 }, { "epoch": 26.96, "learning_rate": 4.0736080702824043e-07, "loss": 0.7826, "step": 324310 }, { "epoch": 26.96, "learning_rate": 4.0724995150070667e-07, "loss": 0.7328, "step": 324320 }, { "epoch": 26.96, "learning_rate": 4.071390959731729e-07, "loss": 0.6651, "step": 324330 }, { "epoch": 26.96, "learning_rate": 4.070282404456392e-07, "loss": 0.7589, "step": 324340 }, { "epoch": 26.96, "learning_rate": 4.0691738491810545e-07, "loss": 0.6838, "step": 324350 }, { "epoch": 26.96, "learning_rate": 4.068065293905717e-07, "loss": 0.813, "step": 324360 }, { "epoch": 26.96, "learning_rate": 4.06695673863038e-07, "loss": 0.7576, "step": 324370 }, { "epoch": 26.96, "learning_rate": 4.0658481833550423e-07, "loss": 0.7236, "step": 324380 }, { "epoch": 26.96, "learning_rate": 4.0647396280797047e-07, "loss": 0.78, "step": 324390 }, { "epoch": 26.96, "learning_rate": 4.0636310728043677e-07, "loss": 0.7415, "step": 324400 }, { "epoch": 26.96, "learning_rate": 4.06252251752903e-07, "loss": 0.7647, "step": 324410 }, { "epoch": 26.97, "learning_rate": 4.0614139622536925e-07, "loss": 0.7563, "step": 324420 }, { "epoch": 26.97, "learning_rate": 4.0603054069783555e-07, "loss": 0.718, "step": 324430 }, { "epoch": 26.97, "learning_rate": 4.059196851703018e-07, "loss": 0.7937, "step": 324440 }, { "epoch": 26.97, "learning_rate": 4.0580882964276803e-07, "loss": 0.7349, "step": 324450 }, { "epoch": 26.97, "learning_rate": 4.0569797411523433e-07, "loss": 0.702, "step": 324460 }, { "epoch": 26.97, "learning_rate": 4.0558711858770057e-07, "loss": 0.7613, "step": 324470 }, { "epoch": 26.97, "learning_rate": 4.054762630601668e-07, "loss": 0.6786, "step": 324480 }, { "epoch": 26.97, "learning_rate": 4.053654075326331e-07, "loss": 0.7267, "step": 324490 }, { "epoch": 26.97, "learning_rate": 4.0525455200509935e-07, "loss": 0.7158, "step": 324500 }, { "epoch": 26.97, "learning_rate": 4.051436964775656e-07, "loss": 0.7336, "step": 324510 }, { "epoch": 26.97, "learning_rate": 4.050328409500319e-07, "loss": 0.7752, "step": 324520 }, { "epoch": 26.97, "learning_rate": 4.0492198542249813e-07, "loss": 0.743, "step": 324530 }, { "epoch": 26.98, "learning_rate": 4.048111298949644e-07, "loss": 0.7191, "step": 324540 }, { "epoch": 26.98, "learning_rate": 4.0470027436743067e-07, "loss": 0.7232, "step": 324550 }, { "epoch": 26.98, "learning_rate": 4.045894188398969e-07, "loss": 0.7719, "step": 324560 }, { "epoch": 26.98, "learning_rate": 4.0447856331236315e-07, "loss": 0.7164, "step": 324570 }, { "epoch": 26.98, "learning_rate": 4.0436770778482945e-07, "loss": 0.7348, "step": 324580 }, { "epoch": 26.98, "learning_rate": 4.042568522572957e-07, "loss": 0.7716, "step": 324590 }, { "epoch": 26.98, "learning_rate": 4.041459967297619e-07, "loss": 0.7713, "step": 324600 }, { "epoch": 26.98, "learning_rate": 4.040351412022282e-07, "loss": 0.7571, "step": 324610 }, { "epoch": 26.98, "learning_rate": 4.039242856746944e-07, "loss": 0.7348, "step": 324620 }, { "epoch": 26.98, "learning_rate": 4.0381343014716066e-07, "loss": 0.6804, "step": 324630 }, { "epoch": 26.98, "learning_rate": 4.0370257461962696e-07, "loss": 0.7479, "step": 324640 }, { "epoch": 26.98, "learning_rate": 4.035917190920932e-07, "loss": 0.7415, "step": 324650 }, { "epoch": 26.99, "learning_rate": 4.0348086356455944e-07, "loss": 0.7563, "step": 324660 }, { "epoch": 26.99, "learning_rate": 4.0337000803702574e-07, "loss": 0.7158, "step": 324670 }, { "epoch": 26.99, "learning_rate": 4.03259152509492e-07, "loss": 0.7432, "step": 324680 }, { "epoch": 26.99, "learning_rate": 4.031482969819582e-07, "loss": 0.6918, "step": 324690 }, { "epoch": 26.99, "learning_rate": 4.0303744145442446e-07, "loss": 0.7344, "step": 324700 }, { "epoch": 26.99, "learning_rate": 4.0292658592689076e-07, "loss": 0.7726, "step": 324710 }, { "epoch": 26.99, "learning_rate": 4.02815730399357e-07, "loss": 0.7641, "step": 324720 }, { "epoch": 26.99, "learning_rate": 4.0270487487182324e-07, "loss": 0.6881, "step": 324730 }, { "epoch": 26.99, "learning_rate": 4.0259401934428954e-07, "loss": 0.7309, "step": 324740 }, { "epoch": 26.99, "learning_rate": 4.024831638167558e-07, "loss": 0.7042, "step": 324750 }, { "epoch": 26.99, "learning_rate": 4.02372308289222e-07, "loss": 0.807, "step": 324760 }, { "epoch": 26.99, "learning_rate": 4.022614527616883e-07, "loss": 0.7486, "step": 324770 }, { "epoch": 27.0, "learning_rate": 4.0215059723415456e-07, "loss": 0.7379, "step": 324780 }, { "epoch": 27.0, "learning_rate": 4.020397417066208e-07, "loss": 0.7042, "step": 324790 }, { "epoch": 27.0, "learning_rate": 4.019288861790871e-07, "loss": 0.6339, "step": 324800 }, { "epoch": 27.0, "learning_rate": 4.0181803065155334e-07, "loss": 0.7882, "step": 324810 }, { "epoch": 27.0, "learning_rate": 4.017071751240196e-07, "loss": 0.7874, "step": 324820 }, { "epoch": 27.0, "learning_rate": 4.015963195964859e-07, "loss": 0.665, "step": 324830 }, { "epoch": 27.0, "eval_loss": 1.1418505907058716, "eval_runtime": 345.5464, "eval_samples_per_second": 7.738, "eval_steps_per_second": 3.869, "eval_wer": 0.6345580652907855, "step": 324837 }, { "epoch": 27.0, "learning_rate": 4.014854640689521e-07, "loss": 0.7055, "step": 324840 }, { "epoch": 27.0, "learning_rate": 4.0137460854141836e-07, "loss": 0.7659, "step": 324850 }, { "epoch": 27.0, "learning_rate": 4.0126375301388466e-07, "loss": 0.7243, "step": 324860 }, { "epoch": 27.0, "learning_rate": 4.011528974863509e-07, "loss": 0.745, "step": 324870 }, { "epoch": 27.0, "learning_rate": 4.0104204195881714e-07, "loss": 0.7275, "step": 324880 }, { "epoch": 27.0, "learning_rate": 4.0093118643128344e-07, "loss": 0.7666, "step": 324890 }, { "epoch": 27.01, "learning_rate": 4.008203309037497e-07, "loss": 0.6841, "step": 324900 }, { "epoch": 27.01, "learning_rate": 4.007094753762159e-07, "loss": 0.7261, "step": 324910 }, { "epoch": 27.01, "learning_rate": 4.005986198486822e-07, "loss": 0.7076, "step": 324920 }, { "epoch": 27.01, "learning_rate": 4.0048776432114846e-07, "loss": 0.7008, "step": 324930 }, { "epoch": 27.01, "learning_rate": 4.003769087936147e-07, "loss": 0.7505, "step": 324940 }, { "epoch": 27.01, "learning_rate": 4.00266053266081e-07, "loss": 0.7677, "step": 324950 }, { "epoch": 27.01, "learning_rate": 4.0015519773854724e-07, "loss": 0.7325, "step": 324960 }, { "epoch": 27.01, "learning_rate": 4.000443422110135e-07, "loss": 0.7318, "step": 324970 }, { "epoch": 27.01, "learning_rate": 3.999334866834798e-07, "loss": 0.6523, "step": 324980 }, { "epoch": 27.01, "learning_rate": 3.99822631155946e-07, "loss": 0.7439, "step": 324990 }, { "epoch": 27.01, "learning_rate": 3.9971177562841227e-07, "loss": 0.7185, "step": 325000 }, { "epoch": 27.01, "learning_rate": 3.9960092010087856e-07, "loss": 0.6995, "step": 325010 }, { "epoch": 27.02, "learning_rate": 3.9949006457334475e-07, "loss": 0.7308, "step": 325020 }, { "epoch": 27.02, "learning_rate": 3.99379209045811e-07, "loss": 0.7622, "step": 325030 }, { "epoch": 27.02, "learning_rate": 3.992683535182773e-07, "loss": 0.7322, "step": 325040 }, { "epoch": 27.02, "learning_rate": 3.9915749799074353e-07, "loss": 0.7175, "step": 325050 }, { "epoch": 27.02, "learning_rate": 3.9904664246320977e-07, "loss": 0.7749, "step": 325060 }, { "epoch": 27.02, "learning_rate": 3.9893578693567607e-07, "loss": 0.7868, "step": 325070 }, { "epoch": 27.02, "learning_rate": 3.988249314081423e-07, "loss": 0.7337, "step": 325080 }, { "epoch": 27.02, "learning_rate": 3.9871407588060855e-07, "loss": 0.7445, "step": 325090 }, { "epoch": 27.02, "learning_rate": 3.986032203530748e-07, "loss": 0.7452, "step": 325100 }, { "epoch": 27.02, "learning_rate": 3.984923648255411e-07, "loss": 0.763, "step": 325110 }, { "epoch": 27.02, "learning_rate": 3.9838150929800733e-07, "loss": 0.7161, "step": 325120 }, { "epoch": 27.02, "learning_rate": 3.982706537704736e-07, "loss": 0.7197, "step": 325130 }, { "epoch": 27.03, "learning_rate": 3.9815979824293987e-07, "loss": 0.706, "step": 325140 }, { "epoch": 27.03, "learning_rate": 3.980489427154061e-07, "loss": 0.7562, "step": 325150 }, { "epoch": 27.03, "learning_rate": 3.9794917274062576e-07, "loss": 0.8002, "step": 325160 }, { "epoch": 27.03, "learning_rate": 3.97838317213092e-07, "loss": 0.6958, "step": 325170 }, { "epoch": 27.03, "learning_rate": 3.9772746168555824e-07, "loss": 0.7531, "step": 325180 }, { "epoch": 27.03, "learning_rate": 3.9761660615802454e-07, "loss": 0.759, "step": 325190 }, { "epoch": 27.03, "learning_rate": 3.975057506304908e-07, "loss": 0.7443, "step": 325200 }, { "epoch": 27.03, "learning_rate": 3.97394895102957e-07, "loss": 0.7535, "step": 325210 }, { "epoch": 27.03, "learning_rate": 3.972840395754233e-07, "loss": 0.6858, "step": 325220 }, { "epoch": 27.03, "learning_rate": 3.9717318404788956e-07, "loss": 0.7231, "step": 325230 }, { "epoch": 27.03, "learning_rate": 3.970623285203558e-07, "loss": 0.7216, "step": 325240 }, { "epoch": 27.03, "learning_rate": 3.969514729928221e-07, "loss": 0.7736, "step": 325250 }, { "epoch": 27.04, "learning_rate": 3.9684061746528834e-07, "loss": 0.7647, "step": 325260 }, { "epoch": 27.04, "learning_rate": 3.967297619377546e-07, "loss": 0.7108, "step": 325270 }, { "epoch": 27.04, "learning_rate": 3.966189064102209e-07, "loss": 0.7028, "step": 325280 }, { "epoch": 27.04, "learning_rate": 3.965080508826871e-07, "loss": 0.7514, "step": 325290 }, { "epoch": 27.04, "learning_rate": 3.9639719535515336e-07, "loss": 0.7986, "step": 325300 }, { "epoch": 27.04, "learning_rate": 3.962863398276196e-07, "loss": 0.7714, "step": 325310 }, { "epoch": 27.04, "learning_rate": 3.961754843000859e-07, "loss": 0.7682, "step": 325320 }, { "epoch": 27.04, "learning_rate": 3.9606462877255214e-07, "loss": 0.7156, "step": 325330 }, { "epoch": 27.04, "learning_rate": 3.959537732450184e-07, "loss": 0.7372, "step": 325340 }, { "epoch": 27.04, "learning_rate": 3.958429177174847e-07, "loss": 0.7845, "step": 325350 }, { "epoch": 27.04, "learning_rate": 3.957320621899509e-07, "loss": 0.7259, "step": 325360 }, { "epoch": 27.04, "learning_rate": 3.9562120666241717e-07, "loss": 0.7474, "step": 325370 }, { "epoch": 27.05, "learning_rate": 3.9551035113488346e-07, "loss": 0.7282, "step": 325380 }, { "epoch": 27.05, "learning_rate": 3.953994956073497e-07, "loss": 0.7437, "step": 325390 }, { "epoch": 27.05, "learning_rate": 3.9528864007981595e-07, "loss": 0.7448, "step": 325400 }, { "epoch": 27.05, "learning_rate": 3.9517778455228224e-07, "loss": 0.7072, "step": 325410 }, { "epoch": 27.05, "learning_rate": 3.950669290247485e-07, "loss": 0.7688, "step": 325420 }, { "epoch": 27.05, "learning_rate": 3.949560734972147e-07, "loss": 0.6976, "step": 325430 }, { "epoch": 27.05, "learning_rate": 3.94845217969681e-07, "loss": 0.7552, "step": 325440 }, { "epoch": 27.05, "learning_rate": 3.9473436244214726e-07, "loss": 0.7577, "step": 325450 }, { "epoch": 27.05, "learning_rate": 3.946235069146135e-07, "loss": 0.7078, "step": 325460 }, { "epoch": 27.05, "learning_rate": 3.945126513870798e-07, "loss": 0.7512, "step": 325470 }, { "epoch": 27.05, "learning_rate": 3.9440179585954604e-07, "loss": 0.7043, "step": 325480 }, { "epoch": 27.05, "learning_rate": 3.942909403320123e-07, "loss": 0.741, "step": 325490 }, { "epoch": 27.06, "learning_rate": 3.941800848044786e-07, "loss": 0.7797, "step": 325500 }, { "epoch": 27.06, "learning_rate": 3.940692292769448e-07, "loss": 0.7059, "step": 325510 }, { "epoch": 27.06, "learning_rate": 3.9395837374941107e-07, "loss": 0.7568, "step": 325520 }, { "epoch": 27.06, "learning_rate": 3.9384751822187736e-07, "loss": 0.7402, "step": 325530 }, { "epoch": 27.06, "learning_rate": 3.937366626943436e-07, "loss": 0.7279, "step": 325540 }, { "epoch": 27.06, "learning_rate": 3.9362580716680985e-07, "loss": 0.6819, "step": 325550 }, { "epoch": 27.06, "learning_rate": 3.9351495163927614e-07, "loss": 0.7353, "step": 325560 }, { "epoch": 27.06, "learning_rate": 3.9340409611174233e-07, "loss": 0.7096, "step": 325570 }, { "epoch": 27.06, "learning_rate": 3.9329324058420857e-07, "loss": 0.7453, "step": 325580 }, { "epoch": 27.06, "learning_rate": 3.9318238505667487e-07, "loss": 0.7374, "step": 325590 }, { "epoch": 27.06, "learning_rate": 3.930715295291411e-07, "loss": 0.7301, "step": 325600 }, { "epoch": 27.06, "learning_rate": 3.9296067400160735e-07, "loss": 0.7226, "step": 325610 }, { "epoch": 27.07, "learning_rate": 3.9284981847407365e-07, "loss": 0.6857, "step": 325620 }, { "epoch": 27.07, "learning_rate": 3.927389629465399e-07, "loss": 0.7669, "step": 325630 }, { "epoch": 27.07, "learning_rate": 3.9262810741900613e-07, "loss": 0.693, "step": 325640 }, { "epoch": 27.07, "learning_rate": 3.9251725189147243e-07, "loss": 0.7391, "step": 325650 }, { "epoch": 27.07, "learning_rate": 3.9240639636393867e-07, "loss": 0.7154, "step": 325660 }, { "epoch": 27.07, "learning_rate": 3.922955408364049e-07, "loss": 0.7644, "step": 325670 }, { "epoch": 27.07, "learning_rate": 3.921846853088712e-07, "loss": 0.7128, "step": 325680 }, { "epoch": 27.07, "learning_rate": 3.9207382978133745e-07, "loss": 0.7736, "step": 325690 }, { "epoch": 27.07, "learning_rate": 3.919629742538037e-07, "loss": 0.7386, "step": 325700 }, { "epoch": 27.07, "learning_rate": 3.9185211872627e-07, "loss": 0.7298, "step": 325710 }, { "epoch": 27.07, "learning_rate": 3.9174126319873623e-07, "loss": 0.7137, "step": 325720 }, { "epoch": 27.07, "learning_rate": 3.916304076712025e-07, "loss": 0.7087, "step": 325730 }, { "epoch": 27.08, "learning_rate": 3.915195521436687e-07, "loss": 0.7749, "step": 325740 }, { "epoch": 27.08, "learning_rate": 3.91408696616135e-07, "loss": 0.7722, "step": 325750 }, { "epoch": 27.08, "learning_rate": 3.9129784108860125e-07, "loss": 0.7412, "step": 325760 }, { "epoch": 27.08, "learning_rate": 3.911869855610675e-07, "loss": 0.7053, "step": 325770 }, { "epoch": 27.08, "learning_rate": 3.910761300335338e-07, "loss": 0.7426, "step": 325780 }, { "epoch": 27.08, "learning_rate": 3.9096527450600003e-07, "loss": 0.7013, "step": 325790 }, { "epoch": 27.08, "learning_rate": 3.908544189784663e-07, "loss": 0.7389, "step": 325800 }, { "epoch": 27.08, "learning_rate": 3.9074356345093257e-07, "loss": 0.7349, "step": 325810 }, { "epoch": 27.08, "learning_rate": 3.906327079233988e-07, "loss": 0.7391, "step": 325820 }, { "epoch": 27.08, "learning_rate": 3.9052185239586506e-07, "loss": 0.7749, "step": 325830 }, { "epoch": 27.08, "learning_rate": 3.9041099686833135e-07, "loss": 0.6938, "step": 325840 }, { "epoch": 27.08, "learning_rate": 3.903001413407976e-07, "loss": 0.7604, "step": 325850 }, { "epoch": 27.09, "learning_rate": 3.9018928581326384e-07, "loss": 0.7214, "step": 325860 }, { "epoch": 27.09, "learning_rate": 3.9007843028573013e-07, "loss": 0.8058, "step": 325870 }, { "epoch": 27.09, "learning_rate": 3.899675747581964e-07, "loss": 0.7474, "step": 325880 }, { "epoch": 27.09, "learning_rate": 3.898567192306626e-07, "loss": 0.7387, "step": 325890 }, { "epoch": 27.09, "learning_rate": 3.897458637031289e-07, "loss": 0.7099, "step": 325900 }, { "epoch": 27.09, "learning_rate": 3.8963500817559515e-07, "loss": 0.6827, "step": 325910 }, { "epoch": 27.09, "learning_rate": 3.895241526480614e-07, "loss": 0.7281, "step": 325920 }, { "epoch": 27.09, "learning_rate": 3.894132971205277e-07, "loss": 0.7757, "step": 325930 }, { "epoch": 27.09, "learning_rate": 3.8930244159299394e-07, "loss": 0.7215, "step": 325940 }, { "epoch": 27.09, "learning_rate": 3.891915860654602e-07, "loss": 0.74, "step": 325950 }, { "epoch": 27.09, "learning_rate": 3.8908073053792647e-07, "loss": 0.7604, "step": 325960 }, { "epoch": 27.09, "learning_rate": 3.889698750103927e-07, "loss": 0.772, "step": 325970 }, { "epoch": 27.1, "learning_rate": 3.888590194828589e-07, "loss": 0.7083, "step": 325980 }, { "epoch": 27.1, "learning_rate": 3.887481639553252e-07, "loss": 0.7124, "step": 325990 }, { "epoch": 27.1, "learning_rate": 3.8863730842779144e-07, "loss": 0.7398, "step": 326000 }, { "epoch": 27.1, "learning_rate": 3.885264529002577e-07, "loss": 0.6899, "step": 326010 }, { "epoch": 27.1, "learning_rate": 3.88415597372724e-07, "loss": 0.715, "step": 326020 }, { "epoch": 27.1, "learning_rate": 3.883047418451902e-07, "loss": 0.7552, "step": 326030 }, { "epoch": 27.1, "learning_rate": 3.8819388631765646e-07, "loss": 0.735, "step": 326040 }, { "epoch": 27.1, "learning_rate": 3.8808303079012276e-07, "loss": 0.7817, "step": 326050 }, { "epoch": 27.1, "learning_rate": 3.87972175262589e-07, "loss": 0.7515, "step": 326060 }, { "epoch": 27.1, "learning_rate": 3.8786131973505525e-07, "loss": 0.72, "step": 326070 }, { "epoch": 27.1, "learning_rate": 3.8775046420752154e-07, "loss": 0.7119, "step": 326080 }, { "epoch": 27.1, "learning_rate": 3.876396086799878e-07, "loss": 0.6971, "step": 326090 }, { "epoch": 27.1, "learning_rate": 3.87528753152454e-07, "loss": 0.7712, "step": 326100 }, { "epoch": 27.11, "learning_rate": 3.874178976249203e-07, "loss": 0.6972, "step": 326110 }, { "epoch": 27.11, "learning_rate": 3.8730704209738656e-07, "loss": 0.7001, "step": 326120 }, { "epoch": 27.11, "learning_rate": 3.871961865698528e-07, "loss": 0.7143, "step": 326130 }, { "epoch": 27.11, "learning_rate": 3.870853310423191e-07, "loss": 0.7214, "step": 326140 }, { "epoch": 27.11, "learning_rate": 3.8697447551478534e-07, "loss": 0.7284, "step": 326150 }, { "epoch": 27.11, "learning_rate": 3.868636199872516e-07, "loss": 0.7319, "step": 326160 }, { "epoch": 27.11, "learning_rate": 3.8675276445971783e-07, "loss": 0.7656, "step": 326170 }, { "epoch": 27.11, "learning_rate": 3.866419089321841e-07, "loss": 0.7375, "step": 326180 }, { "epoch": 27.11, "learning_rate": 3.8653105340465037e-07, "loss": 0.7837, "step": 326190 }, { "epoch": 27.11, "learning_rate": 3.864201978771166e-07, "loss": 0.7796, "step": 326200 }, { "epoch": 27.11, "learning_rate": 3.863093423495829e-07, "loss": 0.7228, "step": 326210 }, { "epoch": 27.11, "learning_rate": 3.8619848682204915e-07, "loss": 0.735, "step": 326220 }, { "epoch": 27.12, "learning_rate": 3.860876312945154e-07, "loss": 0.7233, "step": 326230 }, { "epoch": 27.12, "learning_rate": 3.859767757669817e-07, "loss": 0.7369, "step": 326240 }, { "epoch": 27.12, "learning_rate": 3.858659202394479e-07, "loss": 0.739, "step": 326250 }, { "epoch": 27.12, "learning_rate": 3.8575506471191417e-07, "loss": 0.7868, "step": 326260 }, { "epoch": 27.12, "learning_rate": 3.8564420918438046e-07, "loss": 0.6951, "step": 326270 }, { "epoch": 27.12, "learning_rate": 3.855333536568467e-07, "loss": 0.7873, "step": 326280 }, { "epoch": 27.12, "learning_rate": 3.8542249812931295e-07, "loss": 0.6506, "step": 326290 }, { "epoch": 27.12, "learning_rate": 3.8531164260177924e-07, "loss": 0.7615, "step": 326300 }, { "epoch": 27.12, "learning_rate": 3.852007870742455e-07, "loss": 0.7671, "step": 326310 }, { "epoch": 27.12, "learning_rate": 3.8508993154671173e-07, "loss": 0.7209, "step": 326320 }, { "epoch": 27.12, "learning_rate": 3.84979076019178e-07, "loss": 0.7296, "step": 326330 }, { "epoch": 27.12, "learning_rate": 3.8486822049164427e-07, "loss": 0.7252, "step": 326340 }, { "epoch": 27.13, "learning_rate": 3.847573649641105e-07, "loss": 0.7814, "step": 326350 }, { "epoch": 27.13, "learning_rate": 3.846465094365768e-07, "loss": 0.71, "step": 326360 }, { "epoch": 27.13, "learning_rate": 3.8453565390904305e-07, "loss": 0.7025, "step": 326370 }, { "epoch": 27.13, "learning_rate": 3.844247983815093e-07, "loss": 0.6764, "step": 326380 }, { "epoch": 27.13, "learning_rate": 3.843139428539756e-07, "loss": 0.7941, "step": 326390 }, { "epoch": 27.13, "learning_rate": 3.842030873264418e-07, "loss": 0.7362, "step": 326400 }, { "epoch": 27.13, "learning_rate": 3.84092231798908e-07, "loss": 0.7401, "step": 326410 }, { "epoch": 27.13, "learning_rate": 3.839813762713743e-07, "loss": 0.7277, "step": 326420 }, { "epoch": 27.13, "learning_rate": 3.8387052074384055e-07, "loss": 0.7135, "step": 326430 }, { "epoch": 27.13, "learning_rate": 3.837596652163068e-07, "loss": 0.7548, "step": 326440 }, { "epoch": 27.13, "learning_rate": 3.836488096887731e-07, "loss": 0.778, "step": 326450 }, { "epoch": 27.13, "learning_rate": 3.8353795416123933e-07, "loss": 0.7539, "step": 326460 }, { "epoch": 27.14, "learning_rate": 3.834270986337056e-07, "loss": 0.7689, "step": 326470 }, { "epoch": 27.14, "learning_rate": 3.8331624310617187e-07, "loss": 0.7612, "step": 326480 }, { "epoch": 27.14, "learning_rate": 3.832053875786381e-07, "loss": 0.6939, "step": 326490 }, { "epoch": 27.14, "learning_rate": 3.8309453205110436e-07, "loss": 0.7171, "step": 326500 }, { "epoch": 27.14, "learning_rate": 3.8298367652357065e-07, "loss": 0.744, "step": 326510 }, { "epoch": 27.14, "learning_rate": 3.828728209960369e-07, "loss": 0.7499, "step": 326520 }, { "epoch": 27.14, "learning_rate": 3.8276196546850314e-07, "loss": 0.6809, "step": 326530 }, { "epoch": 27.14, "learning_rate": 3.8265110994096943e-07, "loss": 0.763, "step": 326540 }, { "epoch": 27.14, "learning_rate": 3.825402544134357e-07, "loss": 0.758, "step": 326550 }, { "epoch": 27.14, "learning_rate": 3.824293988859019e-07, "loss": 0.73, "step": 326560 }, { "epoch": 27.14, "learning_rate": 3.8231854335836816e-07, "loss": 0.6886, "step": 326570 }, { "epoch": 27.14, "learning_rate": 3.8220768783083445e-07, "loss": 0.7346, "step": 326580 }, { "epoch": 27.15, "learning_rate": 3.820968323033007e-07, "loss": 0.7651, "step": 326590 }, { "epoch": 27.15, "learning_rate": 3.8198597677576694e-07, "loss": 0.7355, "step": 326600 }, { "epoch": 27.15, "learning_rate": 3.8187512124823323e-07, "loss": 0.7522, "step": 326610 }, { "epoch": 27.15, "learning_rate": 3.817642657206995e-07, "loss": 0.7471, "step": 326620 }, { "epoch": 27.15, "learning_rate": 3.816534101931657e-07, "loss": 0.6431, "step": 326630 }, { "epoch": 27.15, "learning_rate": 3.81542554665632e-07, "loss": 0.7088, "step": 326640 }, { "epoch": 27.15, "learning_rate": 3.8143169913809826e-07, "loss": 0.7794, "step": 326650 }, { "epoch": 27.15, "learning_rate": 3.813208436105645e-07, "loss": 0.6973, "step": 326660 }, { "epoch": 27.15, "learning_rate": 3.812099880830308e-07, "loss": 0.71, "step": 326670 }, { "epoch": 27.15, "learning_rate": 3.8109913255549704e-07, "loss": 0.6951, "step": 326680 }, { "epoch": 27.15, "learning_rate": 3.809882770279633e-07, "loss": 0.7644, "step": 326690 }, { "epoch": 27.15, "learning_rate": 3.808774215004296e-07, "loss": 0.7275, "step": 326700 }, { "epoch": 27.16, "learning_rate": 3.807665659728958e-07, "loss": 0.7299, "step": 326710 }, { "epoch": 27.16, "learning_rate": 3.8065571044536206e-07, "loss": 0.7447, "step": 326720 }, { "epoch": 27.16, "learning_rate": 3.8054485491782836e-07, "loss": 0.7531, "step": 326730 }, { "epoch": 27.16, "learning_rate": 3.804339993902946e-07, "loss": 0.7717, "step": 326740 }, { "epoch": 27.16, "learning_rate": 3.8032314386276084e-07, "loss": 0.76, "step": 326750 }, { "epoch": 27.16, "learning_rate": 3.8021228833522714e-07, "loss": 0.6919, "step": 326760 }, { "epoch": 27.16, "learning_rate": 3.801014328076934e-07, "loss": 0.7811, "step": 326770 }, { "epoch": 27.16, "learning_rate": 3.799905772801596e-07, "loss": 0.7695, "step": 326780 }, { "epoch": 27.16, "learning_rate": 3.798797217526259e-07, "loss": 0.6777, "step": 326790 }, { "epoch": 27.16, "learning_rate": 3.7976886622509216e-07, "loss": 0.7386, "step": 326800 }, { "epoch": 27.16, "learning_rate": 3.7965801069755835e-07, "loss": 0.7014, "step": 326810 }, { "epoch": 27.16, "learning_rate": 3.7954715517002464e-07, "loss": 0.6791, "step": 326820 }, { "epoch": 27.17, "learning_rate": 3.794362996424909e-07, "loss": 0.8058, "step": 326830 }, { "epoch": 27.17, "learning_rate": 3.7932544411495713e-07, "loss": 0.7246, "step": 326840 }, { "epoch": 27.17, "learning_rate": 3.792145885874234e-07, "loss": 0.7521, "step": 326850 }, { "epoch": 27.17, "learning_rate": 3.7910373305988967e-07, "loss": 0.6924, "step": 326860 }, { "epoch": 27.17, "learning_rate": 3.789928775323559e-07, "loss": 0.7166, "step": 326870 }, { "epoch": 27.17, "learning_rate": 3.788820220048222e-07, "loss": 0.7245, "step": 326880 }, { "epoch": 27.17, "learning_rate": 3.7877116647728845e-07, "loss": 0.6924, "step": 326890 }, { "epoch": 27.17, "learning_rate": 3.786603109497547e-07, "loss": 0.7625, "step": 326900 }, { "epoch": 27.17, "learning_rate": 3.78549455422221e-07, "loss": 0.7213, "step": 326910 }, { "epoch": 27.17, "learning_rate": 3.784385998946872e-07, "loss": 0.7286, "step": 326920 }, { "epoch": 27.17, "learning_rate": 3.7832774436715347e-07, "loss": 0.7822, "step": 326930 }, { "epoch": 27.17, "learning_rate": 3.7821688883961976e-07, "loss": 0.7482, "step": 326940 }, { "epoch": 27.18, "learning_rate": 3.78106033312086e-07, "loss": 0.7603, "step": 326950 }, { "epoch": 27.18, "learning_rate": 3.7799517778455225e-07, "loss": 0.7423, "step": 326960 }, { "epoch": 27.18, "learning_rate": 3.7788432225701854e-07, "loss": 0.6927, "step": 326970 }, { "epoch": 27.18, "learning_rate": 3.777734667294848e-07, "loss": 0.7809, "step": 326980 }, { "epoch": 27.18, "learning_rate": 3.7766261120195103e-07, "loss": 0.722, "step": 326990 }, { "epoch": 27.18, "learning_rate": 3.7755175567441727e-07, "loss": 0.7773, "step": 327000 }, { "epoch": 27.18, "learning_rate": 3.7744090014688357e-07, "loss": 0.7383, "step": 327010 }, { "epoch": 27.18, "learning_rate": 3.773300446193498e-07, "loss": 0.6706, "step": 327020 }, { "epoch": 27.18, "learning_rate": 3.7721918909181605e-07, "loss": 0.69, "step": 327030 }, { "epoch": 27.18, "learning_rate": 3.7710833356428235e-07, "loss": 0.7726, "step": 327040 }, { "epoch": 27.18, "learning_rate": 3.769974780367486e-07, "loss": 0.7373, "step": 327050 }, { "epoch": 27.18, "learning_rate": 3.7688662250921483e-07, "loss": 0.6885, "step": 327060 }, { "epoch": 27.19, "learning_rate": 3.767757669816811e-07, "loss": 0.738, "step": 327070 }, { "epoch": 27.19, "learning_rate": 3.7666491145414737e-07, "loss": 0.7019, "step": 327080 }, { "epoch": 27.19, "learning_rate": 3.765540559266136e-07, "loss": 0.7123, "step": 327090 }, { "epoch": 27.19, "learning_rate": 3.764432003990799e-07, "loss": 0.7505, "step": 327100 }, { "epoch": 27.19, "learning_rate": 3.7633234487154615e-07, "loss": 0.7128, "step": 327110 }, { "epoch": 27.19, "learning_rate": 3.762214893440124e-07, "loss": 0.7364, "step": 327120 }, { "epoch": 27.19, "learning_rate": 3.761106338164787e-07, "loss": 0.7716, "step": 327130 }, { "epoch": 27.19, "learning_rate": 3.7599977828894493e-07, "loss": 0.742, "step": 327140 }, { "epoch": 27.19, "learning_rate": 3.7588892276141117e-07, "loss": 0.7962, "step": 327150 }, { "epoch": 27.19, "learning_rate": 3.7577806723387747e-07, "loss": 0.7001, "step": 327160 }, { "epoch": 27.19, "learning_rate": 3.7567829725909706e-07, "loss": 0.7751, "step": 327170 }, { "epoch": 27.19, "learning_rate": 3.7556744173156335e-07, "loss": 0.7552, "step": 327180 }, { "epoch": 27.2, "learning_rate": 3.754565862040296e-07, "loss": 0.7614, "step": 327190 }, { "epoch": 27.2, "learning_rate": 3.7534573067649584e-07, "loss": 0.7968, "step": 327200 }, { "epoch": 27.2, "learning_rate": 3.752348751489621e-07, "loss": 0.7151, "step": 327210 }, { "epoch": 27.2, "learning_rate": 3.751240196214284e-07, "loss": 0.7235, "step": 327220 }, { "epoch": 27.2, "learning_rate": 3.750131640938946e-07, "loss": 0.7072, "step": 327230 }, { "epoch": 27.2, "learning_rate": 3.7490230856636086e-07, "loss": 0.7377, "step": 327240 }, { "epoch": 27.2, "learning_rate": 3.7479145303882716e-07, "loss": 0.7399, "step": 327250 }, { "epoch": 27.2, "learning_rate": 3.746805975112934e-07, "loss": 0.7616, "step": 327260 }, { "epoch": 27.2, "learning_rate": 3.7456974198375964e-07, "loss": 0.7212, "step": 327270 }, { "epoch": 27.2, "learning_rate": 3.7445888645622594e-07, "loss": 0.7451, "step": 327280 }, { "epoch": 27.2, "learning_rate": 3.743480309286922e-07, "loss": 0.7303, "step": 327290 }, { "epoch": 27.2, "learning_rate": 3.742371754011584e-07, "loss": 0.7441, "step": 327300 }, { "epoch": 27.21, "learning_rate": 3.741263198736247e-07, "loss": 0.6839, "step": 327310 }, { "epoch": 27.21, "learning_rate": 3.7401546434609096e-07, "loss": 0.7304, "step": 327320 }, { "epoch": 27.21, "learning_rate": 3.739046088185572e-07, "loss": 0.7312, "step": 327330 }, { "epoch": 27.21, "learning_rate": 3.737937532910235e-07, "loss": 0.7108, "step": 327340 }, { "epoch": 27.21, "learning_rate": 3.7368289776348974e-07, "loss": 0.7734, "step": 327350 }, { "epoch": 27.21, "learning_rate": 3.7357204223595593e-07, "loss": 0.7405, "step": 327360 }, { "epoch": 27.21, "learning_rate": 3.734611867084222e-07, "loss": 0.7129, "step": 327370 }, { "epoch": 27.21, "learning_rate": 3.7335033118088847e-07, "loss": 0.7146, "step": 327380 }, { "epoch": 27.21, "learning_rate": 3.732394756533547e-07, "loss": 0.7429, "step": 327390 }, { "epoch": 27.21, "learning_rate": 3.73128620125821e-07, "loss": 0.728, "step": 327400 }, { "epoch": 27.21, "learning_rate": 3.7301776459828725e-07, "loss": 0.7752, "step": 327410 }, { "epoch": 27.21, "learning_rate": 3.729069090707535e-07, "loss": 0.7605, "step": 327420 }, { "epoch": 27.22, "learning_rate": 3.727960535432198e-07, "loss": 0.6917, "step": 327430 }, { "epoch": 27.22, "learning_rate": 3.72685198015686e-07, "loss": 0.7562, "step": 327440 }, { "epoch": 27.22, "learning_rate": 3.7257434248815227e-07, "loss": 0.7065, "step": 327450 }, { "epoch": 27.22, "learning_rate": 3.7246348696061856e-07, "loss": 0.7172, "step": 327460 }, { "epoch": 27.22, "learning_rate": 3.723526314330848e-07, "loss": 0.7638, "step": 327470 }, { "epoch": 27.22, "learning_rate": 3.7224177590555105e-07, "loss": 0.7639, "step": 327480 }, { "epoch": 27.22, "learning_rate": 3.7213092037801734e-07, "loss": 0.771, "step": 327490 }, { "epoch": 27.22, "learning_rate": 3.720200648504836e-07, "loss": 0.6938, "step": 327500 }, { "epoch": 27.22, "learning_rate": 3.7190920932294983e-07, "loss": 0.7952, "step": 327510 }, { "epoch": 27.22, "learning_rate": 3.717983537954161e-07, "loss": 0.719, "step": 327520 }, { "epoch": 27.22, "learning_rate": 3.7168749826788237e-07, "loss": 0.7276, "step": 327530 }, { "epoch": 27.22, "learning_rate": 3.715766427403486e-07, "loss": 0.7388, "step": 327540 }, { "epoch": 27.23, "learning_rate": 3.714657872128149e-07, "loss": 0.7171, "step": 327550 }, { "epoch": 27.23, "learning_rate": 3.7135493168528115e-07, "loss": 0.6775, "step": 327560 }, { "epoch": 27.23, "learning_rate": 3.712440761577474e-07, "loss": 0.6993, "step": 327570 }, { "epoch": 27.23, "learning_rate": 3.711332206302137e-07, "loss": 0.6672, "step": 327580 }, { "epoch": 27.23, "learning_rate": 3.7102236510267993e-07, "loss": 0.7416, "step": 327590 }, { "epoch": 27.23, "learning_rate": 3.7091150957514617e-07, "loss": 0.7793, "step": 327600 }, { "epoch": 27.23, "learning_rate": 3.7080065404761246e-07, "loss": 0.7082, "step": 327610 }, { "epoch": 27.23, "learning_rate": 3.706897985200787e-07, "loss": 0.7477, "step": 327620 }, { "epoch": 27.23, "learning_rate": 3.7057894299254495e-07, "loss": 0.7145, "step": 327630 }, { "epoch": 27.23, "learning_rate": 3.704680874650112e-07, "loss": 0.7713, "step": 327640 }, { "epoch": 27.23, "learning_rate": 3.703572319374775e-07, "loss": 0.7406, "step": 327650 }, { "epoch": 27.23, "learning_rate": 3.7024637640994373e-07, "loss": 0.6735, "step": 327660 }, { "epoch": 27.24, "learning_rate": 3.7013552088240997e-07, "loss": 0.7174, "step": 327670 }, { "epoch": 27.24, "learning_rate": 3.7002466535487627e-07, "loss": 0.71, "step": 327680 }, { "epoch": 27.24, "learning_rate": 3.699138098273425e-07, "loss": 0.7147, "step": 327690 }, { "epoch": 27.24, "learning_rate": 3.6980295429980875e-07, "loss": 0.8021, "step": 327700 }, { "epoch": 27.24, "learning_rate": 3.6969209877227505e-07, "loss": 0.7181, "step": 327710 }, { "epoch": 27.24, "learning_rate": 3.695812432447413e-07, "loss": 0.7468, "step": 327720 }, { "epoch": 27.24, "learning_rate": 3.6947038771720753e-07, "loss": 0.7203, "step": 327730 }, { "epoch": 27.24, "learning_rate": 3.6935953218967383e-07, "loss": 0.7719, "step": 327740 }, { "epoch": 27.24, "learning_rate": 3.6924867666214007e-07, "loss": 0.6999, "step": 327750 }, { "epoch": 27.24, "learning_rate": 3.691378211346063e-07, "loss": 0.7332, "step": 327760 }, { "epoch": 27.24, "learning_rate": 3.690269656070726e-07, "loss": 0.709, "step": 327770 }, { "epoch": 27.24, "learning_rate": 3.689161100795388e-07, "loss": 0.743, "step": 327780 }, { "epoch": 27.25, "learning_rate": 3.6880525455200504e-07, "loss": 0.7445, "step": 327790 }, { "epoch": 27.25, "learning_rate": 3.6869439902447134e-07, "loss": 0.7932, "step": 327800 }, { "epoch": 27.25, "learning_rate": 3.685835434969376e-07, "loss": 0.7454, "step": 327810 }, { "epoch": 27.25, "learning_rate": 3.684726879694038e-07, "loss": 0.7265, "step": 327820 }, { "epoch": 27.25, "learning_rate": 3.683618324418701e-07, "loss": 0.681, "step": 327830 }, { "epoch": 27.25, "learning_rate": 3.6825097691433636e-07, "loss": 0.6955, "step": 327840 }, { "epoch": 27.25, "learning_rate": 3.681401213868026e-07, "loss": 0.7521, "step": 327850 }, { "epoch": 27.25, "learning_rate": 3.680292658592689e-07, "loss": 0.6875, "step": 327860 }, { "epoch": 27.25, "learning_rate": 3.6791841033173514e-07, "loss": 0.7349, "step": 327870 }, { "epoch": 27.25, "learning_rate": 3.678075548042014e-07, "loss": 0.744, "step": 327880 }, { "epoch": 27.25, "learning_rate": 3.676966992766677e-07, "loss": 0.7607, "step": 327890 }, { "epoch": 27.25, "learning_rate": 3.675858437491339e-07, "loss": 0.7776, "step": 327900 }, { "epoch": 27.26, "learning_rate": 3.6747498822160016e-07, "loss": 0.6964, "step": 327910 }, { "epoch": 27.26, "learning_rate": 3.6736413269406646e-07, "loss": 0.7337, "step": 327920 }, { "epoch": 27.26, "learning_rate": 3.672532771665327e-07, "loss": 0.7228, "step": 327930 }, { "epoch": 27.26, "learning_rate": 3.6714242163899894e-07, "loss": 0.7544, "step": 327940 }, { "epoch": 27.26, "learning_rate": 3.6703156611146524e-07, "loss": 0.7564, "step": 327950 }, { "epoch": 27.26, "learning_rate": 3.669207105839315e-07, "loss": 0.758, "step": 327960 }, { "epoch": 27.26, "learning_rate": 3.668098550563977e-07, "loss": 0.7034, "step": 327970 }, { "epoch": 27.26, "learning_rate": 3.66698999528864e-07, "loss": 0.7641, "step": 327980 }, { "epoch": 27.26, "learning_rate": 3.6658814400133026e-07, "loss": 0.73, "step": 327990 }, { "epoch": 27.26, "learning_rate": 3.664772884737965e-07, "loss": 0.7563, "step": 328000 }, { "epoch": 27.26, "learning_rate": 3.663664329462628e-07, "loss": 0.6989, "step": 328010 }, { "epoch": 27.26, "learning_rate": 3.6625557741872904e-07, "loss": 0.7393, "step": 328020 }, { "epoch": 27.27, "learning_rate": 3.661447218911953e-07, "loss": 0.776, "step": 328030 }, { "epoch": 27.27, "learning_rate": 3.660338663636615e-07, "loss": 0.7548, "step": 328040 }, { "epoch": 27.27, "learning_rate": 3.659230108361278e-07, "loss": 0.7232, "step": 328050 }, { "epoch": 27.27, "learning_rate": 3.6581215530859406e-07, "loss": 0.7002, "step": 328060 }, { "epoch": 27.27, "learning_rate": 3.657012997810603e-07, "loss": 0.7369, "step": 328070 }, { "epoch": 27.27, "learning_rate": 3.655904442535266e-07, "loss": 0.7413, "step": 328080 }, { "epoch": 27.27, "learning_rate": 3.6547958872599284e-07, "loss": 0.7627, "step": 328090 }, { "epoch": 27.27, "learning_rate": 3.653687331984591e-07, "loss": 0.7767, "step": 328100 }, { "epoch": 27.27, "learning_rate": 3.652578776709254e-07, "loss": 0.6771, "step": 328110 }, { "epoch": 27.27, "learning_rate": 3.651470221433916e-07, "loss": 0.7113, "step": 328120 }, { "epoch": 27.27, "learning_rate": 3.6503616661585786e-07, "loss": 0.7026, "step": 328130 }, { "epoch": 27.27, "learning_rate": 3.6492531108832416e-07, "loss": 0.7802, "step": 328140 }, { "epoch": 27.28, "learning_rate": 3.648144555607904e-07, "loss": 0.7675, "step": 328150 }, { "epoch": 27.28, "learning_rate": 3.6470360003325664e-07, "loss": 0.7099, "step": 328160 }, { "epoch": 27.28, "learning_rate": 3.6459274450572294e-07, "loss": 0.792, "step": 328170 }, { "epoch": 27.28, "learning_rate": 3.644818889781892e-07, "loss": 0.7143, "step": 328180 }, { "epoch": 27.28, "learning_rate": 3.6437103345065537e-07, "loss": 0.7136, "step": 328190 }, { "epoch": 27.28, "learning_rate": 3.6426017792312167e-07, "loss": 0.771, "step": 328200 }, { "epoch": 27.28, "learning_rate": 3.641493223955879e-07, "loss": 0.7404, "step": 328210 }, { "epoch": 27.28, "learning_rate": 3.6403846686805415e-07, "loss": 0.6998, "step": 328220 }, { "epoch": 27.28, "learning_rate": 3.6392761134052045e-07, "loss": 0.7102, "step": 328230 }, { "epoch": 27.28, "learning_rate": 3.638167558129867e-07, "loss": 0.7164, "step": 328240 }, { "epoch": 27.28, "learning_rate": 3.6370590028545293e-07, "loss": 0.768, "step": 328250 }, { "epoch": 27.28, "learning_rate": 3.6359504475791923e-07, "loss": 0.7365, "step": 328260 }, { "epoch": 27.29, "learning_rate": 3.6348418923038547e-07, "loss": 0.7508, "step": 328270 }, { "epoch": 27.29, "learning_rate": 3.633733337028517e-07, "loss": 0.7049, "step": 328280 }, { "epoch": 27.29, "learning_rate": 3.63262478175318e-07, "loss": 0.784, "step": 328290 }, { "epoch": 27.29, "learning_rate": 3.6315162264778425e-07, "loss": 0.7986, "step": 328300 }, { "epoch": 27.29, "learning_rate": 3.630407671202505e-07, "loss": 0.7461, "step": 328310 }, { "epoch": 27.29, "learning_rate": 3.629299115927168e-07, "loss": 0.7349, "step": 328320 }, { "epoch": 27.29, "learning_rate": 3.6281905606518303e-07, "loss": 0.7017, "step": 328330 }, { "epoch": 27.29, "learning_rate": 3.6270820053764927e-07, "loss": 0.7206, "step": 328340 }, { "epoch": 27.29, "learning_rate": 3.6259734501011557e-07, "loss": 0.8173, "step": 328350 }, { "epoch": 27.29, "learning_rate": 3.624864894825818e-07, "loss": 0.7488, "step": 328360 }, { "epoch": 27.29, "learning_rate": 3.6237563395504805e-07, "loss": 0.6587, "step": 328370 }, { "epoch": 27.29, "learning_rate": 3.6226477842751435e-07, "loss": 0.7501, "step": 328380 }, { "epoch": 27.3, "learning_rate": 3.621539228999806e-07, "loss": 0.7575, "step": 328390 }, { "epoch": 27.3, "learning_rate": 3.6204306737244683e-07, "loss": 0.7634, "step": 328400 }, { "epoch": 27.3, "learning_rate": 3.6193221184491313e-07, "loss": 0.7381, "step": 328410 }, { "epoch": 27.3, "learning_rate": 3.6182135631737937e-07, "loss": 0.7317, "step": 328420 }, { "epoch": 27.3, "learning_rate": 3.617105007898456e-07, "loss": 0.7255, "step": 328430 }, { "epoch": 27.3, "learning_rate": 3.615996452623119e-07, "loss": 0.7587, "step": 328440 }, { "epoch": 27.3, "learning_rate": 3.6148878973477815e-07, "loss": 0.7238, "step": 328450 }, { "epoch": 27.3, "learning_rate": 3.613779342072444e-07, "loss": 0.7206, "step": 328460 }, { "epoch": 27.3, "learning_rate": 3.6126707867971063e-07, "loss": 0.7079, "step": 328470 }, { "epoch": 27.3, "learning_rate": 3.6115622315217693e-07, "loss": 0.7041, "step": 328480 }, { "epoch": 27.3, "learning_rate": 3.6104536762464317e-07, "loss": 0.7487, "step": 328490 }, { "epoch": 27.3, "learning_rate": 3.609345120971094e-07, "loss": 0.7373, "step": 328500 }, { "epoch": 27.31, "learning_rate": 3.608236565695757e-07, "loss": 0.6893, "step": 328510 }, { "epoch": 27.31, "learning_rate": 3.6071280104204195e-07, "loss": 0.7507, "step": 328520 }, { "epoch": 27.31, "learning_rate": 3.606019455145082e-07, "loss": 0.76, "step": 328530 }, { "epoch": 27.31, "learning_rate": 3.604910899869745e-07, "loss": 0.7645, "step": 328540 }, { "epoch": 27.31, "learning_rate": 3.6038023445944073e-07, "loss": 0.7121, "step": 328550 }, { "epoch": 27.31, "learning_rate": 3.60269378931907e-07, "loss": 0.7585, "step": 328560 }, { "epoch": 27.31, "learning_rate": 3.6015852340437327e-07, "loss": 0.6589, "step": 328570 }, { "epoch": 27.31, "learning_rate": 3.600476678768395e-07, "loss": 0.6988, "step": 328580 }, { "epoch": 27.31, "learning_rate": 3.5993681234930576e-07, "loss": 0.7067, "step": 328590 }, { "epoch": 27.31, "learning_rate": 3.5982595682177205e-07, "loss": 0.7504, "step": 328600 }, { "epoch": 27.31, "learning_rate": 3.5971510129423824e-07, "loss": 0.7055, "step": 328610 }, { "epoch": 27.31, "learning_rate": 3.596042457667045e-07, "loss": 0.7603, "step": 328620 }, { "epoch": 27.32, "learning_rate": 3.594933902391708e-07, "loss": 0.6872, "step": 328630 }, { "epoch": 27.32, "learning_rate": 3.59382534711637e-07, "loss": 0.7673, "step": 328640 }, { "epoch": 27.32, "learning_rate": 3.5927167918410326e-07, "loss": 0.7832, "step": 328650 }, { "epoch": 27.32, "learning_rate": 3.5916082365656956e-07, "loss": 0.7491, "step": 328660 }, { "epoch": 27.32, "learning_rate": 3.590499681290358e-07, "loss": 0.7605, "step": 328670 }, { "epoch": 27.32, "learning_rate": 3.5893911260150204e-07, "loss": 0.7966, "step": 328680 }, { "epoch": 27.32, "learning_rate": 3.5882825707396834e-07, "loss": 0.7583, "step": 328690 }, { "epoch": 27.32, "learning_rate": 3.587174015464346e-07, "loss": 0.7368, "step": 328700 }, { "epoch": 27.32, "learning_rate": 3.586065460189008e-07, "loss": 0.7408, "step": 328710 }, { "epoch": 27.32, "learning_rate": 3.584956904913671e-07, "loss": 0.7247, "step": 328720 }, { "epoch": 27.32, "learning_rate": 3.5838483496383336e-07, "loss": 0.6903, "step": 328730 }, { "epoch": 27.32, "learning_rate": 3.582739794362996e-07, "loss": 0.7537, "step": 328740 }, { "epoch": 27.33, "learning_rate": 3.581631239087659e-07, "loss": 0.7508, "step": 328750 }, { "epoch": 27.33, "learning_rate": 3.5805226838123214e-07, "loss": 0.7266, "step": 328760 }, { "epoch": 27.33, "learning_rate": 3.579414128536984e-07, "loss": 0.7274, "step": 328770 }, { "epoch": 27.33, "learning_rate": 3.578305573261647e-07, "loss": 0.6973, "step": 328780 }, { "epoch": 27.33, "learning_rate": 3.577197017986309e-07, "loss": 0.8163, "step": 328790 }, { "epoch": 27.33, "learning_rate": 3.5760884627109716e-07, "loss": 0.7742, "step": 328800 }, { "epoch": 27.33, "learning_rate": 3.5749799074356346e-07, "loss": 0.7592, "step": 328810 }, { "epoch": 27.33, "learning_rate": 3.573871352160297e-07, "loss": 0.7315, "step": 328820 }, { "epoch": 27.33, "learning_rate": 3.5727627968849594e-07, "loss": 0.763, "step": 328830 }, { "epoch": 27.33, "learning_rate": 3.5716542416096224e-07, "loss": 0.7363, "step": 328840 }, { "epoch": 27.33, "learning_rate": 3.570545686334285e-07, "loss": 0.7599, "step": 328850 }, { "epoch": 27.33, "learning_rate": 3.569437131058947e-07, "loss": 0.7135, "step": 328860 }, { "epoch": 27.34, "learning_rate": 3.5683285757836097e-07, "loss": 0.742, "step": 328870 }, { "epoch": 27.34, "learning_rate": 3.5672200205082726e-07, "loss": 0.7461, "step": 328880 }, { "epoch": 27.34, "learning_rate": 3.566111465232935e-07, "loss": 0.7449, "step": 328890 }, { "epoch": 27.34, "learning_rate": 3.5650029099575975e-07, "loss": 0.7492, "step": 328900 }, { "epoch": 27.34, "learning_rate": 3.5638943546822604e-07, "loss": 0.6967, "step": 328910 }, { "epoch": 27.34, "learning_rate": 3.562785799406923e-07, "loss": 0.6875, "step": 328920 }, { "epoch": 27.34, "learning_rate": 3.561677244131585e-07, "loss": 0.6868, "step": 328930 }, { "epoch": 27.34, "learning_rate": 3.560568688856248e-07, "loss": 0.7382, "step": 328940 }, { "epoch": 27.34, "learning_rate": 3.5594601335809106e-07, "loss": 0.754, "step": 328950 }, { "epoch": 27.34, "learning_rate": 3.558351578305573e-07, "loss": 0.7382, "step": 328960 }, { "epoch": 27.34, "learning_rate": 3.557243023030236e-07, "loss": 0.7386, "step": 328970 }, { "epoch": 27.34, "learning_rate": 3.5561344677548984e-07, "loss": 0.7116, "step": 328980 }, { "epoch": 27.35, "learning_rate": 3.555025912479561e-07, "loss": 0.7909, "step": 328990 }, { "epoch": 27.35, "learning_rate": 3.553917357204224e-07, "loss": 0.6908, "step": 329000 }, { "epoch": 27.35, "learning_rate": 3.552808801928886e-07, "loss": 0.6965, "step": 329010 }, { "epoch": 27.35, "learning_rate": 3.551700246653548e-07, "loss": 0.7486, "step": 329020 }, { "epoch": 27.35, "learning_rate": 3.550591691378211e-07, "loss": 0.7378, "step": 329030 }, { "epoch": 27.35, "learning_rate": 3.5494831361028735e-07, "loss": 0.7028, "step": 329040 }, { "epoch": 27.35, "learning_rate": 3.548374580827536e-07, "loss": 0.7349, "step": 329050 }, { "epoch": 27.35, "learning_rate": 3.547266025552199e-07, "loss": 0.7516, "step": 329060 }, { "epoch": 27.35, "learning_rate": 3.5461574702768613e-07, "loss": 0.7789, "step": 329070 }, { "epoch": 27.35, "learning_rate": 3.545048915001524e-07, "loss": 0.7039, "step": 329080 }, { "epoch": 27.35, "learning_rate": 3.5439403597261867e-07, "loss": 0.7091, "step": 329090 }, { "epoch": 27.35, "learning_rate": 3.542831804450849e-07, "loss": 0.7675, "step": 329100 }, { "epoch": 27.36, "learning_rate": 3.5417232491755115e-07, "loss": 0.7483, "step": 329110 }, { "epoch": 27.36, "learning_rate": 3.5406146939001745e-07, "loss": 0.7452, "step": 329120 }, { "epoch": 27.36, "learning_rate": 3.539506138624837e-07, "loss": 0.6937, "step": 329130 }, { "epoch": 27.36, "learning_rate": 3.5383975833494993e-07, "loss": 0.7251, "step": 329140 }, { "epoch": 27.36, "learning_rate": 3.5372890280741623e-07, "loss": 0.7575, "step": 329150 }, { "epoch": 27.36, "learning_rate": 3.5361804727988247e-07, "loss": 0.7287, "step": 329160 }, { "epoch": 27.36, "learning_rate": 3.535071917523487e-07, "loss": 0.7285, "step": 329170 }, { "epoch": 27.36, "learning_rate": 3.53396336224815e-07, "loss": 0.7139, "step": 329180 }, { "epoch": 27.36, "learning_rate": 3.5328548069728125e-07, "loss": 0.6777, "step": 329190 }, { "epoch": 27.36, "learning_rate": 3.531746251697475e-07, "loss": 0.7063, "step": 329200 }, { "epoch": 27.36, "learning_rate": 3.530637696422138e-07, "loss": 0.7628, "step": 329210 }, { "epoch": 27.36, "learning_rate": 3.5295291411468003e-07, "loss": 0.7138, "step": 329220 }, { "epoch": 27.37, "learning_rate": 3.528420585871463e-07, "loss": 0.7407, "step": 329230 }, { "epoch": 27.37, "learning_rate": 3.5273120305961257e-07, "loss": 0.7226, "step": 329240 }, { "epoch": 27.37, "learning_rate": 3.526203475320788e-07, "loss": 0.7978, "step": 329250 }, { "epoch": 27.37, "learning_rate": 3.5250949200454505e-07, "loss": 0.7177, "step": 329260 }, { "epoch": 27.37, "learning_rate": 3.5239863647701135e-07, "loss": 0.7212, "step": 329270 }, { "epoch": 27.37, "learning_rate": 3.522877809494776e-07, "loss": 0.7308, "step": 329280 }, { "epoch": 27.37, "learning_rate": 3.5217692542194383e-07, "loss": 0.7151, "step": 329290 }, { "epoch": 27.37, "learning_rate": 3.520660698944101e-07, "loss": 0.7469, "step": 329300 }, { "epoch": 27.37, "learning_rate": 3.5195521436687637e-07, "loss": 0.7057, "step": 329310 }, { "epoch": 27.37, "learning_rate": 3.518443588393426e-07, "loss": 0.7495, "step": 329320 }, { "epoch": 27.37, "learning_rate": 3.5173350331180886e-07, "loss": 0.6833, "step": 329330 }, { "epoch": 27.37, "learning_rate": 3.5162264778427515e-07, "loss": 0.755, "step": 329340 }, { "epoch": 27.38, "learning_rate": 3.515117922567414e-07, "loss": 0.6919, "step": 329350 }, { "epoch": 27.38, "learning_rate": 3.5140093672920764e-07, "loss": 0.7151, "step": 329360 }, { "epoch": 27.38, "learning_rate": 3.5129008120167393e-07, "loss": 0.7259, "step": 329370 }, { "epoch": 27.38, "learning_rate": 3.511792256741402e-07, "loss": 0.7912, "step": 329380 }, { "epoch": 27.38, "learning_rate": 3.510683701466064e-07, "loss": 0.7937, "step": 329390 }, { "epoch": 27.38, "learning_rate": 3.509575146190727e-07, "loss": 0.7314, "step": 329400 }, { "epoch": 27.38, "learning_rate": 3.5084665909153896e-07, "loss": 0.7135, "step": 329410 }, { "epoch": 27.38, "learning_rate": 3.507358035640052e-07, "loss": 0.6995, "step": 329420 }, { "epoch": 27.38, "learning_rate": 3.506249480364715e-07, "loss": 0.6978, "step": 329430 }, { "epoch": 27.38, "learning_rate": 3.505140925089377e-07, "loss": 0.7434, "step": 329440 }, { "epoch": 27.38, "learning_rate": 3.504032369814039e-07, "loss": 0.7377, "step": 329450 }, { "epoch": 27.38, "learning_rate": 3.502923814538702e-07, "loss": 0.7516, "step": 329460 }, { "epoch": 27.39, "learning_rate": 3.5018152592633646e-07, "loss": 0.6553, "step": 329470 }, { "epoch": 27.39, "learning_rate": 3.500706703988027e-07, "loss": 0.7519, "step": 329480 }, { "epoch": 27.39, "learning_rate": 3.49959814871269e-07, "loss": 0.7634, "step": 329490 }, { "epoch": 27.39, "learning_rate": 3.4984895934373524e-07, "loss": 0.8106, "step": 329500 }, { "epoch": 27.39, "learning_rate": 3.497381038162015e-07, "loss": 0.7564, "step": 329510 }, { "epoch": 27.39, "learning_rate": 3.496272482886678e-07, "loss": 0.71, "step": 329520 }, { "epoch": 27.39, "learning_rate": 3.49516392761134e-07, "loss": 0.786, "step": 329530 }, { "epoch": 27.39, "learning_rate": 3.4940553723360027e-07, "loss": 0.7204, "step": 329540 }, { "epoch": 27.39, "learning_rate": 3.4929468170606656e-07, "loss": 0.721, "step": 329550 }, { "epoch": 27.39, "learning_rate": 3.491838261785328e-07, "loss": 0.7127, "step": 329560 }, { "epoch": 27.39, "learning_rate": 3.4907297065099905e-07, "loss": 0.7527, "step": 329570 }, { "epoch": 27.39, "learning_rate": 3.4896211512346534e-07, "loss": 0.7029, "step": 329580 }, { "epoch": 27.4, "learning_rate": 3.488512595959316e-07, "loss": 0.7574, "step": 329590 }, { "epoch": 27.4, "learning_rate": 3.487404040683978e-07, "loss": 0.7525, "step": 329600 }, { "epoch": 27.4, "learning_rate": 3.486295485408641e-07, "loss": 0.7149, "step": 329610 }, { "epoch": 27.4, "learning_rate": 3.4851869301333036e-07, "loss": 0.783, "step": 329620 }, { "epoch": 27.4, "learning_rate": 3.484078374857966e-07, "loss": 0.7444, "step": 329630 }, { "epoch": 27.4, "learning_rate": 3.482969819582629e-07, "loss": 0.7301, "step": 329640 }, { "epoch": 27.4, "learning_rate": 3.4818612643072914e-07, "loss": 0.7727, "step": 329650 }, { "epoch": 27.4, "learning_rate": 3.480752709031954e-07, "loss": 0.7173, "step": 329660 }, { "epoch": 27.4, "learning_rate": 3.479644153756617e-07, "loss": 0.7445, "step": 329670 }, { "epoch": 27.4, "learning_rate": 3.478535598481279e-07, "loss": 0.6947, "step": 329680 }, { "epoch": 27.4, "learning_rate": 3.4774270432059417e-07, "loss": 0.6874, "step": 329690 }, { "epoch": 27.4, "learning_rate": 3.4763184879306046e-07, "loss": 0.7759, "step": 329700 }, { "epoch": 27.41, "learning_rate": 3.475209932655267e-07, "loss": 0.7337, "step": 329710 }, { "epoch": 27.41, "learning_rate": 3.4741013773799295e-07, "loss": 0.7086, "step": 329720 }, { "epoch": 27.41, "learning_rate": 3.472992822104592e-07, "loss": 0.7033, "step": 329730 }, { "epoch": 27.41, "learning_rate": 3.471884266829255e-07, "loss": 0.7731, "step": 329740 }, { "epoch": 27.41, "learning_rate": 3.470775711553917e-07, "loss": 0.7432, "step": 329750 }, { "epoch": 27.41, "learning_rate": 3.4696671562785797e-07, "loss": 0.7582, "step": 329760 }, { "epoch": 27.41, "learning_rate": 3.4685586010032426e-07, "loss": 0.7141, "step": 329770 }, { "epoch": 27.41, "learning_rate": 3.467450045727905e-07, "loss": 0.7228, "step": 329780 }, { "epoch": 27.41, "learning_rate": 3.4663414904525675e-07, "loss": 0.788, "step": 329790 }, { "epoch": 27.41, "learning_rate": 3.4652329351772304e-07, "loss": 0.7248, "step": 329800 }, { "epoch": 27.41, "learning_rate": 3.464124379901893e-07, "loss": 0.7503, "step": 329810 }, { "epoch": 27.41, "learning_rate": 3.4630158246265553e-07, "loss": 0.7067, "step": 329820 }, { "epoch": 27.42, "learning_rate": 3.461907269351218e-07, "loss": 0.7329, "step": 329830 }, { "epoch": 27.42, "learning_rate": 3.4607987140758807e-07, "loss": 0.7869, "step": 329840 }, { "epoch": 27.42, "learning_rate": 3.4596901588005426e-07, "loss": 0.6662, "step": 329850 }, { "epoch": 27.42, "learning_rate": 3.458581603525206e-07, "loss": 0.7266, "step": 329860 }, { "epoch": 27.42, "learning_rate": 3.457473048249868e-07, "loss": 0.5787, "step": 329870 }, { "epoch": 27.42, "learning_rate": 3.4563644929745304e-07, "loss": 0.744, "step": 329880 }, { "epoch": 27.42, "learning_rate": 3.4552559376991933e-07, "loss": 0.7215, "step": 329890 }, { "epoch": 27.42, "learning_rate": 3.454147382423856e-07, "loss": 0.7642, "step": 329900 }, { "epoch": 27.42, "learning_rate": 3.453038827148518e-07, "loss": 0.7251, "step": 329910 }, { "epoch": 27.42, "learning_rate": 3.451930271873181e-07, "loss": 0.7661, "step": 329920 }, { "epoch": 27.42, "learning_rate": 3.4508217165978435e-07, "loss": 0.6873, "step": 329930 }, { "epoch": 27.42, "learning_rate": 3.449713161322506e-07, "loss": 0.7547, "step": 329940 }, { "epoch": 27.42, "learning_rate": 3.448604606047169e-07, "loss": 0.7782, "step": 329950 }, { "epoch": 27.43, "learning_rate": 3.4474960507718313e-07, "loss": 0.7099, "step": 329960 }, { "epoch": 27.43, "learning_rate": 3.446387495496494e-07, "loss": 0.7414, "step": 329970 }, { "epoch": 27.43, "learning_rate": 3.4452789402211567e-07, "loss": 0.7473, "step": 329980 }, { "epoch": 27.43, "learning_rate": 3.444170384945819e-07, "loss": 0.7358, "step": 329990 }, { "epoch": 27.43, "learning_rate": 3.4430618296704816e-07, "loss": 0.7809, "step": 330000 }, { "epoch": 27.43, "learning_rate": 3.4419532743951445e-07, "loss": 0.7908, "step": 330010 }, { "epoch": 27.43, "learning_rate": 3.440844719119807e-07, "loss": 0.777, "step": 330020 }, { "epoch": 27.43, "learning_rate": 3.4397361638444694e-07, "loss": 0.6769, "step": 330030 }, { "epoch": 27.43, "learning_rate": 3.4386276085691323e-07, "loss": 0.7266, "step": 330040 }, { "epoch": 27.43, "learning_rate": 3.437519053293795e-07, "loss": 0.7876, "step": 330050 }, { "epoch": 27.43, "learning_rate": 3.436410498018457e-07, "loss": 0.742, "step": 330060 }, { "epoch": 27.43, "learning_rate": 3.43530194274312e-07, "loss": 0.7697, "step": 330070 }, { "epoch": 27.44, "learning_rate": 3.4341933874677825e-07, "loss": 0.7293, "step": 330080 }, { "epoch": 27.44, "learning_rate": 3.433084832192445e-07, "loss": 0.7957, "step": 330090 }, { "epoch": 27.44, "learning_rate": 3.431976276917108e-07, "loss": 0.7599, "step": 330100 }, { "epoch": 27.44, "learning_rate": 3.4308677216417703e-07, "loss": 0.7155, "step": 330110 }, { "epoch": 27.44, "learning_rate": 3.429759166366433e-07, "loss": 0.7199, "step": 330120 }, { "epoch": 27.44, "learning_rate": 3.428650611091095e-07, "loss": 0.7318, "step": 330130 }, { "epoch": 27.44, "learning_rate": 3.427542055815758e-07, "loss": 0.7705, "step": 330140 }, { "epoch": 27.44, "learning_rate": 3.4264335005404206e-07, "loss": 0.7575, "step": 330150 }, { "epoch": 27.44, "learning_rate": 3.425324945265083e-07, "loss": 0.7082, "step": 330160 }, { "epoch": 27.44, "learning_rate": 3.424216389989746e-07, "loss": 0.7406, "step": 330170 }, { "epoch": 27.44, "learning_rate": 3.4231078347144084e-07, "loss": 0.7611, "step": 330180 }, { "epoch": 27.44, "learning_rate": 3.421999279439071e-07, "loss": 0.7446, "step": 330190 }, { "epoch": 27.45, "learning_rate": 3.420890724163734e-07, "loss": 0.7208, "step": 330200 }, { "epoch": 27.45, "learning_rate": 3.419782168888396e-07, "loss": 0.7737, "step": 330210 }, { "epoch": 27.45, "learning_rate": 3.4186736136130586e-07, "loss": 0.7902, "step": 330220 }, { "epoch": 27.45, "learning_rate": 3.4175650583377216e-07, "loss": 0.7131, "step": 330230 }, { "epoch": 27.45, "learning_rate": 3.416456503062384e-07, "loss": 0.7961, "step": 330240 }, { "epoch": 27.45, "learning_rate": 3.4153479477870464e-07, "loss": 0.751, "step": 330250 }, { "epoch": 27.45, "learning_rate": 3.4142393925117094e-07, "loss": 0.6998, "step": 330260 }, { "epoch": 27.45, "learning_rate": 3.413130837236372e-07, "loss": 0.6878, "step": 330270 }, { "epoch": 27.45, "learning_rate": 3.4120222819610337e-07, "loss": 0.7127, "step": 330280 }, { "epoch": 27.45, "learning_rate": 3.4109137266856966e-07, "loss": 0.7408, "step": 330290 }, { "epoch": 27.45, "learning_rate": 3.409805171410359e-07, "loss": 0.7679, "step": 330300 }, { "epoch": 27.45, "learning_rate": 3.4086966161350215e-07, "loss": 0.7491, "step": 330310 }, { "epoch": 27.46, "learning_rate": 3.4075880608596844e-07, "loss": 0.6915, "step": 330320 }, { "epoch": 27.46, "learning_rate": 3.406479505584347e-07, "loss": 0.7247, "step": 330330 }, { "epoch": 27.46, "learning_rate": 3.4053709503090093e-07, "loss": 0.6915, "step": 330340 }, { "epoch": 27.46, "learning_rate": 3.404262395033672e-07, "loss": 0.7458, "step": 330350 }, { "epoch": 27.46, "learning_rate": 3.4031538397583347e-07, "loss": 0.7015, "step": 330360 }, { "epoch": 27.46, "learning_rate": 3.402045284482997e-07, "loss": 0.7929, "step": 330370 }, { "epoch": 27.46, "learning_rate": 3.40093672920766e-07, "loss": 0.7746, "step": 330380 }, { "epoch": 27.46, "learning_rate": 3.3998281739323225e-07, "loss": 0.798, "step": 330390 }, { "epoch": 27.46, "learning_rate": 3.398719618656985e-07, "loss": 0.7718, "step": 330400 }, { "epoch": 27.46, "learning_rate": 3.397611063381648e-07, "loss": 0.6759, "step": 330410 }, { "epoch": 27.46, "learning_rate": 3.39650250810631e-07, "loss": 0.7156, "step": 330420 }, { "epoch": 27.46, "learning_rate": 3.3953939528309727e-07, "loss": 0.7317, "step": 330430 }, { "epoch": 27.47, "learning_rate": 3.3942853975556356e-07, "loss": 0.699, "step": 330440 }, { "epoch": 27.47, "learning_rate": 3.393176842280298e-07, "loss": 0.7489, "step": 330450 }, { "epoch": 27.47, "learning_rate": 3.3920682870049605e-07, "loss": 0.7086, "step": 330460 }, { "epoch": 27.47, "learning_rate": 3.3909597317296234e-07, "loss": 0.7408, "step": 330470 }, { "epoch": 27.47, "learning_rate": 3.389851176454286e-07, "loss": 0.769, "step": 330480 }, { "epoch": 27.47, "learning_rate": 3.3887426211789483e-07, "loss": 0.7712, "step": 330490 }, { "epoch": 27.47, "learning_rate": 3.387634065903611e-07, "loss": 0.8305, "step": 330500 }, { "epoch": 27.47, "learning_rate": 3.3865255106282737e-07, "loss": 0.7424, "step": 330510 }, { "epoch": 27.47, "learning_rate": 3.385416955352936e-07, "loss": 0.6951, "step": 330520 }, { "epoch": 27.47, "learning_rate": 3.384308400077599e-07, "loss": 0.7002, "step": 330530 }, { "epoch": 27.47, "learning_rate": 3.3831998448022615e-07, "loss": 0.717, "step": 330540 }, { "epoch": 27.47, "learning_rate": 3.382091289526924e-07, "loss": 0.729, "step": 330550 }, { "epoch": 27.48, "learning_rate": 3.3809827342515863e-07, "loss": 0.7771, "step": 330560 }, { "epoch": 27.48, "learning_rate": 3.379874178976249e-07, "loss": 0.7296, "step": 330570 }, { "epoch": 27.48, "learning_rate": 3.3787656237009117e-07, "loss": 0.7312, "step": 330580 }, { "epoch": 27.48, "learning_rate": 3.377657068425574e-07, "loss": 0.7342, "step": 330590 }, { "epoch": 27.48, "learning_rate": 3.376548513150237e-07, "loss": 0.7992, "step": 330600 }, { "epoch": 27.48, "learning_rate": 3.3754399578748995e-07, "loss": 0.6947, "step": 330610 }, { "epoch": 27.48, "learning_rate": 3.374331402599562e-07, "loss": 0.7696, "step": 330620 }, { "epoch": 27.48, "learning_rate": 3.373222847324225e-07, "loss": 0.7205, "step": 330630 }, { "epoch": 27.48, "learning_rate": 3.3721142920488873e-07, "loss": 0.723, "step": 330640 }, { "epoch": 27.48, "learning_rate": 3.3710057367735497e-07, "loss": 0.8007, "step": 330650 }, { "epoch": 27.48, "learning_rate": 3.3698971814982127e-07, "loss": 0.7373, "step": 330660 }, { "epoch": 27.48, "learning_rate": 3.368788626222875e-07, "loss": 0.7195, "step": 330670 }, { "epoch": 27.49, "learning_rate": 3.3676800709475375e-07, "loss": 0.7141, "step": 330680 }, { "epoch": 27.49, "learning_rate": 3.3665715156722005e-07, "loss": 0.8111, "step": 330690 }, { "epoch": 27.49, "learning_rate": 3.3654629603968624e-07, "loss": 0.7555, "step": 330700 }, { "epoch": 27.49, "learning_rate": 3.364354405121525e-07, "loss": 0.6794, "step": 330710 }, { "epoch": 27.49, "learning_rate": 3.363245849846188e-07, "loss": 0.6989, "step": 330720 }, { "epoch": 27.49, "learning_rate": 3.36213729457085e-07, "loss": 0.7658, "step": 330730 }, { "epoch": 27.49, "learning_rate": 3.3610287392955126e-07, "loss": 0.7368, "step": 330740 }, { "epoch": 27.49, "learning_rate": 3.3599201840201755e-07, "loss": 0.7209, "step": 330750 }, { "epoch": 27.49, "learning_rate": 3.358811628744838e-07, "loss": 0.7024, "step": 330760 }, { "epoch": 27.49, "learning_rate": 3.3577030734695004e-07, "loss": 0.7386, "step": 330770 }, { "epoch": 27.49, "learning_rate": 3.3565945181941633e-07, "loss": 0.728, "step": 330780 }, { "epoch": 27.49, "learning_rate": 3.355485962918826e-07, "loss": 0.7247, "step": 330790 }, { "epoch": 27.5, "learning_rate": 3.354377407643488e-07, "loss": 0.8029, "step": 330800 }, { "epoch": 27.5, "learning_rate": 3.353268852368151e-07, "loss": 0.7146, "step": 330810 }, { "epoch": 27.5, "learning_rate": 3.3521602970928136e-07, "loss": 0.7051, "step": 330820 }, { "epoch": 27.5, "learning_rate": 3.351051741817476e-07, "loss": 0.7664, "step": 330830 }, { "epoch": 27.5, "learning_rate": 3.349943186542139e-07, "loss": 0.7463, "step": 330840 }, { "epoch": 27.5, "learning_rate": 3.3488346312668014e-07, "loss": 0.714, "step": 330850 }, { "epoch": 27.5, "learning_rate": 3.347726075991464e-07, "loss": 0.7581, "step": 330860 }, { "epoch": 27.5, "learning_rate": 3.346617520716127e-07, "loss": 0.7478, "step": 330870 }, { "epoch": 27.5, "learning_rate": 3.345508965440789e-07, "loss": 0.7694, "step": 330880 }, { "epoch": 27.5, "learning_rate": 3.3444004101654516e-07, "loss": 0.7645, "step": 330890 }, { "epoch": 27.5, "learning_rate": 3.343513565945182e-07, "loss": 0.7904, "step": 330900 }, { "epoch": 27.5, "learning_rate": 3.3424050106698445e-07, "loss": 0.7192, "step": 330910 }, { "epoch": 27.51, "learning_rate": 3.3412964553945074e-07, "loss": 0.7587, "step": 330920 }, { "epoch": 27.51, "learning_rate": 3.34018790011917e-07, "loss": 0.7404, "step": 330930 }, { "epoch": 27.51, "learning_rate": 3.339079344843832e-07, "loss": 0.7816, "step": 330940 }, { "epoch": 27.51, "learning_rate": 3.337970789568495e-07, "loss": 0.7178, "step": 330950 }, { "epoch": 27.51, "learning_rate": 3.336862234293157e-07, "loss": 0.7293, "step": 330960 }, { "epoch": 27.51, "learning_rate": 3.3357536790178196e-07, "loss": 0.7206, "step": 330970 }, { "epoch": 27.51, "learning_rate": 3.334645123742482e-07, "loss": 0.7057, "step": 330980 }, { "epoch": 27.51, "learning_rate": 3.333536568467145e-07, "loss": 0.7877, "step": 330990 }, { "epoch": 27.51, "learning_rate": 3.3324280131918074e-07, "loss": 0.7528, "step": 331000 }, { "epoch": 27.51, "learning_rate": 3.33131945791647e-07, "loss": 0.7746, "step": 331010 }, { "epoch": 27.51, "learning_rate": 3.330210902641133e-07, "loss": 0.7302, "step": 331020 }, { "epoch": 27.51, "learning_rate": 3.329102347365795e-07, "loss": 0.7447, "step": 331030 }, { "epoch": 27.52, "learning_rate": 3.3279937920904576e-07, "loss": 0.7151, "step": 331040 }, { "epoch": 27.52, "learning_rate": 3.3268852368151205e-07, "loss": 0.7438, "step": 331050 }, { "epoch": 27.52, "learning_rate": 3.325776681539783e-07, "loss": 0.7432, "step": 331060 }, { "epoch": 27.52, "learning_rate": 3.3246681262644454e-07, "loss": 0.7523, "step": 331070 }, { "epoch": 27.52, "learning_rate": 3.3235595709891083e-07, "loss": 0.7091, "step": 331080 }, { "epoch": 27.52, "learning_rate": 3.322451015713771e-07, "loss": 0.7361, "step": 331090 }, { "epoch": 27.52, "learning_rate": 3.321342460438433e-07, "loss": 0.7081, "step": 331100 }, { "epoch": 27.52, "learning_rate": 3.320233905163096e-07, "loss": 0.7328, "step": 331110 }, { "epoch": 27.52, "learning_rate": 3.3191253498877586e-07, "loss": 0.7397, "step": 331120 }, { "epoch": 27.52, "learning_rate": 3.318016794612421e-07, "loss": 0.6828, "step": 331130 }, { "epoch": 27.52, "learning_rate": 3.316908239337084e-07, "loss": 0.7276, "step": 331140 }, { "epoch": 27.52, "learning_rate": 3.3157996840617464e-07, "loss": 0.7429, "step": 331150 }, { "epoch": 27.53, "learning_rate": 3.314691128786409e-07, "loss": 0.7752, "step": 331160 }, { "epoch": 27.53, "learning_rate": 3.313582573511072e-07, "loss": 0.7711, "step": 331170 }, { "epoch": 27.53, "learning_rate": 3.312474018235734e-07, "loss": 0.7234, "step": 331180 }, { "epoch": 27.53, "learning_rate": 3.3113654629603966e-07, "loss": 0.7989, "step": 331190 }, { "epoch": 27.53, "learning_rate": 3.3102569076850595e-07, "loss": 0.7331, "step": 331200 }, { "epoch": 27.53, "learning_rate": 3.309148352409722e-07, "loss": 0.7387, "step": 331210 }, { "epoch": 27.53, "learning_rate": 3.3080397971343844e-07, "loss": 0.7251, "step": 331220 }, { "epoch": 27.53, "learning_rate": 3.3069312418590473e-07, "loss": 0.71, "step": 331230 }, { "epoch": 27.53, "learning_rate": 3.30582268658371e-07, "loss": 0.6886, "step": 331240 }, { "epoch": 27.53, "learning_rate": 3.304714131308372e-07, "loss": 0.7606, "step": 331250 }, { "epoch": 27.53, "learning_rate": 3.303605576033035e-07, "loss": 0.7663, "step": 331260 }, { "epoch": 27.53, "learning_rate": 3.3024970207576976e-07, "loss": 0.7098, "step": 331270 }, { "epoch": 27.54, "learning_rate": 3.30138846548236e-07, "loss": 0.6791, "step": 331280 }, { "epoch": 27.54, "learning_rate": 3.300279910207023e-07, "loss": 0.7317, "step": 331290 }, { "epoch": 27.54, "learning_rate": 3.2991713549316854e-07, "loss": 0.7436, "step": 331300 }, { "epoch": 27.54, "learning_rate": 3.298062799656348e-07, "loss": 0.7266, "step": 331310 }, { "epoch": 27.54, "learning_rate": 3.296954244381011e-07, "loss": 0.7344, "step": 331320 }, { "epoch": 27.54, "learning_rate": 3.295845689105673e-07, "loss": 0.7243, "step": 331330 }, { "epoch": 27.54, "learning_rate": 3.2947371338303356e-07, "loss": 0.7171, "step": 331340 }, { "epoch": 27.54, "learning_rate": 3.2936285785549986e-07, "loss": 0.7531, "step": 331350 }, { "epoch": 27.54, "learning_rate": 3.292520023279661e-07, "loss": 0.705, "step": 331360 }, { "epoch": 27.54, "learning_rate": 3.291411468004323e-07, "loss": 0.7356, "step": 331370 }, { "epoch": 27.54, "learning_rate": 3.2903029127289853e-07, "loss": 0.7205, "step": 331380 }, { "epoch": 27.54, "learning_rate": 3.289194357453648e-07, "loss": 0.7369, "step": 331390 }, { "epoch": 27.55, "learning_rate": 3.2880858021783107e-07, "loss": 0.71, "step": 331400 }, { "epoch": 27.55, "learning_rate": 3.286977246902973e-07, "loss": 0.7318, "step": 331410 }, { "epoch": 27.55, "learning_rate": 3.285868691627636e-07, "loss": 0.6913, "step": 331420 }, { "epoch": 27.55, "learning_rate": 3.2847601363522985e-07, "loss": 0.7002, "step": 331430 }, { "epoch": 27.55, "learning_rate": 3.283651581076961e-07, "loss": 0.6605, "step": 331440 }, { "epoch": 27.55, "learning_rate": 3.282543025801624e-07, "loss": 0.7894, "step": 331450 }, { "epoch": 27.55, "learning_rate": 3.2814344705262863e-07, "loss": 0.7632, "step": 331460 }, { "epoch": 27.55, "learning_rate": 3.2803259152509487e-07, "loss": 0.6878, "step": 331470 }, { "epoch": 27.55, "learning_rate": 3.2792173599756117e-07, "loss": 0.7119, "step": 331480 }, { "epoch": 27.55, "learning_rate": 3.278108804700274e-07, "loss": 0.714, "step": 331490 }, { "epoch": 27.55, "learning_rate": 3.2770002494249365e-07, "loss": 0.7556, "step": 331500 }, { "epoch": 27.55, "learning_rate": 3.2758916941495995e-07, "loss": 0.7219, "step": 331510 }, { "epoch": 27.56, "learning_rate": 3.274783138874262e-07, "loss": 0.7494, "step": 331520 }, { "epoch": 27.56, "learning_rate": 3.2736745835989243e-07, "loss": 0.7749, "step": 331530 }, { "epoch": 27.56, "learning_rate": 3.272566028323587e-07, "loss": 0.7863, "step": 331540 }, { "epoch": 27.56, "learning_rate": 3.2714574730482497e-07, "loss": 0.7448, "step": 331550 }, { "epoch": 27.56, "learning_rate": 3.270348917772912e-07, "loss": 0.6275, "step": 331560 }, { "epoch": 27.56, "learning_rate": 3.269240362497575e-07, "loss": 0.7147, "step": 331570 }, { "epoch": 27.56, "learning_rate": 3.2681318072222375e-07, "loss": 0.7226, "step": 331580 }, { "epoch": 27.56, "learning_rate": 3.2670232519469e-07, "loss": 0.7473, "step": 331590 }, { "epoch": 27.56, "learning_rate": 3.265914696671563e-07, "loss": 0.7459, "step": 331600 }, { "epoch": 27.56, "learning_rate": 3.2648061413962253e-07, "loss": 0.7017, "step": 331610 }, { "epoch": 27.56, "learning_rate": 3.2636975861208877e-07, "loss": 0.7405, "step": 331620 }, { "epoch": 27.56, "learning_rate": 3.2625890308455507e-07, "loss": 0.7277, "step": 331630 }, { "epoch": 27.57, "learning_rate": 3.261480475570213e-07, "loss": 0.7555, "step": 331640 }, { "epoch": 27.57, "learning_rate": 3.2603719202948755e-07, "loss": 0.7217, "step": 331650 }, { "epoch": 27.57, "learning_rate": 3.2592633650195385e-07, "loss": 0.7293, "step": 331660 }, { "epoch": 27.57, "learning_rate": 3.258154809744201e-07, "loss": 0.7062, "step": 331670 }, { "epoch": 27.57, "learning_rate": 3.2570462544688633e-07, "loss": 0.7305, "step": 331680 }, { "epoch": 27.57, "learning_rate": 3.2559376991935263e-07, "loss": 0.7392, "step": 331690 }, { "epoch": 27.57, "learning_rate": 3.2548291439181887e-07, "loss": 0.7271, "step": 331700 }, { "epoch": 27.57, "learning_rate": 3.253720588642851e-07, "loss": 0.7238, "step": 331710 }, { "epoch": 27.57, "learning_rate": 3.252612033367514e-07, "loss": 0.7458, "step": 331720 }, { "epoch": 27.57, "learning_rate": 3.2515034780921765e-07, "loss": 0.7459, "step": 331730 }, { "epoch": 27.57, "learning_rate": 3.250394922816839e-07, "loss": 0.702, "step": 331740 }, { "epoch": 27.57, "learning_rate": 3.249286367541502e-07, "loss": 0.7787, "step": 331750 }, { "epoch": 27.58, "learning_rate": 3.2481778122661643e-07, "loss": 0.7532, "step": 331760 }, { "epoch": 27.58, "learning_rate": 3.2470692569908267e-07, "loss": 0.7083, "step": 331770 }, { "epoch": 27.58, "learning_rate": 3.2459607017154897e-07, "loss": 0.7214, "step": 331780 }, { "epoch": 27.58, "learning_rate": 3.2448521464401516e-07, "loss": 0.7189, "step": 331790 }, { "epoch": 27.58, "learning_rate": 3.243743591164814e-07, "loss": 0.7068, "step": 331800 }, { "epoch": 27.58, "learning_rate": 3.2426350358894764e-07, "loss": 0.7065, "step": 331810 }, { "epoch": 27.58, "learning_rate": 3.2415264806141394e-07, "loss": 0.6931, "step": 331820 }, { "epoch": 27.58, "learning_rate": 3.240417925338802e-07, "loss": 0.7868, "step": 331830 }, { "epoch": 27.58, "learning_rate": 3.239309370063464e-07, "loss": 0.7534, "step": 331840 }, { "epoch": 27.58, "learning_rate": 3.238200814788127e-07, "loss": 0.7403, "step": 331850 }, { "epoch": 27.58, "learning_rate": 3.2370922595127896e-07, "loss": 0.696, "step": 331860 }, { "epoch": 27.58, "learning_rate": 3.235983704237452e-07, "loss": 0.7057, "step": 331870 }, { "epoch": 27.59, "learning_rate": 3.234875148962115e-07, "loss": 0.7287, "step": 331880 }, { "epoch": 27.59, "learning_rate": 3.2337665936867774e-07, "loss": 0.7434, "step": 331890 }, { "epoch": 27.59, "learning_rate": 3.23265803841144e-07, "loss": 0.7413, "step": 331900 }, { "epoch": 27.59, "learning_rate": 3.231549483136103e-07, "loss": 0.7201, "step": 331910 }, { "epoch": 27.59, "learning_rate": 3.230440927860765e-07, "loss": 0.7103, "step": 331920 }, { "epoch": 27.59, "learning_rate": 3.2293323725854276e-07, "loss": 0.7535, "step": 331930 }, { "epoch": 27.59, "learning_rate": 3.2282238173100906e-07, "loss": 0.7059, "step": 331940 }, { "epoch": 27.59, "learning_rate": 3.227115262034753e-07, "loss": 0.783, "step": 331950 }, { "epoch": 27.59, "learning_rate": 3.2260067067594154e-07, "loss": 0.7227, "step": 331960 }, { "epoch": 27.59, "learning_rate": 3.2248981514840784e-07, "loss": 0.7152, "step": 331970 }, { "epoch": 27.59, "learning_rate": 3.223789596208741e-07, "loss": 0.7029, "step": 331980 }, { "epoch": 27.59, "learning_rate": 3.222681040933403e-07, "loss": 0.7349, "step": 331990 }, { "epoch": 27.6, "learning_rate": 3.221572485658066e-07, "loss": 0.7969, "step": 332000 }, { "epoch": 27.6, "learning_rate": 3.2204639303827286e-07, "loss": 0.7254, "step": 332010 }, { "epoch": 27.6, "learning_rate": 3.219355375107391e-07, "loss": 0.702, "step": 332020 }, { "epoch": 27.6, "learning_rate": 3.218246819832054e-07, "loss": 0.6814, "step": 332030 }, { "epoch": 27.6, "learning_rate": 3.2171382645567164e-07, "loss": 0.7284, "step": 332040 }, { "epoch": 27.6, "learning_rate": 3.216029709281379e-07, "loss": 0.745, "step": 332050 }, { "epoch": 27.6, "learning_rate": 3.214921154006042e-07, "loss": 0.6612, "step": 332060 }, { "epoch": 27.6, "learning_rate": 3.213812598730704e-07, "loss": 0.708, "step": 332070 }, { "epoch": 27.6, "learning_rate": 3.2127040434553666e-07, "loss": 0.7271, "step": 332080 }, { "epoch": 27.6, "learning_rate": 3.2115954881800296e-07, "loss": 0.7533, "step": 332090 }, { "epoch": 27.6, "learning_rate": 3.210486932904692e-07, "loss": 0.7332, "step": 332100 }, { "epoch": 27.6, "learning_rate": 3.2093783776293544e-07, "loss": 0.7038, "step": 332110 }, { "epoch": 27.61, "learning_rate": 3.2082698223540174e-07, "loss": 0.8004, "step": 332120 }, { "epoch": 27.61, "learning_rate": 3.20716126707868e-07, "loss": 0.7295, "step": 332130 }, { "epoch": 27.61, "learning_rate": 3.206052711803342e-07, "loss": 0.7569, "step": 332140 }, { "epoch": 27.61, "learning_rate": 3.204944156528005e-07, "loss": 0.7052, "step": 332150 }, { "epoch": 27.61, "learning_rate": 3.2038356012526676e-07, "loss": 0.7013, "step": 332160 }, { "epoch": 27.61, "learning_rate": 3.20272704597733e-07, "loss": 0.7759, "step": 332170 }, { "epoch": 27.61, "learning_rate": 3.201618490701993e-07, "loss": 0.7195, "step": 332180 }, { "epoch": 27.61, "learning_rate": 3.2005099354266554e-07, "loss": 0.7588, "step": 332190 }, { "epoch": 27.61, "learning_rate": 3.1994013801513173e-07, "loss": 0.7541, "step": 332200 }, { "epoch": 27.61, "learning_rate": 3.19829282487598e-07, "loss": 0.709, "step": 332210 }, { "epoch": 27.61, "learning_rate": 3.1971842696006427e-07, "loss": 0.7241, "step": 332220 }, { "epoch": 27.61, "learning_rate": 3.196075714325305e-07, "loss": 0.7242, "step": 332230 }, { "epoch": 27.62, "learning_rate": 3.1949671590499675e-07, "loss": 0.7574, "step": 332240 }, { "epoch": 27.62, "learning_rate": 3.1938586037746305e-07, "loss": 0.7569, "step": 332250 }, { "epoch": 27.62, "learning_rate": 3.192750048499293e-07, "loss": 0.7285, "step": 332260 }, { "epoch": 27.62, "learning_rate": 3.1916414932239553e-07, "loss": 0.725, "step": 332270 }, { "epoch": 27.62, "learning_rate": 3.1905329379486183e-07, "loss": 0.6742, "step": 332280 }, { "epoch": 27.62, "learning_rate": 3.1894243826732807e-07, "loss": 0.706, "step": 332290 }, { "epoch": 27.62, "learning_rate": 3.188315827397943e-07, "loss": 0.7757, "step": 332300 }, { "epoch": 27.62, "learning_rate": 3.187207272122606e-07, "loss": 0.7446, "step": 332310 }, { "epoch": 27.62, "learning_rate": 3.1860987168472685e-07, "loss": 0.6964, "step": 332320 }, { "epoch": 27.62, "learning_rate": 3.184990161571931e-07, "loss": 0.7586, "step": 332330 }, { "epoch": 27.62, "learning_rate": 3.183881606296594e-07, "loss": 0.7999, "step": 332340 }, { "epoch": 27.62, "learning_rate": 3.1827730510212563e-07, "loss": 0.7711, "step": 332350 }, { "epoch": 27.63, "learning_rate": 3.1816644957459187e-07, "loss": 0.7253, "step": 332360 }, { "epoch": 27.63, "learning_rate": 3.1805559404705817e-07, "loss": 0.7611, "step": 332370 }, { "epoch": 27.63, "learning_rate": 3.179447385195244e-07, "loss": 0.7841, "step": 332380 }, { "epoch": 27.63, "learning_rate": 3.1783388299199065e-07, "loss": 0.7376, "step": 332390 }, { "epoch": 27.63, "learning_rate": 3.1772302746445695e-07, "loss": 0.7596, "step": 332400 }, { "epoch": 27.63, "learning_rate": 3.176121719369232e-07, "loss": 0.7362, "step": 332410 }, { "epoch": 27.63, "learning_rate": 3.1750131640938943e-07, "loss": 0.7212, "step": 332420 }, { "epoch": 27.63, "learning_rate": 3.1739046088185573e-07, "loss": 0.7387, "step": 332430 }, { "epoch": 27.63, "learning_rate": 3.1727960535432197e-07, "loss": 0.7499, "step": 332440 }, { "epoch": 27.63, "learning_rate": 3.171687498267882e-07, "loss": 0.6645, "step": 332450 }, { "epoch": 27.63, "learning_rate": 3.170578942992545e-07, "loss": 0.7536, "step": 332460 }, { "epoch": 27.63, "learning_rate": 3.1694703877172075e-07, "loss": 0.7144, "step": 332470 }, { "epoch": 27.64, "learning_rate": 3.16836183244187e-07, "loss": 0.6731, "step": 332480 }, { "epoch": 27.64, "learning_rate": 3.167253277166533e-07, "loss": 0.7476, "step": 332490 }, { "epoch": 27.64, "learning_rate": 3.1661447218911953e-07, "loss": 0.7361, "step": 332500 }, { "epoch": 27.64, "learning_rate": 3.165036166615858e-07, "loss": 0.7384, "step": 332510 }, { "epoch": 27.64, "learning_rate": 3.1639276113405207e-07, "loss": 0.7754, "step": 332520 }, { "epoch": 27.64, "learning_rate": 3.162819056065183e-07, "loss": 0.7133, "step": 332530 }, { "epoch": 27.64, "learning_rate": 3.1617105007898455e-07, "loss": 0.6876, "step": 332540 }, { "epoch": 27.64, "learning_rate": 3.1606019455145085e-07, "loss": 0.7492, "step": 332550 }, { "epoch": 27.64, "learning_rate": 3.159493390239171e-07, "loss": 0.7466, "step": 332560 }, { "epoch": 27.64, "learning_rate": 3.1583848349638333e-07, "loss": 0.7613, "step": 332570 }, { "epoch": 27.64, "learning_rate": 3.1572762796884963e-07, "loss": 0.722, "step": 332580 }, { "epoch": 27.64, "learning_rate": 3.1561677244131587e-07, "loss": 0.7202, "step": 332590 }, { "epoch": 27.65, "learning_rate": 3.155059169137821e-07, "loss": 0.7993, "step": 332600 }, { "epoch": 27.65, "learning_rate": 3.153950613862484e-07, "loss": 0.7151, "step": 332610 }, { "epoch": 27.65, "learning_rate": 3.152842058587146e-07, "loss": 0.7241, "step": 332620 }, { "epoch": 27.65, "learning_rate": 3.1517335033118084e-07, "loss": 0.7331, "step": 332630 }, { "epoch": 27.65, "learning_rate": 3.150624948036471e-07, "loss": 0.7198, "step": 332640 }, { "epoch": 27.65, "learning_rate": 3.149516392761134e-07, "loss": 0.7404, "step": 332650 }, { "epoch": 27.65, "learning_rate": 3.148407837485796e-07, "loss": 0.707, "step": 332660 }, { "epoch": 27.65, "learning_rate": 3.1472992822104586e-07, "loss": 0.6832, "step": 332670 }, { "epoch": 27.65, "learning_rate": 3.1461907269351216e-07, "loss": 0.6989, "step": 332680 }, { "epoch": 27.65, "learning_rate": 3.145082171659784e-07, "loss": 0.7722, "step": 332690 }, { "epoch": 27.65, "learning_rate": 3.1439736163844464e-07, "loss": 0.7499, "step": 332700 }, { "epoch": 27.65, "learning_rate": 3.1428650611091094e-07, "loss": 0.8928, "step": 332710 }, { "epoch": 27.66, "learning_rate": 3.141756505833772e-07, "loss": 0.6805, "step": 332720 }, { "epoch": 27.66, "learning_rate": 3.140647950558434e-07, "loss": 0.7089, "step": 332730 }, { "epoch": 27.66, "learning_rate": 3.139539395283097e-07, "loss": 0.7053, "step": 332740 }, { "epoch": 27.66, "learning_rate": 3.1384308400077596e-07, "loss": 0.7647, "step": 332750 }, { "epoch": 27.66, "learning_rate": 3.137322284732422e-07, "loss": 0.7262, "step": 332760 }, { "epoch": 27.66, "learning_rate": 3.136213729457085e-07, "loss": 0.7608, "step": 332770 }, { "epoch": 27.66, "learning_rate": 3.1351051741817474e-07, "loss": 0.6701, "step": 332780 }, { "epoch": 27.66, "learning_rate": 3.13399661890641e-07, "loss": 0.7197, "step": 332790 }, { "epoch": 27.66, "learning_rate": 3.132888063631073e-07, "loss": 0.7966, "step": 332800 }, { "epoch": 27.66, "learning_rate": 3.131779508355735e-07, "loss": 0.7391, "step": 332810 }, { "epoch": 27.66, "learning_rate": 3.1306709530803976e-07, "loss": 0.754, "step": 332820 }, { "epoch": 27.66, "learning_rate": 3.1295623978050606e-07, "loss": 0.7262, "step": 332830 }, { "epoch": 27.67, "learning_rate": 3.128453842529723e-07, "loss": 0.7708, "step": 332840 }, { "epoch": 27.67, "learning_rate": 3.1273452872543854e-07, "loss": 0.7887, "step": 332850 }, { "epoch": 27.67, "learning_rate": 3.1262367319790484e-07, "loss": 0.7148, "step": 332860 }, { "epoch": 27.67, "learning_rate": 3.125128176703711e-07, "loss": 0.7643, "step": 332870 }, { "epoch": 27.67, "learning_rate": 3.124019621428373e-07, "loss": 0.6935, "step": 332880 }, { "epoch": 27.67, "learning_rate": 3.122911066153036e-07, "loss": 0.7634, "step": 332890 }, { "epoch": 27.67, "learning_rate": 3.1218025108776986e-07, "loss": 0.7101, "step": 332900 }, { "epoch": 27.67, "learning_rate": 3.120693955602361e-07, "loss": 0.6623, "step": 332910 }, { "epoch": 27.67, "learning_rate": 3.119585400327024e-07, "loss": 0.7019, "step": 332920 }, { "epoch": 27.67, "learning_rate": 3.1184768450516864e-07, "loss": 0.7632, "step": 332930 }, { "epoch": 27.67, "learning_rate": 3.117368289776349e-07, "loss": 0.7005, "step": 332940 }, { "epoch": 27.67, "learning_rate": 3.116259734501012e-07, "loss": 0.7802, "step": 332950 }, { "epoch": 27.68, "learning_rate": 3.115151179225674e-07, "loss": 0.7336, "step": 332960 }, { "epoch": 27.68, "learning_rate": 3.1140426239503367e-07, "loss": 0.7374, "step": 332970 }, { "epoch": 27.68, "learning_rate": 3.1129340686749996e-07, "loss": 0.7447, "step": 332980 }, { "epoch": 27.68, "learning_rate": 3.111825513399662e-07, "loss": 0.7638, "step": 332990 }, { "epoch": 27.68, "learning_rate": 3.1107169581243245e-07, "loss": 0.7646, "step": 333000 }, { "epoch": 27.68, "learning_rate": 3.1096084028489874e-07, "loss": 0.7173, "step": 333010 }, { "epoch": 27.68, "learning_rate": 3.10849984757365e-07, "loss": 0.7644, "step": 333020 }, { "epoch": 27.68, "learning_rate": 3.1073912922983117e-07, "loss": 0.7206, "step": 333030 }, { "epoch": 27.68, "learning_rate": 3.1062827370229747e-07, "loss": 0.7156, "step": 333040 }, { "epoch": 27.68, "learning_rate": 3.105174181747637e-07, "loss": 0.7199, "step": 333050 }, { "epoch": 27.68, "learning_rate": 3.1040656264722995e-07, "loss": 0.7388, "step": 333060 }, { "epoch": 27.68, "learning_rate": 3.102957071196962e-07, "loss": 0.7327, "step": 333070 }, { "epoch": 27.69, "learning_rate": 3.101848515921625e-07, "loss": 0.6959, "step": 333080 }, { "epoch": 27.69, "learning_rate": 3.1007399606462873e-07, "loss": 0.7764, "step": 333090 }, { "epoch": 27.69, "learning_rate": 3.09963140537095e-07, "loss": 0.7368, "step": 333100 }, { "epoch": 27.69, "learning_rate": 3.0985228500956127e-07, "loss": 0.6577, "step": 333110 }, { "epoch": 27.69, "learning_rate": 3.097414294820275e-07, "loss": 0.7567, "step": 333120 }, { "epoch": 27.69, "learning_rate": 3.0963057395449376e-07, "loss": 0.7151, "step": 333130 }, { "epoch": 27.69, "learning_rate": 3.0951971842696005e-07, "loss": 0.7428, "step": 333140 }, { "epoch": 27.69, "learning_rate": 3.094088628994263e-07, "loss": 0.784, "step": 333150 }, { "epoch": 27.69, "learning_rate": 3.0929800737189254e-07, "loss": 0.6959, "step": 333160 }, { "epoch": 27.69, "learning_rate": 3.0918715184435883e-07, "loss": 0.7509, "step": 333170 }, { "epoch": 27.69, "learning_rate": 3.0907629631682507e-07, "loss": 0.7595, "step": 333180 }, { "epoch": 27.69, "learning_rate": 3.089654407892913e-07, "loss": 0.811, "step": 333190 }, { "epoch": 27.7, "learning_rate": 3.088545852617576e-07, "loss": 0.7383, "step": 333200 }, { "epoch": 27.7, "learning_rate": 3.0874372973422385e-07, "loss": 0.6523, "step": 333210 }, { "epoch": 27.7, "learning_rate": 3.086328742066901e-07, "loss": 0.759, "step": 333220 }, { "epoch": 27.7, "learning_rate": 3.085220186791564e-07, "loss": 0.6835, "step": 333230 }, { "epoch": 27.7, "learning_rate": 3.0841116315162263e-07, "loss": 0.6799, "step": 333240 }, { "epoch": 27.7, "learning_rate": 3.083003076240889e-07, "loss": 0.7943, "step": 333250 }, { "epoch": 27.7, "learning_rate": 3.0818945209655517e-07, "loss": 0.7066, "step": 333260 }, { "epoch": 27.7, "learning_rate": 3.080785965690214e-07, "loss": 0.6648, "step": 333270 }, { "epoch": 27.7, "learning_rate": 3.0796774104148766e-07, "loss": 0.7145, "step": 333280 }, { "epoch": 27.7, "learning_rate": 3.0785688551395395e-07, "loss": 0.7944, "step": 333290 }, { "epoch": 27.7, "learning_rate": 3.077460299864202e-07, "loss": 0.7036, "step": 333300 }, { "epoch": 27.7, "learning_rate": 3.0763517445888644e-07, "loss": 0.7036, "step": 333310 }, { "epoch": 27.71, "learning_rate": 3.0752431893135273e-07, "loss": 0.6764, "step": 333320 }, { "epoch": 27.71, "learning_rate": 3.07413463403819e-07, "loss": 0.7031, "step": 333330 }, { "epoch": 27.71, "learning_rate": 3.073026078762852e-07, "loss": 0.6543, "step": 333340 }, { "epoch": 27.71, "learning_rate": 3.071917523487515e-07, "loss": 0.8063, "step": 333350 }, { "epoch": 27.71, "learning_rate": 3.0708089682121775e-07, "loss": 0.6858, "step": 333360 }, { "epoch": 27.71, "learning_rate": 3.06970041293684e-07, "loss": 0.7503, "step": 333370 }, { "epoch": 27.71, "learning_rate": 3.068591857661503e-07, "loss": 0.6727, "step": 333380 }, { "epoch": 27.71, "learning_rate": 3.0674833023861653e-07, "loss": 0.7116, "step": 333390 }, { "epoch": 27.71, "learning_rate": 3.066374747110828e-07, "loss": 0.7278, "step": 333400 }, { "epoch": 27.71, "learning_rate": 3.0652661918354907e-07, "loss": 0.7059, "step": 333410 }, { "epoch": 27.71, "learning_rate": 3.064157636560153e-07, "loss": 0.6982, "step": 333420 }, { "epoch": 27.71, "learning_rate": 3.0630490812848156e-07, "loss": 0.7636, "step": 333430 }, { "epoch": 27.72, "learning_rate": 3.0619405260094785e-07, "loss": 0.7501, "step": 333440 }, { "epoch": 27.72, "learning_rate": 3.0608319707341404e-07, "loss": 0.7268, "step": 333450 }, { "epoch": 27.72, "learning_rate": 3.059723415458803e-07, "loss": 0.7625, "step": 333460 }, { "epoch": 27.72, "learning_rate": 3.058614860183465e-07, "loss": 0.7112, "step": 333470 }, { "epoch": 27.72, "learning_rate": 3.057506304908128e-07, "loss": 0.6948, "step": 333480 }, { "epoch": 27.72, "learning_rate": 3.0563977496327906e-07, "loss": 0.8128, "step": 333490 }, { "epoch": 27.72, "learning_rate": 3.055289194357453e-07, "loss": 0.7654, "step": 333500 }, { "epoch": 27.72, "learning_rate": 3.054180639082116e-07, "loss": 0.7216, "step": 333510 }, { "epoch": 27.72, "learning_rate": 3.0530720838067784e-07, "loss": 0.6943, "step": 333520 }, { "epoch": 27.72, "learning_rate": 3.051963528531441e-07, "loss": 0.7609, "step": 333530 }, { "epoch": 27.72, "learning_rate": 3.050854973256104e-07, "loss": 0.733, "step": 333540 }, { "epoch": 27.72, "learning_rate": 3.049746417980766e-07, "loss": 0.7585, "step": 333550 }, { "epoch": 27.73, "learning_rate": 3.0486378627054287e-07, "loss": 0.7209, "step": 333560 }, { "epoch": 27.73, "learning_rate": 3.0475293074300916e-07, "loss": 0.7582, "step": 333570 }, { "epoch": 27.73, "learning_rate": 3.046420752154754e-07, "loss": 0.7511, "step": 333580 }, { "epoch": 27.73, "learning_rate": 3.0453121968794165e-07, "loss": 0.7106, "step": 333590 }, { "epoch": 27.73, "learning_rate": 3.0442036416040794e-07, "loss": 0.6943, "step": 333600 }, { "epoch": 27.73, "learning_rate": 3.043095086328742e-07, "loss": 0.7285, "step": 333610 }, { "epoch": 27.73, "learning_rate": 3.0419865310534043e-07, "loss": 0.6956, "step": 333620 }, { "epoch": 27.73, "learning_rate": 3.040877975778067e-07, "loss": 0.7466, "step": 333630 }, { "epoch": 27.73, "learning_rate": 3.0397694205027296e-07, "loss": 0.7422, "step": 333640 }, { "epoch": 27.73, "learning_rate": 3.038660865227392e-07, "loss": 0.7198, "step": 333650 }, { "epoch": 27.73, "learning_rate": 3.037552309952055e-07, "loss": 0.7501, "step": 333660 }, { "epoch": 27.73, "learning_rate": 3.0364437546767174e-07, "loss": 0.7729, "step": 333670 }, { "epoch": 27.74, "learning_rate": 3.03533519940138e-07, "loss": 0.7112, "step": 333680 }, { "epoch": 27.74, "learning_rate": 3.034226644126043e-07, "loss": 0.7649, "step": 333690 }, { "epoch": 27.74, "learning_rate": 3.033118088850705e-07, "loss": 0.7204, "step": 333700 }, { "epoch": 27.74, "learning_rate": 3.0320095335753677e-07, "loss": 0.7281, "step": 333710 }, { "epoch": 27.74, "learning_rate": 3.0309009783000306e-07, "loss": 0.7182, "step": 333720 }, { "epoch": 27.74, "learning_rate": 3.029792423024693e-07, "loss": 0.7464, "step": 333730 }, { "epoch": 27.74, "learning_rate": 3.0286838677493555e-07, "loss": 0.7563, "step": 333740 }, { "epoch": 27.74, "learning_rate": 3.0275753124740184e-07, "loss": 0.7775, "step": 333750 }, { "epoch": 27.74, "learning_rate": 3.026466757198681e-07, "loss": 0.7343, "step": 333760 }, { "epoch": 27.74, "learning_rate": 3.0253582019233433e-07, "loss": 0.7057, "step": 333770 }, { "epoch": 27.74, "learning_rate": 3.024249646648006e-07, "loss": 0.7597, "step": 333780 }, { "epoch": 27.74, "learning_rate": 3.0231410913726687e-07, "loss": 0.8277, "step": 333790 }, { "epoch": 27.74, "learning_rate": 3.022032536097331e-07, "loss": 0.7856, "step": 333800 }, { "epoch": 27.75, "learning_rate": 3.020923980821994e-07, "loss": 0.6499, "step": 333810 }, { "epoch": 27.75, "learning_rate": 3.0198154255466565e-07, "loss": 0.7088, "step": 333820 }, { "epoch": 27.75, "learning_rate": 3.018706870271319e-07, "loss": 0.7509, "step": 333830 }, { "epoch": 27.75, "learning_rate": 3.017598314995982e-07, "loss": 0.7661, "step": 333840 }, { "epoch": 27.75, "learning_rate": 3.016489759720644e-07, "loss": 0.7197, "step": 333850 }, { "epoch": 27.75, "learning_rate": 3.015381204445306e-07, "loss": 0.6947, "step": 333860 }, { "epoch": 27.75, "learning_rate": 3.0142726491699696e-07, "loss": 0.6897, "step": 333870 }, { "epoch": 27.75, "learning_rate": 3.0131640938946315e-07, "loss": 0.749, "step": 333880 }, { "epoch": 27.75, "learning_rate": 3.012055538619294e-07, "loss": 0.676, "step": 333890 }, { "epoch": 27.75, "learning_rate": 3.0109469833439564e-07, "loss": 0.7665, "step": 333900 }, { "epoch": 27.75, "learning_rate": 3.0098384280686193e-07, "loss": 0.7433, "step": 333910 }, { "epoch": 27.75, "learning_rate": 3.008729872793282e-07, "loss": 0.6994, "step": 333920 }, { "epoch": 27.76, "learning_rate": 3.007621317517944e-07, "loss": 0.7126, "step": 333930 }, { "epoch": 27.76, "learning_rate": 3.006512762242607e-07, "loss": 0.7232, "step": 333940 }, { "epoch": 27.76, "learning_rate": 3.0054042069672696e-07, "loss": 0.7889, "step": 333950 }, { "epoch": 27.76, "learning_rate": 3.004295651691932e-07, "loss": 0.7305, "step": 333960 }, { "epoch": 27.76, "learning_rate": 3.003187096416595e-07, "loss": 0.7239, "step": 333970 }, { "epoch": 27.76, "learning_rate": 3.0020785411412574e-07, "loss": 0.7221, "step": 333980 }, { "epoch": 27.76, "learning_rate": 3.00096998586592e-07, "loss": 0.7683, "step": 333990 }, { "epoch": 27.76, "learning_rate": 2.9998614305905827e-07, "loss": 0.7258, "step": 334000 }, { "epoch": 27.76, "learning_rate": 2.998752875315245e-07, "loss": 0.7041, "step": 334010 }, { "epoch": 27.76, "learning_rate": 2.9976443200399076e-07, "loss": 0.6849, "step": 334020 }, { "epoch": 27.76, "learning_rate": 2.9965357647645705e-07, "loss": 0.7382, "step": 334030 }, { "epoch": 27.76, "learning_rate": 2.995427209489233e-07, "loss": 0.7782, "step": 334040 }, { "epoch": 27.77, "learning_rate": 2.9943186542138954e-07, "loss": 0.7353, "step": 334050 }, { "epoch": 27.77, "learning_rate": 2.9932100989385583e-07, "loss": 0.7119, "step": 334060 }, { "epoch": 27.77, "learning_rate": 2.992101543663221e-07, "loss": 0.7193, "step": 334070 }, { "epoch": 27.77, "learning_rate": 2.990992988387883e-07, "loss": 0.7311, "step": 334080 }, { "epoch": 27.77, "learning_rate": 2.989884433112546e-07, "loss": 0.713, "step": 334090 }, { "epoch": 27.77, "learning_rate": 2.9887758778372086e-07, "loss": 0.8044, "step": 334100 }, { "epoch": 27.77, "learning_rate": 2.987667322561871e-07, "loss": 0.7622, "step": 334110 }, { "epoch": 27.77, "learning_rate": 2.986558767286534e-07, "loss": 0.7069, "step": 334120 }, { "epoch": 27.77, "learning_rate": 2.9854502120111964e-07, "loss": 0.7103, "step": 334130 }, { "epoch": 27.77, "learning_rate": 2.984341656735859e-07, "loss": 0.6705, "step": 334140 }, { "epoch": 27.77, "learning_rate": 2.983233101460522e-07, "loss": 0.7941, "step": 334150 }, { "epoch": 27.77, "learning_rate": 2.982124546185184e-07, "loss": 0.9042, "step": 334160 }, { "epoch": 27.78, "learning_rate": 2.9810159909098466e-07, "loss": 0.682, "step": 334170 }, { "epoch": 27.78, "learning_rate": 2.9799074356345095e-07, "loss": 0.7703, "step": 334180 }, { "epoch": 27.78, "learning_rate": 2.978798880359172e-07, "loss": 0.7314, "step": 334190 }, { "epoch": 27.78, "learning_rate": 2.9776903250838344e-07, "loss": 0.7677, "step": 334200 }, { "epoch": 27.78, "learning_rate": 2.9765817698084973e-07, "loss": 0.7035, "step": 334210 }, { "epoch": 27.78, "learning_rate": 2.97547321453316e-07, "loss": 0.7373, "step": 334220 }, { "epoch": 27.78, "learning_rate": 2.974364659257822e-07, "loss": 0.7433, "step": 334230 }, { "epoch": 27.78, "learning_rate": 2.973256103982485e-07, "loss": 0.7572, "step": 334240 }, { "epoch": 27.78, "learning_rate": 2.9721475487071476e-07, "loss": 0.7532, "step": 334250 }, { "epoch": 27.78, "learning_rate": 2.97103899343181e-07, "loss": 0.6956, "step": 334260 }, { "epoch": 27.78, "learning_rate": 2.969930438156473e-07, "loss": 0.748, "step": 334270 }, { "epoch": 27.78, "learning_rate": 2.9688218828811354e-07, "loss": 0.7063, "step": 334280 }, { "epoch": 27.79, "learning_rate": 2.967713327605797e-07, "loss": 0.7481, "step": 334290 }, { "epoch": 27.79, "learning_rate": 2.96660477233046e-07, "loss": 0.7606, "step": 334300 }, { "epoch": 27.79, "learning_rate": 2.9654962170551226e-07, "loss": 0.6923, "step": 334310 }, { "epoch": 27.79, "learning_rate": 2.964387661779785e-07, "loss": 0.734, "step": 334320 }, { "epoch": 27.79, "learning_rate": 2.9632791065044475e-07, "loss": 0.7359, "step": 334330 }, { "epoch": 27.79, "learning_rate": 2.9621705512291104e-07, "loss": 0.7555, "step": 334340 }, { "epoch": 27.79, "learning_rate": 2.961061995953773e-07, "loss": 0.7194, "step": 334350 }, { "epoch": 27.79, "learning_rate": 2.9599534406784353e-07, "loss": 0.7285, "step": 334360 }, { "epoch": 27.79, "learning_rate": 2.958844885403098e-07, "loss": 0.7543, "step": 334370 }, { "epoch": 27.79, "learning_rate": 2.9577363301277607e-07, "loss": 0.7383, "step": 334380 }, { "epoch": 27.79, "learning_rate": 2.956627774852423e-07, "loss": 0.7384, "step": 334390 }, { "epoch": 27.79, "learning_rate": 2.955519219577086e-07, "loss": 0.7486, "step": 334400 }, { "epoch": 27.8, "learning_rate": 2.9544106643017485e-07, "loss": 0.7359, "step": 334410 }, { "epoch": 27.8, "learning_rate": 2.953302109026411e-07, "loss": 0.7576, "step": 334420 }, { "epoch": 27.8, "learning_rate": 2.952193553751074e-07, "loss": 0.7586, "step": 334430 }, { "epoch": 27.8, "learning_rate": 2.9510849984757363e-07, "loss": 0.725, "step": 334440 }, { "epoch": 27.8, "learning_rate": 2.9499764432003987e-07, "loss": 0.7588, "step": 334450 }, { "epoch": 27.8, "learning_rate": 2.9488678879250616e-07, "loss": 0.7204, "step": 334460 }, { "epoch": 27.8, "learning_rate": 2.947759332649724e-07, "loss": 0.7154, "step": 334470 }, { "epoch": 27.8, "learning_rate": 2.9466507773743865e-07, "loss": 0.7158, "step": 334480 }, { "epoch": 27.8, "learning_rate": 2.9455422220990494e-07, "loss": 0.7403, "step": 334490 }, { "epoch": 27.8, "learning_rate": 2.944433666823712e-07, "loss": 0.7429, "step": 334500 }, { "epoch": 27.8, "learning_rate": 2.9433251115483743e-07, "loss": 0.7106, "step": 334510 }, { "epoch": 27.8, "learning_rate": 2.942216556273037e-07, "loss": 0.7435, "step": 334520 }, { "epoch": 27.81, "learning_rate": 2.9411080009976997e-07, "loss": 0.765, "step": 334530 }, { "epoch": 27.81, "learning_rate": 2.939999445722362e-07, "loss": 0.7837, "step": 334540 }, { "epoch": 27.81, "learning_rate": 2.938890890447025e-07, "loss": 0.7078, "step": 334550 }, { "epoch": 27.81, "learning_rate": 2.9377823351716875e-07, "loss": 0.7144, "step": 334560 }, { "epoch": 27.81, "learning_rate": 2.93667377989635e-07, "loss": 0.7475, "step": 334570 }, { "epoch": 27.81, "learning_rate": 2.935565224621013e-07, "loss": 0.7241, "step": 334580 }, { "epoch": 27.81, "learning_rate": 2.9344566693456753e-07, "loss": 0.7292, "step": 334590 }, { "epoch": 27.81, "learning_rate": 2.9333481140703377e-07, "loss": 0.749, "step": 334600 }, { "epoch": 27.81, "learning_rate": 2.9322395587950007e-07, "loss": 0.7309, "step": 334610 }, { "epoch": 27.81, "learning_rate": 2.931131003519663e-07, "loss": 0.6889, "step": 334620 }, { "epoch": 27.81, "learning_rate": 2.9300224482443255e-07, "loss": 0.7423, "step": 334630 }, { "epoch": 27.81, "learning_rate": 2.9289138929689885e-07, "loss": 0.7511, "step": 334640 }, { "epoch": 27.82, "learning_rate": 2.927805337693651e-07, "loss": 0.7278, "step": 334650 }, { "epoch": 27.82, "learning_rate": 2.9266967824183133e-07, "loss": 0.7634, "step": 334660 }, { "epoch": 27.82, "learning_rate": 2.925588227142976e-07, "loss": 0.7257, "step": 334670 }, { "epoch": 27.82, "learning_rate": 2.9244796718676387e-07, "loss": 0.7693, "step": 334680 }, { "epoch": 27.82, "learning_rate": 2.923371116592301e-07, "loss": 0.7525, "step": 334690 }, { "epoch": 27.82, "learning_rate": 2.922262561316964e-07, "loss": 0.6872, "step": 334700 }, { "epoch": 27.82, "learning_rate": 2.921154006041626e-07, "loss": 0.7654, "step": 334710 }, { "epoch": 27.82, "learning_rate": 2.9200454507662884e-07, "loss": 0.7366, "step": 334720 }, { "epoch": 27.82, "learning_rate": 2.918936895490951e-07, "loss": 0.7698, "step": 334730 }, { "epoch": 27.82, "learning_rate": 2.917828340215614e-07, "loss": 0.791, "step": 334740 }, { "epoch": 27.82, "learning_rate": 2.916719784940276e-07, "loss": 0.7529, "step": 334750 }, { "epoch": 27.82, "learning_rate": 2.9156112296649386e-07, "loss": 0.7488, "step": 334760 }, { "epoch": 27.83, "learning_rate": 2.9145026743896016e-07, "loss": 0.7467, "step": 334770 }, { "epoch": 27.83, "learning_rate": 2.913394119114264e-07, "loss": 0.6946, "step": 334780 }, { "epoch": 27.83, "learning_rate": 2.9122855638389264e-07, "loss": 0.7326, "step": 334790 }, { "epoch": 27.83, "learning_rate": 2.9111770085635894e-07, "loss": 0.7627, "step": 334800 }, { "epoch": 27.83, "learning_rate": 2.910068453288252e-07, "loss": 0.7557, "step": 334810 }, { "epoch": 27.83, "learning_rate": 2.908959898012914e-07, "loss": 0.7308, "step": 334820 }, { "epoch": 27.83, "learning_rate": 2.907851342737577e-07, "loss": 0.696, "step": 334830 }, { "epoch": 27.83, "learning_rate": 2.9067427874622396e-07, "loss": 0.7193, "step": 334840 }, { "epoch": 27.83, "learning_rate": 2.905634232186902e-07, "loss": 0.7233, "step": 334850 }, { "epoch": 27.83, "learning_rate": 2.904525676911565e-07, "loss": 0.7297, "step": 334860 }, { "epoch": 27.83, "learning_rate": 2.9034171216362274e-07, "loss": 0.7518, "step": 334870 }, { "epoch": 27.83, "learning_rate": 2.90230856636089e-07, "loss": 0.6423, "step": 334880 }, { "epoch": 27.84, "learning_rate": 2.901200011085553e-07, "loss": 0.7182, "step": 334890 }, { "epoch": 27.84, "learning_rate": 2.900091455810215e-07, "loss": 0.7662, "step": 334900 }, { "epoch": 27.84, "learning_rate": 2.8989829005348776e-07, "loss": 0.7674, "step": 334910 }, { "epoch": 27.84, "learning_rate": 2.8978743452595406e-07, "loss": 0.706, "step": 334920 }, { "epoch": 27.84, "learning_rate": 2.896765789984203e-07, "loss": 0.7737, "step": 334930 }, { "epoch": 27.84, "learning_rate": 2.8956572347088654e-07, "loss": 0.7237, "step": 334940 }, { "epoch": 27.84, "learning_rate": 2.8945486794335284e-07, "loss": 0.694, "step": 334950 }, { "epoch": 27.84, "learning_rate": 2.893440124158191e-07, "loss": 0.6883, "step": 334960 }, { "epoch": 27.84, "learning_rate": 2.892331568882853e-07, "loss": 0.7418, "step": 334970 }, { "epoch": 27.84, "learning_rate": 2.891223013607516e-07, "loss": 0.704, "step": 334980 }, { "epoch": 27.84, "learning_rate": 2.8901144583321786e-07, "loss": 0.7767, "step": 334990 }, { "epoch": 27.84, "learning_rate": 2.889005903056841e-07, "loss": 0.7548, "step": 335000 }, { "epoch": 27.85, "learning_rate": 2.887897347781504e-07, "loss": 0.7665, "step": 335010 }, { "epoch": 27.85, "learning_rate": 2.8867887925061664e-07, "loss": 0.7299, "step": 335020 }, { "epoch": 27.85, "learning_rate": 2.885680237230829e-07, "loss": 0.712, "step": 335030 }, { "epoch": 27.85, "learning_rate": 2.884571681955492e-07, "loss": 0.8051, "step": 335040 }, { "epoch": 27.85, "learning_rate": 2.883463126680154e-07, "loss": 0.7631, "step": 335050 }, { "epoch": 27.85, "learning_rate": 2.8823545714048166e-07, "loss": 0.7329, "step": 335060 }, { "epoch": 27.85, "learning_rate": 2.8812460161294796e-07, "loss": 0.6671, "step": 335070 }, { "epoch": 27.85, "learning_rate": 2.880137460854142e-07, "loss": 0.7596, "step": 335080 }, { "epoch": 27.85, "learning_rate": 2.8790289055788044e-07, "loss": 0.6905, "step": 335090 }, { "epoch": 27.85, "learning_rate": 2.8779203503034674e-07, "loss": 0.7958, "step": 335100 }, { "epoch": 27.85, "learning_rate": 2.87681179502813e-07, "loss": 0.7031, "step": 335110 }, { "epoch": 27.85, "learning_rate": 2.8757032397527917e-07, "loss": 0.7449, "step": 335120 }, { "epoch": 27.86, "learning_rate": 2.8745946844774546e-07, "loss": 0.7267, "step": 335130 }, { "epoch": 27.86, "learning_rate": 2.873486129202117e-07, "loss": 0.7963, "step": 335140 }, { "epoch": 27.86, "learning_rate": 2.8723775739267795e-07, "loss": 0.776, "step": 335150 }, { "epoch": 27.86, "learning_rate": 2.871269018651442e-07, "loss": 0.6858, "step": 335160 }, { "epoch": 27.86, "learning_rate": 2.870160463376105e-07, "loss": 0.6545, "step": 335170 }, { "epoch": 27.86, "learning_rate": 2.8690519081007673e-07, "loss": 0.6916, "step": 335180 }, { "epoch": 27.86, "learning_rate": 2.8679433528254297e-07, "loss": 0.725, "step": 335190 }, { "epoch": 27.86, "learning_rate": 2.8668347975500927e-07, "loss": 0.8287, "step": 335200 }, { "epoch": 27.86, "learning_rate": 2.865726242274755e-07, "loss": 0.7058, "step": 335210 }, { "epoch": 27.86, "learning_rate": 2.8646176869994175e-07, "loss": 0.757, "step": 335220 }, { "epoch": 27.86, "learning_rate": 2.8635091317240805e-07, "loss": 0.7024, "step": 335230 }, { "epoch": 27.86, "learning_rate": 2.862400576448743e-07, "loss": 0.7544, "step": 335240 }, { "epoch": 27.87, "learning_rate": 2.8612920211734053e-07, "loss": 0.7213, "step": 335250 }, { "epoch": 27.87, "learning_rate": 2.8601834658980683e-07, "loss": 0.7637, "step": 335260 }, { "epoch": 27.87, "learning_rate": 2.8590749106227307e-07, "loss": 0.7372, "step": 335270 }, { "epoch": 27.87, "learning_rate": 2.857966355347393e-07, "loss": 0.7681, "step": 335280 }, { "epoch": 27.87, "learning_rate": 2.856857800072056e-07, "loss": 0.7543, "step": 335290 }, { "epoch": 27.87, "learning_rate": 2.8557492447967185e-07, "loss": 0.7794, "step": 335300 }, { "epoch": 27.87, "learning_rate": 2.854640689521381e-07, "loss": 0.7068, "step": 335310 }, { "epoch": 27.87, "learning_rate": 2.853532134246044e-07, "loss": 0.6212, "step": 335320 }, { "epoch": 27.87, "learning_rate": 2.8524235789707063e-07, "loss": 0.7686, "step": 335330 }, { "epoch": 27.87, "learning_rate": 2.8513150236953687e-07, "loss": 0.7004, "step": 335340 }, { "epoch": 27.87, "learning_rate": 2.8502064684200317e-07, "loss": 0.7578, "step": 335350 }, { "epoch": 27.87, "learning_rate": 2.849097913144694e-07, "loss": 0.7737, "step": 335360 }, { "epoch": 27.88, "learning_rate": 2.8479893578693565e-07, "loss": 0.7218, "step": 335370 }, { "epoch": 27.88, "learning_rate": 2.8468808025940195e-07, "loss": 0.723, "step": 335380 }, { "epoch": 27.88, "learning_rate": 2.845772247318682e-07, "loss": 0.7396, "step": 335390 }, { "epoch": 27.88, "learning_rate": 2.8446636920433443e-07, "loss": 0.6834, "step": 335400 }, { "epoch": 27.88, "learning_rate": 2.8435551367680073e-07, "loss": 0.7251, "step": 335410 }, { "epoch": 27.88, "learning_rate": 2.8424465814926697e-07, "loss": 0.663, "step": 335420 }, { "epoch": 27.88, "learning_rate": 2.841338026217332e-07, "loss": 0.6848, "step": 335430 }, { "epoch": 27.88, "learning_rate": 2.840229470941995e-07, "loss": 0.7457, "step": 335440 }, { "epoch": 27.88, "learning_rate": 2.8391209156666575e-07, "loss": 0.7347, "step": 335450 }, { "epoch": 27.88, "learning_rate": 2.83801236039132e-07, "loss": 0.7227, "step": 335460 }, { "epoch": 27.88, "learning_rate": 2.836903805115983e-07, "loss": 0.7371, "step": 335470 }, { "epoch": 27.88, "learning_rate": 2.8357952498406453e-07, "loss": 0.7237, "step": 335480 }, { "epoch": 27.89, "learning_rate": 2.8346866945653077e-07, "loss": 0.7306, "step": 335490 }, { "epoch": 27.89, "learning_rate": 2.8335781392899707e-07, "loss": 0.7216, "step": 335500 }, { "epoch": 27.89, "learning_rate": 2.832469584014633e-07, "loss": 0.7552, "step": 335510 }, { "epoch": 27.89, "learning_rate": 2.8313610287392955e-07, "loss": 0.7736, "step": 335520 }, { "epoch": 27.89, "learning_rate": 2.8302524734639585e-07, "loss": 0.7004, "step": 335530 }, { "epoch": 27.89, "learning_rate": 2.8291439181886204e-07, "loss": 0.7307, "step": 335540 }, { "epoch": 27.89, "learning_rate": 2.828035362913283e-07, "loss": 0.7941, "step": 335550 }, { "epoch": 27.89, "learning_rate": 2.826926807637945e-07, "loss": 0.7479, "step": 335560 }, { "epoch": 27.89, "learning_rate": 2.825818252362608e-07, "loss": 0.7538, "step": 335570 }, { "epoch": 27.89, "learning_rate": 2.8247096970872706e-07, "loss": 0.7514, "step": 335580 }, { "epoch": 27.89, "learning_rate": 2.823601141811933e-07, "loss": 0.7259, "step": 335590 }, { "epoch": 27.89, "learning_rate": 2.822492586536596e-07, "loss": 0.7509, "step": 335600 }, { "epoch": 27.9, "learning_rate": 2.8213840312612584e-07, "loss": 0.7193, "step": 335610 }, { "epoch": 27.9, "learning_rate": 2.820275475985921e-07, "loss": 0.7218, "step": 335620 }, { "epoch": 27.9, "learning_rate": 2.819166920710584e-07, "loss": 0.7645, "step": 335630 }, { "epoch": 27.9, "learning_rate": 2.818058365435246e-07, "loss": 0.7487, "step": 335640 }, { "epoch": 27.9, "learning_rate": 2.8169498101599086e-07, "loss": 0.7483, "step": 335650 }, { "epoch": 27.9, "learning_rate": 2.8158412548845716e-07, "loss": 0.764, "step": 335660 }, { "epoch": 27.9, "learning_rate": 2.814732699609234e-07, "loss": 0.7231, "step": 335670 }, { "epoch": 27.9, "learning_rate": 2.8136241443338964e-07, "loss": 0.7525, "step": 335680 }, { "epoch": 27.9, "learning_rate": 2.8125155890585594e-07, "loss": 0.7941, "step": 335690 }, { "epoch": 27.9, "learning_rate": 2.811407033783222e-07, "loss": 0.7264, "step": 335700 }, { "epoch": 27.9, "learning_rate": 2.810298478507884e-07, "loss": 0.6896, "step": 335710 }, { "epoch": 27.9, "learning_rate": 2.809189923232547e-07, "loss": 0.7616, "step": 335720 }, { "epoch": 27.91, "learning_rate": 2.8080813679572096e-07, "loss": 0.7463, "step": 335730 }, { "epoch": 27.91, "learning_rate": 2.806972812681872e-07, "loss": 0.7726, "step": 335740 }, { "epoch": 27.91, "learning_rate": 2.805864257406535e-07, "loss": 0.7598, "step": 335750 }, { "epoch": 27.91, "learning_rate": 2.8047557021311974e-07, "loss": 0.7087, "step": 335760 }, { "epoch": 27.91, "learning_rate": 2.80364714685586e-07, "loss": 0.7439, "step": 335770 }, { "epoch": 27.91, "learning_rate": 2.802538591580523e-07, "loss": 0.7639, "step": 335780 }, { "epoch": 27.91, "learning_rate": 2.801430036305185e-07, "loss": 0.7217, "step": 335790 }, { "epoch": 27.91, "learning_rate": 2.8003214810298476e-07, "loss": 0.7686, "step": 335800 }, { "epoch": 27.91, "learning_rate": 2.7992129257545106e-07, "loss": 0.771, "step": 335810 }, { "epoch": 27.91, "learning_rate": 2.798104370479173e-07, "loss": 0.7594, "step": 335820 }, { "epoch": 27.91, "learning_rate": 2.7969958152038354e-07, "loss": 0.7549, "step": 335830 }, { "epoch": 27.91, "learning_rate": 2.7958872599284984e-07, "loss": 0.7377, "step": 335840 }, { "epoch": 27.92, "learning_rate": 2.794778704653161e-07, "loss": 0.7626, "step": 335850 }, { "epoch": 27.92, "learning_rate": 2.793670149377823e-07, "loss": 0.682, "step": 335860 }, { "epoch": 27.92, "learning_rate": 2.792561594102486e-07, "loss": 0.7336, "step": 335870 }, { "epoch": 27.92, "learning_rate": 2.7914530388271486e-07, "loss": 0.796, "step": 335880 }, { "epoch": 27.92, "learning_rate": 2.790344483551811e-07, "loss": 0.7601, "step": 335890 }, { "epoch": 27.92, "learning_rate": 2.789235928276474e-07, "loss": 0.7547, "step": 335900 }, { "epoch": 27.92, "learning_rate": 2.7881273730011364e-07, "loss": 0.7012, "step": 335910 }, { "epoch": 27.92, "learning_rate": 2.787018817725799e-07, "loss": 0.7087, "step": 335920 }, { "epoch": 27.92, "learning_rate": 2.785910262450462e-07, "loss": 0.7233, "step": 335930 }, { "epoch": 27.92, "learning_rate": 2.784801707175124e-07, "loss": 0.7396, "step": 335940 }, { "epoch": 27.92, "learning_rate": 2.783693151899786e-07, "loss": 0.7592, "step": 335950 }, { "epoch": 27.92, "learning_rate": 2.782584596624449e-07, "loss": 0.7484, "step": 335960 }, { "epoch": 27.93, "learning_rate": 2.7814760413491115e-07, "loss": 0.7327, "step": 335970 }, { "epoch": 27.93, "learning_rate": 2.780367486073774e-07, "loss": 0.755, "step": 335980 }, { "epoch": 27.93, "learning_rate": 2.7792589307984363e-07, "loss": 0.723, "step": 335990 }, { "epoch": 27.93, "learning_rate": 2.7781503755230993e-07, "loss": 0.7646, "step": 336000 }, { "epoch": 27.93, "learning_rate": 2.7770418202477617e-07, "loss": 0.7871, "step": 336010 }, { "epoch": 27.93, "learning_rate": 2.775933264972424e-07, "loss": 0.7524, "step": 336020 }, { "epoch": 27.93, "learning_rate": 2.774824709697087e-07, "loss": 0.6909, "step": 336030 }, { "epoch": 27.93, "learning_rate": 2.7737161544217495e-07, "loss": 0.809, "step": 336040 }, { "epoch": 27.93, "learning_rate": 2.772607599146412e-07, "loss": 0.8166, "step": 336050 }, { "epoch": 27.93, "learning_rate": 2.771499043871075e-07, "loss": 0.7357, "step": 336060 }, { "epoch": 27.93, "learning_rate": 2.7703904885957373e-07, "loss": 0.7386, "step": 336070 }, { "epoch": 27.93, "learning_rate": 2.7692819333204e-07, "loss": 0.7198, "step": 336080 }, { "epoch": 27.94, "learning_rate": 2.7681733780450627e-07, "loss": 0.7436, "step": 336090 }, { "epoch": 27.94, "learning_rate": 2.767064822769725e-07, "loss": 0.698, "step": 336100 }, { "epoch": 27.94, "learning_rate": 2.7659562674943875e-07, "loss": 0.7136, "step": 336110 }, { "epoch": 27.94, "learning_rate": 2.7648477122190505e-07, "loss": 0.7323, "step": 336120 }, { "epoch": 27.94, "learning_rate": 2.763739156943713e-07, "loss": 0.739, "step": 336130 }, { "epoch": 27.94, "learning_rate": 2.7626306016683753e-07, "loss": 0.7779, "step": 336140 }, { "epoch": 27.94, "learning_rate": 2.7615220463930383e-07, "loss": 0.7675, "step": 336150 }, { "epoch": 27.94, "learning_rate": 2.7604134911177007e-07, "loss": 0.7046, "step": 336160 }, { "epoch": 27.94, "learning_rate": 2.759304935842363e-07, "loss": 0.7591, "step": 336170 }, { "epoch": 27.94, "learning_rate": 2.758196380567026e-07, "loss": 0.7758, "step": 336180 }, { "epoch": 27.94, "learning_rate": 2.7570878252916885e-07, "loss": 0.7713, "step": 336190 }, { "epoch": 27.94, "learning_rate": 2.755979270016351e-07, "loss": 0.7708, "step": 336200 }, { "epoch": 27.95, "learning_rate": 2.754870714741014e-07, "loss": 0.6847, "step": 336210 }, { "epoch": 27.95, "learning_rate": 2.7537621594656763e-07, "loss": 0.7336, "step": 336220 }, { "epoch": 27.95, "learning_rate": 2.752653604190339e-07, "loss": 0.7377, "step": 336230 }, { "epoch": 27.95, "learning_rate": 2.7515450489150017e-07, "loss": 0.7397, "step": 336240 }, { "epoch": 27.95, "learning_rate": 2.750436493639664e-07, "loss": 0.7468, "step": 336250 }, { "epoch": 27.95, "learning_rate": 2.7493279383643266e-07, "loss": 0.7366, "step": 336260 }, { "epoch": 27.95, "learning_rate": 2.7482193830889895e-07, "loss": 0.7599, "step": 336270 }, { "epoch": 27.95, "learning_rate": 2.747110827813652e-07, "loss": 0.6997, "step": 336280 }, { "epoch": 27.95, "learning_rate": 2.7460022725383144e-07, "loss": 0.7258, "step": 336290 }, { "epoch": 27.95, "learning_rate": 2.7448937172629773e-07, "loss": 0.7784, "step": 336300 }, { "epoch": 27.95, "learning_rate": 2.7437851619876397e-07, "loss": 0.743, "step": 336310 }, { "epoch": 27.95, "learning_rate": 2.742676606712302e-07, "loss": 0.7569, "step": 336320 }, { "epoch": 27.96, "learning_rate": 2.741568051436965e-07, "loss": 0.6875, "step": 336330 }, { "epoch": 27.96, "learning_rate": 2.7404594961616275e-07, "loss": 0.7662, "step": 336340 }, { "epoch": 27.96, "learning_rate": 2.73935094088629e-07, "loss": 0.6841, "step": 336350 }, { "epoch": 27.96, "learning_rate": 2.738242385610953e-07, "loss": 0.7157, "step": 336360 }, { "epoch": 27.96, "learning_rate": 2.737133830335615e-07, "loss": 0.7103, "step": 336370 }, { "epoch": 27.96, "learning_rate": 2.736025275060277e-07, "loss": 0.7518, "step": 336380 }, { "epoch": 27.96, "learning_rate": 2.73491671978494e-07, "loss": 0.6852, "step": 336390 }, { "epoch": 27.96, "learning_rate": 2.7338081645096026e-07, "loss": 0.7222, "step": 336400 }, { "epoch": 27.96, "learning_rate": 2.732810464761799e-07, "loss": 0.6684, "step": 336410 }, { "epoch": 27.96, "learning_rate": 2.731701909486462e-07, "loss": 0.7286, "step": 336420 }, { "epoch": 27.96, "learning_rate": 2.7305933542111244e-07, "loss": 0.7666, "step": 336430 }, { "epoch": 27.96, "learning_rate": 2.729484798935787e-07, "loss": 0.7618, "step": 336440 }, { "epoch": 27.97, "learning_rate": 2.72837624366045e-07, "loss": 0.8102, "step": 336450 }, { "epoch": 27.97, "learning_rate": 2.727267688385112e-07, "loss": 0.729, "step": 336460 }, { "epoch": 27.97, "learning_rate": 2.7261591331097747e-07, "loss": 0.6611, "step": 336470 }, { "epoch": 27.97, "learning_rate": 2.7250505778344376e-07, "loss": 0.6833, "step": 336480 }, { "epoch": 27.97, "learning_rate": 2.7239420225591e-07, "loss": 0.685, "step": 336490 }, { "epoch": 27.97, "learning_rate": 2.722833467283762e-07, "loss": 0.7898, "step": 336500 }, { "epoch": 27.97, "learning_rate": 2.721724912008425e-07, "loss": 0.7351, "step": 336510 }, { "epoch": 27.97, "learning_rate": 2.7206163567330873e-07, "loss": 0.7313, "step": 336520 }, { "epoch": 27.97, "learning_rate": 2.7195078014577497e-07, "loss": 0.7715, "step": 336530 }, { "epoch": 27.97, "learning_rate": 2.7183992461824127e-07, "loss": 0.753, "step": 336540 }, { "epoch": 27.97, "learning_rate": 2.717290690907075e-07, "loss": 0.7207, "step": 336550 }, { "epoch": 27.97, "learning_rate": 2.7161821356317375e-07, "loss": 0.7601, "step": 336560 }, { "epoch": 27.98, "learning_rate": 2.7150735803564005e-07, "loss": 0.6582, "step": 336570 }, { "epoch": 27.98, "learning_rate": 2.713965025081063e-07, "loss": 0.7256, "step": 336580 }, { "epoch": 27.98, "learning_rate": 2.7128564698057253e-07, "loss": 0.6925, "step": 336590 }, { "epoch": 27.98, "learning_rate": 2.7117479145303883e-07, "loss": 0.7293, "step": 336600 }, { "epoch": 27.98, "learning_rate": 2.7106393592550507e-07, "loss": 0.7741, "step": 336610 }, { "epoch": 27.98, "learning_rate": 2.709530803979713e-07, "loss": 0.7695, "step": 336620 }, { "epoch": 27.98, "learning_rate": 2.7084222487043756e-07, "loss": 0.7123, "step": 336630 }, { "epoch": 27.98, "learning_rate": 2.7073136934290385e-07, "loss": 0.7389, "step": 336640 }, { "epoch": 27.98, "learning_rate": 2.706205138153701e-07, "loss": 0.7769, "step": 336650 }, { "epoch": 27.98, "learning_rate": 2.7050965828783634e-07, "loss": 0.7312, "step": 336660 }, { "epoch": 27.98, "learning_rate": 2.7039880276030263e-07, "loss": 0.6885, "step": 336670 }, { "epoch": 27.98, "learning_rate": 2.7028794723276887e-07, "loss": 0.7595, "step": 336680 }, { "epoch": 27.99, "learning_rate": 2.701770917052351e-07, "loss": 0.7864, "step": 336690 }, { "epoch": 27.99, "learning_rate": 2.700662361777014e-07, "loss": 0.7522, "step": 336700 }, { "epoch": 27.99, "learning_rate": 2.6995538065016765e-07, "loss": 0.7255, "step": 336710 }, { "epoch": 27.99, "learning_rate": 2.698445251226339e-07, "loss": 0.6988, "step": 336720 }, { "epoch": 27.99, "learning_rate": 2.697336695951002e-07, "loss": 0.686, "step": 336730 }, { "epoch": 27.99, "learning_rate": 2.6962281406756643e-07, "loss": 0.7364, "step": 336740 }, { "epoch": 27.99, "learning_rate": 2.695119585400327e-07, "loss": 0.8051, "step": 336750 }, { "epoch": 27.99, "learning_rate": 2.6940110301249897e-07, "loss": 0.732, "step": 336760 }, { "epoch": 27.99, "learning_rate": 2.692902474849652e-07, "loss": 0.7374, "step": 336770 }, { "epoch": 27.99, "learning_rate": 2.6917939195743146e-07, "loss": 0.774, "step": 336780 }, { "epoch": 27.99, "learning_rate": 2.6906853642989775e-07, "loss": 0.6788, "step": 336790 }, { "epoch": 27.99, "learning_rate": 2.68957680902364e-07, "loss": 0.8169, "step": 336800 }, { "epoch": 28.0, "learning_rate": 2.6884682537483024e-07, "loss": 0.6657, "step": 336810 }, { "epoch": 28.0, "learning_rate": 2.6873596984729653e-07, "loss": 0.6792, "step": 336820 }, { "epoch": 28.0, "learning_rate": 2.686251143197628e-07, "loss": 0.7096, "step": 336830 }, { "epoch": 28.0, "learning_rate": 2.68514258792229e-07, "loss": 0.7411, "step": 336840 }, { "epoch": 28.0, "learning_rate": 2.684034032646953e-07, "loss": 0.704, "step": 336850 }, { "epoch": 28.0, "learning_rate": 2.6829254773716155e-07, "loss": 0.7184, "step": 336860 }, { "epoch": 28.0, "eval_loss": 1.1479755640029907, "eval_runtime": 365.3506, "eval_samples_per_second": 7.319, "eval_steps_per_second": 3.659, "eval_wer": 0.6346098609521926, "step": 336868 }, { "epoch": 28.0, "learning_rate": 2.681816922096278e-07, "loss": 0.7014, "step": 336870 }, { "epoch": 28.0, "learning_rate": 2.680708366820941e-07, "loss": 0.7335, "step": 336880 }, { "epoch": 28.0, "learning_rate": 2.6795998115456033e-07, "loss": 0.7355, "step": 336890 }, { "epoch": 28.0, "learning_rate": 2.678491256270266e-07, "loss": 0.7116, "step": 336900 }, { "epoch": 28.0, "learning_rate": 2.6773827009949287e-07, "loss": 0.6975, "step": 336910 }, { "epoch": 28.0, "learning_rate": 2.6762741457195906e-07, "loss": 0.7265, "step": 336920 }, { "epoch": 28.01, "learning_rate": 2.675165590444253e-07, "loss": 0.7897, "step": 336930 }, { "epoch": 28.01, "learning_rate": 2.674057035168916e-07, "loss": 0.7246, "step": 336940 }, { "epoch": 28.01, "learning_rate": 2.6729484798935784e-07, "loss": 0.7589, "step": 336950 }, { "epoch": 28.01, "learning_rate": 2.671839924618241e-07, "loss": 0.707, "step": 336960 }, { "epoch": 28.01, "learning_rate": 2.670731369342904e-07, "loss": 0.7023, "step": 336970 }, { "epoch": 28.01, "learning_rate": 2.669622814067566e-07, "loss": 0.7494, "step": 336980 }, { "epoch": 28.01, "learning_rate": 2.6685142587922286e-07, "loss": 0.6986, "step": 336990 }, { "epoch": 28.01, "learning_rate": 2.6674057035168916e-07, "loss": 0.7574, "step": 337000 }, { "epoch": 28.01, "learning_rate": 2.666297148241554e-07, "loss": 0.7292, "step": 337010 }, { "epoch": 28.01, "learning_rate": 2.6651885929662164e-07, "loss": 0.7179, "step": 337020 }, { "epoch": 28.01, "learning_rate": 2.664080037690879e-07, "loss": 0.7899, "step": 337030 }, { "epoch": 28.01, "learning_rate": 2.662971482415542e-07, "loss": 0.7011, "step": 337040 }, { "epoch": 28.02, "learning_rate": 2.661862927140204e-07, "loss": 0.8176, "step": 337050 }, { "epoch": 28.02, "learning_rate": 2.6607543718648667e-07, "loss": 0.7074, "step": 337060 }, { "epoch": 28.02, "learning_rate": 2.6596458165895296e-07, "loss": 0.7156, "step": 337070 }, { "epoch": 28.02, "learning_rate": 2.658537261314192e-07, "loss": 0.7749, "step": 337080 }, { "epoch": 28.02, "learning_rate": 2.6574287060388545e-07, "loss": 0.7271, "step": 337090 }, { "epoch": 28.02, "learning_rate": 2.6563201507635174e-07, "loss": 0.721, "step": 337100 }, { "epoch": 28.02, "learning_rate": 2.65521159548818e-07, "loss": 0.7287, "step": 337110 }, { "epoch": 28.02, "learning_rate": 2.6541030402128423e-07, "loss": 0.7169, "step": 337120 }, { "epoch": 28.02, "learning_rate": 2.652994484937505e-07, "loss": 0.7318, "step": 337130 }, { "epoch": 28.02, "learning_rate": 2.6518859296621677e-07, "loss": 0.7066, "step": 337140 }, { "epoch": 28.02, "learning_rate": 2.65077737438683e-07, "loss": 0.7186, "step": 337150 }, { "epoch": 28.02, "learning_rate": 2.649668819111493e-07, "loss": 0.685, "step": 337160 }, { "epoch": 28.03, "learning_rate": 2.6485602638361555e-07, "loss": 0.7164, "step": 337170 }, { "epoch": 28.03, "learning_rate": 2.647451708560818e-07, "loss": 0.7932, "step": 337180 }, { "epoch": 28.03, "learning_rate": 2.646343153285481e-07, "loss": 0.7703, "step": 337190 }, { "epoch": 28.03, "learning_rate": 2.645234598010143e-07, "loss": 0.7004, "step": 337200 }, { "epoch": 28.03, "learning_rate": 2.6441260427348057e-07, "loss": 0.7548, "step": 337210 }, { "epoch": 28.03, "learning_rate": 2.6430174874594686e-07, "loss": 0.764, "step": 337220 }, { "epoch": 28.03, "learning_rate": 2.641908932184131e-07, "loss": 0.7266, "step": 337230 }, { "epoch": 28.03, "learning_rate": 2.6408003769087935e-07, "loss": 0.7199, "step": 337240 }, { "epoch": 28.03, "learning_rate": 2.6396918216334564e-07, "loss": 0.7209, "step": 337250 }, { "epoch": 28.03, "learning_rate": 2.638583266358119e-07, "loss": 0.7615, "step": 337260 }, { "epoch": 28.03, "learning_rate": 2.6374747110827813e-07, "loss": 0.7361, "step": 337270 }, { "epoch": 28.03, "learning_rate": 2.636366155807444e-07, "loss": 0.7325, "step": 337280 }, { "epoch": 28.04, "learning_rate": 2.6352576005321067e-07, "loss": 0.7387, "step": 337290 }, { "epoch": 28.04, "learning_rate": 2.634149045256769e-07, "loss": 0.6552, "step": 337300 }, { "epoch": 28.04, "learning_rate": 2.633040489981432e-07, "loss": 0.7, "step": 337310 }, { "epoch": 28.04, "learning_rate": 2.6319319347060945e-07, "loss": 0.7401, "step": 337320 }, { "epoch": 28.04, "learning_rate": 2.6308233794307564e-07, "loss": 0.7528, "step": 337330 }, { "epoch": 28.04, "learning_rate": 2.6297148241554193e-07, "loss": 0.6913, "step": 337340 }, { "epoch": 28.04, "learning_rate": 2.6286062688800817e-07, "loss": 0.7109, "step": 337350 }, { "epoch": 28.04, "learning_rate": 2.627497713604744e-07, "loss": 0.6677, "step": 337360 }, { "epoch": 28.04, "learning_rate": 2.626389158329407e-07, "loss": 0.7433, "step": 337370 }, { "epoch": 28.04, "learning_rate": 2.6252806030540695e-07, "loss": 0.7592, "step": 337380 }, { "epoch": 28.04, "learning_rate": 2.624172047778732e-07, "loss": 0.7278, "step": 337390 }, { "epoch": 28.04, "learning_rate": 2.623063492503395e-07, "loss": 0.7106, "step": 337400 }, { "epoch": 28.05, "learning_rate": 2.6219549372280573e-07, "loss": 0.6559, "step": 337410 }, { "epoch": 28.05, "learning_rate": 2.62084638195272e-07, "loss": 0.7748, "step": 337420 }, { "epoch": 28.05, "learning_rate": 2.6197378266773827e-07, "loss": 0.6767, "step": 337430 }, { "epoch": 28.05, "learning_rate": 2.618629271402045e-07, "loss": 0.7378, "step": 337440 }, { "epoch": 28.05, "learning_rate": 2.6175207161267076e-07, "loss": 0.7111, "step": 337450 }, { "epoch": 28.05, "learning_rate": 2.61641216085137e-07, "loss": 0.7668, "step": 337460 }, { "epoch": 28.05, "learning_rate": 2.615303605576033e-07, "loss": 0.6939, "step": 337470 }, { "epoch": 28.05, "learning_rate": 2.6141950503006954e-07, "loss": 0.7589, "step": 337480 }, { "epoch": 28.05, "learning_rate": 2.613086495025358e-07, "loss": 0.719, "step": 337490 }, { "epoch": 28.05, "learning_rate": 2.611977939750021e-07, "loss": 0.7101, "step": 337500 }, { "epoch": 28.05, "learning_rate": 2.610869384474683e-07, "loss": 0.7299, "step": 337510 }, { "epoch": 28.05, "learning_rate": 2.6097608291993456e-07, "loss": 0.7375, "step": 337520 }, { "epoch": 28.06, "learning_rate": 2.6086522739240085e-07, "loss": 0.7659, "step": 337530 }, { "epoch": 28.06, "learning_rate": 2.607543718648671e-07, "loss": 0.7277, "step": 337540 }, { "epoch": 28.06, "learning_rate": 2.6064351633733334e-07, "loss": 0.7571, "step": 337550 }, { "epoch": 28.06, "learning_rate": 2.6053266080979963e-07, "loss": 0.7144, "step": 337560 }, { "epoch": 28.06, "learning_rate": 2.604218052822659e-07, "loss": 0.7435, "step": 337570 }, { "epoch": 28.06, "learning_rate": 2.603109497547321e-07, "loss": 0.7125, "step": 337580 }, { "epoch": 28.06, "learning_rate": 2.602000942271984e-07, "loss": 0.7072, "step": 337590 }, { "epoch": 28.06, "learning_rate": 2.6008923869966466e-07, "loss": 0.7527, "step": 337600 }, { "epoch": 28.06, "learning_rate": 2.599783831721309e-07, "loss": 0.7999, "step": 337610 }, { "epoch": 28.06, "learning_rate": 2.598675276445972e-07, "loss": 0.7603, "step": 337620 }, { "epoch": 28.06, "learning_rate": 2.5975667211706344e-07, "loss": 0.7963, "step": 337630 }, { "epoch": 28.06, "learning_rate": 2.596458165895297e-07, "loss": 0.7152, "step": 337640 }, { "epoch": 28.06, "learning_rate": 2.59534961061996e-07, "loss": 0.6925, "step": 337650 }, { "epoch": 28.07, "learning_rate": 2.594241055344622e-07, "loss": 0.7636, "step": 337660 }, { "epoch": 28.07, "learning_rate": 2.5931325000692846e-07, "loss": 0.6757, "step": 337670 }, { "epoch": 28.07, "learning_rate": 2.5920239447939475e-07, "loss": 0.7802, "step": 337680 }, { "epoch": 28.07, "learning_rate": 2.59091538951861e-07, "loss": 0.7751, "step": 337690 }, { "epoch": 28.07, "learning_rate": 2.5898068342432724e-07, "loss": 0.6488, "step": 337700 }, { "epoch": 28.07, "learning_rate": 2.5886982789679353e-07, "loss": 0.6804, "step": 337710 }, { "epoch": 28.07, "learning_rate": 2.587589723692598e-07, "loss": 0.7122, "step": 337720 }, { "epoch": 28.07, "learning_rate": 2.58648116841726e-07, "loss": 0.7092, "step": 337730 }, { "epoch": 28.07, "learning_rate": 2.585372613141923e-07, "loss": 0.7124, "step": 337740 }, { "epoch": 28.07, "learning_rate": 2.584264057866585e-07, "loss": 0.6725, "step": 337750 }, { "epoch": 28.07, "learning_rate": 2.5831555025912475e-07, "loss": 0.7592, "step": 337760 }, { "epoch": 28.07, "learning_rate": 2.5820469473159104e-07, "loss": 0.741, "step": 337770 }, { "epoch": 28.08, "learning_rate": 2.580938392040573e-07, "loss": 0.7368, "step": 337780 }, { "epoch": 28.08, "learning_rate": 2.5798298367652353e-07, "loss": 0.7007, "step": 337790 }, { "epoch": 28.08, "learning_rate": 2.578721281489898e-07, "loss": 0.7163, "step": 337800 }, { "epoch": 28.08, "learning_rate": 2.5776127262145606e-07, "loss": 0.7582, "step": 337810 }, { "epoch": 28.08, "learning_rate": 2.576504170939223e-07, "loss": 0.7307, "step": 337820 }, { "epoch": 28.08, "learning_rate": 2.575395615663886e-07, "loss": 0.7728, "step": 337830 }, { "epoch": 28.08, "learning_rate": 2.5742870603885484e-07, "loss": 0.7076, "step": 337840 }, { "epoch": 28.08, "learning_rate": 2.573178505113211e-07, "loss": 0.6308, "step": 337850 }, { "epoch": 28.08, "learning_rate": 2.5720699498378733e-07, "loss": 0.7406, "step": 337860 }, { "epoch": 28.08, "learning_rate": 2.570961394562536e-07, "loss": 0.7297, "step": 337870 }, { "epoch": 28.08, "learning_rate": 2.5698528392871987e-07, "loss": 0.7995, "step": 337880 }, { "epoch": 28.08, "learning_rate": 2.568744284011861e-07, "loss": 0.7301, "step": 337890 }, { "epoch": 28.09, "learning_rate": 2.567635728736524e-07, "loss": 0.6887, "step": 337900 }, { "epoch": 28.09, "learning_rate": 2.5665271734611865e-07, "loss": 0.751, "step": 337910 }, { "epoch": 28.09, "learning_rate": 2.565418618185849e-07, "loss": 0.7625, "step": 337920 }, { "epoch": 28.09, "learning_rate": 2.564310062910512e-07, "loss": 0.8493, "step": 337930 }, { "epoch": 28.09, "learning_rate": 2.5632015076351743e-07, "loss": 0.7348, "step": 337940 }, { "epoch": 28.09, "learning_rate": 2.5620929523598367e-07, "loss": 0.7347, "step": 337950 }, { "epoch": 28.09, "learning_rate": 2.5609843970844997e-07, "loss": 0.6999, "step": 337960 }, { "epoch": 28.09, "learning_rate": 2.559875841809162e-07, "loss": 0.7303, "step": 337970 }, { "epoch": 28.09, "learning_rate": 2.5587672865338245e-07, "loss": 0.7595, "step": 337980 }, { "epoch": 28.09, "learning_rate": 2.5576587312584875e-07, "loss": 0.6526, "step": 337990 }, { "epoch": 28.09, "learning_rate": 2.55655017598315e-07, "loss": 0.741, "step": 338000 }, { "epoch": 28.09, "learning_rate": 2.5554416207078123e-07, "loss": 0.6952, "step": 338010 }, { "epoch": 28.1, "learning_rate": 2.554333065432475e-07, "loss": 0.7449, "step": 338020 }, { "epoch": 28.1, "learning_rate": 2.5532245101571377e-07, "loss": 0.7569, "step": 338030 }, { "epoch": 28.1, "learning_rate": 2.5521159548818e-07, "loss": 0.7552, "step": 338040 }, { "epoch": 28.1, "learning_rate": 2.551007399606463e-07, "loss": 0.6531, "step": 338050 }, { "epoch": 28.1, "learning_rate": 2.5498988443311255e-07, "loss": 0.7491, "step": 338060 }, { "epoch": 28.1, "learning_rate": 2.548790289055788e-07, "loss": 0.6469, "step": 338070 }, { "epoch": 28.1, "learning_rate": 2.547681733780451e-07, "loss": 0.775, "step": 338080 }, { "epoch": 28.1, "learning_rate": 2.5465731785051133e-07, "loss": 0.7426, "step": 338090 }, { "epoch": 28.1, "learning_rate": 2.5454646232297757e-07, "loss": 0.7206, "step": 338100 }, { "epoch": 28.1, "learning_rate": 2.5443560679544387e-07, "loss": 0.6789, "step": 338110 }, { "epoch": 28.1, "learning_rate": 2.543247512679101e-07, "loss": 0.7513, "step": 338120 }, { "epoch": 28.1, "learning_rate": 2.5421389574037635e-07, "loss": 0.7682, "step": 338130 }, { "epoch": 28.11, "learning_rate": 2.5410304021284265e-07, "loss": 0.7925, "step": 338140 }, { "epoch": 28.11, "learning_rate": 2.539921846853089e-07, "loss": 0.714, "step": 338150 }, { "epoch": 28.11, "learning_rate": 2.538813291577751e-07, "loss": 0.7167, "step": 338160 }, { "epoch": 28.11, "learning_rate": 2.5377047363024137e-07, "loss": 0.6835, "step": 338170 }, { "epoch": 28.11, "learning_rate": 2.536596181027076e-07, "loss": 0.7418, "step": 338180 }, { "epoch": 28.11, "learning_rate": 2.5354876257517386e-07, "loss": 0.6997, "step": 338190 }, { "epoch": 28.11, "learning_rate": 2.5343790704764015e-07, "loss": 0.705, "step": 338200 }, { "epoch": 28.11, "learning_rate": 2.533270515201064e-07, "loss": 0.7075, "step": 338210 }, { "epoch": 28.11, "learning_rate": 2.5321619599257264e-07, "loss": 0.7739, "step": 338220 }, { "epoch": 28.11, "learning_rate": 2.5310534046503893e-07, "loss": 0.7355, "step": 338230 }, { "epoch": 28.11, "learning_rate": 2.529944849375052e-07, "loss": 0.7755, "step": 338240 }, { "epoch": 28.11, "learning_rate": 2.528836294099714e-07, "loss": 0.745, "step": 338250 }, { "epoch": 28.12, "learning_rate": 2.527727738824377e-07, "loss": 0.7372, "step": 338260 }, { "epoch": 28.12, "learning_rate": 2.5266191835490396e-07, "loss": 0.745, "step": 338270 }, { "epoch": 28.12, "learning_rate": 2.525510628273702e-07, "loss": 0.7643, "step": 338280 }, { "epoch": 28.12, "learning_rate": 2.5244020729983644e-07, "loss": 0.713, "step": 338290 }, { "epoch": 28.12, "learning_rate": 2.5232935177230274e-07, "loss": 0.7294, "step": 338300 }, { "epoch": 28.12, "learning_rate": 2.52218496244769e-07, "loss": 0.7642, "step": 338310 }, { "epoch": 28.12, "learning_rate": 2.521076407172352e-07, "loss": 0.7347, "step": 338320 }, { "epoch": 28.12, "learning_rate": 2.519967851897015e-07, "loss": 0.7696, "step": 338330 }, { "epoch": 28.12, "learning_rate": 2.5188592966216776e-07, "loss": 0.7162, "step": 338340 }, { "epoch": 28.12, "learning_rate": 2.51775074134634e-07, "loss": 0.7254, "step": 338350 }, { "epoch": 28.12, "learning_rate": 2.516642186071003e-07, "loss": 0.6852, "step": 338360 }, { "epoch": 28.12, "learning_rate": 2.5155336307956654e-07, "loss": 0.7401, "step": 338370 }, { "epoch": 28.13, "learning_rate": 2.514425075520328e-07, "loss": 0.7874, "step": 338380 }, { "epoch": 28.13, "learning_rate": 2.513316520244991e-07, "loss": 0.7312, "step": 338390 }, { "epoch": 28.13, "learning_rate": 2.512207964969653e-07, "loss": 0.7199, "step": 338400 }, { "epoch": 28.13, "learning_rate": 2.5110994096943156e-07, "loss": 0.7406, "step": 338410 }, { "epoch": 28.13, "learning_rate": 2.5099908544189786e-07, "loss": 0.6946, "step": 338420 }, { "epoch": 28.13, "learning_rate": 2.508882299143641e-07, "loss": 0.7851, "step": 338430 }, { "epoch": 28.13, "learning_rate": 2.5077737438683034e-07, "loss": 0.7138, "step": 338440 }, { "epoch": 28.13, "learning_rate": 2.5066651885929664e-07, "loss": 0.6964, "step": 338450 }, { "epoch": 28.13, "learning_rate": 2.505556633317629e-07, "loss": 0.7562, "step": 338460 }, { "epoch": 28.13, "learning_rate": 2.504448078042291e-07, "loss": 0.7937, "step": 338470 }, { "epoch": 28.13, "learning_rate": 2.503339522766954e-07, "loss": 0.7763, "step": 338480 }, { "epoch": 28.13, "learning_rate": 2.5022309674916166e-07, "loss": 0.7496, "step": 338490 }, { "epoch": 28.14, "learning_rate": 2.501122412216279e-07, "loss": 0.7392, "step": 338500 }, { "epoch": 28.14, "learning_rate": 2.500013856940942e-07, "loss": 0.713, "step": 338510 }, { "epoch": 28.14, "learning_rate": 2.4989053016656044e-07, "loss": 0.7003, "step": 338520 }, { "epoch": 28.14, "learning_rate": 2.497796746390267e-07, "loss": 0.7128, "step": 338530 }, { "epoch": 28.14, "learning_rate": 2.496688191114929e-07, "loss": 0.6782, "step": 338540 }, { "epoch": 28.14, "learning_rate": 2.495579635839592e-07, "loss": 0.7315, "step": 338550 }, { "epoch": 28.14, "learning_rate": 2.4944710805642546e-07, "loss": 0.7428, "step": 338560 }, { "epoch": 28.14, "learning_rate": 2.493362525288917e-07, "loss": 0.7563, "step": 338570 }, { "epoch": 28.14, "learning_rate": 2.4922539700135795e-07, "loss": 0.7345, "step": 338580 }, { "epoch": 28.14, "learning_rate": 2.491145414738242e-07, "loss": 0.7008, "step": 338590 }, { "epoch": 28.14, "learning_rate": 2.490036859462905e-07, "loss": 0.7353, "step": 338600 }, { "epoch": 28.14, "learning_rate": 2.4889283041875673e-07, "loss": 0.7182, "step": 338610 }, { "epoch": 28.15, "learning_rate": 2.4878197489122297e-07, "loss": 0.7145, "step": 338620 }, { "epoch": 28.15, "learning_rate": 2.4867111936368926e-07, "loss": 0.7537, "step": 338630 }, { "epoch": 28.15, "learning_rate": 2.485602638361555e-07, "loss": 0.6666, "step": 338640 }, { "epoch": 28.15, "learning_rate": 2.4844940830862175e-07, "loss": 0.6498, "step": 338650 }, { "epoch": 28.15, "learning_rate": 2.4833855278108804e-07, "loss": 0.6991, "step": 338660 }, { "epoch": 28.15, "learning_rate": 2.482276972535543e-07, "loss": 0.7561, "step": 338670 }, { "epoch": 28.15, "learning_rate": 2.4811684172602053e-07, "loss": 0.7615, "step": 338680 }, { "epoch": 28.15, "learning_rate": 2.480059861984868e-07, "loss": 0.7358, "step": 338690 }, { "epoch": 28.15, "learning_rate": 2.4789513067095307e-07, "loss": 0.7244, "step": 338700 }, { "epoch": 28.15, "learning_rate": 2.477842751434193e-07, "loss": 0.7196, "step": 338710 }, { "epoch": 28.15, "learning_rate": 2.476734196158856e-07, "loss": 0.7438, "step": 338720 }, { "epoch": 28.15, "learning_rate": 2.4756256408835185e-07, "loss": 0.7885, "step": 338730 }, { "epoch": 28.16, "learning_rate": 2.474517085608181e-07, "loss": 0.7163, "step": 338740 }, { "epoch": 28.16, "learning_rate": 2.473408530332844e-07, "loss": 0.6976, "step": 338750 }, { "epoch": 28.16, "learning_rate": 2.4722999750575063e-07, "loss": 0.672, "step": 338760 }, { "epoch": 28.16, "learning_rate": 2.4711914197821687e-07, "loss": 0.7688, "step": 338770 }, { "epoch": 28.16, "learning_rate": 2.4700828645068317e-07, "loss": 0.7656, "step": 338780 }, { "epoch": 28.16, "learning_rate": 2.468974309231494e-07, "loss": 0.7489, "step": 338790 }, { "epoch": 28.16, "learning_rate": 2.4678657539561565e-07, "loss": 0.6851, "step": 338800 }, { "epoch": 28.16, "learning_rate": 2.466757198680819e-07, "loss": 0.6864, "step": 338810 }, { "epoch": 28.16, "learning_rate": 2.4656486434054813e-07, "loss": 0.7119, "step": 338820 }, { "epoch": 28.16, "learning_rate": 2.4645400881301443e-07, "loss": 0.785, "step": 338830 }, { "epoch": 28.16, "learning_rate": 2.4634315328548067e-07, "loss": 0.7574, "step": 338840 }, { "epoch": 28.16, "learning_rate": 2.462322977579469e-07, "loss": 0.7034, "step": 338850 }, { "epoch": 28.17, "learning_rate": 2.461214422304132e-07, "loss": 0.7215, "step": 338860 }, { "epoch": 28.17, "learning_rate": 2.4601058670287945e-07, "loss": 0.6696, "step": 338870 }, { "epoch": 28.17, "learning_rate": 2.458997311753457e-07, "loss": 0.7574, "step": 338880 }, { "epoch": 28.17, "learning_rate": 2.45788875647812e-07, "loss": 0.7652, "step": 338890 }, { "epoch": 28.17, "learning_rate": 2.4567802012027823e-07, "loss": 0.7072, "step": 338900 }, { "epoch": 28.17, "learning_rate": 2.455671645927445e-07, "loss": 0.7355, "step": 338910 }, { "epoch": 28.17, "learning_rate": 2.4545630906521077e-07, "loss": 0.6927, "step": 338920 }, { "epoch": 28.17, "learning_rate": 2.45345453537677e-07, "loss": 0.7763, "step": 338930 }, { "epoch": 28.17, "learning_rate": 2.4523459801014326e-07, "loss": 0.7434, "step": 338940 }, { "epoch": 28.17, "learning_rate": 2.4512374248260955e-07, "loss": 0.7744, "step": 338950 }, { "epoch": 28.17, "learning_rate": 2.450128869550758e-07, "loss": 0.7308, "step": 338960 }, { "epoch": 28.17, "learning_rate": 2.4490203142754204e-07, "loss": 0.7657, "step": 338970 }, { "epoch": 28.18, "learning_rate": 2.4479117590000833e-07, "loss": 0.7539, "step": 338980 }, { "epoch": 28.18, "learning_rate": 2.4468032037247457e-07, "loss": 0.7948, "step": 338990 }, { "epoch": 28.18, "learning_rate": 2.445694648449408e-07, "loss": 0.6807, "step": 339000 }, { "epoch": 28.18, "learning_rate": 2.4445860931740706e-07, "loss": 0.7102, "step": 339010 }, { "epoch": 28.18, "learning_rate": 2.443477537898733e-07, "loss": 0.7715, "step": 339020 }, { "epoch": 28.18, "learning_rate": 2.442368982623396e-07, "loss": 0.7354, "step": 339030 }, { "epoch": 28.18, "learning_rate": 2.4412604273480584e-07, "loss": 0.6504, "step": 339040 }, { "epoch": 28.18, "learning_rate": 2.440151872072721e-07, "loss": 0.7612, "step": 339050 }, { "epoch": 28.18, "learning_rate": 2.439043316797384e-07, "loss": 0.6976, "step": 339060 }, { "epoch": 28.18, "learning_rate": 2.437934761522046e-07, "loss": 0.7293, "step": 339070 }, { "epoch": 28.18, "learning_rate": 2.4368262062467086e-07, "loss": 0.7461, "step": 339080 }, { "epoch": 28.18, "learning_rate": 2.4357176509713716e-07, "loss": 0.7344, "step": 339090 }, { "epoch": 28.19, "learning_rate": 2.434609095696034e-07, "loss": 0.7319, "step": 339100 }, { "epoch": 28.19, "learning_rate": 2.4335005404206964e-07, "loss": 0.7927, "step": 339110 }, { "epoch": 28.19, "learning_rate": 2.4323919851453594e-07, "loss": 0.7645, "step": 339120 }, { "epoch": 28.19, "learning_rate": 2.431283429870022e-07, "loss": 0.7848, "step": 339130 }, { "epoch": 28.19, "learning_rate": 2.430174874594684e-07, "loss": 0.7434, "step": 339140 }, { "epoch": 28.19, "learning_rate": 2.429066319319347e-07, "loss": 0.6993, "step": 339150 }, { "epoch": 28.19, "learning_rate": 2.4279577640440096e-07, "loss": 0.7422, "step": 339160 }, { "epoch": 28.19, "learning_rate": 2.426849208768672e-07, "loss": 0.8021, "step": 339170 }, { "epoch": 28.19, "learning_rate": 2.425740653493335e-07, "loss": 0.7702, "step": 339180 }, { "epoch": 28.19, "learning_rate": 2.4246320982179974e-07, "loss": 0.7415, "step": 339190 }, { "epoch": 28.19, "learning_rate": 2.42352354294266e-07, "loss": 0.6936, "step": 339200 }, { "epoch": 28.19, "learning_rate": 2.422414987667322e-07, "loss": 0.7789, "step": 339210 }, { "epoch": 28.2, "learning_rate": 2.4213064323919847e-07, "loss": 0.6982, "step": 339220 }, { "epoch": 28.2, "learning_rate": 2.4201978771166476e-07, "loss": 0.7637, "step": 339230 }, { "epoch": 28.2, "learning_rate": 2.41908932184131e-07, "loss": 0.7757, "step": 339240 }, { "epoch": 28.2, "learning_rate": 2.4179807665659725e-07, "loss": 0.7476, "step": 339250 }, { "epoch": 28.2, "learning_rate": 2.4168722112906354e-07, "loss": 0.7726, "step": 339260 }, { "epoch": 28.2, "learning_rate": 2.415763656015298e-07, "loss": 0.7594, "step": 339270 }, { "epoch": 28.2, "learning_rate": 2.41465510073996e-07, "loss": 0.7694, "step": 339280 }, { "epoch": 28.2, "learning_rate": 2.413546545464623e-07, "loss": 0.7672, "step": 339290 }, { "epoch": 28.2, "learning_rate": 2.4124379901892856e-07, "loss": 0.736, "step": 339300 }, { "epoch": 28.2, "learning_rate": 2.411329434913948e-07, "loss": 0.729, "step": 339310 }, { "epoch": 28.2, "learning_rate": 2.410220879638611e-07, "loss": 0.744, "step": 339320 }, { "epoch": 28.2, "learning_rate": 2.4091123243632734e-07, "loss": 0.7374, "step": 339330 }, { "epoch": 28.21, "learning_rate": 2.408003769087936e-07, "loss": 0.6994, "step": 339340 }, { "epoch": 28.21, "learning_rate": 2.406895213812599e-07, "loss": 0.7161, "step": 339350 }, { "epoch": 28.21, "learning_rate": 2.405786658537261e-07, "loss": 0.7541, "step": 339360 }, { "epoch": 28.21, "learning_rate": 2.4046781032619237e-07, "loss": 0.6934, "step": 339370 }, { "epoch": 28.21, "learning_rate": 2.4035695479865866e-07, "loss": 0.7089, "step": 339380 }, { "epoch": 28.21, "learning_rate": 2.402460992711249e-07, "loss": 0.6866, "step": 339390 }, { "epoch": 28.21, "learning_rate": 2.4013524374359115e-07, "loss": 0.7476, "step": 339400 }, { "epoch": 28.21, "learning_rate": 2.4002438821605744e-07, "loss": 0.719, "step": 339410 }, { "epoch": 28.21, "learning_rate": 2.399135326885237e-07, "loss": 0.7518, "step": 339420 }, { "epoch": 28.21, "learning_rate": 2.3980267716098993e-07, "loss": 0.7844, "step": 339430 }, { "epoch": 28.21, "learning_rate": 2.3969182163345617e-07, "loss": 0.6714, "step": 339440 }, { "epoch": 28.21, "learning_rate": 2.395809661059224e-07, "loss": 0.718, "step": 339450 }, { "epoch": 28.22, "learning_rate": 2.394701105783887e-07, "loss": 0.7244, "step": 339460 }, { "epoch": 28.22, "learning_rate": 2.3935925505085495e-07, "loss": 0.7721, "step": 339470 }, { "epoch": 28.22, "learning_rate": 2.392483995233212e-07, "loss": 0.7409, "step": 339480 }, { "epoch": 28.22, "learning_rate": 2.391375439957875e-07, "loss": 0.7322, "step": 339490 }, { "epoch": 28.22, "learning_rate": 2.3902668846825373e-07, "loss": 0.7354, "step": 339500 }, { "epoch": 28.22, "learning_rate": 2.3891583294071997e-07, "loss": 0.7368, "step": 339510 }, { "epoch": 28.22, "learning_rate": 2.3880497741318627e-07, "loss": 0.7448, "step": 339520 }, { "epoch": 28.22, "learning_rate": 2.386941218856525e-07, "loss": 0.7618, "step": 339530 }, { "epoch": 28.22, "learning_rate": 2.3858326635811875e-07, "loss": 0.6906, "step": 339540 }, { "epoch": 28.22, "learning_rate": 2.3847241083058505e-07, "loss": 0.7533, "step": 339550 }, { "epoch": 28.22, "learning_rate": 2.383615553030513e-07, "loss": 0.7755, "step": 339560 }, { "epoch": 28.22, "learning_rate": 2.3825069977551753e-07, "loss": 0.7383, "step": 339570 }, { "epoch": 28.23, "learning_rate": 2.381398442479838e-07, "loss": 0.8307, "step": 339580 }, { "epoch": 28.23, "learning_rate": 2.3802898872045007e-07, "loss": 0.7335, "step": 339590 }, { "epoch": 28.23, "learning_rate": 2.379181331929163e-07, "loss": 0.738, "step": 339600 }, { "epoch": 28.23, "learning_rate": 2.3780727766538258e-07, "loss": 0.7606, "step": 339610 }, { "epoch": 28.23, "learning_rate": 2.3769642213784885e-07, "loss": 0.7154, "step": 339620 }, { "epoch": 28.23, "learning_rate": 2.375855666103151e-07, "loss": 0.7616, "step": 339630 }, { "epoch": 28.23, "learning_rate": 2.3747471108278136e-07, "loss": 0.7363, "step": 339640 }, { "epoch": 28.23, "learning_rate": 2.373638555552476e-07, "loss": 0.7166, "step": 339650 }, { "epoch": 28.23, "learning_rate": 2.3725300002771387e-07, "loss": 0.6601, "step": 339660 }, { "epoch": 28.23, "learning_rate": 2.3714214450018014e-07, "loss": 0.7577, "step": 339670 }, { "epoch": 28.23, "learning_rate": 2.3703128897264638e-07, "loss": 0.7287, "step": 339680 }, { "epoch": 28.23, "learning_rate": 2.3692043344511265e-07, "loss": 0.7397, "step": 339690 }, { "epoch": 28.24, "learning_rate": 2.3680957791757892e-07, "loss": 0.7736, "step": 339700 }, { "epoch": 28.24, "learning_rate": 2.3669872239004516e-07, "loss": 0.7178, "step": 339710 }, { "epoch": 28.24, "learning_rate": 2.3658786686251143e-07, "loss": 0.7297, "step": 339720 }, { "epoch": 28.24, "learning_rate": 2.3647701133497768e-07, "loss": 0.7962, "step": 339730 }, { "epoch": 28.24, "learning_rate": 2.3636615580744392e-07, "loss": 0.7734, "step": 339740 }, { "epoch": 28.24, "learning_rate": 2.3625530027991019e-07, "loss": 0.6864, "step": 339750 }, { "epoch": 28.24, "learning_rate": 2.3614444475237646e-07, "loss": 0.742, "step": 339760 }, { "epoch": 28.24, "learning_rate": 2.360335892248427e-07, "loss": 0.7116, "step": 339770 }, { "epoch": 28.24, "learning_rate": 2.3592273369730897e-07, "loss": 0.6995, "step": 339780 }, { "epoch": 28.24, "learning_rate": 2.3581187816977524e-07, "loss": 0.7383, "step": 339790 }, { "epoch": 28.24, "learning_rate": 2.3570102264224148e-07, "loss": 0.7058, "step": 339800 }, { "epoch": 28.24, "learning_rate": 2.3559016711470775e-07, "loss": 0.6983, "step": 339810 }, { "epoch": 28.25, "learning_rate": 2.3547931158717402e-07, "loss": 0.7345, "step": 339820 }, { "epoch": 28.25, "learning_rate": 2.3536845605964026e-07, "loss": 0.7477, "step": 339830 }, { "epoch": 28.25, "learning_rate": 2.3525760053210653e-07, "loss": 0.7423, "step": 339840 }, { "epoch": 28.25, "learning_rate": 2.3514674500457277e-07, "loss": 0.6621, "step": 339850 }, { "epoch": 28.25, "learning_rate": 2.3503588947703904e-07, "loss": 0.7099, "step": 339860 }, { "epoch": 28.25, "learning_rate": 2.349250339495053e-07, "loss": 0.7283, "step": 339870 }, { "epoch": 28.25, "learning_rate": 2.3481417842197155e-07, "loss": 0.7005, "step": 339880 }, { "epoch": 28.25, "learning_rate": 2.3470332289443782e-07, "loss": 0.7314, "step": 339890 }, { "epoch": 28.25, "learning_rate": 2.345924673669041e-07, "loss": 0.6996, "step": 339900 }, { "epoch": 28.25, "learning_rate": 2.3448161183937033e-07, "loss": 0.7203, "step": 339910 }, { "epoch": 28.25, "learning_rate": 2.343707563118366e-07, "loss": 0.7222, "step": 339920 }, { "epoch": 28.25, "learning_rate": 2.3425990078430287e-07, "loss": 0.7714, "step": 339930 }, { "epoch": 28.26, "learning_rate": 2.3414904525676908e-07, "loss": 0.7136, "step": 339940 }, { "epoch": 28.26, "learning_rate": 2.3403818972923535e-07, "loss": 0.7347, "step": 339950 }, { "epoch": 28.26, "learning_rate": 2.3392733420170162e-07, "loss": 0.7394, "step": 339960 }, { "epoch": 28.26, "learning_rate": 2.3381647867416786e-07, "loss": 0.7463, "step": 339970 }, { "epoch": 28.26, "learning_rate": 2.3370562314663413e-07, "loss": 0.7389, "step": 339980 }, { "epoch": 28.26, "learning_rate": 2.335947676191004e-07, "loss": 0.7016, "step": 339990 }, { "epoch": 28.26, "learning_rate": 2.3348391209156664e-07, "loss": 0.7141, "step": 340000 }, { "epoch": 28.26, "learning_rate": 2.333730565640329e-07, "loss": 0.7747, "step": 340010 }, { "epoch": 28.26, "learning_rate": 2.3326220103649918e-07, "loss": 0.7376, "step": 340020 }, { "epoch": 28.26, "learning_rate": 2.3315134550896542e-07, "loss": 0.76, "step": 340030 }, { "epoch": 28.26, "learning_rate": 2.330404899814317e-07, "loss": 0.6924, "step": 340040 }, { "epoch": 28.26, "learning_rate": 2.3292963445389796e-07, "loss": 0.7487, "step": 340050 }, { "epoch": 28.27, "learning_rate": 2.328187789263642e-07, "loss": 0.7358, "step": 340060 }, { "epoch": 28.27, "learning_rate": 2.3270792339883047e-07, "loss": 0.7495, "step": 340070 }, { "epoch": 28.27, "learning_rate": 2.3259706787129672e-07, "loss": 0.7064, "step": 340080 }, { "epoch": 28.27, "learning_rate": 2.3248621234376298e-07, "loss": 0.7621, "step": 340090 }, { "epoch": 28.27, "learning_rate": 2.3237535681622925e-07, "loss": 0.7122, "step": 340100 }, { "epoch": 28.27, "learning_rate": 2.322645012886955e-07, "loss": 0.7253, "step": 340110 }, { "epoch": 28.27, "learning_rate": 2.3215364576116176e-07, "loss": 0.7621, "step": 340120 }, { "epoch": 28.27, "learning_rate": 2.3204279023362803e-07, "loss": 0.7497, "step": 340130 }, { "epoch": 28.27, "learning_rate": 2.3193193470609425e-07, "loss": 0.7022, "step": 340140 }, { "epoch": 28.27, "learning_rate": 2.3182107917856052e-07, "loss": 0.7618, "step": 340150 }, { "epoch": 28.27, "learning_rate": 2.317102236510268e-07, "loss": 0.7306, "step": 340160 }, { "epoch": 28.27, "learning_rate": 2.3159936812349303e-07, "loss": 0.7464, "step": 340170 }, { "epoch": 28.28, "learning_rate": 2.314885125959593e-07, "loss": 0.7078, "step": 340180 }, { "epoch": 28.28, "learning_rate": 2.3137765706842557e-07, "loss": 0.7794, "step": 340190 }, { "epoch": 28.28, "learning_rate": 2.312668015408918e-07, "loss": 0.7354, "step": 340200 }, { "epoch": 28.28, "learning_rate": 2.3115594601335808e-07, "loss": 0.7111, "step": 340210 }, { "epoch": 28.28, "learning_rate": 2.3104509048582435e-07, "loss": 0.7343, "step": 340220 }, { "epoch": 28.28, "learning_rate": 2.309342349582906e-07, "loss": 0.7588, "step": 340230 }, { "epoch": 28.28, "learning_rate": 2.3082337943075686e-07, "loss": 0.7527, "step": 340240 }, { "epoch": 28.28, "learning_rate": 2.3071252390322313e-07, "loss": 0.7233, "step": 340250 }, { "epoch": 28.28, "learning_rate": 2.3060166837568937e-07, "loss": 0.7345, "step": 340260 }, { "epoch": 28.28, "learning_rate": 2.3049081284815564e-07, "loss": 0.7777, "step": 340270 }, { "epoch": 28.28, "learning_rate": 2.3037995732062188e-07, "loss": 0.7686, "step": 340280 }, { "epoch": 28.28, "learning_rate": 2.3026910179308815e-07, "loss": 0.6813, "step": 340290 }, { "epoch": 28.29, "learning_rate": 2.3015824626555442e-07, "loss": 0.7089, "step": 340300 }, { "epoch": 28.29, "learning_rate": 2.3004739073802066e-07, "loss": 0.719, "step": 340310 }, { "epoch": 28.29, "learning_rate": 2.2993653521048693e-07, "loss": 0.7482, "step": 340320 }, { "epoch": 28.29, "learning_rate": 2.298256796829532e-07, "loss": 0.7197, "step": 340330 }, { "epoch": 28.29, "learning_rate": 2.2971482415541944e-07, "loss": 0.6702, "step": 340340 }, { "epoch": 28.29, "learning_rate": 2.296039686278857e-07, "loss": 0.682, "step": 340350 }, { "epoch": 28.29, "learning_rate": 2.2949311310035195e-07, "loss": 0.7456, "step": 340360 }, { "epoch": 28.29, "learning_rate": 2.293822575728182e-07, "loss": 0.721, "step": 340370 }, { "epoch": 28.29, "learning_rate": 2.2927140204528446e-07, "loss": 0.8175, "step": 340380 }, { "epoch": 28.29, "learning_rate": 2.2916054651775073e-07, "loss": 0.7501, "step": 340390 }, { "epoch": 28.29, "learning_rate": 2.2904969099021697e-07, "loss": 0.7292, "step": 340400 }, { "epoch": 28.29, "learning_rate": 2.2893883546268324e-07, "loss": 0.7678, "step": 340410 }, { "epoch": 28.3, "learning_rate": 2.288279799351495e-07, "loss": 0.6786, "step": 340420 }, { "epoch": 28.3, "learning_rate": 2.2871712440761576e-07, "loss": 0.769, "step": 340430 }, { "epoch": 28.3, "learning_rate": 2.2860626888008202e-07, "loss": 0.7432, "step": 340440 }, { "epoch": 28.3, "learning_rate": 2.284954133525483e-07, "loss": 0.7132, "step": 340450 }, { "epoch": 28.3, "learning_rate": 2.2838455782501454e-07, "loss": 0.6854, "step": 340460 }, { "epoch": 28.3, "learning_rate": 2.282737022974808e-07, "loss": 0.7362, "step": 340470 }, { "epoch": 28.3, "learning_rate": 2.2816284676994705e-07, "loss": 0.7114, "step": 340480 }, { "epoch": 28.3, "learning_rate": 2.2805199124241332e-07, "loss": 0.7219, "step": 340490 }, { "epoch": 28.3, "learning_rate": 2.2794113571487958e-07, "loss": 0.7525, "step": 340500 }, { "epoch": 28.3, "learning_rate": 2.2783028018734583e-07, "loss": 0.7255, "step": 340510 }, { "epoch": 28.3, "learning_rate": 2.277194246598121e-07, "loss": 0.725, "step": 340520 }, { "epoch": 28.3, "learning_rate": 2.2760856913227836e-07, "loss": 0.7738, "step": 340530 }, { "epoch": 28.31, "learning_rate": 2.274977136047446e-07, "loss": 0.8094, "step": 340540 }, { "epoch": 28.31, "learning_rate": 2.2738685807721088e-07, "loss": 0.6829, "step": 340550 }, { "epoch": 28.31, "learning_rate": 2.2727600254967714e-07, "loss": 0.6901, "step": 340560 }, { "epoch": 28.31, "learning_rate": 2.2716514702214336e-07, "loss": 0.7372, "step": 340570 }, { "epoch": 28.31, "learning_rate": 2.2705429149460963e-07, "loss": 0.7794, "step": 340580 }, { "epoch": 28.31, "learning_rate": 2.269434359670759e-07, "loss": 0.7701, "step": 340590 }, { "epoch": 28.31, "learning_rate": 2.2683258043954214e-07, "loss": 0.7071, "step": 340600 }, { "epoch": 28.31, "learning_rate": 2.267217249120084e-07, "loss": 0.709, "step": 340610 }, { "epoch": 28.31, "learning_rate": 2.2661086938447468e-07, "loss": 0.7647, "step": 340620 }, { "epoch": 28.31, "learning_rate": 2.2650001385694092e-07, "loss": 0.8221, "step": 340630 }, { "epoch": 28.31, "learning_rate": 2.263891583294072e-07, "loss": 0.719, "step": 340640 }, { "epoch": 28.31, "learning_rate": 2.2627830280187346e-07, "loss": 0.7508, "step": 340650 }, { "epoch": 28.32, "learning_rate": 2.261674472743397e-07, "loss": 0.7179, "step": 340660 }, { "epoch": 28.32, "learning_rate": 2.2605659174680597e-07, "loss": 0.7594, "step": 340670 }, { "epoch": 28.32, "learning_rate": 2.259457362192722e-07, "loss": 0.7851, "step": 340680 }, { "epoch": 28.32, "learning_rate": 2.2583488069173848e-07, "loss": 0.6962, "step": 340690 }, { "epoch": 28.32, "learning_rate": 2.2572402516420475e-07, "loss": 0.7414, "step": 340700 }, { "epoch": 28.32, "learning_rate": 2.25613169636671e-07, "loss": 0.734, "step": 340710 }, { "epoch": 28.32, "learning_rate": 2.2550231410913726e-07, "loss": 0.7657, "step": 340720 }, { "epoch": 28.32, "learning_rate": 2.2539145858160353e-07, "loss": 0.7318, "step": 340730 }, { "epoch": 28.32, "learning_rate": 2.2528060305406977e-07, "loss": 0.7085, "step": 340740 }, { "epoch": 28.32, "learning_rate": 2.2516974752653604e-07, "loss": 0.6964, "step": 340750 }, { "epoch": 28.32, "learning_rate": 2.250588919990023e-07, "loss": 0.7106, "step": 340760 }, { "epoch": 28.32, "learning_rate": 2.2494803647146853e-07, "loss": 0.7168, "step": 340770 }, { "epoch": 28.33, "learning_rate": 2.248371809439348e-07, "loss": 0.759, "step": 340780 }, { "epoch": 28.33, "learning_rate": 2.2472632541640106e-07, "loss": 0.7723, "step": 340790 }, { "epoch": 28.33, "learning_rate": 2.246154698888673e-07, "loss": 0.7835, "step": 340800 }, { "epoch": 28.33, "learning_rate": 2.2450461436133358e-07, "loss": 0.724, "step": 340810 }, { "epoch": 28.33, "learning_rate": 2.2439375883379984e-07, "loss": 0.7155, "step": 340820 }, { "epoch": 28.33, "learning_rate": 2.2428290330626609e-07, "loss": 0.7488, "step": 340830 }, { "epoch": 28.33, "learning_rate": 2.2417204777873236e-07, "loss": 0.7128, "step": 340840 }, { "epoch": 28.33, "learning_rate": 2.2406119225119862e-07, "loss": 0.6768, "step": 340850 }, { "epoch": 28.33, "learning_rate": 2.2395033672366487e-07, "loss": 0.7617, "step": 340860 }, { "epoch": 28.33, "learning_rate": 2.2383948119613114e-07, "loss": 0.7945, "step": 340870 }, { "epoch": 28.33, "learning_rate": 2.237286256685974e-07, "loss": 0.701, "step": 340880 }, { "epoch": 28.33, "learning_rate": 2.2361777014106365e-07, "loss": 0.8004, "step": 340890 }, { "epoch": 28.34, "learning_rate": 2.2350691461352992e-07, "loss": 0.7946, "step": 340900 }, { "epoch": 28.34, "learning_rate": 2.2339605908599616e-07, "loss": 0.7182, "step": 340910 }, { "epoch": 28.34, "learning_rate": 2.2329628911121578e-07, "loss": 0.6626, "step": 340920 }, { "epoch": 28.34, "learning_rate": 2.2318543358368204e-07, "loss": 0.7658, "step": 340930 }, { "epoch": 28.34, "learning_rate": 2.2307457805614831e-07, "loss": 0.6996, "step": 340940 }, { "epoch": 28.34, "learning_rate": 2.2296372252861456e-07, "loss": 0.758, "step": 340950 }, { "epoch": 28.34, "learning_rate": 2.2285286700108083e-07, "loss": 0.7303, "step": 340960 }, { "epoch": 28.34, "learning_rate": 2.227420114735471e-07, "loss": 0.7059, "step": 340970 }, { "epoch": 28.34, "learning_rate": 2.2263115594601334e-07, "loss": 0.7279, "step": 340980 }, { "epoch": 28.34, "learning_rate": 2.225203004184796e-07, "loss": 0.8109, "step": 340990 }, { "epoch": 28.34, "learning_rate": 2.2240944489094587e-07, "loss": 0.71, "step": 341000 }, { "epoch": 28.34, "learning_rate": 2.2229858936341212e-07, "loss": 0.7086, "step": 341010 }, { "epoch": 28.35, "learning_rate": 2.2218773383587839e-07, "loss": 0.732, "step": 341020 }, { "epoch": 28.35, "learning_rate": 2.2207687830834465e-07, "loss": 0.7636, "step": 341030 }, { "epoch": 28.35, "learning_rate": 2.219660227808109e-07, "loss": 0.7172, "step": 341040 }, { "epoch": 28.35, "learning_rate": 2.2185516725327717e-07, "loss": 0.6953, "step": 341050 }, { "epoch": 28.35, "learning_rate": 2.2174431172574343e-07, "loss": 0.723, "step": 341060 }, { "epoch": 28.35, "learning_rate": 2.2163345619820968e-07, "loss": 0.7875, "step": 341070 }, { "epoch": 28.35, "learning_rate": 2.2152260067067595e-07, "loss": 0.7393, "step": 341080 }, { "epoch": 28.35, "learning_rate": 2.2141174514314221e-07, "loss": 0.7101, "step": 341090 }, { "epoch": 28.35, "learning_rate": 2.2130088961560846e-07, "loss": 0.7575, "step": 341100 }, { "epoch": 28.35, "learning_rate": 2.211900340880747e-07, "loss": 0.6884, "step": 341110 }, { "epoch": 28.35, "learning_rate": 2.2107917856054094e-07, "loss": 0.7367, "step": 341120 }, { "epoch": 28.35, "learning_rate": 2.209683230330072e-07, "loss": 0.6993, "step": 341130 }, { "epoch": 28.36, "learning_rate": 2.2085746750547348e-07, "loss": 0.7302, "step": 341140 }, { "epoch": 28.36, "learning_rate": 2.2074661197793972e-07, "loss": 0.7218, "step": 341150 }, { "epoch": 28.36, "learning_rate": 2.20635756450406e-07, "loss": 0.6954, "step": 341160 }, { "epoch": 28.36, "learning_rate": 2.2052490092287226e-07, "loss": 0.718, "step": 341170 }, { "epoch": 28.36, "learning_rate": 2.204140453953385e-07, "loss": 0.759, "step": 341180 }, { "epoch": 28.36, "learning_rate": 2.2030318986780477e-07, "loss": 0.7274, "step": 341190 }, { "epoch": 28.36, "learning_rate": 2.2019233434027104e-07, "loss": 0.702, "step": 341200 }, { "epoch": 28.36, "learning_rate": 2.2008147881273728e-07, "loss": 0.7424, "step": 341210 }, { "epoch": 28.36, "learning_rate": 2.1997062328520355e-07, "loss": 0.7352, "step": 341220 }, { "epoch": 28.36, "learning_rate": 2.1985976775766982e-07, "loss": 0.8029, "step": 341230 }, { "epoch": 28.36, "learning_rate": 2.1974891223013606e-07, "loss": 0.7405, "step": 341240 }, { "epoch": 28.36, "learning_rate": 2.1963805670260233e-07, "loss": 0.7689, "step": 341250 }, { "epoch": 28.37, "learning_rate": 2.195272011750686e-07, "loss": 0.7631, "step": 341260 }, { "epoch": 28.37, "learning_rate": 2.1941634564753484e-07, "loss": 0.7415, "step": 341270 }, { "epoch": 28.37, "learning_rate": 2.193054901200011e-07, "loss": 0.7522, "step": 341280 }, { "epoch": 28.37, "learning_rate": 2.1919463459246738e-07, "loss": 0.7165, "step": 341290 }, { "epoch": 28.37, "learning_rate": 2.1908377906493362e-07, "loss": 0.7159, "step": 341300 }, { "epoch": 28.37, "learning_rate": 2.189729235373999e-07, "loss": 0.695, "step": 341310 }, { "epoch": 28.37, "learning_rate": 2.188620680098661e-07, "loss": 0.7746, "step": 341320 }, { "epoch": 28.37, "learning_rate": 2.1875121248233238e-07, "loss": 0.7608, "step": 341330 }, { "epoch": 28.37, "learning_rate": 2.1864035695479864e-07, "loss": 0.7166, "step": 341340 }, { "epoch": 28.37, "learning_rate": 2.185295014272649e-07, "loss": 0.7194, "step": 341350 }, { "epoch": 28.37, "learning_rate": 2.1841864589973116e-07, "loss": 0.759, "step": 341360 }, { "epoch": 28.37, "learning_rate": 2.1830779037219743e-07, "loss": 0.7664, "step": 341370 }, { "epoch": 28.38, "learning_rate": 2.1819693484466367e-07, "loss": 0.7008, "step": 341380 }, { "epoch": 28.38, "learning_rate": 2.1808607931712994e-07, "loss": 0.6993, "step": 341390 }, { "epoch": 28.38, "learning_rate": 2.179752237895962e-07, "loss": 0.7204, "step": 341400 }, { "epoch": 28.38, "learning_rate": 2.1786436826206245e-07, "loss": 0.7977, "step": 341410 }, { "epoch": 28.38, "learning_rate": 2.1775351273452872e-07, "loss": 0.7674, "step": 341420 }, { "epoch": 28.38, "learning_rate": 2.1764265720699499e-07, "loss": 0.7074, "step": 341430 }, { "epoch": 28.38, "learning_rate": 2.1753180167946123e-07, "loss": 0.7783, "step": 341440 }, { "epoch": 28.38, "learning_rate": 2.174209461519275e-07, "loss": 0.7501, "step": 341450 }, { "epoch": 28.38, "learning_rate": 2.1731009062439377e-07, "loss": 0.6711, "step": 341460 }, { "epoch": 28.38, "learning_rate": 2.1719923509686e-07, "loss": 0.789, "step": 341470 }, { "epoch": 28.38, "learning_rate": 2.1708837956932628e-07, "loss": 0.7543, "step": 341480 }, { "epoch": 28.38, "learning_rate": 2.1697752404179255e-07, "loss": 0.7029, "step": 341490 }, { "epoch": 28.39, "learning_rate": 2.168666685142588e-07, "loss": 0.7563, "step": 341500 }, { "epoch": 28.39, "learning_rate": 2.1675581298672506e-07, "loss": 0.7039, "step": 341510 }, { "epoch": 28.39, "learning_rate": 2.1664495745919127e-07, "loss": 0.769, "step": 341520 }, { "epoch": 28.39, "learning_rate": 2.1653410193165754e-07, "loss": 0.7821, "step": 341530 }, { "epoch": 28.39, "learning_rate": 2.164232464041238e-07, "loss": 0.6658, "step": 341540 }, { "epoch": 28.39, "learning_rate": 2.1631239087659005e-07, "loss": 0.6929, "step": 341550 }, { "epoch": 28.39, "learning_rate": 2.1620153534905632e-07, "loss": 0.7649, "step": 341560 }, { "epoch": 28.39, "learning_rate": 2.160906798215226e-07, "loss": 0.7063, "step": 341570 }, { "epoch": 28.39, "learning_rate": 2.1597982429398883e-07, "loss": 0.7303, "step": 341580 }, { "epoch": 28.39, "learning_rate": 2.158689687664551e-07, "loss": 0.7431, "step": 341590 }, { "epoch": 28.39, "learning_rate": 2.1575811323892137e-07, "loss": 0.7633, "step": 341600 }, { "epoch": 28.39, "learning_rate": 2.1564725771138761e-07, "loss": 0.7375, "step": 341610 }, { "epoch": 28.39, "learning_rate": 2.1553640218385388e-07, "loss": 0.7023, "step": 341620 }, { "epoch": 28.4, "learning_rate": 2.1542554665632015e-07, "loss": 0.7275, "step": 341630 }, { "epoch": 28.4, "learning_rate": 2.153146911287864e-07, "loss": 0.7542, "step": 341640 }, { "epoch": 28.4, "learning_rate": 2.1520383560125266e-07, "loss": 0.6895, "step": 341650 }, { "epoch": 28.4, "learning_rate": 2.1509298007371893e-07, "loss": 0.7338, "step": 341660 }, { "epoch": 28.4, "learning_rate": 2.1498212454618517e-07, "loss": 0.786, "step": 341670 }, { "epoch": 28.4, "learning_rate": 2.1487126901865144e-07, "loss": 0.7856, "step": 341680 }, { "epoch": 28.4, "learning_rate": 2.1477149904387106e-07, "loss": 0.7567, "step": 341690 }, { "epoch": 28.4, "learning_rate": 2.1466064351633733e-07, "loss": 0.7088, "step": 341700 }, { "epoch": 28.4, "learning_rate": 2.1454978798880357e-07, "loss": 0.6798, "step": 341710 }, { "epoch": 28.4, "learning_rate": 2.1443893246126984e-07, "loss": 0.7288, "step": 341720 }, { "epoch": 28.4, "learning_rate": 2.1432807693373608e-07, "loss": 0.7185, "step": 341730 }, { "epoch": 28.4, "learning_rate": 2.1421722140620235e-07, "loss": 0.6841, "step": 341740 }, { "epoch": 28.41, "learning_rate": 2.1410636587866862e-07, "loss": 0.7051, "step": 341750 }, { "epoch": 28.41, "learning_rate": 2.1399551035113486e-07, "loss": 0.7556, "step": 341760 }, { "epoch": 28.41, "learning_rate": 2.1388465482360113e-07, "loss": 0.6426, "step": 341770 }, { "epoch": 28.41, "learning_rate": 2.137737992960674e-07, "loss": 0.7534, "step": 341780 }, { "epoch": 28.41, "learning_rate": 2.1366294376853364e-07, "loss": 0.7311, "step": 341790 }, { "epoch": 28.41, "learning_rate": 2.135520882409999e-07, "loss": 0.6966, "step": 341800 }, { "epoch": 28.41, "learning_rate": 2.1344123271346618e-07, "loss": 0.7346, "step": 341810 }, { "epoch": 28.41, "learning_rate": 2.1333037718593242e-07, "loss": 0.7408, "step": 341820 }, { "epoch": 28.41, "learning_rate": 2.132195216583987e-07, "loss": 0.7955, "step": 341830 }, { "epoch": 28.41, "learning_rate": 2.1310866613086496e-07, "loss": 0.7529, "step": 341840 }, { "epoch": 28.41, "learning_rate": 2.129978106033312e-07, "loss": 0.741, "step": 341850 }, { "epoch": 28.41, "learning_rate": 2.1288695507579745e-07, "loss": 0.6982, "step": 341860 }, { "epoch": 28.42, "learning_rate": 2.1277609954826371e-07, "loss": 0.7344, "step": 341870 }, { "epoch": 28.42, "learning_rate": 2.1266524402072996e-07, "loss": 0.7746, "step": 341880 }, { "epoch": 28.42, "learning_rate": 2.1255438849319623e-07, "loss": 0.736, "step": 341890 }, { "epoch": 28.42, "learning_rate": 2.124435329656625e-07, "loss": 0.7246, "step": 341900 }, { "epoch": 28.42, "learning_rate": 2.1233267743812874e-07, "loss": 0.7175, "step": 341910 }, { "epoch": 28.42, "learning_rate": 2.12221821910595e-07, "loss": 0.7258, "step": 341920 }, { "epoch": 28.42, "learning_rate": 2.1211096638306128e-07, "loss": 0.7504, "step": 341930 }, { "epoch": 28.42, "learning_rate": 2.1200011085552752e-07, "loss": 0.7199, "step": 341940 }, { "epoch": 28.42, "learning_rate": 2.1188925532799379e-07, "loss": 0.7535, "step": 341950 }, { "epoch": 28.42, "learning_rate": 2.1177839980046003e-07, "loss": 0.7152, "step": 341960 }, { "epoch": 28.42, "learning_rate": 2.116675442729263e-07, "loss": 0.679, "step": 341970 }, { "epoch": 28.42, "learning_rate": 2.1155668874539257e-07, "loss": 0.7467, "step": 341980 }, { "epoch": 28.43, "learning_rate": 2.114458332178588e-07, "loss": 0.7304, "step": 341990 }, { "epoch": 28.43, "learning_rate": 2.1133497769032508e-07, "loss": 0.7601, "step": 342000 }, { "epoch": 28.43, "learning_rate": 2.1122412216279135e-07, "loss": 0.6725, "step": 342010 }, { "epoch": 28.43, "learning_rate": 2.111132666352576e-07, "loss": 0.8049, "step": 342020 }, { "epoch": 28.43, "learning_rate": 2.1100241110772386e-07, "loss": 0.7674, "step": 342030 }, { "epoch": 28.43, "learning_rate": 2.1089155558019013e-07, "loss": 0.7699, "step": 342040 }, { "epoch": 28.43, "learning_rate": 2.1078070005265637e-07, "loss": 0.7257, "step": 342050 }, { "epoch": 28.43, "learning_rate": 2.1066984452512264e-07, "loss": 0.7111, "step": 342060 }, { "epoch": 28.43, "learning_rate": 2.1055898899758888e-07, "loss": 0.7408, "step": 342070 }, { "epoch": 28.43, "learning_rate": 2.1044813347005512e-07, "loss": 0.7705, "step": 342080 }, { "epoch": 28.43, "learning_rate": 2.103372779425214e-07, "loss": 0.7182, "step": 342090 }, { "epoch": 28.43, "learning_rate": 2.1022642241498766e-07, "loss": 0.7269, "step": 342100 }, { "epoch": 28.44, "learning_rate": 2.101155668874539e-07, "loss": 0.675, "step": 342110 }, { "epoch": 28.44, "learning_rate": 2.1000471135992017e-07, "loss": 0.7509, "step": 342120 }, { "epoch": 28.44, "learning_rate": 2.0989385583238644e-07, "loss": 0.7331, "step": 342130 }, { "epoch": 28.44, "learning_rate": 2.0978300030485268e-07, "loss": 0.6825, "step": 342140 }, { "epoch": 28.44, "learning_rate": 2.0967214477731895e-07, "loss": 0.7348, "step": 342150 }, { "epoch": 28.44, "learning_rate": 2.095612892497852e-07, "loss": 0.7243, "step": 342160 }, { "epoch": 28.44, "learning_rate": 2.0945043372225146e-07, "loss": 0.7826, "step": 342170 }, { "epoch": 28.44, "learning_rate": 2.0933957819471773e-07, "loss": 0.7928, "step": 342180 }, { "epoch": 28.44, "learning_rate": 2.0922872266718397e-07, "loss": 0.7624, "step": 342190 }, { "epoch": 28.44, "learning_rate": 2.0911786713965024e-07, "loss": 0.7286, "step": 342200 }, { "epoch": 28.44, "learning_rate": 2.090070116121165e-07, "loss": 0.744, "step": 342210 }, { "epoch": 28.44, "learning_rate": 2.0889615608458275e-07, "loss": 0.7361, "step": 342220 }, { "epoch": 28.45, "learning_rate": 2.0878530055704902e-07, "loss": 0.7715, "step": 342230 }, { "epoch": 28.45, "learning_rate": 2.086744450295153e-07, "loss": 0.7424, "step": 342240 }, { "epoch": 28.45, "learning_rate": 2.0856358950198153e-07, "loss": 0.7689, "step": 342250 }, { "epoch": 28.45, "learning_rate": 2.084527339744478e-07, "loss": 0.7741, "step": 342260 }, { "epoch": 28.45, "learning_rate": 2.0834187844691407e-07, "loss": 0.7248, "step": 342270 }, { "epoch": 28.45, "learning_rate": 2.082310229193803e-07, "loss": 0.777, "step": 342280 }, { "epoch": 28.45, "learning_rate": 2.0812016739184656e-07, "loss": 0.7661, "step": 342290 }, { "epoch": 28.45, "learning_rate": 2.0800931186431283e-07, "loss": 0.7924, "step": 342300 }, { "epoch": 28.45, "learning_rate": 2.0789845633677907e-07, "loss": 0.7122, "step": 342310 }, { "epoch": 28.45, "learning_rate": 2.0778760080924534e-07, "loss": 0.7299, "step": 342320 }, { "epoch": 28.45, "learning_rate": 2.076767452817116e-07, "loss": 0.7949, "step": 342330 }, { "epoch": 28.45, "learning_rate": 2.0756588975417785e-07, "loss": 0.734, "step": 342340 }, { "epoch": 28.46, "learning_rate": 2.0745503422664412e-07, "loss": 0.7044, "step": 342350 }, { "epoch": 28.46, "learning_rate": 2.0734417869911036e-07, "loss": 0.7161, "step": 342360 }, { "epoch": 28.46, "learning_rate": 2.0723332317157663e-07, "loss": 0.7025, "step": 342370 }, { "epoch": 28.46, "learning_rate": 2.071224676440429e-07, "loss": 0.7601, "step": 342380 }, { "epoch": 28.46, "learning_rate": 2.0701161211650914e-07, "loss": 0.7058, "step": 342390 }, { "epoch": 28.46, "learning_rate": 2.069007565889754e-07, "loss": 0.6982, "step": 342400 }, { "epoch": 28.46, "learning_rate": 2.0678990106144168e-07, "loss": 0.7736, "step": 342410 }, { "epoch": 28.46, "learning_rate": 2.0667904553390792e-07, "loss": 0.7286, "step": 342420 }, { "epoch": 28.46, "learning_rate": 2.065681900063742e-07, "loss": 0.7466, "step": 342430 }, { "epoch": 28.46, "learning_rate": 2.0645733447884046e-07, "loss": 0.7409, "step": 342440 }, { "epoch": 28.46, "learning_rate": 2.063464789513067e-07, "loss": 0.6819, "step": 342450 }, { "epoch": 28.46, "learning_rate": 2.0623562342377297e-07, "loss": 0.7649, "step": 342460 }, { "epoch": 28.47, "learning_rate": 2.0612476789623924e-07, "loss": 0.7571, "step": 342470 }, { "epoch": 28.47, "learning_rate": 2.0601391236870545e-07, "loss": 0.8064, "step": 342480 }, { "epoch": 28.47, "learning_rate": 2.0590305684117172e-07, "loss": 0.7254, "step": 342490 }, { "epoch": 28.47, "learning_rate": 2.05792201313638e-07, "loss": 0.7527, "step": 342500 }, { "epoch": 28.47, "learning_rate": 2.0568134578610423e-07, "loss": 0.7389, "step": 342510 }, { "epoch": 28.47, "learning_rate": 2.055704902585705e-07, "loss": 0.7183, "step": 342520 }, { "epoch": 28.47, "learning_rate": 2.0545963473103677e-07, "loss": 0.8085, "step": 342530 }, { "epoch": 28.47, "learning_rate": 2.0534877920350301e-07, "loss": 0.6133, "step": 342540 }, { "epoch": 28.47, "learning_rate": 2.0523792367596928e-07, "loss": 0.714, "step": 342550 }, { "epoch": 28.47, "learning_rate": 2.0512706814843555e-07, "loss": 0.6767, "step": 342560 }, { "epoch": 28.47, "learning_rate": 2.050162126209018e-07, "loss": 0.6985, "step": 342570 }, { "epoch": 28.47, "learning_rate": 2.0490535709336806e-07, "loss": 0.7527, "step": 342580 }, { "epoch": 28.48, "learning_rate": 2.047945015658343e-07, "loss": 0.7067, "step": 342590 }, { "epoch": 28.48, "learning_rate": 2.0468364603830057e-07, "loss": 0.7449, "step": 342600 }, { "epoch": 28.48, "learning_rate": 2.0457279051076684e-07, "loss": 0.7111, "step": 342610 }, { "epoch": 28.48, "learning_rate": 2.0446193498323309e-07, "loss": 0.726, "step": 342620 }, { "epoch": 28.48, "learning_rate": 2.0435107945569935e-07, "loss": 0.7508, "step": 342630 }, { "epoch": 28.48, "learning_rate": 2.0424022392816562e-07, "loss": 0.7305, "step": 342640 }, { "epoch": 28.48, "learning_rate": 2.0412936840063187e-07, "loss": 0.7014, "step": 342650 }, { "epoch": 28.48, "learning_rate": 2.0401851287309813e-07, "loss": 0.6771, "step": 342660 }, { "epoch": 28.48, "learning_rate": 2.039076573455644e-07, "loss": 0.7115, "step": 342670 }, { "epoch": 28.48, "learning_rate": 2.0379680181803065e-07, "loss": 0.7446, "step": 342680 }, { "epoch": 28.48, "learning_rate": 2.036859462904969e-07, "loss": 0.7975, "step": 342690 }, { "epoch": 28.48, "learning_rate": 2.0357509076296316e-07, "loss": 0.7204, "step": 342700 }, { "epoch": 28.49, "learning_rate": 2.034642352354294e-07, "loss": 0.7654, "step": 342710 }, { "epoch": 28.49, "learning_rate": 2.0335337970789567e-07, "loss": 0.7126, "step": 342720 }, { "epoch": 28.49, "learning_rate": 2.0324252418036194e-07, "loss": 0.7339, "step": 342730 }, { "epoch": 28.49, "learning_rate": 2.0313166865282818e-07, "loss": 0.7151, "step": 342740 }, { "epoch": 28.49, "learning_rate": 2.0302081312529445e-07, "loss": 0.7388, "step": 342750 }, { "epoch": 28.49, "learning_rate": 2.0290995759776072e-07, "loss": 0.6878, "step": 342760 }, { "epoch": 28.49, "learning_rate": 2.0279910207022696e-07, "loss": 0.736, "step": 342770 }, { "epoch": 28.49, "learning_rate": 2.0268824654269323e-07, "loss": 0.7416, "step": 342780 }, { "epoch": 28.49, "learning_rate": 2.0257739101515947e-07, "loss": 0.7117, "step": 342790 }, { "epoch": 28.49, "learning_rate": 2.0246653548762574e-07, "loss": 0.7482, "step": 342800 }, { "epoch": 28.49, "learning_rate": 2.02355679960092e-07, "loss": 0.727, "step": 342810 }, { "epoch": 28.49, "learning_rate": 2.0224482443255825e-07, "loss": 0.7312, "step": 342820 }, { "epoch": 28.5, "learning_rate": 2.0213396890502452e-07, "loss": 0.7874, "step": 342830 }, { "epoch": 28.5, "learning_rate": 2.020231133774908e-07, "loss": 0.6894, "step": 342840 }, { "epoch": 28.5, "learning_rate": 2.0191225784995703e-07, "loss": 0.7053, "step": 342850 }, { "epoch": 28.5, "learning_rate": 2.018014023224233e-07, "loss": 0.7113, "step": 342860 }, { "epoch": 28.5, "learning_rate": 2.0169054679488957e-07, "loss": 0.756, "step": 342870 }, { "epoch": 28.5, "learning_rate": 2.015796912673558e-07, "loss": 0.7659, "step": 342880 }, { "epoch": 28.5, "learning_rate": 2.0146883573982208e-07, "loss": 0.728, "step": 342890 }, { "epoch": 28.5, "learning_rate": 2.0135798021228835e-07, "loss": 0.778, "step": 342900 }, { "epoch": 28.5, "learning_rate": 2.0124712468475457e-07, "loss": 0.7264, "step": 342910 }, { "epoch": 28.5, "learning_rate": 2.0113626915722083e-07, "loss": 0.707, "step": 342920 }, { "epoch": 28.5, "learning_rate": 2.010254136296871e-07, "loss": 0.8004, "step": 342930 }, { "epoch": 28.5, "learning_rate": 2.0091455810215335e-07, "loss": 0.6631, "step": 342940 }, { "epoch": 28.51, "learning_rate": 2.0080370257461961e-07, "loss": 0.7196, "step": 342950 }, { "epoch": 28.51, "learning_rate": 2.0069284704708588e-07, "loss": 0.7118, "step": 342960 }, { "epoch": 28.51, "learning_rate": 2.0058199151955213e-07, "loss": 0.7764, "step": 342970 }, { "epoch": 28.51, "learning_rate": 2.004711359920184e-07, "loss": 0.6865, "step": 342980 }, { "epoch": 28.51, "learning_rate": 2.0036028046448464e-07, "loss": 0.7393, "step": 342990 }, { "epoch": 28.51, "learning_rate": 2.002494249369509e-07, "loss": 0.7274, "step": 343000 }, { "epoch": 28.51, "learning_rate": 2.0013856940941717e-07, "loss": 0.7215, "step": 343010 }, { "epoch": 28.51, "learning_rate": 2.0002771388188342e-07, "loss": 0.6862, "step": 343020 }, { "epoch": 28.51, "learning_rate": 1.9991685835434969e-07, "loss": 0.7254, "step": 343030 }, { "epoch": 28.51, "learning_rate": 1.9980600282681595e-07, "loss": 0.6922, "step": 343040 }, { "epoch": 28.51, "learning_rate": 1.996951472992822e-07, "loss": 0.7324, "step": 343050 }, { "epoch": 28.51, "learning_rate": 1.9958429177174847e-07, "loss": 0.7698, "step": 343060 }, { "epoch": 28.52, "learning_rate": 1.9947343624421473e-07, "loss": 0.6701, "step": 343070 }, { "epoch": 28.52, "learning_rate": 1.9936258071668098e-07, "loss": 0.7564, "step": 343080 }, { "epoch": 28.52, "learning_rate": 1.9925172518914725e-07, "loss": 0.6909, "step": 343090 }, { "epoch": 28.52, "learning_rate": 1.9914086966161352e-07, "loss": 0.7068, "step": 343100 }, { "epoch": 28.52, "learning_rate": 1.9903001413407973e-07, "loss": 0.7411, "step": 343110 }, { "epoch": 28.52, "learning_rate": 1.98919158606546e-07, "loss": 0.7424, "step": 343120 }, { "epoch": 28.52, "learning_rate": 1.9880830307901227e-07, "loss": 0.7609, "step": 343130 }, { "epoch": 28.52, "learning_rate": 1.986974475514785e-07, "loss": 0.7433, "step": 343140 }, { "epoch": 28.52, "learning_rate": 1.9858659202394478e-07, "loss": 0.6743, "step": 343150 }, { "epoch": 28.52, "learning_rate": 1.9847573649641105e-07, "loss": 0.6844, "step": 343160 }, { "epoch": 28.52, "learning_rate": 1.983648809688773e-07, "loss": 0.7585, "step": 343170 }, { "epoch": 28.52, "learning_rate": 1.9825402544134356e-07, "loss": 0.7133, "step": 343180 }, { "epoch": 28.53, "learning_rate": 1.981431699138098e-07, "loss": 0.6826, "step": 343190 }, { "epoch": 28.53, "learning_rate": 1.9803231438627607e-07, "loss": 0.7305, "step": 343200 }, { "epoch": 28.53, "learning_rate": 1.9792145885874234e-07, "loss": 0.7167, "step": 343210 }, { "epoch": 28.53, "learning_rate": 1.9781060333120858e-07, "loss": 0.6718, "step": 343220 }, { "epoch": 28.53, "learning_rate": 1.9769974780367485e-07, "loss": 0.7979, "step": 343230 }, { "epoch": 28.53, "learning_rate": 1.9758889227614112e-07, "loss": 0.7311, "step": 343240 }, { "epoch": 28.53, "learning_rate": 1.9747803674860736e-07, "loss": 0.7475, "step": 343250 }, { "epoch": 28.53, "learning_rate": 1.9736718122107363e-07, "loss": 0.7449, "step": 343260 }, { "epoch": 28.53, "learning_rate": 1.972563256935399e-07, "loss": 0.7395, "step": 343270 }, { "epoch": 28.53, "learning_rate": 1.9714547016600614e-07, "loss": 0.7572, "step": 343280 }, { "epoch": 28.53, "learning_rate": 1.970346146384724e-07, "loss": 0.708, "step": 343290 }, { "epoch": 28.53, "learning_rate": 1.9692375911093868e-07, "loss": 0.7151, "step": 343300 }, { "epoch": 28.54, "learning_rate": 1.9681290358340492e-07, "loss": 0.7187, "step": 343310 }, { "epoch": 28.54, "learning_rate": 1.9670204805587117e-07, "loss": 0.7654, "step": 343320 }, { "epoch": 28.54, "learning_rate": 1.9659119252833743e-07, "loss": 0.7766, "step": 343330 }, { "epoch": 28.54, "learning_rate": 1.9648033700080368e-07, "loss": 0.7622, "step": 343340 }, { "epoch": 28.54, "learning_rate": 1.9636948147326995e-07, "loss": 0.7242, "step": 343350 }, { "epoch": 28.54, "learning_rate": 1.9625862594573621e-07, "loss": 0.7074, "step": 343360 }, { "epoch": 28.54, "learning_rate": 1.9614777041820246e-07, "loss": 0.7265, "step": 343370 }, { "epoch": 28.54, "learning_rate": 1.9603691489066873e-07, "loss": 0.7662, "step": 343380 }, { "epoch": 28.54, "learning_rate": 1.95926059363135e-07, "loss": 0.7154, "step": 343390 }, { "epoch": 28.54, "learning_rate": 1.9581520383560124e-07, "loss": 0.7369, "step": 343400 }, { "epoch": 28.54, "learning_rate": 1.957043483080675e-07, "loss": 0.7344, "step": 343410 }, { "epoch": 28.54, "learning_rate": 1.9559349278053375e-07, "loss": 0.709, "step": 343420 }, { "epoch": 28.55, "learning_rate": 1.9548263725300002e-07, "loss": 0.7902, "step": 343430 }, { "epoch": 28.55, "learning_rate": 1.9537178172546629e-07, "loss": 0.7214, "step": 343440 }, { "epoch": 28.55, "learning_rate": 1.9526092619793253e-07, "loss": 0.7419, "step": 343450 }, { "epoch": 28.55, "learning_rate": 1.951500706703988e-07, "loss": 0.7112, "step": 343460 }, { "epoch": 28.55, "learning_rate": 1.9503921514286507e-07, "loss": 0.7236, "step": 343470 }, { "epoch": 28.55, "learning_rate": 1.949283596153313e-07, "loss": 0.7468, "step": 343480 }, { "epoch": 28.55, "learning_rate": 1.9481750408779758e-07, "loss": 0.7667, "step": 343490 }, { "epoch": 28.55, "learning_rate": 1.9470664856026385e-07, "loss": 0.6551, "step": 343500 }, { "epoch": 28.55, "learning_rate": 1.945957930327301e-07, "loss": 0.7248, "step": 343510 }, { "epoch": 28.55, "learning_rate": 1.9448493750519636e-07, "loss": 0.7753, "step": 343520 }, { "epoch": 28.55, "learning_rate": 1.943740819776626e-07, "loss": 0.7059, "step": 343530 }, { "epoch": 28.55, "learning_rate": 1.9426322645012884e-07, "loss": 0.6999, "step": 343540 }, { "epoch": 28.56, "learning_rate": 1.941523709225951e-07, "loss": 0.7084, "step": 343550 }, { "epoch": 28.56, "learning_rate": 1.9404151539506138e-07, "loss": 0.7571, "step": 343560 }, { "epoch": 28.56, "learning_rate": 1.9393065986752762e-07, "loss": 0.7279, "step": 343570 }, { "epoch": 28.56, "learning_rate": 1.938198043399939e-07, "loss": 0.7363, "step": 343580 }, { "epoch": 28.56, "learning_rate": 1.9370894881246016e-07, "loss": 0.7356, "step": 343590 }, { "epoch": 28.56, "learning_rate": 1.935980932849264e-07, "loss": 0.7249, "step": 343600 }, { "epoch": 28.56, "learning_rate": 1.9348723775739267e-07, "loss": 0.7092, "step": 343610 }, { "epoch": 28.56, "learning_rate": 1.9337638222985891e-07, "loss": 0.7712, "step": 343620 }, { "epoch": 28.56, "learning_rate": 1.9326552670232518e-07, "loss": 0.7207, "step": 343630 }, { "epoch": 28.56, "learning_rate": 1.9315467117479145e-07, "loss": 0.689, "step": 343640 }, { "epoch": 28.56, "learning_rate": 1.930438156472577e-07, "loss": 0.7679, "step": 343650 }, { "epoch": 28.56, "learning_rate": 1.9293296011972396e-07, "loss": 0.7281, "step": 343660 }, { "epoch": 28.57, "learning_rate": 1.9282210459219023e-07, "loss": 0.7219, "step": 343670 }, { "epoch": 28.57, "learning_rate": 1.9271124906465647e-07, "loss": 0.7484, "step": 343680 }, { "epoch": 28.57, "learning_rate": 1.9260039353712274e-07, "loss": 0.7634, "step": 343690 }, { "epoch": 28.57, "learning_rate": 1.92489538009589e-07, "loss": 0.6816, "step": 343700 }, { "epoch": 28.57, "learning_rate": 1.9237868248205525e-07, "loss": 0.7176, "step": 343710 }, { "epoch": 28.57, "learning_rate": 1.9226782695452152e-07, "loss": 0.7079, "step": 343720 }, { "epoch": 28.57, "learning_rate": 1.921569714269878e-07, "loss": 0.7854, "step": 343730 }, { "epoch": 28.57, "learning_rate": 1.92046115899454e-07, "loss": 0.7104, "step": 343740 }, { "epoch": 28.57, "learning_rate": 1.9193526037192028e-07, "loss": 0.6644, "step": 343750 }, { "epoch": 28.57, "learning_rate": 1.9182440484438655e-07, "loss": 0.7492, "step": 343760 }, { "epoch": 28.57, "learning_rate": 1.917135493168528e-07, "loss": 0.703, "step": 343770 }, { "epoch": 28.57, "learning_rate": 1.9160269378931906e-07, "loss": 0.7845, "step": 343780 }, { "epoch": 28.58, "learning_rate": 1.9149183826178533e-07, "loss": 0.6482, "step": 343790 }, { "epoch": 28.58, "learning_rate": 1.9138098273425157e-07, "loss": 0.6913, "step": 343800 }, { "epoch": 28.58, "learning_rate": 1.9127012720671784e-07, "loss": 0.7194, "step": 343810 }, { "epoch": 28.58, "learning_rate": 1.9115927167918408e-07, "loss": 0.7218, "step": 343820 }, { "epoch": 28.58, "learning_rate": 1.9104841615165035e-07, "loss": 0.81, "step": 343830 }, { "epoch": 28.58, "learning_rate": 1.9093756062411662e-07, "loss": 0.7152, "step": 343840 }, { "epoch": 28.58, "learning_rate": 1.9082670509658286e-07, "loss": 0.728, "step": 343850 }, { "epoch": 28.58, "learning_rate": 1.9071584956904913e-07, "loss": 0.7069, "step": 343860 }, { "epoch": 28.58, "learning_rate": 1.906049940415154e-07, "loss": 0.7617, "step": 343870 }, { "epoch": 28.58, "learning_rate": 1.9049413851398164e-07, "loss": 0.7484, "step": 343880 }, { "epoch": 28.58, "learning_rate": 1.903832829864479e-07, "loss": 0.7931, "step": 343890 }, { "epoch": 28.58, "learning_rate": 1.9027242745891418e-07, "loss": 0.6835, "step": 343900 }, { "epoch": 28.59, "learning_rate": 1.9016157193138042e-07, "loss": 0.7161, "step": 343910 }, { "epoch": 28.59, "learning_rate": 1.900507164038467e-07, "loss": 0.7063, "step": 343920 }, { "epoch": 28.59, "learning_rate": 1.8993986087631296e-07, "loss": 0.7629, "step": 343930 }, { "epoch": 28.59, "learning_rate": 1.8982900534877917e-07, "loss": 0.7936, "step": 343940 }, { "epoch": 28.59, "learning_rate": 1.8971814982124544e-07, "loss": 0.6908, "step": 343950 }, { "epoch": 28.59, "learning_rate": 1.896072942937117e-07, "loss": 0.7306, "step": 343960 }, { "epoch": 28.59, "learning_rate": 1.8949643876617795e-07, "loss": 0.7823, "step": 343970 }, { "epoch": 28.59, "learning_rate": 1.8938558323864422e-07, "loss": 0.7639, "step": 343980 }, { "epoch": 28.59, "learning_rate": 1.892747277111105e-07, "loss": 0.6802, "step": 343990 }, { "epoch": 28.59, "learning_rate": 1.8916387218357673e-07, "loss": 0.7696, "step": 344000 }, { "epoch": 28.59, "learning_rate": 1.89053016656043e-07, "loss": 0.7268, "step": 344010 }, { "epoch": 28.59, "learning_rate": 1.8894216112850927e-07, "loss": 0.7655, "step": 344020 }, { "epoch": 28.6, "learning_rate": 1.8883130560097551e-07, "loss": 0.7424, "step": 344030 }, { "epoch": 28.6, "learning_rate": 1.8872045007344178e-07, "loss": 0.752, "step": 344040 }, { "epoch": 28.6, "learning_rate": 1.8860959454590803e-07, "loss": 0.7187, "step": 344050 }, { "epoch": 28.6, "learning_rate": 1.884987390183743e-07, "loss": 0.7025, "step": 344060 }, { "epoch": 28.6, "learning_rate": 1.8838788349084056e-07, "loss": 0.7692, "step": 344070 }, { "epoch": 28.6, "learning_rate": 1.882770279633068e-07, "loss": 0.7515, "step": 344080 }, { "epoch": 28.6, "learning_rate": 1.8816617243577307e-07, "loss": 0.7214, "step": 344090 }, { "epoch": 28.6, "learning_rate": 1.8805531690823934e-07, "loss": 0.6738, "step": 344100 }, { "epoch": 28.6, "learning_rate": 1.8794446138070559e-07, "loss": 0.7299, "step": 344110 }, { "epoch": 28.6, "learning_rate": 1.8783360585317185e-07, "loss": 0.7734, "step": 344120 }, { "epoch": 28.6, "learning_rate": 1.8772275032563812e-07, "loss": 0.7919, "step": 344130 }, { "epoch": 28.6, "learning_rate": 1.8761189479810437e-07, "loss": 0.7136, "step": 344140 }, { "epoch": 28.61, "learning_rate": 1.875010392705706e-07, "loss": 0.6835, "step": 344150 }, { "epoch": 28.61, "learning_rate": 1.8739018374303688e-07, "loss": 0.7534, "step": 344160 }, { "epoch": 28.61, "learning_rate": 1.8727932821550312e-07, "loss": 0.7353, "step": 344170 }, { "epoch": 28.61, "learning_rate": 1.871684726879694e-07, "loss": 0.7304, "step": 344180 }, { "epoch": 28.61, "learning_rate": 1.8705761716043566e-07, "loss": 0.7228, "step": 344190 }, { "epoch": 28.61, "learning_rate": 1.869467616329019e-07, "loss": 0.7144, "step": 344200 }, { "epoch": 28.61, "learning_rate": 1.8683590610536817e-07, "loss": 0.7529, "step": 344210 }, { "epoch": 28.61, "learning_rate": 1.8672505057783444e-07, "loss": 0.6864, "step": 344220 }, { "epoch": 28.61, "learning_rate": 1.8661419505030068e-07, "loss": 0.7239, "step": 344230 }, { "epoch": 28.61, "learning_rate": 1.8650333952276695e-07, "loss": 0.6928, "step": 344240 }, { "epoch": 28.61, "learning_rate": 1.863924839952332e-07, "loss": 0.7649, "step": 344250 }, { "epoch": 28.61, "learning_rate": 1.8628162846769946e-07, "loss": 0.7232, "step": 344260 }, { "epoch": 28.62, "learning_rate": 1.8617077294016573e-07, "loss": 0.757, "step": 344270 }, { "epoch": 28.62, "learning_rate": 1.8605991741263197e-07, "loss": 0.7829, "step": 344280 }, { "epoch": 28.62, "learning_rate": 1.8594906188509824e-07, "loss": 0.7101, "step": 344290 }, { "epoch": 28.62, "learning_rate": 1.858382063575645e-07, "loss": 0.7114, "step": 344300 }, { "epoch": 28.62, "learning_rate": 1.8572735083003075e-07, "loss": 0.7539, "step": 344310 }, { "epoch": 28.62, "learning_rate": 1.8561649530249702e-07, "loss": 0.7437, "step": 344320 }, { "epoch": 28.62, "learning_rate": 1.855056397749633e-07, "loss": 0.7264, "step": 344330 }, { "epoch": 28.62, "learning_rate": 1.8539478424742953e-07, "loss": 0.6964, "step": 344340 }, { "epoch": 28.62, "learning_rate": 1.852839287198958e-07, "loss": 0.6701, "step": 344350 }, { "epoch": 28.62, "learning_rate": 1.8517307319236207e-07, "loss": 0.7023, "step": 344360 }, { "epoch": 28.62, "learning_rate": 1.8506221766482828e-07, "loss": 0.7638, "step": 344370 }, { "epoch": 28.62, "learning_rate": 1.8495136213729455e-07, "loss": 0.7404, "step": 344380 }, { "epoch": 28.63, "learning_rate": 1.8484050660976082e-07, "loss": 0.7939, "step": 344390 }, { "epoch": 28.63, "learning_rate": 1.8472965108222707e-07, "loss": 0.6819, "step": 344400 }, { "epoch": 28.63, "learning_rate": 1.8461879555469333e-07, "loss": 0.7257, "step": 344410 }, { "epoch": 28.63, "learning_rate": 1.845079400271596e-07, "loss": 0.7194, "step": 344420 }, { "epoch": 28.63, "learning_rate": 1.8439708449962585e-07, "loss": 0.7535, "step": 344430 }, { "epoch": 28.63, "learning_rate": 1.8428622897209211e-07, "loss": 0.7464, "step": 344440 }, { "epoch": 28.63, "learning_rate": 1.8417537344455836e-07, "loss": 0.703, "step": 344450 }, { "epoch": 28.63, "learning_rate": 1.8406451791702463e-07, "loss": 0.6773, "step": 344460 }, { "epoch": 28.63, "learning_rate": 1.839536623894909e-07, "loss": 0.7064, "step": 344470 }, { "epoch": 28.63, "learning_rate": 1.8384280686195714e-07, "loss": 0.7204, "step": 344480 }, { "epoch": 28.63, "learning_rate": 1.837319513344234e-07, "loss": 0.6997, "step": 344490 }, { "epoch": 28.63, "learning_rate": 1.8362109580688967e-07, "loss": 0.7481, "step": 344500 }, { "epoch": 28.64, "learning_rate": 1.8351024027935592e-07, "loss": 0.7188, "step": 344510 }, { "epoch": 28.64, "learning_rate": 1.8339938475182219e-07, "loss": 0.7205, "step": 344520 }, { "epoch": 28.64, "learning_rate": 1.8328852922428845e-07, "loss": 0.8271, "step": 344530 }, { "epoch": 28.64, "learning_rate": 1.831776736967547e-07, "loss": 0.7453, "step": 344540 }, { "epoch": 28.64, "learning_rate": 1.8306681816922097e-07, "loss": 0.7029, "step": 344550 }, { "epoch": 28.64, "learning_rate": 1.8295596264168723e-07, "loss": 0.7388, "step": 344560 }, { "epoch": 28.64, "learning_rate": 1.8284510711415345e-07, "loss": 0.7285, "step": 344570 }, { "epoch": 28.64, "learning_rate": 1.8273425158661972e-07, "loss": 0.7534, "step": 344580 }, { "epoch": 28.64, "learning_rate": 1.82623396059086e-07, "loss": 0.7601, "step": 344590 }, { "epoch": 28.64, "learning_rate": 1.8251254053155223e-07, "loss": 0.7179, "step": 344600 }, { "epoch": 28.64, "learning_rate": 1.824016850040185e-07, "loss": 0.6752, "step": 344610 }, { "epoch": 28.64, "learning_rate": 1.8229082947648477e-07, "loss": 0.7256, "step": 344620 }, { "epoch": 28.65, "learning_rate": 1.82179973948951e-07, "loss": 0.7367, "step": 344630 }, { "epoch": 28.65, "learning_rate": 1.8206911842141728e-07, "loss": 0.7503, "step": 344640 }, { "epoch": 28.65, "learning_rate": 1.8195826289388355e-07, "loss": 0.6837, "step": 344650 }, { "epoch": 28.65, "learning_rate": 1.818474073663498e-07, "loss": 0.7426, "step": 344660 }, { "epoch": 28.65, "learning_rate": 1.8173655183881606e-07, "loss": 0.7444, "step": 344670 }, { "epoch": 28.65, "learning_rate": 1.816256963112823e-07, "loss": 0.7704, "step": 344680 }, { "epoch": 28.65, "learning_rate": 1.8151484078374857e-07, "loss": 0.7215, "step": 344690 }, { "epoch": 28.65, "learning_rate": 1.8140398525621484e-07, "loss": 0.756, "step": 344700 }, { "epoch": 28.65, "learning_rate": 1.8129312972868108e-07, "loss": 0.7372, "step": 344710 }, { "epoch": 28.65, "learning_rate": 1.8118227420114735e-07, "loss": 0.7364, "step": 344720 }, { "epoch": 28.65, "learning_rate": 1.8107141867361362e-07, "loss": 0.7087, "step": 344730 }, { "epoch": 28.65, "learning_rate": 1.8096056314607986e-07, "loss": 0.7322, "step": 344740 }, { "epoch": 28.66, "learning_rate": 1.8084970761854613e-07, "loss": 0.7504, "step": 344750 }, { "epoch": 28.66, "learning_rate": 1.807388520910124e-07, "loss": 0.7322, "step": 344760 }, { "epoch": 28.66, "learning_rate": 1.8062799656347864e-07, "loss": 0.7501, "step": 344770 }, { "epoch": 28.66, "learning_rate": 1.8051714103594489e-07, "loss": 0.7862, "step": 344780 }, { "epoch": 28.66, "learning_rate": 1.8040628550841115e-07, "loss": 0.7125, "step": 344790 }, { "epoch": 28.66, "learning_rate": 1.803065155336308e-07, "loss": 0.7236, "step": 344800 }, { "epoch": 28.66, "learning_rate": 1.8019566000609704e-07, "loss": 0.7195, "step": 344810 }, { "epoch": 28.66, "learning_rate": 1.800848044785633e-07, "loss": 0.7184, "step": 344820 }, { "epoch": 28.66, "learning_rate": 1.7997394895102958e-07, "loss": 0.7305, "step": 344830 }, { "epoch": 28.66, "learning_rate": 1.7986309342349582e-07, "loss": 0.7117, "step": 344840 }, { "epoch": 28.66, "learning_rate": 1.797522378959621e-07, "loss": 0.7812, "step": 344850 }, { "epoch": 28.66, "learning_rate": 1.7964138236842836e-07, "loss": 0.7084, "step": 344860 }, { "epoch": 28.67, "learning_rate": 1.795305268408946e-07, "loss": 0.7715, "step": 344870 }, { "epoch": 28.67, "learning_rate": 1.7941967131336087e-07, "loss": 0.7954, "step": 344880 }, { "epoch": 28.67, "learning_rate": 1.793088157858271e-07, "loss": 0.7222, "step": 344890 }, { "epoch": 28.67, "learning_rate": 1.7919796025829335e-07, "loss": 0.6907, "step": 344900 }, { "epoch": 28.67, "learning_rate": 1.7908710473075962e-07, "loss": 0.7101, "step": 344910 }, { "epoch": 28.67, "learning_rate": 1.7897624920322587e-07, "loss": 0.7707, "step": 344920 }, { "epoch": 28.67, "learning_rate": 1.7886539367569214e-07, "loss": 0.7885, "step": 344930 }, { "epoch": 28.67, "learning_rate": 1.787545381481584e-07, "loss": 0.7035, "step": 344940 }, { "epoch": 28.67, "learning_rate": 1.7864368262062465e-07, "loss": 0.7393, "step": 344950 }, { "epoch": 28.67, "learning_rate": 1.7853282709309092e-07, "loss": 0.6972, "step": 344960 }, { "epoch": 28.67, "learning_rate": 1.7842197156555718e-07, "loss": 0.7111, "step": 344970 }, { "epoch": 28.67, "learning_rate": 1.7831111603802343e-07, "loss": 0.7431, "step": 344980 }, { "epoch": 28.68, "learning_rate": 1.782002605104897e-07, "loss": 0.7377, "step": 344990 }, { "epoch": 28.68, "learning_rate": 1.7808940498295596e-07, "loss": 0.7553, "step": 345000 }, { "epoch": 28.68, "learning_rate": 1.779785494554222e-07, "loss": 0.6827, "step": 345010 }, { "epoch": 28.68, "learning_rate": 1.7786769392788848e-07, "loss": 0.7024, "step": 345020 }, { "epoch": 28.68, "learning_rate": 1.7775683840035474e-07, "loss": 0.7181, "step": 345030 }, { "epoch": 28.68, "learning_rate": 1.7764598287282099e-07, "loss": 0.7115, "step": 345040 }, { "epoch": 28.68, "learning_rate": 1.7753512734528726e-07, "loss": 0.7298, "step": 345050 }, { "epoch": 28.68, "learning_rate": 1.7742427181775352e-07, "loss": 0.6979, "step": 345060 }, { "epoch": 28.68, "learning_rate": 1.7731341629021977e-07, "loss": 0.7254, "step": 345070 }, { "epoch": 28.68, "learning_rate": 1.7720256076268604e-07, "loss": 0.7742, "step": 345080 }, { "epoch": 28.68, "learning_rate": 1.7709170523515228e-07, "loss": 0.7397, "step": 345090 }, { "epoch": 28.68, "learning_rate": 1.7698084970761855e-07, "loss": 0.7335, "step": 345100 }, { "epoch": 28.69, "learning_rate": 1.7686999418008482e-07, "loss": 0.7281, "step": 345110 }, { "epoch": 28.69, "learning_rate": 1.7675913865255103e-07, "loss": 0.697, "step": 345120 }, { "epoch": 28.69, "learning_rate": 1.766482831250173e-07, "loss": 0.7761, "step": 345130 }, { "epoch": 28.69, "learning_rate": 1.7653742759748357e-07, "loss": 0.7308, "step": 345140 }, { "epoch": 28.69, "learning_rate": 1.764265720699498e-07, "loss": 0.7573, "step": 345150 }, { "epoch": 28.69, "learning_rate": 1.7631571654241608e-07, "loss": 0.6971, "step": 345160 }, { "epoch": 28.69, "learning_rate": 1.7620486101488235e-07, "loss": 0.7667, "step": 345170 }, { "epoch": 28.69, "learning_rate": 1.760940054873486e-07, "loss": 0.7166, "step": 345180 }, { "epoch": 28.69, "learning_rate": 1.7598314995981486e-07, "loss": 0.7806, "step": 345190 }, { "epoch": 28.69, "learning_rate": 1.7587229443228113e-07, "loss": 0.7019, "step": 345200 }, { "epoch": 28.69, "learning_rate": 1.7576143890474737e-07, "loss": 0.6832, "step": 345210 }, { "epoch": 28.69, "learning_rate": 1.7565058337721364e-07, "loss": 0.7709, "step": 345220 }, { "epoch": 28.7, "learning_rate": 1.755397278496799e-07, "loss": 0.7879, "step": 345230 }, { "epoch": 28.7, "learning_rate": 1.7542887232214615e-07, "loss": 0.7737, "step": 345240 }, { "epoch": 28.7, "learning_rate": 1.7531801679461242e-07, "loss": 0.692, "step": 345250 }, { "epoch": 28.7, "learning_rate": 1.752071612670787e-07, "loss": 0.717, "step": 345260 }, { "epoch": 28.7, "learning_rate": 1.7509630573954493e-07, "loss": 0.7036, "step": 345270 }, { "epoch": 28.7, "learning_rate": 1.749854502120112e-07, "loss": 0.8204, "step": 345280 }, { "epoch": 28.7, "learning_rate": 1.7487459468447744e-07, "loss": 0.7054, "step": 345290 }, { "epoch": 28.7, "learning_rate": 1.747637391569437e-07, "loss": 0.7292, "step": 345300 }, { "epoch": 28.7, "learning_rate": 1.7465288362940998e-07, "loss": 0.7066, "step": 345310 }, { "epoch": 28.7, "learning_rate": 1.745420281018762e-07, "loss": 0.8247, "step": 345320 }, { "epoch": 28.7, "learning_rate": 1.7443117257434247e-07, "loss": 0.751, "step": 345330 }, { "epoch": 28.7, "learning_rate": 1.7432031704680874e-07, "loss": 0.7414, "step": 345340 }, { "epoch": 28.71, "learning_rate": 1.7420946151927498e-07, "loss": 0.7317, "step": 345350 }, { "epoch": 28.71, "learning_rate": 1.7409860599174125e-07, "loss": 0.6781, "step": 345360 }, { "epoch": 28.71, "learning_rate": 1.7398775046420752e-07, "loss": 0.72, "step": 345370 }, { "epoch": 28.71, "learning_rate": 1.7387689493667376e-07, "loss": 0.7547, "step": 345380 }, { "epoch": 28.71, "learning_rate": 1.7376603940914003e-07, "loss": 0.716, "step": 345390 }, { "epoch": 28.71, "learning_rate": 1.736551838816063e-07, "loss": 0.7086, "step": 345400 }, { "epoch": 28.71, "learning_rate": 1.7354432835407254e-07, "loss": 0.7261, "step": 345410 }, { "epoch": 28.71, "learning_rate": 1.734334728265388e-07, "loss": 0.7186, "step": 345420 }, { "epoch": 28.71, "learning_rate": 1.7332261729900508e-07, "loss": 0.8204, "step": 345430 }, { "epoch": 28.71, "learning_rate": 1.7321176177147132e-07, "loss": 0.7879, "step": 345440 }, { "epoch": 28.71, "learning_rate": 1.7310090624393759e-07, "loss": 0.7252, "step": 345450 }, { "epoch": 28.71, "learning_rate": 1.7299005071640386e-07, "loss": 0.6935, "step": 345460 }, { "epoch": 28.71, "learning_rate": 1.728791951888701e-07, "loss": 0.6806, "step": 345470 }, { "epoch": 28.72, "learning_rate": 1.7276833966133637e-07, "loss": 0.7721, "step": 345480 }, { "epoch": 28.72, "learning_rate": 1.7265748413380264e-07, "loss": 0.7191, "step": 345490 }, { "epoch": 28.72, "learning_rate": 1.7254662860626888e-07, "loss": 0.7232, "step": 345500 }, { "epoch": 28.72, "learning_rate": 1.7243577307873515e-07, "loss": 0.7341, "step": 345510 }, { "epoch": 28.72, "learning_rate": 1.723249175512014e-07, "loss": 0.7752, "step": 345520 }, { "epoch": 28.72, "learning_rate": 1.7221406202366763e-07, "loss": 0.735, "step": 345530 }, { "epoch": 28.72, "learning_rate": 1.721032064961339e-07, "loss": 0.697, "step": 345540 }, { "epoch": 28.72, "learning_rate": 1.7199235096860014e-07, "loss": 0.7235, "step": 345550 }, { "epoch": 28.72, "learning_rate": 1.718814954410664e-07, "loss": 0.6962, "step": 345560 }, { "epoch": 28.72, "learning_rate": 1.7177063991353268e-07, "loss": 0.7338, "step": 345570 }, { "epoch": 28.72, "learning_rate": 1.7165978438599892e-07, "loss": 0.7325, "step": 345580 }, { "epoch": 28.72, "learning_rate": 1.715489288584652e-07, "loss": 0.704, "step": 345590 }, { "epoch": 28.73, "learning_rate": 1.7143807333093146e-07, "loss": 0.7201, "step": 345600 }, { "epoch": 28.73, "learning_rate": 1.713272178033977e-07, "loss": 0.7963, "step": 345610 }, { "epoch": 28.73, "learning_rate": 1.7121636227586397e-07, "loss": 0.7541, "step": 345620 }, { "epoch": 28.73, "learning_rate": 1.7110550674833024e-07, "loss": 0.7318, "step": 345630 }, { "epoch": 28.73, "learning_rate": 1.7099465122079648e-07, "loss": 0.7932, "step": 345640 }, { "epoch": 28.73, "learning_rate": 1.7088379569326275e-07, "loss": 0.6919, "step": 345650 }, { "epoch": 28.73, "learning_rate": 1.7077294016572902e-07, "loss": 0.6662, "step": 345660 }, { "epoch": 28.73, "learning_rate": 1.7066208463819526e-07, "loss": 0.7463, "step": 345670 }, { "epoch": 28.73, "learning_rate": 1.7055122911066153e-07, "loss": 0.7632, "step": 345680 }, { "epoch": 28.73, "learning_rate": 1.704403735831278e-07, "loss": 0.7397, "step": 345690 }, { "epoch": 28.73, "learning_rate": 1.7032951805559404e-07, "loss": 0.7325, "step": 345700 }, { "epoch": 28.73, "learning_rate": 1.702186625280603e-07, "loss": 0.6832, "step": 345710 }, { "epoch": 28.74, "learning_rate": 1.7010780700052656e-07, "loss": 0.7266, "step": 345720 }, { "epoch": 28.74, "learning_rate": 1.6999695147299282e-07, "loss": 0.7167, "step": 345730 }, { "epoch": 28.74, "learning_rate": 1.6988609594545907e-07, "loss": 0.6979, "step": 345740 }, { "epoch": 28.74, "learning_rate": 1.697752404179253e-07, "loss": 0.7265, "step": 345750 }, { "epoch": 28.74, "learning_rate": 1.6966438489039158e-07, "loss": 0.7464, "step": 345760 }, { "epoch": 28.74, "learning_rate": 1.6955352936285785e-07, "loss": 0.7112, "step": 345770 }, { "epoch": 28.74, "learning_rate": 1.694426738353241e-07, "loss": 0.7799, "step": 345780 }, { "epoch": 28.74, "learning_rate": 1.6933181830779036e-07, "loss": 0.7292, "step": 345790 }, { "epoch": 28.74, "learning_rate": 1.6922096278025663e-07, "loss": 0.7422, "step": 345800 }, { "epoch": 28.74, "learning_rate": 1.6911010725272287e-07, "loss": 0.7739, "step": 345810 }, { "epoch": 28.74, "learning_rate": 1.6899925172518914e-07, "loss": 0.7248, "step": 345820 }, { "epoch": 28.74, "learning_rate": 1.688883961976554e-07, "loss": 0.7451, "step": 345830 }, { "epoch": 28.75, "learning_rate": 1.6877754067012165e-07, "loss": 0.718, "step": 345840 }, { "epoch": 28.75, "learning_rate": 1.6866668514258792e-07, "loss": 0.7585, "step": 345850 }, { "epoch": 28.75, "learning_rate": 1.685558296150542e-07, "loss": 0.6986, "step": 345860 }, { "epoch": 28.75, "learning_rate": 1.6844497408752043e-07, "loss": 0.7351, "step": 345870 }, { "epoch": 28.75, "learning_rate": 1.683341185599867e-07, "loss": 0.7163, "step": 345880 }, { "epoch": 28.75, "learning_rate": 1.6822326303245297e-07, "loss": 0.7324, "step": 345890 }, { "epoch": 28.75, "learning_rate": 1.681124075049192e-07, "loss": 0.7299, "step": 345900 }, { "epoch": 28.75, "learning_rate": 1.6800155197738548e-07, "loss": 0.6878, "step": 345910 }, { "epoch": 28.75, "learning_rate": 1.6789069644985172e-07, "loss": 0.7035, "step": 345920 }, { "epoch": 28.75, "learning_rate": 1.67779840922318e-07, "loss": 0.7772, "step": 345930 }, { "epoch": 28.75, "learning_rate": 1.6766898539478426e-07, "loss": 0.7855, "step": 345940 }, { "epoch": 28.75, "learning_rate": 1.6755812986725047e-07, "loss": 0.7175, "step": 345950 }, { "epoch": 28.76, "learning_rate": 1.6744727433971674e-07, "loss": 0.6792, "step": 345960 }, { "epoch": 28.76, "learning_rate": 1.67336418812183e-07, "loss": 0.6991, "step": 345970 }, { "epoch": 28.76, "learning_rate": 1.6722556328464925e-07, "loss": 0.7617, "step": 345980 }, { "epoch": 28.76, "learning_rate": 1.6711470775711552e-07, "loss": 0.7609, "step": 345990 }, { "epoch": 28.76, "learning_rate": 1.670038522295818e-07, "loss": 0.6654, "step": 346000 }, { "epoch": 28.76, "learning_rate": 1.6689299670204803e-07, "loss": 0.7063, "step": 346010 }, { "epoch": 28.76, "learning_rate": 1.667821411745143e-07, "loss": 0.7654, "step": 346020 }, { "epoch": 28.76, "learning_rate": 1.6667128564698057e-07, "loss": 0.7516, "step": 346030 }, { "epoch": 28.76, "learning_rate": 1.6656043011944681e-07, "loss": 0.7043, "step": 346040 }, { "epoch": 28.76, "learning_rate": 1.6644957459191308e-07, "loss": 0.713, "step": 346050 }, { "epoch": 28.76, "learning_rate": 1.6633871906437935e-07, "loss": 0.7065, "step": 346060 }, { "epoch": 28.76, "learning_rate": 1.662278635368456e-07, "loss": 0.7178, "step": 346070 }, { "epoch": 28.77, "learning_rate": 1.6611700800931186e-07, "loss": 0.7763, "step": 346080 }, { "epoch": 28.77, "learning_rate": 1.6600615248177813e-07, "loss": 0.7797, "step": 346090 }, { "epoch": 28.77, "learning_rate": 1.6589529695424437e-07, "loss": 0.736, "step": 346100 }, { "epoch": 28.77, "learning_rate": 1.6578444142671064e-07, "loss": 0.6894, "step": 346110 }, { "epoch": 28.77, "learning_rate": 1.6567358589917689e-07, "loss": 0.7114, "step": 346120 }, { "epoch": 28.77, "learning_rate": 1.6556273037164316e-07, "loss": 0.7576, "step": 346130 }, { "epoch": 28.77, "learning_rate": 1.6545187484410942e-07, "loss": 0.7452, "step": 346140 }, { "epoch": 28.77, "learning_rate": 1.6534101931657564e-07, "loss": 0.7945, "step": 346150 }, { "epoch": 28.77, "learning_rate": 1.652301637890419e-07, "loss": 0.7559, "step": 346160 }, { "epoch": 28.77, "learning_rate": 1.6511930826150818e-07, "loss": 0.7643, "step": 346170 }, { "epoch": 28.77, "learning_rate": 1.6500845273397442e-07, "loss": 0.7532, "step": 346180 }, { "epoch": 28.77, "learning_rate": 1.648975972064407e-07, "loss": 0.7428, "step": 346190 }, { "epoch": 28.78, "learning_rate": 1.6478674167890696e-07, "loss": 0.7762, "step": 346200 }, { "epoch": 28.78, "learning_rate": 1.646758861513732e-07, "loss": 0.7041, "step": 346210 }, { "epoch": 28.78, "learning_rate": 1.6456503062383947e-07, "loss": 0.7367, "step": 346220 }, { "epoch": 28.78, "learning_rate": 1.6445417509630574e-07, "loss": 0.7789, "step": 346230 }, { "epoch": 28.78, "learning_rate": 1.6434331956877198e-07, "loss": 0.7057, "step": 346240 }, { "epoch": 28.78, "learning_rate": 1.6423246404123825e-07, "loss": 0.7408, "step": 346250 }, { "epoch": 28.78, "learning_rate": 1.6412160851370452e-07, "loss": 0.7078, "step": 346260 }, { "epoch": 28.78, "learning_rate": 1.6401075298617076e-07, "loss": 0.7542, "step": 346270 }, { "epoch": 28.78, "learning_rate": 1.6389989745863703e-07, "loss": 0.7135, "step": 346280 }, { "epoch": 28.78, "learning_rate": 1.637890419311033e-07, "loss": 0.7032, "step": 346290 }, { "epoch": 28.78, "learning_rate": 1.6367818640356954e-07, "loss": 0.6927, "step": 346300 }, { "epoch": 28.78, "learning_rate": 1.635673308760358e-07, "loss": 0.7399, "step": 346310 }, { "epoch": 28.79, "learning_rate": 1.6345647534850208e-07, "loss": 0.7951, "step": 346320 }, { "epoch": 28.79, "learning_rate": 1.6334561982096832e-07, "loss": 0.7714, "step": 346330 }, { "epoch": 28.79, "learning_rate": 1.632347642934346e-07, "loss": 0.7299, "step": 346340 }, { "epoch": 28.79, "learning_rate": 1.6312390876590083e-07, "loss": 0.7258, "step": 346350 }, { "epoch": 28.79, "learning_rate": 1.6301305323836707e-07, "loss": 0.7486, "step": 346360 }, { "epoch": 28.79, "learning_rate": 1.6290219771083334e-07, "loss": 0.7361, "step": 346370 }, { "epoch": 28.79, "learning_rate": 1.6279134218329959e-07, "loss": 0.7049, "step": 346380 }, { "epoch": 28.79, "learning_rate": 1.6268048665576585e-07, "loss": 0.7335, "step": 346390 }, { "epoch": 28.79, "learning_rate": 1.6256963112823212e-07, "loss": 0.7244, "step": 346400 }, { "epoch": 28.79, "learning_rate": 1.6245877560069837e-07, "loss": 0.6565, "step": 346410 }, { "epoch": 28.79, "learning_rate": 1.6234792007316463e-07, "loss": 0.6801, "step": 346420 }, { "epoch": 28.79, "learning_rate": 1.622370645456309e-07, "loss": 0.7428, "step": 346430 }, { "epoch": 28.8, "learning_rate": 1.6212620901809715e-07, "loss": 0.7009, "step": 346440 }, { "epoch": 28.8, "learning_rate": 1.6201535349056341e-07, "loss": 0.7116, "step": 346450 }, { "epoch": 28.8, "learning_rate": 1.6190449796302968e-07, "loss": 0.6931, "step": 346460 }, { "epoch": 28.8, "learning_rate": 1.6179364243549593e-07, "loss": 0.7428, "step": 346470 }, { "epoch": 28.8, "learning_rate": 1.616827869079622e-07, "loss": 0.7475, "step": 346480 }, { "epoch": 28.8, "learning_rate": 1.6157193138042846e-07, "loss": 0.7439, "step": 346490 }, { "epoch": 28.8, "learning_rate": 1.614610758528947e-07, "loss": 0.7089, "step": 346500 }, { "epoch": 28.8, "learning_rate": 1.6135022032536098e-07, "loss": 0.7507, "step": 346510 }, { "epoch": 28.8, "learning_rate": 1.6123936479782724e-07, "loss": 0.7609, "step": 346520 }, { "epoch": 28.8, "learning_rate": 1.6112850927029349e-07, "loss": 0.8149, "step": 346530 }, { "epoch": 28.8, "learning_rate": 1.6101765374275976e-07, "loss": 0.6792, "step": 346540 }, { "epoch": 28.8, "learning_rate": 1.60906798215226e-07, "loss": 0.6981, "step": 346550 }, { "epoch": 28.81, "learning_rate": 1.6079594268769227e-07, "loss": 0.7656, "step": 346560 }, { "epoch": 28.81, "learning_rate": 1.6068508716015854e-07, "loss": 0.7535, "step": 346570 }, { "epoch": 28.81, "learning_rate": 1.6057423163262475e-07, "loss": 0.7656, "step": 346580 }, { "epoch": 28.81, "learning_rate": 1.6046337610509102e-07, "loss": 0.7103, "step": 346590 }, { "epoch": 28.81, "learning_rate": 1.603525205775573e-07, "loss": 0.7332, "step": 346600 }, { "epoch": 28.81, "learning_rate": 1.6024166505002353e-07, "loss": 0.7192, "step": 346610 }, { "epoch": 28.81, "learning_rate": 1.601308095224898e-07, "loss": 0.7766, "step": 346620 }, { "epoch": 28.81, "learning_rate": 1.6001995399495607e-07, "loss": 0.7958, "step": 346630 }, { "epoch": 28.81, "learning_rate": 1.599090984674223e-07, "loss": 0.7337, "step": 346640 }, { "epoch": 28.81, "learning_rate": 1.5979824293988858e-07, "loss": 0.7432, "step": 346650 }, { "epoch": 28.81, "learning_rate": 1.5968738741235485e-07, "loss": 0.7257, "step": 346660 }, { "epoch": 28.81, "learning_rate": 1.595765318848211e-07, "loss": 0.8074, "step": 346670 }, { "epoch": 28.82, "learning_rate": 1.5946567635728736e-07, "loss": 0.7449, "step": 346680 }, { "epoch": 28.82, "learning_rate": 1.5935482082975363e-07, "loss": 0.7323, "step": 346690 }, { "epoch": 28.82, "learning_rate": 1.5924396530221987e-07, "loss": 0.7517, "step": 346700 }, { "epoch": 28.82, "learning_rate": 1.5913310977468614e-07, "loss": 0.6683, "step": 346710 }, { "epoch": 28.82, "learning_rate": 1.590222542471524e-07, "loss": 0.6731, "step": 346720 }, { "epoch": 28.82, "learning_rate": 1.5891139871961865e-07, "loss": 0.7438, "step": 346730 }, { "epoch": 28.82, "learning_rate": 1.5880054319208492e-07, "loss": 0.7307, "step": 346740 }, { "epoch": 28.82, "learning_rate": 1.5868968766455116e-07, "loss": 0.6984, "step": 346750 }, { "epoch": 28.82, "learning_rate": 1.5857883213701743e-07, "loss": 0.6742, "step": 346760 }, { "epoch": 28.82, "learning_rate": 1.584679766094837e-07, "loss": 0.7508, "step": 346770 }, { "epoch": 28.82, "learning_rate": 1.5835712108194992e-07, "loss": 0.7428, "step": 346780 }, { "epoch": 28.82, "learning_rate": 1.5824626555441619e-07, "loss": 0.7671, "step": 346790 }, { "epoch": 28.83, "learning_rate": 1.5813541002688245e-07, "loss": 0.6991, "step": 346800 }, { "epoch": 28.83, "learning_rate": 1.580245544993487e-07, "loss": 0.7253, "step": 346810 }, { "epoch": 28.83, "learning_rate": 1.5791369897181497e-07, "loss": 0.7255, "step": 346820 }, { "epoch": 28.83, "learning_rate": 1.5780284344428123e-07, "loss": 0.7909, "step": 346830 }, { "epoch": 28.83, "learning_rate": 1.5769198791674748e-07, "loss": 0.7261, "step": 346840 }, { "epoch": 28.83, "learning_rate": 1.5758113238921375e-07, "loss": 0.7425, "step": 346850 }, { "epoch": 28.83, "learning_rate": 1.5747027686168001e-07, "loss": 0.7074, "step": 346860 }, { "epoch": 28.83, "learning_rate": 1.5735942133414626e-07, "loss": 0.7545, "step": 346870 }, { "epoch": 28.83, "learning_rate": 1.5724856580661253e-07, "loss": 0.7081, "step": 346880 }, { "epoch": 28.83, "learning_rate": 1.571377102790788e-07, "loss": 0.74, "step": 346890 }, { "epoch": 28.83, "learning_rate": 1.5702685475154504e-07, "loss": 0.7451, "step": 346900 }, { "epoch": 28.83, "learning_rate": 1.569159992240113e-07, "loss": 0.694, "step": 346910 }, { "epoch": 28.84, "learning_rate": 1.5680514369647758e-07, "loss": 0.7346, "step": 346920 }, { "epoch": 28.84, "learning_rate": 1.5669428816894382e-07, "loss": 0.7834, "step": 346930 }, { "epoch": 28.84, "learning_rate": 1.5658343264141009e-07, "loss": 0.7278, "step": 346940 }, { "epoch": 28.84, "learning_rate": 1.5647257711387636e-07, "loss": 0.6978, "step": 346950 }, { "epoch": 28.84, "learning_rate": 1.563617215863426e-07, "loss": 0.7027, "step": 346960 }, { "epoch": 28.84, "learning_rate": 1.5625086605880887e-07, "loss": 0.7646, "step": 346970 }, { "epoch": 28.84, "learning_rate": 1.561400105312751e-07, "loss": 0.7037, "step": 346980 }, { "epoch": 28.84, "learning_rate": 1.5602915500374135e-07, "loss": 0.6997, "step": 346990 }, { "epoch": 28.84, "learning_rate": 1.5591829947620762e-07, "loss": 0.7011, "step": 347000 }, { "epoch": 28.84, "learning_rate": 1.5580744394867386e-07, "loss": 0.7638, "step": 347010 }, { "epoch": 28.84, "learning_rate": 1.5569658842114013e-07, "loss": 0.7103, "step": 347020 }, { "epoch": 28.84, "learning_rate": 1.555857328936064e-07, "loss": 0.7346, "step": 347030 }, { "epoch": 28.85, "learning_rate": 1.5547487736607264e-07, "loss": 0.7161, "step": 347040 }, { "epoch": 28.85, "learning_rate": 1.553640218385389e-07, "loss": 0.7025, "step": 347050 }, { "epoch": 28.85, "learning_rate": 1.5525316631100518e-07, "loss": 0.7473, "step": 347060 }, { "epoch": 28.85, "learning_rate": 1.5514231078347142e-07, "loss": 0.7224, "step": 347070 }, { "epoch": 28.85, "learning_rate": 1.550314552559377e-07, "loss": 0.7754, "step": 347080 }, { "epoch": 28.85, "learning_rate": 1.5492059972840396e-07, "loss": 0.7205, "step": 347090 }, { "epoch": 28.85, "learning_rate": 1.548097442008702e-07, "loss": 0.7402, "step": 347100 }, { "epoch": 28.85, "learning_rate": 1.5469888867333647e-07, "loss": 0.7822, "step": 347110 }, { "epoch": 28.85, "learning_rate": 1.5458803314580274e-07, "loss": 0.7351, "step": 347120 }, { "epoch": 28.85, "learning_rate": 1.5447717761826898e-07, "loss": 0.7784, "step": 347130 }, { "epoch": 28.85, "learning_rate": 1.5436632209073525e-07, "loss": 0.7439, "step": 347140 }, { "epoch": 28.85, "learning_rate": 1.5425546656320152e-07, "loss": 0.6869, "step": 347150 }, { "epoch": 28.86, "learning_rate": 1.5414461103566776e-07, "loss": 0.6895, "step": 347160 }, { "epoch": 28.86, "learning_rate": 1.5403375550813403e-07, "loss": 0.764, "step": 347170 }, { "epoch": 28.86, "learning_rate": 1.5392289998060027e-07, "loss": 0.7354, "step": 347180 }, { "epoch": 28.86, "learning_rate": 1.5381204445306654e-07, "loss": 0.7341, "step": 347190 }, { "epoch": 28.86, "learning_rate": 1.5370118892553279e-07, "loss": 0.7886, "step": 347200 }, { "epoch": 28.86, "learning_rate": 1.5359033339799903e-07, "loss": 0.7859, "step": 347210 }, { "epoch": 28.86, "learning_rate": 1.534794778704653e-07, "loss": 0.7533, "step": 347220 }, { "epoch": 28.86, "learning_rate": 1.5336862234293157e-07, "loss": 0.7667, "step": 347230 }, { "epoch": 28.86, "learning_rate": 1.532577668153978e-07, "loss": 0.7224, "step": 347240 }, { "epoch": 28.86, "learning_rate": 1.5314691128786408e-07, "loss": 0.7459, "step": 347250 }, { "epoch": 28.86, "learning_rate": 1.5303605576033035e-07, "loss": 0.7364, "step": 347260 }, { "epoch": 28.86, "learning_rate": 1.529252002327966e-07, "loss": 0.7308, "step": 347270 }, { "epoch": 28.87, "learning_rate": 1.5281434470526286e-07, "loss": 0.7619, "step": 347280 }, { "epoch": 28.87, "learning_rate": 1.5270348917772913e-07, "loss": 0.7436, "step": 347290 }, { "epoch": 28.87, "learning_rate": 1.5259263365019537e-07, "loss": 0.7497, "step": 347300 }, { "epoch": 28.87, "learning_rate": 1.5248177812266164e-07, "loss": 0.7283, "step": 347310 }, { "epoch": 28.87, "learning_rate": 1.523709225951279e-07, "loss": 0.763, "step": 347320 }, { "epoch": 28.87, "learning_rate": 1.5226006706759415e-07, "loss": 0.7662, "step": 347330 }, { "epoch": 28.87, "learning_rate": 1.5214921154006042e-07, "loss": 0.7613, "step": 347340 }, { "epoch": 28.87, "learning_rate": 1.5203835601252669e-07, "loss": 0.7461, "step": 347350 }, { "epoch": 28.87, "learning_rate": 1.5192750048499293e-07, "loss": 0.7153, "step": 347360 }, { "epoch": 28.87, "learning_rate": 1.518166449574592e-07, "loss": 0.7677, "step": 347370 }, { "epoch": 28.87, "learning_rate": 1.5170578942992544e-07, "loss": 0.7929, "step": 347380 }, { "epoch": 28.87, "learning_rate": 1.515949339023917e-07, "loss": 0.7852, "step": 347390 }, { "epoch": 28.88, "learning_rate": 1.5148407837485798e-07, "loss": 0.6824, "step": 347400 }, { "epoch": 28.88, "learning_rate": 1.513732228473242e-07, "loss": 0.7393, "step": 347410 }, { "epoch": 28.88, "learning_rate": 1.5126236731979046e-07, "loss": 0.7666, "step": 347420 }, { "epoch": 28.88, "learning_rate": 1.5115151179225673e-07, "loss": 0.7667, "step": 347430 }, { "epoch": 28.88, "learning_rate": 1.5104065626472297e-07, "loss": 0.7355, "step": 347440 }, { "epoch": 28.88, "learning_rate": 1.5092980073718924e-07, "loss": 0.7476, "step": 347450 }, { "epoch": 28.88, "learning_rate": 1.508189452096555e-07, "loss": 0.7109, "step": 347460 }, { "epoch": 28.88, "learning_rate": 1.5070808968212175e-07, "loss": 0.7189, "step": 347470 }, { "epoch": 28.88, "learning_rate": 1.5059723415458802e-07, "loss": 0.754, "step": 347480 }, { "epoch": 28.88, "learning_rate": 1.504863786270543e-07, "loss": 0.6677, "step": 347490 }, { "epoch": 28.88, "learning_rate": 1.5037552309952053e-07, "loss": 0.6847, "step": 347500 }, { "epoch": 28.88, "learning_rate": 1.502646675719868e-07, "loss": 0.7464, "step": 347510 }, { "epoch": 28.89, "learning_rate": 1.5015381204445307e-07, "loss": 0.6863, "step": 347520 }, { "epoch": 28.89, "learning_rate": 1.5004295651691931e-07, "loss": 0.716, "step": 347530 }, { "epoch": 28.89, "learning_rate": 1.4993210098938558e-07, "loss": 0.7086, "step": 347540 }, { "epoch": 28.89, "learning_rate": 1.4982124546185185e-07, "loss": 0.7057, "step": 347550 }, { "epoch": 28.89, "learning_rate": 1.497103899343181e-07, "loss": 0.6855, "step": 347560 }, { "epoch": 28.89, "learning_rate": 1.4959953440678436e-07, "loss": 0.7407, "step": 347570 }, { "epoch": 28.89, "learning_rate": 1.4948867887925063e-07, "loss": 0.7521, "step": 347580 }, { "epoch": 28.89, "learning_rate": 1.4937782335171687e-07, "loss": 0.7573, "step": 347590 }, { "epoch": 28.89, "learning_rate": 1.4926696782418314e-07, "loss": 0.7003, "step": 347600 }, { "epoch": 28.89, "learning_rate": 1.4915611229664936e-07, "loss": 0.7253, "step": 347610 }, { "epoch": 28.89, "learning_rate": 1.4904525676911563e-07, "loss": 0.7908, "step": 347620 }, { "epoch": 28.89, "learning_rate": 1.489344012415819e-07, "loss": 0.7745, "step": 347630 }, { "epoch": 28.9, "learning_rate": 1.4882354571404814e-07, "loss": 0.7186, "step": 347640 }, { "epoch": 28.9, "learning_rate": 1.487126901865144e-07, "loss": 0.7092, "step": 347650 }, { "epoch": 28.9, "learning_rate": 1.4860183465898068e-07, "loss": 0.7183, "step": 347660 }, { "epoch": 28.9, "learning_rate": 1.4849097913144692e-07, "loss": 0.7251, "step": 347670 }, { "epoch": 28.9, "learning_rate": 1.483801236039132e-07, "loss": 0.7377, "step": 347680 }, { "epoch": 28.9, "learning_rate": 1.4826926807637946e-07, "loss": 0.7563, "step": 347690 }, { "epoch": 28.9, "learning_rate": 1.481584125488457e-07, "loss": 0.7871, "step": 347700 }, { "epoch": 28.9, "learning_rate": 1.4804755702131197e-07, "loss": 0.7293, "step": 347710 }, { "epoch": 28.9, "learning_rate": 1.4793670149377824e-07, "loss": 0.7186, "step": 347720 }, { "epoch": 28.9, "learning_rate": 1.4782584596624448e-07, "loss": 0.7442, "step": 347730 }, { "epoch": 28.9, "learning_rate": 1.4771499043871075e-07, "loss": 0.7586, "step": 347740 }, { "epoch": 28.9, "learning_rate": 1.4760413491117702e-07, "loss": 0.7263, "step": 347750 }, { "epoch": 28.91, "learning_rate": 1.4749327938364326e-07, "loss": 0.7892, "step": 347760 }, { "epoch": 28.91, "learning_rate": 1.4738242385610953e-07, "loss": 0.6631, "step": 347770 }, { "epoch": 28.91, "learning_rate": 1.472715683285758e-07, "loss": 0.7447, "step": 347780 }, { "epoch": 28.91, "learning_rate": 1.4716071280104204e-07, "loss": 0.6116, "step": 347790 }, { "epoch": 28.91, "learning_rate": 1.470498572735083e-07, "loss": 0.6919, "step": 347800 }, { "epoch": 28.91, "learning_rate": 1.4693900174597455e-07, "loss": 0.6541, "step": 347810 }, { "epoch": 28.91, "learning_rate": 1.468281462184408e-07, "loss": 0.7636, "step": 347820 }, { "epoch": 28.91, "learning_rate": 1.4671729069090706e-07, "loss": 0.7544, "step": 347830 }, { "epoch": 28.91, "learning_rate": 1.466064351633733e-07, "loss": 0.7701, "step": 347840 }, { "epoch": 28.91, "learning_rate": 1.4649557963583957e-07, "loss": 0.8073, "step": 347850 }, { "epoch": 28.91, "learning_rate": 1.4638472410830584e-07, "loss": 0.7127, "step": 347860 }, { "epoch": 28.91, "learning_rate": 1.4627386858077209e-07, "loss": 0.7399, "step": 347870 }, { "epoch": 28.92, "learning_rate": 1.4616301305323835e-07, "loss": 0.7371, "step": 347880 }, { "epoch": 28.92, "learning_rate": 1.4605215752570462e-07, "loss": 0.7478, "step": 347890 }, { "epoch": 28.92, "learning_rate": 1.4594130199817087e-07, "loss": 0.7587, "step": 347900 }, { "epoch": 28.92, "learning_rate": 1.4583044647063713e-07, "loss": 0.7503, "step": 347910 }, { "epoch": 28.92, "learning_rate": 1.457195909431034e-07, "loss": 0.7403, "step": 347920 }, { "epoch": 28.92, "learning_rate": 1.4560873541556965e-07, "loss": 0.7516, "step": 347930 }, { "epoch": 28.92, "learning_rate": 1.4549787988803591e-07, "loss": 0.7147, "step": 347940 }, { "epoch": 28.92, "learning_rate": 1.4538702436050218e-07, "loss": 0.7592, "step": 347950 }, { "epoch": 28.92, "learning_rate": 1.4527616883296843e-07, "loss": 0.7411, "step": 347960 }, { "epoch": 28.92, "learning_rate": 1.451653133054347e-07, "loss": 0.7851, "step": 347970 }, { "epoch": 28.92, "learning_rate": 1.4505445777790096e-07, "loss": 0.7661, "step": 347980 }, { "epoch": 28.92, "learning_rate": 1.449436022503672e-07, "loss": 0.7187, "step": 347990 }, { "epoch": 28.93, "learning_rate": 1.4483274672283347e-07, "loss": 0.7012, "step": 348000 }, { "epoch": 28.93, "learning_rate": 1.4472189119529972e-07, "loss": 0.7437, "step": 348010 }, { "epoch": 28.93, "learning_rate": 1.4461103566776599e-07, "loss": 0.804, "step": 348020 }, { "epoch": 28.93, "learning_rate": 1.4450018014023225e-07, "loss": 0.7441, "step": 348030 }, { "epoch": 28.93, "learning_rate": 1.4438932461269847e-07, "loss": 0.6999, "step": 348040 }, { "epoch": 28.93, "learning_rate": 1.4427846908516474e-07, "loss": 0.6984, "step": 348050 }, { "epoch": 28.93, "learning_rate": 1.44167613557631e-07, "loss": 0.7459, "step": 348060 }, { "epoch": 28.93, "learning_rate": 1.4405675803009725e-07, "loss": 0.7362, "step": 348070 }, { "epoch": 28.93, "learning_rate": 1.4394590250256352e-07, "loss": 0.7985, "step": 348080 }, { "epoch": 28.93, "learning_rate": 1.438350469750298e-07, "loss": 0.7618, "step": 348090 }, { "epoch": 28.93, "learning_rate": 1.4372419144749603e-07, "loss": 0.7254, "step": 348100 }, { "epoch": 28.93, "learning_rate": 1.436133359199623e-07, "loss": 0.7325, "step": 348110 }, { "epoch": 28.94, "learning_rate": 1.4350248039242857e-07, "loss": 0.7485, "step": 348120 }, { "epoch": 28.94, "learning_rate": 1.433916248648948e-07, "loss": 0.7135, "step": 348130 }, { "epoch": 28.94, "learning_rate": 1.4328076933736108e-07, "loss": 0.7469, "step": 348140 }, { "epoch": 28.94, "learning_rate": 1.4316991380982735e-07, "loss": 0.6959, "step": 348150 }, { "epoch": 28.94, "learning_rate": 1.430590582822936e-07, "loss": 0.7138, "step": 348160 }, { "epoch": 28.94, "learning_rate": 1.4294820275475986e-07, "loss": 0.7862, "step": 348170 }, { "epoch": 28.94, "learning_rate": 1.4283734722722613e-07, "loss": 0.7371, "step": 348180 }, { "epoch": 28.94, "learning_rate": 1.4272649169969237e-07, "loss": 0.6946, "step": 348190 }, { "epoch": 28.94, "learning_rate": 1.4261563617215864e-07, "loss": 0.7584, "step": 348200 }, { "epoch": 28.94, "learning_rate": 1.4250478064462488e-07, "loss": 0.6874, "step": 348210 }, { "epoch": 28.94, "learning_rate": 1.4239392511709115e-07, "loss": 0.7334, "step": 348220 }, { "epoch": 28.94, "learning_rate": 1.4228306958955742e-07, "loss": 0.7169, "step": 348230 }, { "epoch": 28.95, "learning_rate": 1.4217221406202364e-07, "loss": 0.6771, "step": 348240 }, { "epoch": 28.95, "learning_rate": 1.420613585344899e-07, "loss": 0.753, "step": 348250 }, { "epoch": 28.95, "learning_rate": 1.4195050300695617e-07, "loss": 0.7665, "step": 348260 }, { "epoch": 28.95, "learning_rate": 1.4183964747942242e-07, "loss": 0.7536, "step": 348270 }, { "epoch": 28.95, "learning_rate": 1.4172879195188869e-07, "loss": 0.7205, "step": 348280 }, { "epoch": 28.95, "learning_rate": 1.4161793642435495e-07, "loss": 0.7698, "step": 348290 }, { "epoch": 28.95, "learning_rate": 1.415070808968212e-07, "loss": 0.6873, "step": 348300 }, { "epoch": 28.95, "learning_rate": 1.4139622536928747e-07, "loss": 0.7208, "step": 348310 }, { "epoch": 28.95, "learning_rate": 1.4128536984175373e-07, "loss": 0.767, "step": 348320 }, { "epoch": 28.95, "learning_rate": 1.4117451431421998e-07, "loss": 0.751, "step": 348330 }, { "epoch": 28.95, "learning_rate": 1.4106365878668625e-07, "loss": 0.7179, "step": 348340 }, { "epoch": 28.95, "learning_rate": 1.4095280325915251e-07, "loss": 0.786, "step": 348350 }, { "epoch": 28.96, "learning_rate": 1.4084194773161876e-07, "loss": 0.7607, "step": 348360 }, { "epoch": 28.96, "learning_rate": 1.4073109220408503e-07, "loss": 0.7337, "step": 348370 }, { "epoch": 28.96, "learning_rate": 1.406202366765513e-07, "loss": 0.7647, "step": 348380 }, { "epoch": 28.96, "learning_rate": 1.4050938114901754e-07, "loss": 0.736, "step": 348390 }, { "epoch": 28.96, "learning_rate": 1.403985256214838e-07, "loss": 0.6854, "step": 348400 }, { "epoch": 28.96, "learning_rate": 1.4028767009395007e-07, "loss": 0.7205, "step": 348410 }, { "epoch": 28.96, "learning_rate": 1.4017681456641632e-07, "loss": 0.699, "step": 348420 }, { "epoch": 28.96, "learning_rate": 1.4006595903888259e-07, "loss": 0.734, "step": 348430 }, { "epoch": 28.96, "learning_rate": 1.3995510351134883e-07, "loss": 0.7119, "step": 348440 }, { "epoch": 28.96, "learning_rate": 1.3984424798381507e-07, "loss": 0.7249, "step": 348450 }, { "epoch": 28.96, "learning_rate": 1.3973339245628134e-07, "loss": 0.7368, "step": 348460 }, { "epoch": 28.96, "learning_rate": 1.3962253692874758e-07, "loss": 0.7385, "step": 348470 }, { "epoch": 28.97, "learning_rate": 1.3951168140121385e-07, "loss": 0.7845, "step": 348480 }, { "epoch": 28.97, "learning_rate": 1.3940082587368012e-07, "loss": 0.6957, "step": 348490 }, { "epoch": 28.97, "learning_rate": 1.3928997034614636e-07, "loss": 0.7418, "step": 348500 }, { "epoch": 28.97, "learning_rate": 1.3917911481861263e-07, "loss": 0.74, "step": 348510 }, { "epoch": 28.97, "learning_rate": 1.390682592910789e-07, "loss": 0.7847, "step": 348520 }, { "epoch": 28.97, "learning_rate": 1.3895740376354514e-07, "loss": 0.7854, "step": 348530 }, { "epoch": 28.97, "learning_rate": 1.388465482360114e-07, "loss": 0.6824, "step": 348540 }, { "epoch": 28.97, "learning_rate": 1.3873569270847768e-07, "loss": 0.6859, "step": 348550 }, { "epoch": 28.97, "learning_rate": 1.3862483718094392e-07, "loss": 0.7223, "step": 348560 }, { "epoch": 28.97, "learning_rate": 1.385139816534102e-07, "loss": 0.7088, "step": 348570 }, { "epoch": 28.97, "learning_rate": 1.3840312612587646e-07, "loss": 0.7838, "step": 348580 }, { "epoch": 28.97, "learning_rate": 1.382922705983427e-07, "loss": 0.7099, "step": 348590 }, { "epoch": 28.98, "learning_rate": 1.3818141507080897e-07, "loss": 0.6771, "step": 348600 }, { "epoch": 28.98, "learning_rate": 1.3807055954327524e-07, "loss": 0.7215, "step": 348610 }, { "epoch": 28.98, "learning_rate": 1.3795970401574148e-07, "loss": 0.8001, "step": 348620 }, { "epoch": 28.98, "learning_rate": 1.3784884848820775e-07, "loss": 0.8344, "step": 348630 }, { "epoch": 28.98, "learning_rate": 1.37737992960674e-07, "loss": 0.7934, "step": 348640 }, { "epoch": 28.98, "learning_rate": 1.3762713743314026e-07, "loss": 0.7019, "step": 348650 }, { "epoch": 28.98, "learning_rate": 1.375162819056065e-07, "loss": 0.7631, "step": 348660 }, { "epoch": 28.98, "learning_rate": 1.3740542637807275e-07, "loss": 0.7354, "step": 348670 }, { "epoch": 28.98, "learning_rate": 1.3729457085053902e-07, "loss": 0.8022, "step": 348680 }, { "epoch": 28.98, "learning_rate": 1.3718371532300529e-07, "loss": 0.7176, "step": 348690 }, { "epoch": 28.98, "learning_rate": 1.3707285979547153e-07, "loss": 0.8011, "step": 348700 }, { "epoch": 28.98, "learning_rate": 1.369620042679378e-07, "loss": 0.7217, "step": 348710 }, { "epoch": 28.99, "learning_rate": 1.3685114874040407e-07, "loss": 0.8012, "step": 348720 }, { "epoch": 28.99, "learning_rate": 1.367402932128703e-07, "loss": 0.7378, "step": 348730 }, { "epoch": 28.99, "learning_rate": 1.3662943768533658e-07, "loss": 0.7144, "step": 348740 }, { "epoch": 28.99, "learning_rate": 1.3651858215780285e-07, "loss": 0.6781, "step": 348750 }, { "epoch": 28.99, "learning_rate": 1.364077266302691e-07, "loss": 0.6851, "step": 348760 }, { "epoch": 28.99, "learning_rate": 1.3629687110273536e-07, "loss": 0.7252, "step": 348770 }, { "epoch": 28.99, "learning_rate": 1.3618601557520163e-07, "loss": 0.8122, "step": 348780 }, { "epoch": 28.99, "learning_rate": 1.3607516004766787e-07, "loss": 0.7872, "step": 348790 }, { "epoch": 28.99, "learning_rate": 1.3596430452013414e-07, "loss": 0.6939, "step": 348800 }, { "epoch": 28.99, "learning_rate": 1.358534489926004e-07, "loss": 0.7042, "step": 348810 }, { "epoch": 28.99, "learning_rate": 1.3574259346506665e-07, "loss": 0.6915, "step": 348820 }, { "epoch": 28.99, "learning_rate": 1.3563173793753292e-07, "loss": 0.7349, "step": 348830 }, { "epoch": 29.0, "learning_rate": 1.3552088240999916e-07, "loss": 0.7798, "step": 348840 }, { "epoch": 29.0, "learning_rate": 1.3541002688246543e-07, "loss": 0.7238, "step": 348850 }, { "epoch": 29.0, "learning_rate": 1.352991713549317e-07, "loss": 0.7461, "step": 348860 }, { "epoch": 29.0, "learning_rate": 1.3518831582739791e-07, "loss": 0.6925, "step": 348870 }, { "epoch": 29.0, "learning_rate": 1.3507746029986418e-07, "loss": 0.7609, "step": 348880 }, { "epoch": 29.0, "learning_rate": 1.3496660477233045e-07, "loss": 0.77, "step": 348890 }, { "epoch": 29.0, "eval_loss": 1.1475533246994019, "eval_runtime": 357.2692, "eval_samples_per_second": 7.485, "eval_steps_per_second": 3.742, "eval_wer": 0.6343085043767334, "step": 348899 }, { "epoch": 29.0, "learning_rate": 1.348557492447967e-07, "loss": 0.7455, "step": 348900 }, { "epoch": 29.0, "learning_rate": 1.3474489371726296e-07, "loss": 0.7819, "step": 348910 }, { "epoch": 29.0, "learning_rate": 1.3463403818972923e-07, "loss": 0.6951, "step": 348920 }, { "epoch": 29.0, "learning_rate": 1.3452318266219547e-07, "loss": 0.7786, "step": 348930 }, { "epoch": 29.0, "learning_rate": 1.3441232713466174e-07, "loss": 0.7431, "step": 348940 }, { "epoch": 29.0, "learning_rate": 1.34301471607128e-07, "loss": 0.7451, "step": 348950 }, { "epoch": 29.01, "learning_rate": 1.3419061607959425e-07, "loss": 0.7819, "step": 348960 }, { "epoch": 29.01, "learning_rate": 1.3407976055206052e-07, "loss": 0.7494, "step": 348970 }, { "epoch": 29.01, "learning_rate": 1.339689050245268e-07, "loss": 0.6545, "step": 348980 }, { "epoch": 29.01, "learning_rate": 1.3385804949699303e-07, "loss": 0.7882, "step": 348990 }, { "epoch": 29.01, "learning_rate": 1.337471939694593e-07, "loss": 0.7486, "step": 349000 }, { "epoch": 29.01, "learning_rate": 1.3363633844192557e-07, "loss": 0.8073, "step": 349010 }, { "epoch": 29.01, "learning_rate": 1.3352548291439181e-07, "loss": 0.6824, "step": 349020 }, { "epoch": 29.01, "learning_rate": 1.3341462738685808e-07, "loss": 0.7546, "step": 349030 }, { "epoch": 29.01, "learning_rate": 1.3330377185932435e-07, "loss": 0.7332, "step": 349040 }, { "epoch": 29.01, "learning_rate": 1.331929163317906e-07, "loss": 0.6657, "step": 349050 }, { "epoch": 29.01, "learning_rate": 1.3308206080425686e-07, "loss": 0.8006, "step": 349060 }, { "epoch": 29.01, "learning_rate": 1.3297120527672308e-07, "loss": 0.7511, "step": 349070 }, { "epoch": 29.02, "learning_rate": 1.3286034974918935e-07, "loss": 0.7018, "step": 349080 }, { "epoch": 29.02, "learning_rate": 1.3274949422165562e-07, "loss": 0.7536, "step": 349090 }, { "epoch": 29.02, "learning_rate": 1.3263863869412186e-07, "loss": 0.744, "step": 349100 }, { "epoch": 29.02, "learning_rate": 1.3252778316658813e-07, "loss": 0.8123, "step": 349110 }, { "epoch": 29.02, "learning_rate": 1.324169276390544e-07, "loss": 0.7519, "step": 349120 }, { "epoch": 29.02, "learning_rate": 1.3230607211152064e-07, "loss": 0.7057, "step": 349130 }, { "epoch": 29.02, "learning_rate": 1.321952165839869e-07, "loss": 0.7847, "step": 349140 }, { "epoch": 29.02, "learning_rate": 1.3208436105645318e-07, "loss": 0.7471, "step": 349150 }, { "epoch": 29.02, "learning_rate": 1.3197350552891942e-07, "loss": 0.761, "step": 349160 }, { "epoch": 29.02, "learning_rate": 1.318626500013857e-07, "loss": 0.7424, "step": 349170 }, { "epoch": 29.02, "learning_rate": 1.3175179447385196e-07, "loss": 0.7315, "step": 349180 }, { "epoch": 29.02, "learning_rate": 1.316409389463182e-07, "loss": 0.6952, "step": 349190 }, { "epoch": 29.03, "learning_rate": 1.3153008341878447e-07, "loss": 0.7416, "step": 349200 }, { "epoch": 29.03, "learning_rate": 1.3141922789125074e-07, "loss": 0.7264, "step": 349210 }, { "epoch": 29.03, "learning_rate": 1.3130837236371698e-07, "loss": 0.7032, "step": 349220 }, { "epoch": 29.03, "learning_rate": 1.3119751683618325e-07, "loss": 0.7691, "step": 349230 }, { "epoch": 29.03, "learning_rate": 1.3108666130864952e-07, "loss": 0.733, "step": 349240 }, { "epoch": 29.03, "learning_rate": 1.3097580578111576e-07, "loss": 0.7678, "step": 349250 }, { "epoch": 29.03, "learning_rate": 1.3086495025358203e-07, "loss": 0.7237, "step": 349260 }, { "epoch": 29.03, "learning_rate": 1.3075409472604827e-07, "loss": 0.6797, "step": 349270 }, { "epoch": 29.03, "learning_rate": 1.3064323919851451e-07, "loss": 0.7793, "step": 349280 }, { "epoch": 29.03, "learning_rate": 1.3053238367098078e-07, "loss": 0.7192, "step": 349290 }, { "epoch": 29.03, "learning_rate": 1.3042152814344702e-07, "loss": 0.7403, "step": 349300 }, { "epoch": 29.03, "learning_rate": 1.303106726159133e-07, "loss": 0.7012, "step": 349310 }, { "epoch": 29.03, "learning_rate": 1.3019981708837956e-07, "loss": 0.6936, "step": 349320 }, { "epoch": 29.04, "learning_rate": 1.300889615608458e-07, "loss": 0.7442, "step": 349330 }, { "epoch": 29.04, "learning_rate": 1.2997810603331207e-07, "loss": 0.723, "step": 349340 }, { "epoch": 29.04, "learning_rate": 1.2986725050577834e-07, "loss": 0.7588, "step": 349350 }, { "epoch": 29.04, "learning_rate": 1.2975639497824458e-07, "loss": 0.7924, "step": 349360 }, { "epoch": 29.04, "learning_rate": 1.2964553945071085e-07, "loss": 0.6825, "step": 349370 }, { "epoch": 29.04, "learning_rate": 1.2953468392317712e-07, "loss": 0.6658, "step": 349380 }, { "epoch": 29.04, "learning_rate": 1.2942382839564337e-07, "loss": 0.7001, "step": 349390 }, { "epoch": 29.04, "learning_rate": 1.2931297286810963e-07, "loss": 0.6995, "step": 349400 }, { "epoch": 29.04, "learning_rate": 1.292021173405759e-07, "loss": 0.7743, "step": 349410 }, { "epoch": 29.04, "learning_rate": 1.2909126181304215e-07, "loss": 0.7954, "step": 349420 }, { "epoch": 29.04, "learning_rate": 1.2898040628550841e-07, "loss": 0.7758, "step": 349430 }, { "epoch": 29.04, "learning_rate": 1.2886955075797468e-07, "loss": 0.7353, "step": 349440 }, { "epoch": 29.05, "learning_rate": 1.2875869523044093e-07, "loss": 0.7225, "step": 349450 }, { "epoch": 29.05, "learning_rate": 1.286478397029072e-07, "loss": 0.7799, "step": 349460 }, { "epoch": 29.05, "learning_rate": 1.2853698417537344e-07, "loss": 0.6766, "step": 349470 }, { "epoch": 29.05, "learning_rate": 1.284261286478397e-07, "loss": 0.7061, "step": 349480 }, { "epoch": 29.05, "learning_rate": 1.2831527312030597e-07, "loss": 0.7726, "step": 349490 }, { "epoch": 29.05, "learning_rate": 1.282044175927722e-07, "loss": 0.6965, "step": 349500 }, { "epoch": 29.05, "learning_rate": 1.2809356206523846e-07, "loss": 0.7753, "step": 349510 }, { "epoch": 29.05, "learning_rate": 1.2798270653770473e-07, "loss": 0.702, "step": 349520 }, { "epoch": 29.05, "learning_rate": 1.2787185101017097e-07, "loss": 0.7045, "step": 349530 }, { "epoch": 29.05, "learning_rate": 1.2776099548263724e-07, "loss": 0.7329, "step": 349540 }, { "epoch": 29.05, "learning_rate": 1.276501399551035e-07, "loss": 0.7291, "step": 349550 }, { "epoch": 29.05, "learning_rate": 1.2753928442756975e-07, "loss": 0.7455, "step": 349560 }, { "epoch": 29.06, "learning_rate": 1.2742842890003602e-07, "loss": 0.7631, "step": 349570 }, { "epoch": 29.06, "learning_rate": 1.273175733725023e-07, "loss": 0.7296, "step": 349580 }, { "epoch": 29.06, "learning_rate": 1.2720671784496853e-07, "loss": 0.6927, "step": 349590 }, { "epoch": 29.06, "learning_rate": 1.270958623174348e-07, "loss": 0.7466, "step": 349600 }, { "epoch": 29.06, "learning_rate": 1.2698500678990107e-07, "loss": 0.8106, "step": 349610 }, { "epoch": 29.06, "learning_rate": 1.268741512623673e-07, "loss": 0.7739, "step": 349620 }, { "epoch": 29.06, "learning_rate": 1.2676329573483358e-07, "loss": 0.7737, "step": 349630 }, { "epoch": 29.06, "learning_rate": 1.2665244020729985e-07, "loss": 0.7013, "step": 349640 }, { "epoch": 29.06, "learning_rate": 1.265415846797661e-07, "loss": 0.7599, "step": 349650 }, { "epoch": 29.06, "learning_rate": 1.2643072915223236e-07, "loss": 0.7182, "step": 349660 }, { "epoch": 29.06, "learning_rate": 1.2631987362469863e-07, "loss": 0.7125, "step": 349670 }, { "epoch": 29.06, "learning_rate": 1.2620901809716487e-07, "loss": 0.7306, "step": 349680 }, { "epoch": 29.07, "learning_rate": 1.2609816256963114e-07, "loss": 0.6942, "step": 349690 }, { "epoch": 29.07, "learning_rate": 1.2598730704209736e-07, "loss": 0.7656, "step": 349700 }, { "epoch": 29.07, "learning_rate": 1.2587645151456362e-07, "loss": 0.7048, "step": 349710 }, { "epoch": 29.07, "learning_rate": 1.257655959870299e-07, "loss": 0.6954, "step": 349720 }, { "epoch": 29.07, "learning_rate": 1.2565474045949614e-07, "loss": 0.7563, "step": 349730 }, { "epoch": 29.07, "learning_rate": 1.255438849319624e-07, "loss": 0.7518, "step": 349740 }, { "epoch": 29.07, "learning_rate": 1.2543302940442867e-07, "loss": 0.7034, "step": 349750 }, { "epoch": 29.07, "learning_rate": 1.2532217387689492e-07, "loss": 0.7823, "step": 349760 }, { "epoch": 29.07, "learning_rate": 1.2521131834936119e-07, "loss": 0.6872, "step": 349770 }, { "epoch": 29.07, "learning_rate": 1.2510046282182745e-07, "loss": 0.6875, "step": 349780 }, { "epoch": 29.07, "learning_rate": 1.2498960729429372e-07, "loss": 0.6681, "step": 349790 }, { "epoch": 29.07, "learning_rate": 1.2487875176675997e-07, "loss": 0.7677, "step": 349800 }, { "epoch": 29.08, "learning_rate": 1.247678962392262e-07, "loss": 0.7795, "step": 349810 }, { "epoch": 29.08, "learning_rate": 1.2465704071169248e-07, "loss": 0.7043, "step": 349820 }, { "epoch": 29.08, "learning_rate": 1.2454618518415875e-07, "loss": 0.738, "step": 349830 }, { "epoch": 29.08, "learning_rate": 1.24435329656625e-07, "loss": 0.6959, "step": 349840 }, { "epoch": 29.08, "learning_rate": 1.2432447412909126e-07, "loss": 0.7593, "step": 349850 }, { "epoch": 29.08, "learning_rate": 1.2421361860155753e-07, "loss": 0.7668, "step": 349860 }, { "epoch": 29.08, "learning_rate": 1.2410276307402377e-07, "loss": 0.7213, "step": 349870 }, { "epoch": 29.08, "learning_rate": 1.2399190754649004e-07, "loss": 0.7017, "step": 349880 }, { "epoch": 29.08, "learning_rate": 1.238810520189563e-07, "loss": 0.6876, "step": 349890 }, { "epoch": 29.08, "learning_rate": 1.2377019649142255e-07, "loss": 0.7147, "step": 349900 }, { "epoch": 29.08, "learning_rate": 1.236593409638888e-07, "loss": 0.7176, "step": 349910 }, { "epoch": 29.08, "learning_rate": 1.2354848543635506e-07, "loss": 0.667, "step": 349920 }, { "epoch": 29.09, "learning_rate": 1.2343762990882133e-07, "loss": 0.7527, "step": 349930 }, { "epoch": 29.09, "learning_rate": 1.2333785993404095e-07, "loss": 0.7207, "step": 349940 }, { "epoch": 29.09, "learning_rate": 1.2322700440650722e-07, "loss": 0.7593, "step": 349950 }, { "epoch": 29.09, "learning_rate": 1.2311614887897346e-07, "loss": 0.8102, "step": 349960 }, { "epoch": 29.09, "learning_rate": 1.2300529335143973e-07, "loss": 0.7701, "step": 349970 }, { "epoch": 29.09, "learning_rate": 1.22894437823906e-07, "loss": 0.7131, "step": 349980 }, { "epoch": 29.09, "learning_rate": 1.2278358229637224e-07, "loss": 0.7507, "step": 349990 }, { "epoch": 29.09, "learning_rate": 1.226727267688385e-07, "loss": 0.7013, "step": 350000 }, { "epoch": 29.09, "learning_rate": 1.2256187124130478e-07, "loss": 0.7865, "step": 350010 }, { "epoch": 29.09, "learning_rate": 1.2245101571377102e-07, "loss": 0.7665, "step": 350020 }, { "epoch": 29.09, "learning_rate": 1.2234016018623729e-07, "loss": 0.7758, "step": 350030 }, { "epoch": 29.09, "learning_rate": 1.2222930465870353e-07, "loss": 0.701, "step": 350040 }, { "epoch": 29.1, "learning_rate": 1.221184491311698e-07, "loss": 0.7426, "step": 350050 }, { "epoch": 29.1, "learning_rate": 1.2200759360363604e-07, "loss": 0.7951, "step": 350060 }, { "epoch": 29.1, "learning_rate": 1.218967380761023e-07, "loss": 0.6766, "step": 350070 }, { "epoch": 29.1, "learning_rate": 1.2178588254856858e-07, "loss": 0.7159, "step": 350080 }, { "epoch": 29.1, "learning_rate": 1.2167502702103482e-07, "loss": 0.7487, "step": 350090 }, { "epoch": 29.1, "learning_rate": 1.215641714935011e-07, "loss": 0.7683, "step": 350100 }, { "epoch": 29.1, "learning_rate": 1.2145331596596736e-07, "loss": 0.8044, "step": 350110 }, { "epoch": 29.1, "learning_rate": 1.213424604384336e-07, "loss": 0.7058, "step": 350120 }, { "epoch": 29.1, "learning_rate": 1.2123160491089987e-07, "loss": 0.6767, "step": 350130 }, { "epoch": 29.1, "learning_rate": 1.211207493833661e-07, "loss": 0.6945, "step": 350140 }, { "epoch": 29.1, "learning_rate": 1.2100989385583238e-07, "loss": 0.7252, "step": 350150 }, { "epoch": 29.1, "learning_rate": 1.2089903832829862e-07, "loss": 0.7862, "step": 350160 }, { "epoch": 29.11, "learning_rate": 1.207881828007649e-07, "loss": 0.7773, "step": 350170 }, { "epoch": 29.11, "learning_rate": 1.2067732727323116e-07, "loss": 0.6737, "step": 350180 }, { "epoch": 29.11, "learning_rate": 1.205664717456974e-07, "loss": 0.7445, "step": 350190 }, { "epoch": 29.11, "learning_rate": 1.2045561621816367e-07, "loss": 0.6615, "step": 350200 }, { "epoch": 29.11, "learning_rate": 1.2034476069062994e-07, "loss": 0.7385, "step": 350210 }, { "epoch": 29.11, "learning_rate": 1.2023390516309618e-07, "loss": 0.7542, "step": 350220 }, { "epoch": 29.11, "learning_rate": 1.2012304963556245e-07, "loss": 0.7456, "step": 350230 }, { "epoch": 29.11, "learning_rate": 1.2001219410802872e-07, "loss": 0.7054, "step": 350240 }, { "epoch": 29.11, "learning_rate": 1.1990133858049496e-07, "loss": 0.6738, "step": 350250 }, { "epoch": 29.11, "learning_rate": 1.197904830529612e-07, "loss": 0.7171, "step": 350260 }, { "epoch": 29.11, "learning_rate": 1.1967962752542747e-07, "loss": 0.7345, "step": 350270 }, { "epoch": 29.11, "learning_rate": 1.1956877199789374e-07, "loss": 0.7161, "step": 350280 }, { "epoch": 29.12, "learning_rate": 1.1945791647035999e-07, "loss": 0.7017, "step": 350290 }, { "epoch": 29.12, "learning_rate": 1.1934706094282625e-07, "loss": 0.757, "step": 350300 }, { "epoch": 29.12, "learning_rate": 1.1923620541529252e-07, "loss": 0.7471, "step": 350310 }, { "epoch": 29.12, "learning_rate": 1.1912534988775877e-07, "loss": 0.7241, "step": 350320 }, { "epoch": 29.12, "learning_rate": 1.1901449436022504e-07, "loss": 0.7208, "step": 350330 }, { "epoch": 29.12, "learning_rate": 1.1890363883269129e-07, "loss": 0.7322, "step": 350340 }, { "epoch": 29.12, "learning_rate": 1.1879278330515755e-07, "loss": 0.7273, "step": 350350 }, { "epoch": 29.12, "learning_rate": 1.186819277776238e-07, "loss": 0.7761, "step": 350360 }, { "epoch": 29.12, "learning_rate": 1.1857107225009007e-07, "loss": 0.7589, "step": 350370 }, { "epoch": 29.12, "learning_rate": 1.1846021672255633e-07, "loss": 0.7018, "step": 350380 }, { "epoch": 29.12, "learning_rate": 1.1834936119502258e-07, "loss": 0.7297, "step": 350390 }, { "epoch": 29.12, "learning_rate": 1.1823850566748884e-07, "loss": 0.6822, "step": 350400 }, { "epoch": 29.13, "learning_rate": 1.1812765013995509e-07, "loss": 0.8036, "step": 350410 }, { "epoch": 29.13, "learning_rate": 1.1801679461242135e-07, "loss": 0.6795, "step": 350420 }, { "epoch": 29.13, "learning_rate": 1.1790593908488762e-07, "loss": 0.6988, "step": 350430 }, { "epoch": 29.13, "learning_rate": 1.1779508355735387e-07, "loss": 0.7651, "step": 350440 }, { "epoch": 29.13, "learning_rate": 1.1768422802982013e-07, "loss": 0.769, "step": 350450 }, { "epoch": 29.13, "learning_rate": 1.1757337250228638e-07, "loss": 0.7567, "step": 350460 }, { "epoch": 29.13, "learning_rate": 1.1746251697475265e-07, "loss": 0.6644, "step": 350470 }, { "epoch": 29.13, "learning_rate": 1.1735166144721891e-07, "loss": 0.7137, "step": 350480 }, { "epoch": 29.13, "learning_rate": 1.1724080591968516e-07, "loss": 0.6417, "step": 350490 }, { "epoch": 29.13, "learning_rate": 1.1712995039215143e-07, "loss": 0.7262, "step": 350500 }, { "epoch": 29.13, "learning_rate": 1.1701909486461768e-07, "loss": 0.7146, "step": 350510 }, { "epoch": 29.13, "learning_rate": 1.1690823933708393e-07, "loss": 0.7825, "step": 350520 }, { "epoch": 29.14, "learning_rate": 1.167973838095502e-07, "loss": 0.7168, "step": 350530 }, { "epoch": 29.14, "learning_rate": 1.1668652828201646e-07, "loss": 0.7089, "step": 350540 }, { "epoch": 29.14, "learning_rate": 1.1657567275448271e-07, "loss": 0.7541, "step": 350550 }, { "epoch": 29.14, "learning_rate": 1.1646481722694898e-07, "loss": 0.737, "step": 350560 }, { "epoch": 29.14, "learning_rate": 1.1635396169941524e-07, "loss": 0.7424, "step": 350570 }, { "epoch": 29.14, "learning_rate": 1.1624310617188149e-07, "loss": 0.6631, "step": 350580 }, { "epoch": 29.14, "learning_rate": 1.1613225064434775e-07, "loss": 0.711, "step": 350590 }, { "epoch": 29.14, "learning_rate": 1.1602139511681402e-07, "loss": 0.7447, "step": 350600 }, { "epoch": 29.14, "learning_rate": 1.1591053958928026e-07, "loss": 0.7555, "step": 350610 }, { "epoch": 29.14, "learning_rate": 1.1579968406174651e-07, "loss": 0.7369, "step": 350620 }, { "epoch": 29.14, "learning_rate": 1.1568882853421278e-07, "loss": 0.7481, "step": 350630 }, { "epoch": 29.14, "learning_rate": 1.1557797300667904e-07, "loss": 0.6876, "step": 350640 }, { "epoch": 29.15, "learning_rate": 1.154671174791453e-07, "loss": 0.7169, "step": 350650 }, { "epoch": 29.15, "learning_rate": 1.1535626195161156e-07, "loss": 0.7844, "step": 350660 }, { "epoch": 29.15, "learning_rate": 1.1524540642407782e-07, "loss": 0.7297, "step": 350670 }, { "epoch": 29.15, "learning_rate": 1.1513455089654407e-07, "loss": 0.6738, "step": 350680 }, { "epoch": 29.15, "learning_rate": 1.1502369536901033e-07, "loss": 0.713, "step": 350690 }, { "epoch": 29.15, "learning_rate": 1.149128398414766e-07, "loss": 0.7476, "step": 350700 }, { "epoch": 29.15, "learning_rate": 1.1480198431394286e-07, "loss": 0.7812, "step": 350710 }, { "epoch": 29.15, "learning_rate": 1.146911287864091e-07, "loss": 0.6791, "step": 350720 }, { "epoch": 29.15, "learning_rate": 1.1458027325887537e-07, "loss": 0.6215, "step": 350730 }, { "epoch": 29.15, "learning_rate": 1.1446941773134162e-07, "loss": 0.6939, "step": 350740 }, { "epoch": 29.15, "learning_rate": 1.1435856220380788e-07, "loss": 0.6329, "step": 350750 }, { "epoch": 29.15, "learning_rate": 1.1424770667627415e-07, "loss": 0.744, "step": 350760 }, { "epoch": 29.16, "learning_rate": 1.141368511487404e-07, "loss": 0.7536, "step": 350770 }, { "epoch": 29.16, "learning_rate": 1.1402599562120666e-07, "loss": 0.7298, "step": 350780 }, { "epoch": 29.16, "learning_rate": 1.1391514009367291e-07, "loss": 0.7531, "step": 350790 }, { "epoch": 29.16, "learning_rate": 1.1380428456613918e-07, "loss": 0.721, "step": 350800 }, { "epoch": 29.16, "learning_rate": 1.1369342903860544e-07, "loss": 0.8603, "step": 350810 }, { "epoch": 29.16, "learning_rate": 1.1358257351107168e-07, "loss": 0.7111, "step": 350820 }, { "epoch": 29.16, "learning_rate": 1.1347171798353795e-07, "loss": 0.7004, "step": 350830 }, { "epoch": 29.16, "learning_rate": 1.133608624560042e-07, "loss": 0.7911, "step": 350840 }, { "epoch": 29.16, "learning_rate": 1.1325000692847046e-07, "loss": 0.75, "step": 350850 }, { "epoch": 29.16, "learning_rate": 1.1313915140093673e-07, "loss": 0.7619, "step": 350860 }, { "epoch": 29.16, "learning_rate": 1.1302829587340298e-07, "loss": 0.7077, "step": 350870 }, { "epoch": 29.16, "learning_rate": 1.1291744034586924e-07, "loss": 0.6923, "step": 350880 }, { "epoch": 29.17, "learning_rate": 1.128065848183355e-07, "loss": 0.7069, "step": 350890 }, { "epoch": 29.17, "learning_rate": 1.1269572929080176e-07, "loss": 0.734, "step": 350900 }, { "epoch": 29.17, "learning_rate": 1.1258487376326802e-07, "loss": 0.7286, "step": 350910 }, { "epoch": 29.17, "learning_rate": 1.1247401823573426e-07, "loss": 0.7178, "step": 350920 }, { "epoch": 29.17, "learning_rate": 1.1236316270820053e-07, "loss": 0.7332, "step": 350930 }, { "epoch": 29.17, "learning_rate": 1.1225230718066679e-07, "loss": 0.7449, "step": 350940 }, { "epoch": 29.17, "learning_rate": 1.1214145165313304e-07, "loss": 0.7001, "step": 350950 }, { "epoch": 29.17, "learning_rate": 1.1203059612559931e-07, "loss": 0.7349, "step": 350960 }, { "epoch": 29.17, "learning_rate": 1.1191974059806557e-07, "loss": 0.7867, "step": 350970 }, { "epoch": 29.17, "learning_rate": 1.1180888507053182e-07, "loss": 0.7029, "step": 350980 }, { "epoch": 29.17, "learning_rate": 1.1169802954299808e-07, "loss": 0.7218, "step": 350990 }, { "epoch": 29.17, "learning_rate": 1.1158717401546435e-07, "loss": 0.7418, "step": 351000 }, { "epoch": 29.18, "learning_rate": 1.114763184879306e-07, "loss": 0.7653, "step": 351010 }, { "epoch": 29.18, "learning_rate": 1.1136546296039686e-07, "loss": 0.7126, "step": 351020 }, { "epoch": 29.18, "learning_rate": 1.1125460743286311e-07, "loss": 0.7003, "step": 351030 }, { "epoch": 29.18, "learning_rate": 1.1114375190532937e-07, "loss": 0.7943, "step": 351040 }, { "epoch": 29.18, "learning_rate": 1.1103289637779563e-07, "loss": 0.753, "step": 351050 }, { "epoch": 29.18, "learning_rate": 1.109220408502619e-07, "loss": 0.6888, "step": 351060 }, { "epoch": 29.18, "learning_rate": 1.1081118532272815e-07, "loss": 0.7265, "step": 351070 }, { "epoch": 29.18, "learning_rate": 1.107003297951944e-07, "loss": 0.7666, "step": 351080 }, { "epoch": 29.18, "learning_rate": 1.1058947426766066e-07, "loss": 0.7191, "step": 351090 }, { "epoch": 29.18, "learning_rate": 1.1047861874012693e-07, "loss": 0.7433, "step": 351100 }, { "epoch": 29.18, "learning_rate": 1.1036776321259319e-07, "loss": 0.772, "step": 351110 }, { "epoch": 29.18, "learning_rate": 1.1025690768505944e-07, "loss": 0.7451, "step": 351120 }, { "epoch": 29.19, "learning_rate": 1.101460521575257e-07, "loss": 0.7351, "step": 351130 }, { "epoch": 29.19, "learning_rate": 1.1003519662999195e-07, "loss": 0.7068, "step": 351140 }, { "epoch": 29.19, "learning_rate": 1.0992434110245821e-07, "loss": 0.7295, "step": 351150 }, { "epoch": 29.19, "learning_rate": 1.0981348557492448e-07, "loss": 0.7326, "step": 351160 }, { "epoch": 29.19, "learning_rate": 1.0970263004739073e-07, "loss": 0.7365, "step": 351170 }, { "epoch": 29.19, "learning_rate": 1.0959177451985699e-07, "loss": 0.7297, "step": 351180 }, { "epoch": 29.19, "learning_rate": 1.0948091899232324e-07, "loss": 0.7127, "step": 351190 }, { "epoch": 29.19, "learning_rate": 1.0937006346478951e-07, "loss": 0.7309, "step": 351200 }, { "epoch": 29.19, "learning_rate": 1.0925920793725577e-07, "loss": 0.7424, "step": 351210 }, { "epoch": 29.19, "learning_rate": 1.0914835240972202e-07, "loss": 0.7729, "step": 351220 }, { "epoch": 29.19, "learning_rate": 1.090374968821883e-07, "loss": 0.7106, "step": 351230 }, { "epoch": 29.19, "learning_rate": 1.0892664135465454e-07, "loss": 0.752, "step": 351240 }, { "epoch": 29.2, "learning_rate": 1.0881578582712079e-07, "loss": 0.6741, "step": 351250 }, { "epoch": 29.2, "learning_rate": 1.0870493029958706e-07, "loss": 0.7623, "step": 351260 }, { "epoch": 29.2, "learning_rate": 1.0859407477205332e-07, "loss": 0.7157, "step": 351270 }, { "epoch": 29.2, "learning_rate": 1.0848321924451957e-07, "loss": 0.7605, "step": 351280 }, { "epoch": 29.2, "learning_rate": 1.0837236371698584e-07, "loss": 0.7275, "step": 351290 }, { "epoch": 29.2, "learning_rate": 1.082615081894521e-07, "loss": 0.7426, "step": 351300 }, { "epoch": 29.2, "learning_rate": 1.0816173821467173e-07, "loss": 0.7691, "step": 351310 }, { "epoch": 29.2, "learning_rate": 1.0805088268713798e-07, "loss": 0.6959, "step": 351320 }, { "epoch": 29.2, "learning_rate": 1.0794002715960424e-07, "loss": 0.7099, "step": 351330 }, { "epoch": 29.2, "learning_rate": 1.0782917163207051e-07, "loss": 0.7444, "step": 351340 }, { "epoch": 29.2, "learning_rate": 1.0771831610453676e-07, "loss": 0.6687, "step": 351350 }, { "epoch": 29.2, "learning_rate": 1.07607460577003e-07, "loss": 0.7807, "step": 351360 }, { "epoch": 29.21, "learning_rate": 1.0749660504946927e-07, "loss": 0.7215, "step": 351370 }, { "epoch": 29.21, "learning_rate": 1.0738574952193553e-07, "loss": 0.712, "step": 351380 }, { "epoch": 29.21, "learning_rate": 1.0727489399440179e-07, "loss": 0.7816, "step": 351390 }, { "epoch": 29.21, "learning_rate": 1.0716403846686804e-07, "loss": 0.785, "step": 351400 }, { "epoch": 29.21, "learning_rate": 1.0705318293933431e-07, "loss": 0.7281, "step": 351410 }, { "epoch": 29.21, "learning_rate": 1.0694232741180057e-07, "loss": 0.7861, "step": 351420 }, { "epoch": 29.21, "learning_rate": 1.0683147188426682e-07, "loss": 0.705, "step": 351430 }, { "epoch": 29.21, "learning_rate": 1.0672061635673309e-07, "loss": 0.7304, "step": 351440 }, { "epoch": 29.21, "learning_rate": 1.0660976082919935e-07, "loss": 0.7175, "step": 351450 }, { "epoch": 29.21, "learning_rate": 1.064989053016656e-07, "loss": 0.7708, "step": 351460 }, { "epoch": 29.21, "learning_rate": 1.0638804977413186e-07, "loss": 0.7387, "step": 351470 }, { "epoch": 29.21, "learning_rate": 1.0627719424659811e-07, "loss": 0.7027, "step": 351480 }, { "epoch": 29.22, "learning_rate": 1.0616633871906437e-07, "loss": 0.703, "step": 351490 }, { "epoch": 29.22, "learning_rate": 1.0605548319153064e-07, "loss": 0.7698, "step": 351500 }, { "epoch": 29.22, "learning_rate": 1.0594462766399689e-07, "loss": 0.791, "step": 351510 }, { "epoch": 29.22, "learning_rate": 1.0583377213646315e-07, "loss": 0.7151, "step": 351520 }, { "epoch": 29.22, "learning_rate": 1.057229166089294e-07, "loss": 0.7493, "step": 351530 }, { "epoch": 29.22, "learning_rate": 1.0561206108139567e-07, "loss": 0.6786, "step": 351540 }, { "epoch": 29.22, "learning_rate": 1.0550120555386193e-07, "loss": 0.7323, "step": 351550 }, { "epoch": 29.22, "learning_rate": 1.0539035002632818e-07, "loss": 0.7614, "step": 351560 }, { "epoch": 29.22, "learning_rate": 1.0527949449879444e-07, "loss": 0.6999, "step": 351570 }, { "epoch": 29.22, "learning_rate": 1.051686389712607e-07, "loss": 0.7678, "step": 351580 }, { "epoch": 29.22, "learning_rate": 1.0505778344372695e-07, "loss": 0.7524, "step": 351590 }, { "epoch": 29.22, "learning_rate": 1.0494692791619322e-07, "loss": 0.7978, "step": 351600 }, { "epoch": 29.23, "learning_rate": 1.0483607238865948e-07, "loss": 0.7593, "step": 351610 }, { "epoch": 29.23, "learning_rate": 1.0472521686112573e-07, "loss": 0.7477, "step": 351620 }, { "epoch": 29.23, "learning_rate": 1.0461436133359199e-07, "loss": 0.7079, "step": 351630 }, { "epoch": 29.23, "learning_rate": 1.0450350580605826e-07, "loss": 0.7122, "step": 351640 }, { "epoch": 29.23, "learning_rate": 1.0439265027852451e-07, "loss": 0.7031, "step": 351650 }, { "epoch": 29.23, "learning_rate": 1.0428179475099077e-07, "loss": 0.7594, "step": 351660 }, { "epoch": 29.23, "learning_rate": 1.0417093922345704e-07, "loss": 0.7731, "step": 351670 }, { "epoch": 29.23, "learning_rate": 1.0406008369592328e-07, "loss": 0.7193, "step": 351680 }, { "epoch": 29.23, "learning_rate": 1.0394922816838953e-07, "loss": 0.7666, "step": 351690 }, { "epoch": 29.23, "learning_rate": 1.038383726408558e-07, "loss": 0.688, "step": 351700 }, { "epoch": 29.23, "learning_rate": 1.0372751711332206e-07, "loss": 0.7179, "step": 351710 }, { "epoch": 29.23, "learning_rate": 1.0361666158578831e-07, "loss": 0.7254, "step": 351720 }, { "epoch": 29.24, "learning_rate": 1.0350580605825457e-07, "loss": 0.746, "step": 351730 }, { "epoch": 29.24, "learning_rate": 1.0339495053072084e-07, "loss": 0.7326, "step": 351740 }, { "epoch": 29.24, "learning_rate": 1.032840950031871e-07, "loss": 0.7138, "step": 351750 }, { "epoch": 29.24, "learning_rate": 1.0317323947565335e-07, "loss": 0.754, "step": 351760 }, { "epoch": 29.24, "learning_rate": 1.0306238394811962e-07, "loss": 0.6936, "step": 351770 }, { "epoch": 29.24, "learning_rate": 1.0295152842058586e-07, "loss": 0.7705, "step": 351780 }, { "epoch": 29.24, "learning_rate": 1.0284067289305212e-07, "loss": 0.7597, "step": 351790 }, { "epoch": 29.24, "learning_rate": 1.0272981736551839e-07, "loss": 0.7184, "step": 351800 }, { "epoch": 29.24, "learning_rate": 1.0261896183798464e-07, "loss": 0.7345, "step": 351810 }, { "epoch": 29.24, "learning_rate": 1.025081063104509e-07, "loss": 0.7684, "step": 351820 }, { "epoch": 29.24, "learning_rate": 1.0239725078291715e-07, "loss": 0.7504, "step": 351830 }, { "epoch": 29.24, "learning_rate": 1.0228639525538342e-07, "loss": 0.7167, "step": 351840 }, { "epoch": 29.25, "learning_rate": 1.0217553972784968e-07, "loss": 0.6968, "step": 351850 }, { "epoch": 29.25, "learning_rate": 1.0206468420031593e-07, "loss": 0.736, "step": 351860 }, { "epoch": 29.25, "learning_rate": 1.019538286727822e-07, "loss": 0.6771, "step": 351870 }, { "epoch": 29.25, "learning_rate": 1.0184297314524844e-07, "loss": 0.7507, "step": 351880 }, { "epoch": 29.25, "learning_rate": 1.017321176177147e-07, "loss": 0.6854, "step": 351890 }, { "epoch": 29.25, "learning_rate": 1.0162126209018097e-07, "loss": 0.7274, "step": 351900 }, { "epoch": 29.25, "learning_rate": 1.0151040656264722e-07, "loss": 0.7804, "step": 351910 }, { "epoch": 29.25, "learning_rate": 1.0139955103511348e-07, "loss": 0.7823, "step": 351920 }, { "epoch": 29.25, "learning_rate": 1.0128869550757974e-07, "loss": 0.7626, "step": 351930 }, { "epoch": 29.25, "learning_rate": 1.01177839980046e-07, "loss": 0.7198, "step": 351940 }, { "epoch": 29.25, "learning_rate": 1.0106698445251226e-07, "loss": 0.7195, "step": 351950 }, { "epoch": 29.25, "learning_rate": 1.0095612892497852e-07, "loss": 0.8458, "step": 351960 }, { "epoch": 29.26, "learning_rate": 1.0084527339744478e-07, "loss": 0.7555, "step": 351970 }, { "epoch": 29.26, "learning_rate": 1.0073441786991104e-07, "loss": 0.7623, "step": 351980 }, { "epoch": 29.26, "learning_rate": 1.0062356234237728e-07, "loss": 0.7363, "step": 351990 }, { "epoch": 29.26, "learning_rate": 1.0051270681484355e-07, "loss": 0.7285, "step": 352000 }, { "epoch": 29.26, "learning_rate": 1.0040185128730981e-07, "loss": 0.6782, "step": 352010 }, { "epoch": 29.26, "learning_rate": 1.0029099575977606e-07, "loss": 0.6919, "step": 352020 }, { "epoch": 29.26, "learning_rate": 1.0018014023224232e-07, "loss": 0.644, "step": 352030 }, { "epoch": 29.26, "learning_rate": 1.0006928470470859e-07, "loss": 0.7077, "step": 352040 }, { "epoch": 29.26, "learning_rate": 9.995842917717484e-08, "loss": 0.7148, "step": 352050 }, { "epoch": 29.26, "learning_rate": 9.98475736496411e-08, "loss": 0.7378, "step": 352060 }, { "epoch": 29.26, "learning_rate": 9.973671812210737e-08, "loss": 0.7256, "step": 352070 }, { "epoch": 29.26, "learning_rate": 9.962586259457362e-08, "loss": 0.7168, "step": 352080 }, { "epoch": 29.27, "learning_rate": 9.951500706703987e-08, "loss": 0.7299, "step": 352090 }, { "epoch": 29.27, "learning_rate": 9.940415153950613e-08, "loss": 0.725, "step": 352100 }, { "epoch": 29.27, "learning_rate": 9.929329601197239e-08, "loss": 0.7951, "step": 352110 }, { "epoch": 29.27, "learning_rate": 9.918244048443865e-08, "loss": 0.7218, "step": 352120 }, { "epoch": 29.27, "learning_rate": 9.90715849569049e-08, "loss": 0.7407, "step": 352130 }, { "epoch": 29.27, "learning_rate": 9.896072942937117e-08, "loss": 0.7738, "step": 352140 }, { "epoch": 29.27, "learning_rate": 9.884987390183743e-08, "loss": 0.7959, "step": 352150 }, { "epoch": 29.27, "learning_rate": 9.873901837430368e-08, "loss": 0.8176, "step": 352160 }, { "epoch": 29.27, "learning_rate": 9.862816284676995e-08, "loss": 0.681, "step": 352170 }, { "epoch": 29.27, "learning_rate": 9.85173073192362e-08, "loss": 0.692, "step": 352180 }, { "epoch": 29.27, "learning_rate": 9.840645179170246e-08, "loss": 0.7152, "step": 352190 }, { "epoch": 29.27, "learning_rate": 9.829559626416872e-08, "loss": 0.7444, "step": 352200 }, { "epoch": 29.28, "learning_rate": 9.818474073663497e-08, "loss": 0.7738, "step": 352210 }, { "epoch": 29.28, "learning_rate": 9.807388520910123e-08, "loss": 0.7087, "step": 352220 }, { "epoch": 29.28, "learning_rate": 9.79630296815675e-08, "loss": 0.6988, "step": 352230 }, { "epoch": 29.28, "learning_rate": 9.785217415403375e-08, "loss": 0.7213, "step": 352240 }, { "epoch": 29.28, "learning_rate": 9.774131862650001e-08, "loss": 0.6805, "step": 352250 }, { "epoch": 29.28, "learning_rate": 9.763046309896626e-08, "loss": 0.7287, "step": 352260 }, { "epoch": 29.28, "learning_rate": 9.751960757143253e-08, "loss": 0.7532, "step": 352270 }, { "epoch": 29.28, "learning_rate": 9.740875204389879e-08, "loss": 0.7151, "step": 352280 }, { "epoch": 29.28, "learning_rate": 9.729789651636504e-08, "loss": 0.7519, "step": 352290 }, { "epoch": 29.28, "learning_rate": 9.71870409888313e-08, "loss": 0.7346, "step": 352300 }, { "epoch": 29.28, "learning_rate": 9.707618546129756e-08, "loss": 0.784, "step": 352310 }, { "epoch": 29.28, "learning_rate": 9.696532993376381e-08, "loss": 0.7225, "step": 352320 }, { "epoch": 29.29, "learning_rate": 9.685447440623008e-08, "loss": 0.7073, "step": 352330 }, { "epoch": 29.29, "learning_rate": 9.674361887869634e-08, "loss": 0.7362, "step": 352340 }, { "epoch": 29.29, "learning_rate": 9.663276335116259e-08, "loss": 0.7651, "step": 352350 }, { "epoch": 29.29, "learning_rate": 9.652190782362885e-08, "loss": 0.768, "step": 352360 }, { "epoch": 29.29, "learning_rate": 9.641105229609512e-08, "loss": 0.7098, "step": 352370 }, { "epoch": 29.29, "learning_rate": 9.630019676856137e-08, "loss": 0.7544, "step": 352380 }, { "epoch": 29.29, "learning_rate": 9.618934124102763e-08, "loss": 0.7335, "step": 352390 }, { "epoch": 29.29, "learning_rate": 9.60784857134939e-08, "loss": 0.7099, "step": 352400 }, { "epoch": 29.29, "learning_rate": 9.596763018596014e-08, "loss": 0.7286, "step": 352410 }, { "epoch": 29.29, "learning_rate": 9.58567746584264e-08, "loss": 0.6959, "step": 352420 }, { "epoch": 29.29, "learning_rate": 9.574591913089266e-08, "loss": 0.7483, "step": 352430 }, { "epoch": 29.29, "learning_rate": 9.563506360335892e-08, "loss": 0.6995, "step": 352440 }, { "epoch": 29.3, "learning_rate": 9.552420807582517e-08, "loss": 0.7329, "step": 352450 }, { "epoch": 29.3, "learning_rate": 9.541335254829143e-08, "loss": 0.7617, "step": 352460 }, { "epoch": 29.3, "learning_rate": 9.53024970207577e-08, "loss": 0.734, "step": 352470 }, { "epoch": 29.3, "learning_rate": 9.519164149322395e-08, "loss": 0.7077, "step": 352480 }, { "epoch": 29.3, "learning_rate": 9.508078596569021e-08, "loss": 0.719, "step": 352490 }, { "epoch": 29.3, "learning_rate": 9.496993043815648e-08, "loss": 0.7155, "step": 352500 }, { "epoch": 29.3, "learning_rate": 9.485907491062272e-08, "loss": 0.7318, "step": 352510 }, { "epoch": 29.3, "learning_rate": 9.474821938308898e-08, "loss": 0.7328, "step": 352520 }, { "epoch": 29.3, "learning_rate": 9.463736385555525e-08, "loss": 0.7431, "step": 352530 }, { "epoch": 29.3, "learning_rate": 9.45265083280215e-08, "loss": 0.752, "step": 352540 }, { "epoch": 29.3, "learning_rate": 9.441565280048776e-08, "loss": 0.7172, "step": 352550 }, { "epoch": 29.3, "learning_rate": 9.430479727295401e-08, "loss": 0.7978, "step": 352560 }, { "epoch": 29.31, "learning_rate": 9.419394174542028e-08, "loss": 0.7594, "step": 352570 }, { "epoch": 29.31, "learning_rate": 9.408308621788654e-08, "loss": 0.7107, "step": 352580 }, { "epoch": 29.31, "learning_rate": 9.397223069035279e-08, "loss": 0.7862, "step": 352590 }, { "epoch": 29.31, "learning_rate": 9.386137516281906e-08, "loss": 0.7144, "step": 352600 }, { "epoch": 29.31, "learning_rate": 9.37505196352853e-08, "loss": 0.7317, "step": 352610 }, { "epoch": 29.31, "learning_rate": 9.363966410775156e-08, "loss": 0.7647, "step": 352620 }, { "epoch": 29.31, "learning_rate": 9.352880858021783e-08, "loss": 0.7102, "step": 352630 }, { "epoch": 29.31, "learning_rate": 9.341795305268408e-08, "loss": 0.6994, "step": 352640 }, { "epoch": 29.31, "learning_rate": 9.330709752515034e-08, "loss": 0.7428, "step": 352650 }, { "epoch": 29.31, "learning_rate": 9.31962419976166e-08, "loss": 0.808, "step": 352660 }, { "epoch": 29.31, "learning_rate": 9.308538647008286e-08, "loss": 0.7179, "step": 352670 }, { "epoch": 29.31, "learning_rate": 9.297453094254912e-08, "loss": 0.7254, "step": 352680 }, { "epoch": 29.32, "learning_rate": 9.286367541501538e-08, "loss": 0.7477, "step": 352690 }, { "epoch": 29.32, "learning_rate": 9.275281988748164e-08, "loss": 0.7254, "step": 352700 }, { "epoch": 29.32, "learning_rate": 9.26419643599479e-08, "loss": 0.7481, "step": 352710 }, { "epoch": 29.32, "learning_rate": 9.253110883241414e-08, "loss": 0.7307, "step": 352720 }, { "epoch": 29.32, "learning_rate": 9.242025330488041e-08, "loss": 0.7479, "step": 352730 }, { "epoch": 29.32, "learning_rate": 9.230939777734667e-08, "loss": 0.7054, "step": 352740 }, { "epoch": 29.32, "learning_rate": 9.219854224981292e-08, "loss": 0.7184, "step": 352750 }, { "epoch": 29.32, "learning_rate": 9.208768672227918e-08, "loss": 0.7195, "step": 352760 }, { "epoch": 29.32, "learning_rate": 9.197683119474545e-08, "loss": 0.7609, "step": 352770 }, { "epoch": 29.32, "learning_rate": 9.18659756672117e-08, "loss": 0.736, "step": 352780 }, { "epoch": 29.32, "learning_rate": 9.175512013967796e-08, "loss": 0.7242, "step": 352790 }, { "epoch": 29.32, "learning_rate": 9.164426461214423e-08, "loss": 0.6671, "step": 352800 }, { "epoch": 29.33, "learning_rate": 9.153340908461048e-08, "loss": 0.8169, "step": 352810 }, { "epoch": 29.33, "learning_rate": 9.142255355707673e-08, "loss": 0.6876, "step": 352820 }, { "epoch": 29.33, "learning_rate": 9.1311698029543e-08, "loss": 0.7399, "step": 352830 }, { "epoch": 29.33, "learning_rate": 9.120084250200925e-08, "loss": 0.7668, "step": 352840 }, { "epoch": 29.33, "learning_rate": 9.10899869744755e-08, "loss": 0.723, "step": 352850 }, { "epoch": 29.33, "learning_rate": 9.097913144694177e-08, "loss": 0.7911, "step": 352860 }, { "epoch": 29.33, "learning_rate": 9.086827591940803e-08, "loss": 0.699, "step": 352870 }, { "epoch": 29.33, "learning_rate": 9.075742039187429e-08, "loss": 0.7382, "step": 352880 }, { "epoch": 29.33, "learning_rate": 9.064656486434054e-08, "loss": 0.7477, "step": 352890 }, { "epoch": 29.33, "learning_rate": 9.053570933680681e-08, "loss": 0.708, "step": 352900 }, { "epoch": 29.33, "learning_rate": 9.042485380927307e-08, "loss": 0.714, "step": 352910 }, { "epoch": 29.33, "learning_rate": 9.031399828173932e-08, "loss": 0.698, "step": 352920 }, { "epoch": 29.34, "learning_rate": 9.020314275420558e-08, "loss": 0.7038, "step": 352930 }, { "epoch": 29.34, "learning_rate": 9.009228722667183e-08, "loss": 0.7135, "step": 352940 }, { "epoch": 29.34, "learning_rate": 8.998143169913809e-08, "loss": 0.7519, "step": 352950 }, { "epoch": 29.34, "learning_rate": 8.987057617160436e-08, "loss": 0.7276, "step": 352960 }, { "epoch": 29.34, "learning_rate": 8.975972064407061e-08, "loss": 0.7304, "step": 352970 }, { "epoch": 29.34, "learning_rate": 8.964886511653687e-08, "loss": 0.6929, "step": 352980 }, { "epoch": 29.34, "learning_rate": 8.953800958900312e-08, "loss": 0.7063, "step": 352990 }, { "epoch": 29.34, "learning_rate": 8.942715406146939e-08, "loss": 0.6748, "step": 353000 }, { "epoch": 29.34, "learning_rate": 8.931629853393565e-08, "loss": 0.7594, "step": 353010 }, { "epoch": 29.34, "learning_rate": 8.92054430064019e-08, "loss": 0.7492, "step": 353020 }, { "epoch": 29.34, "learning_rate": 8.909458747886816e-08, "loss": 0.7749, "step": 353030 }, { "epoch": 29.34, "learning_rate": 8.898373195133442e-08, "loss": 0.7233, "step": 353040 }, { "epoch": 29.35, "learning_rate": 8.887287642380067e-08, "loss": 0.739, "step": 353050 }, { "epoch": 29.35, "learning_rate": 8.876202089626694e-08, "loss": 0.77, "step": 353060 }, { "epoch": 29.35, "learning_rate": 8.86511653687332e-08, "loss": 0.7064, "step": 353070 }, { "epoch": 29.35, "learning_rate": 8.854030984119945e-08, "loss": 0.7372, "step": 353080 }, { "epoch": 29.35, "learning_rate": 8.842945431366571e-08, "loss": 0.7728, "step": 353090 }, { "epoch": 29.35, "learning_rate": 8.831859878613198e-08, "loss": 0.7367, "step": 353100 }, { "epoch": 29.35, "learning_rate": 8.820774325859823e-08, "loss": 0.7821, "step": 353110 }, { "epoch": 29.35, "learning_rate": 8.809688773106449e-08, "loss": 0.7416, "step": 353120 }, { "epoch": 29.35, "learning_rate": 8.798603220353076e-08, "loss": 0.7282, "step": 353130 }, { "epoch": 29.35, "learning_rate": 8.7875176675997e-08, "loss": 0.7155, "step": 353140 }, { "epoch": 29.35, "learning_rate": 8.776432114846325e-08, "loss": 0.7366, "step": 353150 }, { "epoch": 29.35, "learning_rate": 8.765346562092952e-08, "loss": 0.7627, "step": 353160 }, { "epoch": 29.35, "learning_rate": 8.754261009339578e-08, "loss": 0.7582, "step": 353170 }, { "epoch": 29.36, "learning_rate": 8.743175456586203e-08, "loss": 0.7063, "step": 353180 }, { "epoch": 29.36, "learning_rate": 8.732089903832829e-08, "loss": 0.7388, "step": 353190 }, { "epoch": 29.36, "learning_rate": 8.721004351079456e-08, "loss": 0.7685, "step": 353200 }, { "epoch": 29.36, "learning_rate": 8.709918798326081e-08, "loss": 0.7122, "step": 353210 }, { "epoch": 29.36, "learning_rate": 8.698833245572707e-08, "loss": 0.7417, "step": 353220 }, { "epoch": 29.36, "learning_rate": 8.687747692819334e-08, "loss": 0.7484, "step": 353230 }, { "epoch": 29.36, "learning_rate": 8.676662140065958e-08, "loss": 0.6883, "step": 353240 }, { "epoch": 29.36, "learning_rate": 8.665576587312584e-08, "loss": 0.6797, "step": 353250 }, { "epoch": 29.36, "learning_rate": 8.65449103455921e-08, "loss": 0.8044, "step": 353260 }, { "epoch": 29.36, "learning_rate": 8.643405481805836e-08, "loss": 0.7005, "step": 353270 }, { "epoch": 29.36, "learning_rate": 8.632319929052462e-08, "loss": 0.7254, "step": 353280 }, { "epoch": 29.36, "learning_rate": 8.621234376299087e-08, "loss": 0.7293, "step": 353290 }, { "epoch": 29.37, "learning_rate": 8.610148823545714e-08, "loss": 0.7091, "step": 353300 }, { "epoch": 29.37, "learning_rate": 8.59906327079234e-08, "loss": 0.755, "step": 353310 }, { "epoch": 29.37, "learning_rate": 8.587977718038965e-08, "loss": 0.6896, "step": 353320 }, { "epoch": 29.37, "learning_rate": 8.576892165285592e-08, "loss": 0.6935, "step": 353330 }, { "epoch": 29.37, "learning_rate": 8.565806612532216e-08, "loss": 0.7128, "step": 353340 }, { "epoch": 29.37, "learning_rate": 8.554721059778842e-08, "loss": 0.6543, "step": 353350 }, { "epoch": 29.37, "learning_rate": 8.543635507025469e-08, "loss": 0.7281, "step": 353360 }, { "epoch": 29.37, "learning_rate": 8.532549954272094e-08, "loss": 0.7171, "step": 353370 }, { "epoch": 29.37, "learning_rate": 8.52146440151872e-08, "loss": 0.7308, "step": 353380 }, { "epoch": 29.37, "learning_rate": 8.510378848765346e-08, "loss": 0.7189, "step": 353390 }, { "epoch": 29.37, "learning_rate": 8.499293296011972e-08, "loss": 0.7527, "step": 353400 }, { "epoch": 29.37, "learning_rate": 8.488207743258598e-08, "loss": 0.7565, "step": 353410 }, { "epoch": 29.38, "learning_rate": 8.477122190505224e-08, "loss": 0.7439, "step": 353420 }, { "epoch": 29.38, "learning_rate": 8.46603663775185e-08, "loss": 0.7682, "step": 353430 }, { "epoch": 29.38, "learning_rate": 8.454951084998476e-08, "loss": 0.7071, "step": 353440 }, { "epoch": 29.38, "learning_rate": 8.4438655322451e-08, "loss": 0.6587, "step": 353450 }, { "epoch": 29.38, "learning_rate": 8.432779979491727e-08, "loss": 0.7764, "step": 353460 }, { "epoch": 29.38, "learning_rate": 8.421694426738353e-08, "loss": 0.7548, "step": 353470 }, { "epoch": 29.38, "learning_rate": 8.410608873984978e-08, "loss": 0.6802, "step": 353480 }, { "epoch": 29.38, "learning_rate": 8.399523321231604e-08, "loss": 0.7466, "step": 353490 }, { "epoch": 29.38, "learning_rate": 8.388437768478231e-08, "loss": 0.7106, "step": 353500 }, { "epoch": 29.38, "learning_rate": 8.377352215724856e-08, "loss": 0.7587, "step": 353510 }, { "epoch": 29.38, "learning_rate": 8.366266662971482e-08, "loss": 0.7308, "step": 353520 }, { "epoch": 29.38, "learning_rate": 8.355181110218109e-08, "loss": 0.7435, "step": 353530 }, { "epoch": 29.39, "learning_rate": 8.344095557464734e-08, "loss": 0.7047, "step": 353540 }, { "epoch": 29.39, "learning_rate": 8.333010004711359e-08, "loss": 0.7278, "step": 353550 }, { "epoch": 29.39, "learning_rate": 8.321924451957985e-08, "loss": 0.727, "step": 353560 }, { "epoch": 29.39, "learning_rate": 8.310838899204611e-08, "loss": 0.7562, "step": 353570 }, { "epoch": 29.39, "learning_rate": 8.299753346451237e-08, "loss": 0.7614, "step": 353580 }, { "epoch": 29.39, "learning_rate": 8.288667793697863e-08, "loss": 0.742, "step": 353590 }, { "epoch": 29.39, "learning_rate": 8.277582240944489e-08, "loss": 0.7428, "step": 353600 }, { "epoch": 29.39, "learning_rate": 8.266496688191115e-08, "loss": 0.7249, "step": 353610 }, { "epoch": 29.39, "learning_rate": 8.25541113543774e-08, "loss": 0.6691, "step": 353620 }, { "epoch": 29.39, "learning_rate": 8.244325582684367e-08, "loss": 0.7101, "step": 353630 }, { "epoch": 29.39, "learning_rate": 8.233240029930993e-08, "loss": 0.7361, "step": 353640 }, { "epoch": 29.39, "learning_rate": 8.222154477177618e-08, "loss": 0.7063, "step": 353650 }, { "epoch": 29.4, "learning_rate": 8.211068924424244e-08, "loss": 0.7709, "step": 353660 }, { "epoch": 29.4, "learning_rate": 8.199983371670869e-08, "loss": 0.7039, "step": 353670 }, { "epoch": 29.4, "learning_rate": 8.188897818917495e-08, "loss": 0.7314, "step": 353680 }, { "epoch": 29.4, "learning_rate": 8.177812266164122e-08, "loss": 0.7508, "step": 353690 }, { "epoch": 29.4, "learning_rate": 8.166726713410747e-08, "loss": 0.8059, "step": 353700 }, { "epoch": 29.4, "learning_rate": 8.155641160657373e-08, "loss": 0.7583, "step": 353710 }, { "epoch": 29.4, "learning_rate": 8.144555607903998e-08, "loss": 0.7006, "step": 353720 }, { "epoch": 29.4, "learning_rate": 8.133470055150625e-08, "loss": 0.7041, "step": 353730 }, { "epoch": 29.4, "learning_rate": 8.122384502397251e-08, "loss": 0.7308, "step": 353740 }, { "epoch": 29.4, "learning_rate": 8.111298949643876e-08, "loss": 0.698, "step": 353750 }, { "epoch": 29.4, "learning_rate": 8.100213396890502e-08, "loss": 0.7712, "step": 353760 }, { "epoch": 29.4, "learning_rate": 8.089127844137128e-08, "loss": 0.7258, "step": 353770 }, { "epoch": 29.41, "learning_rate": 8.078042291383753e-08, "loss": 0.7445, "step": 353780 }, { "epoch": 29.41, "learning_rate": 8.06695673863038e-08, "loss": 0.7091, "step": 353790 }, { "epoch": 29.41, "learning_rate": 8.055871185877006e-08, "loss": 0.7001, "step": 353800 }, { "epoch": 29.41, "learning_rate": 8.044785633123631e-08, "loss": 0.7515, "step": 353810 }, { "epoch": 29.41, "learning_rate": 8.033700080370257e-08, "loss": 0.7306, "step": 353820 }, { "epoch": 29.41, "learning_rate": 8.022614527616884e-08, "loss": 0.7415, "step": 353830 }, { "epoch": 29.41, "learning_rate": 8.011528974863509e-08, "loss": 0.6852, "step": 353840 }, { "epoch": 29.41, "learning_rate": 8.000443422110135e-08, "loss": 0.7307, "step": 353850 }, { "epoch": 29.41, "learning_rate": 7.989357869356762e-08, "loss": 0.7781, "step": 353860 }, { "epoch": 29.41, "learning_rate": 7.978272316603386e-08, "loss": 0.7551, "step": 353870 }, { "epoch": 29.41, "learning_rate": 7.967186763850011e-08, "loss": 0.7897, "step": 353880 }, { "epoch": 29.41, "learning_rate": 7.956101211096638e-08, "loss": 0.7822, "step": 353890 }, { "epoch": 29.42, "learning_rate": 7.945015658343264e-08, "loss": 0.6773, "step": 353900 }, { "epoch": 29.42, "learning_rate": 7.93393010558989e-08, "loss": 0.798, "step": 353910 }, { "epoch": 29.42, "learning_rate": 7.922844552836515e-08, "loss": 0.7508, "step": 353920 }, { "epoch": 29.42, "learning_rate": 7.911759000083142e-08, "loss": 0.7332, "step": 353930 }, { "epoch": 29.42, "learning_rate": 7.900673447329767e-08, "loss": 0.7122, "step": 353940 }, { "epoch": 29.42, "learning_rate": 7.889587894576393e-08, "loss": 0.7254, "step": 353950 }, { "epoch": 29.42, "learning_rate": 7.87850234182302e-08, "loss": 0.8006, "step": 353960 }, { "epoch": 29.42, "learning_rate": 7.867416789069644e-08, "loss": 0.7725, "step": 353970 }, { "epoch": 29.42, "learning_rate": 7.85633123631627e-08, "loss": 0.7574, "step": 353980 }, { "epoch": 29.42, "learning_rate": 7.845245683562897e-08, "loss": 0.8231, "step": 353990 }, { "epoch": 29.42, "learning_rate": 7.834160130809522e-08, "loss": 0.751, "step": 354000 }, { "epoch": 29.42, "learning_rate": 7.823074578056148e-08, "loss": 0.731, "step": 354010 }, { "epoch": 29.43, "learning_rate": 7.811989025302773e-08, "loss": 0.689, "step": 354020 }, { "epoch": 29.43, "learning_rate": 7.8009034725494e-08, "loss": 0.6521, "step": 354030 }, { "epoch": 29.43, "learning_rate": 7.789817919796026e-08, "loss": 0.7056, "step": 354040 }, { "epoch": 29.43, "learning_rate": 7.778732367042651e-08, "loss": 0.699, "step": 354050 }, { "epoch": 29.43, "learning_rate": 7.767646814289278e-08, "loss": 0.6837, "step": 354060 }, { "epoch": 29.43, "learning_rate": 7.756561261535902e-08, "loss": 0.7603, "step": 354070 }, { "epoch": 29.43, "learning_rate": 7.745475708782528e-08, "loss": 0.7283, "step": 354080 }, { "epoch": 29.43, "learning_rate": 7.734390156029155e-08, "loss": 0.7045, "step": 354090 }, { "epoch": 29.43, "learning_rate": 7.72330460327578e-08, "loss": 0.7558, "step": 354100 }, { "epoch": 29.43, "learning_rate": 7.712219050522406e-08, "loss": 0.7431, "step": 354110 }, { "epoch": 29.43, "learning_rate": 7.701133497769031e-08, "loss": 0.6773, "step": 354120 }, { "epoch": 29.43, "learning_rate": 7.690047945015658e-08, "loss": 0.7249, "step": 354130 }, { "epoch": 29.44, "learning_rate": 7.678962392262284e-08, "loss": 0.7156, "step": 354140 }, { "epoch": 29.44, "learning_rate": 7.66787683950891e-08, "loss": 0.7063, "step": 354150 }, { "epoch": 29.44, "learning_rate": 7.656791286755536e-08, "loss": 0.7544, "step": 354160 }, { "epoch": 29.44, "learning_rate": 7.645705734002162e-08, "loss": 0.7594, "step": 354170 }, { "epoch": 29.44, "learning_rate": 7.634620181248786e-08, "loss": 0.697, "step": 354180 }, { "epoch": 29.44, "learning_rate": 7.623534628495413e-08, "loss": 0.7274, "step": 354190 }, { "epoch": 29.44, "learning_rate": 7.612449075742039e-08, "loss": 0.7622, "step": 354200 }, { "epoch": 29.44, "learning_rate": 7.601363522988664e-08, "loss": 0.7527, "step": 354210 }, { "epoch": 29.44, "learning_rate": 7.590277970235291e-08, "loss": 0.7751, "step": 354220 }, { "epoch": 29.44, "learning_rate": 7.579192417481917e-08, "loss": 0.7219, "step": 354230 }, { "epoch": 29.44, "learning_rate": 7.568106864728542e-08, "loss": 0.7328, "step": 354240 }, { "epoch": 29.44, "learning_rate": 7.557021311975168e-08, "loss": 0.716, "step": 354250 }, { "epoch": 29.45, "learning_rate": 7.545935759221795e-08, "loss": 0.7714, "step": 354260 }, { "epoch": 29.45, "learning_rate": 7.53485020646842e-08, "loss": 0.7756, "step": 354270 }, { "epoch": 29.45, "learning_rate": 7.523764653715044e-08, "loss": 0.7407, "step": 354280 }, { "epoch": 29.45, "learning_rate": 7.512679100961671e-08, "loss": 0.7095, "step": 354290 }, { "epoch": 29.45, "learning_rate": 7.501593548208297e-08, "loss": 0.7423, "step": 354300 }, { "epoch": 29.45, "learning_rate": 7.490507995454922e-08, "loss": 0.7542, "step": 354310 }, { "epoch": 29.45, "learning_rate": 7.47942244270155e-08, "loss": 0.757, "step": 354320 }, { "epoch": 29.45, "learning_rate": 7.468336889948175e-08, "loss": 0.7638, "step": 354330 }, { "epoch": 29.45, "learning_rate": 7.4572513371948e-08, "loss": 0.7027, "step": 354340 }, { "epoch": 29.45, "learning_rate": 7.446165784441426e-08, "loss": 0.7437, "step": 354350 }, { "epoch": 29.45, "learning_rate": 7.435080231688053e-08, "loss": 0.7553, "step": 354360 }, { "epoch": 29.45, "learning_rate": 7.423994678934679e-08, "loss": 0.7233, "step": 354370 }, { "epoch": 29.46, "learning_rate": 7.412909126181304e-08, "loss": 0.7722, "step": 354380 }, { "epoch": 29.46, "learning_rate": 7.40182357342793e-08, "loss": 0.7522, "step": 354390 }, { "epoch": 29.46, "learning_rate": 7.390738020674555e-08, "loss": 0.7461, "step": 354400 }, { "epoch": 29.46, "learning_rate": 7.379652467921181e-08, "loss": 0.7421, "step": 354410 }, { "epoch": 29.46, "learning_rate": 7.368566915167808e-08, "loss": 0.6727, "step": 354420 }, { "epoch": 29.46, "learning_rate": 7.357481362414433e-08, "loss": 0.7618, "step": 354430 }, { "epoch": 29.46, "learning_rate": 7.346395809661059e-08, "loss": 0.7344, "step": 354440 }, { "epoch": 29.46, "learning_rate": 7.335310256907684e-08, "loss": 0.7483, "step": 354450 }, { "epoch": 29.46, "learning_rate": 7.324224704154311e-08, "loss": 0.7545, "step": 354460 }, { "epoch": 29.46, "learning_rate": 7.313139151400937e-08, "loss": 0.6776, "step": 354470 }, { "epoch": 29.46, "learning_rate": 7.302053598647562e-08, "loss": 0.6872, "step": 354480 }, { "epoch": 29.46, "learning_rate": 7.290968045894188e-08, "loss": 0.6971, "step": 354490 }, { "epoch": 29.47, "learning_rate": 7.279882493140813e-08, "loss": 0.7679, "step": 354500 }, { "epoch": 29.47, "learning_rate": 7.268796940387439e-08, "loss": 0.7405, "step": 354510 }, { "epoch": 29.47, "learning_rate": 7.257711387634066e-08, "loss": 0.6757, "step": 354520 }, { "epoch": 29.47, "learning_rate": 7.246625834880692e-08, "loss": 0.8002, "step": 354530 }, { "epoch": 29.47, "learning_rate": 7.235540282127317e-08, "loss": 0.7474, "step": 354540 }, { "epoch": 29.47, "learning_rate": 7.224454729373943e-08, "loss": 0.6987, "step": 354550 }, { "epoch": 29.47, "learning_rate": 7.21336917662057e-08, "loss": 0.8004, "step": 354560 }, { "epoch": 29.47, "learning_rate": 7.202283623867195e-08, "loss": 0.7237, "step": 354570 }, { "epoch": 29.47, "learning_rate": 7.19119807111382e-08, "loss": 0.7366, "step": 354580 }, { "epoch": 29.47, "learning_rate": 7.180112518360448e-08, "loss": 0.7083, "step": 354590 }, { "epoch": 29.47, "learning_rate": 7.169026965607072e-08, "loss": 0.7398, "step": 354600 }, { "epoch": 29.47, "learning_rate": 7.157941412853697e-08, "loss": 0.7712, "step": 354610 }, { "epoch": 29.48, "learning_rate": 7.146855860100324e-08, "loss": 0.7037, "step": 354620 }, { "epoch": 29.48, "learning_rate": 7.13577030734695e-08, "loss": 0.7922, "step": 354630 }, { "epoch": 29.48, "learning_rate": 7.124684754593575e-08, "loss": 0.7238, "step": 354640 }, { "epoch": 29.48, "learning_rate": 7.113599201840201e-08, "loss": 0.7193, "step": 354650 }, { "epoch": 29.48, "learning_rate": 7.102513649086828e-08, "loss": 0.7783, "step": 354660 }, { "epoch": 29.48, "learning_rate": 7.091428096333453e-08, "loss": 0.7041, "step": 354670 }, { "epoch": 29.48, "learning_rate": 7.080342543580079e-08, "loss": 0.7766, "step": 354680 }, { "epoch": 29.48, "learning_rate": 7.069256990826706e-08, "loss": 0.7193, "step": 354690 }, { "epoch": 29.48, "learning_rate": 7.05817143807333e-08, "loss": 0.7344, "step": 354700 }, { "epoch": 29.48, "learning_rate": 7.047085885319956e-08, "loss": 0.6884, "step": 354710 }, { "epoch": 29.48, "learning_rate": 7.036000332566583e-08, "loss": 0.7619, "step": 354720 }, { "epoch": 29.48, "learning_rate": 7.024914779813208e-08, "loss": 0.7292, "step": 354730 }, { "epoch": 29.49, "learning_rate": 7.013829227059834e-08, "loss": 0.6628, "step": 354740 }, { "epoch": 29.49, "learning_rate": 7.002743674306459e-08, "loss": 0.7495, "step": 354750 }, { "epoch": 29.49, "learning_rate": 6.991658121553086e-08, "loss": 0.7347, "step": 354760 }, { "epoch": 29.49, "learning_rate": 6.980572568799712e-08, "loss": 0.7096, "step": 354770 }, { "epoch": 29.49, "learning_rate": 6.969487016046337e-08, "loss": 0.7381, "step": 354780 }, { "epoch": 29.49, "learning_rate": 6.958401463292964e-08, "loss": 0.7376, "step": 354790 }, { "epoch": 29.49, "learning_rate": 6.947315910539588e-08, "loss": 0.7195, "step": 354800 }, { "epoch": 29.49, "learning_rate": 6.936230357786214e-08, "loss": 0.7486, "step": 354810 }, { "epoch": 29.49, "learning_rate": 6.925144805032841e-08, "loss": 0.7287, "step": 354820 }, { "epoch": 29.49, "learning_rate": 6.914059252279466e-08, "loss": 0.7463, "step": 354830 }, { "epoch": 29.49, "learning_rate": 6.902973699526092e-08, "loss": 0.723, "step": 354840 }, { "epoch": 29.49, "learning_rate": 6.891888146772717e-08, "loss": 0.7457, "step": 354850 }, { "epoch": 29.5, "learning_rate": 6.880802594019344e-08, "loss": 0.689, "step": 354860 }, { "epoch": 29.5, "learning_rate": 6.86971704126597e-08, "loss": 0.6949, "step": 354870 }, { "epoch": 29.5, "learning_rate": 6.858631488512595e-08, "loss": 0.7248, "step": 354880 }, { "epoch": 29.5, "learning_rate": 6.847545935759222e-08, "loss": 0.6302, "step": 354890 }, { "epoch": 29.5, "learning_rate": 6.836460383005848e-08, "loss": 0.8047, "step": 354900 }, { "epoch": 29.5, "learning_rate": 6.825374830252472e-08, "loss": 0.7396, "step": 354910 }, { "epoch": 29.5, "learning_rate": 6.814289277499099e-08, "loss": 0.688, "step": 354920 }, { "epoch": 29.5, "learning_rate": 6.803203724745725e-08, "loss": 0.7645, "step": 354930 }, { "epoch": 29.5, "learning_rate": 6.79211817199235e-08, "loss": 0.7238, "step": 354940 }, { "epoch": 29.5, "learning_rate": 6.781032619238977e-08, "loss": 0.7247, "step": 354950 }, { "epoch": 29.5, "learning_rate": 6.769947066485603e-08, "loss": 0.7679, "step": 354960 }, { "epoch": 29.5, "learning_rate": 6.758861513732228e-08, "loss": 0.7235, "step": 354970 }, { "epoch": 29.51, "learning_rate": 6.747775960978854e-08, "loss": 0.691, "step": 354980 }, { "epoch": 29.51, "learning_rate": 6.73669040822548e-08, "loss": 0.7, "step": 354990 }, { "epoch": 29.51, "learning_rate": 6.725604855472106e-08, "loss": 0.7284, "step": 355000 }, { "epoch": 29.51, "learning_rate": 6.71451930271873e-08, "loss": 0.753, "step": 355010 }, { "epoch": 29.51, "learning_rate": 6.703433749965357e-08, "loss": 0.7448, "step": 355020 }, { "epoch": 29.51, "learning_rate": 6.692348197211983e-08, "loss": 0.7189, "step": 355030 }, { "epoch": 29.51, "learning_rate": 6.681262644458608e-08, "loss": 0.7012, "step": 355040 }, { "epoch": 29.51, "learning_rate": 6.670177091705235e-08, "loss": 0.7999, "step": 355050 }, { "epoch": 29.51, "learning_rate": 6.659091538951861e-08, "loss": 0.7105, "step": 355060 }, { "epoch": 29.51, "learning_rate": 6.648005986198486e-08, "loss": 0.7296, "step": 355070 }, { "epoch": 29.51, "learning_rate": 6.636920433445112e-08, "loss": 0.7677, "step": 355080 }, { "epoch": 29.51, "learning_rate": 6.625834880691739e-08, "loss": 0.7183, "step": 355090 }, { "epoch": 29.52, "learning_rate": 6.614749327938364e-08, "loss": 0.6879, "step": 355100 }, { "epoch": 29.52, "learning_rate": 6.60366377518499e-08, "loss": 0.722, "step": 355110 }, { "epoch": 29.52, "learning_rate": 6.592578222431616e-08, "loss": 0.7464, "step": 355120 }, { "epoch": 29.52, "learning_rate": 6.581492669678241e-08, "loss": 0.74, "step": 355130 }, { "epoch": 29.52, "learning_rate": 6.570407116924867e-08, "loss": 0.7636, "step": 355140 }, { "epoch": 29.52, "learning_rate": 6.559321564171494e-08, "loss": 0.7595, "step": 355150 }, { "epoch": 29.52, "learning_rate": 6.548236011418119e-08, "loss": 0.7978, "step": 355160 }, { "epoch": 29.52, "learning_rate": 6.537150458664745e-08, "loss": 0.7191, "step": 355170 }, { "epoch": 29.52, "learning_rate": 6.52606490591137e-08, "loss": 0.729, "step": 355180 }, { "epoch": 29.52, "learning_rate": 6.514979353157997e-08, "loss": 0.7534, "step": 355190 }, { "epoch": 29.52, "learning_rate": 6.503893800404623e-08, "loss": 0.7454, "step": 355200 }, { "epoch": 29.52, "learning_rate": 6.492808247651248e-08, "loss": 0.7863, "step": 355210 }, { "epoch": 29.53, "learning_rate": 6.481722694897874e-08, "loss": 0.7491, "step": 355220 }, { "epoch": 29.53, "learning_rate": 6.4706371421445e-08, "loss": 0.7031, "step": 355230 }, { "epoch": 29.53, "learning_rate": 6.459551589391125e-08, "loss": 0.7168, "step": 355240 }, { "epoch": 29.53, "learning_rate": 6.448466036637752e-08, "loss": 0.7217, "step": 355250 }, { "epoch": 29.53, "learning_rate": 6.437380483884377e-08, "loss": 0.7336, "step": 355260 }, { "epoch": 29.53, "learning_rate": 6.426294931131003e-08, "loss": 0.7122, "step": 355270 }, { "epoch": 29.53, "learning_rate": 6.415209378377629e-08, "loss": 0.732, "step": 355280 }, { "epoch": 29.53, "learning_rate": 6.404123825624255e-08, "loss": 0.716, "step": 355290 }, { "epoch": 29.53, "learning_rate": 6.393038272870881e-08, "loss": 0.6997, "step": 355300 }, { "epoch": 29.53, "learning_rate": 6.381952720117507e-08, "loss": 0.8029, "step": 355310 }, { "epoch": 29.53, "learning_rate": 6.370867167364134e-08, "loss": 0.7184, "step": 355320 }, { "epoch": 29.53, "learning_rate": 6.359781614610758e-08, "loss": 0.7086, "step": 355330 }, { "epoch": 29.54, "learning_rate": 6.348696061857383e-08, "loss": 0.7431, "step": 355340 }, { "epoch": 29.54, "learning_rate": 6.33761050910401e-08, "loss": 0.7604, "step": 355350 }, { "epoch": 29.54, "learning_rate": 6.326524956350636e-08, "loss": 0.775, "step": 355360 }, { "epoch": 29.54, "learning_rate": 6.315439403597261e-08, "loss": 0.7103, "step": 355370 }, { "epoch": 29.54, "learning_rate": 6.304353850843887e-08, "loss": 0.713, "step": 355380 }, { "epoch": 29.54, "learning_rate": 6.293268298090514e-08, "loss": 0.7041, "step": 355390 }, { "epoch": 29.54, "learning_rate": 6.282182745337139e-08, "loss": 0.7113, "step": 355400 }, { "epoch": 29.54, "learning_rate": 6.271097192583765e-08, "loss": 0.7302, "step": 355410 }, { "epoch": 29.54, "learning_rate": 6.260011639830392e-08, "loss": 0.7147, "step": 355420 }, { "epoch": 29.54, "learning_rate": 6.248926087077016e-08, "loss": 0.7168, "step": 355430 }, { "epoch": 29.54, "learning_rate": 6.237840534323643e-08, "loss": 0.8033, "step": 355440 }, { "epoch": 29.54, "learning_rate": 6.226754981570268e-08, "loss": 0.7341, "step": 355450 }, { "epoch": 29.55, "learning_rate": 6.215669428816894e-08, "loss": 0.7402, "step": 355460 }, { "epoch": 29.55, "learning_rate": 6.20458387606352e-08, "loss": 0.7166, "step": 355470 }, { "epoch": 29.55, "learning_rate": 6.193498323310145e-08, "loss": 0.756, "step": 355480 }, { "epoch": 29.55, "learning_rate": 6.182412770556772e-08, "loss": 0.7674, "step": 355490 }, { "epoch": 29.55, "learning_rate": 6.171327217803398e-08, "loss": 0.7146, "step": 355500 }, { "epoch": 29.55, "learning_rate": 6.160241665050023e-08, "loss": 0.7675, "step": 355510 }, { "epoch": 29.55, "learning_rate": 6.149156112296649e-08, "loss": 0.7552, "step": 355520 }, { "epoch": 29.55, "learning_rate": 6.138070559543274e-08, "loss": 0.7864, "step": 355530 }, { "epoch": 29.55, "learning_rate": 6.126985006789901e-08, "loss": 0.7128, "step": 355540 }, { "epoch": 29.55, "learning_rate": 6.115899454036527e-08, "loss": 0.7555, "step": 355550 }, { "epoch": 29.55, "learning_rate": 6.104813901283152e-08, "loss": 0.8213, "step": 355560 }, { "epoch": 29.55, "learning_rate": 6.093728348529778e-08, "loss": 0.7539, "step": 355570 }, { "epoch": 29.56, "learning_rate": 6.082642795776405e-08, "loss": 0.6864, "step": 355580 }, { "epoch": 29.56, "learning_rate": 6.07155724302303e-08, "loss": 0.7122, "step": 355590 }, { "epoch": 29.56, "learning_rate": 6.060471690269656e-08, "loss": 0.75, "step": 355600 }, { "epoch": 29.56, "learning_rate": 6.049386137516281e-08, "loss": 0.7639, "step": 355610 }, { "epoch": 29.56, "learning_rate": 6.038300584762907e-08, "loss": 0.656, "step": 355620 }, { "epoch": 29.56, "learning_rate": 6.027215032009534e-08, "loss": 0.7541, "step": 355630 }, { "epoch": 29.56, "learning_rate": 6.01612947925616e-08, "loss": 0.7783, "step": 355640 }, { "epoch": 29.56, "learning_rate": 6.005043926502785e-08, "loss": 0.7685, "step": 355650 }, { "epoch": 29.56, "learning_rate": 5.99395837374941e-08, "loss": 0.7951, "step": 355660 }, { "epoch": 29.56, "learning_rate": 5.982872820996036e-08, "loss": 0.7186, "step": 355670 }, { "epoch": 29.56, "learning_rate": 5.971787268242663e-08, "loss": 0.7194, "step": 355680 }, { "epoch": 29.56, "learning_rate": 5.960701715489289e-08, "loss": 0.7723, "step": 355690 }, { "epoch": 29.57, "learning_rate": 5.949616162735914e-08, "loss": 0.7397, "step": 355700 }, { "epoch": 29.57, "learning_rate": 5.939639165257877e-08, "loss": 0.7461, "step": 355710 }, { "epoch": 29.57, "learning_rate": 5.9285536125045035e-08, "loss": 0.7638, "step": 355720 }, { "epoch": 29.57, "learning_rate": 5.917468059751129e-08, "loss": 0.7056, "step": 355730 }, { "epoch": 29.57, "learning_rate": 5.907491062273092e-08, "loss": 0.7088, "step": 355740 }, { "epoch": 29.57, "learning_rate": 5.8964055095197185e-08, "loss": 0.7469, "step": 355750 }, { "epoch": 29.57, "learning_rate": 5.885319956766344e-08, "loss": 0.8161, "step": 355760 }, { "epoch": 29.57, "learning_rate": 5.8742344040129696e-08, "loss": 0.6993, "step": 355770 }, { "epoch": 29.57, "learning_rate": 5.863148851259596e-08, "loss": 0.6651, "step": 355780 }, { "epoch": 29.57, "learning_rate": 5.8520632985062214e-08, "loss": 0.7056, "step": 355790 }, { "epoch": 29.57, "learning_rate": 5.8409777457528476e-08, "loss": 0.7125, "step": 355800 }, { "epoch": 29.57, "learning_rate": 5.829892192999473e-08, "loss": 0.7805, "step": 355810 }, { "epoch": 29.58, "learning_rate": 5.818806640246099e-08, "loss": 0.708, "step": 355820 }, { "epoch": 29.58, "learning_rate": 5.807721087492725e-08, "loss": 0.7334, "step": 355830 }, { "epoch": 29.58, "learning_rate": 5.7966355347393505e-08, "loss": 0.6927, "step": 355840 }, { "epoch": 29.58, "learning_rate": 5.785549981985977e-08, "loss": 0.6707, "step": 355850 }, { "epoch": 29.58, "learning_rate": 5.774464429232603e-08, "loss": 0.7357, "step": 355860 }, { "epoch": 29.58, "learning_rate": 5.763378876479228e-08, "loss": 0.7392, "step": 355870 }, { "epoch": 29.58, "learning_rate": 5.752293323725854e-08, "loss": 0.7149, "step": 355880 }, { "epoch": 29.58, "learning_rate": 5.7412077709724797e-08, "loss": 0.7814, "step": 355890 }, { "epoch": 29.58, "learning_rate": 5.730122218219106e-08, "loss": 0.7714, "step": 355900 }, { "epoch": 29.58, "learning_rate": 5.719036665465732e-08, "loss": 0.6881, "step": 355910 }, { "epoch": 29.58, "learning_rate": 5.707951112712357e-08, "loss": 0.7443, "step": 355920 }, { "epoch": 29.58, "learning_rate": 5.696865559958983e-08, "loss": 0.6933, "step": 355930 }, { "epoch": 29.59, "learning_rate": 5.685780007205609e-08, "loss": 0.6404, "step": 355940 }, { "epoch": 29.59, "learning_rate": 5.674694454452235e-08, "loss": 0.7399, "step": 355950 }, { "epoch": 29.59, "learning_rate": 5.663608901698861e-08, "loss": 0.6936, "step": 355960 }, { "epoch": 29.59, "learning_rate": 5.652523348945486e-08, "loss": 0.7515, "step": 355970 }, { "epoch": 29.59, "learning_rate": 5.6414377961921124e-08, "loss": 0.764, "step": 355980 }, { "epoch": 29.59, "learning_rate": 5.630352243438738e-08, "loss": 0.7345, "step": 355990 }, { "epoch": 29.59, "learning_rate": 5.619266690685364e-08, "loss": 0.7389, "step": 356000 }, { "epoch": 29.59, "learning_rate": 5.6081811379319904e-08, "loss": 0.7388, "step": 356010 }, { "epoch": 29.59, "learning_rate": 5.597095585178615e-08, "loss": 0.7678, "step": 356020 }, { "epoch": 29.59, "learning_rate": 5.5860100324252415e-08, "loss": 0.7397, "step": 356030 }, { "epoch": 29.59, "learning_rate": 5.574924479671867e-08, "loss": 0.7248, "step": 356040 }, { "epoch": 29.59, "learning_rate": 5.563838926918493e-08, "loss": 0.719, "step": 356050 }, { "epoch": 29.6, "learning_rate": 5.5527533741651195e-08, "loss": 0.7489, "step": 356060 }, { "epoch": 29.6, "learning_rate": 5.5416678214117444e-08, "loss": 0.6851, "step": 356070 }, { "epoch": 29.6, "learning_rate": 5.5305822686583707e-08, "loss": 0.6836, "step": 356080 }, { "epoch": 29.6, "learning_rate": 5.519496715904996e-08, "loss": 0.7063, "step": 356090 }, { "epoch": 29.6, "learning_rate": 5.5084111631516225e-08, "loss": 0.7476, "step": 356100 }, { "epoch": 29.6, "learning_rate": 5.497325610398249e-08, "loss": 0.7547, "step": 356110 }, { "epoch": 29.6, "learning_rate": 5.486240057644874e-08, "loss": 0.728, "step": 356120 }, { "epoch": 29.6, "learning_rate": 5.4751545048915e-08, "loss": 0.7774, "step": 356130 }, { "epoch": 29.6, "learning_rate": 5.4640689521381254e-08, "loss": 0.6937, "step": 356140 }, { "epoch": 29.6, "learning_rate": 5.4529833993847516e-08, "loss": 0.7048, "step": 356150 }, { "epoch": 29.6, "learning_rate": 5.441897846631378e-08, "loss": 0.6827, "step": 356160 }, { "epoch": 29.6, "learning_rate": 5.4308122938780034e-08, "loss": 0.6735, "step": 356170 }, { "epoch": 29.61, "learning_rate": 5.419726741124629e-08, "loss": 0.7075, "step": 356180 }, { "epoch": 29.61, "learning_rate": 5.4086411883712545e-08, "loss": 0.6984, "step": 356190 }, { "epoch": 29.61, "learning_rate": 5.397555635617881e-08, "loss": 0.6915, "step": 356200 }, { "epoch": 29.61, "learning_rate": 5.386470082864507e-08, "loss": 0.7355, "step": 356210 }, { "epoch": 29.61, "learning_rate": 5.3753845301111325e-08, "loss": 0.7927, "step": 356220 }, { "epoch": 29.61, "learning_rate": 5.364298977357758e-08, "loss": 0.6992, "step": 356230 }, { "epoch": 29.61, "learning_rate": 5.3532134246043836e-08, "loss": 0.6437, "step": 356240 }, { "epoch": 29.61, "learning_rate": 5.34212787185101e-08, "loss": 0.6657, "step": 356250 }, { "epoch": 29.61, "learning_rate": 5.331042319097636e-08, "loss": 0.7951, "step": 356260 }, { "epoch": 29.61, "learning_rate": 5.3199567663442617e-08, "loss": 0.7103, "step": 356270 }, { "epoch": 29.61, "learning_rate": 5.308871213590887e-08, "loss": 0.7017, "step": 356280 }, { "epoch": 29.61, "learning_rate": 5.297785660837513e-08, "loss": 0.6791, "step": 356290 }, { "epoch": 29.62, "learning_rate": 5.286700108084139e-08, "loss": 0.7017, "step": 356300 }, { "epoch": 29.62, "learning_rate": 5.275614555330765e-08, "loss": 0.6931, "step": 356310 }, { "epoch": 29.62, "learning_rate": 5.264529002577391e-08, "loss": 0.7582, "step": 356320 }, { "epoch": 29.62, "learning_rate": 5.2534434498240164e-08, "loss": 0.7532, "step": 356330 }, { "epoch": 29.62, "learning_rate": 5.242357897070642e-08, "loss": 0.7032, "step": 356340 }, { "epoch": 29.62, "learning_rate": 5.231272344317268e-08, "loss": 0.7352, "step": 356350 }, { "epoch": 29.62, "learning_rate": 5.2201867915638944e-08, "loss": 0.7177, "step": 356360 }, { "epoch": 29.62, "learning_rate": 5.20910123881052e-08, "loss": 0.733, "step": 356370 }, { "epoch": 29.62, "learning_rate": 5.198015686057146e-08, "loss": 0.7427, "step": 356380 }, { "epoch": 29.62, "learning_rate": 5.186930133303772e-08, "loss": 0.7358, "step": 356390 }, { "epoch": 29.62, "learning_rate": 5.175844580550397e-08, "loss": 0.7211, "step": 356400 }, { "epoch": 29.62, "learning_rate": 5.1647590277970235e-08, "loss": 0.8134, "step": 356410 }, { "epoch": 29.63, "learning_rate": 5.153673475043649e-08, "loss": 0.6813, "step": 356420 }, { "epoch": 29.63, "learning_rate": 5.142587922290275e-08, "loss": 0.7274, "step": 356430 }, { "epoch": 29.63, "learning_rate": 5.131502369536901e-08, "loss": 0.7505, "step": 356440 }, { "epoch": 29.63, "learning_rate": 5.1204168167835264e-08, "loss": 0.7437, "step": 356450 }, { "epoch": 29.63, "learning_rate": 5.1093312640301527e-08, "loss": 0.7792, "step": 356460 }, { "epoch": 29.63, "learning_rate": 5.098245711276778e-08, "loss": 0.7417, "step": 356470 }, { "epoch": 29.63, "learning_rate": 5.0871601585234044e-08, "loss": 0.7193, "step": 356480 }, { "epoch": 29.63, "learning_rate": 5.07607460577003e-08, "loss": 0.7467, "step": 356490 }, { "epoch": 29.63, "learning_rate": 5.0649890530166556e-08, "loss": 0.7201, "step": 356500 }, { "epoch": 29.63, "learning_rate": 5.053903500263282e-08, "loss": 0.7219, "step": 356510 }, { "epoch": 29.63, "learning_rate": 5.0428179475099074e-08, "loss": 0.8069, "step": 356520 }, { "epoch": 29.63, "learning_rate": 5.0317323947565336e-08, "loss": 0.7025, "step": 356530 }, { "epoch": 29.64, "learning_rate": 5.020646842003159e-08, "loss": 0.7055, "step": 356540 }, { "epoch": 29.64, "learning_rate": 5.009561289249785e-08, "loss": 0.7502, "step": 356550 }, { "epoch": 29.64, "learning_rate": 4.998475736496411e-08, "loss": 0.7318, "step": 356560 }, { "epoch": 29.64, "learning_rate": 4.9873901837430365e-08, "loss": 0.6866, "step": 356570 }, { "epoch": 29.64, "learning_rate": 4.976304630989663e-08, "loss": 0.666, "step": 356580 }, { "epoch": 29.64, "learning_rate": 4.965219078236289e-08, "loss": 0.7203, "step": 356590 }, { "epoch": 29.64, "learning_rate": 4.954133525482914e-08, "loss": 0.7209, "step": 356600 }, { "epoch": 29.64, "learning_rate": 4.94304797272954e-08, "loss": 0.7177, "step": 356610 }, { "epoch": 29.64, "learning_rate": 4.9319624199761656e-08, "loss": 0.7526, "step": 356620 }, { "epoch": 29.64, "learning_rate": 4.920876867222792e-08, "loss": 0.6913, "step": 356630 }, { "epoch": 29.64, "learning_rate": 4.909791314469418e-08, "loss": 0.683, "step": 356640 }, { "epoch": 29.64, "learning_rate": 4.898705761716043e-08, "loss": 0.6692, "step": 356650 }, { "epoch": 29.65, "learning_rate": 4.887620208962669e-08, "loss": 0.7665, "step": 356660 }, { "epoch": 29.65, "learning_rate": 4.876534656209295e-08, "loss": 0.7752, "step": 356670 }, { "epoch": 29.65, "learning_rate": 4.865449103455921e-08, "loss": 0.764, "step": 356680 }, { "epoch": 29.65, "learning_rate": 4.854363550702547e-08, "loss": 0.7503, "step": 356690 }, { "epoch": 29.65, "learning_rate": 4.843277997949172e-08, "loss": 0.7251, "step": 356700 }, { "epoch": 29.65, "learning_rate": 4.8321924451957984e-08, "loss": 0.7632, "step": 356710 }, { "epoch": 29.65, "learning_rate": 4.821106892442424e-08, "loss": 0.7243, "step": 356720 }, { "epoch": 29.65, "learning_rate": 4.81002133968905e-08, "loss": 0.7125, "step": 356730 }, { "epoch": 29.65, "learning_rate": 4.7989357869356764e-08, "loss": 0.7182, "step": 356740 }, { "epoch": 29.65, "learning_rate": 4.787850234182301e-08, "loss": 0.7152, "step": 356750 }, { "epoch": 29.65, "learning_rate": 4.7767646814289275e-08, "loss": 0.7436, "step": 356760 }, { "epoch": 29.65, "learning_rate": 4.765679128675553e-08, "loss": 0.7327, "step": 356770 }, { "epoch": 29.66, "learning_rate": 4.754593575922179e-08, "loss": 0.6894, "step": 356780 }, { "epoch": 29.66, "learning_rate": 4.7435080231688055e-08, "loss": 0.7804, "step": 356790 }, { "epoch": 29.66, "learning_rate": 4.7324224704154304e-08, "loss": 0.7093, "step": 356800 }, { "epoch": 29.66, "learning_rate": 4.7213369176620566e-08, "loss": 0.747, "step": 356810 }, { "epoch": 29.66, "learning_rate": 4.710251364908682e-08, "loss": 0.7198, "step": 356820 }, { "epoch": 29.66, "learning_rate": 4.6991658121553084e-08, "loss": 0.6744, "step": 356830 }, { "epoch": 29.66, "learning_rate": 4.6880802594019347e-08, "loss": 0.7048, "step": 356840 }, { "epoch": 29.66, "learning_rate": 4.67699470664856e-08, "loss": 0.7474, "step": 356850 }, { "epoch": 29.66, "learning_rate": 4.665909153895186e-08, "loss": 0.7742, "step": 356860 }, { "epoch": 29.66, "learning_rate": 4.6548236011418113e-08, "loss": 0.6769, "step": 356870 }, { "epoch": 29.66, "learning_rate": 4.6437380483884376e-08, "loss": 0.7201, "step": 356880 }, { "epoch": 29.66, "learning_rate": 4.632652495635064e-08, "loss": 0.7119, "step": 356890 }, { "epoch": 29.67, "learning_rate": 4.6215669428816894e-08, "loss": 0.6916, "step": 356900 }, { "epoch": 29.67, "learning_rate": 4.610481390128315e-08, "loss": 0.8584, "step": 356910 }, { "epoch": 29.67, "learning_rate": 4.5993958373749405e-08, "loss": 0.7315, "step": 356920 }, { "epoch": 29.67, "learning_rate": 4.588310284621567e-08, "loss": 0.6605, "step": 356930 }, { "epoch": 29.67, "learning_rate": 4.577224731868193e-08, "loss": 0.7374, "step": 356940 }, { "epoch": 29.67, "learning_rate": 4.5661391791148185e-08, "loss": 0.7554, "step": 356950 }, { "epoch": 29.67, "learning_rate": 4.555053626361444e-08, "loss": 0.7846, "step": 356960 }, { "epoch": 29.67, "learning_rate": 4.5439680736080696e-08, "loss": 0.7486, "step": 356970 }, { "epoch": 29.67, "learning_rate": 4.532882520854696e-08, "loss": 0.6724, "step": 356980 }, { "epoch": 29.67, "learning_rate": 4.521796968101322e-08, "loss": 0.7083, "step": 356990 }, { "epoch": 29.67, "learning_rate": 4.5107114153479476e-08, "loss": 0.7237, "step": 357000 }, { "epoch": 29.67, "learning_rate": 4.499625862594573e-08, "loss": 0.8004, "step": 357010 }, { "epoch": 29.68, "learning_rate": 4.488540309841199e-08, "loss": 0.7591, "step": 357020 }, { "epoch": 29.68, "learning_rate": 4.477454757087825e-08, "loss": 0.7156, "step": 357030 }, { "epoch": 29.68, "learning_rate": 4.466369204334451e-08, "loss": 0.7102, "step": 357040 }, { "epoch": 29.68, "learning_rate": 4.455283651581077e-08, "loss": 0.7046, "step": 357050 }, { "epoch": 29.68, "learning_rate": 4.4441980988277023e-08, "loss": 0.7356, "step": 357060 }, { "epoch": 29.68, "learning_rate": 4.4331125460743286e-08, "loss": 0.7533, "step": 357070 }, { "epoch": 29.68, "learning_rate": 4.422026993320954e-08, "loss": 0.6578, "step": 357080 }, { "epoch": 29.68, "learning_rate": 4.4109414405675804e-08, "loss": 0.7657, "step": 357090 }, { "epoch": 29.68, "learning_rate": 4.399855887814206e-08, "loss": 0.6919, "step": 357100 }, { "epoch": 29.68, "learning_rate": 4.388770335060832e-08, "loss": 0.7599, "step": 357110 }, { "epoch": 29.68, "learning_rate": 4.377684782307458e-08, "loss": 0.7357, "step": 357120 }, { "epoch": 29.68, "learning_rate": 4.366599229554083e-08, "loss": 0.7452, "step": 357130 }, { "epoch": 29.68, "learning_rate": 4.3555136768007095e-08, "loss": 0.7711, "step": 357140 }, { "epoch": 29.69, "learning_rate": 4.344428124047335e-08, "loss": 0.7574, "step": 357150 }, { "epoch": 29.69, "learning_rate": 4.333342571293961e-08, "loss": 0.7388, "step": 357160 }, { "epoch": 29.69, "learning_rate": 4.322257018540587e-08, "loss": 0.6665, "step": 357170 }, { "epoch": 29.69, "learning_rate": 4.3111714657872124e-08, "loss": 0.7242, "step": 357180 }, { "epoch": 29.69, "learning_rate": 4.3000859130338386e-08, "loss": 0.6984, "step": 357190 }, { "epoch": 29.69, "learning_rate": 4.289000360280464e-08, "loss": 0.6954, "step": 357200 }, { "epoch": 29.69, "learning_rate": 4.2779148075270904e-08, "loss": 0.7823, "step": 357210 }, { "epoch": 29.69, "learning_rate": 4.266829254773716e-08, "loss": 0.7361, "step": 357220 }, { "epoch": 29.69, "learning_rate": 4.2557437020203415e-08, "loss": 0.7534, "step": 357230 }, { "epoch": 29.69, "learning_rate": 4.244658149266968e-08, "loss": 0.7023, "step": 357240 }, { "epoch": 29.69, "learning_rate": 4.2335725965135933e-08, "loss": 0.742, "step": 357250 }, { "epoch": 29.69, "learning_rate": 4.2224870437602196e-08, "loss": 0.7437, "step": 357260 }, { "epoch": 29.7, "learning_rate": 4.211401491006845e-08, "loss": 0.6719, "step": 357270 }, { "epoch": 29.7, "learning_rate": 4.200315938253471e-08, "loss": 0.766, "step": 357280 }, { "epoch": 29.7, "learning_rate": 4.189230385500097e-08, "loss": 0.7215, "step": 357290 }, { "epoch": 29.7, "learning_rate": 4.1781448327467225e-08, "loss": 0.7246, "step": 357300 }, { "epoch": 29.7, "learning_rate": 4.167059279993349e-08, "loss": 0.6963, "step": 357310 }, { "epoch": 29.7, "learning_rate": 4.155973727239975e-08, "loss": 0.7551, "step": 357320 }, { "epoch": 29.7, "learning_rate": 4.1448881744866e-08, "loss": 0.7561, "step": 357330 }, { "epoch": 29.7, "learning_rate": 4.133802621733226e-08, "loss": 0.6741, "step": 357340 }, { "epoch": 29.7, "learning_rate": 4.1227170689798516e-08, "loss": 0.7269, "step": 357350 }, { "epoch": 29.7, "learning_rate": 4.111631516226478e-08, "loss": 0.8132, "step": 357360 }, { "epoch": 29.7, "learning_rate": 4.100545963473104e-08, "loss": 0.7262, "step": 357370 }, { "epoch": 29.7, "learning_rate": 4.089460410719729e-08, "loss": 0.6708, "step": 357380 }, { "epoch": 29.71, "learning_rate": 4.078374857966355e-08, "loss": 0.74, "step": 357390 }, { "epoch": 29.71, "learning_rate": 4.067289305212981e-08, "loss": 0.7613, "step": 357400 }, { "epoch": 29.71, "learning_rate": 4.056203752459607e-08, "loss": 0.7969, "step": 357410 }, { "epoch": 29.71, "learning_rate": 4.045118199706233e-08, "loss": 0.7016, "step": 357420 }, { "epoch": 29.71, "learning_rate": 4.034032646952858e-08, "loss": 0.6932, "step": 357430 }, { "epoch": 29.71, "learning_rate": 4.0229470941994843e-08, "loss": 0.7309, "step": 357440 }, { "epoch": 29.71, "learning_rate": 4.01186154144611e-08, "loss": 0.7255, "step": 357450 }, { "epoch": 29.71, "learning_rate": 4.000775988692736e-08, "loss": 0.8047, "step": 357460 }, { "epoch": 29.71, "learning_rate": 3.9896904359393623e-08, "loss": 0.7166, "step": 357470 }, { "epoch": 29.71, "learning_rate": 3.978604883185987e-08, "loss": 0.7264, "step": 357480 }, { "epoch": 29.71, "learning_rate": 3.9675193304326135e-08, "loss": 0.7414, "step": 357490 }, { "epoch": 29.71, "learning_rate": 3.956433777679239e-08, "loss": 0.7557, "step": 357500 }, { "epoch": 29.72, "learning_rate": 3.945348224925865e-08, "loss": 0.6979, "step": 357510 }, { "epoch": 29.72, "learning_rate": 3.9342626721724915e-08, "loss": 0.6802, "step": 357520 }, { "epoch": 29.72, "learning_rate": 3.9231771194191164e-08, "loss": 0.7503, "step": 357530 }, { "epoch": 29.72, "learning_rate": 3.9120915666657426e-08, "loss": 0.7173, "step": 357540 }, { "epoch": 29.72, "learning_rate": 3.901006013912368e-08, "loss": 0.726, "step": 357550 }, { "epoch": 29.72, "learning_rate": 3.8899204611589944e-08, "loss": 0.7384, "step": 357560 }, { "epoch": 29.72, "learning_rate": 3.8788349084056206e-08, "loss": 0.7358, "step": 357570 }, { "epoch": 29.72, "learning_rate": 3.8677493556522455e-08, "loss": 0.7546, "step": 357580 }, { "epoch": 29.72, "learning_rate": 3.856663802898872e-08, "loss": 0.7937, "step": 357590 }, { "epoch": 29.72, "learning_rate": 3.845578250145497e-08, "loss": 0.6776, "step": 357600 }, { "epoch": 29.72, "learning_rate": 3.8344926973921235e-08, "loss": 0.7455, "step": 357610 }, { "epoch": 29.72, "learning_rate": 3.82340714463875e-08, "loss": 0.7429, "step": 357620 }, { "epoch": 29.73, "learning_rate": 3.8123215918853753e-08, "loss": 0.7889, "step": 357630 }, { "epoch": 29.73, "learning_rate": 3.801236039132001e-08, "loss": 0.6902, "step": 357640 }, { "epoch": 29.73, "learning_rate": 3.7901504863786265e-08, "loss": 0.7132, "step": 357650 }, { "epoch": 29.73, "learning_rate": 3.779064933625253e-08, "loss": 0.7518, "step": 357660 }, { "epoch": 29.73, "learning_rate": 3.767979380871879e-08, "loss": 0.6825, "step": 357670 }, { "epoch": 29.73, "learning_rate": 3.7568938281185045e-08, "loss": 0.7699, "step": 357680 }, { "epoch": 29.73, "learning_rate": 3.74580827536513e-08, "loss": 0.7144, "step": 357690 }, { "epoch": 29.73, "learning_rate": 3.7347227226117556e-08, "loss": 0.7487, "step": 357700 }, { "epoch": 29.73, "learning_rate": 3.723637169858382e-08, "loss": 0.8108, "step": 357710 }, { "epoch": 29.73, "learning_rate": 3.712551617105008e-08, "loss": 0.7865, "step": 357720 }, { "epoch": 29.73, "learning_rate": 3.7014660643516336e-08, "loss": 0.6832, "step": 357730 }, { "epoch": 29.73, "learning_rate": 3.690380511598259e-08, "loss": 0.7556, "step": 357740 }, { "epoch": 29.74, "learning_rate": 3.6792949588448854e-08, "loss": 0.7555, "step": 357750 }, { "epoch": 29.74, "learning_rate": 3.668209406091511e-08, "loss": 0.7752, "step": 357760 }, { "epoch": 29.74, "learning_rate": 3.657123853338137e-08, "loss": 0.7607, "step": 357770 }, { "epoch": 29.74, "learning_rate": 3.646038300584763e-08, "loss": 0.7638, "step": 357780 }, { "epoch": 29.74, "learning_rate": 3.634952747831388e-08, "loss": 0.7577, "step": 357790 }, { "epoch": 29.74, "learning_rate": 3.6238671950780145e-08, "loss": 0.7047, "step": 357800 }, { "epoch": 29.74, "learning_rate": 3.61278164232464e-08, "loss": 0.7331, "step": 357810 }, { "epoch": 29.74, "learning_rate": 3.601696089571266e-08, "loss": 0.673, "step": 357820 }, { "epoch": 29.74, "learning_rate": 3.590610536817892e-08, "loss": 0.6681, "step": 357830 }, { "epoch": 29.74, "learning_rate": 3.579524984064518e-08, "loss": 0.7263, "step": 357840 }, { "epoch": 29.74, "learning_rate": 3.568439431311144e-08, "loss": 0.6842, "step": 357850 }, { "epoch": 29.74, "learning_rate": 3.557353878557769e-08, "loss": 0.7718, "step": 357860 }, { "epoch": 29.75, "learning_rate": 3.5462683258043955e-08, "loss": 0.6828, "step": 357870 }, { "epoch": 29.75, "learning_rate": 3.535182773051021e-08, "loss": 0.7395, "step": 357880 }, { "epoch": 29.75, "learning_rate": 3.524097220297647e-08, "loss": 0.7009, "step": 357890 }, { "epoch": 29.75, "learning_rate": 3.513011667544273e-08, "loss": 0.6814, "step": 357900 }, { "epoch": 29.75, "learning_rate": 3.5019261147908984e-08, "loss": 0.7429, "step": 357910 }, { "epoch": 29.75, "learning_rate": 3.4908405620375246e-08, "loss": 0.7481, "step": 357920 }, { "epoch": 29.75, "learning_rate": 3.47975500928415e-08, "loss": 0.7171, "step": 357930 }, { "epoch": 29.75, "learning_rate": 3.4686694565307764e-08, "loss": 0.6447, "step": 357940 }, { "epoch": 29.75, "learning_rate": 3.457583903777402e-08, "loss": 0.7908, "step": 357950 }, { "epoch": 29.75, "learning_rate": 3.4464983510240275e-08, "loss": 0.7318, "step": 357960 }, { "epoch": 29.75, "learning_rate": 3.435412798270654e-08, "loss": 0.7276, "step": 357970 }, { "epoch": 29.75, "learning_rate": 3.424327245517279e-08, "loss": 0.7141, "step": 357980 }, { "epoch": 29.76, "learning_rate": 3.4132416927639055e-08, "loss": 0.766, "step": 357990 }, { "epoch": 29.76, "learning_rate": 3.402156140010531e-08, "loss": 0.6984, "step": 358000 }, { "epoch": 29.76, "learning_rate": 3.3910705872571567e-08, "loss": 0.7517, "step": 358010 }, { "epoch": 29.76, "learning_rate": 3.379985034503783e-08, "loss": 0.7395, "step": 358020 }, { "epoch": 29.76, "learning_rate": 3.3688994817504085e-08, "loss": 0.684, "step": 358030 }, { "epoch": 29.76, "learning_rate": 3.357813928997035e-08, "loss": 0.7137, "step": 358040 }, { "epoch": 29.76, "learning_rate": 3.346728376243661e-08, "loss": 0.6728, "step": 358050 }, { "epoch": 29.76, "learning_rate": 3.335642823490286e-08, "loss": 0.7378, "step": 358060 }, { "epoch": 29.76, "learning_rate": 3.324557270736912e-08, "loss": 0.7077, "step": 358070 }, { "epoch": 29.76, "learning_rate": 3.3134717179835376e-08, "loss": 0.7607, "step": 358080 }, { "epoch": 29.76, "learning_rate": 3.302386165230164e-08, "loss": 0.7114, "step": 358090 }, { "epoch": 29.76, "learning_rate": 3.29130061247679e-08, "loss": 0.747, "step": 358100 }, { "epoch": 29.77, "learning_rate": 3.280215059723415e-08, "loss": 0.7359, "step": 358110 }, { "epoch": 29.77, "learning_rate": 3.269129506970041e-08, "loss": 0.7165, "step": 358120 }, { "epoch": 29.77, "learning_rate": 3.258043954216667e-08, "loss": 0.7553, "step": 358130 }, { "epoch": 29.77, "learning_rate": 3.246958401463293e-08, "loss": 0.7739, "step": 358140 }, { "epoch": 29.77, "learning_rate": 3.235872848709919e-08, "loss": 0.7209, "step": 358150 }, { "epoch": 29.77, "learning_rate": 3.224787295956544e-08, "loss": 0.7677, "step": 358160 }, { "epoch": 29.77, "learning_rate": 3.21370174320317e-08, "loss": 0.7696, "step": 358170 }, { "epoch": 29.77, "learning_rate": 3.202616190449796e-08, "loss": 0.7579, "step": 358180 }, { "epoch": 29.77, "learning_rate": 3.191530637696422e-08, "loss": 0.7131, "step": 358190 }, { "epoch": 29.77, "learning_rate": 3.180445084943048e-08, "loss": 0.787, "step": 358200 }, { "epoch": 29.77, "learning_rate": 3.169359532189673e-08, "loss": 0.7787, "step": 358210 }, { "epoch": 29.77, "learning_rate": 3.1582739794362994e-08, "loss": 0.7704, "step": 358220 }, { "epoch": 29.78, "learning_rate": 3.147188426682925e-08, "loss": 0.6719, "step": 358230 }, { "epoch": 29.78, "learning_rate": 3.136102873929551e-08, "loss": 0.7503, "step": 358240 }, { "epoch": 29.78, "learning_rate": 3.1250173211761775e-08, "loss": 0.7893, "step": 358250 }, { "epoch": 29.78, "learning_rate": 3.1139317684228024e-08, "loss": 0.756, "step": 358260 }, { "epoch": 29.78, "learning_rate": 3.1028462156694286e-08, "loss": 0.7207, "step": 358270 }, { "epoch": 29.78, "learning_rate": 3.091760662916055e-08, "loss": 0.7292, "step": 358280 }, { "epoch": 29.78, "learning_rate": 3.0806751101626804e-08, "loss": 0.667, "step": 358290 }, { "epoch": 29.78, "learning_rate": 3.069589557409306e-08, "loss": 0.69, "step": 358300 }, { "epoch": 29.78, "learning_rate": 3.058504004655932e-08, "loss": 0.7736, "step": 358310 }, { "epoch": 29.78, "learning_rate": 3.047418451902558e-08, "loss": 0.6451, "step": 358320 }, { "epoch": 29.78, "learning_rate": 3.036332899149184e-08, "loss": 0.7425, "step": 358330 }, { "epoch": 29.78, "learning_rate": 3.0252473463958095e-08, "loss": 0.6662, "step": 358340 }, { "epoch": 29.79, "learning_rate": 3.014161793642435e-08, "loss": 0.7019, "step": 358350 }, { "epoch": 29.79, "learning_rate": 3.003076240889061e-08, "loss": 0.7587, "step": 358360 }, { "epoch": 29.79, "learning_rate": 2.991990688135687e-08, "loss": 0.7272, "step": 358370 }, { "epoch": 29.79, "learning_rate": 2.980905135382313e-08, "loss": 0.7603, "step": 358380 }, { "epoch": 29.79, "learning_rate": 2.9698195826289387e-08, "loss": 0.7596, "step": 358390 }, { "epoch": 29.79, "learning_rate": 2.9587340298755646e-08, "loss": 0.6968, "step": 358400 }, { "epoch": 29.79, "learning_rate": 2.9476484771221904e-08, "loss": 0.7723, "step": 358410 }, { "epoch": 29.79, "learning_rate": 2.9365629243688163e-08, "loss": 0.7561, "step": 358420 }, { "epoch": 29.79, "learning_rate": 2.925477371615442e-08, "loss": 0.7367, "step": 358430 }, { "epoch": 29.79, "learning_rate": 2.9143918188620678e-08, "loss": 0.7101, "step": 358440 }, { "epoch": 29.79, "learning_rate": 2.9033062661086937e-08, "loss": 0.7365, "step": 358450 }, { "epoch": 29.79, "learning_rate": 2.8922207133553196e-08, "loss": 0.7653, "step": 358460 }, { "epoch": 29.8, "learning_rate": 2.8811351606019455e-08, "loss": 0.6873, "step": 358470 }, { "epoch": 29.8, "learning_rate": 2.8700496078485714e-08, "loss": 0.7149, "step": 358480 }, { "epoch": 29.8, "learning_rate": 2.858964055095197e-08, "loss": 0.6893, "step": 358490 }, { "epoch": 29.8, "learning_rate": 2.8478785023418228e-08, "loss": 0.7112, "step": 358500 }, { "epoch": 29.8, "learning_rate": 2.8367929495884487e-08, "loss": 0.7635, "step": 358510 }, { "epoch": 29.8, "learning_rate": 2.8257073968350746e-08, "loss": 0.7662, "step": 358520 }, { "epoch": 29.8, "learning_rate": 2.8146218440817005e-08, "loss": 0.7364, "step": 358530 }, { "epoch": 29.8, "learning_rate": 2.803536291328326e-08, "loss": 0.7399, "step": 358540 }, { "epoch": 29.8, "learning_rate": 2.792450738574952e-08, "loss": 0.7046, "step": 358550 }, { "epoch": 29.8, "learning_rate": 2.781365185821578e-08, "loss": 0.7343, "step": 358560 }, { "epoch": 29.8, "learning_rate": 2.7702796330682038e-08, "loss": 0.7075, "step": 358570 }, { "epoch": 29.8, "learning_rate": 2.7591940803148297e-08, "loss": 0.7116, "step": 358580 }, { "epoch": 29.81, "learning_rate": 2.7481085275614552e-08, "loss": 0.7091, "step": 358590 }, { "epoch": 29.81, "learning_rate": 2.737022974808081e-08, "loss": 0.7716, "step": 358600 }, { "epoch": 29.81, "learning_rate": 2.7259374220547073e-08, "loss": 0.7585, "step": 358610 }, { "epoch": 29.81, "learning_rate": 2.714851869301333e-08, "loss": 0.6918, "step": 358620 }, { "epoch": 29.81, "learning_rate": 2.7037663165479588e-08, "loss": 0.7369, "step": 358630 }, { "epoch": 29.81, "learning_rate": 2.6926807637945844e-08, "loss": 0.737, "step": 358640 }, { "epoch": 29.81, "learning_rate": 2.6815952110412106e-08, "loss": 0.7709, "step": 358650 }, { "epoch": 29.81, "learning_rate": 2.6705096582878365e-08, "loss": 0.7278, "step": 358660 }, { "epoch": 29.81, "learning_rate": 2.659424105534462e-08, "loss": 0.6931, "step": 358670 }, { "epoch": 29.81, "learning_rate": 2.648338552781088e-08, "loss": 0.7417, "step": 358680 }, { "epoch": 29.81, "learning_rate": 2.6372530000277135e-08, "loss": 0.7411, "step": 358690 }, { "epoch": 29.81, "learning_rate": 2.6261674472743397e-08, "loss": 0.6815, "step": 358700 }, { "epoch": 29.82, "learning_rate": 2.6150818945209656e-08, "loss": 0.7083, "step": 358710 }, { "epoch": 29.82, "learning_rate": 2.6039963417675912e-08, "loss": 0.7688, "step": 358720 }, { "epoch": 29.82, "learning_rate": 2.592910789014217e-08, "loss": 0.7428, "step": 358730 }, { "epoch": 29.82, "learning_rate": 2.581825236260843e-08, "loss": 0.7037, "step": 358740 }, { "epoch": 29.82, "learning_rate": 2.570739683507469e-08, "loss": 0.8004, "step": 358750 }, { "epoch": 29.82, "learning_rate": 2.5596541307540948e-08, "loss": 0.7426, "step": 358760 }, { "epoch": 29.82, "learning_rate": 2.5485685780007203e-08, "loss": 0.6823, "step": 358770 }, { "epoch": 29.82, "learning_rate": 2.5374830252473462e-08, "loss": 0.6943, "step": 358780 }, { "epoch": 29.82, "learning_rate": 2.526397472493972e-08, "loss": 0.7158, "step": 358790 }, { "epoch": 29.82, "learning_rate": 2.515311919740598e-08, "loss": 0.7568, "step": 358800 }, { "epoch": 29.82, "learning_rate": 2.504226366987224e-08, "loss": 0.7048, "step": 358810 }, { "epoch": 29.82, "learning_rate": 2.4931408142338495e-08, "loss": 0.8329, "step": 358820 }, { "epoch": 29.83, "learning_rate": 2.4820552614804754e-08, "loss": 0.7297, "step": 358830 }, { "epoch": 29.83, "learning_rate": 2.4709697087271013e-08, "loss": 0.727, "step": 358840 }, { "epoch": 29.83, "learning_rate": 2.459884155973727e-08, "loss": 0.8168, "step": 358850 }, { "epoch": 29.83, "learning_rate": 2.448798603220353e-08, "loss": 0.8085, "step": 358860 }, { "epoch": 29.83, "learning_rate": 2.437713050466979e-08, "loss": 0.6917, "step": 358870 }, { "epoch": 29.83, "learning_rate": 2.4266274977136045e-08, "loss": 0.7158, "step": 358880 }, { "epoch": 29.83, "learning_rate": 2.4155419449602304e-08, "loss": 0.7056, "step": 358890 }, { "epoch": 29.83, "learning_rate": 2.4044563922068563e-08, "loss": 0.7112, "step": 358900 }, { "epoch": 29.83, "learning_rate": 2.3933708394534822e-08, "loss": 0.7728, "step": 358910 }, { "epoch": 29.83, "learning_rate": 2.382285286700108e-08, "loss": 0.757, "step": 358920 }, { "epoch": 29.83, "learning_rate": 2.3711997339467336e-08, "loss": 0.6974, "step": 358930 }, { "epoch": 29.83, "learning_rate": 2.3601141811933595e-08, "loss": 0.7511, "step": 358940 }, { "epoch": 29.84, "learning_rate": 2.3490286284399854e-08, "loss": 0.7452, "step": 358950 }, { "epoch": 29.84, "learning_rate": 2.3379430756866113e-08, "loss": 0.7119, "step": 358960 }, { "epoch": 29.84, "learning_rate": 2.3268575229332372e-08, "loss": 0.6791, "step": 358970 }, { "epoch": 29.84, "learning_rate": 2.3157719701798628e-08, "loss": 0.7331, "step": 358980 }, { "epoch": 29.84, "learning_rate": 2.304686417426489e-08, "loss": 0.7012, "step": 358990 }, { "epoch": 29.84, "learning_rate": 2.293600864673115e-08, "loss": 0.6699, "step": 359000 }, { "epoch": 29.84, "learning_rate": 2.2825153119197405e-08, "loss": 0.7451, "step": 359010 }, { "epoch": 29.84, "learning_rate": 2.2714297591663664e-08, "loss": 0.7308, "step": 359020 }, { "epoch": 29.84, "learning_rate": 2.260344206412992e-08, "loss": 0.7241, "step": 359030 }, { "epoch": 29.84, "learning_rate": 2.249258653659618e-08, "loss": 0.7401, "step": 359040 }, { "epoch": 29.84, "learning_rate": 2.238173100906244e-08, "loss": 0.7006, "step": 359050 }, { "epoch": 29.84, "learning_rate": 2.2270875481528696e-08, "loss": 0.7729, "step": 359060 }, { "epoch": 29.85, "learning_rate": 2.2160019953994955e-08, "loss": 0.7092, "step": 359070 }, { "epoch": 29.85, "learning_rate": 2.204916442646121e-08, "loss": 0.6826, "step": 359080 }, { "epoch": 29.85, "learning_rate": 2.1938308898927473e-08, "loss": 0.6606, "step": 359090 }, { "epoch": 29.85, "learning_rate": 2.1827453371393732e-08, "loss": 0.7183, "step": 359100 }, { "epoch": 29.85, "learning_rate": 2.1716597843859987e-08, "loss": 0.7704, "step": 359110 }, { "epoch": 29.85, "learning_rate": 2.1605742316326246e-08, "loss": 0.716, "step": 359120 }, { "epoch": 29.85, "learning_rate": 2.1494886788792505e-08, "loss": 0.7663, "step": 359130 }, { "epoch": 29.85, "learning_rate": 2.1384031261258764e-08, "loss": 0.7401, "step": 359140 }, { "epoch": 29.85, "learning_rate": 2.1273175733725023e-08, "loss": 0.7963, "step": 359150 }, { "epoch": 29.85, "learning_rate": 2.116232020619128e-08, "loss": 0.7604, "step": 359160 }, { "epoch": 29.85, "learning_rate": 2.1051464678657538e-08, "loss": 0.7271, "step": 359170 }, { "epoch": 29.85, "learning_rate": 2.0940609151123797e-08, "loss": 0.7314, "step": 359180 }, { "epoch": 29.86, "learning_rate": 2.0829753623590056e-08, "loss": 0.7358, "step": 359190 }, { "epoch": 29.86, "learning_rate": 2.0718898096056315e-08, "loss": 0.7494, "step": 359200 }, { "epoch": 29.86, "learning_rate": 2.0608042568522574e-08, "loss": 0.7231, "step": 359210 }, { "epoch": 29.86, "learning_rate": 2.049718704098883e-08, "loss": 0.7253, "step": 359220 }, { "epoch": 29.86, "learning_rate": 2.0386331513455088e-08, "loss": 0.7103, "step": 359230 }, { "epoch": 29.86, "learning_rate": 2.0275475985921347e-08, "loss": 0.7591, "step": 359240 }, { "epoch": 29.86, "learning_rate": 2.0164620458387606e-08, "loss": 0.7534, "step": 359250 }, { "epoch": 29.86, "learning_rate": 2.0053764930853865e-08, "loss": 0.7357, "step": 359260 }, { "epoch": 29.86, "learning_rate": 1.994290940332012e-08, "loss": 0.6939, "step": 359270 }, { "epoch": 29.86, "learning_rate": 1.983205387578638e-08, "loss": 0.7364, "step": 359280 }, { "epoch": 29.86, "learning_rate": 1.972119834825264e-08, "loss": 0.7203, "step": 359290 }, { "epoch": 29.86, "learning_rate": 1.9610342820718897e-08, "loss": 0.7534, "step": 359300 }, { "epoch": 29.87, "learning_rate": 1.9499487293185156e-08, "loss": 0.7608, "step": 359310 }, { "epoch": 29.87, "learning_rate": 1.9388631765651412e-08, "loss": 0.722, "step": 359320 }, { "epoch": 29.87, "learning_rate": 1.9277776238117674e-08, "loss": 0.687, "step": 359330 }, { "epoch": 29.87, "learning_rate": 1.9166920710583933e-08, "loss": 0.6938, "step": 359340 }, { "epoch": 29.87, "learning_rate": 1.905606518305019e-08, "loss": 0.6754, "step": 359350 }, { "epoch": 29.87, "learning_rate": 1.8945209655516448e-08, "loss": 0.8148, "step": 359360 }, { "epoch": 29.87, "learning_rate": 1.8834354127982703e-08, "loss": 0.6887, "step": 359370 }, { "epoch": 29.87, "learning_rate": 1.8723498600448966e-08, "loss": 0.7742, "step": 359380 }, { "epoch": 29.87, "learning_rate": 1.8612643072915225e-08, "loss": 0.7649, "step": 359390 }, { "epoch": 29.87, "learning_rate": 1.850178754538148e-08, "loss": 0.7229, "step": 359400 }, { "epoch": 29.87, "learning_rate": 1.839093201784774e-08, "loss": 0.7337, "step": 359410 }, { "epoch": 29.87, "learning_rate": 1.8280076490313995e-08, "loss": 0.7489, "step": 359420 }, { "epoch": 29.88, "learning_rate": 1.8169220962780257e-08, "loss": 0.6784, "step": 359430 }, { "epoch": 29.88, "learning_rate": 1.8058365435246516e-08, "loss": 0.6918, "step": 359440 }, { "epoch": 29.88, "learning_rate": 1.794750990771277e-08, "loss": 0.6847, "step": 359450 }, { "epoch": 29.88, "learning_rate": 1.783665438017903e-08, "loss": 0.7994, "step": 359460 }, { "epoch": 29.88, "learning_rate": 1.772579885264529e-08, "loss": 0.7498, "step": 359470 }, { "epoch": 29.88, "learning_rate": 1.761494332511155e-08, "loss": 0.7303, "step": 359480 }, { "epoch": 29.88, "learning_rate": 1.7504087797577807e-08, "loss": 0.7534, "step": 359490 }, { "epoch": 29.88, "learning_rate": 1.7393232270044063e-08, "loss": 0.719, "step": 359500 }, { "epoch": 29.88, "learning_rate": 1.7282376742510322e-08, "loss": 0.7435, "step": 359510 }, { "epoch": 29.88, "learning_rate": 1.717152121497658e-08, "loss": 0.6647, "step": 359520 }, { "epoch": 29.88, "learning_rate": 1.706066568744284e-08, "loss": 0.7115, "step": 359530 }, { "epoch": 29.88, "learning_rate": 1.69498101599091e-08, "loss": 0.6737, "step": 359540 }, { "epoch": 29.89, "learning_rate": 1.6838954632375354e-08, "loss": 0.7342, "step": 359550 }, { "epoch": 29.89, "learning_rate": 1.6728099104841613e-08, "loss": 0.7924, "step": 359560 }, { "epoch": 29.89, "learning_rate": 1.6617243577307872e-08, "loss": 0.7505, "step": 359570 }, { "epoch": 29.89, "learning_rate": 1.650638804977413e-08, "loss": 0.7159, "step": 359580 }, { "epoch": 29.89, "learning_rate": 1.639553252224039e-08, "loss": 0.7101, "step": 359590 }, { "epoch": 29.89, "learning_rate": 1.628467699470665e-08, "loss": 0.839, "step": 359600 }, { "epoch": 29.89, "learning_rate": 1.6173821467172905e-08, "loss": 0.7593, "step": 359610 }, { "epoch": 29.89, "learning_rate": 1.6062965939639164e-08, "loss": 0.732, "step": 359620 }, { "epoch": 29.89, "learning_rate": 1.5952110412105423e-08, "loss": 0.6831, "step": 359630 }, { "epoch": 29.89, "learning_rate": 1.584125488457168e-08, "loss": 0.7567, "step": 359640 }, { "epoch": 29.89, "learning_rate": 1.573039935703794e-08, "loss": 0.6949, "step": 359650 }, { "epoch": 29.89, "learning_rate": 1.56195438295042e-08, "loss": 0.7476, "step": 359660 }, { "epoch": 29.9, "learning_rate": 1.5508688301970455e-08, "loss": 0.7702, "step": 359670 }, { "epoch": 29.9, "learning_rate": 1.5397832774436714e-08, "loss": 0.7274, "step": 359680 }, { "epoch": 29.9, "learning_rate": 1.5286977246902973e-08, "loss": 0.7309, "step": 359690 }, { "epoch": 29.9, "learning_rate": 1.5176121719369232e-08, "loss": 0.7139, "step": 359700 }, { "epoch": 29.9, "learning_rate": 1.506526619183549e-08, "loss": 0.7191, "step": 359710 }, { "epoch": 29.9, "learning_rate": 1.4954410664301746e-08, "loss": 0.7133, "step": 359720 }, { "epoch": 29.9, "learning_rate": 1.4843555136768005e-08, "loss": 0.7943, "step": 359730 }, { "epoch": 29.9, "learning_rate": 1.4732699609234264e-08, "loss": 0.6923, "step": 359740 }, { "epoch": 29.9, "learning_rate": 1.4621844081700523e-08, "loss": 0.7659, "step": 359750 }, { "epoch": 29.9, "learning_rate": 1.4510988554166782e-08, "loss": 0.7959, "step": 359760 }, { "epoch": 29.9, "learning_rate": 1.440013302663304e-08, "loss": 0.7383, "step": 359770 }, { "epoch": 29.9, "learning_rate": 1.4289277499099298e-08, "loss": 0.7583, "step": 359780 }, { "epoch": 29.91, "learning_rate": 1.4178421971565557e-08, "loss": 0.6663, "step": 359790 }, { "epoch": 29.91, "learning_rate": 1.4067566444031815e-08, "loss": 0.6941, "step": 359800 }, { "epoch": 29.91, "learning_rate": 1.3956710916498074e-08, "loss": 0.7331, "step": 359810 }, { "epoch": 29.91, "learning_rate": 1.3845855388964331e-08, "loss": 0.7196, "step": 359820 }, { "epoch": 29.91, "learning_rate": 1.373499986143059e-08, "loss": 0.6813, "step": 359830 }, { "epoch": 29.91, "learning_rate": 1.3624144333896849e-08, "loss": 0.7916, "step": 359840 }, { "epoch": 29.91, "learning_rate": 1.3513288806363106e-08, "loss": 0.7291, "step": 359850 }, { "epoch": 29.91, "learning_rate": 1.3402433278829365e-08, "loss": 0.7642, "step": 359860 }, { "epoch": 29.91, "learning_rate": 1.3291577751295622e-08, "loss": 0.7127, "step": 359870 }, { "epoch": 29.91, "learning_rate": 1.3180722223761883e-08, "loss": 0.6789, "step": 359880 }, { "epoch": 29.91, "learning_rate": 1.306986669622814e-08, "loss": 0.731, "step": 359890 }, { "epoch": 29.91, "learning_rate": 1.2959011168694398e-08, "loss": 0.7828, "step": 359900 }, { "epoch": 29.92, "learning_rate": 1.2848155641160656e-08, "loss": 0.7782, "step": 359910 }, { "epoch": 29.92, "learning_rate": 1.2737300113626915e-08, "loss": 0.7177, "step": 359920 }, { "epoch": 29.92, "learning_rate": 1.2626444586093174e-08, "loss": 0.7326, "step": 359930 }, { "epoch": 29.92, "learning_rate": 1.2515589058559432e-08, "loss": 0.7025, "step": 359940 }, { "epoch": 29.92, "learning_rate": 1.240473353102569e-08, "loss": 0.7231, "step": 359950 }, { "epoch": 29.92, "learning_rate": 1.2293878003491948e-08, "loss": 0.7608, "step": 359960 }, { "epoch": 29.92, "learning_rate": 1.2183022475958207e-08, "loss": 0.726, "step": 359970 }, { "epoch": 29.92, "learning_rate": 1.2072166948424466e-08, "loss": 0.7682, "step": 359980 }, { "epoch": 29.92, "learning_rate": 1.1961311420890723e-08, "loss": 0.7274, "step": 359990 }, { "epoch": 29.92, "learning_rate": 1.1850455893356982e-08, "loss": 0.7581, "step": 360000 }, { "epoch": 29.92, "learning_rate": 1.1739600365823241e-08, "loss": 0.7511, "step": 360010 }, { "epoch": 29.92, "learning_rate": 1.1628744838289498e-08, "loss": 0.75, "step": 360020 }, { "epoch": 29.93, "learning_rate": 1.1528974863509131e-08, "loss": 0.7035, "step": 360030 }, { "epoch": 29.93, "learning_rate": 1.141811933597539e-08, "loss": 0.7401, "step": 360040 }, { "epoch": 29.93, "learning_rate": 1.1307263808441647e-08, "loss": 0.7248, "step": 360050 }, { "epoch": 29.93, "learning_rate": 1.1196408280907905e-08, "loss": 0.7136, "step": 360060 }, { "epoch": 29.93, "learning_rate": 1.1085552753374165e-08, "loss": 0.7047, "step": 360070 }, { "epoch": 29.93, "learning_rate": 1.0974697225840423e-08, "loss": 0.7447, "step": 360080 }, { "epoch": 29.93, "learning_rate": 1.0863841698306682e-08, "loss": 0.7519, "step": 360090 }, { "epoch": 29.93, "learning_rate": 1.0752986170772939e-08, "loss": 0.6703, "step": 360100 }, { "epoch": 29.93, "learning_rate": 1.0642130643239198e-08, "loss": 0.7212, "step": 360110 }, { "epoch": 29.93, "learning_rate": 1.0531275115705457e-08, "loss": 0.7727, "step": 360120 }, { "epoch": 29.93, "learning_rate": 1.0420419588171714e-08, "loss": 0.7056, "step": 360130 }, { "epoch": 29.93, "learning_rate": 1.0309564060637973e-08, "loss": 0.702, "step": 360140 }, { "epoch": 29.94, "learning_rate": 1.0198708533104232e-08, "loss": 0.7591, "step": 360150 }, { "epoch": 29.94, "learning_rate": 1.0087853005570491e-08, "loss": 0.7628, "step": 360160 }, { "epoch": 29.94, "learning_rate": 9.976997478036748e-09, "loss": 0.7303, "step": 360170 }, { "epoch": 29.94, "learning_rate": 9.866141950503005e-09, "loss": 0.6506, "step": 360180 }, { "epoch": 29.94, "learning_rate": 9.755286422969266e-09, "loss": 0.7452, "step": 360190 }, { "epoch": 29.94, "learning_rate": 9.644430895435523e-09, "loss": 0.7525, "step": 360200 }, { "epoch": 29.94, "learning_rate": 9.533575367901782e-09, "loss": 0.6981, "step": 360210 }, { "epoch": 29.94, "learning_rate": 9.42271984036804e-09, "loss": 0.7222, "step": 360220 }, { "epoch": 29.94, "learning_rate": 9.311864312834297e-09, "loss": 0.7527, "step": 360230 }, { "epoch": 29.94, "learning_rate": 9.201008785300557e-09, "loss": 0.7317, "step": 360240 }, { "epoch": 29.94, "learning_rate": 9.090153257766815e-09, "loss": 0.7202, "step": 360250 }, { "epoch": 29.94, "learning_rate": 8.979297730233074e-09, "loss": 0.7548, "step": 360260 }, { "epoch": 29.95, "learning_rate": 8.868442202699331e-09, "loss": 0.7281, "step": 360270 }, { "epoch": 29.95, "learning_rate": 8.75758667516559e-09, "loss": 0.7177, "step": 360280 }, { "epoch": 29.95, "learning_rate": 8.646731147631849e-09, "loss": 0.6857, "step": 360290 }, { "epoch": 29.95, "learning_rate": 8.535875620098106e-09, "loss": 0.7487, "step": 360300 }, { "epoch": 29.95, "learning_rate": 8.425020092564365e-09, "loss": 0.7488, "step": 360310 }, { "epoch": 29.95, "learning_rate": 8.314164565030624e-09, "loss": 0.7071, "step": 360320 }, { "epoch": 29.95, "learning_rate": 8.203309037496883e-09, "loss": 0.7262, "step": 360330 }, { "epoch": 29.95, "learning_rate": 8.09245350996314e-09, "loss": 0.7202, "step": 360340 }, { "epoch": 29.95, "learning_rate": 7.981597982429398e-09, "loss": 0.7021, "step": 360350 }, { "epoch": 29.95, "learning_rate": 7.870742454895656e-09, "loss": 0.7516, "step": 360360 }, { "epoch": 29.95, "learning_rate": 7.759886927361915e-09, "loss": 0.7962, "step": 360370 }, { "epoch": 29.95, "learning_rate": 7.649031399828173e-09, "loss": 0.7103, "step": 360380 }, { "epoch": 29.96, "learning_rate": 7.538175872294432e-09, "loss": 0.7572, "step": 360390 }, { "epoch": 29.96, "learning_rate": 7.427320344760691e-09, "loss": 0.6956, "step": 360400 }, { "epoch": 29.96, "learning_rate": 7.316464817226949e-09, "loss": 0.7925, "step": 360410 }, { "epoch": 29.96, "learning_rate": 7.205609289693207e-09, "loss": 0.7231, "step": 360420 }, { "epoch": 29.96, "learning_rate": 7.094753762159465e-09, "loss": 0.6575, "step": 360430 }, { "epoch": 29.96, "learning_rate": 6.983898234625724e-09, "loss": 0.7281, "step": 360440 }, { "epoch": 29.96, "learning_rate": 6.873042707091982e-09, "loss": 0.7684, "step": 360450 }, { "epoch": 29.96, "learning_rate": 6.762187179558241e-09, "loss": 0.7713, "step": 360460 }, { "epoch": 29.96, "learning_rate": 6.651331652024499e-09, "loss": 0.6757, "step": 360470 }, { "epoch": 29.96, "learning_rate": 6.540476124490756e-09, "loss": 0.7258, "step": 360480 }, { "epoch": 29.96, "learning_rate": 6.429620596957015e-09, "loss": 0.7567, "step": 360490 }, { "epoch": 29.96, "learning_rate": 6.318765069423273e-09, "loss": 0.7057, "step": 360500 }, { "epoch": 29.97, "learning_rate": 6.207909541889532e-09, "loss": 0.7636, "step": 360510 }, { "epoch": 29.97, "learning_rate": 6.0970540143557904e-09, "loss": 0.7163, "step": 360520 }, { "epoch": 29.97, "learning_rate": 5.986198486822049e-09, "loss": 0.6408, "step": 360530 }, { "epoch": 29.97, "learning_rate": 5.875342959288307e-09, "loss": 0.7569, "step": 360540 }, { "epoch": 29.97, "learning_rate": 5.764487431754566e-09, "loss": 0.7386, "step": 360550 }, { "epoch": 29.97, "learning_rate": 5.653631904220824e-09, "loss": 0.7585, "step": 360560 }, { "epoch": 29.97, "learning_rate": 5.542776376687083e-09, "loss": 0.6992, "step": 360570 }, { "epoch": 29.97, "learning_rate": 5.431920849153341e-09, "loss": 0.7692, "step": 360580 }, { "epoch": 29.97, "learning_rate": 5.321065321619599e-09, "loss": 0.7746, "step": 360590 }, { "epoch": 29.97, "learning_rate": 5.210209794085857e-09, "loss": 0.7441, "step": 360600 }, { "epoch": 29.97, "learning_rate": 5.099354266552116e-09, "loss": 0.8086, "step": 360610 }, { "epoch": 29.97, "learning_rate": 4.988498739018374e-09, "loss": 0.7469, "step": 360620 }, { "epoch": 29.98, "learning_rate": 4.877643211484633e-09, "loss": 0.7516, "step": 360630 }, { "epoch": 29.98, "learning_rate": 4.766787683950891e-09, "loss": 0.6743, "step": 360640 }, { "epoch": 29.98, "learning_rate": 4.6559321564171484e-09, "loss": 0.673, "step": 360650 }, { "epoch": 29.98, "learning_rate": 4.545076628883407e-09, "loss": 0.8006, "step": 360660 }, { "epoch": 29.98, "learning_rate": 4.4342211013496655e-09, "loss": 0.7512, "step": 360670 }, { "epoch": 29.98, "learning_rate": 4.3233655738159244e-09, "loss": 0.7061, "step": 360680 }, { "epoch": 29.98, "learning_rate": 4.2125100462821825e-09, "loss": 0.7404, "step": 360690 }, { "epoch": 29.98, "learning_rate": 4.1016545187484415e-09, "loss": 0.6937, "step": 360700 }, { "epoch": 29.98, "learning_rate": 3.990798991214699e-09, "loss": 0.7654, "step": 360710 }, { "epoch": 29.98, "learning_rate": 3.879943463680958e-09, "loss": 0.7288, "step": 360720 }, { "epoch": 29.98, "learning_rate": 3.769087936147216e-09, "loss": 0.7335, "step": 360730 }, { "epoch": 29.98, "learning_rate": 3.6582324086134744e-09, "loss": 0.7068, "step": 360740 }, { "epoch": 29.99, "learning_rate": 3.5473768810797325e-09, "loss": 0.7603, "step": 360750 }, { "epoch": 29.99, "learning_rate": 3.436521353545991e-09, "loss": 0.7265, "step": 360760 }, { "epoch": 29.99, "learning_rate": 3.3256658260122495e-09, "loss": 0.7206, "step": 360770 }, { "epoch": 29.99, "learning_rate": 3.2148102984785076e-09, "loss": 0.7594, "step": 360780 }, { "epoch": 29.99, "learning_rate": 3.103954770944766e-09, "loss": 0.6829, "step": 360790 }, { "epoch": 29.99, "learning_rate": 2.9930992434110247e-09, "loss": 0.7291, "step": 360800 }, { "epoch": 29.99, "learning_rate": 2.882243715877283e-09, "loss": 0.7526, "step": 360810 }, { "epoch": 29.99, "learning_rate": 2.7713881883435413e-09, "loss": 0.7655, "step": 360820 }, { "epoch": 29.99, "learning_rate": 2.6716182135631736e-09, "loss": 0.7525, "step": 360830 }, { "epoch": 29.99, "learning_rate": 2.560762686029432e-09, "loss": 0.7255, "step": 360840 }, { "epoch": 29.99, "learning_rate": 2.44990715849569e-09, "loss": 0.7052, "step": 360850 }, { "epoch": 29.99, "learning_rate": 2.3390516309619487e-09, "loss": 0.753, "step": 360860 }, { "epoch": 30.0, "learning_rate": 2.2281961034282073e-09, "loss": 0.7482, "step": 360870 }, { "epoch": 30.0, "learning_rate": 2.1173405758944654e-09, "loss": 0.7295, "step": 360880 }, { "epoch": 30.0, "learning_rate": 2.006485048360724e-09, "loss": 0.6647, "step": 360890 }, { "epoch": 30.0, "learning_rate": 1.895629520826982e-09, "loss": 0.675, "step": 360900 }, { "epoch": 30.0, "learning_rate": 1.7847739932932405e-09, "loss": 0.7455, "step": 360910 }, { "epoch": 30.0, "learning_rate": 1.6739184657594987e-09, "loss": 0.6612, "step": 360920 }, { "epoch": 30.0, "learning_rate": 1.5630629382257572e-09, "loss": 0.727, "step": 360930 }, { "epoch": 30.0, "eval_loss": 1.149397611618042, "eval_runtime": 360.7276, "eval_samples_per_second": 7.413, "eval_steps_per_second": 3.706, "eval_wer": 0.6347935001153631, "step": 360930 }, { "epoch": 30.0, "step": 360930, "total_flos": 2.1871873287819464e+20, "train_loss": 0.7832371163301508, "train_runtime": 175353.2233, "train_samples_per_second": 4.116, "train_steps_per_second": 2.058 } ], "max_steps": 360930, "num_train_epochs": 30, "total_flos": 2.1871873287819464e+20, "trial_name": null, "trial_params": null }