{ "best_metric": 0.9789265722752717, "best_model_checkpoint": "wav2vec2-present/checkpoint-15057", "epoch": 10.0, "eval_steps": 500, "global_step": 21510, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.394700139470014e-07, "loss": 2.8932, "step": 10 }, { "epoch": 0.01, "learning_rate": 2.789400278940028e-07, "loss": 2.8879, "step": 20 }, { "epoch": 0.01, "learning_rate": 4.184100418410042e-07, "loss": 2.8961, "step": 30 }, { "epoch": 0.02, "learning_rate": 5.578800557880056e-07, "loss": 2.8933, "step": 40 }, { "epoch": 0.02, "learning_rate": 6.97350069735007e-07, "loss": 2.8885, "step": 50 }, { "epoch": 0.03, "learning_rate": 8.368200836820084e-07, "loss": 2.8916, "step": 60 }, { "epoch": 0.03, "learning_rate": 9.762900976290097e-07, "loss": 2.8944, "step": 70 }, { "epoch": 0.04, "learning_rate": 1.1157601115760112e-06, "loss": 2.8856, "step": 80 }, { "epoch": 0.04, "learning_rate": 1.2552301255230125e-06, "loss": 2.8918, "step": 90 }, { "epoch": 0.05, "learning_rate": 1.394700139470014e-06, "loss": 2.8833, "step": 100 }, { "epoch": 0.05, "learning_rate": 1.5341701534170154e-06, "loss": 2.8872, "step": 110 }, { "epoch": 0.06, "learning_rate": 1.6736401673640167e-06, "loss": 2.8886, "step": 120 }, { "epoch": 0.06, "learning_rate": 1.8131101813110183e-06, "loss": 2.8821, "step": 130 }, { "epoch": 0.07, "learning_rate": 1.9525801952580194e-06, "loss": 2.8814, "step": 140 }, { "epoch": 0.07, "learning_rate": 2.092050209205021e-06, "loss": 2.8848, "step": 150 }, { "epoch": 0.07, "learning_rate": 2.2315202231520224e-06, "loss": 2.8769, "step": 160 }, { "epoch": 0.08, "learning_rate": 2.3709902370990235e-06, "loss": 2.8785, "step": 170 }, { "epoch": 0.08, "learning_rate": 2.510460251046025e-06, "loss": 2.8798, "step": 180 }, { "epoch": 0.09, "learning_rate": 2.6499302649930266e-06, "loss": 2.8646, "step": 190 }, { "epoch": 0.09, "learning_rate": 2.789400278940028e-06, "loss": 2.8738, "step": 200 }, { "epoch": 0.1, "learning_rate": 2.9288702928870297e-06, "loss": 2.8659, "step": 210 }, { "epoch": 0.1, "learning_rate": 3.068340306834031e-06, "loss": 2.8625, "step": 220 }, { "epoch": 0.11, "learning_rate": 3.207810320781032e-06, "loss": 2.8687, "step": 230 }, { "epoch": 0.11, "learning_rate": 3.3472803347280334e-06, "loss": 2.861, "step": 240 }, { "epoch": 0.12, "learning_rate": 3.486750348675035e-06, "loss": 2.8517, "step": 250 }, { "epoch": 0.12, "learning_rate": 3.6262203626220365e-06, "loss": 2.8432, "step": 260 }, { "epoch": 0.13, "learning_rate": 3.7656903765690376e-06, "loss": 2.8486, "step": 270 }, { "epoch": 0.13, "learning_rate": 3.905160390516039e-06, "loss": 2.8497, "step": 280 }, { "epoch": 0.13, "learning_rate": 4.044630404463041e-06, "loss": 2.8504, "step": 290 }, { "epoch": 0.14, "learning_rate": 4.184100418410042e-06, "loss": 2.8517, "step": 300 }, { "epoch": 0.14, "learning_rate": 4.323570432357044e-06, "loss": 2.8413, "step": 310 }, { "epoch": 0.15, "learning_rate": 4.463040446304045e-06, "loss": 2.8281, "step": 320 }, { "epoch": 0.15, "learning_rate": 4.602510460251047e-06, "loss": 2.8376, "step": 330 }, { "epoch": 0.16, "learning_rate": 4.741980474198047e-06, "loss": 2.8325, "step": 340 }, { "epoch": 0.16, "learning_rate": 4.881450488145049e-06, "loss": 2.8125, "step": 350 }, { "epoch": 0.17, "learning_rate": 5.02092050209205e-06, "loss": 2.7992, "step": 360 }, { "epoch": 0.17, "learning_rate": 5.160390516039051e-06, "loss": 2.7948, "step": 370 }, { "epoch": 0.18, "learning_rate": 5.299860529986053e-06, "loss": 2.7747, "step": 380 }, { "epoch": 0.18, "learning_rate": 5.439330543933054e-06, "loss": 2.7668, "step": 390 }, { "epoch": 0.19, "learning_rate": 5.578800557880056e-06, "loss": 2.7652, "step": 400 }, { "epoch": 0.19, "learning_rate": 5.718270571827057e-06, "loss": 2.7773, "step": 410 }, { "epoch": 0.2, "learning_rate": 5.857740585774059e-06, "loss": 2.7606, "step": 420 }, { "epoch": 0.2, "learning_rate": 5.9972105997210605e-06, "loss": 2.7637, "step": 430 }, { "epoch": 0.2, "learning_rate": 6.136680613668062e-06, "loss": 2.7201, "step": 440 }, { "epoch": 0.21, "learning_rate": 6.276150627615063e-06, "loss": 2.7098, "step": 450 }, { "epoch": 0.21, "learning_rate": 6.415620641562064e-06, "loss": 2.7002, "step": 460 }, { "epoch": 0.22, "learning_rate": 6.555090655509066e-06, "loss": 2.6489, "step": 470 }, { "epoch": 0.22, "learning_rate": 6.680613668061368e-06, "loss": 2.6457, "step": 480 }, { "epoch": 0.23, "learning_rate": 6.820083682008369e-06, "loss": 2.6344, "step": 490 }, { "epoch": 0.23, "learning_rate": 6.95955369595537e-06, "loss": 2.6388, "step": 500 }, { "epoch": 0.24, "learning_rate": 7.099023709902371e-06, "loss": 2.614, "step": 510 }, { "epoch": 0.24, "learning_rate": 7.238493723849372e-06, "loss": 2.6101, "step": 520 }, { "epoch": 0.25, "learning_rate": 7.377963737796374e-06, "loss": 2.5636, "step": 530 }, { "epoch": 0.25, "learning_rate": 7.517433751743376e-06, "loss": 2.5611, "step": 540 }, { "epoch": 0.26, "learning_rate": 7.656903765690377e-06, "loss": 2.5388, "step": 550 }, { "epoch": 0.26, "learning_rate": 7.796373779637378e-06, "loss": 2.5398, "step": 560 }, { "epoch": 0.26, "learning_rate": 7.93584379358438e-06, "loss": 2.4898, "step": 570 }, { "epoch": 0.27, "learning_rate": 8.07531380753138e-06, "loss": 2.4637, "step": 580 }, { "epoch": 0.27, "learning_rate": 8.214783821478383e-06, "loss": 2.4287, "step": 590 }, { "epoch": 0.28, "learning_rate": 8.354253835425383e-06, "loss": 2.4482, "step": 600 }, { "epoch": 0.28, "learning_rate": 8.493723849372385e-06, "loss": 2.4344, "step": 610 }, { "epoch": 0.29, "learning_rate": 8.633193863319387e-06, "loss": 2.336, "step": 620 }, { "epoch": 0.29, "learning_rate": 8.77266387726639e-06, "loss": 2.3321, "step": 630 }, { "epoch": 0.3, "learning_rate": 8.912133891213389e-06, "loss": 2.3578, "step": 640 }, { "epoch": 0.3, "learning_rate": 9.05160390516039e-06, "loss": 2.3621, "step": 650 }, { "epoch": 0.31, "learning_rate": 9.191073919107393e-06, "loss": 2.3569, "step": 660 }, { "epoch": 0.31, "learning_rate": 9.330543933054392e-06, "loss": 2.2825, "step": 670 }, { "epoch": 0.32, "learning_rate": 9.470013947001395e-06, "loss": 2.3117, "step": 680 }, { "epoch": 0.32, "learning_rate": 9.609483960948396e-06, "loss": 2.2235, "step": 690 }, { "epoch": 0.33, "learning_rate": 9.748953974895399e-06, "loss": 2.1834, "step": 700 }, { "epoch": 0.33, "learning_rate": 9.888423988842398e-06, "loss": 2.1857, "step": 710 }, { "epoch": 0.33, "learning_rate": 1.0027894002789401e-05, "loss": 2.1783, "step": 720 }, { "epoch": 0.34, "learning_rate": 1.0167364016736402e-05, "loss": 2.151, "step": 730 }, { "epoch": 0.34, "learning_rate": 1.0306834030683405e-05, "loss": 2.1209, "step": 740 }, { "epoch": 0.35, "learning_rate": 1.0446304044630404e-05, "loss": 2.1109, "step": 750 }, { "epoch": 0.35, "learning_rate": 1.0585774058577405e-05, "loss": 2.056, "step": 760 }, { "epoch": 0.36, "learning_rate": 1.0725244072524408e-05, "loss": 1.9979, "step": 770 }, { "epoch": 0.36, "learning_rate": 1.0864714086471408e-05, "loss": 1.9882, "step": 780 }, { "epoch": 0.37, "learning_rate": 1.100418410041841e-05, "loss": 1.9189, "step": 790 }, { "epoch": 0.37, "learning_rate": 1.1143654114365412e-05, "loss": 1.9409, "step": 800 }, { "epoch": 0.38, "learning_rate": 1.1283124128312414e-05, "loss": 1.9101, "step": 810 }, { "epoch": 0.38, "learning_rate": 1.1422594142259414e-05, "loss": 2.0193, "step": 820 }, { "epoch": 0.39, "learning_rate": 1.1562064156206417e-05, "loss": 1.9348, "step": 830 }, { "epoch": 0.39, "learning_rate": 1.1701534170153418e-05, "loss": 1.9025, "step": 840 }, { "epoch": 0.4, "learning_rate": 1.1841004184100417e-05, "loss": 1.8682, "step": 850 }, { "epoch": 0.4, "learning_rate": 1.198047419804742e-05, "loss": 1.8374, "step": 860 }, { "epoch": 0.4, "learning_rate": 1.2119944211994421e-05, "loss": 1.7407, "step": 870 }, { "epoch": 0.41, "learning_rate": 1.2259414225941424e-05, "loss": 1.7579, "step": 880 }, { "epoch": 0.41, "learning_rate": 1.2398884239888423e-05, "loss": 1.7693, "step": 890 }, { "epoch": 0.42, "learning_rate": 1.2538354253835426e-05, "loss": 1.725, "step": 900 }, { "epoch": 0.42, "learning_rate": 1.2677824267782427e-05, "loss": 1.7028, "step": 910 }, { "epoch": 0.43, "learning_rate": 1.281729428172943e-05, "loss": 1.728, "step": 920 }, { "epoch": 0.43, "learning_rate": 1.295676429567643e-05, "loss": 1.6861, "step": 930 }, { "epoch": 0.44, "learning_rate": 1.309623430962343e-05, "loss": 1.6026, "step": 940 }, { "epoch": 0.44, "learning_rate": 1.3235704323570433e-05, "loss": 1.6721, "step": 950 }, { "epoch": 0.45, "learning_rate": 1.3375174337517433e-05, "loss": 1.6533, "step": 960 }, { "epoch": 0.45, "learning_rate": 1.3514644351464436e-05, "loss": 1.5843, "step": 970 }, { "epoch": 0.46, "learning_rate": 1.3654114365411437e-05, "loss": 1.6248, "step": 980 }, { "epoch": 0.46, "learning_rate": 1.379358437935844e-05, "loss": 1.5543, "step": 990 }, { "epoch": 0.46, "learning_rate": 1.3933054393305439e-05, "loss": 1.6078, "step": 1000 }, { "epoch": 0.47, "learning_rate": 1.4072524407252442e-05, "loss": 1.4884, "step": 1010 }, { "epoch": 0.47, "learning_rate": 1.4211994421199443e-05, "loss": 1.5583, "step": 1020 }, { "epoch": 0.48, "learning_rate": 1.4337517433751745e-05, "loss": 1.4856, "step": 1030 }, { "epoch": 0.48, "learning_rate": 1.4476987447698744e-05, "loss": 1.4153, "step": 1040 }, { "epoch": 0.49, "learning_rate": 1.4616457461645747e-05, "loss": 1.5187, "step": 1050 }, { "epoch": 0.49, "learning_rate": 1.4755927475592748e-05, "loss": 1.4212, "step": 1060 }, { "epoch": 0.5, "learning_rate": 1.4895397489539749e-05, "loss": 1.3842, "step": 1070 }, { "epoch": 0.5, "learning_rate": 1.5034867503486752e-05, "loss": 1.3595, "step": 1080 }, { "epoch": 0.51, "learning_rate": 1.5174337517433753e-05, "loss": 1.3853, "step": 1090 }, { "epoch": 0.51, "learning_rate": 1.5313807531380754e-05, "loss": 1.2961, "step": 1100 }, { "epoch": 0.52, "learning_rate": 1.5453277545327754e-05, "loss": 1.2973, "step": 1110 }, { "epoch": 0.52, "learning_rate": 1.5592747559274756e-05, "loss": 1.2672, "step": 1120 }, { "epoch": 0.53, "learning_rate": 1.573221757322176e-05, "loss": 1.3161, "step": 1130 }, { "epoch": 0.53, "learning_rate": 1.587168758716876e-05, "loss": 1.2184, "step": 1140 }, { "epoch": 0.53, "learning_rate": 1.601115760111576e-05, "loss": 1.2968, "step": 1150 }, { "epoch": 0.54, "learning_rate": 1.615062761506276e-05, "loss": 1.3205, "step": 1160 }, { "epoch": 0.54, "learning_rate": 1.6290097629009764e-05, "loss": 1.1363, "step": 1170 }, { "epoch": 0.55, "learning_rate": 1.6429567642956766e-05, "loss": 1.1579, "step": 1180 }, { "epoch": 0.55, "learning_rate": 1.6569037656903766e-05, "loss": 1.1291, "step": 1190 }, { "epoch": 0.56, "learning_rate": 1.6708507670850765e-05, "loss": 1.1111, "step": 1200 }, { "epoch": 0.56, "learning_rate": 1.6847977684797768e-05, "loss": 1.195, "step": 1210 }, { "epoch": 0.57, "learning_rate": 1.698744769874477e-05, "loss": 1.1692, "step": 1220 }, { "epoch": 0.57, "learning_rate": 1.7126917712691774e-05, "loss": 1.091, "step": 1230 }, { "epoch": 0.58, "learning_rate": 1.7266387726638773e-05, "loss": 1.0087, "step": 1240 }, { "epoch": 0.58, "learning_rate": 1.7405857740585773e-05, "loss": 1.0821, "step": 1250 }, { "epoch": 0.59, "learning_rate": 1.754532775453278e-05, "loss": 1.0786, "step": 1260 }, { "epoch": 0.59, "learning_rate": 1.7684797768479778e-05, "loss": 1.0286, "step": 1270 }, { "epoch": 0.6, "learning_rate": 1.7824267782426778e-05, "loss": 1.0807, "step": 1280 }, { "epoch": 0.6, "learning_rate": 1.796373779637378e-05, "loss": 1.0336, "step": 1290 }, { "epoch": 0.6, "learning_rate": 1.810320781032078e-05, "loss": 1.0355, "step": 1300 }, { "epoch": 0.61, "learning_rate": 1.8242677824267783e-05, "loss": 0.9392, "step": 1310 }, { "epoch": 0.61, "learning_rate": 1.8382147838214785e-05, "loss": 0.9515, "step": 1320 }, { "epoch": 0.62, "learning_rate": 1.8521617852161785e-05, "loss": 0.9423, "step": 1330 }, { "epoch": 0.62, "learning_rate": 1.8661087866108784e-05, "loss": 0.8123, "step": 1340 }, { "epoch": 0.63, "learning_rate": 1.880055788005579e-05, "loss": 1.0167, "step": 1350 }, { "epoch": 0.63, "learning_rate": 1.894002789400279e-05, "loss": 0.9288, "step": 1360 }, { "epoch": 0.64, "learning_rate": 1.9079497907949793e-05, "loss": 0.9445, "step": 1370 }, { "epoch": 0.64, "learning_rate": 1.9218967921896792e-05, "loss": 0.8053, "step": 1380 }, { "epoch": 0.65, "learning_rate": 1.9358437935843795e-05, "loss": 0.9432, "step": 1390 }, { "epoch": 0.65, "learning_rate": 1.9497907949790798e-05, "loss": 0.8761, "step": 1400 }, { "epoch": 0.66, "learning_rate": 1.9637377963737797e-05, "loss": 0.8646, "step": 1410 }, { "epoch": 0.66, "learning_rate": 1.9776847977684796e-05, "loss": 0.8397, "step": 1420 }, { "epoch": 0.66, "learning_rate": 1.99163179916318e-05, "loss": 0.8022, "step": 1430 }, { "epoch": 0.67, "learning_rate": 2.0055788005578802e-05, "loss": 0.6888, "step": 1440 }, { "epoch": 0.67, "learning_rate": 2.01952580195258e-05, "loss": 0.8969, "step": 1450 }, { "epoch": 0.68, "learning_rate": 2.0334728033472804e-05, "loss": 0.7044, "step": 1460 }, { "epoch": 0.68, "learning_rate": 2.0474198047419804e-05, "loss": 0.6346, "step": 1470 }, { "epoch": 0.69, "learning_rate": 2.061366806136681e-05, "loss": 0.7734, "step": 1480 }, { "epoch": 0.69, "learning_rate": 2.075313807531381e-05, "loss": 0.7262, "step": 1490 }, { "epoch": 0.7, "learning_rate": 2.089260808926081e-05, "loss": 0.6095, "step": 1500 }, { "epoch": 0.7, "learning_rate": 2.103207810320781e-05, "loss": 0.7233, "step": 1510 }, { "epoch": 0.71, "learning_rate": 2.1157601115760115e-05, "loss": 0.7737, "step": 1520 }, { "epoch": 0.71, "learning_rate": 2.1297071129707115e-05, "loss": 0.8418, "step": 1530 }, { "epoch": 0.72, "learning_rate": 2.1436541143654114e-05, "loss": 0.5966, "step": 1540 }, { "epoch": 0.72, "learning_rate": 2.1576011157601117e-05, "loss": 0.7214, "step": 1550 }, { "epoch": 0.73, "learning_rate": 2.1715481171548116e-05, "loss": 0.8499, "step": 1560 }, { "epoch": 0.73, "learning_rate": 2.185495118549512e-05, "loss": 0.6569, "step": 1570 }, { "epoch": 0.73, "learning_rate": 2.1994421199442122e-05, "loss": 0.6469, "step": 1580 }, { "epoch": 0.74, "learning_rate": 2.2119944211994422e-05, "loss": 0.6156, "step": 1590 }, { "epoch": 0.74, "learning_rate": 2.2259414225941425e-05, "loss": 0.6293, "step": 1600 }, { "epoch": 0.75, "learning_rate": 2.2398884239888424e-05, "loss": 0.6863, "step": 1610 }, { "epoch": 0.75, "learning_rate": 2.2538354253835427e-05, "loss": 0.6216, "step": 1620 }, { "epoch": 0.76, "learning_rate": 2.2677824267782426e-05, "loss": 0.6734, "step": 1630 }, { "epoch": 0.76, "learning_rate": 2.2817294281729426e-05, "loss": 0.5728, "step": 1640 }, { "epoch": 0.77, "learning_rate": 2.2956764295676432e-05, "loss": 0.5693, "step": 1650 }, { "epoch": 0.77, "learning_rate": 2.309623430962343e-05, "loss": 0.617, "step": 1660 }, { "epoch": 0.78, "learning_rate": 2.3235704323570434e-05, "loss": 0.5586, "step": 1670 }, { "epoch": 0.78, "learning_rate": 2.3375174337517434e-05, "loss": 0.7137, "step": 1680 }, { "epoch": 0.79, "learning_rate": 2.3514644351464436e-05, "loss": 0.6104, "step": 1690 }, { "epoch": 0.79, "learning_rate": 2.365411436541144e-05, "loss": 0.4187, "step": 1700 }, { "epoch": 0.79, "learning_rate": 2.379358437935844e-05, "loss": 0.6468, "step": 1710 }, { "epoch": 0.8, "learning_rate": 2.3933054393305438e-05, "loss": 0.5058, "step": 1720 }, { "epoch": 0.8, "learning_rate": 2.407252440725244e-05, "loss": 0.5845, "step": 1730 }, { "epoch": 0.81, "learning_rate": 2.4211994421199444e-05, "loss": 0.488, "step": 1740 }, { "epoch": 0.81, "learning_rate": 2.4351464435146443e-05, "loss": 0.5375, "step": 1750 }, { "epoch": 0.82, "learning_rate": 2.4490934449093446e-05, "loss": 0.6187, "step": 1760 }, { "epoch": 0.82, "learning_rate": 2.4630404463040445e-05, "loss": 0.4766, "step": 1770 }, { "epoch": 0.83, "learning_rate": 2.4769874476987448e-05, "loss": 0.5328, "step": 1780 }, { "epoch": 0.83, "learning_rate": 2.490934449093445e-05, "loss": 0.3891, "step": 1790 }, { "epoch": 0.84, "learning_rate": 2.504881450488145e-05, "loss": 0.4496, "step": 1800 }, { "epoch": 0.84, "learning_rate": 2.5188284518828453e-05, "loss": 0.5077, "step": 1810 }, { "epoch": 0.85, "learning_rate": 2.5327754532775453e-05, "loss": 0.6491, "step": 1820 }, { "epoch": 0.85, "learning_rate": 2.5467224546722455e-05, "loss": 0.5923, "step": 1830 }, { "epoch": 0.86, "learning_rate": 2.5606694560669458e-05, "loss": 0.5348, "step": 1840 }, { "epoch": 0.86, "learning_rate": 2.5746164574616458e-05, "loss": 0.468, "step": 1850 }, { "epoch": 0.86, "learning_rate": 2.5885634588563457e-05, "loss": 0.6697, "step": 1860 }, { "epoch": 0.87, "learning_rate": 2.6025104602510463e-05, "loss": 0.5131, "step": 1870 }, { "epoch": 0.87, "learning_rate": 2.6164574616457463e-05, "loss": 0.3658, "step": 1880 }, { "epoch": 0.88, "learning_rate": 2.6304044630404462e-05, "loss": 0.4172, "step": 1890 }, { "epoch": 0.88, "learning_rate": 2.6443514644351465e-05, "loss": 0.5263, "step": 1900 }, { "epoch": 0.89, "learning_rate": 2.6582984658298468e-05, "loss": 0.6777, "step": 1910 }, { "epoch": 0.89, "learning_rate": 2.672245467224547e-05, "loss": 0.6603, "step": 1920 }, { "epoch": 0.9, "learning_rate": 2.686192468619247e-05, "loss": 0.5585, "step": 1930 }, { "epoch": 0.9, "learning_rate": 2.700139470013947e-05, "loss": 0.3998, "step": 1940 }, { "epoch": 0.91, "learning_rate": 2.7140864714086472e-05, "loss": 0.4931, "step": 1950 }, { "epoch": 0.91, "learning_rate": 2.7280334728033475e-05, "loss": 0.4954, "step": 1960 }, { "epoch": 0.92, "learning_rate": 2.7419804741980474e-05, "loss": 0.3263, "step": 1970 }, { "epoch": 0.92, "learning_rate": 2.7559274755927477e-05, "loss": 0.3234, "step": 1980 }, { "epoch": 0.93, "learning_rate": 2.7698744769874477e-05, "loss": 0.4315, "step": 1990 }, { "epoch": 0.93, "learning_rate": 2.783821478382148e-05, "loss": 0.6674, "step": 2000 }, { "epoch": 0.93, "learning_rate": 2.7977684797768482e-05, "loss": 0.4425, "step": 2010 }, { "epoch": 0.94, "learning_rate": 2.811715481171548e-05, "loss": 0.5932, "step": 2020 }, { "epoch": 0.94, "learning_rate": 2.825662482566248e-05, "loss": 0.4652, "step": 2030 }, { "epoch": 0.95, "learning_rate": 2.8396094839609484e-05, "loss": 0.2503, "step": 2040 }, { "epoch": 0.95, "learning_rate": 2.8535564853556487e-05, "loss": 0.8047, "step": 2050 }, { "epoch": 0.96, "learning_rate": 2.867503486750349e-05, "loss": 0.4353, "step": 2060 }, { "epoch": 0.96, "learning_rate": 2.881450488145049e-05, "loss": 0.4179, "step": 2070 }, { "epoch": 0.97, "learning_rate": 2.8953974895397488e-05, "loss": 0.6257, "step": 2080 }, { "epoch": 0.97, "learning_rate": 2.9093444909344494e-05, "loss": 0.4073, "step": 2090 }, { "epoch": 0.98, "learning_rate": 2.9232914923291494e-05, "loss": 0.5766, "step": 2100 }, { "epoch": 0.98, "learning_rate": 2.9372384937238493e-05, "loss": 0.3263, "step": 2110 }, { "epoch": 0.99, "learning_rate": 2.9511854951185496e-05, "loss": 0.4164, "step": 2120 }, { "epoch": 0.99, "learning_rate": 2.9651324965132495e-05, "loss": 0.4837, "step": 2130 }, { "epoch": 0.99, "learning_rate": 2.9790794979079498e-05, "loss": 0.5648, "step": 2140 }, { "epoch": 1.0, "learning_rate": 2.99302649930265e-05, "loss": 0.5859, "step": 2150 }, { "epoch": 1.0, "eval_accuracy": 0.9351333552848206, "eval_loss": 0.29516899585723877, "eval_runtime": 17.4865, "eval_samples_per_second": 173.677, "eval_steps_per_second": 43.462, "step": 2151 }, { "epoch": 1.0, "learning_rate": 2.9992251665891835e-05, "loss": 0.5367, "step": 2160 }, { "epoch": 1.01, "learning_rate": 2.9976754997675502e-05, "loss": 0.2168, "step": 2170 }, { "epoch": 1.01, "learning_rate": 2.9961258329459166e-05, "loss": 0.3865, "step": 2180 }, { "epoch": 1.02, "learning_rate": 2.9945761661242834e-05, "loss": 0.4129, "step": 2190 }, { "epoch": 1.02, "learning_rate": 2.99302649930265e-05, "loss": 0.4894, "step": 2200 }, { "epoch": 1.03, "learning_rate": 2.991476832481017e-05, "loss": 0.3326, "step": 2210 }, { "epoch": 1.03, "learning_rate": 2.9899271656593833e-05, "loss": 0.2733, "step": 2220 }, { "epoch": 1.04, "learning_rate": 2.98837749883775e-05, "loss": 0.3845, "step": 2230 }, { "epoch": 1.04, "learning_rate": 2.9868278320161168e-05, "loss": 0.3955, "step": 2240 }, { "epoch": 1.05, "learning_rate": 2.9852781651944835e-05, "loss": 0.7167, "step": 2250 }, { "epoch": 1.05, "learning_rate": 2.98372849837285e-05, "loss": 0.3185, "step": 2260 }, { "epoch": 1.06, "learning_rate": 2.9821788315512167e-05, "loss": 0.4002, "step": 2270 }, { "epoch": 1.06, "learning_rate": 2.980629164729583e-05, "loss": 0.3908, "step": 2280 }, { "epoch": 1.06, "learning_rate": 2.9790794979079498e-05, "loss": 0.3851, "step": 2290 }, { "epoch": 1.07, "learning_rate": 2.9775298310863162e-05, "loss": 0.6374, "step": 2300 }, { "epoch": 1.07, "learning_rate": 2.975980164264683e-05, "loss": 0.3323, "step": 2310 }, { "epoch": 1.08, "learning_rate": 2.9744304974430497e-05, "loss": 0.3535, "step": 2320 }, { "epoch": 1.08, "learning_rate": 2.9728808306214165e-05, "loss": 0.2928, "step": 2330 }, { "epoch": 1.09, "learning_rate": 2.971331163799783e-05, "loss": 0.3505, "step": 2340 }, { "epoch": 1.09, "learning_rate": 2.9697814969781496e-05, "loss": 0.4709, "step": 2350 }, { "epoch": 1.1, "learning_rate": 2.9682318301565164e-05, "loss": 0.4436, "step": 2360 }, { "epoch": 1.1, "learning_rate": 2.966682163334883e-05, "loss": 0.437, "step": 2370 }, { "epoch": 1.11, "learning_rate": 2.9651324965132495e-05, "loss": 0.4205, "step": 2380 }, { "epoch": 1.11, "learning_rate": 2.9635828296916163e-05, "loss": 0.5139, "step": 2390 }, { "epoch": 1.12, "learning_rate": 2.962033162869983e-05, "loss": 0.3445, "step": 2400 }, { "epoch": 1.12, "learning_rate": 2.9604834960483498e-05, "loss": 0.2945, "step": 2410 }, { "epoch": 1.13, "learning_rate": 2.9589338292267162e-05, "loss": 0.7276, "step": 2420 }, { "epoch": 1.13, "learning_rate": 2.957384162405083e-05, "loss": 0.6739, "step": 2430 }, { "epoch": 1.13, "learning_rate": 2.9558344955834497e-05, "loss": 0.4468, "step": 2440 }, { "epoch": 1.14, "learning_rate": 2.9542848287618164e-05, "loss": 0.4889, "step": 2450 }, { "epoch": 1.14, "learning_rate": 2.952735161940183e-05, "loss": 0.4727, "step": 2460 }, { "epoch": 1.15, "learning_rate": 2.9511854951185496e-05, "loss": 0.5521, "step": 2470 }, { "epoch": 1.15, "learning_rate": 2.9496358282969164e-05, "loss": 0.2647, "step": 2480 }, { "epoch": 1.16, "learning_rate": 2.948086161475283e-05, "loss": 0.4498, "step": 2490 }, { "epoch": 1.16, "learning_rate": 2.9465364946536495e-05, "loss": 0.2865, "step": 2500 }, { "epoch": 1.17, "learning_rate": 2.9449868278320163e-05, "loss": 0.281, "step": 2510 }, { "epoch": 1.17, "learning_rate": 2.943437161010383e-05, "loss": 0.4023, "step": 2520 }, { "epoch": 1.18, "learning_rate": 2.9418874941887494e-05, "loss": 0.2375, "step": 2530 }, { "epoch": 1.18, "learning_rate": 2.9403378273671158e-05, "loss": 0.4883, "step": 2540 }, { "epoch": 1.19, "learning_rate": 2.9387881605454826e-05, "loss": 0.4597, "step": 2550 }, { "epoch": 1.19, "learning_rate": 2.9372384937238493e-05, "loss": 0.4231, "step": 2560 }, { "epoch": 1.19, "learning_rate": 2.935688826902216e-05, "loss": 0.1726, "step": 2570 }, { "epoch": 1.2, "learning_rate": 2.9341391600805825e-05, "loss": 0.3009, "step": 2580 }, { "epoch": 1.2, "learning_rate": 2.9325894932589492e-05, "loss": 0.6538, "step": 2590 }, { "epoch": 1.21, "learning_rate": 2.931039826437316e-05, "loss": 0.4962, "step": 2600 }, { "epoch": 1.21, "learning_rate": 2.9294901596156827e-05, "loss": 0.2876, "step": 2610 }, { "epoch": 1.22, "learning_rate": 2.9279404927940495e-05, "loss": 0.2462, "step": 2620 }, { "epoch": 1.22, "learning_rate": 2.926390825972416e-05, "loss": 0.4799, "step": 2630 }, { "epoch": 1.23, "learning_rate": 2.9248411591507826e-05, "loss": 0.4754, "step": 2640 }, { "epoch": 1.23, "learning_rate": 2.9232914923291494e-05, "loss": 0.2026, "step": 2650 }, { "epoch": 1.24, "learning_rate": 2.921741825507516e-05, "loss": 0.1991, "step": 2660 }, { "epoch": 1.24, "learning_rate": 2.9201921586858825e-05, "loss": 0.2708, "step": 2670 }, { "epoch": 1.25, "learning_rate": 2.9186424918642493e-05, "loss": 0.1851, "step": 2680 }, { "epoch": 1.25, "learning_rate": 2.917092825042616e-05, "loss": 0.4528, "step": 2690 }, { "epoch": 1.26, "learning_rate": 2.9155431582209828e-05, "loss": 0.4303, "step": 2700 }, { "epoch": 1.26, "learning_rate": 2.9139934913993492e-05, "loss": 0.3352, "step": 2710 }, { "epoch": 1.26, "learning_rate": 2.912443824577716e-05, "loss": 0.3075, "step": 2720 }, { "epoch": 1.27, "learning_rate": 2.9108941577560827e-05, "loss": 0.1506, "step": 2730 }, { "epoch": 1.27, "learning_rate": 2.9093444909344494e-05, "loss": 0.4589, "step": 2740 }, { "epoch": 1.28, "learning_rate": 2.907794824112816e-05, "loss": 0.3709, "step": 2750 }, { "epoch": 1.28, "learning_rate": 2.9062451572911826e-05, "loss": 0.4069, "step": 2760 }, { "epoch": 1.29, "learning_rate": 2.9046954904695493e-05, "loss": 0.4776, "step": 2770 }, { "epoch": 1.29, "learning_rate": 2.9031458236479158e-05, "loss": 0.5512, "step": 2780 }, { "epoch": 1.3, "learning_rate": 2.901596156826282e-05, "loss": 0.307, "step": 2790 }, { "epoch": 1.3, "learning_rate": 2.9002014566868122e-05, "loss": 0.7173, "step": 2800 }, { "epoch": 1.31, "learning_rate": 2.898651789865179e-05, "loss": 0.533, "step": 2810 }, { "epoch": 1.31, "learning_rate": 2.8971021230435457e-05, "loss": 0.382, "step": 2820 }, { "epoch": 1.32, "learning_rate": 2.8955524562219125e-05, "loss": 0.2306, "step": 2830 }, { "epoch": 1.32, "learning_rate": 2.894002789400279e-05, "loss": 0.5861, "step": 2840 }, { "epoch": 1.32, "learning_rate": 2.8924531225786456e-05, "loss": 0.4831, "step": 2850 }, { "epoch": 1.33, "learning_rate": 2.8909034557570124e-05, "loss": 0.1982, "step": 2860 }, { "epoch": 1.33, "learning_rate": 2.889353788935379e-05, "loss": 0.4137, "step": 2870 }, { "epoch": 1.34, "learning_rate": 2.887804122113746e-05, "loss": 0.2809, "step": 2880 }, { "epoch": 1.34, "learning_rate": 2.8862544552921123e-05, "loss": 0.4817, "step": 2890 }, { "epoch": 1.35, "learning_rate": 2.884704788470479e-05, "loss": 0.3055, "step": 2900 }, { "epoch": 1.35, "learning_rate": 2.8831551216488458e-05, "loss": 0.6572, "step": 2910 }, { "epoch": 1.36, "learning_rate": 2.8816054548272125e-05, "loss": 0.3695, "step": 2920 }, { "epoch": 1.36, "learning_rate": 2.880055788005579e-05, "loss": 0.1977, "step": 2930 }, { "epoch": 1.37, "learning_rate": 2.8785061211839454e-05, "loss": 0.2833, "step": 2940 }, { "epoch": 1.37, "learning_rate": 2.876956454362312e-05, "loss": 0.2818, "step": 2950 }, { "epoch": 1.38, "learning_rate": 2.875406787540679e-05, "loss": 0.4276, "step": 2960 }, { "epoch": 1.38, "learning_rate": 2.8738571207190453e-05, "loss": 0.7242, "step": 2970 }, { "epoch": 1.39, "learning_rate": 2.872307453897412e-05, "loss": 0.3649, "step": 2980 }, { "epoch": 1.39, "learning_rate": 2.8707577870757788e-05, "loss": 0.4253, "step": 2990 }, { "epoch": 1.39, "learning_rate": 2.8692081202541455e-05, "loss": 0.5493, "step": 3000 }, { "epoch": 1.4, "learning_rate": 2.867658453432512e-05, "loss": 0.1422, "step": 3010 }, { "epoch": 1.4, "learning_rate": 2.8661087866108787e-05, "loss": 0.2176, "step": 3020 }, { "epoch": 1.41, "learning_rate": 2.8645591197892454e-05, "loss": 0.2307, "step": 3030 }, { "epoch": 1.41, "learning_rate": 2.863009452967612e-05, "loss": 0.3336, "step": 3040 }, { "epoch": 1.42, "learning_rate": 2.8614597861459786e-05, "loss": 0.4291, "step": 3050 }, { "epoch": 1.42, "learning_rate": 2.8599101193243453e-05, "loss": 0.0654, "step": 3060 }, { "epoch": 1.43, "learning_rate": 2.858360452502712e-05, "loss": 0.3041, "step": 3070 }, { "epoch": 1.43, "learning_rate": 2.8568107856810788e-05, "loss": 0.4646, "step": 3080 }, { "epoch": 1.44, "learning_rate": 2.8552611188594452e-05, "loss": 0.399, "step": 3090 }, { "epoch": 1.44, "learning_rate": 2.853711452037812e-05, "loss": 0.2304, "step": 3100 }, { "epoch": 1.45, "learning_rate": 2.8521617852161787e-05, "loss": 0.3793, "step": 3110 }, { "epoch": 1.45, "learning_rate": 2.8506121183945455e-05, "loss": 0.125, "step": 3120 }, { "epoch": 1.46, "learning_rate": 2.849062451572912e-05, "loss": 0.4181, "step": 3130 }, { "epoch": 1.46, "learning_rate": 2.8475127847512786e-05, "loss": 0.37, "step": 3140 }, { "epoch": 1.46, "learning_rate": 2.8459631179296454e-05, "loss": 0.501, "step": 3150 }, { "epoch": 1.47, "learning_rate": 2.844413451108012e-05, "loss": 0.5434, "step": 3160 }, { "epoch": 1.47, "learning_rate": 2.8428637842863785e-05, "loss": 0.4125, "step": 3170 }, { "epoch": 1.48, "learning_rate": 2.841314117464745e-05, "loss": 0.4479, "step": 3180 }, { "epoch": 1.48, "learning_rate": 2.8397644506431117e-05, "loss": 0.2616, "step": 3190 }, { "epoch": 1.49, "learning_rate": 2.8382147838214784e-05, "loss": 0.3377, "step": 3200 }, { "epoch": 1.49, "learning_rate": 2.836665116999845e-05, "loss": 0.375, "step": 3210 }, { "epoch": 1.5, "learning_rate": 2.8351154501782116e-05, "loss": 0.585, "step": 3220 }, { "epoch": 1.5, "learning_rate": 2.8335657833565784e-05, "loss": 0.5077, "step": 3230 }, { "epoch": 1.51, "learning_rate": 2.832016116534945e-05, "loss": 0.2332, "step": 3240 }, { "epoch": 1.51, "learning_rate": 2.8304664497133115e-05, "loss": 0.4414, "step": 3250 }, { "epoch": 1.52, "learning_rate": 2.8289167828916783e-05, "loss": 0.2384, "step": 3260 }, { "epoch": 1.52, "learning_rate": 2.827367116070045e-05, "loss": 0.3747, "step": 3270 }, { "epoch": 1.52, "learning_rate": 2.8258174492484118e-05, "loss": 0.2938, "step": 3280 }, { "epoch": 1.53, "learning_rate": 2.824267782426778e-05, "loss": 0.3634, "step": 3290 }, { "epoch": 1.53, "learning_rate": 2.822718115605145e-05, "loss": 0.2502, "step": 3300 }, { "epoch": 1.54, "learning_rate": 2.8211684487835117e-05, "loss": 0.3573, "step": 3310 }, { "epoch": 1.54, "learning_rate": 2.8196187819618784e-05, "loss": 0.3062, "step": 3320 }, { "epoch": 1.55, "learning_rate": 2.8180691151402448e-05, "loss": 0.3654, "step": 3330 }, { "epoch": 1.55, "learning_rate": 2.8165194483186116e-05, "loss": 0.2654, "step": 3340 }, { "epoch": 1.56, "learning_rate": 2.8149697814969783e-05, "loss": 0.1328, "step": 3350 }, { "epoch": 1.56, "learning_rate": 2.813420114675345e-05, "loss": 0.4447, "step": 3360 }, { "epoch": 1.57, "learning_rate": 2.8118704478537115e-05, "loss": 0.3217, "step": 3370 }, { "epoch": 1.57, "learning_rate": 2.8103207810320782e-05, "loss": 0.1941, "step": 3380 }, { "epoch": 1.58, "learning_rate": 2.808771114210445e-05, "loss": 0.5132, "step": 3390 }, { "epoch": 1.58, "learning_rate": 2.8072214473888117e-05, "loss": 0.4109, "step": 3400 }, { "epoch": 1.59, "learning_rate": 2.805671780567178e-05, "loss": 0.503, "step": 3410 }, { "epoch": 1.59, "learning_rate": 2.804122113745545e-05, "loss": 0.259, "step": 3420 }, { "epoch": 1.59, "learning_rate": 2.8025724469239113e-05, "loss": 0.1918, "step": 3430 }, { "epoch": 1.6, "learning_rate": 2.801022780102278e-05, "loss": 0.3181, "step": 3440 }, { "epoch": 1.6, "learning_rate": 2.7994731132806444e-05, "loss": 0.1778, "step": 3450 }, { "epoch": 1.61, "learning_rate": 2.7979234464590112e-05, "loss": 0.354, "step": 3460 }, { "epoch": 1.61, "learning_rate": 2.796373779637378e-05, "loss": 0.718, "step": 3470 }, { "epoch": 1.62, "learning_rate": 2.7948241128157447e-05, "loss": 0.2096, "step": 3480 }, { "epoch": 1.62, "learning_rate": 2.793274445994111e-05, "loss": 0.5214, "step": 3490 }, { "epoch": 1.63, "learning_rate": 2.791724779172478e-05, "loss": 0.2787, "step": 3500 }, { "epoch": 1.63, "learning_rate": 2.7901751123508446e-05, "loss": 0.2631, "step": 3510 }, { "epoch": 1.64, "learning_rate": 2.7886254455292113e-05, "loss": 0.3894, "step": 3520 }, { "epoch": 1.64, "learning_rate": 2.7870757787075778e-05, "loss": 0.4931, "step": 3530 }, { "epoch": 1.65, "learning_rate": 2.7855261118859445e-05, "loss": 0.2916, "step": 3540 }, { "epoch": 1.65, "learning_rate": 2.7839764450643113e-05, "loss": 0.3037, "step": 3550 }, { "epoch": 1.66, "learning_rate": 2.782426778242678e-05, "loss": 0.3069, "step": 3560 }, { "epoch": 1.66, "learning_rate": 2.7808771114210444e-05, "loss": 0.2568, "step": 3570 }, { "epoch": 1.66, "learning_rate": 2.779327444599411e-05, "loss": 0.4131, "step": 3580 }, { "epoch": 1.67, "learning_rate": 2.777777777777778e-05, "loss": 0.2753, "step": 3590 }, { "epoch": 1.67, "learning_rate": 2.7762281109561447e-05, "loss": 0.5791, "step": 3600 }, { "epoch": 1.68, "learning_rate": 2.774678444134511e-05, "loss": 0.2685, "step": 3610 }, { "epoch": 1.68, "learning_rate": 2.7731287773128778e-05, "loss": 0.2439, "step": 3620 }, { "epoch": 1.69, "learning_rate": 2.7715791104912446e-05, "loss": 0.6156, "step": 3630 }, { "epoch": 1.69, "learning_rate": 2.7700294436696113e-05, "loss": 0.4206, "step": 3640 }, { "epoch": 1.7, "learning_rate": 2.7684797768479777e-05, "loss": 0.2462, "step": 3650 }, { "epoch": 1.7, "learning_rate": 2.7669301100263445e-05, "loss": 0.3283, "step": 3660 }, { "epoch": 1.71, "learning_rate": 2.7653804432047112e-05, "loss": 0.4734, "step": 3670 }, { "epoch": 1.71, "learning_rate": 2.7638307763830776e-05, "loss": 0.3934, "step": 3680 }, { "epoch": 1.72, "learning_rate": 2.762281109561444e-05, "loss": 0.2597, "step": 3690 }, { "epoch": 1.72, "learning_rate": 2.7607314427398108e-05, "loss": 0.482, "step": 3700 }, { "epoch": 1.72, "learning_rate": 2.7591817759181775e-05, "loss": 0.1531, "step": 3710 }, { "epoch": 1.73, "learning_rate": 2.7576321090965443e-05, "loss": 0.3001, "step": 3720 }, { "epoch": 1.73, "learning_rate": 2.756082442274911e-05, "loss": 0.3956, "step": 3730 }, { "epoch": 1.74, "learning_rate": 2.7545327754532774e-05, "loss": 0.1822, "step": 3740 }, { "epoch": 1.74, "learning_rate": 2.7529831086316442e-05, "loss": 0.5104, "step": 3750 }, { "epoch": 1.75, "learning_rate": 2.751433441810011e-05, "loss": 0.4782, "step": 3760 }, { "epoch": 1.75, "learning_rate": 2.7498837749883777e-05, "loss": 0.3576, "step": 3770 }, { "epoch": 1.76, "learning_rate": 2.748334108166744e-05, "loss": 0.3221, "step": 3780 }, { "epoch": 1.76, "learning_rate": 2.746784441345111e-05, "loss": 0.3456, "step": 3790 }, { "epoch": 1.77, "learning_rate": 2.7452347745234776e-05, "loss": 0.501, "step": 3800 }, { "epoch": 1.77, "learning_rate": 2.7436851077018443e-05, "loss": 0.2229, "step": 3810 }, { "epoch": 1.78, "learning_rate": 2.7421354408802108e-05, "loss": 0.2876, "step": 3820 }, { "epoch": 1.78, "learning_rate": 2.7405857740585775e-05, "loss": 0.3996, "step": 3830 }, { "epoch": 1.79, "learning_rate": 2.7390361072369443e-05, "loss": 0.3382, "step": 3840 }, { "epoch": 1.79, "learning_rate": 2.737486440415311e-05, "loss": 0.2938, "step": 3850 }, { "epoch": 1.79, "learning_rate": 2.7359367735936774e-05, "loss": 0.2648, "step": 3860 }, { "epoch": 1.8, "learning_rate": 2.734387106772044e-05, "loss": 0.2285, "step": 3870 }, { "epoch": 1.8, "learning_rate": 2.732837439950411e-05, "loss": 0.3115, "step": 3880 }, { "epoch": 1.81, "learning_rate": 2.7312877731287777e-05, "loss": 0.5288, "step": 3890 }, { "epoch": 1.81, "learning_rate": 2.729738106307144e-05, "loss": 0.1673, "step": 3900 }, { "epoch": 1.82, "learning_rate": 2.7281884394855108e-05, "loss": 0.3358, "step": 3910 }, { "epoch": 1.82, "learning_rate": 2.7266387726638776e-05, "loss": 0.5848, "step": 3920 }, { "epoch": 1.83, "learning_rate": 2.725089105842244e-05, "loss": 0.3806, "step": 3930 }, { "epoch": 1.83, "learning_rate": 2.7235394390206104e-05, "loss": 0.2968, "step": 3940 }, { "epoch": 1.84, "learning_rate": 2.721989772198977e-05, "loss": 0.2995, "step": 3950 }, { "epoch": 1.84, "learning_rate": 2.720440105377344e-05, "loss": 0.3624, "step": 3960 }, { "epoch": 1.85, "learning_rate": 2.7188904385557106e-05, "loss": 0.2398, "step": 3970 }, { "epoch": 1.85, "learning_rate": 2.717340771734077e-05, "loss": 0.3253, "step": 3980 }, { "epoch": 1.85, "learning_rate": 2.7157911049124438e-05, "loss": 0.2992, "step": 3990 }, { "epoch": 1.86, "learning_rate": 2.7142414380908105e-05, "loss": 0.5173, "step": 4000 }, { "epoch": 1.86, "learning_rate": 2.7126917712691773e-05, "loss": 0.2939, "step": 4010 }, { "epoch": 1.87, "learning_rate": 2.7111421044475437e-05, "loss": 0.519, "step": 4020 }, { "epoch": 1.87, "learning_rate": 2.7095924376259104e-05, "loss": 0.4549, "step": 4030 }, { "epoch": 1.88, "learning_rate": 2.7080427708042772e-05, "loss": 0.2915, "step": 4040 }, { "epoch": 1.88, "learning_rate": 2.706493103982644e-05, "loss": 0.4378, "step": 4050 }, { "epoch": 1.89, "learning_rate": 2.7049434371610103e-05, "loss": 0.3109, "step": 4060 }, { "epoch": 1.89, "learning_rate": 2.703393770339377e-05, "loss": 0.5096, "step": 4070 }, { "epoch": 1.9, "learning_rate": 2.701844103517744e-05, "loss": 0.3356, "step": 4080 }, { "epoch": 1.9, "learning_rate": 2.7002944366961106e-05, "loss": 0.3959, "step": 4090 }, { "epoch": 1.91, "learning_rate": 2.698744769874477e-05, "loss": 0.499, "step": 4100 }, { "epoch": 1.91, "learning_rate": 2.6971951030528437e-05, "loss": 0.3222, "step": 4110 }, { "epoch": 1.92, "learning_rate": 2.6956454362312105e-05, "loss": 0.3265, "step": 4120 }, { "epoch": 1.92, "learning_rate": 2.6940957694095772e-05, "loss": 0.2492, "step": 4130 }, { "epoch": 1.92, "learning_rate": 2.6925461025879437e-05, "loss": 0.6622, "step": 4140 }, { "epoch": 1.93, "learning_rate": 2.6909964357663104e-05, "loss": 0.2932, "step": 4150 }, { "epoch": 1.93, "learning_rate": 2.689446768944677e-05, "loss": 0.8129, "step": 4160 }, { "epoch": 1.94, "learning_rate": 2.687897102123044e-05, "loss": 0.1074, "step": 4170 }, { "epoch": 1.94, "learning_rate": 2.68634743530141e-05, "loss": 0.1133, "step": 4180 }, { "epoch": 1.95, "learning_rate": 2.6847977684797767e-05, "loss": 0.4516, "step": 4190 }, { "epoch": 1.95, "learning_rate": 2.6832481016581435e-05, "loss": 0.3812, "step": 4200 }, { "epoch": 1.96, "learning_rate": 2.6816984348365102e-05, "loss": 0.2656, "step": 4210 }, { "epoch": 1.96, "learning_rate": 2.6801487680148766e-05, "loss": 0.1742, "step": 4220 }, { "epoch": 1.97, "learning_rate": 2.6785991011932434e-05, "loss": 0.3687, "step": 4230 }, { "epoch": 1.97, "learning_rate": 2.67704943437161e-05, "loss": 0.3627, "step": 4240 }, { "epoch": 1.98, "learning_rate": 2.675499767549977e-05, "loss": 0.0979, "step": 4250 }, { "epoch": 1.98, "learning_rate": 2.6739501007283433e-05, "loss": 0.2193, "step": 4260 }, { "epoch": 1.99, "learning_rate": 2.67240043390671e-05, "loss": 0.1529, "step": 4270 }, { "epoch": 1.99, "learning_rate": 2.6708507670850768e-05, "loss": 0.4351, "step": 4280 }, { "epoch": 1.99, "learning_rate": 2.6693011002634435e-05, "loss": 0.3699, "step": 4290 }, { "epoch": 2.0, "learning_rate": 2.66775143344181e-05, "loss": 0.4323, "step": 4300 }, { "epoch": 2.0, "eval_accuracy": 0.9562067830095489, "eval_loss": 0.2042698711156845, "eval_runtime": 17.0558, "eval_samples_per_second": 178.063, "eval_steps_per_second": 44.56, "step": 4302 }, { "epoch": 2.0, "learning_rate": 2.6662017666201767e-05, "loss": 0.4572, "step": 4310 }, { "epoch": 2.01, "learning_rate": 2.6646520997985434e-05, "loss": 0.2285, "step": 4320 }, { "epoch": 2.01, "learning_rate": 2.6631024329769102e-05, "loss": 0.1455, "step": 4330 }, { "epoch": 2.02, "learning_rate": 2.6615527661552766e-05, "loss": 0.2543, "step": 4340 }, { "epoch": 2.02, "learning_rate": 2.6600030993336433e-05, "loss": 0.2346, "step": 4350 }, { "epoch": 2.03, "learning_rate": 2.65845343251201e-05, "loss": 0.1568, "step": 4360 }, { "epoch": 2.03, "learning_rate": 2.656903765690377e-05, "loss": 0.3764, "step": 4370 }, { "epoch": 2.04, "learning_rate": 2.6553540988687432e-05, "loss": 0.1831, "step": 4380 }, { "epoch": 2.04, "learning_rate": 2.65380443204711e-05, "loss": 0.8255, "step": 4390 }, { "epoch": 2.05, "learning_rate": 2.6522547652254767e-05, "loss": 0.339, "step": 4400 }, { "epoch": 2.05, "learning_rate": 2.6507050984038435e-05, "loss": 0.3125, "step": 4410 }, { "epoch": 2.05, "learning_rate": 2.64915543158221e-05, "loss": 0.2821, "step": 4420 }, { "epoch": 2.06, "learning_rate": 2.6476057647605763e-05, "loss": 0.5594, "step": 4430 }, { "epoch": 2.06, "learning_rate": 2.646056097938943e-05, "loss": 0.2578, "step": 4440 }, { "epoch": 2.07, "learning_rate": 2.6445064311173098e-05, "loss": 0.2428, "step": 4450 }, { "epoch": 2.07, "learning_rate": 2.6429567642956762e-05, "loss": 0.2537, "step": 4460 }, { "epoch": 2.08, "learning_rate": 2.641407097474043e-05, "loss": 0.2695, "step": 4470 }, { "epoch": 2.08, "learning_rate": 2.6398574306524097e-05, "loss": 0.3818, "step": 4480 }, { "epoch": 2.09, "learning_rate": 2.6383077638307765e-05, "loss": 0.418, "step": 4490 }, { "epoch": 2.09, "learning_rate": 2.636758097009143e-05, "loss": 0.5186, "step": 4500 }, { "epoch": 2.1, "learning_rate": 2.6352084301875096e-05, "loss": 0.1777, "step": 4510 }, { "epoch": 2.1, "learning_rate": 2.6336587633658764e-05, "loss": 0.3769, "step": 4520 }, { "epoch": 2.11, "learning_rate": 2.632109096544243e-05, "loss": 0.4497, "step": 4530 }, { "epoch": 2.11, "learning_rate": 2.6305594297226095e-05, "loss": 0.3411, "step": 4540 }, { "epoch": 2.12, "learning_rate": 2.6290097629009763e-05, "loss": 0.4039, "step": 4550 }, { "epoch": 2.12, "learning_rate": 2.627460096079343e-05, "loss": 0.424, "step": 4560 }, { "epoch": 2.12, "learning_rate": 2.6259104292577098e-05, "loss": 0.1011, "step": 4570 }, { "epoch": 2.13, "learning_rate": 2.6243607624360762e-05, "loss": 0.1579, "step": 4580 }, { "epoch": 2.13, "learning_rate": 2.622811095614443e-05, "loss": 0.4541, "step": 4590 }, { "epoch": 2.14, "learning_rate": 2.6212614287928097e-05, "loss": 0.4715, "step": 4600 }, { "epoch": 2.14, "learning_rate": 2.6197117619711764e-05, "loss": 0.2024, "step": 4610 }, { "epoch": 2.15, "learning_rate": 2.6181620951495432e-05, "loss": 0.1076, "step": 4620 }, { "epoch": 2.15, "learning_rate": 2.6166124283279096e-05, "loss": 0.284, "step": 4630 }, { "epoch": 2.16, "learning_rate": 2.6150627615062763e-05, "loss": 0.2174, "step": 4640 }, { "epoch": 2.16, "learning_rate": 2.613513094684643e-05, "loss": 0.2124, "step": 4650 }, { "epoch": 2.17, "learning_rate": 2.6119634278630098e-05, "loss": 0.3909, "step": 4660 }, { "epoch": 2.17, "learning_rate": 2.6104137610413762e-05, "loss": 0.2164, "step": 4670 }, { "epoch": 2.18, "learning_rate": 2.6088640942197426e-05, "loss": 0.1218, "step": 4680 }, { "epoch": 2.18, "learning_rate": 2.6073144273981094e-05, "loss": 0.1378, "step": 4690 }, { "epoch": 2.19, "learning_rate": 2.605764760576476e-05, "loss": 0.3855, "step": 4700 }, { "epoch": 2.19, "learning_rate": 2.6042150937548426e-05, "loss": 0.0628, "step": 4710 }, { "epoch": 2.19, "learning_rate": 2.6026654269332093e-05, "loss": 0.2678, "step": 4720 }, { "epoch": 2.2, "learning_rate": 2.601115760111576e-05, "loss": 0.1977, "step": 4730 }, { "epoch": 2.2, "learning_rate": 2.5995660932899428e-05, "loss": 0.1521, "step": 4740 }, { "epoch": 2.21, "learning_rate": 2.5980164264683092e-05, "loss": 0.4095, "step": 4750 }, { "epoch": 2.21, "learning_rate": 2.596466759646676e-05, "loss": 0.2332, "step": 4760 }, { "epoch": 2.22, "learning_rate": 2.5949170928250427e-05, "loss": 0.3119, "step": 4770 }, { "epoch": 2.22, "learning_rate": 2.5933674260034095e-05, "loss": 0.267, "step": 4780 }, { "epoch": 2.23, "learning_rate": 2.591817759181776e-05, "loss": 0.1504, "step": 4790 }, { "epoch": 2.23, "learning_rate": 2.5902680923601426e-05, "loss": 0.208, "step": 4800 }, { "epoch": 2.24, "learning_rate": 2.5887184255385094e-05, "loss": 0.4964, "step": 4810 }, { "epoch": 2.24, "learning_rate": 2.587168758716876e-05, "loss": 0.369, "step": 4820 }, { "epoch": 2.25, "learning_rate": 2.5856190918952425e-05, "loss": 0.347, "step": 4830 }, { "epoch": 2.25, "learning_rate": 2.5840694250736093e-05, "loss": 0.3967, "step": 4840 }, { "epoch": 2.25, "learning_rate": 2.582519758251976e-05, "loss": 0.2601, "step": 4850 }, { "epoch": 2.26, "learning_rate": 2.5809700914303428e-05, "loss": 0.0724, "step": 4860 }, { "epoch": 2.26, "learning_rate": 2.5794204246087092e-05, "loss": 0.2819, "step": 4870 }, { "epoch": 2.27, "learning_rate": 2.577870757787076e-05, "loss": 0.1272, "step": 4880 }, { "epoch": 2.27, "learning_rate": 2.5763210909654427e-05, "loss": 0.327, "step": 4890 }, { "epoch": 2.28, "learning_rate": 2.5747714241438094e-05, "loss": 0.6902, "step": 4900 }, { "epoch": 2.28, "learning_rate": 2.5732217573221758e-05, "loss": 0.3627, "step": 4910 }, { "epoch": 2.29, "learning_rate": 2.5716720905005426e-05, "loss": 0.2974, "step": 4920 }, { "epoch": 2.29, "learning_rate": 2.570122423678909e-05, "loss": 0.3346, "step": 4930 }, { "epoch": 2.3, "learning_rate": 2.5685727568572757e-05, "loss": 0.108, "step": 4940 }, { "epoch": 2.3, "learning_rate": 2.567023090035642e-05, "loss": 0.1823, "step": 4950 }, { "epoch": 2.31, "learning_rate": 2.565473423214009e-05, "loss": 0.301, "step": 4960 }, { "epoch": 2.31, "learning_rate": 2.5639237563923756e-05, "loss": 0.3014, "step": 4970 }, { "epoch": 2.32, "learning_rate": 2.5623740895707424e-05, "loss": 0.2479, "step": 4980 }, { "epoch": 2.32, "learning_rate": 2.5608244227491088e-05, "loss": 0.2455, "step": 4990 }, { "epoch": 2.32, "learning_rate": 2.5592747559274755e-05, "loss": 0.4883, "step": 5000 }, { "epoch": 2.33, "learning_rate": 2.5577250891058423e-05, "loss": 0.2843, "step": 5010 }, { "epoch": 2.33, "learning_rate": 2.556175422284209e-05, "loss": 0.5232, "step": 5020 }, { "epoch": 2.34, "learning_rate": 2.5546257554625755e-05, "loss": 0.1704, "step": 5030 }, { "epoch": 2.34, "learning_rate": 2.5530760886409422e-05, "loss": 0.6146, "step": 5040 }, { "epoch": 2.35, "learning_rate": 2.551526421819309e-05, "loss": 0.2083, "step": 5050 }, { "epoch": 2.35, "learning_rate": 2.5499767549976757e-05, "loss": 0.2732, "step": 5060 }, { "epoch": 2.36, "learning_rate": 2.548427088176042e-05, "loss": 0.4491, "step": 5070 }, { "epoch": 2.36, "learning_rate": 2.546877421354409e-05, "loss": 0.3135, "step": 5080 }, { "epoch": 2.37, "learning_rate": 2.5453277545327756e-05, "loss": 0.2734, "step": 5090 }, { "epoch": 2.37, "learning_rate": 2.5437780877111424e-05, "loss": 0.1615, "step": 5100 }, { "epoch": 2.38, "learning_rate": 2.5422284208895088e-05, "loss": 0.2685, "step": 5110 }, { "epoch": 2.38, "learning_rate": 2.5406787540678755e-05, "loss": 0.4313, "step": 5120 }, { "epoch": 2.38, "learning_rate": 2.5391290872462423e-05, "loss": 0.3828, "step": 5130 }, { "epoch": 2.39, "learning_rate": 2.537579420424609e-05, "loss": 0.1468, "step": 5140 }, { "epoch": 2.39, "learning_rate": 2.5360297536029754e-05, "loss": 0.1752, "step": 5150 }, { "epoch": 2.4, "learning_rate": 2.534480086781342e-05, "loss": 0.3589, "step": 5160 }, { "epoch": 2.4, "learning_rate": 2.532930419959709e-05, "loss": 0.2682, "step": 5170 }, { "epoch": 2.41, "learning_rate": 2.5313807531380753e-05, "loss": 0.4267, "step": 5180 }, { "epoch": 2.41, "learning_rate": 2.5298310863164417e-05, "loss": 0.2382, "step": 5190 }, { "epoch": 2.42, "learning_rate": 2.5282814194948085e-05, "loss": 0.2842, "step": 5200 }, { "epoch": 2.42, "learning_rate": 2.5267317526731752e-05, "loss": 0.2339, "step": 5210 }, { "epoch": 2.43, "learning_rate": 2.525182085851542e-05, "loss": 0.2628, "step": 5220 }, { "epoch": 2.43, "learning_rate": 2.5236324190299084e-05, "loss": 0.4855, "step": 5230 }, { "epoch": 2.44, "learning_rate": 2.522082752208275e-05, "loss": 0.2352, "step": 5240 }, { "epoch": 2.44, "learning_rate": 2.520533085386642e-05, "loss": 0.1419, "step": 5250 }, { "epoch": 2.45, "learning_rate": 2.5189834185650086e-05, "loss": 1.0735, "step": 5260 }, { "epoch": 2.45, "learning_rate": 2.517433751743375e-05, "loss": 0.5396, "step": 5270 }, { "epoch": 2.45, "learning_rate": 2.5158840849217418e-05, "loss": 0.3396, "step": 5280 }, { "epoch": 2.46, "learning_rate": 2.5143344181001085e-05, "loss": 0.4928, "step": 5290 }, { "epoch": 2.46, "learning_rate": 2.5127847512784753e-05, "loss": 0.1598, "step": 5300 }, { "epoch": 2.47, "learning_rate": 2.5112350844568417e-05, "loss": 0.4678, "step": 5310 }, { "epoch": 2.47, "learning_rate": 2.5096854176352085e-05, "loss": 0.359, "step": 5320 }, { "epoch": 2.48, "learning_rate": 2.5081357508135752e-05, "loss": 0.2221, "step": 5330 }, { "epoch": 2.48, "learning_rate": 2.506586083991942e-05, "loss": 0.1983, "step": 5340 }, { "epoch": 2.49, "learning_rate": 2.5050364171703084e-05, "loss": 0.4923, "step": 5350 }, { "epoch": 2.49, "learning_rate": 2.503486750348675e-05, "loss": 0.103, "step": 5360 }, { "epoch": 2.5, "learning_rate": 2.501937083527042e-05, "loss": 0.1654, "step": 5370 }, { "epoch": 2.5, "learning_rate": 2.5003874167054086e-05, "loss": 0.5142, "step": 5380 }, { "epoch": 2.51, "learning_rate": 2.498837749883775e-05, "loss": 0.3632, "step": 5390 }, { "epoch": 2.51, "learning_rate": 2.4972880830621418e-05, "loss": 0.0935, "step": 5400 }, { "epoch": 2.52, "learning_rate": 2.4957384162405085e-05, "loss": 0.4564, "step": 5410 }, { "epoch": 2.52, "learning_rate": 2.4941887494188753e-05, "loss": 0.4198, "step": 5420 }, { "epoch": 2.52, "learning_rate": 2.4926390825972413e-05, "loss": 0.1952, "step": 5430 }, { "epoch": 2.53, "learning_rate": 2.491089415775608e-05, "loss": 0.3286, "step": 5440 }, { "epoch": 2.53, "learning_rate": 2.4895397489539748e-05, "loss": 0.2146, "step": 5450 }, { "epoch": 2.54, "learning_rate": 2.4879900821323416e-05, "loss": 0.3435, "step": 5460 }, { "epoch": 2.54, "learning_rate": 2.4864404153107083e-05, "loss": 0.3927, "step": 5470 }, { "epoch": 2.55, "learning_rate": 2.4848907484890747e-05, "loss": 0.3311, "step": 5480 }, { "epoch": 2.55, "learning_rate": 2.4833410816674415e-05, "loss": 0.3258, "step": 5490 }, { "epoch": 2.56, "learning_rate": 2.4817914148458082e-05, "loss": 0.2766, "step": 5500 }, { "epoch": 2.56, "learning_rate": 2.480241748024175e-05, "loss": 0.311, "step": 5510 }, { "epoch": 2.57, "learning_rate": 2.4786920812025414e-05, "loss": 0.5541, "step": 5520 }, { "epoch": 2.57, "learning_rate": 2.477142414380908e-05, "loss": 0.2717, "step": 5530 }, { "epoch": 2.58, "learning_rate": 2.475592747559275e-05, "loss": 0.2383, "step": 5540 }, { "epoch": 2.58, "learning_rate": 2.4740430807376416e-05, "loss": 0.1974, "step": 5550 }, { "epoch": 2.58, "learning_rate": 2.472493413916008e-05, "loss": 0.3493, "step": 5560 }, { "epoch": 2.59, "learning_rate": 2.4709437470943748e-05, "loss": 0.4594, "step": 5570 }, { "epoch": 2.59, "learning_rate": 2.4693940802727415e-05, "loss": 0.3031, "step": 5580 }, { "epoch": 2.6, "learning_rate": 2.4678444134511083e-05, "loss": 0.1899, "step": 5590 }, { "epoch": 2.6, "learning_rate": 2.4662947466294747e-05, "loss": 0.2106, "step": 5600 }, { "epoch": 2.61, "learning_rate": 2.4647450798078414e-05, "loss": 0.366, "step": 5610 }, { "epoch": 2.61, "learning_rate": 2.4631954129862082e-05, "loss": 0.173, "step": 5620 }, { "epoch": 2.62, "learning_rate": 2.461645746164575e-05, "loss": 0.286, "step": 5630 }, { "epoch": 2.62, "learning_rate": 2.4600960793429414e-05, "loss": 0.3543, "step": 5640 }, { "epoch": 2.63, "learning_rate": 2.458546412521308e-05, "loss": 0.3302, "step": 5650 }, { "epoch": 2.63, "learning_rate": 2.456996745699675e-05, "loss": 0.3367, "step": 5660 }, { "epoch": 2.64, "learning_rate": 2.4554470788780416e-05, "loss": 0.3913, "step": 5670 }, { "epoch": 2.64, "learning_rate": 2.4538974120564077e-05, "loss": 0.421, "step": 5680 }, { "epoch": 2.65, "learning_rate": 2.4523477452347744e-05, "loss": 0.4009, "step": 5690 }, { "epoch": 2.65, "learning_rate": 2.450798078413141e-05, "loss": 0.1738, "step": 5700 }, { "epoch": 2.65, "learning_rate": 2.449248411591508e-05, "loss": 0.2611, "step": 5710 }, { "epoch": 2.66, "learning_rate": 2.4476987447698743e-05, "loss": 0.4684, "step": 5720 }, { "epoch": 2.66, "learning_rate": 2.446149077948241e-05, "loss": 0.2115, "step": 5730 }, { "epoch": 2.67, "learning_rate": 2.4445994111266078e-05, "loss": 0.1809, "step": 5740 }, { "epoch": 2.67, "learning_rate": 2.4430497443049746e-05, "loss": 0.2061, "step": 5750 }, { "epoch": 2.68, "learning_rate": 2.441500077483341e-05, "loss": 0.3943, "step": 5760 }, { "epoch": 2.68, "learning_rate": 2.4399504106617077e-05, "loss": 0.3, "step": 5770 }, { "epoch": 2.69, "learning_rate": 2.4384007438400745e-05, "loss": 0.222, "step": 5780 }, { "epoch": 2.69, "learning_rate": 2.4368510770184412e-05, "loss": 0.3432, "step": 5790 }, { "epoch": 2.7, "learning_rate": 2.4353014101968076e-05, "loss": 0.19, "step": 5800 }, { "epoch": 2.7, "learning_rate": 2.4337517433751744e-05, "loss": 0.323, "step": 5810 }, { "epoch": 2.71, "learning_rate": 2.432202076553541e-05, "loss": 0.3536, "step": 5820 }, { "epoch": 2.71, "learning_rate": 2.430652409731908e-05, "loss": 0.4613, "step": 5830 }, { "epoch": 2.72, "learning_rate": 2.4291027429102743e-05, "loss": 0.1771, "step": 5840 }, { "epoch": 2.72, "learning_rate": 2.427553076088641e-05, "loss": 0.3451, "step": 5850 }, { "epoch": 2.72, "learning_rate": 2.4260034092670078e-05, "loss": 0.2012, "step": 5860 }, { "epoch": 2.73, "learning_rate": 2.4244537424453745e-05, "loss": 0.3176, "step": 5870 }, { "epoch": 2.73, "learning_rate": 2.422904075623741e-05, "loss": 0.2653, "step": 5880 }, { "epoch": 2.74, "learning_rate": 2.4213544088021077e-05, "loss": 0.3311, "step": 5890 }, { "epoch": 2.74, "learning_rate": 2.4198047419804744e-05, "loss": 0.1197, "step": 5900 }, { "epoch": 2.75, "learning_rate": 2.4182550751588412e-05, "loss": 0.1639, "step": 5910 }, { "epoch": 2.75, "learning_rate": 2.4167054083372076e-05, "loss": 0.4772, "step": 5920 }, { "epoch": 2.76, "learning_rate": 2.415155741515574e-05, "loss": 0.2448, "step": 5930 }, { "epoch": 2.76, "learning_rate": 2.4136060746939408e-05, "loss": 0.1919, "step": 5940 }, { "epoch": 2.77, "learning_rate": 2.4120564078723075e-05, "loss": 0.1686, "step": 5950 }, { "epoch": 2.77, "learning_rate": 2.410506741050674e-05, "loss": 0.1621, "step": 5960 }, { "epoch": 2.78, "learning_rate": 2.4089570742290407e-05, "loss": 0.3617, "step": 5970 }, { "epoch": 2.78, "learning_rate": 2.4074074074074074e-05, "loss": 0.6375, "step": 5980 }, { "epoch": 2.78, "learning_rate": 2.405857740585774e-05, "loss": 0.1808, "step": 5990 }, { "epoch": 2.79, "learning_rate": 2.4043080737641406e-05, "loss": 0.2978, "step": 6000 }, { "epoch": 2.79, "learning_rate": 2.4027584069425073e-05, "loss": 0.1222, "step": 6010 }, { "epoch": 2.8, "learning_rate": 2.401208740120874e-05, "loss": 0.3246, "step": 6020 }, { "epoch": 2.8, "learning_rate": 2.3996590732992408e-05, "loss": 0.3239, "step": 6030 }, { "epoch": 2.81, "learning_rate": 2.3981094064776072e-05, "loss": 0.1893, "step": 6040 }, { "epoch": 2.81, "learning_rate": 2.396559739655974e-05, "loss": 0.2506, "step": 6050 }, { "epoch": 2.82, "learning_rate": 2.3950100728343407e-05, "loss": 0.2423, "step": 6060 }, { "epoch": 2.82, "learning_rate": 2.3934604060127075e-05, "loss": 0.6559, "step": 6070 }, { "epoch": 2.83, "learning_rate": 2.391910739191074e-05, "loss": 0.2882, "step": 6080 }, { "epoch": 2.83, "learning_rate": 2.3903610723694406e-05, "loss": 0.4461, "step": 6090 }, { "epoch": 2.84, "learning_rate": 2.3888114055478074e-05, "loss": 0.3032, "step": 6100 }, { "epoch": 2.84, "learning_rate": 2.387261738726174e-05, "loss": 0.1458, "step": 6110 }, { "epoch": 2.85, "learning_rate": 2.3857120719045405e-05, "loss": 0.296, "step": 6120 }, { "epoch": 2.85, "learning_rate": 2.3841624050829073e-05, "loss": 0.186, "step": 6130 }, { "epoch": 2.85, "learning_rate": 2.382612738261274e-05, "loss": 0.2157, "step": 6140 }, { "epoch": 2.86, "learning_rate": 2.3810630714396408e-05, "loss": 0.218, "step": 6150 }, { "epoch": 2.86, "learning_rate": 2.3795134046180072e-05, "loss": 0.3147, "step": 6160 }, { "epoch": 2.87, "learning_rate": 2.377963737796374e-05, "loss": 0.4664, "step": 6170 }, { "epoch": 2.87, "learning_rate": 2.3764140709747403e-05, "loss": 0.3786, "step": 6180 }, { "epoch": 2.88, "learning_rate": 2.374864404153107e-05, "loss": 0.1602, "step": 6190 }, { "epoch": 2.88, "learning_rate": 2.3733147373314735e-05, "loss": 0.0418, "step": 6200 }, { "epoch": 2.89, "learning_rate": 2.3717650705098403e-05, "loss": 0.2606, "step": 6210 }, { "epoch": 2.89, "learning_rate": 2.370215403688207e-05, "loss": 0.2046, "step": 6220 }, { "epoch": 2.9, "learning_rate": 2.3686657368665737e-05, "loss": 0.4652, "step": 6230 }, { "epoch": 2.9, "learning_rate": 2.36711607004494e-05, "loss": 0.3277, "step": 6240 }, { "epoch": 2.91, "learning_rate": 2.365566403223307e-05, "loss": 0.4152, "step": 6250 }, { "epoch": 2.91, "learning_rate": 2.3640167364016737e-05, "loss": 0.2766, "step": 6260 }, { "epoch": 2.91, "learning_rate": 2.3624670695800404e-05, "loss": 0.4198, "step": 6270 }, { "epoch": 2.92, "learning_rate": 2.3609174027584068e-05, "loss": 0.2715, "step": 6280 }, { "epoch": 2.92, "learning_rate": 2.3595227026189372e-05, "loss": 0.247, "step": 6290 }, { "epoch": 2.93, "learning_rate": 2.3579730357973036e-05, "loss": 0.1352, "step": 6300 }, { "epoch": 2.93, "learning_rate": 2.3564233689756704e-05, "loss": 0.2075, "step": 6310 }, { "epoch": 2.94, "learning_rate": 2.354873702154037e-05, "loss": 0.4621, "step": 6320 }, { "epoch": 2.94, "learning_rate": 2.3533240353324035e-05, "loss": 0.221, "step": 6330 }, { "epoch": 2.95, "learning_rate": 2.35177436851077e-05, "loss": 0.1743, "step": 6340 }, { "epoch": 2.95, "learning_rate": 2.3502247016891367e-05, "loss": 0.3211, "step": 6350 }, { "epoch": 2.96, "learning_rate": 2.3486750348675034e-05, "loss": 0.458, "step": 6360 }, { "epoch": 2.96, "learning_rate": 2.3471253680458702e-05, "loss": 0.1484, "step": 6370 }, { "epoch": 2.97, "learning_rate": 2.3455757012242366e-05, "loss": 0.2771, "step": 6380 }, { "epoch": 2.97, "learning_rate": 2.3440260344026034e-05, "loss": 0.3501, "step": 6390 }, { "epoch": 2.98, "learning_rate": 2.34247636758097e-05, "loss": 0.3302, "step": 6400 }, { "epoch": 2.98, "learning_rate": 2.340926700759337e-05, "loss": 0.34, "step": 6410 }, { "epoch": 2.98, "learning_rate": 2.3393770339377033e-05, "loss": 0.3771, "step": 6420 }, { "epoch": 2.99, "learning_rate": 2.33782736711607e-05, "loss": 0.1353, "step": 6430 }, { "epoch": 2.99, "learning_rate": 2.3362777002944368e-05, "loss": 0.2731, "step": 6440 }, { "epoch": 3.0, "learning_rate": 2.3347280334728035e-05, "loss": 0.4494, "step": 6450 }, { "epoch": 3.0, "eval_accuracy": 0.9644385907145209, "eval_loss": 0.16907474398612976, "eval_runtime": 17.2887, "eval_samples_per_second": 175.664, "eval_steps_per_second": 43.959, "step": 6453 }, { "epoch": 3.0, "learning_rate": 2.33317836665117e-05, "loss": 0.4246, "step": 6460 }, { "epoch": 3.01, "learning_rate": 2.3316286998295367e-05, "loss": 0.2103, "step": 6470 }, { "epoch": 3.01, "learning_rate": 2.3300790330079034e-05, "loss": 0.4987, "step": 6480 }, { "epoch": 3.02, "learning_rate": 2.32852936618627e-05, "loss": 0.2063, "step": 6490 }, { "epoch": 3.02, "learning_rate": 2.3269796993646366e-05, "loss": 0.1851, "step": 6500 }, { "epoch": 3.03, "learning_rate": 2.3254300325430033e-05, "loss": 0.1201, "step": 6510 }, { "epoch": 3.03, "learning_rate": 2.32388036572137e-05, "loss": 0.3403, "step": 6520 }, { "epoch": 3.04, "learning_rate": 2.3223306988997368e-05, "loss": 0.0493, "step": 6530 }, { "epoch": 3.04, "learning_rate": 2.3207810320781032e-05, "loss": 0.2367, "step": 6540 }, { "epoch": 3.05, "learning_rate": 2.31923136525647e-05, "loss": 0.2026, "step": 6550 }, { "epoch": 3.05, "learning_rate": 2.3176816984348367e-05, "loss": 0.1488, "step": 6560 }, { "epoch": 3.05, "learning_rate": 2.3161320316132035e-05, "loss": 0.4259, "step": 6570 }, { "epoch": 3.06, "learning_rate": 2.3145823647915695e-05, "loss": 0.2624, "step": 6580 }, { "epoch": 3.06, "learning_rate": 2.3130326979699363e-05, "loss": 0.3641, "step": 6590 }, { "epoch": 3.07, "learning_rate": 2.311483031148303e-05, "loss": 0.2493, "step": 6600 }, { "epoch": 3.07, "learning_rate": 2.3099333643266698e-05, "loss": 0.1795, "step": 6610 }, { "epoch": 3.08, "learning_rate": 2.3083836975050365e-05, "loss": 0.2637, "step": 6620 }, { "epoch": 3.08, "learning_rate": 2.306834030683403e-05, "loss": 0.2974, "step": 6630 }, { "epoch": 3.09, "learning_rate": 2.3052843638617697e-05, "loss": 0.2703, "step": 6640 }, { "epoch": 3.09, "learning_rate": 2.3037346970401364e-05, "loss": 0.3835, "step": 6650 }, { "epoch": 3.1, "learning_rate": 2.3021850302185032e-05, "loss": 0.183, "step": 6660 }, { "epoch": 3.1, "learning_rate": 2.3006353633968696e-05, "loss": 0.1776, "step": 6670 }, { "epoch": 3.11, "learning_rate": 2.2990856965752363e-05, "loss": 0.3091, "step": 6680 }, { "epoch": 3.11, "learning_rate": 2.297536029753603e-05, "loss": 0.2412, "step": 6690 }, { "epoch": 3.11, "learning_rate": 2.29598636293197e-05, "loss": 0.1943, "step": 6700 }, { "epoch": 3.12, "learning_rate": 2.2944366961103363e-05, "loss": 0.2755, "step": 6710 }, { "epoch": 3.12, "learning_rate": 2.292887029288703e-05, "loss": 0.3217, "step": 6720 }, { "epoch": 3.13, "learning_rate": 2.2913373624670698e-05, "loss": 0.365, "step": 6730 }, { "epoch": 3.13, "learning_rate": 2.2897876956454365e-05, "loss": 0.2362, "step": 6740 }, { "epoch": 3.14, "learning_rate": 2.288238028823803e-05, "loss": 0.3217, "step": 6750 }, { "epoch": 3.14, "learning_rate": 2.2866883620021697e-05, "loss": 0.1733, "step": 6760 }, { "epoch": 3.15, "learning_rate": 2.2851386951805364e-05, "loss": 0.2835, "step": 6770 }, { "epoch": 3.15, "learning_rate": 2.283589028358903e-05, "loss": 0.2699, "step": 6780 }, { "epoch": 3.16, "learning_rate": 2.2820393615372696e-05, "loss": 0.2349, "step": 6790 }, { "epoch": 3.16, "learning_rate": 2.2804896947156363e-05, "loss": 0.1391, "step": 6800 }, { "epoch": 3.17, "learning_rate": 2.278940027894003e-05, "loss": 0.277, "step": 6810 }, { "epoch": 3.17, "learning_rate": 2.2773903610723698e-05, "loss": 0.2328, "step": 6820 }, { "epoch": 3.18, "learning_rate": 2.275840694250736e-05, "loss": 0.3107, "step": 6830 }, { "epoch": 3.18, "learning_rate": 2.2742910274291026e-05, "loss": 0.4042, "step": 6840 }, { "epoch": 3.18, "learning_rate": 2.2727413606074694e-05, "loss": 0.368, "step": 6850 }, { "epoch": 3.19, "learning_rate": 2.271191693785836e-05, "loss": 0.2971, "step": 6860 }, { "epoch": 3.19, "learning_rate": 2.2696420269642025e-05, "loss": 0.393, "step": 6870 }, { "epoch": 3.2, "learning_rate": 2.2680923601425693e-05, "loss": 0.1365, "step": 6880 }, { "epoch": 3.2, "learning_rate": 2.266542693320936e-05, "loss": 0.1711, "step": 6890 }, { "epoch": 3.21, "learning_rate": 2.2649930264993028e-05, "loss": 0.1392, "step": 6900 }, { "epoch": 3.21, "learning_rate": 2.2634433596776692e-05, "loss": 0.3548, "step": 6910 }, { "epoch": 3.22, "learning_rate": 2.261893692856036e-05, "loss": 0.2115, "step": 6920 }, { "epoch": 3.22, "learning_rate": 2.2603440260344027e-05, "loss": 0.1837, "step": 6930 }, { "epoch": 3.23, "learning_rate": 2.2587943592127694e-05, "loss": 0.3216, "step": 6940 }, { "epoch": 3.23, "learning_rate": 2.257244692391136e-05, "loss": 0.2356, "step": 6950 }, { "epoch": 3.24, "learning_rate": 2.2556950255695026e-05, "loss": 0.3519, "step": 6960 }, { "epoch": 3.24, "learning_rate": 2.2541453587478693e-05, "loss": 0.2192, "step": 6970 }, { "epoch": 3.25, "learning_rate": 2.252595691926236e-05, "loss": 0.2136, "step": 6980 }, { "epoch": 3.25, "learning_rate": 2.2510460251046025e-05, "loss": 0.1826, "step": 6990 }, { "epoch": 3.25, "learning_rate": 2.2494963582829693e-05, "loss": 0.3629, "step": 7000 }, { "epoch": 3.26, "learning_rate": 2.247946691461336e-05, "loss": 0.2271, "step": 7010 }, { "epoch": 3.26, "learning_rate": 2.2463970246397027e-05, "loss": 0.0843, "step": 7020 }, { "epoch": 3.27, "learning_rate": 2.244847357818069e-05, "loss": 0.2753, "step": 7030 }, { "epoch": 3.27, "learning_rate": 2.243297690996436e-05, "loss": 0.4178, "step": 7040 }, { "epoch": 3.28, "learning_rate": 2.2417480241748027e-05, "loss": 0.0916, "step": 7050 }, { "epoch": 3.28, "learning_rate": 2.2401983573531694e-05, "loss": 0.169, "step": 7060 }, { "epoch": 3.29, "learning_rate": 2.2386486905315358e-05, "loss": 0.2955, "step": 7070 }, { "epoch": 3.29, "learning_rate": 2.2370990237099022e-05, "loss": 0.1452, "step": 7080 }, { "epoch": 3.3, "learning_rate": 2.235549356888269e-05, "loss": 0.2407, "step": 7090 }, { "epoch": 3.3, "learning_rate": 2.2339996900666357e-05, "loss": 0.1063, "step": 7100 }, { "epoch": 3.31, "learning_rate": 2.232450023245002e-05, "loss": 0.3766, "step": 7110 }, { "epoch": 3.31, "learning_rate": 2.230900356423369e-05, "loss": 0.4121, "step": 7120 }, { "epoch": 3.31, "learning_rate": 2.2293506896017356e-05, "loss": 0.1772, "step": 7130 }, { "epoch": 3.32, "learning_rate": 2.2278010227801024e-05, "loss": 0.1767, "step": 7140 }, { "epoch": 3.32, "learning_rate": 2.2262513559584688e-05, "loss": 0.3964, "step": 7150 }, { "epoch": 3.33, "learning_rate": 2.2247016891368355e-05, "loss": 0.2643, "step": 7160 }, { "epoch": 3.33, "learning_rate": 2.2231520223152023e-05, "loss": 0.3653, "step": 7170 }, { "epoch": 3.34, "learning_rate": 2.221602355493569e-05, "loss": 0.1428, "step": 7180 }, { "epoch": 3.34, "learning_rate": 2.2200526886719354e-05, "loss": 0.4344, "step": 7190 }, { "epoch": 3.35, "learning_rate": 2.2185030218503022e-05, "loss": 0.2614, "step": 7200 }, { "epoch": 3.35, "learning_rate": 2.216953355028669e-05, "loss": 0.3546, "step": 7210 }, { "epoch": 3.36, "learning_rate": 2.2154036882070357e-05, "loss": 0.295, "step": 7220 }, { "epoch": 3.36, "learning_rate": 2.213854021385402e-05, "loss": 0.1342, "step": 7230 }, { "epoch": 3.37, "learning_rate": 2.212304354563769e-05, "loss": 0.2365, "step": 7240 }, { "epoch": 3.37, "learning_rate": 2.2107546877421356e-05, "loss": 0.0508, "step": 7250 }, { "epoch": 3.38, "learning_rate": 2.2092050209205023e-05, "loss": 0.1253, "step": 7260 }, { "epoch": 3.38, "learning_rate": 2.2076553540988687e-05, "loss": 0.1935, "step": 7270 }, { "epoch": 3.38, "learning_rate": 2.2061056872772355e-05, "loss": 0.1225, "step": 7280 }, { "epoch": 3.39, "learning_rate": 2.2045560204556022e-05, "loss": 0.3626, "step": 7290 }, { "epoch": 3.39, "learning_rate": 2.203006353633969e-05, "loss": 0.1439, "step": 7300 }, { "epoch": 3.4, "learning_rate": 2.2014566868123354e-05, "loss": 0.2237, "step": 7310 }, { "epoch": 3.4, "learning_rate": 2.199907019990702e-05, "loss": 0.2407, "step": 7320 }, { "epoch": 3.41, "learning_rate": 2.1983573531690686e-05, "loss": 0.2577, "step": 7330 }, { "epoch": 3.41, "learning_rate": 2.1968076863474353e-05, "loss": 0.4271, "step": 7340 }, { "epoch": 3.42, "learning_rate": 2.1952580195258017e-05, "loss": 0.3962, "step": 7350 }, { "epoch": 3.42, "learning_rate": 2.1937083527041685e-05, "loss": 0.1657, "step": 7360 }, { "epoch": 3.43, "learning_rate": 2.1921586858825352e-05, "loss": 0.1609, "step": 7370 }, { "epoch": 3.43, "learning_rate": 2.190609019060902e-05, "loss": 0.3079, "step": 7380 }, { "epoch": 3.44, "learning_rate": 2.1890593522392684e-05, "loss": 0.1627, "step": 7390 }, { "epoch": 3.44, "learning_rate": 2.187509685417635e-05, "loss": 0.1931, "step": 7400 }, { "epoch": 3.44, "learning_rate": 2.185960018596002e-05, "loss": 0.376, "step": 7410 }, { "epoch": 3.45, "learning_rate": 2.1844103517743686e-05, "loss": 0.3854, "step": 7420 }, { "epoch": 3.45, "learning_rate": 2.182860684952735e-05, "loss": 0.6919, "step": 7430 }, { "epoch": 3.46, "learning_rate": 2.1813110181311018e-05, "loss": 0.4219, "step": 7440 }, { "epoch": 3.46, "learning_rate": 2.1797613513094685e-05, "loss": 0.2413, "step": 7450 }, { "epoch": 3.47, "learning_rate": 2.1782116844878353e-05, "loss": 0.1533, "step": 7460 }, { "epoch": 3.47, "learning_rate": 2.176662017666202e-05, "loss": 0.0551, "step": 7470 }, { "epoch": 3.48, "learning_rate": 2.1751123508445684e-05, "loss": 0.1819, "step": 7480 }, { "epoch": 3.48, "learning_rate": 2.1735626840229352e-05, "loss": 0.433, "step": 7490 }, { "epoch": 3.49, "learning_rate": 2.172013017201302e-05, "loss": 0.3456, "step": 7500 }, { "epoch": 3.49, "learning_rate": 2.1704633503796687e-05, "loss": 0.0656, "step": 7510 }, { "epoch": 3.5, "learning_rate": 2.168913683558035e-05, "loss": 0.2767, "step": 7520 }, { "epoch": 3.5, "learning_rate": 2.167364016736402e-05, "loss": 0.3476, "step": 7530 }, { "epoch": 3.51, "learning_rate": 2.1658143499147686e-05, "loss": 0.1522, "step": 7540 }, { "epoch": 3.51, "learning_rate": 2.1642646830931353e-05, "loss": 0.3101, "step": 7550 }, { "epoch": 3.51, "learning_rate": 2.1627150162715017e-05, "loss": 0.1511, "step": 7560 }, { "epoch": 3.52, "learning_rate": 2.1611653494498685e-05, "loss": 0.3927, "step": 7570 }, { "epoch": 3.52, "learning_rate": 2.159615682628235e-05, "loss": 0.1585, "step": 7580 }, { "epoch": 3.53, "learning_rate": 2.1580660158066016e-05, "loss": 0.2809, "step": 7590 }, { "epoch": 3.53, "learning_rate": 2.156516348984968e-05, "loss": 0.2061, "step": 7600 }, { "epoch": 3.54, "learning_rate": 2.1549666821633348e-05, "loss": 0.1537, "step": 7610 }, { "epoch": 3.54, "learning_rate": 2.1534170153417016e-05, "loss": 0.1988, "step": 7620 }, { "epoch": 3.55, "learning_rate": 2.1518673485200683e-05, "loss": 0.2971, "step": 7630 }, { "epoch": 3.55, "learning_rate": 2.1503176816984347e-05, "loss": 0.0679, "step": 7640 }, { "epoch": 3.56, "learning_rate": 2.1487680148768015e-05, "loss": 0.2485, "step": 7650 }, { "epoch": 3.56, "learning_rate": 2.1472183480551682e-05, "loss": 0.2727, "step": 7660 }, { "epoch": 3.57, "learning_rate": 2.145668681233535e-05, "loss": 0.1308, "step": 7670 }, { "epoch": 3.57, "learning_rate": 2.1441190144119014e-05, "loss": 0.2575, "step": 7680 }, { "epoch": 3.58, "learning_rate": 2.142569347590268e-05, "loss": 0.371, "step": 7690 }, { "epoch": 3.58, "learning_rate": 2.141019680768635e-05, "loss": 0.2831, "step": 7700 }, { "epoch": 3.58, "learning_rate": 2.1394700139470016e-05, "loss": 0.1156, "step": 7710 }, { "epoch": 3.59, "learning_rate": 2.137920347125368e-05, "loss": 0.2441, "step": 7720 }, { "epoch": 3.59, "learning_rate": 2.1363706803037348e-05, "loss": 0.351, "step": 7730 }, { "epoch": 3.6, "learning_rate": 2.1348210134821015e-05, "loss": 0.2607, "step": 7740 }, { "epoch": 3.6, "learning_rate": 2.1332713466604683e-05, "loss": 0.2863, "step": 7750 }, { "epoch": 3.61, "learning_rate": 2.1317216798388347e-05, "loss": 0.3064, "step": 7760 }, { "epoch": 3.61, "learning_rate": 2.1301720130172014e-05, "loss": 0.3971, "step": 7770 }, { "epoch": 3.62, "learning_rate": 2.1286223461955682e-05, "loss": 0.2833, "step": 7780 }, { "epoch": 3.62, "learning_rate": 2.127072679373935e-05, "loss": 0.1994, "step": 7790 }, { "epoch": 3.63, "learning_rate": 2.1255230125523013e-05, "loss": 0.3087, "step": 7800 }, { "epoch": 3.63, "learning_rate": 2.123973345730668e-05, "loss": 0.3272, "step": 7810 }, { "epoch": 3.64, "learning_rate": 2.1224236789090345e-05, "loss": 0.1855, "step": 7820 }, { "epoch": 3.64, "learning_rate": 2.1208740120874012e-05, "loss": 0.1629, "step": 7830 }, { "epoch": 3.64, "learning_rate": 2.1193243452657676e-05, "loss": 0.2977, "step": 7840 }, { "epoch": 3.65, "learning_rate": 2.1177746784441344e-05, "loss": 0.2975, "step": 7850 }, { "epoch": 3.65, "learning_rate": 2.116225011622501e-05, "loss": 0.1847, "step": 7860 }, { "epoch": 3.66, "learning_rate": 2.114675344800868e-05, "loss": 0.2838, "step": 7870 }, { "epoch": 3.66, "learning_rate": 2.1131256779792343e-05, "loss": 0.2486, "step": 7880 }, { "epoch": 3.67, "learning_rate": 2.111576011157601e-05, "loss": 0.2301, "step": 7890 }, { "epoch": 3.67, "learning_rate": 2.1100263443359678e-05, "loss": 0.3353, "step": 7900 }, { "epoch": 3.68, "learning_rate": 2.1084766775143345e-05, "loss": 0.2155, "step": 7910 }, { "epoch": 3.68, "learning_rate": 2.106927010692701e-05, "loss": 0.0853, "step": 7920 }, { "epoch": 3.69, "learning_rate": 2.1053773438710677e-05, "loss": 0.279, "step": 7930 }, { "epoch": 3.69, "learning_rate": 2.1038276770494345e-05, "loss": 0.2432, "step": 7940 }, { "epoch": 3.7, "learning_rate": 2.1022780102278012e-05, "loss": 0.2808, "step": 7950 }, { "epoch": 3.7, "learning_rate": 2.1007283434061676e-05, "loss": 0.4477, "step": 7960 }, { "epoch": 3.71, "learning_rate": 2.0991786765845344e-05, "loss": 0.2767, "step": 7970 }, { "epoch": 3.71, "learning_rate": 2.097629009762901e-05, "loss": 0.2519, "step": 7980 }, { "epoch": 3.71, "learning_rate": 2.096079342941268e-05, "loss": 0.1456, "step": 7990 }, { "epoch": 3.72, "learning_rate": 2.0945296761196343e-05, "loss": 0.081, "step": 8000 }, { "epoch": 3.72, "learning_rate": 2.092980009298001e-05, "loss": 0.2688, "step": 8010 }, { "epoch": 3.73, "learning_rate": 2.0914303424763678e-05, "loss": 0.4485, "step": 8020 }, { "epoch": 3.73, "learning_rate": 2.0898806756547345e-05, "loss": 0.1985, "step": 8030 }, { "epoch": 3.74, "learning_rate": 2.088331008833101e-05, "loss": 0.181, "step": 8040 }, { "epoch": 3.74, "learning_rate": 2.0867813420114677e-05, "loss": 0.3206, "step": 8050 }, { "epoch": 3.75, "learning_rate": 2.0852316751898344e-05, "loss": 0.266, "step": 8060 }, { "epoch": 3.75, "learning_rate": 2.0836820083682008e-05, "loss": 0.386, "step": 8070 }, { "epoch": 3.76, "learning_rate": 2.0821323415465672e-05, "loss": 0.4394, "step": 8080 }, { "epoch": 3.76, "learning_rate": 2.080582674724934e-05, "loss": 0.2419, "step": 8090 }, { "epoch": 3.77, "learning_rate": 2.0790330079033007e-05, "loss": 0.3, "step": 8100 }, { "epoch": 3.77, "learning_rate": 2.0774833410816675e-05, "loss": 0.4203, "step": 8110 }, { "epoch": 3.77, "learning_rate": 2.075933674260034e-05, "loss": 0.0996, "step": 8120 }, { "epoch": 3.78, "learning_rate": 2.0743840074384006e-05, "loss": 0.392, "step": 8130 }, { "epoch": 3.78, "learning_rate": 2.0728343406167674e-05, "loss": 0.0694, "step": 8140 }, { "epoch": 3.79, "learning_rate": 2.071284673795134e-05, "loss": 0.27, "step": 8150 }, { "epoch": 3.79, "learning_rate": 2.0697350069735005e-05, "loss": 0.1992, "step": 8160 }, { "epoch": 3.8, "learning_rate": 2.0681853401518673e-05, "loss": 0.2648, "step": 8170 }, { "epoch": 3.8, "learning_rate": 2.066635673330234e-05, "loss": 0.2639, "step": 8180 }, { "epoch": 3.81, "learning_rate": 2.0650860065086008e-05, "loss": 0.1874, "step": 8190 }, { "epoch": 3.81, "learning_rate": 2.0635363396869672e-05, "loss": 0.2049, "step": 8200 }, { "epoch": 3.82, "learning_rate": 2.061986672865334e-05, "loss": 0.1137, "step": 8210 }, { "epoch": 3.82, "learning_rate": 2.0604370060437007e-05, "loss": 0.2709, "step": 8220 }, { "epoch": 3.83, "learning_rate": 2.0588873392220674e-05, "loss": 0.0748, "step": 8230 }, { "epoch": 3.83, "learning_rate": 2.057337672400434e-05, "loss": 0.2456, "step": 8240 }, { "epoch": 3.84, "learning_rate": 2.0557880055788006e-05, "loss": 0.2471, "step": 8250 }, { "epoch": 3.84, "learning_rate": 2.0542383387571674e-05, "loss": 0.2883, "step": 8260 }, { "epoch": 3.84, "learning_rate": 2.052688671935534e-05, "loss": 0.1922, "step": 8270 }, { "epoch": 3.85, "learning_rate": 2.0511390051139005e-05, "loss": 0.2462, "step": 8280 }, { "epoch": 3.85, "learning_rate": 2.0495893382922673e-05, "loss": 0.4388, "step": 8290 }, { "epoch": 3.86, "learning_rate": 2.048039671470634e-05, "loss": 0.146, "step": 8300 }, { "epoch": 3.86, "learning_rate": 2.0464900046490008e-05, "loss": 0.3036, "step": 8310 }, { "epoch": 3.87, "learning_rate": 2.044940337827367e-05, "loss": 0.1348, "step": 8320 }, { "epoch": 3.87, "learning_rate": 2.0433906710057336e-05, "loss": 0.1958, "step": 8330 }, { "epoch": 3.88, "learning_rate": 2.0418410041841003e-05, "loss": 0.3578, "step": 8340 }, { "epoch": 3.88, "learning_rate": 2.040291337362467e-05, "loss": 0.2913, "step": 8350 }, { "epoch": 3.89, "learning_rate": 2.0387416705408338e-05, "loss": 0.3328, "step": 8360 }, { "epoch": 3.89, "learning_rate": 2.0371920037192002e-05, "loss": 0.2062, "step": 8370 }, { "epoch": 3.9, "learning_rate": 2.035642336897567e-05, "loss": 0.1622, "step": 8380 }, { "epoch": 3.9, "learning_rate": 2.0340926700759337e-05, "loss": 0.0684, "step": 8390 }, { "epoch": 3.91, "learning_rate": 2.0325430032543005e-05, "loss": 0.1468, "step": 8400 }, { "epoch": 3.91, "learning_rate": 2.030993336432667e-05, "loss": 0.2684, "step": 8410 }, { "epoch": 3.91, "learning_rate": 2.0294436696110336e-05, "loss": 0.1253, "step": 8420 }, { "epoch": 3.92, "learning_rate": 2.0278940027894004e-05, "loss": 0.0528, "step": 8430 }, { "epoch": 3.92, "learning_rate": 2.026344335967767e-05, "loss": 0.3669, "step": 8440 }, { "epoch": 3.93, "learning_rate": 2.0247946691461335e-05, "loss": 0.41, "step": 8450 }, { "epoch": 3.93, "learning_rate": 2.0232450023245003e-05, "loss": 0.2348, "step": 8460 }, { "epoch": 3.94, "learning_rate": 2.021695335502867e-05, "loss": 0.2706, "step": 8470 }, { "epoch": 3.94, "learning_rate": 2.0201456686812338e-05, "loss": 0.3618, "step": 8480 }, { "epoch": 3.95, "learning_rate": 2.0185960018596002e-05, "loss": 0.2847, "step": 8490 }, { "epoch": 3.95, "learning_rate": 2.017046335037967e-05, "loss": 0.3707, "step": 8500 }, { "epoch": 3.96, "learning_rate": 2.0154966682163337e-05, "loss": 0.1629, "step": 8510 }, { "epoch": 3.96, "learning_rate": 2.0139470013947004e-05, "loss": 0.1829, "step": 8520 }, { "epoch": 3.97, "learning_rate": 2.012397334573067e-05, "loss": 0.0678, "step": 8530 }, { "epoch": 3.97, "learning_rate": 2.0108476677514336e-05, "loss": 0.1555, "step": 8540 }, { "epoch": 3.97, "learning_rate": 2.0092980009298004e-05, "loss": 0.167, "step": 8550 }, { "epoch": 3.98, "learning_rate": 2.007748334108167e-05, "loss": 0.2657, "step": 8560 }, { "epoch": 3.98, "learning_rate": 2.0061986672865332e-05, "loss": 0.2729, "step": 8570 }, { "epoch": 3.99, "learning_rate": 2.0046490004649e-05, "loss": 0.3074, "step": 8580 }, { "epoch": 3.99, "learning_rate": 2.0030993336432667e-05, "loss": 0.3672, "step": 8590 }, { "epoch": 4.0, "learning_rate": 2.0015496668216334e-05, "loss": 0.0351, "step": 8600 }, { "epoch": 4.0, "eval_accuracy": 0.9677313137965097, "eval_loss": 0.14472757279872894, "eval_runtime": 17.3686, "eval_samples_per_second": 174.856, "eval_steps_per_second": 43.757, "step": 8604 }, { "epoch": 4.0, "learning_rate": 1.9999999999999998e-05, "loss": 0.1173, "step": 8610 }, { "epoch": 4.01, "learning_rate": 1.9984503331783666e-05, "loss": 0.3015, "step": 8620 }, { "epoch": 4.01, "learning_rate": 1.9969006663567333e-05, "loss": 0.3571, "step": 8630 }, { "epoch": 4.02, "learning_rate": 1.9953509995351e-05, "loss": 0.2678, "step": 8640 }, { "epoch": 4.02, "learning_rate": 1.9938013327134665e-05, "loss": 0.3516, "step": 8650 }, { "epoch": 4.03, "learning_rate": 1.9922516658918332e-05, "loss": 0.2841, "step": 8660 }, { "epoch": 4.03, "learning_rate": 1.9907019990702e-05, "loss": 0.2212, "step": 8670 }, { "epoch": 4.04, "learning_rate": 1.9891523322485667e-05, "loss": 0.2416, "step": 8680 }, { "epoch": 4.04, "learning_rate": 1.987602665426933e-05, "loss": 0.1888, "step": 8690 }, { "epoch": 4.04, "learning_rate": 1.9860529986053e-05, "loss": 0.3491, "step": 8700 }, { "epoch": 4.05, "learning_rate": 1.9845033317836666e-05, "loss": 0.1847, "step": 8710 }, { "epoch": 4.05, "learning_rate": 1.9829536649620334e-05, "loss": 0.2327, "step": 8720 }, { "epoch": 4.06, "learning_rate": 1.9814039981403998e-05, "loss": 0.368, "step": 8730 }, { "epoch": 4.06, "learning_rate": 1.9798543313187665e-05, "loss": 0.1673, "step": 8740 }, { "epoch": 4.07, "learning_rate": 1.9783046644971333e-05, "loss": 0.366, "step": 8750 }, { "epoch": 4.07, "learning_rate": 1.9767549976755e-05, "loss": 0.2762, "step": 8760 }, { "epoch": 4.08, "learning_rate": 1.9752053308538664e-05, "loss": 0.0122, "step": 8770 }, { "epoch": 4.08, "learning_rate": 1.9736556640322332e-05, "loss": 0.3858, "step": 8780 }, { "epoch": 4.09, "learning_rate": 1.9721059972106e-05, "loss": 0.2058, "step": 8790 }, { "epoch": 4.09, "learning_rate": 1.9705563303889667e-05, "loss": 0.1502, "step": 8800 }, { "epoch": 4.1, "learning_rate": 1.969006663567333e-05, "loss": 0.3947, "step": 8810 }, { "epoch": 4.1, "learning_rate": 1.9674569967456995e-05, "loss": 0.1435, "step": 8820 }, { "epoch": 4.11, "learning_rate": 1.9659073299240663e-05, "loss": 0.366, "step": 8830 }, { "epoch": 4.11, "learning_rate": 1.964357663102433e-05, "loss": 0.2266, "step": 8840 }, { "epoch": 4.11, "learning_rate": 1.9628079962807994e-05, "loss": 0.1253, "step": 8850 }, { "epoch": 4.12, "learning_rate": 1.961258329459166e-05, "loss": 0.1908, "step": 8860 }, { "epoch": 4.12, "learning_rate": 1.959708662637533e-05, "loss": 0.1677, "step": 8870 }, { "epoch": 4.13, "learning_rate": 1.9581589958158997e-05, "loss": 0.3631, "step": 8880 }, { "epoch": 4.13, "learning_rate": 1.956609328994266e-05, "loss": 0.2653, "step": 8890 }, { "epoch": 4.14, "learning_rate": 1.9550596621726328e-05, "loss": 0.1417, "step": 8900 }, { "epoch": 4.14, "learning_rate": 1.9535099953509996e-05, "loss": 0.1626, "step": 8910 }, { "epoch": 4.15, "learning_rate": 1.9519603285293663e-05, "loss": 0.269, "step": 8920 }, { "epoch": 4.15, "learning_rate": 1.9504106617077327e-05, "loss": 0.4557, "step": 8930 }, { "epoch": 4.16, "learning_rate": 1.9488609948860995e-05, "loss": 0.2997, "step": 8940 }, { "epoch": 4.16, "learning_rate": 1.9473113280644662e-05, "loss": 0.4433, "step": 8950 }, { "epoch": 4.17, "learning_rate": 1.945761661242833e-05, "loss": 0.446, "step": 8960 }, { "epoch": 4.17, "learning_rate": 1.9442119944211994e-05, "loss": 0.3395, "step": 8970 }, { "epoch": 4.17, "learning_rate": 1.942662327599566e-05, "loss": 0.1092, "step": 8980 }, { "epoch": 4.18, "learning_rate": 1.941112660777933e-05, "loss": 0.1988, "step": 8990 }, { "epoch": 4.18, "learning_rate": 1.9395629939562996e-05, "loss": 0.0444, "step": 9000 }, { "epoch": 4.19, "learning_rate": 1.938013327134666e-05, "loss": 0.0706, "step": 9010 }, { "epoch": 4.19, "learning_rate": 1.9364636603130328e-05, "loss": 0.1558, "step": 9020 }, { "epoch": 4.2, "learning_rate": 1.9349139934913995e-05, "loss": 0.3305, "step": 9030 }, { "epoch": 4.2, "learning_rate": 1.9333643266697663e-05, "loss": 0.3989, "step": 9040 }, { "epoch": 4.21, "learning_rate": 1.9318146598481327e-05, "loss": 0.2291, "step": 9050 }, { "epoch": 4.21, "learning_rate": 1.9302649930264994e-05, "loss": 0.392, "step": 9060 }, { "epoch": 4.22, "learning_rate": 1.928715326204866e-05, "loss": 0.2284, "step": 9070 }, { "epoch": 4.22, "learning_rate": 1.9271656593832326e-05, "loss": 0.3651, "step": 9080 }, { "epoch": 4.23, "learning_rate": 1.925615992561599e-05, "loss": 0.0411, "step": 9090 }, { "epoch": 4.23, "learning_rate": 1.9240663257399658e-05, "loss": 0.3452, "step": 9100 }, { "epoch": 4.24, "learning_rate": 1.9225166589183325e-05, "loss": 0.1801, "step": 9110 }, { "epoch": 4.24, "learning_rate": 1.9209669920966993e-05, "loss": 0.1883, "step": 9120 }, { "epoch": 4.24, "learning_rate": 1.9194173252750657e-05, "loss": 0.3017, "step": 9130 }, { "epoch": 4.25, "learning_rate": 1.9178676584534324e-05, "loss": 0.1604, "step": 9140 }, { "epoch": 4.25, "learning_rate": 1.916317991631799e-05, "loss": 0.4053, "step": 9150 }, { "epoch": 4.26, "learning_rate": 1.914768324810166e-05, "loss": 0.3137, "step": 9160 }, { "epoch": 4.26, "learning_rate": 1.9132186579885323e-05, "loss": 0.2369, "step": 9170 }, { "epoch": 4.27, "learning_rate": 1.911668991166899e-05, "loss": 0.227, "step": 9180 }, { "epoch": 4.27, "learning_rate": 1.9101193243452658e-05, "loss": 0.2225, "step": 9190 }, { "epoch": 4.28, "learning_rate": 1.9085696575236326e-05, "loss": 0.0715, "step": 9200 }, { "epoch": 4.28, "learning_rate": 1.9070199907019993e-05, "loss": 0.229, "step": 9210 }, { "epoch": 4.29, "learning_rate": 1.9054703238803657e-05, "loss": 0.1222, "step": 9220 }, { "epoch": 4.29, "learning_rate": 1.9039206570587325e-05, "loss": 0.1746, "step": 9230 }, { "epoch": 4.3, "learning_rate": 1.9023709902370992e-05, "loss": 0.2233, "step": 9240 }, { "epoch": 4.3, "learning_rate": 1.900821323415466e-05, "loss": 0.1788, "step": 9250 }, { "epoch": 4.3, "learning_rate": 1.8992716565938324e-05, "loss": 0.212, "step": 9260 }, { "epoch": 4.31, "learning_rate": 1.897721989772199e-05, "loss": 0.4573, "step": 9270 }, { "epoch": 4.31, "learning_rate": 1.896172322950566e-05, "loss": 0.2735, "step": 9280 }, { "epoch": 4.32, "learning_rate": 1.8946226561289326e-05, "loss": 0.0787, "step": 9290 }, { "epoch": 4.32, "learning_rate": 1.893072989307299e-05, "loss": 0.0995, "step": 9300 }, { "epoch": 4.33, "learning_rate": 1.8915233224856658e-05, "loss": 0.2497, "step": 9310 }, { "epoch": 4.33, "learning_rate": 1.8899736556640322e-05, "loss": 0.1778, "step": 9320 }, { "epoch": 4.34, "learning_rate": 1.888423988842399e-05, "loss": 0.1694, "step": 9330 }, { "epoch": 4.34, "learning_rate": 1.8868743220207653e-05, "loss": 0.2727, "step": 9340 }, { "epoch": 4.35, "learning_rate": 1.885324655199132e-05, "loss": 0.4632, "step": 9350 }, { "epoch": 4.35, "learning_rate": 1.883774988377499e-05, "loss": 0.3306, "step": 9360 }, { "epoch": 4.36, "learning_rate": 1.8822253215558656e-05, "loss": 0.3646, "step": 9370 }, { "epoch": 4.36, "learning_rate": 1.880675654734232e-05, "loss": 0.1806, "step": 9380 }, { "epoch": 4.37, "learning_rate": 1.8791259879125987e-05, "loss": 0.2507, "step": 9390 }, { "epoch": 4.37, "learning_rate": 1.8775763210909655e-05, "loss": 0.2634, "step": 9400 }, { "epoch": 4.37, "learning_rate": 1.8760266542693322e-05, "loss": 0.1891, "step": 9410 }, { "epoch": 4.38, "learning_rate": 1.8744769874476987e-05, "loss": 0.189, "step": 9420 }, { "epoch": 4.38, "learning_rate": 1.8729273206260654e-05, "loss": 0.2814, "step": 9430 }, { "epoch": 4.39, "learning_rate": 1.871377653804432e-05, "loss": 0.4847, "step": 9440 }, { "epoch": 4.39, "learning_rate": 1.869827986982799e-05, "loss": 0.3275, "step": 9450 }, { "epoch": 4.4, "learning_rate": 1.8682783201611653e-05, "loss": 0.3991, "step": 9460 }, { "epoch": 4.4, "learning_rate": 1.866728653339532e-05, "loss": 0.359, "step": 9470 }, { "epoch": 4.41, "learning_rate": 1.8651789865178988e-05, "loss": 0.1361, "step": 9480 }, { "epoch": 4.41, "learning_rate": 1.8636293196962656e-05, "loss": 0.4369, "step": 9490 }, { "epoch": 4.42, "learning_rate": 1.862079652874632e-05, "loss": 0.1532, "step": 9500 }, { "epoch": 4.42, "learning_rate": 1.8605299860529987e-05, "loss": 0.1969, "step": 9510 }, { "epoch": 4.43, "learning_rate": 1.8589803192313655e-05, "loss": 0.0733, "step": 9520 }, { "epoch": 4.43, "learning_rate": 1.8574306524097322e-05, "loss": 0.0648, "step": 9530 }, { "epoch": 4.44, "learning_rate": 1.8558809855880986e-05, "loss": 0.12, "step": 9540 }, { "epoch": 4.44, "learning_rate": 1.8543313187664654e-05, "loss": 0.2015, "step": 9550 }, { "epoch": 4.44, "learning_rate": 1.852781651944832e-05, "loss": 0.145, "step": 9560 }, { "epoch": 4.45, "learning_rate": 1.8512319851231985e-05, "loss": 0.2925, "step": 9570 }, { "epoch": 4.45, "learning_rate": 1.849682318301565e-05, "loss": 0.0852, "step": 9580 }, { "epoch": 4.46, "learning_rate": 1.8481326514799317e-05, "loss": 0.6667, "step": 9590 }, { "epoch": 4.46, "learning_rate": 1.8465829846582984e-05, "loss": 0.3139, "step": 9600 }, { "epoch": 4.47, "learning_rate": 1.8450333178366652e-05, "loss": 0.1729, "step": 9610 }, { "epoch": 4.47, "learning_rate": 1.8434836510150316e-05, "loss": 0.2929, "step": 9620 }, { "epoch": 4.48, "learning_rate": 1.8419339841933983e-05, "loss": 0.0262, "step": 9630 }, { "epoch": 4.48, "learning_rate": 1.840384317371765e-05, "loss": 0.1509, "step": 9640 }, { "epoch": 4.49, "learning_rate": 1.838834650550132e-05, "loss": 0.1843, "step": 9650 }, { "epoch": 4.49, "learning_rate": 1.8372849837284982e-05, "loss": 0.3832, "step": 9660 }, { "epoch": 4.5, "learning_rate": 1.835735316906865e-05, "loss": 0.1706, "step": 9670 }, { "epoch": 4.5, "learning_rate": 1.8341856500852317e-05, "loss": 0.1408, "step": 9680 }, { "epoch": 4.5, "learning_rate": 1.8326359832635985e-05, "loss": 0.1749, "step": 9690 }, { "epoch": 4.51, "learning_rate": 1.831086316441965e-05, "loss": 0.3377, "step": 9700 }, { "epoch": 4.51, "learning_rate": 1.8295366496203316e-05, "loss": 0.0584, "step": 9710 }, { "epoch": 4.52, "learning_rate": 1.8279869827986984e-05, "loss": 0.0664, "step": 9720 }, { "epoch": 4.52, "learning_rate": 1.826437315977065e-05, "loss": 0.2053, "step": 9730 }, { "epoch": 4.53, "learning_rate": 1.8248876491554316e-05, "loss": 0.0655, "step": 9740 }, { "epoch": 4.53, "learning_rate": 1.8233379823337983e-05, "loss": 0.2331, "step": 9750 }, { "epoch": 4.54, "learning_rate": 1.821788315512165e-05, "loss": 0.227, "step": 9760 }, { "epoch": 4.54, "learning_rate": 1.8202386486905318e-05, "loss": 0.2126, "step": 9770 }, { "epoch": 4.55, "learning_rate": 1.8186889818688982e-05, "loss": 0.1872, "step": 9780 }, { "epoch": 4.55, "learning_rate": 1.817139315047265e-05, "loss": 0.3639, "step": 9790 }, { "epoch": 4.56, "learning_rate": 1.8155896482256317e-05, "loss": 0.2239, "step": 9800 }, { "epoch": 4.56, "learning_rate": 1.8140399814039985e-05, "loss": 0.1346, "step": 9810 }, { "epoch": 4.57, "learning_rate": 1.8124903145823645e-05, "loss": 0.1937, "step": 9820 }, { "epoch": 4.57, "learning_rate": 1.8109406477607313e-05, "loss": 0.1042, "step": 9830 }, { "epoch": 4.57, "learning_rate": 1.809390980939098e-05, "loss": 0.3263, "step": 9840 }, { "epoch": 4.58, "learning_rate": 1.8078413141174648e-05, "loss": 0.2908, "step": 9850 }, { "epoch": 4.58, "learning_rate": 1.8062916472958312e-05, "loss": 0.1898, "step": 9860 }, { "epoch": 4.59, "learning_rate": 1.804741980474198e-05, "loss": 0.0576, "step": 9870 }, { "epoch": 4.59, "learning_rate": 1.8031923136525647e-05, "loss": 0.2679, "step": 9880 }, { "epoch": 4.6, "learning_rate": 1.8016426468309314e-05, "loss": 0.219, "step": 9890 }, { "epoch": 4.6, "learning_rate": 1.800092980009298e-05, "loss": 0.1807, "step": 9900 }, { "epoch": 4.61, "learning_rate": 1.7985433131876646e-05, "loss": 0.1964, "step": 9910 }, { "epoch": 4.61, "learning_rate": 1.7969936463660313e-05, "loss": 0.192, "step": 9920 }, { "epoch": 4.62, "learning_rate": 1.795443979544398e-05, "loss": 0.35, "step": 9930 }, { "epoch": 4.62, "learning_rate": 1.7938943127227645e-05, "loss": 0.2089, "step": 9940 }, { "epoch": 4.63, "learning_rate": 1.7923446459011312e-05, "loss": 0.3019, "step": 9950 }, { "epoch": 4.63, "learning_rate": 1.790794979079498e-05, "loss": 0.197, "step": 9960 }, { "epoch": 4.64, "learning_rate": 1.7892453122578647e-05, "loss": 0.0417, "step": 9970 }, { "epoch": 4.64, "learning_rate": 1.787695645436231e-05, "loss": 0.3343, "step": 9980 }, { "epoch": 4.64, "learning_rate": 1.786145978614598e-05, "loss": 0.2121, "step": 9990 }, { "epoch": 4.65, "learning_rate": 1.7845963117929646e-05, "loss": 0.2491, "step": 10000 }, { "epoch": 4.65, "learning_rate": 1.7830466449713314e-05, "loss": 0.4517, "step": 10010 }, { "epoch": 4.66, "learning_rate": 1.7814969781496978e-05, "loss": 0.007, "step": 10020 }, { "epoch": 4.66, "learning_rate": 1.7799473113280646e-05, "loss": 0.1944, "step": 10030 }, { "epoch": 4.67, "learning_rate": 1.7783976445064313e-05, "loss": 0.2048, "step": 10040 }, { "epoch": 4.67, "learning_rate": 1.776847977684798e-05, "loss": 0.2641, "step": 10050 }, { "epoch": 4.68, "learning_rate": 1.7752983108631648e-05, "loss": 0.1171, "step": 10060 }, { "epoch": 4.68, "learning_rate": 1.773748644041531e-05, "loss": 0.1774, "step": 10070 }, { "epoch": 4.69, "learning_rate": 1.7721989772198976e-05, "loss": 0.2047, "step": 10080 }, { "epoch": 4.69, "learning_rate": 1.7706493103982644e-05, "loss": 0.2553, "step": 10090 }, { "epoch": 4.7, "learning_rate": 1.769099643576631e-05, "loss": 0.2305, "step": 10100 }, { "epoch": 4.7, "learning_rate": 1.7675499767549975e-05, "loss": 0.1751, "step": 10110 }, { "epoch": 4.7, "learning_rate": 1.7660003099333643e-05, "loss": 0.2144, "step": 10120 }, { "epoch": 4.71, "learning_rate": 1.764450643111731e-05, "loss": 0.1307, "step": 10130 }, { "epoch": 4.71, "learning_rate": 1.7629009762900978e-05, "loss": 0.2372, "step": 10140 }, { "epoch": 4.72, "learning_rate": 1.7613513094684642e-05, "loss": 0.1058, "step": 10150 }, { "epoch": 4.72, "learning_rate": 1.759801642646831e-05, "loss": 0.3989, "step": 10160 }, { "epoch": 4.73, "learning_rate": 1.7582519758251977e-05, "loss": 0.1809, "step": 10170 }, { "epoch": 4.73, "learning_rate": 1.7567023090035644e-05, "loss": 0.1928, "step": 10180 }, { "epoch": 4.74, "learning_rate": 1.755152642181931e-05, "loss": 0.0986, "step": 10190 }, { "epoch": 4.74, "learning_rate": 1.7536029753602976e-05, "loss": 0.3917, "step": 10200 }, { "epoch": 4.75, "learning_rate": 1.7520533085386643e-05, "loss": 0.4439, "step": 10210 }, { "epoch": 4.75, "learning_rate": 1.750503641717031e-05, "loss": 0.4091, "step": 10220 }, { "epoch": 4.76, "learning_rate": 1.7489539748953975e-05, "loss": 0.0528, "step": 10230 }, { "epoch": 4.76, "learning_rate": 1.7474043080737642e-05, "loss": 0.3893, "step": 10240 }, { "epoch": 4.77, "learning_rate": 1.745854641252131e-05, "loss": 0.3417, "step": 10250 }, { "epoch": 4.77, "learning_rate": 1.7443049744304977e-05, "loss": 0.3438, "step": 10260 }, { "epoch": 4.77, "learning_rate": 1.742755307608864e-05, "loss": 0.2202, "step": 10270 }, { "epoch": 4.78, "learning_rate": 1.741205640787231e-05, "loss": 0.1588, "step": 10280 }, { "epoch": 4.78, "learning_rate": 1.7396559739655976e-05, "loss": 0.2943, "step": 10290 }, { "epoch": 4.79, "learning_rate": 1.7381063071439644e-05, "loss": 0.3582, "step": 10300 }, { "epoch": 4.79, "learning_rate": 1.7365566403223308e-05, "loss": 0.063, "step": 10310 }, { "epoch": 4.8, "learning_rate": 1.7350069735006972e-05, "loss": 0.2663, "step": 10320 }, { "epoch": 4.8, "learning_rate": 1.733457306679064e-05, "loss": 0.2395, "step": 10330 }, { "epoch": 4.81, "learning_rate": 1.7319076398574307e-05, "loss": 0.1856, "step": 10340 }, { "epoch": 4.81, "learning_rate": 1.730357973035797e-05, "loss": 0.4515, "step": 10350 }, { "epoch": 4.82, "learning_rate": 1.728808306214164e-05, "loss": 0.1686, "step": 10360 }, { "epoch": 4.82, "learning_rate": 1.7272586393925306e-05, "loss": 0.2511, "step": 10370 }, { "epoch": 4.83, "learning_rate": 1.7257089725708974e-05, "loss": 0.0803, "step": 10380 }, { "epoch": 4.83, "learning_rate": 1.7241593057492638e-05, "loss": 0.0816, "step": 10390 }, { "epoch": 4.83, "learning_rate": 1.7226096389276305e-05, "loss": 0.2426, "step": 10400 }, { "epoch": 4.84, "learning_rate": 1.7210599721059973e-05, "loss": 0.302, "step": 10410 }, { "epoch": 4.84, "learning_rate": 1.719510305284364e-05, "loss": 0.3127, "step": 10420 }, { "epoch": 4.85, "learning_rate": 1.7179606384627304e-05, "loss": 0.0458, "step": 10430 }, { "epoch": 4.85, "learning_rate": 1.7164109716410972e-05, "loss": 0.3047, "step": 10440 }, { "epoch": 4.86, "learning_rate": 1.714861304819464e-05, "loss": 0.1506, "step": 10450 }, { "epoch": 4.86, "learning_rate": 1.7133116379978307e-05, "loss": 0.1487, "step": 10460 }, { "epoch": 4.87, "learning_rate": 1.711761971176197e-05, "loss": 0.0061, "step": 10470 }, { "epoch": 4.87, "learning_rate": 1.7102123043545638e-05, "loss": 0.2508, "step": 10480 }, { "epoch": 4.88, "learning_rate": 1.7086626375329306e-05, "loss": 0.1569, "step": 10490 }, { "epoch": 4.88, "learning_rate": 1.7071129707112973e-05, "loss": 0.0749, "step": 10500 }, { "epoch": 4.89, "learning_rate": 1.7055633038896637e-05, "loss": 0.0238, "step": 10510 }, { "epoch": 4.89, "learning_rate": 1.7040136370680305e-05, "loss": 0.0766, "step": 10520 }, { "epoch": 4.9, "learning_rate": 1.7024639702463972e-05, "loss": 0.2067, "step": 10530 }, { "epoch": 4.9, "learning_rate": 1.700914303424764e-05, "loss": 0.4927, "step": 10540 }, { "epoch": 4.9, "learning_rate": 1.6993646366031304e-05, "loss": 0.43, "step": 10550 }, { "epoch": 4.91, "learning_rate": 1.697814969781497e-05, "loss": 0.0936, "step": 10560 }, { "epoch": 4.91, "learning_rate": 1.6962653029598635e-05, "loss": 0.1476, "step": 10570 }, { "epoch": 4.92, "learning_rate": 1.6947156361382303e-05, "loss": 0.1279, "step": 10580 }, { "epoch": 4.92, "learning_rate": 1.6931659693165967e-05, "loss": 0.1488, "step": 10590 }, { "epoch": 4.93, "learning_rate": 1.6916163024949635e-05, "loss": 0.1668, "step": 10600 }, { "epoch": 4.93, "learning_rate": 1.6900666356733302e-05, "loss": 0.351, "step": 10610 }, { "epoch": 4.94, "learning_rate": 1.688516968851697e-05, "loss": 0.2326, "step": 10620 }, { "epoch": 4.94, "learning_rate": 1.6869673020300634e-05, "loss": 0.184, "step": 10630 }, { "epoch": 4.95, "learning_rate": 1.68541763520843e-05, "loss": 0.4558, "step": 10640 }, { "epoch": 4.95, "learning_rate": 1.683867968386797e-05, "loss": 0.1829, "step": 10650 }, { "epoch": 4.96, "learning_rate": 1.6823183015651636e-05, "loss": 0.0798, "step": 10660 }, { "epoch": 4.96, "learning_rate": 1.68076863474353e-05, "loss": 0.1519, "step": 10670 }, { "epoch": 4.97, "learning_rate": 1.6793739346040604e-05, "loss": 0.2262, "step": 10680 }, { "epoch": 4.97, "learning_rate": 1.677824267782427e-05, "loss": 0.2732, "step": 10690 }, { "epoch": 4.97, "learning_rate": 1.6762746009607936e-05, "loss": 0.2281, "step": 10700 }, { "epoch": 4.98, "learning_rate": 1.6747249341391603e-05, "loss": 0.0631, "step": 10710 }, { "epoch": 4.98, "learning_rate": 1.6731752673175267e-05, "loss": 0.18, "step": 10720 }, { "epoch": 4.99, "learning_rate": 1.671625600495893e-05, "loss": 0.1363, "step": 10730 }, { "epoch": 4.99, "learning_rate": 1.67007593367426e-05, "loss": 0.4271, "step": 10740 }, { "epoch": 5.0, "learning_rate": 1.6685262668526266e-05, "loss": 0.2679, "step": 10750 }, { "epoch": 5.0, "eval_accuracy": 0.9703654922621008, "eval_loss": 0.13722212612628937, "eval_runtime": 17.106, "eval_samples_per_second": 177.54, "eval_steps_per_second": 44.429, "step": 10755 }, { "epoch": 5.0, "learning_rate": 1.6669766000309934e-05, "loss": 0.0703, "step": 10760 }, { "epoch": 5.01, "learning_rate": 1.6654269332093598e-05, "loss": 0.2159, "step": 10770 }, { "epoch": 5.01, "learning_rate": 1.6638772663877266e-05, "loss": 0.3982, "step": 10780 }, { "epoch": 5.02, "learning_rate": 1.6623275995660933e-05, "loss": 0.1444, "step": 10790 }, { "epoch": 5.02, "learning_rate": 1.66077793274446e-05, "loss": 0.3431, "step": 10800 }, { "epoch": 5.03, "learning_rate": 1.6592282659228265e-05, "loss": 0.1391, "step": 10810 }, { "epoch": 5.03, "learning_rate": 1.6576785991011932e-05, "loss": 0.0821, "step": 10820 }, { "epoch": 5.03, "learning_rate": 1.65612893227956e-05, "loss": 0.0049, "step": 10830 }, { "epoch": 5.04, "learning_rate": 1.6545792654579267e-05, "loss": 0.1551, "step": 10840 }, { "epoch": 5.04, "learning_rate": 1.653029598636293e-05, "loss": 0.1058, "step": 10850 }, { "epoch": 5.05, "learning_rate": 1.65147993181466e-05, "loss": 0.4053, "step": 10860 }, { "epoch": 5.05, "learning_rate": 1.6499302649930266e-05, "loss": 0.1804, "step": 10870 }, { "epoch": 5.06, "learning_rate": 1.6483805981713934e-05, "loss": 0.311, "step": 10880 }, { "epoch": 5.06, "learning_rate": 1.6468309313497598e-05, "loss": 0.3197, "step": 10890 }, { "epoch": 5.07, "learning_rate": 1.6452812645281265e-05, "loss": 0.1787, "step": 10900 }, { "epoch": 5.07, "learning_rate": 1.6437315977064933e-05, "loss": 0.2355, "step": 10910 }, { "epoch": 5.08, "learning_rate": 1.64218193088486e-05, "loss": 0.2442, "step": 10920 }, { "epoch": 5.08, "learning_rate": 1.6406322640632264e-05, "loss": 0.097, "step": 10930 }, { "epoch": 5.09, "learning_rate": 1.6390825972415932e-05, "loss": 0.1611, "step": 10940 }, { "epoch": 5.09, "learning_rate": 1.63753293041996e-05, "loss": 0.4332, "step": 10950 }, { "epoch": 5.1, "learning_rate": 1.6359832635983267e-05, "loss": 0.1403, "step": 10960 }, { "epoch": 5.1, "learning_rate": 1.6344335967766927e-05, "loss": 0.2731, "step": 10970 }, { "epoch": 5.1, "learning_rate": 1.6328839299550595e-05, "loss": 0.1247, "step": 10980 }, { "epoch": 5.11, "learning_rate": 1.6313342631334262e-05, "loss": 0.1658, "step": 10990 }, { "epoch": 5.11, "learning_rate": 1.629784596311793e-05, "loss": 0.267, "step": 11000 }, { "epoch": 5.12, "learning_rate": 1.6282349294901594e-05, "loss": 0.2864, "step": 11010 }, { "epoch": 5.12, "learning_rate": 1.626685262668526e-05, "loss": 0.056, "step": 11020 }, { "epoch": 5.13, "learning_rate": 1.625135595846893e-05, "loss": 0.2699, "step": 11030 }, { "epoch": 5.13, "learning_rate": 1.6235859290252596e-05, "loss": 0.0831, "step": 11040 }, { "epoch": 5.14, "learning_rate": 1.622036262203626e-05, "loss": 0.1419, "step": 11050 }, { "epoch": 5.14, "learning_rate": 1.6204865953819928e-05, "loss": 0.3128, "step": 11060 }, { "epoch": 5.15, "learning_rate": 1.6189369285603595e-05, "loss": 0.3543, "step": 11070 }, { "epoch": 5.15, "learning_rate": 1.6173872617387263e-05, "loss": 0.4131, "step": 11080 }, { "epoch": 5.16, "learning_rate": 1.6158375949170927e-05, "loss": 0.1686, "step": 11090 }, { "epoch": 5.16, "learning_rate": 1.6142879280954595e-05, "loss": 0.1019, "step": 11100 }, { "epoch": 5.17, "learning_rate": 1.6127382612738262e-05, "loss": 0.0761, "step": 11110 }, { "epoch": 5.17, "learning_rate": 1.611188594452193e-05, "loss": 0.047, "step": 11120 }, { "epoch": 5.17, "learning_rate": 1.6096389276305594e-05, "loss": 0.1922, "step": 11130 }, { "epoch": 5.18, "learning_rate": 1.608089260808926e-05, "loss": 0.2174, "step": 11140 }, { "epoch": 5.18, "learning_rate": 1.606539593987293e-05, "loss": 0.0466, "step": 11150 }, { "epoch": 5.19, "learning_rate": 1.6049899271656596e-05, "loss": 0.1752, "step": 11160 }, { "epoch": 5.19, "learning_rate": 1.603440260344026e-05, "loss": 0.4495, "step": 11170 }, { "epoch": 5.2, "learning_rate": 1.6018905935223928e-05, "loss": 0.3565, "step": 11180 }, { "epoch": 5.2, "learning_rate": 1.6003409267007595e-05, "loss": 0.1406, "step": 11190 }, { "epoch": 5.21, "learning_rate": 1.5987912598791263e-05, "loss": 0.0822, "step": 11200 }, { "epoch": 5.21, "learning_rate": 1.597241593057493e-05, "loss": 0.0941, "step": 11210 }, { "epoch": 5.22, "learning_rate": 1.595691926235859e-05, "loss": 0.3932, "step": 11220 }, { "epoch": 5.22, "learning_rate": 1.5941422594142258e-05, "loss": 0.0531, "step": 11230 }, { "epoch": 5.23, "learning_rate": 1.5925925925925926e-05, "loss": 0.1834, "step": 11240 }, { "epoch": 5.23, "learning_rate": 1.5910429257709593e-05, "loss": 0.0858, "step": 11250 }, { "epoch": 5.23, "learning_rate": 1.5894932589493257e-05, "loss": 0.1469, "step": 11260 }, { "epoch": 5.24, "learning_rate": 1.5879435921276925e-05, "loss": 0.0554, "step": 11270 }, { "epoch": 5.24, "learning_rate": 1.5863939253060592e-05, "loss": 0.1853, "step": 11280 }, { "epoch": 5.25, "learning_rate": 1.584844258484426e-05, "loss": 0.136, "step": 11290 }, { "epoch": 5.25, "learning_rate": 1.5832945916627924e-05, "loss": 0.2439, "step": 11300 }, { "epoch": 5.26, "learning_rate": 1.581744924841159e-05, "loss": 0.317, "step": 11310 }, { "epoch": 5.26, "learning_rate": 1.580195258019526e-05, "loss": 0.2662, "step": 11320 }, { "epoch": 5.27, "learning_rate": 1.5786455911978926e-05, "loss": 0.3763, "step": 11330 }, { "epoch": 5.27, "learning_rate": 1.577095924376259e-05, "loss": 0.3602, "step": 11340 }, { "epoch": 5.28, "learning_rate": 1.5755462575546258e-05, "loss": 0.1409, "step": 11350 }, { "epoch": 5.28, "learning_rate": 1.5739965907329925e-05, "loss": 0.2269, "step": 11360 }, { "epoch": 5.29, "learning_rate": 1.5724469239113593e-05, "loss": 0.2376, "step": 11370 }, { "epoch": 5.29, "learning_rate": 1.5708972570897257e-05, "loss": 0.0921, "step": 11380 }, { "epoch": 5.3, "learning_rate": 1.5693475902680924e-05, "loss": 0.1173, "step": 11390 }, { "epoch": 5.3, "learning_rate": 1.5677979234464592e-05, "loss": 0.4219, "step": 11400 }, { "epoch": 5.3, "learning_rate": 1.566248256624826e-05, "loss": 0.0347, "step": 11410 }, { "epoch": 5.31, "learning_rate": 1.5646985898031924e-05, "loss": 0.3427, "step": 11420 }, { "epoch": 5.31, "learning_rate": 1.563148922981559e-05, "loss": 0.1206, "step": 11430 }, { "epoch": 5.32, "learning_rate": 1.561599256159926e-05, "loss": 0.2318, "step": 11440 }, { "epoch": 5.32, "learning_rate": 1.5600495893382926e-05, "loss": 0.123, "step": 11450 }, { "epoch": 5.33, "learning_rate": 1.558499922516659e-05, "loss": 0.2684, "step": 11460 }, { "epoch": 5.33, "learning_rate": 1.5569502556950254e-05, "loss": 0.4133, "step": 11470 }, { "epoch": 5.34, "learning_rate": 1.5554005888733922e-05, "loss": 0.4216, "step": 11480 }, { "epoch": 5.34, "learning_rate": 1.553850922051759e-05, "loss": 0.1955, "step": 11490 }, { "epoch": 5.35, "learning_rate": 1.5523012552301253e-05, "loss": 0.1309, "step": 11500 }, { "epoch": 5.35, "learning_rate": 1.550751588408492e-05, "loss": 0.2917, "step": 11510 }, { "epoch": 5.36, "learning_rate": 1.5492019215868588e-05, "loss": 0.2985, "step": 11520 }, { "epoch": 5.36, "learning_rate": 1.5476522547652256e-05, "loss": 0.1159, "step": 11530 }, { "epoch": 5.36, "learning_rate": 1.546102587943592e-05, "loss": 0.0084, "step": 11540 }, { "epoch": 5.37, "learning_rate": 1.5445529211219587e-05, "loss": 0.1886, "step": 11550 }, { "epoch": 5.37, "learning_rate": 1.5430032543003255e-05, "loss": 0.1164, "step": 11560 }, { "epoch": 5.38, "learning_rate": 1.5414535874786922e-05, "loss": 0.2624, "step": 11570 }, { "epoch": 5.38, "learning_rate": 1.5399039206570586e-05, "loss": 0.1023, "step": 11580 }, { "epoch": 5.39, "learning_rate": 1.538509220517589e-05, "loss": 0.3386, "step": 11590 }, { "epoch": 5.39, "learning_rate": 1.5369595536959555e-05, "loss": 0.3027, "step": 11600 }, { "epoch": 5.4, "learning_rate": 1.5354098868743222e-05, "loss": 0.2126, "step": 11610 }, { "epoch": 5.4, "learning_rate": 1.5338602200526886e-05, "loss": 0.2166, "step": 11620 }, { "epoch": 5.41, "learning_rate": 1.5323105532310554e-05, "loss": 0.1497, "step": 11630 }, { "epoch": 5.41, "learning_rate": 1.5307608864094218e-05, "loss": 0.1867, "step": 11640 }, { "epoch": 5.42, "learning_rate": 1.5292112195877885e-05, "loss": 0.1521, "step": 11650 }, { "epoch": 5.42, "learning_rate": 1.5276615527661553e-05, "loss": 0.1259, "step": 11660 }, { "epoch": 5.43, "learning_rate": 1.526111885944522e-05, "loss": 0.2591, "step": 11670 }, { "epoch": 5.43, "learning_rate": 1.5245622191228884e-05, "loss": 0.0995, "step": 11680 }, { "epoch": 5.43, "learning_rate": 1.5230125523012552e-05, "loss": 0.2385, "step": 11690 }, { "epoch": 5.44, "learning_rate": 1.521462885479622e-05, "loss": 0.1062, "step": 11700 }, { "epoch": 5.44, "learning_rate": 1.5199132186579887e-05, "loss": 0.302, "step": 11710 }, { "epoch": 5.45, "learning_rate": 1.5183635518363551e-05, "loss": 0.1853, "step": 11720 }, { "epoch": 5.45, "learning_rate": 1.5168138850147218e-05, "loss": 0.2605, "step": 11730 }, { "epoch": 5.46, "learning_rate": 1.5152642181930886e-05, "loss": 0.2215, "step": 11740 }, { "epoch": 5.46, "learning_rate": 1.5137145513714553e-05, "loss": 0.2838, "step": 11750 }, { "epoch": 5.47, "learning_rate": 1.5121648845498217e-05, "loss": 0.1278, "step": 11760 }, { "epoch": 5.47, "learning_rate": 1.5106152177281885e-05, "loss": 0.0232, "step": 11770 }, { "epoch": 5.48, "learning_rate": 1.5090655509065552e-05, "loss": 0.3235, "step": 11780 }, { "epoch": 5.48, "learning_rate": 1.507515884084922e-05, "loss": 0.2472, "step": 11790 }, { "epoch": 5.49, "learning_rate": 1.5059662172632884e-05, "loss": 0.2624, "step": 11800 }, { "epoch": 5.49, "learning_rate": 1.504416550441655e-05, "loss": 0.2014, "step": 11810 }, { "epoch": 5.5, "learning_rate": 1.5028668836200217e-05, "loss": 0.229, "step": 11820 }, { "epoch": 5.5, "learning_rate": 1.5013172167983885e-05, "loss": 0.0053, "step": 11830 }, { "epoch": 5.5, "learning_rate": 1.499767549976755e-05, "loss": 0.063, "step": 11840 }, { "epoch": 5.51, "learning_rate": 1.4982178831551216e-05, "loss": 0.0395, "step": 11850 }, { "epoch": 5.51, "learning_rate": 1.4966682163334884e-05, "loss": 0.0545, "step": 11860 }, { "epoch": 5.52, "learning_rate": 1.495118549511855e-05, "loss": 0.2367, "step": 11870 }, { "epoch": 5.52, "learning_rate": 1.4935688826902217e-05, "loss": 0.2555, "step": 11880 }, { "epoch": 5.53, "learning_rate": 1.4920192158685883e-05, "loss": 0.216, "step": 11890 }, { "epoch": 5.53, "learning_rate": 1.490469549046955e-05, "loss": 0.0395, "step": 11900 }, { "epoch": 5.54, "learning_rate": 1.4889198822253216e-05, "loss": 0.1207, "step": 11910 }, { "epoch": 5.54, "learning_rate": 1.4873702154036884e-05, "loss": 0.0864, "step": 11920 }, { "epoch": 5.55, "learning_rate": 1.4858205485820548e-05, "loss": 0.0692, "step": 11930 }, { "epoch": 5.55, "learning_rate": 1.4842708817604215e-05, "loss": 0.0309, "step": 11940 }, { "epoch": 5.56, "learning_rate": 1.4827212149387881e-05, "loss": 0.2822, "step": 11950 }, { "epoch": 5.56, "learning_rate": 1.4811715481171548e-05, "loss": 0.0721, "step": 11960 }, { "epoch": 5.56, "learning_rate": 1.4796218812955214e-05, "loss": 0.2282, "step": 11970 }, { "epoch": 5.57, "learning_rate": 1.4780722144738882e-05, "loss": 0.5436, "step": 11980 }, { "epoch": 5.57, "learning_rate": 1.4765225476522548e-05, "loss": 0.3879, "step": 11990 }, { "epoch": 5.58, "learning_rate": 1.4749728808306215e-05, "loss": 0.2802, "step": 12000 }, { "epoch": 5.58, "learning_rate": 1.473423214008988e-05, "loss": 0.0243, "step": 12010 }, { "epoch": 5.59, "learning_rate": 1.4718735471873548e-05, "loss": 0.1327, "step": 12020 }, { "epoch": 5.59, "learning_rate": 1.4703238803657214e-05, "loss": 0.056, "step": 12030 }, { "epoch": 5.6, "learning_rate": 1.4687742135440882e-05, "loss": 0.284, "step": 12040 }, { "epoch": 5.6, "learning_rate": 1.4672245467224547e-05, "loss": 0.3406, "step": 12050 }, { "epoch": 5.61, "learning_rate": 1.4656748799008213e-05, "loss": 0.2064, "step": 12060 }, { "epoch": 5.61, "learning_rate": 1.4641252130791879e-05, "loss": 0.2296, "step": 12070 }, { "epoch": 5.62, "learning_rate": 1.4625755462575546e-05, "loss": 0.1643, "step": 12080 }, { "epoch": 5.62, "learning_rate": 1.4610258794359212e-05, "loss": 0.2724, "step": 12090 }, { "epoch": 5.63, "learning_rate": 1.459476212614288e-05, "loss": 0.1311, "step": 12100 }, { "epoch": 5.63, "learning_rate": 1.4579265457926545e-05, "loss": 0.1393, "step": 12110 }, { "epoch": 5.63, "learning_rate": 1.4563768789710213e-05, "loss": 0.144, "step": 12120 }, { "epoch": 5.64, "learning_rate": 1.4548272121493879e-05, "loss": 0.1708, "step": 12130 }, { "epoch": 5.64, "learning_rate": 1.4532775453277546e-05, "loss": 0.1765, "step": 12140 }, { "epoch": 5.65, "learning_rate": 1.4517278785061212e-05, "loss": 0.0997, "step": 12150 }, { "epoch": 5.65, "learning_rate": 1.450178211684488e-05, "loss": 0.2217, "step": 12160 }, { "epoch": 5.66, "learning_rate": 1.4486285448628545e-05, "loss": 0.1893, "step": 12170 }, { "epoch": 5.66, "learning_rate": 1.4470788780412211e-05, "loss": 0.129, "step": 12180 }, { "epoch": 5.67, "learning_rate": 1.4455292112195877e-05, "loss": 0.3474, "step": 12190 }, { "epoch": 5.67, "learning_rate": 1.4439795443979544e-05, "loss": 0.2942, "step": 12200 }, { "epoch": 5.68, "learning_rate": 1.442429877576321e-05, "loss": 0.147, "step": 12210 }, { "epoch": 5.68, "learning_rate": 1.4408802107546878e-05, "loss": 0.206, "step": 12220 }, { "epoch": 5.69, "learning_rate": 1.4393305439330543e-05, "loss": 0.0984, "step": 12230 }, { "epoch": 5.69, "learning_rate": 1.4377808771114211e-05, "loss": 0.5019, "step": 12240 }, { "epoch": 5.7, "learning_rate": 1.4362312102897877e-05, "loss": 0.1503, "step": 12250 }, { "epoch": 5.7, "learning_rate": 1.4346815434681544e-05, "loss": 0.4062, "step": 12260 }, { "epoch": 5.7, "learning_rate": 1.433131876646521e-05, "loss": 0.0735, "step": 12270 }, { "epoch": 5.71, "learning_rate": 1.4315822098248877e-05, "loss": 0.3409, "step": 12280 }, { "epoch": 5.71, "learning_rate": 1.4300325430032543e-05, "loss": 0.1813, "step": 12290 }, { "epoch": 5.72, "learning_rate": 1.428482876181621e-05, "loss": 0.2068, "step": 12300 }, { "epoch": 5.72, "learning_rate": 1.4269332093599875e-05, "loss": 0.2818, "step": 12310 }, { "epoch": 5.73, "learning_rate": 1.4253835425383542e-05, "loss": 0.2827, "step": 12320 }, { "epoch": 5.73, "learning_rate": 1.423833875716721e-05, "loss": 0.2609, "step": 12330 }, { "epoch": 5.74, "learning_rate": 1.4222842088950876e-05, "loss": 0.1641, "step": 12340 }, { "epoch": 5.74, "learning_rate": 1.4207345420734543e-05, "loss": 0.1817, "step": 12350 }, { "epoch": 5.75, "learning_rate": 1.4191848752518209e-05, "loss": 0.3664, "step": 12360 }, { "epoch": 5.75, "learning_rate": 1.4176352084301876e-05, "loss": 0.0603, "step": 12370 }, { "epoch": 5.76, "learning_rate": 1.4160855416085542e-05, "loss": 0.216, "step": 12380 }, { "epoch": 5.76, "learning_rate": 1.414535874786921e-05, "loss": 0.1701, "step": 12390 }, { "epoch": 5.76, "learning_rate": 1.4129862079652875e-05, "loss": 0.2231, "step": 12400 }, { "epoch": 5.77, "learning_rate": 1.4114365411436543e-05, "loss": 0.2279, "step": 12410 }, { "epoch": 5.77, "learning_rate": 1.4098868743220209e-05, "loss": 0.0225, "step": 12420 }, { "epoch": 5.78, "learning_rate": 1.4083372075003874e-05, "loss": 0.2637, "step": 12430 }, { "epoch": 5.78, "learning_rate": 1.406787540678754e-05, "loss": 0.1246, "step": 12440 }, { "epoch": 5.79, "learning_rate": 1.4052378738571208e-05, "loss": 0.0886, "step": 12450 }, { "epoch": 5.79, "learning_rate": 1.4036882070354874e-05, "loss": 0.0999, "step": 12460 }, { "epoch": 5.8, "learning_rate": 1.4021385402138541e-05, "loss": 0.0849, "step": 12470 }, { "epoch": 5.8, "learning_rate": 1.4005888733922207e-05, "loss": 0.0611, "step": 12480 }, { "epoch": 5.81, "learning_rate": 1.3990392065705874e-05, "loss": 0.3946, "step": 12490 }, { "epoch": 5.81, "learning_rate": 1.397489539748954e-05, "loss": 0.1693, "step": 12500 }, { "epoch": 5.82, "learning_rate": 1.3959398729273208e-05, "loss": 0.0813, "step": 12510 }, { "epoch": 5.82, "learning_rate": 1.3943902061056873e-05, "loss": 0.2583, "step": 12520 }, { "epoch": 5.83, "learning_rate": 1.3928405392840541e-05, "loss": 0.083, "step": 12530 }, { "epoch": 5.83, "learning_rate": 1.3912908724624207e-05, "loss": 0.3325, "step": 12540 }, { "epoch": 5.83, "learning_rate": 1.3897412056407872e-05, "loss": 0.2105, "step": 12550 }, { "epoch": 5.84, "learning_rate": 1.3881915388191538e-05, "loss": 0.2928, "step": 12560 }, { "epoch": 5.84, "learning_rate": 1.3866418719975206e-05, "loss": 0.2176, "step": 12570 }, { "epoch": 5.85, "learning_rate": 1.3850922051758872e-05, "loss": 0.1962, "step": 12580 }, { "epoch": 5.85, "learning_rate": 1.3835425383542539e-05, "loss": 0.0099, "step": 12590 }, { "epoch": 5.86, "learning_rate": 1.3819928715326205e-05, "loss": 0.5605, "step": 12600 }, { "epoch": 5.86, "learning_rate": 1.3804432047109872e-05, "loss": 0.1368, "step": 12610 }, { "epoch": 5.87, "learning_rate": 1.3788935378893538e-05, "loss": 0.3033, "step": 12620 }, { "epoch": 5.87, "learning_rate": 1.3773438710677206e-05, "loss": 0.2857, "step": 12630 }, { "epoch": 5.88, "learning_rate": 1.3757942042460871e-05, "loss": 0.0981, "step": 12640 }, { "epoch": 5.88, "learning_rate": 1.3742445374244539e-05, "loss": 0.0775, "step": 12650 }, { "epoch": 5.89, "learning_rate": 1.3726948706028205e-05, "loss": 0.2109, "step": 12660 }, { "epoch": 5.89, "learning_rate": 1.3711452037811872e-05, "loss": 0.3579, "step": 12670 }, { "epoch": 5.89, "learning_rate": 1.3695955369595536e-05, "loss": 0.0032, "step": 12680 }, { "epoch": 5.9, "learning_rate": 1.3680458701379204e-05, "loss": 0.1483, "step": 12690 }, { "epoch": 5.9, "learning_rate": 1.366496203316287e-05, "loss": 0.133, "step": 12700 }, { "epoch": 5.91, "learning_rate": 1.3649465364946537e-05, "loss": 0.3291, "step": 12710 }, { "epoch": 5.91, "learning_rate": 1.3633968696730203e-05, "loss": 0.0629, "step": 12720 }, { "epoch": 5.92, "learning_rate": 1.361847202851387e-05, "loss": 0.1384, "step": 12730 }, { "epoch": 5.92, "learning_rate": 1.3602975360297536e-05, "loss": 0.2241, "step": 12740 }, { "epoch": 5.93, "learning_rate": 1.3587478692081203e-05, "loss": 0.1742, "step": 12750 }, { "epoch": 5.93, "learning_rate": 1.357198202386487e-05, "loss": 0.3987, "step": 12760 }, { "epoch": 5.94, "learning_rate": 1.3556485355648537e-05, "loss": 0.1664, "step": 12770 }, { "epoch": 5.94, "learning_rate": 1.3540988687432203e-05, "loss": 0.1917, "step": 12780 }, { "epoch": 5.95, "learning_rate": 1.352549201921587e-05, "loss": 0.2952, "step": 12790 }, { "epoch": 5.95, "learning_rate": 1.3509995350999534e-05, "loss": 0.1671, "step": 12800 }, { "epoch": 5.96, "learning_rate": 1.3494498682783202e-05, "loss": 0.1415, "step": 12810 }, { "epoch": 5.96, "learning_rate": 1.3479002014566867e-05, "loss": 0.0288, "step": 12820 }, { "epoch": 5.96, "learning_rate": 1.3463505346350535e-05, "loss": 0.114, "step": 12830 }, { "epoch": 5.97, "learning_rate": 1.34480086781342e-05, "loss": 0.2097, "step": 12840 }, { "epoch": 5.97, "learning_rate": 1.3432512009917868e-05, "loss": 0.443, "step": 12850 }, { "epoch": 5.98, "learning_rate": 1.3417015341701534e-05, "loss": 0.0946, "step": 12860 }, { "epoch": 5.98, "learning_rate": 1.3401518673485201e-05, "loss": 0.0602, "step": 12870 }, { "epoch": 5.99, "learning_rate": 1.3386022005268867e-05, "loss": 0.2549, "step": 12880 }, { "epoch": 5.99, "learning_rate": 1.3370525337052535e-05, "loss": 0.279, "step": 12890 }, { "epoch": 6.0, "learning_rate": 1.33550286688362e-05, "loss": 0.3252, "step": 12900 }, { "epoch": 6.0, "eval_accuracy": 0.9720118538030952, "eval_loss": 0.12808209657669067, "eval_runtime": 17.5753, "eval_samples_per_second": 172.8, "eval_steps_per_second": 43.243, "step": 12906 }, { "epoch": 6.0, "learning_rate": 1.3339532000619868e-05, "loss": 0.1309, "step": 12910 }, { "epoch": 6.01, "learning_rate": 1.3324035332403534e-05, "loss": 0.2778, "step": 12920 }, { "epoch": 6.01, "learning_rate": 1.33085386641872e-05, "loss": 0.2875, "step": 12930 }, { "epoch": 6.02, "learning_rate": 1.3293041995970865e-05, "loss": 0.2078, "step": 12940 }, { "epoch": 6.02, "learning_rate": 1.3277545327754533e-05, "loss": 0.2939, "step": 12950 }, { "epoch": 6.03, "learning_rate": 1.3262048659538199e-05, "loss": 0.1103, "step": 12960 }, { "epoch": 6.03, "learning_rate": 1.3246551991321866e-05, "loss": 0.1293, "step": 12970 }, { "epoch": 6.03, "learning_rate": 1.3231055323105532e-05, "loss": 0.166, "step": 12980 }, { "epoch": 6.04, "learning_rate": 1.32155586548892e-05, "loss": 0.0301, "step": 12990 }, { "epoch": 6.04, "learning_rate": 1.3200061986672865e-05, "loss": 0.1238, "step": 13000 }, { "epoch": 6.05, "learning_rate": 1.3184565318456533e-05, "loss": 0.2215, "step": 13010 }, { "epoch": 6.05, "learning_rate": 1.3169068650240198e-05, "loss": 0.1132, "step": 13020 }, { "epoch": 6.06, "learning_rate": 1.3153571982023866e-05, "loss": 0.2113, "step": 13030 }, { "epoch": 6.06, "learning_rate": 1.3138075313807532e-05, "loss": 0.2348, "step": 13040 }, { "epoch": 6.07, "learning_rate": 1.3122578645591198e-05, "loss": 0.1862, "step": 13050 }, { "epoch": 6.07, "learning_rate": 1.3107081977374863e-05, "loss": 0.1097, "step": 13060 }, { "epoch": 6.08, "learning_rate": 1.309158530915853e-05, "loss": 0.2081, "step": 13070 }, { "epoch": 6.08, "learning_rate": 1.3076088640942197e-05, "loss": 0.1265, "step": 13080 }, { "epoch": 6.09, "learning_rate": 1.3060591972725864e-05, "loss": 0.1855, "step": 13090 }, { "epoch": 6.09, "learning_rate": 1.304509530450953e-05, "loss": 0.0711, "step": 13100 }, { "epoch": 6.09, "learning_rate": 1.3029598636293197e-05, "loss": 0.0704, "step": 13110 }, { "epoch": 6.1, "learning_rate": 1.3014101968076863e-05, "loss": 0.2293, "step": 13120 }, { "epoch": 6.1, "learning_rate": 1.299860529986053e-05, "loss": 0.1046, "step": 13130 }, { "epoch": 6.11, "learning_rate": 1.2983108631644196e-05, "loss": 0.2733, "step": 13140 }, { "epoch": 6.11, "learning_rate": 1.2967611963427864e-05, "loss": 0.2281, "step": 13150 }, { "epoch": 6.12, "learning_rate": 1.295211529521153e-05, "loss": 0.0939, "step": 13160 }, { "epoch": 6.12, "learning_rate": 1.2936618626995197e-05, "loss": 0.1873, "step": 13170 }, { "epoch": 6.13, "learning_rate": 1.2921121958778861e-05, "loss": 0.141, "step": 13180 }, { "epoch": 6.13, "learning_rate": 1.2905625290562529e-05, "loss": 0.1002, "step": 13190 }, { "epoch": 6.14, "learning_rate": 1.2890128622346196e-05, "loss": 0.1087, "step": 13200 }, { "epoch": 6.14, "learning_rate": 1.2874631954129862e-05, "loss": 0.1113, "step": 13210 }, { "epoch": 6.15, "learning_rate": 1.285913528591353e-05, "loss": 0.1038, "step": 13220 }, { "epoch": 6.15, "learning_rate": 1.2843638617697195e-05, "loss": 0.2177, "step": 13230 }, { "epoch": 6.16, "learning_rate": 1.2828141949480863e-05, "loss": 0.0688, "step": 13240 }, { "epoch": 6.16, "learning_rate": 1.2812645281264529e-05, "loss": 0.037, "step": 13250 }, { "epoch": 6.16, "learning_rate": 1.2797148613048196e-05, "loss": 0.1282, "step": 13260 }, { "epoch": 6.17, "learning_rate": 1.2781651944831862e-05, "loss": 0.2578, "step": 13270 }, { "epoch": 6.17, "learning_rate": 1.276615527661553e-05, "loss": 0.4221, "step": 13280 }, { "epoch": 6.18, "learning_rate": 1.2750658608399195e-05, "loss": 0.0246, "step": 13290 }, { "epoch": 6.18, "learning_rate": 1.2735161940182861e-05, "loss": 0.1784, "step": 13300 }, { "epoch": 6.19, "learning_rate": 1.2719665271966527e-05, "loss": 0.192, "step": 13310 }, { "epoch": 6.19, "learning_rate": 1.2704168603750194e-05, "loss": 0.1078, "step": 13320 }, { "epoch": 6.2, "learning_rate": 1.268867193553386e-05, "loss": 0.0037, "step": 13330 }, { "epoch": 6.2, "learning_rate": 1.2673175267317527e-05, "loss": 0.2057, "step": 13340 }, { "epoch": 6.21, "learning_rate": 1.2657678599101193e-05, "loss": 0.3116, "step": 13350 }, { "epoch": 6.21, "learning_rate": 1.264218193088486e-05, "loss": 0.003, "step": 13360 }, { "epoch": 6.22, "learning_rate": 1.2626685262668527e-05, "loss": 0.2409, "step": 13370 }, { "epoch": 6.22, "learning_rate": 1.2611188594452194e-05, "loss": 0.1635, "step": 13380 }, { "epoch": 6.23, "learning_rate": 1.259569192623586e-05, "loss": 0.2466, "step": 13390 }, { "epoch": 6.23, "learning_rate": 1.2580195258019527e-05, "loss": 0.3034, "step": 13400 }, { "epoch": 6.23, "learning_rate": 1.2564698589803193e-05, "loss": 0.0746, "step": 13410 }, { "epoch": 6.24, "learning_rate": 1.254920192158686e-05, "loss": 0.1879, "step": 13420 }, { "epoch": 6.24, "learning_rate": 1.2533705253370525e-05, "loss": 0.2697, "step": 13430 }, { "epoch": 6.25, "learning_rate": 1.2518208585154192e-05, "loss": 0.128, "step": 13440 }, { "epoch": 6.25, "learning_rate": 1.2502711916937858e-05, "loss": 0.2179, "step": 13450 }, { "epoch": 6.26, "learning_rate": 1.2487215248721525e-05, "loss": 0.1675, "step": 13460 }, { "epoch": 6.26, "learning_rate": 1.2471718580505191e-05, "loss": 0.2036, "step": 13470 }, { "epoch": 6.27, "learning_rate": 1.2456221912288859e-05, "loss": 0.176, "step": 13480 }, { "epoch": 6.27, "learning_rate": 1.2440725244072524e-05, "loss": 0.0898, "step": 13490 }, { "epoch": 6.28, "learning_rate": 1.2425228575856192e-05, "loss": 0.2254, "step": 13500 }, { "epoch": 6.28, "learning_rate": 1.2409731907639858e-05, "loss": 0.0578, "step": 13510 }, { "epoch": 6.29, "learning_rate": 1.2394235239423525e-05, "loss": 0.0738, "step": 13520 }, { "epoch": 6.29, "learning_rate": 1.2378738571207191e-05, "loss": 0.3309, "step": 13530 }, { "epoch": 6.29, "learning_rate": 1.2363241902990859e-05, "loss": 0.3371, "step": 13540 }, { "epoch": 6.3, "learning_rate": 1.2347745234774523e-05, "loss": 0.1685, "step": 13550 }, { "epoch": 6.3, "learning_rate": 1.233224856655819e-05, "loss": 0.1555, "step": 13560 }, { "epoch": 6.31, "learning_rate": 1.2316751898341856e-05, "loss": 0.2535, "step": 13570 }, { "epoch": 6.31, "learning_rate": 1.2301255230125523e-05, "loss": 0.0701, "step": 13580 }, { "epoch": 6.32, "learning_rate": 1.228575856190919e-05, "loss": 0.1508, "step": 13590 }, { "epoch": 6.32, "learning_rate": 1.2270261893692857e-05, "loss": 0.2139, "step": 13600 }, { "epoch": 6.33, "learning_rate": 1.2254765225476522e-05, "loss": 0.005, "step": 13610 }, { "epoch": 6.33, "learning_rate": 1.223926855726019e-05, "loss": 0.1364, "step": 13620 }, { "epoch": 6.34, "learning_rate": 1.2223771889043856e-05, "loss": 0.2343, "step": 13630 }, { "epoch": 6.34, "learning_rate": 1.2208275220827523e-05, "loss": 0.2291, "step": 13640 }, { "epoch": 6.35, "learning_rate": 1.2192778552611189e-05, "loss": 0.3999, "step": 13650 }, { "epoch": 6.35, "learning_rate": 1.2177281884394856e-05, "loss": 0.2729, "step": 13660 }, { "epoch": 6.36, "learning_rate": 1.2161785216178522e-05, "loss": 0.2382, "step": 13670 }, { "epoch": 6.36, "learning_rate": 1.2146288547962188e-05, "loss": 0.2228, "step": 13680 }, { "epoch": 6.36, "learning_rate": 1.2130791879745854e-05, "loss": 0.1734, "step": 13690 }, { "epoch": 6.37, "learning_rate": 1.2115295211529521e-05, "loss": 0.1089, "step": 13700 }, { "epoch": 6.37, "learning_rate": 1.2099798543313187e-05, "loss": 0.0143, "step": 13710 }, { "epoch": 6.38, "learning_rate": 1.2084301875096855e-05, "loss": 0.0997, "step": 13720 }, { "epoch": 6.38, "learning_rate": 1.206880520688052e-05, "loss": 0.0652, "step": 13730 }, { "epoch": 6.39, "learning_rate": 1.2053308538664188e-05, "loss": 0.4293, "step": 13740 }, { "epoch": 6.39, "learning_rate": 1.2037811870447854e-05, "loss": 0.122, "step": 13750 }, { "epoch": 6.4, "learning_rate": 1.2022315202231521e-05, "loss": 0.1703, "step": 13760 }, { "epoch": 6.4, "learning_rate": 1.2006818534015187e-05, "loss": 0.0039, "step": 13770 }, { "epoch": 6.41, "learning_rate": 1.1991321865798854e-05, "loss": 0.2788, "step": 13780 }, { "epoch": 6.41, "learning_rate": 1.197582519758252e-05, "loss": 0.1009, "step": 13790 }, { "epoch": 6.42, "learning_rate": 1.1960328529366186e-05, "loss": 0.0464, "step": 13800 }, { "epoch": 6.42, "learning_rate": 1.1944831861149852e-05, "loss": 0.141, "step": 13810 }, { "epoch": 6.42, "learning_rate": 1.192933519293352e-05, "loss": 0.122, "step": 13820 }, { "epoch": 6.43, "learning_rate": 1.1913838524717185e-05, "loss": 0.1549, "step": 13830 }, { "epoch": 6.43, "learning_rate": 1.1899891523322486e-05, "loss": 0.2195, "step": 13840 }, { "epoch": 6.44, "learning_rate": 1.1884394855106152e-05, "loss": 0.3122, "step": 13850 }, { "epoch": 6.44, "learning_rate": 1.1868898186889819e-05, "loss": 0.2803, "step": 13860 }, { "epoch": 6.45, "learning_rate": 1.1853401518673485e-05, "loss": 0.0183, "step": 13870 }, { "epoch": 6.45, "learning_rate": 1.1837904850457152e-05, "loss": 0.1637, "step": 13880 }, { "epoch": 6.46, "learning_rate": 1.1822408182240818e-05, "loss": 0.1848, "step": 13890 }, { "epoch": 6.46, "learning_rate": 1.1806911514024486e-05, "loss": 0.2463, "step": 13900 }, { "epoch": 6.47, "learning_rate": 1.1791414845808151e-05, "loss": 0.0659, "step": 13910 }, { "epoch": 6.47, "learning_rate": 1.1775918177591819e-05, "loss": 0.0059, "step": 13920 }, { "epoch": 6.48, "learning_rate": 1.1760421509375485e-05, "loss": 0.1391, "step": 13930 }, { "epoch": 6.48, "learning_rate": 1.1744924841159152e-05, "loss": 0.0399, "step": 13940 }, { "epoch": 6.49, "learning_rate": 1.1729428172942816e-05, "loss": 0.0984, "step": 13950 }, { "epoch": 6.49, "learning_rate": 1.1713931504726484e-05, "loss": 0.2245, "step": 13960 }, { "epoch": 6.49, "learning_rate": 1.169843483651015e-05, "loss": 0.0638, "step": 13970 }, { "epoch": 6.5, "learning_rate": 1.1682938168293817e-05, "loss": 0.1447, "step": 13980 }, { "epoch": 6.5, "learning_rate": 1.1667441500077483e-05, "loss": 0.1398, "step": 13990 }, { "epoch": 6.51, "learning_rate": 1.165194483186115e-05, "loss": 0.0596, "step": 14000 }, { "epoch": 6.51, "learning_rate": 1.1636448163644816e-05, "loss": 0.2698, "step": 14010 }, { "epoch": 6.52, "learning_rate": 1.1620951495428484e-05, "loss": 0.3052, "step": 14020 }, { "epoch": 6.52, "learning_rate": 1.160545482721215e-05, "loss": 0.1935, "step": 14030 }, { "epoch": 6.53, "learning_rate": 1.1589958158995817e-05, "loss": 0.2589, "step": 14040 }, { "epoch": 6.53, "learning_rate": 1.1574461490779483e-05, "loss": 0.3373, "step": 14050 }, { "epoch": 6.54, "learning_rate": 1.155896482256315e-05, "loss": 0.3851, "step": 14060 }, { "epoch": 6.54, "learning_rate": 1.1543468154346816e-05, "loss": 0.1823, "step": 14070 }, { "epoch": 6.55, "learning_rate": 1.1527971486130482e-05, "loss": 0.1581, "step": 14080 }, { "epoch": 6.55, "learning_rate": 1.1512474817914148e-05, "loss": 0.1346, "step": 14090 }, { "epoch": 6.56, "learning_rate": 1.1496978149697815e-05, "loss": 0.053, "step": 14100 }, { "epoch": 6.56, "learning_rate": 1.148148148148148e-05, "loss": 0.1271, "step": 14110 }, { "epoch": 6.56, "learning_rate": 1.1465984813265148e-05, "loss": 0.0857, "step": 14120 }, { "epoch": 6.57, "learning_rate": 1.1450488145048814e-05, "loss": 0.1693, "step": 14130 }, { "epoch": 6.57, "learning_rate": 1.1434991476832482e-05, "loss": 0.335, "step": 14140 }, { "epoch": 6.58, "learning_rate": 1.1419494808616147e-05, "loss": 0.2926, "step": 14150 }, { "epoch": 6.58, "learning_rate": 1.1403998140399815e-05, "loss": 0.3188, "step": 14160 }, { "epoch": 6.59, "learning_rate": 1.138850147218348e-05, "loss": 0.3365, "step": 14170 }, { "epoch": 6.59, "learning_rate": 1.1373004803967148e-05, "loss": 0.2765, "step": 14180 }, { "epoch": 6.6, "learning_rate": 1.1357508135750814e-05, "loss": 0.2927, "step": 14190 }, { "epoch": 6.6, "learning_rate": 1.134201146753448e-05, "loss": 0.4226, "step": 14200 }, { "epoch": 6.61, "learning_rate": 1.1326514799318145e-05, "loss": 0.3253, "step": 14210 }, { "epoch": 6.61, "learning_rate": 1.1311018131101813e-05, "loss": 0.1654, "step": 14220 }, { "epoch": 6.62, "learning_rate": 1.1295521462885479e-05, "loss": 0.2147, "step": 14230 }, { "epoch": 6.62, "learning_rate": 1.1280024794669146e-05, "loss": 0.0685, "step": 14240 }, { "epoch": 6.62, "learning_rate": 1.1264528126452812e-05, "loss": 0.1078, "step": 14250 }, { "epoch": 6.63, "learning_rate": 1.124903145823648e-05, "loss": 0.0877, "step": 14260 }, { "epoch": 6.63, "learning_rate": 1.1233534790020145e-05, "loss": 0.2331, "step": 14270 }, { "epoch": 6.64, "learning_rate": 1.1218038121803813e-05, "loss": 0.1169, "step": 14280 }, { "epoch": 6.64, "learning_rate": 1.1202541453587479e-05, "loss": 0.3452, "step": 14290 }, { "epoch": 6.65, "learning_rate": 1.1187044785371146e-05, "loss": 0.0466, "step": 14300 }, { "epoch": 6.65, "learning_rate": 1.1171548117154812e-05, "loss": 0.0307, "step": 14310 }, { "epoch": 6.66, "learning_rate": 1.115605144893848e-05, "loss": 0.1214, "step": 14320 }, { "epoch": 6.66, "learning_rate": 1.1140554780722145e-05, "loss": 0.1335, "step": 14330 }, { "epoch": 6.67, "learning_rate": 1.1125058112505811e-05, "loss": 0.2897, "step": 14340 }, { "epoch": 6.67, "learning_rate": 1.1109561444289478e-05, "loss": 0.2502, "step": 14350 }, { "epoch": 6.68, "learning_rate": 1.1094064776073144e-05, "loss": 0.1572, "step": 14360 }, { "epoch": 6.68, "learning_rate": 1.1078568107856812e-05, "loss": 0.216, "step": 14370 }, { "epoch": 6.69, "learning_rate": 1.1063071439640477e-05, "loss": 0.0477, "step": 14380 }, { "epoch": 6.69, "learning_rate": 1.1047574771424145e-05, "loss": 0.2136, "step": 14390 }, { "epoch": 6.69, "learning_rate": 1.103207810320781e-05, "loss": 0.0107, "step": 14400 }, { "epoch": 6.7, "learning_rate": 1.1016581434991478e-05, "loss": 0.1131, "step": 14410 }, { "epoch": 6.7, "learning_rate": 1.1001084766775144e-05, "loss": 0.11, "step": 14420 }, { "epoch": 6.71, "learning_rate": 1.0985588098558811e-05, "loss": 0.1941, "step": 14430 }, { "epoch": 6.71, "learning_rate": 1.0970091430342477e-05, "loss": 0.1927, "step": 14440 }, { "epoch": 6.72, "learning_rate": 1.0954594762126143e-05, "loss": 0.1965, "step": 14450 }, { "epoch": 6.72, "learning_rate": 1.0939098093909809e-05, "loss": 0.0492, "step": 14460 }, { "epoch": 6.73, "learning_rate": 1.0923601425693476e-05, "loss": 0.1702, "step": 14470 }, { "epoch": 6.73, "learning_rate": 1.0908104757477142e-05, "loss": 0.2058, "step": 14480 }, { "epoch": 6.74, "learning_rate": 1.089260808926081e-05, "loss": 0.0383, "step": 14490 }, { "epoch": 6.74, "learning_rate": 1.0877111421044475e-05, "loss": 0.2255, "step": 14500 }, { "epoch": 6.75, "learning_rate": 1.0861614752828143e-05, "loss": 0.1561, "step": 14510 }, { "epoch": 6.75, "learning_rate": 1.0846118084611809e-05, "loss": 0.3958, "step": 14520 }, { "epoch": 6.75, "learning_rate": 1.0830621416395476e-05, "loss": 0.1192, "step": 14530 }, { "epoch": 6.76, "learning_rate": 1.0815124748179142e-05, "loss": 0.0829, "step": 14540 }, { "epoch": 6.76, "learning_rate": 1.079962807996281e-05, "loss": 0.1938, "step": 14550 }, { "epoch": 6.77, "learning_rate": 1.0784131411746475e-05, "loss": 0.0591, "step": 14560 }, { "epoch": 6.77, "learning_rate": 1.0768634743530143e-05, "loss": 0.0797, "step": 14570 }, { "epoch": 6.78, "learning_rate": 1.0753138075313807e-05, "loss": 0.1026, "step": 14580 }, { "epoch": 6.78, "learning_rate": 1.0737641407097474e-05, "loss": 0.208, "step": 14590 }, { "epoch": 6.79, "learning_rate": 1.072214473888114e-05, "loss": 0.4293, "step": 14600 }, { "epoch": 6.79, "learning_rate": 1.0706648070664808e-05, "loss": 0.2139, "step": 14610 }, { "epoch": 6.8, "learning_rate": 1.0691151402448473e-05, "loss": 0.3856, "step": 14620 }, { "epoch": 6.8, "learning_rate": 1.0675654734232141e-05, "loss": 0.0709, "step": 14630 }, { "epoch": 6.81, "learning_rate": 1.0660158066015807e-05, "loss": 0.1399, "step": 14640 }, { "epoch": 6.81, "learning_rate": 1.0644661397799474e-05, "loss": 0.1463, "step": 14650 }, { "epoch": 6.82, "learning_rate": 1.062916472958314e-05, "loss": 0.2953, "step": 14660 }, { "epoch": 6.82, "learning_rate": 1.0613668061366807e-05, "loss": 0.2367, "step": 14670 }, { "epoch": 6.82, "learning_rate": 1.0598171393150473e-05, "loss": 0.0831, "step": 14680 }, { "epoch": 6.83, "learning_rate": 1.058267472493414e-05, "loss": 0.0993, "step": 14690 }, { "epoch": 6.83, "learning_rate": 1.0567178056717805e-05, "loss": 0.1645, "step": 14700 }, { "epoch": 6.84, "learning_rate": 1.0551681388501472e-05, "loss": 0.0895, "step": 14710 }, { "epoch": 6.84, "learning_rate": 1.0536184720285138e-05, "loss": 0.2147, "step": 14720 }, { "epoch": 6.85, "learning_rate": 1.0520688052068806e-05, "loss": 0.3754, "step": 14730 }, { "epoch": 6.85, "learning_rate": 1.0505191383852471e-05, "loss": 0.2089, "step": 14740 }, { "epoch": 6.86, "learning_rate": 1.0489694715636139e-05, "loss": 0.1646, "step": 14750 }, { "epoch": 6.86, "learning_rate": 1.0474198047419805e-05, "loss": 0.1797, "step": 14760 }, { "epoch": 6.87, "learning_rate": 1.0458701379203472e-05, "loss": 0.2464, "step": 14770 }, { "epoch": 6.87, "learning_rate": 1.0443204710987138e-05, "loss": 0.3507, "step": 14780 }, { "epoch": 6.88, "learning_rate": 1.0427708042770805e-05, "loss": 0.091, "step": 14790 }, { "epoch": 6.88, "learning_rate": 1.0412211374554471e-05, "loss": 0.415, "step": 14800 }, { "epoch": 6.89, "learning_rate": 1.0396714706338139e-05, "loss": 0.2619, "step": 14810 }, { "epoch": 6.89, "learning_rate": 1.0381218038121804e-05, "loss": 0.0688, "step": 14820 }, { "epoch": 6.89, "learning_rate": 1.036572136990547e-05, "loss": 0.1622, "step": 14830 }, { "epoch": 6.9, "learning_rate": 1.0350224701689136e-05, "loss": 0.0825, "step": 14840 }, { "epoch": 6.9, "learning_rate": 1.0334728033472803e-05, "loss": 0.2034, "step": 14850 }, { "epoch": 6.91, "learning_rate": 1.031923136525647e-05, "loss": 0.0951, "step": 14860 }, { "epoch": 6.91, "learning_rate": 1.0303734697040137e-05, "loss": 0.2086, "step": 14870 }, { "epoch": 6.92, "learning_rate": 1.0288238028823803e-05, "loss": 0.0577, "step": 14880 }, { "epoch": 6.92, "learning_rate": 1.027274136060747e-05, "loss": 0.2179, "step": 14890 }, { "epoch": 6.93, "learning_rate": 1.0257244692391136e-05, "loss": 0.1198, "step": 14900 }, { "epoch": 6.93, "learning_rate": 1.0241748024174803e-05, "loss": 0.1049, "step": 14910 }, { "epoch": 6.94, "learning_rate": 1.0226251355958469e-05, "loss": 0.3032, "step": 14920 }, { "epoch": 6.94, "learning_rate": 1.0210754687742137e-05, "loss": 0.3674, "step": 14930 }, { "epoch": 6.95, "learning_rate": 1.0195258019525802e-05, "loss": 0.1696, "step": 14940 }, { "epoch": 6.95, "learning_rate": 1.0179761351309468e-05, "loss": 0.2785, "step": 14950 }, { "epoch": 6.95, "learning_rate": 1.0164264683093134e-05, "loss": 0.1236, "step": 14960 }, { "epoch": 6.96, "learning_rate": 1.0148768014876801e-05, "loss": 0.231, "step": 14970 }, { "epoch": 6.96, "learning_rate": 1.0133271346660467e-05, "loss": 0.1885, "step": 14980 }, { "epoch": 6.97, "learning_rate": 1.0117774678444135e-05, "loss": 0.2478, "step": 14990 }, { "epoch": 6.97, "learning_rate": 1.01022780102278e-05, "loss": 0.3233, "step": 15000 }, { "epoch": 6.98, "learning_rate": 1.0086781342011468e-05, "loss": 0.1368, "step": 15010 }, { "epoch": 6.98, "learning_rate": 1.0071284673795134e-05, "loss": 0.1488, "step": 15020 }, { "epoch": 6.99, "learning_rate": 1.0055788005578801e-05, "loss": 0.1132, "step": 15030 }, { "epoch": 6.99, "learning_rate": 1.0040291337362467e-05, "loss": 0.3882, "step": 15040 }, { "epoch": 7.0, "learning_rate": 1.0024794669146135e-05, "loss": 0.1319, "step": 15050 }, { "epoch": 7.0, "eval_accuracy": 0.9789265722752717, "eval_loss": 0.10872756689786911, "eval_runtime": 17.2429, "eval_samples_per_second": 176.131, "eval_steps_per_second": 44.076, "step": 15057 }, { "epoch": 7.0, "learning_rate": 1.00092980009298e-05, "loss": 0.1708, "step": 15060 }, { "epoch": 7.01, "learning_rate": 9.993801332713468e-06, "loss": 0.2515, "step": 15070 }, { "epoch": 7.01, "learning_rate": 9.978304664497132e-06, "loss": 0.1733, "step": 15080 }, { "epoch": 7.02, "learning_rate": 9.9628079962808e-06, "loss": 0.1955, "step": 15090 }, { "epoch": 7.02, "learning_rate": 9.947311328064465e-06, "loss": 0.3123, "step": 15100 }, { "epoch": 7.02, "learning_rate": 9.931814659848133e-06, "loss": 0.0549, "step": 15110 }, { "epoch": 7.03, "learning_rate": 9.916317991631798e-06, "loss": 0.0458, "step": 15120 }, { "epoch": 7.03, "learning_rate": 9.900821323415466e-06, "loss": 0.0786, "step": 15130 }, { "epoch": 7.04, "learning_rate": 9.885324655199132e-06, "loss": 0.1529, "step": 15140 }, { "epoch": 7.04, "learning_rate": 9.8698279869828e-06, "loss": 0.0907, "step": 15150 }, { "epoch": 7.05, "learning_rate": 9.854331318766465e-06, "loss": 0.092, "step": 15160 }, { "epoch": 7.05, "learning_rate": 9.838834650550132e-06, "loss": 0.3792, "step": 15170 }, { "epoch": 7.06, "learning_rate": 9.823337982333798e-06, "loss": 0.1769, "step": 15180 }, { "epoch": 7.06, "learning_rate": 9.807841314117466e-06, "loss": 0.1373, "step": 15190 }, { "epoch": 7.07, "learning_rate": 9.792344645901132e-06, "loss": 0.1044, "step": 15200 }, { "epoch": 7.07, "learning_rate": 9.776847977684797e-06, "loss": 0.0664, "step": 15210 }, { "epoch": 7.08, "learning_rate": 9.761351309468465e-06, "loss": 0.2296, "step": 15220 }, { "epoch": 7.08, "learning_rate": 9.74585464125213e-06, "loss": 0.3984, "step": 15230 }, { "epoch": 7.09, "learning_rate": 9.730357973035798e-06, "loss": 0.1523, "step": 15240 }, { "epoch": 7.09, "learning_rate": 9.714861304819464e-06, "loss": 0.0526, "step": 15250 }, { "epoch": 7.09, "learning_rate": 9.699364636603131e-06, "loss": 0.1269, "step": 15260 }, { "epoch": 7.1, "learning_rate": 9.683867968386797e-06, "loss": 0.289, "step": 15270 }, { "epoch": 7.1, "learning_rate": 9.668371300170465e-06, "loss": 0.0285, "step": 15280 }, { "epoch": 7.11, "learning_rate": 9.65287463195413e-06, "loss": 0.0599, "step": 15290 }, { "epoch": 7.11, "learning_rate": 9.637377963737798e-06, "loss": 0.121, "step": 15300 }, { "epoch": 7.12, "learning_rate": 9.621881295521464e-06, "loss": 0.0041, "step": 15310 }, { "epoch": 7.12, "learning_rate": 9.60638462730513e-06, "loss": 0.2209, "step": 15320 }, { "epoch": 7.13, "learning_rate": 9.590887959088795e-06, "loss": 0.1529, "step": 15330 }, { "epoch": 7.13, "learning_rate": 9.575391290872463e-06, "loss": 0.1067, "step": 15340 }, { "epoch": 7.14, "learning_rate": 9.559894622656129e-06, "loss": 0.0675, "step": 15350 }, { "epoch": 7.14, "learning_rate": 9.544397954439796e-06, "loss": 0.0939, "step": 15360 }, { "epoch": 7.15, "learning_rate": 9.528901286223462e-06, "loss": 0.297, "step": 15370 }, { "epoch": 7.15, "learning_rate": 9.51340461800713e-06, "loss": 0.0538, "step": 15380 }, { "epoch": 7.15, "learning_rate": 9.497907949790795e-06, "loss": 0.1045, "step": 15390 }, { "epoch": 7.16, "learning_rate": 9.482411281574463e-06, "loss": 0.1477, "step": 15400 }, { "epoch": 7.16, "learning_rate": 9.466914613358128e-06, "loss": 0.061, "step": 15410 }, { "epoch": 7.17, "learning_rate": 9.451417945141796e-06, "loss": 0.0951, "step": 15420 }, { "epoch": 7.17, "learning_rate": 9.435921276925462e-06, "loss": 0.1163, "step": 15430 }, { "epoch": 7.18, "learning_rate": 9.42042460870913e-06, "loss": 0.2016, "step": 15440 }, { "epoch": 7.18, "learning_rate": 9.404927940492793e-06, "loss": 0.0333, "step": 15450 }, { "epoch": 7.19, "learning_rate": 9.38943127227646e-06, "loss": 0.0091, "step": 15460 }, { "epoch": 7.19, "learning_rate": 9.373934604060127e-06, "loss": 0.3396, "step": 15470 }, { "epoch": 7.2, "learning_rate": 9.358437935843794e-06, "loss": 0.0027, "step": 15480 }, { "epoch": 7.2, "learning_rate": 9.34294126762746e-06, "loss": 0.1906, "step": 15490 }, { "epoch": 7.21, "learning_rate": 9.327444599411127e-06, "loss": 0.2862, "step": 15500 }, { "epoch": 7.21, "learning_rate": 9.311947931194793e-06, "loss": 0.0614, "step": 15510 }, { "epoch": 7.22, "learning_rate": 9.29645126297846e-06, "loss": 0.133, "step": 15520 }, { "epoch": 7.22, "learning_rate": 9.280954594762126e-06, "loss": 0.1031, "step": 15530 }, { "epoch": 7.22, "learning_rate": 9.265457926545794e-06, "loss": 0.1839, "step": 15540 }, { "epoch": 7.23, "learning_rate": 9.24996125832946e-06, "loss": 0.0742, "step": 15550 }, { "epoch": 7.23, "learning_rate": 9.234464590113127e-06, "loss": 0.2748, "step": 15560 }, { "epoch": 7.24, "learning_rate": 9.218967921896791e-06, "loss": 0.3583, "step": 15570 }, { "epoch": 7.24, "learning_rate": 9.203471253680459e-06, "loss": 0.0343, "step": 15580 }, { "epoch": 7.25, "learning_rate": 9.187974585464124e-06, "loss": 0.3678, "step": 15590 }, { "epoch": 7.25, "learning_rate": 9.172477917247792e-06, "loss": 0.0024, "step": 15600 }, { "epoch": 7.26, "learning_rate": 9.156981249031458e-06, "loss": 0.111, "step": 15610 }, { "epoch": 7.26, "learning_rate": 9.141484580815125e-06, "loss": 0.1994, "step": 15620 }, { "epoch": 7.27, "learning_rate": 9.125987912598791e-06, "loss": 0.2164, "step": 15630 }, { "epoch": 7.27, "learning_rate": 9.110491244382459e-06, "loss": 0.2001, "step": 15640 }, { "epoch": 7.28, "learning_rate": 9.094994576166124e-06, "loss": 0.0191, "step": 15650 }, { "epoch": 7.28, "learning_rate": 9.079497907949792e-06, "loss": 0.1286, "step": 15660 }, { "epoch": 7.28, "learning_rate": 9.064001239733458e-06, "loss": 0.1652, "step": 15670 }, { "epoch": 7.29, "learning_rate": 9.048504571517125e-06, "loss": 0.1685, "step": 15680 }, { "epoch": 7.29, "learning_rate": 9.033007903300791e-06, "loss": 0.1938, "step": 15690 }, { "epoch": 7.3, "learning_rate": 9.017511235084457e-06, "loss": 0.1407, "step": 15700 }, { "epoch": 7.3, "learning_rate": 9.002014566868122e-06, "loss": 0.1829, "step": 15710 }, { "epoch": 7.31, "learning_rate": 8.98651789865179e-06, "loss": 0.0607, "step": 15720 }, { "epoch": 7.31, "learning_rate": 8.971021230435456e-06, "loss": 0.3167, "step": 15730 }, { "epoch": 7.32, "learning_rate": 8.955524562219123e-06, "loss": 0.1105, "step": 15740 }, { "epoch": 7.32, "learning_rate": 8.940027894002789e-06, "loss": 0.1907, "step": 15750 }, { "epoch": 7.33, "learning_rate": 8.924531225786456e-06, "loss": 0.0641, "step": 15760 }, { "epoch": 7.33, "learning_rate": 8.909034557570122e-06, "loss": 0.2064, "step": 15770 }, { "epoch": 7.34, "learning_rate": 8.89353788935379e-06, "loss": 0.0045, "step": 15780 }, { "epoch": 7.34, "learning_rate": 8.878041221137456e-06, "loss": 0.1104, "step": 15790 }, { "epoch": 7.35, "learning_rate": 8.862544552921123e-06, "loss": 0.0997, "step": 15800 }, { "epoch": 7.35, "learning_rate": 8.847047884704789e-06, "loss": 0.1006, "step": 15810 }, { "epoch": 7.35, "learning_rate": 8.831551216488455e-06, "loss": 0.0891, "step": 15820 }, { "epoch": 7.36, "learning_rate": 8.81605454827212e-06, "loss": 0.0535, "step": 15830 }, { "epoch": 7.36, "learning_rate": 8.800557880055788e-06, "loss": 0.2747, "step": 15840 }, { "epoch": 7.37, "learning_rate": 8.785061211839454e-06, "loss": 0.1308, "step": 15850 }, { "epoch": 7.37, "learning_rate": 8.769564543623121e-06, "loss": 0.079, "step": 15860 }, { "epoch": 7.38, "learning_rate": 8.754067875406787e-06, "loss": 0.0534, "step": 15870 }, { "epoch": 7.38, "learning_rate": 8.738571207190454e-06, "loss": 0.1435, "step": 15880 }, { "epoch": 7.39, "learning_rate": 8.72307453897412e-06, "loss": 0.0688, "step": 15890 }, { "epoch": 7.39, "learning_rate": 8.707577870757788e-06, "loss": 0.1386, "step": 15900 }, { "epoch": 7.4, "learning_rate": 8.692081202541453e-06, "loss": 0.2127, "step": 15910 }, { "epoch": 7.4, "learning_rate": 8.676584534325121e-06, "loss": 0.1386, "step": 15920 }, { "epoch": 7.41, "learning_rate": 8.661087866108787e-06, "loss": 0.0835, "step": 15930 }, { "epoch": 7.41, "learning_rate": 8.645591197892454e-06, "loss": 0.2212, "step": 15940 }, { "epoch": 7.42, "learning_rate": 8.630094529676118e-06, "loss": 0.2225, "step": 15950 }, { "epoch": 7.42, "learning_rate": 8.614597861459786e-06, "loss": 0.0939, "step": 15960 }, { "epoch": 7.42, "learning_rate": 8.599101193243452e-06, "loss": 0.0194, "step": 15970 }, { "epoch": 7.43, "learning_rate": 8.583604525027119e-06, "loss": 0.2879, "step": 15980 }, { "epoch": 7.43, "learning_rate": 8.568107856810785e-06, "loss": 0.0863, "step": 15990 }, { "epoch": 7.44, "learning_rate": 8.552611188594452e-06, "loss": 0.145, "step": 16000 }, { "epoch": 7.44, "learning_rate": 8.537114520378118e-06, "loss": 0.1236, "step": 16010 }, { "epoch": 7.45, "learning_rate": 8.521617852161786e-06, "loss": 0.2345, "step": 16020 }, { "epoch": 7.45, "learning_rate": 8.506121183945451e-06, "loss": 0.2312, "step": 16030 }, { "epoch": 7.46, "learning_rate": 8.490624515729119e-06, "loss": 0.0682, "step": 16040 }, { "epoch": 7.46, "learning_rate": 8.475127847512786e-06, "loss": 0.1497, "step": 16050 }, { "epoch": 7.47, "learning_rate": 8.459631179296452e-06, "loss": 0.0016, "step": 16060 }, { "epoch": 7.47, "learning_rate": 8.444134511080118e-06, "loss": 0.3009, "step": 16070 }, { "epoch": 7.48, "learning_rate": 8.428637842863784e-06, "loss": 0.2538, "step": 16080 }, { "epoch": 7.48, "learning_rate": 8.413141174647451e-06, "loss": 0.0944, "step": 16090 }, { "epoch": 7.48, "learning_rate": 8.397644506431117e-06, "loss": 0.1941, "step": 16100 }, { "epoch": 7.49, "learning_rate": 8.382147838214785e-06, "loss": 0.007, "step": 16110 }, { "epoch": 7.49, "learning_rate": 8.36665116999845e-06, "loss": 0.3934, "step": 16120 }, { "epoch": 7.5, "learning_rate": 8.351154501782118e-06, "loss": 0.0915, "step": 16130 }, { "epoch": 7.5, "learning_rate": 8.335657833565784e-06, "loss": 0.1373, "step": 16140 }, { "epoch": 7.51, "learning_rate": 8.320161165349451e-06, "loss": 0.0626, "step": 16150 }, { "epoch": 7.51, "learning_rate": 8.304664497133117e-06, "loss": 0.0624, "step": 16160 }, { "epoch": 7.52, "learning_rate": 8.289167828916784e-06, "loss": 0.0458, "step": 16170 }, { "epoch": 7.52, "learning_rate": 8.27367116070045e-06, "loss": 0.2246, "step": 16180 }, { "epoch": 7.53, "learning_rate": 8.258174492484118e-06, "loss": 0.1318, "step": 16190 }, { "epoch": 7.53, "learning_rate": 8.242677824267782e-06, "loss": 0.0221, "step": 16200 }, { "epoch": 7.54, "learning_rate": 8.22718115605145e-06, "loss": 0.2664, "step": 16210 }, { "epoch": 7.54, "learning_rate": 8.211684487835115e-06, "loss": 0.0027, "step": 16220 }, { "epoch": 7.55, "learning_rate": 8.196187819618782e-06, "loss": 0.1597, "step": 16230 }, { "epoch": 7.55, "learning_rate": 8.180691151402448e-06, "loss": 0.2088, "step": 16240 }, { "epoch": 7.55, "learning_rate": 8.165194483186116e-06, "loss": 0.2231, "step": 16250 }, { "epoch": 7.56, "learning_rate": 8.149697814969782e-06, "loss": 0.2694, "step": 16260 }, { "epoch": 7.56, "learning_rate": 8.134201146753449e-06, "loss": 0.0034, "step": 16270 }, { "epoch": 7.57, "learning_rate": 8.118704478537115e-06, "loss": 0.0549, "step": 16280 }, { "epoch": 7.57, "learning_rate": 8.103207810320782e-06, "loss": 0.1103, "step": 16290 }, { "epoch": 7.58, "learning_rate": 8.087711142104448e-06, "loss": 0.0032, "step": 16300 }, { "epoch": 7.58, "learning_rate": 8.072214473888116e-06, "loss": 0.0827, "step": 16310 }, { "epoch": 7.59, "learning_rate": 8.05671780567178e-06, "loss": 0.1303, "step": 16320 }, { "epoch": 7.59, "learning_rate": 8.041221137455447e-06, "loss": 0.129, "step": 16330 }, { "epoch": 7.6, "learning_rate": 8.025724469239113e-06, "loss": 0.1739, "step": 16340 }, { "epoch": 7.6, "learning_rate": 8.01022780102278e-06, "loss": 0.0765, "step": 16350 }, { "epoch": 7.61, "learning_rate": 7.994731132806446e-06, "loss": 0.1083, "step": 16360 }, { "epoch": 7.61, "learning_rate": 7.979234464590114e-06, "loss": 0.0901, "step": 16370 }, { "epoch": 7.62, "learning_rate": 7.96373779637378e-06, "loss": 0.0506, "step": 16380 }, { "epoch": 7.62, "learning_rate": 7.948241128157447e-06, "loss": 0.0382, "step": 16390 }, { "epoch": 7.62, "learning_rate": 7.932744459941113e-06, "loss": 0.0841, "step": 16400 }, { "epoch": 7.63, "learning_rate": 7.91724779172478e-06, "loss": 0.2492, "step": 16410 }, { "epoch": 7.63, "learning_rate": 7.901751123508446e-06, "loss": 0.0846, "step": 16420 }, { "epoch": 7.64, "learning_rate": 7.886254455292114e-06, "loss": 0.0028, "step": 16430 }, { "epoch": 7.64, "learning_rate": 7.87075778707578e-06, "loss": 0.1131, "step": 16440 }, { "epoch": 7.65, "learning_rate": 7.855261118859445e-06, "loss": 0.1876, "step": 16450 }, { "epoch": 7.65, "learning_rate": 7.839764450643111e-06, "loss": 0.088, "step": 16460 }, { "epoch": 7.66, "learning_rate": 7.824267782426778e-06, "loss": 0.2712, "step": 16470 }, { "epoch": 7.66, "learning_rate": 7.808771114210444e-06, "loss": 0.1309, "step": 16480 }, { "epoch": 7.67, "learning_rate": 7.793274445994112e-06, "loss": 0.1477, "step": 16490 }, { "epoch": 7.67, "learning_rate": 7.777777777777777e-06, "loss": 0.1527, "step": 16500 }, { "epoch": 7.68, "learning_rate": 7.762281109561445e-06, "loss": 0.0907, "step": 16510 }, { "epoch": 7.68, "learning_rate": 7.74678444134511e-06, "loss": 0.0049, "step": 16520 }, { "epoch": 7.68, "learning_rate": 7.731287773128778e-06, "loss": 0.2083, "step": 16530 }, { "epoch": 7.69, "learning_rate": 7.715791104912444e-06, "loss": 0.1156, "step": 16540 }, { "epoch": 7.69, "learning_rate": 7.700294436696112e-06, "loss": 0.2825, "step": 16550 }, { "epoch": 7.7, "learning_rate": 7.684797768479777e-06, "loss": 0.1159, "step": 16560 }, { "epoch": 7.7, "learning_rate": 7.669301100263443e-06, "loss": 0.0711, "step": 16570 }, { "epoch": 7.71, "learning_rate": 7.653804432047109e-06, "loss": 0.2192, "step": 16580 }, { "epoch": 7.71, "learning_rate": 7.638307763830776e-06, "loss": 0.1037, "step": 16590 }, { "epoch": 7.72, "learning_rate": 7.622811095614442e-06, "loss": 0.1424, "step": 16600 }, { "epoch": 7.72, "learning_rate": 7.60731442739811e-06, "loss": 0.216, "step": 16610 }, { "epoch": 7.73, "learning_rate": 7.5918177591817754e-06, "loss": 0.0876, "step": 16620 }, { "epoch": 7.73, "learning_rate": 7.576321090965443e-06, "loss": 0.1751, "step": 16630 }, { "epoch": 7.74, "learning_rate": 7.560824422749109e-06, "loss": 0.1445, "step": 16640 }, { "epoch": 7.74, "learning_rate": 7.545327754532776e-06, "loss": 0.1459, "step": 16650 }, { "epoch": 7.75, "learning_rate": 7.529831086316442e-06, "loss": 0.222, "step": 16660 }, { "epoch": 7.75, "learning_rate": 7.514334418100109e-06, "loss": 0.0253, "step": 16670 }, { "epoch": 7.75, "learning_rate": 7.498837749883775e-06, "loss": 0.2423, "step": 16680 }, { "epoch": 7.76, "learning_rate": 7.483341081667442e-06, "loss": 0.2054, "step": 16690 }, { "epoch": 7.76, "learning_rate": 7.4678444134511085e-06, "loss": 0.1258, "step": 16700 }, { "epoch": 7.77, "learning_rate": 7.452347745234775e-06, "loss": 0.0495, "step": 16710 }, { "epoch": 7.77, "learning_rate": 7.436851077018442e-06, "loss": 0.0716, "step": 16720 }, { "epoch": 7.78, "learning_rate": 7.421354408802108e-06, "loss": 0.0371, "step": 16730 }, { "epoch": 7.78, "learning_rate": 7.405857740585774e-06, "loss": 0.1346, "step": 16740 }, { "epoch": 7.79, "learning_rate": 7.390361072369441e-06, "loss": 0.1465, "step": 16750 }, { "epoch": 7.79, "learning_rate": 7.3748644041531075e-06, "loss": 0.025, "step": 16760 }, { "epoch": 7.8, "learning_rate": 7.359367735936774e-06, "loss": 0.2293, "step": 16770 }, { "epoch": 7.8, "learning_rate": 7.343871067720441e-06, "loss": 0.1768, "step": 16780 }, { "epoch": 7.81, "learning_rate": 7.3283743995041066e-06, "loss": 0.091, "step": 16790 }, { "epoch": 7.81, "learning_rate": 7.312877731287773e-06, "loss": 0.1603, "step": 16800 }, { "epoch": 7.81, "learning_rate": 7.29738106307144e-06, "loss": 0.0076, "step": 16810 }, { "epoch": 7.82, "learning_rate": 7.2818843948551065e-06, "loss": 0.2233, "step": 16820 }, { "epoch": 7.82, "learning_rate": 7.266387726638773e-06, "loss": 0.0052, "step": 16830 }, { "epoch": 7.83, "learning_rate": 7.25089105842244e-06, "loss": 0.0976, "step": 16840 }, { "epoch": 7.83, "learning_rate": 7.2353943902061055e-06, "loss": 0.1401, "step": 16850 }, { "epoch": 7.84, "learning_rate": 7.219897721989772e-06, "loss": 0.1559, "step": 16860 }, { "epoch": 7.84, "learning_rate": 7.204401053773439e-06, "loss": 0.2169, "step": 16870 }, { "epoch": 7.85, "learning_rate": 7.1889043855571055e-06, "loss": 0.0884, "step": 16880 }, { "epoch": 7.85, "learning_rate": 7.173407717340772e-06, "loss": 0.0743, "step": 16890 }, { "epoch": 7.86, "learning_rate": 7.157911049124439e-06, "loss": 0.3376, "step": 16900 }, { "epoch": 7.86, "learning_rate": 7.142414380908105e-06, "loss": 0.0255, "step": 16910 }, { "epoch": 7.87, "learning_rate": 7.126917712691771e-06, "loss": 0.0286, "step": 16920 }, { "epoch": 7.87, "learning_rate": 7.111421044475438e-06, "loss": 0.0028, "step": 16930 }, { "epoch": 7.88, "learning_rate": 7.0959243762591044e-06, "loss": 0.2599, "step": 16940 }, { "epoch": 7.88, "learning_rate": 7.080427708042771e-06, "loss": 0.0389, "step": 16950 }, { "epoch": 7.88, "learning_rate": 7.064931039826438e-06, "loss": 0.1285, "step": 16960 }, { "epoch": 7.89, "learning_rate": 7.049434371610104e-06, "loss": 0.1612, "step": 16970 }, { "epoch": 7.89, "learning_rate": 7.03393770339377e-06, "loss": 0.0285, "step": 16980 }, { "epoch": 7.9, "learning_rate": 7.018441035177437e-06, "loss": 0.0944, "step": 16990 }, { "epoch": 7.9, "learning_rate": 7.002944366961103e-06, "loss": 0.1581, "step": 17000 }, { "epoch": 7.91, "learning_rate": 6.98744769874477e-06, "loss": 0.202, "step": 17010 }, { "epoch": 7.91, "learning_rate": 6.971951030528437e-06, "loss": 0.1744, "step": 17020 }, { "epoch": 7.92, "learning_rate": 6.9580040291337366e-06, "loss": 0.3009, "step": 17030 }, { "epoch": 7.92, "learning_rate": 6.942507360917403e-06, "loss": 0.0864, "step": 17040 }, { "epoch": 7.93, "learning_rate": 6.92701069270107e-06, "loss": 0.212, "step": 17050 }, { "epoch": 7.93, "learning_rate": 6.9115140244847365e-06, "loss": 0.2234, "step": 17060 }, { "epoch": 7.94, "learning_rate": 6.896017356268402e-06, "loss": 0.0449, "step": 17070 }, { "epoch": 7.94, "learning_rate": 6.880520688052069e-06, "loss": 0.0892, "step": 17080 }, { "epoch": 7.95, "learning_rate": 6.8650240198357356e-06, "loss": 0.2014, "step": 17090 }, { "epoch": 7.95, "learning_rate": 6.849527351619402e-06, "loss": 0.174, "step": 17100 }, { "epoch": 7.95, "learning_rate": 6.834030683403069e-06, "loss": 0.0537, "step": 17110 }, { "epoch": 7.96, "learning_rate": 6.8185340151867355e-06, "loss": 0.2684, "step": 17120 }, { "epoch": 7.96, "learning_rate": 6.803037346970401e-06, "loss": 0.0025, "step": 17130 }, { "epoch": 7.97, "learning_rate": 6.787540678754068e-06, "loss": 0.007, "step": 17140 }, { "epoch": 7.97, "learning_rate": 6.7720440105377345e-06, "loss": 0.1587, "step": 17150 }, { "epoch": 7.98, "learning_rate": 6.756547342321401e-06, "loss": 0.2571, "step": 17160 }, { "epoch": 7.98, "learning_rate": 6.741050674105068e-06, "loss": 0.0534, "step": 17170 }, { "epoch": 7.99, "learning_rate": 6.7255540058887344e-06, "loss": 0.1896, "step": 17180 }, { "epoch": 7.99, "learning_rate": 6.7100573376724e-06, "loss": 0.1856, "step": 17190 }, { "epoch": 8.0, "learning_rate": 6.694560669456067e-06, "loss": 0.0646, "step": 17200 }, { "epoch": 8.0, "eval_accuracy": 0.9739874876522885, "eval_loss": 0.13712750375270844, "eval_runtime": 17.5393, "eval_samples_per_second": 173.154, "eval_steps_per_second": 43.331, "step": 17208 }, { "epoch": 8.0, "learning_rate": 6.6790640012397335e-06, "loss": 0.2262, "step": 17210 }, { "epoch": 8.01, "learning_rate": 6.6635673330234e-06, "loss": 0.1837, "step": 17220 }, { "epoch": 8.01, "learning_rate": 6.648070664807067e-06, "loss": 0.1265, "step": 17230 }, { "epoch": 8.01, "learning_rate": 6.632573996590733e-06, "loss": 0.1258, "step": 17240 }, { "epoch": 8.02, "learning_rate": 6.617077328374399e-06, "loss": 0.0651, "step": 17250 }, { "epoch": 8.02, "learning_rate": 6.601580660158066e-06, "loss": 0.3102, "step": 17260 }, { "epoch": 8.03, "learning_rate": 6.5860839919417325e-06, "loss": 0.1612, "step": 17270 }, { "epoch": 8.03, "learning_rate": 6.570587323725399e-06, "loss": 0.1483, "step": 17280 }, { "epoch": 8.04, "learning_rate": 6.555090655509066e-06, "loss": 0.0733, "step": 17290 }, { "epoch": 8.04, "learning_rate": 6.539593987292732e-06, "loss": 0.0171, "step": 17300 }, { "epoch": 8.05, "learning_rate": 6.524097319076399e-06, "loss": 0.2636, "step": 17310 }, { "epoch": 8.05, "learning_rate": 6.508600650860065e-06, "loss": 0.2274, "step": 17320 }, { "epoch": 8.06, "learning_rate": 6.4931039826437315e-06, "loss": 0.0884, "step": 17330 }, { "epoch": 8.06, "learning_rate": 6.477607314427398e-06, "loss": 0.2319, "step": 17340 }, { "epoch": 8.07, "learning_rate": 6.462110646211065e-06, "loss": 0.0403, "step": 17350 }, { "epoch": 8.07, "learning_rate": 6.446613977994731e-06, "loss": 0.0503, "step": 17360 }, { "epoch": 8.08, "learning_rate": 6.431117309778398e-06, "loss": 0.0743, "step": 17370 }, { "epoch": 8.08, "learning_rate": 6.415620641562064e-06, "loss": 0.0994, "step": 17380 }, { "epoch": 8.08, "learning_rate": 6.4001239733457304e-06, "loss": 0.0959, "step": 17390 }, { "epoch": 8.09, "learning_rate": 6.384627305129397e-06, "loss": 0.1529, "step": 17400 }, { "epoch": 8.09, "learning_rate": 6.369130636913064e-06, "loss": 0.0031, "step": 17410 }, { "epoch": 8.1, "learning_rate": 6.35363396869673e-06, "loss": 0.1075, "step": 17420 }, { "epoch": 8.1, "learning_rate": 6.338137300480397e-06, "loss": 0.0573, "step": 17430 }, { "epoch": 8.11, "learning_rate": 6.322640632264063e-06, "loss": 0.2425, "step": 17440 }, { "epoch": 8.11, "learning_rate": 6.307143964047729e-06, "loss": 0.1474, "step": 17450 }, { "epoch": 8.12, "learning_rate": 6.291647295831396e-06, "loss": 0.2, "step": 17460 }, { "epoch": 8.12, "learning_rate": 6.276150627615063e-06, "loss": 0.1569, "step": 17470 }, { "epoch": 8.13, "learning_rate": 6.260653959398729e-06, "loss": 0.1137, "step": 17480 }, { "epoch": 8.13, "learning_rate": 6.245157291182396e-06, "loss": 0.0912, "step": 17490 }, { "epoch": 8.14, "learning_rate": 6.229660622966062e-06, "loss": 0.1301, "step": 17500 }, { "epoch": 8.14, "learning_rate": 6.214163954749728e-06, "loss": 0.0062, "step": 17510 }, { "epoch": 8.15, "learning_rate": 6.198667286533395e-06, "loss": 0.1619, "step": 17520 }, { "epoch": 8.15, "learning_rate": 6.183170618317062e-06, "loss": 0.1377, "step": 17530 }, { "epoch": 8.15, "learning_rate": 6.167673950100728e-06, "loss": 0.0386, "step": 17540 }, { "epoch": 8.16, "learning_rate": 6.152177281884395e-06, "loss": 0.0695, "step": 17550 }, { "epoch": 8.16, "learning_rate": 6.136680613668062e-06, "loss": 0.0603, "step": 17560 }, { "epoch": 8.17, "learning_rate": 6.121183945451727e-06, "loss": 0.2312, "step": 17570 }, { "epoch": 8.17, "learning_rate": 6.105687277235394e-06, "loss": 0.018, "step": 17580 }, { "epoch": 8.18, "learning_rate": 6.090190609019061e-06, "loss": 0.1271, "step": 17590 }, { "epoch": 8.18, "learning_rate": 6.074693940802727e-06, "loss": 0.1665, "step": 17600 }, { "epoch": 8.19, "learning_rate": 6.059197272586394e-06, "loss": 0.1065, "step": 17610 }, { "epoch": 8.19, "learning_rate": 6.043700604370061e-06, "loss": 0.5536, "step": 17620 }, { "epoch": 8.2, "learning_rate": 6.028203936153727e-06, "loss": 0.1297, "step": 17630 }, { "epoch": 8.2, "learning_rate": 6.012707267937394e-06, "loss": 0.097, "step": 17640 }, { "epoch": 8.21, "learning_rate": 5.9972105997210605e-06, "loss": 0.0464, "step": 17650 }, { "epoch": 8.21, "learning_rate": 5.981713931504727e-06, "loss": 0.0168, "step": 17660 }, { "epoch": 8.21, "learning_rate": 5.966217263288394e-06, "loss": 0.0492, "step": 17670 }, { "epoch": 8.22, "learning_rate": 5.95072059507206e-06, "loss": 0.1815, "step": 17680 }, { "epoch": 8.22, "learning_rate": 5.935223926855726e-06, "loss": 0.2915, "step": 17690 }, { "epoch": 8.23, "learning_rate": 5.919727258639393e-06, "loss": 0.0628, "step": 17700 }, { "epoch": 8.23, "learning_rate": 5.9042305904230594e-06, "loss": 0.0442, "step": 17710 }, { "epoch": 8.24, "learning_rate": 5.888733922206726e-06, "loss": 0.0826, "step": 17720 }, { "epoch": 8.24, "learning_rate": 5.873237253990393e-06, "loss": 0.1191, "step": 17730 }, { "epoch": 8.25, "learning_rate": 5.857740585774059e-06, "loss": 0.1648, "step": 17740 }, { "epoch": 8.25, "learning_rate": 5.842243917557725e-06, "loss": 0.0023, "step": 17750 }, { "epoch": 8.26, "learning_rate": 5.826747249341392e-06, "loss": 0.1562, "step": 17760 }, { "epoch": 8.26, "learning_rate": 5.811250581125058e-06, "loss": 0.0411, "step": 17770 }, { "epoch": 8.27, "learning_rate": 5.795753912908725e-06, "loss": 0.0362, "step": 17780 }, { "epoch": 8.27, "learning_rate": 5.780257244692392e-06, "loss": 0.1763, "step": 17790 }, { "epoch": 8.28, "learning_rate": 5.764760576476058e-06, "loss": 0.0708, "step": 17800 }, { "epoch": 8.28, "learning_rate": 5.749263908259724e-06, "loss": 0.3768, "step": 17810 }, { "epoch": 8.28, "learning_rate": 5.733767240043391e-06, "loss": 0.277, "step": 17820 }, { "epoch": 8.29, "learning_rate": 5.718270571827057e-06, "loss": 0.1965, "step": 17830 }, { "epoch": 8.29, "learning_rate": 5.702773903610724e-06, "loss": 0.1794, "step": 17840 }, { "epoch": 8.3, "learning_rate": 5.687277235394391e-06, "loss": 0.0979, "step": 17850 }, { "epoch": 8.3, "learning_rate": 5.671780567178057e-06, "loss": 0.072, "step": 17860 }, { "epoch": 8.31, "learning_rate": 5.656283898961724e-06, "loss": 0.1873, "step": 17870 }, { "epoch": 8.31, "learning_rate": 5.64078723074539e-06, "loss": 0.0778, "step": 17880 }, { "epoch": 8.32, "learning_rate": 5.625290562529056e-06, "loss": 0.173, "step": 17890 }, { "epoch": 8.32, "learning_rate": 5.609793894312723e-06, "loss": 0.1449, "step": 17900 }, { "epoch": 8.33, "learning_rate": 5.59429722609639e-06, "loss": 0.0297, "step": 17910 }, { "epoch": 8.33, "learning_rate": 5.578800557880056e-06, "loss": 0.0418, "step": 17920 }, { "epoch": 8.34, "learning_rate": 5.563303889663723e-06, "loss": 0.0307, "step": 17930 }, { "epoch": 8.34, "learning_rate": 5.547807221447389e-06, "loss": 0.1582, "step": 17940 }, { "epoch": 8.34, "learning_rate": 5.532310553231055e-06, "loss": 0.1351, "step": 17950 }, { "epoch": 8.35, "learning_rate": 5.516813885014722e-06, "loss": 0.0991, "step": 17960 }, { "epoch": 8.35, "learning_rate": 5.501317216798389e-06, "loss": 0.0395, "step": 17970 }, { "epoch": 8.36, "learning_rate": 5.485820548582055e-06, "loss": 0.3475, "step": 17980 }, { "epoch": 8.36, "learning_rate": 5.470323880365722e-06, "loss": 0.1425, "step": 17990 }, { "epoch": 8.37, "learning_rate": 5.454827212149388e-06, "loss": 0.1808, "step": 18000 }, { "epoch": 8.37, "learning_rate": 5.439330543933054e-06, "loss": 0.034, "step": 18010 }, { "epoch": 8.38, "learning_rate": 5.423833875716721e-06, "loss": 0.1168, "step": 18020 }, { "epoch": 8.38, "learning_rate": 5.408337207500388e-06, "loss": 0.1169, "step": 18030 }, { "epoch": 8.39, "learning_rate": 5.392840539284054e-06, "loss": 0.05, "step": 18040 }, { "epoch": 8.39, "learning_rate": 5.377343871067721e-06, "loss": 0.1126, "step": 18050 }, { "epoch": 8.4, "learning_rate": 5.361847202851387e-06, "loss": 0.0158, "step": 18060 }, { "epoch": 8.4, "learning_rate": 5.346350534635053e-06, "loss": 0.015, "step": 18070 }, { "epoch": 8.41, "learning_rate": 5.33085386641872e-06, "loss": 0.0189, "step": 18080 }, { "epoch": 8.41, "learning_rate": 5.315357198202387e-06, "loss": 0.1123, "step": 18090 }, { "epoch": 8.41, "learning_rate": 5.299860529986053e-06, "loss": 0.1492, "step": 18100 }, { "epoch": 8.42, "learning_rate": 5.28436386176972e-06, "loss": 0.0464, "step": 18110 }, { "epoch": 8.42, "learning_rate": 5.2688671935533865e-06, "loss": 0.2331, "step": 18120 }, { "epoch": 8.43, "learning_rate": 5.253370525337052e-06, "loss": 0.1383, "step": 18130 }, { "epoch": 8.43, "learning_rate": 5.237873857120719e-06, "loss": 0.1527, "step": 18140 }, { "epoch": 8.44, "learning_rate": 5.2223771889043856e-06, "loss": 0.1064, "step": 18150 }, { "epoch": 8.44, "learning_rate": 5.206880520688052e-06, "loss": 0.1365, "step": 18160 }, { "epoch": 8.45, "learning_rate": 5.191383852471719e-06, "loss": 0.1485, "step": 18170 }, { "epoch": 8.45, "learning_rate": 5.1758871842553855e-06, "loss": 0.0667, "step": 18180 }, { "epoch": 8.46, "learning_rate": 5.160390516039051e-06, "loss": 0.2232, "step": 18190 }, { "epoch": 8.46, "learning_rate": 5.144893847822718e-06, "loss": 0.1358, "step": 18200 }, { "epoch": 8.47, "learning_rate": 5.1293971796063845e-06, "loss": 0.2614, "step": 18210 }, { "epoch": 8.47, "learning_rate": 5.113900511390051e-06, "loss": 0.1439, "step": 18220 }, { "epoch": 8.48, "learning_rate": 5.098403843173718e-06, "loss": 0.1751, "step": 18230 }, { "epoch": 8.48, "learning_rate": 5.0829071749573844e-06, "loss": 0.0027, "step": 18240 }, { "epoch": 8.48, "learning_rate": 5.06741050674105e-06, "loss": 0.2695, "step": 18250 }, { "epoch": 8.49, "learning_rate": 5.051913838524717e-06, "loss": 0.187, "step": 18260 }, { "epoch": 8.49, "learning_rate": 5.0364171703083835e-06, "loss": 0.3292, "step": 18270 }, { "epoch": 8.5, "learning_rate": 5.02092050209205e-06, "loss": 0.0624, "step": 18280 }, { "epoch": 8.5, "learning_rate": 5.005423833875717e-06, "loss": 0.0631, "step": 18290 }, { "epoch": 8.51, "learning_rate": 4.9899271656593834e-06, "loss": 0.0393, "step": 18300 }, { "epoch": 8.51, "learning_rate": 4.974430497443049e-06, "loss": 0.1088, "step": 18310 }, { "epoch": 8.52, "learning_rate": 4.958933829226716e-06, "loss": 0.0956, "step": 18320 }, { "epoch": 8.52, "learning_rate": 4.9434371610103825e-06, "loss": 0.0216, "step": 18330 }, { "epoch": 8.53, "learning_rate": 4.927940492794049e-06, "loss": 0.1236, "step": 18340 }, { "epoch": 8.53, "learning_rate": 4.912443824577716e-06, "loss": 0.3147, "step": 18350 }, { "epoch": 8.54, "learning_rate": 4.896947156361382e-06, "loss": 0.3294, "step": 18360 }, { "epoch": 8.54, "learning_rate": 4.881450488145049e-06, "loss": 0.0474, "step": 18370 }, { "epoch": 8.54, "learning_rate": 4.865953819928715e-06, "loss": 0.1255, "step": 18380 }, { "epoch": 8.55, "learning_rate": 4.8504571517123815e-06, "loss": 0.0888, "step": 18390 }, { "epoch": 8.55, "learning_rate": 4.834960483496048e-06, "loss": 0.1456, "step": 18400 }, { "epoch": 8.56, "learning_rate": 4.819463815279715e-06, "loss": 0.1489, "step": 18410 }, { "epoch": 8.56, "learning_rate": 4.803967147063381e-06, "loss": 0.0018, "step": 18420 }, { "epoch": 8.57, "learning_rate": 4.788470478847048e-06, "loss": 0.1444, "step": 18430 }, { "epoch": 8.57, "learning_rate": 4.772973810630714e-06, "loss": 0.1743, "step": 18440 }, { "epoch": 8.58, "learning_rate": 4.7574771424143804e-06, "loss": 0.0658, "step": 18450 }, { "epoch": 8.58, "learning_rate": 4.741980474198047e-06, "loss": 0.1066, "step": 18460 }, { "epoch": 8.59, "learning_rate": 4.726483805981714e-06, "loss": 0.1067, "step": 18470 }, { "epoch": 8.59, "learning_rate": 4.71098713776538e-06, "loss": 0.0035, "step": 18480 }, { "epoch": 8.6, "learning_rate": 4.695490469549048e-06, "loss": 0.1949, "step": 18490 }, { "epoch": 8.6, "learning_rate": 4.679993801332714e-06, "loss": 0.0048, "step": 18500 }, { "epoch": 8.61, "learning_rate": 4.66449713311638e-06, "loss": 0.2269, "step": 18510 }, { "epoch": 8.61, "learning_rate": 4.649000464900047e-06, "loss": 0.0265, "step": 18520 }, { "epoch": 8.61, "learning_rate": 4.6335037966837135e-06, "loss": 0.0228, "step": 18530 }, { "epoch": 8.62, "learning_rate": 4.61800712846738e-06, "loss": 0.243, "step": 18540 }, { "epoch": 8.62, "learning_rate": 4.602510460251047e-06, "loss": 0.2173, "step": 18550 }, { "epoch": 8.63, "learning_rate": 4.587013792034713e-06, "loss": 0.0026, "step": 18560 }, { "epoch": 8.63, "learning_rate": 4.571517123818379e-06, "loss": 0.0094, "step": 18570 }, { "epoch": 8.64, "learning_rate": 4.556020455602046e-06, "loss": 0.1997, "step": 18580 }, { "epoch": 8.64, "learning_rate": 4.5405237873857125e-06, "loss": 0.2019, "step": 18590 }, { "epoch": 8.65, "learning_rate": 4.525027119169379e-06, "loss": 0.2062, "step": 18600 }, { "epoch": 8.65, "learning_rate": 4.509530450953046e-06, "loss": 0.1384, "step": 18610 }, { "epoch": 8.66, "learning_rate": 4.494033782736712e-06, "loss": 0.0141, "step": 18620 }, { "epoch": 8.66, "learning_rate": 4.478537114520378e-06, "loss": 0.0996, "step": 18630 }, { "epoch": 8.67, "learning_rate": 4.463040446304045e-06, "loss": 0.4844, "step": 18640 }, { "epoch": 8.67, "learning_rate": 4.4475437780877115e-06, "loss": 0.1961, "step": 18650 }, { "epoch": 8.68, "learning_rate": 4.432047109871378e-06, "loss": 0.1568, "step": 18660 }, { "epoch": 8.68, "learning_rate": 4.416550441655045e-06, "loss": 0.1181, "step": 18670 }, { "epoch": 8.68, "learning_rate": 4.401053773438711e-06, "loss": 0.176, "step": 18680 }, { "epoch": 8.69, "learning_rate": 4.385557105222377e-06, "loss": 0.2728, "step": 18690 }, { "epoch": 8.69, "learning_rate": 4.370060437006044e-06, "loss": 0.2356, "step": 18700 }, { "epoch": 8.7, "learning_rate": 4.3545637687897105e-06, "loss": 0.1333, "step": 18710 }, { "epoch": 8.7, "learning_rate": 4.339067100573377e-06, "loss": 0.1476, "step": 18720 }, { "epoch": 8.71, "learning_rate": 4.323570432357044e-06, "loss": 0.1592, "step": 18730 }, { "epoch": 8.71, "learning_rate": 4.30807376414071e-06, "loss": 0.1635, "step": 18740 }, { "epoch": 8.72, "learning_rate": 4.292577095924376e-06, "loss": 0.0086, "step": 18750 }, { "epoch": 8.72, "learning_rate": 4.277080427708043e-06, "loss": 0.2478, "step": 18760 }, { "epoch": 8.73, "learning_rate": 4.2615837594917095e-06, "loss": 0.1388, "step": 18770 }, { "epoch": 8.73, "learning_rate": 4.246087091275376e-06, "loss": 0.0523, "step": 18780 }, { "epoch": 8.74, "learning_rate": 4.230590423059043e-06, "loss": 0.1501, "step": 18790 }, { "epoch": 8.74, "learning_rate": 4.215093754842709e-06, "loss": 0.0029, "step": 18800 }, { "epoch": 8.74, "learning_rate": 4.199597086626375e-06, "loss": 0.063, "step": 18810 }, { "epoch": 8.75, "learning_rate": 4.184100418410042e-06, "loss": 0.0687, "step": 18820 }, { "epoch": 8.75, "learning_rate": 4.1686037501937084e-06, "loss": 0.1215, "step": 18830 }, { "epoch": 8.76, "learning_rate": 4.153107081977375e-06, "loss": 0.1735, "step": 18840 }, { "epoch": 8.76, "learning_rate": 4.137610413761042e-06, "loss": 0.0016, "step": 18850 }, { "epoch": 8.77, "learning_rate": 4.122113745544708e-06, "loss": 0.0648, "step": 18860 }, { "epoch": 8.77, "learning_rate": 4.106617077328374e-06, "loss": 0.2182, "step": 18870 }, { "epoch": 8.78, "learning_rate": 4.091120409112041e-06, "loss": 0.1601, "step": 18880 }, { "epoch": 8.78, "learning_rate": 4.075623740895707e-06, "loss": 0.11, "step": 18890 }, { "epoch": 8.79, "learning_rate": 4.060127072679374e-06, "loss": 0.1182, "step": 18900 }, { "epoch": 8.79, "learning_rate": 4.044630404463041e-06, "loss": 0.2342, "step": 18910 }, { "epoch": 8.8, "learning_rate": 4.029133736246707e-06, "loss": 0.0474, "step": 18920 }, { "epoch": 8.8, "learning_rate": 4.013637068030374e-06, "loss": 0.1305, "step": 18930 }, { "epoch": 8.81, "learning_rate": 3.99814039981404e-06, "loss": 0.141, "step": 18940 }, { "epoch": 8.81, "learning_rate": 3.982643731597706e-06, "loss": 0.2511, "step": 18950 }, { "epoch": 8.81, "learning_rate": 3.967147063381373e-06, "loss": 0.1161, "step": 18960 }, { "epoch": 8.82, "learning_rate": 3.95165039516504e-06, "loss": 0.1686, "step": 18970 }, { "epoch": 8.82, "learning_rate": 3.936153726948706e-06, "loss": 0.2254, "step": 18980 }, { "epoch": 8.83, "learning_rate": 3.920657058732373e-06, "loss": 0.079, "step": 18990 }, { "epoch": 8.83, "learning_rate": 3.905160390516039e-06, "loss": 0.0219, "step": 19000 }, { "epoch": 8.84, "learning_rate": 3.889663722299705e-06, "loss": 0.1602, "step": 19010 }, { "epoch": 8.84, "learning_rate": 3.874167054083372e-06, "loss": 0.0658, "step": 19020 }, { "epoch": 8.85, "learning_rate": 3.858670385867039e-06, "loss": 0.0332, "step": 19030 }, { "epoch": 8.85, "learning_rate": 3.843173717650705e-06, "loss": 0.3521, "step": 19040 }, { "epoch": 8.86, "learning_rate": 3.827677049434372e-06, "loss": 0.0052, "step": 19050 }, { "epoch": 8.86, "learning_rate": 3.812180381218038e-06, "loss": 0.2244, "step": 19060 }, { "epoch": 8.87, "learning_rate": 3.7966837130017048e-06, "loss": 0.2198, "step": 19070 }, { "epoch": 8.87, "learning_rate": 3.781187044785371e-06, "loss": 0.1291, "step": 19080 }, { "epoch": 8.87, "learning_rate": 3.7656903765690376e-06, "loss": 0.0885, "step": 19090 }, { "epoch": 8.88, "learning_rate": 3.7501937083527043e-06, "loss": 0.1136, "step": 19100 }, { "epoch": 8.88, "learning_rate": 3.7346970401363705e-06, "loss": 0.0143, "step": 19110 }, { "epoch": 8.89, "learning_rate": 3.719200371920037e-06, "loss": 0.1678, "step": 19120 }, { "epoch": 8.89, "learning_rate": 3.7037037037037037e-06, "loss": 0.101, "step": 19130 }, { "epoch": 8.9, "learning_rate": 3.6882070354873704e-06, "loss": 0.0724, "step": 19140 }, { "epoch": 8.9, "learning_rate": 3.672710367271037e-06, "loss": 0.172, "step": 19150 }, { "epoch": 8.91, "learning_rate": 3.6572136990547037e-06, "loss": 0.058, "step": 19160 }, { "epoch": 8.91, "learning_rate": 3.64171703083837e-06, "loss": 0.0545, "step": 19170 }, { "epoch": 8.92, "learning_rate": 3.6262203626220365e-06, "loss": 0.0608, "step": 19180 }, { "epoch": 8.92, "learning_rate": 3.610723694405703e-06, "loss": 0.0018, "step": 19190 }, { "epoch": 8.93, "learning_rate": 3.5952270261893694e-06, "loss": 0.1482, "step": 19200 }, { "epoch": 8.93, "learning_rate": 3.579730357973036e-06, "loss": 0.1264, "step": 19210 }, { "epoch": 8.94, "learning_rate": 3.5642336897567026e-06, "loss": 0.058, "step": 19220 }, { "epoch": 8.94, "learning_rate": 3.548737021540369e-06, "loss": 0.184, "step": 19230 }, { "epoch": 8.94, "learning_rate": 3.5332403533240355e-06, "loss": 0.1888, "step": 19240 }, { "epoch": 8.95, "learning_rate": 3.517743685107702e-06, "loss": 0.0683, "step": 19250 }, { "epoch": 8.95, "learning_rate": 3.5022470168913683e-06, "loss": 0.0876, "step": 19260 }, { "epoch": 8.96, "learning_rate": 3.486750348675035e-06, "loss": 0.0173, "step": 19270 }, { "epoch": 8.96, "learning_rate": 3.4712536804587016e-06, "loss": 0.3668, "step": 19280 }, { "epoch": 8.97, "learning_rate": 3.4557570122423682e-06, "loss": 0.1494, "step": 19290 }, { "epoch": 8.97, "learning_rate": 3.4402603440260345e-06, "loss": 0.0465, "step": 19300 }, { "epoch": 8.98, "learning_rate": 3.424763675809701e-06, "loss": 0.2211, "step": 19310 }, { "epoch": 8.98, "learning_rate": 3.4092670075933677e-06, "loss": 0.1247, "step": 19320 }, { "epoch": 8.99, "learning_rate": 3.393770339377034e-06, "loss": 0.0963, "step": 19330 }, { "epoch": 8.99, "learning_rate": 3.3782736711607006e-06, "loss": 0.0996, "step": 19340 }, { "epoch": 9.0, "learning_rate": 3.3627770029443672e-06, "loss": 0.1035, "step": 19350 }, { "epoch": 9.0, "eval_accuracy": 0.9776094830424761, "eval_loss": 0.1219358742237091, "eval_runtime": 17.1629, "eval_samples_per_second": 176.951, "eval_steps_per_second": 44.281, "step": 19359 }, { "epoch": 9.0, "learning_rate": 3.3472803347280334e-06, "loss": 0.1543, "step": 19360 }, { "epoch": 9.01, "learning_rate": 3.3317836665117e-06, "loss": 0.0617, "step": 19370 }, { "epoch": 9.01, "learning_rate": 3.3162869982953667e-06, "loss": 0.1007, "step": 19380 }, { "epoch": 9.01, "learning_rate": 3.300790330079033e-06, "loss": 0.158, "step": 19390 }, { "epoch": 9.02, "learning_rate": 3.2852936618626996e-06, "loss": 0.0319, "step": 19400 }, { "epoch": 9.02, "learning_rate": 3.269796993646366e-06, "loss": 0.2304, "step": 19410 }, { "epoch": 9.03, "learning_rate": 3.2543003254300324e-06, "loss": 0.0612, "step": 19420 }, { "epoch": 9.03, "learning_rate": 3.238803657213699e-06, "loss": 0.1506, "step": 19430 }, { "epoch": 9.04, "learning_rate": 3.2233069889973657e-06, "loss": 0.0054, "step": 19440 }, { "epoch": 9.04, "learning_rate": 3.207810320781032e-06, "loss": 0.15, "step": 19450 }, { "epoch": 9.05, "learning_rate": 3.1923136525646985e-06, "loss": 0.2068, "step": 19460 }, { "epoch": 9.05, "learning_rate": 3.176816984348365e-06, "loss": 0.0853, "step": 19470 }, { "epoch": 9.06, "learning_rate": 3.1613203161320314e-06, "loss": 0.0149, "step": 19480 }, { "epoch": 9.06, "learning_rate": 3.145823647915698e-06, "loss": 0.0633, "step": 19490 }, { "epoch": 9.07, "learning_rate": 3.1303269796993647e-06, "loss": 0.1486, "step": 19500 }, { "epoch": 9.07, "learning_rate": 3.114830311483031e-06, "loss": 0.1867, "step": 19510 }, { "epoch": 9.07, "learning_rate": 3.0993336432666975e-06, "loss": 0.0844, "step": 19520 }, { "epoch": 9.08, "learning_rate": 3.083836975050364e-06, "loss": 0.0564, "step": 19530 }, { "epoch": 9.08, "learning_rate": 3.068340306834031e-06, "loss": 0.076, "step": 19540 }, { "epoch": 9.09, "learning_rate": 3.052843638617697e-06, "loss": 0.1528, "step": 19550 }, { "epoch": 9.09, "learning_rate": 3.0373469704013636e-06, "loss": 0.2519, "step": 19560 }, { "epoch": 9.1, "learning_rate": 3.0218503021850307e-06, "loss": 0.1174, "step": 19570 }, { "epoch": 9.1, "learning_rate": 3.006353633968697e-06, "loss": 0.1181, "step": 19580 }, { "epoch": 9.11, "learning_rate": 2.9908569657523636e-06, "loss": 0.121, "step": 19590 }, { "epoch": 9.11, "learning_rate": 2.97536029753603e-06, "loss": 0.0385, "step": 19600 }, { "epoch": 9.12, "learning_rate": 2.9598636293196964e-06, "loss": 0.0413, "step": 19610 }, { "epoch": 9.12, "learning_rate": 2.944366961103363e-06, "loss": 0.1413, "step": 19620 }, { "epoch": 9.13, "learning_rate": 2.9288702928870297e-06, "loss": 0.0248, "step": 19630 }, { "epoch": 9.13, "learning_rate": 2.913373624670696e-06, "loss": 0.1415, "step": 19640 }, { "epoch": 9.14, "learning_rate": 2.8978769564543625e-06, "loss": 0.139, "step": 19650 }, { "epoch": 9.14, "learning_rate": 2.882380288238029e-06, "loss": 0.0755, "step": 19660 }, { "epoch": 9.14, "learning_rate": 2.8668836200216954e-06, "loss": 0.1845, "step": 19670 }, { "epoch": 9.15, "learning_rate": 2.851386951805362e-06, "loss": 0.0354, "step": 19680 }, { "epoch": 9.15, "learning_rate": 2.8358902835890287e-06, "loss": 0.1874, "step": 19690 }, { "epoch": 9.16, "learning_rate": 2.820393615372695e-06, "loss": 0.0131, "step": 19700 }, { "epoch": 9.16, "learning_rate": 2.8048969471563615e-06, "loss": 0.147, "step": 19710 }, { "epoch": 9.17, "learning_rate": 2.7909499457616614e-06, "loss": 0.3334, "step": 19720 }, { "epoch": 9.17, "learning_rate": 2.7754532775453276e-06, "loss": 0.2987, "step": 19730 }, { "epoch": 9.18, "learning_rate": 2.7599566093289942e-06, "loss": 0.0704, "step": 19740 }, { "epoch": 9.18, "learning_rate": 2.744459941112661e-06, "loss": 0.1546, "step": 19750 }, { "epoch": 9.19, "learning_rate": 2.728963272896327e-06, "loss": 0.0019, "step": 19760 }, { "epoch": 9.19, "learning_rate": 2.7134666046799937e-06, "loss": 0.0304, "step": 19770 }, { "epoch": 9.2, "learning_rate": 2.6979699364636604e-06, "loss": 0.0064, "step": 19780 }, { "epoch": 9.2, "learning_rate": 2.6824732682473266e-06, "loss": 0.1358, "step": 19790 }, { "epoch": 9.21, "learning_rate": 2.6669766000309932e-06, "loss": 0.0273, "step": 19800 }, { "epoch": 9.21, "learning_rate": 2.65147993181466e-06, "loss": 0.0752, "step": 19810 }, { "epoch": 9.21, "learning_rate": 2.635983263598326e-06, "loss": 0.2115, "step": 19820 }, { "epoch": 9.22, "learning_rate": 2.620486595381993e-06, "loss": 0.0997, "step": 19830 }, { "epoch": 9.22, "learning_rate": 2.6049899271656598e-06, "loss": 0.0718, "step": 19840 }, { "epoch": 9.23, "learning_rate": 2.589493258949326e-06, "loss": 0.1535, "step": 19850 }, { "epoch": 9.23, "learning_rate": 2.5739965907329926e-06, "loss": 0.0045, "step": 19860 }, { "epoch": 9.24, "learning_rate": 2.5584999225166593e-06, "loss": 0.0463, "step": 19870 }, { "epoch": 9.24, "learning_rate": 2.5430032543003255e-06, "loss": 0.1217, "step": 19880 }, { "epoch": 9.25, "learning_rate": 2.527506586083992e-06, "loss": 0.0023, "step": 19890 }, { "epoch": 9.25, "learning_rate": 2.5120099178676588e-06, "loss": 0.1413, "step": 19900 }, { "epoch": 9.26, "learning_rate": 2.496513249651325e-06, "loss": 0.1249, "step": 19910 }, { "epoch": 9.26, "learning_rate": 2.4810165814349916e-06, "loss": 0.2606, "step": 19920 }, { "epoch": 9.27, "learning_rate": 2.4655199132186582e-06, "loss": 0.0981, "step": 19930 }, { "epoch": 9.27, "learning_rate": 2.4500232450023245e-06, "loss": 0.0172, "step": 19940 }, { "epoch": 9.27, "learning_rate": 2.434526576785991e-06, "loss": 0.2191, "step": 19950 }, { "epoch": 9.28, "learning_rate": 2.4190299085696577e-06, "loss": 0.126, "step": 19960 }, { "epoch": 9.28, "learning_rate": 2.4035332403533244e-06, "loss": 0.0535, "step": 19970 }, { "epoch": 9.29, "learning_rate": 2.3880365721369906e-06, "loss": 0.1782, "step": 19980 }, { "epoch": 9.29, "learning_rate": 2.3725399039206572e-06, "loss": 0.0335, "step": 19990 }, { "epoch": 9.3, "learning_rate": 2.357043235704324e-06, "loss": 0.061, "step": 20000 }, { "epoch": 9.3, "learning_rate": 2.34154656748799e-06, "loss": 0.1047, "step": 20010 }, { "epoch": 9.31, "learning_rate": 2.3260498992716567e-06, "loss": 0.0417, "step": 20020 }, { "epoch": 9.31, "learning_rate": 2.3105532310553233e-06, "loss": 0.1548, "step": 20030 }, { "epoch": 9.32, "learning_rate": 2.2950565628389896e-06, "loss": 0.1097, "step": 20040 }, { "epoch": 9.32, "learning_rate": 2.279559894622656e-06, "loss": 0.1449, "step": 20050 }, { "epoch": 9.33, "learning_rate": 2.264063226406323e-06, "loss": 0.1538, "step": 20060 }, { "epoch": 9.33, "learning_rate": 2.248566558189989e-06, "loss": 0.0429, "step": 20070 }, { "epoch": 9.34, "learning_rate": 2.2330698899736557e-06, "loss": 0.2382, "step": 20080 }, { "epoch": 9.34, "learning_rate": 2.2175732217573223e-06, "loss": 0.2756, "step": 20090 }, { "epoch": 9.34, "learning_rate": 2.2020765535409885e-06, "loss": 0.0469, "step": 20100 }, { "epoch": 9.35, "learning_rate": 2.186579885324655e-06, "loss": 0.4543, "step": 20110 }, { "epoch": 9.35, "learning_rate": 2.171083217108322e-06, "loss": 0.1226, "step": 20120 }, { "epoch": 9.36, "learning_rate": 2.155586548891988e-06, "loss": 0.1591, "step": 20130 }, { "epoch": 9.36, "learning_rate": 2.1400898806756547e-06, "loss": 0.043, "step": 20140 }, { "epoch": 9.37, "learning_rate": 2.1245932124593213e-06, "loss": 0.0016, "step": 20150 }, { "epoch": 9.37, "learning_rate": 2.1090965442429875e-06, "loss": 0.0589, "step": 20160 }, { "epoch": 9.38, "learning_rate": 2.093599876026654e-06, "loss": 0.1102, "step": 20170 }, { "epoch": 9.38, "learning_rate": 2.0781032078103208e-06, "loss": 0.035, "step": 20180 }, { "epoch": 9.39, "learning_rate": 2.062606539593987e-06, "loss": 0.0646, "step": 20190 }, { "epoch": 9.39, "learning_rate": 2.0471098713776536e-06, "loss": 0.1542, "step": 20200 }, { "epoch": 9.4, "learning_rate": 2.0316132031613203e-06, "loss": 0.0998, "step": 20210 }, { "epoch": 9.4, "learning_rate": 2.016116534944987e-06, "loss": 0.0874, "step": 20220 }, { "epoch": 9.4, "learning_rate": 2.000619866728653e-06, "loss": 0.0861, "step": 20230 }, { "epoch": 9.41, "learning_rate": 1.9851231985123198e-06, "loss": 0.0186, "step": 20240 }, { "epoch": 9.41, "learning_rate": 1.9696265302959864e-06, "loss": 0.1726, "step": 20250 }, { "epoch": 9.42, "learning_rate": 1.9541298620796526e-06, "loss": 0.0626, "step": 20260 }, { "epoch": 9.42, "learning_rate": 1.9386331938633197e-06, "loss": 0.0663, "step": 20270 }, { "epoch": 9.43, "learning_rate": 1.9231365256469863e-06, "loss": 0.0071, "step": 20280 }, { "epoch": 9.43, "learning_rate": 1.9076398574306525e-06, "loss": 0.3218, "step": 20290 }, { "epoch": 9.44, "learning_rate": 1.8921431892143192e-06, "loss": 0.1188, "step": 20300 }, { "epoch": 9.44, "learning_rate": 1.8766465209979856e-06, "loss": 0.0067, "step": 20310 }, { "epoch": 9.45, "learning_rate": 1.861149852781652e-06, "loss": 0.2181, "step": 20320 }, { "epoch": 9.45, "learning_rate": 1.8456531845653184e-06, "loss": 0.2211, "step": 20330 }, { "epoch": 9.46, "learning_rate": 1.8301565163489849e-06, "loss": 0.1074, "step": 20340 }, { "epoch": 9.46, "learning_rate": 1.8146598481326515e-06, "loss": 0.1332, "step": 20350 }, { "epoch": 9.47, "learning_rate": 1.799163179916318e-06, "loss": 0.0103, "step": 20360 }, { "epoch": 9.47, "learning_rate": 1.7836665116999844e-06, "loss": 0.1835, "step": 20370 }, { "epoch": 9.47, "learning_rate": 1.7681698434836512e-06, "loss": 0.2221, "step": 20380 }, { "epoch": 9.48, "learning_rate": 1.7526731752673176e-06, "loss": 0.0057, "step": 20390 }, { "epoch": 9.48, "learning_rate": 1.737176507050984e-06, "loss": 0.4088, "step": 20400 }, { "epoch": 9.49, "learning_rate": 1.7216798388346507e-06, "loss": 0.1164, "step": 20410 }, { "epoch": 9.49, "learning_rate": 1.7061831706183171e-06, "loss": 0.1692, "step": 20420 }, { "epoch": 9.5, "learning_rate": 1.6906865024019838e-06, "loss": 0.2444, "step": 20430 }, { "epoch": 9.5, "learning_rate": 1.6751898341856502e-06, "loss": 0.1398, "step": 20440 }, { "epoch": 9.51, "learning_rate": 1.6596931659693166e-06, "loss": 0.0526, "step": 20450 }, { "epoch": 9.51, "learning_rate": 1.6441964977529832e-06, "loss": 0.0673, "step": 20460 }, { "epoch": 9.52, "learning_rate": 1.6286998295366497e-06, "loss": 0.1691, "step": 20470 }, { "epoch": 9.52, "learning_rate": 1.613203161320316e-06, "loss": 0.1642, "step": 20480 }, { "epoch": 9.53, "learning_rate": 1.5977064931039827e-06, "loss": 0.1555, "step": 20490 }, { "epoch": 9.53, "learning_rate": 1.5822098248876492e-06, "loss": 0.0718, "step": 20500 }, { "epoch": 9.54, "learning_rate": 1.5667131566713156e-06, "loss": 0.0409, "step": 20510 }, { "epoch": 9.54, "learning_rate": 1.5512164884549822e-06, "loss": 0.2544, "step": 20520 }, { "epoch": 9.54, "learning_rate": 1.5357198202386486e-06, "loss": 0.122, "step": 20530 }, { "epoch": 9.55, "learning_rate": 1.5202231520223153e-06, "loss": 0.0019, "step": 20540 }, { "epoch": 9.55, "learning_rate": 1.5047264838059817e-06, "loss": 0.0084, "step": 20550 }, { "epoch": 9.56, "learning_rate": 1.4892298155896481e-06, "loss": 0.053, "step": 20560 }, { "epoch": 9.56, "learning_rate": 1.4737331473733148e-06, "loss": 0.0945, "step": 20570 }, { "epoch": 9.57, "learning_rate": 1.4582364791569812e-06, "loss": 0.1029, "step": 20580 }, { "epoch": 9.57, "learning_rate": 1.4427398109406478e-06, "loss": 0.0045, "step": 20590 }, { "epoch": 9.58, "learning_rate": 1.4272431427243145e-06, "loss": 0.0014, "step": 20600 }, { "epoch": 9.58, "learning_rate": 1.411746474507981e-06, "loss": 0.1044, "step": 20610 }, { "epoch": 9.59, "learning_rate": 1.3962498062916473e-06, "loss": 0.1153, "step": 20620 }, { "epoch": 9.59, "learning_rate": 1.380753138075314e-06, "loss": 0.0612, "step": 20630 }, { "epoch": 9.6, "learning_rate": 1.3652564698589804e-06, "loss": 0.0897, "step": 20640 }, { "epoch": 9.6, "learning_rate": 1.3497598016426468e-06, "loss": 0.0051, "step": 20650 }, { "epoch": 9.6, "learning_rate": 1.3342631334263134e-06, "loss": 0.1668, "step": 20660 }, { "epoch": 9.61, "learning_rate": 1.3187664652099799e-06, "loss": 0.0149, "step": 20670 }, { "epoch": 9.61, "learning_rate": 1.3032697969936465e-06, "loss": 0.0824, "step": 20680 }, { "epoch": 9.62, "learning_rate": 1.287773128777313e-06, "loss": 0.052, "step": 20690 }, { "epoch": 9.62, "learning_rate": 1.2722764605609794e-06, "loss": 0.2652, "step": 20700 }, { "epoch": 9.63, "learning_rate": 1.256779792344646e-06, "loss": 0.1066, "step": 20710 }, { "epoch": 9.63, "learning_rate": 1.2412831241283124e-06, "loss": 0.0279, "step": 20720 }, { "epoch": 9.64, "learning_rate": 1.2257864559119789e-06, "loss": 0.1973, "step": 20730 }, { "epoch": 9.64, "learning_rate": 1.2102897876956455e-06, "loss": 0.0739, "step": 20740 }, { "epoch": 9.65, "learning_rate": 1.194793119479312e-06, "loss": 0.2884, "step": 20750 }, { "epoch": 9.65, "learning_rate": 1.1792964512629783e-06, "loss": 0.0648, "step": 20760 }, { "epoch": 9.66, "learning_rate": 1.163799783046645e-06, "loss": 0.1665, "step": 20770 }, { "epoch": 9.66, "learning_rate": 1.1483031148303114e-06, "loss": 0.092, "step": 20780 }, { "epoch": 9.67, "learning_rate": 1.1328064466139778e-06, "loss": 0.0071, "step": 20790 }, { "epoch": 9.67, "learning_rate": 1.1173097783976445e-06, "loss": 0.081, "step": 20800 }, { "epoch": 9.67, "learning_rate": 1.101813110181311e-06, "loss": 0.1156, "step": 20810 }, { "epoch": 9.68, "learning_rate": 1.0863164419649777e-06, "loss": 0.2028, "step": 20820 }, { "epoch": 9.68, "learning_rate": 1.0708197737486442e-06, "loss": 0.1469, "step": 20830 }, { "epoch": 9.69, "learning_rate": 1.0553231055323106e-06, "loss": 0.3479, "step": 20840 }, { "epoch": 9.69, "learning_rate": 1.0398264373159772e-06, "loss": 0.0947, "step": 20850 }, { "epoch": 9.7, "learning_rate": 1.0243297690996437e-06, "loss": 0.0593, "step": 20860 }, { "epoch": 9.7, "learning_rate": 1.00883310088331e-06, "loss": 0.2242, "step": 20870 }, { "epoch": 9.71, "learning_rate": 9.933364326669767e-07, "loss": 0.1784, "step": 20880 }, { "epoch": 9.71, "learning_rate": 9.778397644506431e-07, "loss": 0.0704, "step": 20890 }, { "epoch": 9.72, "learning_rate": 9.623430962343096e-07, "loss": 0.074, "step": 20900 }, { "epoch": 9.72, "learning_rate": 9.468464280179762e-07, "loss": 0.2409, "step": 20910 }, { "epoch": 9.73, "learning_rate": 9.313497598016426e-07, "loss": 0.0582, "step": 20920 }, { "epoch": 9.73, "learning_rate": 9.158530915853092e-07, "loss": 0.0093, "step": 20930 }, { "epoch": 9.74, "learning_rate": 9.003564233689757e-07, "loss": 0.0868, "step": 20940 }, { "epoch": 9.74, "learning_rate": 8.848597551526421e-07, "loss": 0.0017, "step": 20950 }, { "epoch": 9.74, "learning_rate": 8.693630869363087e-07, "loss": 0.0244, "step": 20960 }, { "epoch": 9.75, "learning_rate": 8.538664187199753e-07, "loss": 0.0585, "step": 20970 }, { "epoch": 9.75, "learning_rate": 8.383697505036418e-07, "loss": 0.2519, "step": 20980 }, { "epoch": 9.76, "learning_rate": 8.228730822873082e-07, "loss": 0.2187, "step": 20990 }, { "epoch": 9.76, "learning_rate": 8.073764140709748e-07, "loss": 0.1091, "step": 21000 }, { "epoch": 9.77, "learning_rate": 7.918797458546413e-07, "loss": 0.0514, "step": 21010 }, { "epoch": 9.77, "learning_rate": 7.763830776383077e-07, "loss": 0.0412, "step": 21020 }, { "epoch": 9.78, "learning_rate": 7.608864094219743e-07, "loss": 0.125, "step": 21030 }, { "epoch": 9.78, "learning_rate": 7.453897412056408e-07, "loss": 0.1665, "step": 21040 }, { "epoch": 9.79, "learning_rate": 7.298930729893073e-07, "loss": 0.3963, "step": 21050 }, { "epoch": 9.79, "learning_rate": 7.143964047729738e-07, "loss": 0.1001, "step": 21060 }, { "epoch": 9.8, "learning_rate": 6.988997365566403e-07, "loss": 0.0236, "step": 21070 }, { "epoch": 9.8, "learning_rate": 6.834030683403069e-07, "loss": 0.1739, "step": 21080 }, { "epoch": 9.8, "learning_rate": 6.679064001239734e-07, "loss": 0.1423, "step": 21090 }, { "epoch": 9.81, "learning_rate": 6.524097319076399e-07, "loss": 0.061, "step": 21100 }, { "epoch": 9.81, "learning_rate": 6.369130636913064e-07, "loss": 0.0032, "step": 21110 }, { "epoch": 9.82, "learning_rate": 6.214163954749729e-07, "loss": 0.0032, "step": 21120 }, { "epoch": 9.82, "learning_rate": 6.059197272586394e-07, "loss": 0.0029, "step": 21130 }, { "epoch": 9.83, "learning_rate": 5.904230590423059e-07, "loss": 0.0771, "step": 21140 }, { "epoch": 9.83, "learning_rate": 5.749263908259724e-07, "loss": 0.0379, "step": 21150 }, { "epoch": 9.84, "learning_rate": 5.59429722609639e-07, "loss": 0.2727, "step": 21160 }, { "epoch": 9.84, "learning_rate": 5.439330543933054e-07, "loss": 0.0425, "step": 21170 }, { "epoch": 9.85, "learning_rate": 5.284363861769719e-07, "loss": 0.0654, "step": 21180 }, { "epoch": 9.85, "learning_rate": 5.129397179606386e-07, "loss": 0.0291, "step": 21190 }, { "epoch": 9.86, "learning_rate": 4.97443049744305e-07, "loss": 0.0981, "step": 21200 }, { "epoch": 9.86, "learning_rate": 4.819463815279715e-07, "loss": 0.3052, "step": 21210 }, { "epoch": 9.87, "learning_rate": 4.6644971331163805e-07, "loss": 0.087, "step": 21220 }, { "epoch": 9.87, "learning_rate": 4.5095304509530453e-07, "loss": 0.1416, "step": 21230 }, { "epoch": 9.87, "learning_rate": 4.35456376878971e-07, "loss": 0.0807, "step": 21240 }, { "epoch": 9.88, "learning_rate": 4.1995970866263754e-07, "loss": 0.0561, "step": 21250 }, { "epoch": 9.88, "learning_rate": 4.04463040446304e-07, "loss": 0.215, "step": 21260 }, { "epoch": 9.89, "learning_rate": 3.889663722299706e-07, "loss": 0.2723, "step": 21270 }, { "epoch": 9.89, "learning_rate": 3.734697040136371e-07, "loss": 0.0546, "step": 21280 }, { "epoch": 9.9, "learning_rate": 3.579730357973036e-07, "loss": 0.108, "step": 21290 }, { "epoch": 9.9, "learning_rate": 3.424763675809701e-07, "loss": 0.0655, "step": 21300 }, { "epoch": 9.91, "learning_rate": 3.269796993646366e-07, "loss": 0.4156, "step": 21310 }, { "epoch": 9.91, "learning_rate": 3.114830311483031e-07, "loss": 0.1386, "step": 21320 }, { "epoch": 9.92, "learning_rate": 2.9598636293196963e-07, "loss": 0.4026, "step": 21330 }, { "epoch": 9.92, "learning_rate": 2.8048969471563616e-07, "loss": 0.167, "step": 21340 }, { "epoch": 9.93, "learning_rate": 2.6499302649930264e-07, "loss": 0.1878, "step": 21350 }, { "epoch": 9.93, "learning_rate": 2.4949635828296917e-07, "loss": 0.1537, "step": 21360 }, { "epoch": 9.93, "learning_rate": 2.3399969006663568e-07, "loss": 0.0609, "step": 21370 }, { "epoch": 9.94, "learning_rate": 2.1850302185030218e-07, "loss": 0.3141, "step": 21380 }, { "epoch": 9.94, "learning_rate": 2.030063536339687e-07, "loss": 0.2971, "step": 21390 }, { "epoch": 9.95, "learning_rate": 1.8750968541763522e-07, "loss": 0.1231, "step": 21400 }, { "epoch": 9.95, "learning_rate": 1.7201301720130172e-07, "loss": 0.0516, "step": 21410 }, { "epoch": 9.96, "learning_rate": 1.5651634898496825e-07, "loss": 0.2032, "step": 21420 }, { "epoch": 9.96, "learning_rate": 1.4101968076863473e-07, "loss": 0.0427, "step": 21430 }, { "epoch": 9.97, "learning_rate": 1.2552301255230124e-07, "loss": 0.1642, "step": 21440 }, { "epoch": 9.97, "learning_rate": 1.1002634433596777e-07, "loss": 0.1457, "step": 21450 }, { "epoch": 9.98, "learning_rate": 9.452967611963427e-08, "loss": 0.1659, "step": 21460 }, { "epoch": 9.98, "learning_rate": 7.903300790330079e-08, "loss": 0.1698, "step": 21470 }, { "epoch": 9.99, "learning_rate": 6.353633968696731e-08, "loss": 0.1093, "step": 21480 }, { "epoch": 9.99, "learning_rate": 4.8039671470633816e-08, "loss": 0.2687, "step": 21490 }, { "epoch": 10.0, "learning_rate": 3.254300325430033e-08, "loss": 0.0359, "step": 21500 }, { "epoch": 10.0, "learning_rate": 1.704633503796684e-08, "loss": 0.1148, "step": 21510 }, { "epoch": 10.0, "eval_accuracy": 0.9782680276588739, "eval_loss": 0.11879671365022659, "eval_runtime": 17.2485, "eval_samples_per_second": 176.073, "eval_steps_per_second": 44.062, "step": 21510 }, { "epoch": 10.0, "step": 21510, "total_flos": 1.7013193016084636e+18, "train_loss": 0.3477993663641144, "train_runtime": 4068.2187, "train_samples_per_second": 42.294, "train_steps_per_second": 5.287 } ], "logging_steps": 10, "max_steps": 21510, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "total_flos": 1.7013193016084636e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }