{ "best_metric": 0.2431023269891739, "best_model_checkpoint": "/leonardo_work/IscrC_AGENT/PROFES2025/results/balanced_per_dataset/oss_similar/checkpoint-4328", "epoch": 6.0, "eval_steps": 500, "global_step": 12984, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.9990757855822555e-05, "loss": 0.645, "step": 10 }, { "epoch": 0.01, "learning_rate": 1.9981515711645104e-05, "loss": 0.4998, "step": 20 }, { "epoch": 0.01, "learning_rate": 1.9972273567467654e-05, "loss": 0.3892, "step": 30 }, { "epoch": 0.02, "learning_rate": 1.9963031423290204e-05, "loss": 0.4802, "step": 40 }, { "epoch": 0.02, "learning_rate": 1.9953789279112757e-05, "loss": 0.3542, "step": 50 }, { "epoch": 0.03, "learning_rate": 1.9944547134935307e-05, "loss": 0.3915, "step": 60 }, { "epoch": 0.03, "learning_rate": 1.9935304990757857e-05, "loss": 0.4396, "step": 70 }, { "epoch": 0.04, "learning_rate": 1.9926062846580406e-05, "loss": 0.3767, "step": 80 }, { "epoch": 0.04, "learning_rate": 1.991682070240296e-05, "loss": 0.422, "step": 90 }, { "epoch": 0.05, "learning_rate": 1.9907578558225512e-05, "loss": 0.4054, "step": 100 }, { "epoch": 0.05, "learning_rate": 1.9898336414048062e-05, "loss": 0.3924, "step": 110 }, { "epoch": 0.06, "learning_rate": 1.9889094269870612e-05, "loss": 0.3433, "step": 120 }, { "epoch": 0.06, "learning_rate": 1.987985212569316e-05, "loss": 0.2842, "step": 130 }, { "epoch": 0.06, "learning_rate": 1.9870609981515715e-05, "loss": 0.3997, "step": 140 }, { "epoch": 0.07, "learning_rate": 1.9861367837338265e-05, "loss": 0.3216, "step": 150 }, { "epoch": 0.07, "learning_rate": 1.9852125693160814e-05, "loss": 0.2942, "step": 160 }, { "epoch": 0.08, "learning_rate": 1.9842883548983364e-05, "loss": 0.396, "step": 170 }, { "epoch": 0.08, "learning_rate": 1.9833641404805917e-05, "loss": 0.3627, "step": 180 }, { "epoch": 0.09, "learning_rate": 1.9824399260628467e-05, "loss": 0.3582, "step": 190 }, { "epoch": 0.09, "learning_rate": 1.9815157116451017e-05, "loss": 0.3736, "step": 200 }, { "epoch": 0.1, "learning_rate": 1.980591497227357e-05, "loss": 0.377, "step": 210 }, { "epoch": 0.1, "learning_rate": 1.979667282809612e-05, "loss": 0.3599, "step": 220 }, { "epoch": 0.11, "learning_rate": 1.9787430683918673e-05, "loss": 0.2997, "step": 230 }, { "epoch": 0.11, "learning_rate": 1.9778188539741222e-05, "loss": 0.4779, "step": 240 }, { "epoch": 0.12, "learning_rate": 1.9768946395563772e-05, "loss": 0.3352, "step": 250 }, { "epoch": 0.12, "learning_rate": 1.9759704251386322e-05, "loss": 0.3111, "step": 260 }, { "epoch": 0.12, "learning_rate": 1.9750462107208875e-05, "loss": 0.3793, "step": 270 }, { "epoch": 0.13, "learning_rate": 1.9741219963031425e-05, "loss": 0.3818, "step": 280 }, { "epoch": 0.13, "learning_rate": 1.9731977818853974e-05, "loss": 0.2979, "step": 290 }, { "epoch": 0.14, "learning_rate": 1.9722735674676527e-05, "loss": 0.397, "step": 300 }, { "epoch": 0.14, "learning_rate": 1.9713493530499077e-05, "loss": 0.2687, "step": 310 }, { "epoch": 0.15, "learning_rate": 1.970425138632163e-05, "loss": 0.4506, "step": 320 }, { "epoch": 0.15, "learning_rate": 1.969500924214418e-05, "loss": 0.3477, "step": 330 }, { "epoch": 0.16, "learning_rate": 1.968576709796673e-05, "loss": 0.3147, "step": 340 }, { "epoch": 0.16, "learning_rate": 1.967652495378928e-05, "loss": 0.2732, "step": 350 }, { "epoch": 0.17, "learning_rate": 1.9667282809611833e-05, "loss": 0.4006, "step": 360 }, { "epoch": 0.17, "learning_rate": 1.9658040665434382e-05, "loss": 0.3907, "step": 370 }, { "epoch": 0.18, "learning_rate": 1.9648798521256932e-05, "loss": 0.3515, "step": 380 }, { "epoch": 0.18, "learning_rate": 1.9639556377079485e-05, "loss": 0.2796, "step": 390 }, { "epoch": 0.18, "learning_rate": 1.9630314232902035e-05, "loss": 0.3384, "step": 400 }, { "epoch": 0.19, "learning_rate": 1.9621072088724588e-05, "loss": 0.463, "step": 410 }, { "epoch": 0.19, "learning_rate": 1.9611829944547138e-05, "loss": 0.3087, "step": 420 }, { "epoch": 0.2, "learning_rate": 1.9602587800369687e-05, "loss": 0.359, "step": 430 }, { "epoch": 0.2, "learning_rate": 1.9593345656192237e-05, "loss": 0.3398, "step": 440 }, { "epoch": 0.21, "learning_rate": 1.958410351201479e-05, "loss": 0.2786, "step": 450 }, { "epoch": 0.21, "learning_rate": 1.957486136783734e-05, "loss": 0.2328, "step": 460 }, { "epoch": 0.22, "learning_rate": 1.956561922365989e-05, "loss": 0.3837, "step": 470 }, { "epoch": 0.22, "learning_rate": 1.9556377079482443e-05, "loss": 0.3297, "step": 480 }, { "epoch": 0.23, "learning_rate": 1.9547134935304993e-05, "loss": 0.389, "step": 490 }, { "epoch": 0.23, "learning_rate": 1.9537892791127542e-05, "loss": 0.3253, "step": 500 }, { "epoch": 0.24, "learning_rate": 1.9528650646950092e-05, "loss": 0.3159, "step": 510 }, { "epoch": 0.24, "learning_rate": 1.9519408502772645e-05, "loss": 0.2802, "step": 520 }, { "epoch": 0.24, "learning_rate": 1.9510166358595195e-05, "loss": 0.291, "step": 530 }, { "epoch": 0.25, "learning_rate": 1.9500924214417748e-05, "loss": 0.3166, "step": 540 }, { "epoch": 0.25, "learning_rate": 1.9491682070240298e-05, "loss": 0.2574, "step": 550 }, { "epoch": 0.26, "learning_rate": 1.9482439926062848e-05, "loss": 0.3106, "step": 560 }, { "epoch": 0.26, "learning_rate": 1.94731977818854e-05, "loss": 0.312, "step": 570 }, { "epoch": 0.27, "learning_rate": 1.946395563770795e-05, "loss": 0.3265, "step": 580 }, { "epoch": 0.27, "learning_rate": 1.94547134935305e-05, "loss": 0.263, "step": 590 }, { "epoch": 0.28, "learning_rate": 1.944547134935305e-05, "loss": 0.2956, "step": 600 }, { "epoch": 0.28, "learning_rate": 1.9436229205175603e-05, "loss": 0.3203, "step": 610 }, { "epoch": 0.29, "learning_rate": 1.9426987060998153e-05, "loss": 0.318, "step": 620 }, { "epoch": 0.29, "learning_rate": 1.9417744916820706e-05, "loss": 0.2331, "step": 630 }, { "epoch": 0.3, "learning_rate": 1.9408502772643256e-05, "loss": 0.2732, "step": 640 }, { "epoch": 0.3, "learning_rate": 1.9399260628465805e-05, "loss": 0.2832, "step": 650 }, { "epoch": 0.3, "learning_rate": 1.9390018484288355e-05, "loss": 0.2683, "step": 660 }, { "epoch": 0.31, "learning_rate": 1.9380776340110908e-05, "loss": 0.3397, "step": 670 }, { "epoch": 0.31, "learning_rate": 1.9371534195933458e-05, "loss": 0.3558, "step": 680 }, { "epoch": 0.32, "learning_rate": 1.9362292051756008e-05, "loss": 0.2801, "step": 690 }, { "epoch": 0.32, "learning_rate": 1.935304990757856e-05, "loss": 0.2773, "step": 700 }, { "epoch": 0.33, "learning_rate": 1.934380776340111e-05, "loss": 0.341, "step": 710 }, { "epoch": 0.33, "learning_rate": 1.9334565619223664e-05, "loss": 0.2735, "step": 720 }, { "epoch": 0.34, "learning_rate": 1.932532347504621e-05, "loss": 0.2615, "step": 730 }, { "epoch": 0.34, "learning_rate": 1.9316081330868763e-05, "loss": 0.3008, "step": 740 }, { "epoch": 0.35, "learning_rate": 1.9306839186691313e-05, "loss": 0.2606, "step": 750 }, { "epoch": 0.35, "learning_rate": 1.9297597042513866e-05, "loss": 0.3216, "step": 760 }, { "epoch": 0.36, "learning_rate": 1.9288354898336416e-05, "loss": 0.2735, "step": 770 }, { "epoch": 0.36, "learning_rate": 1.9279112754158965e-05, "loss": 0.2418, "step": 780 }, { "epoch": 0.37, "learning_rate": 1.926987060998152e-05, "loss": 0.2823, "step": 790 }, { "epoch": 0.37, "learning_rate": 1.9260628465804068e-05, "loss": 0.2942, "step": 800 }, { "epoch": 0.37, "learning_rate": 1.9251386321626618e-05, "loss": 0.2762, "step": 810 }, { "epoch": 0.38, "learning_rate": 1.9242144177449168e-05, "loss": 0.2546, "step": 820 }, { "epoch": 0.38, "learning_rate": 1.923290203327172e-05, "loss": 0.353, "step": 830 }, { "epoch": 0.39, "learning_rate": 1.922365988909427e-05, "loss": 0.2817, "step": 840 }, { "epoch": 0.39, "learning_rate": 1.9214417744916824e-05, "loss": 0.2555, "step": 850 }, { "epoch": 0.4, "learning_rate": 1.9205175600739373e-05, "loss": 0.222, "step": 860 }, { "epoch": 0.4, "learning_rate": 1.9195933456561923e-05, "loss": 0.3104, "step": 870 }, { "epoch": 0.41, "learning_rate": 1.9186691312384476e-05, "loss": 0.2916, "step": 880 }, { "epoch": 0.41, "learning_rate": 1.9177449168207026e-05, "loss": 0.1869, "step": 890 }, { "epoch": 0.42, "learning_rate": 1.9168207024029576e-05, "loss": 0.2228, "step": 900 }, { "epoch": 0.42, "learning_rate": 1.9158964879852125e-05, "loss": 0.3616, "step": 910 }, { "epoch": 0.43, "learning_rate": 1.914972273567468e-05, "loss": 0.3472, "step": 920 }, { "epoch": 0.43, "learning_rate": 1.9140480591497228e-05, "loss": 0.3787, "step": 930 }, { "epoch": 0.43, "learning_rate": 1.913123844731978e-05, "loss": 0.2733, "step": 940 }, { "epoch": 0.44, "learning_rate": 1.912199630314233e-05, "loss": 0.2785, "step": 950 }, { "epoch": 0.44, "learning_rate": 1.911275415896488e-05, "loss": 0.3325, "step": 960 }, { "epoch": 0.45, "learning_rate": 1.9103512014787434e-05, "loss": 0.2449, "step": 970 }, { "epoch": 0.45, "learning_rate": 1.9094269870609984e-05, "loss": 0.3416, "step": 980 }, { "epoch": 0.46, "learning_rate": 1.9085027726432533e-05, "loss": 0.321, "step": 990 }, { "epoch": 0.46, "learning_rate": 1.9075785582255083e-05, "loss": 0.1878, "step": 1000 }, { "epoch": 0.47, "learning_rate": 1.9066543438077636e-05, "loss": 0.3348, "step": 1010 }, { "epoch": 0.47, "learning_rate": 1.9057301293900186e-05, "loss": 0.245, "step": 1020 }, { "epoch": 0.48, "learning_rate": 1.904805914972274e-05, "loss": 0.321, "step": 1030 }, { "epoch": 0.48, "learning_rate": 1.9038817005545285e-05, "loss": 0.2211, "step": 1040 }, { "epoch": 0.49, "learning_rate": 1.902957486136784e-05, "loss": 0.4672, "step": 1050 }, { "epoch": 0.49, "learning_rate": 1.902033271719039e-05, "loss": 0.2489, "step": 1060 }, { "epoch": 0.49, "learning_rate": 1.901109057301294e-05, "loss": 0.303, "step": 1070 }, { "epoch": 0.5, "learning_rate": 1.900184842883549e-05, "loss": 0.2474, "step": 1080 }, { "epoch": 0.5, "learning_rate": 1.899260628465804e-05, "loss": 0.2143, "step": 1090 }, { "epoch": 0.51, "learning_rate": 1.8983364140480594e-05, "loss": 0.1973, "step": 1100 }, { "epoch": 0.51, "learning_rate": 1.8974121996303144e-05, "loss": 0.3738, "step": 1110 }, { "epoch": 0.52, "learning_rate": 1.8964879852125693e-05, "loss": 0.4042, "step": 1120 }, { "epoch": 0.52, "learning_rate": 1.8955637707948243e-05, "loss": 0.2559, "step": 1130 }, { "epoch": 0.53, "learning_rate": 1.8946395563770796e-05, "loss": 0.2039, "step": 1140 }, { "epoch": 0.53, "learning_rate": 1.893715341959335e-05, "loss": 0.3548, "step": 1150 }, { "epoch": 0.54, "learning_rate": 1.89279112754159e-05, "loss": 0.2605, "step": 1160 }, { "epoch": 0.54, "learning_rate": 1.891866913123845e-05, "loss": 0.2701, "step": 1170 }, { "epoch": 0.55, "learning_rate": 1.8909426987061e-05, "loss": 0.1977, "step": 1180 }, { "epoch": 0.55, "learning_rate": 1.890018484288355e-05, "loss": 0.2768, "step": 1190 }, { "epoch": 0.55, "learning_rate": 1.88909426987061e-05, "loss": 0.2601, "step": 1200 }, { "epoch": 0.56, "learning_rate": 1.888170055452865e-05, "loss": 0.2162, "step": 1210 }, { "epoch": 0.56, "learning_rate": 1.88724584103512e-05, "loss": 0.2896, "step": 1220 }, { "epoch": 0.57, "learning_rate": 1.8863216266173754e-05, "loss": 0.2559, "step": 1230 }, { "epoch": 0.57, "learning_rate": 1.8853974121996307e-05, "loss": 0.2492, "step": 1240 }, { "epoch": 0.58, "learning_rate": 1.8844731977818857e-05, "loss": 0.2718, "step": 1250 }, { "epoch": 0.58, "learning_rate": 1.8835489833641407e-05, "loss": 0.2398, "step": 1260 }, { "epoch": 0.59, "learning_rate": 1.8826247689463956e-05, "loss": 0.249, "step": 1270 }, { "epoch": 0.59, "learning_rate": 1.881700554528651e-05, "loss": 0.3046, "step": 1280 }, { "epoch": 0.6, "learning_rate": 1.880776340110906e-05, "loss": 0.2072, "step": 1290 }, { "epoch": 0.6, "learning_rate": 1.879852125693161e-05, "loss": 0.2565, "step": 1300 }, { "epoch": 0.61, "learning_rate": 1.878927911275416e-05, "loss": 0.4009, "step": 1310 }, { "epoch": 0.61, "learning_rate": 1.8780036968576712e-05, "loss": 0.3884, "step": 1320 }, { "epoch": 0.61, "learning_rate": 1.8770794824399265e-05, "loss": 0.208, "step": 1330 }, { "epoch": 0.62, "learning_rate": 1.876155268022181e-05, "loss": 0.2609, "step": 1340 }, { "epoch": 0.62, "learning_rate": 1.8752310536044364e-05, "loss": 0.2701, "step": 1350 }, { "epoch": 0.63, "learning_rate": 1.8743068391866914e-05, "loss": 0.2781, "step": 1360 }, { "epoch": 0.63, "learning_rate": 1.8733826247689467e-05, "loss": 0.2367, "step": 1370 }, { "epoch": 0.64, "learning_rate": 1.8724584103512017e-05, "loss": 0.2415, "step": 1380 }, { "epoch": 0.64, "learning_rate": 1.8715341959334567e-05, "loss": 0.2468, "step": 1390 }, { "epoch": 0.65, "learning_rate": 1.8706099815157116e-05, "loss": 0.2839, "step": 1400 }, { "epoch": 0.65, "learning_rate": 1.869685767097967e-05, "loss": 0.3095, "step": 1410 }, { "epoch": 0.66, "learning_rate": 1.868761552680222e-05, "loss": 0.2856, "step": 1420 }, { "epoch": 0.66, "learning_rate": 1.867837338262477e-05, "loss": 0.2742, "step": 1430 }, { "epoch": 0.67, "learning_rate": 1.8669131238447322e-05, "loss": 0.2031, "step": 1440 }, { "epoch": 0.67, "learning_rate": 1.8659889094269872e-05, "loss": 0.2492, "step": 1450 }, { "epoch": 0.67, "learning_rate": 1.8650646950092425e-05, "loss": 0.1564, "step": 1460 }, { "epoch": 0.68, "learning_rate": 1.8641404805914975e-05, "loss": 0.3162, "step": 1470 }, { "epoch": 0.68, "learning_rate": 1.8632162661737524e-05, "loss": 0.2934, "step": 1480 }, { "epoch": 0.69, "learning_rate": 1.8622920517560074e-05, "loss": 0.2433, "step": 1490 }, { "epoch": 0.69, "learning_rate": 1.8613678373382627e-05, "loss": 0.331, "step": 1500 }, { "epoch": 0.7, "learning_rate": 1.8604436229205177e-05, "loss": 0.2777, "step": 1510 }, { "epoch": 0.7, "learning_rate": 1.8595194085027727e-05, "loss": 0.1969, "step": 1520 }, { "epoch": 0.71, "learning_rate": 1.858595194085028e-05, "loss": 0.198, "step": 1530 }, { "epoch": 0.71, "learning_rate": 1.857670979667283e-05, "loss": 0.3084, "step": 1540 }, { "epoch": 0.72, "learning_rate": 1.8567467652495383e-05, "loss": 0.3091, "step": 1550 }, { "epoch": 0.72, "learning_rate": 1.8558225508317932e-05, "loss": 0.2424, "step": 1560 }, { "epoch": 0.73, "learning_rate": 1.8548983364140482e-05, "loss": 0.345, "step": 1570 }, { "epoch": 0.73, "learning_rate": 1.8539741219963032e-05, "loss": 0.2742, "step": 1580 }, { "epoch": 0.73, "learning_rate": 1.8530499075785585e-05, "loss": 0.2964, "step": 1590 }, { "epoch": 0.74, "learning_rate": 1.8521256931608135e-05, "loss": 0.3566, "step": 1600 }, { "epoch": 0.74, "learning_rate": 1.8512014787430684e-05, "loss": 0.2224, "step": 1610 }, { "epoch": 0.75, "learning_rate": 1.8502772643253238e-05, "loss": 0.2502, "step": 1620 }, { "epoch": 0.75, "learning_rate": 1.8493530499075787e-05, "loss": 0.2158, "step": 1630 }, { "epoch": 0.76, "learning_rate": 1.848428835489834e-05, "loss": 0.2398, "step": 1640 }, { "epoch": 0.76, "learning_rate": 1.8475046210720887e-05, "loss": 0.3376, "step": 1650 }, { "epoch": 0.77, "learning_rate": 1.846580406654344e-05, "loss": 0.2386, "step": 1660 }, { "epoch": 0.77, "learning_rate": 1.845656192236599e-05, "loss": 0.2496, "step": 1670 }, { "epoch": 0.78, "learning_rate": 1.8447319778188543e-05, "loss": 0.3359, "step": 1680 }, { "epoch": 0.78, "learning_rate": 1.8438077634011092e-05, "loss": 0.2807, "step": 1690 }, { "epoch": 0.79, "learning_rate": 1.8428835489833642e-05, "loss": 0.2356, "step": 1700 }, { "epoch": 0.79, "learning_rate": 1.8419593345656195e-05, "loss": 0.3027, "step": 1710 }, { "epoch": 0.79, "learning_rate": 1.8410351201478745e-05, "loss": 0.2389, "step": 1720 }, { "epoch": 0.8, "learning_rate": 1.8401109057301295e-05, "loss": 0.2883, "step": 1730 }, { "epoch": 0.8, "learning_rate": 1.8391866913123844e-05, "loss": 0.3262, "step": 1740 }, { "epoch": 0.81, "learning_rate": 1.8382624768946398e-05, "loss": 0.2065, "step": 1750 }, { "epoch": 0.81, "learning_rate": 1.8373382624768947e-05, "loss": 0.2642, "step": 1760 }, { "epoch": 0.82, "learning_rate": 1.83641404805915e-05, "loss": 0.2412, "step": 1770 }, { "epoch": 0.82, "learning_rate": 1.835489833641405e-05, "loss": 0.2694, "step": 1780 }, { "epoch": 0.83, "learning_rate": 1.83456561922366e-05, "loss": 0.222, "step": 1790 }, { "epoch": 0.83, "learning_rate": 1.833641404805915e-05, "loss": 0.2839, "step": 1800 }, { "epoch": 0.84, "learning_rate": 1.8327171903881703e-05, "loss": 0.3128, "step": 1810 }, { "epoch": 0.84, "learning_rate": 1.8317929759704252e-05, "loss": 0.2249, "step": 1820 }, { "epoch": 0.85, "learning_rate": 1.8308687615526802e-05, "loss": 0.1887, "step": 1830 }, { "epoch": 0.85, "learning_rate": 1.8299445471349355e-05, "loss": 0.3051, "step": 1840 }, { "epoch": 0.85, "learning_rate": 1.8290203327171905e-05, "loss": 0.2477, "step": 1850 }, { "epoch": 0.86, "learning_rate": 1.8280961182994458e-05, "loss": 0.236, "step": 1860 }, { "epoch": 0.86, "learning_rate": 1.8271719038817008e-05, "loss": 0.2025, "step": 1870 }, { "epoch": 0.87, "learning_rate": 1.8262476894639558e-05, "loss": 0.3716, "step": 1880 }, { "epoch": 0.87, "learning_rate": 1.8253234750462107e-05, "loss": 0.2937, "step": 1890 }, { "epoch": 0.88, "learning_rate": 1.824399260628466e-05, "loss": 0.1978, "step": 1900 }, { "epoch": 0.88, "learning_rate": 1.823475046210721e-05, "loss": 0.3899, "step": 1910 }, { "epoch": 0.89, "learning_rate": 1.822550831792976e-05, "loss": 0.2514, "step": 1920 }, { "epoch": 0.89, "learning_rate": 1.8216266173752313e-05, "loss": 0.2661, "step": 1930 }, { "epoch": 0.9, "learning_rate": 1.8207024029574863e-05, "loss": 0.2912, "step": 1940 }, { "epoch": 0.9, "learning_rate": 1.8197781885397413e-05, "loss": 0.233, "step": 1950 }, { "epoch": 0.91, "learning_rate": 1.8188539741219962e-05, "loss": 0.2231, "step": 1960 }, { "epoch": 0.91, "learning_rate": 1.8179297597042515e-05, "loss": 0.1796, "step": 1970 }, { "epoch": 0.91, "learning_rate": 1.8170055452865065e-05, "loss": 0.2496, "step": 1980 }, { "epoch": 0.92, "learning_rate": 1.8160813308687618e-05, "loss": 0.2744, "step": 1990 }, { "epoch": 0.92, "learning_rate": 1.8151571164510168e-05, "loss": 0.2565, "step": 2000 }, { "epoch": 0.93, "learning_rate": 1.8142329020332718e-05, "loss": 0.293, "step": 2010 }, { "epoch": 0.93, "learning_rate": 1.813308687615527e-05, "loss": 0.2161, "step": 2020 }, { "epoch": 0.94, "learning_rate": 1.812384473197782e-05, "loss": 0.2917, "step": 2030 }, { "epoch": 0.94, "learning_rate": 1.811460258780037e-05, "loss": 0.2542, "step": 2040 }, { "epoch": 0.95, "learning_rate": 1.810536044362292e-05, "loss": 0.2621, "step": 2050 }, { "epoch": 0.95, "learning_rate": 1.8096118299445473e-05, "loss": 0.2446, "step": 2060 }, { "epoch": 0.96, "learning_rate": 1.8086876155268023e-05, "loss": 0.2341, "step": 2070 }, { "epoch": 0.96, "learning_rate": 1.8077634011090576e-05, "loss": 0.1989, "step": 2080 }, { "epoch": 0.97, "learning_rate": 1.8068391866913126e-05, "loss": 0.2537, "step": 2090 }, { "epoch": 0.97, "learning_rate": 1.8059149722735675e-05, "loss": 0.2761, "step": 2100 }, { "epoch": 0.98, "learning_rate": 1.804990757855823e-05, "loss": 0.2352, "step": 2110 }, { "epoch": 0.98, "learning_rate": 1.8040665434380778e-05, "loss": 0.2072, "step": 2120 }, { "epoch": 0.98, "learning_rate": 1.8031423290203328e-05, "loss": 0.2255, "step": 2130 }, { "epoch": 0.99, "learning_rate": 1.8022181146025878e-05, "loss": 0.2, "step": 2140 }, { "epoch": 0.99, "learning_rate": 1.801293900184843e-05, "loss": 0.4262, "step": 2150 }, { "epoch": 1.0, "learning_rate": 1.800369685767098e-05, "loss": 0.1726, "step": 2160 }, { "epoch": 1.0, "eval_FN": 92, "eval_FP": 2929, "eval_TN": 18785, "eval_TP": 2010, "eval_accuracy": 0.8731525025193148, "eval_f1": 0.5709416276097146, "eval_loss": 0.3263120651245117, "eval_precision": 0.4069649726665317, "eval_recall": 0.956232159847764, "eval_runtime": 163.0673, "eval_samples_per_second": 146.05, "eval_steps_per_second": 9.131, "step": 2164 }, { "epoch": 1.0, "learning_rate": 1.7994454713493534e-05, "loss": 0.1182, "step": 2170 }, { "epoch": 1.01, "learning_rate": 1.7985212569316083e-05, "loss": 0.2573, "step": 2180 }, { "epoch": 1.01, "learning_rate": 1.7975970425138633e-05, "loss": 0.3027, "step": 2190 }, { "epoch": 1.02, "learning_rate": 1.7966728280961186e-05, "loss": 0.2406, "step": 2200 }, { "epoch": 1.02, "learning_rate": 1.7957486136783736e-05, "loss": 0.2316, "step": 2210 }, { "epoch": 1.03, "learning_rate": 1.7948243992606286e-05, "loss": 0.2582, "step": 2220 }, { "epoch": 1.03, "learning_rate": 1.7939001848428835e-05, "loss": 0.1965, "step": 2230 }, { "epoch": 1.04, "learning_rate": 1.792975970425139e-05, "loss": 0.1878, "step": 2240 }, { "epoch": 1.04, "learning_rate": 1.7920517560073938e-05, "loss": 0.1569, "step": 2250 }, { "epoch": 1.04, "learning_rate": 1.7911275415896488e-05, "loss": 0.239, "step": 2260 }, { "epoch": 1.05, "learning_rate": 1.7902033271719038e-05, "loss": 0.2346, "step": 2270 }, { "epoch": 1.05, "learning_rate": 1.789279112754159e-05, "loss": 0.2595, "step": 2280 }, { "epoch": 1.06, "learning_rate": 1.7883548983364144e-05, "loss": 0.1091, "step": 2290 }, { "epoch": 1.06, "learning_rate": 1.7874306839186694e-05, "loss": 0.2256, "step": 2300 }, { "epoch": 1.07, "learning_rate": 1.7865064695009243e-05, "loss": 0.2107, "step": 2310 }, { "epoch": 1.07, "learning_rate": 1.7855822550831793e-05, "loss": 0.2015, "step": 2320 }, { "epoch": 1.08, "learning_rate": 1.7846580406654346e-05, "loss": 0.201, "step": 2330 }, { "epoch": 1.08, "learning_rate": 1.7837338262476896e-05, "loss": 0.2187, "step": 2340 }, { "epoch": 1.09, "learning_rate": 1.7828096118299446e-05, "loss": 0.1775, "step": 2350 }, { "epoch": 1.09, "learning_rate": 1.7818853974121995e-05, "loss": 0.1631, "step": 2360 }, { "epoch": 1.1, "learning_rate": 1.780961182994455e-05, "loss": 0.3356, "step": 2370 }, { "epoch": 1.1, "learning_rate": 1.7800369685767102e-05, "loss": 0.2472, "step": 2380 }, { "epoch": 1.1, "learning_rate": 1.779112754158965e-05, "loss": 0.185, "step": 2390 }, { "epoch": 1.11, "learning_rate": 1.77818853974122e-05, "loss": 0.2038, "step": 2400 }, { "epoch": 1.11, "learning_rate": 1.777264325323475e-05, "loss": 0.2035, "step": 2410 }, { "epoch": 1.12, "learning_rate": 1.7763401109057304e-05, "loss": 0.275, "step": 2420 }, { "epoch": 1.12, "learning_rate": 1.7754158964879854e-05, "loss": 0.2519, "step": 2430 }, { "epoch": 1.13, "learning_rate": 1.7744916820702404e-05, "loss": 0.2738, "step": 2440 }, { "epoch": 1.13, "learning_rate": 1.7735674676524953e-05, "loss": 0.1933, "step": 2450 }, { "epoch": 1.14, "learning_rate": 1.7726432532347506e-05, "loss": 0.2377, "step": 2460 }, { "epoch": 1.14, "learning_rate": 1.771719038817006e-05, "loss": 0.2853, "step": 2470 }, { "epoch": 1.15, "learning_rate": 1.770794824399261e-05, "loss": 0.2498, "step": 2480 }, { "epoch": 1.15, "learning_rate": 1.769870609981516e-05, "loss": 0.2371, "step": 2490 }, { "epoch": 1.16, "learning_rate": 1.768946395563771e-05, "loss": 0.2118, "step": 2500 }, { "epoch": 1.16, "learning_rate": 1.7680221811460262e-05, "loss": 0.234, "step": 2510 }, { "epoch": 1.16, "learning_rate": 1.767097966728281e-05, "loss": 0.1483, "step": 2520 }, { "epoch": 1.17, "learning_rate": 1.766173752310536e-05, "loss": 0.251, "step": 2530 }, { "epoch": 1.17, "learning_rate": 1.765249537892791e-05, "loss": 0.2158, "step": 2540 }, { "epoch": 1.18, "learning_rate": 1.7643253234750464e-05, "loss": 0.2246, "step": 2550 }, { "epoch": 1.18, "learning_rate": 1.7634011090573014e-05, "loss": 0.3044, "step": 2560 }, { "epoch": 1.19, "learning_rate": 1.7624768946395564e-05, "loss": 0.1206, "step": 2570 }, { "epoch": 1.19, "learning_rate": 1.7615526802218117e-05, "loss": 0.1592, "step": 2580 }, { "epoch": 1.2, "learning_rate": 1.7606284658040666e-05, "loss": 0.2763, "step": 2590 }, { "epoch": 1.2, "learning_rate": 1.759704251386322e-05, "loss": 0.2753, "step": 2600 }, { "epoch": 1.21, "learning_rate": 1.758780036968577e-05, "loss": 0.1143, "step": 2610 }, { "epoch": 1.21, "learning_rate": 1.757855822550832e-05, "loss": 0.1845, "step": 2620 }, { "epoch": 1.22, "learning_rate": 1.756931608133087e-05, "loss": 0.2183, "step": 2630 }, { "epoch": 1.22, "learning_rate": 1.7560073937153422e-05, "loss": 0.1932, "step": 2640 }, { "epoch": 1.22, "learning_rate": 1.755083179297597e-05, "loss": 0.1866, "step": 2650 }, { "epoch": 1.23, "learning_rate": 1.754158964879852e-05, "loss": 0.2009, "step": 2660 }, { "epoch": 1.23, "learning_rate": 1.7532347504621074e-05, "loss": 0.3199, "step": 2670 }, { "epoch": 1.24, "learning_rate": 1.7523105360443624e-05, "loss": 0.1804, "step": 2680 }, { "epoch": 1.24, "learning_rate": 1.7513863216266177e-05, "loss": 0.1572, "step": 2690 }, { "epoch": 1.25, "learning_rate": 1.7504621072088727e-05, "loss": 0.2734, "step": 2700 }, { "epoch": 1.25, "learning_rate": 1.7495378927911277e-05, "loss": 0.1999, "step": 2710 }, { "epoch": 1.26, "learning_rate": 1.7486136783733826e-05, "loss": 0.2374, "step": 2720 }, { "epoch": 1.26, "learning_rate": 1.747689463955638e-05, "loss": 0.2591, "step": 2730 }, { "epoch": 1.27, "learning_rate": 1.746765249537893e-05, "loss": 0.1921, "step": 2740 }, { "epoch": 1.27, "learning_rate": 1.745841035120148e-05, "loss": 0.2127, "step": 2750 }, { "epoch": 1.28, "learning_rate": 1.7449168207024032e-05, "loss": 0.1742, "step": 2760 }, { "epoch": 1.28, "learning_rate": 1.7439926062846582e-05, "loss": 0.1432, "step": 2770 }, { "epoch": 1.28, "learning_rate": 1.7430683918669135e-05, "loss": 0.1152, "step": 2780 }, { "epoch": 1.29, "learning_rate": 1.7421441774491685e-05, "loss": 0.2379, "step": 2790 }, { "epoch": 1.29, "learning_rate": 1.7412199630314234e-05, "loss": 0.1968, "step": 2800 }, { "epoch": 1.3, "learning_rate": 1.7402957486136784e-05, "loss": 0.1386, "step": 2810 }, { "epoch": 1.3, "learning_rate": 1.7393715341959337e-05, "loss": 0.2756, "step": 2820 }, { "epoch": 1.31, "learning_rate": 1.7384473197781887e-05, "loss": 0.1597, "step": 2830 }, { "epoch": 1.31, "learning_rate": 1.7375231053604437e-05, "loss": 0.2474, "step": 2840 }, { "epoch": 1.32, "learning_rate": 1.736598890942699e-05, "loss": 0.2746, "step": 2850 }, { "epoch": 1.32, "learning_rate": 1.735674676524954e-05, "loss": 0.1844, "step": 2860 }, { "epoch": 1.33, "learning_rate": 1.734750462107209e-05, "loss": 0.2099, "step": 2870 }, { "epoch": 1.33, "learning_rate": 1.733826247689464e-05, "loss": 0.205, "step": 2880 }, { "epoch": 1.34, "learning_rate": 1.7329020332717192e-05, "loss": 0.1502, "step": 2890 }, { "epoch": 1.34, "learning_rate": 1.7319778188539742e-05, "loss": 0.261, "step": 2900 }, { "epoch": 1.34, "learning_rate": 1.7310536044362295e-05, "loss": 0.2628, "step": 2910 }, { "epoch": 1.35, "learning_rate": 1.7301293900184845e-05, "loss": 0.2606, "step": 2920 }, { "epoch": 1.35, "learning_rate": 1.7292051756007395e-05, "loss": 0.1922, "step": 2930 }, { "epoch": 1.36, "learning_rate": 1.7282809611829944e-05, "loss": 0.1863, "step": 2940 }, { "epoch": 1.36, "learning_rate": 1.7273567467652497e-05, "loss": 0.1937, "step": 2950 }, { "epoch": 1.37, "learning_rate": 1.7264325323475047e-05, "loss": 0.2392, "step": 2960 }, { "epoch": 1.37, "learning_rate": 1.7255083179297597e-05, "loss": 0.2937, "step": 2970 }, { "epoch": 1.38, "learning_rate": 1.724584103512015e-05, "loss": 0.181, "step": 2980 }, { "epoch": 1.38, "learning_rate": 1.72365988909427e-05, "loss": 0.252, "step": 2990 }, { "epoch": 1.39, "learning_rate": 1.7227356746765253e-05, "loss": 0.2678, "step": 3000 }, { "epoch": 1.39, "learning_rate": 1.7218114602587803e-05, "loss": 0.2635, "step": 3010 }, { "epoch": 1.4, "learning_rate": 1.7208872458410352e-05, "loss": 0.2266, "step": 3020 }, { "epoch": 1.4, "learning_rate": 1.7199630314232902e-05, "loss": 0.164, "step": 3030 }, { "epoch": 1.4, "learning_rate": 1.7190388170055455e-05, "loss": 0.2325, "step": 3040 }, { "epoch": 1.41, "learning_rate": 1.7181146025878005e-05, "loss": 0.3001, "step": 3050 }, { "epoch": 1.41, "learning_rate": 1.7171903881700555e-05, "loss": 0.2545, "step": 3060 }, { "epoch": 1.42, "learning_rate": 1.7162661737523108e-05, "loss": 0.2396, "step": 3070 }, { "epoch": 1.42, "learning_rate": 1.7153419593345657e-05, "loss": 0.2246, "step": 3080 }, { "epoch": 1.43, "learning_rate": 1.714417744916821e-05, "loss": 0.2116, "step": 3090 }, { "epoch": 1.43, "learning_rate": 1.7134935304990757e-05, "loss": 0.1519, "step": 3100 }, { "epoch": 1.44, "learning_rate": 1.712569316081331e-05, "loss": 0.2038, "step": 3110 }, { "epoch": 1.44, "learning_rate": 1.711645101663586e-05, "loss": 0.2458, "step": 3120 }, { "epoch": 1.45, "learning_rate": 1.7107208872458413e-05, "loss": 0.2483, "step": 3130 }, { "epoch": 1.45, "learning_rate": 1.7097966728280963e-05, "loss": 0.1882, "step": 3140 }, { "epoch": 1.46, "learning_rate": 1.7088724584103512e-05, "loss": 0.1183, "step": 3150 }, { "epoch": 1.46, "learning_rate": 1.7079482439926065e-05, "loss": 0.2328, "step": 3160 }, { "epoch": 1.46, "learning_rate": 1.7070240295748615e-05, "loss": 0.2078, "step": 3170 }, { "epoch": 1.47, "learning_rate": 1.7060998151571165e-05, "loss": 0.1605, "step": 3180 }, { "epoch": 1.47, "learning_rate": 1.7051756007393715e-05, "loss": 0.1842, "step": 3190 }, { "epoch": 1.48, "learning_rate": 1.7042513863216268e-05, "loss": 0.207, "step": 3200 }, { "epoch": 1.48, "learning_rate": 1.7033271719038817e-05, "loss": 0.245, "step": 3210 }, { "epoch": 1.49, "learning_rate": 1.702402957486137e-05, "loss": 0.1013, "step": 3220 }, { "epoch": 1.49, "learning_rate": 1.701478743068392e-05, "loss": 0.2845, "step": 3230 }, { "epoch": 1.5, "learning_rate": 1.700554528650647e-05, "loss": 0.1863, "step": 3240 }, { "epoch": 1.5, "learning_rate": 1.6996303142329023e-05, "loss": 0.2356, "step": 3250 }, { "epoch": 1.51, "learning_rate": 1.6987060998151573e-05, "loss": 0.1522, "step": 3260 }, { "epoch": 1.51, "learning_rate": 1.6977818853974123e-05, "loss": 0.2728, "step": 3270 }, { "epoch": 1.52, "learning_rate": 1.6968576709796672e-05, "loss": 0.3639, "step": 3280 }, { "epoch": 1.52, "learning_rate": 1.6959334565619225e-05, "loss": 0.2112, "step": 3290 }, { "epoch": 1.52, "learning_rate": 1.6950092421441775e-05, "loss": 0.3073, "step": 3300 }, { "epoch": 1.53, "learning_rate": 1.6940850277264328e-05, "loss": 0.3143, "step": 3310 }, { "epoch": 1.53, "learning_rate": 1.6931608133086878e-05, "loss": 0.1862, "step": 3320 }, { "epoch": 1.54, "learning_rate": 1.6922365988909428e-05, "loss": 0.138, "step": 3330 }, { "epoch": 1.54, "learning_rate": 1.691312384473198e-05, "loss": 0.2097, "step": 3340 }, { "epoch": 1.55, "learning_rate": 1.690388170055453e-05, "loss": 0.1495, "step": 3350 }, { "epoch": 1.55, "learning_rate": 1.689463955637708e-05, "loss": 0.1226, "step": 3360 }, { "epoch": 1.56, "learning_rate": 1.688539741219963e-05, "loss": 0.1731, "step": 3370 }, { "epoch": 1.56, "learning_rate": 1.6876155268022183e-05, "loss": 0.2506, "step": 3380 }, { "epoch": 1.57, "learning_rate": 1.6866913123844733e-05, "loss": 0.2873, "step": 3390 }, { "epoch": 1.57, "learning_rate": 1.6857670979667286e-05, "loss": 0.1957, "step": 3400 }, { "epoch": 1.58, "learning_rate": 1.6848428835489832e-05, "loss": 0.1876, "step": 3410 }, { "epoch": 1.58, "learning_rate": 1.6839186691312386e-05, "loss": 0.1845, "step": 3420 }, { "epoch": 1.59, "learning_rate": 1.682994454713494e-05, "loss": 0.1528, "step": 3430 }, { "epoch": 1.59, "learning_rate": 1.682070240295749e-05, "loss": 0.2422, "step": 3440 }, { "epoch": 1.59, "learning_rate": 1.6811460258780038e-05, "loss": 0.2416, "step": 3450 }, { "epoch": 1.6, "learning_rate": 1.6802218114602588e-05, "loss": 0.2082, "step": 3460 }, { "epoch": 1.6, "learning_rate": 1.679297597042514e-05, "loss": 0.2268, "step": 3470 }, { "epoch": 1.61, "learning_rate": 1.678373382624769e-05, "loss": 0.2279, "step": 3480 }, { "epoch": 1.61, "learning_rate": 1.677449168207024e-05, "loss": 0.1483, "step": 3490 }, { "epoch": 1.62, "learning_rate": 1.676524953789279e-05, "loss": 0.1867, "step": 3500 }, { "epoch": 1.62, "learning_rate": 1.6756007393715343e-05, "loss": 0.2421, "step": 3510 }, { "epoch": 1.63, "learning_rate": 1.6746765249537896e-05, "loss": 0.2955, "step": 3520 }, { "epoch": 1.63, "learning_rate": 1.6737523105360446e-05, "loss": 0.1093, "step": 3530 }, { "epoch": 1.64, "learning_rate": 1.6728280961182996e-05, "loss": 0.1543, "step": 3540 }, { "epoch": 1.64, "learning_rate": 1.6719038817005546e-05, "loss": 0.2723, "step": 3550 }, { "epoch": 1.65, "learning_rate": 1.67097966728281e-05, "loss": 0.2535, "step": 3560 }, { "epoch": 1.65, "learning_rate": 1.670055452865065e-05, "loss": 0.1417, "step": 3570 }, { "epoch": 1.65, "learning_rate": 1.6691312384473198e-05, "loss": 0.1761, "step": 3580 }, { "epoch": 1.66, "learning_rate": 1.6682070240295748e-05, "loss": 0.1922, "step": 3590 }, { "epoch": 1.66, "learning_rate": 1.66728280961183e-05, "loss": 0.2028, "step": 3600 }, { "epoch": 1.67, "learning_rate": 1.6663585951940854e-05, "loss": 0.2838, "step": 3610 }, { "epoch": 1.67, "learning_rate": 1.6654343807763404e-05, "loss": 0.1669, "step": 3620 }, { "epoch": 1.68, "learning_rate": 1.6645101663585954e-05, "loss": 0.2483, "step": 3630 }, { "epoch": 1.68, "learning_rate": 1.6635859519408503e-05, "loss": 0.2392, "step": 3640 }, { "epoch": 1.69, "learning_rate": 1.6626617375231056e-05, "loss": 0.2248, "step": 3650 }, { "epoch": 1.69, "learning_rate": 1.6617375231053606e-05, "loss": 0.1174, "step": 3660 }, { "epoch": 1.7, "learning_rate": 1.6608133086876156e-05, "loss": 0.1857, "step": 3670 }, { "epoch": 1.7, "learning_rate": 1.6598890942698706e-05, "loss": 0.1231, "step": 3680 }, { "epoch": 1.71, "learning_rate": 1.658964879852126e-05, "loss": 0.1952, "step": 3690 }, { "epoch": 1.71, "learning_rate": 1.658040665434381e-05, "loss": 0.3529, "step": 3700 }, { "epoch": 1.71, "learning_rate": 1.6571164510166358e-05, "loss": 0.1616, "step": 3710 }, { "epoch": 1.72, "learning_rate": 1.656192236598891e-05, "loss": 0.1455, "step": 3720 }, { "epoch": 1.72, "learning_rate": 1.655268022181146e-05, "loss": 0.2894, "step": 3730 }, { "epoch": 1.73, "learning_rate": 1.6543438077634014e-05, "loss": 0.2665, "step": 3740 }, { "epoch": 1.73, "learning_rate": 1.6534195933456564e-05, "loss": 0.2044, "step": 3750 }, { "epoch": 1.74, "learning_rate": 1.6524953789279114e-05, "loss": 0.2238, "step": 3760 }, { "epoch": 1.74, "learning_rate": 1.6515711645101663e-05, "loss": 0.2045, "step": 3770 }, { "epoch": 1.75, "learning_rate": 1.6506469500924216e-05, "loss": 0.1811, "step": 3780 }, { "epoch": 1.75, "learning_rate": 1.6497227356746766e-05, "loss": 0.1808, "step": 3790 }, { "epoch": 1.76, "learning_rate": 1.6487985212569316e-05, "loss": 0.1648, "step": 3800 }, { "epoch": 1.76, "learning_rate": 1.647874306839187e-05, "loss": 0.2987, "step": 3810 }, { "epoch": 1.77, "learning_rate": 1.646950092421442e-05, "loss": 0.1723, "step": 3820 }, { "epoch": 1.77, "learning_rate": 1.6460258780036972e-05, "loss": 0.2308, "step": 3830 }, { "epoch": 1.77, "learning_rate": 1.645101663585952e-05, "loss": 0.1469, "step": 3840 }, { "epoch": 1.78, "learning_rate": 1.644177449168207e-05, "loss": 0.2144, "step": 3850 }, { "epoch": 1.78, "learning_rate": 1.643253234750462e-05, "loss": 0.18, "step": 3860 }, { "epoch": 1.79, "learning_rate": 1.6423290203327174e-05, "loss": 0.2589, "step": 3870 }, { "epoch": 1.79, "learning_rate": 1.6414048059149724e-05, "loss": 0.37, "step": 3880 }, { "epoch": 1.8, "learning_rate": 1.6404805914972274e-05, "loss": 0.1886, "step": 3890 }, { "epoch": 1.8, "learning_rate": 1.6395563770794827e-05, "loss": 0.2182, "step": 3900 }, { "epoch": 1.81, "learning_rate": 1.6386321626617377e-05, "loss": 0.2496, "step": 3910 }, { "epoch": 1.81, "learning_rate": 1.637707948243993e-05, "loss": 0.1864, "step": 3920 }, { "epoch": 1.82, "learning_rate": 1.636783733826248e-05, "loss": 0.1147, "step": 3930 }, { "epoch": 1.82, "learning_rate": 1.635859519408503e-05, "loss": 0.2666, "step": 3940 }, { "epoch": 1.83, "learning_rate": 1.634935304990758e-05, "loss": 0.1679, "step": 3950 }, { "epoch": 1.83, "learning_rate": 1.6340110905730132e-05, "loss": 0.1789, "step": 3960 }, { "epoch": 1.83, "learning_rate": 1.633086876155268e-05, "loss": 0.2757, "step": 3970 }, { "epoch": 1.84, "learning_rate": 1.632162661737523e-05, "loss": 0.2133, "step": 3980 }, { "epoch": 1.84, "learning_rate": 1.6312384473197785e-05, "loss": 0.2088, "step": 3990 }, { "epoch": 1.85, "learning_rate": 1.6303142329020334e-05, "loss": 0.2124, "step": 4000 }, { "epoch": 1.85, "learning_rate": 1.6293900184842887e-05, "loss": 0.1544, "step": 4010 }, { "epoch": 1.86, "learning_rate": 1.6284658040665434e-05, "loss": 0.1481, "step": 4020 }, { "epoch": 1.86, "learning_rate": 1.6275415896487987e-05, "loss": 0.1955, "step": 4030 }, { "epoch": 1.87, "learning_rate": 1.6266173752310537e-05, "loss": 0.1783, "step": 4040 }, { "epoch": 1.87, "learning_rate": 1.625693160813309e-05, "loss": 0.1733, "step": 4050 }, { "epoch": 1.88, "learning_rate": 1.624768946395564e-05, "loss": 0.208, "step": 4060 }, { "epoch": 1.88, "learning_rate": 1.623844731977819e-05, "loss": 0.2737, "step": 4070 }, { "epoch": 1.89, "learning_rate": 1.622920517560074e-05, "loss": 0.2596, "step": 4080 }, { "epoch": 1.89, "learning_rate": 1.6219963031423292e-05, "loss": 0.1047, "step": 4090 }, { "epoch": 1.89, "learning_rate": 1.6210720887245842e-05, "loss": 0.2686, "step": 4100 }, { "epoch": 1.9, "learning_rate": 1.620147874306839e-05, "loss": 0.1282, "step": 4110 }, { "epoch": 1.9, "learning_rate": 1.6192236598890945e-05, "loss": 0.2604, "step": 4120 }, { "epoch": 1.91, "learning_rate": 1.6182994454713494e-05, "loss": 0.226, "step": 4130 }, { "epoch": 1.91, "learning_rate": 1.6173752310536047e-05, "loss": 0.2136, "step": 4140 }, { "epoch": 1.92, "learning_rate": 1.6164510166358597e-05, "loss": 0.1586, "step": 4150 }, { "epoch": 1.92, "learning_rate": 1.6155268022181147e-05, "loss": 0.2335, "step": 4160 }, { "epoch": 1.93, "learning_rate": 1.6146025878003697e-05, "loss": 0.2073, "step": 4170 }, { "epoch": 1.93, "learning_rate": 1.613678373382625e-05, "loss": 0.2272, "step": 4180 }, { "epoch": 1.94, "learning_rate": 1.61275415896488e-05, "loss": 0.1896, "step": 4190 }, { "epoch": 1.94, "learning_rate": 1.611829944547135e-05, "loss": 0.2434, "step": 4200 }, { "epoch": 1.95, "learning_rate": 1.6109057301293902e-05, "loss": 0.2461, "step": 4210 }, { "epoch": 1.95, "learning_rate": 1.6099815157116452e-05, "loss": 0.1402, "step": 4220 }, { "epoch": 1.95, "learning_rate": 1.6090573012939005e-05, "loss": 0.1827, "step": 4230 }, { "epoch": 1.96, "learning_rate": 1.6081330868761555e-05, "loss": 0.1196, "step": 4240 }, { "epoch": 1.96, "learning_rate": 1.6072088724584105e-05, "loss": 0.1763, "step": 4250 }, { "epoch": 1.97, "learning_rate": 1.6062846580406654e-05, "loss": 0.236, "step": 4260 }, { "epoch": 1.97, "learning_rate": 1.6053604436229207e-05, "loss": 0.3238, "step": 4270 }, { "epoch": 1.98, "learning_rate": 1.6044362292051757e-05, "loss": 0.1966, "step": 4280 }, { "epoch": 1.98, "learning_rate": 1.6035120147874307e-05, "loss": 0.1612, "step": 4290 }, { "epoch": 1.99, "learning_rate": 1.602587800369686e-05, "loss": 0.1087, "step": 4300 }, { "epoch": 1.99, "learning_rate": 1.601663585951941e-05, "loss": 0.2229, "step": 4310 }, { "epoch": 2.0, "learning_rate": 1.600739371534196e-05, "loss": 0.1677, "step": 4320 }, { "epoch": 2.0, "eval_FN": 154, "eval_FP": 1915, "eval_TN": 19799, "eval_TP": 1948, "eval_accuracy": 0.9131256298286866, "eval_f1": 0.6531433361274099, "eval_loss": 0.2431023269891739, "eval_precision": 0.5042712917421693, "eval_recall": 0.9267364414843007, "eval_runtime": 163.0468, "eval_samples_per_second": 146.069, "eval_steps_per_second": 9.132, "step": 4328 }, { "epoch": 2.0, "learning_rate": 1.599815157116451e-05, "loss": 0.1693, "step": 4330 }, { "epoch": 2.01, "learning_rate": 1.5988909426987062e-05, "loss": 0.0778, "step": 4340 }, { "epoch": 2.01, "learning_rate": 1.5979667282809612e-05, "loss": 0.0899, "step": 4350 }, { "epoch": 2.01, "learning_rate": 1.5970425138632165e-05, "loss": 0.134, "step": 4360 }, { "epoch": 2.02, "learning_rate": 1.5961182994454715e-05, "loss": 0.3045, "step": 4370 }, { "epoch": 2.02, "learning_rate": 1.5951940850277265e-05, "loss": 0.1845, "step": 4380 }, { "epoch": 2.03, "learning_rate": 1.5942698706099818e-05, "loss": 0.2025, "step": 4390 }, { "epoch": 2.03, "learning_rate": 1.5933456561922367e-05, "loss": 0.12, "step": 4400 }, { "epoch": 2.04, "learning_rate": 1.5924214417744917e-05, "loss": 0.1379, "step": 4410 }, { "epoch": 2.04, "learning_rate": 1.5914972273567467e-05, "loss": 0.1515, "step": 4420 }, { "epoch": 2.05, "learning_rate": 1.590573012939002e-05, "loss": 0.2069, "step": 4430 }, { "epoch": 2.05, "learning_rate": 1.589648798521257e-05, "loss": 0.1782, "step": 4440 }, { "epoch": 2.06, "learning_rate": 1.5887245841035123e-05, "loss": 0.1266, "step": 4450 }, { "epoch": 2.06, "learning_rate": 1.5878003696857673e-05, "loss": 0.2352, "step": 4460 }, { "epoch": 2.07, "learning_rate": 1.5868761552680222e-05, "loss": 0.0707, "step": 4470 }, { "epoch": 2.07, "learning_rate": 1.5859519408502776e-05, "loss": 0.1604, "step": 4480 }, { "epoch": 2.07, "learning_rate": 1.5850277264325325e-05, "loss": 0.2198, "step": 4490 }, { "epoch": 2.08, "learning_rate": 1.5841035120147875e-05, "loss": 0.1885, "step": 4500 }, { "epoch": 2.08, "learning_rate": 1.5831792975970425e-05, "loss": 0.142, "step": 4510 }, { "epoch": 2.09, "learning_rate": 1.5822550831792978e-05, "loss": 0.1663, "step": 4520 }, { "epoch": 2.09, "learning_rate": 1.5813308687615528e-05, "loss": 0.1457, "step": 4530 }, { "epoch": 2.1, "learning_rate": 1.580406654343808e-05, "loss": 0.2221, "step": 4540 }, { "epoch": 2.1, "learning_rate": 1.579482439926063e-05, "loss": 0.2707, "step": 4550 }, { "epoch": 2.11, "learning_rate": 1.578558225508318e-05, "loss": 0.1669, "step": 4560 }, { "epoch": 2.11, "learning_rate": 1.5776340110905733e-05, "loss": 0.3118, "step": 4570 }, { "epoch": 2.12, "learning_rate": 1.5767097966728283e-05, "loss": 0.1553, "step": 4580 }, { "epoch": 2.12, "learning_rate": 1.5757855822550833e-05, "loss": 0.2063, "step": 4590 }, { "epoch": 2.13, "learning_rate": 1.5748613678373382e-05, "loss": 0.1895, "step": 4600 }, { "epoch": 2.13, "learning_rate": 1.5739371534195936e-05, "loss": 0.1753, "step": 4610 }, { "epoch": 2.13, "learning_rate": 1.5730129390018485e-05, "loss": 0.1931, "step": 4620 }, { "epoch": 2.14, "learning_rate": 1.5720887245841035e-05, "loss": 0.1164, "step": 4630 }, { "epoch": 2.14, "learning_rate": 1.5711645101663585e-05, "loss": 0.1091, "step": 4640 }, { "epoch": 2.15, "learning_rate": 1.5702402957486138e-05, "loss": 0.1515, "step": 4650 }, { "epoch": 2.15, "learning_rate": 1.569316081330869e-05, "loss": 0.1247, "step": 4660 }, { "epoch": 2.16, "learning_rate": 1.568391866913124e-05, "loss": 0.1266, "step": 4670 }, { "epoch": 2.16, "learning_rate": 1.567467652495379e-05, "loss": 0.1313, "step": 4680 }, { "epoch": 2.17, "learning_rate": 1.566543438077634e-05, "loss": 0.2272, "step": 4690 }, { "epoch": 2.17, "learning_rate": 1.5656192236598893e-05, "loss": 0.3112, "step": 4700 }, { "epoch": 2.18, "learning_rate": 1.5646950092421443e-05, "loss": 0.2119, "step": 4710 }, { "epoch": 2.18, "learning_rate": 1.5637707948243993e-05, "loss": 0.1471, "step": 4720 }, { "epoch": 2.19, "learning_rate": 1.5628465804066542e-05, "loss": 0.1577, "step": 4730 }, { "epoch": 2.19, "learning_rate": 1.5619223659889096e-05, "loss": 0.1623, "step": 4740 }, { "epoch": 2.2, "learning_rate": 1.560998151571165e-05, "loss": 0.0885, "step": 4750 }, { "epoch": 2.2, "learning_rate": 1.56007393715342e-05, "loss": 0.1159, "step": 4760 }, { "epoch": 2.2, "learning_rate": 1.5591497227356748e-05, "loss": 0.2285, "step": 4770 }, { "epoch": 2.21, "learning_rate": 1.5582255083179298e-05, "loss": 0.2184, "step": 4780 }, { "epoch": 2.21, "learning_rate": 1.557301293900185e-05, "loss": 0.1567, "step": 4790 }, { "epoch": 2.22, "learning_rate": 1.55637707948244e-05, "loss": 0.1285, "step": 4800 }, { "epoch": 2.22, "learning_rate": 1.555452865064695e-05, "loss": 0.2089, "step": 4810 }, { "epoch": 2.23, "learning_rate": 1.55452865064695e-05, "loss": 0.1846, "step": 4820 }, { "epoch": 2.23, "learning_rate": 1.5536044362292053e-05, "loss": 0.2071, "step": 4830 }, { "epoch": 2.24, "learning_rate": 1.5526802218114603e-05, "loss": 0.1728, "step": 4840 }, { "epoch": 2.24, "learning_rate": 1.5517560073937156e-05, "loss": 0.1569, "step": 4850 }, { "epoch": 2.25, "learning_rate": 1.5508317929759706e-05, "loss": 0.1715, "step": 4860 }, { "epoch": 2.25, "learning_rate": 1.5499075785582256e-05, "loss": 0.1174, "step": 4870 }, { "epoch": 2.26, "learning_rate": 1.548983364140481e-05, "loss": 0.2248, "step": 4880 }, { "epoch": 2.26, "learning_rate": 1.548059149722736e-05, "loss": 0.153, "step": 4890 }, { "epoch": 2.26, "learning_rate": 1.5471349353049908e-05, "loss": 0.0981, "step": 4900 }, { "epoch": 2.27, "learning_rate": 1.5462107208872458e-05, "loss": 0.1613, "step": 4910 }, { "epoch": 2.27, "learning_rate": 1.545286506469501e-05, "loss": 0.1446, "step": 4920 }, { "epoch": 2.28, "learning_rate": 1.544362292051756e-05, "loss": 0.2063, "step": 4930 }, { "epoch": 2.28, "learning_rate": 1.543438077634011e-05, "loss": 0.0891, "step": 4940 }, { "epoch": 2.29, "learning_rate": 1.5425138632162664e-05, "loss": 0.2701, "step": 4950 }, { "epoch": 2.29, "learning_rate": 1.5415896487985213e-05, "loss": 0.2333, "step": 4960 }, { "epoch": 2.3, "learning_rate": 1.5406654343807767e-05, "loss": 0.0945, "step": 4970 }, { "epoch": 2.3, "learning_rate": 1.5397412199630316e-05, "loss": 0.1551, "step": 4980 }, { "epoch": 2.31, "learning_rate": 1.5388170055452866e-05, "loss": 0.2299, "step": 4990 }, { "epoch": 2.31, "learning_rate": 1.5378927911275416e-05, "loss": 0.1652, "step": 5000 }, { "epoch": 2.32, "learning_rate": 1.536968576709797e-05, "loss": 0.1054, "step": 5010 }, { "epoch": 2.32, "learning_rate": 1.536044362292052e-05, "loss": 0.1389, "step": 5020 }, { "epoch": 2.32, "learning_rate": 1.5351201478743068e-05, "loss": 0.1398, "step": 5030 }, { "epoch": 2.33, "learning_rate": 1.534195933456562e-05, "loss": 0.1632, "step": 5040 }, { "epoch": 2.33, "learning_rate": 1.533271719038817e-05, "loss": 0.1121, "step": 5050 }, { "epoch": 2.34, "learning_rate": 1.5323475046210724e-05, "loss": 0.1749, "step": 5060 }, { "epoch": 2.34, "learning_rate": 1.5314232902033274e-05, "loss": 0.2336, "step": 5070 }, { "epoch": 2.35, "learning_rate": 1.5304990757855824e-05, "loss": 0.1849, "step": 5080 }, { "epoch": 2.35, "learning_rate": 1.5295748613678373e-05, "loss": 0.1283, "step": 5090 }, { "epoch": 2.36, "learning_rate": 1.5286506469500927e-05, "loss": 0.1509, "step": 5100 }, { "epoch": 2.36, "learning_rate": 1.5277264325323476e-05, "loss": 0.1285, "step": 5110 }, { "epoch": 2.37, "learning_rate": 1.5268022181146026e-05, "loss": 0.2081, "step": 5120 }, { "epoch": 2.37, "learning_rate": 1.5258780036968579e-05, "loss": 0.0792, "step": 5130 }, { "epoch": 2.38, "learning_rate": 1.5249537892791129e-05, "loss": 0.1762, "step": 5140 }, { "epoch": 2.38, "learning_rate": 1.524029574861368e-05, "loss": 0.2162, "step": 5150 }, { "epoch": 2.38, "learning_rate": 1.523105360443623e-05, "loss": 0.3345, "step": 5160 }, { "epoch": 2.39, "learning_rate": 1.5221811460258781e-05, "loss": 0.1134, "step": 5170 }, { "epoch": 2.39, "learning_rate": 1.5212569316081331e-05, "loss": 0.1394, "step": 5180 }, { "epoch": 2.4, "learning_rate": 1.5203327171903883e-05, "loss": 0.1631, "step": 5190 }, { "epoch": 2.4, "learning_rate": 1.5194085027726432e-05, "loss": 0.1021, "step": 5200 }, { "epoch": 2.41, "learning_rate": 1.5184842883548985e-05, "loss": 0.1588, "step": 5210 }, { "epoch": 2.41, "learning_rate": 1.5175600739371535e-05, "loss": 0.145, "step": 5220 }, { "epoch": 2.42, "learning_rate": 1.5166358595194087e-05, "loss": 0.1502, "step": 5230 }, { "epoch": 2.42, "learning_rate": 1.5157116451016638e-05, "loss": 0.1955, "step": 5240 }, { "epoch": 2.43, "learning_rate": 1.5147874306839188e-05, "loss": 0.1758, "step": 5250 }, { "epoch": 2.43, "learning_rate": 1.513863216266174e-05, "loss": 0.1631, "step": 5260 }, { "epoch": 2.44, "learning_rate": 1.5129390018484289e-05, "loss": 0.2541, "step": 5270 }, { "epoch": 2.44, "learning_rate": 1.512014787430684e-05, "loss": 0.1209, "step": 5280 }, { "epoch": 2.44, "learning_rate": 1.511090573012939e-05, "loss": 0.1804, "step": 5290 }, { "epoch": 2.45, "learning_rate": 1.5101663585951941e-05, "loss": 0.0976, "step": 5300 }, { "epoch": 2.45, "learning_rate": 1.5092421441774491e-05, "loss": 0.1198, "step": 5310 }, { "epoch": 2.46, "learning_rate": 1.5083179297597044e-05, "loss": 0.0974, "step": 5320 }, { "epoch": 2.46, "learning_rate": 1.5073937153419596e-05, "loss": 0.2567, "step": 5330 }, { "epoch": 2.47, "learning_rate": 1.5064695009242145e-05, "loss": 0.1927, "step": 5340 }, { "epoch": 2.47, "learning_rate": 1.5055452865064697e-05, "loss": 0.106, "step": 5350 }, { "epoch": 2.48, "learning_rate": 1.5046210720887247e-05, "loss": 0.1234, "step": 5360 }, { "epoch": 2.48, "learning_rate": 1.5036968576709798e-05, "loss": 0.1687, "step": 5370 }, { "epoch": 2.49, "learning_rate": 1.5027726432532348e-05, "loss": 0.1556, "step": 5380 }, { "epoch": 2.49, "learning_rate": 1.50184842883549e-05, "loss": 0.2823, "step": 5390 }, { "epoch": 2.5, "learning_rate": 1.5009242144177449e-05, "loss": 0.1963, "step": 5400 }, { "epoch": 2.5, "learning_rate": 1.5000000000000002e-05, "loss": 0.1522, "step": 5410 }, { "epoch": 2.5, "learning_rate": 1.4990757855822553e-05, "loss": 0.1814, "step": 5420 }, { "epoch": 2.51, "learning_rate": 1.4981515711645103e-05, "loss": 0.1369, "step": 5430 }, { "epoch": 2.51, "learning_rate": 1.4972273567467655e-05, "loss": 0.1202, "step": 5440 }, { "epoch": 2.52, "learning_rate": 1.4963031423290204e-05, "loss": 0.1905, "step": 5450 }, { "epoch": 2.52, "learning_rate": 1.4953789279112756e-05, "loss": 0.0854, "step": 5460 }, { "epoch": 2.53, "learning_rate": 1.4944547134935306e-05, "loss": 0.1451, "step": 5470 }, { "epoch": 2.53, "learning_rate": 1.4935304990757857e-05, "loss": 0.1844, "step": 5480 }, { "epoch": 2.54, "learning_rate": 1.4926062846580407e-05, "loss": 0.1622, "step": 5490 }, { "epoch": 2.54, "learning_rate": 1.4916820702402958e-05, "loss": 0.1502, "step": 5500 }, { "epoch": 2.55, "learning_rate": 1.4907578558225511e-05, "loss": 0.1883, "step": 5510 }, { "epoch": 2.55, "learning_rate": 1.4898336414048061e-05, "loss": 0.1838, "step": 5520 }, { "epoch": 2.56, "learning_rate": 1.4889094269870612e-05, "loss": 0.1045, "step": 5530 }, { "epoch": 2.56, "learning_rate": 1.4879852125693162e-05, "loss": 0.188, "step": 5540 }, { "epoch": 2.56, "learning_rate": 1.4870609981515714e-05, "loss": 0.1753, "step": 5550 }, { "epoch": 2.57, "learning_rate": 1.4861367837338263e-05, "loss": 0.1206, "step": 5560 }, { "epoch": 2.57, "learning_rate": 1.4852125693160815e-05, "loss": 0.0749, "step": 5570 }, { "epoch": 2.58, "learning_rate": 1.4842883548983364e-05, "loss": 0.1198, "step": 5580 }, { "epoch": 2.58, "learning_rate": 1.4833641404805916e-05, "loss": 0.1161, "step": 5590 }, { "epoch": 2.59, "learning_rate": 1.4824399260628467e-05, "loss": 0.2238, "step": 5600 }, { "epoch": 2.59, "learning_rate": 1.4815157116451017e-05, "loss": 0.2453, "step": 5610 }, { "epoch": 2.6, "learning_rate": 1.480591497227357e-05, "loss": 0.2279, "step": 5620 }, { "epoch": 2.6, "learning_rate": 1.479667282809612e-05, "loss": 0.2033, "step": 5630 }, { "epoch": 2.61, "learning_rate": 1.4787430683918671e-05, "loss": 0.2203, "step": 5640 }, { "epoch": 2.61, "learning_rate": 1.4778188539741221e-05, "loss": 0.1777, "step": 5650 }, { "epoch": 2.62, "learning_rate": 1.4768946395563772e-05, "loss": 0.0941, "step": 5660 }, { "epoch": 2.62, "learning_rate": 1.4759704251386322e-05, "loss": 0.1303, "step": 5670 }, { "epoch": 2.62, "learning_rate": 1.4750462107208874e-05, "loss": 0.1256, "step": 5680 }, { "epoch": 2.63, "learning_rate": 1.4741219963031423e-05, "loss": 0.1631, "step": 5690 }, { "epoch": 2.63, "learning_rate": 1.4731977818853975e-05, "loss": 0.222, "step": 5700 }, { "epoch": 2.64, "learning_rate": 1.4722735674676528e-05, "loss": 0.2531, "step": 5710 }, { "epoch": 2.64, "learning_rate": 1.4713493530499076e-05, "loss": 0.295, "step": 5720 }, { "epoch": 2.65, "learning_rate": 1.4704251386321629e-05, "loss": 0.1892, "step": 5730 }, { "epoch": 2.65, "learning_rate": 1.4695009242144179e-05, "loss": 0.1502, "step": 5740 }, { "epoch": 2.66, "learning_rate": 1.468576709796673e-05, "loss": 0.1864, "step": 5750 }, { "epoch": 2.66, "learning_rate": 1.467652495378928e-05, "loss": 0.1066, "step": 5760 }, { "epoch": 2.67, "learning_rate": 1.4667282809611831e-05, "loss": 0.0748, "step": 5770 }, { "epoch": 2.67, "learning_rate": 1.4658040665434381e-05, "loss": 0.1447, "step": 5780 }, { "epoch": 2.68, "learning_rate": 1.4648798521256932e-05, "loss": 0.1479, "step": 5790 }, { "epoch": 2.68, "learning_rate": 1.4639556377079484e-05, "loss": 0.0488, "step": 5800 }, { "epoch": 2.68, "learning_rate": 1.4630314232902034e-05, "loss": 0.1795, "step": 5810 }, { "epoch": 2.69, "learning_rate": 1.4621072088724587e-05, "loss": 0.1834, "step": 5820 }, { "epoch": 2.69, "learning_rate": 1.4611829944547136e-05, "loss": 0.1199, "step": 5830 }, { "epoch": 2.7, "learning_rate": 1.4602587800369688e-05, "loss": 0.0923, "step": 5840 }, { "epoch": 2.7, "learning_rate": 1.4593345656192238e-05, "loss": 0.1359, "step": 5850 }, { "epoch": 2.71, "learning_rate": 1.4584103512014789e-05, "loss": 0.2247, "step": 5860 }, { "epoch": 2.71, "learning_rate": 1.4574861367837339e-05, "loss": 0.2223, "step": 5870 }, { "epoch": 2.72, "learning_rate": 1.456561922365989e-05, "loss": 0.199, "step": 5880 }, { "epoch": 2.72, "learning_rate": 1.4556377079482442e-05, "loss": 0.0742, "step": 5890 }, { "epoch": 2.73, "learning_rate": 1.4547134935304991e-05, "loss": 0.2031, "step": 5900 }, { "epoch": 2.73, "learning_rate": 1.4537892791127543e-05, "loss": 0.1722, "step": 5910 }, { "epoch": 2.74, "learning_rate": 1.4528650646950093e-05, "loss": 0.2189, "step": 5920 }, { "epoch": 2.74, "learning_rate": 1.4519408502772646e-05, "loss": 0.194, "step": 5930 }, { "epoch": 2.74, "learning_rate": 1.4510166358595195e-05, "loss": 0.2184, "step": 5940 }, { "epoch": 2.75, "learning_rate": 1.4500924214417747e-05, "loss": 0.1603, "step": 5950 }, { "epoch": 2.75, "learning_rate": 1.4491682070240297e-05, "loss": 0.1252, "step": 5960 }, { "epoch": 2.76, "learning_rate": 1.4482439926062848e-05, "loss": 0.2046, "step": 5970 }, { "epoch": 2.76, "learning_rate": 1.44731977818854e-05, "loss": 0.2342, "step": 5980 }, { "epoch": 2.77, "learning_rate": 1.4463955637707949e-05, "loss": 0.1965, "step": 5990 }, { "epoch": 2.77, "learning_rate": 1.44547134935305e-05, "loss": 0.0897, "step": 6000 }, { "epoch": 2.78, "learning_rate": 1.444547134935305e-05, "loss": 0.1382, "step": 6010 }, { "epoch": 2.78, "learning_rate": 1.4436229205175603e-05, "loss": 0.1913, "step": 6020 }, { "epoch": 2.79, "learning_rate": 1.4426987060998151e-05, "loss": 0.2165, "step": 6030 }, { "epoch": 2.79, "learning_rate": 1.4417744916820705e-05, "loss": 0.2323, "step": 6040 }, { "epoch": 2.8, "learning_rate": 1.4408502772643254e-05, "loss": 0.1614, "step": 6050 }, { "epoch": 2.8, "learning_rate": 1.4399260628465806e-05, "loss": 0.1031, "step": 6060 }, { "epoch": 2.8, "learning_rate": 1.4390018484288355e-05, "loss": 0.1484, "step": 6070 }, { "epoch": 2.81, "learning_rate": 1.4380776340110907e-05, "loss": 0.1863, "step": 6080 }, { "epoch": 2.81, "learning_rate": 1.4371534195933458e-05, "loss": 0.1886, "step": 6090 }, { "epoch": 2.82, "learning_rate": 1.4362292051756008e-05, "loss": 0.19, "step": 6100 }, { "epoch": 2.82, "learning_rate": 1.435304990757856e-05, "loss": 0.1077, "step": 6110 }, { "epoch": 2.83, "learning_rate": 1.434380776340111e-05, "loss": 0.2046, "step": 6120 }, { "epoch": 2.83, "learning_rate": 1.4334565619223662e-05, "loss": 0.1591, "step": 6130 }, { "epoch": 2.84, "learning_rate": 1.432532347504621e-05, "loss": 0.1402, "step": 6140 }, { "epoch": 2.84, "learning_rate": 1.4316081330868763e-05, "loss": 0.1378, "step": 6150 }, { "epoch": 2.85, "learning_rate": 1.4306839186691313e-05, "loss": 0.2014, "step": 6160 }, { "epoch": 2.85, "learning_rate": 1.4297597042513865e-05, "loss": 0.0909, "step": 6170 }, { "epoch": 2.86, "learning_rate": 1.4288354898336416e-05, "loss": 0.1678, "step": 6180 }, { "epoch": 2.86, "learning_rate": 1.4279112754158966e-05, "loss": 0.1332, "step": 6190 }, { "epoch": 2.87, "learning_rate": 1.4269870609981517e-05, "loss": 0.175, "step": 6200 }, { "epoch": 2.87, "learning_rate": 1.4260628465804067e-05, "loss": 0.1509, "step": 6210 }, { "epoch": 2.87, "learning_rate": 1.4251386321626618e-05, "loss": 0.1605, "step": 6220 }, { "epoch": 2.88, "learning_rate": 1.4242144177449168e-05, "loss": 0.2096, "step": 6230 }, { "epoch": 2.88, "learning_rate": 1.4232902033271721e-05, "loss": 0.1479, "step": 6240 }, { "epoch": 2.89, "learning_rate": 1.4223659889094271e-05, "loss": 0.1447, "step": 6250 }, { "epoch": 2.89, "learning_rate": 1.4214417744916822e-05, "loss": 0.111, "step": 6260 }, { "epoch": 2.9, "learning_rate": 1.4205175600739374e-05, "loss": 0.2485, "step": 6270 }, { "epoch": 2.9, "learning_rate": 1.4195933456561923e-05, "loss": 0.2003, "step": 6280 }, { "epoch": 2.91, "learning_rate": 1.4186691312384475e-05, "loss": 0.1885, "step": 6290 }, { "epoch": 2.91, "learning_rate": 1.4177449168207025e-05, "loss": 0.1717, "step": 6300 }, { "epoch": 2.92, "learning_rate": 1.4168207024029576e-05, "loss": 0.1828, "step": 6310 }, { "epoch": 2.92, "learning_rate": 1.4158964879852126e-05, "loss": 0.1587, "step": 6320 }, { "epoch": 2.93, "learning_rate": 1.4149722735674677e-05, "loss": 0.1554, "step": 6330 }, { "epoch": 2.93, "learning_rate": 1.4140480591497227e-05, "loss": 0.1474, "step": 6340 }, { "epoch": 2.93, "learning_rate": 1.413123844731978e-05, "loss": 0.2028, "step": 6350 }, { "epoch": 2.94, "learning_rate": 1.4121996303142331e-05, "loss": 0.186, "step": 6360 }, { "epoch": 2.94, "learning_rate": 1.4112754158964881e-05, "loss": 0.2351, "step": 6370 }, { "epoch": 2.95, "learning_rate": 1.4103512014787433e-05, "loss": 0.2059, "step": 6380 }, { "epoch": 2.95, "learning_rate": 1.4094269870609982e-05, "loss": 0.1439, "step": 6390 }, { "epoch": 2.96, "learning_rate": 1.4085027726432534e-05, "loss": 0.0755, "step": 6400 }, { "epoch": 2.96, "learning_rate": 1.4075785582255084e-05, "loss": 0.0884, "step": 6410 }, { "epoch": 2.97, "learning_rate": 1.4066543438077635e-05, "loss": 0.1204, "step": 6420 }, { "epoch": 2.97, "learning_rate": 1.4057301293900185e-05, "loss": 0.2709, "step": 6430 }, { "epoch": 2.98, "learning_rate": 1.4048059149722738e-05, "loss": 0.1441, "step": 6440 }, { "epoch": 2.98, "learning_rate": 1.4038817005545286e-05, "loss": 0.3135, "step": 6450 }, { "epoch": 2.99, "learning_rate": 1.4029574861367839e-05, "loss": 0.1247, "step": 6460 }, { "epoch": 2.99, "learning_rate": 1.402033271719039e-05, "loss": 0.1411, "step": 6470 }, { "epoch": 2.99, "learning_rate": 1.401109057301294e-05, "loss": 0.1754, "step": 6480 }, { "epoch": 3.0, "learning_rate": 1.4001848428835492e-05, "loss": 0.1889, "step": 6490 }, { "epoch": 3.0, "eval_FN": 126, "eval_FP": 2026, "eval_TN": 19688, "eval_TP": 1976, "eval_accuracy": 0.9096405777628485, "eval_f1": 0.6474442988204456, "eval_loss": 0.30875712633132935, "eval_precision": 0.49375312343828087, "eval_recall": 0.9400570884871551, "eval_runtime": 163.0348, "eval_samples_per_second": 146.079, "eval_steps_per_second": 9.133, "step": 6492 }, { "epoch": 3.0, "learning_rate": 1.3992606284658041e-05, "loss": 0.092, "step": 6500 }, { "epoch": 3.01, "learning_rate": 1.3983364140480593e-05, "loss": 0.1608, "step": 6510 }, { "epoch": 3.01, "learning_rate": 1.3974121996303142e-05, "loss": 0.07, "step": 6520 }, { "epoch": 3.02, "learning_rate": 1.3964879852125694e-05, "loss": 0.1854, "step": 6530 }, { "epoch": 3.02, "learning_rate": 1.3955637707948244e-05, "loss": 0.0796, "step": 6540 }, { "epoch": 3.03, "learning_rate": 1.3946395563770797e-05, "loss": 0.2506, "step": 6550 }, { "epoch": 3.03, "learning_rate": 1.3937153419593348e-05, "loss": 0.1543, "step": 6560 }, { "epoch": 3.04, "learning_rate": 1.3927911275415898e-05, "loss": 0.0829, "step": 6570 }, { "epoch": 3.04, "learning_rate": 1.391866913123845e-05, "loss": 0.0894, "step": 6580 }, { "epoch": 3.05, "learning_rate": 1.3909426987060999e-05, "loss": 0.13, "step": 6590 }, { "epoch": 3.05, "learning_rate": 1.390018484288355e-05, "loss": 0.0936, "step": 6600 }, { "epoch": 3.05, "learning_rate": 1.38909426987061e-05, "loss": 0.2314, "step": 6610 }, { "epoch": 3.06, "learning_rate": 1.3881700554528652e-05, "loss": 0.1633, "step": 6620 }, { "epoch": 3.06, "learning_rate": 1.3872458410351201e-05, "loss": 0.1514, "step": 6630 }, { "epoch": 3.07, "learning_rate": 1.3863216266173753e-05, "loss": 0.1215, "step": 6640 }, { "epoch": 3.07, "learning_rate": 1.3853974121996306e-05, "loss": 0.2375, "step": 6650 }, { "epoch": 3.08, "learning_rate": 1.3844731977818856e-05, "loss": 0.1384, "step": 6660 }, { "epoch": 3.08, "learning_rate": 1.3835489833641407e-05, "loss": 0.1254, "step": 6670 }, { "epoch": 3.09, "learning_rate": 1.3826247689463957e-05, "loss": 0.1134, "step": 6680 }, { "epoch": 3.09, "learning_rate": 1.3817005545286508e-05, "loss": 0.1303, "step": 6690 }, { "epoch": 3.1, "learning_rate": 1.3807763401109058e-05, "loss": 0.0661, "step": 6700 }, { "epoch": 3.1, "learning_rate": 1.379852125693161e-05, "loss": 0.1399, "step": 6710 }, { "epoch": 3.11, "learning_rate": 1.3789279112754159e-05, "loss": 0.0628, "step": 6720 }, { "epoch": 3.11, "learning_rate": 1.378003696857671e-05, "loss": 0.0966, "step": 6730 }, { "epoch": 3.11, "learning_rate": 1.3770794824399264e-05, "loss": 0.1229, "step": 6740 }, { "epoch": 3.12, "learning_rate": 1.3761552680221812e-05, "loss": 0.1257, "step": 6750 }, { "epoch": 3.12, "learning_rate": 1.3752310536044365e-05, "loss": 0.1688, "step": 6760 }, { "epoch": 3.13, "learning_rate": 1.3743068391866914e-05, "loss": 0.1208, "step": 6770 }, { "epoch": 3.13, "learning_rate": 1.3733826247689466e-05, "loss": 0.0698, "step": 6780 }, { "epoch": 3.14, "learning_rate": 1.3724584103512016e-05, "loss": 0.147, "step": 6790 }, { "epoch": 3.14, "learning_rate": 1.3715341959334567e-05, "loss": 0.0728, "step": 6800 }, { "epoch": 3.15, "learning_rate": 1.3706099815157117e-05, "loss": 0.1901, "step": 6810 }, { "epoch": 3.15, "learning_rate": 1.3696857670979668e-05, "loss": 0.1266, "step": 6820 }, { "epoch": 3.16, "learning_rate": 1.3687615526802218e-05, "loss": 0.0909, "step": 6830 }, { "epoch": 3.16, "learning_rate": 1.367837338262477e-05, "loss": 0.1212, "step": 6840 }, { "epoch": 3.17, "learning_rate": 1.3669131238447322e-05, "loss": 0.1651, "step": 6850 }, { "epoch": 3.17, "learning_rate": 1.3659889094269872e-05, "loss": 0.1628, "step": 6860 }, { "epoch": 3.17, "learning_rate": 1.3650646950092424e-05, "loss": 0.071, "step": 6870 }, { "epoch": 3.18, "learning_rate": 1.3641404805914973e-05, "loss": 0.1509, "step": 6880 }, { "epoch": 3.18, "learning_rate": 1.3632162661737525e-05, "loss": 0.0614, "step": 6890 }, { "epoch": 3.19, "learning_rate": 1.3622920517560075e-05, "loss": 0.1359, "step": 6900 }, { "epoch": 3.19, "learning_rate": 1.3613678373382626e-05, "loss": 0.1815, "step": 6910 }, { "epoch": 3.2, "learning_rate": 1.3604436229205176e-05, "loss": 0.1053, "step": 6920 }, { "epoch": 3.2, "learning_rate": 1.3595194085027727e-05, "loss": 0.1322, "step": 6930 }, { "epoch": 3.21, "learning_rate": 1.3585951940850279e-05, "loss": 0.2098, "step": 6940 }, { "epoch": 3.21, "learning_rate": 1.3576709796672828e-05, "loss": 0.1107, "step": 6950 }, { "epoch": 3.22, "learning_rate": 1.3567467652495381e-05, "loss": 0.0465, "step": 6960 }, { "epoch": 3.22, "learning_rate": 1.3558225508317931e-05, "loss": 0.1872, "step": 6970 }, { "epoch": 3.23, "learning_rate": 1.3548983364140483e-05, "loss": 0.1557, "step": 6980 }, { "epoch": 3.23, "learning_rate": 1.3539741219963032e-05, "loss": 0.1685, "step": 6990 }, { "epoch": 3.23, "learning_rate": 1.3530499075785584e-05, "loss": 0.0711, "step": 7000 }, { "epoch": 3.24, "learning_rate": 1.3521256931608133e-05, "loss": 0.034, "step": 7010 }, { "epoch": 3.24, "learning_rate": 1.3512014787430685e-05, "loss": 0.0841, "step": 7020 }, { "epoch": 3.25, "learning_rate": 1.3502772643253236e-05, "loss": 0.0744, "step": 7030 }, { "epoch": 3.25, "learning_rate": 1.3493530499075786e-05, "loss": 0.1943, "step": 7040 }, { "epoch": 3.26, "learning_rate": 1.3484288354898339e-05, "loss": 0.1761, "step": 7050 }, { "epoch": 3.26, "learning_rate": 1.3475046210720887e-05, "loss": 0.104, "step": 7060 }, { "epoch": 3.27, "learning_rate": 1.346580406654344e-05, "loss": 0.1992, "step": 7070 }, { "epoch": 3.27, "learning_rate": 1.345656192236599e-05, "loss": 0.0787, "step": 7080 }, { "epoch": 3.28, "learning_rate": 1.3447319778188541e-05, "loss": 0.1542, "step": 7090 }, { "epoch": 3.28, "learning_rate": 1.3438077634011091e-05, "loss": 0.2017, "step": 7100 }, { "epoch": 3.29, "learning_rate": 1.3428835489833643e-05, "loss": 0.1848, "step": 7110 }, { "epoch": 3.29, "learning_rate": 1.3419593345656194e-05, "loss": 0.1599, "step": 7120 }, { "epoch": 3.29, "learning_rate": 1.3410351201478744e-05, "loss": 0.147, "step": 7130 }, { "epoch": 3.3, "learning_rate": 1.3401109057301295e-05, "loss": 0.1278, "step": 7140 }, { "epoch": 3.3, "learning_rate": 1.3391866913123845e-05, "loss": 0.1537, "step": 7150 }, { "epoch": 3.31, "learning_rate": 1.3382624768946398e-05, "loss": 0.1828, "step": 7160 }, { "epoch": 3.31, "learning_rate": 1.3373382624768946e-05, "loss": 0.0564, "step": 7170 }, { "epoch": 3.32, "learning_rate": 1.33641404805915e-05, "loss": 0.1579, "step": 7180 }, { "epoch": 3.32, "learning_rate": 1.3354898336414049e-05, "loss": 0.2135, "step": 7190 }, { "epoch": 3.33, "learning_rate": 1.33456561922366e-05, "loss": 0.1095, "step": 7200 }, { "epoch": 3.33, "learning_rate": 1.333641404805915e-05, "loss": 0.1526, "step": 7210 }, { "epoch": 3.34, "learning_rate": 1.3327171903881701e-05, "loss": 0.101, "step": 7220 }, { "epoch": 3.34, "learning_rate": 1.3317929759704253e-05, "loss": 0.1614, "step": 7230 }, { "epoch": 3.35, "learning_rate": 1.3308687615526803e-05, "loss": 0.2209, "step": 7240 }, { "epoch": 3.35, "learning_rate": 1.3299445471349354e-05, "loss": 0.0681, "step": 7250 }, { "epoch": 3.35, "learning_rate": 1.3290203327171904e-05, "loss": 0.1329, "step": 7260 }, { "epoch": 3.36, "learning_rate": 1.3280961182994457e-05, "loss": 0.1506, "step": 7270 }, { "epoch": 3.36, "learning_rate": 1.3271719038817007e-05, "loss": 0.2083, "step": 7280 }, { "epoch": 3.37, "learning_rate": 1.3262476894639558e-05, "loss": 0.1681, "step": 7290 }, { "epoch": 3.37, "learning_rate": 1.3253234750462108e-05, "loss": 0.0829, "step": 7300 }, { "epoch": 3.38, "learning_rate": 1.324399260628466e-05, "loss": 0.1119, "step": 7310 }, { "epoch": 3.38, "learning_rate": 1.323475046210721e-05, "loss": 0.1995, "step": 7320 }, { "epoch": 3.39, "learning_rate": 1.322550831792976e-05, "loss": 0.0635, "step": 7330 }, { "epoch": 3.39, "learning_rate": 1.3216266173752312e-05, "loss": 0.0325, "step": 7340 }, { "epoch": 3.4, "learning_rate": 1.3207024029574862e-05, "loss": 0.1415, "step": 7350 }, { "epoch": 3.4, "learning_rate": 1.3197781885397413e-05, "loss": 0.0952, "step": 7360 }, { "epoch": 3.41, "learning_rate": 1.3188539741219963e-05, "loss": 0.1257, "step": 7370 }, { "epoch": 3.41, "learning_rate": 1.3179297597042516e-05, "loss": 0.0877, "step": 7380 }, { "epoch": 3.41, "learning_rate": 1.3170055452865066e-05, "loss": 0.1186, "step": 7390 }, { "epoch": 3.42, "learning_rate": 1.3160813308687617e-05, "loss": 0.123, "step": 7400 }, { "epoch": 3.42, "learning_rate": 1.3151571164510168e-05, "loss": 0.1545, "step": 7410 }, { "epoch": 3.43, "learning_rate": 1.3142329020332718e-05, "loss": 0.2534, "step": 7420 }, { "epoch": 3.43, "learning_rate": 1.313308687615527e-05, "loss": 0.1597, "step": 7430 }, { "epoch": 3.44, "learning_rate": 1.312384473197782e-05, "loss": 0.1211, "step": 7440 }, { "epoch": 3.44, "learning_rate": 1.311460258780037e-05, "loss": 0.1496, "step": 7450 }, { "epoch": 3.45, "learning_rate": 1.310536044362292e-05, "loss": 0.1237, "step": 7460 }, { "epoch": 3.45, "learning_rate": 1.3096118299445474e-05, "loss": 0.1392, "step": 7470 }, { "epoch": 3.46, "learning_rate": 1.3086876155268022e-05, "loss": 0.1304, "step": 7480 }, { "epoch": 3.46, "learning_rate": 1.3077634011090575e-05, "loss": 0.1449, "step": 7490 }, { "epoch": 3.47, "learning_rate": 1.3068391866913126e-05, "loss": 0.1421, "step": 7500 }, { "epoch": 3.47, "learning_rate": 1.3059149722735676e-05, "loss": 0.1672, "step": 7510 }, { "epoch": 3.48, "learning_rate": 1.3049907578558227e-05, "loss": 0.0367, "step": 7520 }, { "epoch": 3.48, "learning_rate": 1.3040665434380777e-05, "loss": 0.0744, "step": 7530 }, { "epoch": 3.48, "learning_rate": 1.3031423290203328e-05, "loss": 0.18, "step": 7540 }, { "epoch": 3.49, "learning_rate": 1.3022181146025878e-05, "loss": 0.1495, "step": 7550 }, { "epoch": 3.49, "learning_rate": 1.301293900184843e-05, "loss": 0.1859, "step": 7560 }, { "epoch": 3.5, "learning_rate": 1.300369685767098e-05, "loss": 0.1321, "step": 7570 }, { "epoch": 3.5, "learning_rate": 1.2994454713493532e-05, "loss": 0.2258, "step": 7580 }, { "epoch": 3.51, "learning_rate": 1.2985212569316082e-05, "loss": 0.1329, "step": 7590 }, { "epoch": 3.51, "learning_rate": 1.2975970425138634e-05, "loss": 0.256, "step": 7600 }, { "epoch": 3.52, "learning_rate": 1.2966728280961185e-05, "loss": 0.0857, "step": 7610 }, { "epoch": 3.52, "learning_rate": 1.2957486136783735e-05, "loss": 0.1456, "step": 7620 }, { "epoch": 3.53, "learning_rate": 1.2948243992606286e-05, "loss": 0.1097, "step": 7630 }, { "epoch": 3.53, "learning_rate": 1.2939001848428836e-05, "loss": 0.1276, "step": 7640 }, { "epoch": 3.54, "learning_rate": 1.2929759704251387e-05, "loss": 0.0831, "step": 7650 }, { "epoch": 3.54, "learning_rate": 1.2920517560073937e-05, "loss": 0.1594, "step": 7660 }, { "epoch": 3.54, "learning_rate": 1.2911275415896488e-05, "loss": 0.2551, "step": 7670 }, { "epoch": 3.55, "learning_rate": 1.2902033271719038e-05, "loss": 0.1945, "step": 7680 }, { "epoch": 3.55, "learning_rate": 1.2892791127541591e-05, "loss": 0.1369, "step": 7690 }, { "epoch": 3.56, "learning_rate": 1.2883548983364143e-05, "loss": 0.1532, "step": 7700 }, { "epoch": 3.56, "learning_rate": 1.2874306839186692e-05, "loss": 0.1241, "step": 7710 }, { "epoch": 3.57, "learning_rate": 1.2865064695009244e-05, "loss": 0.1157, "step": 7720 }, { "epoch": 3.57, "learning_rate": 1.2855822550831794e-05, "loss": 0.0908, "step": 7730 }, { "epoch": 3.58, "learning_rate": 1.2846580406654345e-05, "loss": 0.1243, "step": 7740 }, { "epoch": 3.58, "learning_rate": 1.2837338262476895e-05, "loss": 0.0662, "step": 7750 }, { "epoch": 3.59, "learning_rate": 1.2828096118299446e-05, "loss": 0.106, "step": 7760 }, { "epoch": 3.59, "learning_rate": 1.2818853974121996e-05, "loss": 0.1555, "step": 7770 }, { "epoch": 3.6, "learning_rate": 1.2809611829944549e-05, "loss": 0.0597, "step": 7780 }, { "epoch": 3.6, "learning_rate": 1.28003696857671e-05, "loss": 0.2435, "step": 7790 }, { "epoch": 3.6, "learning_rate": 1.279112754158965e-05, "loss": 0.0433, "step": 7800 }, { "epoch": 3.61, "learning_rate": 1.2781885397412202e-05, "loss": 0.173, "step": 7810 }, { "epoch": 3.61, "learning_rate": 1.2772643253234751e-05, "loss": 0.1033, "step": 7820 }, { "epoch": 3.62, "learning_rate": 1.2763401109057303e-05, "loss": 0.1205, "step": 7830 }, { "epoch": 3.62, "learning_rate": 1.2754158964879853e-05, "loss": 0.1439, "step": 7840 }, { "epoch": 3.63, "learning_rate": 1.2744916820702404e-05, "loss": 0.1431, "step": 7850 }, { "epoch": 3.63, "learning_rate": 1.2735674676524954e-05, "loss": 0.1154, "step": 7860 }, { "epoch": 3.64, "learning_rate": 1.2726432532347505e-05, "loss": 0.1756, "step": 7870 }, { "epoch": 3.64, "learning_rate": 1.2717190388170058e-05, "loss": 0.1284, "step": 7880 }, { "epoch": 3.65, "learning_rate": 1.2707948243992608e-05, "loss": 0.1489, "step": 7890 }, { "epoch": 3.65, "learning_rate": 1.269870609981516e-05, "loss": 0.165, "step": 7900 }, { "epoch": 3.66, "learning_rate": 1.2689463955637709e-05, "loss": 0.1441, "step": 7910 }, { "epoch": 3.66, "learning_rate": 1.268022181146026e-05, "loss": 0.0829, "step": 7920 }, { "epoch": 3.66, "learning_rate": 1.267097966728281e-05, "loss": 0.2279, "step": 7930 }, { "epoch": 3.67, "learning_rate": 1.2661737523105362e-05, "loss": 0.071, "step": 7940 }, { "epoch": 3.67, "learning_rate": 1.2652495378927911e-05, "loss": 0.2191, "step": 7950 }, { "epoch": 3.68, "learning_rate": 1.2643253234750463e-05, "loss": 0.0741, "step": 7960 }, { "epoch": 3.68, "learning_rate": 1.2634011090573013e-05, "loss": 0.1252, "step": 7970 }, { "epoch": 3.69, "learning_rate": 1.2624768946395564e-05, "loss": 0.1331, "step": 7980 }, { "epoch": 3.69, "learning_rate": 1.2615526802218117e-05, "loss": 0.1392, "step": 7990 }, { "epoch": 3.7, "learning_rate": 1.2606284658040667e-05, "loss": 0.1508, "step": 8000 }, { "epoch": 3.7, "learning_rate": 1.2597042513863218e-05, "loss": 0.0846, "step": 8010 }, { "epoch": 3.71, "learning_rate": 1.2587800369685768e-05, "loss": 0.1584, "step": 8020 }, { "epoch": 3.71, "learning_rate": 1.257855822550832e-05, "loss": 0.1701, "step": 8030 }, { "epoch": 3.72, "learning_rate": 1.2569316081330869e-05, "loss": 0.1294, "step": 8040 }, { "epoch": 3.72, "learning_rate": 1.256007393715342e-05, "loss": 0.1925, "step": 8050 }, { "epoch": 3.72, "learning_rate": 1.255083179297597e-05, "loss": 0.1043, "step": 8060 }, { "epoch": 3.73, "learning_rate": 1.2541589648798522e-05, "loss": 0.1026, "step": 8070 }, { "epoch": 3.73, "learning_rate": 1.2532347504621075e-05, "loss": 0.1082, "step": 8080 }, { "epoch": 3.74, "learning_rate": 1.2523105360443623e-05, "loss": 0.1443, "step": 8090 }, { "epoch": 3.74, "learning_rate": 1.2513863216266176e-05, "loss": 0.2675, "step": 8100 }, { "epoch": 3.75, "learning_rate": 1.2504621072088726e-05, "loss": 0.2078, "step": 8110 }, { "epoch": 3.75, "learning_rate": 1.2495378927911277e-05, "loss": 0.1008, "step": 8120 }, { "epoch": 3.76, "learning_rate": 1.2486136783733827e-05, "loss": 0.1177, "step": 8130 }, { "epoch": 3.76, "learning_rate": 1.2476894639556378e-05, "loss": 0.0531, "step": 8140 }, { "epoch": 3.77, "learning_rate": 1.2467652495378928e-05, "loss": 0.101, "step": 8150 }, { "epoch": 3.77, "learning_rate": 1.245841035120148e-05, "loss": 0.1183, "step": 8160 }, { "epoch": 3.78, "learning_rate": 1.2449168207024031e-05, "loss": 0.0745, "step": 8170 }, { "epoch": 3.78, "learning_rate": 1.243992606284658e-05, "loss": 0.0899, "step": 8180 }, { "epoch": 3.78, "learning_rate": 1.2430683918669134e-05, "loss": 0.1172, "step": 8190 }, { "epoch": 3.79, "learning_rate": 1.2421441774491683e-05, "loss": 0.17, "step": 8200 }, { "epoch": 3.79, "learning_rate": 1.2412199630314235e-05, "loss": 0.2534, "step": 8210 }, { "epoch": 3.8, "learning_rate": 1.2402957486136785e-05, "loss": 0.1343, "step": 8220 }, { "epoch": 3.8, "learning_rate": 1.2393715341959336e-05, "loss": 0.1981, "step": 8230 }, { "epoch": 3.81, "learning_rate": 1.2384473197781886e-05, "loss": 0.209, "step": 8240 }, { "epoch": 3.81, "learning_rate": 1.2375231053604437e-05, "loss": 0.1779, "step": 8250 }, { "epoch": 3.82, "learning_rate": 1.2365988909426989e-05, "loss": 0.2018, "step": 8260 }, { "epoch": 3.82, "learning_rate": 1.2356746765249538e-05, "loss": 0.0883, "step": 8270 }, { "epoch": 3.83, "learning_rate": 1.234750462107209e-05, "loss": 0.1144, "step": 8280 }, { "epoch": 3.83, "learning_rate": 1.233826247689464e-05, "loss": 0.0888, "step": 8290 }, { "epoch": 3.84, "learning_rate": 1.2329020332717193e-05, "loss": 0.1038, "step": 8300 }, { "epoch": 3.84, "learning_rate": 1.2319778188539742e-05, "loss": 0.1542, "step": 8310 }, { "epoch": 3.84, "learning_rate": 1.2310536044362294e-05, "loss": 0.089, "step": 8320 }, { "epoch": 3.85, "learning_rate": 1.2301293900184844e-05, "loss": 0.0975, "step": 8330 }, { "epoch": 3.85, "learning_rate": 1.2292051756007395e-05, "loss": 0.1068, "step": 8340 }, { "epoch": 3.86, "learning_rate": 1.2282809611829945e-05, "loss": 0.0622, "step": 8350 }, { "epoch": 3.86, "learning_rate": 1.2273567467652496e-05, "loss": 0.261, "step": 8360 }, { "epoch": 3.87, "learning_rate": 1.2264325323475048e-05, "loss": 0.2745, "step": 8370 }, { "epoch": 3.87, "learning_rate": 1.2255083179297597e-05, "loss": 0.1443, "step": 8380 }, { "epoch": 3.88, "learning_rate": 1.224584103512015e-05, "loss": 0.0845, "step": 8390 }, { "epoch": 3.88, "learning_rate": 1.2236598890942698e-05, "loss": 0.1453, "step": 8400 }, { "epoch": 3.89, "learning_rate": 1.2227356746765252e-05, "loss": 0.1805, "step": 8410 }, { "epoch": 3.89, "learning_rate": 1.2218114602587801e-05, "loss": 0.0862, "step": 8420 }, { "epoch": 3.9, "learning_rate": 1.2208872458410353e-05, "loss": 0.1698, "step": 8430 }, { "epoch": 3.9, "learning_rate": 1.2199630314232902e-05, "loss": 0.1081, "step": 8440 }, { "epoch": 3.9, "learning_rate": 1.2190388170055454e-05, "loss": 0.1509, "step": 8450 }, { "epoch": 3.91, "learning_rate": 1.2181146025878005e-05, "loss": 0.0978, "step": 8460 }, { "epoch": 3.91, "learning_rate": 1.2171903881700555e-05, "loss": 0.1355, "step": 8470 }, { "epoch": 3.92, "learning_rate": 1.2162661737523106e-05, "loss": 0.0728, "step": 8480 }, { "epoch": 3.92, "learning_rate": 1.2153419593345656e-05, "loss": 0.1311, "step": 8490 }, { "epoch": 3.93, "learning_rate": 1.214417744916821e-05, "loss": 0.1439, "step": 8500 }, { "epoch": 3.93, "learning_rate": 1.2134935304990757e-05, "loss": 0.1587, "step": 8510 }, { "epoch": 3.94, "learning_rate": 1.212569316081331e-05, "loss": 0.1838, "step": 8520 }, { "epoch": 3.94, "learning_rate": 1.211645101663586e-05, "loss": 0.1913, "step": 8530 }, { "epoch": 3.95, "learning_rate": 1.2107208872458412e-05, "loss": 0.1058, "step": 8540 }, { "epoch": 3.95, "learning_rate": 1.2097966728280963e-05, "loss": 0.1247, "step": 8550 }, { "epoch": 3.96, "learning_rate": 1.2088724584103513e-05, "loss": 0.078, "step": 8560 }, { "epoch": 3.96, "learning_rate": 1.2079482439926064e-05, "loss": 0.2963, "step": 8570 }, { "epoch": 3.96, "learning_rate": 1.2070240295748614e-05, "loss": 0.2009, "step": 8580 }, { "epoch": 3.97, "learning_rate": 1.2060998151571165e-05, "loss": 0.1388, "step": 8590 }, { "epoch": 3.97, "learning_rate": 1.2051756007393715e-05, "loss": 0.0504, "step": 8600 }, { "epoch": 3.98, "learning_rate": 1.2042513863216268e-05, "loss": 0.1085, "step": 8610 }, { "epoch": 3.98, "learning_rate": 1.2033271719038818e-05, "loss": 0.0852, "step": 8620 }, { "epoch": 3.99, "learning_rate": 1.202402957486137e-05, "loss": 0.1902, "step": 8630 }, { "epoch": 3.99, "learning_rate": 1.201478743068392e-05, "loss": 0.1269, "step": 8640 }, { "epoch": 4.0, "learning_rate": 1.200554528650647e-05, "loss": 0.0604, "step": 8650 }, { "epoch": 4.0, "eval_FN": 116, "eval_FP": 2082, "eval_TN": 19632, "eval_TP": 1986, "eval_accuracy": 0.9077091031239503, "eval_f1": 0.6437601296596435, "eval_loss": 0.36759352684020996, "eval_precision": 0.4882005899705015, "eval_recall": 0.9448144624167459, "eval_runtime": 163.0163, "eval_samples_per_second": 146.096, "eval_steps_per_second": 9.134, "step": 8656 }, { "epoch": 4.0, "learning_rate": 1.1996303142329022e-05, "loss": 0.1082, "step": 8660 }, { "epoch": 4.01, "learning_rate": 1.1987060998151572e-05, "loss": 0.051, "step": 8670 }, { "epoch": 4.01, "learning_rate": 1.1977818853974123e-05, "loss": 0.1289, "step": 8680 }, { "epoch": 4.02, "learning_rate": 1.1968576709796673e-05, "loss": 0.1679, "step": 8690 }, { "epoch": 4.02, "learning_rate": 1.1959334565619224e-05, "loss": 0.1295, "step": 8700 }, { "epoch": 4.02, "learning_rate": 1.1950092421441774e-05, "loss": 0.0724, "step": 8710 }, { "epoch": 4.03, "learning_rate": 1.1940850277264327e-05, "loss": 0.1341, "step": 8720 }, { "epoch": 4.03, "learning_rate": 1.1931608133086877e-05, "loss": 0.0611, "step": 8730 }, { "epoch": 4.04, "learning_rate": 1.1922365988909428e-05, "loss": 0.1045, "step": 8740 }, { "epoch": 4.04, "learning_rate": 1.191312384473198e-05, "loss": 0.0857, "step": 8750 }, { "epoch": 4.05, "learning_rate": 1.190388170055453e-05, "loss": 0.0524, "step": 8760 }, { "epoch": 4.05, "learning_rate": 1.189463955637708e-05, "loss": 0.1058, "step": 8770 }, { "epoch": 4.06, "learning_rate": 1.188539741219963e-05, "loss": 0.0925, "step": 8780 }, { "epoch": 4.06, "learning_rate": 1.1876155268022182e-05, "loss": 0.0465, "step": 8790 }, { "epoch": 4.07, "learning_rate": 1.1866913123844732e-05, "loss": 0.0521, "step": 8800 }, { "epoch": 4.07, "learning_rate": 1.1857670979667285e-05, "loss": 0.1578, "step": 8810 }, { "epoch": 4.08, "learning_rate": 1.1848428835489833e-05, "loss": 0.0924, "step": 8820 }, { "epoch": 4.08, "learning_rate": 1.1839186691312386e-05, "loss": 0.109, "step": 8830 }, { "epoch": 4.09, "learning_rate": 1.1829944547134937e-05, "loss": 0.0679, "step": 8840 }, { "epoch": 4.09, "learning_rate": 1.1820702402957487e-05, "loss": 0.0937, "step": 8850 }, { "epoch": 4.09, "learning_rate": 1.1811460258780039e-05, "loss": 0.1044, "step": 8860 }, { "epoch": 4.1, "learning_rate": 1.1802218114602588e-05, "loss": 0.0542, "step": 8870 }, { "epoch": 4.1, "learning_rate": 1.179297597042514e-05, "loss": 0.0512, "step": 8880 }, { "epoch": 4.11, "learning_rate": 1.178373382624769e-05, "loss": 0.0507, "step": 8890 }, { "epoch": 4.11, "learning_rate": 1.177449168207024e-05, "loss": 0.0565, "step": 8900 }, { "epoch": 4.12, "learning_rate": 1.176524953789279e-05, "loss": 0.1484, "step": 8910 }, { "epoch": 4.12, "learning_rate": 1.1756007393715344e-05, "loss": 0.0784, "step": 8920 }, { "epoch": 4.13, "learning_rate": 1.1746765249537895e-05, "loss": 0.1945, "step": 8930 }, { "epoch": 4.13, "learning_rate": 1.1737523105360445e-05, "loss": 0.0373, "step": 8940 }, { "epoch": 4.14, "learning_rate": 1.1728280961182996e-05, "loss": 0.0702, "step": 8950 }, { "epoch": 4.14, "learning_rate": 1.1719038817005546e-05, "loss": 0.011, "step": 8960 }, { "epoch": 4.15, "learning_rate": 1.1709796672828097e-05, "loss": 0.1058, "step": 8970 }, { "epoch": 4.15, "learning_rate": 1.1700554528650647e-05, "loss": 0.1382, "step": 8980 }, { "epoch": 4.15, "learning_rate": 1.1691312384473199e-05, "loss": 0.0719, "step": 8990 }, { "epoch": 4.16, "learning_rate": 1.1682070240295748e-05, "loss": 0.0361, "step": 9000 }, { "epoch": 4.16, "learning_rate": 1.16728280961183e-05, "loss": 0.076, "step": 9010 }, { "epoch": 4.17, "learning_rate": 1.1663585951940853e-05, "loss": 0.1234, "step": 9020 }, { "epoch": 4.17, "learning_rate": 1.1654343807763403e-05, "loss": 0.0558, "step": 9030 }, { "epoch": 4.18, "learning_rate": 1.1645101663585954e-05, "loss": 0.1283, "step": 9040 }, { "epoch": 4.18, "learning_rate": 1.1635859519408504e-05, "loss": 0.1385, "step": 9050 }, { "epoch": 4.19, "learning_rate": 1.1626617375231055e-05, "loss": 0.0979, "step": 9060 }, { "epoch": 4.19, "learning_rate": 1.1617375231053605e-05, "loss": 0.1694, "step": 9070 }, { "epoch": 4.2, "learning_rate": 1.1608133086876156e-05, "loss": 0.0424, "step": 9080 }, { "epoch": 4.2, "learning_rate": 1.1598890942698706e-05, "loss": 0.1151, "step": 9090 }, { "epoch": 4.21, "learning_rate": 1.1589648798521257e-05, "loss": 0.1428, "step": 9100 }, { "epoch": 4.21, "learning_rate": 1.1580406654343807e-05, "loss": 0.1413, "step": 9110 }, { "epoch": 4.21, "learning_rate": 1.1571164510166359e-05, "loss": 0.0312, "step": 9120 }, { "epoch": 4.22, "learning_rate": 1.1561922365988912e-05, "loss": 0.1292, "step": 9130 }, { "epoch": 4.22, "learning_rate": 1.1552680221811461e-05, "loss": 0.1285, "step": 9140 }, { "epoch": 4.23, "learning_rate": 1.1543438077634013e-05, "loss": 0.0558, "step": 9150 }, { "epoch": 4.23, "learning_rate": 1.1534195933456563e-05, "loss": 0.1014, "step": 9160 }, { "epoch": 4.24, "learning_rate": 1.1524953789279114e-05, "loss": 0.0933, "step": 9170 }, { "epoch": 4.24, "learning_rate": 1.1515711645101664e-05, "loss": 0.1363, "step": 9180 }, { "epoch": 4.25, "learning_rate": 1.1506469500924215e-05, "loss": 0.109, "step": 9190 }, { "epoch": 4.25, "learning_rate": 1.1497227356746765e-05, "loss": 0.0724, "step": 9200 }, { "epoch": 4.26, "learning_rate": 1.1487985212569316e-05, "loss": 0.1461, "step": 9210 }, { "epoch": 4.26, "learning_rate": 1.147874306839187e-05, "loss": 0.1487, "step": 9220 }, { "epoch": 4.27, "learning_rate": 1.146950092421442e-05, "loss": 0.1147, "step": 9230 }, { "epoch": 4.27, "learning_rate": 1.146025878003697e-05, "loss": 0.1593, "step": 9240 }, { "epoch": 4.27, "learning_rate": 1.145101663585952e-05, "loss": 0.0551, "step": 9250 }, { "epoch": 4.28, "learning_rate": 1.1441774491682072e-05, "loss": 0.1572, "step": 9260 }, { "epoch": 4.28, "learning_rate": 1.1432532347504622e-05, "loss": 0.2398, "step": 9270 }, { "epoch": 4.29, "learning_rate": 1.1423290203327173e-05, "loss": 0.0658, "step": 9280 }, { "epoch": 4.29, "learning_rate": 1.1414048059149723e-05, "loss": 0.1447, "step": 9290 }, { "epoch": 4.3, "learning_rate": 1.1404805914972274e-05, "loss": 0.1724, "step": 9300 }, { "epoch": 4.3, "learning_rate": 1.1395563770794826e-05, "loss": 0.1096, "step": 9310 }, { "epoch": 4.31, "learning_rate": 1.1386321626617375e-05, "loss": 0.0611, "step": 9320 }, { "epoch": 4.31, "learning_rate": 1.1377079482439928e-05, "loss": 0.0716, "step": 9330 }, { "epoch": 4.32, "learning_rate": 1.1367837338262478e-05, "loss": 0.0975, "step": 9340 }, { "epoch": 4.32, "learning_rate": 1.135859519408503e-05, "loss": 0.1534, "step": 9350 }, { "epoch": 4.33, "learning_rate": 1.134935304990758e-05, "loss": 0.0633, "step": 9360 }, { "epoch": 4.33, "learning_rate": 1.134011090573013e-05, "loss": 0.1068, "step": 9370 }, { "epoch": 4.33, "learning_rate": 1.133086876155268e-05, "loss": 0.0876, "step": 9380 }, { "epoch": 4.34, "learning_rate": 1.1321626617375232e-05, "loss": 0.0489, "step": 9390 }, { "epoch": 4.34, "learning_rate": 1.1312384473197783e-05, "loss": 0.1216, "step": 9400 }, { "epoch": 4.35, "learning_rate": 1.1303142329020333e-05, "loss": 0.0671, "step": 9410 }, { "epoch": 4.35, "learning_rate": 1.1293900184842886e-05, "loss": 0.0943, "step": 9420 }, { "epoch": 4.36, "learning_rate": 1.1284658040665434e-05, "loss": 0.1554, "step": 9430 }, { "epoch": 4.36, "learning_rate": 1.1275415896487987e-05, "loss": 0.1475, "step": 9440 }, { "epoch": 4.37, "learning_rate": 1.1266173752310537e-05, "loss": 0.0797, "step": 9450 }, { "epoch": 4.37, "learning_rate": 1.1256931608133088e-05, "loss": 0.1987, "step": 9460 }, { "epoch": 4.38, "learning_rate": 1.1247689463955638e-05, "loss": 0.0725, "step": 9470 }, { "epoch": 4.38, "learning_rate": 1.123844731977819e-05, "loss": 0.1361, "step": 9480 }, { "epoch": 4.39, "learning_rate": 1.122920517560074e-05, "loss": 0.0907, "step": 9490 }, { "epoch": 4.39, "learning_rate": 1.121996303142329e-05, "loss": 0.2568, "step": 9500 }, { "epoch": 4.39, "learning_rate": 1.1210720887245842e-05, "loss": 0.0981, "step": 9510 }, { "epoch": 4.4, "learning_rate": 1.1201478743068392e-05, "loss": 0.066, "step": 9520 }, { "epoch": 4.4, "learning_rate": 1.1192236598890945e-05, "loss": 0.1515, "step": 9530 }, { "epoch": 4.41, "learning_rate": 1.1182994454713493e-05, "loss": 0.104, "step": 9540 }, { "epoch": 4.41, "learning_rate": 1.1173752310536046e-05, "loss": 0.0885, "step": 9550 }, { "epoch": 4.42, "learning_rate": 1.1164510166358596e-05, "loss": 0.0112, "step": 9560 }, { "epoch": 4.42, "learning_rate": 1.1155268022181147e-05, "loss": 0.0673, "step": 9570 }, { "epoch": 4.43, "learning_rate": 1.1146025878003697e-05, "loss": 0.0387, "step": 9580 }, { "epoch": 4.43, "learning_rate": 1.1136783733826248e-05, "loss": 0.0766, "step": 9590 }, { "epoch": 4.44, "learning_rate": 1.11275415896488e-05, "loss": 0.0799, "step": 9600 }, { "epoch": 4.44, "learning_rate": 1.111829944547135e-05, "loss": 0.1403, "step": 9610 }, { "epoch": 4.45, "learning_rate": 1.1109057301293901e-05, "loss": 0.0781, "step": 9620 }, { "epoch": 4.45, "learning_rate": 1.109981515711645e-05, "loss": 0.0869, "step": 9630 }, { "epoch": 4.45, "learning_rate": 1.1090573012939004e-05, "loss": 0.0622, "step": 9640 }, { "epoch": 4.46, "learning_rate": 1.1081330868761554e-05, "loss": 0.1337, "step": 9650 }, { "epoch": 4.46, "learning_rate": 1.1072088724584105e-05, "loss": 0.08, "step": 9660 }, { "epoch": 4.47, "learning_rate": 1.1062846580406655e-05, "loss": 0.1921, "step": 9670 }, { "epoch": 4.47, "learning_rate": 1.1053604436229206e-05, "loss": 0.0962, "step": 9680 }, { "epoch": 4.48, "learning_rate": 1.1044362292051758e-05, "loss": 0.0523, "step": 9690 }, { "epoch": 4.48, "learning_rate": 1.1035120147874307e-05, "loss": 0.0911, "step": 9700 }, { "epoch": 4.49, "learning_rate": 1.1025878003696859e-05, "loss": 0.1357, "step": 9710 }, { "epoch": 4.49, "learning_rate": 1.1016635859519409e-05, "loss": 0.1388, "step": 9720 }, { "epoch": 4.5, "learning_rate": 1.100739371534196e-05, "loss": 0.155, "step": 9730 }, { "epoch": 4.5, "learning_rate": 1.099815157116451e-05, "loss": 0.1643, "step": 9740 }, { "epoch": 4.51, "learning_rate": 1.0988909426987063e-05, "loss": 0.0661, "step": 9750 }, { "epoch": 4.51, "learning_rate": 1.0979667282809613e-05, "loss": 0.0781, "step": 9760 }, { "epoch": 4.51, "learning_rate": 1.0970425138632164e-05, "loss": 0.1619, "step": 9770 }, { "epoch": 4.52, "learning_rate": 1.0961182994454715e-05, "loss": 0.148, "step": 9780 }, { "epoch": 4.52, "learning_rate": 1.0951940850277265e-05, "loss": 0.1887, "step": 9790 }, { "epoch": 4.53, "learning_rate": 1.0942698706099817e-05, "loss": 0.0532, "step": 9800 }, { "epoch": 4.53, "learning_rate": 1.0933456561922366e-05, "loss": 0.2194, "step": 9810 }, { "epoch": 4.54, "learning_rate": 1.0924214417744918e-05, "loss": 0.1177, "step": 9820 }, { "epoch": 4.54, "learning_rate": 1.0914972273567467e-05, "loss": 0.0839, "step": 9830 }, { "epoch": 4.55, "learning_rate": 1.090573012939002e-05, "loss": 0.0282, "step": 9840 }, { "epoch": 4.55, "learning_rate": 1.0896487985212569e-05, "loss": 0.2399, "step": 9850 }, { "epoch": 4.56, "learning_rate": 1.0887245841035122e-05, "loss": 0.1123, "step": 9860 }, { "epoch": 4.56, "learning_rate": 1.0878003696857671e-05, "loss": 0.064, "step": 9870 }, { "epoch": 4.57, "learning_rate": 1.0868761552680223e-05, "loss": 0.0658, "step": 9880 }, { "epoch": 4.57, "learning_rate": 1.0859519408502774e-05, "loss": 0.0971, "step": 9890 }, { "epoch": 4.57, "learning_rate": 1.0850277264325324e-05, "loss": 0.0899, "step": 9900 }, { "epoch": 4.58, "learning_rate": 1.0841035120147875e-05, "loss": 0.0902, "step": 9910 }, { "epoch": 4.58, "learning_rate": 1.0831792975970425e-05, "loss": 0.0749, "step": 9920 }, { "epoch": 4.59, "learning_rate": 1.0822550831792977e-05, "loss": 0.1266, "step": 9930 }, { "epoch": 4.59, "learning_rate": 1.0813308687615526e-05, "loss": 0.121, "step": 9940 }, { "epoch": 4.6, "learning_rate": 1.080406654343808e-05, "loss": 0.0678, "step": 9950 }, { "epoch": 4.6, "learning_rate": 1.0794824399260629e-05, "loss": 0.1851, "step": 9960 }, { "epoch": 4.61, "learning_rate": 1.078558225508318e-05, "loss": 0.1122, "step": 9970 }, { "epoch": 4.61, "learning_rate": 1.0776340110905732e-05, "loss": 0.1105, "step": 9980 }, { "epoch": 4.62, "learning_rate": 1.0767097966728282e-05, "loss": 0.0409, "step": 9990 }, { "epoch": 4.62, "learning_rate": 1.0757855822550833e-05, "loss": 0.1091, "step": 10000 }, { "epoch": 4.63, "learning_rate": 1.0748613678373383e-05, "loss": 0.1947, "step": 10010 }, { "epoch": 4.63, "learning_rate": 1.0739371534195934e-05, "loss": 0.0772, "step": 10020 }, { "epoch": 4.63, "learning_rate": 1.0730129390018484e-05, "loss": 0.0593, "step": 10030 }, { "epoch": 4.64, "learning_rate": 1.0720887245841035e-05, "loss": 0.1024, "step": 10040 }, { "epoch": 4.64, "learning_rate": 1.0711645101663585e-05, "loss": 0.0684, "step": 10050 }, { "epoch": 4.65, "learning_rate": 1.0702402957486138e-05, "loss": 0.0773, "step": 10060 }, { "epoch": 4.65, "learning_rate": 1.069316081330869e-05, "loss": 0.3008, "step": 10070 }, { "epoch": 4.66, "learning_rate": 1.068391866913124e-05, "loss": 0.1019, "step": 10080 }, { "epoch": 4.66, "learning_rate": 1.0674676524953791e-05, "loss": 0.0934, "step": 10090 }, { "epoch": 4.67, "learning_rate": 1.066543438077634e-05, "loss": 0.1444, "step": 10100 }, { "epoch": 4.67, "learning_rate": 1.0656192236598892e-05, "loss": 0.1014, "step": 10110 }, { "epoch": 4.68, "learning_rate": 1.0646950092421442e-05, "loss": 0.0793, "step": 10120 }, { "epoch": 4.68, "learning_rate": 1.0637707948243993e-05, "loss": 0.182, "step": 10130 }, { "epoch": 4.69, "learning_rate": 1.0628465804066543e-05, "loss": 0.1439, "step": 10140 }, { "epoch": 4.69, "learning_rate": 1.0619223659889096e-05, "loss": 0.1289, "step": 10150 }, { "epoch": 4.7, "learning_rate": 1.0609981515711647e-05, "loss": 0.172, "step": 10160 }, { "epoch": 4.7, "learning_rate": 1.0600739371534197e-05, "loss": 0.1431, "step": 10170 }, { "epoch": 4.7, "learning_rate": 1.0591497227356749e-05, "loss": 0.0665, "step": 10180 }, { "epoch": 4.71, "learning_rate": 1.0582255083179298e-05, "loss": 0.1395, "step": 10190 }, { "epoch": 4.71, "learning_rate": 1.057301293900185e-05, "loss": 0.0785, "step": 10200 }, { "epoch": 4.72, "learning_rate": 1.05637707948244e-05, "loss": 0.1169, "step": 10210 }, { "epoch": 4.72, "learning_rate": 1.0554528650646951e-05, "loss": 0.0939, "step": 10220 }, { "epoch": 4.73, "learning_rate": 1.05452865064695e-05, "loss": 0.1058, "step": 10230 }, { "epoch": 4.73, "learning_rate": 1.0536044362292052e-05, "loss": 0.0177, "step": 10240 }, { "epoch": 4.74, "learning_rate": 1.0526802218114602e-05, "loss": 0.1094, "step": 10250 }, { "epoch": 4.74, "learning_rate": 1.0517560073937155e-05, "loss": 0.1778, "step": 10260 }, { "epoch": 4.75, "learning_rate": 1.0508317929759706e-05, "loss": 0.0481, "step": 10270 }, { "epoch": 4.75, "learning_rate": 1.0499075785582256e-05, "loss": 0.1544, "step": 10280 }, { "epoch": 4.76, "learning_rate": 1.0489833641404808e-05, "loss": 0.101, "step": 10290 }, { "epoch": 4.76, "learning_rate": 1.0480591497227357e-05, "loss": 0.1339, "step": 10300 }, { "epoch": 4.76, "learning_rate": 1.0471349353049909e-05, "loss": 0.0552, "step": 10310 }, { "epoch": 4.77, "learning_rate": 1.0462107208872458e-05, "loss": 0.1504, "step": 10320 }, { "epoch": 4.77, "learning_rate": 1.045286506469501e-05, "loss": 0.1033, "step": 10330 }, { "epoch": 4.78, "learning_rate": 1.044362292051756e-05, "loss": 0.071, "step": 10340 }, { "epoch": 4.78, "learning_rate": 1.0434380776340111e-05, "loss": 0.088, "step": 10350 }, { "epoch": 4.79, "learning_rate": 1.0425138632162664e-05, "loss": 0.0489, "step": 10360 }, { "epoch": 4.79, "learning_rate": 1.0415896487985214e-05, "loss": 0.1291, "step": 10370 }, { "epoch": 4.8, "learning_rate": 1.0406654343807765e-05, "loss": 0.1819, "step": 10380 }, { "epoch": 4.8, "learning_rate": 1.0397412199630315e-05, "loss": 0.1201, "step": 10390 }, { "epoch": 4.81, "learning_rate": 1.0388170055452866e-05, "loss": 0.1016, "step": 10400 }, { "epoch": 4.81, "learning_rate": 1.0378927911275416e-05, "loss": 0.1445, "step": 10410 }, { "epoch": 4.82, "learning_rate": 1.0369685767097968e-05, "loss": 0.2022, "step": 10420 }, { "epoch": 4.82, "learning_rate": 1.0360443622920517e-05, "loss": 0.0565, "step": 10430 }, { "epoch": 4.82, "learning_rate": 1.0351201478743069e-05, "loss": 0.0481, "step": 10440 }, { "epoch": 4.83, "learning_rate": 1.0341959334565622e-05, "loss": 0.0786, "step": 10450 }, { "epoch": 4.83, "learning_rate": 1.033271719038817e-05, "loss": 0.0345, "step": 10460 }, { "epoch": 4.84, "learning_rate": 1.0323475046210723e-05, "loss": 0.0016, "step": 10470 }, { "epoch": 4.84, "learning_rate": 1.0314232902033273e-05, "loss": 0.1368, "step": 10480 }, { "epoch": 4.85, "learning_rate": 1.0304990757855824e-05, "loss": 0.1308, "step": 10490 }, { "epoch": 4.85, "learning_rate": 1.0295748613678374e-05, "loss": 0.0899, "step": 10500 }, { "epoch": 4.86, "learning_rate": 1.0286506469500925e-05, "loss": 0.1872, "step": 10510 }, { "epoch": 4.86, "learning_rate": 1.0277264325323475e-05, "loss": 0.1168, "step": 10520 }, { "epoch": 4.87, "learning_rate": 1.0268022181146026e-05, "loss": 0.1262, "step": 10530 }, { "epoch": 4.87, "learning_rate": 1.0258780036968578e-05, "loss": 0.1019, "step": 10540 }, { "epoch": 4.88, "learning_rate": 1.0249537892791128e-05, "loss": 0.0433, "step": 10550 }, { "epoch": 4.88, "learning_rate": 1.024029574861368e-05, "loss": 0.1067, "step": 10560 }, { "epoch": 4.88, "learning_rate": 1.023105360443623e-05, "loss": 0.2071, "step": 10570 }, { "epoch": 4.89, "learning_rate": 1.0221811460258782e-05, "loss": 0.1151, "step": 10580 }, { "epoch": 4.89, "learning_rate": 1.0212569316081332e-05, "loss": 0.0884, "step": 10590 }, { "epoch": 4.9, "learning_rate": 1.0203327171903883e-05, "loss": 0.1918, "step": 10600 }, { "epoch": 4.9, "learning_rate": 1.0194085027726433e-05, "loss": 0.0662, "step": 10610 }, { "epoch": 4.91, "learning_rate": 1.0184842883548984e-05, "loss": 0.0316, "step": 10620 }, { "epoch": 4.91, "learning_rate": 1.0175600739371534e-05, "loss": 0.0494, "step": 10630 }, { "epoch": 4.92, "learning_rate": 1.0166358595194085e-05, "loss": 0.0921, "step": 10640 }, { "epoch": 4.92, "learning_rate": 1.0157116451016637e-05, "loss": 0.0776, "step": 10650 }, { "epoch": 4.93, "learning_rate": 1.0147874306839186e-05, "loss": 0.1395, "step": 10660 }, { "epoch": 4.93, "learning_rate": 1.013863216266174e-05, "loss": 0.1255, "step": 10670 }, { "epoch": 4.94, "learning_rate": 1.012939001848429e-05, "loss": 0.092, "step": 10680 }, { "epoch": 4.94, "learning_rate": 1.012014787430684e-05, "loss": 0.2602, "step": 10690 }, { "epoch": 4.94, "learning_rate": 1.011090573012939e-05, "loss": 0.2088, "step": 10700 }, { "epoch": 4.95, "learning_rate": 1.0101663585951942e-05, "loss": 0.1179, "step": 10710 }, { "epoch": 4.95, "learning_rate": 1.0092421441774492e-05, "loss": 0.1746, "step": 10720 }, { "epoch": 4.96, "learning_rate": 1.0083179297597043e-05, "loss": 0.0274, "step": 10730 }, { "epoch": 4.96, "learning_rate": 1.0073937153419595e-05, "loss": 0.1696, "step": 10740 }, { "epoch": 4.97, "learning_rate": 1.0064695009242144e-05, "loss": 0.1125, "step": 10750 }, { "epoch": 4.97, "learning_rate": 1.0055452865064697e-05, "loss": 0.073, "step": 10760 }, { "epoch": 4.98, "learning_rate": 1.0046210720887245e-05, "loss": 0.1056, "step": 10770 }, { "epoch": 4.98, "learning_rate": 1.0036968576709799e-05, "loss": 0.116, "step": 10780 }, { "epoch": 4.99, "learning_rate": 1.0027726432532348e-05, "loss": 0.0398, "step": 10790 }, { "epoch": 4.99, "learning_rate": 1.00184842883549e-05, "loss": 0.1308, "step": 10800 }, { "epoch": 5.0, "learning_rate": 1.000924214417745e-05, "loss": 0.0522, "step": 10810 }, { "epoch": 5.0, "learning_rate": 1e-05, "loss": 0.1169, "step": 10820 }, { "epoch": 5.0, "eval_FN": 125, "eval_FP": 1944, "eval_TN": 19770, "eval_TP": 1977, "eval_accuracy": 0.9131256298286866, "eval_f1": 0.6564834799933588, "eval_loss": 0.4379582703113556, "eval_precision": 0.5042081101759756, "eval_recall": 0.9405328258801142, "eval_runtime": 163.0096, "eval_samples_per_second": 146.102, "eval_steps_per_second": 9.134, "step": 10820 }, { "epoch": 5.0, "learning_rate": 9.990757855822552e-06, "loss": 0.0351, "step": 10830 }, { "epoch": 5.01, "learning_rate": 9.981515711645102e-06, "loss": 0.0751, "step": 10840 }, { "epoch": 5.01, "learning_rate": 9.972273567467653e-06, "loss": 0.0391, "step": 10850 }, { "epoch": 5.02, "learning_rate": 9.963031423290203e-06, "loss": 0.0372, "step": 10860 }, { "epoch": 5.02, "learning_rate": 9.953789279112756e-06, "loss": 0.0825, "step": 10870 }, { "epoch": 5.03, "learning_rate": 9.944547134935306e-06, "loss": 0.0685, "step": 10880 }, { "epoch": 5.03, "learning_rate": 9.935304990757857e-06, "loss": 0.0773, "step": 10890 }, { "epoch": 5.04, "learning_rate": 9.926062846580407e-06, "loss": 0.0423, "step": 10900 }, { "epoch": 5.04, "learning_rate": 9.916820702402959e-06, "loss": 0.0313, "step": 10910 }, { "epoch": 5.05, "learning_rate": 9.907578558225508e-06, "loss": 0.0235, "step": 10920 }, { "epoch": 5.05, "learning_rate": 9.89833641404806e-06, "loss": 0.1314, "step": 10930 }, { "epoch": 5.06, "learning_rate": 9.889094269870611e-06, "loss": 0.0663, "step": 10940 }, { "epoch": 5.06, "learning_rate": 9.879852125693161e-06, "loss": 0.0201, "step": 10950 }, { "epoch": 5.06, "learning_rate": 9.870609981515712e-06, "loss": 0.0721, "step": 10960 }, { "epoch": 5.07, "learning_rate": 9.861367837338264e-06, "loss": 0.0546, "step": 10970 }, { "epoch": 5.07, "learning_rate": 9.852125693160815e-06, "loss": 0.1795, "step": 10980 }, { "epoch": 5.08, "learning_rate": 9.842883548983365e-06, "loss": 0.0565, "step": 10990 }, { "epoch": 5.08, "learning_rate": 9.833641404805916e-06, "loss": 0.0081, "step": 11000 }, { "epoch": 5.09, "learning_rate": 9.824399260628466e-06, "loss": 0.1445, "step": 11010 }, { "epoch": 5.09, "learning_rate": 9.815157116451017e-06, "loss": 0.1145, "step": 11020 }, { "epoch": 5.1, "learning_rate": 9.805914972273569e-06, "loss": 0.1049, "step": 11030 }, { "epoch": 5.1, "learning_rate": 9.796672828096119e-06, "loss": 0.0794, "step": 11040 }, { "epoch": 5.11, "learning_rate": 9.78743068391867e-06, "loss": 0.0236, "step": 11050 }, { "epoch": 5.11, "learning_rate": 9.778188539741221e-06, "loss": 0.1974, "step": 11060 }, { "epoch": 5.12, "learning_rate": 9.768946395563771e-06, "loss": 0.0343, "step": 11070 }, { "epoch": 5.12, "learning_rate": 9.759704251386323e-06, "loss": 0.1158, "step": 11080 }, { "epoch": 5.12, "learning_rate": 9.750462107208874e-06, "loss": 0.1455, "step": 11090 }, { "epoch": 5.13, "learning_rate": 9.741219963031424e-06, "loss": 0.084, "step": 11100 }, { "epoch": 5.13, "learning_rate": 9.731977818853975e-06, "loss": 0.1178, "step": 11110 }, { "epoch": 5.14, "learning_rate": 9.722735674676525e-06, "loss": 0.1075, "step": 11120 }, { "epoch": 5.14, "learning_rate": 9.713493530499076e-06, "loss": 0.0842, "step": 11130 }, { "epoch": 5.15, "learning_rate": 9.704251386321628e-06, "loss": 0.0488, "step": 11140 }, { "epoch": 5.15, "learning_rate": 9.695009242144177e-06, "loss": 0.0873, "step": 11150 }, { "epoch": 5.16, "learning_rate": 9.685767097966729e-06, "loss": 0.1114, "step": 11160 }, { "epoch": 5.16, "learning_rate": 9.67652495378928e-06, "loss": 0.1371, "step": 11170 }, { "epoch": 5.17, "learning_rate": 9.667282809611832e-06, "loss": 0.0076, "step": 11180 }, { "epoch": 5.17, "learning_rate": 9.658040665434381e-06, "loss": 0.1993, "step": 11190 }, { "epoch": 5.18, "learning_rate": 9.648798521256933e-06, "loss": 0.1206, "step": 11200 }, { "epoch": 5.18, "learning_rate": 9.639556377079483e-06, "loss": 0.0485, "step": 11210 }, { "epoch": 5.18, "learning_rate": 9.630314232902034e-06, "loss": 0.0754, "step": 11220 }, { "epoch": 5.19, "learning_rate": 9.621072088724584e-06, "loss": 0.0652, "step": 11230 }, { "epoch": 5.19, "learning_rate": 9.611829944547135e-06, "loss": 0.0163, "step": 11240 }, { "epoch": 5.2, "learning_rate": 9.602587800369687e-06, "loss": 0.1658, "step": 11250 }, { "epoch": 5.2, "learning_rate": 9.593345656192238e-06, "loss": 0.0985, "step": 11260 }, { "epoch": 5.21, "learning_rate": 9.584103512014788e-06, "loss": 0.056, "step": 11270 }, { "epoch": 5.21, "learning_rate": 9.57486136783734e-06, "loss": 0.1117, "step": 11280 }, { "epoch": 5.22, "learning_rate": 9.56561922365989e-06, "loss": 0.0694, "step": 11290 }, { "epoch": 5.22, "learning_rate": 9.55637707948244e-06, "loss": 0.0633, "step": 11300 }, { "epoch": 5.23, "learning_rate": 9.547134935304992e-06, "loss": 0.0383, "step": 11310 }, { "epoch": 5.23, "learning_rate": 9.537892791127542e-06, "loss": 0.0434, "step": 11320 }, { "epoch": 5.24, "learning_rate": 9.528650646950093e-06, "loss": 0.0694, "step": 11330 }, { "epoch": 5.24, "learning_rate": 9.519408502772643e-06, "loss": 0.0672, "step": 11340 }, { "epoch": 5.24, "learning_rate": 9.510166358595196e-06, "loss": 0.072, "step": 11350 }, { "epoch": 5.25, "learning_rate": 9.500924214417746e-06, "loss": 0.14, "step": 11360 }, { "epoch": 5.25, "learning_rate": 9.491682070240297e-06, "loss": 0.0665, "step": 11370 }, { "epoch": 5.26, "learning_rate": 9.482439926062847e-06, "loss": 0.0677, "step": 11380 }, { "epoch": 5.26, "learning_rate": 9.473197781885398e-06, "loss": 0.1633, "step": 11390 }, { "epoch": 5.27, "learning_rate": 9.46395563770795e-06, "loss": 0.1085, "step": 11400 }, { "epoch": 5.27, "learning_rate": 9.4547134935305e-06, "loss": 0.0661, "step": 11410 }, { "epoch": 5.28, "learning_rate": 9.44547134935305e-06, "loss": 0.0482, "step": 11420 }, { "epoch": 5.28, "learning_rate": 9.4362292051756e-06, "loss": 0.1308, "step": 11430 }, { "epoch": 5.29, "learning_rate": 9.426987060998154e-06, "loss": 0.0506, "step": 11440 }, { "epoch": 5.29, "learning_rate": 9.417744916820703e-06, "loss": 0.0103, "step": 11450 }, { "epoch": 5.3, "learning_rate": 9.408502772643255e-06, "loss": 0.0349, "step": 11460 }, { "epoch": 5.3, "learning_rate": 9.399260628465804e-06, "loss": 0.123, "step": 11470 }, { "epoch": 5.3, "learning_rate": 9.390018484288356e-06, "loss": 0.0835, "step": 11480 }, { "epoch": 5.31, "learning_rate": 9.380776340110906e-06, "loss": 0.0877, "step": 11490 }, { "epoch": 5.31, "learning_rate": 9.371534195933457e-06, "loss": 0.0154, "step": 11500 }, { "epoch": 5.32, "learning_rate": 9.362292051756008e-06, "loss": 0.129, "step": 11510 }, { "epoch": 5.32, "learning_rate": 9.353049907578558e-06, "loss": 0.1207, "step": 11520 }, { "epoch": 5.33, "learning_rate": 9.34380776340111e-06, "loss": 0.0922, "step": 11530 }, { "epoch": 5.33, "learning_rate": 9.334565619223661e-06, "loss": 0.0393, "step": 11540 }, { "epoch": 5.34, "learning_rate": 9.325323475046212e-06, "loss": 0.0615, "step": 11550 }, { "epoch": 5.34, "learning_rate": 9.316081330868762e-06, "loss": 0.0946, "step": 11560 }, { "epoch": 5.35, "learning_rate": 9.306839186691314e-06, "loss": 0.0513, "step": 11570 }, { "epoch": 5.35, "learning_rate": 9.297597042513863e-06, "loss": 0.1176, "step": 11580 }, { "epoch": 5.36, "learning_rate": 9.288354898336415e-06, "loss": 0.1198, "step": 11590 }, { "epoch": 5.36, "learning_rate": 9.279112754158966e-06, "loss": 0.1448, "step": 11600 }, { "epoch": 5.37, "learning_rate": 9.269870609981516e-06, "loss": 0.1646, "step": 11610 }, { "epoch": 5.37, "learning_rate": 9.260628465804067e-06, "loss": 0.1092, "step": 11620 }, { "epoch": 5.37, "learning_rate": 9.251386321626619e-06, "loss": 0.0604, "step": 11630 }, { "epoch": 5.38, "learning_rate": 9.24214417744917e-06, "loss": 0.0522, "step": 11640 }, { "epoch": 5.38, "learning_rate": 9.23290203327172e-06, "loss": 0.1473, "step": 11650 }, { "epoch": 5.39, "learning_rate": 9.223659889094271e-06, "loss": 0.0849, "step": 11660 }, { "epoch": 5.39, "learning_rate": 9.214417744916821e-06, "loss": 0.0113, "step": 11670 }, { "epoch": 5.4, "learning_rate": 9.205175600739372e-06, "loss": 0.1668, "step": 11680 }, { "epoch": 5.4, "learning_rate": 9.195933456561922e-06, "loss": 0.1992, "step": 11690 }, { "epoch": 5.41, "learning_rate": 9.186691312384474e-06, "loss": 0.206, "step": 11700 }, { "epoch": 5.41, "learning_rate": 9.177449168207025e-06, "loss": 0.0176, "step": 11710 }, { "epoch": 5.42, "learning_rate": 9.168207024029575e-06, "loss": 0.003, "step": 11720 }, { "epoch": 5.42, "learning_rate": 9.158964879852126e-06, "loss": 0.058, "step": 11730 }, { "epoch": 5.43, "learning_rate": 9.149722735674678e-06, "loss": 0.0337, "step": 11740 }, { "epoch": 5.43, "learning_rate": 9.140480591497229e-06, "loss": 0.073, "step": 11750 }, { "epoch": 5.43, "learning_rate": 9.131238447319779e-06, "loss": 0.1181, "step": 11760 }, { "epoch": 5.44, "learning_rate": 9.12199630314233e-06, "loss": 0.1188, "step": 11770 }, { "epoch": 5.44, "learning_rate": 9.11275415896488e-06, "loss": 0.0015, "step": 11780 }, { "epoch": 5.45, "learning_rate": 9.103512014787431e-06, "loss": 0.0722, "step": 11790 }, { "epoch": 5.45, "learning_rate": 9.094269870609981e-06, "loss": 0.186, "step": 11800 }, { "epoch": 5.46, "learning_rate": 9.085027726432533e-06, "loss": 0.0883, "step": 11810 }, { "epoch": 5.46, "learning_rate": 9.075785582255084e-06, "loss": 0.0668, "step": 11820 }, { "epoch": 5.47, "learning_rate": 9.066543438077635e-06, "loss": 0.057, "step": 11830 }, { "epoch": 5.47, "learning_rate": 9.057301293900185e-06, "loss": 0.123, "step": 11840 }, { "epoch": 5.48, "learning_rate": 9.048059149722737e-06, "loss": 0.0769, "step": 11850 }, { "epoch": 5.48, "learning_rate": 9.038817005545288e-06, "loss": 0.0957, "step": 11860 }, { "epoch": 5.49, "learning_rate": 9.029574861367838e-06, "loss": 0.0804, "step": 11870 }, { "epoch": 5.49, "learning_rate": 9.020332717190389e-06, "loss": 0.0688, "step": 11880 }, { "epoch": 5.49, "learning_rate": 9.011090573012939e-06, "loss": 0.0364, "step": 11890 }, { "epoch": 5.5, "learning_rate": 9.00184842883549e-06, "loss": 0.035, "step": 11900 }, { "epoch": 5.5, "learning_rate": 8.992606284658042e-06, "loss": 0.084, "step": 11910 }, { "epoch": 5.51, "learning_rate": 8.983364140480593e-06, "loss": 0.0892, "step": 11920 }, { "epoch": 5.51, "learning_rate": 8.974121996303143e-06, "loss": 0.0666, "step": 11930 }, { "epoch": 5.52, "learning_rate": 8.964879852125694e-06, "loss": 0.1695, "step": 11940 }, { "epoch": 5.52, "learning_rate": 8.955637707948244e-06, "loss": 0.1019, "step": 11950 }, { "epoch": 5.53, "learning_rate": 8.946395563770795e-06, "loss": 0.0094, "step": 11960 }, { "epoch": 5.53, "learning_rate": 8.937153419593347e-06, "loss": 0.097, "step": 11970 }, { "epoch": 5.54, "learning_rate": 8.927911275415897e-06, "loss": 0.1172, "step": 11980 }, { "epoch": 5.54, "learning_rate": 8.918669131238448e-06, "loss": 0.036, "step": 11990 }, { "epoch": 5.55, "learning_rate": 8.909426987060998e-06, "loss": 0.168, "step": 12000 }, { "epoch": 5.55, "learning_rate": 8.900184842883551e-06, "loss": 0.0432, "step": 12010 }, { "epoch": 5.55, "learning_rate": 8.8909426987061e-06, "loss": 0.083, "step": 12020 }, { "epoch": 5.56, "learning_rate": 8.881700554528652e-06, "loss": 0.1215, "step": 12030 }, { "epoch": 5.56, "learning_rate": 8.872458410351202e-06, "loss": 0.0898, "step": 12040 }, { "epoch": 5.57, "learning_rate": 8.863216266173753e-06, "loss": 0.1445, "step": 12050 }, { "epoch": 5.57, "learning_rate": 8.853974121996305e-06, "loss": 0.1195, "step": 12060 }, { "epoch": 5.58, "learning_rate": 8.844731977818854e-06, "loss": 0.0988, "step": 12070 }, { "epoch": 5.58, "learning_rate": 8.835489833641406e-06, "loss": 0.0579, "step": 12080 }, { "epoch": 5.59, "learning_rate": 8.826247689463955e-06, "loss": 0.1439, "step": 12090 }, { "epoch": 5.59, "learning_rate": 8.817005545286507e-06, "loss": 0.0537, "step": 12100 }, { "epoch": 5.6, "learning_rate": 8.807763401109058e-06, "loss": 0.0552, "step": 12110 }, { "epoch": 5.6, "learning_rate": 8.79852125693161e-06, "loss": 0.1439, "step": 12120 }, { "epoch": 5.61, "learning_rate": 8.78927911275416e-06, "loss": 0.0093, "step": 12130 }, { "epoch": 5.61, "learning_rate": 8.780036968576711e-06, "loss": 0.0467, "step": 12140 }, { "epoch": 5.61, "learning_rate": 8.77079482439926e-06, "loss": 0.0353, "step": 12150 }, { "epoch": 5.62, "learning_rate": 8.761552680221812e-06, "loss": 0.1434, "step": 12160 }, { "epoch": 5.62, "learning_rate": 8.752310536044363e-06, "loss": 0.0622, "step": 12170 }, { "epoch": 5.63, "learning_rate": 8.743068391866913e-06, "loss": 0.0587, "step": 12180 }, { "epoch": 5.63, "learning_rate": 8.733826247689465e-06, "loss": 0.1256, "step": 12190 }, { "epoch": 5.64, "learning_rate": 8.724584103512016e-06, "loss": 0.0981, "step": 12200 }, { "epoch": 5.64, "learning_rate": 8.715341959334567e-06, "loss": 0.0864, "step": 12210 }, { "epoch": 5.65, "learning_rate": 8.706099815157117e-06, "loss": 0.0339, "step": 12220 }, { "epoch": 5.65, "learning_rate": 8.696857670979669e-06, "loss": 0.0703, "step": 12230 }, { "epoch": 5.66, "learning_rate": 8.687615526802218e-06, "loss": 0.1032, "step": 12240 }, { "epoch": 5.66, "learning_rate": 8.67837338262477e-06, "loss": 0.0815, "step": 12250 }, { "epoch": 5.67, "learning_rate": 8.66913123844732e-06, "loss": 0.0095, "step": 12260 }, { "epoch": 5.67, "learning_rate": 8.659889094269871e-06, "loss": 0.0013, "step": 12270 }, { "epoch": 5.67, "learning_rate": 8.650646950092422e-06, "loss": 0.0285, "step": 12280 }, { "epoch": 5.68, "learning_rate": 8.641404805914972e-06, "loss": 0.0864, "step": 12290 }, { "epoch": 5.68, "learning_rate": 8.632162661737524e-06, "loss": 0.2098, "step": 12300 }, { "epoch": 5.69, "learning_rate": 8.622920517560075e-06, "loss": 0.036, "step": 12310 }, { "epoch": 5.69, "learning_rate": 8.613678373382626e-06, "loss": 0.1334, "step": 12320 }, { "epoch": 5.7, "learning_rate": 8.604436229205176e-06, "loss": 0.054, "step": 12330 }, { "epoch": 5.7, "learning_rate": 8.595194085027728e-06, "loss": 0.0309, "step": 12340 }, { "epoch": 5.71, "learning_rate": 8.585951940850277e-06, "loss": 0.149, "step": 12350 }, { "epoch": 5.71, "learning_rate": 8.576709796672829e-06, "loss": 0.0733, "step": 12360 }, { "epoch": 5.72, "learning_rate": 8.567467652495378e-06, "loss": 0.1669, "step": 12370 }, { "epoch": 5.72, "learning_rate": 8.55822550831793e-06, "loss": 0.0256, "step": 12380 }, { "epoch": 5.73, "learning_rate": 8.548983364140481e-06, "loss": 0.1261, "step": 12390 }, { "epoch": 5.73, "learning_rate": 8.539741219963033e-06, "loss": 0.1179, "step": 12400 }, { "epoch": 5.73, "learning_rate": 8.530499075785582e-06, "loss": 0.0727, "step": 12410 }, { "epoch": 5.74, "learning_rate": 8.521256931608134e-06, "loss": 0.0226, "step": 12420 }, { "epoch": 5.74, "learning_rate": 8.512014787430685e-06, "loss": 0.0388, "step": 12430 }, { "epoch": 5.75, "learning_rate": 8.502772643253235e-06, "loss": 0.1524, "step": 12440 }, { "epoch": 5.75, "learning_rate": 8.493530499075786e-06, "loss": 0.0831, "step": 12450 }, { "epoch": 5.76, "learning_rate": 8.484288354898336e-06, "loss": 0.041, "step": 12460 }, { "epoch": 5.76, "learning_rate": 8.475046210720888e-06, "loss": 0.0833, "step": 12470 }, { "epoch": 5.77, "learning_rate": 8.465804066543439e-06, "loss": 0.1354, "step": 12480 }, { "epoch": 5.77, "learning_rate": 8.45656192236599e-06, "loss": 0.0766, "step": 12490 }, { "epoch": 5.78, "learning_rate": 8.44731977818854e-06, "loss": 0.1108, "step": 12500 }, { "epoch": 5.78, "learning_rate": 8.438077634011092e-06, "loss": 0.1022, "step": 12510 }, { "epoch": 5.79, "learning_rate": 8.428835489833643e-06, "loss": 0.014, "step": 12520 }, { "epoch": 5.79, "learning_rate": 8.419593345656193e-06, "loss": 0.0543, "step": 12530 }, { "epoch": 5.79, "learning_rate": 8.410351201478744e-06, "loss": 0.0026, "step": 12540 }, { "epoch": 5.8, "learning_rate": 8.401109057301294e-06, "loss": 0.1942, "step": 12550 }, { "epoch": 5.8, "learning_rate": 8.391866913123845e-06, "loss": 0.0936, "step": 12560 }, { "epoch": 5.81, "learning_rate": 8.382624768946395e-06, "loss": 0.1245, "step": 12570 }, { "epoch": 5.81, "learning_rate": 8.373382624768948e-06, "loss": 0.1322, "step": 12580 }, { "epoch": 5.82, "learning_rate": 8.364140480591498e-06, "loss": 0.0564, "step": 12590 }, { "epoch": 5.82, "learning_rate": 8.35489833641405e-06, "loss": 0.0607, "step": 12600 }, { "epoch": 5.83, "learning_rate": 8.345656192236599e-06, "loss": 0.0633, "step": 12610 }, { "epoch": 5.83, "learning_rate": 8.33641404805915e-06, "loss": 0.0827, "step": 12620 }, { "epoch": 5.84, "learning_rate": 8.327171903881702e-06, "loss": 0.0877, "step": 12630 }, { "epoch": 5.84, "learning_rate": 8.317929759704252e-06, "loss": 0.2427, "step": 12640 }, { "epoch": 5.85, "learning_rate": 8.308687615526803e-06, "loss": 0.1079, "step": 12650 }, { "epoch": 5.85, "learning_rate": 8.299445471349353e-06, "loss": 0.0038, "step": 12660 }, { "epoch": 5.85, "learning_rate": 8.290203327171904e-06, "loss": 0.0943, "step": 12670 }, { "epoch": 5.86, "learning_rate": 8.280961182994456e-06, "loss": 0.158, "step": 12680 }, { "epoch": 5.86, "learning_rate": 8.271719038817007e-06, "loss": 0.0641, "step": 12690 }, { "epoch": 5.87, "learning_rate": 8.262476894639557e-06, "loss": 0.1222, "step": 12700 }, { "epoch": 5.87, "learning_rate": 8.253234750462108e-06, "loss": 0.0283, "step": 12710 }, { "epoch": 5.88, "learning_rate": 8.243992606284658e-06, "loss": 0.0865, "step": 12720 }, { "epoch": 5.88, "learning_rate": 8.23475046210721e-06, "loss": 0.02, "step": 12730 }, { "epoch": 5.89, "learning_rate": 8.22550831792976e-06, "loss": 0.0128, "step": 12740 }, { "epoch": 5.89, "learning_rate": 8.21626617375231e-06, "loss": 0.0559, "step": 12750 }, { "epoch": 5.9, "learning_rate": 8.207024029574862e-06, "loss": 0.1199, "step": 12760 }, { "epoch": 5.9, "learning_rate": 8.197781885397413e-06, "loss": 0.0876, "step": 12770 }, { "epoch": 5.91, "learning_rate": 8.188539741219965e-06, "loss": 0.0643, "step": 12780 }, { "epoch": 5.91, "learning_rate": 8.179297597042515e-06, "loss": 0.0084, "step": 12790 }, { "epoch": 5.91, "learning_rate": 8.170055452865066e-06, "loss": 0.0582, "step": 12800 }, { "epoch": 5.92, "learning_rate": 8.160813308687616e-06, "loss": 0.1264, "step": 12810 }, { "epoch": 5.92, "learning_rate": 8.151571164510167e-06, "loss": 0.126, "step": 12820 }, { "epoch": 5.93, "learning_rate": 8.142329020332717e-06, "loss": 0.0457, "step": 12830 }, { "epoch": 5.93, "learning_rate": 8.133086876155268e-06, "loss": 0.0645, "step": 12840 }, { "epoch": 5.94, "learning_rate": 8.12384473197782e-06, "loss": 0.0637, "step": 12850 }, { "epoch": 5.94, "learning_rate": 8.11460258780037e-06, "loss": 0.0471, "step": 12860 }, { "epoch": 5.95, "learning_rate": 8.105360443622921e-06, "loss": 0.1886, "step": 12870 }, { "epoch": 5.95, "learning_rate": 8.096118299445472e-06, "loss": 0.0834, "step": 12880 }, { "epoch": 5.96, "learning_rate": 8.086876155268024e-06, "loss": 0.0334, "step": 12890 }, { "epoch": 5.96, "learning_rate": 8.077634011090573e-06, "loss": 0.0762, "step": 12900 }, { "epoch": 5.97, "learning_rate": 8.068391866913125e-06, "loss": 0.1851, "step": 12910 }, { "epoch": 5.97, "learning_rate": 8.059149722735675e-06, "loss": 0.0745, "step": 12920 }, { "epoch": 5.98, "learning_rate": 8.049907578558226e-06, "loss": 0.0648, "step": 12930 }, { "epoch": 5.98, "learning_rate": 8.040665434380777e-06, "loss": 0.1227, "step": 12940 }, { "epoch": 5.98, "learning_rate": 8.031423290203327e-06, "loss": 0.0676, "step": 12950 }, { "epoch": 5.99, "learning_rate": 8.022181146025879e-06, "loss": 0.159, "step": 12960 }, { "epoch": 5.99, "learning_rate": 8.01293900184843e-06, "loss": 0.0602, "step": 12970 }, { "epoch": 6.0, "learning_rate": 8.00369685767098e-06, "loss": 0.0397, "step": 12980 }, { "epoch": 6.0, "eval_FN": 154, "eval_FP": 1834, "eval_TN": 19880, "eval_TP": 1948, "eval_accuracy": 0.9165267047363117, "eval_f1": 0.6621346023113528, "eval_loss": 0.5028613209724426, "eval_precision": 0.5150713907985193, "eval_recall": 0.9267364414843007, "eval_runtime": 163.027, "eval_samples_per_second": 146.086, "eval_steps_per_second": 9.133, "step": 12984 } ], "logging_steps": 10, "max_steps": 21640, "num_train_epochs": 10, "save_steps": 500, "total_flos": 5.464711375405056e+16, "trial_name": null, "trial_params": null }