{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 39912, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 9.988975746642615e-06, "loss": 3.3419, "step": 50 }, { "epoch": 0.01, "learning_rate": 9.97644818600922e-06, "loss": 2.1466, "step": 100 }, { "epoch": 0.01, "learning_rate": 9.963920625375829e-06, "loss": 1.7654, "step": 150 }, { "epoch": 0.02, "learning_rate": 9.951393064742433e-06, "loss": 1.4769, "step": 200 }, { "epoch": 0.02, "learning_rate": 9.938865504109041e-06, "loss": 1.6047, "step": 250 }, { "epoch": 0.02, "learning_rate": 9.926337943475647e-06, "loss": 1.581, "step": 300 }, { "epoch": 0.03, "learning_rate": 9.913810382842254e-06, "loss": 1.4987, "step": 350 }, { "epoch": 0.03, "learning_rate": 9.901282822208862e-06, "loss": 1.4837, "step": 400 }, { "epoch": 0.03, "learning_rate": 9.888755261575466e-06, "loss": 1.4321, "step": 450 }, { "epoch": 0.04, "learning_rate": 9.876227700942074e-06, "loss": 1.4264, "step": 500 }, { "epoch": 0.04, "learning_rate": 9.86370014030868e-06, "loss": 1.3971, "step": 550 }, { "epoch": 0.05, "learning_rate": 9.851172579675286e-06, "loss": 1.442, "step": 600 }, { "epoch": 0.05, "learning_rate": 9.838645019041893e-06, "loss": 1.3419, "step": 650 }, { "epoch": 0.05, "learning_rate": 9.826117458408499e-06, "loss": 1.4171, "step": 700 }, { "epoch": 0.06, "learning_rate": 9.813589897775107e-06, "loss": 1.4661, "step": 750 }, { "epoch": 0.06, "learning_rate": 9.801062337141713e-06, "loss": 1.3163, "step": 800 }, { "epoch": 0.06, "learning_rate": 9.78853477650832e-06, "loss": 1.3701, "step": 850 }, { "epoch": 0.07, "learning_rate": 9.776007215874925e-06, "loss": 1.3991, "step": 900 }, { "epoch": 0.07, "learning_rate": 9.764231308879536e-06, "loss": 1.125, "step": 950 }, { "epoch": 0.08, "learning_rate": 9.751703748246142e-06, "loss": 0.4997, "step": 1000 }, { "epoch": 0.08, "learning_rate": 9.739176187612749e-06, "loss": 0.504, "step": 1050 }, { "epoch": 0.08, "learning_rate": 9.726648626979357e-06, "loss": 0.4567, "step": 1100 }, { "epoch": 0.09, "learning_rate": 9.714121066345961e-06, "loss": 0.4345, "step": 1150 }, { "epoch": 0.09, "learning_rate": 9.701593505712569e-06, "loss": 0.3392, "step": 1200 }, { "epoch": 0.09, "learning_rate": 9.689065945079175e-06, "loss": 0.4173, "step": 1250 }, { "epoch": 0.1, "learning_rate": 9.676538384445782e-06, "loss": 0.4116, "step": 1300 }, { "epoch": 0.1, "learning_rate": 9.664010823812388e-06, "loss": 0.4069, "step": 1350 }, { "epoch": 0.11, "learning_rate": 9.651483263178994e-06, "loss": 0.4034, "step": 1400 }, { "epoch": 0.11, "learning_rate": 9.638955702545602e-06, "loss": 0.3894, "step": 1450 }, { "epoch": 0.11, "learning_rate": 9.626428141912208e-06, "loss": 0.4058, "step": 1500 }, { "epoch": 0.12, "learning_rate": 9.613900581278814e-06, "loss": 0.3719, "step": 1550 }, { "epoch": 0.12, "learning_rate": 9.60137302064542e-06, "loss": 0.398, "step": 1600 }, { "epoch": 0.12, "learning_rate": 9.588845460012027e-06, "loss": 0.2995, "step": 1650 }, { "epoch": 0.13, "learning_rate": 9.576317899378635e-06, "loss": 0.3297, "step": 1700 }, { "epoch": 0.13, "learning_rate": 9.563790338745241e-06, "loss": 0.3102, "step": 1750 }, { "epoch": 0.14, "learning_rate": 9.551262778111847e-06, "loss": 0.3882, "step": 1800 }, { "epoch": 0.14, "learning_rate": 9.538735217478453e-06, "loss": 0.4243, "step": 1850 }, { "epoch": 0.14, "learning_rate": 9.52620765684506e-06, "loss": 0.4063, "step": 1900 }, { "epoch": 0.15, "learning_rate": 9.513680096211666e-06, "loss": 0.3378, "step": 1950 }, { "epoch": 0.15, "learning_rate": 9.501152535578274e-06, "loss": 0.444, "step": 2000 }, { "epoch": 0.15, "learning_rate": 9.48862497494488e-06, "loss": 0.3442, "step": 2050 }, { "epoch": 0.16, "learning_rate": 9.476097414311486e-06, "loss": 0.3599, "step": 2100 }, { "epoch": 0.16, "learning_rate": 9.463569853678092e-06, "loss": 0.4417, "step": 2150 }, { "epoch": 0.17, "learning_rate": 9.451042293044699e-06, "loss": 0.3398, "step": 2200 }, { "epoch": 0.17, "learning_rate": 9.438514732411306e-06, "loss": 0.4124, "step": 2250 }, { "epoch": 0.17, "learning_rate": 9.425987171777911e-06, "loss": 0.3668, "step": 2300 }, { "epoch": 0.18, "learning_rate": 9.413459611144519e-06, "loss": 0.3484, "step": 2350 }, { "epoch": 0.18, "learning_rate": 9.400932050511125e-06, "loss": 0.3153, "step": 2400 }, { "epoch": 0.18, "learning_rate": 9.388404489877731e-06, "loss": 0.3886, "step": 2450 }, { "epoch": 0.19, "learning_rate": 9.37587692924434e-06, "loss": 0.3519, "step": 2500 }, { "epoch": 0.19, "learning_rate": 9.363349368610944e-06, "loss": 0.2856, "step": 2550 }, { "epoch": 0.2, "learning_rate": 9.350821807977552e-06, "loss": 0.3399, "step": 2600 }, { "epoch": 0.2, "learning_rate": 9.338294247344158e-06, "loss": 0.3406, "step": 2650 }, { "epoch": 0.2, "learning_rate": 9.325766686710764e-06, "loss": 0.3541, "step": 2700 }, { "epoch": 0.21, "learning_rate": 9.313239126077372e-06, "loss": 0.3573, "step": 2750 }, { "epoch": 0.21, "learning_rate": 9.300711565443977e-06, "loss": 0.3527, "step": 2800 }, { "epoch": 0.21, "learning_rate": 9.288184004810585e-06, "loss": 0.3678, "step": 2850 }, { "epoch": 0.22, "learning_rate": 9.27565644417719e-06, "loss": 0.3185, "step": 2900 }, { "epoch": 0.22, "learning_rate": 9.263128883543797e-06, "loss": 0.3216, "step": 2950 }, { "epoch": 0.23, "learning_rate": 9.250601322910405e-06, "loss": 0.3137, "step": 3000 }, { "epoch": 0.23, "learning_rate": 9.23807376227701e-06, "loss": 0.3626, "step": 3050 }, { "epoch": 0.23, "learning_rate": 9.225546201643617e-06, "loss": 0.3488, "step": 3100 }, { "epoch": 0.24, "learning_rate": 9.213018641010224e-06, "loss": 0.3627, "step": 3150 }, { "epoch": 0.24, "learning_rate": 9.20049108037683e-06, "loss": 0.3051, "step": 3200 }, { "epoch": 0.24, "learning_rate": 9.187963519743436e-06, "loss": 0.3838, "step": 3250 }, { "epoch": 0.25, "learning_rate": 9.175435959110042e-06, "loss": 0.3439, "step": 3300 }, { "epoch": 0.25, "learning_rate": 9.16290839847665e-06, "loss": 0.352, "step": 3350 }, { "epoch": 0.26, "learning_rate": 9.150380837843256e-06, "loss": 0.3984, "step": 3400 }, { "epoch": 0.26, "learning_rate": 9.137853277209863e-06, "loss": 0.3368, "step": 3450 }, { "epoch": 0.26, "learning_rate": 9.125325716576469e-06, "loss": 0.3056, "step": 3500 }, { "epoch": 0.27, "learning_rate": 9.112798155943075e-06, "loss": 0.3133, "step": 3550 }, { "epoch": 0.27, "learning_rate": 9.100270595309683e-06, "loss": 0.3852, "step": 3600 }, { "epoch": 0.27, "learning_rate": 9.08774303467629e-06, "loss": 0.2698, "step": 3650 }, { "epoch": 0.28, "learning_rate": 9.075215474042895e-06, "loss": 0.398, "step": 3700 }, { "epoch": 0.28, "learning_rate": 9.062687913409502e-06, "loss": 0.308, "step": 3750 }, { "epoch": 0.29, "learning_rate": 9.050160352776108e-06, "loss": 0.3749, "step": 3800 }, { "epoch": 0.29, "learning_rate": 9.037632792142714e-06, "loss": 0.3018, "step": 3850 }, { "epoch": 0.29, "learning_rate": 9.025105231509322e-06, "loss": 0.3239, "step": 3900 }, { "epoch": 0.3, "learning_rate": 9.012577670875928e-06, "loss": 0.2677, "step": 3950 }, { "epoch": 0.3, "learning_rate": 9.000050110242534e-06, "loss": 0.2714, "step": 4000 }, { "epoch": 0.3, "learning_rate": 8.98752254960914e-06, "loss": 0.2999, "step": 4050 }, { "epoch": 0.31, "learning_rate": 8.974994988975747e-06, "loss": 0.3023, "step": 4100 }, { "epoch": 0.31, "learning_rate": 8.962467428342355e-06, "loss": 0.3228, "step": 4150 }, { "epoch": 0.32, "learning_rate": 8.94993986770896e-06, "loss": 0.2647, "step": 4200 }, { "epoch": 0.32, "learning_rate": 8.937412307075567e-06, "loss": 0.3581, "step": 4250 }, { "epoch": 0.32, "learning_rate": 8.924884746442173e-06, "loss": 0.3389, "step": 4300 }, { "epoch": 0.33, "learning_rate": 8.91235718580878e-06, "loss": 0.3797, "step": 4350 }, { "epoch": 0.33, "learning_rate": 8.899829625175388e-06, "loss": 0.3023, "step": 4400 }, { "epoch": 0.33, "learning_rate": 8.887302064541992e-06, "loss": 0.2709, "step": 4450 }, { "epoch": 0.34, "learning_rate": 8.8747745039086e-06, "loss": 0.3533, "step": 4500 }, { "epoch": 0.34, "learning_rate": 8.862246943275206e-06, "loss": 0.2852, "step": 4550 }, { "epoch": 0.35, "learning_rate": 8.849719382641812e-06, "loss": 0.3157, "step": 4600 }, { "epoch": 0.35, "learning_rate": 8.83719182200842e-06, "loss": 0.3187, "step": 4650 }, { "epoch": 0.35, "learning_rate": 8.824664261375025e-06, "loss": 0.318, "step": 4700 }, { "epoch": 0.36, "learning_rate": 8.812136700741633e-06, "loss": 0.3457, "step": 4750 }, { "epoch": 0.36, "learning_rate": 8.799609140108239e-06, "loss": 0.3347, "step": 4800 }, { "epoch": 0.36, "learning_rate": 8.787081579474845e-06, "loss": 0.2931, "step": 4850 }, { "epoch": 0.37, "learning_rate": 8.774554018841453e-06, "loss": 0.3019, "step": 4900 }, { "epoch": 0.37, "learning_rate": 8.762026458208058e-06, "loss": 0.2998, "step": 4950 }, { "epoch": 0.38, "learning_rate": 8.749498897574666e-06, "loss": 0.2842, "step": 5000 }, { "epoch": 0.38, "learning_rate": 8.736971336941272e-06, "loss": 0.3356, "step": 5050 }, { "epoch": 0.38, "learning_rate": 8.724443776307878e-06, "loss": 0.3036, "step": 5100 }, { "epoch": 0.39, "learning_rate": 8.711916215674484e-06, "loss": 0.2718, "step": 5150 }, { "epoch": 0.39, "learning_rate": 8.69938865504109e-06, "loss": 0.2997, "step": 5200 }, { "epoch": 0.39, "learning_rate": 8.686861094407698e-06, "loss": 0.3109, "step": 5250 }, { "epoch": 0.4, "learning_rate": 8.674333533774305e-06, "loss": 0.2624, "step": 5300 }, { "epoch": 0.4, "learning_rate": 8.661805973140911e-06, "loss": 0.319, "step": 5350 }, { "epoch": 0.41, "learning_rate": 8.649278412507517e-06, "loss": 0.2912, "step": 5400 }, { "epoch": 0.41, "learning_rate": 8.636750851874123e-06, "loss": 0.3112, "step": 5450 }, { "epoch": 0.41, "learning_rate": 8.62422329124073e-06, "loss": 0.3211, "step": 5500 }, { "epoch": 0.42, "learning_rate": 8.611695730607337e-06, "loss": 0.305, "step": 5550 }, { "epoch": 0.42, "learning_rate": 8.599168169973944e-06, "loss": 0.3497, "step": 5600 }, { "epoch": 0.42, "learning_rate": 8.58664060934055e-06, "loss": 0.3449, "step": 5650 }, { "epoch": 0.43, "learning_rate": 8.574113048707156e-06, "loss": 0.3943, "step": 5700 }, { "epoch": 0.43, "learning_rate": 8.561585488073762e-06, "loss": 0.2814, "step": 5750 }, { "epoch": 0.44, "learning_rate": 8.54905792744037e-06, "loss": 0.316, "step": 5800 }, { "epoch": 0.44, "learning_rate": 8.536530366806977e-06, "loss": 0.2893, "step": 5850 }, { "epoch": 0.44, "learning_rate": 8.524002806173583e-06, "loss": 0.3096, "step": 5900 }, { "epoch": 0.45, "learning_rate": 8.511475245540189e-06, "loss": 0.2938, "step": 5950 }, { "epoch": 0.45, "learning_rate": 8.498947684906795e-06, "loss": 0.2381, "step": 6000 }, { "epoch": 0.45, "learning_rate": 8.486420124273403e-06, "loss": 0.2592, "step": 6050 }, { "epoch": 0.46, "learning_rate": 8.473892563640008e-06, "loss": 0.3162, "step": 6100 }, { "epoch": 0.46, "learning_rate": 8.461365003006616e-06, "loss": 0.2905, "step": 6150 }, { "epoch": 0.47, "learning_rate": 8.448837442373222e-06, "loss": 0.2742, "step": 6200 }, { "epoch": 0.47, "learning_rate": 8.436309881739828e-06, "loss": 0.2994, "step": 6250 }, { "epoch": 0.47, "learning_rate": 8.423782321106436e-06, "loss": 0.2806, "step": 6300 }, { "epoch": 0.48, "learning_rate": 8.41125476047304e-06, "loss": 0.2868, "step": 6350 }, { "epoch": 0.48, "learning_rate": 8.398727199839648e-06, "loss": 0.3883, "step": 6400 }, { "epoch": 0.48, "learning_rate": 8.386199639206255e-06, "loss": 0.3111, "step": 6450 }, { "epoch": 0.49, "learning_rate": 8.37367207857286e-06, "loss": 0.2853, "step": 6500 }, { "epoch": 0.49, "learning_rate": 8.361144517939469e-06, "loss": 0.2741, "step": 6550 }, { "epoch": 0.5, "learning_rate": 8.348616957306073e-06, "loss": 0.2604, "step": 6600 }, { "epoch": 0.5, "learning_rate": 8.336089396672681e-06, "loss": 0.294, "step": 6650 }, { "epoch": 0.5, "learning_rate": 8.323561836039287e-06, "loss": 0.2728, "step": 6700 }, { "epoch": 0.51, "learning_rate": 8.311034275405894e-06, "loss": 0.2965, "step": 6750 }, { "epoch": 0.51, "learning_rate": 8.298506714772502e-06, "loss": 0.2178, "step": 6800 }, { "epoch": 0.51, "learning_rate": 8.285979154139106e-06, "loss": 0.283, "step": 6850 }, { "epoch": 0.52, "learning_rate": 8.273451593505714e-06, "loss": 0.2512, "step": 6900 }, { "epoch": 0.52, "learning_rate": 8.26092403287232e-06, "loss": 0.3288, "step": 6950 }, { "epoch": 0.53, "learning_rate": 8.248396472238926e-06, "loss": 0.3238, "step": 7000 }, { "epoch": 0.53, "learning_rate": 8.235868911605533e-06, "loss": 0.3111, "step": 7050 }, { "epoch": 0.53, "learning_rate": 8.223341350972139e-06, "loss": 0.2927, "step": 7100 }, { "epoch": 0.54, "learning_rate": 8.210813790338747e-06, "loss": 0.2656, "step": 7150 }, { "epoch": 0.54, "learning_rate": 8.198286229705353e-06, "loss": 0.2824, "step": 7200 }, { "epoch": 0.54, "learning_rate": 8.18575866907196e-06, "loss": 0.2994, "step": 7250 }, { "epoch": 0.55, "learning_rate": 8.173231108438565e-06, "loss": 0.3092, "step": 7300 }, { "epoch": 0.55, "learning_rate": 8.160703547805172e-06, "loss": 0.2535, "step": 7350 }, { "epoch": 0.56, "learning_rate": 8.148175987171778e-06, "loss": 0.254, "step": 7400 }, { "epoch": 0.56, "learning_rate": 8.135648426538386e-06, "loss": 0.2797, "step": 7450 }, { "epoch": 0.56, "learning_rate": 8.123120865904992e-06, "loss": 0.2635, "step": 7500 }, { "epoch": 0.57, "learning_rate": 8.110593305271598e-06, "loss": 0.271, "step": 7550 }, { "epoch": 0.57, "learning_rate": 8.098065744638204e-06, "loss": 0.3131, "step": 7600 }, { "epoch": 0.58, "learning_rate": 8.08553818400481e-06, "loss": 0.266, "step": 7650 }, { "epoch": 0.58, "learning_rate": 8.073010623371419e-06, "loss": 0.2765, "step": 7700 }, { "epoch": 0.58, "learning_rate": 8.060483062738025e-06, "loss": 0.3463, "step": 7750 }, { "epoch": 0.59, "learning_rate": 8.047955502104631e-06, "loss": 0.3163, "step": 7800 }, { "epoch": 0.59, "learning_rate": 8.035427941471237e-06, "loss": 0.3108, "step": 7850 }, { "epoch": 0.59, "learning_rate": 8.022900380837843e-06, "loss": 0.244, "step": 7900 }, { "epoch": 0.6, "learning_rate": 8.010372820204451e-06, "loss": 0.2798, "step": 7950 }, { "epoch": 0.6, "learning_rate": 7.997845259571056e-06, "loss": 0.3019, "step": 8000 }, { "epoch": 0.61, "learning_rate": 7.985317698937664e-06, "loss": 0.2541, "step": 8050 }, { "epoch": 0.61, "learning_rate": 7.97279013830427e-06, "loss": 0.303, "step": 8100 }, { "epoch": 0.61, "learning_rate": 7.960262577670876e-06, "loss": 0.2793, "step": 8150 }, { "epoch": 0.62, "learning_rate": 7.947735017037484e-06, "loss": 0.3295, "step": 8200 }, { "epoch": 0.62, "learning_rate": 7.935207456404089e-06, "loss": 0.2729, "step": 8250 }, { "epoch": 0.62, "learning_rate": 7.922679895770697e-06, "loss": 0.2907, "step": 8300 }, { "epoch": 0.63, "learning_rate": 7.910152335137303e-06, "loss": 0.2629, "step": 8350 }, { "epoch": 0.63, "learning_rate": 7.897624774503909e-06, "loss": 0.2181, "step": 8400 }, { "epoch": 0.64, "learning_rate": 7.885097213870517e-06, "loss": 0.3072, "step": 8450 }, { "epoch": 0.64, "learning_rate": 7.872569653237122e-06, "loss": 0.2183, "step": 8500 }, { "epoch": 0.64, "learning_rate": 7.86004209260373e-06, "loss": 0.2554, "step": 8550 }, { "epoch": 0.65, "learning_rate": 7.847514531970336e-06, "loss": 0.2644, "step": 8600 }, { "epoch": 0.65, "learning_rate": 7.834986971336942e-06, "loss": 0.2844, "step": 8650 }, { "epoch": 0.65, "learning_rate": 7.82245941070355e-06, "loss": 0.2938, "step": 8700 }, { "epoch": 0.66, "learning_rate": 7.809931850070154e-06, "loss": 0.2484, "step": 8750 }, { "epoch": 0.66, "learning_rate": 7.797404289436762e-06, "loss": 0.2555, "step": 8800 }, { "epoch": 0.67, "learning_rate": 7.784876728803368e-06, "loss": 0.2861, "step": 8850 }, { "epoch": 0.67, "learning_rate": 7.772349168169975e-06, "loss": 0.2805, "step": 8900 }, { "epoch": 0.67, "learning_rate": 7.759821607536581e-06, "loss": 0.2554, "step": 8950 }, { "epoch": 0.68, "learning_rate": 7.747294046903187e-06, "loss": 0.2374, "step": 9000 }, { "epoch": 0.68, "learning_rate": 7.734766486269795e-06, "loss": 0.2382, "step": 9050 }, { "epoch": 0.68, "learning_rate": 7.722238925636401e-06, "loss": 0.307, "step": 9100 }, { "epoch": 0.69, "learning_rate": 7.709711365003007e-06, "loss": 0.2953, "step": 9150 }, { "epoch": 0.69, "learning_rate": 7.697183804369614e-06, "loss": 0.312, "step": 9200 }, { "epoch": 0.7, "learning_rate": 7.68465624373622e-06, "loss": 0.3371, "step": 9250 }, { "epoch": 0.7, "learning_rate": 7.672128683102826e-06, "loss": 0.3123, "step": 9300 }, { "epoch": 0.7, "learning_rate": 7.659601122469434e-06, "loss": 0.2979, "step": 9350 }, { "epoch": 0.71, "learning_rate": 7.64707356183604e-06, "loss": 0.2655, "step": 9400 }, { "epoch": 0.71, "learning_rate": 7.634546001202647e-06, "loss": 0.293, "step": 9450 }, { "epoch": 0.71, "learning_rate": 7.622018440569254e-06, "loss": 0.2724, "step": 9500 }, { "epoch": 0.72, "learning_rate": 7.609490879935859e-06, "loss": 0.2549, "step": 9550 }, { "epoch": 0.72, "learning_rate": 7.596963319302466e-06, "loss": 0.2383, "step": 9600 }, { "epoch": 0.73, "learning_rate": 7.584435758669073e-06, "loss": 0.3682, "step": 9650 }, { "epoch": 0.73, "learning_rate": 7.571908198035679e-06, "loss": 0.3049, "step": 9700 }, { "epoch": 0.73, "learning_rate": 7.559380637402286e-06, "loss": 0.2522, "step": 9750 }, { "epoch": 0.74, "learning_rate": 7.546853076768892e-06, "loss": 0.3385, "step": 9800 }, { "epoch": 0.74, "learning_rate": 7.534325516135499e-06, "loss": 0.2306, "step": 9850 }, { "epoch": 0.74, "learning_rate": 7.521797955502105e-06, "loss": 0.2639, "step": 9900 }, { "epoch": 0.75, "learning_rate": 7.509270394868712e-06, "loss": 0.2643, "step": 9950 }, { "epoch": 0.75, "learning_rate": 7.496742834235319e-06, "loss": 0.2674, "step": 10000 }, { "epoch": 0.76, "learning_rate": 7.4842152736019246e-06, "loss": 0.2248, "step": 10050 }, { "epoch": 0.76, "learning_rate": 7.471687712968532e-06, "loss": 0.2558, "step": 10100 }, { "epoch": 0.76, "learning_rate": 7.459160152335138e-06, "loss": 0.2937, "step": 10150 }, { "epoch": 0.77, "learning_rate": 7.446632591701745e-06, "loss": 0.2297, "step": 10200 }, { "epoch": 0.77, "learning_rate": 7.43410503106835e-06, "loss": 0.2728, "step": 10250 }, { "epoch": 0.77, "learning_rate": 7.421577470434957e-06, "loss": 0.2819, "step": 10300 }, { "epoch": 0.78, "learning_rate": 7.4090499098015644e-06, "loss": 0.2745, "step": 10350 }, { "epoch": 0.78, "learning_rate": 7.396522349168171e-06, "loss": 0.2283, "step": 10400 }, { "epoch": 0.79, "learning_rate": 7.383994788534778e-06, "loss": 0.357, "step": 10450 }, { "epoch": 0.79, "learning_rate": 7.371467227901383e-06, "loss": 0.2901, "step": 10500 }, { "epoch": 0.79, "learning_rate": 7.35893966726799e-06, "loss": 0.2207, "step": 10550 }, { "epoch": 0.8, "learning_rate": 7.346412106634597e-06, "loss": 0.2898, "step": 10600 }, { "epoch": 0.8, "learning_rate": 7.3338845460012035e-06, "loss": 0.2482, "step": 10650 }, { "epoch": 0.8, "learning_rate": 7.3213569853678105e-06, "loss": 0.2333, "step": 10700 }, { "epoch": 0.81, "learning_rate": 7.308829424734416e-06, "loss": 0.2796, "step": 10750 }, { "epoch": 0.81, "learning_rate": 7.296301864101023e-06, "loss": 0.2594, "step": 10800 }, { "epoch": 0.82, "learning_rate": 7.283774303467629e-06, "loss": 0.2918, "step": 10850 }, { "epoch": 0.82, "learning_rate": 7.271246742834236e-06, "loss": 0.3055, "step": 10900 }, { "epoch": 0.82, "learning_rate": 7.258719182200843e-06, "loss": 0.2863, "step": 10950 }, { "epoch": 0.83, "learning_rate": 7.246191621567449e-06, "loss": 0.2995, "step": 11000 }, { "epoch": 0.83, "learning_rate": 7.233664060934056e-06, "loss": 0.2065, "step": 11050 }, { "epoch": 0.83, "learning_rate": 7.221136500300662e-06, "loss": 0.296, "step": 11100 }, { "epoch": 0.84, "learning_rate": 7.208608939667269e-06, "loss": 0.2704, "step": 11150 }, { "epoch": 0.84, "learning_rate": 7.1960813790338745e-06, "loss": 0.2284, "step": 11200 }, { "epoch": 0.85, "learning_rate": 7.1835538184004815e-06, "loss": 0.356, "step": 11250 }, { "epoch": 0.85, "learning_rate": 7.171026257767089e-06, "loss": 0.3024, "step": 11300 }, { "epoch": 0.85, "learning_rate": 7.158498697133695e-06, "loss": 0.2644, "step": 11350 }, { "epoch": 0.86, "learning_rate": 7.145971136500302e-06, "loss": 0.2668, "step": 11400 }, { "epoch": 0.86, "learning_rate": 7.133443575866907e-06, "loss": 0.2337, "step": 11450 }, { "epoch": 0.86, "learning_rate": 7.120916015233514e-06, "loss": 0.2522, "step": 11500 }, { "epoch": 0.87, "learning_rate": 7.108388454600121e-06, "loss": 0.2578, "step": 11550 }, { "epoch": 0.87, "learning_rate": 7.095860893966728e-06, "loss": 0.2453, "step": 11600 }, { "epoch": 0.88, "learning_rate": 7.083333333333335e-06, "loss": 0.2782, "step": 11650 }, { "epoch": 0.88, "learning_rate": 7.07080577269994e-06, "loss": 0.2345, "step": 11700 }, { "epoch": 0.88, "learning_rate": 7.058278212066547e-06, "loss": 0.2312, "step": 11750 }, { "epoch": 0.89, "learning_rate": 7.045750651433153e-06, "loss": 0.2479, "step": 11800 }, { "epoch": 0.89, "learning_rate": 7.0332230907997604e-06, "loss": 0.2239, "step": 11850 }, { "epoch": 0.89, "learning_rate": 7.020695530166367e-06, "loss": 0.2877, "step": 11900 }, { "epoch": 0.9, "learning_rate": 7.008167969532973e-06, "loss": 0.3235, "step": 11950 }, { "epoch": 0.9, "learning_rate": 6.99564040889958e-06, "loss": 0.2194, "step": 12000 }, { "epoch": 0.91, "learning_rate": 6.983112848266186e-06, "loss": 0.233, "step": 12050 }, { "epoch": 0.91, "learning_rate": 6.970585287632793e-06, "loss": 0.3014, "step": 12100 }, { "epoch": 0.91, "learning_rate": 6.958057726999399e-06, "loss": 0.2789, "step": 12150 }, { "epoch": 0.92, "learning_rate": 6.945530166366006e-06, "loss": 0.2465, "step": 12200 }, { "epoch": 0.92, "learning_rate": 6.933002605732613e-06, "loss": 0.2327, "step": 12250 }, { "epoch": 0.92, "learning_rate": 6.920475045099219e-06, "loss": 0.2878, "step": 12300 }, { "epoch": 0.93, "learning_rate": 6.907947484465826e-06, "loss": 0.3226, "step": 12350 }, { "epoch": 0.93, "learning_rate": 6.895419923832431e-06, "loss": 0.2277, "step": 12400 }, { "epoch": 0.94, "learning_rate": 6.8828923631990385e-06, "loss": 0.2458, "step": 12450 }, { "epoch": 0.94, "learning_rate": 6.8703648025656455e-06, "loss": 0.2458, "step": 12500 }, { "epoch": 0.94, "learning_rate": 6.857837241932252e-06, "loss": 0.2474, "step": 12550 }, { "epoch": 0.95, "learning_rate": 6.845560232511526e-06, "loss": 0.2596, "step": 12600 }, { "epoch": 0.95, "learning_rate": 6.833032671878133e-06, "loss": 0.2835, "step": 12650 }, { "epoch": 0.95, "learning_rate": 6.820505111244738e-06, "loss": 0.2835, "step": 12700 }, { "epoch": 0.96, "learning_rate": 6.807977550611345e-06, "loss": 0.3121, "step": 12750 }, { "epoch": 0.96, "learning_rate": 6.795449989977952e-06, "loss": 0.2801, "step": 12800 }, { "epoch": 0.97, "learning_rate": 6.7829224293445584e-06, "loss": 0.2506, "step": 12850 }, { "epoch": 0.97, "learning_rate": 6.7703948687111655e-06, "loss": 0.2275, "step": 12900 }, { "epoch": 0.97, "learning_rate": 6.757867308077771e-06, "loss": 0.2385, "step": 12950 }, { "epoch": 0.98, "learning_rate": 6.745339747444378e-06, "loss": 0.279, "step": 13000 }, { "epoch": 0.98, "learning_rate": 6.732812186810985e-06, "loss": 0.2528, "step": 13050 }, { "epoch": 0.98, "learning_rate": 6.720284626177591e-06, "loss": 0.283, "step": 13100 }, { "epoch": 0.99, "learning_rate": 6.707757065544198e-06, "loss": 0.3245, "step": 13150 }, { "epoch": 0.99, "learning_rate": 6.695229504910804e-06, "loss": 0.1986, "step": 13200 }, { "epoch": 1.0, "learning_rate": 6.682701944277411e-06, "loss": 0.2088, "step": 13250 }, { "epoch": 1.0, "learning_rate": 6.670174383644017e-06, "loss": 0.2689, "step": 13300 }, { "epoch": 1.0, "exact_match": 50.67703831748776, "f1": 58.73053658167741, "step": 13304 }, { "epoch": 1.0, "learning_rate": 6.657646823010624e-06, "loss": 0.1773, "step": 13350 }, { "epoch": 1.01, "learning_rate": 6.645119262377231e-06, "loss": 0.1641, "step": 13400 }, { "epoch": 1.01, "learning_rate": 6.6325917017438365e-06, "loss": 0.1244, "step": 13450 }, { "epoch": 1.01, "learning_rate": 6.6200641411104436e-06, "loss": 0.1949, "step": 13500 }, { "epoch": 1.02, "learning_rate": 6.60753658047705e-06, "loss": 0.1713, "step": 13550 }, { "epoch": 1.02, "learning_rate": 6.595009019843657e-06, "loss": 0.1529, "step": 13600 }, { "epoch": 1.03, "learning_rate": 6.582481459210262e-06, "loss": 0.1954, "step": 13650 }, { "epoch": 1.03, "learning_rate": 6.569953898576869e-06, "loss": 0.1638, "step": 13700 }, { "epoch": 1.03, "learning_rate": 6.557426337943476e-06, "loss": 0.1552, "step": 13750 }, { "epoch": 1.04, "learning_rate": 6.544898777310083e-06, "loss": 0.1747, "step": 13800 }, { "epoch": 1.04, "learning_rate": 6.53237121667669e-06, "loss": 0.1706, "step": 13850 }, { "epoch": 1.04, "learning_rate": 6.519843656043295e-06, "loss": 0.1998, "step": 13900 }, { "epoch": 1.05, "learning_rate": 6.507316095409902e-06, "loss": 0.1637, "step": 13950 }, { "epoch": 1.05, "learning_rate": 6.494788534776509e-06, "loss": 0.1617, "step": 14000 }, { "epoch": 1.06, "learning_rate": 6.482260974143115e-06, "loss": 0.1525, "step": 14050 }, { "epoch": 1.06, "learning_rate": 6.4697334135097225e-06, "loss": 0.1929, "step": 14100 }, { "epoch": 1.06, "learning_rate": 6.457205852876328e-06, "loss": 0.2203, "step": 14150 }, { "epoch": 1.07, "learning_rate": 6.444678292242935e-06, "loss": 0.1827, "step": 14200 }, { "epoch": 1.07, "learning_rate": 6.432150731609541e-06, "loss": 0.1955, "step": 14250 }, { "epoch": 1.07, "learning_rate": 6.419623170976148e-06, "loss": 0.1926, "step": 14300 }, { "epoch": 1.08, "learning_rate": 6.407095610342755e-06, "loss": 0.1723, "step": 14350 }, { "epoch": 1.08, "learning_rate": 6.394568049709361e-06, "loss": 0.1696, "step": 14400 }, { "epoch": 1.09, "learning_rate": 6.382040489075968e-06, "loss": 0.1261, "step": 14450 }, { "epoch": 1.09, "learning_rate": 6.369512928442574e-06, "loss": 0.2407, "step": 14500 }, { "epoch": 1.09, "learning_rate": 6.356985367809181e-06, "loss": 0.2039, "step": 14550 }, { "epoch": 1.1, "learning_rate": 6.344457807175786e-06, "loss": 0.1747, "step": 14600 }, { "epoch": 1.1, "learning_rate": 6.3319302465423934e-06, "loss": 0.1654, "step": 14650 }, { "epoch": 1.1, "learning_rate": 6.3194026859090005e-06, "loss": 0.1957, "step": 14700 }, { "epoch": 1.11, "learning_rate": 6.306875125275607e-06, "loss": 0.1789, "step": 14750 }, { "epoch": 1.11, "learning_rate": 6.294347564642214e-06, "loss": 0.1771, "step": 14800 }, { "epoch": 1.12, "learning_rate": 6.281820004008819e-06, "loss": 0.1725, "step": 14850 }, { "epoch": 1.12, "learning_rate": 6.269292443375426e-06, "loss": 0.1903, "step": 14900 }, { "epoch": 1.12, "learning_rate": 6.256764882742033e-06, "loss": 0.1681, "step": 14950 }, { "epoch": 1.13, "learning_rate": 6.2442373221086395e-06, "loss": 0.1824, "step": 15000 }, { "epoch": 1.13, "learning_rate": 6.231709761475247e-06, "loss": 0.1126, "step": 15050 }, { "epoch": 1.13, "learning_rate": 6.219182200841852e-06, "loss": 0.1662, "step": 15100 }, { "epoch": 1.14, "learning_rate": 6.206654640208459e-06, "loss": 0.2035, "step": 15150 }, { "epoch": 1.14, "learning_rate": 6.194127079575065e-06, "loss": 0.1658, "step": 15200 }, { "epoch": 1.15, "learning_rate": 6.181599518941672e-06, "loss": 0.1869, "step": 15250 }, { "epoch": 1.15, "learning_rate": 6.169071958308279e-06, "loss": 0.1606, "step": 15300 }, { "epoch": 1.15, "learning_rate": 6.156544397674885e-06, "loss": 0.1854, "step": 15350 }, { "epoch": 1.16, "learning_rate": 6.144016837041492e-06, "loss": 0.1845, "step": 15400 }, { "epoch": 1.16, "learning_rate": 6.131489276408098e-06, "loss": 0.1742, "step": 15450 }, { "epoch": 1.17, "learning_rate": 6.118961715774705e-06, "loss": 0.1677, "step": 15500 }, { "epoch": 1.17, "learning_rate": 6.1064341551413105e-06, "loss": 0.1238, "step": 15550 }, { "epoch": 1.17, "learning_rate": 6.093906594507918e-06, "loss": 0.224, "step": 15600 }, { "epoch": 1.18, "learning_rate": 6.081379033874525e-06, "loss": 0.2019, "step": 15650 }, { "epoch": 1.18, "learning_rate": 6.068851473241131e-06, "loss": 0.1631, "step": 15700 }, { "epoch": 1.18, "learning_rate": 6.056323912607738e-06, "loss": 0.2136, "step": 15750 }, { "epoch": 1.19, "learning_rate": 6.043796351974343e-06, "loss": 0.1555, "step": 15800 }, { "epoch": 1.19, "learning_rate": 6.03126879134095e-06, "loss": 0.1692, "step": 15850 }, { "epoch": 1.2, "learning_rate": 6.0187412307075575e-06, "loss": 0.1336, "step": 15900 }, { "epoch": 1.2, "learning_rate": 6.006213670074164e-06, "loss": 0.1642, "step": 15950 }, { "epoch": 1.2, "learning_rate": 5.993686109440771e-06, "loss": 0.2149, "step": 16000 }, { "epoch": 1.21, "learning_rate": 5.981158548807376e-06, "loss": 0.1683, "step": 16050 }, { "epoch": 1.21, "learning_rate": 5.968630988173983e-06, "loss": 0.1604, "step": 16100 }, { "epoch": 1.21, "learning_rate": 5.956103427540589e-06, "loss": 0.1808, "step": 16150 }, { "epoch": 1.22, "learning_rate": 5.9435758669071965e-06, "loss": 0.169, "step": 16200 }, { "epoch": 1.22, "learning_rate": 5.9310483062738036e-06, "loss": 0.195, "step": 16250 }, { "epoch": 1.23, "learning_rate": 5.918520745640409e-06, "loss": 0.1336, "step": 16300 }, { "epoch": 1.23, "learning_rate": 5.905993185007016e-06, "loss": 0.1956, "step": 16350 }, { "epoch": 1.23, "learning_rate": 5.893465624373622e-06, "loss": 0.1569, "step": 16400 }, { "epoch": 1.24, "learning_rate": 5.880938063740229e-06, "loss": 0.1466, "step": 16450 }, { "epoch": 1.24, "learning_rate": 5.868410503106835e-06, "loss": 0.1757, "step": 16500 }, { "epoch": 1.24, "learning_rate": 5.855882942473442e-06, "loss": 0.1571, "step": 16550 }, { "epoch": 1.25, "learning_rate": 5.843355381840049e-06, "loss": 0.2717, "step": 16600 }, { "epoch": 1.25, "learning_rate": 5.830827821206655e-06, "loss": 0.1132, "step": 16650 }, { "epoch": 1.26, "learning_rate": 5.818300260573262e-06, "loss": 0.1617, "step": 16700 }, { "epoch": 1.26, "learning_rate": 5.8057726999398675e-06, "loss": 0.2091, "step": 16750 }, { "epoch": 1.26, "learning_rate": 5.7932451393064745e-06, "loss": 0.1631, "step": 16800 }, { "epoch": 1.27, "learning_rate": 5.780717578673081e-06, "loss": 0.1768, "step": 16850 }, { "epoch": 1.27, "learning_rate": 5.768190018039688e-06, "loss": 0.1947, "step": 16900 }, { "epoch": 1.27, "learning_rate": 5.755662457406295e-06, "loss": 0.173, "step": 16950 }, { "epoch": 1.28, "learning_rate": 5.7431348967729e-06, "loss": 0.2037, "step": 17000 }, { "epoch": 1.28, "learning_rate": 5.730607336139507e-06, "loss": 0.2082, "step": 17050 }, { "epoch": 1.29, "learning_rate": 5.7180797755061136e-06, "loss": 0.162, "step": 17100 }, { "epoch": 1.29, "learning_rate": 5.705552214872721e-06, "loss": 0.1825, "step": 17150 }, { "epoch": 1.29, "learning_rate": 5.693024654239328e-06, "loss": 0.1638, "step": 17200 }, { "epoch": 1.3, "learning_rate": 5.680497093605933e-06, "loss": 0.1579, "step": 17250 }, { "epoch": 1.3, "learning_rate": 5.66796953297254e-06, "loss": 0.124, "step": 17300 }, { "epoch": 1.3, "learning_rate": 5.655441972339146e-06, "loss": 0.1596, "step": 17350 }, { "epoch": 1.31, "learning_rate": 5.6429144117057534e-06, "loss": 0.1544, "step": 17400 }, { "epoch": 1.31, "learning_rate": 5.630386851072359e-06, "loss": 0.1865, "step": 17450 }, { "epoch": 1.32, "learning_rate": 5.617859290438966e-06, "loss": 0.1335, "step": 17500 }, { "epoch": 1.32, "learning_rate": 5.605331729805573e-06, "loss": 0.1816, "step": 17550 }, { "epoch": 1.32, "learning_rate": 5.592804169172179e-06, "loss": 0.1921, "step": 17600 }, { "epoch": 1.33, "learning_rate": 5.580276608538786e-06, "loss": 0.1669, "step": 17650 }, { "epoch": 1.33, "learning_rate": 5.567749047905392e-06, "loss": 0.1636, "step": 17700 }, { "epoch": 1.33, "learning_rate": 5.555221487271999e-06, "loss": 0.2091, "step": 17750 }, { "epoch": 1.34, "learning_rate": 5.542693926638605e-06, "loss": 0.1951, "step": 17800 }, { "epoch": 1.34, "learning_rate": 5.530166366005212e-06, "loss": 0.2197, "step": 17850 }, { "epoch": 1.35, "learning_rate": 5.517638805371819e-06, "loss": 0.1353, "step": 17900 }, { "epoch": 1.35, "learning_rate": 5.5051112447384244e-06, "loss": 0.1587, "step": 17950 }, { "epoch": 1.35, "learning_rate": 5.4925836841050315e-06, "loss": 0.1769, "step": 18000 }, { "epoch": 1.36, "learning_rate": 5.480056123471638e-06, "loss": 0.1714, "step": 18050 }, { "epoch": 1.36, "learning_rate": 5.467528562838245e-06, "loss": 0.1517, "step": 18100 }, { "epoch": 1.36, "learning_rate": 5.455001002204852e-06, "loss": 0.2699, "step": 18150 }, { "epoch": 1.37, "learning_rate": 5.442473441571457e-06, "loss": 0.1771, "step": 18200 }, { "epoch": 1.37, "learning_rate": 5.429945880938064e-06, "loss": 0.1817, "step": 18250 }, { "epoch": 1.38, "learning_rate": 5.4174183203046705e-06, "loss": 0.1863, "step": 18300 }, { "epoch": 1.38, "learning_rate": 5.404890759671278e-06, "loss": 0.1275, "step": 18350 }, { "epoch": 1.38, "learning_rate": 5.392363199037883e-06, "loss": 0.1511, "step": 18400 }, { "epoch": 1.39, "learning_rate": 5.37983563840449e-06, "loss": 0.1792, "step": 18450 }, { "epoch": 1.39, "learning_rate": 5.367308077771097e-06, "loss": 0.2001, "step": 18500 }, { "epoch": 1.39, "learning_rate": 5.354780517137703e-06, "loss": 0.1179, "step": 18550 }, { "epoch": 1.4, "learning_rate": 5.34225295650431e-06, "loss": 0.2148, "step": 18600 }, { "epoch": 1.4, "learning_rate": 5.329725395870916e-06, "loss": 0.1888, "step": 18650 }, { "epoch": 1.41, "learning_rate": 5.317197835237523e-06, "loss": 0.1352, "step": 18700 }, { "epoch": 1.41, "learning_rate": 5.304670274604129e-06, "loss": 0.1844, "step": 18750 }, { "epoch": 1.41, "learning_rate": 5.292142713970736e-06, "loss": 0.1412, "step": 18800 }, { "epoch": 1.42, "learning_rate": 5.279615153337343e-06, "loss": 0.127, "step": 18850 }, { "epoch": 1.42, "learning_rate": 5.2670875927039486e-06, "loss": 0.2379, "step": 18900 }, { "epoch": 1.42, "learning_rate": 5.254560032070556e-06, "loss": 0.1905, "step": 18950 }, { "epoch": 1.43, "learning_rate": 5.242032471437162e-06, "loss": 0.1319, "step": 19000 }, { "epoch": 1.43, "learning_rate": 5.229755462016437e-06, "loss": 0.2084, "step": 19050 }, { "epoch": 1.44, "learning_rate": 5.217227901383043e-06, "loss": 0.1748, "step": 19100 }, { "epoch": 1.44, "learning_rate": 5.20470034074965e-06, "loss": 0.1661, "step": 19150 }, { "epoch": 1.44, "learning_rate": 5.192172780116256e-06, "loss": 0.1644, "step": 19200 }, { "epoch": 1.45, "learning_rate": 5.179645219482863e-06, "loss": 0.1735, "step": 19250 }, { "epoch": 1.45, "learning_rate": 5.16711765884947e-06, "loss": 0.1325, "step": 19300 }, { "epoch": 1.45, "learning_rate": 5.154590098216076e-06, "loss": 0.183, "step": 19350 }, { "epoch": 1.46, "learning_rate": 5.142062537582683e-06, "loss": 0.134, "step": 19400 }, { "epoch": 1.46, "learning_rate": 5.129534976949289e-06, "loss": 0.1634, "step": 19450 }, { "epoch": 1.47, "learning_rate": 5.117007416315896e-06, "loss": 0.1737, "step": 19500 }, { "epoch": 1.47, "learning_rate": 5.104479855682501e-06, "loss": 0.1713, "step": 19550 }, { "epoch": 1.47, "learning_rate": 5.091952295049108e-06, "loss": 0.1965, "step": 19600 }, { "epoch": 1.48, "learning_rate": 5.0794247344157155e-06, "loss": 0.1532, "step": 19650 }, { "epoch": 1.48, "learning_rate": 5.066897173782322e-06, "loss": 0.1611, "step": 19700 }, { "epoch": 1.48, "learning_rate": 5.054369613148929e-06, "loss": 0.17, "step": 19750 }, { "epoch": 1.49, "learning_rate": 5.041842052515534e-06, "loss": 0.1967, "step": 19800 }, { "epoch": 1.49, "learning_rate": 5.029314491882141e-06, "loss": 0.1759, "step": 19850 }, { "epoch": 1.5, "learning_rate": 5.0167869312487474e-06, "loss": 0.1987, "step": 19900 }, { "epoch": 1.5, "learning_rate": 5.0042593706153545e-06, "loss": 0.196, "step": 19950 }, { "epoch": 1.5, "learning_rate": 4.991731809981961e-06, "loss": 0.1686, "step": 20000 }, { "epoch": 1.51, "learning_rate": 4.979204249348567e-06, "loss": 0.1594, "step": 20050 }, { "epoch": 1.51, "learning_rate": 4.966676688715174e-06, "loss": 0.2131, "step": 20100 }, { "epoch": 1.51, "learning_rate": 4.95414912808178e-06, "loss": 0.1629, "step": 20150 }, { "epoch": 1.52, "learning_rate": 4.941621567448387e-06, "loss": 0.1937, "step": 20200 }, { "epoch": 1.52, "learning_rate": 4.9290940068149935e-06, "loss": 0.1514, "step": 20250 }, { "epoch": 1.53, "learning_rate": 4.9165664461816e-06, "loss": 0.2125, "step": 20300 }, { "epoch": 1.53, "learning_rate": 4.904038885548206e-06, "loss": 0.1556, "step": 20350 }, { "epoch": 1.53, "learning_rate": 4.891511324914813e-06, "loss": 0.2029, "step": 20400 }, { "epoch": 1.54, "learning_rate": 4.87898376428142e-06, "loss": 0.1697, "step": 20450 }, { "epoch": 1.54, "learning_rate": 4.866456203648026e-06, "loss": 0.1713, "step": 20500 }, { "epoch": 1.54, "learning_rate": 4.8539286430146325e-06, "loss": 0.2214, "step": 20550 }, { "epoch": 1.55, "learning_rate": 4.841401082381239e-06, "loss": 0.187, "step": 20600 }, { "epoch": 1.55, "learning_rate": 4.828873521747846e-06, "loss": 0.184, "step": 20650 }, { "epoch": 1.56, "learning_rate": 4.816345961114452e-06, "loss": 0.1558, "step": 20700 }, { "epoch": 1.56, "learning_rate": 4.803818400481059e-06, "loss": 0.1726, "step": 20750 }, { "epoch": 1.56, "learning_rate": 4.791290839847665e-06, "loss": 0.1698, "step": 20800 }, { "epoch": 1.57, "learning_rate": 4.7787632792142716e-06, "loss": 0.1554, "step": 20850 }, { "epoch": 1.57, "learning_rate": 4.766235718580879e-06, "loss": 0.1194, "step": 20900 }, { "epoch": 1.57, "learning_rate": 4.753708157947485e-06, "loss": 0.1769, "step": 20950 }, { "epoch": 1.58, "learning_rate": 4.741180597314091e-06, "loss": 0.1527, "step": 21000 }, { "epoch": 1.58, "learning_rate": 4.728653036680698e-06, "loss": 0.1611, "step": 21050 }, { "epoch": 1.59, "learning_rate": 4.716125476047304e-06, "loss": 0.1656, "step": 21100 }, { "epoch": 1.59, "learning_rate": 4.7035979154139114e-06, "loss": 0.1757, "step": 21150 }, { "epoch": 1.59, "learning_rate": 4.691070354780518e-06, "loss": 0.1548, "step": 21200 }, { "epoch": 1.6, "learning_rate": 4.678542794147124e-06, "loss": 0.1966, "step": 21250 }, { "epoch": 1.6, "learning_rate": 4.66601523351373e-06, "loss": 0.2066, "step": 21300 }, { "epoch": 1.6, "learning_rate": 4.653487672880337e-06, "loss": 0.1643, "step": 21350 }, { "epoch": 1.61, "learning_rate": 4.640960112246944e-06, "loss": 0.1381, "step": 21400 }, { "epoch": 1.61, "learning_rate": 4.6284325516135505e-06, "loss": 0.192, "step": 21450 }, { "epoch": 1.62, "learning_rate": 4.615904990980157e-06, "loss": 0.1672, "step": 21500 }, { "epoch": 1.62, "learning_rate": 4.603377430346763e-06, "loss": 0.1314, "step": 21550 }, { "epoch": 1.62, "learning_rate": 4.59084986971337e-06, "loss": 0.1535, "step": 21600 }, { "epoch": 1.63, "learning_rate": 4.578322309079976e-06, "loss": 0.1496, "step": 21650 }, { "epoch": 1.63, "learning_rate": 4.565794748446583e-06, "loss": 0.2039, "step": 21700 }, { "epoch": 1.63, "learning_rate": 4.5532671878131895e-06, "loss": 0.1683, "step": 21750 }, { "epoch": 1.64, "learning_rate": 4.540739627179796e-06, "loss": 0.1543, "step": 21800 }, { "epoch": 1.64, "learning_rate": 4.528212066546403e-06, "loss": 0.1674, "step": 21850 }, { "epoch": 1.65, "learning_rate": 4.515684505913009e-06, "loss": 0.1616, "step": 21900 }, { "epoch": 1.65, "learning_rate": 4.503156945279615e-06, "loss": 0.1564, "step": 21950 }, { "epoch": 1.65, "learning_rate": 4.4906293846462215e-06, "loss": 0.2053, "step": 22000 }, { "epoch": 1.66, "learning_rate": 4.4781018240128285e-06, "loss": 0.1983, "step": 22050 }, { "epoch": 1.66, "learning_rate": 4.465574263379436e-06, "loss": 0.1356, "step": 22100 }, { "epoch": 1.66, "learning_rate": 4.4532972539587095e-06, "loss": 0.1438, "step": 22150 }, { "epoch": 1.67, "learning_rate": 4.440769693325316e-06, "loss": 0.1685, "step": 22200 }, { "epoch": 1.67, "learning_rate": 4.428242132691923e-06, "loss": 0.1975, "step": 22250 }, { "epoch": 1.68, "learning_rate": 4.415714572058529e-06, "loss": 0.154, "step": 22300 }, { "epoch": 1.68, "learning_rate": 4.403187011425136e-06, "loss": 0.1801, "step": 22350 }, { "epoch": 1.68, "learning_rate": 4.390659450791742e-06, "loss": 0.1704, "step": 22400 }, { "epoch": 1.69, "learning_rate": 4.3781318901583485e-06, "loss": 0.1482, "step": 22450 }, { "epoch": 1.69, "learning_rate": 4.365604329524955e-06, "loss": 0.1672, "step": 22500 }, { "epoch": 1.69, "learning_rate": 4.353076768891562e-06, "loss": 0.1976, "step": 22550 }, { "epoch": 1.7, "learning_rate": 4.340549208258169e-06, "loss": 0.1454, "step": 22600 }, { "epoch": 1.7, "learning_rate": 4.328021647624775e-06, "loss": 0.1509, "step": 22650 }, { "epoch": 1.71, "learning_rate": 4.315494086991381e-06, "loss": 0.188, "step": 22700 }, { "epoch": 1.71, "learning_rate": 4.3029665263579875e-06, "loss": 0.123, "step": 22750 }, { "epoch": 1.71, "learning_rate": 4.290438965724595e-06, "loss": 0.1235, "step": 22800 }, { "epoch": 1.72, "learning_rate": 4.277911405091201e-06, "loss": 0.1649, "step": 22850 }, { "epoch": 1.72, "learning_rate": 4.265383844457808e-06, "loss": 0.1943, "step": 22900 }, { "epoch": 1.73, "learning_rate": 4.252856283824414e-06, "loss": 0.2243, "step": 22950 }, { "epoch": 1.73, "learning_rate": 4.24032872319102e-06, "loss": 0.1624, "step": 23000 }, { "epoch": 1.73, "learning_rate": 4.227801162557627e-06, "loss": 0.1998, "step": 23050 }, { "epoch": 1.74, "learning_rate": 4.215273601924234e-06, "loss": 0.228, "step": 23100 }, { "epoch": 1.74, "learning_rate": 4.20274604129084e-06, "loss": 0.1541, "step": 23150 }, { "epoch": 1.74, "learning_rate": 4.190218480657447e-06, "loss": 0.1396, "step": 23200 }, { "epoch": 1.75, "learning_rate": 4.177690920024053e-06, "loss": 0.155, "step": 23250 }, { "epoch": 1.75, "learning_rate": 4.16516335939066e-06, "loss": 0.1451, "step": 23300 }, { "epoch": 1.76, "learning_rate": 4.152635798757266e-06, "loss": 0.1628, "step": 23350 }, { "epoch": 1.76, "learning_rate": 4.140108238123873e-06, "loss": 0.1594, "step": 23400 }, { "epoch": 1.76, "learning_rate": 4.127580677490479e-06, "loss": 0.1636, "step": 23450 }, { "epoch": 1.77, "learning_rate": 4.1153036680697536e-06, "loss": 0.1437, "step": 23500 }, { "epoch": 1.77, "learning_rate": 4.102776107436361e-06, "loss": 0.179, "step": 23550 }, { "epoch": 1.77, "learning_rate": 4.090248546802967e-06, "loss": 0.1833, "step": 23600 }, { "epoch": 1.78, "learning_rate": 4.077720986169573e-06, "loss": 0.1654, "step": 23650 }, { "epoch": 1.78, "learning_rate": 4.065193425536179e-06, "loss": 0.143, "step": 23700 }, { "epoch": 1.79, "learning_rate": 4.052665864902786e-06, "loss": 0.1591, "step": 23750 }, { "epoch": 1.79, "learning_rate": 4.0401383042693934e-06, "loss": 0.1652, "step": 23800 }, { "epoch": 1.79, "learning_rate": 4.027610743636e-06, "loss": 0.2014, "step": 23850 }, { "epoch": 1.8, "learning_rate": 4.015083183002606e-06, "loss": 0.1846, "step": 23900 }, { "epoch": 1.8, "learning_rate": 4.002555622369212e-06, "loss": 0.1707, "step": 23950 }, { "epoch": 1.8, "learning_rate": 3.990028061735819e-06, "loss": 0.1681, "step": 24000 }, { "epoch": 1.81, "learning_rate": 3.977500501102426e-06, "loss": 0.1255, "step": 24050 }, { "epoch": 1.81, "learning_rate": 3.9649729404690325e-06, "loss": 0.133, "step": 24100 }, { "epoch": 1.82, "learning_rate": 3.952445379835639e-06, "loss": 0.1571, "step": 24150 }, { "epoch": 1.82, "learning_rate": 3.939917819202245e-06, "loss": 0.1481, "step": 24200 }, { "epoch": 1.82, "learning_rate": 3.927390258568852e-06, "loss": 0.1768, "step": 24250 }, { "epoch": 1.83, "learning_rate": 3.914862697935458e-06, "loss": 0.1688, "step": 24300 }, { "epoch": 1.83, "learning_rate": 3.902335137302064e-06, "loss": 0.1771, "step": 24350 }, { "epoch": 1.83, "learning_rate": 3.8898075766686715e-06, "loss": 0.1335, "step": 24400 }, { "epoch": 1.84, "learning_rate": 3.877280016035278e-06, "loss": 0.1584, "step": 24450 }, { "epoch": 1.84, "learning_rate": 3.864752455401885e-06, "loss": 0.1639, "step": 24500 }, { "epoch": 1.85, "learning_rate": 3.852224894768491e-06, "loss": 0.2169, "step": 24550 }, { "epoch": 1.85, "learning_rate": 3.839697334135097e-06, "loss": 0.172, "step": 24600 }, { "epoch": 1.85, "learning_rate": 3.8271697735017034e-06, "loss": 0.1578, "step": 24650 }, { "epoch": 1.86, "learning_rate": 3.814642212868311e-06, "loss": 0.2391, "step": 24700 }, { "epoch": 1.86, "learning_rate": 3.802114652234917e-06, "loss": 0.1298, "step": 24750 }, { "epoch": 1.86, "learning_rate": 3.789587091601524e-06, "loss": 0.1388, "step": 24800 }, { "epoch": 1.87, "learning_rate": 3.77705953096813e-06, "loss": 0.1849, "step": 24850 }, { "epoch": 1.87, "learning_rate": 3.7645319703347367e-06, "loss": 0.1633, "step": 24900 }, { "epoch": 1.88, "learning_rate": 3.752004409701343e-06, "loss": 0.1805, "step": 24950 }, { "epoch": 1.88, "learning_rate": 3.73947684906795e-06, "loss": 0.1458, "step": 25000 }, { "epoch": 1.88, "learning_rate": 3.7269492884345566e-06, "loss": 0.1759, "step": 25050 }, { "epoch": 1.89, "learning_rate": 3.714421727801163e-06, "loss": 0.1507, "step": 25100 }, { "epoch": 1.89, "learning_rate": 3.7018941671677695e-06, "loss": 0.1418, "step": 25150 }, { "epoch": 1.89, "learning_rate": 3.6893666065343757e-06, "loss": 0.159, "step": 25200 }, { "epoch": 1.9, "learning_rate": 3.6768390459009823e-06, "loss": 0.1676, "step": 25250 }, { "epoch": 1.9, "learning_rate": 3.6643114852675886e-06, "loss": 0.1894, "step": 25300 }, { "epoch": 1.91, "learning_rate": 3.6517839246341956e-06, "loss": 0.1964, "step": 25350 }, { "epoch": 1.91, "learning_rate": 3.6392563640008023e-06, "loss": 0.1178, "step": 25400 }, { "epoch": 1.91, "learning_rate": 3.6267288033674085e-06, "loss": 0.1419, "step": 25450 }, { "epoch": 1.92, "learning_rate": 3.614201242734015e-06, "loss": 0.1724, "step": 25500 }, { "epoch": 1.92, "learning_rate": 3.6016736821006214e-06, "loss": 0.1865, "step": 25550 }, { "epoch": 1.92, "learning_rate": 3.589146121467228e-06, "loss": 0.1528, "step": 25600 }, { "epoch": 1.93, "learning_rate": 3.576618560833835e-06, "loss": 0.1541, "step": 25650 }, { "epoch": 1.93, "learning_rate": 3.5640910002004413e-06, "loss": 0.1823, "step": 25700 }, { "epoch": 1.94, "learning_rate": 3.551563439567048e-06, "loss": 0.154, "step": 25750 }, { "epoch": 1.94, "learning_rate": 3.539035878933654e-06, "loss": 0.1809, "step": 25800 }, { "epoch": 1.94, "learning_rate": 3.526508318300261e-06, "loss": 0.1521, "step": 25850 }, { "epoch": 1.95, "learning_rate": 3.513980757666867e-06, "loss": 0.1799, "step": 25900 }, { "epoch": 1.95, "learning_rate": 3.501453197033474e-06, "loss": 0.1869, "step": 25950 }, { "epoch": 1.95, "learning_rate": 3.4889256364000808e-06, "loss": 0.1046, "step": 26000 }, { "epoch": 1.96, "learning_rate": 3.476398075766687e-06, "loss": 0.1949, "step": 26050 }, { "epoch": 1.96, "learning_rate": 3.4638705151332936e-06, "loss": 0.1614, "step": 26100 }, { "epoch": 1.97, "learning_rate": 3.4513429544999e-06, "loss": 0.1762, "step": 26150 }, { "epoch": 1.97, "learning_rate": 3.4388153938665065e-06, "loss": 0.1222, "step": 26200 }, { "epoch": 1.97, "learning_rate": 3.4262878332331127e-06, "loss": 0.182, "step": 26250 }, { "epoch": 1.98, "learning_rate": 3.4137602725997198e-06, "loss": 0.1699, "step": 26300 }, { "epoch": 1.98, "learning_rate": 3.4012327119663264e-06, "loss": 0.125, "step": 26350 }, { "epoch": 1.98, "learning_rate": 3.3887051513329327e-06, "loss": 0.1787, "step": 26400 }, { "epoch": 1.99, "learning_rate": 3.3761775906995393e-06, "loss": 0.1633, "step": 26450 }, { "epoch": 1.99, "learning_rate": 3.3636500300661455e-06, "loss": 0.1523, "step": 26500 }, { "epoch": 2.0, "learning_rate": 3.351122469432752e-06, "loss": 0.1927, "step": 26550 }, { "epoch": 2.0, "learning_rate": 3.3385949087993592e-06, "loss": 0.1643, "step": 26600 }, { "epoch": 2.0, "exact_match": 51.08038029386344, "f1": 59.25556094017093, "step": 26608 }, { "epoch": 2.0, "learning_rate": 3.3260673481659655e-06, "loss": 0.0722, "step": 26650 }, { "epoch": 2.01, "learning_rate": 3.313539787532572e-06, "loss": 0.1278, "step": 26700 }, { "epoch": 2.01, "learning_rate": 3.3010122268991783e-06, "loss": 0.0787, "step": 26750 }, { "epoch": 2.01, "learning_rate": 3.288484666265785e-06, "loss": 0.0707, "step": 26800 }, { "epoch": 2.02, "learning_rate": 3.275957105632391e-06, "loss": 0.1228, "step": 26850 }, { "epoch": 2.02, "learning_rate": 3.2634295449989983e-06, "loss": 0.1, "step": 26900 }, { "epoch": 2.03, "learning_rate": 3.250901984365605e-06, "loss": 0.1194, "step": 26950 }, { "epoch": 2.03, "learning_rate": 3.238374423732211e-06, "loss": 0.0841, "step": 27000 }, { "epoch": 2.03, "learning_rate": 3.2258468630988178e-06, "loss": 0.1544, "step": 27050 }, { "epoch": 2.04, "learning_rate": 3.213319302465424e-06, "loss": 0.0739, "step": 27100 }, { "epoch": 2.04, "learning_rate": 3.2007917418320306e-06, "loss": 0.1805, "step": 27150 }, { "epoch": 2.04, "learning_rate": 3.188264181198637e-06, "loss": 0.0618, "step": 27200 }, { "epoch": 2.05, "learning_rate": 3.175736620565244e-06, "loss": 0.0966, "step": 27250 }, { "epoch": 2.05, "learning_rate": 3.1632090599318506e-06, "loss": 0.1268, "step": 27300 }, { "epoch": 2.06, "learning_rate": 3.150681499298457e-06, "loss": 0.0946, "step": 27350 }, { "epoch": 2.06, "learning_rate": 3.1381539386650634e-06, "loss": 0.0949, "step": 27400 }, { "epoch": 2.06, "learning_rate": 3.1256263780316697e-06, "loss": 0.0996, "step": 27450 }, { "epoch": 2.07, "learning_rate": 3.1130988173982763e-06, "loss": 0.0612, "step": 27500 }, { "epoch": 2.07, "learning_rate": 3.1005712567648834e-06, "loss": 0.0901, "step": 27550 }, { "epoch": 2.07, "learning_rate": 3.0880436961314896e-06, "loss": 0.1236, "step": 27600 }, { "epoch": 2.08, "learning_rate": 3.0755161354980963e-06, "loss": 0.0711, "step": 27650 }, { "epoch": 2.08, "learning_rate": 3.0629885748647025e-06, "loss": 0.0429, "step": 27700 }, { "epoch": 2.09, "learning_rate": 3.050461014231309e-06, "loss": 0.1027, "step": 27750 }, { "epoch": 2.09, "learning_rate": 3.0379334535979153e-06, "loss": 0.0642, "step": 27800 }, { "epoch": 2.09, "learning_rate": 3.0254058929645224e-06, "loss": 0.127, "step": 27850 }, { "epoch": 2.1, "learning_rate": 3.012878332331129e-06, "loss": 0.1012, "step": 27900 }, { "epoch": 2.1, "learning_rate": 3.0003507716977353e-06, "loss": 0.0799, "step": 27950 }, { "epoch": 2.1, "learning_rate": 2.987823211064342e-06, "loss": 0.0823, "step": 28000 }, { "epoch": 2.11, "learning_rate": 2.975295650430948e-06, "loss": 0.1013, "step": 28050 }, { "epoch": 2.11, "learning_rate": 2.962768089797555e-06, "loss": 0.0876, "step": 28100 }, { "epoch": 2.12, "learning_rate": 2.950240529164161e-06, "loss": 0.1052, "step": 28150 }, { "epoch": 2.12, "learning_rate": 2.937712968530768e-06, "loss": 0.0826, "step": 28200 }, { "epoch": 2.12, "learning_rate": 2.9251854078973747e-06, "loss": 0.0864, "step": 28250 }, { "epoch": 2.13, "learning_rate": 2.912657847263981e-06, "loss": 0.0799, "step": 28300 }, { "epoch": 2.13, "learning_rate": 2.9001302866305876e-06, "loss": 0.1057, "step": 28350 }, { "epoch": 2.13, "learning_rate": 2.887602725997194e-06, "loss": 0.091, "step": 28400 }, { "epoch": 2.14, "learning_rate": 2.8750751653638005e-06, "loss": 0.0827, "step": 28450 }, { "epoch": 2.14, "learning_rate": 2.8625476047304075e-06, "loss": 0.1339, "step": 28500 }, { "epoch": 2.15, "learning_rate": 2.8500200440970138e-06, "loss": 0.1096, "step": 28550 }, { "epoch": 2.15, "learning_rate": 2.8374924834636204e-06, "loss": 0.1513, "step": 28600 }, { "epoch": 2.15, "learning_rate": 2.8249649228302266e-06, "loss": 0.0939, "step": 28650 }, { "epoch": 2.16, "learning_rate": 2.8124373621968333e-06, "loss": 0.1388, "step": 28700 }, { "epoch": 2.16, "learning_rate": 2.7999098015634395e-06, "loss": 0.1259, "step": 28750 }, { "epoch": 2.16, "learning_rate": 2.787382240930046e-06, "loss": 0.1103, "step": 28800 }, { "epoch": 2.17, "learning_rate": 2.775105231509321e-06, "loss": 0.1445, "step": 28850 }, { "epoch": 2.17, "learning_rate": 2.762577670875927e-06, "loss": 0.0697, "step": 28900 }, { "epoch": 2.18, "learning_rate": 2.7500501102425337e-06, "loss": 0.1085, "step": 28950 }, { "epoch": 2.18, "learning_rate": 2.73752254960914e-06, "loss": 0.074, "step": 29000 }, { "epoch": 2.18, "learning_rate": 2.724994988975747e-06, "loss": 0.0952, "step": 29050 }, { "epoch": 2.19, "learning_rate": 2.7124674283423536e-06, "loss": 0.0524, "step": 29100 }, { "epoch": 2.19, "learning_rate": 2.69993986770896e-06, "loss": 0.0844, "step": 29150 }, { "epoch": 2.19, "learning_rate": 2.6874123070755665e-06, "loss": 0.1059, "step": 29200 }, { "epoch": 2.2, "learning_rate": 2.6748847464421727e-06, "loss": 0.1191, "step": 29250 }, { "epoch": 2.2, "learning_rate": 2.6623571858087794e-06, "loss": 0.113, "step": 29300 }, { "epoch": 2.21, "learning_rate": 2.6498296251753865e-06, "loss": 0.1183, "step": 29350 }, { "epoch": 2.21, "learning_rate": 2.6373020645419927e-06, "loss": 0.1229, "step": 29400 }, { "epoch": 2.21, "learning_rate": 2.6247745039085993e-06, "loss": 0.1276, "step": 29450 }, { "epoch": 2.22, "learning_rate": 2.6122469432752055e-06, "loss": 0.1084, "step": 29500 }, { "epoch": 2.22, "learning_rate": 2.599719382641812e-06, "loss": 0.0889, "step": 29550 }, { "epoch": 2.22, "learning_rate": 2.5871918220084184e-06, "loss": 0.098, "step": 29600 }, { "epoch": 2.23, "learning_rate": 2.574664261375025e-06, "loss": 0.0969, "step": 29650 }, { "epoch": 2.23, "learning_rate": 2.562136700741632e-06, "loss": 0.0944, "step": 29700 }, { "epoch": 2.24, "learning_rate": 2.5496091401082383e-06, "loss": 0.1021, "step": 29750 }, { "epoch": 2.24, "learning_rate": 2.537081579474845e-06, "loss": 0.0927, "step": 29800 }, { "epoch": 2.24, "learning_rate": 2.5245540188414512e-06, "loss": 0.0985, "step": 29850 }, { "epoch": 2.25, "learning_rate": 2.512026458208058e-06, "loss": 0.1503, "step": 29900 }, { "epoch": 2.25, "learning_rate": 2.4994988975746645e-06, "loss": 0.0803, "step": 29950 }, { "epoch": 2.25, "learning_rate": 2.486971336941271e-06, "loss": 0.1176, "step": 30000 }, { "epoch": 2.26, "learning_rate": 2.4744437763078774e-06, "loss": 0.0791, "step": 30050 }, { "epoch": 2.26, "learning_rate": 2.461916215674484e-06, "loss": 0.0985, "step": 30100 }, { "epoch": 2.27, "learning_rate": 2.4493886550410907e-06, "loss": 0.1402, "step": 30150 }, { "epoch": 2.27, "learning_rate": 2.436861094407697e-06, "loss": 0.0957, "step": 30200 }, { "epoch": 2.27, "learning_rate": 2.424333533774304e-06, "loss": 0.1503, "step": 30250 }, { "epoch": 2.28, "learning_rate": 2.41180597314091e-06, "loss": 0.1002, "step": 30300 }, { "epoch": 2.28, "learning_rate": 2.399278412507517e-06, "loss": 0.109, "step": 30350 }, { "epoch": 2.29, "learning_rate": 2.3867508518741235e-06, "loss": 0.1081, "step": 30400 }, { "epoch": 2.29, "learning_rate": 2.3742232912407297e-06, "loss": 0.1553, "step": 30450 }, { "epoch": 2.29, "learning_rate": 2.3616957306073363e-06, "loss": 0.0772, "step": 30500 }, { "epoch": 2.3, "learning_rate": 2.349168169973943e-06, "loss": 0.1092, "step": 30550 }, { "epoch": 2.3, "learning_rate": 2.3366406093405496e-06, "loss": 0.0924, "step": 30600 }, { "epoch": 2.3, "learning_rate": 2.324113048707156e-06, "loss": 0.0791, "step": 30650 }, { "epoch": 2.31, "learning_rate": 2.3115854880737625e-06, "loss": 0.1556, "step": 30700 }, { "epoch": 2.31, "learning_rate": 2.299057927440369e-06, "loss": 0.1471, "step": 30750 }, { "epoch": 2.32, "learning_rate": 2.2865303668069754e-06, "loss": 0.1204, "step": 30800 }, { "epoch": 2.32, "learning_rate": 2.274002806173582e-06, "loss": 0.1114, "step": 30850 }, { "epoch": 2.32, "learning_rate": 2.2614752455401887e-06, "loss": 0.0769, "step": 30900 }, { "epoch": 2.33, "learning_rate": 2.2489476849067953e-06, "loss": 0.0799, "step": 30950 }, { "epoch": 2.33, "learning_rate": 2.2364201242734015e-06, "loss": 0.1004, "step": 31000 }, { "epoch": 2.33, "learning_rate": 2.224143114852676e-06, "loss": 0.0891, "step": 31050 }, { "epoch": 2.34, "learning_rate": 2.211615554219283e-06, "loss": 0.0904, "step": 31100 }, { "epoch": 2.34, "learning_rate": 2.199087993585889e-06, "loss": 0.102, "step": 31150 }, { "epoch": 2.35, "learning_rate": 2.1865604329524957e-06, "loss": 0.0646, "step": 31200 }, { "epoch": 2.35, "learning_rate": 2.1740328723191024e-06, "loss": 0.0763, "step": 31250 }, { "epoch": 2.35, "learning_rate": 2.1615053116857086e-06, "loss": 0.1146, "step": 31300 }, { "epoch": 2.36, "learning_rate": 2.1489777510523153e-06, "loss": 0.0961, "step": 31350 }, { "epoch": 2.36, "learning_rate": 2.136450190418922e-06, "loss": 0.0968, "step": 31400 }, { "epoch": 2.36, "learning_rate": 2.1239226297855285e-06, "loss": 0.0856, "step": 31450 }, { "epoch": 2.37, "learning_rate": 2.1113950691521348e-06, "loss": 0.1081, "step": 31500 }, { "epoch": 2.37, "learning_rate": 2.0988675085187414e-06, "loss": 0.1148, "step": 31550 }, { "epoch": 2.38, "learning_rate": 2.086339947885348e-06, "loss": 0.0963, "step": 31600 }, { "epoch": 2.38, "learning_rate": 2.0738123872519543e-06, "loss": 0.0929, "step": 31650 }, { "epoch": 2.38, "learning_rate": 2.061284826618561e-06, "loss": 0.1196, "step": 31700 }, { "epoch": 2.39, "learning_rate": 2.0487572659851676e-06, "loss": 0.0971, "step": 31750 }, { "epoch": 2.39, "learning_rate": 2.0362297053517742e-06, "loss": 0.1274, "step": 31800 }, { "epoch": 2.39, "learning_rate": 2.0237021447183804e-06, "loss": 0.0692, "step": 31850 }, { "epoch": 2.4, "learning_rate": 2.011174584084987e-06, "loss": 0.0835, "step": 31900 }, { "epoch": 2.4, "learning_rate": 1.9986470234515937e-06, "loss": 0.1217, "step": 31950 }, { "epoch": 2.41, "learning_rate": 1.9861194628182e-06, "loss": 0.0869, "step": 32000 }, { "epoch": 2.41, "learning_rate": 1.973591902184807e-06, "loss": 0.0988, "step": 32050 }, { "epoch": 2.41, "learning_rate": 1.9610643415514132e-06, "loss": 0.1166, "step": 32100 }, { "epoch": 2.42, "learning_rate": 1.94853678091802e-06, "loss": 0.0718, "step": 32150 }, { "epoch": 2.42, "learning_rate": 1.9360092202846265e-06, "loss": 0.0431, "step": 32200 }, { "epoch": 2.42, "learning_rate": 1.9234816596512328e-06, "loss": 0.0896, "step": 32250 }, { "epoch": 2.43, "learning_rate": 1.9109540990178394e-06, "loss": 0.0971, "step": 32300 }, { "epoch": 2.43, "learning_rate": 1.898426538384446e-06, "loss": 0.0939, "step": 32350 }, { "epoch": 2.44, "learning_rate": 1.8858989777510525e-06, "loss": 0.1138, "step": 32400 }, { "epoch": 2.44, "learning_rate": 1.873371417117659e-06, "loss": 0.0826, "step": 32450 }, { "epoch": 2.44, "learning_rate": 1.8608438564842653e-06, "loss": 0.0847, "step": 32500 }, { "epoch": 2.45, "learning_rate": 1.8483162958508722e-06, "loss": 0.112, "step": 32550 }, { "epoch": 2.45, "learning_rate": 1.8357887352174786e-06, "loss": 0.126, "step": 32600 }, { "epoch": 2.45, "learning_rate": 1.823261174584085e-06, "loss": 0.0649, "step": 32650 }, { "epoch": 2.46, "learning_rate": 1.8107336139506917e-06, "loss": 0.1242, "step": 32700 }, { "epoch": 2.46, "learning_rate": 1.7982060533172982e-06, "loss": 0.1085, "step": 32750 }, { "epoch": 2.47, "learning_rate": 1.7856784926839046e-06, "loss": 0.0953, "step": 32800 }, { "epoch": 2.47, "learning_rate": 1.7731509320505114e-06, "loss": 0.0651, "step": 32850 }, { "epoch": 2.47, "learning_rate": 1.7606233714171179e-06, "loss": 0.1182, "step": 32900 }, { "epoch": 2.48, "learning_rate": 1.7480958107837243e-06, "loss": 0.0717, "step": 32950 }, { "epoch": 2.48, "learning_rate": 1.735568250150331e-06, "loss": 0.1015, "step": 33000 }, { "epoch": 2.48, "learning_rate": 1.7230406895169374e-06, "loss": 0.1009, "step": 33050 }, { "epoch": 2.49, "learning_rate": 1.7105131288835438e-06, "loss": 0.0879, "step": 33100 }, { "epoch": 2.49, "learning_rate": 1.6979855682501507e-06, "loss": 0.1216, "step": 33150 }, { "epoch": 2.5, "learning_rate": 1.6854580076167571e-06, "loss": 0.0753, "step": 33200 }, { "epoch": 2.5, "learning_rate": 1.6729304469833636e-06, "loss": 0.0711, "step": 33250 }, { "epoch": 2.5, "learning_rate": 1.66040288634997e-06, "loss": 0.1099, "step": 33300 }, { "epoch": 2.51, "learning_rate": 1.6478753257165766e-06, "loss": 0.129, "step": 33350 }, { "epoch": 2.51, "learning_rate": 1.635347765083183e-06, "loss": 0.0877, "step": 33400 }, { "epoch": 2.51, "learning_rate": 1.6228202044497895e-06, "loss": 0.1112, "step": 33450 }, { "epoch": 2.52, "learning_rate": 1.6102926438163964e-06, "loss": 0.1186, "step": 33500 }, { "epoch": 2.52, "learning_rate": 1.5977650831830028e-06, "loss": 0.0815, "step": 33550 }, { "epoch": 2.53, "learning_rate": 1.5852375225496092e-06, "loss": 0.1255, "step": 33600 }, { "epoch": 2.53, "learning_rate": 1.5727099619162159e-06, "loss": 0.0942, "step": 33650 }, { "epoch": 2.53, "learning_rate": 1.5601824012828223e-06, "loss": 0.1259, "step": 33700 }, { "epoch": 2.54, "learning_rate": 1.5476548406494287e-06, "loss": 0.0945, "step": 33750 }, { "epoch": 2.54, "learning_rate": 1.5351272800160356e-06, "loss": 0.0805, "step": 33800 }, { "epoch": 2.54, "learning_rate": 1.522599719382642e-06, "loss": 0.0851, "step": 33850 }, { "epoch": 2.55, "learning_rate": 1.5100721587492485e-06, "loss": 0.0815, "step": 33900 }, { "epoch": 2.55, "learning_rate": 1.4975445981158551e-06, "loss": 0.101, "step": 33950 }, { "epoch": 2.56, "learning_rate": 1.4850170374824615e-06, "loss": 0.1006, "step": 34000 }, { "epoch": 2.56, "learning_rate": 1.472489476849068e-06, "loss": 0.0759, "step": 34050 }, { "epoch": 2.56, "learning_rate": 1.4599619162156748e-06, "loss": 0.0765, "step": 34100 }, { "epoch": 2.57, "learning_rate": 1.4474343555822813e-06, "loss": 0.0956, "step": 34150 }, { "epoch": 2.57, "learning_rate": 1.4349067949488877e-06, "loss": 0.1312, "step": 34200 }, { "epoch": 2.57, "learning_rate": 1.4223792343154941e-06, "loss": 0.1217, "step": 34250 }, { "epoch": 2.58, "learning_rate": 1.4098516736821008e-06, "loss": 0.1011, "step": 34300 }, { "epoch": 2.58, "learning_rate": 1.3973241130487072e-06, "loss": 0.0896, "step": 34350 }, { "epoch": 2.59, "learning_rate": 1.3847965524153136e-06, "loss": 0.07, "step": 34400 }, { "epoch": 2.59, "learning_rate": 1.3722689917819205e-06, "loss": 0.0848, "step": 34450 }, { "epoch": 2.59, "learning_rate": 1.359741431148527e-06, "loss": 0.0787, "step": 34500 }, { "epoch": 2.6, "learning_rate": 1.3472138705151334e-06, "loss": 0.0794, "step": 34550 }, { "epoch": 2.6, "learning_rate": 1.33468630988174e-06, "loss": 0.0896, "step": 34600 }, { "epoch": 2.6, "learning_rate": 1.3221587492483465e-06, "loss": 0.0942, "step": 34650 }, { "epoch": 2.61, "learning_rate": 1.3096311886149529e-06, "loss": 0.0948, "step": 34700 }, { "epoch": 2.61, "learning_rate": 1.2971036279815597e-06, "loss": 0.1178, "step": 34750 }, { "epoch": 2.62, "learning_rate": 1.2845760673481662e-06, "loss": 0.0669, "step": 34800 }, { "epoch": 2.62, "learning_rate": 1.2720485067147726e-06, "loss": 0.1142, "step": 34850 }, { "epoch": 2.62, "learning_rate": 1.2595209460813793e-06, "loss": 0.0687, "step": 34900 }, { "epoch": 2.63, "learning_rate": 1.2469933854479857e-06, "loss": 0.1004, "step": 34950 }, { "epoch": 2.63, "learning_rate": 1.2344658248145921e-06, "loss": 0.0904, "step": 35000 }, { "epoch": 2.63, "learning_rate": 1.2219382641811988e-06, "loss": 0.092, "step": 35050 }, { "epoch": 2.64, "learning_rate": 1.2094107035478054e-06, "loss": 0.0983, "step": 35100 }, { "epoch": 2.64, "learning_rate": 1.1968831429144118e-06, "loss": 0.0464, "step": 35150 }, { "epoch": 2.65, "learning_rate": 1.1843555822810183e-06, "loss": 0.1265, "step": 35200 }, { "epoch": 2.65, "learning_rate": 1.171828021647625e-06, "loss": 0.0809, "step": 35250 }, { "epoch": 2.65, "learning_rate": 1.1595510122268992e-06, "loss": 0.1048, "step": 35300 }, { "epoch": 2.66, "learning_rate": 1.1472740028061737e-06, "loss": 0.1366, "step": 35350 }, { "epoch": 2.66, "learning_rate": 1.1347464421727801e-06, "loss": 0.1373, "step": 35400 }, { "epoch": 2.66, "learning_rate": 1.1222188815393868e-06, "loss": 0.0448, "step": 35450 }, { "epoch": 2.67, "learning_rate": 1.1096913209059932e-06, "loss": 0.062, "step": 35500 }, { "epoch": 2.67, "learning_rate": 1.0971637602725999e-06, "loss": 0.0721, "step": 35550 }, { "epoch": 2.68, "learning_rate": 1.0846361996392063e-06, "loss": 0.0927, "step": 35600 }, { "epoch": 2.68, "learning_rate": 1.072108639005813e-06, "loss": 0.077, "step": 35650 }, { "epoch": 2.68, "learning_rate": 1.0595810783724194e-06, "loss": 0.095, "step": 35700 }, { "epoch": 2.69, "learning_rate": 1.0470535177390258e-06, "loss": 0.1275, "step": 35750 }, { "epoch": 2.69, "learning_rate": 1.0345259571056325e-06, "loss": 0.1027, "step": 35800 }, { "epoch": 2.69, "learning_rate": 1.0219983964722389e-06, "loss": 0.0658, "step": 35850 }, { "epoch": 2.7, "learning_rate": 1.0094708358388455e-06, "loss": 0.1137, "step": 35900 }, { "epoch": 2.7, "learning_rate": 9.969432752054522e-07, "loss": 0.0858, "step": 35950 }, { "epoch": 2.71, "learning_rate": 9.844157145720586e-07, "loss": 0.1581, "step": 36000 }, { "epoch": 2.71, "learning_rate": 9.71888153938665e-07, "loss": 0.1337, "step": 36050 }, { "epoch": 2.71, "learning_rate": 9.593605933052717e-07, "loss": 0.1082, "step": 36100 }, { "epoch": 2.72, "learning_rate": 9.468330326718781e-07, "loss": 0.0852, "step": 36150 }, { "epoch": 2.72, "learning_rate": 9.343054720384848e-07, "loss": 0.1358, "step": 36200 }, { "epoch": 2.72, "learning_rate": 9.217779114050912e-07, "loss": 0.1008, "step": 36250 }, { "epoch": 2.73, "learning_rate": 9.092503507716977e-07, "loss": 0.0993, "step": 36300 }, { "epoch": 2.73, "learning_rate": 8.967227901383044e-07, "loss": 0.0818, "step": 36350 }, { "epoch": 2.74, "learning_rate": 8.841952295049108e-07, "loss": 0.034, "step": 36400 }, { "epoch": 2.74, "learning_rate": 8.716676688715174e-07, "loss": 0.1407, "step": 36450 }, { "epoch": 2.74, "learning_rate": 8.59140108238124e-07, "loss": 0.1252, "step": 36500 }, { "epoch": 2.75, "learning_rate": 8.466125476047304e-07, "loss": 0.1026, "step": 36550 }, { "epoch": 2.75, "learning_rate": 8.34084986971337e-07, "loss": 0.1041, "step": 36600 }, { "epoch": 2.75, "learning_rate": 8.215574263379436e-07, "loss": 0.0534, "step": 36650 }, { "epoch": 2.76, "learning_rate": 8.090298657045501e-07, "loss": 0.078, "step": 36700 }, { "epoch": 2.76, "learning_rate": 7.965023050711566e-07, "loss": 0.0818, "step": 36750 }, { "epoch": 2.77, "learning_rate": 7.83974744437763e-07, "loss": 0.1133, "step": 36800 }, { "epoch": 2.77, "learning_rate": 7.714471838043697e-07, "loss": 0.0813, "step": 36850 }, { "epoch": 2.77, "learning_rate": 7.589196231709762e-07, "loss": 0.0808, "step": 36900 }, { "epoch": 2.78, "learning_rate": 7.463920625375827e-07, "loss": 0.112, "step": 36950 }, { "epoch": 2.78, "learning_rate": 7.338645019041893e-07, "loss": 0.1386, "step": 37000 }, { "epoch": 2.78, "learning_rate": 7.213369412707958e-07, "loss": 0.0884, "step": 37050 }, { "epoch": 2.79, "learning_rate": 7.088093806374023e-07, "loss": 0.0881, "step": 37100 }, { "epoch": 2.79, "learning_rate": 6.962818200040089e-07, "loss": 0.0914, "step": 37150 }, { "epoch": 2.8, "learning_rate": 6.837542593706154e-07, "loss": 0.0976, "step": 37200 }, { "epoch": 2.8, "learning_rate": 6.712266987372219e-07, "loss": 0.0754, "step": 37250 }, { "epoch": 2.8, "learning_rate": 6.586991381038285e-07, "loss": 0.0551, "step": 37300 }, { "epoch": 2.81, "learning_rate": 6.46171577470435e-07, "loss": 0.0751, "step": 37350 }, { "epoch": 2.81, "learning_rate": 6.336440168370415e-07, "loss": 0.0754, "step": 37400 }, { "epoch": 2.81, "learning_rate": 6.211164562036481e-07, "loss": 0.1558, "step": 37450 }, { "epoch": 2.82, "learning_rate": 6.085888955702546e-07, "loss": 0.0613, "step": 37500 }, { "epoch": 2.82, "learning_rate": 5.960613349368611e-07, "loss": 0.1061, "step": 37550 }, { "epoch": 2.83, "learning_rate": 5.835337743034677e-07, "loss": 0.1007, "step": 37600 }, { "epoch": 2.83, "learning_rate": 5.710062136700742e-07, "loss": 0.0988, "step": 37650 }, { "epoch": 2.83, "learning_rate": 5.584786530366808e-07, "loss": 0.093, "step": 37700 }, { "epoch": 2.84, "learning_rate": 5.459510924032873e-07, "loss": 0.0538, "step": 37750 }, { "epoch": 2.84, "learning_rate": 5.334235317698938e-07, "loss": 0.1133, "step": 37800 }, { "epoch": 2.85, "learning_rate": 5.208959711365004e-07, "loss": 0.0627, "step": 37850 }, { "epoch": 2.85, "learning_rate": 5.083684105031069e-07, "loss": 0.1405, "step": 37900 }, { "epoch": 2.85, "learning_rate": 4.958408498697135e-07, "loss": 0.052, "step": 37950 }, { "epoch": 2.86, "learning_rate": 4.8331328923632e-07, "loss": 0.0724, "step": 38000 }, { "epoch": 2.86, "learning_rate": 4.707857286029265e-07, "loss": 0.0511, "step": 38050 }, { "epoch": 2.86, "learning_rate": 4.58258167969533e-07, "loss": 0.1113, "step": 38100 }, { "epoch": 2.87, "learning_rate": 4.4573060733613956e-07, "loss": 0.065, "step": 38150 }, { "epoch": 2.87, "learning_rate": 4.3320304670274605e-07, "loss": 0.0608, "step": 38200 }, { "epoch": 2.88, "learning_rate": 4.206754860693526e-07, "loss": 0.1273, "step": 38250 }, { "epoch": 2.88, "learning_rate": 4.081479254359592e-07, "loss": 0.0798, "step": 38300 }, { "epoch": 2.88, "learning_rate": 3.9562036480256566e-07, "loss": 0.089, "step": 38350 }, { "epoch": 2.89, "learning_rate": 3.830928041691722e-07, "loss": 0.0976, "step": 38400 }, { "epoch": 2.89, "learning_rate": 3.7056524353577874e-07, "loss": 0.1121, "step": 38450 }, { "epoch": 2.89, "learning_rate": 3.580376829023853e-07, "loss": 0.0719, "step": 38500 }, { "epoch": 2.9, "learning_rate": 3.455101222689918e-07, "loss": 0.0832, "step": 38550 }, { "epoch": 2.9, "learning_rate": 3.329825616355983e-07, "loss": 0.0517, "step": 38600 }, { "epoch": 2.91, "learning_rate": 3.2045500100220485e-07, "loss": 0.0982, "step": 38650 }, { "epoch": 2.91, "learning_rate": 3.079274403688114e-07, "loss": 0.115, "step": 38700 }, { "epoch": 2.91, "learning_rate": 2.9539987973541793e-07, "loss": 0.0898, "step": 38750 }, { "epoch": 2.92, "learning_rate": 2.8287231910202447e-07, "loss": 0.0668, "step": 38800 }, { "epoch": 2.92, "learning_rate": 2.70344758468631e-07, "loss": 0.0522, "step": 38850 }, { "epoch": 2.92, "learning_rate": 2.5781719783523755e-07, "loss": 0.1142, "step": 38900 }, { "epoch": 2.93, "learning_rate": 2.452896372018441e-07, "loss": 0.0738, "step": 38950 }, { "epoch": 2.93, "learning_rate": 2.327620765684506e-07, "loss": 0.1125, "step": 39000 }, { "epoch": 2.94, "learning_rate": 2.2023451593505714e-07, "loss": 0.104, "step": 39050 }, { "epoch": 2.94, "learning_rate": 2.0770695530166365e-07, "loss": 0.091, "step": 39100 }, { "epoch": 2.94, "learning_rate": 1.9517939466827022e-07, "loss": 0.0815, "step": 39150 }, { "epoch": 2.95, "learning_rate": 1.8265183403487673e-07, "loss": 0.089, "step": 39200 }, { "epoch": 2.95, "learning_rate": 1.7012427340148327e-07, "loss": 0.1148, "step": 39250 }, { "epoch": 2.95, "learning_rate": 1.5759671276808984e-07, "loss": 0.0725, "step": 39300 }, { "epoch": 2.96, "learning_rate": 1.4506915213469635e-07, "loss": 0.0447, "step": 39350 }, { "epoch": 2.96, "learning_rate": 1.3254159150130287e-07, "loss": 0.0976, "step": 39400 }, { "epoch": 2.97, "learning_rate": 1.200140308679094e-07, "loss": 0.0626, "step": 39450 }, { "epoch": 2.97, "learning_rate": 1.0748647023451595e-07, "loss": 0.1057, "step": 39500 }, { "epoch": 2.97, "learning_rate": 9.495890960112247e-08, "loss": 0.0659, "step": 39550 }, { "epoch": 2.98, "learning_rate": 8.243134896772901e-08, "loss": 0.113, "step": 39600 }, { "epoch": 2.98, "learning_rate": 6.990378833433555e-08, "loss": 0.0941, "step": 39650 }, { "epoch": 2.98, "learning_rate": 5.762677891360995e-08, "loss": 0.0771, "step": 39700 }, { "epoch": 2.99, "learning_rate": 4.509921828021648e-08, "loss": 0.0667, "step": 39750 }, { "epoch": 2.99, "learning_rate": 3.2571657646823014e-08, "loss": 0.0772, "step": 39800 }, { "epoch": 3.0, "learning_rate": 2.0044097013429547e-08, "loss": 0.08, "step": 39850 }, { "epoch": 3.0, "learning_rate": 7.51653638003608e-09, "loss": 0.0902, "step": 39900 }, { "epoch": 3.0, "exact_match": 51.31086142322097, "f1": 58.231894243296836, "step": 39912 } ], "max_steps": 39912, "num_train_epochs": 3, "total_flos": 4.447693873675008e+17, "trial_name": null, "trial_params": null }