{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.741114852225963, "eval_steps": 500, "global_step": 10000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0037411148522259632, "grad_norm": 17.02508544921875, "learning_rate": 1.8e-06, "loss": 1.1433, "step": 10 }, { "epoch": 0.0074822297044519264, "grad_norm": 4.791806697845459, "learning_rate": 3.8e-06, "loss": 0.8585, "step": 20 }, { "epoch": 0.01122334455667789, "grad_norm": 3.3285908699035645, "learning_rate": 5.8e-06, "loss": 0.3189, "step": 30 }, { "epoch": 0.014964459408903853, "grad_norm": 1.4266235828399658, "learning_rate": 7.8e-06, "loss": 0.1972, "step": 40 }, { "epoch": 0.01870557426112982, "grad_norm": 1.6862940788269043, "learning_rate": 9.800000000000001e-06, "loss": 0.1487, "step": 50 }, { "epoch": 0.02244668911335578, "grad_norm": 1.2625620365142822, "learning_rate": 1.18e-05, "loss": 0.1488, "step": 60 }, { "epoch": 0.026187803965581742, "grad_norm": 0.9922752976417542, "learning_rate": 1.3800000000000002e-05, "loss": 0.0987, "step": 70 }, { "epoch": 0.029928918817807706, "grad_norm": 1.0211018323898315, "learning_rate": 1.58e-05, "loss": 0.1064, "step": 80 }, { "epoch": 0.03367003367003367, "grad_norm": 0.7366190552711487, "learning_rate": 1.78e-05, "loss": 0.0967, "step": 90 }, { "epoch": 0.03741114852225964, "grad_norm": 0.9447920322418213, "learning_rate": 1.9800000000000004e-05, "loss": 0.0878, "step": 100 }, { "epoch": 0.0411522633744856, "grad_norm": 1.1731523275375366, "learning_rate": 2.18e-05, "loss": 0.09, "step": 110 }, { "epoch": 0.04489337822671156, "grad_norm": 0.673734724521637, "learning_rate": 2.38e-05, "loss": 0.0813, "step": 120 }, { "epoch": 0.048634493078937524, "grad_norm": 1.3691606521606445, "learning_rate": 2.58e-05, "loss": 0.0889, "step": 130 }, { "epoch": 0.052375607931163484, "grad_norm": 0.832733690738678, "learning_rate": 2.7800000000000005e-05, "loss": 0.0833, "step": 140 }, { "epoch": 0.05611672278338945, "grad_norm": 1.352574110031128, "learning_rate": 2.98e-05, "loss": 0.0822, "step": 150 }, { "epoch": 0.05985783763561541, "grad_norm": 1.1349575519561768, "learning_rate": 3.18e-05, "loss": 0.0944, "step": 160 }, { "epoch": 0.06359895248784138, "grad_norm": 0.8123451471328735, "learning_rate": 3.38e-05, "loss": 0.0782, "step": 170 }, { "epoch": 0.06734006734006734, "grad_norm": 0.760729968547821, "learning_rate": 3.58e-05, "loss": 0.0745, "step": 180 }, { "epoch": 0.0710811821922933, "grad_norm": 0.6299128532409668, "learning_rate": 3.7800000000000004e-05, "loss": 0.0646, "step": 190 }, { "epoch": 0.07482229704451927, "grad_norm": 1.0762784481048584, "learning_rate": 3.9800000000000005e-05, "loss": 0.067, "step": 200 }, { "epoch": 0.07856341189674523, "grad_norm": 0.8238391280174255, "learning_rate": 4.18e-05, "loss": 0.0877, "step": 210 }, { "epoch": 0.0823045267489712, "grad_norm": 1.008367657661438, "learning_rate": 4.38e-05, "loss": 0.07, "step": 220 }, { "epoch": 0.08604564160119715, "grad_norm": 1.0195974111557007, "learning_rate": 4.58e-05, "loss": 0.066, "step": 230 }, { "epoch": 0.08978675645342311, "grad_norm": 0.8270877599716187, "learning_rate": 4.78e-05, "loss": 0.0685, "step": 240 }, { "epoch": 0.09352787130564909, "grad_norm": 0.6405667066574097, "learning_rate": 4.9800000000000004e-05, "loss": 0.0652, "step": 250 }, { "epoch": 0.09726898615787505, "grad_norm": 0.6703678965568542, "learning_rate": 5.1800000000000005e-05, "loss": 0.0633, "step": 260 }, { "epoch": 0.10101010101010101, "grad_norm": 1.194146990776062, "learning_rate": 5.380000000000001e-05, "loss": 0.0722, "step": 270 }, { "epoch": 0.10475121586232697, "grad_norm": 0.8179264068603516, "learning_rate": 5.580000000000001e-05, "loss": 0.0613, "step": 280 }, { "epoch": 0.10849233071455294, "grad_norm": 0.8530933856964111, "learning_rate": 5.7799999999999995e-05, "loss": 0.068, "step": 290 }, { "epoch": 0.1122334455667789, "grad_norm": 1.207253098487854, "learning_rate": 5.9800000000000003e-05, "loss": 0.0688, "step": 300 }, { "epoch": 0.11597456041900486, "grad_norm": 0.6586894989013672, "learning_rate": 6.18e-05, "loss": 0.0678, "step": 310 }, { "epoch": 0.11971567527123082, "grad_norm": 0.9384670853614807, "learning_rate": 6.38e-05, "loss": 0.0739, "step": 320 }, { "epoch": 0.12345679012345678, "grad_norm": 0.9630885720252991, "learning_rate": 6.58e-05, "loss": 0.0757, "step": 330 }, { "epoch": 0.12719790497568276, "grad_norm": 0.6490210294723511, "learning_rate": 6.780000000000001e-05, "loss": 0.0606, "step": 340 }, { "epoch": 0.1309390198279087, "grad_norm": 0.8993610739707947, "learning_rate": 6.98e-05, "loss": 0.0583, "step": 350 }, { "epoch": 0.13468013468013468, "grad_norm": 0.6225480437278748, "learning_rate": 7.18e-05, "loss": 0.0558, "step": 360 }, { "epoch": 0.13842124953236065, "grad_norm": 0.7200071215629578, "learning_rate": 7.38e-05, "loss": 0.0662, "step": 370 }, { "epoch": 0.1421623643845866, "grad_norm": 0.8367483019828796, "learning_rate": 7.58e-05, "loss": 0.0559, "step": 380 }, { "epoch": 0.14590347923681257, "grad_norm": 0.8006858825683594, "learning_rate": 7.780000000000001e-05, "loss": 0.0626, "step": 390 }, { "epoch": 0.14964459408903855, "grad_norm": 1.0067211389541626, "learning_rate": 7.98e-05, "loss": 0.0641, "step": 400 }, { "epoch": 0.1533857089412645, "grad_norm": 0.5660077333450317, "learning_rate": 8.18e-05, "loss": 0.0646, "step": 410 }, { "epoch": 0.15712682379349047, "grad_norm": 0.644584596157074, "learning_rate": 8.38e-05, "loss": 0.0644, "step": 420 }, { "epoch": 0.1608679386457164, "grad_norm": 1.2482008934020996, "learning_rate": 8.58e-05, "loss": 0.063, "step": 430 }, { "epoch": 0.1646090534979424, "grad_norm": 1.2091466188430786, "learning_rate": 8.78e-05, "loss": 0.0613, "step": 440 }, { "epoch": 0.16835016835016836, "grad_norm": 0.8460163474082947, "learning_rate": 8.98e-05, "loss": 0.0617, "step": 450 }, { "epoch": 0.1720912832023943, "grad_norm": 0.8080103993415833, "learning_rate": 9.180000000000001e-05, "loss": 0.0657, "step": 460 }, { "epoch": 0.17583239805462028, "grad_norm": 1.288371205329895, "learning_rate": 9.38e-05, "loss": 0.0655, "step": 470 }, { "epoch": 0.17957351290684623, "grad_norm": 1.3084444999694824, "learning_rate": 9.58e-05, "loss": 0.0681, "step": 480 }, { "epoch": 0.1833146277590722, "grad_norm": 0.8987330198287964, "learning_rate": 9.78e-05, "loss": 0.061, "step": 490 }, { "epoch": 0.18705574261129818, "grad_norm": 0.9008154273033142, "learning_rate": 9.98e-05, "loss": 0.0536, "step": 500 }, { "epoch": 0.19079685746352412, "grad_norm": 0.6806870698928833, "learning_rate": 9.9999778549206e-05, "loss": 0.0638, "step": 510 }, { "epoch": 0.1945379723157501, "grad_norm": 0.5620561838150024, "learning_rate": 9.999901304280685e-05, "loss": 0.0511, "step": 520 }, { "epoch": 0.19827908716797607, "grad_norm": 0.3904803395271301, "learning_rate": 9.999770075521164e-05, "loss": 0.0575, "step": 530 }, { "epoch": 0.20202020202020202, "grad_norm": 0.5881960988044739, "learning_rate": 9.99958417007713e-05, "loss": 0.0551, "step": 540 }, { "epoch": 0.205761316872428, "grad_norm": 0.6463646292686462, "learning_rate": 9.999343589981615e-05, "loss": 0.0513, "step": 550 }, { "epoch": 0.20950243172465394, "grad_norm": 0.5675182938575745, "learning_rate": 9.999048337865568e-05, "loss": 0.0487, "step": 560 }, { "epoch": 0.2132435465768799, "grad_norm": 0.6210518479347229, "learning_rate": 9.998698416957815e-05, "loss": 0.05, "step": 570 }, { "epoch": 0.21698466142910589, "grad_norm": 0.4495689868927002, "learning_rate": 9.998293831085037e-05, "loss": 0.0477, "step": 580 }, { "epoch": 0.22072577628133183, "grad_norm": 0.41341087222099304, "learning_rate": 9.997834584671719e-05, "loss": 0.0524, "step": 590 }, { "epoch": 0.2244668911335578, "grad_norm": 0.5380939245223999, "learning_rate": 9.997320682740107e-05, "loss": 0.0524, "step": 600 }, { "epoch": 0.22820800598578375, "grad_norm": 0.6887893676757812, "learning_rate": 9.996752130910149e-05, "loss": 0.0583, "step": 610 }, { "epoch": 0.23194912083800973, "grad_norm": 0.49558568000793457, "learning_rate": 9.99612893539944e-05, "loss": 0.0446, "step": 620 }, { "epoch": 0.2356902356902357, "grad_norm": 0.7658884525299072, "learning_rate": 9.995451103023144e-05, "loss": 0.0458, "step": 630 }, { "epoch": 0.23943135054246165, "grad_norm": 0.48816511034965515, "learning_rate": 9.994718641193928e-05, "loss": 0.0437, "step": 640 }, { "epoch": 0.24317246539468762, "grad_norm": 0.3644234836101532, "learning_rate": 9.993931557921874e-05, "loss": 0.0466, "step": 650 }, { "epoch": 0.24691358024691357, "grad_norm": 0.47743165493011475, "learning_rate": 9.993089861814402e-05, "loss": 0.0396, "step": 660 }, { "epoch": 0.25065469509913957, "grad_norm": 0.8837734460830688, "learning_rate": 9.992193562076166e-05, "loss": 0.0531, "step": 670 }, { "epoch": 0.2543958099513655, "grad_norm": 0.5635887980461121, "learning_rate": 9.991242668508954e-05, "loss": 0.0502, "step": 680 }, { "epoch": 0.25813692480359146, "grad_norm": 0.6310935616493225, "learning_rate": 9.990237191511587e-05, "loss": 0.0433, "step": 690 }, { "epoch": 0.2618780396558174, "grad_norm": 0.7606408596038818, "learning_rate": 9.989177142079802e-05, "loss": 0.0464, "step": 700 }, { "epoch": 0.2656191545080434, "grad_norm": 0.7729790210723877, "learning_rate": 9.988062531806126e-05, "loss": 0.0492, "step": 710 }, { "epoch": 0.26936026936026936, "grad_norm": 0.5342724919319153, "learning_rate": 9.986893372879762e-05, "loss": 0.0513, "step": 720 }, { "epoch": 0.2731013842124953, "grad_norm": 0.520664632320404, "learning_rate": 9.985669678086443e-05, "loss": 0.047, "step": 730 }, { "epoch": 0.2768424990647213, "grad_norm": 0.46461135149002075, "learning_rate": 9.984391460808298e-05, "loss": 0.0369, "step": 740 }, { "epoch": 0.28058361391694725, "grad_norm": 0.38246703147888184, "learning_rate": 9.983058735023709e-05, "loss": 0.049, "step": 750 }, { "epoch": 0.2843247287691732, "grad_norm": 0.5732721090316772, "learning_rate": 9.98167151530715e-05, "loss": 0.0414, "step": 760 }, { "epoch": 0.2880658436213992, "grad_norm": 0.5618869662284851, "learning_rate": 9.980229816829034e-05, "loss": 0.0424, "step": 770 }, { "epoch": 0.29180695847362514, "grad_norm": 0.23848414421081543, "learning_rate": 9.978733655355544e-05, "loss": 0.0436, "step": 780 }, { "epoch": 0.2955480733258511, "grad_norm": 0.4440571963787079, "learning_rate": 9.977183047248464e-05, "loss": 0.0401, "step": 790 }, { "epoch": 0.2992891881780771, "grad_norm": 0.624907910823822, "learning_rate": 9.975578009464992e-05, "loss": 0.0425, "step": 800 }, { "epoch": 0.30303030303030304, "grad_norm": 0.608042299747467, "learning_rate": 9.97391855955757e-05, "loss": 0.0441, "step": 810 }, { "epoch": 0.306771417882529, "grad_norm": 0.40443912148475647, "learning_rate": 9.972204715673669e-05, "loss": 0.0481, "step": 820 }, { "epoch": 0.31051253273475493, "grad_norm": 0.3812810778617859, "learning_rate": 9.970436496555617e-05, "loss": 0.0447, "step": 830 }, { "epoch": 0.31425364758698093, "grad_norm": 0.5271909236907959, "learning_rate": 9.968613921540373e-05, "loss": 0.0458, "step": 840 }, { "epoch": 0.3179947624392069, "grad_norm": 0.5360590219497681, "learning_rate": 9.966737010559326e-05, "loss": 0.0477, "step": 850 }, { "epoch": 0.3217358772914328, "grad_norm": 0.8906615972518921, "learning_rate": 9.964805784138072e-05, "loss": 0.0443, "step": 860 }, { "epoch": 0.3254769921436588, "grad_norm": 0.39080411195755005, "learning_rate": 9.962820263396195e-05, "loss": 0.0419, "step": 870 }, { "epoch": 0.3292181069958848, "grad_norm": 0.5974912643432617, "learning_rate": 9.960780470047033e-05, "loss": 0.0381, "step": 880 }, { "epoch": 0.3329592218481107, "grad_norm": 0.5096368789672852, "learning_rate": 9.958686426397437e-05, "loss": 0.0381, "step": 890 }, { "epoch": 0.3367003367003367, "grad_norm": 0.6472828388214111, "learning_rate": 9.956538155347534e-05, "loss": 0.0434, "step": 900 }, { "epoch": 0.34044145155256267, "grad_norm": 0.47276273369789124, "learning_rate": 9.95433568039047e-05, "loss": 0.0399, "step": 910 }, { "epoch": 0.3441825664047886, "grad_norm": 0.53548264503479, "learning_rate": 9.952079025612162e-05, "loss": 0.0453, "step": 920 }, { "epoch": 0.3479236812570146, "grad_norm": 0.5280567407608032, "learning_rate": 9.949768215691022e-05, "loss": 0.0388, "step": 930 }, { "epoch": 0.35166479610924056, "grad_norm": 0.6925433278083801, "learning_rate": 9.9474032758977e-05, "loss": 0.0377, "step": 940 }, { "epoch": 0.3554059109614665, "grad_norm": 0.5303664803504944, "learning_rate": 9.944984232094794e-05, "loss": 0.0484, "step": 950 }, { "epoch": 0.35914702581369246, "grad_norm": 0.3471393585205078, "learning_rate": 9.942511110736584e-05, "loss": 0.0346, "step": 960 }, { "epoch": 0.36288814066591846, "grad_norm": 0.48182055354118347, "learning_rate": 9.939983938868726e-05, "loss": 0.0355, "step": 970 }, { "epoch": 0.3666292555181444, "grad_norm": 0.3831946849822998, "learning_rate": 9.93740274412797e-05, "loss": 0.0371, "step": 980 }, { "epoch": 0.37037037037037035, "grad_norm": 0.47959959506988525, "learning_rate": 9.934767554741846e-05, "loss": 0.0378, "step": 990 }, { "epoch": 0.37411148522259635, "grad_norm": 0.660990297794342, "learning_rate": 9.932078399528361e-05, "loss": 0.0381, "step": 1000 }, { "epoch": 0.3778526000748223, "grad_norm": 0.51953125, "learning_rate": 9.929335307895689e-05, "loss": 0.035, "step": 1010 }, { "epoch": 0.38159371492704824, "grad_norm": 0.41909974813461304, "learning_rate": 9.926538309841839e-05, "loss": 0.0414, "step": 1020 }, { "epoch": 0.38533482977927425, "grad_norm": 0.6112796664237976, "learning_rate": 9.923687435954334e-05, "loss": 0.0415, "step": 1030 }, { "epoch": 0.3890759446315002, "grad_norm": 0.40855440497398376, "learning_rate": 9.920782717409873e-05, "loss": 0.0386, "step": 1040 }, { "epoch": 0.39281705948372614, "grad_norm": 0.5720258355140686, "learning_rate": 9.917824185973994e-05, "loss": 0.0366, "step": 1050 }, { "epoch": 0.39655817433595214, "grad_norm": 0.6682026982307434, "learning_rate": 9.914811874000723e-05, "loss": 0.0424, "step": 1060 }, { "epoch": 0.4002992891881781, "grad_norm": 0.48405346274375916, "learning_rate": 9.911745814432218e-05, "loss": 0.0404, "step": 1070 }, { "epoch": 0.40404040404040403, "grad_norm": 0.3977043032646179, "learning_rate": 9.90862604079842e-05, "loss": 0.0423, "step": 1080 }, { "epoch": 0.40778151889263, "grad_norm": 0.7593915462493896, "learning_rate": 9.90545258721667e-05, "loss": 0.0348, "step": 1090 }, { "epoch": 0.411522633744856, "grad_norm": 0.4718012511730194, "learning_rate": 9.90222548839135e-05, "loss": 0.0375, "step": 1100 }, { "epoch": 0.4152637485970819, "grad_norm": 0.6483708024024963, "learning_rate": 9.898944779613495e-05, "loss": 0.0412, "step": 1110 }, { "epoch": 0.4190048634493079, "grad_norm": 0.4278785288333893, "learning_rate": 9.89561049676041e-05, "loss": 0.0376, "step": 1120 }, { "epoch": 0.4227459783015339, "grad_norm": 0.38154011964797974, "learning_rate": 9.89222267629528e-05, "loss": 0.044, "step": 1130 }, { "epoch": 0.4264870931537598, "grad_norm": 0.6112357378005981, "learning_rate": 9.888781355266763e-05, "loss": 0.0436, "step": 1140 }, { "epoch": 0.43022820800598577, "grad_norm": 0.48649874329566956, "learning_rate": 9.885286571308598e-05, "loss": 0.0462, "step": 1150 }, { "epoch": 0.43396932285821177, "grad_norm": 0.4547445774078369, "learning_rate": 9.881738362639182e-05, "loss": 0.0463, "step": 1160 }, { "epoch": 0.4377104377104377, "grad_norm": 0.7134367823600769, "learning_rate": 9.878136768061154e-05, "loss": 0.0377, "step": 1170 }, { "epoch": 0.44145155256266366, "grad_norm": 0.321601539850235, "learning_rate": 9.874481826960979e-05, "loss": 0.0381, "step": 1180 }, { "epoch": 0.44519266741488966, "grad_norm": 0.4698393940925598, "learning_rate": 9.870773579308503e-05, "loss": 0.04, "step": 1190 }, { "epoch": 0.4489337822671156, "grad_norm": 0.3788212835788727, "learning_rate": 9.867012065656533e-05, "loss": 0.0374, "step": 1200 }, { "epoch": 0.45267489711934156, "grad_norm": 0.4497498571872711, "learning_rate": 9.863197327140376e-05, "loss": 0.036, "step": 1210 }, { "epoch": 0.4564160119715675, "grad_norm": 0.3863726556301117, "learning_rate": 9.859329405477403e-05, "loss": 0.0339, "step": 1220 }, { "epoch": 0.4601571268237935, "grad_norm": 0.2938261926174164, "learning_rate": 9.855408342966585e-05, "loss": 0.032, "step": 1230 }, { "epoch": 0.46389824167601945, "grad_norm": 0.3013354539871216, "learning_rate": 9.851434182488033e-05, "loss": 0.0354, "step": 1240 }, { "epoch": 0.4676393565282454, "grad_norm": 0.4552702009677887, "learning_rate": 9.84740696750253e-05, "loss": 0.0391, "step": 1250 }, { "epoch": 0.4713804713804714, "grad_norm": 0.49028006196022034, "learning_rate": 9.843326742051055e-05, "loss": 0.0392, "step": 1260 }, { "epoch": 0.47512158623269735, "grad_norm": 0.6744625568389893, "learning_rate": 9.839193550754297e-05, "loss": 0.0412, "step": 1270 }, { "epoch": 0.4788627010849233, "grad_norm": 0.5665445923805237, "learning_rate": 9.835007438812177e-05, "loss": 0.04, "step": 1280 }, { "epoch": 0.4826038159371493, "grad_norm": 0.7302022576332092, "learning_rate": 9.830768452003341e-05, "loss": 0.0425, "step": 1290 }, { "epoch": 0.48634493078937524, "grad_norm": 0.4387602210044861, "learning_rate": 9.826476636684671e-05, "loss": 0.0363, "step": 1300 }, { "epoch": 0.4900860456416012, "grad_norm": 0.33703622221946716, "learning_rate": 9.822132039790773e-05, "loss": 0.0301, "step": 1310 }, { "epoch": 0.49382716049382713, "grad_norm": 0.47823086380958557, "learning_rate": 9.817734708833461e-05, "loss": 0.0396, "step": 1320 }, { "epoch": 0.49756827534605313, "grad_norm": 0.47683411836624146, "learning_rate": 9.813284691901243e-05, "loss": 0.035, "step": 1330 }, { "epoch": 0.5013093901982791, "grad_norm": 0.39012542366981506, "learning_rate": 9.808782037658792e-05, "loss": 0.0335, "step": 1340 }, { "epoch": 0.5050505050505051, "grad_norm": 0.3132041096687317, "learning_rate": 9.804226795346411e-05, "loss": 0.0304, "step": 1350 }, { "epoch": 0.508791619902731, "grad_norm": 0.44083914160728455, "learning_rate": 9.799619014779503e-05, "loss": 0.0317, "step": 1360 }, { "epoch": 0.512532734754957, "grad_norm": 0.33324187994003296, "learning_rate": 9.794958746348013e-05, "loss": 0.0295, "step": 1370 }, { "epoch": 0.5162738496071829, "grad_norm": 0.45786622166633606, "learning_rate": 9.790246041015896e-05, "loss": 0.0379, "step": 1380 }, { "epoch": 0.5200149644594089, "grad_norm": 0.3370918929576874, "learning_rate": 9.785480950320538e-05, "loss": 0.0333, "step": 1390 }, { "epoch": 0.5237560793116348, "grad_norm": 0.4481145441532135, "learning_rate": 9.78066352637221e-05, "loss": 0.0358, "step": 1400 }, { "epoch": 0.5274971941638609, "grad_norm": 0.3912205100059509, "learning_rate": 9.775793821853488e-05, "loss": 0.0358, "step": 1410 }, { "epoch": 0.5312383090160868, "grad_norm": 0.38478127121925354, "learning_rate": 9.77087189001868e-05, "loss": 0.0376, "step": 1420 }, { "epoch": 0.5349794238683128, "grad_norm": 0.3669814169406891, "learning_rate": 9.765897784693243e-05, "loss": 0.0332, "step": 1430 }, { "epoch": 0.5387205387205387, "grad_norm": 0.3463030159473419, "learning_rate": 9.760871560273197e-05, "loss": 0.0354, "step": 1440 }, { "epoch": 0.5424616535727647, "grad_norm": 0.44608238339424133, "learning_rate": 9.755793271724526e-05, "loss": 0.0336, "step": 1450 }, { "epoch": 0.5462027684249906, "grad_norm": 0.48410654067993164, "learning_rate": 9.750662974582584e-05, "loss": 0.0335, "step": 1460 }, { "epoch": 0.5499438832772167, "grad_norm": 0.5201867818832397, "learning_rate": 9.745480724951473e-05, "loss": 0.0338, "step": 1470 }, { "epoch": 0.5536849981294426, "grad_norm": 0.5328148603439331, "learning_rate": 9.740246579503447e-05, "loss": 0.0388, "step": 1480 }, { "epoch": 0.5574261129816686, "grad_norm": 0.3780251741409302, "learning_rate": 9.734960595478284e-05, "loss": 0.0321, "step": 1490 }, { "epoch": 0.5611672278338945, "grad_norm": 0.41768187284469604, "learning_rate": 9.729622830682657e-05, "loss": 0.0443, "step": 1500 }, { "epoch": 0.5649083426861204, "grad_norm": 0.3527023494243622, "learning_rate": 9.724233343489504e-05, "loss": 0.0321, "step": 1510 }, { "epoch": 0.5686494575383464, "grad_norm": 0.2629494369029999, "learning_rate": 9.718792192837396e-05, "loss": 0.0328, "step": 1520 }, { "epoch": 0.5723905723905723, "grad_norm": 0.31315693259239197, "learning_rate": 9.713299438229886e-05, "loss": 0.0368, "step": 1530 }, { "epoch": 0.5761316872427984, "grad_norm": 0.42263349890708923, "learning_rate": 9.707755139734855e-05, "loss": 0.0377, "step": 1540 }, { "epoch": 0.5798728020950243, "grad_norm": 0.5311586260795593, "learning_rate": 9.702159357983866e-05, "loss": 0.0374, "step": 1550 }, { "epoch": 0.5836139169472503, "grad_norm": 0.4374777674674988, "learning_rate": 9.696512154171492e-05, "loss": 0.04, "step": 1560 }, { "epoch": 0.5873550317994762, "grad_norm": 0.6670434474945068, "learning_rate": 9.690813590054645e-05, "loss": 0.0369, "step": 1570 }, { "epoch": 0.5910961466517022, "grad_norm": 0.46329158544540405, "learning_rate": 9.685063727951914e-05, "loss": 0.0363, "step": 1580 }, { "epoch": 0.5948372615039281, "grad_norm": 0.4257690906524658, "learning_rate": 9.679262630742865e-05, "loss": 0.0409, "step": 1590 }, { "epoch": 0.5985783763561542, "grad_norm": 0.592140793800354, "learning_rate": 9.673410361867373e-05, "loss": 0.0391, "step": 1600 }, { "epoch": 0.6023194912083801, "grad_norm": 0.3188071548938751, "learning_rate": 9.667506985324909e-05, "loss": 0.0338, "step": 1610 }, { "epoch": 0.6060606060606061, "grad_norm": 0.5234414935112, "learning_rate": 9.661552565673855e-05, "loss": 0.0328, "step": 1620 }, { "epoch": 0.609801720912832, "grad_norm": 0.39909306168556213, "learning_rate": 9.655547168030789e-05, "loss": 0.0343, "step": 1630 }, { "epoch": 0.613542835765058, "grad_norm": 0.4576509892940521, "learning_rate": 9.649490858069777e-05, "loss": 0.0322, "step": 1640 }, { "epoch": 0.6172839506172839, "grad_norm": 0.3588407635688782, "learning_rate": 9.643383702021658e-05, "loss": 0.0391, "step": 1650 }, { "epoch": 0.6210250654695099, "grad_norm": 0.36579328775405884, "learning_rate": 9.637225766673307e-05, "loss": 0.0279, "step": 1660 }, { "epoch": 0.6247661803217359, "grad_norm": 0.2157442569732666, "learning_rate": 9.631017119366922e-05, "loss": 0.0336, "step": 1670 }, { "epoch": 0.6285072951739619, "grad_norm": 0.40536561608314514, "learning_rate": 9.624757827999273e-05, "loss": 0.0349, "step": 1680 }, { "epoch": 0.6322484100261878, "grad_norm": 0.49367502331733704, "learning_rate": 9.618447961020971e-05, "loss": 0.0364, "step": 1690 }, { "epoch": 0.6359895248784138, "grad_norm": 0.36784517765045166, "learning_rate": 9.612087587435707e-05, "loss": 0.0314, "step": 1700 }, { "epoch": 0.6397306397306397, "grad_norm": 0.34298601746559143, "learning_rate": 9.605676776799508e-05, "loss": 0.034, "step": 1710 }, { "epoch": 0.6434717545828657, "grad_norm": 0.353328138589859, "learning_rate": 9.599215599219973e-05, "loss": 0.0324, "step": 1720 }, { "epoch": 0.6472128694350917, "grad_norm": 0.3937336504459381, "learning_rate": 9.592704125355505e-05, "loss": 0.043, "step": 1730 }, { "epoch": 0.6509539842873177, "grad_norm": 0.41546669602394104, "learning_rate": 9.586142426414538e-05, "loss": 0.0329, "step": 1740 }, { "epoch": 0.6546950991395436, "grad_norm": 0.47751739621162415, "learning_rate": 9.57953057415476e-05, "loss": 0.0317, "step": 1750 }, { "epoch": 0.6584362139917695, "grad_norm": 0.5308637022972107, "learning_rate": 9.572868640882328e-05, "loss": 0.035, "step": 1760 }, { "epoch": 0.6621773288439955, "grad_norm": 0.4483676254749298, "learning_rate": 9.56615669945108e-05, "loss": 0.0353, "step": 1770 }, { "epoch": 0.6659184436962214, "grad_norm": 0.38733407855033875, "learning_rate": 9.55939482326173e-05, "loss": 0.0346, "step": 1780 }, { "epoch": 0.6696595585484474, "grad_norm": 0.5232917070388794, "learning_rate": 9.552583086261069e-05, "loss": 0.0401, "step": 1790 }, { "epoch": 0.6734006734006734, "grad_norm": 0.4769097864627838, "learning_rate": 9.545721562941168e-05, "loss": 0.0334, "step": 1800 }, { "epoch": 0.6771417882528994, "grad_norm": 0.4775874614715576, "learning_rate": 9.538810328338543e-05, "loss": 0.0361, "step": 1810 }, { "epoch": 0.6808829031051253, "grad_norm": 0.5033540725708008, "learning_rate": 9.531849458033349e-05, "loss": 0.0336, "step": 1820 }, { "epoch": 0.6846240179573513, "grad_norm": 0.48805513978004456, "learning_rate": 9.524839028148547e-05, "loss": 0.0341, "step": 1830 }, { "epoch": 0.6883651328095772, "grad_norm": 0.2720470726490021, "learning_rate": 9.517779115349077e-05, "loss": 0.0372, "step": 1840 }, { "epoch": 0.6921062476618032, "grad_norm": 0.36638906598091125, "learning_rate": 9.510669796841014e-05, "loss": 0.0339, "step": 1850 }, { "epoch": 0.6958473625140292, "grad_norm": 0.3842012286186218, "learning_rate": 9.503511150370727e-05, "loss": 0.0401, "step": 1860 }, { "epoch": 0.6995884773662552, "grad_norm": 0.4729894995689392, "learning_rate": 9.496303254224024e-05, "loss": 0.0358, "step": 1870 }, { "epoch": 0.7033295922184811, "grad_norm": 0.3032234013080597, "learning_rate": 9.489046187225306e-05, "loss": 0.028, "step": 1880 }, { "epoch": 0.7070707070707071, "grad_norm": 0.2613847255706787, "learning_rate": 9.481740028736692e-05, "loss": 0.0329, "step": 1890 }, { "epoch": 0.710811821922933, "grad_norm": 0.25959843397140503, "learning_rate": 9.474384858657164e-05, "loss": 0.0323, "step": 1900 }, { "epoch": 0.714552936775159, "grad_norm": 0.5603151917457581, "learning_rate": 9.466980757421679e-05, "loss": 0.0345, "step": 1910 }, { "epoch": 0.7182940516273849, "grad_norm": 0.5443153977394104, "learning_rate": 9.459527806000305e-05, "loss": 0.0323, "step": 1920 }, { "epoch": 0.722035166479611, "grad_norm": 0.37534889578819275, "learning_rate": 9.452026085897325e-05, "loss": 0.0377, "step": 1930 }, { "epoch": 0.7257762813318369, "grad_norm": 0.4493940472602844, "learning_rate": 9.444475679150348e-05, "loss": 0.032, "step": 1940 }, { "epoch": 0.7295173961840629, "grad_norm": 0.4103681147098541, "learning_rate": 9.436876668329411e-05, "loss": 0.0341, "step": 1950 }, { "epoch": 0.7332585110362888, "grad_norm": 0.391550749540329, "learning_rate": 9.429229136536079e-05, "loss": 0.0298, "step": 1960 }, { "epoch": 0.7369996258885148, "grad_norm": 0.35158851742744446, "learning_rate": 9.421533167402534e-05, "loss": 0.0336, "step": 1970 }, { "epoch": 0.7407407407407407, "grad_norm": 0.23098671436309814, "learning_rate": 9.413788845090666e-05, "loss": 0.0366, "step": 1980 }, { "epoch": 0.7444818555929668, "grad_norm": 0.2609816789627075, "learning_rate": 9.405996254291136e-05, "loss": 0.0285, "step": 1990 }, { "epoch": 0.7482229704451927, "grad_norm": 0.3347592353820801, "learning_rate": 9.398155480222474e-05, "loss": 0.0314, "step": 2000 }, { "epoch": 0.7519640852974186, "grad_norm": 0.40114060044288635, "learning_rate": 9.390266608630128e-05, "loss": 0.034, "step": 2010 }, { "epoch": 0.7557052001496446, "grad_norm": 0.5549983382225037, "learning_rate": 9.38232972578553e-05, "loss": 0.0348, "step": 2020 }, { "epoch": 0.7594463150018705, "grad_norm": 0.2647467851638794, "learning_rate": 9.374344918485164e-05, "loss": 0.0315, "step": 2030 }, { "epoch": 0.7631874298540965, "grad_norm": 0.3262116014957428, "learning_rate": 9.366312274049602e-05, "loss": 0.0367, "step": 2040 }, { "epoch": 0.7669285447063224, "grad_norm": 0.42954355478286743, "learning_rate": 9.358231880322554e-05, "loss": 0.0282, "step": 2050 }, { "epoch": 0.7706696595585485, "grad_norm": 0.2570165693759918, "learning_rate": 9.350103825669916e-05, "loss": 0.0268, "step": 2060 }, { "epoch": 0.7744107744107744, "grad_norm": 0.3323398232460022, "learning_rate": 9.341928198978787e-05, "loss": 0.0285, "step": 2070 }, { "epoch": 0.7781518892630004, "grad_norm": 0.36893975734710693, "learning_rate": 9.333705089656512e-05, "loss": 0.0296, "step": 2080 }, { "epoch": 0.7818930041152263, "grad_norm": 0.4238148033618927, "learning_rate": 9.325434587629698e-05, "loss": 0.0258, "step": 2090 }, { "epoch": 0.7856341189674523, "grad_norm": 0.34525614976882935, "learning_rate": 9.31711678334323e-05, "loss": 0.0267, "step": 2100 }, { "epoch": 0.7893752338196782, "grad_norm": 0.3897114396095276, "learning_rate": 9.308751767759282e-05, "loss": 0.0252, "step": 2110 }, { "epoch": 0.7931163486719043, "grad_norm": 0.42835620045661926, "learning_rate": 9.300339632356325e-05, "loss": 0.0291, "step": 2120 }, { "epoch": 0.7968574635241302, "grad_norm": 0.2764631509780884, "learning_rate": 9.291880469128124e-05, "loss": 0.0303, "step": 2130 }, { "epoch": 0.8005985783763562, "grad_norm": 0.47408175468444824, "learning_rate": 9.283374370582732e-05, "loss": 0.032, "step": 2140 }, { "epoch": 0.8043396932285821, "grad_norm": 0.4677067697048187, "learning_rate": 9.274821429741482e-05, "loss": 0.0369, "step": 2150 }, { "epoch": 0.8080808080808081, "grad_norm": 0.47226765751838684, "learning_rate": 9.266221740137961e-05, "loss": 0.031, "step": 2160 }, { "epoch": 0.811821922933034, "grad_norm": 0.3887719511985779, "learning_rate": 9.257575395817001e-05, "loss": 0.0325, "step": 2170 }, { "epoch": 0.81556303778526, "grad_norm": 0.44030317664146423, "learning_rate": 9.248882491333637e-05, "loss": 0.0312, "step": 2180 }, { "epoch": 0.819304152637486, "grad_norm": 0.2606617510318756, "learning_rate": 9.240143121752076e-05, "loss": 0.0259, "step": 2190 }, { "epoch": 0.823045267489712, "grad_norm": 0.4468190371990204, "learning_rate": 9.23135738264467e-05, "loss": 0.0283, "step": 2200 }, { "epoch": 0.8267863823419379, "grad_norm": 0.5245052576065063, "learning_rate": 9.222525370090849e-05, "loss": 0.0327, "step": 2210 }, { "epoch": 0.8305274971941639, "grad_norm": 0.28287234902381897, "learning_rate": 9.213647180676088e-05, "loss": 0.0248, "step": 2220 }, { "epoch": 0.8342686120463898, "grad_norm": 0.3006393313407898, "learning_rate": 9.204722911490846e-05, "loss": 0.0336, "step": 2230 }, { "epoch": 0.8380097268986157, "grad_norm": 0.5069670081138611, "learning_rate": 9.1957526601295e-05, "loss": 0.0271, "step": 2240 }, { "epoch": 0.8417508417508418, "grad_norm": 0.2521437108516693, "learning_rate": 9.186736524689281e-05, "loss": 0.037, "step": 2250 }, { "epoch": 0.8454919566030678, "grad_norm": 0.42655009031295776, "learning_rate": 9.177674603769204e-05, "loss": 0.0325, "step": 2260 }, { "epoch": 0.8492330714552937, "grad_norm": 0.4272267818450928, "learning_rate": 9.168566996468983e-05, "loss": 0.0309, "step": 2270 }, { "epoch": 0.8529741863075196, "grad_norm": 0.43500322103500366, "learning_rate": 9.159413802387951e-05, "loss": 0.034, "step": 2280 }, { "epoch": 0.8567153011597456, "grad_norm": 0.31469467282295227, "learning_rate": 9.150215121623974e-05, "loss": 0.0282, "step": 2290 }, { "epoch": 0.8604564160119715, "grad_norm": 0.5759372711181641, "learning_rate": 9.140971054772349e-05, "loss": 0.0285, "step": 2300 }, { "epoch": 0.8641975308641975, "grad_norm": 0.44727516174316406, "learning_rate": 9.131681702924713e-05, "loss": 0.0366, "step": 2310 }, { "epoch": 0.8679386457164235, "grad_norm": 0.3861224949359894, "learning_rate": 9.122347167667926e-05, "loss": 0.0247, "step": 2320 }, { "epoch": 0.8716797605686495, "grad_norm": 0.2653941214084625, "learning_rate": 9.112967551082973e-05, "loss": 0.0347, "step": 2330 }, { "epoch": 0.8754208754208754, "grad_norm": 0.31173861026763916, "learning_rate": 9.103542955743835e-05, "loss": 0.0309, "step": 2340 }, { "epoch": 0.8791619902731014, "grad_norm": 0.4051002264022827, "learning_rate": 9.094073484716381e-05, "loss": 0.0349, "step": 2350 }, { "epoch": 0.8829031051253273, "grad_norm": 0.22519412636756897, "learning_rate": 9.084559241557226e-05, "loss": 0.0315, "step": 2360 }, { "epoch": 0.8866442199775533, "grad_norm": 0.33349311351776123, "learning_rate": 9.075000330312608e-05, "loss": 0.0256, "step": 2370 }, { "epoch": 0.8903853348297793, "grad_norm": 0.3948225677013397, "learning_rate": 9.065396855517253e-05, "loss": 0.0258, "step": 2380 }, { "epoch": 0.8941264496820053, "grad_norm": 0.45785120129585266, "learning_rate": 9.055748922193219e-05, "loss": 0.0323, "step": 2390 }, { "epoch": 0.8978675645342312, "grad_norm": 0.3857654333114624, "learning_rate": 9.046056635848761e-05, "loss": 0.0355, "step": 2400 }, { "epoch": 0.9016086793864572, "grad_norm": 0.47140881419181824, "learning_rate": 9.036320102477169e-05, "loss": 0.0331, "step": 2410 }, { "epoch": 0.9053497942386831, "grad_norm": 0.3516587018966675, "learning_rate": 9.02653942855561e-05, "loss": 0.0285, "step": 2420 }, { "epoch": 0.9090909090909091, "grad_norm": 0.4761723577976227, "learning_rate": 9.016714721043971e-05, "loss": 0.0282, "step": 2430 }, { "epoch": 0.912832023943135, "grad_norm": 0.5998897552490234, "learning_rate": 9.006846087383675e-05, "loss": 0.0288, "step": 2440 }, { "epoch": 0.9165731387953611, "grad_norm": 0.28774669766426086, "learning_rate": 8.996933635496523e-05, "loss": 0.0308, "step": 2450 }, { "epoch": 0.920314253647587, "grad_norm": 0.5049461722373962, "learning_rate": 8.986977473783498e-05, "loss": 0.0363, "step": 2460 }, { "epoch": 0.924055368499813, "grad_norm": 0.6429200172424316, "learning_rate": 8.97697771112359e-05, "loss": 0.0345, "step": 2470 }, { "epoch": 0.9277964833520389, "grad_norm": 0.6414297223091125, "learning_rate": 8.966934456872602e-05, "loss": 0.0401, "step": 2480 }, { "epoch": 0.9315375982042648, "grad_norm": 0.2305152714252472, "learning_rate": 8.95684782086195e-05, "loss": 0.0256, "step": 2490 }, { "epoch": 0.9352787130564908, "grad_norm": 0.4283386468887329, "learning_rate": 8.946717913397476e-05, "loss": 0.0345, "step": 2500 }, { "epoch": 0.9390198279087167, "grad_norm": 0.44220566749572754, "learning_rate": 8.93654484525822e-05, "loss": 0.0355, "step": 2510 }, { "epoch": 0.9427609427609428, "grad_norm": 0.2329157590866089, "learning_rate": 8.926328727695226e-05, "loss": 0.0292, "step": 2520 }, { "epoch": 0.9465020576131687, "grad_norm": 0.48807236552238464, "learning_rate": 8.916069672430319e-05, "loss": 0.0259, "step": 2530 }, { "epoch": 0.9502431724653947, "grad_norm": 0.41240090131759644, "learning_rate": 8.905767791654884e-05, "loss": 0.0354, "step": 2540 }, { "epoch": 0.9539842873176206, "grad_norm": 0.3037407398223877, "learning_rate": 8.895423198028638e-05, "loss": 0.0329, "step": 2550 }, { "epoch": 0.9577254021698466, "grad_norm": 0.43554624915122986, "learning_rate": 8.885036004678402e-05, "loss": 0.0285, "step": 2560 }, { "epoch": 0.9614665170220725, "grad_norm": 0.24113765358924866, "learning_rate": 8.874606325196857e-05, "loss": 0.0291, "step": 2570 }, { "epoch": 0.9652076318742986, "grad_norm": 0.32713815569877625, "learning_rate": 8.864134273641304e-05, "loss": 0.0311, "step": 2580 }, { "epoch": 0.9689487467265245, "grad_norm": 0.2834579050540924, "learning_rate": 8.853619964532427e-05, "loss": 0.0292, "step": 2590 }, { "epoch": 0.9726898615787505, "grad_norm": 0.36258581280708313, "learning_rate": 8.843063512853019e-05, "loss": 0.0306, "step": 2600 }, { "epoch": 0.9764309764309764, "grad_norm": 0.49483734369277954, "learning_rate": 8.832465034046749e-05, "loss": 0.0308, "step": 2610 }, { "epoch": 0.9801720912832024, "grad_norm": 0.33802834153175354, "learning_rate": 8.821824644016882e-05, "loss": 0.0249, "step": 2620 }, { "epoch": 0.9839132061354283, "grad_norm": 0.3404453992843628, "learning_rate": 8.811142459125019e-05, "loss": 0.0254, "step": 2630 }, { "epoch": 0.9876543209876543, "grad_norm": 0.48888707160949707, "learning_rate": 8.800418596189822e-05, "loss": 0.0244, "step": 2640 }, { "epoch": 0.9913954358398803, "grad_norm": 0.32727181911468506, "learning_rate": 8.789653172485737e-05, "loss": 0.0353, "step": 2650 }, { "epoch": 0.9951365506921063, "grad_norm": 0.360033243894577, "learning_rate": 8.778846305741715e-05, "loss": 0.0371, "step": 2660 }, { "epoch": 0.9988776655443322, "grad_norm": 0.26748213171958923, "learning_rate": 8.767998114139918e-05, "loss": 0.0318, "step": 2670 }, { "epoch": 1.0026187803965583, "grad_norm": 0.4873751103878021, "learning_rate": 8.757108716314429e-05, "loss": 0.0351, "step": 2680 }, { "epoch": 1.0063598952487842, "grad_norm": 0.2240825593471527, "learning_rate": 8.746178231349962e-05, "loss": 0.0267, "step": 2690 }, { "epoch": 1.0101010101010102, "grad_norm": 0.5218035578727722, "learning_rate": 8.735206778780549e-05, "loss": 0.0376, "step": 2700 }, { "epoch": 1.0138421249532361, "grad_norm": 0.29314035177230835, "learning_rate": 8.724194478588234e-05, "loss": 0.0241, "step": 2710 }, { "epoch": 1.017583239805462, "grad_norm": 0.6064900755882263, "learning_rate": 8.713141451201772e-05, "loss": 0.0284, "step": 2720 }, { "epoch": 1.021324354657688, "grad_norm": 0.43421754240989685, "learning_rate": 8.702047817495295e-05, "loss": 0.0303, "step": 2730 }, { "epoch": 1.025065469509914, "grad_norm": 0.4205641448497772, "learning_rate": 8.69091369878701e-05, "loss": 0.0277, "step": 2740 }, { "epoch": 1.02880658436214, "grad_norm": 0.3387092053890228, "learning_rate": 8.679739216837849e-05, "loss": 0.0246, "step": 2750 }, { "epoch": 1.0325476992143658, "grad_norm": 0.42095112800598145, "learning_rate": 8.66852449385016e-05, "loss": 0.0274, "step": 2760 }, { "epoch": 1.0362888140665918, "grad_norm": 0.4284825921058655, "learning_rate": 8.657269652466356e-05, "loss": 0.0341, "step": 2770 }, { "epoch": 1.0400299289188177, "grad_norm": 0.31076720356941223, "learning_rate": 8.645974815767577e-05, "loss": 0.0268, "step": 2780 }, { "epoch": 1.0437710437710437, "grad_norm": 0.2871668338775635, "learning_rate": 8.634640107272351e-05, "loss": 0.0265, "step": 2790 }, { "epoch": 1.0475121586232696, "grad_norm": 0.34878435730934143, "learning_rate": 8.623265650935234e-05, "loss": 0.0306, "step": 2800 }, { "epoch": 1.0512532734754958, "grad_norm": 0.4318048357963562, "learning_rate": 8.611851571145456e-05, "loss": 0.0302, "step": 2810 }, { "epoch": 1.0549943883277217, "grad_norm": 0.22337259352207184, "learning_rate": 8.600397992725566e-05, "loss": 0.0244, "step": 2820 }, { "epoch": 1.0587355031799477, "grad_norm": 0.3190123438835144, "learning_rate": 8.588905040930061e-05, "loss": 0.0261, "step": 2830 }, { "epoch": 1.0624766180321736, "grad_norm": 0.35420218110084534, "learning_rate": 8.577372841444022e-05, "loss": 0.0277, "step": 2840 }, { "epoch": 1.0662177328843996, "grad_norm": 0.24409593641757965, "learning_rate": 8.565801520381736e-05, "loss": 0.0275, "step": 2850 }, { "epoch": 1.0699588477366255, "grad_norm": 0.25100982189178467, "learning_rate": 8.554191204285313e-05, "loss": 0.0246, "step": 2860 }, { "epoch": 1.0736999625888515, "grad_norm": 0.29165083169937134, "learning_rate": 8.542542020123315e-05, "loss": 0.0262, "step": 2870 }, { "epoch": 1.0774410774410774, "grad_norm": 0.31709662079811096, "learning_rate": 8.530854095289347e-05, "loss": 0.0284, "step": 2880 }, { "epoch": 1.0811821922933034, "grad_norm": 0.3668610453605652, "learning_rate": 8.519127557600688e-05, "loss": 0.0254, "step": 2890 }, { "epoch": 1.0849233071455293, "grad_norm": 0.23724283277988434, "learning_rate": 8.507362535296871e-05, "loss": 0.0259, "step": 2900 }, { "epoch": 1.0886644219977553, "grad_norm": 0.3781913220882416, "learning_rate": 8.495559157038299e-05, "loss": 0.0318, "step": 2910 }, { "epoch": 1.0924055368499812, "grad_norm": 0.47767624258995056, "learning_rate": 8.483717551904823e-05, "loss": 0.0279, "step": 2920 }, { "epoch": 1.0961466517022074, "grad_norm": 0.20124982297420502, "learning_rate": 8.47183784939434e-05, "loss": 0.0241, "step": 2930 }, { "epoch": 1.0998877665544333, "grad_norm": 0.3772740066051483, "learning_rate": 8.459920179421374e-05, "loss": 0.0274, "step": 2940 }, { "epoch": 1.1036288814066593, "grad_norm": 0.33155831694602966, "learning_rate": 8.447964672315656e-05, "loss": 0.0235, "step": 2950 }, { "epoch": 1.1073699962588852, "grad_norm": 0.27965983748435974, "learning_rate": 8.435971458820692e-05, "loss": 0.0305, "step": 2960 }, { "epoch": 1.1111111111111112, "grad_norm": 0.25103560090065, "learning_rate": 8.423940670092345e-05, "loss": 0.0284, "step": 2970 }, { "epoch": 1.114852225963337, "grad_norm": 0.20029625296592712, "learning_rate": 8.411872437697394e-05, "loss": 0.0273, "step": 2980 }, { "epoch": 1.118593340815563, "grad_norm": 0.22890183329582214, "learning_rate": 8.399766893612096e-05, "loss": 0.0234, "step": 2990 }, { "epoch": 1.122334455667789, "grad_norm": 0.3330659866333008, "learning_rate": 8.38762417022074e-05, "loss": 0.0292, "step": 3000 }, { "epoch": 1.126075570520015, "grad_norm": 0.35837337374687195, "learning_rate": 8.375444400314204e-05, "loss": 0.0232, "step": 3010 }, { "epoch": 1.129816685372241, "grad_norm": 0.19744303822517395, "learning_rate": 8.3632277170885e-05, "loss": 0.0285, "step": 3020 }, { "epoch": 1.1335578002244668, "grad_norm": 0.33773621916770935, "learning_rate": 8.350974254143318e-05, "loss": 0.028, "step": 3030 }, { "epoch": 1.1372989150766928, "grad_norm": 0.2594667077064514, "learning_rate": 8.338684145480566e-05, "loss": 0.0259, "step": 3040 }, { "epoch": 1.1410400299289187, "grad_norm": 0.4783274531364441, "learning_rate": 8.326357525502904e-05, "loss": 0.0276, "step": 3050 }, { "epoch": 1.144781144781145, "grad_norm": 0.38231635093688965, "learning_rate": 8.313994529012273e-05, "loss": 0.0276, "step": 3060 }, { "epoch": 1.1485222596333706, "grad_norm": 0.33478593826293945, "learning_rate": 8.301595291208422e-05, "loss": 0.0308, "step": 3070 }, { "epoch": 1.1522633744855968, "grad_norm": 0.32905465364456177, "learning_rate": 8.289159947687427e-05, "loss": 0.0273, "step": 3080 }, { "epoch": 1.1560044893378227, "grad_norm": 0.5116546750068665, "learning_rate": 8.276688634440216e-05, "loss": 0.0299, "step": 3090 }, { "epoch": 1.1597456041900487, "grad_norm": 0.34199628233909607, "learning_rate": 8.26418148785107e-05, "loss": 0.0282, "step": 3100 }, { "epoch": 1.1634867190422746, "grad_norm": 0.2961914539337158, "learning_rate": 8.251638644696141e-05, "loss": 0.0305, "step": 3110 }, { "epoch": 1.1672278338945006, "grad_norm": 0.2669938802719116, "learning_rate": 8.23906024214195e-05, "loss": 0.0237, "step": 3120 }, { "epoch": 1.1709689487467265, "grad_norm": 0.36852970719337463, "learning_rate": 8.226446417743897e-05, "loss": 0.0275, "step": 3130 }, { "epoch": 1.1747100635989525, "grad_norm": 0.383256196975708, "learning_rate": 8.213797309444742e-05, "loss": 0.0302, "step": 3140 }, { "epoch": 1.1784511784511784, "grad_norm": 0.45852595567703247, "learning_rate": 8.201113055573105e-05, "loss": 0.0301, "step": 3150 }, { "epoch": 1.1821922933034044, "grad_norm": 0.47743692994117737, "learning_rate": 8.188393794841958e-05, "loss": 0.0208, "step": 3160 }, { "epoch": 1.1859334081556303, "grad_norm": 0.43809884786605835, "learning_rate": 8.175639666347094e-05, "loss": 0.0288, "step": 3170 }, { "epoch": 1.1896745230078563, "grad_norm": 0.2332601696252823, "learning_rate": 8.162850809565623e-05, "loss": 0.0256, "step": 3180 }, { "epoch": 1.1934156378600824, "grad_norm": 0.31275442242622375, "learning_rate": 8.150027364354431e-05, "loss": 0.0263, "step": 3190 }, { "epoch": 1.1971567527123081, "grad_norm": 0.3896496593952179, "learning_rate": 8.137169470948662e-05, "loss": 0.0309, "step": 3200 }, { "epoch": 1.2008978675645343, "grad_norm": 0.26046687364578247, "learning_rate": 8.124277269960179e-05, "loss": 0.0231, "step": 3210 }, { "epoch": 1.2046389824167603, "grad_norm": 0.2999742329120636, "learning_rate": 8.111350902376023e-05, "loss": 0.026, "step": 3220 }, { "epoch": 1.2083800972689862, "grad_norm": 0.2441067099571228, "learning_rate": 8.098390509556883e-05, "loss": 0.0268, "step": 3230 }, { "epoch": 1.2121212121212122, "grad_norm": 0.49826550483703613, "learning_rate": 8.085396233235536e-05, "loss": 0.0245, "step": 3240 }, { "epoch": 1.215862326973438, "grad_norm": 0.28262612223625183, "learning_rate": 8.072368215515306e-05, "loss": 0.0205, "step": 3250 }, { "epoch": 1.219603441825664, "grad_norm": 0.3456815779209137, "learning_rate": 8.059306598868506e-05, "loss": 0.0295, "step": 3260 }, { "epoch": 1.22334455667789, "grad_norm": 0.468960702419281, "learning_rate": 8.046211526134888e-05, "loss": 0.0307, "step": 3270 }, { "epoch": 1.227085671530116, "grad_norm": 0.4227088987827301, "learning_rate": 8.033083140520065e-05, "loss": 0.0266, "step": 3280 }, { "epoch": 1.2308267863823419, "grad_norm": 0.4055134654045105, "learning_rate": 8.019921585593962e-05, "loss": 0.0284, "step": 3290 }, { "epoch": 1.2345679012345678, "grad_norm": 0.3345150351524353, "learning_rate": 8.006727005289232e-05, "loss": 0.0259, "step": 3300 }, { "epoch": 1.2383090160867938, "grad_norm": 0.34676501154899597, "learning_rate": 7.993499543899692e-05, "loss": 0.0203, "step": 3310 }, { "epoch": 1.24205013093902, "grad_norm": 0.1966428905725479, "learning_rate": 7.980239346078742e-05, "loss": 0.0209, "step": 3320 }, { "epoch": 1.2457912457912457, "grad_norm": 0.3057464361190796, "learning_rate": 7.966946556837778e-05, "loss": 0.0282, "step": 3330 }, { "epoch": 1.2495323606434718, "grad_norm": 0.34205764532089233, "learning_rate": 7.953621321544616e-05, "loss": 0.0275, "step": 3340 }, { "epoch": 1.2532734754956978, "grad_norm": 0.3899560570716858, "learning_rate": 7.940263785921896e-05, "loss": 0.0274, "step": 3350 }, { "epoch": 1.2570145903479237, "grad_norm": 0.47032690048217773, "learning_rate": 7.926874096045482e-05, "loss": 0.0282, "step": 3360 }, { "epoch": 1.2607557052001497, "grad_norm": 0.3247891366481781, "learning_rate": 7.913452398342881e-05, "loss": 0.0285, "step": 3370 }, { "epoch": 1.2644968200523756, "grad_norm": 0.2296462208032608, "learning_rate": 7.89999883959163e-05, "loss": 0.0274, "step": 3380 }, { "epoch": 1.2682379349046016, "grad_norm": 0.30213096737861633, "learning_rate": 7.886513566917687e-05, "loss": 0.0256, "step": 3390 }, { "epoch": 1.2719790497568275, "grad_norm": 0.29009246826171875, "learning_rate": 7.872996727793838e-05, "loss": 0.0253, "step": 3400 }, { "epoch": 1.2757201646090535, "grad_norm": 0.3411046266555786, "learning_rate": 7.859448470038069e-05, "loss": 0.0228, "step": 3410 }, { "epoch": 1.2794612794612794, "grad_norm": 0.3254791796207428, "learning_rate": 7.845868941811956e-05, "loss": 0.0278, "step": 3420 }, { "epoch": 1.2832023943135054, "grad_norm": 0.3163411319255829, "learning_rate": 7.832258291619043e-05, "loss": 0.0236, "step": 3430 }, { "epoch": 1.2869435091657313, "grad_norm": 0.32634803652763367, "learning_rate": 7.81861666830322e-05, "loss": 0.0211, "step": 3440 }, { "epoch": 1.2906846240179575, "grad_norm": 0.25385865569114685, "learning_rate": 7.804944221047097e-05, "loss": 0.0273, "step": 3450 }, { "epoch": 1.2944257388701832, "grad_norm": 0.20743024349212646, "learning_rate": 7.791241099370364e-05, "loss": 0.0292, "step": 3460 }, { "epoch": 1.2981668537224094, "grad_norm": 0.27996236085891724, "learning_rate": 7.777507453128163e-05, "loss": 0.0263, "step": 3470 }, { "epoch": 1.3019079685746353, "grad_norm": 0.38357776403427124, "learning_rate": 7.763743432509451e-05, "loss": 0.024, "step": 3480 }, { "epoch": 1.3056490834268613, "grad_norm": 0.6913120150566101, "learning_rate": 7.749949188035353e-05, "loss": 0.0271, "step": 3490 }, { "epoch": 1.3093901982790872, "grad_norm": 0.4913928508758545, "learning_rate": 7.736124870557516e-05, "loss": 0.0336, "step": 3500 }, { "epoch": 1.3131313131313131, "grad_norm": 0.2989908456802368, "learning_rate": 7.722270631256459e-05, "loss": 0.0281, "step": 3510 }, { "epoch": 1.316872427983539, "grad_norm": 0.27403488755226135, "learning_rate": 7.708386621639925e-05, "loss": 0.028, "step": 3520 }, { "epoch": 1.320613542835765, "grad_norm": 0.3731701374053955, "learning_rate": 7.694472993541219e-05, "loss": 0.0236, "step": 3530 }, { "epoch": 1.324354657687991, "grad_norm": 0.4018571972846985, "learning_rate": 7.680529899117547e-05, "loss": 0.0291, "step": 3540 }, { "epoch": 1.328095772540217, "grad_norm": 0.1894017904996872, "learning_rate": 7.666557490848358e-05, "loss": 0.0283, "step": 3550 }, { "epoch": 1.3318368873924429, "grad_norm": 0.21181367337703705, "learning_rate": 7.65255592153367e-05, "loss": 0.0274, "step": 3560 }, { "epoch": 1.3355780022446688, "grad_norm": 0.28919756412506104, "learning_rate": 7.638525344292402e-05, "loss": 0.0257, "step": 3570 }, { "epoch": 1.339319117096895, "grad_norm": 0.30317360162734985, "learning_rate": 7.624465912560697e-05, "loss": 0.0276, "step": 3580 }, { "epoch": 1.3430602319491207, "grad_norm": 0.23174327611923218, "learning_rate": 7.610377780090249e-05, "loss": 0.024, "step": 3590 }, { "epoch": 1.3468013468013469, "grad_norm": 0.2625187933444977, "learning_rate": 7.596261100946618e-05, "loss": 0.0241, "step": 3600 }, { "epoch": 1.3505424616535728, "grad_norm": 0.3646719455718994, "learning_rate": 7.582116029507542e-05, "loss": 0.0253, "step": 3610 }, { "epoch": 1.3542835765057988, "grad_norm": 0.2938189208507538, "learning_rate": 7.56794272046126e-05, "loss": 0.021, "step": 3620 }, { "epoch": 1.3580246913580247, "grad_norm": 0.22771486639976501, "learning_rate": 7.55374132880481e-05, "loss": 0.0281, "step": 3630 }, { "epoch": 1.3617658062102507, "grad_norm": 0.27394601702690125, "learning_rate": 7.539512009842333e-05, "loss": 0.0255, "step": 3640 }, { "epoch": 1.3655069210624766, "grad_norm": 0.364091157913208, "learning_rate": 7.525254919183382e-05, "loss": 0.0313, "step": 3650 }, { "epoch": 1.3692480359147026, "grad_norm": 0.19840072095394135, "learning_rate": 7.510970212741215e-05, "loss": 0.0245, "step": 3660 }, { "epoch": 1.3729891507669285, "grad_norm": 0.31430599093437195, "learning_rate": 7.496658046731096e-05, "loss": 0.0249, "step": 3670 }, { "epoch": 1.3767302656191545, "grad_norm": 0.2724277377128601, "learning_rate": 7.482318577668578e-05, "loss": 0.0243, "step": 3680 }, { "epoch": 1.3804713804713804, "grad_norm": 0.5015077590942383, "learning_rate": 7.467951962367796e-05, "loss": 0.0217, "step": 3690 }, { "epoch": 1.3842124953236064, "grad_norm": 0.3409787118434906, "learning_rate": 7.453558357939755e-05, "loss": 0.0219, "step": 3700 }, { "epoch": 1.3879536101758325, "grad_norm": 0.30788445472717285, "learning_rate": 7.439137921790606e-05, "loss": 0.0313, "step": 3710 }, { "epoch": 1.3916947250280582, "grad_norm": 0.4548020660877228, "learning_rate": 7.42469081161993e-05, "loss": 0.0213, "step": 3720 }, { "epoch": 1.3954358398802844, "grad_norm": 0.23044447600841522, "learning_rate": 7.410217185419006e-05, "loss": 0.0236, "step": 3730 }, { "epoch": 1.3991769547325104, "grad_norm": 0.186404749751091, "learning_rate": 7.395717201469095e-05, "loss": 0.0227, "step": 3740 }, { "epoch": 1.4029180695847363, "grad_norm": 0.26861947774887085, "learning_rate": 7.381191018339696e-05, "loss": 0.0221, "step": 3750 }, { "epoch": 1.4066591844369623, "grad_norm": 0.23036730289459229, "learning_rate": 7.36663879488682e-05, "loss": 0.0232, "step": 3760 }, { "epoch": 1.4104002992891882, "grad_norm": 0.3724324107170105, "learning_rate": 7.352060690251254e-05, "loss": 0.0281, "step": 3770 }, { "epoch": 1.4141414141414141, "grad_norm": 0.2776467204093933, "learning_rate": 7.337456863856811e-05, "loss": 0.0237, "step": 3780 }, { "epoch": 1.41788252899364, "grad_norm": 0.3593941628932953, "learning_rate": 7.3228274754086e-05, "loss": 0.0258, "step": 3790 }, { "epoch": 1.421623643845866, "grad_norm": 0.29246586561203003, "learning_rate": 7.308172684891267e-05, "loss": 0.0306, "step": 3800 }, { "epoch": 1.425364758698092, "grad_norm": 0.32171130180358887, "learning_rate": 7.293492652567255e-05, "loss": 0.0266, "step": 3810 }, { "epoch": 1.429105873550318, "grad_norm": 0.41450801491737366, "learning_rate": 7.278787538975043e-05, "loss": 0.0309, "step": 3820 }, { "epoch": 1.4328469884025439, "grad_norm": 0.3938450515270233, "learning_rate": 7.2640575049274e-05, "loss": 0.0298, "step": 3830 }, { "epoch": 1.43658810325477, "grad_norm": 0.2718420922756195, "learning_rate": 7.249302711509616e-05, "loss": 0.0268, "step": 3840 }, { "epoch": 1.4403292181069958, "grad_norm": 0.2625464200973511, "learning_rate": 7.23452332007775e-05, "loss": 0.0268, "step": 3850 }, { "epoch": 1.444070332959222, "grad_norm": 0.31042203307151794, "learning_rate": 7.219719492256858e-05, "loss": 0.024, "step": 3860 }, { "epoch": 1.4478114478114479, "grad_norm": 0.30697736144065857, "learning_rate": 7.20489138993923e-05, "loss": 0.0216, "step": 3870 }, { "epoch": 1.4515525626636738, "grad_norm": 0.2939979135990143, "learning_rate": 7.190039175282614e-05, "loss": 0.023, "step": 3880 }, { "epoch": 1.4552936775158998, "grad_norm": 0.3324795365333557, "learning_rate": 7.175163010708455e-05, "loss": 0.0258, "step": 3890 }, { "epoch": 1.4590347923681257, "grad_norm": 0.23444055020809174, "learning_rate": 7.1602630589001e-05, "loss": 0.0256, "step": 3900 }, { "epoch": 1.4627759072203517, "grad_norm": 0.25306805968284607, "learning_rate": 7.14533948280104e-05, "loss": 0.0232, "step": 3910 }, { "epoch": 1.4665170220725776, "grad_norm": 0.27952897548675537, "learning_rate": 7.130392445613109e-05, "loss": 0.0211, "step": 3920 }, { "epoch": 1.4702581369248036, "grad_norm": 0.191734179854393, "learning_rate": 7.115422110794711e-05, "loss": 0.0246, "step": 3930 }, { "epoch": 1.4739992517770295, "grad_norm": 0.36508625745773315, "learning_rate": 7.100428642059033e-05, "loss": 0.0256, "step": 3940 }, { "epoch": 1.4777403666292555, "grad_norm": 0.334015429019928, "learning_rate": 7.08541220337224e-05, "loss": 0.0262, "step": 3950 }, { "epoch": 1.4814814814814814, "grad_norm": 0.27967652678489685, "learning_rate": 7.070372958951706e-05, "loss": 0.0211, "step": 3960 }, { "epoch": 1.4852225963337076, "grad_norm": 0.3775809109210968, "learning_rate": 7.055311073264194e-05, "loss": 0.0247, "step": 3970 }, { "epoch": 1.4889637111859333, "grad_norm": 0.275065153837204, "learning_rate": 7.040226711024077e-05, "loss": 0.0222, "step": 3980 }, { "epoch": 1.4927048260381595, "grad_norm": 0.17159883677959442, "learning_rate": 7.02512003719152e-05, "loss": 0.0225, "step": 3990 }, { "epoch": 1.4964459408903854, "grad_norm": 0.3455808758735657, "learning_rate": 7.00999121697069e-05, "loss": 0.0265, "step": 4000 }, { "epoch": 1.5001870557426114, "grad_norm": 0.2919713258743286, "learning_rate": 6.99484041580794e-05, "loss": 0.0226, "step": 4010 }, { "epoch": 1.5039281705948373, "grad_norm": 0.5340808033943176, "learning_rate": 6.979667799390004e-05, "loss": 0.0248, "step": 4020 }, { "epoch": 1.5076692854470632, "grad_norm": 0.19946816563606262, "learning_rate": 6.964473533642185e-05, "loss": 0.0249, "step": 4030 }, { "epoch": 1.5114104002992892, "grad_norm": 0.42186009883880615, "learning_rate": 6.949257784726539e-05, "loss": 0.0224, "step": 4040 }, { "epoch": 1.5151515151515151, "grad_norm": 0.4386235475540161, "learning_rate": 6.934020719040056e-05, "loss": 0.0231, "step": 4050 }, { "epoch": 1.518892630003741, "grad_norm": 0.32893458008766174, "learning_rate": 6.918762503212848e-05, "loss": 0.0233, "step": 4060 }, { "epoch": 1.522633744855967, "grad_norm": 0.24568119645118713, "learning_rate": 6.903483304106319e-05, "loss": 0.0255, "step": 4070 }, { "epoch": 1.5263748597081932, "grad_norm": 0.36781996488571167, "learning_rate": 6.888183288811341e-05, "loss": 0.0216, "step": 4080 }, { "epoch": 1.530115974560419, "grad_norm": 0.2870953381061554, "learning_rate": 6.87286262464643e-05, "loss": 0.0248, "step": 4090 }, { "epoch": 1.533857089412645, "grad_norm": 0.32376402616500854, "learning_rate": 6.857521479155915e-05, "loss": 0.0289, "step": 4100 }, { "epoch": 1.5375982042648708, "grad_norm": 0.2937352657318115, "learning_rate": 6.842160020108104e-05, "loss": 0.0249, "step": 4110 }, { "epoch": 1.541339319117097, "grad_norm": 0.33050253987312317, "learning_rate": 6.826778415493455e-05, "loss": 0.026, "step": 4120 }, { "epoch": 1.5450804339693227, "grad_norm": 0.3373938798904419, "learning_rate": 6.811376833522729e-05, "loss": 0.0245, "step": 4130 }, { "epoch": 1.5488215488215489, "grad_norm": 0.28396037220954895, "learning_rate": 6.795955442625159e-05, "loss": 0.0274, "step": 4140 }, { "epoch": 1.5525626636737748, "grad_norm": 0.3609504997730255, "learning_rate": 6.780514411446608e-05, "loss": 0.0254, "step": 4150 }, { "epoch": 1.5563037785260008, "grad_norm": 0.35062408447265625, "learning_rate": 6.765053908847716e-05, "loss": 0.0174, "step": 4160 }, { "epoch": 1.5600448933782267, "grad_norm": 0.20122836530208588, "learning_rate": 6.749574103902064e-05, "loss": 0.0254, "step": 4170 }, { "epoch": 1.5637860082304527, "grad_norm": 0.3732946813106537, "learning_rate": 6.734075165894317e-05, "loss": 0.025, "step": 4180 }, { "epoch": 1.5675271230826786, "grad_norm": 0.4406556487083435, "learning_rate": 6.71855726431838e-05, "loss": 0.0259, "step": 4190 }, { "epoch": 1.5712682379349046, "grad_norm": 0.252871572971344, "learning_rate": 6.703020568875538e-05, "loss": 0.023, "step": 4200 }, { "epoch": 1.5750093527871307, "grad_norm": 0.2938448488712311, "learning_rate": 6.687465249472603e-05, "loss": 0.021, "step": 4210 }, { "epoch": 1.5787504676393564, "grad_norm": 0.3739776909351349, "learning_rate": 6.671891476220055e-05, "loss": 0.0232, "step": 4220 }, { "epoch": 1.5824915824915826, "grad_norm": 0.3613285720348358, "learning_rate": 6.656299419430183e-05, "loss": 0.0204, "step": 4230 }, { "epoch": 1.5862326973438083, "grad_norm": 0.4985050559043884, "learning_rate": 6.640689249615223e-05, "loss": 0.0288, "step": 4240 }, { "epoch": 1.5899738121960345, "grad_norm": 0.35770168900489807, "learning_rate": 6.625061137485491e-05, "loss": 0.0221, "step": 4250 }, { "epoch": 1.5937149270482602, "grad_norm": 0.2838495671749115, "learning_rate": 6.609415253947517e-05, "loss": 0.027, "step": 4260 }, { "epoch": 1.5974560419004864, "grad_norm": 0.32523518800735474, "learning_rate": 6.593751770102178e-05, "loss": 0.0237, "step": 4270 }, { "epoch": 1.6011971567527123, "grad_norm": 0.4098782241344452, "learning_rate": 6.578070857242823e-05, "loss": 0.0202, "step": 4280 }, { "epoch": 1.6049382716049383, "grad_norm": 0.36475688219070435, "learning_rate": 6.562372686853402e-05, "loss": 0.022, "step": 4290 }, { "epoch": 1.6086793864571642, "grad_norm": 0.3406974971294403, "learning_rate": 6.546657430606593e-05, "loss": 0.0224, "step": 4300 }, { "epoch": 1.6124205013093902, "grad_norm": 0.29489773511886597, "learning_rate": 6.530925260361918e-05, "loss": 0.0187, "step": 4310 }, { "epoch": 1.6161616161616161, "grad_norm": 0.37340787053108215, "learning_rate": 6.515176348163871e-05, "loss": 0.022, "step": 4320 }, { "epoch": 1.619902731013842, "grad_norm": 0.2942691445350647, "learning_rate": 6.499410866240032e-05, "loss": 0.02, "step": 4330 }, { "epoch": 1.6236438458660682, "grad_norm": 0.3701339066028595, "learning_rate": 6.48362898699919e-05, "loss": 0.0209, "step": 4340 }, { "epoch": 1.627384960718294, "grad_norm": 0.21612368524074554, "learning_rate": 6.467830883029443e-05, "loss": 0.0212, "step": 4350 }, { "epoch": 1.6311260755705201, "grad_norm": 0.25939878821372986, "learning_rate": 6.452016727096326e-05, "loss": 0.0206, "step": 4360 }, { "epoch": 1.6348671904227459, "grad_norm": 0.3929308354854584, "learning_rate": 6.436186692140916e-05, "loss": 0.0227, "step": 4370 }, { "epoch": 1.638608305274972, "grad_norm": 0.3359788954257965, "learning_rate": 6.420340951277938e-05, "loss": 0.0214, "step": 4380 }, { "epoch": 1.6423494201271978, "grad_norm": 0.3818546235561371, "learning_rate": 6.404479677793874e-05, "loss": 0.0235, "step": 4390 }, { "epoch": 1.646090534979424, "grad_norm": 0.32386520504951477, "learning_rate": 6.388603045145075e-05, "loss": 0.0298, "step": 4400 }, { "epoch": 1.6498316498316499, "grad_norm": 0.46876636147499084, "learning_rate": 6.372711226955843e-05, "loss": 0.0283, "step": 4410 }, { "epoch": 1.6535727646838758, "grad_norm": 0.4112206995487213, "learning_rate": 6.356804397016564e-05, "loss": 0.0282, "step": 4420 }, { "epoch": 1.6573138795361018, "grad_norm": 0.49336132407188416, "learning_rate": 6.340882729281779e-05, "loss": 0.0292, "step": 4430 }, { "epoch": 1.6610549943883277, "grad_norm": 0.24539493024349213, "learning_rate": 6.324946397868294e-05, "loss": 0.0329, "step": 4440 }, { "epoch": 1.6647961092405537, "grad_norm": 0.5865260362625122, "learning_rate": 6.308995577053276e-05, "loss": 0.0239, "step": 4450 }, { "epoch": 1.6685372240927796, "grad_norm": 0.2988983690738678, "learning_rate": 6.293030441272347e-05, "loss": 0.0252, "step": 4460 }, { "epoch": 1.6722783389450058, "grad_norm": 0.3108481466770172, "learning_rate": 6.277051165117677e-05, "loss": 0.0229, "step": 4470 }, { "epoch": 1.6760194537972315, "grad_norm": 0.27330243587493896, "learning_rate": 6.261057923336064e-05, "loss": 0.0227, "step": 4480 }, { "epoch": 1.6797605686494577, "grad_norm": 0.3634282648563385, "learning_rate": 6.245050890827042e-05, "loss": 0.023, "step": 4490 }, { "epoch": 1.6835016835016834, "grad_norm": 0.2809161841869354, "learning_rate": 6.229030242640952e-05, "loss": 0.0212, "step": 4500 }, { "epoch": 1.6872427983539096, "grad_norm": 0.3430100679397583, "learning_rate": 6.212996153977037e-05, "loss": 0.0243, "step": 4510 }, { "epoch": 1.6909839132061353, "grad_norm": 0.222294881939888, "learning_rate": 6.196948800181523e-05, "loss": 0.0207, "step": 4520 }, { "epoch": 1.6947250280583614, "grad_norm": 0.3100249767303467, "learning_rate": 6.180888356745695e-05, "loss": 0.0209, "step": 4530 }, { "epoch": 1.6984661429105874, "grad_norm": 0.16362985968589783, "learning_rate": 6.164814999303995e-05, "loss": 0.0193, "step": 4540 }, { "epoch": 1.7022072577628133, "grad_norm": 0.2831319272518158, "learning_rate": 6.148728903632081e-05, "loss": 0.0171, "step": 4550 }, { "epoch": 1.7059483726150393, "grad_norm": 0.29249995946884155, "learning_rate": 6.132630245644921e-05, "loss": 0.0192, "step": 4560 }, { "epoch": 1.7096894874672652, "grad_norm": 0.2789478003978729, "learning_rate": 6.116519201394857e-05, "loss": 0.0236, "step": 4570 }, { "epoch": 1.7134306023194912, "grad_norm": 0.2566201984882355, "learning_rate": 6.10039594706969e-05, "loss": 0.022, "step": 4580 }, { "epoch": 1.7171717171717171, "grad_norm": 0.22762757539749146, "learning_rate": 6.084260658990744e-05, "loss": 0.022, "step": 4590 }, { "epoch": 1.7209128320239433, "grad_norm": 0.5444832444190979, "learning_rate": 6.068113513610943e-05, "loss": 0.0227, "step": 4600 }, { "epoch": 1.724653946876169, "grad_norm": 0.25110071897506714, "learning_rate": 6.0519546875128876e-05, "loss": 0.022, "step": 4610 }, { "epoch": 1.7283950617283952, "grad_norm": 0.21300631761550903, "learning_rate": 6.035784357406906e-05, "loss": 0.0206, "step": 4620 }, { "epoch": 1.732136176580621, "grad_norm": 0.21147823333740234, "learning_rate": 6.01960270012914e-05, "loss": 0.0197, "step": 4630 }, { "epoch": 1.735877291432847, "grad_norm": 0.3472244143486023, "learning_rate": 6.003409892639599e-05, "loss": 0.0208, "step": 4640 }, { "epoch": 1.7396184062850728, "grad_norm": 0.32721859216690063, "learning_rate": 5.9872061120202336e-05, "loss": 0.0235, "step": 4650 }, { "epoch": 1.743359521137299, "grad_norm": 0.3088419437408447, "learning_rate": 5.9709915354729914e-05, "loss": 0.0274, "step": 4660 }, { "epoch": 1.747100635989525, "grad_norm": 0.23240110278129578, "learning_rate": 5.9547663403178824e-05, "loss": 0.0251, "step": 4670 }, { "epoch": 1.7508417508417509, "grad_norm": 0.275183767080307, "learning_rate": 5.9385307039910445e-05, "loss": 0.0163, "step": 4680 }, { "epoch": 1.7545828656939768, "grad_norm": 0.3597809076309204, "learning_rate": 5.922284804042792e-05, "loss": 0.0233, "step": 4690 }, { "epoch": 1.7583239805462028, "grad_norm": 0.21040143072605133, "learning_rate": 5.906028818135687e-05, "loss": 0.0244, "step": 4700 }, { "epoch": 1.7620650953984287, "grad_norm": 0.3422279357910156, "learning_rate": 5.889762924042585e-05, "loss": 0.0232, "step": 4710 }, { "epoch": 1.7658062102506547, "grad_norm": 0.38286828994750977, "learning_rate": 5.873487299644699e-05, "loss": 0.0212, "step": 4720 }, { "epoch": 1.7695473251028808, "grad_norm": 0.30202779173851013, "learning_rate": 5.857202122929649e-05, "loss": 0.0224, "step": 4730 }, { "epoch": 1.7732884399551065, "grad_norm": 0.2874910831451416, "learning_rate": 5.840907571989518e-05, "loss": 0.0225, "step": 4740 }, { "epoch": 1.7770295548073327, "grad_norm": 0.4306831657886505, "learning_rate": 5.824603825018904e-05, "loss": 0.025, "step": 4750 }, { "epoch": 1.7807706696595584, "grad_norm": 0.3383546769618988, "learning_rate": 5.808291060312975e-05, "loss": 0.0212, "step": 4760 }, { "epoch": 1.7845117845117846, "grad_norm": 0.18069937825202942, "learning_rate": 5.7919694562655083e-05, "loss": 0.0225, "step": 4770 }, { "epoch": 1.7882528993640103, "grad_norm": 0.15908648073673248, "learning_rate": 5.775639191366954e-05, "loss": 0.0232, "step": 4780 }, { "epoch": 1.7919940142162365, "grad_norm": 0.383430540561676, "learning_rate": 5.75930044420247e-05, "loss": 0.0212, "step": 4790 }, { "epoch": 1.7957351290684624, "grad_norm": 0.2795654535293579, "learning_rate": 5.74295339344998e-05, "loss": 0.0251, "step": 4800 }, { "epoch": 1.7994762439206884, "grad_norm": 0.3390541672706604, "learning_rate": 5.726598217878211e-05, "loss": 0.02, "step": 4810 }, { "epoch": 1.8032173587729143, "grad_norm": 0.3117806017398834, "learning_rate": 5.71023509634474e-05, "loss": 0.0207, "step": 4820 }, { "epoch": 1.8069584736251403, "grad_norm": 0.3557172119617462, "learning_rate": 5.693864207794049e-05, "loss": 0.024, "step": 4830 }, { "epoch": 1.8106995884773662, "grad_norm": 0.33640408515930176, "learning_rate": 5.677485731255545e-05, "loss": 0.0295, "step": 4840 }, { "epoch": 1.8144407033295922, "grad_norm": 0.2714289724826813, "learning_rate": 5.6610998458416296e-05, "loss": 0.0199, "step": 4850 }, { "epoch": 1.8181818181818183, "grad_norm": 0.2625892758369446, "learning_rate": 5.644706730745716e-05, "loss": 0.0244, "step": 4860 }, { "epoch": 1.821922933034044, "grad_norm": 0.3447360694408417, "learning_rate": 5.628306565240287e-05, "loss": 0.0216, "step": 4870 }, { "epoch": 1.8256640478862702, "grad_norm": 0.3025824725627899, "learning_rate": 5.611899528674923e-05, "loss": 0.0251, "step": 4880 }, { "epoch": 1.829405162738496, "grad_norm": 0.2317887246608734, "learning_rate": 5.595485800474349e-05, "loss": 0.0242, "step": 4890 }, { "epoch": 1.8331462775907221, "grad_norm": 0.29264649748802185, "learning_rate": 5.579065560136467e-05, "loss": 0.026, "step": 4900 }, { "epoch": 1.8368873924429479, "grad_norm": 0.31220492720603943, "learning_rate": 5.562638987230392e-05, "loss": 0.0233, "step": 4910 }, { "epoch": 1.840628507295174, "grad_norm": 0.38808026909828186, "learning_rate": 5.546206261394498e-05, "loss": 0.0191, "step": 4920 }, { "epoch": 1.8443696221474, "grad_norm": 0.17305053770542145, "learning_rate": 5.529767562334437e-05, "loss": 0.0243, "step": 4930 }, { "epoch": 1.848110736999626, "grad_norm": 0.2331216037273407, "learning_rate": 5.5133230698211926e-05, "loss": 0.0204, "step": 4940 }, { "epoch": 1.8518518518518519, "grad_norm": 0.2123974710702896, "learning_rate": 5.496872963689096e-05, "loss": 0.0233, "step": 4950 }, { "epoch": 1.8555929667040778, "grad_norm": 0.33283835649490356, "learning_rate": 5.4804174238338756e-05, "loss": 0.0196, "step": 4960 }, { "epoch": 1.8593340815563038, "grad_norm": 0.3125302195549011, "learning_rate": 5.463956630210678e-05, "loss": 0.0252, "step": 4970 }, { "epoch": 1.8630751964085297, "grad_norm": 0.20862814784049988, "learning_rate": 5.4474907628321046e-05, "loss": 0.0259, "step": 4980 }, { "epoch": 1.8668163112607559, "grad_norm": 0.30136552453041077, "learning_rate": 5.431020001766244e-05, "loss": 0.019, "step": 4990 }, { "epoch": 1.8705574261129816, "grad_norm": 0.34731629490852356, "learning_rate": 5.4145445271346986e-05, "loss": 0.0194, "step": 5000 }, { "epoch": 1.8742985409652078, "grad_norm": 0.27950456738471985, "learning_rate": 5.398064519110622e-05, "loss": 0.0239, "step": 5010 }, { "epoch": 1.8780396558174335, "grad_norm": 0.3187279999256134, "learning_rate": 5.3815801579167394e-05, "loss": 0.0219, "step": 5020 }, { "epoch": 1.8817807706696597, "grad_norm": 0.38543984293937683, "learning_rate": 5.365091623823382e-05, "loss": 0.0219, "step": 5030 }, { "epoch": 1.8855218855218854, "grad_norm": 0.34158027172088623, "learning_rate": 5.348599097146521e-05, "loss": 0.0229, "step": 5040 }, { "epoch": 1.8892630003741115, "grad_norm": 0.24398422241210938, "learning_rate": 5.3321027582457836e-05, "loss": 0.0194, "step": 5050 }, { "epoch": 1.8930041152263375, "grad_norm": 0.15488313138484955, "learning_rate": 5.315602787522491e-05, "loss": 0.0197, "step": 5060 }, { "epoch": 1.8967452300785634, "grad_norm": 0.25961771607398987, "learning_rate": 5.299099365417678e-05, "loss": 0.0198, "step": 5070 }, { "epoch": 1.9004863449307894, "grad_norm": 0.26580238342285156, "learning_rate": 5.2825926724101236e-05, "loss": 0.0178, "step": 5080 }, { "epoch": 1.9042274597830153, "grad_norm": 0.31745824217796326, "learning_rate": 5.26608288901438e-05, "loss": 0.0204, "step": 5090 }, { "epoch": 1.9079685746352413, "grad_norm": 0.2733217477798462, "learning_rate": 5.24957019577879e-05, "loss": 0.0263, "step": 5100 }, { "epoch": 1.9117096894874672, "grad_norm": 0.2861520051956177, "learning_rate": 5.2330547732835266e-05, "loss": 0.0215, "step": 5110 }, { "epoch": 1.9154508043396934, "grad_norm": 0.2053968906402588, "learning_rate": 5.2165368021385996e-05, "loss": 0.0235, "step": 5120 }, { "epoch": 1.9191919191919191, "grad_norm": 0.28862056136131287, "learning_rate": 5.200016462981897e-05, "loss": 0.0165, "step": 5130 }, { "epoch": 1.9229330340441453, "grad_norm": 0.2290293574333191, "learning_rate": 5.1834939364772015e-05, "loss": 0.0196, "step": 5140 }, { "epoch": 1.926674148896371, "grad_norm": 0.28860804438591003, "learning_rate": 5.166969403312214e-05, "loss": 0.0156, "step": 5150 }, { "epoch": 1.9304152637485972, "grad_norm": 0.33095401525497437, "learning_rate": 5.1504430441965844e-05, "loss": 0.0212, "step": 5160 }, { "epoch": 1.934156378600823, "grad_norm": 0.2501102685928345, "learning_rate": 5.133915039859923e-05, "loss": 0.0167, "step": 5170 }, { "epoch": 1.937897493453049, "grad_norm": 0.20527279376983643, "learning_rate": 5.1173855710498444e-05, "loss": 0.0197, "step": 5180 }, { "epoch": 1.941638608305275, "grad_norm": 0.253751277923584, "learning_rate": 5.100854818529967e-05, "loss": 0.0222, "step": 5190 }, { "epoch": 1.945379723157501, "grad_norm": 0.27957385778427124, "learning_rate": 5.084322963077951e-05, "loss": 0.0209, "step": 5200 }, { "epoch": 1.949120838009727, "grad_norm": 0.28290441632270813, "learning_rate": 5.067790185483522e-05, "loss": 0.0195, "step": 5210 }, { "epoch": 1.9528619528619529, "grad_norm": 0.2167370319366455, "learning_rate": 5.0512566665464844e-05, "loss": 0.0173, "step": 5220 }, { "epoch": 1.9566030677141788, "grad_norm": 0.23134873807430267, "learning_rate": 5.034722587074755e-05, "loss": 0.0178, "step": 5230 }, { "epoch": 1.9603441825664047, "grad_norm": 0.4448991119861603, "learning_rate": 5.018188127882375e-05, "loss": 0.0191, "step": 5240 }, { "epoch": 1.964085297418631, "grad_norm": 0.3436511754989624, "learning_rate": 5.0016534697875417e-05, "loss": 0.0164, "step": 5250 }, { "epoch": 1.9678264122708566, "grad_norm": 0.2869562804698944, "learning_rate": 4.9851187936106294e-05, "loss": 0.021, "step": 5260 }, { "epoch": 1.9715675271230828, "grad_norm": 0.34927162528038025, "learning_rate": 4.968584280172206e-05, "loss": 0.019, "step": 5270 }, { "epoch": 1.9753086419753085, "grad_norm": 0.34091734886169434, "learning_rate": 4.95205011029106e-05, "loss": 0.0207, "step": 5280 }, { "epoch": 1.9790497568275347, "grad_norm": 0.2956140339374542, "learning_rate": 4.935516464782227e-05, "loss": 0.0211, "step": 5290 }, { "epoch": 1.9827908716797604, "grad_norm": 0.6074177622795105, "learning_rate": 4.918983524455003e-05, "loss": 0.0235, "step": 5300 }, { "epoch": 1.9865319865319866, "grad_norm": 0.22638049721717834, "learning_rate": 4.9024514701109766e-05, "loss": 0.0206, "step": 5310 }, { "epoch": 1.9902731013842125, "grad_norm": 0.2546844780445099, "learning_rate": 4.885920482542043e-05, "loss": 0.021, "step": 5320 }, { "epoch": 1.9940142162364385, "grad_norm": 0.2224981039762497, "learning_rate": 4.869390742528438e-05, "loss": 0.0198, "step": 5330 }, { "epoch": 1.9977553310886644, "grad_norm": 0.3474802076816559, "learning_rate": 4.852862430836744e-05, "loss": 0.02, "step": 5340 }, { "epoch": 2.0014964459408904, "grad_norm": 0.25409021973609924, "learning_rate": 4.836335728217933e-05, "loss": 0.0242, "step": 5350 }, { "epoch": 2.0052375607931165, "grad_norm": 0.2210186868906021, "learning_rate": 4.819810815405379e-05, "loss": 0.0212, "step": 5360 }, { "epoch": 2.0089786756453423, "grad_norm": 0.15420910716056824, "learning_rate": 4.803287873112877e-05, "loss": 0.0209, "step": 5370 }, { "epoch": 2.0127197904975684, "grad_norm": 0.24931998550891876, "learning_rate": 4.786767082032681e-05, "loss": 0.0194, "step": 5380 }, { "epoch": 2.016460905349794, "grad_norm": 0.24309349060058594, "learning_rate": 4.77024862283351e-05, "loss": 0.0175, "step": 5390 }, { "epoch": 2.0202020202020203, "grad_norm": 0.17444559931755066, "learning_rate": 4.753732676158593e-05, "loss": 0.0171, "step": 5400 }, { "epoch": 2.023943135054246, "grad_norm": 0.20029720664024353, "learning_rate": 4.737219422623672e-05, "loss": 0.0166, "step": 5410 }, { "epoch": 2.0276842499064722, "grad_norm": 0.3070124685764313, "learning_rate": 4.720709042815044e-05, "loss": 0.0174, "step": 5420 }, { "epoch": 2.031425364758698, "grad_norm": 0.3694189786911011, "learning_rate": 4.704201717287578e-05, "loss": 0.0196, "step": 5430 }, { "epoch": 2.035166479610924, "grad_norm": 0.1867385357618332, "learning_rate": 4.6876976265627404e-05, "loss": 0.0164, "step": 5440 }, { "epoch": 2.03890759446315, "grad_norm": 0.2945535480976105, "learning_rate": 4.671196951126626e-05, "loss": 0.0254, "step": 5450 }, { "epoch": 2.042648709315376, "grad_norm": 0.2910444140434265, "learning_rate": 4.654699871427971e-05, "loss": 0.0196, "step": 5460 }, { "epoch": 2.0463898241676017, "grad_norm": 0.20165494084358215, "learning_rate": 4.6382065678762034e-05, "loss": 0.0189, "step": 5470 }, { "epoch": 2.050130939019828, "grad_norm": 0.2304479032754898, "learning_rate": 4.6217172208394424e-05, "loss": 0.0167, "step": 5480 }, { "epoch": 2.053872053872054, "grad_norm": 0.16487933695316315, "learning_rate": 4.605232010642549e-05, "loss": 0.0135, "step": 5490 }, { "epoch": 2.05761316872428, "grad_norm": 0.33820945024490356, "learning_rate": 4.588751117565142e-05, "loss": 0.016, "step": 5500 }, { "epoch": 2.061354283576506, "grad_norm": 0.2941293716430664, "learning_rate": 4.5722747218396214e-05, "loss": 0.0167, "step": 5510 }, { "epoch": 2.0650953984287317, "grad_norm": 0.354253888130188, "learning_rate": 4.5558030036492194e-05, "loss": 0.0171, "step": 5520 }, { "epoch": 2.068836513280958, "grad_norm": 0.24254831671714783, "learning_rate": 4.539336143125999e-05, "loss": 0.0215, "step": 5530 }, { "epoch": 2.0725776281331836, "grad_norm": 0.2116146981716156, "learning_rate": 4.522874320348916e-05, "loss": 0.018, "step": 5540 }, { "epoch": 2.0763187429854097, "grad_norm": 0.276692271232605, "learning_rate": 4.506417715341821e-05, "loss": 0.0156, "step": 5550 }, { "epoch": 2.0800598578376355, "grad_norm": 0.27233535051345825, "learning_rate": 4.489966508071511e-05, "loss": 0.0203, "step": 5560 }, { "epoch": 2.0838009726898616, "grad_norm": 0.2607994079589844, "learning_rate": 4.4735208784457575e-05, "loss": 0.0171, "step": 5570 }, { "epoch": 2.0875420875420874, "grad_norm": 0.43651294708251953, "learning_rate": 4.457081006311325e-05, "loss": 0.0216, "step": 5580 }, { "epoch": 2.0912832023943135, "grad_norm": 0.3976624310016632, "learning_rate": 4.440647071452027e-05, "loss": 0.0184, "step": 5590 }, { "epoch": 2.0950243172465393, "grad_norm": 0.37377631664276123, "learning_rate": 4.424219253586737e-05, "loss": 0.0225, "step": 5600 }, { "epoch": 2.0987654320987654, "grad_norm": 0.39576050639152527, "learning_rate": 4.407797732367443e-05, "loss": 0.023, "step": 5610 }, { "epoch": 2.1025065469509916, "grad_norm": 0.27604079246520996, "learning_rate": 4.391382687377268e-05, "loss": 0.0195, "step": 5620 }, { "epoch": 2.1062476618032173, "grad_norm": 0.2743885815143585, "learning_rate": 4.374974298128512e-05, "loss": 0.0174, "step": 5630 }, { "epoch": 2.1099887766554435, "grad_norm": 0.23557454347610474, "learning_rate": 4.358572744060699e-05, "loss": 0.0202, "step": 5640 }, { "epoch": 2.113729891507669, "grad_norm": 0.2986251413822174, "learning_rate": 4.342178204538588e-05, "loss": 0.0188, "step": 5650 }, { "epoch": 2.1174710063598954, "grad_norm": 0.2979719042778015, "learning_rate": 4.325790858850241e-05, "loss": 0.0179, "step": 5660 }, { "epoch": 2.121212121212121, "grad_norm": 0.3879520893096924, "learning_rate": 4.309410886205043e-05, "loss": 0.0187, "step": 5670 }, { "epoch": 2.1249532360643473, "grad_norm": 0.21463420987129211, "learning_rate": 4.293038465731752e-05, "loss": 0.0173, "step": 5680 }, { "epoch": 2.128694350916573, "grad_norm": 0.3232002258300781, "learning_rate": 4.276673776476533e-05, "loss": 0.0201, "step": 5690 }, { "epoch": 2.132435465768799, "grad_norm": 0.3064553141593933, "learning_rate": 4.260316997401007e-05, "loss": 0.0205, "step": 5700 }, { "epoch": 2.136176580621025, "grad_norm": 0.19188669323921204, "learning_rate": 4.243968307380293e-05, "loss": 0.0209, "step": 5710 }, { "epoch": 2.139917695473251, "grad_norm": 0.21677309274673462, "learning_rate": 4.22762788520104e-05, "loss": 0.0215, "step": 5720 }, { "epoch": 2.1436588103254772, "grad_norm": 0.23933960497379303, "learning_rate": 4.211295909559491e-05, "loss": 0.0244, "step": 5730 }, { "epoch": 2.147399925177703, "grad_norm": 0.22662416100502014, "learning_rate": 4.194972559059511e-05, "loss": 0.0164, "step": 5740 }, { "epoch": 2.151141040029929, "grad_norm": 0.2875952124595642, "learning_rate": 4.178658012210651e-05, "loss": 0.0164, "step": 5750 }, { "epoch": 2.154882154882155, "grad_norm": 0.43141087889671326, "learning_rate": 4.162352447426177e-05, "loss": 0.0181, "step": 5760 }, { "epoch": 2.158623269734381, "grad_norm": 0.30970656871795654, "learning_rate": 4.146056043021135e-05, "loss": 0.0179, "step": 5770 }, { "epoch": 2.1623643845866067, "grad_norm": 0.22642281651496887, "learning_rate": 4.1297689772103944e-05, "loss": 0.0218, "step": 5780 }, { "epoch": 2.166105499438833, "grad_norm": 0.2946833074092865, "learning_rate": 4.113491428106694e-05, "loss": 0.0179, "step": 5790 }, { "epoch": 2.1698466142910586, "grad_norm": 0.1789426952600479, "learning_rate": 4.0972235737187055e-05, "loss": 0.0149, "step": 5800 }, { "epoch": 2.173587729143285, "grad_norm": 0.21605348587036133, "learning_rate": 4.080965591949076e-05, "loss": 0.0175, "step": 5810 }, { "epoch": 2.1773288439955105, "grad_norm": 0.25184544920921326, "learning_rate": 4.0647176605924924e-05, "loss": 0.0161, "step": 5820 }, { "epoch": 2.1810699588477367, "grad_norm": 0.22409023344516754, "learning_rate": 4.0484799573337255e-05, "loss": 0.0203, "step": 5830 }, { "epoch": 2.1848110736999624, "grad_norm": 0.20124594867229462, "learning_rate": 4.032252659745699e-05, "loss": 0.0181, "step": 5840 }, { "epoch": 2.1885521885521886, "grad_norm": 0.28657492995262146, "learning_rate": 4.016035945287539e-05, "loss": 0.0209, "step": 5850 }, { "epoch": 2.1922933034044148, "grad_norm": 0.14598681032657623, "learning_rate": 3.999829991302635e-05, "loss": 0.0165, "step": 5860 }, { "epoch": 2.1960344182566405, "grad_norm": 0.24327030777931213, "learning_rate": 3.983634975016707e-05, "loss": 0.0164, "step": 5870 }, { "epoch": 2.1997755331088666, "grad_norm": 0.2913753390312195, "learning_rate": 3.967451073535854e-05, "loss": 0.0224, "step": 5880 }, { "epoch": 2.2035166479610924, "grad_norm": 0.21831396222114563, "learning_rate": 3.951278463844633e-05, "loss": 0.0184, "step": 5890 }, { "epoch": 2.2072577628133185, "grad_norm": 0.3016241490840912, "learning_rate": 3.935117322804111e-05, "loss": 0.0208, "step": 5900 }, { "epoch": 2.2109988776655443, "grad_norm": 0.3228060007095337, "learning_rate": 3.918967827149938e-05, "loss": 0.0168, "step": 5910 }, { "epoch": 2.2147399925177704, "grad_norm": 0.23735462129116058, "learning_rate": 3.9028301534904094e-05, "loss": 0.0168, "step": 5920 }, { "epoch": 2.218481107369996, "grad_norm": 0.30591052770614624, "learning_rate": 3.88670447830454e-05, "loss": 0.0209, "step": 5930 }, { "epoch": 2.2222222222222223, "grad_norm": 0.3659260869026184, "learning_rate": 3.870590977940132e-05, "loss": 0.0188, "step": 5940 }, { "epoch": 2.225963337074448, "grad_norm": 0.23576043546199799, "learning_rate": 3.8544898286118404e-05, "loss": 0.0167, "step": 5950 }, { "epoch": 2.229704451926674, "grad_norm": 0.25881415605545044, "learning_rate": 3.838401206399257e-05, "loss": 0.0148, "step": 5960 }, { "epoch": 2.2334455667789, "grad_norm": 0.2762620151042938, "learning_rate": 3.822325287244975e-05, "loss": 0.0169, "step": 5970 }, { "epoch": 2.237186681631126, "grad_norm": 0.3642794191837311, "learning_rate": 3.8062622469526725e-05, "loss": 0.0169, "step": 5980 }, { "epoch": 2.2409277964833523, "grad_norm": 0.21441468596458435, "learning_rate": 3.790212261185183e-05, "loss": 0.015, "step": 5990 }, { "epoch": 2.244668911335578, "grad_norm": 0.23103970289230347, "learning_rate": 3.7741755054625794e-05, "loss": 0.017, "step": 6000 }, { "epoch": 2.248410026187804, "grad_norm": 0.20473939180374146, "learning_rate": 3.758152155160255e-05, "loss": 0.0146, "step": 6010 }, { "epoch": 2.25215114104003, "grad_norm": 0.37483030557632446, "learning_rate": 3.742142385506999e-05, "loss": 0.0185, "step": 6020 }, { "epoch": 2.255892255892256, "grad_norm": 0.19525596499443054, "learning_rate": 3.72614637158309e-05, "loss": 0.0146, "step": 6030 }, { "epoch": 2.259633370744482, "grad_norm": 0.30579522252082825, "learning_rate": 3.710164288318371e-05, "loss": 0.019, "step": 6040 }, { "epoch": 2.263374485596708, "grad_norm": 0.21009796857833862, "learning_rate": 3.694196310490345e-05, "loss": 0.0135, "step": 6050 }, { "epoch": 2.2671156004489337, "grad_norm": 0.1928977221250534, "learning_rate": 3.678242612722259e-05, "loss": 0.0157, "step": 6060 }, { "epoch": 2.27085671530116, "grad_norm": 0.18404719233512878, "learning_rate": 3.6623033694811953e-05, "loss": 0.016, "step": 6070 }, { "epoch": 2.2745978301533856, "grad_norm": 0.28890717029571533, "learning_rate": 3.6463787550761665e-05, "loss": 0.0182, "step": 6080 }, { "epoch": 2.2783389450056117, "grad_norm": 0.2614186704158783, "learning_rate": 3.630468943656202e-05, "loss": 0.0209, "step": 6090 }, { "epoch": 2.2820800598578375, "grad_norm": 0.20812998712062836, "learning_rate": 3.6145741092084523e-05, "loss": 0.0128, "step": 6100 }, { "epoch": 2.2858211747100636, "grad_norm": 0.37274596095085144, "learning_rate": 3.598694425556278e-05, "loss": 0.0174, "step": 6110 }, { "epoch": 2.28956228956229, "grad_norm": 0.16998857259750366, "learning_rate": 3.58283006635736e-05, "loss": 0.0161, "step": 6120 }, { "epoch": 2.2933034044145155, "grad_norm": 0.29129543900489807, "learning_rate": 3.566981205101781e-05, "loss": 0.0173, "step": 6130 }, { "epoch": 2.2970445192667412, "grad_norm": 0.17275606095790863, "learning_rate": 3.5511480151101556e-05, "loss": 0.0175, "step": 6140 }, { "epoch": 2.3007856341189674, "grad_norm": 0.30297523736953735, "learning_rate": 3.5353306695317104e-05, "loss": 0.0152, "step": 6150 }, { "epoch": 2.3045267489711936, "grad_norm": 0.42855364084243774, "learning_rate": 3.519529341342402e-05, "loss": 0.018, "step": 6160 }, { "epoch": 2.3082678638234193, "grad_norm": 0.19860711693763733, "learning_rate": 3.503744203343026e-05, "loss": 0.0168, "step": 6170 }, { "epoch": 2.3120089786756455, "grad_norm": 0.26660144329071045, "learning_rate": 3.487975428157318e-05, "loss": 0.017, "step": 6180 }, { "epoch": 2.315750093527871, "grad_norm": 0.16718719899654388, "learning_rate": 3.472223188230083e-05, "loss": 0.0187, "step": 6190 }, { "epoch": 2.3194912083800974, "grad_norm": 0.16757002472877502, "learning_rate": 3.4564876558252866e-05, "loss": 0.0174, "step": 6200 }, { "epoch": 2.323232323232323, "grad_norm": 0.18706180155277252, "learning_rate": 3.440769003024195e-05, "loss": 0.0162, "step": 6210 }, { "epoch": 2.3269734380845493, "grad_norm": 0.16543851792812347, "learning_rate": 3.425067401723477e-05, "loss": 0.0198, "step": 6220 }, { "epoch": 2.330714552936775, "grad_norm": 0.3040480613708496, "learning_rate": 3.409383023633325e-05, "loss": 0.0175, "step": 6230 }, { "epoch": 2.334455667789001, "grad_norm": 0.2680160403251648, "learning_rate": 3.3937160402755894e-05, "loss": 0.0151, "step": 6240 }, { "epoch": 2.3381967826412273, "grad_norm": 0.23572330176830292, "learning_rate": 3.378066622981885e-05, "loss": 0.0185, "step": 6250 }, { "epoch": 2.341937897493453, "grad_norm": 0.2043328732252121, "learning_rate": 3.362434942891738e-05, "loss": 0.0189, "step": 6260 }, { "epoch": 2.3456790123456788, "grad_norm": 0.2374141365289688, "learning_rate": 3.346821170950693e-05, "loss": 0.0154, "step": 6270 }, { "epoch": 2.349420127197905, "grad_norm": 0.3297994136810303, "learning_rate": 3.3312254779084585e-05, "loss": 0.017, "step": 6280 }, { "epoch": 2.353161242050131, "grad_norm": 0.43878716230392456, "learning_rate": 3.315648034317039e-05, "loss": 0.0205, "step": 6290 }, { "epoch": 2.356902356902357, "grad_norm": 0.3108702600002289, "learning_rate": 3.3000890105288564e-05, "loss": 0.0142, "step": 6300 }, { "epoch": 2.360643471754583, "grad_norm": 0.3650645911693573, "learning_rate": 3.284548576694908e-05, "loss": 0.0177, "step": 6310 }, { "epoch": 2.3643845866068087, "grad_norm": 0.2159041315317154, "learning_rate": 3.2690269027628815e-05, "loss": 0.0154, "step": 6320 }, { "epoch": 2.368125701459035, "grad_norm": 0.15692351758480072, "learning_rate": 3.253524158475324e-05, "loss": 0.0168, "step": 6330 }, { "epoch": 2.3718668163112606, "grad_norm": 0.14521300792694092, "learning_rate": 3.238040513367757e-05, "loss": 0.0175, "step": 6340 }, { "epoch": 2.375607931163487, "grad_norm": 0.20541329681873322, "learning_rate": 3.222576136766843e-05, "loss": 0.0153, "step": 6350 }, { "epoch": 2.3793490460157125, "grad_norm": 0.19821497797966003, "learning_rate": 3.2071311977885324e-05, "loss": 0.0176, "step": 6360 }, { "epoch": 2.3830901608679387, "grad_norm": 0.3472003936767578, "learning_rate": 3.191705865336197e-05, "loss": 0.0178, "step": 6370 }, { "epoch": 2.386831275720165, "grad_norm": 0.2596975862979889, "learning_rate": 3.1763003080988075e-05, "loss": 0.0163, "step": 6380 }, { "epoch": 2.3905723905723906, "grad_norm": 0.16466554999351501, "learning_rate": 3.160914694549063e-05, "loss": 0.0193, "step": 6390 }, { "epoch": 2.3943135054246163, "grad_norm": 0.21997660398483276, "learning_rate": 3.145549192941573e-05, "loss": 0.0191, "step": 6400 }, { "epoch": 2.3980546202768425, "grad_norm": 0.25570929050445557, "learning_rate": 3.130203971310999e-05, "loss": 0.0183, "step": 6410 }, { "epoch": 2.4017957351290686, "grad_norm": 0.1411362588405609, "learning_rate": 3.114879197470225e-05, "loss": 0.0144, "step": 6420 }, { "epoch": 2.4055368499812944, "grad_norm": 0.20954521000385284, "learning_rate": 3.0995750390085285e-05, "loss": 0.0169, "step": 6430 }, { "epoch": 2.4092779648335205, "grad_norm": 0.30015450716018677, "learning_rate": 3.084291663289728e-05, "loss": 0.0169, "step": 6440 }, { "epoch": 2.4130190796857462, "grad_norm": 0.15651580691337585, "learning_rate": 3.069029237450375e-05, "loss": 0.016, "step": 6450 }, { "epoch": 2.4167601945379724, "grad_norm": 0.32543665170669556, "learning_rate": 3.053787928397911e-05, "loss": 0.0153, "step": 6460 }, { "epoch": 2.420501309390198, "grad_norm": 0.46803927421569824, "learning_rate": 3.0385679028088526e-05, "loss": 0.0161, "step": 6470 }, { "epoch": 2.4242424242424243, "grad_norm": 0.16482849419116974, "learning_rate": 3.023369327126959e-05, "loss": 0.0147, "step": 6480 }, { "epoch": 2.42798353909465, "grad_norm": 0.1604306846857071, "learning_rate": 3.0081923675614198e-05, "loss": 0.0135, "step": 6490 }, { "epoch": 2.431724653946876, "grad_norm": 0.2500206232070923, "learning_rate": 2.993037190085034e-05, "loss": 0.0164, "step": 6500 }, { "epoch": 2.4354657687991024, "grad_norm": 0.2318236529827118, "learning_rate": 2.977903960432392e-05, "loss": 0.0168, "step": 6510 }, { "epoch": 2.439206883651328, "grad_norm": 0.26150035858154297, "learning_rate": 2.9627928440980722e-05, "loss": 0.0176, "step": 6520 }, { "epoch": 2.442947998503554, "grad_norm": 0.20711714029312134, "learning_rate": 2.9477040063348183e-05, "loss": 0.0195, "step": 6530 }, { "epoch": 2.44668911335578, "grad_norm": 0.18188390135765076, "learning_rate": 2.9326376121517456e-05, "loss": 0.0144, "step": 6540 }, { "epoch": 2.450430228208006, "grad_norm": 0.1919107586145401, "learning_rate": 2.9175938263125236e-05, "loss": 0.0147, "step": 6550 }, { "epoch": 2.454171343060232, "grad_norm": 0.24911712110042572, "learning_rate": 2.9025728133335873e-05, "loss": 0.0174, "step": 6560 }, { "epoch": 2.457912457912458, "grad_norm": 0.22733992338180542, "learning_rate": 2.8875747374823288e-05, "loss": 0.019, "step": 6570 }, { "epoch": 2.4616535727646838, "grad_norm": 0.2578478157520294, "learning_rate": 2.872599762775298e-05, "loss": 0.0186, "step": 6580 }, { "epoch": 2.46539468761691, "grad_norm": 0.1725238561630249, "learning_rate": 2.857648052976425e-05, "loss": 0.0135, "step": 6590 }, { "epoch": 2.4691358024691357, "grad_norm": 0.27192002534866333, "learning_rate": 2.8427197715952047e-05, "loss": 0.0151, "step": 6600 }, { "epoch": 2.472876917321362, "grad_norm": 0.21206064522266388, "learning_rate": 2.8278150818849393e-05, "loss": 0.013, "step": 6610 }, { "epoch": 2.4766180321735876, "grad_norm": 0.3139741122722626, "learning_rate": 2.812934146840922e-05, "loss": 0.0142, "step": 6620 }, { "epoch": 2.4803591470258137, "grad_norm": 0.22338928282260895, "learning_rate": 2.7980771291986764e-05, "loss": 0.0165, "step": 6630 }, { "epoch": 2.48410026187804, "grad_norm": 0.21458615362644196, "learning_rate": 2.783244191432167e-05, "loss": 0.0161, "step": 6640 }, { "epoch": 2.4878413767302656, "grad_norm": 0.24410220980644226, "learning_rate": 2.768435495752022e-05, "loss": 0.0131, "step": 6650 }, { "epoch": 2.4915824915824913, "grad_norm": 0.23939315974712372, "learning_rate": 2.753651204103771e-05, "loss": 0.0156, "step": 6660 }, { "epoch": 2.4953236064347175, "grad_norm": 0.17102040350437164, "learning_rate": 2.7388914781660523e-05, "loss": 0.0162, "step": 6670 }, { "epoch": 2.4990647212869437, "grad_norm": 0.28020262718200684, "learning_rate": 2.7241564793488693e-05, "loss": 0.0182, "step": 6680 }, { "epoch": 2.5028058361391694, "grad_norm": 0.20062921941280365, "learning_rate": 2.7094463687918037e-05, "loss": 0.0168, "step": 6690 }, { "epoch": 2.5065469509913956, "grad_norm": 0.32931846380233765, "learning_rate": 2.694761307362268e-05, "loss": 0.0174, "step": 6700 }, { "epoch": 2.5102880658436213, "grad_norm": 0.21541456878185272, "learning_rate": 2.6801014556537467e-05, "loss": 0.017, "step": 6710 }, { "epoch": 2.5140291806958475, "grad_norm": 0.3027949631214142, "learning_rate": 2.6654669739840243e-05, "loss": 0.0186, "step": 6720 }, { "epoch": 2.517770295548073, "grad_norm": 0.32505419850349426, "learning_rate": 2.650858022393451e-05, "loss": 0.0185, "step": 6730 }, { "epoch": 2.5215114104002994, "grad_norm": 0.310419499874115, "learning_rate": 2.6362747606431747e-05, "loss": 0.0185, "step": 6740 }, { "epoch": 2.525252525252525, "grad_norm": 0.30839967727661133, "learning_rate": 2.6217173482134172e-05, "loss": 0.0138, "step": 6750 }, { "epoch": 2.5289936401047513, "grad_norm": 0.1608007848262787, "learning_rate": 2.6071859443017044e-05, "loss": 0.0121, "step": 6760 }, { "epoch": 2.5327347549569774, "grad_norm": 0.23935818672180176, "learning_rate": 2.5926807078211414e-05, "loss": 0.014, "step": 6770 }, { "epoch": 2.536475869809203, "grad_norm": 0.32283279299736023, "learning_rate": 2.5782017973986728e-05, "loss": 0.0157, "step": 6780 }, { "epoch": 2.540216984661429, "grad_norm": 0.1547023206949234, "learning_rate": 2.5637493713733374e-05, "loss": 0.0162, "step": 6790 }, { "epoch": 2.543958099513655, "grad_norm": 0.17620313167572021, "learning_rate": 2.549323587794559e-05, "loss": 0.0182, "step": 6800 }, { "epoch": 2.547699214365881, "grad_norm": 0.20630207657814026, "learning_rate": 2.5349246044203895e-05, "loss": 0.016, "step": 6810 }, { "epoch": 2.551440329218107, "grad_norm": 0.21221694350242615, "learning_rate": 2.520552578715808e-05, "loss": 0.0115, "step": 6820 }, { "epoch": 2.555181444070333, "grad_norm": 0.23569606244564056, "learning_rate": 2.506207667850981e-05, "loss": 0.0136, "step": 6830 }, { "epoch": 2.558922558922559, "grad_norm": 0.20318588614463806, "learning_rate": 2.4918900286995555e-05, "loss": 0.0123, "step": 6840 }, { "epoch": 2.562663673774785, "grad_norm": 0.3156757056713104, "learning_rate": 2.4775998178369458e-05, "loss": 0.0138, "step": 6850 }, { "epoch": 2.5664047886270107, "grad_norm": 0.22016100585460663, "learning_rate": 2.4633371915386017e-05, "loss": 0.0151, "step": 6860 }, { "epoch": 2.570145903479237, "grad_norm": 0.22827444970607758, "learning_rate": 2.4491023057783235e-05, "loss": 0.0157, "step": 6870 }, { "epoch": 2.5738870183314626, "grad_norm": 0.32534608244895935, "learning_rate": 2.4348953162265375e-05, "loss": 0.0163, "step": 6880 }, { "epoch": 2.5776281331836888, "grad_norm": 0.18326835334300995, "learning_rate": 2.420716378248607e-05, "loss": 0.016, "step": 6890 }, { "epoch": 2.581369248035915, "grad_norm": 0.14346428215503693, "learning_rate": 2.4065656469031266e-05, "loss": 0.0127, "step": 6900 }, { "epoch": 2.5851103628881407, "grad_norm": 0.20246578752994537, "learning_rate": 2.3924432769402268e-05, "loss": 0.0151, "step": 6910 }, { "epoch": 2.5888514777403664, "grad_norm": 0.16612553596496582, "learning_rate": 2.3783494227998844e-05, "loss": 0.0154, "step": 6920 }, { "epoch": 2.5925925925925926, "grad_norm": 0.1964840292930603, "learning_rate": 2.3642842386102264e-05, "loss": 0.0118, "step": 6930 }, { "epoch": 2.5963337074448187, "grad_norm": 0.24009421467781067, "learning_rate": 2.3502478781858567e-05, "loss": 0.0117, "step": 6940 }, { "epoch": 2.6000748222970445, "grad_norm": 0.1698220670223236, "learning_rate": 2.3362404950261628e-05, "loss": 0.0154, "step": 6950 }, { "epoch": 2.6038159371492706, "grad_norm": 0.22486582398414612, "learning_rate": 2.3222622423136458e-05, "loss": 0.0136, "step": 6960 }, { "epoch": 2.6075570520014963, "grad_norm": 0.2081894725561142, "learning_rate": 2.3083132729122332e-05, "loss": 0.0154, "step": 6970 }, { "epoch": 2.6112981668537225, "grad_norm": 0.24647600948810577, "learning_rate": 2.294393739365621e-05, "loss": 0.0167, "step": 6980 }, { "epoch": 2.6150392817059482, "grad_norm": 0.21671847999095917, "learning_rate": 2.2805037938956e-05, "loss": 0.014, "step": 6990 }, { "epoch": 2.6187803965581744, "grad_norm": 0.24416930973529816, "learning_rate": 2.266643588400386e-05, "loss": 0.0143, "step": 7000 }, { "epoch": 2.6225215114104, "grad_norm": 0.2721308469772339, "learning_rate": 2.252813274452969e-05, "loss": 0.0166, "step": 7010 }, { "epoch": 2.6262626262626263, "grad_norm": 0.3171102702617645, "learning_rate": 2.2390130032994427e-05, "loss": 0.014, "step": 7020 }, { "epoch": 2.6300037411148525, "grad_norm": 0.3358794152736664, "learning_rate": 2.2252429258573633e-05, "loss": 0.0144, "step": 7030 }, { "epoch": 2.633744855967078, "grad_norm": 0.18865622580051422, "learning_rate": 2.2115031927140904e-05, "loss": 0.015, "step": 7040 }, { "epoch": 2.637485970819304, "grad_norm": 0.20533905923366547, "learning_rate": 2.1977939541251463e-05, "loss": 0.0214, "step": 7050 }, { "epoch": 2.64122708567153, "grad_norm": 0.20112332701683044, "learning_rate": 2.1841153600125684e-05, "loss": 0.0165, "step": 7060 }, { "epoch": 2.6449682005237563, "grad_norm": 0.2379152625799179, "learning_rate": 2.170467559963267e-05, "loss": 0.0145, "step": 7070 }, { "epoch": 2.648709315375982, "grad_norm": 0.2994200885295868, "learning_rate": 2.1568507032273982e-05, "loss": 0.0116, "step": 7080 }, { "epoch": 2.652450430228208, "grad_norm": 0.17949609458446503, "learning_rate": 2.1432649387167264e-05, "loss": 0.0132, "step": 7090 }, { "epoch": 2.656191545080434, "grad_norm": 0.5923390984535217, "learning_rate": 2.1297104150029973e-05, "loss": 0.0162, "step": 7100 }, { "epoch": 2.65993265993266, "grad_norm": 0.21756808459758759, "learning_rate": 2.116187280316307e-05, "loss": 0.0139, "step": 7110 }, { "epoch": 2.6636737747848858, "grad_norm": 0.26974067091941833, "learning_rate": 2.1026956825434908e-05, "loss": 0.0157, "step": 7120 }, { "epoch": 2.667414889637112, "grad_norm": 0.16553683578968048, "learning_rate": 2.0892357692265017e-05, "loss": 0.0149, "step": 7130 }, { "epoch": 2.6711560044893377, "grad_norm": 0.19363921880722046, "learning_rate": 2.0758076875607947e-05, "loss": 0.0145, "step": 7140 }, { "epoch": 2.674897119341564, "grad_norm": 0.1948203146457672, "learning_rate": 2.0624115843937207e-05, "loss": 0.0163, "step": 7150 }, { "epoch": 2.67863823419379, "grad_norm": 0.17585095763206482, "learning_rate": 2.0490476062229157e-05, "loss": 0.015, "step": 7160 }, { "epoch": 2.6823793490460157, "grad_norm": 0.2775144577026367, "learning_rate": 2.035715899194704e-05, "loss": 0.0153, "step": 7170 }, { "epoch": 2.6861204638982414, "grad_norm": 0.19702889025211334, "learning_rate": 2.022416609102499e-05, "loss": 0.013, "step": 7180 }, { "epoch": 2.6898615787504676, "grad_norm": 0.19541750848293304, "learning_rate": 2.009149881385205e-05, "loss": 0.0192, "step": 7190 }, { "epoch": 2.6936026936026938, "grad_norm": 0.2100462168455124, "learning_rate": 1.995915861125634e-05, "loss": 0.0146, "step": 7200 }, { "epoch": 2.6973438084549195, "grad_norm": 0.24915558099746704, "learning_rate": 1.9827146930489065e-05, "loss": 0.012, "step": 7210 }, { "epoch": 2.7010849233071457, "grad_norm": 0.18870487809181213, "learning_rate": 1.9695465215208848e-05, "loss": 0.0169, "step": 7220 }, { "epoch": 2.7048260381593714, "grad_norm": 0.22451074421405792, "learning_rate": 1.9564114905465813e-05, "loss": 0.0123, "step": 7230 }, { "epoch": 2.7085671530115976, "grad_norm": 0.20154976844787598, "learning_rate": 1.9433097437685936e-05, "loss": 0.0154, "step": 7240 }, { "epoch": 2.7123082678638233, "grad_norm": 0.24041222035884857, "learning_rate": 1.930241424465521e-05, "loss": 0.0127, "step": 7250 }, { "epoch": 2.7160493827160495, "grad_norm": 0.25206032395362854, "learning_rate": 1.9172066755504115e-05, "loss": 0.0126, "step": 7260 }, { "epoch": 2.719790497568275, "grad_norm": 0.24070556461811066, "learning_rate": 1.9042056395691914e-05, "loss": 0.0111, "step": 7270 }, { "epoch": 2.7235316124205013, "grad_norm": 0.17949923872947693, "learning_rate": 1.8912384586991066e-05, "loss": 0.015, "step": 7280 }, { "epoch": 2.7272727272727275, "grad_norm": 0.27001944184303284, "learning_rate": 1.8783052747471717e-05, "loss": 0.013, "step": 7290 }, { "epoch": 2.7310138421249532, "grad_norm": 0.15652543306350708, "learning_rate": 1.865406229148611e-05, "loss": 0.017, "step": 7300 }, { "epoch": 2.734754956977179, "grad_norm": 0.21091312170028687, "learning_rate": 1.8525414629653233e-05, "loss": 0.015, "step": 7310 }, { "epoch": 2.738496071829405, "grad_norm": 0.22678574919700623, "learning_rate": 1.8397111168843255e-05, "loss": 0.0124, "step": 7320 }, { "epoch": 2.7422371866816313, "grad_norm": 0.1798311024904251, "learning_rate": 1.8269153312162323e-05, "loss": 0.0131, "step": 7330 }, { "epoch": 2.745978301533857, "grad_norm": 0.19291439652442932, "learning_rate": 1.8141542458937054e-05, "loss": 0.0121, "step": 7340 }, { "epoch": 2.749719416386083, "grad_norm": 0.22950465977191925, "learning_rate": 1.8014280004699268e-05, "loss": 0.0116, "step": 7350 }, { "epoch": 2.753460531238309, "grad_norm": 0.13598524034023285, "learning_rate": 1.788736734117078e-05, "loss": 0.0132, "step": 7360 }, { "epoch": 2.757201646090535, "grad_norm": 0.30417415499687195, "learning_rate": 1.7760805856248152e-05, "loss": 0.0147, "step": 7370 }, { "epoch": 2.760942760942761, "grad_norm": 0.22558195888996124, "learning_rate": 1.7634596933987518e-05, "loss": 0.0135, "step": 7380 }, { "epoch": 2.764683875794987, "grad_norm": 0.17475451529026031, "learning_rate": 1.7508741954589404e-05, "loss": 0.015, "step": 7390 }, { "epoch": 2.7684249906472127, "grad_norm": 0.15876902639865875, "learning_rate": 1.7383242294383717e-05, "loss": 0.0149, "step": 7400 }, { "epoch": 2.772166105499439, "grad_norm": 0.19047552347183228, "learning_rate": 1.7258099325814632e-05, "loss": 0.0113, "step": 7410 }, { "epoch": 2.775907220351665, "grad_norm": 0.2459321767091751, "learning_rate": 1.7133314417425594e-05, "loss": 0.0142, "step": 7420 }, { "epoch": 2.7796483352038908, "grad_norm": 0.1472325176000595, "learning_rate": 1.7008888933844408e-05, "loss": 0.0128, "step": 7430 }, { "epoch": 2.7833894500561165, "grad_norm": 0.17218124866485596, "learning_rate": 1.6884824235768172e-05, "loss": 0.0165, "step": 7440 }, { "epoch": 2.7871305649083427, "grad_norm": 0.22930486500263214, "learning_rate": 1.6761121679948592e-05, "loss": 0.0123, "step": 7450 }, { "epoch": 2.790871679760569, "grad_norm": 0.31197240948677063, "learning_rate": 1.663778261917695e-05, "loss": 0.0142, "step": 7460 }, { "epoch": 2.7946127946127945, "grad_norm": 0.2777099311351776, "learning_rate": 1.651480840226952e-05, "loss": 0.0131, "step": 7470 }, { "epoch": 2.7983539094650207, "grad_norm": 0.3287126123905182, "learning_rate": 1.639220037405258e-05, "loss": 0.015, "step": 7480 }, { "epoch": 2.8020950243172464, "grad_norm": 0.1915455460548401, "learning_rate": 1.6269959875347906e-05, "loss": 0.0149, "step": 7490 }, { "epoch": 2.8058361391694726, "grad_norm": 0.16787977516651154, "learning_rate": 1.614808824295802e-05, "loss": 0.0136, "step": 7500 }, { "epoch": 2.8095772540216983, "grad_norm": 0.13508717715740204, "learning_rate": 1.602658680965152e-05, "loss": 0.0118, "step": 7510 }, { "epoch": 2.8133183688739245, "grad_norm": 0.18300871551036835, "learning_rate": 1.5905456904148686e-05, "loss": 0.0165, "step": 7520 }, { "epoch": 2.8170594837261502, "grad_norm": 0.1492556631565094, "learning_rate": 1.57846998511067e-05, "loss": 0.0157, "step": 7530 }, { "epoch": 2.8208005985783764, "grad_norm": 0.1677132397890091, "learning_rate": 1.566431697110538e-05, "loss": 0.0127, "step": 7540 }, { "epoch": 2.8245417134306026, "grad_norm": 0.2438063621520996, "learning_rate": 1.554430958063259e-05, "loss": 0.0137, "step": 7550 }, { "epoch": 2.8282828282828283, "grad_norm": 0.22230641543865204, "learning_rate": 1.5424678992069912e-05, "loss": 0.0114, "step": 7560 }, { "epoch": 2.832023943135054, "grad_norm": 0.19847676157951355, "learning_rate": 1.5305426513678362e-05, "loss": 0.0122, "step": 7570 }, { "epoch": 2.83576505798728, "grad_norm": 0.18906627595424652, "learning_rate": 1.518655344958388e-05, "loss": 0.0152, "step": 7580 }, { "epoch": 2.8395061728395063, "grad_norm": 0.16126906871795654, "learning_rate": 1.5068061099763275e-05, "loss": 0.0136, "step": 7590 }, { "epoch": 2.843247287691732, "grad_norm": 0.18800556659698486, "learning_rate": 1.494995076002988e-05, "loss": 0.015, "step": 7600 }, { "epoch": 2.8469884025439582, "grad_norm": 0.1715501844882965, "learning_rate": 1.4832223722019456e-05, "loss": 0.0114, "step": 7610 }, { "epoch": 2.850729517396184, "grad_norm": 0.18554693460464478, "learning_rate": 1.4714881273176035e-05, "loss": 0.0114, "step": 7620 }, { "epoch": 2.85447063224841, "grad_norm": 0.195853129029274, "learning_rate": 1.4597924696737835e-05, "loss": 0.0139, "step": 7630 }, { "epoch": 2.858211747100636, "grad_norm": 0.1509513556957245, "learning_rate": 1.4481355271723252e-05, "loss": 0.0144, "step": 7640 }, { "epoch": 2.861952861952862, "grad_norm": 0.15556424856185913, "learning_rate": 1.4365174272916809e-05, "loss": 0.0168, "step": 7650 }, { "epoch": 2.8656939768050878, "grad_norm": 0.1636345535516739, "learning_rate": 1.4249382970855319e-05, "loss": 0.0128, "step": 7660 }, { "epoch": 2.869435091657314, "grad_norm": 0.15965251624584198, "learning_rate": 1.4133982631813903e-05, "loss": 0.0121, "step": 7670 }, { "epoch": 2.87317620650954, "grad_norm": 0.1975402683019638, "learning_rate": 1.4018974517792194e-05, "loss": 0.0125, "step": 7680 }, { "epoch": 2.876917321361766, "grad_norm": 0.15535545349121094, "learning_rate": 1.390435988650048e-05, "loss": 0.0118, "step": 7690 }, { "epoch": 2.8806584362139915, "grad_norm": 0.19011558592319489, "learning_rate": 1.3790139991346006e-05, "loss": 0.0113, "step": 7700 }, { "epoch": 2.8843995510662177, "grad_norm": 0.2678299844264984, "learning_rate": 1.367631608141926e-05, "loss": 0.0134, "step": 7710 }, { "epoch": 2.888140665918444, "grad_norm": 0.20724204182624817, "learning_rate": 1.3562889401480278e-05, "loss": 0.0134, "step": 7720 }, { "epoch": 2.8918817807706696, "grad_norm": 0.27841416001319885, "learning_rate": 1.3449861191945074e-05, "loss": 0.0151, "step": 7730 }, { "epoch": 2.8956228956228958, "grad_norm": 0.2686276435852051, "learning_rate": 1.3337232688872009e-05, "loss": 0.0145, "step": 7740 }, { "epoch": 2.8993640104751215, "grad_norm": 0.12801076471805573, "learning_rate": 1.3225005123948364e-05, "loss": 0.0109, "step": 7750 }, { "epoch": 2.9031051253273477, "grad_norm": 0.18463996052742004, "learning_rate": 1.311317972447681e-05, "loss": 0.0122, "step": 7760 }, { "epoch": 2.9068462401795734, "grad_norm": 0.12304924428462982, "learning_rate": 1.3001757713361996e-05, "loss": 0.0113, "step": 7770 }, { "epoch": 2.9105873550317996, "grad_norm": 0.17583929002285004, "learning_rate": 1.2890740309097204e-05, "loss": 0.0152, "step": 7780 }, { "epoch": 2.9143284698840253, "grad_norm": 0.19922421872615814, "learning_rate": 1.2780128725750944e-05, "loss": 0.0116, "step": 7790 }, { "epoch": 2.9180695847362514, "grad_norm": 0.11062078922986984, "learning_rate": 1.266992417295379e-05, "loss": 0.0118, "step": 7800 }, { "epoch": 2.9218106995884776, "grad_norm": 0.1883121281862259, "learning_rate": 1.2560127855885073e-05, "loss": 0.0128, "step": 7810 }, { "epoch": 2.9255518144407033, "grad_norm": 0.22456538677215576, "learning_rate": 1.2450740975259745e-05, "loss": 0.0138, "step": 7820 }, { "epoch": 2.929292929292929, "grad_norm": 0.2607845067977905, "learning_rate": 1.234176472731517e-05, "loss": 0.0168, "step": 7830 }, { "epoch": 2.9330340441451552, "grad_norm": 0.14727471768856049, "learning_rate": 1.2233200303798158e-05, "loss": 0.0129, "step": 7840 }, { "epoch": 2.9367751589973814, "grad_norm": 0.141793355345726, "learning_rate": 1.2125048891951846e-05, "loss": 0.0124, "step": 7850 }, { "epoch": 2.940516273849607, "grad_norm": 0.1903418004512787, "learning_rate": 1.2017311674502745e-05, "loss": 0.0115, "step": 7860 }, { "epoch": 2.9442573887018333, "grad_norm": 0.2796107232570648, "learning_rate": 1.1909989829647822e-05, "loss": 0.013, "step": 7870 }, { "epoch": 2.947998503554059, "grad_norm": 0.10285747051239014, "learning_rate": 1.1803084531041553e-05, "loss": 0.0137, "step": 7880 }, { "epoch": 2.951739618406285, "grad_norm": 0.24880318343639374, "learning_rate": 1.1696596947783162e-05, "loss": 0.0133, "step": 7890 }, { "epoch": 2.955480733258511, "grad_norm": 0.13212153315544128, "learning_rate": 1.1590528244403803e-05, "loss": 0.0109, "step": 7900 }, { "epoch": 2.959221848110737, "grad_norm": 0.6443137526512146, "learning_rate": 1.148487958085382e-05, "loss": 0.0144, "step": 7910 }, { "epoch": 2.962962962962963, "grad_norm": 0.1918213814496994, "learning_rate": 1.1379652112490086e-05, "loss": 0.0104, "step": 7920 }, { "epoch": 2.966704077815189, "grad_norm": 0.19077420234680176, "learning_rate": 1.1274846990063315e-05, "loss": 0.0113, "step": 7930 }, { "epoch": 2.970445192667415, "grad_norm": 0.2022288739681244, "learning_rate": 1.117046535970554e-05, "loss": 0.0154, "step": 7940 }, { "epoch": 2.974186307519641, "grad_norm": 0.2173662930727005, "learning_rate": 1.106650836291755e-05, "loss": 0.0175, "step": 7950 }, { "epoch": 2.9779274223718666, "grad_norm": 0.2489825338125229, "learning_rate": 1.0962977136556418e-05, "loss": 0.0176, "step": 7960 }, { "epoch": 2.9816685372240928, "grad_norm": 0.2380887120962143, "learning_rate": 1.0859872812823024e-05, "loss": 0.0135, "step": 7970 }, { "epoch": 2.985409652076319, "grad_norm": 0.24386374652385712, "learning_rate": 1.0757196519249747e-05, "loss": 0.014, "step": 7980 }, { "epoch": 2.9891507669285446, "grad_norm": 0.21567919850349426, "learning_rate": 1.0654949378688077e-05, "loss": 0.0166, "step": 7990 }, { "epoch": 2.992891881780771, "grad_norm": 0.1395067274570465, "learning_rate": 1.0553132509296376e-05, "loss": 0.0144, "step": 8000 }, { "epoch": 2.9966329966329965, "grad_norm": 0.22245754301548004, "learning_rate": 1.0451747024527613e-05, "loss": 0.0128, "step": 8010 }, { "epoch": 3.0003741114852227, "grad_norm": 0.20228365063667297, "learning_rate": 1.0350794033117189e-05, "loss": 0.0126, "step": 8020 }, { "epoch": 3.0041152263374484, "grad_norm": 0.15564678609371185, "learning_rate": 1.0250274639070856e-05, "loss": 0.0133, "step": 8030 }, { "epoch": 3.0078563411896746, "grad_norm": 0.1504611372947693, "learning_rate": 1.0150189941652599e-05, "loss": 0.0108, "step": 8040 }, { "epoch": 3.0115974560419003, "grad_norm": 0.14716286957263947, "learning_rate": 1.0050541035372635e-05, "loss": 0.0107, "step": 8050 }, { "epoch": 3.0153385708941265, "grad_norm": 0.1882041096687317, "learning_rate": 9.951329009975458e-06, "loss": 0.0123, "step": 8060 }, { "epoch": 3.019079685746352, "grad_norm": 0.21221651136875153, "learning_rate": 9.852554950427845e-06, "loss": 0.0121, "step": 8070 }, { "epoch": 3.0228208005985784, "grad_norm": 0.3421564996242523, "learning_rate": 9.754219936907105e-06, "loss": 0.012, "step": 8080 }, { "epoch": 3.0265619154508046, "grad_norm": 0.14587301015853882, "learning_rate": 9.656325044789194e-06, "loss": 0.0089, "step": 8090 }, { "epoch": 3.0303030303030303, "grad_norm": 0.09474743157625198, "learning_rate": 9.55887134463697e-06, "loss": 0.0104, "step": 8100 }, { "epoch": 3.0340441451552564, "grad_norm": 0.32023847103118896, "learning_rate": 9.461859902188475e-06, "loss": 0.0137, "step": 8110 }, { "epoch": 3.037785260007482, "grad_norm": 0.29455092549324036, "learning_rate": 9.365291778345303e-06, "loss": 0.0123, "step": 8120 }, { "epoch": 3.0415263748597083, "grad_norm": 0.32340162992477417, "learning_rate": 9.269168029160991e-06, "loss": 0.013, "step": 8130 }, { "epoch": 3.045267489711934, "grad_norm": 0.21549555659294128, "learning_rate": 9.173489705829447e-06, "loss": 0.0104, "step": 8140 }, { "epoch": 3.0490086045641602, "grad_norm": 0.20175765454769135, "learning_rate": 9.078257854673516e-06, "loss": 0.0116, "step": 8150 }, { "epoch": 3.052749719416386, "grad_norm": 0.40521299839019775, "learning_rate": 8.983473517133429e-06, "loss": 0.0138, "step": 8160 }, { "epoch": 3.056490834268612, "grad_norm": 0.1355249136686325, "learning_rate": 8.889137729755537e-06, "loss": 0.0108, "step": 8170 }, { "epoch": 3.060231949120838, "grad_norm": 0.22012631595134735, "learning_rate": 8.79525152418087e-06, "loss": 0.015, "step": 8180 }, { "epoch": 3.063973063973064, "grad_norm": 0.23543012142181396, "learning_rate": 8.701815927133961e-06, "loss": 0.0137, "step": 8190 }, { "epoch": 3.0677141788252897, "grad_norm": 0.14043422043323517, "learning_rate": 8.608831960411534e-06, "loss": 0.0133, "step": 8200 }, { "epoch": 3.071455293677516, "grad_norm": 0.23171964287757874, "learning_rate": 8.516300640871321e-06, "loss": 0.0126, "step": 8210 }, { "epoch": 3.075196408529742, "grad_norm": 0.17311547696590424, "learning_rate": 8.424222980421038e-06, "loss": 0.0127, "step": 8220 }, { "epoch": 3.078937523381968, "grad_norm": 0.13064007461071014, "learning_rate": 8.332599986007184e-06, "loss": 0.0144, "step": 8230 }, { "epoch": 3.082678638234194, "grad_norm": 0.09867999702692032, "learning_rate": 8.241432659604203e-06, "loss": 0.0085, "step": 8240 }, { "epoch": 3.0864197530864197, "grad_norm": 0.21161766350269318, "learning_rate": 8.150721998203331e-06, "loss": 0.01, "step": 8250 }, { "epoch": 3.090160867938646, "grad_norm": 0.12894974648952484, "learning_rate": 8.06046899380184e-06, "loss": 0.0097, "step": 8260 }, { "epoch": 3.0939019827908716, "grad_norm": 0.2258317470550537, "learning_rate": 7.970674633392133e-06, "loss": 0.0123, "step": 8270 }, { "epoch": 3.0976430976430978, "grad_norm": 0.16293363273143768, "learning_rate": 7.881339898950924e-06, "loss": 0.0117, "step": 8280 }, { "epoch": 3.1013842124953235, "grad_norm": 0.20401722192764282, "learning_rate": 7.792465767428597e-06, "loss": 0.0121, "step": 8290 }, { "epoch": 3.1051253273475496, "grad_norm": 0.17369692027568817, "learning_rate": 7.704053210738376e-06, "loss": 0.0104, "step": 8300 }, { "epoch": 3.1088664421997754, "grad_norm": 0.10309801250696182, "learning_rate": 7.6161031957458494e-06, "loss": 0.0153, "step": 8310 }, { "epoch": 3.1126075570520015, "grad_norm": 0.24022147059440613, "learning_rate": 7.5286166842582605e-06, "loss": 0.0117, "step": 8320 }, { "epoch": 3.1163486719042273, "grad_norm": 0.2186022698879242, "learning_rate": 7.4415946330140814e-06, "loss": 0.0139, "step": 8330 }, { "epoch": 3.1200897867564534, "grad_norm": 0.10497766733169556, "learning_rate": 7.3550379936725644e-06, "loss": 0.0108, "step": 8340 }, { "epoch": 3.1238309016086796, "grad_norm": 0.17294737696647644, "learning_rate": 7.2689477128032035e-06, "loss": 0.0135, "step": 8350 }, { "epoch": 3.1275720164609053, "grad_norm": 0.11572030186653137, "learning_rate": 7.183324731875551e-06, "loss": 0.0121, "step": 8360 }, { "epoch": 3.1313131313131315, "grad_norm": 0.1874912828207016, "learning_rate": 7.098169987248782e-06, "loss": 0.0111, "step": 8370 }, { "epoch": 3.135054246165357, "grad_norm": 0.1388218104839325, "learning_rate": 7.013484410161553e-06, "loss": 0.012, "step": 8380 }, { "epoch": 3.1387953610175834, "grad_norm": 0.19207575917243958, "learning_rate": 6.92926892672176e-06, "loss": 0.0106, "step": 8390 }, { "epoch": 3.142536475869809, "grad_norm": 0.13874013721942902, "learning_rate": 6.845524457896446e-06, "loss": 0.0095, "step": 8400 }, { "epoch": 3.1462775907220353, "grad_norm": 0.13649015128612518, "learning_rate": 6.7622519195017165e-06, "loss": 0.0101, "step": 8410 }, { "epoch": 3.150018705574261, "grad_norm": 0.16018860042095184, "learning_rate": 6.679452222192684e-06, "loss": 0.0113, "step": 8420 }, { "epoch": 3.153759820426487, "grad_norm": 0.18968181312084198, "learning_rate": 6.597126271453579e-06, "loss": 0.0112, "step": 8430 }, { "epoch": 3.157500935278713, "grad_norm": 0.12014936655759811, "learning_rate": 6.51527496758782e-06, "loss": 0.0089, "step": 8440 }, { "epoch": 3.161242050130939, "grad_norm": 0.2412385493516922, "learning_rate": 6.433899205708155e-06, "loss": 0.0106, "step": 8450 }, { "epoch": 3.164983164983165, "grad_norm": 0.09179742634296417, "learning_rate": 6.352999875726856e-06, "loss": 0.01, "step": 8460 }, { "epoch": 3.168724279835391, "grad_norm": 0.15963038802146912, "learning_rate": 6.272577862346052e-06, "loss": 0.013, "step": 8470 }, { "epoch": 3.1724653946876167, "grad_norm": 0.3198035657405853, "learning_rate": 6.192634045047996e-06, "loss": 0.0108, "step": 8480 }, { "epoch": 3.176206509539843, "grad_norm": 0.16383133828639984, "learning_rate": 6.113169298085458e-06, "loss": 0.0173, "step": 8490 }, { "epoch": 3.179947624392069, "grad_norm": 0.17310111224651337, "learning_rate": 6.034184490472195e-06, "loss": 0.0102, "step": 8500 }, { "epoch": 3.1836887392442947, "grad_norm": 0.1703815758228302, "learning_rate": 5.955680485973386e-06, "loss": 0.0127, "step": 8510 }, { "epoch": 3.187429854096521, "grad_norm": 0.1699196696281433, "learning_rate": 5.877658143096265e-06, "loss": 0.0137, "step": 8520 }, { "epoch": 3.1911709689487466, "grad_norm": 0.0890703797340393, "learning_rate": 5.800118315080661e-06, "loss": 0.0111, "step": 8530 }, { "epoch": 3.194912083800973, "grad_norm": 0.15813036262989044, "learning_rate": 5.723061849889716e-06, "loss": 0.009, "step": 8540 }, { "epoch": 3.1986531986531985, "grad_norm": 0.19414351880550385, "learning_rate": 5.646489590200604e-06, "loss": 0.0115, "step": 8550 }, { "epoch": 3.2023943135054247, "grad_norm": 0.18250255286693573, "learning_rate": 5.570402373395256e-06, "loss": 0.0097, "step": 8560 }, { "epoch": 3.2061354283576504, "grad_norm": 0.23800674080848694, "learning_rate": 5.494801031551305e-06, "loss": 0.0121, "step": 8570 }, { "epoch": 3.2098765432098766, "grad_norm": 0.15510377287864685, "learning_rate": 5.41968639143291e-06, "loss": 0.0112, "step": 8580 }, { "epoch": 3.2136176580621023, "grad_norm": 0.14344389736652374, "learning_rate": 5.345059274481751e-06, "loss": 0.0089, "step": 8590 }, { "epoch": 3.2173587729143285, "grad_norm": 0.20855914056301117, "learning_rate": 5.270920496808002e-06, "loss": 0.0145, "step": 8600 }, { "epoch": 3.221099887766554, "grad_norm": 0.20587198436260223, "learning_rate": 5.1972708691814695e-06, "loss": 0.0122, "step": 8610 }, { "epoch": 3.2248410026187804, "grad_norm": 0.25085127353668213, "learning_rate": 5.124111197022674e-06, "loss": 0.0128, "step": 8620 }, { "epoch": 3.2285821174710065, "grad_norm": 0.1824440360069275, "learning_rate": 5.051442280394081e-06, "loss": 0.0114, "step": 8630 }, { "epoch": 3.2323232323232323, "grad_norm": 0.11182162910699844, "learning_rate": 4.979264913991322e-06, "loss": 0.0126, "step": 8640 }, { "epoch": 3.2360643471754584, "grad_norm": 0.16700823605060577, "learning_rate": 4.907579887134489e-06, "loss": 0.0147, "step": 8650 }, { "epoch": 3.239805462027684, "grad_norm": 0.19674766063690186, "learning_rate": 4.836387983759572e-06, "loss": 0.0111, "step": 8660 }, { "epoch": 3.2435465768799103, "grad_norm": 0.1505567729473114, "learning_rate": 4.765689982409816e-06, "loss": 0.0112, "step": 8670 }, { "epoch": 3.247287691732136, "grad_norm": 0.17502973973751068, "learning_rate": 4.695486656227233e-06, "loss": 0.014, "step": 8680 }, { "epoch": 3.251028806584362, "grad_norm": 0.18293088674545288, "learning_rate": 4.625778772944156e-06, "loss": 0.0132, "step": 8690 }, { "epoch": 3.254769921436588, "grad_norm": 0.13057301938533783, "learning_rate": 4.556567094874825e-06, "loss": 0.0117, "step": 8700 }, { "epoch": 3.258511036288814, "grad_norm": 0.11447414755821228, "learning_rate": 4.487852378907059e-06, "loss": 0.0101, "step": 8710 }, { "epoch": 3.2622521511410403, "grad_norm": 0.13413608074188232, "learning_rate": 4.419635376493986e-06, "loss": 0.0146, "step": 8720 }, { "epoch": 3.265993265993266, "grad_norm": 0.1693476140499115, "learning_rate": 4.351916833645825e-06, "loss": 0.0118, "step": 8730 }, { "epoch": 3.2697343808454917, "grad_norm": 0.21208976209163666, "learning_rate": 4.284697490921691e-06, "loss": 0.0119, "step": 8740 }, { "epoch": 3.273475495697718, "grad_norm": 0.10538821667432785, "learning_rate": 4.2179780834215585e-06, "loss": 0.0111, "step": 8750 }, { "epoch": 3.277216610549944, "grad_norm": 0.14154087007045746, "learning_rate": 4.151759340778178e-06, "loss": 0.0132, "step": 8760 }, { "epoch": 3.28095772540217, "grad_norm": 0.15282033383846283, "learning_rate": 4.086041987149109e-06, "loss": 0.0122, "step": 8770 }, { "epoch": 3.284698840254396, "grad_norm": 0.18356429040431976, "learning_rate": 4.020826741208811e-06, "loss": 0.0126, "step": 8780 }, { "epoch": 3.2884399551066217, "grad_norm": 0.14408963918685913, "learning_rate": 3.956114316140746e-06, "loss": 0.0133, "step": 8790 }, { "epoch": 3.292181069958848, "grad_norm": 0.187092587351799, "learning_rate": 3.891905419629643e-06, "loss": 0.0115, "step": 8800 }, { "epoch": 3.2959221848110736, "grad_norm": 0.12146936357021332, "learning_rate": 3.8282007538536946e-06, "loss": 0.0145, "step": 8810 }, { "epoch": 3.2996632996632997, "grad_norm": 0.19648513197898865, "learning_rate": 3.7650010154769265e-06, "loss": 0.0096, "step": 8820 }, { "epoch": 3.3034044145155255, "grad_norm": 0.23693928122520447, "learning_rate": 3.7023068956415608e-06, "loss": 0.0123, "step": 8830 }, { "epoch": 3.3071455293677516, "grad_norm": 0.12296415865421295, "learning_rate": 3.6401190799604303e-06, "loss": 0.0089, "step": 8840 }, { "epoch": 3.3108866442199774, "grad_norm": 0.15223371982574463, "learning_rate": 3.578438248509536e-06, "loss": 0.0096, "step": 8850 }, { "epoch": 3.3146277590722035, "grad_norm": 0.09198801219463348, "learning_rate": 3.5172650758205583e-06, "loss": 0.0127, "step": 8860 }, { "epoch": 3.3183688739244293, "grad_norm": 0.13911937177181244, "learning_rate": 3.45660023087353e-06, "loss": 0.01, "step": 8870 }, { "epoch": 3.3221099887766554, "grad_norm": 0.2076379954814911, "learning_rate": 3.3964443770894528e-06, "loss": 0.0134, "step": 8880 }, { "epoch": 3.3258511036288816, "grad_norm": 0.12881630659103394, "learning_rate": 3.3367981723231245e-06, "loss": 0.0095, "step": 8890 }, { "epoch": 3.3295922184811073, "grad_norm": 0.17935588955879211, "learning_rate": 3.2776622688558746e-06, "loss": 0.012, "step": 8900 }, { "epoch": 3.3333333333333335, "grad_norm": 0.11089276522397995, "learning_rate": 3.2190373133884677e-06, "loss": 0.0084, "step": 8910 }, { "epoch": 3.337074448185559, "grad_norm": 0.24297654628753662, "learning_rate": 3.1609239470340446e-06, "loss": 0.0115, "step": 8920 }, { "epoch": 3.3408155630377854, "grad_norm": 0.2520841062068939, "learning_rate": 3.1033228053110373e-06, "loss": 0.0127, "step": 8930 }, { "epoch": 3.344556677890011, "grad_norm": 0.13098332285881042, "learning_rate": 3.0462345181363314e-06, "loss": 0.0125, "step": 8940 }, { "epoch": 3.3482977927422373, "grad_norm": 0.2393638789653778, "learning_rate": 2.9896597098182654e-06, "loss": 0.0115, "step": 8950 }, { "epoch": 3.352038907594463, "grad_norm": 0.10311155021190643, "learning_rate": 2.933598999049891e-06, "loss": 0.0115, "step": 8960 }, { "epoch": 3.355780022446689, "grad_norm": 0.17939159274101257, "learning_rate": 2.8780529989021697e-06, "loss": 0.0105, "step": 8970 }, { "epoch": 3.359521137298915, "grad_norm": 0.22261027991771698, "learning_rate": 2.823022316817242e-06, "loss": 0.0121, "step": 8980 }, { "epoch": 3.363262252151141, "grad_norm": 0.15594719350337982, "learning_rate": 2.7685075546018456e-06, "loss": 0.0095, "step": 8990 }, { "epoch": 3.3670033670033668, "grad_norm": 0.1378454715013504, "learning_rate": 2.7145093084206598e-06, "loss": 0.0117, "step": 9000 }, { "epoch": 3.370744481855593, "grad_norm": 0.1606973558664322, "learning_rate": 2.661028168789892e-06, "loss": 0.0109, "step": 9010 }, { "epoch": 3.374485596707819, "grad_norm": 0.1344575732946396, "learning_rate": 2.6080647205706855e-06, "loss": 0.0086, "step": 9020 }, { "epoch": 3.378226711560045, "grad_norm": 0.09569799900054932, "learning_rate": 2.555619542962834e-06, "loss": 0.0116, "step": 9030 }, { "epoch": 3.381967826412271, "grad_norm": 0.15203677117824554, "learning_rate": 2.503693209498409e-06, "loss": 0.0104, "step": 9040 }, { "epoch": 3.3857089412644967, "grad_norm": 0.116244837641716, "learning_rate": 2.452286288035449e-06, "loss": 0.0087, "step": 9050 }, { "epoch": 3.389450056116723, "grad_norm": 0.14773325622081757, "learning_rate": 2.4013993407518363e-06, "loss": 0.0118, "step": 9060 }, { "epoch": 3.3931911709689486, "grad_norm": 0.14030255377292633, "learning_rate": 2.351032924139063e-06, "loss": 0.009, "step": 9070 }, { "epoch": 3.396932285821175, "grad_norm": 0.2661314606666565, "learning_rate": 2.30118758899619e-06, "loss": 0.0125, "step": 9080 }, { "epoch": 3.4006734006734005, "grad_norm": 0.29545965790748596, "learning_rate": 2.2518638804238157e-06, "loss": 0.0099, "step": 9090 }, { "epoch": 3.4044145155256267, "grad_norm": 0.1429222673177719, "learning_rate": 2.203062337818118e-06, "loss": 0.011, "step": 9100 }, { "epoch": 3.4081556303778524, "grad_norm": 0.16229914128780365, "learning_rate": 2.1547834948649483e-06, "loss": 0.0143, "step": 9110 }, { "epoch": 3.4118967452300786, "grad_norm": 0.17764617502689362, "learning_rate": 2.1070278795340017e-06, "loss": 0.0122, "step": 9120 }, { "epoch": 3.4156378600823043, "grad_norm": 0.10751409828662872, "learning_rate": 2.059796014073029e-06, "loss": 0.0076, "step": 9130 }, { "epoch": 3.4193789749345305, "grad_norm": 0.09254039078950882, "learning_rate": 2.01308841500214e-06, "loss": 0.01, "step": 9140 }, { "epoch": 3.4231200897867566, "grad_norm": 0.1744944453239441, "learning_rate": 1.9669055931081704e-06, "loss": 0.0121, "step": 9150 }, { "epoch": 3.4268612046389824, "grad_norm": 0.13842961192131042, "learning_rate": 1.9212480534390507e-06, "loss": 0.0129, "step": 9160 }, { "epoch": 3.4306023194912085, "grad_norm": 0.20856042206287384, "learning_rate": 1.8761162952983246e-06, "loss": 0.011, "step": 9170 }, { "epoch": 3.4343434343434343, "grad_norm": 0.21447379887104034, "learning_rate": 1.8315108122396618e-06, "loss": 0.0121, "step": 9180 }, { "epoch": 3.4380845491956604, "grad_norm": 0.17928040027618408, "learning_rate": 1.787432092061475e-06, "loss": 0.0105, "step": 9190 }, { "epoch": 3.441825664047886, "grad_norm": 0.10926397144794464, "learning_rate": 1.743880616801602e-06, "loss": 0.0124, "step": 9200 }, { "epoch": 3.4455667789001123, "grad_norm": 0.1515166461467743, "learning_rate": 1.7008568627319865e-06, "loss": 0.0095, "step": 9210 }, { "epoch": 3.449307893752338, "grad_norm": 0.21321187913417816, "learning_rate": 1.6583613003535226e-06, "loss": 0.0145, "step": 9220 }, { "epoch": 3.453049008604564, "grad_norm": 0.16350412368774414, "learning_rate": 1.6163943943908522e-06, "loss": 0.0127, "step": 9230 }, { "epoch": 3.45679012345679, "grad_norm": 0.2898126244544983, "learning_rate": 1.5749566037873476e-06, "loss": 0.0106, "step": 9240 }, { "epoch": 3.460531238309016, "grad_norm": 0.11183870583772659, "learning_rate": 1.5340483817000428e-06, "loss": 0.0134, "step": 9250 }, { "epoch": 3.464272353161242, "grad_norm": 0.15630406141281128, "learning_rate": 1.4936701754947101e-06, "loss": 0.0113, "step": 9260 }, { "epoch": 3.468013468013468, "grad_norm": 0.23219314217567444, "learning_rate": 1.4538224267409361e-06, "loss": 0.0119, "step": 9270 }, { "epoch": 3.471754582865694, "grad_norm": 0.10736443102359772, "learning_rate": 1.414505571207314e-06, "loss": 0.0085, "step": 9280 }, { "epoch": 3.47549569771792, "grad_norm": 0.1311621367931366, "learning_rate": 1.3757200388566816e-06, "loss": 0.0092, "step": 9290 }, { "epoch": 3.479236812570146, "grad_norm": 0.4300353229045868, "learning_rate": 1.3374662538414074e-06, "loss": 0.0116, "step": 9300 }, { "epoch": 3.4829779274223718, "grad_norm": 0.1427564024925232, "learning_rate": 1.2997446344987617e-06, "loss": 0.0113, "step": 9310 }, { "epoch": 3.486719042274598, "grad_norm": 0.16483499109745026, "learning_rate": 1.262555593346315e-06, "loss": 0.011, "step": 9320 }, { "epoch": 3.4904601571268237, "grad_norm": 0.11956904828548431, "learning_rate": 1.2258995370774685e-06, "loss": 0.0115, "step": 9330 }, { "epoch": 3.49420127197905, "grad_norm": 0.17861485481262207, "learning_rate": 1.1897768665569798e-06, "loss": 0.0132, "step": 9340 }, { "epoch": 3.4979423868312756, "grad_norm": 0.18356084823608398, "learning_rate": 1.1541879768165954e-06, "loss": 0.0113, "step": 9350 }, { "epoch": 3.5016835016835017, "grad_norm": 0.18782168626785278, "learning_rate": 1.1191332570507085e-06, "loss": 0.0109, "step": 9360 }, { "epoch": 3.505424616535728, "grad_norm": 0.15168991684913635, "learning_rate": 1.0846130906121132e-06, "loss": 0.017, "step": 9370 }, { "epoch": 3.5091657313879536, "grad_norm": 0.2619721591472626, "learning_rate": 1.0506278550078131e-06, "loss": 0.0127, "step": 9380 }, { "epoch": 3.5129068462401793, "grad_norm": 0.10294197499752045, "learning_rate": 1.0171779218949185e-06, "loss": 0.0125, "step": 9390 }, { "epoch": 3.5166479610924055, "grad_norm": 0.10926692932844162, "learning_rate": 9.842636570765174e-07, "loss": 0.0118, "step": 9400 }, { "epoch": 3.5203890759446317, "grad_norm": 0.27442243695259094, "learning_rate": 9.518854204977612e-07, "loss": 0.0083, "step": 9410 }, { "epoch": 3.5241301907968574, "grad_norm": 0.1546885073184967, "learning_rate": 9.200435662418349e-07, "loss": 0.0103, "step": 9420 }, { "epoch": 3.5278713056490836, "grad_norm": 0.1417083889245987, "learning_rate": 8.887384425261658e-07, "loss": 0.0098, "step": 9430 }, { "epoch": 3.5316124205013093, "grad_norm": 0.1587194949388504, "learning_rate": 8.579703916985648e-07, "loss": 0.0124, "step": 9440 }, { "epoch": 3.5353535353535355, "grad_norm": 0.10446324944496155, "learning_rate": 8.277397502335194e-07, "loss": 0.0112, "step": 9450 }, { "epoch": 3.539094650205761, "grad_norm": 0.1368294358253479, "learning_rate": 7.980468487284675e-07, "loss": 0.0098, "step": 9460 }, { "epoch": 3.5428357650579874, "grad_norm": 0.11586947739124298, "learning_rate": 7.688920119002297e-07, "loss": 0.0112, "step": 9470 }, { "epoch": 3.546576879910213, "grad_norm": 0.22867673635482788, "learning_rate": 7.402755585814269e-07, "loss": 0.0138, "step": 9480 }, { "epoch": 3.5503179947624393, "grad_norm": 0.17664995789527893, "learning_rate": 7.121978017170073e-07, "loss": 0.0134, "step": 9490 }, { "epoch": 3.5540591096146654, "grad_norm": 0.18866032361984253, "learning_rate": 6.846590483608306e-07, "loss": 0.0115, "step": 9500 }, { "epoch": 3.557800224466891, "grad_norm": 0.0888948068022728, "learning_rate": 6.576595996722834e-07, "loss": 0.0166, "step": 9510 }, { "epoch": 3.561541339319117, "grad_norm": 0.1634044051170349, "learning_rate": 6.311997509130141e-07, "loss": 0.0119, "step": 9520 }, { "epoch": 3.565282454171343, "grad_norm": 0.1629437506198883, "learning_rate": 6.052797914436803e-07, "loss": 0.0126, "step": 9530 }, { "epoch": 3.569023569023569, "grad_norm": 0.18659256398677826, "learning_rate": 5.799000047208181e-07, "loss": 0.0108, "step": 9540 }, { "epoch": 3.572764683875795, "grad_norm": 0.2813478410243988, "learning_rate": 5.550606682937054e-07, "loss": 0.0138, "step": 9550 }, { "epoch": 3.576505798728021, "grad_norm": 0.18325838446617126, "learning_rate": 5.307620538013481e-07, "loss": 0.0117, "step": 9560 }, { "epoch": 3.580246913580247, "grad_norm": 0.15332446992397308, "learning_rate": 5.070044269694874e-07, "loss": 0.0123, "step": 9570 }, { "epoch": 3.583988028432473, "grad_norm": 0.20441709458827972, "learning_rate": 4.837880476077417e-07, "loss": 0.0117, "step": 9580 }, { "epoch": 3.5877291432846987, "grad_norm": 0.09962929040193558, "learning_rate": 4.6111316960670835e-07, "loss": 0.008, "step": 9590 }, { "epoch": 3.591470258136925, "grad_norm": 0.17490775883197784, "learning_rate": 4.389800409352218e-07, "loss": 0.0099, "step": 9600 }, { "epoch": 3.5952113729891506, "grad_norm": 0.21243557333946228, "learning_rate": 4.173889036376277e-07, "loss": 0.0114, "step": 9610 }, { "epoch": 3.598952487841377, "grad_norm": 0.19654090702533722, "learning_rate": 3.963399938311463e-07, "loss": 0.0133, "step": 9620 }, { "epoch": 3.602693602693603, "grad_norm": 0.19779029488563538, "learning_rate": 3.7583354170328545e-07, "loss": 0.0131, "step": 9630 }, { "epoch": 3.6064347175458287, "grad_norm": 0.11353166401386261, "learning_rate": 3.558697715093207e-07, "loss": 0.0094, "step": 9640 }, { "epoch": 3.6101758323980544, "grad_norm": 0.18174801766872406, "learning_rate": 3.3644890156983576e-07, "loss": 0.0121, "step": 9650 }, { "epoch": 3.6139169472502806, "grad_norm": 0.1357123702764511, "learning_rate": 3.175711442683638e-07, "loss": 0.0098, "step": 9660 }, { "epoch": 3.6176580621025067, "grad_norm": 0.1404295414686203, "learning_rate": 2.9923670604902197e-07, "loss": 0.0114, "step": 9670 }, { "epoch": 3.6213991769547325, "grad_norm": 0.2583100199699402, "learning_rate": 2.814457874143028e-07, "loss": 0.0114, "step": 9680 }, { "epoch": 3.6251402918069586, "grad_norm": 0.18862521648406982, "learning_rate": 2.641985829228366e-07, "loss": 0.0112, "step": 9690 }, { "epoch": 3.6288814066591843, "grad_norm": 0.14347001910209656, "learning_rate": 2.474952811872877e-07, "loss": 0.0101, "step": 9700 }, { "epoch": 3.6326225215114105, "grad_norm": 0.16209819912910461, "learning_rate": 2.3133606487228397e-07, "loss": 0.0098, "step": 9710 }, { "epoch": 3.6363636363636362, "grad_norm": 0.18712249398231506, "learning_rate": 2.157211106924295e-07, "loss": 0.0116, "step": 9720 }, { "epoch": 3.6401047512158624, "grad_norm": 0.19661355018615723, "learning_rate": 2.006505894103672e-07, "loss": 0.0131, "step": 9730 }, { "epoch": 3.643845866068088, "grad_norm": 0.09593728184700012, "learning_rate": 1.8612466583489696e-07, "loss": 0.0134, "step": 9740 }, { "epoch": 3.6475869809203143, "grad_norm": 0.11589605361223221, "learning_rate": 1.7214349881918834e-07, "loss": 0.0158, "step": 9750 }, { "epoch": 3.6513280957725405, "grad_norm": 0.08160290122032166, "learning_rate": 1.5870724125904845e-07, "loss": 0.0098, "step": 9760 }, { "epoch": 3.655069210624766, "grad_norm": 0.18357650935649872, "learning_rate": 1.4581604009124006e-07, "loss": 0.0114, "step": 9770 }, { "epoch": 3.658810325476992, "grad_norm": 0.13412582874298096, "learning_rate": 1.334700362918717e-07, "loss": 0.0095, "step": 9780 }, { "epoch": 3.662551440329218, "grad_norm": 0.29154735803604126, "learning_rate": 1.2166936487486015e-07, "loss": 0.0103, "step": 9790 }, { "epoch": 3.6662925551814443, "grad_norm": 0.1771175116300583, "learning_rate": 1.1041415489045914e-07, "loss": 0.0105, "step": 9800 }, { "epoch": 3.67003367003367, "grad_norm": 0.1554066240787506, "learning_rate": 9.970452942384412e-08, "loss": 0.0102, "step": 9810 }, { "epoch": 3.673774784885896, "grad_norm": 0.23401008546352386, "learning_rate": 8.954060559375754e-08, "loss": 0.0091, "step": 9820 }, { "epoch": 3.677515899738122, "grad_norm": 0.21162456274032593, "learning_rate": 7.99224945512489e-08, "loss": 0.0155, "step": 9830 }, { "epoch": 3.681257014590348, "grad_norm": 0.14729242026805878, "learning_rate": 7.085030147843675e-08, "loss": 0.0126, "step": 9840 }, { "epoch": 3.6849981294425738, "grad_norm": 0.11147643625736237, "learning_rate": 6.232412558736523e-08, "loss": 0.0122, "step": 9850 }, { "epoch": 3.6887392442948, "grad_norm": 0.18676379323005676, "learning_rate": 5.434406011893822e-08, "loss": 0.013, "step": 9860 }, { "epoch": 3.6924803591470257, "grad_norm": 0.1786031872034073, "learning_rate": 4.6910192341864664e-08, "loss": 0.0099, "step": 9870 }, { "epoch": 3.696221473999252, "grad_norm": 0.17283251881599426, "learning_rate": 4.0022603551737035e-08, "loss": 0.0131, "step": 9880 }, { "epoch": 3.699962588851478, "grad_norm": 0.09560641646385193, "learning_rate": 3.3681369070120985e-08, "loss": 0.0122, "step": 9890 }, { "epoch": 3.7037037037037037, "grad_norm": 0.10062969475984573, "learning_rate": 2.7886558243744866e-08, "loss": 0.0147, "step": 9900 }, { "epoch": 3.7074448185559294, "grad_norm": 0.1090511754155159, "learning_rate": 2.2638234443722596e-08, "loss": 0.0097, "step": 9910 }, { "epoch": 3.7111859334081556, "grad_norm": 0.14127151668071747, "learning_rate": 1.7936455064887504e-08, "loss": 0.0146, "step": 9920 }, { "epoch": 3.714927048260382, "grad_norm": 0.15329216420650482, "learning_rate": 1.378127152514841e-08, "loss": 0.0099, "step": 9930 }, { "epoch": 3.7186681631126075, "grad_norm": 0.11805541068315506, "learning_rate": 1.0172729264917857e-08, "loss": 0.0119, "step": 9940 }, { "epoch": 3.7224092779648337, "grad_norm": 0.18322564661502838, "learning_rate": 7.1108677466458215e-09, "loss": 0.0108, "step": 9950 }, { "epoch": 3.7261503928170594, "grad_norm": 0.10214464366436005, "learning_rate": 4.595720454353414e-09, "loss": 0.0119, "step": 9960 }, { "epoch": 3.7298915076692856, "grad_norm": 0.277861088514328, "learning_rate": 2.627314893294264e-09, "loss": 0.0102, "step": 9970 }, { "epoch": 3.7336326225215113, "grad_norm": 0.12992411851882935, "learning_rate": 1.2056725896270048e-09, "loss": 0.0103, "step": 9980 }, { "epoch": 3.7373737373737375, "grad_norm": 0.1691821813583374, "learning_rate": 3.308090902098826e-10, "loss": 0.0112, "step": 9990 }, { "epoch": 3.741114852225963, "grad_norm": 0.16597244143486023, "learning_rate": 2.7339624120159555e-12, "loss": 0.0093, "step": 10000 }, { "epoch": 3.741114852225963, "step": 10000, "total_flos": 0.0, "train_loss": 0.026995109889656307, "train_runtime": 33302.8767, "train_samples_per_second": 9.609, "train_steps_per_second": 0.3 } ], "logging_steps": 10, "max_steps": 10000, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }