{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 7728, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002587991718426501, "grad_norm": 0.6931016445159912, "learning_rate": 4.9961180124223606e-05, "loss": 1.2213, "step": 10 }, { "epoch": 0.005175983436853002, "grad_norm": 0.48186811804771423, "learning_rate": 4.9918046928916494e-05, "loss": 0.6617, "step": 20 }, { "epoch": 0.007763975155279503, "grad_norm": 0.4067845642566681, "learning_rate": 4.987491373360939e-05, "loss": 0.5725, "step": 30 }, { "epoch": 0.010351966873706004, "grad_norm": 0.4268130958080292, "learning_rate": 4.9831780538302284e-05, "loss": 0.5456, "step": 40 }, { "epoch": 0.012939958592132506, "grad_norm": 0.4061700701713562, "learning_rate": 4.978864734299517e-05, "loss": 0.5057, "step": 50 }, { "epoch": 0.015527950310559006, "grad_norm": 0.4203609526157379, "learning_rate": 4.974551414768806e-05, "loss": 0.493, "step": 60 }, { "epoch": 0.018115942028985508, "grad_norm": 0.4072072505950928, "learning_rate": 4.9702380952380955e-05, "loss": 0.5016, "step": 70 }, { "epoch": 0.020703933747412008, "grad_norm": 0.35524892807006836, "learning_rate": 4.965924775707384e-05, "loss": 0.4801, "step": 80 }, { "epoch": 0.023291925465838508, "grad_norm": 0.422678142786026, "learning_rate": 4.961611456176674e-05, "loss": 0.4675, "step": 90 }, { "epoch": 0.025879917184265012, "grad_norm": 0.7197648882865906, "learning_rate": 4.957298136645963e-05, "loss": 0.4504, "step": 100 }, { "epoch": 0.028467908902691512, "grad_norm": 0.38139602541923523, "learning_rate": 4.952984817115252e-05, "loss": 0.4661, "step": 110 }, { "epoch": 0.031055900621118012, "grad_norm": 0.3637668490409851, "learning_rate": 4.948671497584541e-05, "loss": 0.4291, "step": 120 }, { "epoch": 0.03364389233954451, "grad_norm": 0.3413495421409607, "learning_rate": 4.94435817805383e-05, "loss": 0.4337, "step": 130 }, { "epoch": 0.036231884057971016, "grad_norm": 0.3850350081920624, "learning_rate": 4.94004485852312e-05, "loss": 0.4353, "step": 140 }, { "epoch": 0.03881987577639751, "grad_norm": 0.3495863378047943, "learning_rate": 4.9357315389924086e-05, "loss": 0.429, "step": 150 }, { "epoch": 0.041407867494824016, "grad_norm": 0.3324839472770691, "learning_rate": 4.931418219461698e-05, "loss": 0.4254, "step": 160 }, { "epoch": 0.04399585921325052, "grad_norm": 0.3240760862827301, "learning_rate": 4.927104899930987e-05, "loss": 0.418, "step": 170 }, { "epoch": 0.046583850931677016, "grad_norm": 0.32717740535736084, "learning_rate": 4.922791580400276e-05, "loss": 0.4181, "step": 180 }, { "epoch": 0.04917184265010352, "grad_norm": 0.37864601612091064, "learning_rate": 4.918478260869566e-05, "loss": 0.416, "step": 190 }, { "epoch": 0.051759834368530024, "grad_norm": 0.3354615569114685, "learning_rate": 4.9141649413388546e-05, "loss": 0.4171, "step": 200 }, { "epoch": 0.05434782608695652, "grad_norm": 0.3466266095638275, "learning_rate": 4.9098516218081434e-05, "loss": 0.4143, "step": 210 }, { "epoch": 0.056935817805383024, "grad_norm": 0.31229594349861145, "learning_rate": 4.905538302277433e-05, "loss": 0.3969, "step": 220 }, { "epoch": 0.05952380952380952, "grad_norm": 0.33017608523368835, "learning_rate": 4.9012249827467224e-05, "loss": 0.4029, "step": 230 }, { "epoch": 0.062111801242236024, "grad_norm": 0.3223104774951935, "learning_rate": 4.896911663216011e-05, "loss": 0.4077, "step": 240 }, { "epoch": 0.06469979296066253, "grad_norm": 0.3475039601325989, "learning_rate": 4.8925983436853006e-05, "loss": 0.4054, "step": 250 }, { "epoch": 0.06728778467908902, "grad_norm": 0.3325633108615875, "learning_rate": 4.8882850241545894e-05, "loss": 0.3936, "step": 260 }, { "epoch": 0.06987577639751552, "grad_norm": 0.3039849102497101, "learning_rate": 4.883971704623879e-05, "loss": 0.3983, "step": 270 }, { "epoch": 0.07246376811594203, "grad_norm": 0.3026624023914337, "learning_rate": 4.8796583850931684e-05, "loss": 0.3917, "step": 280 }, { "epoch": 0.07505175983436853, "grad_norm": 0.28852379322052, "learning_rate": 4.875345065562457e-05, "loss": 0.386, "step": 290 }, { "epoch": 0.07763975155279502, "grad_norm": 0.29932525753974915, "learning_rate": 4.871031746031746e-05, "loss": 0.3878, "step": 300 }, { "epoch": 0.08022774327122154, "grad_norm": 0.2904777526855469, "learning_rate": 4.8667184265010355e-05, "loss": 0.3827, "step": 310 }, { "epoch": 0.08281573498964803, "grad_norm": 0.29514485597610474, "learning_rate": 4.862405106970325e-05, "loss": 0.3917, "step": 320 }, { "epoch": 0.08540372670807453, "grad_norm": 0.29739001393318176, "learning_rate": 4.858091787439614e-05, "loss": 0.3873, "step": 330 }, { "epoch": 0.08799171842650104, "grad_norm": 0.2792510688304901, "learning_rate": 4.8537784679089025e-05, "loss": 0.3815, "step": 340 }, { "epoch": 0.09057971014492754, "grad_norm": 0.3052826225757599, "learning_rate": 4.849465148378192e-05, "loss": 0.3818, "step": 350 }, { "epoch": 0.09316770186335403, "grad_norm": 0.28388407826423645, "learning_rate": 4.8451518288474815e-05, "loss": 0.3865, "step": 360 }, { "epoch": 0.09575569358178054, "grad_norm": 0.313395619392395, "learning_rate": 4.84083850931677e-05, "loss": 0.3747, "step": 370 }, { "epoch": 0.09834368530020704, "grad_norm": 0.30021408200263977, "learning_rate": 4.83652518978606e-05, "loss": 0.3838, "step": 380 }, { "epoch": 0.10093167701863354, "grad_norm": 0.2741802930831909, "learning_rate": 4.8322118702553486e-05, "loss": 0.3713, "step": 390 }, { "epoch": 0.10351966873706005, "grad_norm": 0.29940980672836304, "learning_rate": 4.8278985507246374e-05, "loss": 0.3916, "step": 400 }, { "epoch": 0.10610766045548654, "grad_norm": 0.29653653502464294, "learning_rate": 4.8235852311939275e-05, "loss": 0.3836, "step": 410 }, { "epoch": 0.10869565217391304, "grad_norm": 0.31111636757850647, "learning_rate": 4.819271911663216e-05, "loss": 0.3723, "step": 420 }, { "epoch": 0.11128364389233955, "grad_norm": 0.30432841181755066, "learning_rate": 4.814958592132505e-05, "loss": 0.391, "step": 430 }, { "epoch": 0.11387163561076605, "grad_norm": 0.2829114496707916, "learning_rate": 4.8106452726017946e-05, "loss": 0.3831, "step": 440 }, { "epoch": 0.11645962732919254, "grad_norm": 0.2797948718070984, "learning_rate": 4.806331953071084e-05, "loss": 0.3729, "step": 450 }, { "epoch": 0.11904761904761904, "grad_norm": 0.29887112975120544, "learning_rate": 4.802018633540373e-05, "loss": 0.3693, "step": 460 }, { "epoch": 0.12163561076604555, "grad_norm": 0.2550595700740814, "learning_rate": 4.7977053140096624e-05, "loss": 0.3694, "step": 470 }, { "epoch": 0.12422360248447205, "grad_norm": 0.28271788358688354, "learning_rate": 4.793391994478951e-05, "loss": 0.3769, "step": 480 }, { "epoch": 0.12681159420289856, "grad_norm": 0.27268651127815247, "learning_rate": 4.78907867494824e-05, "loss": 0.3717, "step": 490 }, { "epoch": 0.12939958592132506, "grad_norm": 0.3002064824104309, "learning_rate": 4.78476535541753e-05, "loss": 0.3648, "step": 500 }, { "epoch": 0.13198757763975155, "grad_norm": 0.28463032841682434, "learning_rate": 4.780452035886819e-05, "loss": 0.3633, "step": 510 }, { "epoch": 0.13457556935817805, "grad_norm": 0.29805323481559753, "learning_rate": 4.776138716356108e-05, "loss": 0.3642, "step": 520 }, { "epoch": 0.13716356107660455, "grad_norm": 0.2904551327228546, "learning_rate": 4.771825396825397e-05, "loss": 0.3696, "step": 530 }, { "epoch": 0.13975155279503104, "grad_norm": 0.2726401388645172, "learning_rate": 4.767512077294686e-05, "loss": 0.3629, "step": 540 }, { "epoch": 0.14233954451345757, "grad_norm": 0.2827688753604889, "learning_rate": 4.7631987577639755e-05, "loss": 0.3613, "step": 550 }, { "epoch": 0.14492753623188406, "grad_norm": 0.25535234808921814, "learning_rate": 4.758885438233265e-05, "loss": 0.3691, "step": 560 }, { "epoch": 0.14751552795031056, "grad_norm": 0.3313714563846588, "learning_rate": 4.754572118702554e-05, "loss": 0.3719, "step": 570 }, { "epoch": 0.15010351966873706, "grad_norm": 0.3062281906604767, "learning_rate": 4.7502587991718425e-05, "loss": 0.359, "step": 580 }, { "epoch": 0.15269151138716355, "grad_norm": 0.26143062114715576, "learning_rate": 4.745945479641132e-05, "loss": 0.3633, "step": 590 }, { "epoch": 0.15527950310559005, "grad_norm": 0.2947162091732025, "learning_rate": 4.7416321601104215e-05, "loss": 0.3534, "step": 600 }, { "epoch": 0.15786749482401657, "grad_norm": 0.280143678188324, "learning_rate": 4.73731884057971e-05, "loss": 0.3681, "step": 610 }, { "epoch": 0.16045548654244307, "grad_norm": 0.2904067039489746, "learning_rate": 4.733005521048999e-05, "loss": 0.3669, "step": 620 }, { "epoch": 0.16304347826086957, "grad_norm": 0.2655963897705078, "learning_rate": 4.7286922015182886e-05, "loss": 0.364, "step": 630 }, { "epoch": 0.16563146997929606, "grad_norm": 0.2548169493675232, "learning_rate": 4.724378881987578e-05, "loss": 0.3604, "step": 640 }, { "epoch": 0.16821946169772256, "grad_norm": 0.26068902015686035, "learning_rate": 4.720065562456867e-05, "loss": 0.3573, "step": 650 }, { "epoch": 0.17080745341614906, "grad_norm": 0.2658487558364868, "learning_rate": 4.715752242926156e-05, "loss": 0.3769, "step": 660 }, { "epoch": 0.17339544513457558, "grad_norm": 0.2844776213169098, "learning_rate": 4.711438923395445e-05, "loss": 0.3538, "step": 670 }, { "epoch": 0.17598343685300208, "grad_norm": 0.2560563385486603, "learning_rate": 4.7071256038647346e-05, "loss": 0.3525, "step": 680 }, { "epoch": 0.17857142857142858, "grad_norm": 0.278079092502594, "learning_rate": 4.702812284334024e-05, "loss": 0.3497, "step": 690 }, { "epoch": 0.18115942028985507, "grad_norm": 0.2821943461894989, "learning_rate": 4.698498964803313e-05, "loss": 0.3561, "step": 700 }, { "epoch": 0.18374741200828157, "grad_norm": 0.2607298195362091, "learning_rate": 4.694185645272602e-05, "loss": 0.3616, "step": 710 }, { "epoch": 0.18633540372670807, "grad_norm": 0.27013707160949707, "learning_rate": 4.689872325741891e-05, "loss": 0.3502, "step": 720 }, { "epoch": 0.18892339544513456, "grad_norm": 0.265015184879303, "learning_rate": 4.6855590062111806e-05, "loss": 0.3463, "step": 730 }, { "epoch": 0.1915113871635611, "grad_norm": 0.27620813250541687, "learning_rate": 4.6812456866804694e-05, "loss": 0.3567, "step": 740 }, { "epoch": 0.19409937888198758, "grad_norm": 0.2566974461078644, "learning_rate": 4.676932367149759e-05, "loss": 0.3521, "step": 750 }, { "epoch": 0.19668737060041408, "grad_norm": 0.2620496153831482, "learning_rate": 4.672619047619048e-05, "loss": 0.3474, "step": 760 }, { "epoch": 0.19927536231884058, "grad_norm": 0.2598465383052826, "learning_rate": 4.668305728088337e-05, "loss": 0.3525, "step": 770 }, { "epoch": 0.20186335403726707, "grad_norm": 0.28414371609687805, "learning_rate": 4.663992408557627e-05, "loss": 0.3415, "step": 780 }, { "epoch": 0.20445134575569357, "grad_norm": 0.27969351410865784, "learning_rate": 4.6596790890269155e-05, "loss": 0.3597, "step": 790 }, { "epoch": 0.2070393374741201, "grad_norm": 0.26387929916381836, "learning_rate": 4.655365769496204e-05, "loss": 0.3452, "step": 800 }, { "epoch": 0.2096273291925466, "grad_norm": 0.27556657791137695, "learning_rate": 4.651052449965494e-05, "loss": 0.3418, "step": 810 }, { "epoch": 0.2122153209109731, "grad_norm": 0.25666093826293945, "learning_rate": 4.646739130434783e-05, "loss": 0.3494, "step": 820 }, { "epoch": 0.21480331262939958, "grad_norm": 0.24122317135334015, "learning_rate": 4.642425810904072e-05, "loss": 0.3667, "step": 830 }, { "epoch": 0.21739130434782608, "grad_norm": 0.2530350983142853, "learning_rate": 4.638112491373361e-05, "loss": 0.3543, "step": 840 }, { "epoch": 0.21997929606625258, "grad_norm": 0.26871258020401, "learning_rate": 4.63379917184265e-05, "loss": 0.3432, "step": 850 }, { "epoch": 0.2225672877846791, "grad_norm": 0.2797186076641083, "learning_rate": 4.629485852311939e-05, "loss": 0.3451, "step": 860 }, { "epoch": 0.2251552795031056, "grad_norm": 0.2654234766960144, "learning_rate": 4.6251725327812286e-05, "loss": 0.3495, "step": 870 }, { "epoch": 0.2277432712215321, "grad_norm": 0.2519735097885132, "learning_rate": 4.620859213250518e-05, "loss": 0.3499, "step": 880 }, { "epoch": 0.2303312629399586, "grad_norm": 0.24566596746444702, "learning_rate": 4.616545893719807e-05, "loss": 0.3555, "step": 890 }, { "epoch": 0.2329192546583851, "grad_norm": 0.27151158452033997, "learning_rate": 4.6122325741890956e-05, "loss": 0.3573, "step": 900 }, { "epoch": 0.23550724637681159, "grad_norm": 0.27960848808288574, "learning_rate": 4.607919254658386e-05, "loss": 0.3593, "step": 910 }, { "epoch": 0.23809523809523808, "grad_norm": 0.23981152474880219, "learning_rate": 4.6036059351276746e-05, "loss": 0.3459, "step": 920 }, { "epoch": 0.2406832298136646, "grad_norm": 0.25497132539749146, "learning_rate": 4.5992926155969634e-05, "loss": 0.3509, "step": 930 }, { "epoch": 0.2432712215320911, "grad_norm": 0.27302148938179016, "learning_rate": 4.594979296066253e-05, "loss": 0.3426, "step": 940 }, { "epoch": 0.2458592132505176, "grad_norm": 0.2586531639099121, "learning_rate": 4.590665976535542e-05, "loss": 0.3445, "step": 950 }, { "epoch": 0.2484472049689441, "grad_norm": 0.22465559840202332, "learning_rate": 4.586352657004831e-05, "loss": 0.3415, "step": 960 }, { "epoch": 0.2510351966873706, "grad_norm": 0.25479137897491455, "learning_rate": 4.5820393374741206e-05, "loss": 0.3355, "step": 970 }, { "epoch": 0.2536231884057971, "grad_norm": 0.2489393651485443, "learning_rate": 4.5777260179434094e-05, "loss": 0.3427, "step": 980 }, { "epoch": 0.2562111801242236, "grad_norm": 0.24661508202552795, "learning_rate": 4.573412698412698e-05, "loss": 0.3311, "step": 990 }, { "epoch": 0.2587991718426501, "grad_norm": 0.24593059718608856, "learning_rate": 4.569099378881988e-05, "loss": 0.3388, "step": 1000 }, { "epoch": 0.2613871635610766, "grad_norm": 0.2396044135093689, "learning_rate": 4.564786059351277e-05, "loss": 0.3508, "step": 1010 }, { "epoch": 0.2639751552795031, "grad_norm": 0.275534063577652, "learning_rate": 4.560472739820566e-05, "loss": 0.3451, "step": 1020 }, { "epoch": 0.2665631469979296, "grad_norm": 0.2593844532966614, "learning_rate": 4.5561594202898555e-05, "loss": 0.3359, "step": 1030 }, { "epoch": 0.2691511387163561, "grad_norm": 0.2667211592197418, "learning_rate": 4.551846100759144e-05, "loss": 0.3446, "step": 1040 }, { "epoch": 0.2717391304347826, "grad_norm": 0.26292136311531067, "learning_rate": 4.547532781228434e-05, "loss": 0.3418, "step": 1050 }, { "epoch": 0.2743271221532091, "grad_norm": 0.2429954707622528, "learning_rate": 4.543219461697723e-05, "loss": 0.3411, "step": 1060 }, { "epoch": 0.2769151138716356, "grad_norm": 0.23935279250144958, "learning_rate": 4.538906142167012e-05, "loss": 0.3479, "step": 1070 }, { "epoch": 0.2795031055900621, "grad_norm": 0.24318240582942963, "learning_rate": 4.534592822636301e-05, "loss": 0.3363, "step": 1080 }, { "epoch": 0.28209109730848864, "grad_norm": 0.23401808738708496, "learning_rate": 4.53027950310559e-05, "loss": 0.3507, "step": 1090 }, { "epoch": 0.28467908902691513, "grad_norm": 0.235195592045784, "learning_rate": 4.52596618357488e-05, "loss": 0.3452, "step": 1100 }, { "epoch": 0.28726708074534163, "grad_norm": 0.25817984342575073, "learning_rate": 4.5216528640441686e-05, "loss": 0.3227, "step": 1110 }, { "epoch": 0.2898550724637681, "grad_norm": 0.2499350905418396, "learning_rate": 4.5173395445134574e-05, "loss": 0.341, "step": 1120 }, { "epoch": 0.2924430641821946, "grad_norm": 0.23882877826690674, "learning_rate": 4.513026224982747e-05, "loss": 0.3484, "step": 1130 }, { "epoch": 0.2950310559006211, "grad_norm": 0.2699326276779175, "learning_rate": 4.508712905452036e-05, "loss": 0.3427, "step": 1140 }, { "epoch": 0.2976190476190476, "grad_norm": 0.2389804571866989, "learning_rate": 4.504399585921325e-05, "loss": 0.3188, "step": 1150 }, { "epoch": 0.3002070393374741, "grad_norm": 0.24539288878440857, "learning_rate": 4.5000862663906146e-05, "loss": 0.3434, "step": 1160 }, { "epoch": 0.3027950310559006, "grad_norm": 0.25557300448417664, "learning_rate": 4.4957729468599034e-05, "loss": 0.3202, "step": 1170 }, { "epoch": 0.3053830227743271, "grad_norm": 0.2359408438205719, "learning_rate": 4.491459627329193e-05, "loss": 0.3416, "step": 1180 }, { "epoch": 0.3079710144927536, "grad_norm": 0.2432994544506073, "learning_rate": 4.4871463077984824e-05, "loss": 0.3386, "step": 1190 }, { "epoch": 0.3105590062111801, "grad_norm": 0.24209333956241608, "learning_rate": 4.482832988267771e-05, "loss": 0.3364, "step": 1200 }, { "epoch": 0.31314699792960665, "grad_norm": 0.25228288769721985, "learning_rate": 4.47851966873706e-05, "loss": 0.3245, "step": 1210 }, { "epoch": 0.31573498964803315, "grad_norm": 0.21681800484657288, "learning_rate": 4.4742063492063494e-05, "loss": 0.3417, "step": 1220 }, { "epoch": 0.31832298136645965, "grad_norm": 0.23574399948120117, "learning_rate": 4.469893029675639e-05, "loss": 0.3399, "step": 1230 }, { "epoch": 0.32091097308488614, "grad_norm": 0.22972829639911652, "learning_rate": 4.465579710144928e-05, "loss": 0.3245, "step": 1240 }, { "epoch": 0.32349896480331264, "grad_norm": 0.22471453249454498, "learning_rate": 4.461266390614217e-05, "loss": 0.3273, "step": 1250 }, { "epoch": 0.32608695652173914, "grad_norm": 0.2130855917930603, "learning_rate": 4.456953071083506e-05, "loss": 0.3279, "step": 1260 }, { "epoch": 0.32867494824016563, "grad_norm": 0.22941111028194427, "learning_rate": 4.452639751552795e-05, "loss": 0.3263, "step": 1270 }, { "epoch": 0.33126293995859213, "grad_norm": 0.24117586016654968, "learning_rate": 4.448326432022085e-05, "loss": 0.3337, "step": 1280 }, { "epoch": 0.3338509316770186, "grad_norm": 0.2593615651130676, "learning_rate": 4.444013112491374e-05, "loss": 0.3368, "step": 1290 }, { "epoch": 0.3364389233954451, "grad_norm": 0.23699291050434113, "learning_rate": 4.4396997929606625e-05, "loss": 0.332, "step": 1300 }, { "epoch": 0.3390269151138716, "grad_norm": 0.2599596381187439, "learning_rate": 4.435386473429952e-05, "loss": 0.3303, "step": 1310 }, { "epoch": 0.3416149068322981, "grad_norm": 0.23753949999809265, "learning_rate": 4.4310731538992415e-05, "loss": 0.3349, "step": 1320 }, { "epoch": 0.3442028985507246, "grad_norm": 0.2286694347858429, "learning_rate": 4.42675983436853e-05, "loss": 0.3342, "step": 1330 }, { "epoch": 0.34679089026915116, "grad_norm": 0.23095780611038208, "learning_rate": 4.422446514837819e-05, "loss": 0.3242, "step": 1340 }, { "epoch": 0.34937888198757766, "grad_norm": 0.2591758072376251, "learning_rate": 4.4181331953071086e-05, "loss": 0.3307, "step": 1350 }, { "epoch": 0.35196687370600416, "grad_norm": 0.23518985509872437, "learning_rate": 4.4138198757763974e-05, "loss": 0.3186, "step": 1360 }, { "epoch": 0.35455486542443065, "grad_norm": 0.2448560744524002, "learning_rate": 4.409506556245687e-05, "loss": 0.3198, "step": 1370 }, { "epoch": 0.35714285714285715, "grad_norm": 0.24746116995811462, "learning_rate": 4.405193236714976e-05, "loss": 0.3346, "step": 1380 }, { "epoch": 0.35973084886128365, "grad_norm": 0.2440098077058792, "learning_rate": 4.400879917184265e-05, "loss": 0.3164, "step": 1390 }, { "epoch": 0.36231884057971014, "grad_norm": 0.2528471350669861, "learning_rate": 4.396566597653554e-05, "loss": 0.3293, "step": 1400 }, { "epoch": 0.36490683229813664, "grad_norm": 0.25530192255973816, "learning_rate": 4.3922532781228434e-05, "loss": 0.3368, "step": 1410 }, { "epoch": 0.36749482401656314, "grad_norm": 0.21804003417491913, "learning_rate": 4.387939958592133e-05, "loss": 0.3204, "step": 1420 }, { "epoch": 0.37008281573498963, "grad_norm": 0.22486785054206848, "learning_rate": 4.383626639061422e-05, "loss": 0.3309, "step": 1430 }, { "epoch": 0.37267080745341613, "grad_norm": 0.2279578149318695, "learning_rate": 4.379313319530711e-05, "loss": 0.33, "step": 1440 }, { "epoch": 0.3752587991718426, "grad_norm": 0.23841218650341034, "learning_rate": 4.375e-05, "loss": 0.3144, "step": 1450 }, { "epoch": 0.3778467908902691, "grad_norm": 0.2441750168800354, "learning_rate": 4.3706866804692894e-05, "loss": 0.336, "step": 1460 }, { "epoch": 0.3804347826086957, "grad_norm": 0.22941255569458008, "learning_rate": 4.366373360938579e-05, "loss": 0.3419, "step": 1470 }, { "epoch": 0.3830227743271222, "grad_norm": 0.22717274725437164, "learning_rate": 4.362060041407868e-05, "loss": 0.3341, "step": 1480 }, { "epoch": 0.38561076604554867, "grad_norm": 0.22173310816287994, "learning_rate": 4.3577467218771565e-05, "loss": 0.3285, "step": 1490 }, { "epoch": 0.38819875776397517, "grad_norm": 0.26800036430358887, "learning_rate": 4.353433402346446e-05, "loss": 0.3263, "step": 1500 }, { "epoch": 0.39078674948240166, "grad_norm": 0.2275414764881134, "learning_rate": 4.3491200828157355e-05, "loss": 0.3393, "step": 1510 }, { "epoch": 0.39337474120082816, "grad_norm": 0.23832468688488007, "learning_rate": 4.344806763285024e-05, "loss": 0.3207, "step": 1520 }, { "epoch": 0.39596273291925466, "grad_norm": 0.24205411970615387, "learning_rate": 4.340493443754314e-05, "loss": 0.3174, "step": 1530 }, { "epoch": 0.39855072463768115, "grad_norm": 0.23856307566165924, "learning_rate": 4.3361801242236025e-05, "loss": 0.3286, "step": 1540 }, { "epoch": 0.40113871635610765, "grad_norm": 0.22671808302402496, "learning_rate": 4.331866804692892e-05, "loss": 0.3274, "step": 1550 }, { "epoch": 0.40372670807453415, "grad_norm": 0.21958813071250916, "learning_rate": 4.3275534851621815e-05, "loss": 0.3205, "step": 1560 }, { "epoch": 0.40631469979296064, "grad_norm": 0.2193451225757599, "learning_rate": 4.32324016563147e-05, "loss": 0.3153, "step": 1570 }, { "epoch": 0.40890269151138714, "grad_norm": 0.22171197831630707, "learning_rate": 4.318926846100759e-05, "loss": 0.3314, "step": 1580 }, { "epoch": 0.4114906832298137, "grad_norm": 0.23245662450790405, "learning_rate": 4.3146135265700486e-05, "loss": 0.3202, "step": 1590 }, { "epoch": 0.4140786749482402, "grad_norm": 0.20662301778793335, "learning_rate": 4.310300207039338e-05, "loss": 0.3112, "step": 1600 }, { "epoch": 0.4166666666666667, "grad_norm": 0.2323458194732666, "learning_rate": 4.305986887508627e-05, "loss": 0.3208, "step": 1610 }, { "epoch": 0.4192546583850932, "grad_norm": 0.21535032987594604, "learning_rate": 4.3016735679779156e-05, "loss": 0.3248, "step": 1620 }, { "epoch": 0.4218426501035197, "grad_norm": 0.2329694777727127, "learning_rate": 4.297360248447205e-05, "loss": 0.3265, "step": 1630 }, { "epoch": 0.4244306418219462, "grad_norm": 0.22817054390907288, "learning_rate": 4.2930469289164946e-05, "loss": 0.333, "step": 1640 }, { "epoch": 0.42701863354037267, "grad_norm": 0.22383803129196167, "learning_rate": 4.2887336093857834e-05, "loss": 0.3293, "step": 1650 }, { "epoch": 0.42960662525879917, "grad_norm": 0.2358909696340561, "learning_rate": 4.284420289855073e-05, "loss": 0.3214, "step": 1660 }, { "epoch": 0.43219461697722567, "grad_norm": 0.2268248051404953, "learning_rate": 4.280106970324362e-05, "loss": 0.3223, "step": 1670 }, { "epoch": 0.43478260869565216, "grad_norm": 0.22738555073738098, "learning_rate": 4.2757936507936505e-05, "loss": 0.3326, "step": 1680 }, { "epoch": 0.43737060041407866, "grad_norm": 0.206409752368927, "learning_rate": 4.2714803312629406e-05, "loss": 0.3324, "step": 1690 }, { "epoch": 0.43995859213250516, "grad_norm": 0.24513110518455505, "learning_rate": 4.2671670117322294e-05, "loss": 0.324, "step": 1700 }, { "epoch": 0.44254658385093165, "grad_norm": 0.21265286207199097, "learning_rate": 4.262853692201518e-05, "loss": 0.3196, "step": 1710 }, { "epoch": 0.4451345755693582, "grad_norm": 0.24437908828258514, "learning_rate": 4.258540372670808e-05, "loss": 0.3248, "step": 1720 }, { "epoch": 0.4477225672877847, "grad_norm": 0.2429364174604416, "learning_rate": 4.2542270531400965e-05, "loss": 0.3271, "step": 1730 }, { "epoch": 0.4503105590062112, "grad_norm": 0.2221539318561554, "learning_rate": 4.249913733609386e-05, "loss": 0.3208, "step": 1740 }, { "epoch": 0.4528985507246377, "grad_norm": 0.24334411323070526, "learning_rate": 4.2456004140786755e-05, "loss": 0.3265, "step": 1750 }, { "epoch": 0.4554865424430642, "grad_norm": 0.23080968856811523, "learning_rate": 4.241287094547964e-05, "loss": 0.3151, "step": 1760 }, { "epoch": 0.4580745341614907, "grad_norm": 0.21543864905834198, "learning_rate": 4.236973775017253e-05, "loss": 0.3307, "step": 1770 }, { "epoch": 0.4606625258799172, "grad_norm": 0.25965455174446106, "learning_rate": 4.232660455486543e-05, "loss": 0.3257, "step": 1780 }, { "epoch": 0.4632505175983437, "grad_norm": 0.22642041742801666, "learning_rate": 4.228347135955832e-05, "loss": 0.3128, "step": 1790 }, { "epoch": 0.4658385093167702, "grad_norm": 0.24067285656929016, "learning_rate": 4.224033816425121e-05, "loss": 0.3051, "step": 1800 }, { "epoch": 0.4684265010351967, "grad_norm": 0.21340426802635193, "learning_rate": 4.21972049689441e-05, "loss": 0.3247, "step": 1810 }, { "epoch": 0.47101449275362317, "grad_norm": 0.22851435840129852, "learning_rate": 4.215407177363699e-05, "loss": 0.3161, "step": 1820 }, { "epoch": 0.47360248447204967, "grad_norm": 0.22671709954738617, "learning_rate": 4.2110938578329886e-05, "loss": 0.3197, "step": 1830 }, { "epoch": 0.47619047619047616, "grad_norm": 0.22201639413833618, "learning_rate": 4.2067805383022774e-05, "loss": 0.3166, "step": 1840 }, { "epoch": 0.4787784679089027, "grad_norm": 0.22487780451774597, "learning_rate": 4.202467218771567e-05, "loss": 0.3101, "step": 1850 }, { "epoch": 0.4813664596273292, "grad_norm": 0.2108740210533142, "learning_rate": 4.1981538992408556e-05, "loss": 0.3208, "step": 1860 }, { "epoch": 0.4839544513457557, "grad_norm": 0.22232213616371155, "learning_rate": 4.193840579710145e-05, "loss": 0.3248, "step": 1870 }, { "epoch": 0.4865424430641822, "grad_norm": 0.2102160006761551, "learning_rate": 4.1895272601794346e-05, "loss": 0.3112, "step": 1880 }, { "epoch": 0.4891304347826087, "grad_norm": 0.2171991467475891, "learning_rate": 4.1852139406487234e-05, "loss": 0.3201, "step": 1890 }, { "epoch": 0.4917184265010352, "grad_norm": 0.22287575900554657, "learning_rate": 4.180900621118012e-05, "loss": 0.3178, "step": 1900 }, { "epoch": 0.4943064182194617, "grad_norm": 0.23184508085250854, "learning_rate": 4.176587301587302e-05, "loss": 0.3156, "step": 1910 }, { "epoch": 0.4968944099378882, "grad_norm": 0.23387432098388672, "learning_rate": 4.172273982056591e-05, "loss": 0.3067, "step": 1920 }, { "epoch": 0.4994824016563147, "grad_norm": 0.2195172756910324, "learning_rate": 4.16796066252588e-05, "loss": 0.3149, "step": 1930 }, { "epoch": 0.5020703933747412, "grad_norm": 0.23636245727539062, "learning_rate": 4.1636473429951694e-05, "loss": 0.3335, "step": 1940 }, { "epoch": 0.5046583850931677, "grad_norm": 0.23955215513706207, "learning_rate": 4.159334023464458e-05, "loss": 0.3207, "step": 1950 }, { "epoch": 0.5072463768115942, "grad_norm": 0.23382526636123657, "learning_rate": 4.155020703933748e-05, "loss": 0.3203, "step": 1960 }, { "epoch": 0.5098343685300207, "grad_norm": 0.20842687785625458, "learning_rate": 4.150707384403037e-05, "loss": 0.3144, "step": 1970 }, { "epoch": 0.5124223602484472, "grad_norm": 0.230192631483078, "learning_rate": 4.146394064872326e-05, "loss": 0.3133, "step": 1980 }, { "epoch": 0.5150103519668737, "grad_norm": 0.29996928572654724, "learning_rate": 4.142080745341615e-05, "loss": 0.3145, "step": 1990 }, { "epoch": 0.5175983436853002, "grad_norm": 0.2318979650735855, "learning_rate": 4.137767425810904e-05, "loss": 0.3245, "step": 2000 }, { "epoch": 0.5201863354037267, "grad_norm": 0.25185373425483704, "learning_rate": 4.133454106280194e-05, "loss": 0.3179, "step": 2010 }, { "epoch": 0.5227743271221532, "grad_norm": 0.2322726994752884, "learning_rate": 4.1291407867494825e-05, "loss": 0.3242, "step": 2020 }, { "epoch": 0.5253623188405797, "grad_norm": 0.2243122011423111, "learning_rate": 4.124827467218772e-05, "loss": 0.3083, "step": 2030 }, { "epoch": 0.5279503105590062, "grad_norm": 0.23717275261878967, "learning_rate": 4.120514147688061e-05, "loss": 0.3168, "step": 2040 }, { "epoch": 0.5305383022774327, "grad_norm": 0.20267385244369507, "learning_rate": 4.11620082815735e-05, "loss": 0.3193, "step": 2050 }, { "epoch": 0.5331262939958592, "grad_norm": 0.2284848392009735, "learning_rate": 4.11188750862664e-05, "loss": 0.3189, "step": 2060 }, { "epoch": 0.5357142857142857, "grad_norm": 0.24308684468269348, "learning_rate": 4.1075741890959286e-05, "loss": 0.3135, "step": 2070 }, { "epoch": 0.5383022774327122, "grad_norm": 0.2117205113172531, "learning_rate": 4.1032608695652174e-05, "loss": 0.3168, "step": 2080 }, { "epoch": 0.5408902691511387, "grad_norm": 0.2043170928955078, "learning_rate": 4.098947550034506e-05, "loss": 0.3124, "step": 2090 }, { "epoch": 0.5434782608695652, "grad_norm": 0.22353848814964294, "learning_rate": 4.094634230503796e-05, "loss": 0.3148, "step": 2100 }, { "epoch": 0.5460662525879917, "grad_norm": 0.218248650431633, "learning_rate": 4.090320910973085e-05, "loss": 0.3152, "step": 2110 }, { "epoch": 0.5486542443064182, "grad_norm": 0.2373238354921341, "learning_rate": 4.086007591442374e-05, "loss": 0.3225, "step": 2120 }, { "epoch": 0.5512422360248447, "grad_norm": 0.213827446103096, "learning_rate": 4.0816942719116634e-05, "loss": 0.3058, "step": 2130 }, { "epoch": 0.5538302277432712, "grad_norm": 0.22780118882656097, "learning_rate": 4.077380952380952e-05, "loss": 0.3082, "step": 2140 }, { "epoch": 0.5564182194616977, "grad_norm": 0.22952698171138763, "learning_rate": 4.073067632850242e-05, "loss": 0.3186, "step": 2150 }, { "epoch": 0.5590062111801242, "grad_norm": 0.21455378830432892, "learning_rate": 4.068754313319531e-05, "loss": 0.3075, "step": 2160 }, { "epoch": 0.5615942028985508, "grad_norm": 0.24111777544021606, "learning_rate": 4.06444099378882e-05, "loss": 0.308, "step": 2170 }, { "epoch": 0.5641821946169773, "grad_norm": 0.21158650517463684, "learning_rate": 4.060127674258109e-05, "loss": 0.3235, "step": 2180 }, { "epoch": 0.5667701863354038, "grad_norm": 0.2563655972480774, "learning_rate": 4.055814354727398e-05, "loss": 0.3259, "step": 2190 }, { "epoch": 0.5693581780538303, "grad_norm": 0.2210429161787033, "learning_rate": 4.051501035196688e-05, "loss": 0.3127, "step": 2200 }, { "epoch": 0.5719461697722568, "grad_norm": 0.22102981805801392, "learning_rate": 4.0471877156659765e-05, "loss": 0.3369, "step": 2210 }, { "epoch": 0.5745341614906833, "grad_norm": 0.22597503662109375, "learning_rate": 4.042874396135266e-05, "loss": 0.3301, "step": 2220 }, { "epoch": 0.5771221532091098, "grad_norm": 0.23010863363742828, "learning_rate": 4.038561076604555e-05, "loss": 0.3317, "step": 2230 }, { "epoch": 0.5797101449275363, "grad_norm": 0.22111916542053223, "learning_rate": 4.034247757073844e-05, "loss": 0.3237, "step": 2240 }, { "epoch": 0.5822981366459627, "grad_norm": 0.2222849726676941, "learning_rate": 4.029934437543134e-05, "loss": 0.3071, "step": 2250 }, { "epoch": 0.5848861283643892, "grad_norm": 0.2242390662431717, "learning_rate": 4.0256211180124225e-05, "loss": 0.3149, "step": 2260 }, { "epoch": 0.5874741200828157, "grad_norm": 0.23385004699230194, "learning_rate": 4.0213077984817113e-05, "loss": 0.3046, "step": 2270 }, { "epoch": 0.5900621118012422, "grad_norm": 0.21285676956176758, "learning_rate": 4.016994478951001e-05, "loss": 0.311, "step": 2280 }, { "epoch": 0.5926501035196687, "grad_norm": 0.2448578029870987, "learning_rate": 4.01268115942029e-05, "loss": 0.3218, "step": 2290 }, { "epoch": 0.5952380952380952, "grad_norm": 0.21924273669719696, "learning_rate": 4.008367839889579e-05, "loss": 0.3103, "step": 2300 }, { "epoch": 0.5978260869565217, "grad_norm": 0.21449491381645203, "learning_rate": 4.0040545203588686e-05, "loss": 0.3096, "step": 2310 }, { "epoch": 0.6004140786749482, "grad_norm": 0.20816919207572937, "learning_rate": 3.9997412008281574e-05, "loss": 0.3173, "step": 2320 }, { "epoch": 0.6030020703933747, "grad_norm": 0.22972124814987183, "learning_rate": 3.995427881297447e-05, "loss": 0.317, "step": 2330 }, { "epoch": 0.6055900621118012, "grad_norm": 0.2285618633031845, "learning_rate": 3.9911145617667356e-05, "loss": 0.3058, "step": 2340 }, { "epoch": 0.6081780538302277, "grad_norm": 0.21451903879642487, "learning_rate": 3.986801242236025e-05, "loss": 0.3146, "step": 2350 }, { "epoch": 0.6107660455486542, "grad_norm": 0.21774156391620636, "learning_rate": 3.982487922705314e-05, "loss": 0.309, "step": 2360 }, { "epoch": 0.6133540372670807, "grad_norm": 0.22307203710079193, "learning_rate": 3.9781746031746034e-05, "loss": 0.3156, "step": 2370 }, { "epoch": 0.6159420289855072, "grad_norm": 0.24002742767333984, "learning_rate": 3.973861283643893e-05, "loss": 0.3051, "step": 2380 }, { "epoch": 0.6185300207039337, "grad_norm": 0.21402250230312347, "learning_rate": 3.969547964113182e-05, "loss": 0.3051, "step": 2390 }, { "epoch": 0.6211180124223602, "grad_norm": 0.2224249541759491, "learning_rate": 3.9652346445824705e-05, "loss": 0.3063, "step": 2400 }, { "epoch": 0.6237060041407867, "grad_norm": 0.22487872838974, "learning_rate": 3.96092132505176e-05, "loss": 0.3111, "step": 2410 }, { "epoch": 0.6262939958592133, "grad_norm": 0.2085420936346054, "learning_rate": 3.9566080055210494e-05, "loss": 0.3085, "step": 2420 }, { "epoch": 0.6288819875776398, "grad_norm": 0.25433823466300964, "learning_rate": 3.952294685990338e-05, "loss": 0.2949, "step": 2430 }, { "epoch": 0.6314699792960663, "grad_norm": 0.23129135370254517, "learning_rate": 3.947981366459628e-05, "loss": 0.3101, "step": 2440 }, { "epoch": 0.6340579710144928, "grad_norm": 0.20423346757888794, "learning_rate": 3.9436680469289165e-05, "loss": 0.3079, "step": 2450 }, { "epoch": 0.6366459627329193, "grad_norm": 0.21036268770694733, "learning_rate": 3.939354727398206e-05, "loss": 0.3095, "step": 2460 }, { "epoch": 0.6392339544513458, "grad_norm": 0.2136411815881729, "learning_rate": 3.9350414078674955e-05, "loss": 0.3132, "step": 2470 }, { "epoch": 0.6418219461697723, "grad_norm": 0.2161836177110672, "learning_rate": 3.930728088336784e-05, "loss": 0.3127, "step": 2480 }, { "epoch": 0.6444099378881988, "grad_norm": 0.2031654566526413, "learning_rate": 3.926414768806073e-05, "loss": 0.3076, "step": 2490 }, { "epoch": 0.6469979296066253, "grad_norm": 0.22428163886070251, "learning_rate": 3.9221014492753625e-05, "loss": 0.3169, "step": 2500 }, { "epoch": 0.6495859213250518, "grad_norm": 0.21044711768627167, "learning_rate": 3.917788129744652e-05, "loss": 0.3131, "step": 2510 }, { "epoch": 0.6521739130434783, "grad_norm": 0.22925981879234314, "learning_rate": 3.913474810213941e-05, "loss": 0.3048, "step": 2520 }, { "epoch": 0.6547619047619048, "grad_norm": 0.20247575640678406, "learning_rate": 3.90916149068323e-05, "loss": 0.3126, "step": 2530 }, { "epoch": 0.6573498964803313, "grad_norm": 0.22203323245048523, "learning_rate": 3.904848171152519e-05, "loss": 0.3129, "step": 2540 }, { "epoch": 0.6599378881987578, "grad_norm": 0.20326444506645203, "learning_rate": 3.900534851621808e-05, "loss": 0.3032, "step": 2550 }, { "epoch": 0.6625258799171843, "grad_norm": 0.20740875601768494, "learning_rate": 3.896221532091098e-05, "loss": 0.311, "step": 2560 }, { "epoch": 0.6651138716356108, "grad_norm": 0.2004554718732834, "learning_rate": 3.891908212560387e-05, "loss": 0.2979, "step": 2570 }, { "epoch": 0.6677018633540373, "grad_norm": 0.2173566371202469, "learning_rate": 3.8875948930296756e-05, "loss": 0.3123, "step": 2580 }, { "epoch": 0.6702898550724637, "grad_norm": 0.22329995036125183, "learning_rate": 3.883281573498965e-05, "loss": 0.307, "step": 2590 }, { "epoch": 0.6728778467908902, "grad_norm": 0.2122991532087326, "learning_rate": 3.878968253968254e-05, "loss": 0.3136, "step": 2600 }, { "epoch": 0.6754658385093167, "grad_norm": 0.2094232439994812, "learning_rate": 3.8746549344375434e-05, "loss": 0.3026, "step": 2610 }, { "epoch": 0.6780538302277432, "grad_norm": 0.23355460166931152, "learning_rate": 3.870341614906832e-05, "loss": 0.3047, "step": 2620 }, { "epoch": 0.6806418219461697, "grad_norm": 0.22046047449111938, "learning_rate": 3.866028295376122e-05, "loss": 0.3081, "step": 2630 }, { "epoch": 0.6832298136645962, "grad_norm": 0.20763075351715088, "learning_rate": 3.8617149758454105e-05, "loss": 0.2954, "step": 2640 }, { "epoch": 0.6858178053830227, "grad_norm": 0.2164374738931656, "learning_rate": 3.8574016563147e-05, "loss": 0.3046, "step": 2650 }, { "epoch": 0.6884057971014492, "grad_norm": 0.39815595746040344, "learning_rate": 3.8530883367839894e-05, "loss": 0.3071, "step": 2660 }, { "epoch": 0.6909937888198758, "grad_norm": 0.22524535655975342, "learning_rate": 3.848775017253278e-05, "loss": 0.3077, "step": 2670 }, { "epoch": 0.6935817805383023, "grad_norm": 0.2300335317850113, "learning_rate": 3.844461697722567e-05, "loss": 0.3087, "step": 2680 }, { "epoch": 0.6961697722567288, "grad_norm": 0.2301955223083496, "learning_rate": 3.8401483781918565e-05, "loss": 0.3141, "step": 2690 }, { "epoch": 0.6987577639751553, "grad_norm": 0.2139981985092163, "learning_rate": 3.835835058661146e-05, "loss": 0.2946, "step": 2700 }, { "epoch": 0.7013457556935818, "grad_norm": 0.2879856526851654, "learning_rate": 3.831521739130435e-05, "loss": 0.305, "step": 2710 }, { "epoch": 0.7039337474120083, "grad_norm": 0.21703338623046875, "learning_rate": 3.827208419599724e-05, "loss": 0.3122, "step": 2720 }, { "epoch": 0.7065217391304348, "grad_norm": 0.21222138404846191, "learning_rate": 3.822895100069013e-05, "loss": 0.3105, "step": 2730 }, { "epoch": 0.7091097308488613, "grad_norm": 0.22085881233215332, "learning_rate": 3.8185817805383025e-05, "loss": 0.3051, "step": 2740 }, { "epoch": 0.7116977225672878, "grad_norm": 0.2120286077260971, "learning_rate": 3.814268461007592e-05, "loss": 0.3161, "step": 2750 }, { "epoch": 0.7142857142857143, "grad_norm": 0.2191096544265747, "learning_rate": 3.809955141476881e-05, "loss": 0.3036, "step": 2760 }, { "epoch": 0.7168737060041408, "grad_norm": 0.19695864617824554, "learning_rate": 3.8056418219461696e-05, "loss": 0.3033, "step": 2770 }, { "epoch": 0.7194616977225673, "grad_norm": 0.2128693163394928, "learning_rate": 3.801328502415459e-05, "loss": 0.3106, "step": 2780 }, { "epoch": 0.7220496894409938, "grad_norm": 0.2155313342809677, "learning_rate": 3.7970151828847486e-05, "loss": 0.3061, "step": 2790 }, { "epoch": 0.7246376811594203, "grad_norm": 0.212551549077034, "learning_rate": 3.7927018633540374e-05, "loss": 0.3094, "step": 2800 }, { "epoch": 0.7272256728778468, "grad_norm": 0.21915146708488464, "learning_rate": 3.788388543823327e-05, "loss": 0.3208, "step": 2810 }, { "epoch": 0.7298136645962733, "grad_norm": 0.20482341945171356, "learning_rate": 3.7840752242926156e-05, "loss": 0.3107, "step": 2820 }, { "epoch": 0.7324016563146998, "grad_norm": 0.20442645251750946, "learning_rate": 3.779761904761905e-05, "loss": 0.3091, "step": 2830 }, { "epoch": 0.7349896480331263, "grad_norm": 0.22753652930259705, "learning_rate": 3.7754485852311946e-05, "loss": 0.2987, "step": 2840 }, { "epoch": 0.7375776397515528, "grad_norm": 0.21697330474853516, "learning_rate": 3.7711352657004834e-05, "loss": 0.3187, "step": 2850 }, { "epoch": 0.7401656314699793, "grad_norm": 0.23610110580921173, "learning_rate": 3.766821946169772e-05, "loss": 0.3155, "step": 2860 }, { "epoch": 0.7427536231884058, "grad_norm": 0.20602217316627502, "learning_rate": 3.762508626639062e-05, "loss": 0.3174, "step": 2870 }, { "epoch": 0.7453416149068323, "grad_norm": 0.207588329911232, "learning_rate": 3.758195307108351e-05, "loss": 0.3043, "step": 2880 }, { "epoch": 0.7479296066252588, "grad_norm": 0.2304246574640274, "learning_rate": 3.75388198757764e-05, "loss": 0.3038, "step": 2890 }, { "epoch": 0.7505175983436853, "grad_norm": 0.201001837849617, "learning_rate": 3.749568668046929e-05, "loss": 0.2988, "step": 2900 }, { "epoch": 0.7531055900621118, "grad_norm": 0.2201271653175354, "learning_rate": 3.745255348516218e-05, "loss": 0.2997, "step": 2910 }, { "epoch": 0.7556935817805382, "grad_norm": 0.18496201932430267, "learning_rate": 3.740942028985508e-05, "loss": 0.3031, "step": 2920 }, { "epoch": 0.7582815734989649, "grad_norm": 0.21594169735908508, "learning_rate": 3.7366287094547965e-05, "loss": 0.3067, "step": 2930 }, { "epoch": 0.7608695652173914, "grad_norm": 0.21081900596618652, "learning_rate": 3.732315389924086e-05, "loss": 0.2986, "step": 2940 }, { "epoch": 0.7634575569358178, "grad_norm": 0.2343406081199646, "learning_rate": 3.728002070393375e-05, "loss": 0.2988, "step": 2950 }, { "epoch": 0.7660455486542443, "grad_norm": 0.22097930312156677, "learning_rate": 3.7236887508626636e-05, "loss": 0.2976, "step": 2960 }, { "epoch": 0.7686335403726708, "grad_norm": 0.20536422729492188, "learning_rate": 3.719375431331954e-05, "loss": 0.3097, "step": 2970 }, { "epoch": 0.7712215320910973, "grad_norm": 0.21830050647258759, "learning_rate": 3.7150621118012425e-05, "loss": 0.3014, "step": 2980 }, { "epoch": 0.7738095238095238, "grad_norm": 0.2149060070514679, "learning_rate": 3.7107487922705313e-05, "loss": 0.3075, "step": 2990 }, { "epoch": 0.7763975155279503, "grad_norm": 0.19886595010757446, "learning_rate": 3.706435472739821e-05, "loss": 0.3144, "step": 3000 }, { "epoch": 0.7789855072463768, "grad_norm": 0.20575444400310516, "learning_rate": 3.7021221532091096e-05, "loss": 0.2999, "step": 3010 }, { "epoch": 0.7815734989648033, "grad_norm": 0.2196149230003357, "learning_rate": 3.697808833678399e-05, "loss": 0.3094, "step": 3020 }, { "epoch": 0.7841614906832298, "grad_norm": 0.21629364788532257, "learning_rate": 3.6934955141476886e-05, "loss": 0.308, "step": 3030 }, { "epoch": 0.7867494824016563, "grad_norm": 0.2137310653924942, "learning_rate": 3.6891821946169774e-05, "loss": 0.2986, "step": 3040 }, { "epoch": 0.7893374741200828, "grad_norm": 0.20199188590049744, "learning_rate": 3.684868875086266e-05, "loss": 0.3064, "step": 3050 }, { "epoch": 0.7919254658385093, "grad_norm": 0.21547473967075348, "learning_rate": 3.6805555555555556e-05, "loss": 0.3013, "step": 3060 }, { "epoch": 0.7945134575569358, "grad_norm": 0.2733719050884247, "learning_rate": 3.676242236024845e-05, "loss": 0.3029, "step": 3070 }, { "epoch": 0.7971014492753623, "grad_norm": 0.29441699385643005, "learning_rate": 3.671928916494134e-05, "loss": 0.3011, "step": 3080 }, { "epoch": 0.7996894409937888, "grad_norm": 0.21802516281604767, "learning_rate": 3.6676155969634234e-05, "loss": 0.296, "step": 3090 }, { "epoch": 0.8022774327122153, "grad_norm": 0.20233801007270813, "learning_rate": 3.663302277432712e-05, "loss": 0.306, "step": 3100 }, { "epoch": 0.8048654244306418, "grad_norm": 0.20554248988628387, "learning_rate": 3.658988957902002e-05, "loss": 0.309, "step": 3110 }, { "epoch": 0.8074534161490683, "grad_norm": 0.20972499251365662, "learning_rate": 3.6546756383712905e-05, "loss": 0.2979, "step": 3120 }, { "epoch": 0.8100414078674948, "grad_norm": 0.22347532212734222, "learning_rate": 3.65036231884058e-05, "loss": 0.3086, "step": 3130 }, { "epoch": 0.8126293995859213, "grad_norm": 0.20977842807769775, "learning_rate": 3.646048999309869e-05, "loss": 0.3035, "step": 3140 }, { "epoch": 0.8152173913043478, "grad_norm": 0.21505331993103027, "learning_rate": 3.641735679779158e-05, "loss": 0.2932, "step": 3150 }, { "epoch": 0.8178053830227743, "grad_norm": 0.19368258118629456, "learning_rate": 3.637422360248448e-05, "loss": 0.3048, "step": 3160 }, { "epoch": 0.8203933747412008, "grad_norm": 0.19016410410404205, "learning_rate": 3.6331090407177365e-05, "loss": 0.3049, "step": 3170 }, { "epoch": 0.8229813664596274, "grad_norm": 0.21808278560638428, "learning_rate": 3.628795721187025e-05, "loss": 0.2878, "step": 3180 }, { "epoch": 0.8255693581780539, "grad_norm": 0.20243072509765625, "learning_rate": 3.624482401656315e-05, "loss": 0.3085, "step": 3190 }, { "epoch": 0.8281573498964804, "grad_norm": 0.21477043628692627, "learning_rate": 3.620169082125604e-05, "loss": 0.3004, "step": 3200 }, { "epoch": 0.8307453416149069, "grad_norm": 0.1993860900402069, "learning_rate": 3.615855762594893e-05, "loss": 0.3021, "step": 3210 }, { "epoch": 0.8333333333333334, "grad_norm": 0.20048989355564117, "learning_rate": 3.6115424430641825e-05, "loss": 0.2965, "step": 3220 }, { "epoch": 0.8359213250517599, "grad_norm": 0.2104330211877823, "learning_rate": 3.6072291235334713e-05, "loss": 0.2941, "step": 3230 }, { "epoch": 0.8385093167701864, "grad_norm": 0.22518469393253326, "learning_rate": 3.602915804002761e-05, "loss": 0.3117, "step": 3240 }, { "epoch": 0.8410973084886129, "grad_norm": 0.20357628166675568, "learning_rate": 3.59860248447205e-05, "loss": 0.297, "step": 3250 }, { "epoch": 0.8436853002070394, "grad_norm": 0.23179523646831512, "learning_rate": 3.594289164941339e-05, "loss": 0.2973, "step": 3260 }, { "epoch": 0.8462732919254659, "grad_norm": 0.22814355790615082, "learning_rate": 3.589975845410628e-05, "loss": 0.2988, "step": 3270 }, { "epoch": 0.8488612836438924, "grad_norm": 0.2123464047908783, "learning_rate": 3.5856625258799174e-05, "loss": 0.295, "step": 3280 }, { "epoch": 0.8514492753623188, "grad_norm": 0.216710165143013, "learning_rate": 3.581349206349207e-05, "loss": 0.2984, "step": 3290 }, { "epoch": 0.8540372670807453, "grad_norm": 0.22064447402954102, "learning_rate": 3.5770358868184956e-05, "loss": 0.3082, "step": 3300 }, { "epoch": 0.8566252587991718, "grad_norm": 0.21648381650447845, "learning_rate": 3.572722567287785e-05, "loss": 0.2935, "step": 3310 }, { "epoch": 0.8592132505175983, "grad_norm": 0.20240244269371033, "learning_rate": 3.568409247757074e-05, "loss": 0.3108, "step": 3320 }, { "epoch": 0.8618012422360248, "grad_norm": 0.2264847606420517, "learning_rate": 3.5640959282263634e-05, "loss": 0.2998, "step": 3330 }, { "epoch": 0.8643892339544513, "grad_norm": 0.22666993737220764, "learning_rate": 3.559782608695653e-05, "loss": 0.313, "step": 3340 }, { "epoch": 0.8669772256728778, "grad_norm": 0.19765187799930573, "learning_rate": 3.555469289164942e-05, "loss": 0.3089, "step": 3350 }, { "epoch": 0.8695652173913043, "grad_norm": 0.21958757936954498, "learning_rate": 3.5511559696342305e-05, "loss": 0.2925, "step": 3360 }, { "epoch": 0.8721532091097308, "grad_norm": 0.21202827990055084, "learning_rate": 3.546842650103519e-05, "loss": 0.3076, "step": 3370 }, { "epoch": 0.8747412008281573, "grad_norm": 0.2199050486087799, "learning_rate": 3.5425293305728094e-05, "loss": 0.3054, "step": 3380 }, { "epoch": 0.8773291925465838, "grad_norm": 0.21413950622081757, "learning_rate": 3.538216011042098e-05, "loss": 0.3118, "step": 3390 }, { "epoch": 0.8799171842650103, "grad_norm": 0.24077115952968597, "learning_rate": 3.533902691511387e-05, "loss": 0.2901, "step": 3400 }, { "epoch": 0.8825051759834368, "grad_norm": 0.19935116171836853, "learning_rate": 3.5295893719806765e-05, "loss": 0.3031, "step": 3410 }, { "epoch": 0.8850931677018633, "grad_norm": 0.19705252349376678, "learning_rate": 3.525276052449965e-05, "loss": 0.3059, "step": 3420 }, { "epoch": 0.8876811594202898, "grad_norm": 0.19009386003017426, "learning_rate": 3.520962732919255e-05, "loss": 0.3127, "step": 3430 }, { "epoch": 0.8902691511387164, "grad_norm": 0.21051499247550964, "learning_rate": 3.516649413388544e-05, "loss": 0.2901, "step": 3440 }, { "epoch": 0.8928571428571429, "grad_norm": 0.20724424719810486, "learning_rate": 3.512336093857833e-05, "loss": 0.2997, "step": 3450 }, { "epoch": 0.8954451345755694, "grad_norm": 0.21805281937122345, "learning_rate": 3.508022774327122e-05, "loss": 0.3128, "step": 3460 }, { "epoch": 0.8980331262939959, "grad_norm": 0.21885521709918976, "learning_rate": 3.5037094547964113e-05, "loss": 0.3124, "step": 3470 }, { "epoch": 0.9006211180124224, "grad_norm": 0.2068813443183899, "learning_rate": 3.499396135265701e-05, "loss": 0.3038, "step": 3480 }, { "epoch": 0.9032091097308489, "grad_norm": 0.19752545654773712, "learning_rate": 3.4950828157349896e-05, "loss": 0.2945, "step": 3490 }, { "epoch": 0.9057971014492754, "grad_norm": 0.215012788772583, "learning_rate": 3.490769496204279e-05, "loss": 0.292, "step": 3500 }, { "epoch": 0.9083850931677019, "grad_norm": 0.20747481286525726, "learning_rate": 3.486456176673568e-05, "loss": 0.3053, "step": 3510 }, { "epoch": 0.9109730848861284, "grad_norm": 0.20236340165138245, "learning_rate": 3.4821428571428574e-05, "loss": 0.2889, "step": 3520 }, { "epoch": 0.9135610766045549, "grad_norm": 0.20136864483356476, "learning_rate": 3.477829537612147e-05, "loss": 0.3006, "step": 3530 }, { "epoch": 0.9161490683229814, "grad_norm": 0.191153421998024, "learning_rate": 3.4735162180814356e-05, "loss": 0.3053, "step": 3540 }, { "epoch": 0.9187370600414079, "grad_norm": 0.2002895325422287, "learning_rate": 3.4692028985507244e-05, "loss": 0.31, "step": 3550 }, { "epoch": 0.9213250517598344, "grad_norm": 0.20413583517074585, "learning_rate": 3.464889579020014e-05, "loss": 0.302, "step": 3560 }, { "epoch": 0.9239130434782609, "grad_norm": 0.2050822377204895, "learning_rate": 3.4605762594893034e-05, "loss": 0.2897, "step": 3570 }, { "epoch": 0.9265010351966874, "grad_norm": 0.22073592245578766, "learning_rate": 3.456262939958592e-05, "loss": 0.2921, "step": 3580 }, { "epoch": 0.9290890269151139, "grad_norm": 0.20891468226909637, "learning_rate": 3.451949620427882e-05, "loss": 0.3029, "step": 3590 }, { "epoch": 0.9316770186335404, "grad_norm": 0.19531622529029846, "learning_rate": 3.4476363008971705e-05, "loss": 0.3053, "step": 3600 }, { "epoch": 0.9342650103519669, "grad_norm": 0.19616830348968506, "learning_rate": 3.44332298136646e-05, "loss": 0.2917, "step": 3610 }, { "epoch": 0.9368530020703933, "grad_norm": 0.18781477212905884, "learning_rate": 3.439009661835749e-05, "loss": 0.2925, "step": 3620 }, { "epoch": 0.9394409937888198, "grad_norm": 0.1944524645805359, "learning_rate": 3.434696342305038e-05, "loss": 0.3008, "step": 3630 }, { "epoch": 0.9420289855072463, "grad_norm": 0.22709321975708008, "learning_rate": 3.430383022774327e-05, "loss": 0.2905, "step": 3640 }, { "epoch": 0.9446169772256728, "grad_norm": 0.20355206727981567, "learning_rate": 3.4260697032436165e-05, "loss": 0.2929, "step": 3650 }, { "epoch": 0.9472049689440993, "grad_norm": 0.18706360459327698, "learning_rate": 3.421756383712906e-05, "loss": 0.2871, "step": 3660 }, { "epoch": 0.9497929606625258, "grad_norm": 0.21115171909332275, "learning_rate": 3.417443064182195e-05, "loss": 0.3022, "step": 3670 }, { "epoch": 0.9523809523809523, "grad_norm": 0.19551020860671997, "learning_rate": 3.4131297446514836e-05, "loss": 0.3045, "step": 3680 }, { "epoch": 0.9549689440993789, "grad_norm": 0.20669394731521606, "learning_rate": 3.408816425120773e-05, "loss": 0.2981, "step": 3690 }, { "epoch": 0.9575569358178054, "grad_norm": 0.20334820449352264, "learning_rate": 3.4045031055900625e-05, "loss": 0.2926, "step": 3700 }, { "epoch": 0.9601449275362319, "grad_norm": 0.2088611125946045, "learning_rate": 3.4001897860593513e-05, "loss": 0.3081, "step": 3710 }, { "epoch": 0.9627329192546584, "grad_norm": 0.19300073385238647, "learning_rate": 3.395876466528641e-05, "loss": 0.2918, "step": 3720 }, { "epoch": 0.9653209109730849, "grad_norm": 0.20454266667366028, "learning_rate": 3.3915631469979296e-05, "loss": 0.301, "step": 3730 }, { "epoch": 0.9679089026915114, "grad_norm": 0.20170961320400238, "learning_rate": 3.3872498274672184e-05, "loss": 0.291, "step": 3740 }, { "epoch": 0.9704968944099379, "grad_norm": 0.18805700540542603, "learning_rate": 3.3829365079365086e-05, "loss": 0.3003, "step": 3750 }, { "epoch": 0.9730848861283644, "grad_norm": 0.2026686817407608, "learning_rate": 3.3786231884057974e-05, "loss": 0.3019, "step": 3760 }, { "epoch": 0.9756728778467909, "grad_norm": 0.21092383563518524, "learning_rate": 3.374309868875086e-05, "loss": 0.299, "step": 3770 }, { "epoch": 0.9782608695652174, "grad_norm": 0.20221301913261414, "learning_rate": 3.3699965493443756e-05, "loss": 0.3063, "step": 3780 }, { "epoch": 0.9808488612836439, "grad_norm": 0.20995080471038818, "learning_rate": 3.365683229813665e-05, "loss": 0.2861, "step": 3790 }, { "epoch": 0.9834368530020704, "grad_norm": 0.20308387279510498, "learning_rate": 3.361369910282954e-05, "loss": 0.2995, "step": 3800 }, { "epoch": 0.9860248447204969, "grad_norm": 0.2107851803302765, "learning_rate": 3.3570565907522434e-05, "loss": 0.3118, "step": 3810 }, { "epoch": 0.9886128364389234, "grad_norm": 0.22725960612297058, "learning_rate": 3.352743271221532e-05, "loss": 0.2925, "step": 3820 }, { "epoch": 0.9912008281573499, "grad_norm": 0.2126699984073639, "learning_rate": 3.348429951690821e-05, "loss": 0.2965, "step": 3830 }, { "epoch": 0.9937888198757764, "grad_norm": 0.1876717060804367, "learning_rate": 3.344116632160111e-05, "loss": 0.2863, "step": 3840 }, { "epoch": 0.9963768115942029, "grad_norm": 0.19136710464954376, "learning_rate": 3.3398033126294e-05, "loss": 0.2893, "step": 3850 }, { "epoch": 0.9989648033126294, "grad_norm": 0.20953720808029175, "learning_rate": 3.335489993098689e-05, "loss": 0.2902, "step": 3860 }, { "epoch": 1.0015527950310559, "grad_norm": 0.1966995745897293, "learning_rate": 3.3311766735679776e-05, "loss": 0.2897, "step": 3870 }, { "epoch": 1.0041407867494825, "grad_norm": 0.20064373314380646, "learning_rate": 3.326863354037267e-05, "loss": 0.2857, "step": 3880 }, { "epoch": 1.0067287784679089, "grad_norm": 0.21787600219249725, "learning_rate": 3.3225500345065565e-05, "loss": 0.2868, "step": 3890 }, { "epoch": 1.0093167701863355, "grad_norm": 0.20619697868824005, "learning_rate": 3.318236714975845e-05, "loss": 0.2872, "step": 3900 }, { "epoch": 1.0119047619047619, "grad_norm": 0.1993846893310547, "learning_rate": 3.313923395445135e-05, "loss": 0.2867, "step": 3910 }, { "epoch": 1.0144927536231885, "grad_norm": 0.21129782497882843, "learning_rate": 3.3096100759144236e-05, "loss": 0.2811, "step": 3920 }, { "epoch": 1.0170807453416149, "grad_norm": 0.20419564843177795, "learning_rate": 3.305296756383713e-05, "loss": 0.2745, "step": 3930 }, { "epoch": 1.0196687370600415, "grad_norm": 0.18639621138572693, "learning_rate": 3.3009834368530025e-05, "loss": 0.2866, "step": 3940 }, { "epoch": 1.0222567287784678, "grad_norm": 0.21988655626773834, "learning_rate": 3.2966701173222913e-05, "loss": 0.2854, "step": 3950 }, { "epoch": 1.0248447204968945, "grad_norm": 0.1930243968963623, "learning_rate": 3.29235679779158e-05, "loss": 0.2776, "step": 3960 }, { "epoch": 1.0274327122153208, "grad_norm": 0.1990118771791458, "learning_rate": 3.2880434782608696e-05, "loss": 0.2814, "step": 3970 }, { "epoch": 1.0300207039337475, "grad_norm": 0.19535651803016663, "learning_rate": 3.283730158730159e-05, "loss": 0.2853, "step": 3980 }, { "epoch": 1.0326086956521738, "grad_norm": 0.2245965152978897, "learning_rate": 3.279416839199448e-05, "loss": 0.2845, "step": 3990 }, { "epoch": 1.0351966873706004, "grad_norm": 0.20509561896324158, "learning_rate": 3.2751035196687374e-05, "loss": 0.2899, "step": 4000 }, { "epoch": 1.0377846790890268, "grad_norm": 0.21699312329292297, "learning_rate": 3.270790200138026e-05, "loss": 0.2811, "step": 4010 }, { "epoch": 1.0403726708074534, "grad_norm": 0.21619072556495667, "learning_rate": 3.2664768806073156e-05, "loss": 0.285, "step": 4020 }, { "epoch": 1.0429606625258798, "grad_norm": 0.20293161273002625, "learning_rate": 3.262163561076605e-05, "loss": 0.279, "step": 4030 }, { "epoch": 1.0455486542443064, "grad_norm": 0.2242215871810913, "learning_rate": 3.257850241545894e-05, "loss": 0.2835, "step": 4040 }, { "epoch": 1.0481366459627328, "grad_norm": 0.20812055468559265, "learning_rate": 3.253536922015183e-05, "loss": 0.2855, "step": 4050 }, { "epoch": 1.0507246376811594, "grad_norm": 0.2371463179588318, "learning_rate": 3.249223602484472e-05, "loss": 0.2925, "step": 4060 }, { "epoch": 1.0533126293995858, "grad_norm": 0.20706847310066223, "learning_rate": 3.244910282953762e-05, "loss": 0.2687, "step": 4070 }, { "epoch": 1.0559006211180124, "grad_norm": 0.23508736491203308, "learning_rate": 3.2405969634230505e-05, "loss": 0.2829, "step": 4080 }, { "epoch": 1.058488612836439, "grad_norm": 0.2040328085422516, "learning_rate": 3.23628364389234e-05, "loss": 0.2789, "step": 4090 }, { "epoch": 1.0610766045548654, "grad_norm": 0.20989084243774414, "learning_rate": 3.231970324361629e-05, "loss": 0.2866, "step": 4100 }, { "epoch": 1.063664596273292, "grad_norm": 0.20459486544132233, "learning_rate": 3.227657004830918e-05, "loss": 0.2839, "step": 4110 }, { "epoch": 1.0662525879917184, "grad_norm": 0.20525234937667847, "learning_rate": 3.223343685300207e-05, "loss": 0.2772, "step": 4120 }, { "epoch": 1.068840579710145, "grad_norm": 0.22750186920166016, "learning_rate": 3.2190303657694965e-05, "loss": 0.2868, "step": 4130 }, { "epoch": 1.0714285714285714, "grad_norm": 0.20014546811580658, "learning_rate": 3.214717046238785e-05, "loss": 0.2851, "step": 4140 }, { "epoch": 1.074016563146998, "grad_norm": 0.21684785187244415, "learning_rate": 3.210403726708074e-05, "loss": 0.2736, "step": 4150 }, { "epoch": 1.0766045548654244, "grad_norm": 0.21611499786376953, "learning_rate": 3.206090407177364e-05, "loss": 0.2838, "step": 4160 }, { "epoch": 1.079192546583851, "grad_norm": 0.22447840869426727, "learning_rate": 3.201777087646653e-05, "loss": 0.2759, "step": 4170 }, { "epoch": 1.0817805383022774, "grad_norm": 0.20259734988212585, "learning_rate": 3.197463768115942e-05, "loss": 0.2773, "step": 4180 }, { "epoch": 1.084368530020704, "grad_norm": 0.20831549167633057, "learning_rate": 3.1931504485852313e-05, "loss": 0.2791, "step": 4190 }, { "epoch": 1.0869565217391304, "grad_norm": 0.19910798966884613, "learning_rate": 3.188837129054521e-05, "loss": 0.2775, "step": 4200 }, { "epoch": 1.089544513457557, "grad_norm": 0.21417391300201416, "learning_rate": 3.1845238095238096e-05, "loss": 0.2813, "step": 4210 }, { "epoch": 1.0921325051759834, "grad_norm": 0.2036023885011673, "learning_rate": 3.180210489993099e-05, "loss": 0.2818, "step": 4220 }, { "epoch": 1.09472049689441, "grad_norm": 0.19122059643268585, "learning_rate": 3.175897170462388e-05, "loss": 0.2794, "step": 4230 }, { "epoch": 1.0973084886128364, "grad_norm": 0.2032182216644287, "learning_rate": 3.171583850931677e-05, "loss": 0.2797, "step": 4240 }, { "epoch": 1.099896480331263, "grad_norm": 0.22476878762245178, "learning_rate": 3.167270531400967e-05, "loss": 0.2919, "step": 4250 }, { "epoch": 1.1024844720496894, "grad_norm": 0.21088774502277374, "learning_rate": 3.1629572118702556e-05, "loss": 0.2816, "step": 4260 }, { "epoch": 1.105072463768116, "grad_norm": 0.2437673956155777, "learning_rate": 3.1586438923395444e-05, "loss": 0.2831, "step": 4270 }, { "epoch": 1.1076604554865424, "grad_norm": 0.21279916167259216, "learning_rate": 3.154330572808834e-05, "loss": 0.284, "step": 4280 }, { "epoch": 1.110248447204969, "grad_norm": 0.20391355454921722, "learning_rate": 3.150017253278123e-05, "loss": 0.2825, "step": 4290 }, { "epoch": 1.1128364389233953, "grad_norm": 0.21171489357948303, "learning_rate": 3.145703933747412e-05, "loss": 0.2775, "step": 4300 }, { "epoch": 1.115424430641822, "grad_norm": 0.2001040130853653, "learning_rate": 3.141390614216702e-05, "loss": 0.2831, "step": 4310 }, { "epoch": 1.1180124223602483, "grad_norm": 0.18857017159461975, "learning_rate": 3.1370772946859905e-05, "loss": 0.2695, "step": 4320 }, { "epoch": 1.120600414078675, "grad_norm": 0.21368324756622314, "learning_rate": 3.132763975155279e-05, "loss": 0.2731, "step": 4330 }, { "epoch": 1.1231884057971016, "grad_norm": 0.20488175749778748, "learning_rate": 3.128450655624569e-05, "loss": 0.284, "step": 4340 }, { "epoch": 1.125776397515528, "grad_norm": 0.18714292347431183, "learning_rate": 3.124137336093858e-05, "loss": 0.2845, "step": 4350 }, { "epoch": 1.1283643892339545, "grad_norm": 0.20056986808776855, "learning_rate": 3.119824016563147e-05, "loss": 0.2759, "step": 4360 }, { "epoch": 1.130952380952381, "grad_norm": 0.1975480616092682, "learning_rate": 3.1155106970324365e-05, "loss": 0.2874, "step": 4370 }, { "epoch": 1.1335403726708075, "grad_norm": 0.20651063323020935, "learning_rate": 3.111197377501725e-05, "loss": 0.2783, "step": 4380 }, { "epoch": 1.136128364389234, "grad_norm": 0.212539941072464, "learning_rate": 3.106884057971015e-05, "loss": 0.2946, "step": 4390 }, { "epoch": 1.1387163561076605, "grad_norm": 0.20712485909461975, "learning_rate": 3.1025707384403036e-05, "loss": 0.2874, "step": 4400 }, { "epoch": 1.141304347826087, "grad_norm": 0.20916777849197388, "learning_rate": 3.098257418909593e-05, "loss": 0.2902, "step": 4410 }, { "epoch": 1.1438923395445135, "grad_norm": 0.18801477551460266, "learning_rate": 3.093944099378882e-05, "loss": 0.2807, "step": 4420 }, { "epoch": 1.14648033126294, "grad_norm": 0.21907158195972443, "learning_rate": 3.0896307798481713e-05, "loss": 0.2837, "step": 4430 }, { "epoch": 1.1490683229813665, "grad_norm": 0.20964211225509644, "learning_rate": 3.085317460317461e-05, "loss": 0.2811, "step": 4440 }, { "epoch": 1.151656314699793, "grad_norm": 0.19841931760311127, "learning_rate": 3.0810041407867496e-05, "loss": 0.2816, "step": 4450 }, { "epoch": 1.1542443064182195, "grad_norm": 0.20696336030960083, "learning_rate": 3.0766908212560384e-05, "loss": 0.2857, "step": 4460 }, { "epoch": 1.156832298136646, "grad_norm": 0.21968398988246918, "learning_rate": 3.072377501725328e-05, "loss": 0.2911, "step": 4470 }, { "epoch": 1.1594202898550725, "grad_norm": 0.2119816243648529, "learning_rate": 3.0680641821946174e-05, "loss": 0.2836, "step": 4480 }, { "epoch": 1.162008281573499, "grad_norm": 0.20051179826259613, "learning_rate": 3.063750862663906e-05, "loss": 0.2807, "step": 4490 }, { "epoch": 1.1645962732919255, "grad_norm": 0.20480915904045105, "learning_rate": 3.0594375431331956e-05, "loss": 0.2799, "step": 4500 }, { "epoch": 1.1671842650103519, "grad_norm": 0.1936984360218048, "learning_rate": 3.0551242236024844e-05, "loss": 0.2841, "step": 4510 }, { "epoch": 1.1697722567287785, "grad_norm": 0.17650452256202698, "learning_rate": 3.0508109040717736e-05, "loss": 0.2796, "step": 4520 }, { "epoch": 1.1723602484472049, "grad_norm": 0.2266344577074051, "learning_rate": 3.046497584541063e-05, "loss": 0.2839, "step": 4530 }, { "epoch": 1.1749482401656315, "grad_norm": 0.21390888094902039, "learning_rate": 3.0421842650103522e-05, "loss": 0.29, "step": 4540 }, { "epoch": 1.177536231884058, "grad_norm": 0.20884661376476288, "learning_rate": 3.037870945479641e-05, "loss": 0.2954, "step": 4550 }, { "epoch": 1.1801242236024845, "grad_norm": 0.20614804327487946, "learning_rate": 3.0335576259489308e-05, "loss": 0.284, "step": 4560 }, { "epoch": 1.1827122153209109, "grad_norm": 0.22237960994243622, "learning_rate": 3.0292443064182196e-05, "loss": 0.2769, "step": 4570 }, { "epoch": 1.1853002070393375, "grad_norm": 0.20414669811725616, "learning_rate": 3.0249309868875088e-05, "loss": 0.288, "step": 4580 }, { "epoch": 1.187888198757764, "grad_norm": 0.21255841851234436, "learning_rate": 3.0206176673567982e-05, "loss": 0.2908, "step": 4590 }, { "epoch": 1.1904761904761905, "grad_norm": 0.1876077502965927, "learning_rate": 3.016304347826087e-05, "loss": 0.2814, "step": 4600 }, { "epoch": 1.193064182194617, "grad_norm": 0.2036699801683426, "learning_rate": 3.0119910282953762e-05, "loss": 0.2773, "step": 4610 }, { "epoch": 1.1956521739130435, "grad_norm": 0.206691175699234, "learning_rate": 3.0076777087646656e-05, "loss": 0.2873, "step": 4620 }, { "epoch": 1.19824016563147, "grad_norm": 0.1894364207983017, "learning_rate": 3.0033643892339548e-05, "loss": 0.2776, "step": 4630 }, { "epoch": 1.2008281573498965, "grad_norm": 0.2230517864227295, "learning_rate": 2.9990510697032436e-05, "loss": 0.2913, "step": 4640 }, { "epoch": 1.203416149068323, "grad_norm": 0.21492069959640503, "learning_rate": 2.9947377501725327e-05, "loss": 0.2735, "step": 4650 }, { "epoch": 1.2060041407867494, "grad_norm": 0.22130122780799866, "learning_rate": 2.9904244306418222e-05, "loss": 0.2805, "step": 4660 }, { "epoch": 1.208592132505176, "grad_norm": 0.2193043977022171, "learning_rate": 2.9861111111111113e-05, "loss": 0.2823, "step": 4670 }, { "epoch": 1.2111801242236024, "grad_norm": 0.2020953744649887, "learning_rate": 2.9817977915804e-05, "loss": 0.2746, "step": 4680 }, { "epoch": 1.213768115942029, "grad_norm": 0.19789685308933258, "learning_rate": 2.9774844720496896e-05, "loss": 0.2789, "step": 4690 }, { "epoch": 1.2163561076604554, "grad_norm": 0.23847202956676483, "learning_rate": 2.9731711525189788e-05, "loss": 0.2858, "step": 4700 }, { "epoch": 1.218944099378882, "grad_norm": 0.21631298959255219, "learning_rate": 2.9688578329882676e-05, "loss": 0.2783, "step": 4710 }, { "epoch": 1.2215320910973084, "grad_norm": 0.19795972108840942, "learning_rate": 2.9645445134575574e-05, "loss": 0.2852, "step": 4720 }, { "epoch": 1.224120082815735, "grad_norm": 0.2208348512649536, "learning_rate": 2.9602311939268462e-05, "loss": 0.2757, "step": 4730 }, { "epoch": 1.2267080745341614, "grad_norm": 0.2082773745059967, "learning_rate": 2.9559178743961353e-05, "loss": 0.2688, "step": 4740 }, { "epoch": 1.229296066252588, "grad_norm": 0.208180770277977, "learning_rate": 2.9516045548654248e-05, "loss": 0.2778, "step": 4750 }, { "epoch": 1.2318840579710144, "grad_norm": 0.2316160351037979, "learning_rate": 2.9472912353347136e-05, "loss": 0.283, "step": 4760 }, { "epoch": 1.234472049689441, "grad_norm": 0.20870406925678253, "learning_rate": 2.9429779158040027e-05, "loss": 0.2833, "step": 4770 }, { "epoch": 1.2370600414078674, "grad_norm": 0.18954645097255707, "learning_rate": 2.9386645962732922e-05, "loss": 0.2747, "step": 4780 }, { "epoch": 1.239648033126294, "grad_norm": 0.19666893780231476, "learning_rate": 2.9343512767425813e-05, "loss": 0.2795, "step": 4790 }, { "epoch": 1.2422360248447206, "grad_norm": 0.20144566893577576, "learning_rate": 2.93003795721187e-05, "loss": 0.2831, "step": 4800 }, { "epoch": 1.244824016563147, "grad_norm": 0.20662471652030945, "learning_rate": 2.92572463768116e-05, "loss": 0.2806, "step": 4810 }, { "epoch": 1.2474120082815734, "grad_norm": 0.20573922991752625, "learning_rate": 2.9214113181504488e-05, "loss": 0.2781, "step": 4820 }, { "epoch": 1.25, "grad_norm": 0.1996840089559555, "learning_rate": 2.917097998619738e-05, "loss": 0.2767, "step": 4830 }, { "epoch": 1.2525879917184266, "grad_norm": 0.22875703871250153, "learning_rate": 2.9127846790890274e-05, "loss": 0.2793, "step": 4840 }, { "epoch": 1.255175983436853, "grad_norm": 0.19148211181163788, "learning_rate": 2.9084713595583162e-05, "loss": 0.2734, "step": 4850 }, { "epoch": 1.2577639751552794, "grad_norm": 0.2000264972448349, "learning_rate": 2.9041580400276053e-05, "loss": 0.2747, "step": 4860 }, { "epoch": 1.260351966873706, "grad_norm": 0.20301419496536255, "learning_rate": 2.8998447204968948e-05, "loss": 0.2824, "step": 4870 }, { "epoch": 1.2629399585921326, "grad_norm": 0.20807796716690063, "learning_rate": 2.895531400966184e-05, "loss": 0.2737, "step": 4880 }, { "epoch": 1.265527950310559, "grad_norm": 0.21532008051872253, "learning_rate": 2.8912180814354727e-05, "loss": 0.2951, "step": 4890 }, { "epoch": 1.2681159420289856, "grad_norm": 0.20902346074581146, "learning_rate": 2.886904761904762e-05, "loss": 0.2806, "step": 4900 }, { "epoch": 1.270703933747412, "grad_norm": 0.20580431818962097, "learning_rate": 2.8825914423740513e-05, "loss": 0.2942, "step": 4910 }, { "epoch": 1.2732919254658386, "grad_norm": 0.22487808763980865, "learning_rate": 2.87827812284334e-05, "loss": 0.2797, "step": 4920 }, { "epoch": 1.275879917184265, "grad_norm": 0.20283977687358856, "learning_rate": 2.8739648033126293e-05, "loss": 0.2718, "step": 4930 }, { "epoch": 1.2784679089026916, "grad_norm": 0.18678729236125946, "learning_rate": 2.8696514837819188e-05, "loss": 0.287, "step": 4940 }, { "epoch": 1.281055900621118, "grad_norm": 0.20551638305187225, "learning_rate": 2.865338164251208e-05, "loss": 0.2768, "step": 4950 }, { "epoch": 1.2836438923395446, "grad_norm": 0.208012193441391, "learning_rate": 2.8610248447204967e-05, "loss": 0.2756, "step": 4960 }, { "epoch": 1.286231884057971, "grad_norm": 0.19745701551437378, "learning_rate": 2.8567115251897865e-05, "loss": 0.2877, "step": 4970 }, { "epoch": 1.2888198757763976, "grad_norm": 0.19310729205608368, "learning_rate": 2.8523982056590753e-05, "loss": 0.2751, "step": 4980 }, { "epoch": 1.291407867494824, "grad_norm": 0.19812437891960144, "learning_rate": 2.8480848861283644e-05, "loss": 0.2637, "step": 4990 }, { "epoch": 1.2939958592132506, "grad_norm": 0.20688922703266144, "learning_rate": 2.843771566597654e-05, "loss": 0.2833, "step": 5000 }, { "epoch": 1.296583850931677, "grad_norm": 0.19578444957733154, "learning_rate": 2.8394582470669427e-05, "loss": 0.2741, "step": 5010 }, { "epoch": 1.2991718426501035, "grad_norm": 0.2112204134464264, "learning_rate": 2.835144927536232e-05, "loss": 0.2827, "step": 5020 }, { "epoch": 1.30175983436853, "grad_norm": 0.20422010123729706, "learning_rate": 2.8308316080055213e-05, "loss": 0.2806, "step": 5030 }, { "epoch": 1.3043478260869565, "grad_norm": 0.22117148339748383, "learning_rate": 2.8265182884748105e-05, "loss": 0.2828, "step": 5040 }, { "epoch": 1.3069358178053831, "grad_norm": 0.20923538506031036, "learning_rate": 2.8222049689440993e-05, "loss": 0.2896, "step": 5050 }, { "epoch": 1.3095238095238095, "grad_norm": 0.2134866565465927, "learning_rate": 2.8178916494133888e-05, "loss": 0.2799, "step": 5060 }, { "epoch": 1.312111801242236, "grad_norm": 0.20939190685749054, "learning_rate": 2.813578329882678e-05, "loss": 0.2778, "step": 5070 }, { "epoch": 1.3146997929606625, "grad_norm": 0.20852287113666534, "learning_rate": 2.809265010351967e-05, "loss": 0.2712, "step": 5080 }, { "epoch": 1.3172877846790891, "grad_norm": 0.18680156767368317, "learning_rate": 2.8049516908212565e-05, "loss": 0.288, "step": 5090 }, { "epoch": 1.3198757763975155, "grad_norm": 0.19748736917972565, "learning_rate": 2.8006383712905453e-05, "loss": 0.2727, "step": 5100 }, { "epoch": 1.322463768115942, "grad_norm": 0.19935381412506104, "learning_rate": 2.7963250517598344e-05, "loss": 0.2727, "step": 5110 }, { "epoch": 1.3250517598343685, "grad_norm": 0.20346301794052124, "learning_rate": 2.792011732229124e-05, "loss": 0.2852, "step": 5120 }, { "epoch": 1.3276397515527951, "grad_norm": 0.20282778143882751, "learning_rate": 2.787698412698413e-05, "loss": 0.29, "step": 5130 }, { "epoch": 1.3302277432712215, "grad_norm": 0.20782440900802612, "learning_rate": 2.783385093167702e-05, "loss": 0.2741, "step": 5140 }, { "epoch": 1.3328157349896481, "grad_norm": 0.20595425367355347, "learning_rate": 2.779071773636991e-05, "loss": 0.2819, "step": 5150 }, { "epoch": 1.3354037267080745, "grad_norm": 0.18362931907176971, "learning_rate": 2.7747584541062805e-05, "loss": 0.2826, "step": 5160 }, { "epoch": 1.337991718426501, "grad_norm": 0.20354659855365753, "learning_rate": 2.7704451345755693e-05, "loss": 0.2703, "step": 5170 }, { "epoch": 1.3405797101449275, "grad_norm": 0.2250794768333435, "learning_rate": 2.7665631469979297e-05, "loss": 0.269, "step": 5180 }, { "epoch": 1.343167701863354, "grad_norm": 0.18797485530376434, "learning_rate": 2.7622498274672188e-05, "loss": 0.2834, "step": 5190 }, { "epoch": 1.3457556935817805, "grad_norm": 0.18781961500644684, "learning_rate": 2.7579365079365083e-05, "loss": 0.2626, "step": 5200 }, { "epoch": 1.348343685300207, "grad_norm": 0.21970486640930176, "learning_rate": 2.753623188405797e-05, "loss": 0.2794, "step": 5210 }, { "epoch": 1.3509316770186335, "grad_norm": 0.1888144314289093, "learning_rate": 2.7493098688750862e-05, "loss": 0.2756, "step": 5220 }, { "epoch": 1.35351966873706, "grad_norm": 0.21122311055660248, "learning_rate": 2.7449965493443757e-05, "loss": 0.2759, "step": 5230 }, { "epoch": 1.3561076604554865, "grad_norm": 0.20177538692951202, "learning_rate": 2.740683229813665e-05, "loss": 0.2759, "step": 5240 }, { "epoch": 1.358695652173913, "grad_norm": 0.20434828102588654, "learning_rate": 2.7363699102829536e-05, "loss": 0.2769, "step": 5250 }, { "epoch": 1.3612836438923395, "grad_norm": 0.19432629644870758, "learning_rate": 2.7320565907522435e-05, "loss": 0.2755, "step": 5260 }, { "epoch": 1.363871635610766, "grad_norm": 0.21479980647563934, "learning_rate": 2.7277432712215323e-05, "loss": 0.2882, "step": 5270 }, { "epoch": 1.3664596273291925, "grad_norm": 0.20082104206085205, "learning_rate": 2.7234299516908214e-05, "loss": 0.2759, "step": 5280 }, { "epoch": 1.369047619047619, "grad_norm": 0.22913457453250885, "learning_rate": 2.719116632160111e-05, "loss": 0.2841, "step": 5290 }, { "epoch": 1.3716356107660457, "grad_norm": 0.19600068032741547, "learning_rate": 2.7148033126293997e-05, "loss": 0.2819, "step": 5300 }, { "epoch": 1.374223602484472, "grad_norm": 0.18606539070606232, "learning_rate": 2.7104899930986888e-05, "loss": 0.2712, "step": 5310 }, { "epoch": 1.3768115942028984, "grad_norm": 0.2032352238893509, "learning_rate": 2.7061766735679776e-05, "loss": 0.265, "step": 5320 }, { "epoch": 1.379399585921325, "grad_norm": 0.20583760738372803, "learning_rate": 2.7018633540372674e-05, "loss": 0.2814, "step": 5330 }, { "epoch": 1.3819875776397517, "grad_norm": 0.20506004989147186, "learning_rate": 2.6975500345065562e-05, "loss": 0.2849, "step": 5340 }, { "epoch": 1.384575569358178, "grad_norm": 0.20336943864822388, "learning_rate": 2.6932367149758454e-05, "loss": 0.2861, "step": 5350 }, { "epoch": 1.3871635610766044, "grad_norm": 0.21229679882526398, "learning_rate": 2.688923395445135e-05, "loss": 0.2848, "step": 5360 }, { "epoch": 1.389751552795031, "grad_norm": 0.1943487524986267, "learning_rate": 2.684610075914424e-05, "loss": 0.2813, "step": 5370 }, { "epoch": 1.3923395445134576, "grad_norm": 0.2057686150074005, "learning_rate": 2.6802967563837128e-05, "loss": 0.2774, "step": 5380 }, { "epoch": 1.394927536231884, "grad_norm": 0.18183177709579468, "learning_rate": 2.6759834368530023e-05, "loss": 0.2814, "step": 5390 }, { "epoch": 1.3975155279503104, "grad_norm": 0.21541506052017212, "learning_rate": 2.6716701173222914e-05, "loss": 0.2788, "step": 5400 }, { "epoch": 1.400103519668737, "grad_norm": 0.19158130884170532, "learning_rate": 2.6673567977915802e-05, "loss": 0.2898, "step": 5410 }, { "epoch": 1.4026915113871636, "grad_norm": 0.19460628926753998, "learning_rate": 2.66304347826087e-05, "loss": 0.276, "step": 5420 }, { "epoch": 1.40527950310559, "grad_norm": 0.19198273122310638, "learning_rate": 2.6587301587301588e-05, "loss": 0.2766, "step": 5430 }, { "epoch": 1.4078674948240166, "grad_norm": 0.20514032244682312, "learning_rate": 2.654416839199448e-05, "loss": 0.2893, "step": 5440 }, { "epoch": 1.410455486542443, "grad_norm": 0.20267118513584137, "learning_rate": 2.6501035196687374e-05, "loss": 0.2787, "step": 5450 }, { "epoch": 1.4130434782608696, "grad_norm": 0.2155541032552719, "learning_rate": 2.6457902001380262e-05, "loss": 0.2823, "step": 5460 }, { "epoch": 1.415631469979296, "grad_norm": 0.21240340173244476, "learning_rate": 2.6414768806073154e-05, "loss": 0.2793, "step": 5470 }, { "epoch": 1.4182194616977226, "grad_norm": 0.20921996235847473, "learning_rate": 2.637163561076605e-05, "loss": 0.2802, "step": 5480 }, { "epoch": 1.420807453416149, "grad_norm": 0.20031003654003143, "learning_rate": 2.632850241545894e-05, "loss": 0.2691, "step": 5490 }, { "epoch": 1.4233954451345756, "grad_norm": 0.1978559046983719, "learning_rate": 2.6285369220151828e-05, "loss": 0.2783, "step": 5500 }, { "epoch": 1.425983436853002, "grad_norm": 0.20545430481433868, "learning_rate": 2.6242236024844723e-05, "loss": 0.283, "step": 5510 }, { "epoch": 1.4285714285714286, "grad_norm": 0.24126268923282623, "learning_rate": 2.6199102829537614e-05, "loss": 0.2828, "step": 5520 }, { "epoch": 1.431159420289855, "grad_norm": 0.21742559969425201, "learning_rate": 2.6155969634230505e-05, "loss": 0.2789, "step": 5530 }, { "epoch": 1.4337474120082816, "grad_norm": 0.2103467881679535, "learning_rate": 2.61128364389234e-05, "loss": 0.2822, "step": 5540 }, { "epoch": 1.4363354037267082, "grad_norm": 0.19214099645614624, "learning_rate": 2.6069703243616288e-05, "loss": 0.2697, "step": 5550 }, { "epoch": 1.4389233954451346, "grad_norm": 0.21156474947929382, "learning_rate": 2.602657004830918e-05, "loss": 0.2765, "step": 5560 }, { "epoch": 1.441511387163561, "grad_norm": 0.2017282396554947, "learning_rate": 2.5983436853002067e-05, "loss": 0.2782, "step": 5570 }, { "epoch": 1.4440993788819876, "grad_norm": 0.20170588791370392, "learning_rate": 2.5940303657694966e-05, "loss": 0.2781, "step": 5580 }, { "epoch": 1.4466873706004142, "grad_norm": 0.27326133847236633, "learning_rate": 2.5897170462387854e-05, "loss": 0.2826, "step": 5590 }, { "epoch": 1.4492753623188406, "grad_norm": 0.19904714822769165, "learning_rate": 2.5854037267080745e-05, "loss": 0.2753, "step": 5600 }, { "epoch": 1.451863354037267, "grad_norm": 0.205663800239563, "learning_rate": 2.581090407177364e-05, "loss": 0.2897, "step": 5610 }, { "epoch": 1.4544513457556936, "grad_norm": 0.18975305557250977, "learning_rate": 2.5767770876466528e-05, "loss": 0.2815, "step": 5620 }, { "epoch": 1.4570393374741202, "grad_norm": 0.21230220794677734, "learning_rate": 2.572463768115942e-05, "loss": 0.2919, "step": 5630 }, { "epoch": 1.4596273291925466, "grad_norm": 0.20411543548107147, "learning_rate": 2.5681504485852314e-05, "loss": 0.2901, "step": 5640 }, { "epoch": 1.462215320910973, "grad_norm": 0.1978524625301361, "learning_rate": 2.5638371290545205e-05, "loss": 0.2842, "step": 5650 }, { "epoch": 1.4648033126293996, "grad_norm": 0.18695814907550812, "learning_rate": 2.5595238095238093e-05, "loss": 0.2761, "step": 5660 }, { "epoch": 1.4673913043478262, "grad_norm": 0.21033859252929688, "learning_rate": 2.5552104899930988e-05, "loss": 0.2782, "step": 5670 }, { "epoch": 1.4699792960662525, "grad_norm": 0.19550427794456482, "learning_rate": 2.550897170462388e-05, "loss": 0.2802, "step": 5680 }, { "epoch": 1.4725672877846792, "grad_norm": 0.21018573641777039, "learning_rate": 2.546583850931677e-05, "loss": 0.2751, "step": 5690 }, { "epoch": 1.4751552795031055, "grad_norm": 0.1967909336090088, "learning_rate": 2.5422705314009666e-05, "loss": 0.2759, "step": 5700 }, { "epoch": 1.4777432712215322, "grad_norm": 0.1938430666923523, "learning_rate": 2.5379572118702554e-05, "loss": 0.2837, "step": 5710 }, { "epoch": 1.4803312629399585, "grad_norm": 0.2072574943304062, "learning_rate": 2.5336438923395445e-05, "loss": 0.2814, "step": 5720 }, { "epoch": 1.4829192546583851, "grad_norm": 0.19119413197040558, "learning_rate": 2.529330572808834e-05, "loss": 0.2781, "step": 5730 }, { "epoch": 1.4855072463768115, "grad_norm": 0.19592414796352386, "learning_rate": 2.525017253278123e-05, "loss": 0.2761, "step": 5740 }, { "epoch": 1.4880952380952381, "grad_norm": 0.20186804234981537, "learning_rate": 2.520703933747412e-05, "loss": 0.2721, "step": 5750 }, { "epoch": 1.4906832298136645, "grad_norm": 0.19301468133926392, "learning_rate": 2.5163906142167014e-05, "loss": 0.2759, "step": 5760 }, { "epoch": 1.4932712215320911, "grad_norm": 0.19003848731517792, "learning_rate": 2.5120772946859905e-05, "loss": 0.2808, "step": 5770 }, { "epoch": 1.4958592132505175, "grad_norm": 0.21416200697422028, "learning_rate": 2.5077639751552793e-05, "loss": 0.2679, "step": 5780 }, { "epoch": 1.4984472049689441, "grad_norm": 0.21335680782794952, "learning_rate": 2.503450655624569e-05, "loss": 0.2737, "step": 5790 }, { "epoch": 1.5010351966873707, "grad_norm": 0.1855931133031845, "learning_rate": 2.499137336093858e-05, "loss": 0.2787, "step": 5800 }, { "epoch": 1.5036231884057971, "grad_norm": 0.20533353090286255, "learning_rate": 2.494824016563147e-05, "loss": 0.2781, "step": 5810 }, { "epoch": 1.5062111801242235, "grad_norm": 0.18676544725894928, "learning_rate": 2.4905106970324362e-05, "loss": 0.2737, "step": 5820 }, { "epoch": 1.50879917184265, "grad_norm": 0.2079932987689972, "learning_rate": 2.4861973775017257e-05, "loss": 0.2647, "step": 5830 }, { "epoch": 1.5113871635610767, "grad_norm": 0.1954832375049591, "learning_rate": 2.4818840579710145e-05, "loss": 0.2774, "step": 5840 }, { "epoch": 1.513975155279503, "grad_norm": 0.21631035208702087, "learning_rate": 2.4775707384403036e-05, "loss": 0.2775, "step": 5850 }, { "epoch": 1.5165631469979295, "grad_norm": 0.19149789214134216, "learning_rate": 2.473257418909593e-05, "loss": 0.2783, "step": 5860 }, { "epoch": 1.519151138716356, "grad_norm": 0.21757644414901733, "learning_rate": 2.468944099378882e-05, "loss": 0.2729, "step": 5870 }, { "epoch": 1.5217391304347827, "grad_norm": 0.20997533202171326, "learning_rate": 2.4646307798481714e-05, "loss": 0.2821, "step": 5880 }, { "epoch": 1.524327122153209, "grad_norm": 0.19383445382118225, "learning_rate": 2.4603174603174602e-05, "loss": 0.2778, "step": 5890 }, { "epoch": 1.5269151138716355, "grad_norm": 0.19153636693954468, "learning_rate": 2.4560041407867497e-05, "loss": 0.2823, "step": 5900 }, { "epoch": 1.529503105590062, "grad_norm": 0.20183731615543365, "learning_rate": 2.4516908212560388e-05, "loss": 0.284, "step": 5910 }, { "epoch": 1.5320910973084887, "grad_norm": 0.19239327311515808, "learning_rate": 2.447377501725328e-05, "loss": 0.2744, "step": 5920 }, { "epoch": 1.534679089026915, "grad_norm": 0.19152939319610596, "learning_rate": 2.443064182194617e-05, "loss": 0.274, "step": 5930 }, { "epoch": 1.5372670807453415, "grad_norm": 0.20555827021598816, "learning_rate": 2.4387508626639062e-05, "loss": 0.2755, "step": 5940 }, { "epoch": 1.539855072463768, "grad_norm": 0.1939895898103714, "learning_rate": 2.4344375431331954e-05, "loss": 0.2671, "step": 5950 }, { "epoch": 1.5424430641821947, "grad_norm": 0.20898254215717316, "learning_rate": 2.4301242236024845e-05, "loss": 0.2698, "step": 5960 }, { "epoch": 1.545031055900621, "grad_norm": 0.20771819353103638, "learning_rate": 2.425810904071774e-05, "loss": 0.2766, "step": 5970 }, { "epoch": 1.5476190476190477, "grad_norm": 0.23418374359607697, "learning_rate": 2.4214975845410628e-05, "loss": 0.2756, "step": 5980 }, { "epoch": 1.550207039337474, "grad_norm": 0.20295991003513336, "learning_rate": 2.4171842650103523e-05, "loss": 0.2734, "step": 5990 }, { "epoch": 1.5527950310559007, "grad_norm": 0.20638880133628845, "learning_rate": 2.4128709454796414e-05, "loss": 0.2745, "step": 6000 }, { "epoch": 1.5553830227743273, "grad_norm": 0.20611557364463806, "learning_rate": 2.4085576259489305e-05, "loss": 0.2868, "step": 6010 }, { "epoch": 1.5579710144927537, "grad_norm": 0.21041472256183624, "learning_rate": 2.4042443064182197e-05, "loss": 0.2775, "step": 6020 }, { "epoch": 1.56055900621118, "grad_norm": 0.1944635957479477, "learning_rate": 2.3999309868875085e-05, "loss": 0.2753, "step": 6030 }, { "epoch": 1.5631469979296067, "grad_norm": 0.19726218283176422, "learning_rate": 2.395617667356798e-05, "loss": 0.2823, "step": 6040 }, { "epoch": 1.5657349896480333, "grad_norm": 0.20652392506599426, "learning_rate": 2.391304347826087e-05, "loss": 0.2689, "step": 6050 }, { "epoch": 1.5683229813664596, "grad_norm": 0.1904771625995636, "learning_rate": 2.3869910282953762e-05, "loss": 0.273, "step": 6060 }, { "epoch": 1.570910973084886, "grad_norm": 0.20847630500793457, "learning_rate": 2.3826777087646654e-05, "loss": 0.2734, "step": 6070 }, { "epoch": 1.5734989648033126, "grad_norm": 0.18985170125961304, "learning_rate": 2.3783643892339545e-05, "loss": 0.2716, "step": 6080 }, { "epoch": 1.5760869565217392, "grad_norm": 0.21426165103912354, "learning_rate": 2.3740510697032436e-05, "loss": 0.2698, "step": 6090 }, { "epoch": 1.5786749482401656, "grad_norm": 0.2173684686422348, "learning_rate": 2.3697377501725328e-05, "loss": 0.285, "step": 6100 }, { "epoch": 1.581262939958592, "grad_norm": 0.19787850975990295, "learning_rate": 2.3654244306418223e-05, "loss": 0.27, "step": 6110 }, { "epoch": 1.5838509316770186, "grad_norm": 0.19278573989868164, "learning_rate": 2.361111111111111e-05, "loss": 0.272, "step": 6120 }, { "epoch": 1.5864389233954452, "grad_norm": 0.21055203676223755, "learning_rate": 2.3567977915804005e-05, "loss": 0.2826, "step": 6130 }, { "epoch": 1.5890269151138716, "grad_norm": 0.20687265694141388, "learning_rate": 2.3524844720496897e-05, "loss": 0.2714, "step": 6140 }, { "epoch": 1.591614906832298, "grad_norm": 0.21255378425121307, "learning_rate": 2.3481711525189788e-05, "loss": 0.2808, "step": 6150 }, { "epoch": 1.5942028985507246, "grad_norm": 0.20416966080665588, "learning_rate": 2.343857832988268e-05, "loss": 0.2805, "step": 6160 }, { "epoch": 1.5967908902691512, "grad_norm": 0.20834051072597504, "learning_rate": 2.339544513457557e-05, "loss": 0.2752, "step": 6170 }, { "epoch": 1.5993788819875776, "grad_norm": 0.19759848713874817, "learning_rate": 2.3352311939268462e-05, "loss": 0.2732, "step": 6180 }, { "epoch": 1.601966873706004, "grad_norm": 0.21195858716964722, "learning_rate": 2.3309178743961354e-05, "loss": 0.2878, "step": 6190 }, { "epoch": 1.6045548654244306, "grad_norm": 0.18112218379974365, "learning_rate": 2.3266045548654245e-05, "loss": 0.277, "step": 6200 }, { "epoch": 1.6071428571428572, "grad_norm": 0.2216740995645523, "learning_rate": 2.3222912353347136e-05, "loss": 0.2743, "step": 6210 }, { "epoch": 1.6097308488612836, "grad_norm": 0.19420769810676575, "learning_rate": 2.317977915804003e-05, "loss": 0.2687, "step": 6220 }, { "epoch": 1.6123188405797102, "grad_norm": 0.20138053596019745, "learning_rate": 2.313664596273292e-05, "loss": 0.2867, "step": 6230 }, { "epoch": 1.6149068322981366, "grad_norm": 0.19675815105438232, "learning_rate": 2.3093512767425814e-05, "loss": 0.2632, "step": 6240 }, { "epoch": 1.6174948240165632, "grad_norm": 0.18572789430618286, "learning_rate": 2.3050379572118705e-05, "loss": 0.2763, "step": 6250 }, { "epoch": 1.6200828157349898, "grad_norm": 0.22142665088176727, "learning_rate": 2.3007246376811593e-05, "loss": 0.2843, "step": 6260 }, { "epoch": 1.6226708074534162, "grad_norm": 0.19245979189872742, "learning_rate": 2.2964113181504488e-05, "loss": 0.282, "step": 6270 }, { "epoch": 1.6252587991718426, "grad_norm": 0.19960767030715942, "learning_rate": 2.2920979986197376e-05, "loss": 0.2757, "step": 6280 }, { "epoch": 1.6278467908902692, "grad_norm": 0.1969170719385147, "learning_rate": 2.287784679089027e-05, "loss": 0.2834, "step": 6290 }, { "epoch": 1.6304347826086958, "grad_norm": 0.20468299090862274, "learning_rate": 2.2834713595583162e-05, "loss": 0.2768, "step": 6300 }, { "epoch": 1.6330227743271222, "grad_norm": 0.21196874976158142, "learning_rate": 2.2791580400276054e-05, "loss": 0.2768, "step": 6310 }, { "epoch": 1.6356107660455486, "grad_norm": 0.20282064378261566, "learning_rate": 2.2748447204968945e-05, "loss": 0.2705, "step": 6320 }, { "epoch": 1.6381987577639752, "grad_norm": 0.19569437205791473, "learning_rate": 2.2705314009661836e-05, "loss": 0.2825, "step": 6330 }, { "epoch": 1.6407867494824018, "grad_norm": 0.21149498224258423, "learning_rate": 2.2662180814354728e-05, "loss": 0.2781, "step": 6340 }, { "epoch": 1.6433747412008282, "grad_norm": 0.19336047768592834, "learning_rate": 2.261904761904762e-05, "loss": 0.2722, "step": 6350 }, { "epoch": 1.6459627329192545, "grad_norm": 0.19740383327007294, "learning_rate": 2.2575914423740514e-05, "loss": 0.2749, "step": 6360 }, { "epoch": 1.6485507246376812, "grad_norm": 0.20502516627311707, "learning_rate": 2.2532781228433402e-05, "loss": 0.2709, "step": 6370 }, { "epoch": 1.6511387163561078, "grad_norm": 0.1982286423444748, "learning_rate": 2.2489648033126297e-05, "loss": 0.2721, "step": 6380 }, { "epoch": 1.6537267080745341, "grad_norm": 0.20207327604293823, "learning_rate": 2.2446514837819188e-05, "loss": 0.285, "step": 6390 }, { "epoch": 1.6563146997929605, "grad_norm": 0.19832180440425873, "learning_rate": 2.240338164251208e-05, "loss": 0.283, "step": 6400 }, { "epoch": 1.6589026915113871, "grad_norm": 0.23319384455680847, "learning_rate": 2.236024844720497e-05, "loss": 0.2753, "step": 6410 }, { "epoch": 1.6614906832298137, "grad_norm": 0.19634345173835754, "learning_rate": 2.231711525189786e-05, "loss": 0.2718, "step": 6420 }, { "epoch": 1.6640786749482401, "grad_norm": 0.2094293087720871, "learning_rate": 2.2273982056590754e-05, "loss": 0.2676, "step": 6430 }, { "epoch": 1.6666666666666665, "grad_norm": 0.19552995264530182, "learning_rate": 2.2230848861283645e-05, "loss": 0.267, "step": 6440 }, { "epoch": 1.6692546583850931, "grad_norm": 0.19639810919761658, "learning_rate": 2.2187715665976536e-05, "loss": 0.2789, "step": 6450 }, { "epoch": 1.6718426501035197, "grad_norm": 0.1981237679719925, "learning_rate": 2.2144582470669428e-05, "loss": 0.2815, "step": 6460 }, { "epoch": 1.6744306418219461, "grad_norm": 0.21538740396499634, "learning_rate": 2.2101449275362323e-05, "loss": 0.2787, "step": 6470 }, { "epoch": 1.6770186335403725, "grad_norm": 0.23236703872680664, "learning_rate": 2.205831608005521e-05, "loss": 0.2694, "step": 6480 }, { "epoch": 1.6796066252587991, "grad_norm": 0.1944168359041214, "learning_rate": 2.2015182884748102e-05, "loss": 0.2736, "step": 6490 }, { "epoch": 1.6821946169772257, "grad_norm": 0.19319669902324677, "learning_rate": 2.1972049689440997e-05, "loss": 0.2637, "step": 6500 }, { "epoch": 1.6847826086956523, "grad_norm": 0.1919366717338562, "learning_rate": 2.1928916494133885e-05, "loss": 0.2771, "step": 6510 }, { "epoch": 1.6873706004140787, "grad_norm": 0.2012830674648285, "learning_rate": 2.188578329882678e-05, "loss": 0.2652, "step": 6520 }, { "epoch": 1.689958592132505, "grad_norm": 0.20478034019470215, "learning_rate": 2.1842650103519667e-05, "loss": 0.2749, "step": 6530 }, { "epoch": 1.6925465838509317, "grad_norm": 0.17857521772384644, "learning_rate": 2.1799516908212562e-05, "loss": 0.2779, "step": 6540 }, { "epoch": 1.6951345755693583, "grad_norm": 0.198260098695755, "learning_rate": 2.1756383712905454e-05, "loss": 0.2692, "step": 6550 }, { "epoch": 1.6977225672877847, "grad_norm": 0.2041163593530655, "learning_rate": 2.1713250517598345e-05, "loss": 0.2876, "step": 6560 }, { "epoch": 1.700310559006211, "grad_norm": 0.19581981003284454, "learning_rate": 2.1670117322291236e-05, "loss": 0.2732, "step": 6570 }, { "epoch": 1.7028985507246377, "grad_norm": 0.21552933752536774, "learning_rate": 2.1626984126984128e-05, "loss": 0.2755, "step": 6580 }, { "epoch": 1.7054865424430643, "grad_norm": 0.18474365770816803, "learning_rate": 2.158385093167702e-05, "loss": 0.2742, "step": 6590 }, { "epoch": 1.7080745341614907, "grad_norm": 0.1958833485841751, "learning_rate": 2.154071773636991e-05, "loss": 0.2761, "step": 6600 }, { "epoch": 1.710662525879917, "grad_norm": 0.21241448819637299, "learning_rate": 2.1497584541062805e-05, "loss": 0.2755, "step": 6610 }, { "epoch": 1.7132505175983437, "grad_norm": 0.1859632134437561, "learning_rate": 2.1454451345755693e-05, "loss": 0.2675, "step": 6620 }, { "epoch": 1.7158385093167703, "grad_norm": 0.18138276040554047, "learning_rate": 2.1411318150448588e-05, "loss": 0.277, "step": 6630 }, { "epoch": 1.7184265010351967, "grad_norm": 0.21567761898040771, "learning_rate": 2.136818495514148e-05, "loss": 0.2751, "step": 6640 }, { "epoch": 1.721014492753623, "grad_norm": 0.2187628597021103, "learning_rate": 2.1325051759834367e-05, "loss": 0.2786, "step": 6650 }, { "epoch": 1.7236024844720497, "grad_norm": 0.1880040168762207, "learning_rate": 2.1281918564527262e-05, "loss": 0.2861, "step": 6660 }, { "epoch": 1.7261904761904763, "grad_norm": 0.18701395392417908, "learning_rate": 2.123878536922015e-05, "loss": 0.261, "step": 6670 }, { "epoch": 1.7287784679089027, "grad_norm": 0.19089701771736145, "learning_rate": 2.1195652173913045e-05, "loss": 0.2784, "step": 6680 }, { "epoch": 1.731366459627329, "grad_norm": 0.1895458698272705, "learning_rate": 2.1152518978605936e-05, "loss": 0.2841, "step": 6690 }, { "epoch": 1.7339544513457557, "grad_norm": 0.19079262018203735, "learning_rate": 2.1109385783298828e-05, "loss": 0.2799, "step": 6700 }, { "epoch": 1.7365424430641823, "grad_norm": 0.19622786343097687, "learning_rate": 2.106625258799172e-05, "loss": 0.2688, "step": 6710 }, { "epoch": 1.7391304347826086, "grad_norm": 0.21237607300281525, "learning_rate": 2.102311939268461e-05, "loss": 0.278, "step": 6720 }, { "epoch": 1.741718426501035, "grad_norm": 0.20015180110931396, "learning_rate": 2.0979986197377502e-05, "loss": 0.2825, "step": 6730 }, { "epoch": 1.7443064182194616, "grad_norm": 0.22043476998806, "learning_rate": 2.0936853002070393e-05, "loss": 0.2697, "step": 6740 }, { "epoch": 1.7468944099378882, "grad_norm": 0.1935938447713852, "learning_rate": 2.0893719806763288e-05, "loss": 0.2715, "step": 6750 }, { "epoch": 1.7494824016563149, "grad_norm": 0.21081463992595673, "learning_rate": 2.0850586611456176e-05, "loss": 0.2761, "step": 6760 }, { "epoch": 1.7520703933747412, "grad_norm": 0.19441653788089752, "learning_rate": 2.080745341614907e-05, "loss": 0.275, "step": 6770 }, { "epoch": 1.7546583850931676, "grad_norm": 0.21199271082878113, "learning_rate": 2.076432022084196e-05, "loss": 0.2592, "step": 6780 }, { "epoch": 1.7572463768115942, "grad_norm": 0.19131699204444885, "learning_rate": 2.0721187025534854e-05, "loss": 0.2775, "step": 6790 }, { "epoch": 1.7598343685300208, "grad_norm": 0.20551328361034393, "learning_rate": 2.0678053830227745e-05, "loss": 0.2642, "step": 6800 }, { "epoch": 1.7624223602484472, "grad_norm": 0.1989978551864624, "learning_rate": 2.0634920634920636e-05, "loss": 0.2744, "step": 6810 }, { "epoch": 1.7650103519668736, "grad_norm": 0.20336061716079712, "learning_rate": 2.0591787439613528e-05, "loss": 0.2645, "step": 6820 }, { "epoch": 1.7675983436853002, "grad_norm": 0.1846802830696106, "learning_rate": 2.054865424430642e-05, "loss": 0.2826, "step": 6830 }, { "epoch": 1.7701863354037268, "grad_norm": 0.2088494598865509, "learning_rate": 2.050552104899931e-05, "loss": 0.2765, "step": 6840 }, { "epoch": 1.7727743271221532, "grad_norm": 0.22022396326065063, "learning_rate": 2.0462387853692202e-05, "loss": 0.2668, "step": 6850 }, { "epoch": 1.7753623188405796, "grad_norm": 0.1923859864473343, "learning_rate": 2.0419254658385097e-05, "loss": 0.272, "step": 6860 }, { "epoch": 1.7779503105590062, "grad_norm": 0.21392539143562317, "learning_rate": 2.0376121463077985e-05, "loss": 0.2761, "step": 6870 }, { "epoch": 1.7805383022774328, "grad_norm": 0.19041626155376434, "learning_rate": 2.0332988267770876e-05, "loss": 0.2735, "step": 6880 }, { "epoch": 1.7831262939958592, "grad_norm": 0.21040987968444824, "learning_rate": 2.028985507246377e-05, "loss": 0.2742, "step": 6890 }, { "epoch": 1.7857142857142856, "grad_norm": 0.19723209738731384, "learning_rate": 2.024672187715666e-05, "loss": 0.2676, "step": 6900 }, { "epoch": 1.7883022774327122, "grad_norm": 0.21089300513267517, "learning_rate": 2.0203588681849554e-05, "loss": 0.2703, "step": 6910 }, { "epoch": 1.7908902691511388, "grad_norm": 0.18884050846099854, "learning_rate": 2.016045548654244e-05, "loss": 0.2719, "step": 6920 }, { "epoch": 1.7934782608695652, "grad_norm": 0.19870036840438843, "learning_rate": 2.0117322291235336e-05, "loss": 0.2744, "step": 6930 }, { "epoch": 1.7960662525879916, "grad_norm": 0.20100484788417816, "learning_rate": 2.0074189095928228e-05, "loss": 0.2731, "step": 6940 }, { "epoch": 1.7986542443064182, "grad_norm": 0.1931971311569214, "learning_rate": 2.003105590062112e-05, "loss": 0.2769, "step": 6950 }, { "epoch": 1.8012422360248448, "grad_norm": 0.2118457704782486, "learning_rate": 1.998792270531401e-05, "loss": 0.2766, "step": 6960 }, { "epoch": 1.8038302277432712, "grad_norm": 0.1875993311405182, "learning_rate": 1.9944789510006902e-05, "loss": 0.2711, "step": 6970 }, { "epoch": 1.8064182194616976, "grad_norm": 0.19404591619968414, "learning_rate": 1.9901656314699793e-05, "loss": 0.2691, "step": 6980 }, { "epoch": 1.8090062111801242, "grad_norm": 0.20889738202095032, "learning_rate": 1.9858523119392685e-05, "loss": 0.2792, "step": 6990 }, { "epoch": 1.8115942028985508, "grad_norm": 0.19283007085323334, "learning_rate": 1.981538992408558e-05, "loss": 0.2707, "step": 7000 }, { "epoch": 1.8141821946169774, "grad_norm": 0.2058730572462082, "learning_rate": 1.9772256728778467e-05, "loss": 0.2768, "step": 7010 }, { "epoch": 1.8167701863354038, "grad_norm": 0.1965474933385849, "learning_rate": 1.9729123533471362e-05, "loss": 0.2704, "step": 7020 }, { "epoch": 1.8193581780538302, "grad_norm": 0.21187111735343933, "learning_rate": 1.9685990338164254e-05, "loss": 0.2637, "step": 7030 }, { "epoch": 1.8219461697722568, "grad_norm": 0.20169232785701752, "learning_rate": 1.9642857142857145e-05, "loss": 0.2698, "step": 7040 }, { "epoch": 1.8245341614906834, "grad_norm": 0.2075551301240921, "learning_rate": 1.9599723947550036e-05, "loss": 0.2606, "step": 7050 }, { "epoch": 1.8271221532091098, "grad_norm": 0.19754406809806824, "learning_rate": 1.9556590752242924e-05, "loss": 0.2706, "step": 7060 }, { "epoch": 1.8297101449275361, "grad_norm": 0.20495067536830902, "learning_rate": 1.951345755693582e-05, "loss": 0.27, "step": 7070 }, { "epoch": 1.8322981366459627, "grad_norm": 0.20887307822704315, "learning_rate": 1.947032436162871e-05, "loss": 0.2775, "step": 7080 }, { "epoch": 1.8348861283643894, "grad_norm": 0.19987981021404266, "learning_rate": 1.9427191166321602e-05, "loss": 0.2742, "step": 7090 }, { "epoch": 1.8374741200828157, "grad_norm": 0.21831856667995453, "learning_rate": 1.9384057971014493e-05, "loss": 0.2751, "step": 7100 }, { "epoch": 1.8400621118012421, "grad_norm": 0.19449429214000702, "learning_rate": 1.9340924775707385e-05, "loss": 0.2779, "step": 7110 }, { "epoch": 1.8426501035196687, "grad_norm": 0.2008129507303238, "learning_rate": 1.9297791580400276e-05, "loss": 0.2707, "step": 7120 }, { "epoch": 1.8452380952380953, "grad_norm": 0.20419888198375702, "learning_rate": 1.9254658385093167e-05, "loss": 0.2602, "step": 7130 }, { "epoch": 1.8478260869565217, "grad_norm": 0.20065145194530487, "learning_rate": 1.9211525189786062e-05, "loss": 0.2683, "step": 7140 }, { "epoch": 1.8504140786749481, "grad_norm": 0.1982513964176178, "learning_rate": 1.916839199447895e-05, "loss": 0.2808, "step": 7150 }, { "epoch": 1.8530020703933747, "grad_norm": 0.18309429287910461, "learning_rate": 1.9125258799171845e-05, "loss": 0.2795, "step": 7160 }, { "epoch": 1.8555900621118013, "grad_norm": 0.21153387427330017, "learning_rate": 1.9082125603864733e-05, "loss": 0.2712, "step": 7170 }, { "epoch": 1.8581780538302277, "grad_norm": 0.1983746439218521, "learning_rate": 1.9038992408557628e-05, "loss": 0.27, "step": 7180 }, { "epoch": 1.860766045548654, "grad_norm": 0.18508397042751312, "learning_rate": 1.899585921325052e-05, "loss": 0.2703, "step": 7190 }, { "epoch": 1.8633540372670807, "grad_norm": 0.1981285661458969, "learning_rate": 1.895272601794341e-05, "loss": 0.2685, "step": 7200 }, { "epoch": 1.8659420289855073, "grad_norm": 0.22482812404632568, "learning_rate": 1.8909592822636302e-05, "loss": 0.2722, "step": 7210 }, { "epoch": 1.8685300207039337, "grad_norm": 0.17429296672344208, "learning_rate": 1.8866459627329193e-05, "loss": 0.2706, "step": 7220 }, { "epoch": 1.87111801242236, "grad_norm": 0.1882694512605667, "learning_rate": 1.8823326432022085e-05, "loss": 0.2713, "step": 7230 }, { "epoch": 1.8737060041407867, "grad_norm": 0.1910208910703659, "learning_rate": 1.8780193236714976e-05, "loss": 0.2684, "step": 7240 }, { "epoch": 1.8762939958592133, "grad_norm": 0.19706323742866516, "learning_rate": 1.873706004140787e-05, "loss": 0.2647, "step": 7250 }, { "epoch": 1.87888198757764, "grad_norm": 0.21187639236450195, "learning_rate": 1.869392684610076e-05, "loss": 0.2797, "step": 7260 }, { "epoch": 1.8814699792960663, "grad_norm": 0.20016558468341827, "learning_rate": 1.8650793650793654e-05, "loss": 0.2731, "step": 7270 }, { "epoch": 1.8840579710144927, "grad_norm": 0.19838570058345795, "learning_rate": 1.8607660455486545e-05, "loss": 0.2735, "step": 7280 }, { "epoch": 1.8866459627329193, "grad_norm": 0.20789624750614166, "learning_rate": 1.8564527260179433e-05, "loss": 0.2716, "step": 7290 }, { "epoch": 1.889233954451346, "grad_norm": 0.20426179468631744, "learning_rate": 1.8521394064872328e-05, "loss": 0.2682, "step": 7300 }, { "epoch": 1.8918219461697723, "grad_norm": 0.19371093809604645, "learning_rate": 1.8478260869565216e-05, "loss": 0.2762, "step": 7310 }, { "epoch": 1.8944099378881987, "grad_norm": 0.1775299459695816, "learning_rate": 1.843512767425811e-05, "loss": 0.2746, "step": 7320 }, { "epoch": 1.8969979296066253, "grad_norm": 0.21058380603790283, "learning_rate": 1.8391994478951002e-05, "loss": 0.2652, "step": 7330 }, { "epoch": 1.8995859213250519, "grad_norm": 0.19346512854099274, "learning_rate": 1.8348861283643893e-05, "loss": 0.272, "step": 7340 }, { "epoch": 1.9021739130434783, "grad_norm": 0.18280893564224243, "learning_rate": 1.8305728088336785e-05, "loss": 0.2744, "step": 7350 }, { "epoch": 1.9047619047619047, "grad_norm": 0.20643116533756256, "learning_rate": 1.8262594893029676e-05, "loss": 0.2779, "step": 7360 }, { "epoch": 1.9073498964803313, "grad_norm": 0.182168647646904, "learning_rate": 1.8219461697722567e-05, "loss": 0.2708, "step": 7370 }, { "epoch": 1.9099378881987579, "grad_norm": 0.19439440965652466, "learning_rate": 1.817632850241546e-05, "loss": 0.2682, "step": 7380 }, { "epoch": 1.9125258799171843, "grad_norm": 0.18823355436325073, "learning_rate": 1.8133195307108354e-05, "loss": 0.2629, "step": 7390 }, { "epoch": 1.9151138716356106, "grad_norm": 0.18337075412273407, "learning_rate": 1.809006211180124e-05, "loss": 0.2675, "step": 7400 }, { "epoch": 1.9177018633540373, "grad_norm": 0.19854582846164703, "learning_rate": 1.8046928916494136e-05, "loss": 0.2745, "step": 7410 }, { "epoch": 1.9202898550724639, "grad_norm": 0.19245949387550354, "learning_rate": 1.8003795721187024e-05, "loss": 0.2707, "step": 7420 }, { "epoch": 1.9228778467908902, "grad_norm": 0.20844367146492004, "learning_rate": 1.796066252587992e-05, "loss": 0.273, "step": 7430 }, { "epoch": 1.9254658385093166, "grad_norm": 0.20758184790611267, "learning_rate": 1.791752933057281e-05, "loss": 0.2718, "step": 7440 }, { "epoch": 1.9280538302277432, "grad_norm": 0.19265791773796082, "learning_rate": 1.78743961352657e-05, "loss": 0.278, "step": 7450 }, { "epoch": 1.9306418219461698, "grad_norm": 0.21054716408252716, "learning_rate": 1.7831262939958593e-05, "loss": 0.2798, "step": 7460 }, { "epoch": 1.9332298136645962, "grad_norm": 0.21932169795036316, "learning_rate": 1.7788129744651485e-05, "loss": 0.2619, "step": 7470 }, { "epoch": 1.9358178053830226, "grad_norm": 0.19597266614437103, "learning_rate": 1.7744996549344376e-05, "loss": 0.2686, "step": 7480 }, { "epoch": 1.9384057971014492, "grad_norm": 0.18867290019989014, "learning_rate": 1.7701863354037267e-05, "loss": 0.2758, "step": 7490 }, { "epoch": 1.9409937888198758, "grad_norm": 0.20822232961654663, "learning_rate": 1.7658730158730162e-05, "loss": 0.264, "step": 7500 }, { "epoch": 1.9435817805383024, "grad_norm": 0.20569127798080444, "learning_rate": 1.761559696342305e-05, "loss": 0.2685, "step": 7510 }, { "epoch": 1.9461697722567288, "grad_norm": 0.19487345218658447, "learning_rate": 1.757246376811594e-05, "loss": 0.2704, "step": 7520 }, { "epoch": 1.9487577639751552, "grad_norm": 0.19858413934707642, "learning_rate": 1.7529330572808836e-05, "loss": 0.2811, "step": 7530 }, { "epoch": 1.9513457556935818, "grad_norm": 0.2053307443857193, "learning_rate": 1.7486197377501724e-05, "loss": 0.2706, "step": 7540 }, { "epoch": 1.9539337474120084, "grad_norm": 0.2085588127374649, "learning_rate": 1.744306418219462e-05, "loss": 0.267, "step": 7550 }, { "epoch": 1.9565217391304348, "grad_norm": 0.20521822571754456, "learning_rate": 1.7399930986887507e-05, "loss": 0.2733, "step": 7560 }, { "epoch": 1.9591097308488612, "grad_norm": 0.20257830619812012, "learning_rate": 1.7356797791580402e-05, "loss": 0.2795, "step": 7570 }, { "epoch": 1.9616977225672878, "grad_norm": 0.20972435176372528, "learning_rate": 1.7313664596273293e-05, "loss": 0.261, "step": 7580 }, { "epoch": 1.9642857142857144, "grad_norm": 0.1922076791524887, "learning_rate": 1.7270531400966185e-05, "loss": 0.259, "step": 7590 }, { "epoch": 1.9668737060041408, "grad_norm": 0.2023407369852066, "learning_rate": 1.7227398205659076e-05, "loss": 0.26, "step": 7600 }, { "epoch": 1.9694616977225672, "grad_norm": 0.2070726901292801, "learning_rate": 1.7184265010351967e-05, "loss": 0.2756, "step": 7610 }, { "epoch": 1.9720496894409938, "grad_norm": 0.19282975792884827, "learning_rate": 1.714113181504486e-05, "loss": 0.2667, "step": 7620 }, { "epoch": 1.9746376811594204, "grad_norm": 0.1871107816696167, "learning_rate": 1.709799861973775e-05, "loss": 0.2596, "step": 7630 }, { "epoch": 1.9772256728778468, "grad_norm": 0.18695834279060364, "learning_rate": 1.7054865424430645e-05, "loss": 0.2713, "step": 7640 }, { "epoch": 1.9798136645962732, "grad_norm": 0.1977001577615738, "learning_rate": 1.7011732229123533e-05, "loss": 0.2708, "step": 7650 }, { "epoch": 1.9824016563146998, "grad_norm": 0.2192411720752716, "learning_rate": 1.6968599033816428e-05, "loss": 0.2642, "step": 7660 }, { "epoch": 1.9849896480331264, "grad_norm": 0.20032544434070587, "learning_rate": 1.6925465838509316e-05, "loss": 0.2604, "step": 7670 }, { "epoch": 1.9875776397515528, "grad_norm": 0.20344774425029755, "learning_rate": 1.688233264320221e-05, "loss": 0.2743, "step": 7680 }, { "epoch": 1.9901656314699792, "grad_norm": 0.21191217005252838, "learning_rate": 1.6839199447895102e-05, "loss": 0.2688, "step": 7690 }, { "epoch": 1.9927536231884058, "grad_norm": 0.17852450907230377, "learning_rate": 1.679606625258799e-05, "loss": 0.2762, "step": 7700 }, { "epoch": 1.9953416149068324, "grad_norm": 0.2022544890642166, "learning_rate": 1.6752933057280885e-05, "loss": 0.2823, "step": 7710 }, { "epoch": 1.9979296066252588, "grad_norm": 0.1877758651971817, "learning_rate": 1.6709799861973776e-05, "loss": 0.2638, "step": 7720 } ], "logging_steps": 10, "max_steps": 11592, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8.072391866659635e+17, "train_batch_size": 6, "trial_name": null, "trial_params": null }