{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1353, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0007393715341959334, "grad_norm": 41.82886505126953, "learning_rate": 0.0, "loss": 0.39577627182006836, "step": 1 }, { "epoch": 0.0014787430683918669, "grad_norm": 43.62828826904297, "learning_rate": 4.098360655737705e-08, "loss": 0.3961445689201355, "step": 2 }, { "epoch": 0.0022181146025878, "grad_norm": 45.121517181396484, "learning_rate": 8.19672131147541e-08, "loss": 0.3883833587169647, "step": 3 }, { "epoch": 0.0029574861367837337, "grad_norm": 44.83428192138672, "learning_rate": 1.2295081967213116e-07, "loss": 0.40789830684661865, "step": 4 }, { "epoch": 0.0036968576709796672, "grad_norm": 53.180477142333984, "learning_rate": 1.639344262295082e-07, "loss": 0.44509774446487427, "step": 5 }, { "epoch": 0.0044362292051756, "grad_norm": 43.048526763916016, "learning_rate": 2.0491803278688524e-07, "loss": 0.4160611033439636, "step": 6 }, { "epoch": 0.005175600739371534, "grad_norm": 31.297637939453125, "learning_rate": 2.459016393442623e-07, "loss": 0.3154001235961914, "step": 7 }, { "epoch": 0.005914972273567467, "grad_norm": 36.778350830078125, "learning_rate": 2.8688524590163937e-07, "loss": 0.34796035289764404, "step": 8 }, { "epoch": 0.006654343807763401, "grad_norm": 28.320602416992188, "learning_rate": 3.278688524590164e-07, "loss": 0.3645447790622711, "step": 9 }, { "epoch": 0.0073937153419593345, "grad_norm": 26.17709732055664, "learning_rate": 3.6885245901639347e-07, "loss": 0.3941017985343933, "step": 10 }, { "epoch": 0.008133086876155268, "grad_norm": 26.445171356201172, "learning_rate": 4.0983606557377047e-07, "loss": 0.34486323595046997, "step": 11 }, { "epoch": 0.0088724584103512, "grad_norm": 23.53899574279785, "learning_rate": 4.508196721311476e-07, "loss": 0.32150036096572876, "step": 12 }, { "epoch": 0.009611829944547136, "grad_norm": 25.64048957824707, "learning_rate": 4.918032786885246e-07, "loss": 0.29557716846466064, "step": 13 }, { "epoch": 0.010351201478743069, "grad_norm": 20.494646072387695, "learning_rate": 5.327868852459017e-07, "loss": 0.28796228766441345, "step": 14 }, { "epoch": 0.011090573012939002, "grad_norm": 22.410762786865234, "learning_rate": 5.737704918032787e-07, "loss": 0.3153987228870392, "step": 15 }, { "epoch": 0.011829944547134935, "grad_norm": 16.51301383972168, "learning_rate": 6.147540983606558e-07, "loss": 0.268312931060791, "step": 16 }, { "epoch": 0.012569316081330868, "grad_norm": 14.446939468383789, "learning_rate": 6.557377049180328e-07, "loss": 0.27858996391296387, "step": 17 }, { "epoch": 0.013308687615526803, "grad_norm": 16.552818298339844, "learning_rate": 6.967213114754098e-07, "loss": 0.27712690830230713, "step": 18 }, { "epoch": 0.014048059149722736, "grad_norm": 17.830724716186523, "learning_rate": 7.377049180327869e-07, "loss": 0.3013070821762085, "step": 19 }, { "epoch": 0.014787430683918669, "grad_norm": 15.094914436340332, "learning_rate": 7.78688524590164e-07, "loss": 0.2992064356803894, "step": 20 }, { "epoch": 0.015526802218114602, "grad_norm": 12.978255271911621, "learning_rate": 8.196721311475409e-07, "loss": 0.2892266511917114, "step": 21 }, { "epoch": 0.016266173752310535, "grad_norm": 15.632125854492188, "learning_rate": 8.606557377049181e-07, "loss": 0.3257095515727997, "step": 22 }, { "epoch": 0.017005545286506468, "grad_norm": 17.52192497253418, "learning_rate": 9.016393442622952e-07, "loss": 0.26500624418258667, "step": 23 }, { "epoch": 0.0177449168207024, "grad_norm": 22.568397521972656, "learning_rate": 9.426229508196721e-07, "loss": 0.30868929624557495, "step": 24 }, { "epoch": 0.018484288354898338, "grad_norm": 30.946823120117188, "learning_rate": 9.836065573770493e-07, "loss": 0.341650128364563, "step": 25 }, { "epoch": 0.01922365988909427, "grad_norm": 23.599288940429688, "learning_rate": 1.0245901639344263e-06, "loss": 0.3018481731414795, "step": 26 }, { "epoch": 0.019963031423290204, "grad_norm": 12.915389060974121, "learning_rate": 1.0655737704918034e-06, "loss": 0.255690336227417, "step": 27 }, { "epoch": 0.020702402957486137, "grad_norm": 4.828853130340576, "learning_rate": 1.1065573770491804e-06, "loss": 0.24793919920921326, "step": 28 }, { "epoch": 0.02144177449168207, "grad_norm": 7.216000556945801, "learning_rate": 1.1475409836065575e-06, "loss": 0.2728981673717499, "step": 29 }, { "epoch": 0.022181146025878003, "grad_norm": 20.403059005737305, "learning_rate": 1.1885245901639345e-06, "loss": 0.29784220457077026, "step": 30 }, { "epoch": 0.022920517560073937, "grad_norm": 24.058977127075195, "learning_rate": 1.2295081967213116e-06, "loss": 0.3200542628765106, "step": 31 }, { "epoch": 0.02365988909426987, "grad_norm": 22.61942481994629, "learning_rate": 1.2704918032786886e-06, "loss": 0.2977902293205261, "step": 32 }, { "epoch": 0.024399260628465803, "grad_norm": 17.05254554748535, "learning_rate": 1.3114754098360657e-06, "loss": 0.28311583399772644, "step": 33 }, { "epoch": 0.025138632162661736, "grad_norm": 13.681181907653809, "learning_rate": 1.352459016393443e-06, "loss": 0.263553261756897, "step": 34 }, { "epoch": 0.025878003696857672, "grad_norm": 4.427638530731201, "learning_rate": 1.3934426229508196e-06, "loss": 0.24522951245307922, "step": 35 }, { "epoch": 0.026617375231053605, "grad_norm": 8.677863121032715, "learning_rate": 1.4344262295081968e-06, "loss": 0.24220284819602966, "step": 36 }, { "epoch": 0.02735674676524954, "grad_norm": 12.438057899475098, "learning_rate": 1.4754098360655739e-06, "loss": 0.2582142651081085, "step": 37 }, { "epoch": 0.02809611829944547, "grad_norm": 19.662607192993164, "learning_rate": 1.516393442622951e-06, "loss": 0.2944411635398865, "step": 38 }, { "epoch": 0.028835489833641405, "grad_norm": 15.692110061645508, "learning_rate": 1.557377049180328e-06, "loss": 0.2920330762863159, "step": 39 }, { "epoch": 0.029574861367837338, "grad_norm": 12.463593482971191, "learning_rate": 1.5983606557377053e-06, "loss": 0.2791077792644501, "step": 40 }, { "epoch": 0.03031423290203327, "grad_norm": 7.102624893188477, "learning_rate": 1.6393442622950819e-06, "loss": 0.23491504788398743, "step": 41 }, { "epoch": 0.031053604436229204, "grad_norm": 3.370135545730591, "learning_rate": 1.6803278688524592e-06, "loss": 0.24000954627990723, "step": 42 }, { "epoch": 0.03179297597042514, "grad_norm": 4.321382999420166, "learning_rate": 1.7213114754098362e-06, "loss": 0.259482741355896, "step": 43 }, { "epoch": 0.03253234750462107, "grad_norm": 12.374532699584961, "learning_rate": 1.7622950819672133e-06, "loss": 0.25031858682632446, "step": 44 }, { "epoch": 0.033271719038817, "grad_norm": 17.417724609375, "learning_rate": 1.8032786885245903e-06, "loss": 0.2694057822227478, "step": 45 }, { "epoch": 0.034011090573012936, "grad_norm": 11.75733470916748, "learning_rate": 1.8442622950819674e-06, "loss": 0.24549782276153564, "step": 46 }, { "epoch": 0.03475046210720887, "grad_norm": 8.331439971923828, "learning_rate": 1.8852459016393442e-06, "loss": 0.20991119742393494, "step": 47 }, { "epoch": 0.0354898336414048, "grad_norm": 4.818135738372803, "learning_rate": 1.9262295081967215e-06, "loss": 0.22587916254997253, "step": 48 }, { "epoch": 0.03622920517560074, "grad_norm": 6.449060916900635, "learning_rate": 1.9672131147540985e-06, "loss": 0.21461454033851624, "step": 49 }, { "epoch": 0.036968576709796676, "grad_norm": 18.1987361907959, "learning_rate": 2.0081967213114756e-06, "loss": 0.28996536135673523, "step": 50 }, { "epoch": 0.03770794824399261, "grad_norm": 15.74471664428711, "learning_rate": 2.0491803278688526e-06, "loss": 0.26668763160705566, "step": 51 }, { "epoch": 0.03844731977818854, "grad_norm": 10.495340347290039, "learning_rate": 2.0901639344262297e-06, "loss": 0.2676393389701843, "step": 52 }, { "epoch": 0.039186691312384475, "grad_norm": 9.458422660827637, "learning_rate": 2.1311475409836067e-06, "loss": 0.22141633927822113, "step": 53 }, { "epoch": 0.03992606284658041, "grad_norm": 9.127469062805176, "learning_rate": 2.1721311475409838e-06, "loss": 0.24063923954963684, "step": 54 }, { "epoch": 0.04066543438077634, "grad_norm": 11.918418884277344, "learning_rate": 2.213114754098361e-06, "loss": 0.23009678721427917, "step": 55 }, { "epoch": 0.041404805914972274, "grad_norm": 12.165032386779785, "learning_rate": 2.254098360655738e-06, "loss": 0.2415492683649063, "step": 56 }, { "epoch": 0.04214417744916821, "grad_norm": 8.690532684326172, "learning_rate": 2.295081967213115e-06, "loss": 0.2201872169971466, "step": 57 }, { "epoch": 0.04288354898336414, "grad_norm": 6.020841598510742, "learning_rate": 2.336065573770492e-06, "loss": 0.21306461095809937, "step": 58 }, { "epoch": 0.043622920517560074, "grad_norm": 10.067004203796387, "learning_rate": 2.377049180327869e-06, "loss": 0.22832569479942322, "step": 59 }, { "epoch": 0.04436229205175601, "grad_norm": 12.942950248718262, "learning_rate": 2.418032786885246e-06, "loss": 0.2675108015537262, "step": 60 }, { "epoch": 0.04510166358595194, "grad_norm": 8.809064865112305, "learning_rate": 2.459016393442623e-06, "loss": 0.2304268479347229, "step": 61 }, { "epoch": 0.04584103512014787, "grad_norm": 3.882194995880127, "learning_rate": 2.5e-06, "loss": 0.24520593881607056, "step": 62 }, { "epoch": 0.046580406654343806, "grad_norm": 11.194753646850586, "learning_rate": 2.5409836065573773e-06, "loss": 0.2392072230577469, "step": 63 }, { "epoch": 0.04731977818853974, "grad_norm": 10.121578216552734, "learning_rate": 2.5819672131147543e-06, "loss": 0.22638732194900513, "step": 64 }, { "epoch": 0.04805914972273567, "grad_norm": 9.011906623840332, "learning_rate": 2.6229508196721314e-06, "loss": 0.25158917903900146, "step": 65 }, { "epoch": 0.048798521256931605, "grad_norm": 4.107776165008545, "learning_rate": 2.6639344262295084e-06, "loss": 0.2215217649936676, "step": 66 }, { "epoch": 0.04953789279112754, "grad_norm": 4.162323474884033, "learning_rate": 2.704918032786886e-06, "loss": 0.22548258304595947, "step": 67 }, { "epoch": 0.05027726432532347, "grad_norm": 8.808723449707031, "learning_rate": 2.745901639344263e-06, "loss": 0.24540020525455475, "step": 68 }, { "epoch": 0.05101663585951941, "grad_norm": 9.407150268554688, "learning_rate": 2.786885245901639e-06, "loss": 0.24976441264152527, "step": 69 }, { "epoch": 0.051756007393715345, "grad_norm": 3.1315934658050537, "learning_rate": 2.8278688524590166e-06, "loss": 0.21074530482292175, "step": 70 }, { "epoch": 0.05249537892791128, "grad_norm": 5.516967296600342, "learning_rate": 2.8688524590163937e-06, "loss": 0.23217648267745972, "step": 71 }, { "epoch": 0.05323475046210721, "grad_norm": 6.458528518676758, "learning_rate": 2.9098360655737707e-06, "loss": 0.24738115072250366, "step": 72 }, { "epoch": 0.053974121996303144, "grad_norm": 6.4828901290893555, "learning_rate": 2.9508196721311478e-06, "loss": 0.2421148419380188, "step": 73 }, { "epoch": 0.05471349353049908, "grad_norm": 4.693951606750488, "learning_rate": 2.991803278688525e-06, "loss": 0.21221855282783508, "step": 74 }, { "epoch": 0.05545286506469501, "grad_norm": 5.373523235321045, "learning_rate": 3.032786885245902e-06, "loss": 0.19335052371025085, "step": 75 }, { "epoch": 0.05619223659889094, "grad_norm": 6.908679485321045, "learning_rate": 3.073770491803279e-06, "loss": 0.2266283631324768, "step": 76 }, { "epoch": 0.056931608133086876, "grad_norm": 5.548397541046143, "learning_rate": 3.114754098360656e-06, "loss": 0.20439353585243225, "step": 77 }, { "epoch": 0.05767097966728281, "grad_norm": 3.499976634979248, "learning_rate": 3.155737704918033e-06, "loss": 0.230841726064682, "step": 78 }, { "epoch": 0.05841035120147874, "grad_norm": 3.373450994491577, "learning_rate": 3.1967213114754105e-06, "loss": 0.1977718472480774, "step": 79 }, { "epoch": 0.059149722735674676, "grad_norm": 6.480327606201172, "learning_rate": 3.2377049180327876e-06, "loss": 0.2362918108701706, "step": 80 }, { "epoch": 0.05988909426987061, "grad_norm": 2.622467279434204, "learning_rate": 3.2786885245901638e-06, "loss": 0.20688095688819885, "step": 81 }, { "epoch": 0.06062846580406654, "grad_norm": 11.898148536682129, "learning_rate": 3.3196721311475413e-06, "loss": 0.22245919704437256, "step": 82 }, { "epoch": 0.061367837338262475, "grad_norm": 2.7481648921966553, "learning_rate": 3.3606557377049183e-06, "loss": 0.21636639535427094, "step": 83 }, { "epoch": 0.06210720887245841, "grad_norm": 4.782436847686768, "learning_rate": 3.4016393442622954e-06, "loss": 0.20911897718906403, "step": 84 }, { "epoch": 0.06284658040665435, "grad_norm": 6.658738613128662, "learning_rate": 3.4426229508196724e-06, "loss": 0.22788047790527344, "step": 85 }, { "epoch": 0.06358595194085027, "grad_norm": 3.3672688007354736, "learning_rate": 3.4836065573770495e-06, "loss": 0.19663548469543457, "step": 86 }, { "epoch": 0.06432532347504621, "grad_norm": 4.698397159576416, "learning_rate": 3.5245901639344265e-06, "loss": 0.20169639587402344, "step": 87 }, { "epoch": 0.06506469500924214, "grad_norm": 6.411549091339111, "learning_rate": 3.5655737704918036e-06, "loss": 0.2064359486103058, "step": 88 }, { "epoch": 0.06580406654343808, "grad_norm": 2.3855221271514893, "learning_rate": 3.6065573770491806e-06, "loss": 0.19425924122333527, "step": 89 }, { "epoch": 0.066543438077634, "grad_norm": 2.8847012519836426, "learning_rate": 3.6475409836065577e-06, "loss": 0.2077484428882599, "step": 90 }, { "epoch": 0.06728280961182995, "grad_norm": 5.38006067276001, "learning_rate": 3.6885245901639347e-06, "loss": 0.20762400329113007, "step": 91 }, { "epoch": 0.06802218114602587, "grad_norm": 5.595937252044678, "learning_rate": 3.729508196721312e-06, "loss": 0.2006339728832245, "step": 92 }, { "epoch": 0.06876155268022181, "grad_norm": 6.048823833465576, "learning_rate": 3.7704918032786884e-06, "loss": 0.2086416482925415, "step": 93 }, { "epoch": 0.06950092421441774, "grad_norm": 12.724146842956543, "learning_rate": 3.811475409836066e-06, "loss": 0.21837687492370605, "step": 94 }, { "epoch": 0.07024029574861368, "grad_norm": 4.319859504699707, "learning_rate": 3.852459016393443e-06, "loss": 0.2234213650226593, "step": 95 }, { "epoch": 0.0709796672828096, "grad_norm": 7.019913673400879, "learning_rate": 3.8934426229508196e-06, "loss": 0.19699649512767792, "step": 96 }, { "epoch": 0.07171903881700555, "grad_norm": 10.094223022460938, "learning_rate": 3.934426229508197e-06, "loss": 0.24272720515727997, "step": 97 }, { "epoch": 0.07245841035120149, "grad_norm": 4.013901710510254, "learning_rate": 3.975409836065574e-06, "loss": 0.21634478867053986, "step": 98 }, { "epoch": 0.07319778188539741, "grad_norm": 8.776777267456055, "learning_rate": 4.016393442622951e-06, "loss": 0.19404113292694092, "step": 99 }, { "epoch": 0.07393715341959335, "grad_norm": 3.951009511947632, "learning_rate": 4.057377049180329e-06, "loss": 0.20147749781608582, "step": 100 }, { "epoch": 0.07467652495378928, "grad_norm": 5.765294075012207, "learning_rate": 4.098360655737705e-06, "loss": 0.21484899520874023, "step": 101 }, { "epoch": 0.07541589648798522, "grad_norm": 4.302549362182617, "learning_rate": 4.139344262295083e-06, "loss": 0.19479814171791077, "step": 102 }, { "epoch": 0.07615526802218114, "grad_norm": 5.873546123504639, "learning_rate": 4.180327868852459e-06, "loss": 0.22802744805812836, "step": 103 }, { "epoch": 0.07689463955637708, "grad_norm": 15.526389122009277, "learning_rate": 4.221311475409837e-06, "loss": 0.256289005279541, "step": 104 }, { "epoch": 0.07763401109057301, "grad_norm": 2.88378643989563, "learning_rate": 4.2622950819672135e-06, "loss": 0.22099198400974274, "step": 105 }, { "epoch": 0.07837338262476895, "grad_norm": 11.6503267288208, "learning_rate": 4.30327868852459e-06, "loss": 0.23699139058589935, "step": 106 }, { "epoch": 0.07911275415896488, "grad_norm": 7.808468818664551, "learning_rate": 4.3442622950819676e-06, "loss": 0.2278435230255127, "step": 107 }, { "epoch": 0.07985212569316082, "grad_norm": 1.6177762746810913, "learning_rate": 4.385245901639344e-06, "loss": 0.2016463726758957, "step": 108 }, { "epoch": 0.08059149722735674, "grad_norm": 10.278399467468262, "learning_rate": 4.426229508196722e-06, "loss": 0.20470306277275085, "step": 109 }, { "epoch": 0.08133086876155268, "grad_norm": 3.661545753479004, "learning_rate": 4.467213114754098e-06, "loss": 0.23780176043510437, "step": 110 }, { "epoch": 0.08207024029574861, "grad_norm": 6.013368606567383, "learning_rate": 4.508196721311476e-06, "loss": 0.2386183738708496, "step": 111 }, { "epoch": 0.08280961182994455, "grad_norm": 3.6877310276031494, "learning_rate": 4.549180327868853e-06, "loss": 0.1903471052646637, "step": 112 }, { "epoch": 0.08354898336414047, "grad_norm": 3.259579658508301, "learning_rate": 4.59016393442623e-06, "loss": 0.22512444853782654, "step": 113 }, { "epoch": 0.08428835489833642, "grad_norm": 5.941078186035156, "learning_rate": 4.631147540983607e-06, "loss": 0.2321382462978363, "step": 114 }, { "epoch": 0.08502772643253234, "grad_norm": 5.045360565185547, "learning_rate": 4.672131147540984e-06, "loss": 0.20236289501190186, "step": 115 }, { "epoch": 0.08576709796672828, "grad_norm": 4.184108734130859, "learning_rate": 4.7131147540983615e-06, "loss": 0.2230832725763321, "step": 116 }, { "epoch": 0.08650646950092422, "grad_norm": 3.779632329940796, "learning_rate": 4.754098360655738e-06, "loss": 0.22199736535549164, "step": 117 }, { "epoch": 0.08724584103512015, "grad_norm": 4.972632884979248, "learning_rate": 4.795081967213115e-06, "loss": 0.19952507317066193, "step": 118 }, { "epoch": 0.08798521256931609, "grad_norm": 5.0896711349487305, "learning_rate": 4.836065573770492e-06, "loss": 0.21386322379112244, "step": 119 }, { "epoch": 0.08872458410351201, "grad_norm": 9.250158309936523, "learning_rate": 4.877049180327869e-06, "loss": 0.21761557459831238, "step": 120 }, { "epoch": 0.08946395563770795, "grad_norm": 6.128583908081055, "learning_rate": 4.918032786885246e-06, "loss": 0.20839637517929077, "step": 121 }, { "epoch": 0.09020332717190388, "grad_norm": 8.853307723999023, "learning_rate": 4.959016393442623e-06, "loss": 0.2305302619934082, "step": 122 }, { "epoch": 0.09094269870609982, "grad_norm": 5.29646110534668, "learning_rate": 5e-06, "loss": 0.21244560182094574, "step": 123 }, { "epoch": 0.09168207024029575, "grad_norm": 5.730811595916748, "learning_rate": 4.999999283656351e-06, "loss": 0.23975282907485962, "step": 124 }, { "epoch": 0.09242144177449169, "grad_norm": 5.424437522888184, "learning_rate": 4.999997134625859e-06, "loss": 0.21328279376029968, "step": 125 }, { "epoch": 0.09316081330868761, "grad_norm": 6.461747169494629, "learning_rate": 4.999993552909891e-06, "loss": 0.2058568298816681, "step": 126 }, { "epoch": 0.09390018484288355, "grad_norm": 8.057741165161133, "learning_rate": 4.99998853851073e-06, "loss": 0.21561354398727417, "step": 127 }, { "epoch": 0.09463955637707948, "grad_norm": 3.5628254413604736, "learning_rate": 4.9999820914315674e-06, "loss": 0.2102605104446411, "step": 128 }, { "epoch": 0.09537892791127542, "grad_norm": 3.3406596183776855, "learning_rate": 4.999974211676508e-06, "loss": 0.23227381706237793, "step": 129 }, { "epoch": 0.09611829944547134, "grad_norm": 3.3146913051605225, "learning_rate": 4.999964899250572e-06, "loss": 0.22322767972946167, "step": 130 }, { "epoch": 0.09685767097966728, "grad_norm": 7.157834529876709, "learning_rate": 4.999954154159686e-06, "loss": 0.20672239363193512, "step": 131 }, { "epoch": 0.09759704251386321, "grad_norm": 4.482982635498047, "learning_rate": 4.999941976410694e-06, "loss": 0.23313236236572266, "step": 132 }, { "epoch": 0.09833641404805915, "grad_norm": 5.742522716522217, "learning_rate": 4.9999283660113485e-06, "loss": 0.22553284466266632, "step": 133 }, { "epoch": 0.09907578558225508, "grad_norm": 3.9572412967681885, "learning_rate": 4.999913322970318e-06, "loss": 0.23487737774848938, "step": 134 }, { "epoch": 0.09981515711645102, "grad_norm": 3.3733437061309814, "learning_rate": 4.999896847297178e-06, "loss": 0.20446071028709412, "step": 135 }, { "epoch": 0.10055452865064694, "grad_norm": 12.901237487792969, "learning_rate": 4.999878939002423e-06, "loss": 0.22576099634170532, "step": 136 }, { "epoch": 0.10129390018484288, "grad_norm": 1.9093260765075684, "learning_rate": 4.999859598097453e-06, "loss": 0.2094370722770691, "step": 137 }, { "epoch": 0.10203327171903882, "grad_norm": 3.8334360122680664, "learning_rate": 4.999838824594586e-06, "loss": 0.2088109850883484, "step": 138 }, { "epoch": 0.10277264325323475, "grad_norm": 8.575350761413574, "learning_rate": 4.999816618507047e-06, "loss": 0.21401375532150269, "step": 139 }, { "epoch": 0.10351201478743069, "grad_norm": 5.358882904052734, "learning_rate": 4.999792979848979e-06, "loss": 0.1906435787677765, "step": 140 }, { "epoch": 0.10425138632162662, "grad_norm": 6.528226852416992, "learning_rate": 4.99976790863543e-06, "loss": 0.21349413692951202, "step": 141 }, { "epoch": 0.10499075785582256, "grad_norm": 5.476285457611084, "learning_rate": 4.9997414048823665e-06, "loss": 0.21039831638336182, "step": 142 }, { "epoch": 0.10573012939001848, "grad_norm": 3.1280858516693115, "learning_rate": 4.999713468606664e-06, "loss": 0.1783124804496765, "step": 143 }, { "epoch": 0.10646950092421442, "grad_norm": 10.677936553955078, "learning_rate": 4.999684099826112e-06, "loss": 0.22802439332008362, "step": 144 }, { "epoch": 0.10720887245841035, "grad_norm": 4.9018473625183105, "learning_rate": 4.999653298559409e-06, "loss": 0.20103749632835388, "step": 145 }, { "epoch": 0.10794824399260629, "grad_norm": 5.392449855804443, "learning_rate": 4.9996210648261685e-06, "loss": 0.21897855401039124, "step": 146 }, { "epoch": 0.10868761552680221, "grad_norm": 6.58085823059082, "learning_rate": 4.999587398646918e-06, "loss": 0.23399052023887634, "step": 147 }, { "epoch": 0.10942698706099815, "grad_norm": 2.1531617641448975, "learning_rate": 4.999552300043091e-06, "loss": 0.2223932147026062, "step": 148 }, { "epoch": 0.11016635859519408, "grad_norm": 3.768397569656372, "learning_rate": 4.9995157690370374e-06, "loss": 0.20590761303901672, "step": 149 }, { "epoch": 0.11090573012939002, "grad_norm": 3.721367597579956, "learning_rate": 4.999477805652019e-06, "loss": 0.18851682543754578, "step": 150 }, { "epoch": 0.11164510166358595, "grad_norm": 6.270774841308594, "learning_rate": 4.9994384099122086e-06, "loss": 0.2077135443687439, "step": 151 }, { "epoch": 0.11238447319778189, "grad_norm": 6.959105014801025, "learning_rate": 4.999397581842691e-06, "loss": 0.22356319427490234, "step": 152 }, { "epoch": 0.11312384473197781, "grad_norm": 4.501737594604492, "learning_rate": 4.999355321469464e-06, "loss": 0.188577800989151, "step": 153 }, { "epoch": 0.11386321626617375, "grad_norm": 4.608864784240723, "learning_rate": 4.9993116288194374e-06, "loss": 0.19051173329353333, "step": 154 }, { "epoch": 0.11460258780036968, "grad_norm": 3.079270124435425, "learning_rate": 4.999266503920432e-06, "loss": 0.21547457575798035, "step": 155 }, { "epoch": 0.11534195933456562, "grad_norm": 3.4958338737487793, "learning_rate": 4.99921994680118e-06, "loss": 0.20264063775539398, "step": 156 }, { "epoch": 0.11608133086876156, "grad_norm": 4.142209053039551, "learning_rate": 4.9991719574913276e-06, "loss": 0.20127679407596588, "step": 157 }, { "epoch": 0.11682070240295749, "grad_norm": 5.374937057495117, "learning_rate": 4.999122536021434e-06, "loss": 0.2312670350074768, "step": 158 }, { "epoch": 0.11756007393715343, "grad_norm": 7.3549394607543945, "learning_rate": 4.999071682422964e-06, "loss": 0.19996589422225952, "step": 159 }, { "epoch": 0.11829944547134935, "grad_norm": 2.401292085647583, "learning_rate": 4.999019396728302e-06, "loss": 0.21850746870040894, "step": 160 }, { "epoch": 0.11903881700554529, "grad_norm": 10.5030517578125, "learning_rate": 4.99896567897074e-06, "loss": 0.21915699541568756, "step": 161 }, { "epoch": 0.11977818853974122, "grad_norm": 11.845870971679688, "learning_rate": 4.998910529184482e-06, "loss": 0.20758046209812164, "step": 162 }, { "epoch": 0.12051756007393716, "grad_norm": 6.772263526916504, "learning_rate": 4.998853947404646e-06, "loss": 0.20164796710014343, "step": 163 }, { "epoch": 0.12125693160813308, "grad_norm": 12.04313850402832, "learning_rate": 4.998795933667259e-06, "loss": 0.24618496000766754, "step": 164 }, { "epoch": 0.12199630314232902, "grad_norm": 4.162416934967041, "learning_rate": 4.998736488009262e-06, "loss": 0.20156514644622803, "step": 165 }, { "epoch": 0.12273567467652495, "grad_norm": 4.30323600769043, "learning_rate": 4.998675610468508e-06, "loss": 0.23311716318130493, "step": 166 }, { "epoch": 0.12347504621072089, "grad_norm": 12.958264350891113, "learning_rate": 4.998613301083759e-06, "loss": 0.2217358946800232, "step": 167 }, { "epoch": 0.12421441774491682, "grad_norm": 2.4791245460510254, "learning_rate": 4.998549559894691e-06, "loss": 0.19415906071662903, "step": 168 }, { "epoch": 0.12495378927911276, "grad_norm": 7.254051208496094, "learning_rate": 4.998484386941892e-06, "loss": 0.19829492270946503, "step": 169 }, { "epoch": 0.1256931608133087, "grad_norm": 5.16053581237793, "learning_rate": 4.998417782266859e-06, "loss": 0.17138540744781494, "step": 170 }, { "epoch": 0.12643253234750462, "grad_norm": 5.878444671630859, "learning_rate": 4.998349745912004e-06, "loss": 0.21023114025592804, "step": 171 }, { "epoch": 0.12717190388170055, "grad_norm": 3.826645851135254, "learning_rate": 4.99828027792065e-06, "loss": 0.21292969584465027, "step": 172 }, { "epoch": 0.12791127541589647, "grad_norm": 12.801521301269531, "learning_rate": 4.998209378337029e-06, "loss": 0.22789156436920166, "step": 173 }, { "epoch": 0.12865064695009243, "grad_norm": 8.937321662902832, "learning_rate": 4.998137047206288e-06, "loss": 0.210373654961586, "step": 174 }, { "epoch": 0.12939001848428835, "grad_norm": 3.6342132091522217, "learning_rate": 4.998063284574482e-06, "loss": 0.20943859219551086, "step": 175 }, { "epoch": 0.13012939001848428, "grad_norm": 6.840196132659912, "learning_rate": 4.9979880904885805e-06, "loss": 0.1745193898677826, "step": 176 }, { "epoch": 0.13086876155268024, "grad_norm": 11.029228210449219, "learning_rate": 4.997911464996462e-06, "loss": 0.21482783555984497, "step": 177 }, { "epoch": 0.13160813308687616, "grad_norm": 9.73087215423584, "learning_rate": 4.99783340814692e-06, "loss": 0.229659765958786, "step": 178 }, { "epoch": 0.1323475046210721, "grad_norm": 1.992520809173584, "learning_rate": 4.9977539199896556e-06, "loss": 0.18343789875507355, "step": 179 }, { "epoch": 0.133086876155268, "grad_norm": 9.423386573791504, "learning_rate": 4.9976730005752835e-06, "loss": 0.23588994145393372, "step": 180 }, { "epoch": 0.13382624768946397, "grad_norm": 8.643245697021484, "learning_rate": 4.997590649955328e-06, "loss": 0.20269909501075745, "step": 181 }, { "epoch": 0.1345656192236599, "grad_norm": 2.357172966003418, "learning_rate": 4.997506868182228e-06, "loss": 0.21033409237861633, "step": 182 }, { "epoch": 0.13530499075785582, "grad_norm": 2.892446756362915, "learning_rate": 4.997421655309331e-06, "loss": 0.19526968896389008, "step": 183 }, { "epoch": 0.13604436229205175, "grad_norm": 5.728464126586914, "learning_rate": 4.9973350113908935e-06, "loss": 0.20251791179180145, "step": 184 }, { "epoch": 0.1367837338262477, "grad_norm": 5.5191240310668945, "learning_rate": 4.997246936482088e-06, "loss": 0.19868972897529602, "step": 185 }, { "epoch": 0.13752310536044363, "grad_norm": 5.181105613708496, "learning_rate": 4.9971574306389976e-06, "loss": 0.22018973529338837, "step": 186 }, { "epoch": 0.13826247689463955, "grad_norm": 3.9759182929992676, "learning_rate": 4.9970664939186135e-06, "loss": 0.23818320035934448, "step": 187 }, { "epoch": 0.13900184842883548, "grad_norm": 3.5860955715179443, "learning_rate": 4.996974126378839e-06, "loss": 0.2143045961856842, "step": 188 }, { "epoch": 0.13974121996303143, "grad_norm": 3.866260290145874, "learning_rate": 4.996880328078491e-06, "loss": 0.2421102374792099, "step": 189 }, { "epoch": 0.14048059149722736, "grad_norm": 4.419630527496338, "learning_rate": 4.996785099077295e-06, "loss": 0.19339701533317566, "step": 190 }, { "epoch": 0.14121996303142328, "grad_norm": 4.27023458480835, "learning_rate": 4.996688439435887e-06, "loss": 0.20477066934108734, "step": 191 }, { "epoch": 0.1419593345656192, "grad_norm": 1.380745530128479, "learning_rate": 4.996590349215815e-06, "loss": 0.19095931947231293, "step": 192 }, { "epoch": 0.14269870609981516, "grad_norm": 5.694972038269043, "learning_rate": 4.99649082847954e-06, "loss": 0.24175378680229187, "step": 193 }, { "epoch": 0.1434380776340111, "grad_norm": 5.279901027679443, "learning_rate": 4.9963898772904295e-06, "loss": 0.21104538440704346, "step": 194 }, { "epoch": 0.14417744916820702, "grad_norm": 3.0650622844696045, "learning_rate": 4.9962874957127655e-06, "loss": 0.22902226448059082, "step": 195 }, { "epoch": 0.14491682070240297, "grad_norm": 4.527248859405518, "learning_rate": 4.996183683811739e-06, "loss": 0.21409283578395844, "step": 196 }, { "epoch": 0.1456561922365989, "grad_norm": 5.509324550628662, "learning_rate": 4.996078441653453e-06, "loss": 0.20544184744358063, "step": 197 }, { "epoch": 0.14639556377079482, "grad_norm": 1.6277881860733032, "learning_rate": 4.995971769304919e-06, "loss": 0.17666375637054443, "step": 198 }, { "epoch": 0.14713493530499075, "grad_norm": 7.744825839996338, "learning_rate": 4.9958636668340615e-06, "loss": 0.21810278296470642, "step": 199 }, { "epoch": 0.1478743068391867, "grad_norm": 5.199048042297363, "learning_rate": 4.995754134309715e-06, "loss": 0.19525423645973206, "step": 200 }, { "epoch": 0.14861367837338263, "grad_norm": 2.28080677986145, "learning_rate": 4.995643171801623e-06, "loss": 0.1834719181060791, "step": 201 }, { "epoch": 0.14935304990757856, "grad_norm": 1.6865932941436768, "learning_rate": 4.995530779380442e-06, "loss": 0.20241200923919678, "step": 202 }, { "epoch": 0.15009242144177448, "grad_norm": 5.409422397613525, "learning_rate": 4.995416957117738e-06, "loss": 0.20601588487625122, "step": 203 }, { "epoch": 0.15083179297597044, "grad_norm": 4.950964450836182, "learning_rate": 4.995301705085987e-06, "loss": 0.18962004780769348, "step": 204 }, { "epoch": 0.15157116451016636, "grad_norm": 3.6908178329467773, "learning_rate": 4.995185023358576e-06, "loss": 0.21325714886188507, "step": 205 }, { "epoch": 0.1523105360443623, "grad_norm": 4.639225959777832, "learning_rate": 4.995066912009801e-06, "loss": 0.21426555514335632, "step": 206 }, { "epoch": 0.15304990757855821, "grad_norm": 3.2748031616210938, "learning_rate": 4.994947371114871e-06, "loss": 0.2186756134033203, "step": 207 }, { "epoch": 0.15378927911275417, "grad_norm": 2.254979372024536, "learning_rate": 4.994826400749901e-06, "loss": 0.1997169405221939, "step": 208 }, { "epoch": 0.1545286506469501, "grad_norm": 5.723446846008301, "learning_rate": 4.994704000991922e-06, "loss": 0.21458649635314941, "step": 209 }, { "epoch": 0.15526802218114602, "grad_norm": 8.66995906829834, "learning_rate": 4.994580171918871e-06, "loss": 0.17107975482940674, "step": 210 }, { "epoch": 0.15600739371534195, "grad_norm": 4.7440385818481445, "learning_rate": 4.994454913609596e-06, "loss": 0.17914769053459167, "step": 211 }, { "epoch": 0.1567467652495379, "grad_norm": 9.750540733337402, "learning_rate": 4.9943282261438544e-06, "loss": 0.21522103250026703, "step": 212 }, { "epoch": 0.15748613678373383, "grad_norm": 4.822422027587891, "learning_rate": 4.994200109602316e-06, "loss": 0.19541355967521667, "step": 213 }, { "epoch": 0.15822550831792975, "grad_norm": 3.5090742111206055, "learning_rate": 4.994070564066557e-06, "loss": 0.20041882991790771, "step": 214 }, { "epoch": 0.1589648798521257, "grad_norm": 6.856600284576416, "learning_rate": 4.993939589619067e-06, "loss": 0.1975751519203186, "step": 215 }, { "epoch": 0.15970425138632163, "grad_norm": 6.34645414352417, "learning_rate": 4.993807186343243e-06, "loss": 0.2111305147409439, "step": 216 }, { "epoch": 0.16044362292051756, "grad_norm": 1.900739073753357, "learning_rate": 4.9936733543233945e-06, "loss": 0.199153333902359, "step": 217 }, { "epoch": 0.16118299445471349, "grad_norm": 4.955422401428223, "learning_rate": 4.9935380936447375e-06, "loss": 0.20386546850204468, "step": 218 }, { "epoch": 0.16192236598890944, "grad_norm": 7.813543796539307, "learning_rate": 4.993401404393399e-06, "loss": 0.2609780430793762, "step": 219 }, { "epoch": 0.16266173752310537, "grad_norm": 1.6157500743865967, "learning_rate": 4.993263286656418e-06, "loss": 0.20290344953536987, "step": 220 }, { "epoch": 0.1634011090573013, "grad_norm": 5.039777755737305, "learning_rate": 4.993123740521737e-06, "loss": 0.210049107670784, "step": 221 }, { "epoch": 0.16414048059149722, "grad_norm": 7.681420803070068, "learning_rate": 4.992982766078216e-06, "loss": 0.22556757926940918, "step": 222 }, { "epoch": 0.16487985212569317, "grad_norm": 3.397508382797241, "learning_rate": 4.9928403634156194e-06, "loss": 0.204172283411026, "step": 223 }, { "epoch": 0.1656192236598891, "grad_norm": 2.7787954807281494, "learning_rate": 4.99269653262462e-06, "loss": 0.20344090461730957, "step": 224 }, { "epoch": 0.16635859519408502, "grad_norm": 3.201289176940918, "learning_rate": 4.992551273796805e-06, "loss": 0.20635998249053955, "step": 225 }, { "epoch": 0.16709796672828095, "grad_norm": 4.470575332641602, "learning_rate": 4.992404587024666e-06, "loss": 0.22582820057868958, "step": 226 }, { "epoch": 0.1678373382624769, "grad_norm": 3.059220314025879, "learning_rate": 4.992256472401606e-06, "loss": 0.20810261368751526, "step": 227 }, { "epoch": 0.16857670979667283, "grad_norm": 1.876301646232605, "learning_rate": 4.992106930021938e-06, "loss": 0.19764043390750885, "step": 228 }, { "epoch": 0.16931608133086876, "grad_norm": 4.272731781005859, "learning_rate": 4.991955959980882e-06, "loss": 0.20379337668418884, "step": 229 }, { "epoch": 0.17005545286506468, "grad_norm": 3.321269989013672, "learning_rate": 4.991803562374568e-06, "loss": 0.2033572942018509, "step": 230 }, { "epoch": 0.17079482439926064, "grad_norm": 3.107696056365967, "learning_rate": 4.991649737300037e-06, "loss": 0.22836437821388245, "step": 231 }, { "epoch": 0.17153419593345656, "grad_norm": 2.4938621520996094, "learning_rate": 4.991494484855235e-06, "loss": 0.2060500979423523, "step": 232 }, { "epoch": 0.1722735674676525, "grad_norm": 4.81053352355957, "learning_rate": 4.99133780513902e-06, "loss": 0.23198115825653076, "step": 233 }, { "epoch": 0.17301293900184844, "grad_norm": 3.2090816497802734, "learning_rate": 4.9911796982511576e-06, "loss": 0.21067175269126892, "step": 234 }, { "epoch": 0.17375231053604437, "grad_norm": 4.876527309417725, "learning_rate": 4.991020164292322e-06, "loss": 0.20077307522296906, "step": 235 }, { "epoch": 0.1744916820702403, "grad_norm": 2.8745005130767822, "learning_rate": 4.990859203364098e-06, "loss": 0.20144228637218475, "step": 236 }, { "epoch": 0.17523105360443622, "grad_norm": 5.046237468719482, "learning_rate": 4.990696815568975e-06, "loss": 0.21053576469421387, "step": 237 }, { "epoch": 0.17597042513863217, "grad_norm": 2.6758482456207275, "learning_rate": 4.9905330010103555e-06, "loss": 0.18410198390483856, "step": 238 }, { "epoch": 0.1767097966728281, "grad_norm": 2.8499555587768555, "learning_rate": 4.990367759792547e-06, "loss": 0.20831406116485596, "step": 239 }, { "epoch": 0.17744916820702403, "grad_norm": 4.266246318817139, "learning_rate": 4.990201092020768e-06, "loss": 0.1823267638683319, "step": 240 }, { "epoch": 0.17818853974121995, "grad_norm": 4.220733165740967, "learning_rate": 4.990032997801143e-06, "loss": 0.22271020710468292, "step": 241 }, { "epoch": 0.1789279112754159, "grad_norm": 2.7826857566833496, "learning_rate": 4.989863477240707e-06, "loss": 0.20133298635482788, "step": 242 }, { "epoch": 0.17966728280961183, "grad_norm": 4.39431619644165, "learning_rate": 4.989692530447402e-06, "loss": 0.1989506185054779, "step": 243 }, { "epoch": 0.18040665434380776, "grad_norm": 3.409743070602417, "learning_rate": 4.989520157530077e-06, "loss": 0.20215828716754913, "step": 244 }, { "epoch": 0.18114602587800369, "grad_norm": 4.522077560424805, "learning_rate": 4.989346358598493e-06, "loss": 0.1758376955986023, "step": 245 }, { "epoch": 0.18188539741219964, "grad_norm": 7.542318344116211, "learning_rate": 4.989171133763314e-06, "loss": 0.1875760555267334, "step": 246 }, { "epoch": 0.18262476894639557, "grad_norm": 7.179322719573975, "learning_rate": 4.988994483136115e-06, "loss": 0.21247649192810059, "step": 247 }, { "epoch": 0.1833641404805915, "grad_norm": 2.9111220836639404, "learning_rate": 4.988816406829379e-06, "loss": 0.20692162215709686, "step": 248 }, { "epoch": 0.18410351201478742, "grad_norm": 4.467881202697754, "learning_rate": 4.988636904956497e-06, "loss": 0.1803518533706665, "step": 249 }, { "epoch": 0.18484288354898337, "grad_norm": 7.424746513366699, "learning_rate": 4.988455977631764e-06, "loss": 0.22172431647777557, "step": 250 }, { "epoch": 0.1855822550831793, "grad_norm": 3.99017596244812, "learning_rate": 4.988273624970388e-06, "loss": 0.17181606590747833, "step": 251 }, { "epoch": 0.18632162661737522, "grad_norm": 5.996110439300537, "learning_rate": 4.988089847088481e-06, "loss": 0.17217034101486206, "step": 252 }, { "epoch": 0.18706099815157118, "grad_norm": 5.99023962020874, "learning_rate": 4.987904644103063e-06, "loss": 0.21597784757614136, "step": 253 }, { "epoch": 0.1878003696857671, "grad_norm": 4.2016072273254395, "learning_rate": 4.987718016132063e-06, "loss": 0.17583534121513367, "step": 254 }, { "epoch": 0.18853974121996303, "grad_norm": 2.455101251602173, "learning_rate": 4.9875299632943165e-06, "loss": 0.21074146032333374, "step": 255 }, { "epoch": 0.18927911275415896, "grad_norm": 5.065545082092285, "learning_rate": 4.9873404857095645e-06, "loss": 0.19428284466266632, "step": 256 }, { "epoch": 0.1900184842883549, "grad_norm": 6.558977127075195, "learning_rate": 4.987149583498459e-06, "loss": 0.23250046372413635, "step": 257 }, { "epoch": 0.19075785582255084, "grad_norm": 5.555972099304199, "learning_rate": 4.986957256782555e-06, "loss": 0.1705315262079239, "step": 258 }, { "epoch": 0.19149722735674676, "grad_norm": 6.838784217834473, "learning_rate": 4.986763505684317e-06, "loss": 0.21824459731578827, "step": 259 }, { "epoch": 0.1922365988909427, "grad_norm": 3.4801340103149414, "learning_rate": 4.986568330327118e-06, "loss": 0.18072687089443207, "step": 260 }, { "epoch": 0.19297597042513864, "grad_norm": 1.6046411991119385, "learning_rate": 4.986371730835233e-06, "loss": 0.2021583765745163, "step": 261 }, { "epoch": 0.19371534195933457, "grad_norm": 8.73495101928711, "learning_rate": 4.986173707333848e-06, "loss": 0.19706220924854279, "step": 262 }, { "epoch": 0.1944547134935305, "grad_norm": 4.29037618637085, "learning_rate": 4.985974259949056e-06, "loss": 0.20952951908111572, "step": 263 }, { "epoch": 0.19519408502772642, "grad_norm": 3.9060888290405273, "learning_rate": 4.985773388807852e-06, "loss": 0.21210977435112, "step": 264 }, { "epoch": 0.19593345656192238, "grad_norm": 12.160238265991211, "learning_rate": 4.985571094038143e-06, "loss": 0.23767417669296265, "step": 265 }, { "epoch": 0.1966728280961183, "grad_norm": 3.222282648086548, "learning_rate": 4.985367375768738e-06, "loss": 0.17967182397842407, "step": 266 }, { "epoch": 0.19741219963031423, "grad_norm": 1.6907967329025269, "learning_rate": 4.985162234129357e-06, "loss": 0.18400558829307556, "step": 267 }, { "epoch": 0.19815157116451015, "grad_norm": 5.50957727432251, "learning_rate": 4.984955669250623e-06, "loss": 0.1888962686061859, "step": 268 }, { "epoch": 0.1988909426987061, "grad_norm": 5.426759719848633, "learning_rate": 4.984747681264066e-06, "loss": 0.20472025871276855, "step": 269 }, { "epoch": 0.19963031423290203, "grad_norm": 2.0567116737365723, "learning_rate": 4.984538270302123e-06, "loss": 0.21856941282749176, "step": 270 }, { "epoch": 0.20036968576709796, "grad_norm": 3.721407651901245, "learning_rate": 4.984327436498135e-06, "loss": 0.21690595149993896, "step": 271 }, { "epoch": 0.2011090573012939, "grad_norm": 4.885490894317627, "learning_rate": 4.984115179986352e-06, "loss": 0.18959935009479523, "step": 272 }, { "epoch": 0.20184842883548984, "grad_norm": 1.5273241996765137, "learning_rate": 4.9839015009019255e-06, "loss": 0.19999068975448608, "step": 273 }, { "epoch": 0.20258780036968577, "grad_norm": 2.3311514854431152, "learning_rate": 4.98368639938092e-06, "loss": 0.21286432445049286, "step": 274 }, { "epoch": 0.2033271719038817, "grad_norm": 2.2482807636260986, "learning_rate": 4.983469875560297e-06, "loss": 0.1955692321062088, "step": 275 }, { "epoch": 0.20406654343807765, "grad_norm": 5.392755031585693, "learning_rate": 4.983251929577932e-06, "loss": 0.2153123915195465, "step": 276 }, { "epoch": 0.20480591497227357, "grad_norm": 3.6413066387176514, "learning_rate": 4.9830325615726e-06, "loss": 0.2079029381275177, "step": 277 }, { "epoch": 0.2055452865064695, "grad_norm": 3.016688108444214, "learning_rate": 4.982811771683982e-06, "loss": 0.19337427616119385, "step": 278 }, { "epoch": 0.20628465804066543, "grad_norm": 5.16331148147583, "learning_rate": 4.982589560052668e-06, "loss": 0.18010802567005157, "step": 279 }, { "epoch": 0.20702402957486138, "grad_norm": 5.901681423187256, "learning_rate": 4.9823659268201526e-06, "loss": 0.1627712845802307, "step": 280 }, { "epoch": 0.2077634011090573, "grad_norm": 5.180253028869629, "learning_rate": 4.982140872128831e-06, "loss": 0.22618380188941956, "step": 281 }, { "epoch": 0.20850277264325323, "grad_norm": 3.7634496688842773, "learning_rate": 4.981914396122009e-06, "loss": 0.19755639135837555, "step": 282 }, { "epoch": 0.20924214417744916, "grad_norm": 3.8151557445526123, "learning_rate": 4.981686498943895e-06, "loss": 0.21719706058502197, "step": 283 }, { "epoch": 0.2099815157116451, "grad_norm": 1.6722397804260254, "learning_rate": 4.981457180739601e-06, "loss": 0.18496403098106384, "step": 284 }, { "epoch": 0.21072088724584104, "grad_norm": 2.570924758911133, "learning_rate": 4.9812264416551465e-06, "loss": 0.16369685530662537, "step": 285 }, { "epoch": 0.21146025878003696, "grad_norm": 9.273048400878906, "learning_rate": 4.980994281837455e-06, "loss": 0.21571588516235352, "step": 286 }, { "epoch": 0.2121996303142329, "grad_norm": 2.93292498588562, "learning_rate": 4.980760701434353e-06, "loss": 0.21369490027427673, "step": 287 }, { "epoch": 0.21293900184842884, "grad_norm": 6.583449363708496, "learning_rate": 4.980525700594573e-06, "loss": 0.1661558598279953, "step": 288 }, { "epoch": 0.21367837338262477, "grad_norm": 5.399322509765625, "learning_rate": 4.980289279467753e-06, "loss": 0.19664588570594788, "step": 289 }, { "epoch": 0.2144177449168207, "grad_norm": 3.9231719970703125, "learning_rate": 4.980051438204433e-06, "loss": 0.1953173279762268, "step": 290 }, { "epoch": 0.21515711645101662, "grad_norm": 5.800563812255859, "learning_rate": 4.979812176956059e-06, "loss": 0.1774912029504776, "step": 291 }, { "epoch": 0.21589648798521258, "grad_norm": 4.565061092376709, "learning_rate": 4.97957149587498e-06, "loss": 0.2211931198835373, "step": 292 }, { "epoch": 0.2166358595194085, "grad_norm": 3.8341434001922607, "learning_rate": 4.979329395114451e-06, "loss": 0.1612946093082428, "step": 293 }, { "epoch": 0.21737523105360443, "grad_norm": 3.221891403198242, "learning_rate": 4.979085874828628e-06, "loss": 0.1794719099998474, "step": 294 }, { "epoch": 0.21811460258780038, "grad_norm": 6.422857284545898, "learning_rate": 4.978840935172573e-06, "loss": 0.2118307650089264, "step": 295 }, { "epoch": 0.2188539741219963, "grad_norm": 7.082592487335205, "learning_rate": 4.978594576302252e-06, "loss": 0.2010461539030075, "step": 296 }, { "epoch": 0.21959334565619223, "grad_norm": 7.824831008911133, "learning_rate": 4.9783467983745325e-06, "loss": 0.22383564710617065, "step": 297 }, { "epoch": 0.22033271719038816, "grad_norm": 5.248904705047607, "learning_rate": 4.978097601547188e-06, "loss": 0.20682084560394287, "step": 298 }, { "epoch": 0.22107208872458411, "grad_norm": 2.659776449203491, "learning_rate": 4.977846985978895e-06, "loss": 0.22223111987113953, "step": 299 }, { "epoch": 0.22181146025878004, "grad_norm": 2.6486568450927734, "learning_rate": 4.977594951829233e-06, "loss": 0.19220009446144104, "step": 300 }, { "epoch": 0.22255083179297597, "grad_norm": 2.1504580974578857, "learning_rate": 4.9773414992586835e-06, "loss": 0.2079121172428131, "step": 301 }, { "epoch": 0.2232902033271719, "grad_norm": 1.2692382335662842, "learning_rate": 4.977086628428634e-06, "loss": 0.18244265019893646, "step": 302 }, { "epoch": 0.22402957486136785, "grad_norm": 3.913120746612549, "learning_rate": 4.976830339501372e-06, "loss": 0.2229979932308197, "step": 303 }, { "epoch": 0.22476894639556377, "grad_norm": 2.697962999343872, "learning_rate": 4.97657263264009e-06, "loss": 0.2039739191532135, "step": 304 }, { "epoch": 0.2255083179297597, "grad_norm": 3.0162973403930664, "learning_rate": 4.976313508008882e-06, "loss": 0.215459406375885, "step": 305 }, { "epoch": 0.22624768946395563, "grad_norm": 1.6634107828140259, "learning_rate": 4.976052965772748e-06, "loss": 0.1940179318189621, "step": 306 }, { "epoch": 0.22698706099815158, "grad_norm": 1.9431514739990234, "learning_rate": 4.975791006097586e-06, "loss": 0.1942770630121231, "step": 307 }, { "epoch": 0.2277264325323475, "grad_norm": 6.323486328125, "learning_rate": 4.9755276291501995e-06, "loss": 0.1426488310098648, "step": 308 }, { "epoch": 0.22846580406654343, "grad_norm": 2.9403443336486816, "learning_rate": 4.975262835098294e-06, "loss": 0.21374762058258057, "step": 309 }, { "epoch": 0.22920517560073936, "grad_norm": 2.9680335521698, "learning_rate": 4.974996624110477e-06, "loss": 0.183905690908432, "step": 310 }, { "epoch": 0.2299445471349353, "grad_norm": 4.240804195404053, "learning_rate": 4.974728996356258e-06, "loss": 0.20215249061584473, "step": 311 }, { "epoch": 0.23068391866913124, "grad_norm": 4.961662292480469, "learning_rate": 4.9744599520060495e-06, "loss": 0.23449715971946716, "step": 312 }, { "epoch": 0.23142329020332716, "grad_norm": 4.812536239624023, "learning_rate": 4.9741894912311645e-06, "loss": 0.18681053817272186, "step": 313 }, { "epoch": 0.23216266173752312, "grad_norm": 7.933840751647949, "learning_rate": 4.9739176142038195e-06, "loss": 0.22535490989685059, "step": 314 }, { "epoch": 0.23290203327171904, "grad_norm": 2.9638919830322266, "learning_rate": 4.973644321097132e-06, "loss": 0.1969749480485916, "step": 315 }, { "epoch": 0.23364140480591497, "grad_norm": 3.4510436058044434, "learning_rate": 4.9733696120851226e-06, "loss": 0.18606729805469513, "step": 316 }, { "epoch": 0.2343807763401109, "grad_norm": 6.439594745635986, "learning_rate": 4.973093487342711e-06, "loss": 0.20119549334049225, "step": 317 }, { "epoch": 0.23512014787430685, "grad_norm": 4.457034111022949, "learning_rate": 4.972815947045718e-06, "loss": 0.210362046957016, "step": 318 }, { "epoch": 0.23585951940850278, "grad_norm": 2.5687339305877686, "learning_rate": 4.97253699137087e-06, "loss": 0.17477798461914062, "step": 319 }, { "epoch": 0.2365988909426987, "grad_norm": 5.151020050048828, "learning_rate": 4.9722566204957925e-06, "loss": 0.20246729254722595, "step": 320 }, { "epoch": 0.23733826247689463, "grad_norm": 4.75622034072876, "learning_rate": 4.971974834599009e-06, "loss": 0.2294383943080902, "step": 321 }, { "epoch": 0.23807763401109058, "grad_norm": 1.4919968843460083, "learning_rate": 4.971691633859947e-06, "loss": 0.17302784323692322, "step": 322 }, { "epoch": 0.2388170055452865, "grad_norm": 3.1454358100891113, "learning_rate": 4.971407018458937e-06, "loss": 0.16424450278282166, "step": 323 }, { "epoch": 0.23955637707948244, "grad_norm": 4.614196300506592, "learning_rate": 4.971120988577205e-06, "loss": 0.2002214789390564, "step": 324 }, { "epoch": 0.24029574861367836, "grad_norm": 2.8245813846588135, "learning_rate": 4.970833544396883e-06, "loss": 0.18749310076236725, "step": 325 }, { "epoch": 0.24103512014787432, "grad_norm": 2.6643552780151367, "learning_rate": 4.970544686100999e-06, "loss": 0.22568783164024353, "step": 326 }, { "epoch": 0.24177449168207024, "grad_norm": 6.18652868270874, "learning_rate": 4.970254413873484e-06, "loss": 0.198804572224617, "step": 327 }, { "epoch": 0.24251386321626617, "grad_norm": 5.638988018035889, "learning_rate": 4.96996272789917e-06, "loss": 0.20017044246196747, "step": 328 }, { "epoch": 0.2432532347504621, "grad_norm": 1.6891944408416748, "learning_rate": 4.969669628363787e-06, "loss": 0.19843482971191406, "step": 329 }, { "epoch": 0.24399260628465805, "grad_norm": 7.28590202331543, "learning_rate": 4.969375115453966e-06, "loss": 0.21186861395835876, "step": 330 }, { "epoch": 0.24473197781885397, "grad_norm": 5.366207599639893, "learning_rate": 4.969079189357238e-06, "loss": 0.20902897417545319, "step": 331 }, { "epoch": 0.2454713493530499, "grad_norm": 2.8776323795318604, "learning_rate": 4.9687818502620345e-06, "loss": 0.18302834033966064, "step": 332 }, { "epoch": 0.24621072088724585, "grad_norm": 1.7674108743667603, "learning_rate": 4.968483098357686e-06, "loss": 0.20859597623348236, "step": 333 }, { "epoch": 0.24695009242144178, "grad_norm": 3.011740207672119, "learning_rate": 4.968182933834422e-06, "loss": 0.22383351624011993, "step": 334 }, { "epoch": 0.2476894639556377, "grad_norm": 4.919951915740967, "learning_rate": 4.967881356883374e-06, "loss": 0.17659124732017517, "step": 335 }, { "epoch": 0.24842883548983363, "grad_norm": 1.964464783668518, "learning_rate": 4.967578367696569e-06, "loss": 0.19458222389221191, "step": 336 }, { "epoch": 0.2491682070240296, "grad_norm": 1.867526650428772, "learning_rate": 4.967273966466937e-06, "loss": 0.18991440534591675, "step": 337 }, { "epoch": 0.2499075785582255, "grad_norm": 5.571962356567383, "learning_rate": 4.966968153388304e-06, "loss": 0.19718895852565765, "step": 338 }, { "epoch": 0.25064695009242144, "grad_norm": 3.211603879928589, "learning_rate": 4.966660928655398e-06, "loss": 0.17445315420627594, "step": 339 }, { "epoch": 0.2513863216266174, "grad_norm": 2.6039721965789795, "learning_rate": 4.966352292463843e-06, "loss": 0.19233497977256775, "step": 340 }, { "epoch": 0.2521256931608133, "grad_norm": 3.65705943107605, "learning_rate": 4.966042245010164e-06, "loss": 0.19684341549873352, "step": 341 }, { "epoch": 0.25286506469500925, "grad_norm": 4.470652103424072, "learning_rate": 4.9657307864917825e-06, "loss": 0.18955132365226746, "step": 342 }, { "epoch": 0.2536044362292052, "grad_norm": 4.388053894042969, "learning_rate": 4.9654179171070205e-06, "loss": 0.20763079822063446, "step": 343 }, { "epoch": 0.2543438077634011, "grad_norm": 4.710072040557861, "learning_rate": 4.965103637055098e-06, "loss": 0.22144585847854614, "step": 344 }, { "epoch": 0.25508317929759705, "grad_norm": 1.4955312013626099, "learning_rate": 4.9647879465361325e-06, "loss": 0.1773630678653717, "step": 345 }, { "epoch": 0.25582255083179295, "grad_norm": 3.3636786937713623, "learning_rate": 4.96447084575114e-06, "loss": 0.21012577414512634, "step": 346 }, { "epoch": 0.2565619223659889, "grad_norm": 5.696310520172119, "learning_rate": 4.964152334902033e-06, "loss": 0.18874293565750122, "step": 347 }, { "epoch": 0.25730129390018486, "grad_norm": 3.7143826484680176, "learning_rate": 4.963832414191625e-06, "loss": 0.22474437952041626, "step": 348 }, { "epoch": 0.25804066543438076, "grad_norm": 3.10502290725708, "learning_rate": 4.963511083823625e-06, "loss": 0.16501834988594055, "step": 349 }, { "epoch": 0.2587800369685767, "grad_norm": 9.2413330078125, "learning_rate": 4.963188344002639e-06, "loss": 0.23573072254657745, "step": 350 }, { "epoch": 0.25951940850277266, "grad_norm": 4.487480640411377, "learning_rate": 4.962864194934173e-06, "loss": 0.1941886842250824, "step": 351 }, { "epoch": 0.26025878003696856, "grad_norm": 8.03272819519043, "learning_rate": 4.962538636824628e-06, "loss": 0.22661951184272766, "step": 352 }, { "epoch": 0.2609981515711645, "grad_norm": 3.8579957485198975, "learning_rate": 4.962211669881305e-06, "loss": 0.17571735382080078, "step": 353 }, { "epoch": 0.26173752310536047, "grad_norm": 1.5561574697494507, "learning_rate": 4.961883294312397e-06, "loss": 0.18316079676151276, "step": 354 }, { "epoch": 0.26247689463955637, "grad_norm": 3.325822591781616, "learning_rate": 4.961553510327e-06, "loss": 0.18487504124641418, "step": 355 }, { "epoch": 0.2632162661737523, "grad_norm": 2.027827501296997, "learning_rate": 4.9612223181351025e-06, "loss": 0.20551136136054993, "step": 356 }, { "epoch": 0.2639556377079482, "grad_norm": 1.90366530418396, "learning_rate": 4.96088971794759e-06, "loss": 0.19524309039115906, "step": 357 }, { "epoch": 0.2646950092421442, "grad_norm": 2.6779723167419434, "learning_rate": 4.9605557099762476e-06, "loss": 0.20615121722221375, "step": 358 }, { "epoch": 0.26543438077634013, "grad_norm": 3.2860589027404785, "learning_rate": 4.960220294433754e-06, "loss": 0.22218099236488342, "step": 359 }, { "epoch": 0.266173752310536, "grad_norm": 1.532070517539978, "learning_rate": 4.959883471533685e-06, "loss": 0.18928663432598114, "step": 360 }, { "epoch": 0.266913123844732, "grad_norm": 2.1958556175231934, "learning_rate": 4.959545241490514e-06, "loss": 0.180155947804451, "step": 361 }, { "epoch": 0.26765249537892793, "grad_norm": 1.4508006572723389, "learning_rate": 4.959205604519608e-06, "loss": 0.1717934012413025, "step": 362 }, { "epoch": 0.26839186691312383, "grad_norm": 4.675447463989258, "learning_rate": 4.958864560837229e-06, "loss": 0.14431101083755493, "step": 363 }, { "epoch": 0.2691312384473198, "grad_norm": 4.392378807067871, "learning_rate": 4.958522110660538e-06, "loss": 0.19377386569976807, "step": 364 }, { "epoch": 0.2698706099815157, "grad_norm": 4.7742438316345215, "learning_rate": 4.95817825420759e-06, "loss": 0.20461544394493103, "step": 365 }, { "epoch": 0.27060998151571164, "grad_norm": 1.655267596244812, "learning_rate": 4.957832991697337e-06, "loss": 0.18722176551818848, "step": 366 }, { "epoch": 0.2713493530499076, "grad_norm": 4.925625801086426, "learning_rate": 4.957486323349622e-06, "loss": 0.19576066732406616, "step": 367 }, { "epoch": 0.2720887245841035, "grad_norm": 1.7563157081604004, "learning_rate": 4.95713824938519e-06, "loss": 0.2177518606185913, "step": 368 }, { "epoch": 0.27282809611829945, "grad_norm": 3.2427380084991455, "learning_rate": 4.956788770025673e-06, "loss": 0.2151784896850586, "step": 369 }, { "epoch": 0.2735674676524954, "grad_norm": 2.3777709007263184, "learning_rate": 4.956437885493603e-06, "loss": 0.19427549839019775, "step": 370 }, { "epoch": 0.2743068391866913, "grad_norm": 2.077960729598999, "learning_rate": 4.956085596012407e-06, "loss": 0.1898365616798401, "step": 371 }, { "epoch": 0.27504621072088725, "grad_norm": 3.064556837081909, "learning_rate": 4.955731901806405e-06, "loss": 0.22009505331516266, "step": 372 }, { "epoch": 0.2757855822550832, "grad_norm": 5.471397876739502, "learning_rate": 4.955376803100811e-06, "loss": 0.2028864175081253, "step": 373 }, { "epoch": 0.2765249537892791, "grad_norm": 1.9317107200622559, "learning_rate": 4.955020300121735e-06, "loss": 0.19085127115249634, "step": 374 }, { "epoch": 0.27726432532347506, "grad_norm": 3.02215576171875, "learning_rate": 4.954662393096179e-06, "loss": 0.14925025403499603, "step": 375 }, { "epoch": 0.27800369685767096, "grad_norm": 1.817172646522522, "learning_rate": 4.9543030822520415e-06, "loss": 0.15173056721687317, "step": 376 }, { "epoch": 0.2787430683918669, "grad_norm": 3.618594169616699, "learning_rate": 4.953942367818113e-06, "loss": 0.20655080676078796, "step": 377 }, { "epoch": 0.27948243992606286, "grad_norm": 4.648283958435059, "learning_rate": 4.953580250024079e-06, "loss": 0.22417806088924408, "step": 378 }, { "epoch": 0.28022181146025876, "grad_norm": 2.133479118347168, "learning_rate": 4.953216729100516e-06, "loss": 0.18681496381759644, "step": 379 }, { "epoch": 0.2809611829944547, "grad_norm": 4.717971324920654, "learning_rate": 4.952851805278898e-06, "loss": 0.15082715451717377, "step": 380 }, { "epoch": 0.28170055452865067, "grad_norm": 3.1319923400878906, "learning_rate": 4.952485478791591e-06, "loss": 0.17995312809944153, "step": 381 }, { "epoch": 0.28243992606284657, "grad_norm": 3.2635958194732666, "learning_rate": 4.9521177498718505e-06, "loss": 0.21016179025173187, "step": 382 }, { "epoch": 0.2831792975970425, "grad_norm": 4.120973587036133, "learning_rate": 4.951748618753829e-06, "loss": 0.18626368045806885, "step": 383 }, { "epoch": 0.2839186691312384, "grad_norm": 1.9164432287216187, "learning_rate": 4.951378085672572e-06, "loss": 0.16371814906597137, "step": 384 }, { "epoch": 0.2846580406654344, "grad_norm": 2.4474034309387207, "learning_rate": 4.9510061508640145e-06, "loss": 0.1972341388463974, "step": 385 }, { "epoch": 0.28539741219963033, "grad_norm": 4.209344387054443, "learning_rate": 4.950632814564988e-06, "loss": 0.18546301126480103, "step": 386 }, { "epoch": 0.2861367837338262, "grad_norm": 2.3941431045532227, "learning_rate": 4.950258077013212e-06, "loss": 0.19239214062690735, "step": 387 }, { "epoch": 0.2868761552680222, "grad_norm": 3.9577436447143555, "learning_rate": 4.949881938447303e-06, "loss": 0.20545785129070282, "step": 388 }, { "epoch": 0.28761552680221814, "grad_norm": 1.2644165754318237, "learning_rate": 4.949504399106765e-06, "loss": 0.19426003098487854, "step": 389 }, { "epoch": 0.28835489833641403, "grad_norm": 3.023110866546631, "learning_rate": 4.949125459231998e-06, "loss": 0.1979704052209854, "step": 390 }, { "epoch": 0.28909426987061, "grad_norm": 2.0273332595825195, "learning_rate": 4.948745119064291e-06, "loss": 0.16092219948768616, "step": 391 }, { "epoch": 0.28983364140480594, "grad_norm": 2.1678147315979004, "learning_rate": 4.948363378845825e-06, "loss": 0.20010335743427277, "step": 392 }, { "epoch": 0.29057301293900184, "grad_norm": 2.0422074794769287, "learning_rate": 4.947980238819674e-06, "loss": 0.18285232782363892, "step": 393 }, { "epoch": 0.2913123844731978, "grad_norm": 2.1470749378204346, "learning_rate": 4.947595699229803e-06, "loss": 0.17655855417251587, "step": 394 }, { "epoch": 0.2920517560073937, "grad_norm": 3.2475504875183105, "learning_rate": 4.947209760321066e-06, "loss": 0.19992129504680634, "step": 395 }, { "epoch": 0.29279112754158965, "grad_norm": 1.3587104082107544, "learning_rate": 4.94682242233921e-06, "loss": 0.16686829924583435, "step": 396 }, { "epoch": 0.2935304990757856, "grad_norm": 4.252788543701172, "learning_rate": 4.946433685530873e-06, "loss": 0.19102458655834198, "step": 397 }, { "epoch": 0.2942698706099815, "grad_norm": 2.1154394149780273, "learning_rate": 4.946043550143582e-06, "loss": 0.16859833896160126, "step": 398 }, { "epoch": 0.29500924214417745, "grad_norm": 4.0571608543396, "learning_rate": 4.945652016425757e-06, "loss": 0.18891999125480652, "step": 399 }, { "epoch": 0.2957486136783734, "grad_norm": 5.455165386199951, "learning_rate": 4.945259084626706e-06, "loss": 0.19426238536834717, "step": 400 }, { "epoch": 0.2964879852125693, "grad_norm": 3.197988510131836, "learning_rate": 4.94486475499663e-06, "loss": 0.21753697097301483, "step": 401 }, { "epoch": 0.29722735674676526, "grad_norm": 3.004603147506714, "learning_rate": 4.944469027786616e-06, "loss": 0.18005123734474182, "step": 402 }, { "epoch": 0.29796672828096116, "grad_norm": 2.420356035232544, "learning_rate": 4.944071903248646e-06, "loss": 0.1920320987701416, "step": 403 }, { "epoch": 0.2987060998151571, "grad_norm": 1.3282697200775146, "learning_rate": 4.943673381635586e-06, "loss": 0.20268066227436066, "step": 404 }, { "epoch": 0.29944547134935307, "grad_norm": 1.6986092329025269, "learning_rate": 4.9432734632011955e-06, "loss": 0.19831685721874237, "step": 405 }, { "epoch": 0.30018484288354896, "grad_norm": 4.763225078582764, "learning_rate": 4.942872148200124e-06, "loss": 0.18764550983905792, "step": 406 }, { "epoch": 0.3009242144177449, "grad_norm": 1.343257188796997, "learning_rate": 4.9424694368879076e-06, "loss": 0.17525959014892578, "step": 407 }, { "epoch": 0.30166358595194087, "grad_norm": 4.338349342346191, "learning_rate": 4.942065329520973e-06, "loss": 0.19736026227474213, "step": 408 }, { "epoch": 0.30240295748613677, "grad_norm": 2.9514787197113037, "learning_rate": 4.941659826356636e-06, "loss": 0.21636824309825897, "step": 409 }, { "epoch": 0.3031423290203327, "grad_norm": 4.1063151359558105, "learning_rate": 4.941252927653099e-06, "loss": 0.19319623708724976, "step": 410 }, { "epoch": 0.3038817005545287, "grad_norm": 3.9939539432525635, "learning_rate": 4.9408446336694565e-06, "loss": 0.20732679963111877, "step": 411 }, { "epoch": 0.3046210720887246, "grad_norm": 3.238866090774536, "learning_rate": 4.94043494466569e-06, "loss": 0.19890454411506653, "step": 412 }, { "epoch": 0.30536044362292053, "grad_norm": 2.324962854385376, "learning_rate": 4.940023860902667e-06, "loss": 0.17705708742141724, "step": 413 }, { "epoch": 0.30609981515711643, "grad_norm": 1.179255485534668, "learning_rate": 4.939611382642145e-06, "loss": 0.17000886797904968, "step": 414 }, { "epoch": 0.3068391866913124, "grad_norm": 1.3157126903533936, "learning_rate": 4.939197510146772e-06, "loss": 0.1866738200187683, "step": 415 }, { "epoch": 0.30757855822550834, "grad_norm": 2.030996084213257, "learning_rate": 4.9387822436800795e-06, "loss": 0.16800588369369507, "step": 416 }, { "epoch": 0.30831792975970423, "grad_norm": 2.4362869262695312, "learning_rate": 4.938365583506489e-06, "loss": 0.19858375191688538, "step": 417 }, { "epoch": 0.3090573012939002, "grad_norm": 4.595205783843994, "learning_rate": 4.937947529891308e-06, "loss": 0.14379513263702393, "step": 418 }, { "epoch": 0.30979667282809614, "grad_norm": 2.5465688705444336, "learning_rate": 4.937528083100733e-06, "loss": 0.19342434406280518, "step": 419 }, { "epoch": 0.31053604436229204, "grad_norm": 3.1635794639587402, "learning_rate": 4.937107243401847e-06, "loss": 0.1961977481842041, "step": 420 }, { "epoch": 0.311275415896488, "grad_norm": 1.4956053495407104, "learning_rate": 4.9366850110626165e-06, "loss": 0.18433625996112823, "step": 421 }, { "epoch": 0.3120147874306839, "grad_norm": 3.896792411804199, "learning_rate": 4.936261386351902e-06, "loss": 0.20037433505058289, "step": 422 }, { "epoch": 0.31275415896487985, "grad_norm": 1.513039231300354, "learning_rate": 4.935836369539446e-06, "loss": 0.1851411908864975, "step": 423 }, { "epoch": 0.3134935304990758, "grad_norm": 2.587890625, "learning_rate": 4.935409960895875e-06, "loss": 0.20852617919445038, "step": 424 }, { "epoch": 0.3142329020332717, "grad_norm": 2.4374547004699707, "learning_rate": 4.934982160692707e-06, "loss": 0.16787847876548767, "step": 425 }, { "epoch": 0.31497227356746765, "grad_norm": 2.765841245651245, "learning_rate": 4.934552969202343e-06, "loss": 0.17904826998710632, "step": 426 }, { "epoch": 0.3157116451016636, "grad_norm": 1.6950918436050415, "learning_rate": 4.934122386698071e-06, "loss": 0.18176405131816864, "step": 427 }, { "epoch": 0.3164510166358595, "grad_norm": 6.185370445251465, "learning_rate": 4.9336904134540644e-06, "loss": 0.2078048288822174, "step": 428 }, { "epoch": 0.31719038817005546, "grad_norm": 3.4578983783721924, "learning_rate": 4.933257049745382e-06, "loss": 0.16704431176185608, "step": 429 }, { "epoch": 0.3179297597042514, "grad_norm": 4.327828407287598, "learning_rate": 4.932822295847967e-06, "loss": 0.21701598167419434, "step": 430 }, { "epoch": 0.3186691312384473, "grad_norm": 2.504053831100464, "learning_rate": 4.932386152038651e-06, "loss": 0.18014076352119446, "step": 431 }, { "epoch": 0.31940850277264327, "grad_norm": 2.8309123516082764, "learning_rate": 4.931948618595147e-06, "loss": 0.19842250645160675, "step": 432 }, { "epoch": 0.32014787430683916, "grad_norm": 3.813372850418091, "learning_rate": 4.931509695796055e-06, "loss": 0.17601725459098816, "step": 433 }, { "epoch": 0.3208872458410351, "grad_norm": 2.5739028453826904, "learning_rate": 4.931069383920859e-06, "loss": 0.193696528673172, "step": 434 }, { "epoch": 0.32162661737523107, "grad_norm": 2.5279541015625, "learning_rate": 4.930627683249928e-06, "loss": 0.18102174997329712, "step": 435 }, { "epoch": 0.32236598890942697, "grad_norm": 2.5266284942626953, "learning_rate": 4.930184594064513e-06, "loss": 0.1833610236644745, "step": 436 }, { "epoch": 0.3231053604436229, "grad_norm": 7.800679683685303, "learning_rate": 4.929740116646753e-06, "loss": 0.20358334481716156, "step": 437 }, { "epoch": 0.3238447319778189, "grad_norm": 1.8812980651855469, "learning_rate": 4.929294251279668e-06, "loss": 0.19719475507736206, "step": 438 }, { "epoch": 0.3245841035120148, "grad_norm": 3.0061776638031006, "learning_rate": 4.928846998247164e-06, "loss": 0.16976672410964966, "step": 439 }, { "epoch": 0.32532347504621073, "grad_norm": 3.5746450424194336, "learning_rate": 4.928398357834028e-06, "loss": 0.1690438687801361, "step": 440 }, { "epoch": 0.32606284658040663, "grad_norm": 3.484279155731201, "learning_rate": 4.927948330325931e-06, "loss": 0.19455695152282715, "step": 441 }, { "epoch": 0.3268022181146026, "grad_norm": 3.2888169288635254, "learning_rate": 4.927496916009429e-06, "loss": 0.1968076527118683, "step": 442 }, { "epoch": 0.32754158964879854, "grad_norm": 2.8307578563690186, "learning_rate": 4.927044115171961e-06, "loss": 0.21008911728858948, "step": 443 }, { "epoch": 0.32828096118299444, "grad_norm": 2.035918712615967, "learning_rate": 4.926589928101847e-06, "loss": 0.21038123965263367, "step": 444 }, { "epoch": 0.3290203327171904, "grad_norm": 3.8375089168548584, "learning_rate": 4.92613435508829e-06, "loss": 0.20502425730228424, "step": 445 }, { "epoch": 0.32975970425138634, "grad_norm": 2.430025339126587, "learning_rate": 4.925677396421378e-06, "loss": 0.18770356476306915, "step": 446 }, { "epoch": 0.33049907578558224, "grad_norm": 3.0859756469726562, "learning_rate": 4.925219052392076e-06, "loss": 0.1940561830997467, "step": 447 }, { "epoch": 0.3312384473197782, "grad_norm": 2.578903913497925, "learning_rate": 4.924759323292237e-06, "loss": 0.1918293535709381, "step": 448 }, { "epoch": 0.33197781885397415, "grad_norm": 4.3484086990356445, "learning_rate": 4.924298209414594e-06, "loss": 0.20070844888687134, "step": 449 }, { "epoch": 0.33271719038817005, "grad_norm": 5.233785629272461, "learning_rate": 4.92383571105276e-06, "loss": 0.19226934015750885, "step": 450 }, { "epoch": 0.333456561922366, "grad_norm": 5.312265396118164, "learning_rate": 4.923371828501231e-06, "loss": 0.17979136109352112, "step": 451 }, { "epoch": 0.3341959334565619, "grad_norm": 4.207983493804932, "learning_rate": 4.922906562055383e-06, "loss": 0.18927723169326782, "step": 452 }, { "epoch": 0.33493530499075785, "grad_norm": 3.6746509075164795, "learning_rate": 4.922439912011476e-06, "loss": 0.17239272594451904, "step": 453 }, { "epoch": 0.3356746765249538, "grad_norm": 4.2154951095581055, "learning_rate": 4.92197187866665e-06, "loss": 0.1992768496274948, "step": 454 }, { "epoch": 0.3364140480591497, "grad_norm": 4.084573745727539, "learning_rate": 4.921502462318923e-06, "loss": 0.173785001039505, "step": 455 }, { "epoch": 0.33715341959334566, "grad_norm": 3.175710439682007, "learning_rate": 4.9210316632671976e-06, "loss": 0.1951555460691452, "step": 456 }, { "epoch": 0.3378927911275416, "grad_norm": 4.644819259643555, "learning_rate": 4.920559481811253e-06, "loss": 0.2152632772922516, "step": 457 }, { "epoch": 0.3386321626617375, "grad_norm": 3.5581958293914795, "learning_rate": 4.920085918251754e-06, "loss": 0.16869685053825378, "step": 458 }, { "epoch": 0.33937153419593347, "grad_norm": 5.551098346710205, "learning_rate": 4.91961097289024e-06, "loss": 0.18419837951660156, "step": 459 }, { "epoch": 0.34011090573012936, "grad_norm": 4.317574501037598, "learning_rate": 4.919134646029132e-06, "loss": 0.19256368279457092, "step": 460 }, { "epoch": 0.3408502772643253, "grad_norm": 1.4986698627471924, "learning_rate": 4.918656937971731e-06, "loss": 0.19777914881706238, "step": 461 }, { "epoch": 0.3415896487985213, "grad_norm": 3.350541591644287, "learning_rate": 4.9181778490222196e-06, "loss": 0.17946472764015198, "step": 462 }, { "epoch": 0.34232902033271717, "grad_norm": 5.112035751342773, "learning_rate": 4.917697379485655e-06, "loss": 0.20278307795524597, "step": 463 }, { "epoch": 0.3430683918669131, "grad_norm": 2.811821937561035, "learning_rate": 4.9172155296679795e-06, "loss": 0.22073101997375488, "step": 464 }, { "epoch": 0.3438077634011091, "grad_norm": 6.288913726806641, "learning_rate": 4.916732299876007e-06, "loss": 0.1886208951473236, "step": 465 }, { "epoch": 0.344547134935305, "grad_norm": 6.074789047241211, "learning_rate": 4.916247690417437e-06, "loss": 0.19286949932575226, "step": 466 }, { "epoch": 0.34528650646950093, "grad_norm": 0.8568958044052124, "learning_rate": 4.915761701600843e-06, "loss": 0.1920541673898697, "step": 467 }, { "epoch": 0.3460258780036969, "grad_norm": 4.819847583770752, "learning_rate": 4.915274333735679e-06, "loss": 0.1961280107498169, "step": 468 }, { "epoch": 0.3467652495378928, "grad_norm": 3.67781662940979, "learning_rate": 4.9147855871322755e-06, "loss": 0.17463059723377228, "step": 469 }, { "epoch": 0.34750462107208874, "grad_norm": 4.987102508544922, "learning_rate": 4.914295462101843e-06, "loss": 0.18125495314598083, "step": 470 }, { "epoch": 0.34824399260628464, "grad_norm": 2.9594712257385254, "learning_rate": 4.913803958956469e-06, "loss": 0.16773444414138794, "step": 471 }, { "epoch": 0.3489833641404806, "grad_norm": 7.884833812713623, "learning_rate": 4.913311078009116e-06, "loss": 0.1950250267982483, "step": 472 }, { "epoch": 0.34972273567467654, "grad_norm": 4.33767032623291, "learning_rate": 4.912816819573628e-06, "loss": 0.1456274837255478, "step": 473 }, { "epoch": 0.35046210720887244, "grad_norm": 3.581660509109497, "learning_rate": 4.912321183964724e-06, "loss": 0.18589167296886444, "step": 474 }, { "epoch": 0.3512014787430684, "grad_norm": 4.151760101318359, "learning_rate": 4.911824171497998e-06, "loss": 0.2012072205543518, "step": 475 }, { "epoch": 0.35194085027726435, "grad_norm": 4.453433513641357, "learning_rate": 4.911325782489923e-06, "loss": 0.17583242058753967, "step": 476 }, { "epoch": 0.35268022181146025, "grad_norm": 2.979870557785034, "learning_rate": 4.91082601725785e-06, "loss": 0.1413826048374176, "step": 477 }, { "epoch": 0.3534195933456562, "grad_norm": 2.302248001098633, "learning_rate": 4.910324876120004e-06, "loss": 0.20201097428798676, "step": 478 }, { "epoch": 0.3541589648798521, "grad_norm": 3.7518746852874756, "learning_rate": 4.909822359395484e-06, "loss": 0.19214878976345062, "step": 479 }, { "epoch": 0.35489833641404805, "grad_norm": 5.772529125213623, "learning_rate": 4.90931846740427e-06, "loss": 0.20354825258255005, "step": 480 }, { "epoch": 0.355637707948244, "grad_norm": 3.072641134262085, "learning_rate": 4.908813200467216e-06, "loss": 0.200429767370224, "step": 481 }, { "epoch": 0.3563770794824399, "grad_norm": 1.9725290536880493, "learning_rate": 4.908306558906048e-06, "loss": 0.18670910596847534, "step": 482 }, { "epoch": 0.35711645101663586, "grad_norm": 3.459484338760376, "learning_rate": 4.907798543043372e-06, "loss": 0.1918652057647705, "step": 483 }, { "epoch": 0.3578558225508318, "grad_norm": 3.267130136489868, "learning_rate": 4.907289153202665e-06, "loss": 0.18087346851825714, "step": 484 }, { "epoch": 0.3585951940850277, "grad_norm": 3.0090889930725098, "learning_rate": 4.9067783897082835e-06, "loss": 0.16905726492404938, "step": 485 }, { "epoch": 0.35933456561922367, "grad_norm": 2.823331356048584, "learning_rate": 4.906266252885454e-06, "loss": 0.1696850061416626, "step": 486 }, { "epoch": 0.3600739371534196, "grad_norm": 2.9213433265686035, "learning_rate": 4.9057527430602815e-06, "loss": 0.1698223352432251, "step": 487 }, { "epoch": 0.3608133086876155, "grad_norm": 1.8607254028320312, "learning_rate": 4.905237860559741e-06, "loss": 0.17930160462856293, "step": 488 }, { "epoch": 0.3615526802218115, "grad_norm": 3.277202844619751, "learning_rate": 4.9047216057116866e-06, "loss": 0.16621139645576477, "step": 489 }, { "epoch": 0.36229205175600737, "grad_norm": 3.695712089538574, "learning_rate": 4.904203978844841e-06, "loss": 0.17710039019584656, "step": 490 }, { "epoch": 0.3630314232902033, "grad_norm": 5.686550140380859, "learning_rate": 4.903684980288805e-06, "loss": 0.20494574308395386, "step": 491 }, { "epoch": 0.3637707948243993, "grad_norm": 2.676255941390991, "learning_rate": 4.903164610374048e-06, "loss": 0.1764630228281021, "step": 492 }, { "epoch": 0.3645101663585952, "grad_norm": 2.358436346054077, "learning_rate": 4.902642869431919e-06, "loss": 0.17097067832946777, "step": 493 }, { "epoch": 0.36524953789279113, "grad_norm": 2.53021240234375, "learning_rate": 4.902119757794635e-06, "loss": 0.14994224905967712, "step": 494 }, { "epoch": 0.3659889094269871, "grad_norm": 1.4023953676223755, "learning_rate": 4.901595275795287e-06, "loss": 0.185845285654068, "step": 495 }, { "epoch": 0.366728280961183, "grad_norm": 2.738544464111328, "learning_rate": 4.90106942376784e-06, "loss": 0.1734868586063385, "step": 496 }, { "epoch": 0.36746765249537894, "grad_norm": 1.9607151746749878, "learning_rate": 4.900542202047128e-06, "loss": 0.14070618152618408, "step": 497 }, { "epoch": 0.36820702402957484, "grad_norm": 1.9084216356277466, "learning_rate": 4.900013610968861e-06, "loss": 0.18144294619560242, "step": 498 }, { "epoch": 0.3689463955637708, "grad_norm": 3.969682216644287, "learning_rate": 4.899483650869621e-06, "loss": 0.16393789649009705, "step": 499 }, { "epoch": 0.36968576709796674, "grad_norm": 5.385253429412842, "learning_rate": 4.898952322086857e-06, "loss": 0.1486317217350006, "step": 500 }, { "epoch": 0.37042513863216264, "grad_norm": 2.9472525119781494, "learning_rate": 4.898419624958893e-06, "loss": 0.18063047528266907, "step": 501 }, { "epoch": 0.3711645101663586, "grad_norm": 5.679952621459961, "learning_rate": 4.897885559824925e-06, "loss": 0.18142956495285034, "step": 502 }, { "epoch": 0.37190388170055455, "grad_norm": 3.3808836936950684, "learning_rate": 4.897350127025019e-06, "loss": 0.1520889699459076, "step": 503 }, { "epoch": 0.37264325323475045, "grad_norm": 2.3147964477539062, "learning_rate": 4.89681332690011e-06, "loss": 0.1520254760980606, "step": 504 }, { "epoch": 0.3733826247689464, "grad_norm": 2.7464115619659424, "learning_rate": 4.896275159792007e-06, "loss": 0.17388701438903809, "step": 505 }, { "epoch": 0.37412199630314236, "grad_norm": 2.2185728549957275, "learning_rate": 4.895735626043389e-06, "loss": 0.18630501627922058, "step": 506 }, { "epoch": 0.37486136783733826, "grad_norm": 2.2162303924560547, "learning_rate": 4.895194725997801e-06, "loss": 0.19179809093475342, "step": 507 }, { "epoch": 0.3756007393715342, "grad_norm": 2.1078503131866455, "learning_rate": 4.8946524599996636e-06, "loss": 0.1656232476234436, "step": 508 }, { "epoch": 0.3763401109057301, "grad_norm": 4.562495708465576, "learning_rate": 4.894108828394264e-06, "loss": 0.21129556000232697, "step": 509 }, { "epoch": 0.37707948243992606, "grad_norm": 4.112639904022217, "learning_rate": 4.893563831527758e-06, "loss": 0.14961448311805725, "step": 510 }, { "epoch": 0.377818853974122, "grad_norm": 1.8613570928573608, "learning_rate": 4.893017469747175e-06, "loss": 0.17004230618476868, "step": 511 }, { "epoch": 0.3785582255083179, "grad_norm": 3.892235517501831, "learning_rate": 4.892469743400409e-06, "loss": 0.18642263114452362, "step": 512 }, { "epoch": 0.37929759704251387, "grad_norm": 2.2070419788360596, "learning_rate": 4.8919206528362245e-06, "loss": 0.21431925892829895, "step": 513 }, { "epoch": 0.3800369685767098, "grad_norm": 3.40138578414917, "learning_rate": 4.891370198404256e-06, "loss": 0.18731634318828583, "step": 514 }, { "epoch": 0.3807763401109057, "grad_norm": 1.8638018369674683, "learning_rate": 4.890818380455005e-06, "loss": 0.18315660953521729, "step": 515 }, { "epoch": 0.3815157116451017, "grad_norm": 3.1206178665161133, "learning_rate": 4.890265199339841e-06, "loss": 0.19617031514644623, "step": 516 }, { "epoch": 0.3822550831792976, "grad_norm": 1.5831366777420044, "learning_rate": 4.889710655411002e-06, "loss": 0.16518330574035645, "step": 517 }, { "epoch": 0.3829944547134935, "grad_norm": 2.227609634399414, "learning_rate": 4.889154749021593e-06, "loss": 0.16776011884212494, "step": 518 }, { "epoch": 0.3837338262476895, "grad_norm": 1.6013351678848267, "learning_rate": 4.888597480525591e-06, "loss": 0.18260546028614044, "step": 519 }, { "epoch": 0.3844731977818854, "grad_norm": 2.1580371856689453, "learning_rate": 4.888038850277833e-06, "loss": 0.16654786467552185, "step": 520 }, { "epoch": 0.38521256931608133, "grad_norm": 6.153237342834473, "learning_rate": 4.887478858634027e-06, "loss": 0.21952766180038452, "step": 521 }, { "epoch": 0.3859519408502773, "grad_norm": 1.8256964683532715, "learning_rate": 4.8869175059507505e-06, "loss": 0.1774391382932663, "step": 522 }, { "epoch": 0.3866913123844732, "grad_norm": 2.3875010013580322, "learning_rate": 4.886354792585441e-06, "loss": 0.17089591920375824, "step": 523 }, { "epoch": 0.38743068391866914, "grad_norm": 7.740001678466797, "learning_rate": 4.8857907188964085e-06, "loss": 0.13523267209529877, "step": 524 }, { "epoch": 0.38817005545286504, "grad_norm": 2.437002182006836, "learning_rate": 4.885225285242827e-06, "loss": 0.1886606514453888, "step": 525 }, { "epoch": 0.388909426987061, "grad_norm": 4.7654948234558105, "learning_rate": 4.884658491984735e-06, "loss": 0.17527072131633759, "step": 526 }, { "epoch": 0.38964879852125694, "grad_norm": 5.581814765930176, "learning_rate": 4.884090339483039e-06, "loss": 0.19239792227745056, "step": 527 }, { "epoch": 0.39038817005545284, "grad_norm": 3.2211484909057617, "learning_rate": 4.883520828099511e-06, "loss": 0.20401902496814728, "step": 528 }, { "epoch": 0.3911275415896488, "grad_norm": 3.96870493888855, "learning_rate": 4.882949958196784e-06, "loss": 0.19675013422966003, "step": 529 }, { "epoch": 0.39186691312384475, "grad_norm": 4.657577991485596, "learning_rate": 4.882377730138362e-06, "loss": 0.1720069944858551, "step": 530 }, { "epoch": 0.39260628465804065, "grad_norm": 4.620642185211182, "learning_rate": 4.8818041442886114e-06, "loss": 0.19151407480239868, "step": 531 }, { "epoch": 0.3933456561922366, "grad_norm": 2.7471158504486084, "learning_rate": 4.881229201012762e-06, "loss": 0.19531698524951935, "step": 532 }, { "epoch": 0.39408502772643256, "grad_norm": 4.209203243255615, "learning_rate": 4.880652900676909e-06, "loss": 0.17959073185920715, "step": 533 }, { "epoch": 0.39482439926062846, "grad_norm": 2.169490098953247, "learning_rate": 4.880075243648012e-06, "loss": 0.16387662291526794, "step": 534 }, { "epoch": 0.3955637707948244, "grad_norm": 2.23712158203125, "learning_rate": 4.879496230293893e-06, "loss": 0.21319183707237244, "step": 535 }, { "epoch": 0.3963031423290203, "grad_norm": 2.408522605895996, "learning_rate": 4.8789158609832404e-06, "loss": 0.1802571713924408, "step": 536 }, { "epoch": 0.39704251386321626, "grad_norm": 4.590185642242432, "learning_rate": 4.8783341360856025e-06, "loss": 0.19302377104759216, "step": 537 }, { "epoch": 0.3977818853974122, "grad_norm": 4.470290184020996, "learning_rate": 4.877751055971393e-06, "loss": 0.17637348175048828, "step": 538 }, { "epoch": 0.3985212569316081, "grad_norm": 5.832351207733154, "learning_rate": 4.877166621011889e-06, "loss": 0.19481545686721802, "step": 539 }, { "epoch": 0.39926062846580407, "grad_norm": 4.515493869781494, "learning_rate": 4.876580831579229e-06, "loss": 0.1793508678674698, "step": 540 }, { "epoch": 0.4, "grad_norm": 4.743751049041748, "learning_rate": 4.875993688046414e-06, "loss": 0.18941152095794678, "step": 541 }, { "epoch": 0.4007393715341959, "grad_norm": 3.208313465118408, "learning_rate": 4.875405190787308e-06, "loss": 0.2104940563440323, "step": 542 }, { "epoch": 0.4014787430683919, "grad_norm": 6.612025737762451, "learning_rate": 4.874815340176637e-06, "loss": 0.16686353087425232, "step": 543 }, { "epoch": 0.4022181146025878, "grad_norm": 3.009010076522827, "learning_rate": 4.874224136589988e-06, "loss": 0.15105843544006348, "step": 544 }, { "epoch": 0.4029574861367837, "grad_norm": 1.3085659742355347, "learning_rate": 4.8736315804038086e-06, "loss": 0.15873828530311584, "step": 545 }, { "epoch": 0.4036968576709797, "grad_norm": 2.3922126293182373, "learning_rate": 4.87303767199541e-06, "loss": 0.17829346656799316, "step": 546 }, { "epoch": 0.4044362292051756, "grad_norm": 5.232816696166992, "learning_rate": 4.872442411742964e-06, "loss": 0.1995542347431183, "step": 547 }, { "epoch": 0.40517560073937153, "grad_norm": 1.7204935550689697, "learning_rate": 4.8718458000255006e-06, "loss": 0.16186335682868958, "step": 548 }, { "epoch": 0.4059149722735675, "grad_norm": 2.549182653427124, "learning_rate": 4.871247837222915e-06, "loss": 0.18451234698295593, "step": 549 }, { "epoch": 0.4066543438077634, "grad_norm": 3.116356372833252, "learning_rate": 4.8706485237159575e-06, "loss": 0.16837669909000397, "step": 550 }, { "epoch": 0.40739371534195934, "grad_norm": 4.5641889572143555, "learning_rate": 4.870047859886241e-06, "loss": 0.1848747432231903, "step": 551 }, { "epoch": 0.4081330868761553, "grad_norm": 3.239764928817749, "learning_rate": 4.86944584611624e-06, "loss": 0.13390296697616577, "step": 552 }, { "epoch": 0.4088724584103512, "grad_norm": 2.7174062728881836, "learning_rate": 4.868842482789285e-06, "loss": 0.15561188757419586, "step": 553 }, { "epoch": 0.40961182994454715, "grad_norm": 3.0754411220550537, "learning_rate": 4.868237770289569e-06, "loss": 0.1861303597688675, "step": 554 }, { "epoch": 0.41035120147874304, "grad_norm": 3.5655486583709717, "learning_rate": 4.867631709002142e-06, "loss": 0.19067852199077606, "step": 555 }, { "epoch": 0.411090573012939, "grad_norm": 4.766719341278076, "learning_rate": 4.867024299312912e-06, "loss": 0.18927815556526184, "step": 556 }, { "epoch": 0.41182994454713495, "grad_norm": 4.282045841217041, "learning_rate": 4.866415541608649e-06, "loss": 0.17940691113471985, "step": 557 }, { "epoch": 0.41256931608133085, "grad_norm": 2.0632221698760986, "learning_rate": 4.865805436276979e-06, "loss": 0.163138747215271, "step": 558 }, { "epoch": 0.4133086876155268, "grad_norm": 2.138874053955078, "learning_rate": 4.865193983706386e-06, "loss": 0.1592516452074051, "step": 559 }, { "epoch": 0.41404805914972276, "grad_norm": 2.169502019882202, "learning_rate": 4.864581184286213e-06, "loss": 0.19060909748077393, "step": 560 }, { "epoch": 0.41478743068391866, "grad_norm": 5.698884963989258, "learning_rate": 4.863967038406659e-06, "loss": 0.13918736577033997, "step": 561 }, { "epoch": 0.4155268022181146, "grad_norm": 1.7531590461730957, "learning_rate": 4.863351546458783e-06, "loss": 0.18046881258487701, "step": 562 }, { "epoch": 0.4162661737523105, "grad_norm": 2.2431998252868652, "learning_rate": 4.862734708834497e-06, "loss": 0.1554529070854187, "step": 563 }, { "epoch": 0.41700554528650646, "grad_norm": 7.14267635345459, "learning_rate": 4.8621165259265745e-06, "loss": 0.18022370338439941, "step": 564 }, { "epoch": 0.4177449168207024, "grad_norm": 5.350924491882324, "learning_rate": 4.861496998128643e-06, "loss": 0.21169528365135193, "step": 565 }, { "epoch": 0.4184842883548983, "grad_norm": 2.7265310287475586, "learning_rate": 4.8608761258351855e-06, "loss": 0.17061878740787506, "step": 566 }, { "epoch": 0.41922365988909427, "grad_norm": 6.492031574249268, "learning_rate": 4.860253909441543e-06, "loss": 0.18847240507602692, "step": 567 }, { "epoch": 0.4199630314232902, "grad_norm": 7.95707893371582, "learning_rate": 4.859630349343913e-06, "loss": 0.15528300404548645, "step": 568 }, { "epoch": 0.4207024029574861, "grad_norm": 2.238361358642578, "learning_rate": 4.8590054459393466e-06, "loss": 0.18504366278648376, "step": 569 }, { "epoch": 0.4214417744916821, "grad_norm": 4.159053802490234, "learning_rate": 4.85837919962575e-06, "loss": 0.16755273938179016, "step": 570 }, { "epoch": 0.42218114602587803, "grad_norm": 4.831380367279053, "learning_rate": 4.857751610801887e-06, "loss": 0.17332260310649872, "step": 571 }, { "epoch": 0.4229205175600739, "grad_norm": 6.363707542419434, "learning_rate": 4.857122679867373e-06, "loss": 0.20205330848693848, "step": 572 }, { "epoch": 0.4236598890942699, "grad_norm": 1.5152571201324463, "learning_rate": 4.856492407222681e-06, "loss": 0.16709044575691223, "step": 573 }, { "epoch": 0.4243992606284658, "grad_norm": 4.529736042022705, "learning_rate": 4.855860793269136e-06, "loss": 0.19394269585609436, "step": 574 }, { "epoch": 0.42513863216266173, "grad_norm": 6.36679744720459, "learning_rate": 4.8552278384089205e-06, "loss": 0.18316340446472168, "step": 575 }, { "epoch": 0.4258780036968577, "grad_norm": 2.3298587799072266, "learning_rate": 4.854593543045066e-06, "loss": 0.19012309610843658, "step": 576 }, { "epoch": 0.4266173752310536, "grad_norm": 3.188291072845459, "learning_rate": 4.85395790758146e-06, "loss": 0.161784827709198, "step": 577 }, { "epoch": 0.42735674676524954, "grad_norm": 1.6403833627700806, "learning_rate": 4.853320932422845e-06, "loss": 0.19538724422454834, "step": 578 }, { "epoch": 0.4280961182994455, "grad_norm": 1.400687336921692, "learning_rate": 4.852682617974813e-06, "loss": 0.18570873141288757, "step": 579 }, { "epoch": 0.4288354898336414, "grad_norm": 3.08847975730896, "learning_rate": 4.852042964643813e-06, "loss": 0.18615923821926117, "step": 580 }, { "epoch": 0.42957486136783735, "grad_norm": 2.1283464431762695, "learning_rate": 4.851401972837142e-06, "loss": 0.19270402193069458, "step": 581 }, { "epoch": 0.43031423290203324, "grad_norm": 2.443974018096924, "learning_rate": 4.850759642962953e-06, "loss": 0.18501827120780945, "step": 582 }, { "epoch": 0.4310536044362292, "grad_norm": 2.6958086490631104, "learning_rate": 4.850115975430248e-06, "loss": 0.184330552816391, "step": 583 }, { "epoch": 0.43179297597042515, "grad_norm": 3.032975196838379, "learning_rate": 4.849470970648883e-06, "loss": 0.16360600292682648, "step": 584 }, { "epoch": 0.43253234750462105, "grad_norm": 2.377028465270996, "learning_rate": 4.848824629029566e-06, "loss": 0.1570342779159546, "step": 585 }, { "epoch": 0.433271719038817, "grad_norm": 2.3597986698150635, "learning_rate": 4.848176950983853e-06, "loss": 0.15508556365966797, "step": 586 }, { "epoch": 0.43401109057301296, "grad_norm": 3.5149123668670654, "learning_rate": 4.847527936924154e-06, "loss": 0.17341238260269165, "step": 587 }, { "epoch": 0.43475046210720886, "grad_norm": 2.002178907394409, "learning_rate": 4.846877587263728e-06, "loss": 0.17277827858924866, "step": 588 }, { "epoch": 0.4354898336414048, "grad_norm": 2.3497071266174316, "learning_rate": 4.846225902416686e-06, "loss": 0.17303788661956787, "step": 589 }, { "epoch": 0.43622920517560076, "grad_norm": 1.4045473337173462, "learning_rate": 4.845572882797987e-06, "loss": 0.18533827364444733, "step": 590 }, { "epoch": 0.43696857670979666, "grad_norm": 5.458283424377441, "learning_rate": 4.8449185288234425e-06, "loss": 0.16188675165176392, "step": 591 }, { "epoch": 0.4377079482439926, "grad_norm": 2.3139994144439697, "learning_rate": 4.844262840909712e-06, "loss": 0.1740817278623581, "step": 592 }, { "epoch": 0.4384473197781885, "grad_norm": 2.515165090560913, "learning_rate": 4.8436058194743034e-06, "loss": 0.18890434503555298, "step": 593 }, { "epoch": 0.43918669131238447, "grad_norm": 2.579596519470215, "learning_rate": 4.842947464935577e-06, "loss": 0.18913450837135315, "step": 594 }, { "epoch": 0.4399260628465804, "grad_norm": 6.075092792510986, "learning_rate": 4.842287777712739e-06, "loss": 0.17811734974384308, "step": 595 }, { "epoch": 0.4406654343807763, "grad_norm": 1.496395230293274, "learning_rate": 4.841626758225845e-06, "loss": 0.15902525186538696, "step": 596 }, { "epoch": 0.4414048059149723, "grad_norm": 2.3022255897521973, "learning_rate": 4.8409644068958e-06, "loss": 0.17672201991081238, "step": 597 }, { "epoch": 0.44214417744916823, "grad_norm": 5.081460475921631, "learning_rate": 4.8403007241443545e-06, "loss": 0.1813834309577942, "step": 598 }, { "epoch": 0.44288354898336413, "grad_norm": 3.415648937225342, "learning_rate": 4.8396357103941096e-06, "loss": 0.14309723675251007, "step": 599 }, { "epoch": 0.4436229205175601, "grad_norm": 2.820394992828369, "learning_rate": 4.838969366068513e-06, "loss": 0.1877417266368866, "step": 600 }, { "epoch": 0.444362292051756, "grad_norm": 3.2249021530151367, "learning_rate": 4.838301691591859e-06, "loss": 0.20784884691238403, "step": 601 }, { "epoch": 0.44510166358595193, "grad_norm": 4.827783107757568, "learning_rate": 4.8376326873892885e-06, "loss": 0.1602255254983902, "step": 602 }, { "epoch": 0.4458410351201479, "grad_norm": 3.4432904720306396, "learning_rate": 4.836962353886792e-06, "loss": 0.16869941353797913, "step": 603 }, { "epoch": 0.4465804066543438, "grad_norm": 3.3691577911376953, "learning_rate": 4.836290691511202e-06, "loss": 0.18920360505580902, "step": 604 }, { "epoch": 0.44731977818853974, "grad_norm": 1.7535011768341064, "learning_rate": 4.835617700690201e-06, "loss": 0.1592336744070053, "step": 605 }, { "epoch": 0.4480591497227357, "grad_norm": 2.055260419845581, "learning_rate": 4.834943381852315e-06, "loss": 0.15363892912864685, "step": 606 }, { "epoch": 0.4487985212569316, "grad_norm": 2.3964030742645264, "learning_rate": 4.8342677354269164e-06, "loss": 0.18163526058197021, "step": 607 }, { "epoch": 0.44953789279112755, "grad_norm": 3.4508090019226074, "learning_rate": 4.833590761844224e-06, "loss": 0.14943230152130127, "step": 608 }, { "epoch": 0.4502772643253235, "grad_norm": 4.812906265258789, "learning_rate": 4.832912461535299e-06, "loss": 0.15799014270305634, "step": 609 }, { "epoch": 0.4510166358595194, "grad_norm": 3.711688280105591, "learning_rate": 4.832232834932051e-06, "loss": 0.19815614819526672, "step": 610 }, { "epoch": 0.45175600739371535, "grad_norm": 2.9581902027130127, "learning_rate": 4.83155188246723e-06, "loss": 0.15151053667068481, "step": 611 }, { "epoch": 0.45249537892791125, "grad_norm": 5.7485809326171875, "learning_rate": 4.830869604574434e-06, "loss": 0.1953774392604828, "step": 612 }, { "epoch": 0.4532347504621072, "grad_norm": 3.04312801361084, "learning_rate": 4.830186001688104e-06, "loss": 0.16871272027492523, "step": 613 }, { "epoch": 0.45397412199630316, "grad_norm": 3.351126194000244, "learning_rate": 4.8295010742435215e-06, "loss": 0.16671720147132874, "step": 614 }, { "epoch": 0.45471349353049906, "grad_norm": 2.709904193878174, "learning_rate": 4.828814822676817e-06, "loss": 0.1444385051727295, "step": 615 }, { "epoch": 0.455452865064695, "grad_norm": 3.4417622089385986, "learning_rate": 4.828127247424959e-06, "loss": 0.17129871249198914, "step": 616 }, { "epoch": 0.45619223659889097, "grad_norm": 1.5835530757904053, "learning_rate": 4.827438348925762e-06, "loss": 0.16144095361232758, "step": 617 }, { "epoch": 0.45693160813308686, "grad_norm": 2.589468240737915, "learning_rate": 4.826748127617881e-06, "loss": 0.12764352560043335, "step": 618 }, { "epoch": 0.4576709796672828, "grad_norm": 2.0649001598358154, "learning_rate": 4.826056583940816e-06, "loss": 0.17904524505138397, "step": 619 }, { "epoch": 0.4584103512014787, "grad_norm": 2.1847739219665527, "learning_rate": 4.825363718334905e-06, "loss": 0.14998069405555725, "step": 620 }, { "epoch": 0.45914972273567467, "grad_norm": 2.3135342597961426, "learning_rate": 4.824669531241333e-06, "loss": 0.1659822165966034, "step": 621 }, { "epoch": 0.4598890942698706, "grad_norm": 3.2587273120880127, "learning_rate": 4.823974023102122e-06, "loss": 0.1796584129333496, "step": 622 }, { "epoch": 0.4606284658040665, "grad_norm": 3.390627145767212, "learning_rate": 4.8232771943601365e-06, "loss": 0.20018035173416138, "step": 623 }, { "epoch": 0.4613678373382625, "grad_norm": 2.0575685501098633, "learning_rate": 4.822579045459083e-06, "loss": 0.15734675526618958, "step": 624 }, { "epoch": 0.46210720887245843, "grad_norm": 3.43595290184021, "learning_rate": 4.821879576843507e-06, "loss": 0.14812694489955902, "step": 625 }, { "epoch": 0.46284658040665433, "grad_norm": 2.3066301345825195, "learning_rate": 4.821178788958795e-06, "loss": 0.15190483629703522, "step": 626 }, { "epoch": 0.4635859519408503, "grad_norm": 2.715143918991089, "learning_rate": 4.820476682251174e-06, "loss": 0.1483217477798462, "step": 627 }, { "epoch": 0.46432532347504624, "grad_norm": 4.144500255584717, "learning_rate": 4.8197732571677115e-06, "loss": 0.15923362970352173, "step": 628 }, { "epoch": 0.46506469500924214, "grad_norm": 1.8484433889389038, "learning_rate": 4.819068514156311e-06, "loss": 0.13856196403503418, "step": 629 }, { "epoch": 0.4658040665434381, "grad_norm": 3.299104690551758, "learning_rate": 4.818362453665719e-06, "loss": 0.20151162147521973, "step": 630 }, { "epoch": 0.466543438077634, "grad_norm": 3.4568839073181152, "learning_rate": 4.817655076145519e-06, "loss": 0.16786408424377441, "step": 631 }, { "epoch": 0.46728280961182994, "grad_norm": 2.4027838706970215, "learning_rate": 4.816946382046135e-06, "loss": 0.15152481198310852, "step": 632 }, { "epoch": 0.4680221811460259, "grad_norm": 3.5514273643493652, "learning_rate": 4.816236371818825e-06, "loss": 0.17088866233825684, "step": 633 }, { "epoch": 0.4687615526802218, "grad_norm": 1.9951978921890259, "learning_rate": 4.815525045915691e-06, "loss": 0.16185985505580902, "step": 634 }, { "epoch": 0.46950092421441775, "grad_norm": 2.368016004562378, "learning_rate": 4.814812404789667e-06, "loss": 0.1465839445590973, "step": 635 }, { "epoch": 0.4702402957486137, "grad_norm": 5.485845565795898, "learning_rate": 4.81409844889453e-06, "loss": 0.1960115134716034, "step": 636 }, { "epoch": 0.4709796672828096, "grad_norm": 2.507629871368408, "learning_rate": 4.81338317868489e-06, "loss": 0.16547927260398865, "step": 637 }, { "epoch": 0.47171903881700555, "grad_norm": 2.9249675273895264, "learning_rate": 4.812666594616195e-06, "loss": 0.18071894347667694, "step": 638 }, { "epoch": 0.47245841035120145, "grad_norm": 8.35390567779541, "learning_rate": 4.811948697144729e-06, "loss": 0.1699737310409546, "step": 639 }, { "epoch": 0.4731977818853974, "grad_norm": 1.8072086572647095, "learning_rate": 4.811229486727614e-06, "loss": 0.1789650321006775, "step": 640 }, { "epoch": 0.47393715341959336, "grad_norm": 3.2761032581329346, "learning_rate": 4.810508963822808e-06, "loss": 0.15378229320049286, "step": 641 }, { "epoch": 0.47467652495378926, "grad_norm": 5.414395332336426, "learning_rate": 4.809787128889103e-06, "loss": 0.16661874949932098, "step": 642 }, { "epoch": 0.4754158964879852, "grad_norm": 6.623290061950684, "learning_rate": 4.809063982386127e-06, "loss": 0.20721176266670227, "step": 643 }, { "epoch": 0.47615526802218117, "grad_norm": 3.0554277896881104, "learning_rate": 4.808339524774345e-06, "loss": 0.15209609270095825, "step": 644 }, { "epoch": 0.47689463955637706, "grad_norm": 5.524651527404785, "learning_rate": 4.8076137565150535e-06, "loss": 0.1879250705242157, "step": 645 }, { "epoch": 0.477634011090573, "grad_norm": 6.139001369476318, "learning_rate": 4.8068866780703874e-06, "loss": 0.19285783171653748, "step": 646 }, { "epoch": 0.478373382624769, "grad_norm": 3.092604398727417, "learning_rate": 4.806158289903311e-06, "loss": 0.1338043361902237, "step": 647 }, { "epoch": 0.47911275415896487, "grad_norm": 3.0564653873443604, "learning_rate": 4.805428592477628e-06, "loss": 0.1743101179599762, "step": 648 }, { "epoch": 0.4798521256931608, "grad_norm": 1.7672133445739746, "learning_rate": 4.804697586257972e-06, "loss": 0.13569793105125427, "step": 649 }, { "epoch": 0.4805914972273567, "grad_norm": 3.2575244903564453, "learning_rate": 4.803965271709811e-06, "loss": 0.13112036883831024, "step": 650 }, { "epoch": 0.4813308687615527, "grad_norm": 6.401089191436768, "learning_rate": 4.803231649299447e-06, "loss": 0.18618854880332947, "step": 651 }, { "epoch": 0.48207024029574863, "grad_norm": 3.732339382171631, "learning_rate": 4.802496719494014e-06, "loss": 0.17861336469650269, "step": 652 }, { "epoch": 0.48280961182994453, "grad_norm": 3.230048418045044, "learning_rate": 4.801760482761477e-06, "loss": 0.16654075682163239, "step": 653 }, { "epoch": 0.4835489833641405, "grad_norm": 4.619693279266357, "learning_rate": 4.801022939570636e-06, "loss": 0.1600017249584198, "step": 654 }, { "epoch": 0.48428835489833644, "grad_norm": 4.672868728637695, "learning_rate": 4.800284090391122e-06, "loss": 0.16701439023017883, "step": 655 }, { "epoch": 0.48502772643253234, "grad_norm": 2.353252410888672, "learning_rate": 4.799543935693396e-06, "loss": 0.14792703092098236, "step": 656 }, { "epoch": 0.4857670979667283, "grad_norm": 2.49165415763855, "learning_rate": 4.798802475948751e-06, "loss": 0.1891474425792694, "step": 657 }, { "epoch": 0.4865064695009242, "grad_norm": 5.1499834060668945, "learning_rate": 4.798059711629313e-06, "loss": 0.15494169294834137, "step": 658 }, { "epoch": 0.48724584103512014, "grad_norm": 3.5186126232147217, "learning_rate": 4.797315643208036e-06, "loss": 0.1836242377758026, "step": 659 }, { "epoch": 0.4879852125693161, "grad_norm": 1.800987958908081, "learning_rate": 4.796570271158707e-06, "loss": 0.18176795542240143, "step": 660 }, { "epoch": 0.488724584103512, "grad_norm": 2.5391438007354736, "learning_rate": 4.795823595955939e-06, "loss": 0.15545226633548737, "step": 661 }, { "epoch": 0.48946395563770795, "grad_norm": 6.6065473556518555, "learning_rate": 4.7950756180751804e-06, "loss": 0.16782599687576294, "step": 662 }, { "epoch": 0.4902033271719039, "grad_norm": 3.1068971157073975, "learning_rate": 4.794326337992703e-06, "loss": 0.1702817976474762, "step": 663 }, { "epoch": 0.4909426987060998, "grad_norm": 1.8538126945495605, "learning_rate": 4.793575756185614e-06, "loss": 0.16124844551086426, "step": 664 }, { "epoch": 0.49168207024029575, "grad_norm": 5.253505229949951, "learning_rate": 4.792823873131844e-06, "loss": 0.16606001555919647, "step": 665 }, { "epoch": 0.4924214417744917, "grad_norm": 4.241441249847412, "learning_rate": 4.792070689310154e-06, "loss": 0.18842411041259766, "step": 666 }, { "epoch": 0.4931608133086876, "grad_norm": 3.5139057636260986, "learning_rate": 4.791316205200136e-06, "loss": 0.15279416739940643, "step": 667 }, { "epoch": 0.49390018484288356, "grad_norm": 2.381545066833496, "learning_rate": 4.790560421282207e-06, "loss": 0.19262418150901794, "step": 668 }, { "epoch": 0.49463955637707946, "grad_norm": 1.9676443338394165, "learning_rate": 4.789803338037611e-06, "loss": 0.18425406515598297, "step": 669 }, { "epoch": 0.4953789279112754, "grad_norm": 3.8371763229370117, "learning_rate": 4.789044955948421e-06, "loss": 0.16363278031349182, "step": 670 }, { "epoch": 0.49611829944547137, "grad_norm": 1.765910267829895, "learning_rate": 4.788285275497538e-06, "loss": 0.17435094714164734, "step": 671 }, { "epoch": 0.49685767097966727, "grad_norm": 2.146967649459839, "learning_rate": 4.787524297168688e-06, "loss": 0.1694641411304474, "step": 672 }, { "epoch": 0.4975970425138632, "grad_norm": 5.4114251136779785, "learning_rate": 4.7867620214464235e-06, "loss": 0.14772212505340576, "step": 673 }, { "epoch": 0.4983364140480592, "grad_norm": 2.7055184841156006, "learning_rate": 4.785998448816123e-06, "loss": 0.16656965017318726, "step": 674 }, { "epoch": 0.49907578558225507, "grad_norm": 3.963123321533203, "learning_rate": 4.785233579763993e-06, "loss": 0.17154648900032043, "step": 675 }, { "epoch": 0.499815157116451, "grad_norm": 4.260042190551758, "learning_rate": 4.7844674147770615e-06, "loss": 0.17692404985427856, "step": 676 }, { "epoch": 0.500554528650647, "grad_norm": 2.0187723636627197, "learning_rate": 4.7836999543431865e-06, "loss": 0.16861923038959503, "step": 677 }, { "epoch": 0.5012939001848429, "grad_norm": 3.41925048828125, "learning_rate": 4.782931198951046e-06, "loss": 0.14844869077205658, "step": 678 }, { "epoch": 0.5020332717190388, "grad_norm": 3.441349983215332, "learning_rate": 4.7821611490901465e-06, "loss": 0.1628400981426239, "step": 679 }, { "epoch": 0.5027726432532348, "grad_norm": 4.1626434326171875, "learning_rate": 4.7813898052508165e-06, "loss": 0.17210349440574646, "step": 680 }, { "epoch": 0.5035120147874307, "grad_norm": 2.501157283782959, "learning_rate": 4.780617167924209e-06, "loss": 0.15621748566627502, "step": 681 }, { "epoch": 0.5042513863216266, "grad_norm": 3.340528964996338, "learning_rate": 4.779843237602303e-06, "loss": 0.17958465218544006, "step": 682 }, { "epoch": 0.5049907578558226, "grad_norm": 3.768277406692505, "learning_rate": 4.779068014777894e-06, "loss": 0.1524442583322525, "step": 683 }, { "epoch": 0.5057301293900185, "grad_norm": 3.8651115894317627, "learning_rate": 4.778291499944609e-06, "loss": 0.14457586407661438, "step": 684 }, { "epoch": 0.5064695009242144, "grad_norm": 2.8135881423950195, "learning_rate": 4.777513693596892e-06, "loss": 0.15564002096652985, "step": 685 }, { "epoch": 0.5072088724584104, "grad_norm": 2.3213863372802734, "learning_rate": 4.776734596230012e-06, "loss": 0.17202946543693542, "step": 686 }, { "epoch": 0.5079482439926063, "grad_norm": 2.5218937397003174, "learning_rate": 4.775954208340059e-06, "loss": 0.15667319297790527, "step": 687 }, { "epoch": 0.5086876155268022, "grad_norm": 1.7216167449951172, "learning_rate": 4.775172530423944e-06, "loss": 0.15292949974536896, "step": 688 }, { "epoch": 0.5094269870609982, "grad_norm": 2.7372326850891113, "learning_rate": 4.774389562979401e-06, "loss": 0.15320277214050293, "step": 689 }, { "epoch": 0.5101663585951941, "grad_norm": 2.343390941619873, "learning_rate": 4.773605306504984e-06, "loss": 0.1601538360118866, "step": 690 }, { "epoch": 0.51090573012939, "grad_norm": 2.6403021812438965, "learning_rate": 4.772819761500069e-06, "loss": 0.17365440726280212, "step": 691 }, { "epoch": 0.5116451016635859, "grad_norm": 2.694927453994751, "learning_rate": 4.772032928464853e-06, "loss": 0.1474243402481079, "step": 692 }, { "epoch": 0.5123844731977819, "grad_norm": 2.5230448246002197, "learning_rate": 4.771244807900348e-06, "loss": 0.13418862223625183, "step": 693 }, { "epoch": 0.5131238447319778, "grad_norm": 3.527421712875366, "learning_rate": 4.770455400308393e-06, "loss": 0.17688745260238647, "step": 694 }, { "epoch": 0.5138632162661737, "grad_norm": 2.78898024559021, "learning_rate": 4.769664706191642e-06, "loss": 0.1545880287885666, "step": 695 }, { "epoch": 0.5146025878003697, "grad_norm": 3.2859508991241455, "learning_rate": 4.76887272605357e-06, "loss": 0.2074928879737854, "step": 696 }, { "epoch": 0.5153419593345656, "grad_norm": 2.0945019721984863, "learning_rate": 4.7680794603984695e-06, "loss": 0.15830013155937195, "step": 697 }, { "epoch": 0.5160813308687615, "grad_norm": 3.715263605117798, "learning_rate": 4.767284909731453e-06, "loss": 0.16822434961795807, "step": 698 }, { "epoch": 0.5168207024029575, "grad_norm": 2.462273120880127, "learning_rate": 4.7664890745584505e-06, "loss": 0.15109318494796753, "step": 699 }, { "epoch": 0.5175600739371534, "grad_norm": 2.509509801864624, "learning_rate": 4.765691955386208e-06, "loss": 0.20115962624549866, "step": 700 }, { "epoch": 0.5182994454713493, "grad_norm": 1.8282169103622437, "learning_rate": 4.764893552722295e-06, "loss": 0.15242740511894226, "step": 701 }, { "epoch": 0.5190388170055453, "grad_norm": 1.346789002418518, "learning_rate": 4.764093867075091e-06, "loss": 0.15789571404457092, "step": 702 }, { "epoch": 0.5197781885397412, "grad_norm": 2.656355381011963, "learning_rate": 4.763292898953797e-06, "loss": 0.18069152534008026, "step": 703 }, { "epoch": 0.5205175600739371, "grad_norm": 2.5779054164886475, "learning_rate": 4.7624906488684295e-06, "loss": 0.10757294297218323, "step": 704 }, { "epoch": 0.5212569316081331, "grad_norm": 2.278080463409424, "learning_rate": 4.7616871173298205e-06, "loss": 0.14798283576965332, "step": 705 }, { "epoch": 0.521996303142329, "grad_norm": 2.4438042640686035, "learning_rate": 4.76088230484962e-06, "loss": 0.20000644028186798, "step": 706 }, { "epoch": 0.5227356746765249, "grad_norm": 3.593514919281006, "learning_rate": 4.76007621194029e-06, "loss": 0.1649719774723053, "step": 707 }, { "epoch": 0.5234750462107209, "grad_norm": 1.722262978553772, "learning_rate": 4.759268839115112e-06, "loss": 0.18969015777111053, "step": 708 }, { "epoch": 0.5242144177449168, "grad_norm": 3.946950912475586, "learning_rate": 4.758460186888181e-06, "loss": 0.1584019958972931, "step": 709 }, { "epoch": 0.5249537892791127, "grad_norm": 4.075962543487549, "learning_rate": 4.757650255774404e-06, "loss": 0.14005787670612335, "step": 710 }, { "epoch": 0.5256931608133086, "grad_norm": 2.16629958152771, "learning_rate": 4.756839046289506e-06, "loss": 0.12683147192001343, "step": 711 }, { "epoch": 0.5264325323475046, "grad_norm": 3.8803517818450928, "learning_rate": 4.756026558950025e-06, "loss": 0.15798993408679962, "step": 712 }, { "epoch": 0.5271719038817005, "grad_norm": 4.278544902801514, "learning_rate": 4.7552127942733115e-06, "loss": 0.1668548583984375, "step": 713 }, { "epoch": 0.5279112754158964, "grad_norm": 2.8580543994903564, "learning_rate": 4.75439775277753e-06, "loss": 0.1563376784324646, "step": 714 }, { "epoch": 0.5286506469500925, "grad_norm": 3.067194938659668, "learning_rate": 4.7535814349816586e-06, "loss": 0.18622975051403046, "step": 715 }, { "epoch": 0.5293900184842883, "grad_norm": 2.9218876361846924, "learning_rate": 4.7527638414054874e-06, "loss": 0.1670919507741928, "step": 716 }, { "epoch": 0.5301293900184842, "grad_norm": 6.6586079597473145, "learning_rate": 4.751944972569618e-06, "loss": 0.20902583003044128, "step": 717 }, { "epoch": 0.5308687615526803, "grad_norm": 3.5635130405426025, "learning_rate": 4.751124828995466e-06, "loss": 0.18023723363876343, "step": 718 }, { "epoch": 0.5316081330868762, "grad_norm": 2.9417660236358643, "learning_rate": 4.750303411205259e-06, "loss": 0.18108922243118286, "step": 719 }, { "epoch": 0.532347504621072, "grad_norm": 5.261779308319092, "learning_rate": 4.749480719722033e-06, "loss": 0.17399466037750244, "step": 720 }, { "epoch": 0.5330868761552681, "grad_norm": 5.429581165313721, "learning_rate": 4.748656755069637e-06, "loss": 0.18948733806610107, "step": 721 }, { "epoch": 0.533826247689464, "grad_norm": 2.128791093826294, "learning_rate": 4.74783151777273e-06, "loss": 0.1551417112350464, "step": 722 }, { "epoch": 0.5345656192236599, "grad_norm": 5.089292049407959, "learning_rate": 4.747005008356783e-06, "loss": 0.15517191588878632, "step": 723 }, { "epoch": 0.5353049907578559, "grad_norm": 4.941212177276611, "learning_rate": 4.746177227348075e-06, "loss": 0.19986218214035034, "step": 724 }, { "epoch": 0.5360443622920518, "grad_norm": 5.505227088928223, "learning_rate": 4.745348175273696e-06, "loss": 0.17089636623859406, "step": 725 }, { "epoch": 0.5367837338262477, "grad_norm": 2.668928384780884, "learning_rate": 4.744517852661544e-06, "loss": 0.1419331282377243, "step": 726 }, { "epoch": 0.5375231053604437, "grad_norm": 4.491743087768555, "learning_rate": 4.743686260040327e-06, "loss": 0.1639789491891861, "step": 727 }, { "epoch": 0.5382624768946396, "grad_norm": 4.847233295440674, "learning_rate": 4.742853397939562e-06, "loss": 0.18690389394760132, "step": 728 }, { "epoch": 0.5390018484288355, "grad_norm": 2.2415013313293457, "learning_rate": 4.742019266889575e-06, "loss": 0.14381393790245056, "step": 729 }, { "epoch": 0.5397412199630314, "grad_norm": 4.188422679901123, "learning_rate": 4.741183867421497e-06, "loss": 0.16937853395938873, "step": 730 }, { "epoch": 0.5404805914972274, "grad_norm": 3.549654245376587, "learning_rate": 4.740347200067268e-06, "loss": 0.13147613406181335, "step": 731 }, { "epoch": 0.5412199630314233, "grad_norm": 2.5654592514038086, "learning_rate": 4.7395092653596385e-06, "loss": 0.1743842363357544, "step": 732 }, { "epoch": 0.5419593345656192, "grad_norm": 3.090766668319702, "learning_rate": 4.73867006383216e-06, "loss": 0.16973069310188293, "step": 733 }, { "epoch": 0.5426987060998152, "grad_norm": 2.5740044116973877, "learning_rate": 4.737829596019198e-06, "loss": 0.12078191339969635, "step": 734 }, { "epoch": 0.5434380776340111, "grad_norm": 4.234180927276611, "learning_rate": 4.736987862455916e-06, "loss": 0.2068130373954773, "step": 735 }, { "epoch": 0.544177449168207, "grad_norm": 1.7133214473724365, "learning_rate": 4.736144863678291e-06, "loss": 0.16659721732139587, "step": 736 }, { "epoch": 0.544916820702403, "grad_norm": 2.647073984146118, "learning_rate": 4.735300600223102e-06, "loss": 0.12879198789596558, "step": 737 }, { "epoch": 0.5456561922365989, "grad_norm": 3.3823318481445312, "learning_rate": 4.7344550726279324e-06, "loss": 0.15147635340690613, "step": 738 }, { "epoch": 0.5463955637707948, "grad_norm": 3.4671883583068848, "learning_rate": 4.733608281431172e-06, "loss": 0.18467684090137482, "step": 739 }, { "epoch": 0.5471349353049908, "grad_norm": 2.13327693939209, "learning_rate": 4.732760227172016e-06, "loss": 0.16004934906959534, "step": 740 }, { "epoch": 0.5478743068391867, "grad_norm": 3.816216468811035, "learning_rate": 4.731910910390461e-06, "loss": 0.17592908442020416, "step": 741 }, { "epoch": 0.5486136783733826, "grad_norm": 2.4422860145568848, "learning_rate": 4.731060331627313e-06, "loss": 0.13157811760902405, "step": 742 }, { "epoch": 0.5493530499075786, "grad_norm": 2.3336808681488037, "learning_rate": 4.730208491424174e-06, "loss": 0.15509945154190063, "step": 743 }, { "epoch": 0.5500924214417745, "grad_norm": 2.2770748138427734, "learning_rate": 4.729355390323456e-06, "loss": 0.17931202054023743, "step": 744 }, { "epoch": 0.5508317929759704, "grad_norm": 3.2836380004882812, "learning_rate": 4.7285010288683685e-06, "loss": 0.1565467268228531, "step": 745 }, { "epoch": 0.5515711645101664, "grad_norm": 2.530832290649414, "learning_rate": 4.7276454076029286e-06, "loss": 0.16641592979431152, "step": 746 }, { "epoch": 0.5523105360443623, "grad_norm": 2.293135643005371, "learning_rate": 4.72678852707195e-06, "loss": 0.15423284471035004, "step": 747 }, { "epoch": 0.5530499075785582, "grad_norm": 4.384251117706299, "learning_rate": 4.7259303878210554e-06, "loss": 0.16930267214775085, "step": 748 }, { "epoch": 0.5537892791127541, "grad_norm": 3.5636847019195557, "learning_rate": 4.725070990396662e-06, "loss": 0.17344018816947937, "step": 749 }, { "epoch": 0.5545286506469501, "grad_norm": 3.61458158493042, "learning_rate": 4.724210335345992e-06, "loss": 0.15688879787921906, "step": 750 }, { "epoch": 0.555268022181146, "grad_norm": 3.9319772720336914, "learning_rate": 4.723348423217066e-06, "loss": 0.1448701173067093, "step": 751 }, { "epoch": 0.5560073937153419, "grad_norm": 4.074562072753906, "learning_rate": 4.722485254558709e-06, "loss": 0.19377128779888153, "step": 752 }, { "epoch": 0.5567467652495379, "grad_norm": 2.694023847579956, "learning_rate": 4.721620829920541e-06, "loss": 0.13138365745544434, "step": 753 }, { "epoch": 0.5574861367837338, "grad_norm": 4.746366024017334, "learning_rate": 4.720755149852986e-06, "loss": 0.1745488941669464, "step": 754 }, { "epoch": 0.5582255083179297, "grad_norm": 1.7620019912719727, "learning_rate": 4.7198882149072664e-06, "loss": 0.14545203745365143, "step": 755 }, { "epoch": 0.5589648798521257, "grad_norm": 3.990035057067871, "learning_rate": 4.7190200256354e-06, "loss": 0.15669745206832886, "step": 756 }, { "epoch": 0.5597042513863216, "grad_norm": 4.311541557312012, "learning_rate": 4.71815058259021e-06, "loss": 0.18237072229385376, "step": 757 }, { "epoch": 0.5604436229205175, "grad_norm": 2.8181302547454834, "learning_rate": 4.71727988632531e-06, "loss": 0.12621194124221802, "step": 758 }, { "epoch": 0.5611829944547135, "grad_norm": 2.9871037006378174, "learning_rate": 4.7164079373951194e-06, "loss": 0.19890844821929932, "step": 759 }, { "epoch": 0.5619223659889094, "grad_norm": 3.705742359161377, "learning_rate": 4.71553473635485e-06, "loss": 0.18368574976921082, "step": 760 }, { "epoch": 0.5626617375231053, "grad_norm": 4.602762222290039, "learning_rate": 4.714660283760512e-06, "loss": 0.16002175211906433, "step": 761 }, { "epoch": 0.5634011090573013, "grad_norm": 3.2789206504821777, "learning_rate": 4.7137845801689145e-06, "loss": 0.15745803713798523, "step": 762 }, { "epoch": 0.5641404805914972, "grad_norm": 2.595759630203247, "learning_rate": 4.7129076261376595e-06, "loss": 0.17154577374458313, "step": 763 }, { "epoch": 0.5648798521256931, "grad_norm": 5.3933000564575195, "learning_rate": 4.712029422225149e-06, "loss": 0.19739414751529694, "step": 764 }, { "epoch": 0.5656192236598891, "grad_norm": 7.134160995483398, "learning_rate": 4.71114996899058e-06, "loss": 0.1704511046409607, "step": 765 }, { "epoch": 0.566358595194085, "grad_norm": 3.53788161277771, "learning_rate": 4.710269266993943e-06, "loss": 0.1462898552417755, "step": 766 }, { "epoch": 0.5670979667282809, "grad_norm": 4.170438289642334, "learning_rate": 4.709387316796025e-06, "loss": 0.1679409295320511, "step": 767 }, { "epoch": 0.5678373382624768, "grad_norm": 5.376193523406982, "learning_rate": 4.708504118958408e-06, "loss": 0.13407905399799347, "step": 768 }, { "epoch": 0.5685767097966729, "grad_norm": 4.9290385246276855, "learning_rate": 4.7076196740434685e-06, "loss": 0.17424923181533813, "step": 769 }, { "epoch": 0.5693160813308688, "grad_norm": 3.747292995452881, "learning_rate": 4.706733982614375e-06, "loss": 0.1472903937101364, "step": 770 }, { "epoch": 0.5700554528650646, "grad_norm": 2.4772136211395264, "learning_rate": 4.705847045235094e-06, "loss": 0.1382380723953247, "step": 771 }, { "epoch": 0.5707948243992607, "grad_norm": 5.55945348739624, "learning_rate": 4.704958862470381e-06, "loss": 0.16387763619422913, "step": 772 }, { "epoch": 0.5715341959334566, "grad_norm": 4.411791801452637, "learning_rate": 4.704069434885787e-06, "loss": 0.1993158459663391, "step": 773 }, { "epoch": 0.5722735674676525, "grad_norm": 3.5378975868225098, "learning_rate": 4.703178763047654e-06, "loss": 0.17219647765159607, "step": 774 }, { "epoch": 0.5730129390018485, "grad_norm": 2.185805320739746, "learning_rate": 4.702286847523118e-06, "loss": 0.1375434547662735, "step": 775 }, { "epoch": 0.5737523105360444, "grad_norm": 3.99980092048645, "learning_rate": 4.7013936888801074e-06, "loss": 0.16684383153915405, "step": 776 }, { "epoch": 0.5744916820702403, "grad_norm": 2.881304979324341, "learning_rate": 4.700499287687339e-06, "loss": 0.15422748029232025, "step": 777 }, { "epoch": 0.5752310536044363, "grad_norm": 2.058443784713745, "learning_rate": 4.699603644514323e-06, "loss": 0.13026408851146698, "step": 778 }, { "epoch": 0.5759704251386322, "grad_norm": 3.243410348892212, "learning_rate": 4.69870675993136e-06, "loss": 0.10882095992565155, "step": 779 }, { "epoch": 0.5767097966728281, "grad_norm": 2.5407626628875732, "learning_rate": 4.697808634509541e-06, "loss": 0.15967699885368347, "step": 780 }, { "epoch": 0.5774491682070241, "grad_norm": 3.38043475151062, "learning_rate": 4.6969092688207495e-06, "loss": 0.17022819817066193, "step": 781 }, { "epoch": 0.57818853974122, "grad_norm": 2.4365482330322266, "learning_rate": 4.696008663437654e-06, "loss": 0.13741746544837952, "step": 782 }, { "epoch": 0.5789279112754159, "grad_norm": 2.5507407188415527, "learning_rate": 4.695106818933716e-06, "loss": 0.1290266513824463, "step": 783 }, { "epoch": 0.5796672828096119, "grad_norm": 2.752326011657715, "learning_rate": 4.694203735883185e-06, "loss": 0.16375917196273804, "step": 784 }, { "epoch": 0.5804066543438078, "grad_norm": 2.164813756942749, "learning_rate": 4.693299414861097e-06, "loss": 0.14548903703689575, "step": 785 }, { "epoch": 0.5811460258780037, "grad_norm": 2.7518274784088135, "learning_rate": 4.692393856443281e-06, "loss": 0.13392478227615356, "step": 786 }, { "epoch": 0.5818853974121996, "grad_norm": 3.160531759262085, "learning_rate": 4.691487061206351e-06, "loss": 0.12435350567102432, "step": 787 }, { "epoch": 0.5826247689463956, "grad_norm": 3.1571621894836426, "learning_rate": 4.690579029727707e-06, "loss": 0.12562653422355652, "step": 788 }, { "epoch": 0.5833641404805915, "grad_norm": 3.2757465839385986, "learning_rate": 4.68966976258554e-06, "loss": 0.13271868228912354, "step": 789 }, { "epoch": 0.5841035120147874, "grad_norm": 4.019262313842773, "learning_rate": 4.688759260358824e-06, "loss": 0.20915158092975616, "step": 790 }, { "epoch": 0.5848428835489834, "grad_norm": 2.7750794887542725, "learning_rate": 4.687847523627323e-06, "loss": 0.14903540909290314, "step": 791 }, { "epoch": 0.5855822550831793, "grad_norm": 3.8179593086242676, "learning_rate": 4.686934552971582e-06, "loss": 0.11250423640012741, "step": 792 }, { "epoch": 0.5863216266173752, "grad_norm": 4.755896091461182, "learning_rate": 4.6860203489729395e-06, "loss": 0.1758948564529419, "step": 793 }, { "epoch": 0.5870609981515712, "grad_norm": 2.8282487392425537, "learning_rate": 4.685104912213512e-06, "loss": 0.16034367680549622, "step": 794 }, { "epoch": 0.5878003696857671, "grad_norm": 4.784858226776123, "learning_rate": 4.6841882432762045e-06, "loss": 0.18371433019638062, "step": 795 }, { "epoch": 0.588539741219963, "grad_norm": 2.436652421951294, "learning_rate": 4.683270342744705e-06, "loss": 0.15164797008037567, "step": 796 }, { "epoch": 0.589279112754159, "grad_norm": 1.8144644498825073, "learning_rate": 4.682351211203488e-06, "loss": 0.15852400660514832, "step": 797 }, { "epoch": 0.5900184842883549, "grad_norm": 2.091435432434082, "learning_rate": 4.68143084923781e-06, "loss": 0.1579521745443344, "step": 798 }, { "epoch": 0.5907578558225508, "grad_norm": 2.591963768005371, "learning_rate": 4.68050925743371e-06, "loss": 0.14259767532348633, "step": 799 }, { "epoch": 0.5914972273567468, "grad_norm": 1.8591457605361938, "learning_rate": 4.679586436378013e-06, "loss": 0.1663329154253006, "step": 800 }, { "epoch": 0.5922365988909427, "grad_norm": 3.080106019973755, "learning_rate": 4.678662386658325e-06, "loss": 0.18536719679832458, "step": 801 }, { "epoch": 0.5929759704251386, "grad_norm": 1.8075209856033325, "learning_rate": 4.677737108863035e-06, "loss": 0.14151671528816223, "step": 802 }, { "epoch": 0.5937153419593346, "grad_norm": 2.6482961177825928, "learning_rate": 4.676810603581312e-06, "loss": 0.15199026465415955, "step": 803 }, { "epoch": 0.5944547134935305, "grad_norm": 3.3663501739501953, "learning_rate": 4.67588287140311e-06, "loss": 0.16286498308181763, "step": 804 }, { "epoch": 0.5951940850277264, "grad_norm": 2.3374996185302734, "learning_rate": 4.674953912919161e-06, "loss": 0.1739034652709961, "step": 805 }, { "epoch": 0.5959334565619223, "grad_norm": 3.3302481174468994, "learning_rate": 4.67402372872098e-06, "loss": 0.1344042420387268, "step": 806 }, { "epoch": 0.5966728280961183, "grad_norm": 3.4289963245391846, "learning_rate": 4.673092319400862e-06, "loss": 0.11309123784303665, "step": 807 }, { "epoch": 0.5974121996303142, "grad_norm": 6.576144218444824, "learning_rate": 4.67215968555188e-06, "loss": 0.20009011030197144, "step": 808 }, { "epoch": 0.5981515711645101, "grad_norm": 4.249537467956543, "learning_rate": 4.671225827767891e-06, "loss": 0.13477951288223267, "step": 809 }, { "epoch": 0.5988909426987061, "grad_norm": 2.8184189796447754, "learning_rate": 4.670290746643527e-06, "loss": 0.12623950839042664, "step": 810 }, { "epoch": 0.599630314232902, "grad_norm": 4.3566670417785645, "learning_rate": 4.669354442774201e-06, "loss": 0.16115516424179077, "step": 811 }, { "epoch": 0.6003696857670979, "grad_norm": 4.825724124908447, "learning_rate": 4.668416916756106e-06, "loss": 0.11342727392911911, "step": 812 }, { "epoch": 0.6011090573012939, "grad_norm": 5.438233375549316, "learning_rate": 4.66747816918621e-06, "loss": 0.11713738739490509, "step": 813 }, { "epoch": 0.6018484288354898, "grad_norm": 2.6600842475891113, "learning_rate": 4.66653820066226e-06, "loss": 0.13618376851081848, "step": 814 }, { "epoch": 0.6025878003696857, "grad_norm": 3.9937188625335693, "learning_rate": 4.665597011782782e-06, "loss": 0.18719980120658875, "step": 815 }, { "epoch": 0.6033271719038817, "grad_norm": 4.529217720031738, "learning_rate": 4.664654603147078e-06, "loss": 0.18820664286613464, "step": 816 }, { "epoch": 0.6040665434380776, "grad_norm": 2.238294839859009, "learning_rate": 4.6637109753552274e-06, "loss": 0.16447341442108154, "step": 817 }, { "epoch": 0.6048059149722735, "grad_norm": 2.7982404232025146, "learning_rate": 4.662766129008083e-06, "loss": 0.17174923419952393, "step": 818 }, { "epoch": 0.6055452865064695, "grad_norm": 3.839876651763916, "learning_rate": 4.661820064707277e-06, "loss": 0.12739691138267517, "step": 819 }, { "epoch": 0.6062846580406654, "grad_norm": 4.759812355041504, "learning_rate": 4.660872783055215e-06, "loss": 0.1510804295539856, "step": 820 }, { "epoch": 0.6070240295748613, "grad_norm": 2.4284396171569824, "learning_rate": 4.65992428465508e-06, "loss": 0.11400407552719116, "step": 821 }, { "epoch": 0.6077634011090574, "grad_norm": 2.4829514026641846, "learning_rate": 4.658974570110826e-06, "loss": 0.16546960175037384, "step": 822 }, { "epoch": 0.6085027726432533, "grad_norm": 3.8732802867889404, "learning_rate": 4.658023640027186e-06, "loss": 0.16657531261444092, "step": 823 }, { "epoch": 0.6092421441774492, "grad_norm": 3.4654600620269775, "learning_rate": 4.6570714950096616e-06, "loss": 0.14007113873958588, "step": 824 }, { "epoch": 0.609981515711645, "grad_norm": 2.0508153438568115, "learning_rate": 4.656118135664534e-06, "loss": 0.13597795367240906, "step": 825 }, { "epoch": 0.6107208872458411, "grad_norm": 2.4878275394439697, "learning_rate": 4.6551635625988545e-06, "loss": 0.14345982670783997, "step": 826 }, { "epoch": 0.611460258780037, "grad_norm": 2.895340919494629, "learning_rate": 4.654207776420446e-06, "loss": 0.12393543869256973, "step": 827 }, { "epoch": 0.6121996303142329, "grad_norm": 5.310749053955078, "learning_rate": 4.653250777737905e-06, "loss": 0.17174899578094482, "step": 828 }, { "epoch": 0.6129390018484289, "grad_norm": 2.2492661476135254, "learning_rate": 4.652292567160603e-06, "loss": 0.1287853717803955, "step": 829 }, { "epoch": 0.6136783733826248, "grad_norm": 2.5783681869506836, "learning_rate": 4.6513331452986775e-06, "loss": 0.14274033904075623, "step": 830 }, { "epoch": 0.6144177449168207, "grad_norm": 5.915743350982666, "learning_rate": 4.650372512763041e-06, "loss": 0.18231043219566345, "step": 831 }, { "epoch": 0.6151571164510167, "grad_norm": 4.482907772064209, "learning_rate": 4.649410670165377e-06, "loss": 0.18846265971660614, "step": 832 }, { "epoch": 0.6158964879852126, "grad_norm": 5.086235523223877, "learning_rate": 4.648447618118137e-06, "loss": 0.1632586419582367, "step": 833 }, { "epoch": 0.6166358595194085, "grad_norm": 4.184924602508545, "learning_rate": 4.647483357234547e-06, "loss": 0.1270846128463745, "step": 834 }, { "epoch": 0.6173752310536045, "grad_norm": 2.137194871902466, "learning_rate": 4.646517888128599e-06, "loss": 0.1303587704896927, "step": 835 }, { "epoch": 0.6181146025878004, "grad_norm": 2.5376205444335938, "learning_rate": 4.645551211415055e-06, "loss": 0.13980650901794434, "step": 836 }, { "epoch": 0.6188539741219963, "grad_norm": 3.1505329608917236, "learning_rate": 4.644583327709446e-06, "loss": 0.1414906084537506, "step": 837 }, { "epoch": 0.6195933456561923, "grad_norm": 3.3970324993133545, "learning_rate": 4.643614237628071e-06, "loss": 0.1438775360584259, "step": 838 }, { "epoch": 0.6203327171903882, "grad_norm": 3.074084520339966, "learning_rate": 4.642643941788e-06, "loss": 0.1902793049812317, "step": 839 }, { "epoch": 0.6210720887245841, "grad_norm": 3.9760305881500244, "learning_rate": 4.641672440807068e-06, "loss": 0.15291133522987366, "step": 840 }, { "epoch": 0.6218114602587801, "grad_norm": 3.0540902614593506, "learning_rate": 4.640699735303879e-06, "loss": 0.10921189934015274, "step": 841 }, { "epoch": 0.622550831792976, "grad_norm": 2.9761950969696045, "learning_rate": 4.639725825897801e-06, "loss": 0.13473181426525116, "step": 842 }, { "epoch": 0.6232902033271719, "grad_norm": 3.0858960151672363, "learning_rate": 4.638750713208973e-06, "loss": 0.16126051545143127, "step": 843 }, { "epoch": 0.6240295748613678, "grad_norm": 5.787192344665527, "learning_rate": 4.637774397858297e-06, "loss": 0.11963057518005371, "step": 844 }, { "epoch": 0.6247689463955638, "grad_norm": 3.011857032775879, "learning_rate": 4.636796880467441e-06, "loss": 0.16159473359584808, "step": 845 }, { "epoch": 0.6255083179297597, "grad_norm": 2.067073106765747, "learning_rate": 4.63581816165884e-06, "loss": 0.13979306817054749, "step": 846 }, { "epoch": 0.6262476894639556, "grad_norm": 2.323418378829956, "learning_rate": 4.634838242055693e-06, "loss": 0.15418553352355957, "step": 847 }, { "epoch": 0.6269870609981516, "grad_norm": 3.7476606369018555, "learning_rate": 4.633857122281963e-06, "loss": 0.1481591761112213, "step": 848 }, { "epoch": 0.6277264325323475, "grad_norm": 3.1903626918792725, "learning_rate": 4.632874802962379e-06, "loss": 0.1634623110294342, "step": 849 }, { "epoch": 0.6284658040665434, "grad_norm": 2.6922860145568848, "learning_rate": 4.6318912847224325e-06, "loss": 0.11368513107299805, "step": 850 }, { "epoch": 0.6292051756007394, "grad_norm": 3.72097110748291, "learning_rate": 4.630906568188378e-06, "loss": 0.14688491821289062, "step": 851 }, { "epoch": 0.6299445471349353, "grad_norm": 4.57450008392334, "learning_rate": 4.629920653987234e-06, "loss": 0.11524900794029236, "step": 852 }, { "epoch": 0.6306839186691312, "grad_norm": 3.108323574066162, "learning_rate": 4.628933542746781e-06, "loss": 0.13968993723392487, "step": 853 }, { "epoch": 0.6314232902033272, "grad_norm": 4.571876049041748, "learning_rate": 4.627945235095563e-06, "loss": 0.16889196634292603, "step": 854 }, { "epoch": 0.6321626617375231, "grad_norm": 3.5804479122161865, "learning_rate": 4.626955731662884e-06, "loss": 0.13069257140159607, "step": 855 }, { "epoch": 0.632902033271719, "grad_norm": 3.727830410003662, "learning_rate": 4.6259650330788104e-06, "loss": 0.13132549822330475, "step": 856 }, { "epoch": 0.633641404805915, "grad_norm": 2.817883014678955, "learning_rate": 4.62497313997417e-06, "loss": 0.156022310256958, "step": 857 }, { "epoch": 0.6343807763401109, "grad_norm": 3.061676025390625, "learning_rate": 4.623980052980549e-06, "loss": 0.12266946583986282, "step": 858 }, { "epoch": 0.6351201478743068, "grad_norm": 3.3481407165527344, "learning_rate": 4.6229857727302975e-06, "loss": 0.140580415725708, "step": 859 }, { "epoch": 0.6358595194085028, "grad_norm": 3.650984048843384, "learning_rate": 4.621990299856521e-06, "loss": 0.1375465989112854, "step": 860 }, { "epoch": 0.6365988909426987, "grad_norm": 3.0388832092285156, "learning_rate": 4.62099363499309e-06, "loss": 0.12522810697555542, "step": 861 }, { "epoch": 0.6373382624768946, "grad_norm": 3.3366925716400146, "learning_rate": 4.619995778774627e-06, "loss": 0.1459694504737854, "step": 862 }, { "epoch": 0.6380776340110905, "grad_norm": 3.993812322616577, "learning_rate": 4.618996731836521e-06, "loss": 0.17939409613609314, "step": 863 }, { "epoch": 0.6388170055452865, "grad_norm": 2.6570732593536377, "learning_rate": 4.617996494814911e-06, "loss": 0.13610704243183136, "step": 864 }, { "epoch": 0.6395563770794824, "grad_norm": 3.9445607662200928, "learning_rate": 4.6169950683467e-06, "loss": 0.08996204286813736, "step": 865 }, { "epoch": 0.6402957486136783, "grad_norm": 3.650254487991333, "learning_rate": 4.615992453069546e-06, "loss": 0.1556396782398224, "step": 866 }, { "epoch": 0.6410351201478743, "grad_norm": 5.67866325378418, "learning_rate": 4.614988649621864e-06, "loss": 0.13273398578166962, "step": 867 }, { "epoch": 0.6417744916820702, "grad_norm": 4.126612663269043, "learning_rate": 4.613983658642826e-06, "loss": 0.12064468115568161, "step": 868 }, { "epoch": 0.6425138632162661, "grad_norm": 5.859738826751709, "learning_rate": 4.6129774807723596e-06, "loss": 0.19294096529483795, "step": 869 }, { "epoch": 0.6432532347504621, "grad_norm": 3.8913021087646484, "learning_rate": 4.611970116651149e-06, "loss": 0.16202887892723083, "step": 870 }, { "epoch": 0.643992606284658, "grad_norm": 2.434398889541626, "learning_rate": 4.610961566920632e-06, "loss": 0.16113388538360596, "step": 871 }, { "epoch": 0.6447319778188539, "grad_norm": 5.033020973205566, "learning_rate": 4.609951832223004e-06, "loss": 0.16166633367538452, "step": 872 }, { "epoch": 0.64547134935305, "grad_norm": 2.824805498123169, "learning_rate": 4.608940913201212e-06, "loss": 0.17702506482601166, "step": 873 }, { "epoch": 0.6462107208872458, "grad_norm": 2.676481008529663, "learning_rate": 4.60792881049896e-06, "loss": 0.12405809760093689, "step": 874 }, { "epoch": 0.6469500924214417, "grad_norm": 2.965719699859619, "learning_rate": 4.606915524760704e-06, "loss": 0.14849960803985596, "step": 875 }, { "epoch": 0.6476894639556378, "grad_norm": 3.846078872680664, "learning_rate": 4.605901056631653e-06, "loss": 0.15090373158454895, "step": 876 }, { "epoch": 0.6484288354898337, "grad_norm": 2.1301252841949463, "learning_rate": 4.60488540675777e-06, "loss": 0.11621060967445374, "step": 877 }, { "epoch": 0.6491682070240296, "grad_norm": 3.4088220596313477, "learning_rate": 4.60386857578577e-06, "loss": 0.13544222712516785, "step": 878 }, { "epoch": 0.6499075785582256, "grad_norm": 2.657604217529297, "learning_rate": 4.602850564363119e-06, "loss": 0.1473982185125351, "step": 879 }, { "epoch": 0.6506469500924215, "grad_norm": 3.1488847732543945, "learning_rate": 4.6018313731380375e-06, "loss": 0.13950097560882568, "step": 880 }, { "epoch": 0.6513863216266174, "grad_norm": 2.748117208480835, "learning_rate": 4.600811002759494e-06, "loss": 0.12969301640987396, "step": 881 }, { "epoch": 0.6521256931608133, "grad_norm": 3.4834654331207275, "learning_rate": 4.5997894538772095e-06, "loss": 0.12963443994522095, "step": 882 }, { "epoch": 0.6528650646950093, "grad_norm": 3.689753293991089, "learning_rate": 4.5987667271416544e-06, "loss": 0.12309286743402481, "step": 883 }, { "epoch": 0.6536044362292052, "grad_norm": 4.205737590789795, "learning_rate": 4.597742823204053e-06, "loss": 0.13294869661331177, "step": 884 }, { "epoch": 0.6543438077634011, "grad_norm": 4.607655048370361, "learning_rate": 4.596717742716372e-06, "loss": 0.17672327160835266, "step": 885 }, { "epoch": 0.6550831792975971, "grad_norm": 4.8295159339904785, "learning_rate": 4.595691486331334e-06, "loss": 0.16422435641288757, "step": 886 }, { "epoch": 0.655822550831793, "grad_norm": 5.725269794464111, "learning_rate": 4.594664054702407e-06, "loss": 0.14099374413490295, "step": 887 }, { "epoch": 0.6565619223659889, "grad_norm": 4.958497047424316, "learning_rate": 4.593635448483807e-06, "loss": 0.12831911444664001, "step": 888 }, { "epoch": 0.6573012939001849, "grad_norm": 2.7722439765930176, "learning_rate": 4.5926056683305e-06, "loss": 0.11747337877750397, "step": 889 }, { "epoch": 0.6580406654343808, "grad_norm": 3.642746686935425, "learning_rate": 4.591574714898199e-06, "loss": 0.09945312887430191, "step": 890 }, { "epoch": 0.6587800369685767, "grad_norm": 4.526064872741699, "learning_rate": 4.590542588843361e-06, "loss": 0.176011323928833, "step": 891 }, { "epoch": 0.6595194085027727, "grad_norm": 2.6406877040863037, "learning_rate": 4.589509290823195e-06, "loss": 0.13916009664535522, "step": 892 }, { "epoch": 0.6602587800369686, "grad_norm": 3.4166059494018555, "learning_rate": 4.588474821495652e-06, "loss": 0.11502349376678467, "step": 893 }, { "epoch": 0.6609981515711645, "grad_norm": 4.169234752655029, "learning_rate": 4.587439181519431e-06, "loss": 0.07498799264431, "step": 894 }, { "epoch": 0.6617375231053605, "grad_norm": 3.9462358951568604, "learning_rate": 4.586402371553974e-06, "loss": 0.15872886776924133, "step": 895 }, { "epoch": 0.6624768946395564, "grad_norm": 3.4353039264678955, "learning_rate": 4.585364392259472e-06, "loss": 0.1531192809343338, "step": 896 }, { "epoch": 0.6632162661737523, "grad_norm": 4.095661640167236, "learning_rate": 4.584325244296857e-06, "loss": 0.15357008576393127, "step": 897 }, { "epoch": 0.6639556377079483, "grad_norm": 2.5745861530303955, "learning_rate": 4.583284928327805e-06, "loss": 0.15138821303844452, "step": 898 }, { "epoch": 0.6646950092421442, "grad_norm": 3.4843149185180664, "learning_rate": 4.58224344501474e-06, "loss": 0.15188537538051605, "step": 899 }, { "epoch": 0.6654343807763401, "grad_norm": 4.33956241607666, "learning_rate": 4.581200795020824e-06, "loss": 0.1427384912967682, "step": 900 }, { "epoch": 0.666173752310536, "grad_norm": 5.883729457855225, "learning_rate": 4.580156979009965e-06, "loss": 0.1459416300058365, "step": 901 }, { "epoch": 0.666913123844732, "grad_norm": 4.148133277893066, "learning_rate": 4.579111997646814e-06, "loss": 0.14203105866909027, "step": 902 }, { "epoch": 0.6676524953789279, "grad_norm": 2.506080389022827, "learning_rate": 4.578065851596761e-06, "loss": 0.13446840643882751, "step": 903 }, { "epoch": 0.6683918669131238, "grad_norm": 4.657020568847656, "learning_rate": 4.57701854152594e-06, "loss": 0.15476399660110474, "step": 904 }, { "epoch": 0.6691312384473198, "grad_norm": 2.4924607276916504, "learning_rate": 4.575970068101227e-06, "loss": 0.17470020055770874, "step": 905 }, { "epoch": 0.6698706099815157, "grad_norm": 4.3477020263671875, "learning_rate": 4.574920431990235e-06, "loss": 0.13414892554283142, "step": 906 }, { "epoch": 0.6706099815157116, "grad_norm": 2.4202544689178467, "learning_rate": 4.5738696338613205e-06, "loss": 0.17305223643779755, "step": 907 }, { "epoch": 0.6713493530499076, "grad_norm": 3.0944859981536865, "learning_rate": 4.5728176743835814e-06, "loss": 0.11263453960418701, "step": 908 }, { "epoch": 0.6720887245841035, "grad_norm": 3.085806369781494, "learning_rate": 4.571764554226848e-06, "loss": 0.08359186351299286, "step": 909 }, { "epoch": 0.6728280961182994, "grad_norm": 4.176019668579102, "learning_rate": 4.5707102740616995e-06, "loss": 0.1703004091978073, "step": 910 }, { "epoch": 0.6735674676524954, "grad_norm": 2.579944610595703, "learning_rate": 4.569654834559446e-06, "loss": 0.17574048042297363, "step": 911 }, { "epoch": 0.6743068391866913, "grad_norm": 2.1564531326293945, "learning_rate": 4.568598236392139e-06, "loss": 0.15242262184619904, "step": 912 }, { "epoch": 0.6750462107208872, "grad_norm": 3.180447816848755, "learning_rate": 4.567540480232567e-06, "loss": 0.14276322722434998, "step": 913 }, { "epoch": 0.6757855822550832, "grad_norm": 2.486830949783325, "learning_rate": 4.566481566754255e-06, "loss": 0.12397731840610504, "step": 914 }, { "epoch": 0.6765249537892791, "grad_norm": 2.9408986568450928, "learning_rate": 4.565421496631469e-06, "loss": 0.10757972300052643, "step": 915 }, { "epoch": 0.677264325323475, "grad_norm": 4.077757358551025, "learning_rate": 4.564360270539207e-06, "loss": 0.1269952356815338, "step": 916 }, { "epoch": 0.678003696857671, "grad_norm": 3.2421720027923584, "learning_rate": 4.563297889153205e-06, "loss": 0.16037526726722717, "step": 917 }, { "epoch": 0.6787430683918669, "grad_norm": 5.249151706695557, "learning_rate": 4.562234353149934e-06, "loss": 0.11621865630149841, "step": 918 }, { "epoch": 0.6794824399260628, "grad_norm": 4.3541717529296875, "learning_rate": 4.561169663206599e-06, "loss": 0.14546369016170502, "step": 919 }, { "epoch": 0.6802218114602587, "grad_norm": 3.3286101818084717, "learning_rate": 4.560103820001144e-06, "loss": 0.14481991529464722, "step": 920 }, { "epoch": 0.6809611829944547, "grad_norm": 4.736220836639404, "learning_rate": 4.559036824212242e-06, "loss": 0.13298285007476807, "step": 921 }, { "epoch": 0.6817005545286506, "grad_norm": 4.186515808105469, "learning_rate": 4.5579686765193046e-06, "loss": 0.12137126922607422, "step": 922 }, { "epoch": 0.6824399260628465, "grad_norm": 1.977213978767395, "learning_rate": 4.556899377602474e-06, "loss": 0.15767601132392883, "step": 923 }, { "epoch": 0.6831792975970425, "grad_norm": 3.3122644424438477, "learning_rate": 4.5558289281426255e-06, "loss": 0.14476807415485382, "step": 924 }, { "epoch": 0.6839186691312384, "grad_norm": 5.153812408447266, "learning_rate": 4.554757328821368e-06, "loss": 0.059564124792814255, "step": 925 }, { "epoch": 0.6846580406654343, "grad_norm": 2.3860626220703125, "learning_rate": 4.553684580321042e-06, "loss": 0.15030890703201294, "step": 926 }, { "epoch": 0.6853974121996304, "grad_norm": 2.3708791732788086, "learning_rate": 4.552610683324721e-06, "loss": 0.16770091652870178, "step": 927 }, { "epoch": 0.6861367837338262, "grad_norm": 2.414897918701172, "learning_rate": 4.551535638516208e-06, "loss": 0.12617656588554382, "step": 928 }, { "epoch": 0.6868761552680221, "grad_norm": 2.7362213134765625, "learning_rate": 4.550459446580039e-06, "loss": 0.16617020964622498, "step": 929 }, { "epoch": 0.6876155268022182, "grad_norm": 3.579512357711792, "learning_rate": 4.549382108201477e-06, "loss": 0.1553082913160324, "step": 930 }, { "epoch": 0.6883548983364141, "grad_norm": 3.2399935722351074, "learning_rate": 4.548303624066518e-06, "loss": 0.10713831335306168, "step": 931 }, { "epoch": 0.68909426987061, "grad_norm": 3.066535711288452, "learning_rate": 4.547223994861888e-06, "loss": 0.12249761074781418, "step": 932 }, { "epoch": 0.689833641404806, "grad_norm": 2.5635292530059814, "learning_rate": 4.54614322127504e-06, "loss": 0.13524934649467468, "step": 933 }, { "epoch": 0.6905730129390019, "grad_norm": 2.6976327896118164, "learning_rate": 4.545061303994155e-06, "loss": 0.15150555968284607, "step": 934 }, { "epoch": 0.6913123844731978, "grad_norm": 2.578932285308838, "learning_rate": 4.543978243708145e-06, "loss": 0.1724955439567566, "step": 935 }, { "epoch": 0.6920517560073938, "grad_norm": 2.875854730606079, "learning_rate": 4.542894041106648e-06, "loss": 0.14080220460891724, "step": 936 }, { "epoch": 0.6927911275415897, "grad_norm": 2.75457763671875, "learning_rate": 4.541808696880031e-06, "loss": 0.12353220582008362, "step": 937 }, { "epoch": 0.6935304990757856, "grad_norm": 4.086211681365967, "learning_rate": 4.540722211719386e-06, "loss": 0.17197787761688232, "step": 938 }, { "epoch": 0.6942698706099815, "grad_norm": 3.139321804046631, "learning_rate": 4.539634586316532e-06, "loss": 0.11134091764688492, "step": 939 }, { "epoch": 0.6950092421441775, "grad_norm": 2.0771453380584717, "learning_rate": 4.538545821364016e-06, "loss": 0.12768277525901794, "step": 940 }, { "epoch": 0.6957486136783734, "grad_norm": 5.730567455291748, "learning_rate": 4.5374559175551075e-06, "loss": 0.1357649564743042, "step": 941 }, { "epoch": 0.6964879852125693, "grad_norm": 3.1061503887176514, "learning_rate": 4.536364875583802e-06, "loss": 0.09956662356853485, "step": 942 }, { "epoch": 0.6972273567467653, "grad_norm": 2.7885420322418213, "learning_rate": 4.535272696144823e-06, "loss": 0.09394440799951553, "step": 943 }, { "epoch": 0.6979667282809612, "grad_norm": 3.268977642059326, "learning_rate": 4.534179379933614e-06, "loss": 0.13582715392112732, "step": 944 }, { "epoch": 0.6987060998151571, "grad_norm": 4.384754180908203, "learning_rate": 4.533084927646343e-06, "loss": 0.13507215678691864, "step": 945 }, { "epoch": 0.6994454713493531, "grad_norm": 3.657912015914917, "learning_rate": 4.531989339979904e-06, "loss": 0.12236467003822327, "step": 946 }, { "epoch": 0.700184842883549, "grad_norm": 3.789090871810913, "learning_rate": 4.530892617631911e-06, "loss": 0.11131218820810318, "step": 947 }, { "epoch": 0.7009242144177449, "grad_norm": 2.455336093902588, "learning_rate": 4.529794761300704e-06, "loss": 0.12990456819534302, "step": 948 }, { "epoch": 0.7016635859519409, "grad_norm": 2.8196473121643066, "learning_rate": 4.528695771685341e-06, "loss": 0.15524879097938538, "step": 949 }, { "epoch": 0.7024029574861368, "grad_norm": 4.920297145843506, "learning_rate": 4.527595649485603e-06, "loss": 0.1328004151582718, "step": 950 }, { "epoch": 0.7031423290203327, "grad_norm": 4.343266010284424, "learning_rate": 4.526494395401996e-06, "loss": 0.15761369466781616, "step": 951 }, { "epoch": 0.7038817005545287, "grad_norm": 4.234330177307129, "learning_rate": 4.52539201013574e-06, "loss": 0.13302293419837952, "step": 952 }, { "epoch": 0.7046210720887246, "grad_norm": 4.571441650390625, "learning_rate": 4.52428849438878e-06, "loss": 0.17403501272201538, "step": 953 }, { "epoch": 0.7053604436229205, "grad_norm": 4.656363010406494, "learning_rate": 4.52318384886378e-06, "loss": 0.12864331901073456, "step": 954 }, { "epoch": 0.7060998151571165, "grad_norm": 3.5135886669158936, "learning_rate": 4.522078074264122e-06, "loss": 0.1431354135274887, "step": 955 }, { "epoch": 0.7068391866913124, "grad_norm": 4.51563024520874, "learning_rate": 4.520971171293909e-06, "loss": 0.11968652158975601, "step": 956 }, { "epoch": 0.7075785582255083, "grad_norm": 5.098189830780029, "learning_rate": 4.51986314065796e-06, "loss": 0.14905951917171478, "step": 957 }, { "epoch": 0.7083179297597042, "grad_norm": 3.188690662384033, "learning_rate": 4.518753983061814e-06, "loss": 0.1345970630645752, "step": 958 }, { "epoch": 0.7090573012939002, "grad_norm": 3.1782190799713135, "learning_rate": 4.517643699211728e-06, "loss": 0.12796521186828613, "step": 959 }, { "epoch": 0.7097966728280961, "grad_norm": 3.376465320587158, "learning_rate": 4.516532289814674e-06, "loss": 0.1357830911874771, "step": 960 }, { "epoch": 0.710536044362292, "grad_norm": 4.234277725219727, "learning_rate": 4.515419755578343e-06, "loss": 0.11514236778020859, "step": 961 }, { "epoch": 0.711275415896488, "grad_norm": 3.1300365924835205, "learning_rate": 4.514306097211138e-06, "loss": 0.14779509603977203, "step": 962 }, { "epoch": 0.7120147874306839, "grad_norm": 3.3429832458496094, "learning_rate": 4.513191315422184e-06, "loss": 0.12326538562774658, "step": 963 }, { "epoch": 0.7127541589648798, "grad_norm": 2.498469114303589, "learning_rate": 4.5120754109213185e-06, "loss": 0.134253591299057, "step": 964 }, { "epoch": 0.7134935304990758, "grad_norm": 3.425813913345337, "learning_rate": 4.510958384419091e-06, "loss": 0.09084688127040863, "step": 965 }, { "epoch": 0.7142329020332717, "grad_norm": 2.6926586627960205, "learning_rate": 4.50984023662677e-06, "loss": 0.11388084292411804, "step": 966 }, { "epoch": 0.7149722735674676, "grad_norm": 4.193363189697266, "learning_rate": 4.508720968256335e-06, "loss": 0.15023046731948853, "step": 967 }, { "epoch": 0.7157116451016636, "grad_norm": 4.55891752243042, "learning_rate": 4.507600580020481e-06, "loss": 0.10495650768280029, "step": 968 }, { "epoch": 0.7164510166358595, "grad_norm": 4.3082594871521, "learning_rate": 4.506479072632614e-06, "loss": 0.1308721899986267, "step": 969 }, { "epoch": 0.7171903881700554, "grad_norm": 2.880636692047119, "learning_rate": 4.505356446806855e-06, "loss": 0.11227679252624512, "step": 970 }, { "epoch": 0.7179297597042514, "grad_norm": 3.2387328147888184, "learning_rate": 4.504232703258034e-06, "loss": 0.1487547606229782, "step": 971 }, { "epoch": 0.7186691312384473, "grad_norm": 3.096862554550171, "learning_rate": 4.503107842701696e-06, "loss": 0.14352305233478546, "step": 972 }, { "epoch": 0.7194085027726432, "grad_norm": 3.5253679752349854, "learning_rate": 4.501981865854096e-06, "loss": 0.09951135516166687, "step": 973 }, { "epoch": 0.7201478743068392, "grad_norm": 3.58921217918396, "learning_rate": 4.500854773432199e-06, "loss": 0.09769683331251144, "step": 974 }, { "epoch": 0.7208872458410351, "grad_norm": 3.631120204925537, "learning_rate": 4.499726566153682e-06, "loss": 0.12253621220588684, "step": 975 }, { "epoch": 0.721626617375231, "grad_norm": 3.9342267513275146, "learning_rate": 4.49859724473693e-06, "loss": 0.097439706325531, "step": 976 }, { "epoch": 0.7223659889094269, "grad_norm": 2.979447841644287, "learning_rate": 4.497466809901038e-06, "loss": 0.13357670605182648, "step": 977 }, { "epoch": 0.723105360443623, "grad_norm": 3.7270028591156006, "learning_rate": 4.496335262365811e-06, "loss": 0.16792944073677063, "step": 978 }, { "epoch": 0.7238447319778188, "grad_norm": 4.278367519378662, "learning_rate": 4.495202602851762e-06, "loss": 0.1163327544927597, "step": 979 }, { "epoch": 0.7245841035120147, "grad_norm": 4.553407669067383, "learning_rate": 4.494068832080111e-06, "loss": 0.14824670553207397, "step": 980 }, { "epoch": 0.7253234750462108, "grad_norm": 3.1803860664367676, "learning_rate": 4.492933950772786e-06, "loss": 0.14143678545951843, "step": 981 }, { "epoch": 0.7260628465804067, "grad_norm": 3.9788050651550293, "learning_rate": 4.491797959652424e-06, "loss": 0.15169188380241394, "step": 982 }, { "epoch": 0.7268022181146025, "grad_norm": 4.845324993133545, "learning_rate": 4.490660859442368e-06, "loss": 0.13505685329437256, "step": 983 }, { "epoch": 0.7275415896487986, "grad_norm": 3.4502904415130615, "learning_rate": 4.489522650866663e-06, "loss": 0.10711633414030075, "step": 984 }, { "epoch": 0.7282809611829945, "grad_norm": 3.076472043991089, "learning_rate": 4.4883833346500664e-06, "loss": 0.14841115474700928, "step": 985 }, { "epoch": 0.7290203327171904, "grad_norm": 3.6944658756256104, "learning_rate": 4.487242911518036e-06, "loss": 0.12790890038013458, "step": 986 }, { "epoch": 0.7297597042513864, "grad_norm": 3.3809659481048584, "learning_rate": 4.486101382196737e-06, "loss": 0.04775594174861908, "step": 987 }, { "epoch": 0.7304990757855823, "grad_norm": 2.9861137866973877, "learning_rate": 4.484958747413038e-06, "loss": 0.11784778535366058, "step": 988 }, { "epoch": 0.7312384473197782, "grad_norm": 3.6210427284240723, "learning_rate": 4.483815007894511e-06, "loss": 0.15171775221824646, "step": 989 }, { "epoch": 0.7319778188539742, "grad_norm": 3.0571489334106445, "learning_rate": 4.4826701643694335e-06, "loss": 0.136599600315094, "step": 990 }, { "epoch": 0.7327171903881701, "grad_norm": 2.6709654331207275, "learning_rate": 4.481524217566783e-06, "loss": 0.15372419357299805, "step": 991 }, { "epoch": 0.733456561922366, "grad_norm": 3.1521079540252686, "learning_rate": 4.480377168216241e-06, "loss": 0.11068348586559296, "step": 992 }, { "epoch": 0.734195933456562, "grad_norm": 3.238267660140991, "learning_rate": 4.479229017048192e-06, "loss": 0.11461320519447327, "step": 993 }, { "epoch": 0.7349353049907579, "grad_norm": 3.1177589893341064, "learning_rate": 4.47807976479372e-06, "loss": 0.1321772038936615, "step": 994 }, { "epoch": 0.7356746765249538, "grad_norm": 3.451059579849243, "learning_rate": 4.476929412184613e-06, "loss": 0.1311279535293579, "step": 995 }, { "epoch": 0.7364140480591497, "grad_norm": 4.165340423583984, "learning_rate": 4.4757779599533565e-06, "loss": 0.17522203922271729, "step": 996 }, { "epoch": 0.7371534195933457, "grad_norm": 4.099287986755371, "learning_rate": 4.474625408833138e-06, "loss": 0.12204056233167648, "step": 997 }, { "epoch": 0.7378927911275416, "grad_norm": 4.342482089996338, "learning_rate": 4.473471759557845e-06, "loss": 0.09473098069429398, "step": 998 }, { "epoch": 0.7386321626617375, "grad_norm": 5.000842571258545, "learning_rate": 4.472317012862062e-06, "loss": 0.1432323455810547, "step": 999 }, { "epoch": 0.7393715341959335, "grad_norm": 4.301971435546875, "learning_rate": 4.4711611694810755e-06, "loss": 0.10806432366371155, "step": 1000 }, { "epoch": 0.7401109057301294, "grad_norm": 3.8276031017303467, "learning_rate": 4.4700042301508674e-06, "loss": 0.12284094095230103, "step": 1001 }, { "epoch": 0.7408502772643253, "grad_norm": 4.613646507263184, "learning_rate": 4.468846195608119e-06, "loss": 0.1353500783443451, "step": 1002 }, { "epoch": 0.7415896487985213, "grad_norm": 3.263678550720215, "learning_rate": 4.467687066590209e-06, "loss": 0.08983175456523895, "step": 1003 }, { "epoch": 0.7423290203327172, "grad_norm": 3.073976755142212, "learning_rate": 4.466526843835214e-06, "loss": 0.12559247016906738, "step": 1004 }, { "epoch": 0.7430683918669131, "grad_norm": 4.5271196365356445, "learning_rate": 4.465365528081903e-06, "loss": 0.09394796192646027, "step": 1005 }, { "epoch": 0.7438077634011091, "grad_norm": 3.309659957885742, "learning_rate": 4.464203120069746e-06, "loss": 0.09333689510822296, "step": 1006 }, { "epoch": 0.744547134935305, "grad_norm": 2.9283828735351562, "learning_rate": 4.463039620538904e-06, "loss": 0.11844326555728912, "step": 1007 }, { "epoch": 0.7452865064695009, "grad_norm": 4.667318820953369, "learning_rate": 4.461875030230238e-06, "loss": 0.09407253563404083, "step": 1008 }, { "epoch": 0.7460258780036969, "grad_norm": 5.4395856857299805, "learning_rate": 4.460709349885298e-06, "loss": 0.12424294650554657, "step": 1009 }, { "epoch": 0.7467652495378928, "grad_norm": 2.809845447540283, "learning_rate": 4.4595425802463326e-06, "loss": 0.150425523519516, "step": 1010 }, { "epoch": 0.7475046210720887, "grad_norm": 2.969723701477051, "learning_rate": 4.458374722056282e-06, "loss": 0.1579154133796692, "step": 1011 }, { "epoch": 0.7482439926062847, "grad_norm": 4.244015693664551, "learning_rate": 4.45720577605878e-06, "loss": 0.12015755474567413, "step": 1012 }, { "epoch": 0.7489833641404806, "grad_norm": 5.793033123016357, "learning_rate": 4.456035742998152e-06, "loss": 0.16730783879756927, "step": 1013 }, { "epoch": 0.7497227356746765, "grad_norm": 3.7295827865600586, "learning_rate": 4.454864623619417e-06, "loss": 0.11468426883220673, "step": 1014 }, { "epoch": 0.7504621072088724, "grad_norm": 4.940803527832031, "learning_rate": 4.453692418668285e-06, "loss": 0.17425070703029633, "step": 1015 }, { "epoch": 0.7512014787430684, "grad_norm": 6.385009765625, "learning_rate": 4.4525191288911575e-06, "loss": 0.16845598816871643, "step": 1016 }, { "epoch": 0.7519408502772643, "grad_norm": 3.470512866973877, "learning_rate": 4.451344755035126e-06, "loss": 0.09072493016719818, "step": 1017 }, { "epoch": 0.7526802218114602, "grad_norm": 2.9659676551818848, "learning_rate": 4.450169297847975e-06, "loss": 0.13771381974220276, "step": 1018 }, { "epoch": 0.7534195933456562, "grad_norm": 3.7065649032592773, "learning_rate": 4.448992758078173e-06, "loss": 0.09956687688827515, "step": 1019 }, { "epoch": 0.7541589648798521, "grad_norm": 5.255659580230713, "learning_rate": 4.447815136474886e-06, "loss": 0.1142631322145462, "step": 1020 }, { "epoch": 0.754898336414048, "grad_norm": 5.15312385559082, "learning_rate": 4.446636433787963e-06, "loss": 0.1562822461128235, "step": 1021 }, { "epoch": 0.755637707948244, "grad_norm": 4.78173303604126, "learning_rate": 4.44545665076794e-06, "loss": 0.08186087012290955, "step": 1022 }, { "epoch": 0.7563770794824399, "grad_norm": 3.0329394340515137, "learning_rate": 4.444275788166047e-06, "loss": 0.10984876751899719, "step": 1023 }, { "epoch": 0.7571164510166358, "grad_norm": 3.0205187797546387, "learning_rate": 4.443093846734197e-06, "loss": 0.12802478671073914, "step": 1024 }, { "epoch": 0.7578558225508318, "grad_norm": 3.444718360900879, "learning_rate": 4.441910827224992e-06, "loss": 0.11648163199424744, "step": 1025 }, { "epoch": 0.7585951940850277, "grad_norm": 4.654865741729736, "learning_rate": 4.440726730391717e-06, "loss": 0.15019533038139343, "step": 1026 }, { "epoch": 0.7593345656192236, "grad_norm": 4.706758975982666, "learning_rate": 4.4395415569883485e-06, "loss": 0.1424315869808197, "step": 1027 }, { "epoch": 0.7600739371534196, "grad_norm": 3.7103044986724854, "learning_rate": 4.438355307769545e-06, "loss": 0.10315121710300446, "step": 1028 }, { "epoch": 0.7608133086876155, "grad_norm": 4.332380294799805, "learning_rate": 4.437167983490649e-06, "loss": 0.14905458688735962, "step": 1029 }, { "epoch": 0.7615526802218114, "grad_norm": 3.726127862930298, "learning_rate": 4.43597958490769e-06, "loss": 0.09660619497299194, "step": 1030 }, { "epoch": 0.7622920517560073, "grad_norm": 3.6322402954101562, "learning_rate": 4.4347901127773814e-06, "loss": 0.127705916762352, "step": 1031 }, { "epoch": 0.7630314232902033, "grad_norm": 4.630151271820068, "learning_rate": 4.433599567857118e-06, "loss": 0.1547194868326187, "step": 1032 }, { "epoch": 0.7637707948243992, "grad_norm": 4.316861152648926, "learning_rate": 4.4324079509049805e-06, "loss": 0.1301060914993286, "step": 1033 }, { "epoch": 0.7645101663585951, "grad_norm": 3.71181583404541, "learning_rate": 4.431215262679731e-06, "loss": 0.1329740583896637, "step": 1034 }, { "epoch": 0.7652495378927912, "grad_norm": 3.1251254081726074, "learning_rate": 4.430021503940812e-06, "loss": 0.11432172358036041, "step": 1035 }, { "epoch": 0.765988909426987, "grad_norm": 3.074392080307007, "learning_rate": 4.428826675448351e-06, "loss": 0.11303959786891937, "step": 1036 }, { "epoch": 0.766728280961183, "grad_norm": 5.431188106536865, "learning_rate": 4.4276307779631535e-06, "loss": 0.14231106638908386, "step": 1037 }, { "epoch": 0.767467652495379, "grad_norm": 3.579179525375366, "learning_rate": 4.426433812246709e-06, "loss": 0.11836551874876022, "step": 1038 }, { "epoch": 0.7682070240295749, "grad_norm": 3.5403294563293457, "learning_rate": 4.425235779061184e-06, "loss": 0.09758812189102173, "step": 1039 }, { "epoch": 0.7689463955637708, "grad_norm": 4.34117317199707, "learning_rate": 4.424036679169425e-06, "loss": 0.1525457501411438, "step": 1040 }, { "epoch": 0.7696857670979668, "grad_norm": 3.8997256755828857, "learning_rate": 4.42283651333496e-06, "loss": 0.15682314336299896, "step": 1041 }, { "epoch": 0.7704251386321627, "grad_norm": 4.488009452819824, "learning_rate": 4.421635282321996e-06, "loss": 0.12856236100196838, "step": 1042 }, { "epoch": 0.7711645101663586, "grad_norm": 3.1330573558807373, "learning_rate": 4.420432986895415e-06, "loss": 0.11694025993347168, "step": 1043 }, { "epoch": 0.7719038817005546, "grad_norm": 4.095642566680908, "learning_rate": 4.419229627820777e-06, "loss": 0.10856086015701294, "step": 1044 }, { "epoch": 0.7726432532347505, "grad_norm": 4.891101360321045, "learning_rate": 4.418025205864324e-06, "loss": 0.08907091617584229, "step": 1045 }, { "epoch": 0.7733826247689464, "grad_norm": 3.7393009662628174, "learning_rate": 4.416819721792969e-06, "loss": 0.14010024070739746, "step": 1046 }, { "epoch": 0.7741219963031424, "grad_norm": 3.0926103591918945, "learning_rate": 4.415613176374306e-06, "loss": 0.14573585987091064, "step": 1047 }, { "epoch": 0.7748613678373383, "grad_norm": 4.161059379577637, "learning_rate": 4.414405570376601e-06, "loss": 0.13213640451431274, "step": 1048 }, { "epoch": 0.7756007393715342, "grad_norm": 3.8655312061309814, "learning_rate": 4.413196904568798e-06, "loss": 0.11837577074766159, "step": 1049 }, { "epoch": 0.7763401109057301, "grad_norm": 2.934983730316162, "learning_rate": 4.411987179720513e-06, "loss": 0.15042786300182343, "step": 1050 }, { "epoch": 0.7770794824399261, "grad_norm": 3.1665167808532715, "learning_rate": 4.410776396602041e-06, "loss": 0.13773328065872192, "step": 1051 }, { "epoch": 0.777818853974122, "grad_norm": 3.4579412937164307, "learning_rate": 4.409564555984347e-06, "loss": 0.10990186780691147, "step": 1052 }, { "epoch": 0.7785582255083179, "grad_norm": 3.798758029937744, "learning_rate": 4.408351658639069e-06, "loss": 0.16405028104782104, "step": 1053 }, { "epoch": 0.7792975970425139, "grad_norm": 3.057284116744995, "learning_rate": 4.407137705338521e-06, "loss": 0.11780878901481628, "step": 1054 }, { "epoch": 0.7800369685767098, "grad_norm": 2.5485527515411377, "learning_rate": 4.405922696855688e-06, "loss": 0.1054721251130104, "step": 1055 }, { "epoch": 0.7807763401109057, "grad_norm": 3.5711874961853027, "learning_rate": 4.404706633964223e-06, "loss": 0.05926886200904846, "step": 1056 }, { "epoch": 0.7815157116451017, "grad_norm": 3.9506704807281494, "learning_rate": 4.4034895174384575e-06, "loss": 0.10840491205453873, "step": 1057 }, { "epoch": 0.7822550831792976, "grad_norm": 4.124415397644043, "learning_rate": 4.40227134805339e-06, "loss": 0.15816934406757355, "step": 1058 }, { "epoch": 0.7829944547134935, "grad_norm": 4.59228515625, "learning_rate": 4.401052126584689e-06, "loss": 0.10812373459339142, "step": 1059 }, { "epoch": 0.7837338262476895, "grad_norm": 4.6335248947143555, "learning_rate": 4.399831853808694e-06, "loss": 0.15220823884010315, "step": 1060 }, { "epoch": 0.7844731977818854, "grad_norm": 4.5994415283203125, "learning_rate": 4.398610530502414e-06, "loss": 0.06704859435558319, "step": 1061 }, { "epoch": 0.7852125693160813, "grad_norm": 3.7176032066345215, "learning_rate": 4.397388157443524e-06, "loss": 0.10231754183769226, "step": 1062 }, { "epoch": 0.7859519408502773, "grad_norm": 4.658238410949707, "learning_rate": 4.396164735410372e-06, "loss": 0.1601904034614563, "step": 1063 }, { "epoch": 0.7866913123844732, "grad_norm": 3.2539734840393066, "learning_rate": 4.394940265181973e-06, "loss": 0.11078985035419464, "step": 1064 }, { "epoch": 0.7874306839186691, "grad_norm": 3.480057954788208, "learning_rate": 4.393714747538006e-06, "loss": 0.07022696733474731, "step": 1065 }, { "epoch": 0.7881700554528651, "grad_norm": 3.4934566020965576, "learning_rate": 4.392488183258821e-06, "loss": 0.12046889960765839, "step": 1066 }, { "epoch": 0.788909426987061, "grad_norm": 4.862364768981934, "learning_rate": 4.391260573125431e-06, "loss": 0.12558847665786743, "step": 1067 }, { "epoch": 0.7896487985212569, "grad_norm": 4.002211570739746, "learning_rate": 4.390031917919517e-06, "loss": 0.08621713519096375, "step": 1068 }, { "epoch": 0.7903881700554528, "grad_norm": 4.407464981079102, "learning_rate": 4.388802218423427e-06, "loss": 0.07491995394229889, "step": 1069 }, { "epoch": 0.7911275415896488, "grad_norm": 4.965733051300049, "learning_rate": 4.38757147542017e-06, "loss": 0.10412773489952087, "step": 1070 }, { "epoch": 0.7918669131238447, "grad_norm": 3.8768069744110107, "learning_rate": 4.386339689693423e-06, "loss": 0.10370329022407532, "step": 1071 }, { "epoch": 0.7926062846580406, "grad_norm": 3.48356294631958, "learning_rate": 4.385106862027523e-06, "loss": 0.08797916769981384, "step": 1072 }, { "epoch": 0.7933456561922366, "grad_norm": 4.467541217803955, "learning_rate": 4.383872993207476e-06, "loss": 0.09247865527868271, "step": 1073 }, { "epoch": 0.7940850277264325, "grad_norm": 4.759343147277832, "learning_rate": 4.382638084018946e-06, "loss": 0.08023039996623993, "step": 1074 }, { "epoch": 0.7948243992606284, "grad_norm": 4.145780563354492, "learning_rate": 4.381402135248262e-06, "loss": 0.07448101788759232, "step": 1075 }, { "epoch": 0.7955637707948244, "grad_norm": 5.380306243896484, "learning_rate": 4.380165147682414e-06, "loss": 0.17995554208755493, "step": 1076 }, { "epoch": 0.7963031423290203, "grad_norm": 4.189385414123535, "learning_rate": 4.3789271221090526e-06, "loss": 0.08834831416606903, "step": 1077 }, { "epoch": 0.7970425138632162, "grad_norm": 4.361270904541016, "learning_rate": 4.377688059316493e-06, "loss": 0.08982397615909576, "step": 1078 }, { "epoch": 0.7977818853974122, "grad_norm": 4.826642036437988, "learning_rate": 4.376447960093705e-06, "loss": 0.1408912092447281, "step": 1079 }, { "epoch": 0.7985212569316081, "grad_norm": 4.813187599182129, "learning_rate": 4.375206825230326e-06, "loss": 0.1289343386888504, "step": 1080 }, { "epoch": 0.799260628465804, "grad_norm": 3.77323055267334, "learning_rate": 4.373964655516644e-06, "loss": 0.1403437703847885, "step": 1081 }, { "epoch": 0.8, "grad_norm": 3.925605297088623, "learning_rate": 4.372721451743614e-06, "loss": 0.1362844705581665, "step": 1082 }, { "epoch": 0.8007393715341959, "grad_norm": 5.2319769859313965, "learning_rate": 4.3714772147028435e-06, "loss": 0.1369437575340271, "step": 1083 }, { "epoch": 0.8014787430683918, "grad_norm": 4.0832085609436035, "learning_rate": 4.370231945186601e-06, "loss": 0.1626933366060257, "step": 1084 }, { "epoch": 0.8022181146025879, "grad_norm": 4.958282947540283, "learning_rate": 4.368985643987813e-06, "loss": 0.12660440802574158, "step": 1085 }, { "epoch": 0.8029574861367837, "grad_norm": 3.015860080718994, "learning_rate": 4.36773831190006e-06, "loss": 0.0835014134645462, "step": 1086 }, { "epoch": 0.8036968576709796, "grad_norm": 3.699962615966797, "learning_rate": 4.366489949717582e-06, "loss": 0.10912549495697021, "step": 1087 }, { "epoch": 0.8044362292051755, "grad_norm": 3.466352701187134, "learning_rate": 4.365240558235273e-06, "loss": 0.1263538897037506, "step": 1088 }, { "epoch": 0.8051756007393716, "grad_norm": 3.4847095012664795, "learning_rate": 4.363990138248682e-06, "loss": 0.12289801239967346, "step": 1089 }, { "epoch": 0.8059149722735675, "grad_norm": 4.3868021965026855, "learning_rate": 4.362738690554014e-06, "loss": 0.15050289034843445, "step": 1090 }, { "epoch": 0.8066543438077634, "grad_norm": 3.830744981765747, "learning_rate": 4.361486215948129e-06, "loss": 0.15856748819351196, "step": 1091 }, { "epoch": 0.8073937153419594, "grad_norm": 3.2205562591552734, "learning_rate": 4.36023271522854e-06, "loss": 0.0985897034406662, "step": 1092 }, { "epoch": 0.8081330868761553, "grad_norm": 3.5952553749084473, "learning_rate": 4.358978189193414e-06, "loss": 0.10707056522369385, "step": 1093 }, { "epoch": 0.8088724584103512, "grad_norm": 4.056792736053467, "learning_rate": 4.357722638641568e-06, "loss": 0.15898500382900238, "step": 1094 }, { "epoch": 0.8096118299445472, "grad_norm": 4.795555114746094, "learning_rate": 4.356466064372477e-06, "loss": 0.09049156308174133, "step": 1095 }, { "epoch": 0.8103512014787431, "grad_norm": 4.664809703826904, "learning_rate": 4.355208467186262e-06, "loss": 0.11915402859449387, "step": 1096 }, { "epoch": 0.811090573012939, "grad_norm": 5.429905891418457, "learning_rate": 4.353949847883699e-06, "loss": 0.14194725453853607, "step": 1097 }, { "epoch": 0.811829944547135, "grad_norm": 3.267343521118164, "learning_rate": 4.352690207266214e-06, "loss": 0.09627373516559601, "step": 1098 }, { "epoch": 0.8125693160813309, "grad_norm": 3.2231621742248535, "learning_rate": 4.351429546135882e-06, "loss": 0.11011523753404617, "step": 1099 }, { "epoch": 0.8133086876155268, "grad_norm": 5.045790195465088, "learning_rate": 4.35016786529543e-06, "loss": 0.14922398328781128, "step": 1100 }, { "epoch": 0.8140480591497228, "grad_norm": 5.927290916442871, "learning_rate": 4.348905165548232e-06, "loss": 0.11651769280433655, "step": 1101 }, { "epoch": 0.8147874306839187, "grad_norm": 4.366883754730225, "learning_rate": 4.347641447698312e-06, "loss": 0.1010495126247406, "step": 1102 }, { "epoch": 0.8155268022181146, "grad_norm": 4.721738338470459, "learning_rate": 4.346376712550343e-06, "loss": 0.09401537477970123, "step": 1103 }, { "epoch": 0.8162661737523106, "grad_norm": 5.2394514083862305, "learning_rate": 4.345110960909646e-06, "loss": 0.12403249740600586, "step": 1104 }, { "epoch": 0.8170055452865065, "grad_norm": 5.364976406097412, "learning_rate": 4.343844193582186e-06, "loss": 0.147696852684021, "step": 1105 }, { "epoch": 0.8177449168207024, "grad_norm": 3.611374616622925, "learning_rate": 4.342576411374578e-06, "loss": 0.13404588401317596, "step": 1106 }, { "epoch": 0.8184842883548983, "grad_norm": 7.3889241218566895, "learning_rate": 4.341307615094083e-06, "loss": 0.1340368092060089, "step": 1107 }, { "epoch": 0.8192236598890943, "grad_norm": 4.742089748382568, "learning_rate": 4.340037805548604e-06, "loss": 0.11093439161777496, "step": 1108 }, { "epoch": 0.8199630314232902, "grad_norm": 4.571777820587158, "learning_rate": 4.338766983546696e-06, "loss": 0.07661059498786926, "step": 1109 }, { "epoch": 0.8207024029574861, "grad_norm": 3.9848506450653076, "learning_rate": 4.337495149897554e-06, "loss": 0.1231122836470604, "step": 1110 }, { "epoch": 0.8214417744916821, "grad_norm": 4.304333686828613, "learning_rate": 4.336222305411015e-06, "loss": 0.10031025856733322, "step": 1111 }, { "epoch": 0.822181146025878, "grad_norm": 4.002439975738525, "learning_rate": 4.334948450897566e-06, "loss": 0.1259452849626541, "step": 1112 }, { "epoch": 0.8229205175600739, "grad_norm": 6.081990718841553, "learning_rate": 4.333673587168331e-06, "loss": 0.11296384036540985, "step": 1113 }, { "epoch": 0.8236598890942699, "grad_norm": 3.0429458618164062, "learning_rate": 4.332397715035082e-06, "loss": 0.13570339977741241, "step": 1114 }, { "epoch": 0.8243992606284658, "grad_norm": 3.550652265548706, "learning_rate": 4.331120835310228e-06, "loss": 0.09068205207586288, "step": 1115 }, { "epoch": 0.8251386321626617, "grad_norm": 4.057523250579834, "learning_rate": 4.329842948806824e-06, "loss": 0.10631458461284637, "step": 1116 }, { "epoch": 0.8258780036968577, "grad_norm": 5.220094203948975, "learning_rate": 4.328564056338564e-06, "loss": 0.1011129766702652, "step": 1117 }, { "epoch": 0.8266173752310536, "grad_norm": 4.175957679748535, "learning_rate": 4.32728415871978e-06, "loss": 0.11098681390285492, "step": 1118 }, { "epoch": 0.8273567467652495, "grad_norm": 5.087501525878906, "learning_rate": 4.326003256765451e-06, "loss": 0.12823797762393951, "step": 1119 }, { "epoch": 0.8280961182994455, "grad_norm": 4.3205132484436035, "learning_rate": 4.3247213512911865e-06, "loss": 0.10650534182786942, "step": 1120 }, { "epoch": 0.8288354898336414, "grad_norm": 4.8850579261779785, "learning_rate": 4.323438443113244e-06, "loss": 0.05091463401913643, "step": 1121 }, { "epoch": 0.8295748613678373, "grad_norm": 4.639087200164795, "learning_rate": 4.322154533048513e-06, "loss": 0.11076568067073822, "step": 1122 }, { "epoch": 0.8303142329020333, "grad_norm": 4.183625221252441, "learning_rate": 4.320869621914523e-06, "loss": 0.1219034194946289, "step": 1123 }, { "epoch": 0.8310536044362292, "grad_norm": 4.170482635498047, "learning_rate": 4.319583710529441e-06, "loss": 0.09538013488054276, "step": 1124 }, { "epoch": 0.8317929759704251, "grad_norm": 3.433311700820923, "learning_rate": 4.318296799712072e-06, "loss": 0.1139390766620636, "step": 1125 }, { "epoch": 0.832532347504621, "grad_norm": 3.377533197402954, "learning_rate": 4.3170088902818555e-06, "loss": 0.11526491492986679, "step": 1126 }, { "epoch": 0.833271719038817, "grad_norm": 3.397477388381958, "learning_rate": 4.315719983058869e-06, "loss": 0.11460348963737488, "step": 1127 }, { "epoch": 0.8340110905730129, "grad_norm": 3.4270198345184326, "learning_rate": 4.314430078863822e-06, "loss": 0.12226006388664246, "step": 1128 }, { "epoch": 0.8347504621072088, "grad_norm": 4.024859428405762, "learning_rate": 4.313139178518061e-06, "loss": 0.05568765103816986, "step": 1129 }, { "epoch": 0.8354898336414048, "grad_norm": 3.441519021987915, "learning_rate": 4.311847282843569e-06, "loss": 0.08979318290948868, "step": 1130 }, { "epoch": 0.8362292051756007, "grad_norm": 3.4934847354888916, "learning_rate": 4.310554392662959e-06, "loss": 0.10136081278324127, "step": 1131 }, { "epoch": 0.8369685767097966, "grad_norm": 4.2913432121276855, "learning_rate": 4.309260508799478e-06, "loss": 0.055248796939849854, "step": 1132 }, { "epoch": 0.8377079482439926, "grad_norm": 3.63981556892395, "learning_rate": 4.307965632077008e-06, "loss": 0.09314166754484177, "step": 1133 }, { "epoch": 0.8384473197781885, "grad_norm": 4.0997772216796875, "learning_rate": 4.30666976332006e-06, "loss": 0.09392005205154419, "step": 1134 }, { "epoch": 0.8391866913123844, "grad_norm": 4.407551288604736, "learning_rate": 4.30537290335378e-06, "loss": 0.09989340603351593, "step": 1135 }, { "epoch": 0.8399260628465804, "grad_norm": 4.090407848358154, "learning_rate": 4.304075053003941e-06, "loss": 0.143600732088089, "step": 1136 }, { "epoch": 0.8406654343807763, "grad_norm": 3.140794038772583, "learning_rate": 4.302776213096953e-06, "loss": 0.15805703401565552, "step": 1137 }, { "epoch": 0.8414048059149722, "grad_norm": 5.294073104858398, "learning_rate": 4.301476384459849e-06, "loss": 0.12483671307563782, "step": 1138 }, { "epoch": 0.8421441774491683, "grad_norm": 4.682164669036865, "learning_rate": 4.300175567920295e-06, "loss": 0.07956940680742264, "step": 1139 }, { "epoch": 0.8428835489833642, "grad_norm": 2.713045835494995, "learning_rate": 4.2988737643065875e-06, "loss": 0.1524038016796112, "step": 1140 }, { "epoch": 0.84362292051756, "grad_norm": 3.2270216941833496, "learning_rate": 4.297570974447648e-06, "loss": 0.09864692389965057, "step": 1141 }, { "epoch": 0.8443622920517561, "grad_norm": 4.733347415924072, "learning_rate": 4.2962671991730285e-06, "loss": 0.1421889066696167, "step": 1142 }, { "epoch": 0.845101663585952, "grad_norm": 4.795095920562744, "learning_rate": 4.2949624393129086e-06, "loss": 0.10048935562372208, "step": 1143 }, { "epoch": 0.8458410351201479, "grad_norm": 3.202786684036255, "learning_rate": 4.293656695698093e-06, "loss": 0.12751218676567078, "step": 1144 }, { "epoch": 0.8465804066543438, "grad_norm": 5.87075138092041, "learning_rate": 4.292349969160014e-06, "loss": 0.10262735933065414, "step": 1145 }, { "epoch": 0.8473197781885398, "grad_norm": 5.9777727127075195, "learning_rate": 4.291042260530731e-06, "loss": 0.1136728972196579, "step": 1146 }, { "epoch": 0.8480591497227357, "grad_norm": 4.752411842346191, "learning_rate": 4.289733570642925e-06, "loss": 0.10690313577651978, "step": 1147 }, { "epoch": 0.8487985212569316, "grad_norm": 3.7315940856933594, "learning_rate": 4.288423900329905e-06, "loss": 0.11281999945640564, "step": 1148 }, { "epoch": 0.8495378927911276, "grad_norm": 4.414241790771484, "learning_rate": 4.287113250425604e-06, "loss": 0.14240163564682007, "step": 1149 }, { "epoch": 0.8502772643253235, "grad_norm": 5.773587703704834, "learning_rate": 4.285801621764578e-06, "loss": 0.1174812912940979, "step": 1150 }, { "epoch": 0.8510166358595194, "grad_norm": 3.8137402534484863, "learning_rate": 4.284489015182007e-06, "loss": 0.09907488524913788, "step": 1151 }, { "epoch": 0.8517560073937154, "grad_norm": 3.5066800117492676, "learning_rate": 4.283175431513693e-06, "loss": 0.1483834683895111, "step": 1152 }, { "epoch": 0.8524953789279113, "grad_norm": 4.522121906280518, "learning_rate": 4.2818608715960584e-06, "loss": 0.12369982898235321, "step": 1153 }, { "epoch": 0.8532347504621072, "grad_norm": 3.1111514568328857, "learning_rate": 4.280545336266151e-06, "loss": 0.13387322425842285, "step": 1154 }, { "epoch": 0.8539741219963032, "grad_norm": 3.450465679168701, "learning_rate": 4.279228826361638e-06, "loss": 0.12323737144470215, "step": 1155 }, { "epoch": 0.8547134935304991, "grad_norm": 4.110988616943359, "learning_rate": 4.2779113427208056e-06, "loss": 0.1234850287437439, "step": 1156 }, { "epoch": 0.855452865064695, "grad_norm": 3.1531054973602295, "learning_rate": 4.276592886182562e-06, "loss": 0.11744730174541473, "step": 1157 }, { "epoch": 0.856192236598891, "grad_norm": 3.7445943355560303, "learning_rate": 4.275273457586435e-06, "loss": 0.10212409496307373, "step": 1158 }, { "epoch": 0.8569316081330869, "grad_norm": 4.671864986419678, "learning_rate": 4.273953057772569e-06, "loss": 0.06579458713531494, "step": 1159 }, { "epoch": 0.8576709796672828, "grad_norm": 3.028651714324951, "learning_rate": 4.272631687581731e-06, "loss": 0.12674367427825928, "step": 1160 }, { "epoch": 0.8584103512014788, "grad_norm": 3.4275496006011963, "learning_rate": 4.2713093478553e-06, "loss": 0.10183057188987732, "step": 1161 }, { "epoch": 0.8591497227356747, "grad_norm": 4.318497180938721, "learning_rate": 4.269986039435279e-06, "loss": 0.0989375188946724, "step": 1162 }, { "epoch": 0.8598890942698706, "grad_norm": 4.464252948760986, "learning_rate": 4.268661763164283e-06, "loss": 0.10240474343299866, "step": 1163 }, { "epoch": 0.8606284658040665, "grad_norm": 3.873328685760498, "learning_rate": 4.267336519885544e-06, "loss": 0.06877413392066956, "step": 1164 }, { "epoch": 0.8613678373382625, "grad_norm": 4.128834247589111, "learning_rate": 4.266010310442912e-06, "loss": 0.11454368382692337, "step": 1165 }, { "epoch": 0.8621072088724584, "grad_norm": 4.657775402069092, "learning_rate": 4.26468313568085e-06, "loss": 0.13100416958332062, "step": 1166 }, { "epoch": 0.8628465804066543, "grad_norm": 4.0468525886535645, "learning_rate": 4.263354996444436e-06, "loss": 0.11461474746465683, "step": 1167 }, { "epoch": 0.8635859519408503, "grad_norm": 3.5055675506591797, "learning_rate": 4.262025893579364e-06, "loss": 0.10288431495428085, "step": 1168 }, { "epoch": 0.8643253234750462, "grad_norm": 3.3785266876220703, "learning_rate": 4.260695827931939e-06, "loss": 0.07772387564182281, "step": 1169 }, { "epoch": 0.8650646950092421, "grad_norm": 5.094358921051025, "learning_rate": 4.25936480034908e-06, "loss": 0.08118944615125656, "step": 1170 }, { "epoch": 0.8658040665434381, "grad_norm": 4.603518962860107, "learning_rate": 4.258032811678318e-06, "loss": 0.11738453060388565, "step": 1171 }, { "epoch": 0.866543438077634, "grad_norm": 3.2271652221679688, "learning_rate": 4.256699862767799e-06, "loss": 0.1261729598045349, "step": 1172 }, { "epoch": 0.8672828096118299, "grad_norm": 2.517132043838501, "learning_rate": 4.255365954466277e-06, "loss": 0.14873254299163818, "step": 1173 }, { "epoch": 0.8680221811460259, "grad_norm": 3.3770012855529785, "learning_rate": 4.254031087623118e-06, "loss": 0.1408088356256485, "step": 1174 }, { "epoch": 0.8687615526802218, "grad_norm": 3.4629411697387695, "learning_rate": 4.2526952630882975e-06, "loss": 0.109095498919487, "step": 1175 }, { "epoch": 0.8695009242144177, "grad_norm": 4.285280227661133, "learning_rate": 4.251358481712403e-06, "loss": 0.1256469041109085, "step": 1176 }, { "epoch": 0.8702402957486137, "grad_norm": 3.6253135204315186, "learning_rate": 4.2500207443466294e-06, "loss": 0.1172708198428154, "step": 1177 }, { "epoch": 0.8709796672828096, "grad_norm": 2.884662389755249, "learning_rate": 4.24868205184278e-06, "loss": 0.13808462023735046, "step": 1178 }, { "epoch": 0.8717190388170055, "grad_norm": 4.277608394622803, "learning_rate": 4.247342405053268e-06, "loss": 0.11289553344249725, "step": 1179 }, { "epoch": 0.8724584103512015, "grad_norm": 4.568155765533447, "learning_rate": 4.246001804831114e-06, "loss": 0.11420642584562302, "step": 1180 }, { "epoch": 0.8731977818853974, "grad_norm": 3.131044626235962, "learning_rate": 4.244660252029943e-06, "loss": 0.13885129988193512, "step": 1181 }, { "epoch": 0.8739371534195933, "grad_norm": 3.653550386428833, "learning_rate": 4.24331774750399e-06, "loss": 0.13048779964447021, "step": 1182 }, { "epoch": 0.8746765249537892, "grad_norm": 5.042903900146484, "learning_rate": 4.2419742921080955e-06, "loss": 0.10125723481178284, "step": 1183 }, { "epoch": 0.8754158964879852, "grad_norm": 3.2546491622924805, "learning_rate": 4.240629886697703e-06, "loss": 0.12209078669548035, "step": 1184 }, { "epoch": 0.8761552680221811, "grad_norm": 3.691352605819702, "learning_rate": 4.239284532128864e-06, "loss": 0.09987484663724899, "step": 1185 }, { "epoch": 0.876894639556377, "grad_norm": 4.601605415344238, "learning_rate": 4.237938229258231e-06, "loss": 0.06197035312652588, "step": 1186 }, { "epoch": 0.877634011090573, "grad_norm": 3.138929605484009, "learning_rate": 4.236590978943064e-06, "loss": 0.07892890274524689, "step": 1187 }, { "epoch": 0.8783733826247689, "grad_norm": 5.2468366622924805, "learning_rate": 4.2352427820412235e-06, "loss": 0.136566162109375, "step": 1188 }, { "epoch": 0.8791127541589648, "grad_norm": 5.104057312011719, "learning_rate": 4.233893639411174e-06, "loss": 0.05382546782493591, "step": 1189 }, { "epoch": 0.8798521256931608, "grad_norm": 3.6312601566314697, "learning_rate": 4.232543551911983e-06, "loss": 0.10541169345378876, "step": 1190 }, { "epoch": 0.8805914972273567, "grad_norm": 4.509280204772949, "learning_rate": 4.231192520403317e-06, "loss": 0.11507546901702881, "step": 1191 }, { "epoch": 0.8813308687615526, "grad_norm": 3.625985860824585, "learning_rate": 4.2298405457454455e-06, "loss": 0.1259494125843048, "step": 1192 }, { "epoch": 0.8820702402957487, "grad_norm": 3.4276950359344482, "learning_rate": 4.228487628799239e-06, "loss": 0.0951765924692154, "step": 1193 }, { "epoch": 0.8828096118299446, "grad_norm": 4.718158721923828, "learning_rate": 4.227133770426166e-06, "loss": 0.09472831338644028, "step": 1194 }, { "epoch": 0.8835489833641405, "grad_norm": 4.31313419342041, "learning_rate": 4.225778971488297e-06, "loss": 0.10616838186979294, "step": 1195 }, { "epoch": 0.8842883548983365, "grad_norm": 4.259148597717285, "learning_rate": 4.2244232328483e-06, "loss": 0.09777378290891647, "step": 1196 }, { "epoch": 0.8850277264325324, "grad_norm": 3.522304058074951, "learning_rate": 4.223066555369442e-06, "loss": 0.09520726650953293, "step": 1197 }, { "epoch": 0.8857670979667283, "grad_norm": 4.522335529327393, "learning_rate": 4.221708939915585e-06, "loss": 0.11107456684112549, "step": 1198 }, { "epoch": 0.8865064695009243, "grad_norm": 5.611830711364746, "learning_rate": 4.220350387351192e-06, "loss": 0.12145137786865234, "step": 1199 }, { "epoch": 0.8872458410351202, "grad_norm": 5.135848522186279, "learning_rate": 4.2189908985413205e-06, "loss": 0.15155455470085144, "step": 1200 }, { "epoch": 0.8879852125693161, "grad_norm": 3.507323741912842, "learning_rate": 4.217630474351626e-06, "loss": 0.10698793828487396, "step": 1201 }, { "epoch": 0.888724584103512, "grad_norm": 3.8518481254577637, "learning_rate": 4.2162691156483585e-06, "loss": 0.10755527019500732, "step": 1202 }, { "epoch": 0.889463955637708, "grad_norm": 4.757392406463623, "learning_rate": 4.214906823298362e-06, "loss": 0.08136763423681259, "step": 1203 }, { "epoch": 0.8902033271719039, "grad_norm": 4.827852249145508, "learning_rate": 4.213543598169077e-06, "loss": 0.11479585617780685, "step": 1204 }, { "epoch": 0.8909426987060998, "grad_norm": 6.22097110748291, "learning_rate": 4.212179441128536e-06, "loss": 0.1310763955116272, "step": 1205 }, { "epoch": 0.8916820702402958, "grad_norm": 4.574062824249268, "learning_rate": 4.210814353045366e-06, "loss": 0.1207951232790947, "step": 1206 }, { "epoch": 0.8924214417744917, "grad_norm": 4.922646522521973, "learning_rate": 4.209448334788787e-06, "loss": 0.09180278331041336, "step": 1207 }, { "epoch": 0.8931608133086876, "grad_norm": 5.306274890899658, "learning_rate": 4.2080813872286116e-06, "loss": 0.11574852466583252, "step": 1208 }, { "epoch": 0.8939001848428836, "grad_norm": 5.073375225067139, "learning_rate": 4.206713511235243e-06, "loss": 0.08840446919202805, "step": 1209 }, { "epoch": 0.8946395563770795, "grad_norm": 4.491574287414551, "learning_rate": 4.205344707679676e-06, "loss": 0.11611642688512802, "step": 1210 }, { "epoch": 0.8953789279112754, "grad_norm": 6.172915935516357, "learning_rate": 4.203974977433497e-06, "loss": 0.11296108365058899, "step": 1211 }, { "epoch": 0.8961182994454714, "grad_norm": 4.59376859664917, "learning_rate": 4.2026043213688796e-06, "loss": 0.12445296347141266, "step": 1212 }, { "epoch": 0.8968576709796673, "grad_norm": 4.161900997161865, "learning_rate": 4.201232740358591e-06, "loss": 0.10526718199253082, "step": 1213 }, { "epoch": 0.8975970425138632, "grad_norm": 4.273694038391113, "learning_rate": 4.199860235275985e-06, "loss": 0.10048109292984009, "step": 1214 }, { "epoch": 0.8983364140480592, "grad_norm": 3.3003787994384766, "learning_rate": 4.198486806995003e-06, "loss": 0.12065263092517853, "step": 1215 }, { "epoch": 0.8990757855822551, "grad_norm": 5.827729225158691, "learning_rate": 4.197112456390176e-06, "loss": 0.11512844264507294, "step": 1216 }, { "epoch": 0.899815157116451, "grad_norm": 4.764509677886963, "learning_rate": 4.195737184336621e-06, "loss": 0.0967230349779129, "step": 1217 }, { "epoch": 0.900554528650647, "grad_norm": 3.8554062843322754, "learning_rate": 4.194360991710043e-06, "loss": 0.12172935903072357, "step": 1218 }, { "epoch": 0.9012939001848429, "grad_norm": 4.7679667472839355, "learning_rate": 4.192983879386733e-06, "loss": 0.07612208276987076, "step": 1219 }, { "epoch": 0.9020332717190388, "grad_norm": 4.284624099731445, "learning_rate": 4.191605848243567e-06, "loss": 0.09311556816101074, "step": 1220 }, { "epoch": 0.9027726432532347, "grad_norm": 3.891477346420288, "learning_rate": 4.190226899158005e-06, "loss": 0.10882353037595749, "step": 1221 }, { "epoch": 0.9035120147874307, "grad_norm": 4.645151615142822, "learning_rate": 4.188847033008093e-06, "loss": 0.0890505313873291, "step": 1222 }, { "epoch": 0.9042513863216266, "grad_norm": 4.650264263153076, "learning_rate": 4.187466250672462e-06, "loss": 0.08286353945732117, "step": 1223 }, { "epoch": 0.9049907578558225, "grad_norm": 3.6191720962524414, "learning_rate": 4.186084553030324e-06, "loss": 0.09563601762056351, "step": 1224 }, { "epoch": 0.9057301293900185, "grad_norm": 4.540883541107178, "learning_rate": 4.1847019409614745e-06, "loss": 0.10246805846691132, "step": 1225 }, { "epoch": 0.9064695009242144, "grad_norm": 5.049047470092773, "learning_rate": 4.183318415346293e-06, "loss": 0.09047120809555054, "step": 1226 }, { "epoch": 0.9072088724584103, "grad_norm": 4.775219917297363, "learning_rate": 4.181933977065739e-06, "loss": 0.14578622579574585, "step": 1227 }, { "epoch": 0.9079482439926063, "grad_norm": 4.364152908325195, "learning_rate": 4.1805486270013505e-06, "loss": 0.10839129239320755, "step": 1228 }, { "epoch": 0.9086876155268022, "grad_norm": 5.023606777191162, "learning_rate": 4.179162366035253e-06, "loss": 0.14155837893486023, "step": 1229 }, { "epoch": 0.9094269870609981, "grad_norm": 4.269718647003174, "learning_rate": 4.177775195050147e-06, "loss": 0.10429368913173676, "step": 1230 }, { "epoch": 0.9101663585951941, "grad_norm": 3.308919668197632, "learning_rate": 4.176387114929312e-06, "loss": 0.13513942062854767, "step": 1231 }, { "epoch": 0.91090573012939, "grad_norm": 3.8883273601531982, "learning_rate": 4.17499812655661e-06, "loss": 0.07203197479248047, "step": 1232 }, { "epoch": 0.9116451016635859, "grad_norm": 4.152498245239258, "learning_rate": 4.173608230816477e-06, "loss": 0.11868232488632202, "step": 1233 }, { "epoch": 0.9123844731977819, "grad_norm": 4.16183614730835, "learning_rate": 4.172217428593931e-06, "loss": 0.10275726020336151, "step": 1234 }, { "epoch": 0.9131238447319778, "grad_norm": 3.0722570419311523, "learning_rate": 4.1708257207745626e-06, "loss": 0.07490702718496323, "step": 1235 }, { "epoch": 0.9138632162661737, "grad_norm": 4.776163578033447, "learning_rate": 4.169433108244544e-06, "loss": 0.09838491678237915, "step": 1236 }, { "epoch": 0.9146025878003697, "grad_norm": 3.5118207931518555, "learning_rate": 4.168039591890621e-06, "loss": 0.09625010937452316, "step": 1237 }, { "epoch": 0.9153419593345656, "grad_norm": 3.626150131225586, "learning_rate": 4.166645172600114e-06, "loss": 0.08407920598983765, "step": 1238 }, { "epoch": 0.9160813308687615, "grad_norm": 3.469034194946289, "learning_rate": 4.165249851260921e-06, "loss": 0.09896586090326309, "step": 1239 }, { "epoch": 0.9168207024029574, "grad_norm": 3.402148485183716, "learning_rate": 4.1638536287615106e-06, "loss": 0.12628710269927979, "step": 1240 }, { "epoch": 0.9175600739371534, "grad_norm": 4.945196628570557, "learning_rate": 4.162456505990927e-06, "loss": 0.07911120355129242, "step": 1241 }, { "epoch": 0.9182994454713493, "grad_norm": 4.36090087890625, "learning_rate": 4.1610584838387914e-06, "loss": 0.06231238320469856, "step": 1242 }, { "epoch": 0.9190388170055452, "grad_norm": 4.123326301574707, "learning_rate": 4.159659563195291e-06, "loss": 0.08200837671756744, "step": 1243 }, { "epoch": 0.9197781885397412, "grad_norm": 5.509344100952148, "learning_rate": 4.15825974495119e-06, "loss": 0.10661721229553223, "step": 1244 }, { "epoch": 0.9205175600739371, "grad_norm": 4.544158935546875, "learning_rate": 4.156859029997822e-06, "loss": 0.07194264978170395, "step": 1245 }, { "epoch": 0.921256931608133, "grad_norm": 4.8869733810424805, "learning_rate": 4.155457419227092e-06, "loss": 0.08625375479459763, "step": 1246 }, { "epoch": 0.921996303142329, "grad_norm": 3.1364047527313232, "learning_rate": 4.154054913531477e-06, "loss": 0.09823141992092133, "step": 1247 }, { "epoch": 0.922735674676525, "grad_norm": 5.323268413543701, "learning_rate": 4.152651513804019e-06, "loss": 0.08519968390464783, "step": 1248 }, { "epoch": 0.9234750462107209, "grad_norm": 4.293143272399902, "learning_rate": 4.151247220938336e-06, "loss": 0.10828883200883865, "step": 1249 }, { "epoch": 0.9242144177449169, "grad_norm": 3.203274965286255, "learning_rate": 4.14984203582861e-06, "loss": 0.12068073451519012, "step": 1250 }, { "epoch": 0.9249537892791128, "grad_norm": 4.086752891540527, "learning_rate": 4.1484359593695915e-06, "loss": 0.09746316075325012, "step": 1251 }, { "epoch": 0.9256931608133087, "grad_norm": 3.6207518577575684, "learning_rate": 4.147028992456602e-06, "loss": 0.09430903196334839, "step": 1252 }, { "epoch": 0.9264325323475047, "grad_norm": 3.473966598510742, "learning_rate": 4.145621135985526e-06, "loss": 0.09553971886634827, "step": 1253 }, { "epoch": 0.9271719038817006, "grad_norm": 4.9774065017700195, "learning_rate": 4.144212390852816e-06, "loss": 0.07701139152050018, "step": 1254 }, { "epoch": 0.9279112754158965, "grad_norm": 4.072710037231445, "learning_rate": 4.142802757955491e-06, "loss": 0.11291126906871796, "step": 1255 }, { "epoch": 0.9286506469500925, "grad_norm": 4.668191909790039, "learning_rate": 4.141392238191134e-06, "loss": 0.10610712319612503, "step": 1256 }, { "epoch": 0.9293900184842884, "grad_norm": 4.041755199432373, "learning_rate": 4.139980832457893e-06, "loss": 0.08400414139032364, "step": 1257 }, { "epoch": 0.9301293900184843, "grad_norm": 3.6267757415771484, "learning_rate": 4.138568541654481e-06, "loss": 0.10473158955574036, "step": 1258 }, { "epoch": 0.9308687615526802, "grad_norm": 4.071776866912842, "learning_rate": 4.137155366680176e-06, "loss": 0.10587053000926971, "step": 1259 }, { "epoch": 0.9316081330868762, "grad_norm": 4.303316593170166, "learning_rate": 4.135741308434812e-06, "loss": 0.07450859248638153, "step": 1260 }, { "epoch": 0.9323475046210721, "grad_norm": 4.715449333190918, "learning_rate": 4.134326367818795e-06, "loss": 0.11014540493488312, "step": 1261 }, { "epoch": 0.933086876155268, "grad_norm": 3.6790318489074707, "learning_rate": 4.132910545733087e-06, "loss": 0.06833720207214355, "step": 1262 }, { "epoch": 0.933826247689464, "grad_norm": 3.779191493988037, "learning_rate": 4.131493843079213e-06, "loss": 0.13604629039764404, "step": 1263 }, { "epoch": 0.9345656192236599, "grad_norm": 5.21082878112793, "learning_rate": 4.130076260759256e-06, "loss": 0.08535236865282059, "step": 1264 }, { "epoch": 0.9353049907578558, "grad_norm": 4.282204627990723, "learning_rate": 4.128657799675864e-06, "loss": 0.09649982303380966, "step": 1265 }, { "epoch": 0.9360443622920518, "grad_norm": 4.575429439544678, "learning_rate": 4.127238460732242e-06, "loss": 0.07200303673744202, "step": 1266 }, { "epoch": 0.9367837338262477, "grad_norm": 5.194964408874512, "learning_rate": 4.1258182448321515e-06, "loss": 0.09556837379932404, "step": 1267 }, { "epoch": 0.9375231053604436, "grad_norm": 6.3188652992248535, "learning_rate": 4.124397152879918e-06, "loss": 0.1024852842092514, "step": 1268 }, { "epoch": 0.9382624768946396, "grad_norm": 3.4918107986450195, "learning_rate": 4.122975185780419e-06, "loss": 0.10205800086259842, "step": 1269 }, { "epoch": 0.9390018484288355, "grad_norm": 5.327855587005615, "learning_rate": 4.121552344439093e-06, "loss": 0.04604736343026161, "step": 1270 }, { "epoch": 0.9397412199630314, "grad_norm": 5.488301753997803, "learning_rate": 4.120128629761935e-06, "loss": 0.0632362961769104, "step": 1271 }, { "epoch": 0.9404805914972274, "grad_norm": 3.7058446407318115, "learning_rate": 4.118704042655493e-06, "loss": 0.11410466581583023, "step": 1272 }, { "epoch": 0.9412199630314233, "grad_norm": 4.797382354736328, "learning_rate": 4.1172785840268744e-06, "loss": 0.06260962039232254, "step": 1273 }, { "epoch": 0.9419593345656192, "grad_norm": 6.006154537200928, "learning_rate": 4.115852254783741e-06, "loss": 0.09344232082366943, "step": 1274 }, { "epoch": 0.9426987060998152, "grad_norm": 4.887182235717773, "learning_rate": 4.114425055834304e-06, "loss": 0.065268874168396, "step": 1275 }, { "epoch": 0.9434380776340111, "grad_norm": 5.227149963378906, "learning_rate": 4.112996988087336e-06, "loss": 0.11767076700925827, "step": 1276 }, { "epoch": 0.944177449168207, "grad_norm": 4.8395094871521, "learning_rate": 4.111568052452156e-06, "loss": 0.08265776932239532, "step": 1277 }, { "epoch": 0.9449168207024029, "grad_norm": 4.8410749435424805, "learning_rate": 4.1101382498386405e-06, "loss": 0.10517295449972153, "step": 1278 }, { "epoch": 0.9456561922365989, "grad_norm": 4.370154857635498, "learning_rate": 4.1087075811572165e-06, "loss": 0.09528413414955139, "step": 1279 }, { "epoch": 0.9463955637707948, "grad_norm": 3.492783784866333, "learning_rate": 4.107276047318861e-06, "loss": 0.10392051935195923, "step": 1280 }, { "epoch": 0.9471349353049907, "grad_norm": 4.356719017028809, "learning_rate": 4.105843649235104e-06, "loss": 0.0777992457151413, "step": 1281 }, { "epoch": 0.9478743068391867, "grad_norm": 5.045681953430176, "learning_rate": 4.104410387818024e-06, "loss": 0.08246183395385742, "step": 1282 }, { "epoch": 0.9486136783733826, "grad_norm": 5.71662712097168, "learning_rate": 4.10297626398025e-06, "loss": 0.08751735091209412, "step": 1283 }, { "epoch": 0.9493530499075785, "grad_norm": 3.3451008796691895, "learning_rate": 4.101541278634962e-06, "loss": 0.10268744826316833, "step": 1284 }, { "epoch": 0.9500924214417745, "grad_norm": 4.011295795440674, "learning_rate": 4.100105432695884e-06, "loss": 0.1315554678440094, "step": 1285 }, { "epoch": 0.9508317929759704, "grad_norm": 4.596782207489014, "learning_rate": 4.0986687270772934e-06, "loss": 0.08879611641168594, "step": 1286 }, { "epoch": 0.9515711645101663, "grad_norm": 4.0701470375061035, "learning_rate": 4.09723116269401e-06, "loss": 0.06543806940317154, "step": 1287 }, { "epoch": 0.9523105360443623, "grad_norm": 3.4468512535095215, "learning_rate": 4.095792740461405e-06, "loss": 0.08646194636821747, "step": 1288 }, { "epoch": 0.9530499075785582, "grad_norm": 4.512137413024902, "learning_rate": 4.094353461295393e-06, "loss": 0.0580766424536705, "step": 1289 }, { "epoch": 0.9537892791127541, "grad_norm": 4.347107887268066, "learning_rate": 4.092913326112434e-06, "loss": 0.07942931354045868, "step": 1290 }, { "epoch": 0.9545286506469501, "grad_norm": 5.879266262054443, "learning_rate": 4.091472335829534e-06, "loss": 0.0786149725317955, "step": 1291 }, { "epoch": 0.955268022181146, "grad_norm": 4.667703151702881, "learning_rate": 4.090030491364244e-06, "loss": 0.07337147742509842, "step": 1292 }, { "epoch": 0.9560073937153419, "grad_norm": 4.880917549133301, "learning_rate": 4.088587793634658e-06, "loss": 0.06828370690345764, "step": 1293 }, { "epoch": 0.956746765249538, "grad_norm": 5.172056674957275, "learning_rate": 4.087144243559414e-06, "loss": 0.06143511086702347, "step": 1294 }, { "epoch": 0.9574861367837338, "grad_norm": 4.973568439483643, "learning_rate": 4.085699842057693e-06, "loss": 0.12137329578399658, "step": 1295 }, { "epoch": 0.9582255083179297, "grad_norm": 4.830620765686035, "learning_rate": 4.084254590049216e-06, "loss": 0.04479135572910309, "step": 1296 }, { "epoch": 0.9589648798521256, "grad_norm": 6.375425338745117, "learning_rate": 4.082808488454248e-06, "loss": 0.07957334816455841, "step": 1297 }, { "epoch": 0.9597042513863216, "grad_norm": 4.395008087158203, "learning_rate": 4.081361538193595e-06, "loss": 0.13761422038078308, "step": 1298 }, { "epoch": 0.9604436229205175, "grad_norm": 3.8686347007751465, "learning_rate": 4.0799137401885995e-06, "loss": 0.06390014290809631, "step": 1299 }, { "epoch": 0.9611829944547134, "grad_norm": 3.746307611465454, "learning_rate": 4.07846509536115e-06, "loss": 0.08418642729520798, "step": 1300 }, { "epoch": 0.9619223659889095, "grad_norm": 3.3596956729888916, "learning_rate": 4.077015604633669e-06, "loss": 0.03335687518119812, "step": 1301 }, { "epoch": 0.9626617375231054, "grad_norm": 4.220990180969238, "learning_rate": 4.07556526892912e-06, "loss": 0.09509570896625519, "step": 1302 }, { "epoch": 0.9634011090573013, "grad_norm": 4.228139877319336, "learning_rate": 4.074114089171006e-06, "loss": 0.12093635648488998, "step": 1303 }, { "epoch": 0.9641404805914973, "grad_norm": 3.9738502502441406, "learning_rate": 4.0726620662833616e-06, "loss": 0.1030249148607254, "step": 1304 }, { "epoch": 0.9648798521256932, "grad_norm": 3.7936480045318604, "learning_rate": 4.071209201190766e-06, "loss": 0.09457199275493622, "step": 1305 }, { "epoch": 0.9656192236598891, "grad_norm": 7.6213178634643555, "learning_rate": 4.069755494818329e-06, "loss": 0.10822607576847076, "step": 1306 }, { "epoch": 0.9663585951940851, "grad_norm": 3.731292486190796, "learning_rate": 4.068300948091698e-06, "loss": 0.13445788621902466, "step": 1307 }, { "epoch": 0.967097966728281, "grad_norm": 4.565194129943848, "learning_rate": 4.066845561937057e-06, "loss": 0.044161491096019745, "step": 1308 }, { "epoch": 0.9678373382624769, "grad_norm": 3.6431515216827393, "learning_rate": 4.065389337281121e-06, "loss": 0.12753576040267944, "step": 1309 }, { "epoch": 0.9685767097966729, "grad_norm": 5.884459972381592, "learning_rate": 4.063932275051143e-06, "loss": 0.07471480965614319, "step": 1310 }, { "epoch": 0.9693160813308688, "grad_norm": 4.4653544425964355, "learning_rate": 4.0624743761749045e-06, "loss": 0.09699045121669769, "step": 1311 }, { "epoch": 0.9700554528650647, "grad_norm": 3.9848930835723877, "learning_rate": 4.061015641580726e-06, "loss": 0.09959234297275543, "step": 1312 }, { "epoch": 0.9707948243992607, "grad_norm": 3.6540212631225586, "learning_rate": 4.059556072197453e-06, "loss": 0.08766701817512512, "step": 1313 }, { "epoch": 0.9715341959334566, "grad_norm": 4.040307998657227, "learning_rate": 4.058095668954468e-06, "loss": 0.13566088676452637, "step": 1314 }, { "epoch": 0.9722735674676525, "grad_norm": 4.373073101043701, "learning_rate": 4.056634432781683e-06, "loss": 0.0876464992761612, "step": 1315 }, { "epoch": 0.9730129390018484, "grad_norm": 3.8923001289367676, "learning_rate": 4.05517236460954e-06, "loss": 0.13118982315063477, "step": 1316 }, { "epoch": 0.9737523105360444, "grad_norm": 3.9692318439483643, "learning_rate": 4.0537094653690105e-06, "loss": 0.10863399505615234, "step": 1317 }, { "epoch": 0.9744916820702403, "grad_norm": 5.029035568237305, "learning_rate": 4.052245735991595e-06, "loss": 0.08711151778697968, "step": 1318 }, { "epoch": 0.9752310536044362, "grad_norm": 3.9442999362945557, "learning_rate": 4.050781177409323e-06, "loss": 0.0701448917388916, "step": 1319 }, { "epoch": 0.9759704251386322, "grad_norm": 3.7249343395233154, "learning_rate": 4.049315790554752e-06, "loss": 0.09325215220451355, "step": 1320 }, { "epoch": 0.9767097966728281, "grad_norm": 3.3376567363739014, "learning_rate": 4.047849576360968e-06, "loss": 0.08947093784809113, "step": 1321 }, { "epoch": 0.977449168207024, "grad_norm": 4.218324184417725, "learning_rate": 4.0463825357615815e-06, "loss": 0.1028720885515213, "step": 1322 }, { "epoch": 0.97818853974122, "grad_norm": 5.664226055145264, "learning_rate": 4.044914669690732e-06, "loss": 0.07790728658437729, "step": 1323 }, { "epoch": 0.9789279112754159, "grad_norm": 4.216891288757324, "learning_rate": 4.043445979083081e-06, "loss": 0.08726905286312103, "step": 1324 }, { "epoch": 0.9796672828096118, "grad_norm": 4.220721244812012, "learning_rate": 4.041976464873819e-06, "loss": 0.06695814430713654, "step": 1325 }, { "epoch": 0.9804066543438078, "grad_norm": 5.439157485961914, "learning_rate": 4.040506127998658e-06, "loss": 0.08059584349393845, "step": 1326 }, { "epoch": 0.9811460258780037, "grad_norm": 3.786301851272583, "learning_rate": 4.039034969393836e-06, "loss": 0.0861954391002655, "step": 1327 }, { "epoch": 0.9818853974121996, "grad_norm": 5.715299606323242, "learning_rate": 4.037562989996112e-06, "loss": 0.13647568225860596, "step": 1328 }, { "epoch": 0.9826247689463956, "grad_norm": 4.03038215637207, "learning_rate": 4.036090190742768e-06, "loss": 0.10691842436790466, "step": 1329 }, { "epoch": 0.9833641404805915, "grad_norm": 3.2221875190734863, "learning_rate": 4.034616572571611e-06, "loss": 0.06676600873470306, "step": 1330 }, { "epoch": 0.9841035120147874, "grad_norm": 4.375216007232666, "learning_rate": 4.033142136420965e-06, "loss": 0.11836910247802734, "step": 1331 }, { "epoch": 0.9848428835489834, "grad_norm": 4.405242443084717, "learning_rate": 4.031666883229678e-06, "loss": 0.07826778292655945, "step": 1332 }, { "epoch": 0.9855822550831793, "grad_norm": 4.8143534660339355, "learning_rate": 4.0301908139371196e-06, "loss": 0.10140824317932129, "step": 1333 }, { "epoch": 0.9863216266173752, "grad_norm": 2.795078754425049, "learning_rate": 4.028713929483173e-06, "loss": 0.0805973932147026, "step": 1334 }, { "epoch": 0.9870609981515711, "grad_norm": 4.251298904418945, "learning_rate": 4.027236230808246e-06, "loss": 0.08804316818714142, "step": 1335 }, { "epoch": 0.9878003696857671, "grad_norm": 3.9247071743011475, "learning_rate": 4.0257577188532635e-06, "loss": 0.07347789406776428, "step": 1336 }, { "epoch": 0.988539741219963, "grad_norm": 3.698575258255005, "learning_rate": 4.024278394559667e-06, "loss": 0.1090582013130188, "step": 1337 }, { "epoch": 0.9892791127541589, "grad_norm": 4.064996242523193, "learning_rate": 4.022798258869417e-06, "loss": 0.09269186109304428, "step": 1338 }, { "epoch": 0.9900184842883549, "grad_norm": 4.68333101272583, "learning_rate": 4.021317312724989e-06, "loss": 0.09658917784690857, "step": 1339 }, { "epoch": 0.9907578558225508, "grad_norm": 5.275736331939697, "learning_rate": 4.019835557069375e-06, "loss": 0.04948625713586807, "step": 1340 }, { "epoch": 0.9914972273567467, "grad_norm": 4.875097274780273, "learning_rate": 4.018352992846084e-06, "loss": 0.10814017057418823, "step": 1341 }, { "epoch": 0.9922365988909427, "grad_norm": 4.828421115875244, "learning_rate": 4.016869620999138e-06, "loss": 0.10405051708221436, "step": 1342 }, { "epoch": 0.9929759704251386, "grad_norm": 5.1702423095703125, "learning_rate": 4.015385442473073e-06, "loss": 0.1032736748456955, "step": 1343 }, { "epoch": 0.9937153419593345, "grad_norm": 3.815901041030884, "learning_rate": 4.013900458212941e-06, "loss": 0.09491760283708572, "step": 1344 }, { "epoch": 0.9944547134935305, "grad_norm": 3.8174691200256348, "learning_rate": 4.012414669164305e-06, "loss": 0.08529795706272125, "step": 1345 }, { "epoch": 0.9951940850277264, "grad_norm": 4.892879486083984, "learning_rate": 4.0109280762732424e-06, "loss": 0.08335202187299728, "step": 1346 }, { "epoch": 0.9959334565619223, "grad_norm": 3.640155792236328, "learning_rate": 4.009440680486339e-06, "loss": 0.11789075285196304, "step": 1347 }, { "epoch": 0.9966728280961183, "grad_norm": 4.183467388153076, "learning_rate": 4.007952482750693e-06, "loss": 0.08038797974586487, "step": 1348 }, { "epoch": 0.9974121996303142, "grad_norm": 4.174394130706787, "learning_rate": 4.006463484013918e-06, "loss": 0.06798119843006134, "step": 1349 }, { "epoch": 0.9981515711645101, "grad_norm": 4.779728889465332, "learning_rate": 4.004973685224131e-06, "loss": 0.07222880423069, "step": 1350 }, { "epoch": 0.9988909426987062, "grad_norm": 5.675201416015625, "learning_rate": 4.003483087329962e-06, "loss": 0.06448063999414444, "step": 1351 }, { "epoch": 0.999630314232902, "grad_norm": 4.250618934631348, "learning_rate": 4.001991691280549e-06, "loss": 0.08716219663619995, "step": 1352 }, { "epoch": 1.0, "grad_norm": 6.10059928894043, "learning_rate": 4.000499498025538e-06, "loss": 0.08914235234260559, "step": 1353 } ], "logging_steps": 1, "max_steps": 4059, "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": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }