{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.3683030710603004, "eval_steps": 500, "global_step": 15260, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0027796458193230216, "grad_norm": 9.012969970703125, "learning_rate": 1.0157273918741808e-06, "loss": 8.8089, "step": 31 }, { "epoch": 0.005559291638646043, "grad_norm": 5.6620192527771, "learning_rate": 2.0314547837483616e-06, "loss": 8.4351, "step": 62 }, { "epoch": 0.008338937457969065, "grad_norm": 6.994854927062988, "learning_rate": 3.0471821756225426e-06, "loss": 7.9593, "step": 93 }, { "epoch": 0.011118583277292086, "grad_norm": 13.229604721069336, "learning_rate": 4.062909567496723e-06, "loss": 7.4462, "step": 124 }, { "epoch": 0.013898229096615108, "grad_norm": 15.080535888671875, "learning_rate": 5.078636959370905e-06, "loss": 7.1616, "step": 155 }, { "epoch": 0.01667787491593813, "grad_norm": 12.822982788085938, "learning_rate": 6.094364351245085e-06, "loss": 6.9606, "step": 186 }, { "epoch": 0.019457520735261153, "grad_norm": 16.252538681030273, "learning_rate": 7.110091743119267e-06, "loss": 6.8272, "step": 217 }, { "epoch": 0.022237166554584173, "grad_norm": 15.957731246948242, "learning_rate": 8.125819134993446e-06, "loss": 6.7124, "step": 248 }, { "epoch": 0.025016812373907196, "grad_norm": 12.819754600524902, "learning_rate": 9.141546526867629e-06, "loss": 6.6177, "step": 279 }, { "epoch": 0.027796458193230216, "grad_norm": 15.852622032165527, "learning_rate": 1.015727391874181e-05, "loss": 6.4938, "step": 310 }, { "epoch": 0.03057610401255324, "grad_norm": 14.386216163635254, "learning_rate": 1.117300131061599e-05, "loss": 6.4049, "step": 341 }, { "epoch": 0.03335574983187626, "grad_norm": 17.984745025634766, "learning_rate": 1.218872870249017e-05, "loss": 6.2177, "step": 372 }, { "epoch": 0.03613539565119928, "grad_norm": 11.26113510131836, "learning_rate": 1.3204456094364351e-05, "loss": 6.1328, "step": 403 }, { "epoch": 0.038915041470522306, "grad_norm": 12.1831693649292, "learning_rate": 1.4220183486238533e-05, "loss": 5.9936, "step": 434 }, { "epoch": 0.04169468728984533, "grad_norm": 11.754878044128418, "learning_rate": 1.5235910878112714e-05, "loss": 5.8999, "step": 465 }, { "epoch": 0.044474333109168346, "grad_norm": 13.444028854370117, "learning_rate": 1.6251638269986893e-05, "loss": 5.7806, "step": 496 }, { "epoch": 0.04725397892849137, "grad_norm": 11.331082344055176, "learning_rate": 1.7267365661861077e-05, "loss": 5.6861, "step": 527 }, { "epoch": 0.05003362474781439, "grad_norm": 11.335689544677734, "learning_rate": 1.8283093053735257e-05, "loss": 5.5929, "step": 558 }, { "epoch": 0.052813270567137416, "grad_norm": 13.345412254333496, "learning_rate": 1.9298820445609438e-05, "loss": 5.5168, "step": 589 }, { "epoch": 0.05559291638646043, "grad_norm": 14.618036270141602, "learning_rate": 2.031454783748362e-05, "loss": 5.4084, "step": 620 }, { "epoch": 0.058372562205783456, "grad_norm": 8.540396690368652, "learning_rate": 2.13302752293578e-05, "loss": 5.328, "step": 651 }, { "epoch": 0.06115220802510648, "grad_norm": 10.201196670532227, "learning_rate": 2.234600262123198e-05, "loss": 5.2521, "step": 682 }, { "epoch": 0.0639318538444295, "grad_norm": 8.642182350158691, "learning_rate": 2.336173001310616e-05, "loss": 5.1689, "step": 713 }, { "epoch": 0.06671149966375252, "grad_norm": 12.399177551269531, "learning_rate": 2.437745740498034e-05, "loss": 5.1196, "step": 744 }, { "epoch": 0.06949114548307554, "grad_norm": 9.496380805969238, "learning_rate": 2.5393184796854525e-05, "loss": 5.0453, "step": 775 }, { "epoch": 0.07227079130239857, "grad_norm": 8.562884330749512, "learning_rate": 2.6408912188728702e-05, "loss": 4.9657, "step": 806 }, { "epoch": 0.07505043712172159, "grad_norm": 8.08729362487793, "learning_rate": 2.7424639580602886e-05, "loss": 4.9296, "step": 837 }, { "epoch": 0.07783008294104461, "grad_norm": 7.915094375610352, "learning_rate": 2.8440366972477066e-05, "loss": 4.8488, "step": 868 }, { "epoch": 0.08060972876036764, "grad_norm": 7.101661682128906, "learning_rate": 2.9456094364351244e-05, "loss": 4.8021, "step": 899 }, { "epoch": 0.08338937457969066, "grad_norm": 6.275183200836182, "learning_rate": 3.0471821756225428e-05, "loss": 4.7345, "step": 930 }, { "epoch": 0.08616902039901367, "grad_norm": 6.350998401641846, "learning_rate": 3.148754914809961e-05, "loss": 4.6746, "step": 961 }, { "epoch": 0.08894866621833669, "grad_norm": 7.120944976806641, "learning_rate": 3.2503276539973785e-05, "loss": 4.6101, "step": 992 }, { "epoch": 0.09172831203765971, "grad_norm": 6.11423921585083, "learning_rate": 3.351900393184797e-05, "loss": 4.5679, "step": 1023 }, { "epoch": 0.09450795785698274, "grad_norm": 6.339328289031982, "learning_rate": 3.453473132372215e-05, "loss": 4.5126, "step": 1054 }, { "epoch": 0.09728760367630576, "grad_norm": 10.269830703735352, "learning_rate": 3.555045871559633e-05, "loss": 4.4597, "step": 1085 }, { "epoch": 0.10006724949562879, "grad_norm": 5.776120662689209, "learning_rate": 3.6566186107470514e-05, "loss": 4.4408, "step": 1116 }, { "epoch": 0.10284689531495181, "grad_norm": 6.201286315917969, "learning_rate": 3.7581913499344695e-05, "loss": 4.3918, "step": 1147 }, { "epoch": 0.10562654113427483, "grad_norm": 5.641777038574219, "learning_rate": 3.8597640891218876e-05, "loss": 4.3731, "step": 1178 }, { "epoch": 0.10840618695359784, "grad_norm": 5.453923225402832, "learning_rate": 3.9613368283093056e-05, "loss": 4.2671, "step": 1209 }, { "epoch": 0.11118583277292086, "grad_norm": 5.152379512786865, "learning_rate": 4.062909567496724e-05, "loss": 4.2864, "step": 1240 }, { "epoch": 0.11396547859224389, "grad_norm": 5.2209153175354, "learning_rate": 4.164482306684142e-05, "loss": 4.282, "step": 1271 }, { "epoch": 0.11674512441156691, "grad_norm": 4.788177967071533, "learning_rate": 4.26605504587156e-05, "loss": 4.2331, "step": 1302 }, { "epoch": 0.11952477023088993, "grad_norm": 4.940870761871338, "learning_rate": 4.367627785058978e-05, "loss": 4.1933, "step": 1333 }, { "epoch": 0.12230441605021296, "grad_norm": 5.946582794189453, "learning_rate": 4.469200524246396e-05, "loss": 4.1688, "step": 1364 }, { "epoch": 0.12508406186953597, "grad_norm": 4.6552958488464355, "learning_rate": 4.570773263433814e-05, "loss": 4.1135, "step": 1395 }, { "epoch": 0.127863707688859, "grad_norm": 4.827516078948975, "learning_rate": 4.672346002621232e-05, "loss": 4.1121, "step": 1426 }, { "epoch": 0.13064335350818201, "grad_norm": 4.1209917068481445, "learning_rate": 4.77391874180865e-05, "loss": 4.0969, "step": 1457 }, { "epoch": 0.13342299932750504, "grad_norm": 4.2564802169799805, "learning_rate": 4.875491480996068e-05, "loss": 4.0791, "step": 1488 }, { "epoch": 0.13620264514682806, "grad_norm": 3.873272657394409, "learning_rate": 4.977064220183487e-05, "loss": 4.1008, "step": 1519 }, { "epoch": 0.13898229096615108, "grad_norm": 3.919401168823242, "learning_rate": 4.9999915451558777e-05, "loss": 4.047, "step": 1550 }, { "epoch": 0.1417619367854741, "grad_norm": 4.050148010253906, "learning_rate": 4.999955597496219e-05, "loss": 4.0279, "step": 1581 }, { "epoch": 0.14454158260479713, "grad_norm": 4.243306636810303, "learning_rate": 4.9998914381774255e-05, "loss": 4.0072, "step": 1612 }, { "epoch": 0.14732122842412015, "grad_norm": 19.370807647705078, "learning_rate": 4.999799067923527e-05, "loss": 4.0009, "step": 1643 }, { "epoch": 0.15010087424344318, "grad_norm": 3.8522801399230957, "learning_rate": 4.999678487776908e-05, "loss": 3.9695, "step": 1674 }, { "epoch": 0.1528805200627662, "grad_norm": 3.519608736038208, "learning_rate": 4.9995296990983006e-05, "loss": 3.9632, "step": 1705 }, { "epoch": 0.15566016588208922, "grad_norm": 3.812213897705078, "learning_rate": 4.999352703566763e-05, "loss": 3.9421, "step": 1736 }, { "epoch": 0.15843981170141225, "grad_norm": 3.684826135635376, "learning_rate": 4.999147503179668e-05, "loss": 3.9056, "step": 1767 }, { "epoch": 0.16121945752073527, "grad_norm": 3.6039719581604004, "learning_rate": 4.998914100252672e-05, "loss": 3.8937, "step": 1798 }, { "epoch": 0.1639991033400583, "grad_norm": 3.4558818340301514, "learning_rate": 4.998652497419696e-05, "loss": 3.8713, "step": 1829 }, { "epoch": 0.16677874915938132, "grad_norm": 3.3009331226348877, "learning_rate": 4.9983626976328927e-05, "loss": 3.8929, "step": 1860 }, { "epoch": 0.1695583949787043, "grad_norm": 3.433112382888794, "learning_rate": 4.998044704162613e-05, "loss": 3.8611, "step": 1891 }, { "epoch": 0.17233804079802734, "grad_norm": 3.2907469272613525, "learning_rate": 4.9976985205973705e-05, "loss": 3.8459, "step": 1922 }, { "epoch": 0.17511768661735036, "grad_norm": 3.1534502506256104, "learning_rate": 4.997324150843799e-05, "loss": 3.8152, "step": 1953 }, { "epoch": 0.17789733243667338, "grad_norm": 3.21655011177063, "learning_rate": 4.99692159912661e-05, "loss": 3.8318, "step": 1984 }, { "epoch": 0.1806769782559964, "grad_norm": 3.26338529586792, "learning_rate": 4.996490869988546e-05, "loss": 3.8047, "step": 2015 }, { "epoch": 0.18345662407531943, "grad_norm": 3.2187154293060303, "learning_rate": 4.996031968290326e-05, "loss": 3.8082, "step": 2046 }, { "epoch": 0.18623626989464245, "grad_norm": 3.153524875640869, "learning_rate": 4.995544899210594e-05, "loss": 3.8092, "step": 2077 }, { "epoch": 0.18901591571396548, "grad_norm": 3.033869504928589, "learning_rate": 4.9950296682458583e-05, "loss": 3.7729, "step": 2108 }, { "epoch": 0.1917955615332885, "grad_norm": 3.2953057289123535, "learning_rate": 4.994486281210429e-05, "loss": 3.7558, "step": 2139 }, { "epoch": 0.19457520735261152, "grad_norm": 3.220686912536621, "learning_rate": 4.9939147442363566e-05, "loss": 3.7482, "step": 2170 }, { "epoch": 0.19735485317193455, "grad_norm": 3.0368878841400146, "learning_rate": 4.9933150637733574e-05, "loss": 3.7542, "step": 2201 }, { "epoch": 0.20013449899125757, "grad_norm": 3.2065186500549316, "learning_rate": 4.992687246588743e-05, "loss": 3.7435, "step": 2232 }, { "epoch": 0.2029141448105806, "grad_norm": 3.1103830337524414, "learning_rate": 4.992031299767347e-05, "loss": 3.7183, "step": 2263 }, { "epoch": 0.20569379062990362, "grad_norm": 3.092560291290283, "learning_rate": 4.9913472307114386e-05, "loss": 3.7109, "step": 2294 }, { "epoch": 0.20847343644922664, "grad_norm": 3.1417951583862305, "learning_rate": 4.9906350471406446e-05, "loss": 3.7034, "step": 2325 }, { "epoch": 0.21125308226854966, "grad_norm": 3.0740373134613037, "learning_rate": 4.989894757091861e-05, "loss": 3.7072, "step": 2356 }, { "epoch": 0.2140327280878727, "grad_norm": 3.1177079677581787, "learning_rate": 4.989126368919158e-05, "loss": 3.6724, "step": 2387 }, { "epoch": 0.21681237390719568, "grad_norm": 2.946838855743408, "learning_rate": 4.988329891293693e-05, "loss": 3.6936, "step": 2418 }, { "epoch": 0.2195920197265187, "grad_norm": 2.851635456085205, "learning_rate": 4.987505333203608e-05, "loss": 3.6925, "step": 2449 }, { "epoch": 0.22237166554584173, "grad_norm": 2.841735601425171, "learning_rate": 4.9866527039539276e-05, "loss": 3.6946, "step": 2480 }, { "epoch": 0.22515131136516475, "grad_norm": 2.942103385925293, "learning_rate": 4.9857720131664594e-05, "loss": 3.6578, "step": 2511 }, { "epoch": 0.22793095718448778, "grad_norm": 2.8731508255004883, "learning_rate": 4.9848632707796773e-05, "loss": 3.6532, "step": 2542 }, { "epoch": 0.2307106030038108, "grad_norm": 2.66916561126709, "learning_rate": 4.9839264870486155e-05, "loss": 3.6784, "step": 2573 }, { "epoch": 0.23349024882313382, "grad_norm": 2.7230560779571533, "learning_rate": 4.9829616725447526e-05, "loss": 3.6274, "step": 2604 }, { "epoch": 0.23626989464245685, "grad_norm": 2.6979317665100098, "learning_rate": 4.981968838155888e-05, "loss": 3.6508, "step": 2635 }, { "epoch": 0.23904954046177987, "grad_norm": 2.828092098236084, "learning_rate": 4.980947995086024e-05, "loss": 3.6432, "step": 2666 }, { "epoch": 0.2418291862811029, "grad_norm": 2.77974271774292, "learning_rate": 4.979899154855234e-05, "loss": 3.6416, "step": 2697 }, { "epoch": 0.24460883210042592, "grad_norm": 2.941502809524536, "learning_rate": 4.9788223292995386e-05, "loss": 3.6298, "step": 2728 }, { "epoch": 0.24738847791974894, "grad_norm": 2.8036599159240723, "learning_rate": 4.977717530570768e-05, "loss": 3.6196, "step": 2759 }, { "epoch": 0.25016812373907193, "grad_norm": 3.6867358684539795, "learning_rate": 4.976584771136425e-05, "loss": 3.6403, "step": 2790 }, { "epoch": 0.252947769558395, "grad_norm": 2.673445463180542, "learning_rate": 4.975424063779547e-05, "loss": 3.5951, "step": 2821 }, { "epoch": 0.255727415377718, "grad_norm": 2.853241443634033, "learning_rate": 4.974235421598557e-05, "loss": 3.59, "step": 2852 }, { "epoch": 0.25850706119704103, "grad_norm": 2.672149896621704, "learning_rate": 4.973018858007122e-05, "loss": 3.5891, "step": 2883 }, { "epoch": 0.26128670701636403, "grad_norm": 2.8042409420013428, "learning_rate": 4.9717743867339963e-05, "loss": 3.6142, "step": 2914 }, { "epoch": 0.2640663528356871, "grad_norm": 2.5302071571350098, "learning_rate": 4.9705020218228695e-05, "loss": 3.5835, "step": 2945 }, { "epoch": 0.2668459986550101, "grad_norm": 2.7771754264831543, "learning_rate": 4.969201777632205e-05, "loss": 3.5982, "step": 2976 }, { "epoch": 0.2696256444743331, "grad_norm": 2.5498504638671875, "learning_rate": 4.9678736688350846e-05, "loss": 3.5839, "step": 3007 }, { "epoch": 0.2724052902936561, "grad_norm": 3.0297176837921143, "learning_rate": 4.966517710419033e-05, "loss": 3.5915, "step": 3038 }, { "epoch": 0.2751849361129792, "grad_norm": 2.695497989654541, "learning_rate": 4.965133917685858e-05, "loss": 3.5526, "step": 3069 }, { "epoch": 0.27796458193230217, "grad_norm": 2.634571075439453, "learning_rate": 4.9637223062514714e-05, "loss": 3.5695, "step": 3100 }, { "epoch": 0.2807442277516252, "grad_norm": 2.6347239017486572, "learning_rate": 4.962282892045718e-05, "loss": 3.5694, "step": 3131 }, { "epoch": 0.2835238735709482, "grad_norm": 2.5763373374938965, "learning_rate": 4.9608156913121904e-05, "loss": 3.5427, "step": 3162 }, { "epoch": 0.28630351939027127, "grad_norm": 2.5541677474975586, "learning_rate": 4.959320720608049e-05, "loss": 3.5716, "step": 3193 }, { "epoch": 0.28908316520959426, "grad_norm": 2.656294822692871, "learning_rate": 4.9577979968038354e-05, "loss": 3.5053, "step": 3224 }, { "epoch": 0.29186281102891726, "grad_norm": 2.5195116996765137, "learning_rate": 4.956247537083282e-05, "loss": 3.5467, "step": 3255 }, { "epoch": 0.2946424568482403, "grad_norm": 2.6532673835754395, "learning_rate": 4.9546693589431145e-05, "loss": 3.5251, "step": 3286 }, { "epoch": 0.2974221026675633, "grad_norm": 2.37542462348938, "learning_rate": 4.9530634801928595e-05, "loss": 3.5256, "step": 3317 }, { "epoch": 0.30020174848688636, "grad_norm": 2.5843489170074463, "learning_rate": 4.9514299189546395e-05, "loss": 3.5313, "step": 3348 }, { "epoch": 0.30298139430620935, "grad_norm": 2.532468557357788, "learning_rate": 4.949768693662973e-05, "loss": 3.5038, "step": 3379 }, { "epoch": 0.3057610401255324, "grad_norm": 2.527435302734375, "learning_rate": 4.948079823064559e-05, "loss": 3.5093, "step": 3410 }, { "epoch": 0.3085406859448554, "grad_norm": 2.451413869857788, "learning_rate": 4.946363326218074e-05, "loss": 3.5185, "step": 3441 }, { "epoch": 0.31132033176417845, "grad_norm": 2.611423969268799, "learning_rate": 4.9446192224939525e-05, "loss": 3.5165, "step": 3472 }, { "epoch": 0.31409997758350144, "grad_norm": 2.503922939300537, "learning_rate": 4.942847531574167e-05, "loss": 3.4938, "step": 3503 }, { "epoch": 0.3168796234028245, "grad_norm": 2.561654806137085, "learning_rate": 4.941048273452008e-05, "loss": 3.4674, "step": 3534 }, { "epoch": 0.3196592692221475, "grad_norm": 3.26798152923584, "learning_rate": 4.9392214684318605e-05, "loss": 3.4999, "step": 3565 }, { "epoch": 0.32243891504147054, "grad_norm": 2.450745105743408, "learning_rate": 4.93736713712897e-05, "loss": 3.4882, "step": 3596 }, { "epoch": 0.32521856086079354, "grad_norm": 2.631754159927368, "learning_rate": 4.9354853004692124e-05, "loss": 3.4813, "step": 3627 }, { "epoch": 0.3279982066801166, "grad_norm": 2.5118045806884766, "learning_rate": 4.93357597968886e-05, "loss": 3.4987, "step": 3658 }, { "epoch": 0.3307778524994396, "grad_norm": 2.5276923179626465, "learning_rate": 4.931639196334338e-05, "loss": 3.4835, "step": 3689 }, { "epoch": 0.33355749831876264, "grad_norm": 2.574352502822876, "learning_rate": 4.9296749722619826e-05, "loss": 3.5156, "step": 3720 }, { "epoch": 0.33633714413808563, "grad_norm": 2.3906681537628174, "learning_rate": 4.9276833296377966e-05, "loss": 3.4983, "step": 3751 }, { "epoch": 0.3391167899574086, "grad_norm": 2.3432400226593018, "learning_rate": 4.925664290937196e-05, "loss": 3.4442, "step": 3782 }, { "epoch": 0.3418964357767317, "grad_norm": 2.4267373085021973, "learning_rate": 4.9236178789447576e-05, "loss": 3.4829, "step": 3813 }, { "epoch": 0.3446760815960547, "grad_norm": 2.3619213104248047, "learning_rate": 4.921544116753962e-05, "loss": 3.4604, "step": 3844 }, { "epoch": 0.3474557274153777, "grad_norm": 2.476457357406616, "learning_rate": 4.919443027766935e-05, "loss": 3.4714, "step": 3875 }, { "epoch": 0.3502353732347007, "grad_norm": 2.2075233459472656, "learning_rate": 4.91731463569418e-05, "loss": 3.4627, "step": 3906 }, { "epoch": 0.35301501905402377, "grad_norm": 2.3251192569732666, "learning_rate": 4.915158964554312e-05, "loss": 3.4641, "step": 3937 }, { "epoch": 0.35579466487334677, "grad_norm": 2.4196231365203857, "learning_rate": 4.912976038673786e-05, "loss": 3.4076, "step": 3968 }, { "epoch": 0.3585743106926698, "grad_norm": 2.4416725635528564, "learning_rate": 4.9107658826866254e-05, "loss": 3.463, "step": 3999 }, { "epoch": 0.3613539565119928, "grad_norm": 2.3500940799713135, "learning_rate": 4.908528521534139e-05, "loss": 3.478, "step": 4030 }, { "epoch": 0.36413360233131586, "grad_norm": 2.3429739475250244, "learning_rate": 4.906263980464644e-05, "loss": 3.4437, "step": 4061 }, { "epoch": 0.36691324815063886, "grad_norm": 2.5604615211486816, "learning_rate": 4.903972285033178e-05, "loss": 3.4703, "step": 4092 }, { "epoch": 0.3696928939699619, "grad_norm": 2.4725446701049805, "learning_rate": 4.901653461101213e-05, "loss": 3.4554, "step": 4123 }, { "epoch": 0.3724725397892849, "grad_norm": 2.291586399078369, "learning_rate": 4.8993075348363626e-05, "loss": 3.4455, "step": 4154 }, { "epoch": 0.37525218560860796, "grad_norm": 2.3323886394500732, "learning_rate": 4.896934532712084e-05, "loss": 3.4203, "step": 4185 }, { "epoch": 0.37803183142793095, "grad_norm": 2.3561739921569824, "learning_rate": 4.8945344815073846e-05, "loss": 3.4557, "step": 4216 }, { "epoch": 0.380811477247254, "grad_norm": 2.3202600479125977, "learning_rate": 4.892107408306516e-05, "loss": 3.4446, "step": 4247 }, { "epoch": 0.383591123066577, "grad_norm": 2.3766143321990967, "learning_rate": 4.889653340498669e-05, "loss": 3.4709, "step": 4278 }, { "epoch": 0.3863707688859, "grad_norm": 2.1723828315734863, "learning_rate": 4.8871723057776664e-05, "loss": 3.4439, "step": 4309 }, { "epoch": 0.38915041470522305, "grad_norm": 2.4008755683898926, "learning_rate": 4.8846643321416476e-05, "loss": 3.4173, "step": 4340 }, { "epoch": 0.39193006052454604, "grad_norm": 2.351132869720459, "learning_rate": 4.882129447892753e-05, "loss": 3.4055, "step": 4371 }, { "epoch": 0.3947097063438691, "grad_norm": 2.4292497634887695, "learning_rate": 4.8795676816368076e-05, "loss": 3.4096, "step": 4402 }, { "epoch": 0.3974893521631921, "grad_norm": 2.3505067825317383, "learning_rate": 4.876979062282995e-05, "loss": 3.4164, "step": 4433 }, { "epoch": 0.40026899798251514, "grad_norm": 2.372157335281372, "learning_rate": 4.8743636190435325e-05, "loss": 3.4229, "step": 4464 }, { "epoch": 0.40304864380183814, "grad_norm": 2.3175127506256104, "learning_rate": 4.871721381433344e-05, "loss": 3.4155, "step": 4495 }, { "epoch": 0.4058282896211612, "grad_norm": 2.3510518074035645, "learning_rate": 4.869052379269719e-05, "loss": 3.4177, "step": 4526 }, { "epoch": 0.4086079354404842, "grad_norm": 2.3506274223327637, "learning_rate": 4.866356642671985e-05, "loss": 3.4048, "step": 4557 }, { "epoch": 0.41138758125980723, "grad_norm": 2.2985119819641113, "learning_rate": 4.8636342020611634e-05, "loss": 3.4022, "step": 4588 }, { "epoch": 0.41416722707913023, "grad_norm": 2.342514753341675, "learning_rate": 4.860885088159626e-05, "loss": 3.4082, "step": 4619 }, { "epoch": 0.4169468728984533, "grad_norm": 2.2110369205474854, "learning_rate": 4.858109331990751e-05, "loss": 3.3916, "step": 4650 }, { "epoch": 0.4197265187177763, "grad_norm": 2.2878293991088867, "learning_rate": 4.855306964878567e-05, "loss": 3.3851, "step": 4681 }, { "epoch": 0.4225061645370993, "grad_norm": 2.3494646549224854, "learning_rate": 4.8524780184474084e-05, "loss": 3.4091, "step": 4712 }, { "epoch": 0.4252858103564223, "grad_norm": 2.3722164630889893, "learning_rate": 4.8496225246215496e-05, "loss": 3.3858, "step": 4743 }, { "epoch": 0.4280654561757454, "grad_norm": 2.4473116397857666, "learning_rate": 4.8467405156248505e-05, "loss": 3.4045, "step": 4774 }, { "epoch": 0.43084510199506837, "grad_norm": 2.6271281242370605, "learning_rate": 4.843832023980392e-05, "loss": 3.3902, "step": 4805 }, { "epoch": 0.43362474781439136, "grad_norm": 2.2729909420013428, "learning_rate": 4.840897082510106e-05, "loss": 3.394, "step": 4836 }, { "epoch": 0.4364043936337144, "grad_norm": 2.2466001510620117, "learning_rate": 4.8379357243344084e-05, "loss": 3.4198, "step": 4867 }, { "epoch": 0.4391840394530374, "grad_norm": 2.2691309452056885, "learning_rate": 4.8349479828718236e-05, "loss": 3.4044, "step": 4898 }, { "epoch": 0.44196368527236046, "grad_norm": 2.3264501094818115, "learning_rate": 4.8319338918386075e-05, "loss": 3.407, "step": 4929 }, { "epoch": 0.44474333109168346, "grad_norm": 2.199679374694824, "learning_rate": 4.828893485248369e-05, "loss": 3.3488, "step": 4960 }, { "epoch": 0.4475229769110065, "grad_norm": 2.2347097396850586, "learning_rate": 4.825826797411682e-05, "loss": 3.3713, "step": 4991 }, { "epoch": 0.4503026227303295, "grad_norm": 2.107295036315918, "learning_rate": 4.822733862935702e-05, "loss": 3.3618, "step": 5022 }, { "epoch": 0.45308226854965256, "grad_norm": 2.2157092094421387, "learning_rate": 4.819614716723775e-05, "loss": 3.3641, "step": 5053 }, { "epoch": 0.45586191436897555, "grad_norm": 2.1321468353271484, "learning_rate": 4.8164693939750425e-05, "loss": 3.3874, "step": 5084 }, { "epoch": 0.4586415601882986, "grad_norm": 2.1471335887908936, "learning_rate": 4.813297930184042e-05, "loss": 3.3489, "step": 5115 }, { "epoch": 0.4614212060076216, "grad_norm": 2.474858045578003, "learning_rate": 4.810100361140314e-05, "loss": 3.3785, "step": 5146 }, { "epoch": 0.46420085182694465, "grad_norm": 2.2046587467193604, "learning_rate": 4.8068767229279885e-05, "loss": 3.3427, "step": 5177 }, { "epoch": 0.46698049764626764, "grad_norm": 2.2125439643859863, "learning_rate": 4.8036270519253854e-05, "loss": 3.3519, "step": 5208 }, { "epoch": 0.4697601434655907, "grad_norm": 2.2569172382354736, "learning_rate": 4.8003513848046e-05, "loss": 3.3803, "step": 5239 }, { "epoch": 0.4725397892849137, "grad_norm": 2.0965545177459717, "learning_rate": 4.79704975853109e-05, "loss": 3.3394, "step": 5270 }, { "epoch": 0.47531943510423674, "grad_norm": 2.2493419647216797, "learning_rate": 4.793722210363262e-05, "loss": 3.3476, "step": 5301 }, { "epoch": 0.47809908092355974, "grad_norm": 2.2152726650238037, "learning_rate": 4.7903687778520414e-05, "loss": 3.3549, "step": 5332 }, { "epoch": 0.4808787267428828, "grad_norm": 2.2980692386627197, "learning_rate": 4.7869894988404593e-05, "loss": 3.3661, "step": 5363 }, { "epoch": 0.4836583725622058, "grad_norm": 2.221606731414795, "learning_rate": 4.783584411463221e-05, "loss": 3.3421, "step": 5394 }, { "epoch": 0.4864380183815288, "grad_norm": 2.5827386379241943, "learning_rate": 4.780153554146274e-05, "loss": 3.3719, "step": 5425 }, { "epoch": 0.48921766420085183, "grad_norm": 2.4041783809661865, "learning_rate": 4.7766969656063766e-05, "loss": 3.3744, "step": 5456 }, { "epoch": 0.4919973100201748, "grad_norm": 2.113762140274048, "learning_rate": 4.773214684850662e-05, "loss": 3.3434, "step": 5487 }, { "epoch": 0.4947769558394979, "grad_norm": 2.2005934715270996, "learning_rate": 4.769706751176193e-05, "loss": 3.3319, "step": 5518 }, { "epoch": 0.4975566016588209, "grad_norm": 2.1655445098876953, "learning_rate": 4.7661732041695264e-05, "loss": 3.337, "step": 5549 }, { "epoch": 0.5003362474781439, "grad_norm": 2.1906204223632812, "learning_rate": 4.762614083706258e-05, "loss": 3.3352, "step": 5580 }, { "epoch": 0.503115893297467, "grad_norm": 2.1618640422821045, "learning_rate": 4.759029429950581e-05, "loss": 3.3002, "step": 5611 }, { "epoch": 0.50589553911679, "grad_norm": 2.196354389190674, "learning_rate": 4.7554192833548235e-05, "loss": 3.3706, "step": 5642 }, { "epoch": 0.508675184936113, "grad_norm": 2.258183717727661, "learning_rate": 4.751783684659e-05, "loss": 3.3336, "step": 5673 }, { "epoch": 0.511454830755436, "grad_norm": 2.233896493911743, "learning_rate": 4.748122674890348e-05, "loss": 3.3192, "step": 5704 }, { "epoch": 0.5142344765747591, "grad_norm": 2.067518949508667, "learning_rate": 4.7444362953628654e-05, "loss": 3.3154, "step": 5735 }, { "epoch": 0.5170141223940821, "grad_norm": 2.074993133544922, "learning_rate": 4.7407245876768424e-05, "loss": 3.3178, "step": 5766 }, { "epoch": 0.5197937682134051, "grad_norm": 2.1448609828948975, "learning_rate": 4.736987593718397e-05, "loss": 3.3403, "step": 5797 }, { "epoch": 0.5225734140327281, "grad_norm": 2.1654341220855713, "learning_rate": 4.733225355658999e-05, "loss": 3.3061, "step": 5828 }, { "epoch": 0.5253530598520512, "grad_norm": 2.3800811767578125, "learning_rate": 4.7294379159549926e-05, "loss": 3.3461, "step": 5859 }, { "epoch": 0.5281327056713742, "grad_norm": 2.2466440200805664, "learning_rate": 4.725625317347119e-05, "loss": 3.3161, "step": 5890 }, { "epoch": 0.5309123514906972, "grad_norm": 2.2604174613952637, "learning_rate": 4.7217876028600374e-05, "loss": 3.3191, "step": 5921 }, { "epoch": 0.5336919973100201, "grad_norm": 2.1068217754364014, "learning_rate": 4.717924815801832e-05, "loss": 3.3305, "step": 5952 }, { "epoch": 0.5364716431293431, "grad_norm": 2.078378200531006, "learning_rate": 4.714036999763532e-05, "loss": 3.3105, "step": 5983 }, { "epoch": 0.5392512889486663, "grad_norm": 2.120563507080078, "learning_rate": 4.7101241986186116e-05, "loss": 3.3029, "step": 6014 }, { "epoch": 0.5420309347679892, "grad_norm": 2.4018023014068604, "learning_rate": 4.7061864565225e-05, "loss": 3.3271, "step": 6045 }, { "epoch": 0.5448105805873122, "grad_norm": 2.1769769191741943, "learning_rate": 4.702223817912081e-05, "loss": 3.3202, "step": 6076 }, { "epoch": 0.5475902264066352, "grad_norm": 2.2606041431427, "learning_rate": 4.698236327505195e-05, "loss": 3.328, "step": 6107 }, { "epoch": 0.5503698722259583, "grad_norm": 2.0148673057556152, "learning_rate": 4.694224030300127e-05, "loss": 3.321, "step": 6138 }, { "epoch": 0.5531495180452813, "grad_norm": 2.204648494720459, "learning_rate": 4.690186971575107e-05, "loss": 3.3163, "step": 6169 }, { "epoch": 0.5559291638646043, "grad_norm": 2.116101026535034, "learning_rate": 4.6861251968877916e-05, "loss": 3.3168, "step": 6200 }, { "epoch": 0.5587088096839273, "grad_norm": 2.1526737213134766, "learning_rate": 4.68203875207476e-05, "loss": 3.3286, "step": 6231 }, { "epoch": 0.5614884555032504, "grad_norm": 2.1621978282928467, "learning_rate": 4.677927683250983e-05, "loss": 3.2935, "step": 6262 }, { "epoch": 0.5642681013225734, "grad_norm": 2.039001941680908, "learning_rate": 4.6737920368093156e-05, "loss": 3.2964, "step": 6293 }, { "epoch": 0.5670477471418964, "grad_norm": 2.0557541847229004, "learning_rate": 4.669631859419965e-05, "loss": 3.2933, "step": 6324 }, { "epoch": 0.5698273929612194, "grad_norm": 2.0704591274261475, "learning_rate": 4.6654471980299676e-05, "loss": 3.2733, "step": 6355 }, { "epoch": 0.5726070387805425, "grad_norm": 2.0741264820098877, "learning_rate": 4.661238099862658e-05, "loss": 3.2808, "step": 6386 }, { "epoch": 0.5753866845998655, "grad_norm": 2.081774950027466, "learning_rate": 4.657004612417138e-05, "loss": 3.3013, "step": 6417 }, { "epoch": 0.5781663304191885, "grad_norm": 2.3074076175689697, "learning_rate": 4.6527467834677374e-05, "loss": 3.3015, "step": 6448 }, { "epoch": 0.5809459762385115, "grad_norm": 2.070481538772583, "learning_rate": 4.648464661063478e-05, "loss": 3.3201, "step": 6479 }, { "epoch": 0.5837256220578345, "grad_norm": 2.8896186351776123, "learning_rate": 4.6441582935275264e-05, "loss": 3.2986, "step": 6510 }, { "epoch": 0.5865052678771576, "grad_norm": 2.132897138595581, "learning_rate": 4.6398277294566586e-05, "loss": 3.3078, "step": 6541 }, { "epoch": 0.5892849136964806, "grad_norm": 2.049975633621216, "learning_rate": 4.6354730177207e-05, "loss": 3.3065, "step": 6572 }, { "epoch": 0.5920645595158036, "grad_norm": 2.059072494506836, "learning_rate": 4.6310942074619787e-05, "loss": 3.2919, "step": 6603 }, { "epoch": 0.5948442053351266, "grad_norm": 2.1366543769836426, "learning_rate": 4.626691348094777e-05, "loss": 3.318, "step": 6634 }, { "epoch": 0.5976238511544497, "grad_norm": 2.196328639984131, "learning_rate": 4.622264489304762e-05, "loss": 3.2828, "step": 6665 }, { "epoch": 0.6004034969737727, "grad_norm": 2.102091073989868, "learning_rate": 4.617813681048434e-05, "loss": 3.2776, "step": 6696 }, { "epoch": 0.6031831427930957, "grad_norm": 2.030512809753418, "learning_rate": 4.61333897355256e-05, "loss": 3.3112, "step": 6727 }, { "epoch": 0.6059627886124187, "grad_norm": 2.165297031402588, "learning_rate": 4.608840417313604e-05, "loss": 3.2957, "step": 6758 }, { "epoch": 0.6087424344317418, "grad_norm": 2.1030540466308594, "learning_rate": 4.6043180630971646e-05, "loss": 3.2941, "step": 6789 }, { "epoch": 0.6115220802510648, "grad_norm": 2.4561312198638916, "learning_rate": 4.599771961937391e-05, "loss": 3.3059, "step": 6820 }, { "epoch": 0.6143017260703878, "grad_norm": 2.0763375759124756, "learning_rate": 4.5952021651364204e-05, "loss": 3.298, "step": 6851 }, { "epoch": 0.6170813718897108, "grad_norm": 2.0811164379119873, "learning_rate": 4.590608724263786e-05, "loss": 3.2479, "step": 6882 }, { "epoch": 0.6198610177090339, "grad_norm": 2.046067476272583, "learning_rate": 4.585991691155845e-05, "loss": 3.2624, "step": 6913 }, { "epoch": 0.6226406635283569, "grad_norm": 2.2052958011627197, "learning_rate": 4.581351117915188e-05, "loss": 3.281, "step": 6944 }, { "epoch": 0.6254203093476799, "grad_norm": 1.959435224533081, "learning_rate": 4.5766870569100534e-05, "loss": 3.2629, "step": 6975 }, { "epoch": 0.6281999551670029, "grad_norm": 2.1152093410491943, "learning_rate": 4.571999560773736e-05, "loss": 3.2438, "step": 7006 }, { "epoch": 0.6309796009863259, "grad_norm": 1.990297555923462, "learning_rate": 4.5672886824039915e-05, "loss": 3.2702, "step": 7037 }, { "epoch": 0.633759246805649, "grad_norm": 1.9708343744277954, "learning_rate": 4.5625544749624435e-05, "loss": 3.2711, "step": 7068 }, { "epoch": 0.636538892624972, "grad_norm": 2.0719597339630127, "learning_rate": 4.5577969918739794e-05, "loss": 3.2617, "step": 7099 }, { "epoch": 0.639318538444295, "grad_norm": 1.9742841720581055, "learning_rate": 4.5530162868261486e-05, "loss": 3.2435, "step": 7130 }, { "epoch": 0.642098184263618, "grad_norm": 1.9801511764526367, "learning_rate": 4.548212413768558e-05, "loss": 3.2844, "step": 7161 }, { "epoch": 0.6448778300829411, "grad_norm": 1.896723985671997, "learning_rate": 4.543385426912261e-05, "loss": 3.2623, "step": 7192 }, { "epoch": 0.6476574759022641, "grad_norm": 1.9870046377182007, "learning_rate": 4.53853538072915e-05, "loss": 3.2629, "step": 7223 }, { "epoch": 0.6504371217215871, "grad_norm": 1.9941246509552002, "learning_rate": 4.533662329951336e-05, "loss": 3.2689, "step": 7254 }, { "epoch": 0.6532167675409101, "grad_norm": 2.104779005050659, "learning_rate": 4.528766329570536e-05, "loss": 3.2661, "step": 7285 }, { "epoch": 0.6559964133602332, "grad_norm": 2.0418860912323, "learning_rate": 4.523847434837447e-05, "loss": 3.2368, "step": 7316 }, { "epoch": 0.6587760591795562, "grad_norm": 2.008305549621582, "learning_rate": 4.518905701261128e-05, "loss": 3.2292, "step": 7347 }, { "epoch": 0.6615557049988792, "grad_norm": 1.9720836877822876, "learning_rate": 4.5139411846083715e-05, "loss": 3.2326, "step": 7378 }, { "epoch": 0.6643353508182022, "grad_norm": 2.144597291946411, "learning_rate": 4.508953940903073e-05, "loss": 3.2545, "step": 7409 }, { "epoch": 0.6671149966375253, "grad_norm": 2.044677972793579, "learning_rate": 4.5039440264255994e-05, "loss": 3.2522, "step": 7440 }, { "epoch": 0.6698946424568483, "grad_norm": 2.0666587352752686, "learning_rate": 4.498911497712155e-05, "loss": 3.2563, "step": 7471 }, { "epoch": 0.6726742882761713, "grad_norm": 2.0450077056884766, "learning_rate": 4.493856411554142e-05, "loss": 3.2622, "step": 7502 }, { "epoch": 0.6754539340954943, "grad_norm": 2.0837104320526123, "learning_rate": 4.4887788249975206e-05, "loss": 3.2166, "step": 7533 }, { "epoch": 0.6782335799148173, "grad_norm": 1.960066556930542, "learning_rate": 4.4836787953421656e-05, "loss": 3.2551, "step": 7564 }, { "epoch": 0.6810132257341404, "grad_norm": 2.063417673110962, "learning_rate": 4.478556380141218e-05, "loss": 3.26, "step": 7595 }, { "epoch": 0.6837928715534634, "grad_norm": 2.146414279937744, "learning_rate": 4.4734116372004375e-05, "loss": 3.242, "step": 7626 }, { "epoch": 0.6865725173727864, "grad_norm": 2.0153274536132812, "learning_rate": 4.4682446245775477e-05, "loss": 3.2638, "step": 7657 }, { "epoch": 0.6893521631921093, "grad_norm": 2.0109503269195557, "learning_rate": 4.463055400581586e-05, "loss": 3.2362, "step": 7688 }, { "epoch": 0.6921318090114325, "grad_norm": 2.022961378097534, "learning_rate": 4.4578440237722374e-05, "loss": 3.2551, "step": 7719 }, { "epoch": 0.6949114548307554, "grad_norm": 2.004865884780884, "learning_rate": 4.452610552959183e-05, "loss": 3.2195, "step": 7750 }, { "epoch": 0.6976911006500784, "grad_norm": 2.102989435195923, "learning_rate": 4.447355047201428e-05, "loss": 3.2446, "step": 7781 }, { "epoch": 0.7004707464694014, "grad_norm": 2.077101230621338, "learning_rate": 4.4420775658066414e-05, "loss": 3.2212, "step": 7812 }, { "epoch": 0.7032503922887245, "grad_norm": 2.093027114868164, "learning_rate": 4.436778168330484e-05, "loss": 3.2369, "step": 7843 }, { "epoch": 0.7060300381080475, "grad_norm": 1.9160785675048828, "learning_rate": 4.4314569145759353e-05, "loss": 3.2311, "step": 7874 }, { "epoch": 0.7088096839273705, "grad_norm": 2.0607402324676514, "learning_rate": 4.42611386459262e-05, "loss": 3.2522, "step": 7905 }, { "epoch": 0.7115893297466935, "grad_norm": 2.021075487136841, "learning_rate": 4.420749078676133e-05, "loss": 3.2234, "step": 7936 }, { "epoch": 0.7143689755660166, "grad_norm": 2.0619757175445557, "learning_rate": 4.4153626173673516e-05, "loss": 3.225, "step": 7967 }, { "epoch": 0.7171486213853396, "grad_norm": 1.9858311414718628, "learning_rate": 4.409954541451762e-05, "loss": 3.2551, "step": 7998 }, { "epoch": 0.7199282672046626, "grad_norm": 2.0410025119781494, "learning_rate": 4.404524911958764e-05, "loss": 3.2265, "step": 8029 }, { "epoch": 0.7227079130239856, "grad_norm": 1.9730476140975952, "learning_rate": 4.399073790160989e-05, "loss": 3.2298, "step": 8060 }, { "epoch": 0.7254875588433086, "grad_norm": 2.037961006164551, "learning_rate": 4.393601237573607e-05, "loss": 3.2282, "step": 8091 }, { "epoch": 0.7282672046626317, "grad_norm": 1.9044350385665894, "learning_rate": 4.388107315953628e-05, "loss": 3.2495, "step": 8122 }, { "epoch": 0.7310468504819547, "grad_norm": 2.097494602203369, "learning_rate": 4.382592087299212e-05, "loss": 3.2229, "step": 8153 }, { "epoch": 0.7338264963012777, "grad_norm": 2.014116048812866, "learning_rate": 4.377055613848964e-05, "loss": 3.2354, "step": 8184 }, { "epoch": 0.7366061421206007, "grad_norm": 1.8900959491729736, "learning_rate": 4.3714979580812355e-05, "loss": 3.2029, "step": 8215 }, { "epoch": 0.7393857879399238, "grad_norm": 2.092454195022583, "learning_rate": 4.365919182713416e-05, "loss": 3.1969, "step": 8246 }, { "epoch": 0.7421654337592468, "grad_norm": 1.9832301139831543, "learning_rate": 4.360319350701226e-05, "loss": 3.2563, "step": 8277 }, { "epoch": 0.7449450795785698, "grad_norm": 2.038874387741089, "learning_rate": 4.3546985252380115e-05, "loss": 3.2226, "step": 8308 }, { "epoch": 0.7477247253978928, "grad_norm": 1.9169414043426514, "learning_rate": 4.349056769754021e-05, "loss": 3.2469, "step": 8339 }, { "epoch": 0.7505043712172159, "grad_norm": 1.8921377658843994, "learning_rate": 4.3433941479156994e-05, "loss": 3.1965, "step": 8370 }, { "epoch": 0.7532840170365389, "grad_norm": 1.893687129020691, "learning_rate": 4.3377107236249647e-05, "loss": 3.2391, "step": 8401 }, { "epoch": 0.7560636628558619, "grad_norm": 1.9864296913146973, "learning_rate": 4.332006561018488e-05, "loss": 3.2318, "step": 8432 }, { "epoch": 0.7588433086751849, "grad_norm": 2.1311209201812744, "learning_rate": 4.3262817244669683e-05, "loss": 3.2566, "step": 8463 }, { "epoch": 0.761622954494508, "grad_norm": 1.9401289224624634, "learning_rate": 4.3205362785744083e-05, "loss": 3.202, "step": 8494 }, { "epoch": 0.764402600313831, "grad_norm": 1.9595686197280884, "learning_rate": 4.314770288177384e-05, "loss": 3.2308, "step": 8525 }, { "epoch": 0.767182246133154, "grad_norm": 2.201599597930908, "learning_rate": 4.308983818344313e-05, "loss": 3.2234, "step": 8556 }, { "epoch": 0.769961891952477, "grad_norm": 2.4435086250305176, "learning_rate": 4.3031769343747206e-05, "loss": 3.2091, "step": 8587 }, { "epoch": 0.7727415377718, "grad_norm": 1.9813133478164673, "learning_rate": 4.297349701798505e-05, "loss": 3.2196, "step": 8618 }, { "epoch": 0.7755211835911231, "grad_norm": 2.008185863494873, "learning_rate": 4.2915021863751916e-05, "loss": 3.2411, "step": 8649 }, { "epoch": 0.7783008294104461, "grad_norm": 1.8839123249053955, "learning_rate": 4.285634454093198e-05, "loss": 3.2193, "step": 8680 }, { "epoch": 0.7810804752297691, "grad_norm": 1.9559476375579834, "learning_rate": 4.279746571169086e-05, "loss": 3.1888, "step": 8711 }, { "epoch": 0.7838601210490921, "grad_norm": 2.0515148639678955, "learning_rate": 4.2738386040468136e-05, "loss": 3.1983, "step": 8742 }, { "epoch": 0.7866397668684152, "grad_norm": 2.064584255218506, "learning_rate": 4.2679106193969866e-05, "loss": 3.2198, "step": 8773 }, { "epoch": 0.7894194126877382, "grad_norm": 1.9931387901306152, "learning_rate": 4.261962684116106e-05, "loss": 3.1869, "step": 8804 }, { "epoch": 0.7921990585070612, "grad_norm": 1.978033423423767, "learning_rate": 4.2559948653258145e-05, "loss": 3.206, "step": 8835 }, { "epoch": 0.7949787043263842, "grad_norm": 1.9826278686523438, "learning_rate": 4.250007230372134e-05, "loss": 3.2089, "step": 8866 }, { "epoch": 0.7977583501457073, "grad_norm": 1.8395289182662964, "learning_rate": 4.2439998468247126e-05, "loss": 3.1741, "step": 8897 }, { "epoch": 0.8005379959650303, "grad_norm": 1.8760936260223389, "learning_rate": 4.2379727824760566e-05, "loss": 3.1888, "step": 8928 }, { "epoch": 0.8033176417843533, "grad_norm": 2.04682993888855, "learning_rate": 4.231926105340768e-05, "loss": 3.2082, "step": 8959 }, { "epoch": 0.8060972876036763, "grad_norm": 2.0639662742614746, "learning_rate": 4.225859883654776e-05, "loss": 3.2422, "step": 8990 }, { "epoch": 0.8088769334229994, "grad_norm": 1.8841536045074463, "learning_rate": 4.219774185874569e-05, "loss": 3.2068, "step": 9021 }, { "epoch": 0.8116565792423224, "grad_norm": 1.9644831418991089, "learning_rate": 4.213669080676418e-05, "loss": 3.2078, "step": 9052 }, { "epoch": 0.8144362250616454, "grad_norm": 1.933451771736145, "learning_rate": 4.2075446369556056e-05, "loss": 3.2052, "step": 9083 }, { "epoch": 0.8172158708809684, "grad_norm": 1.968398094177246, "learning_rate": 4.201400923825648e-05, "loss": 3.185, "step": 9114 }, { "epoch": 0.8199955167002914, "grad_norm": 1.9496296644210815, "learning_rate": 4.195238010617511e-05, "loss": 3.1678, "step": 9145 }, { "epoch": 0.8227751625196145, "grad_norm": 1.933290958404541, "learning_rate": 4.1890559668788344e-05, "loss": 3.1987, "step": 9176 }, { "epoch": 0.8255548083389375, "grad_norm": 1.92232346534729, "learning_rate": 4.1828548623731405e-05, "loss": 3.2024, "step": 9207 }, { "epoch": 0.8283344541582605, "grad_norm": 2.029100179672241, "learning_rate": 4.1766347670790506e-05, "loss": 3.1616, "step": 9238 }, { "epoch": 0.8311140999775835, "grad_norm": 2.071643114089966, "learning_rate": 4.170395751189495e-05, "loss": 3.1797, "step": 9269 }, { "epoch": 0.8338937457969066, "grad_norm": 1.8804633617401123, "learning_rate": 4.164137885110921e-05, "loss": 3.1841, "step": 9300 }, { "epoch": 0.8366733916162296, "grad_norm": 1.929567813873291, "learning_rate": 4.157861239462495e-05, "loss": 3.177, "step": 9331 }, { "epoch": 0.8394530374355526, "grad_norm": 1.9015624523162842, "learning_rate": 4.1515658850753114e-05, "loss": 3.2134, "step": 9362 }, { "epoch": 0.8422326832548755, "grad_norm": 1.91888427734375, "learning_rate": 4.145251892991588e-05, "loss": 3.1466, "step": 9393 }, { "epoch": 0.8450123290741987, "grad_norm": 2.033877372741699, "learning_rate": 4.138919334463868e-05, "loss": 3.1802, "step": 9424 }, { "epoch": 0.8477919748935216, "grad_norm": 1.9958734512329102, "learning_rate": 4.1325682809542124e-05, "loss": 3.17, "step": 9455 }, { "epoch": 0.8505716207128446, "grad_norm": 1.941024661064148, "learning_rate": 4.126198804133398e-05, "loss": 3.1876, "step": 9486 }, { "epoch": 0.8533512665321676, "grad_norm": 1.9628397226333618, "learning_rate": 4.1198109758801055e-05, "loss": 3.1944, "step": 9517 }, { "epoch": 0.8561309123514907, "grad_norm": 1.9526383876800537, "learning_rate": 4.113404868280107e-05, "loss": 3.2019, "step": 9548 }, { "epoch": 0.8589105581708137, "grad_norm": 1.9171335697174072, "learning_rate": 4.106980553625457e-05, "loss": 3.1993, "step": 9579 }, { "epoch": 0.8616902039901367, "grad_norm": 2.0531489849090576, "learning_rate": 4.100538104413674e-05, "loss": 3.1918, "step": 9610 }, { "epoch": 0.8644698498094597, "grad_norm": 1.840210199356079, "learning_rate": 4.09407759334692e-05, "loss": 3.1762, "step": 9641 }, { "epoch": 0.8672494956287827, "grad_norm": 1.990539789199829, "learning_rate": 4.087599093331186e-05, "loss": 3.1746, "step": 9672 }, { "epoch": 0.8700291414481058, "grad_norm": 2.0064046382904053, "learning_rate": 4.081102677475462e-05, "loss": 3.1779, "step": 9703 }, { "epoch": 0.8728087872674288, "grad_norm": 1.959908127784729, "learning_rate": 4.0745884190909194e-05, "loss": 3.1502, "step": 9734 }, { "epoch": 0.8755884330867518, "grad_norm": 1.9566411972045898, "learning_rate": 4.0680563916900796e-05, "loss": 3.1801, "step": 9765 }, { "epoch": 0.8783680789060748, "grad_norm": 2.0030715465545654, "learning_rate": 4.0615066689859815e-05, "loss": 3.1597, "step": 9796 }, { "epoch": 0.8811477247253979, "grad_norm": 1.9277180433273315, "learning_rate": 4.0549393248913584e-05, "loss": 3.1501, "step": 9827 }, { "epoch": 0.8839273705447209, "grad_norm": 1.887507677078247, "learning_rate": 4.048354433517794e-05, "loss": 3.1713, "step": 9858 }, { "epoch": 0.8867070163640439, "grad_norm": 1.9514687061309814, "learning_rate": 4.0417520691748916e-05, "loss": 3.1726, "step": 9889 }, { "epoch": 0.8894866621833669, "grad_norm": 2.0142714977264404, "learning_rate": 4.035132306369438e-05, "loss": 3.1824, "step": 9920 }, { "epoch": 0.89226630800269, "grad_norm": 1.9494922161102295, "learning_rate": 4.028495219804555e-05, "loss": 3.2172, "step": 9951 }, { "epoch": 0.895045953822013, "grad_norm": 1.8487540483474731, "learning_rate": 4.021840884378864e-05, "loss": 3.2064, "step": 9982 }, { "epoch": 0.897825599641336, "grad_norm": 1.8519740104675293, "learning_rate": 4.015169375185633e-05, "loss": 3.191, "step": 10013 }, { "epoch": 0.900605245460659, "grad_norm": 1.909957766532898, "learning_rate": 4.0084807675119396e-05, "loss": 3.1534, "step": 10044 }, { "epoch": 0.9033848912799821, "grad_norm": 2.1778204441070557, "learning_rate": 4.0017751368378106e-05, "loss": 3.1926, "step": 10075 }, { "epoch": 0.9061645370993051, "grad_norm": 1.9085873365402222, "learning_rate": 3.995052558835377e-05, "loss": 3.1589, "step": 10106 }, { "epoch": 0.9089441829186281, "grad_norm": 1.863411784172058, "learning_rate": 3.988313109368017e-05, "loss": 3.172, "step": 10137 }, { "epoch": 0.9117238287379511, "grad_norm": 1.8036720752716064, "learning_rate": 3.981556864489504e-05, "loss": 3.1451, "step": 10168 }, { "epoch": 0.9145034745572741, "grad_norm": 1.8620129823684692, "learning_rate": 3.974783900443142e-05, "loss": 3.1732, "step": 10199 }, { "epoch": 0.9172831203765972, "grad_norm": 2.0112087726593018, "learning_rate": 3.9679942936609095e-05, "loss": 3.163, "step": 10230 }, { "epoch": 0.9200627661959202, "grad_norm": 1.8342541456222534, "learning_rate": 3.961188120762596e-05, "loss": 3.1561, "step": 10261 }, { "epoch": 0.9228424120152432, "grad_norm": 2.3467628955841064, "learning_rate": 3.954365458554938e-05, "loss": 3.1595, "step": 10292 }, { "epoch": 0.9256220578345662, "grad_norm": 1.8928585052490234, "learning_rate": 3.947526384030751e-05, "loss": 3.1701, "step": 10323 }, { "epoch": 0.9284017036538893, "grad_norm": 1.9733792543411255, "learning_rate": 3.9406709743680624e-05, "loss": 3.1957, "step": 10354 }, { "epoch": 0.9311813494732123, "grad_norm": 1.8375611305236816, "learning_rate": 3.9337993069292366e-05, "loss": 3.1562, "step": 10385 }, { "epoch": 0.9339609952925353, "grad_norm": 1.8635389804840088, "learning_rate": 3.926911459260109e-05, "loss": 3.1841, "step": 10416 }, { "epoch": 0.9367406411118583, "grad_norm": 1.8488346338272095, "learning_rate": 3.920007509089102e-05, "loss": 3.1715, "step": 10447 }, { "epoch": 0.9395202869311814, "grad_norm": 1.828251838684082, "learning_rate": 3.913087534326357e-05, "loss": 3.1825, "step": 10478 }, { "epoch": 0.9422999327505044, "grad_norm": 1.895739197731018, "learning_rate": 3.9061516130628475e-05, "loss": 3.1692, "step": 10509 }, { "epoch": 0.9450795785698274, "grad_norm": 1.8475978374481201, "learning_rate": 3.8991998235695025e-05, "loss": 3.1661, "step": 10540 }, { "epoch": 0.9478592243891504, "grad_norm": 1.9761695861816406, "learning_rate": 3.8922322442963224e-05, "loss": 3.1217, "step": 10571 }, { "epoch": 0.9506388702084735, "grad_norm": 1.8657857179641724, "learning_rate": 3.885248953871491e-05, "loss": 3.1508, "step": 10602 }, { "epoch": 0.9534185160277965, "grad_norm": 2.033208131790161, "learning_rate": 3.8782500311004915e-05, "loss": 3.1541, "step": 10633 }, { "epoch": 0.9561981618471195, "grad_norm": 1.9058306217193604, "learning_rate": 3.871235554965218e-05, "loss": 3.1583, "step": 10664 }, { "epoch": 0.9589778076664425, "grad_norm": 12.429788589477539, "learning_rate": 3.864205604623078e-05, "loss": 3.1472, "step": 10695 }, { "epoch": 0.9617574534857656, "grad_norm": 1.928039312362671, "learning_rate": 3.857160259406107e-05, "loss": 3.1632, "step": 10726 }, { "epoch": 0.9645370993050886, "grad_norm": 1.8084813356399536, "learning_rate": 3.8500995988200674e-05, "loss": 3.1645, "step": 10757 }, { "epoch": 0.9673167451244116, "grad_norm": 1.8052054643630981, "learning_rate": 3.843023702543556e-05, "loss": 3.1284, "step": 10788 }, { "epoch": 0.9700963909437346, "grad_norm": 1.9415054321289062, "learning_rate": 3.8359326504270984e-05, "loss": 3.1147, "step": 10819 }, { "epoch": 0.9728760367630576, "grad_norm": 1.9183542728424072, "learning_rate": 3.828826522492255e-05, "loss": 3.1178, "step": 10850 }, { "epoch": 0.9756556825823807, "grad_norm": 1.8961682319641113, "learning_rate": 3.821705398930713e-05, "loss": 3.1385, "step": 10881 }, { "epoch": 0.9784353284017037, "grad_norm": 1.937819480895996, "learning_rate": 3.814569360103385e-05, "loss": 3.1569, "step": 10912 }, { "epoch": 0.9812149742210267, "grad_norm": 2.237182855606079, "learning_rate": 3.807418486539499e-05, "loss": 3.1669, "step": 10943 }, { "epoch": 0.9839946200403497, "grad_norm": 1.9500761032104492, "learning_rate": 3.80025285893569e-05, "loss": 3.1556, "step": 10974 }, { "epoch": 0.9867742658596728, "grad_norm": 1.9348506927490234, "learning_rate": 3.793072558155093e-05, "loss": 3.1553, "step": 11005 }, { "epoch": 0.9895539116789958, "grad_norm": 1.8740767240524292, "learning_rate": 3.785877665226426e-05, "loss": 3.1818, "step": 11036 }, { "epoch": 0.9923335574983188, "grad_norm": 1.837488055229187, "learning_rate": 3.778668261343079e-05, "loss": 3.1655, "step": 11067 }, { "epoch": 0.9951132033176417, "grad_norm": 1.8872405290603638, "learning_rate": 3.771444427862192e-05, "loss": 3.1629, "step": 11098 }, { "epoch": 0.9978928491369649, "grad_norm": 1.7856714725494385, "learning_rate": 3.7642062463037465e-05, "loss": 3.1384, "step": 11129 }, { "epoch": 1.0006724949562877, "grad_norm": 1.9878672361373901, "learning_rate": 3.7569537983496373e-05, "loss": 3.107, "step": 11160 }, { "epoch": 1.003452140775611, "grad_norm": 1.9204086065292358, "learning_rate": 3.749687165842753e-05, "loss": 2.9639, "step": 11191 }, { "epoch": 1.006231786594934, "grad_norm": 1.9229450225830078, "learning_rate": 3.7424064307860536e-05, "loss": 2.9639, "step": 11222 }, { "epoch": 1.009011432414257, "grad_norm": 1.944447636604309, "learning_rate": 3.735111675341645e-05, "loss": 2.9491, "step": 11253 }, { "epoch": 1.01179107823358, "grad_norm": 2.0207080841064453, "learning_rate": 3.7278029818298524e-05, "loss": 2.9621, "step": 11284 }, { "epoch": 1.014570724052903, "grad_norm": 2.230640172958374, "learning_rate": 3.720480432728287e-05, "loss": 2.9564, "step": 11315 }, { "epoch": 1.017350369872226, "grad_norm": 1.8823405504226685, "learning_rate": 3.71314411067092e-05, "loss": 2.9552, "step": 11346 }, { "epoch": 1.020130015691549, "grad_norm": 1.8951125144958496, "learning_rate": 3.70579409844715e-05, "loss": 2.9475, "step": 11377 }, { "epoch": 1.022909661510872, "grad_norm": 1.9785139560699463, "learning_rate": 3.698430479000865e-05, "loss": 2.9564, "step": 11408 }, { "epoch": 1.025689307330195, "grad_norm": 1.9839940071105957, "learning_rate": 3.691053335429509e-05, "loss": 2.9541, "step": 11439 }, { "epoch": 1.0284689531495181, "grad_norm": 1.9339096546173096, "learning_rate": 3.683662750983147e-05, "loss": 2.9177, "step": 11470 }, { "epoch": 1.0312485989688411, "grad_norm": 1.984049916267395, "learning_rate": 3.676258809063518e-05, "loss": 2.9599, "step": 11501 }, { "epoch": 1.0340282447881641, "grad_norm": 1.9555659294128418, "learning_rate": 3.6688415932231004e-05, "loss": 2.9415, "step": 11532 }, { "epoch": 1.0368078906074871, "grad_norm": 2.0060806274414062, "learning_rate": 3.661411187164166e-05, "loss": 2.9804, "step": 11563 }, { "epoch": 1.0395875364268101, "grad_norm": 1.9450613260269165, "learning_rate": 3.65396767473784e-05, "loss": 2.9409, "step": 11594 }, { "epoch": 1.0423671822461331, "grad_norm": 2.0419921875, "learning_rate": 3.6465111399431465e-05, "loss": 2.9735, "step": 11625 }, { "epoch": 1.0451468280654561, "grad_norm": 2.0117428302764893, "learning_rate": 3.6390416669260674e-05, "loss": 2.9655, "step": 11656 }, { "epoch": 1.047926473884779, "grad_norm": 2.0134499073028564, "learning_rate": 3.63155933997859e-05, "loss": 2.9225, "step": 11687 }, { "epoch": 1.0507061197041023, "grad_norm": 1.96694016456604, "learning_rate": 3.624064243537758e-05, "loss": 2.9609, "step": 11718 }, { "epoch": 1.0534857655234253, "grad_norm": 1.929091453552246, "learning_rate": 3.616556462184716e-05, "loss": 2.9189, "step": 11749 }, { "epoch": 1.0562654113427483, "grad_norm": 1.9514384269714355, "learning_rate": 3.609036080643755e-05, "loss": 2.9447, "step": 11780 }, { "epoch": 1.0590450571620713, "grad_norm": 1.9550822973251343, "learning_rate": 3.60150318378136e-05, "loss": 2.9315, "step": 11811 }, { "epoch": 1.0618247029813943, "grad_norm": 1.9250727891921997, "learning_rate": 3.5939578566052465e-05, "loss": 2.9483, "step": 11842 }, { "epoch": 1.0646043488007173, "grad_norm": 2.0025384426116943, "learning_rate": 3.586400184263408e-05, "loss": 2.9102, "step": 11873 }, { "epoch": 1.0673839946200403, "grad_norm": 1.95062255859375, "learning_rate": 3.578830252043148e-05, "loss": 2.9166, "step": 11904 }, { "epoch": 1.0701636404393633, "grad_norm": 1.9655905961990356, "learning_rate": 3.571248145370125e-05, "loss": 2.9251, "step": 11935 }, { "epoch": 1.0729432862586863, "grad_norm": 1.8943630456924438, "learning_rate": 3.5636539498073794e-05, "loss": 2.9817, "step": 11966 }, { "epoch": 1.0757229320780095, "grad_norm": 2.025667905807495, "learning_rate": 3.556047751054378e-05, "loss": 2.9599, "step": 11997 }, { "epoch": 1.0785025778973325, "grad_norm": 1.9214924573898315, "learning_rate": 3.548429634946039e-05, "loss": 2.9434, "step": 12028 }, { "epoch": 1.0812822237166555, "grad_norm": 1.9672141075134277, "learning_rate": 3.540799687451768e-05, "loss": 2.9244, "step": 12059 }, { "epoch": 1.0840618695359785, "grad_norm": 2.0361907482147217, "learning_rate": 3.533157994674485e-05, "loss": 2.9728, "step": 12090 }, { "epoch": 1.0868415153553015, "grad_norm": 2.1192681789398193, "learning_rate": 3.5255046428496546e-05, "loss": 2.9137, "step": 12121 }, { "epoch": 1.0896211611746245, "grad_norm": 1.8768310546875, "learning_rate": 3.517839718344311e-05, "loss": 2.9491, "step": 12152 }, { "epoch": 1.0924008069939475, "grad_norm": 1.8967385292053223, "learning_rate": 3.510163307656086e-05, "loss": 2.9351, "step": 12183 }, { "epoch": 1.0951804528132705, "grad_norm": 1.9647105932235718, "learning_rate": 3.5024754974122324e-05, "loss": 2.9505, "step": 12214 }, { "epoch": 1.0979600986325937, "grad_norm": 1.902198076248169, "learning_rate": 3.494776374368643e-05, "loss": 2.8994, "step": 12245 }, { "epoch": 1.1007397444519167, "grad_norm": 1.930614709854126, "learning_rate": 3.4870660254088724e-05, "loss": 2.9536, "step": 12276 }, { "epoch": 1.1035193902712397, "grad_norm": 1.955419898033142, "learning_rate": 3.479344537543164e-05, "loss": 2.9369, "step": 12307 }, { "epoch": 1.1062990360905627, "grad_norm": 1.9790080785751343, "learning_rate": 3.4716119979074565e-05, "loss": 2.9629, "step": 12338 }, { "epoch": 1.1090786819098857, "grad_norm": 2.02301025390625, "learning_rate": 3.463868493762412e-05, "loss": 2.9438, "step": 12369 }, { "epoch": 1.1118583277292087, "grad_norm": 1.8974666595458984, "learning_rate": 3.456114112492418e-05, "loss": 2.9653, "step": 12400 }, { "epoch": 1.1146379735485317, "grad_norm": 2.0910682678222656, "learning_rate": 3.4483489416046164e-05, "loss": 2.9659, "step": 12431 }, { "epoch": 1.1174176193678547, "grad_norm": 2.0032594203948975, "learning_rate": 3.440573068727905e-05, "loss": 2.928, "step": 12462 }, { "epoch": 1.1201972651871777, "grad_norm": 2.1574766635894775, "learning_rate": 3.4327865816119495e-05, "loss": 2.9336, "step": 12493 }, { "epoch": 1.1229769110065009, "grad_norm": 1.9993735551834106, "learning_rate": 3.4249895681262025e-05, "loss": 2.917, "step": 12524 }, { "epoch": 1.1257565568258239, "grad_norm": 1.946427822113037, "learning_rate": 3.417182116258899e-05, "loss": 2.9023, "step": 12555 }, { "epoch": 1.1285362026451469, "grad_norm": 1.9485125541687012, "learning_rate": 3.409364314116074e-05, "loss": 2.9553, "step": 12586 }, { "epoch": 1.1313158484644699, "grad_norm": 2.0353407859802246, "learning_rate": 3.401536249920559e-05, "loss": 2.9402, "step": 12617 }, { "epoch": 1.1340954942837929, "grad_norm": 2.0576653480529785, "learning_rate": 3.393698012010998e-05, "loss": 2.9421, "step": 12648 }, { "epoch": 1.1368751401031159, "grad_norm": 1.9606209993362427, "learning_rate": 3.385849688840839e-05, "loss": 2.9613, "step": 12679 }, { "epoch": 1.1396547859224389, "grad_norm": 1.9826381206512451, "learning_rate": 3.3779913689773414e-05, "loss": 2.9301, "step": 12710 }, { "epoch": 1.1424344317417618, "grad_norm": 1.9487073421478271, "learning_rate": 3.370123141100578e-05, "loss": 2.9691, "step": 12741 }, { "epoch": 1.1452140775610848, "grad_norm": 2.0785021781921387, "learning_rate": 3.3622450940024305e-05, "loss": 2.9394, "step": 12772 }, { "epoch": 1.147993723380408, "grad_norm": 1.9334497451782227, "learning_rate": 3.35435731658559e-05, "loss": 2.922, "step": 12803 }, { "epoch": 1.150773369199731, "grad_norm": 2.0320358276367188, "learning_rate": 3.346459897862552e-05, "loss": 2.929, "step": 12834 }, { "epoch": 1.153553015019054, "grad_norm": 2.089158535003662, "learning_rate": 3.338552926954613e-05, "loss": 2.9489, "step": 12865 }, { "epoch": 1.156332660838377, "grad_norm": 1.8891345262527466, "learning_rate": 3.330636493090868e-05, "loss": 2.9368, "step": 12896 }, { "epoch": 1.1591123066577, "grad_norm": 1.978514313697815, "learning_rate": 3.322710685607193e-05, "loss": 2.9454, "step": 12927 }, { "epoch": 1.161891952477023, "grad_norm": 1.9743033647537231, "learning_rate": 3.314775593945251e-05, "loss": 2.918, "step": 12958 }, { "epoch": 1.164671598296346, "grad_norm": 1.9501724243164062, "learning_rate": 3.3068313076514714e-05, "loss": 2.9332, "step": 12989 }, { "epoch": 1.1674512441156693, "grad_norm": 1.9802473783493042, "learning_rate": 3.298877916376047e-05, "loss": 2.9643, "step": 13020 }, { "epoch": 1.1702308899349922, "grad_norm": 2.1636433601379395, "learning_rate": 3.290915509871915e-05, "loss": 2.9412, "step": 13051 }, { "epoch": 1.1730105357543152, "grad_norm": 1.9422581195831299, "learning_rate": 3.282944177993753e-05, "loss": 2.9529, "step": 13082 }, { "epoch": 1.1757901815736382, "grad_norm": 1.9173604249954224, "learning_rate": 3.274964010696957e-05, "loss": 2.9203, "step": 13113 }, { "epoch": 1.1785698273929612, "grad_norm": 1.9598551988601685, "learning_rate": 3.266975098036629e-05, "loss": 2.9352, "step": 13144 }, { "epoch": 1.1813494732122842, "grad_norm": 2.061182975769043, "learning_rate": 3.258977530166562e-05, "loss": 2.9321, "step": 13175 }, { "epoch": 1.1841291190316072, "grad_norm": 1.9192544221878052, "learning_rate": 3.250971397338227e-05, "loss": 2.8922, "step": 13206 }, { "epoch": 1.1869087648509302, "grad_norm": 1.93052339553833, "learning_rate": 3.2429567898997404e-05, "loss": 2.9131, "step": 13237 }, { "epoch": 1.1896884106702532, "grad_norm": 2.030632734298706, "learning_rate": 3.234933798294859e-05, "loss": 2.9486, "step": 13268 }, { "epoch": 1.1924680564895764, "grad_norm": 1.9135621786117554, "learning_rate": 3.2269025130619535e-05, "loss": 2.9352, "step": 13299 }, { "epoch": 1.1952477023088994, "grad_norm": 1.8833742141723633, "learning_rate": 3.218863024832985e-05, "loss": 2.9311, "step": 13330 }, { "epoch": 1.1980273481282224, "grad_norm": 1.9402114152908325, "learning_rate": 3.2108154243324864e-05, "loss": 2.9479, "step": 13361 }, { "epoch": 1.2008069939475454, "grad_norm": 2.003957509994507, "learning_rate": 3.2027598023765345e-05, "loss": 2.9194, "step": 13392 }, { "epoch": 1.2035866397668684, "grad_norm": 2.00201416015625, "learning_rate": 3.194696249871729e-05, "loss": 2.9315, "step": 13423 }, { "epoch": 1.2063662855861914, "grad_norm": 1.996684193611145, "learning_rate": 3.186624857814164e-05, "loss": 2.9418, "step": 13454 }, { "epoch": 1.2091459314055144, "grad_norm": 2.089789628982544, "learning_rate": 3.178545717288401e-05, "loss": 2.9315, "step": 13485 }, { "epoch": 1.2119255772248374, "grad_norm": 1.8793665170669556, "learning_rate": 3.170458919466444e-05, "loss": 2.926, "step": 13516 }, { "epoch": 1.2147052230441604, "grad_norm": 2.1354544162750244, "learning_rate": 3.1623645556067063e-05, "loss": 2.9212, "step": 13547 }, { "epoch": 1.2174848688634836, "grad_norm": 2.031564950942993, "learning_rate": 3.154262717052985e-05, "loss": 2.9156, "step": 13578 }, { "epoch": 1.2202645146828066, "grad_norm": 1.9664191007614136, "learning_rate": 3.146153495233426e-05, "loss": 2.9165, "step": 13609 }, { "epoch": 1.2230441605021296, "grad_norm": 1.9077311754226685, "learning_rate": 3.1380369816594944e-05, "loss": 2.9243, "step": 13640 }, { "epoch": 1.2258238063214526, "grad_norm": 2.0613224506378174, "learning_rate": 3.129913267924946e-05, "loss": 2.9397, "step": 13671 }, { "epoch": 1.2286034521407756, "grad_norm": 1.9298268556594849, "learning_rate": 3.121782445704782e-05, "loss": 2.8912, "step": 13702 }, { "epoch": 1.2313830979600986, "grad_norm": 1.9356482028961182, "learning_rate": 3.11364460675423e-05, "loss": 2.9502, "step": 13733 }, { "epoch": 1.2341627437794216, "grad_norm": 2.0454516410827637, "learning_rate": 3.1054998429076934e-05, "loss": 2.9337, "step": 13764 }, { "epoch": 1.2369423895987446, "grad_norm": 1.947540283203125, "learning_rate": 3.097348246077728e-05, "loss": 2.9286, "step": 13795 }, { "epoch": 1.2397220354180676, "grad_norm": 1.9849016666412354, "learning_rate": 3.0891899082539924e-05, "loss": 2.9462, "step": 13826 }, { "epoch": 1.2425016812373908, "grad_norm": 1.9809448719024658, "learning_rate": 3.0810249215022233e-05, "loss": 2.9319, "step": 13857 }, { "epoch": 1.2452813270567138, "grad_norm": 1.9004404544830322, "learning_rate": 3.0728533779631865e-05, "loss": 2.9222, "step": 13888 }, { "epoch": 1.2480609728760368, "grad_norm": 2.0778489112854004, "learning_rate": 3.064675369851637e-05, "loss": 2.9352, "step": 13919 }, { "epoch": 1.2508406186953598, "grad_norm": 2.0006306171417236, "learning_rate": 3.056490989455289e-05, "loss": 2.9176, "step": 13950 }, { "epoch": 1.2536202645146828, "grad_norm": 2.164907217025757, "learning_rate": 3.0483003291337596e-05, "loss": 2.904, "step": 13981 }, { "epoch": 1.2563999103340058, "grad_norm": 1.9432871341705322, "learning_rate": 3.040103481317539e-05, "loss": 2.9387, "step": 14012 }, { "epoch": 1.2591795561533288, "grad_norm": 2.0023536682128906, "learning_rate": 3.03190053850694e-05, "loss": 2.9053, "step": 14043 }, { "epoch": 1.261959201972652, "grad_norm": 1.9094126224517822, "learning_rate": 3.0236915932710573e-05, "loss": 2.9342, "step": 14074 }, { "epoch": 1.2647388477919748, "grad_norm": 2.038862466812134, "learning_rate": 3.0154767382467232e-05, "loss": 2.9419, "step": 14105 }, { "epoch": 1.267518493611298, "grad_norm": 1.9701634645462036, "learning_rate": 3.0072560661374582e-05, "loss": 2.939, "step": 14136 }, { "epoch": 1.270298139430621, "grad_norm": 2.041240692138672, "learning_rate": 2.999029669712431e-05, "loss": 2.9024, "step": 14167 }, { "epoch": 1.273077785249944, "grad_norm": 1.8705273866653442, "learning_rate": 2.990797641805408e-05, "loss": 2.9491, "step": 14198 }, { "epoch": 1.275857431069267, "grad_norm": 1.8689632415771484, "learning_rate": 2.982560075313704e-05, "loss": 2.9109, "step": 14229 }, { "epoch": 1.27863707688859, "grad_norm": 1.901034951210022, "learning_rate": 2.9743170631971368e-05, "loss": 2.9159, "step": 14260 }, { "epoch": 1.281416722707913, "grad_norm": 1.9830548763275146, "learning_rate": 2.9660686984769792e-05, "loss": 2.9175, "step": 14291 }, { "epoch": 1.284196368527236, "grad_norm": 1.9754098653793335, "learning_rate": 2.9578150742349047e-05, "loss": 2.9495, "step": 14322 }, { "epoch": 1.2869760143465592, "grad_norm": 1.8658026456832886, "learning_rate": 2.949556283611942e-05, "loss": 2.9543, "step": 14353 }, { "epoch": 1.2897556601658822, "grad_norm": 1.9385013580322266, "learning_rate": 2.9412924198074206e-05, "loss": 2.9235, "step": 14384 }, { "epoch": 1.2925353059852052, "grad_norm": 1.94545316696167, "learning_rate": 2.9330235760779208e-05, "loss": 2.9281, "step": 14415 }, { "epoch": 1.2953149518045282, "grad_norm": 1.9916470050811768, "learning_rate": 2.9247498457362188e-05, "loss": 2.9382, "step": 14446 }, { "epoch": 1.2980945976238512, "grad_norm": 1.9545270204544067, "learning_rate": 2.9164713221502373e-05, "loss": 2.9397, "step": 14477 }, { "epoch": 1.3008742434431741, "grad_norm": 1.945106029510498, "learning_rate": 2.9081880987419912e-05, "loss": 2.9453, "step": 14508 }, { "epoch": 1.3036538892624971, "grad_norm": 1.961753010749817, "learning_rate": 2.8999002689865296e-05, "loss": 2.9255, "step": 14539 }, { "epoch": 1.3064335350818201, "grad_norm": 1.9291094541549683, "learning_rate": 2.8916079264108852e-05, "loss": 2.9054, "step": 14570 }, { "epoch": 1.3092131809011431, "grad_norm": 1.9437432289123535, "learning_rate": 2.883311164593017e-05, "loss": 2.9095, "step": 14601 }, { "epoch": 1.3119928267204664, "grad_norm": 1.9449868202209473, "learning_rate": 2.875010077160754e-05, "loss": 2.929, "step": 14632 }, { "epoch": 1.3147724725397893, "grad_norm": 1.8561278581619263, "learning_rate": 2.866704757790741e-05, "loss": 2.9131, "step": 14663 }, { "epoch": 1.3175521183591123, "grad_norm": 2.0299785137176514, "learning_rate": 2.858395300207376e-05, "loss": 2.9359, "step": 14694 }, { "epoch": 1.3203317641784353, "grad_norm": 1.9579997062683105, "learning_rate": 2.8500817981817607e-05, "loss": 2.9344, "step": 14725 }, { "epoch": 1.3231114099977583, "grad_norm": 1.9907282590866089, "learning_rate": 2.8417643455306336e-05, "loss": 2.9267, "step": 14756 }, { "epoch": 1.3258910558170813, "grad_norm": 2.115506172180176, "learning_rate": 2.8334430361153185e-05, "loss": 2.93, "step": 14787 }, { "epoch": 1.3286707016364043, "grad_norm": 1.935970425605774, "learning_rate": 2.8251179638406612e-05, "loss": 2.9119, "step": 14818 }, { "epoch": 1.3314503474557275, "grad_norm": 1.9706645011901855, "learning_rate": 2.8167892226539704e-05, "loss": 2.9245, "step": 14849 }, { "epoch": 1.3342299932750503, "grad_norm": 2.091217279434204, "learning_rate": 2.8084569065439588e-05, "loss": 2.8958, "step": 14880 }, { "epoch": 1.3370096390943735, "grad_norm": 1.9113187789916992, "learning_rate": 2.8001211095396807e-05, "loss": 2.8936, "step": 14911 }, { "epoch": 1.3397892849136965, "grad_norm": 1.9416507482528687, "learning_rate": 2.791781925709473e-05, "loss": 2.9198, "step": 14942 }, { "epoch": 1.3425689307330195, "grad_norm": 1.911167860031128, "learning_rate": 2.7834394491598908e-05, "loss": 2.9352, "step": 14973 }, { "epoch": 1.3453485765523425, "grad_norm": 1.8569062948226929, "learning_rate": 2.7750937740346485e-05, "loss": 2.8868, "step": 15004 }, { "epoch": 1.3481282223716655, "grad_norm": 1.9254045486450195, "learning_rate": 2.7667449945135564e-05, "loss": 2.906, "step": 15035 }, { "epoch": 1.3509078681909885, "grad_norm": 1.9615710973739624, "learning_rate": 2.7583932048114557e-05, "loss": 2.9148, "step": 15066 }, { "epoch": 1.3536875140103115, "grad_norm": 2.1133556365966797, "learning_rate": 2.7500384991771587e-05, "loss": 2.8988, "step": 15097 }, { "epoch": 1.3564671598296347, "grad_norm": 1.9478425979614258, "learning_rate": 2.7416809718923825e-05, "loss": 2.9332, "step": 15128 }, { "epoch": 1.3592468056489575, "grad_norm": 2.005472183227539, "learning_rate": 2.7333207172706864e-05, "loss": 2.9305, "step": 15159 }, { "epoch": 1.3620264514682807, "grad_norm": 1.9226336479187012, "learning_rate": 2.7249578296564088e-05, "loss": 2.9176, "step": 15190 }, { "epoch": 1.3648060972876037, "grad_norm": 1.9458688497543335, "learning_rate": 2.7165924034235973e-05, "loss": 2.8914, "step": 15221 }, { "epoch": 1.3675857431069267, "grad_norm": 1.930293083190918, "learning_rate": 2.708224532974953e-05, "loss": 2.9399, "step": 15252 } ], "logging_steps": 31, "max_steps": 30517, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 3052, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.1319563003407368e+19, "train_batch_size": 8, "trial_name": null, "trial_params": null }