{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.19115141797775329, "eval_steps": 500, "global_step": 7630, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.000776630924942379, "grad_norm": 19.31844711303711, "learning_rate": 1.0157273918741808e-06, "loss": 8.0914, "step": 31 }, { "epoch": 0.001553261849884758, "grad_norm": 15.708772659301758, "learning_rate": 2.0314547837483616e-06, "loss": 7.0861, "step": 62 }, { "epoch": 0.002329892774827137, "grad_norm": 10.70508861541748, "learning_rate": 3.0471821756225426e-06, "loss": 5.7478, "step": 93 }, { "epoch": 0.003106523699769516, "grad_norm": 4.4315900802612305, "learning_rate": 4.062909567496723e-06, "loss": 4.763, "step": 124 }, { "epoch": 0.003883154624711895, "grad_norm": 5.228023052215576, "learning_rate": 5.078636959370905e-06, "loss": 4.1438, "step": 155 }, { "epoch": 0.004659785549654274, "grad_norm": 4.417849540710449, "learning_rate": 6.094364351245085e-06, "loss": 3.8013, "step": 186 }, { "epoch": 0.005436416474596653, "grad_norm": 6.3335280418396, "learning_rate": 7.110091743119267e-06, "loss": 3.6086, "step": 217 }, { "epoch": 0.006213047399539032, "grad_norm": 6.3932647705078125, "learning_rate": 8.125819134993446e-06, "loss": 3.4676, "step": 248 }, { "epoch": 0.006989678324481411, "grad_norm": 6.310016632080078, "learning_rate": 9.141546526867629e-06, "loss": 3.3426, "step": 279 }, { "epoch": 0.00776630924942379, "grad_norm": 4.848681449890137, "learning_rate": 1.015727391874181e-05, "loss": 3.2305, "step": 310 }, { "epoch": 0.00854294017436617, "grad_norm": 7.16106653213501, "learning_rate": 1.117300131061599e-05, "loss": 3.1615, "step": 341 }, { "epoch": 0.009319571099308548, "grad_norm": 4.73142671585083, "learning_rate": 1.218872870249017e-05, "loss": 3.0865, "step": 372 }, { "epoch": 0.010096202024250926, "grad_norm": 4.504674911499023, "learning_rate": 1.3204456094364351e-05, "loss": 3.035, "step": 403 }, { "epoch": 0.010872832949193306, "grad_norm": 4.620588779449463, "learning_rate": 1.4220183486238533e-05, "loss": 2.932, "step": 434 }, { "epoch": 0.011649463874135685, "grad_norm": 4.8418965339660645, "learning_rate": 1.5235910878112714e-05, "loss": 2.8965, "step": 465 }, { "epoch": 0.012426094799078065, "grad_norm": 4.36681604385376, "learning_rate": 1.6251638269986893e-05, "loss": 2.8569, "step": 496 }, { "epoch": 0.013202725724020443, "grad_norm": 4.929416179656982, "learning_rate": 1.7267365661861077e-05, "loss": 2.8155, "step": 527 }, { "epoch": 0.013979356648962823, "grad_norm": 4.269941806793213, "learning_rate": 1.8283093053735257e-05, "loss": 2.7682, "step": 558 }, { "epoch": 0.014755987573905201, "grad_norm": 4.4052534103393555, "learning_rate": 1.9298820445609438e-05, "loss": 2.7076, "step": 589 }, { "epoch": 0.01553261849884758, "grad_norm": 4.1759843826293945, "learning_rate": 2.031454783748362e-05, "loss": 2.7143, "step": 620 }, { "epoch": 0.01630924942378996, "grad_norm": 3.320908546447754, "learning_rate": 2.13302752293578e-05, "loss": 2.6696, "step": 651 }, { "epoch": 0.01708588034873234, "grad_norm": 3.201021194458008, "learning_rate": 2.234600262123198e-05, "loss": 2.6321, "step": 682 }, { "epoch": 0.017862511273674716, "grad_norm": 3.675868272781372, "learning_rate": 2.336173001310616e-05, "loss": 2.6029, "step": 713 }, { "epoch": 0.018639142198617096, "grad_norm": 3.0218663215637207, "learning_rate": 2.437745740498034e-05, "loss": 2.5883, "step": 744 }, { "epoch": 0.019415773123559476, "grad_norm": 3.260049343109131, "learning_rate": 2.5393184796854525e-05, "loss": 2.5625, "step": 775 }, { "epoch": 0.020192404048501852, "grad_norm": 3.212430000305176, "learning_rate": 2.6408912188728702e-05, "loss": 2.5631, "step": 806 }, { "epoch": 0.020969034973444232, "grad_norm": 2.770608901977539, "learning_rate": 2.7424639580602886e-05, "loss": 2.5256, "step": 837 }, { "epoch": 0.021745665898386612, "grad_norm": 2.8963048458099365, "learning_rate": 2.8440366972477066e-05, "loss": 2.5202, "step": 868 }, { "epoch": 0.022522296823328992, "grad_norm": 2.7916104793548584, "learning_rate": 2.9456094364351244e-05, "loss": 2.476, "step": 899 }, { "epoch": 0.02329892774827137, "grad_norm": 2.6866674423217773, "learning_rate": 3.0471821756225428e-05, "loss": 2.4706, "step": 930 }, { "epoch": 0.02407555867321375, "grad_norm": 2.606696605682373, "learning_rate": 3.148754914809961e-05, "loss": 2.4627, "step": 961 }, { "epoch": 0.02485218959815613, "grad_norm": 2.7148895263671875, "learning_rate": 3.2503276539973785e-05, "loss": 2.4254, "step": 992 }, { "epoch": 0.025628820523098506, "grad_norm": 2.5046658515930176, "learning_rate": 3.351900393184797e-05, "loss": 2.4078, "step": 1023 }, { "epoch": 0.026405451448040886, "grad_norm": 2.4350714683532715, "learning_rate": 3.453473132372215e-05, "loss": 2.3691, "step": 1054 }, { "epoch": 0.027182082372983266, "grad_norm": 2.339318037033081, "learning_rate": 3.555045871559633e-05, "loss": 2.3795, "step": 1085 }, { "epoch": 0.027958713297925646, "grad_norm": 3.8952598571777344, "learning_rate": 3.6566186107470514e-05, "loss": 2.3635, "step": 1116 }, { "epoch": 0.028735344222868022, "grad_norm": 2.1903908252716064, "learning_rate": 3.7581913499344695e-05, "loss": 2.3589, "step": 1147 }, { "epoch": 0.029511975147810402, "grad_norm": 5.00233793258667, "learning_rate": 3.8597640891218876e-05, "loss": 2.3063, "step": 1178 }, { "epoch": 0.030288606072752782, "grad_norm": 4.72776460647583, "learning_rate": 3.9613368283093056e-05, "loss": 2.3281, "step": 1209 }, { "epoch": 0.03106523699769516, "grad_norm": 2.184804916381836, "learning_rate": 4.062909567496724e-05, "loss": 2.2672, "step": 1240 }, { "epoch": 0.03184186792263754, "grad_norm": 2.3042352199554443, "learning_rate": 4.164482306684142e-05, "loss": 2.2846, "step": 1271 }, { "epoch": 0.03261849884757992, "grad_norm": 2.271709442138672, "learning_rate": 4.26605504587156e-05, "loss": 2.2655, "step": 1302 }, { "epoch": 0.0333951297725223, "grad_norm": 2.3952088356018066, "learning_rate": 4.367627785058978e-05, "loss": 2.2523, "step": 1333 }, { "epoch": 0.03417176069746468, "grad_norm": 2.034968614578247, "learning_rate": 4.469200524246396e-05, "loss": 2.2543, "step": 1364 }, { "epoch": 0.03494839162240705, "grad_norm": 2.070462942123413, "learning_rate": 4.570773263433814e-05, "loss": 2.233, "step": 1395 }, { "epoch": 0.03572502254734943, "grad_norm": 2.1028084754943848, "learning_rate": 4.672346002621232e-05, "loss": 2.2411, "step": 1426 }, { "epoch": 0.03650165347229181, "grad_norm": 1.983056902885437, "learning_rate": 4.77391874180865e-05, "loss": 2.2273, "step": 1457 }, { "epoch": 0.03727828439723419, "grad_norm": 1.9587653875350952, "learning_rate": 4.875491480996068e-05, "loss": 2.2128, "step": 1488 }, { "epoch": 0.03805491532217657, "grad_norm": 1.8616324663162231, "learning_rate": 4.977064220183487e-05, "loss": 2.2045, "step": 1519 }, { "epoch": 0.03883154624711895, "grad_norm": 2.7953391075134277, "learning_rate": 4.9999915451558777e-05, "loss": 2.1679, "step": 1550 }, { "epoch": 0.03960817717206133, "grad_norm": 1.8601350784301758, "learning_rate": 4.999955597496219e-05, "loss": 2.1936, "step": 1581 }, { "epoch": 0.040384808097003705, "grad_norm": 1.7780190706253052, "learning_rate": 4.9998914381774255e-05, "loss": 2.1935, "step": 1612 }, { "epoch": 0.041161439021946085, "grad_norm": 1.6555310487747192, "learning_rate": 4.999799067923527e-05, "loss": 2.1441, "step": 1643 }, { "epoch": 0.041938069946888465, "grad_norm": 3.3240256309509277, "learning_rate": 4.999678487776908e-05, "loss": 2.1462, "step": 1674 }, { "epoch": 0.042714700871830845, "grad_norm": 1.7667723894119263, "learning_rate": 4.9995296990983006e-05, "loss": 2.1364, "step": 1705 }, { "epoch": 0.043491331796773225, "grad_norm": 2.1140077114105225, "learning_rate": 4.999352703566763e-05, "loss": 2.1486, "step": 1736 }, { "epoch": 0.044267962721715605, "grad_norm": 1.6703864336013794, "learning_rate": 4.999147503179668e-05, "loss": 2.1454, "step": 1767 }, { "epoch": 0.045044593646657985, "grad_norm": 1.7508599758148193, "learning_rate": 4.998914100252672e-05, "loss": 2.132, "step": 1798 }, { "epoch": 0.04582122457160036, "grad_norm": 1.6556063890457153, "learning_rate": 4.998652497419696e-05, "loss": 2.1009, "step": 1829 }, { "epoch": 0.04659785549654274, "grad_norm": 2.0815255641937256, "learning_rate": 4.9983626976328927e-05, "loss": 2.0912, "step": 1860 }, { "epoch": 0.04737448642148512, "grad_norm": 1.6446202993392944, "learning_rate": 4.998044704162613e-05, "loss": 2.0768, "step": 1891 }, { "epoch": 0.0481511173464275, "grad_norm": 1.5588979721069336, "learning_rate": 4.9976985205973705e-05, "loss": 2.1137, "step": 1922 }, { "epoch": 0.04892774827136988, "grad_norm": 2.4484736919403076, "learning_rate": 4.997324150843799e-05, "loss": 2.0816, "step": 1953 }, { "epoch": 0.04970437919631226, "grad_norm": 1.626017451286316, "learning_rate": 4.99692159912661e-05, "loss": 2.0697, "step": 1984 }, { "epoch": 0.05048101012125464, "grad_norm": 1.5020952224731445, "learning_rate": 4.996490869988546e-05, "loss": 2.0623, "step": 2015 }, { "epoch": 0.05125764104619701, "grad_norm": 1.5254911184310913, "learning_rate": 4.996031968290326e-05, "loss": 2.0614, "step": 2046 }, { "epoch": 0.05203427197113939, "grad_norm": 7.960453987121582, "learning_rate": 4.995544899210594e-05, "loss": 2.052, "step": 2077 }, { "epoch": 0.05281090289608177, "grad_norm": 1.4704298973083496, "learning_rate": 4.9950296682458583e-05, "loss": 2.0536, "step": 2108 }, { "epoch": 0.05358753382102415, "grad_norm": 1.520493984222412, "learning_rate": 4.994486281210429e-05, "loss": 2.0365, "step": 2139 }, { "epoch": 0.05436416474596653, "grad_norm": 1.558133602142334, "learning_rate": 4.9939147442363566e-05, "loss": 2.0203, "step": 2170 }, { "epoch": 0.05514079567090891, "grad_norm": 1.4657914638519287, "learning_rate": 4.9933150637733574e-05, "loss": 2.0153, "step": 2201 }, { "epoch": 0.05591742659585129, "grad_norm": 1.4615249633789062, "learning_rate": 4.992687246588743e-05, "loss": 1.998, "step": 2232 }, { "epoch": 0.056694057520793664, "grad_norm": 1.5175402164459229, "learning_rate": 4.992031299767347e-05, "loss": 1.9849, "step": 2263 }, { "epoch": 0.057470688445736044, "grad_norm": 1.4774690866470337, "learning_rate": 4.9913472307114386e-05, "loss": 2.0004, "step": 2294 }, { "epoch": 0.058247319370678424, "grad_norm": 1.4400330781936646, "learning_rate": 4.9906350471406446e-05, "loss": 1.997, "step": 2325 }, { "epoch": 0.059023950295620804, "grad_norm": 1.4439043998718262, "learning_rate": 4.989894757091861e-05, "loss": 2.0006, "step": 2356 }, { "epoch": 0.059800581220563184, "grad_norm": 1.4139447212219238, "learning_rate": 4.989126368919158e-05, "loss": 1.9874, "step": 2387 }, { "epoch": 0.060577212145505564, "grad_norm": 1.501980185508728, "learning_rate": 4.988329891293693e-05, "loss": 1.9996, "step": 2418 }, { "epoch": 0.06135384307044794, "grad_norm": 1.4147136211395264, "learning_rate": 4.987505333203608e-05, "loss": 2.011, "step": 2449 }, { "epoch": 0.06213047399539032, "grad_norm": 1.8178402185440063, "learning_rate": 4.9866527039539276e-05, "loss": 1.9716, "step": 2480 }, { "epoch": 0.0629071049203327, "grad_norm": 1.3381493091583252, "learning_rate": 4.9857720131664594e-05, "loss": 1.9703, "step": 2511 }, { "epoch": 0.06368373584527508, "grad_norm": 1.4357298612594604, "learning_rate": 4.9848632707796773e-05, "loss": 1.9866, "step": 2542 }, { "epoch": 0.06446036677021745, "grad_norm": 1.3444238901138306, "learning_rate": 4.9839264870486155e-05, "loss": 1.9693, "step": 2573 }, { "epoch": 0.06523699769515984, "grad_norm": 1.3933724164962769, "learning_rate": 4.9829616725447526e-05, "loss": 1.9557, "step": 2604 }, { "epoch": 0.06601362862010221, "grad_norm": 28.06955337524414, "learning_rate": 4.981968838155888e-05, "loss": 1.9641, "step": 2635 }, { "epoch": 0.0667902595450446, "grad_norm": 1.4004745483398438, "learning_rate": 4.980947995086024e-05, "loss": 1.979, "step": 2666 }, { "epoch": 0.06756689046998697, "grad_norm": 2.8693289756774902, "learning_rate": 4.979899154855234e-05, "loss": 1.9526, "step": 2697 }, { "epoch": 0.06834352139492936, "grad_norm": 1.7132235765457153, "learning_rate": 4.9788223292995386e-05, "loss": 1.9425, "step": 2728 }, { "epoch": 0.06912015231987173, "grad_norm": 1.3773481845855713, "learning_rate": 4.977717530570768e-05, "loss": 1.9852, "step": 2759 }, { "epoch": 0.0698967832448141, "grad_norm": 1.337936282157898, "learning_rate": 4.976584771136425e-05, "loss": 1.9758, "step": 2790 }, { "epoch": 0.07067341416975649, "grad_norm": 1.4963557720184326, "learning_rate": 4.975424063779547e-05, "loss": 1.9753, "step": 2821 }, { "epoch": 0.07145004509469886, "grad_norm": 1.324593186378479, "learning_rate": 4.974235421598557e-05, "loss": 1.9486, "step": 2852 }, { "epoch": 0.07222667601964125, "grad_norm": 2.7807044982910156, "learning_rate": 4.973018858007122e-05, "loss": 1.9234, "step": 2883 }, { "epoch": 0.07300330694458362, "grad_norm": 9.35367488861084, "learning_rate": 4.9717743867339963e-05, "loss": 1.9714, "step": 2914 }, { "epoch": 0.07377993786952601, "grad_norm": 7.89553689956665, "learning_rate": 4.9705020218228695e-05, "loss": 1.9319, "step": 2945 }, { "epoch": 0.07455656879446838, "grad_norm": 1.3350094556808472, "learning_rate": 4.969201777632205e-05, "loss": 1.9251, "step": 2976 }, { "epoch": 0.07533319971941076, "grad_norm": 1.3224897384643555, "learning_rate": 4.9678736688350846e-05, "loss": 1.9306, "step": 3007 }, { "epoch": 0.07610983064435314, "grad_norm": 1.2839077711105347, "learning_rate": 4.966517710419033e-05, "loss": 1.9446, "step": 3038 }, { "epoch": 0.07688646156929552, "grad_norm": 1.283780574798584, "learning_rate": 4.965133917685858e-05, "loss": 1.923, "step": 3069 }, { "epoch": 0.0776630924942379, "grad_norm": 4.104744911193848, "learning_rate": 4.9637223062514714e-05, "loss": 1.9272, "step": 3100 }, { "epoch": 0.07843972341918028, "grad_norm": 1.2491049766540527, "learning_rate": 4.962282892045718e-05, "loss": 1.9283, "step": 3131 }, { "epoch": 0.07921635434412266, "grad_norm": 1.3095839023590088, "learning_rate": 4.9608156913121904e-05, "loss": 1.909, "step": 3162 }, { "epoch": 0.07999298526906504, "grad_norm": 1.4149360656738281, "learning_rate": 4.959320720608049e-05, "loss": 1.9218, "step": 3193 }, { "epoch": 0.08076961619400741, "grad_norm": 1.295985460281372, "learning_rate": 4.9577979968038354e-05, "loss": 1.9058, "step": 3224 }, { "epoch": 0.0815462471189498, "grad_norm": 1.2115492820739746, "learning_rate": 4.956247537083282e-05, "loss": 1.9217, "step": 3255 }, { "epoch": 0.08232287804389217, "grad_norm": 1.199232578277588, "learning_rate": 4.9546693589431145e-05, "loss": 1.9132, "step": 3286 }, { "epoch": 0.08309950896883456, "grad_norm": 1.291377305984497, "learning_rate": 4.9530634801928595e-05, "loss": 1.9157, "step": 3317 }, { "epoch": 0.08387613989377693, "grad_norm": 1.1573243141174316, "learning_rate": 4.9514299189546395e-05, "loss": 1.8986, "step": 3348 }, { "epoch": 0.08465277081871932, "grad_norm": 1.1673740148544312, "learning_rate": 4.949768693662973e-05, "loss": 1.913, "step": 3379 }, { "epoch": 0.08542940174366169, "grad_norm": 1.2315590381622314, "learning_rate": 4.948079823064559e-05, "loss": 1.9106, "step": 3410 }, { "epoch": 0.08620603266860406, "grad_norm": 5.395792484283447, "learning_rate": 4.946363326218074e-05, "loss": 1.9167, "step": 3441 }, { "epoch": 0.08698266359354645, "grad_norm": 2.3968420028686523, "learning_rate": 4.9446192224939525e-05, "loss": 1.8859, "step": 3472 }, { "epoch": 0.08775929451848882, "grad_norm": 1.2546100616455078, "learning_rate": 4.942847531574167e-05, "loss": 1.9214, "step": 3503 }, { "epoch": 0.08853592544343121, "grad_norm": 2.857767343521118, "learning_rate": 4.941048273452008e-05, "loss": 1.8984, "step": 3534 }, { "epoch": 0.08931255636837358, "grad_norm": 1.1898611783981323, "learning_rate": 4.9392214684318605e-05, "loss": 1.8913, "step": 3565 }, { "epoch": 0.09008918729331597, "grad_norm": 1.206209659576416, "learning_rate": 4.93736713712897e-05, "loss": 1.9059, "step": 3596 }, { "epoch": 0.09086581821825834, "grad_norm": 1.1964539289474487, "learning_rate": 4.9354853004692124e-05, "loss": 1.8819, "step": 3627 }, { "epoch": 0.09164244914320072, "grad_norm": 1.262360692024231, "learning_rate": 4.93357597968886e-05, "loss": 1.8778, "step": 3658 }, { "epoch": 0.0924190800681431, "grad_norm": 1.1671788692474365, "learning_rate": 4.931639196334338e-05, "loss": 1.877, "step": 3689 }, { "epoch": 0.09319571099308548, "grad_norm": 1.385147213935852, "learning_rate": 4.9296749722619826e-05, "loss": 1.8759, "step": 3720 }, { "epoch": 0.09397234191802786, "grad_norm": 1.2124735116958618, "learning_rate": 4.9276833296377966e-05, "loss": 1.8614, "step": 3751 }, { "epoch": 0.09474897284297024, "grad_norm": 1.1881778240203857, "learning_rate": 4.925664290937196e-05, "loss": 1.8644, "step": 3782 }, { "epoch": 0.09552560376791262, "grad_norm": 1.1497128009796143, "learning_rate": 4.9236178789447576e-05, "loss": 1.856, "step": 3813 }, { "epoch": 0.096302234692855, "grad_norm": 1.172032117843628, "learning_rate": 4.921544116753962e-05, "loss": 1.8611, "step": 3844 }, { "epoch": 0.09707886561779737, "grad_norm": 1.2735902070999146, "learning_rate": 4.919443027766935e-05, "loss": 1.8567, "step": 3875 }, { "epoch": 0.09785549654273976, "grad_norm": 1.1539477109909058, "learning_rate": 4.91731463569418e-05, "loss": 1.8672, "step": 3906 }, { "epoch": 0.09863212746768213, "grad_norm": 1.1640018224716187, "learning_rate": 4.915158964554312e-05, "loss": 1.8498, "step": 3937 }, { "epoch": 0.09940875839262452, "grad_norm": 1.169787883758545, "learning_rate": 4.912976038673786e-05, "loss": 1.8531, "step": 3968 }, { "epoch": 0.10018538931756689, "grad_norm": 1.177053689956665, "learning_rate": 4.9107658826866254e-05, "loss": 1.8399, "step": 3999 }, { "epoch": 0.10096202024250928, "grad_norm": 1.0724283456802368, "learning_rate": 4.908528521534139e-05, "loss": 1.8448, "step": 4030 }, { "epoch": 0.10173865116745165, "grad_norm": 1.1025402545928955, "learning_rate": 4.906263980464644e-05, "loss": 1.8572, "step": 4061 }, { "epoch": 0.10251528209239402, "grad_norm": 1.1584198474884033, "learning_rate": 4.903972285033178e-05, "loss": 1.8599, "step": 4092 }, { "epoch": 0.10329191301733641, "grad_norm": 1.144680142402649, "learning_rate": 4.901653461101213e-05, "loss": 1.8362, "step": 4123 }, { "epoch": 0.10406854394227878, "grad_norm": 1.136489748954773, "learning_rate": 4.8993075348363626e-05, "loss": 1.8446, "step": 4154 }, { "epoch": 0.10484517486722117, "grad_norm": 1.1922993659973145, "learning_rate": 4.896934532712084e-05, "loss": 1.8731, "step": 4185 }, { "epoch": 0.10562180579216354, "grad_norm": 1.229602336883545, "learning_rate": 4.8945344815073846e-05, "loss": 1.8356, "step": 4216 }, { "epoch": 0.10639843671710593, "grad_norm": 1.223044514656067, "learning_rate": 4.892107408306516e-05, "loss": 1.826, "step": 4247 }, { "epoch": 0.1071750676420483, "grad_norm": 2.0546789169311523, "learning_rate": 4.889653340498669e-05, "loss": 1.8433, "step": 4278 }, { "epoch": 0.10795169856699068, "grad_norm": 1.132135272026062, "learning_rate": 4.8871723057776664e-05, "loss": 1.8349, "step": 4309 }, { "epoch": 0.10872832949193306, "grad_norm": 1.141804575920105, "learning_rate": 4.8846643321416476e-05, "loss": 1.8588, "step": 4340 }, { "epoch": 0.10950496041687544, "grad_norm": 1.2166588306427002, "learning_rate": 4.882129447892753e-05, "loss": 1.8221, "step": 4371 }, { "epoch": 0.11028159134181782, "grad_norm": 1.1246964931488037, "learning_rate": 4.8795676816368076e-05, "loss": 1.8243, "step": 4402 }, { "epoch": 0.1110582222667602, "grad_norm": 1.1591781377792358, "learning_rate": 4.876979062282995e-05, "loss": 1.8276, "step": 4433 }, { "epoch": 0.11183485319170258, "grad_norm": 1.3351600170135498, "learning_rate": 4.8743636190435325e-05, "loss": 1.8396, "step": 4464 }, { "epoch": 0.11261148411664496, "grad_norm": 1.1741563081741333, "learning_rate": 4.871721381433344e-05, "loss": 1.829, "step": 4495 }, { "epoch": 0.11338811504158733, "grad_norm": 1.2419747114181519, "learning_rate": 4.869052379269719e-05, "loss": 1.8105, "step": 4526 }, { "epoch": 0.11416474596652972, "grad_norm": 1.146235704421997, "learning_rate": 4.866356642671985e-05, "loss": 1.8284, "step": 4557 }, { "epoch": 0.11494137689147209, "grad_norm": 1.0712112188339233, "learning_rate": 4.8636342020611634e-05, "loss": 1.8329, "step": 4588 }, { "epoch": 0.11571800781641448, "grad_norm": 1.1644688844680786, "learning_rate": 4.860885088159626e-05, "loss": 1.8186, "step": 4619 }, { "epoch": 0.11649463874135685, "grad_norm": 1.112260341644287, "learning_rate": 4.858109331990751e-05, "loss": 1.8385, "step": 4650 }, { "epoch": 0.11727126966629922, "grad_norm": 1.1103355884552002, "learning_rate": 4.855306964878567e-05, "loss": 1.8172, "step": 4681 }, { "epoch": 0.11804790059124161, "grad_norm": 1.1322386264801025, "learning_rate": 4.8524780184474084e-05, "loss": 1.8342, "step": 4712 }, { "epoch": 0.11882453151618398, "grad_norm": 1.2622575759887695, "learning_rate": 4.8496225246215496e-05, "loss": 1.7997, "step": 4743 }, { "epoch": 0.11960116244112637, "grad_norm": 1.0932341814041138, "learning_rate": 4.8467405156248505e-05, "loss": 1.8125, "step": 4774 }, { "epoch": 0.12037779336606874, "grad_norm": 1.08563232421875, "learning_rate": 4.843832023980392e-05, "loss": 1.817, "step": 4805 }, { "epoch": 0.12115442429101113, "grad_norm": 1.1124180555343628, "learning_rate": 4.840897082510106e-05, "loss": 1.8146, "step": 4836 }, { "epoch": 0.1219310552159535, "grad_norm": 1.0874966382980347, "learning_rate": 4.8379357243344084e-05, "loss": 1.7897, "step": 4867 }, { "epoch": 0.12270768614089587, "grad_norm": 1.1009818315505981, "learning_rate": 4.8349479828718236e-05, "loss": 1.8177, "step": 4898 }, { "epoch": 0.12348431706583826, "grad_norm": 1.0934672355651855, "learning_rate": 4.8319338918386075e-05, "loss": 1.8121, "step": 4929 }, { "epoch": 0.12426094799078063, "grad_norm": 1.0754870176315308, "learning_rate": 4.828893485248369e-05, "loss": 1.8298, "step": 4960 }, { "epoch": 0.125037578915723, "grad_norm": 1.0648986101150513, "learning_rate": 4.825826797411682e-05, "loss": 1.7933, "step": 4991 }, { "epoch": 0.1258142098406654, "grad_norm": 1.0323240756988525, "learning_rate": 4.822733862935702e-05, "loss": 1.818, "step": 5022 }, { "epoch": 0.12659084076560778, "grad_norm": 1.1894131898880005, "learning_rate": 4.819614716723775e-05, "loss": 1.7932, "step": 5053 }, { "epoch": 0.12736747169055015, "grad_norm": 1.047052025794983, "learning_rate": 4.8164693939750425e-05, "loss": 1.8382, "step": 5084 }, { "epoch": 0.12814410261549253, "grad_norm": 1.1111092567443848, "learning_rate": 4.813297930184042e-05, "loss": 1.7988, "step": 5115 }, { "epoch": 0.1289207335404349, "grad_norm": 1.0632669925689697, "learning_rate": 4.810100361140314e-05, "loss": 1.7971, "step": 5146 }, { "epoch": 0.1296973644653773, "grad_norm": 1.1448324918746948, "learning_rate": 4.8068767229279885e-05, "loss": 1.7677, "step": 5177 }, { "epoch": 0.13047399539031967, "grad_norm": 1.0809260606765747, "learning_rate": 4.8036270519253854e-05, "loss": 1.7829, "step": 5208 }, { "epoch": 0.13125062631526205, "grad_norm": 1.0866914987564087, "learning_rate": 4.8003513848046e-05, "loss": 1.7746, "step": 5239 }, { "epoch": 0.13202725724020442, "grad_norm": 1.021988034248352, "learning_rate": 4.79704975853109e-05, "loss": 1.8037, "step": 5270 }, { "epoch": 0.13280388816514682, "grad_norm": 1.064077615737915, "learning_rate": 4.793722210363262e-05, "loss": 1.7969, "step": 5301 }, { "epoch": 0.1335805190900892, "grad_norm": 1.087003469467163, "learning_rate": 4.7903687778520414e-05, "loss": 1.7823, "step": 5332 }, { "epoch": 0.13435715001503157, "grad_norm": 1.0024127960205078, "learning_rate": 4.7869894988404593e-05, "loss": 1.7784, "step": 5363 }, { "epoch": 0.13513378093997394, "grad_norm": 1.1223832368850708, "learning_rate": 4.783584411463221e-05, "loss": 1.7926, "step": 5394 }, { "epoch": 0.13591041186491631, "grad_norm": 1.0648205280303955, "learning_rate": 4.780153554146274e-05, "loss": 1.795, "step": 5425 }, { "epoch": 0.13668704278985871, "grad_norm": 1.0414562225341797, "learning_rate": 4.7766969656063766e-05, "loss": 1.7706, "step": 5456 }, { "epoch": 0.1374636737148011, "grad_norm": 1.0693738460540771, "learning_rate": 4.773214684850662e-05, "loss": 1.7972, "step": 5487 }, { "epoch": 0.13824030463974346, "grad_norm": 1.019546627998352, "learning_rate": 4.769706751176193e-05, "loss": 1.8109, "step": 5518 }, { "epoch": 0.13901693556468583, "grad_norm": 1.0026518106460571, "learning_rate": 4.7661732041695264e-05, "loss": 1.7599, "step": 5549 }, { "epoch": 0.1397935664896282, "grad_norm": 1.0571423768997192, "learning_rate": 4.762614083706258e-05, "loss": 1.8028, "step": 5580 }, { "epoch": 0.1405701974145706, "grad_norm": 1.0544196367263794, "learning_rate": 4.759029429950581e-05, "loss": 1.7804, "step": 5611 }, { "epoch": 0.14134682833951298, "grad_norm": 1.0218669176101685, "learning_rate": 4.7554192833548235e-05, "loss": 1.7707, "step": 5642 }, { "epoch": 0.14212345926445535, "grad_norm": 1.1020311117172241, "learning_rate": 4.751783684659e-05, "loss": 1.7893, "step": 5673 }, { "epoch": 0.14290009018939773, "grad_norm": 1.055177927017212, "learning_rate": 4.748122674890348e-05, "loss": 1.753, "step": 5704 }, { "epoch": 0.14367672111434013, "grad_norm": 1.0327739715576172, "learning_rate": 4.7444362953628654e-05, "loss": 1.7662, "step": 5735 }, { "epoch": 0.1444533520392825, "grad_norm": 1.0046563148498535, "learning_rate": 4.7407245876768424e-05, "loss": 1.7901, "step": 5766 }, { "epoch": 0.14522998296422487, "grad_norm": 1.0504815578460693, "learning_rate": 4.736987593718397e-05, "loss": 1.7735, "step": 5797 }, { "epoch": 0.14600661388916725, "grad_norm": 1.081047534942627, "learning_rate": 4.733225355658999e-05, "loss": 1.7837, "step": 5828 }, { "epoch": 0.14678324481410962, "grad_norm": 1.012346863746643, "learning_rate": 4.7294379159549926e-05, "loss": 1.7705, "step": 5859 }, { "epoch": 0.14755987573905202, "grad_norm": 0.9958217740058899, "learning_rate": 4.725625317347119e-05, "loss": 1.7649, "step": 5890 }, { "epoch": 0.1483365066639944, "grad_norm": 1.0760499238967896, "learning_rate": 4.7217876028600374e-05, "loss": 1.7945, "step": 5921 }, { "epoch": 0.14911313758893677, "grad_norm": 1.1010396480560303, "learning_rate": 4.717924815801832e-05, "loss": 1.7756, "step": 5952 }, { "epoch": 0.14988976851387914, "grad_norm": 1.0379377603530884, "learning_rate": 4.714036999763532e-05, "loss": 1.771, "step": 5983 }, { "epoch": 0.1506663994388215, "grad_norm": 1.0273206233978271, "learning_rate": 4.7101241986186116e-05, "loss": 1.7571, "step": 6014 }, { "epoch": 0.15144303036376391, "grad_norm": 1.0275596380233765, "learning_rate": 4.7061864565225e-05, "loss": 1.7668, "step": 6045 }, { "epoch": 0.1522196612887063, "grad_norm": 1.076374888420105, "learning_rate": 4.702223817912081e-05, "loss": 1.7819, "step": 6076 }, { "epoch": 0.15299629221364866, "grad_norm": 1.0678372383117676, "learning_rate": 4.698236327505195e-05, "loss": 1.7811, "step": 6107 }, { "epoch": 0.15377292313859103, "grad_norm": 1.017540693283081, "learning_rate": 4.694224030300127e-05, "loss": 1.7638, "step": 6138 }, { "epoch": 0.1545495540635334, "grad_norm": 1.0062652826309204, "learning_rate": 4.690186971575107e-05, "loss": 1.7535, "step": 6169 }, { "epoch": 0.1553261849884758, "grad_norm": 1.0092757940292358, "learning_rate": 4.6861251968877916e-05, "loss": 1.7671, "step": 6200 }, { "epoch": 0.15610281591341818, "grad_norm": 0.9981346130371094, "learning_rate": 4.68203875207476e-05, "loss": 1.755, "step": 6231 }, { "epoch": 0.15687944683836055, "grad_norm": 2.156689167022705, "learning_rate": 4.677927683250983e-05, "loss": 1.7679, "step": 6262 }, { "epoch": 0.15765607776330293, "grad_norm": 0.9837804436683655, "learning_rate": 4.6737920368093156e-05, "loss": 1.7523, "step": 6293 }, { "epoch": 0.15843270868824533, "grad_norm": 1.1614326238632202, "learning_rate": 4.669631859419965e-05, "loss": 1.7484, "step": 6324 }, { "epoch": 0.1592093396131877, "grad_norm": 1.0423202514648438, "learning_rate": 4.6654471980299676e-05, "loss": 1.7707, "step": 6355 }, { "epoch": 0.15998597053813007, "grad_norm": 0.9598566293716431, "learning_rate": 4.661238099862658e-05, "loss": 1.7544, "step": 6386 }, { "epoch": 0.16076260146307245, "grad_norm": 1.053193211555481, "learning_rate": 4.657004612417138e-05, "loss": 1.7627, "step": 6417 }, { "epoch": 0.16153923238801482, "grad_norm": 1.0258429050445557, "learning_rate": 4.6527467834677374e-05, "loss": 1.7397, "step": 6448 }, { "epoch": 0.16231586331295722, "grad_norm": 1.0296120643615723, "learning_rate": 4.648464661063478e-05, "loss": 1.76, "step": 6479 }, { "epoch": 0.1630924942378996, "grad_norm": 1.0015708208084106, "learning_rate": 4.6441582935275264e-05, "loss": 1.7542, "step": 6510 }, { "epoch": 0.16386912516284197, "grad_norm": 0.982397198677063, "learning_rate": 4.6398277294566586e-05, "loss": 1.7278, "step": 6541 }, { "epoch": 0.16464575608778434, "grad_norm": 0.9919869303703308, "learning_rate": 4.6354730177207e-05, "loss": 1.7419, "step": 6572 }, { "epoch": 0.1654223870127267, "grad_norm": 1.0046809911727905, "learning_rate": 4.6310942074619787e-05, "loss": 1.7669, "step": 6603 }, { "epoch": 0.1661990179376691, "grad_norm": 0.9675459265708923, "learning_rate": 4.626691348094777e-05, "loss": 1.7453, "step": 6634 }, { "epoch": 0.1669756488626115, "grad_norm": 0.9798470735549927, "learning_rate": 4.622264489304762e-05, "loss": 1.7438, "step": 6665 }, { "epoch": 0.16775227978755386, "grad_norm": 0.9938516616821289, "learning_rate": 4.617813681048434e-05, "loss": 1.7503, "step": 6696 }, { "epoch": 0.16852891071249623, "grad_norm": 0.9619422554969788, "learning_rate": 4.61333897355256e-05, "loss": 1.7642, "step": 6727 }, { "epoch": 0.16930554163743863, "grad_norm": 0.9402725100517273, "learning_rate": 4.608840417313604e-05, "loss": 1.7389, "step": 6758 }, { "epoch": 0.170082172562381, "grad_norm": 0.9799749255180359, "learning_rate": 4.6043180630971646e-05, "loss": 1.7454, "step": 6789 }, { "epoch": 0.17085880348732338, "grad_norm": 0.920802116394043, "learning_rate": 4.599771961937391e-05, "loss": 1.7384, "step": 6820 }, { "epoch": 0.17163543441226575, "grad_norm": 0.9431501626968384, "learning_rate": 4.5952021651364204e-05, "loss": 1.7194, "step": 6851 }, { "epoch": 0.17241206533720813, "grad_norm": 0.9482398629188538, "learning_rate": 4.590608724263786e-05, "loss": 1.7513, "step": 6882 }, { "epoch": 0.17318869626215053, "grad_norm": 0.9813526272773743, "learning_rate": 4.585991691155845e-05, "loss": 1.7451, "step": 6913 }, { "epoch": 0.1739653271870929, "grad_norm": 1.0157101154327393, "learning_rate": 4.581351117915188e-05, "loss": 1.7464, "step": 6944 }, { "epoch": 0.17474195811203527, "grad_norm": 0.9638293981552124, "learning_rate": 4.5766870569100534e-05, "loss": 1.7313, "step": 6975 }, { "epoch": 0.17551858903697765, "grad_norm": 0.9673603773117065, "learning_rate": 4.571999560773736e-05, "loss": 1.748, "step": 7006 }, { "epoch": 0.17629521996192002, "grad_norm": 0.9882768392562866, "learning_rate": 4.5672886824039915e-05, "loss": 1.7384, "step": 7037 }, { "epoch": 0.17707185088686242, "grad_norm": 0.9788867235183716, "learning_rate": 4.5625544749624435e-05, "loss": 1.7522, "step": 7068 }, { "epoch": 0.1778484818118048, "grad_norm": 0.9794373512268066, "learning_rate": 4.5577969918739794e-05, "loss": 1.7077, "step": 7099 }, { "epoch": 0.17862511273674717, "grad_norm": 1.0159693956375122, "learning_rate": 4.5530162868261486e-05, "loss": 1.7346, "step": 7130 }, { "epoch": 0.17940174366168954, "grad_norm": 1.0156211853027344, "learning_rate": 4.548212413768558e-05, "loss": 1.7447, "step": 7161 }, { "epoch": 0.18017837458663194, "grad_norm": 0.9733012318611145, "learning_rate": 4.543385426912261e-05, "loss": 1.7293, "step": 7192 }, { "epoch": 0.1809550055115743, "grad_norm": 0.9807786345481873, "learning_rate": 4.53853538072915e-05, "loss": 1.7389, "step": 7223 }, { "epoch": 0.18173163643651669, "grad_norm": 0.972074031829834, "learning_rate": 4.533662329951336e-05, "loss": 1.7218, "step": 7254 }, { "epoch": 0.18250826736145906, "grad_norm": 0.9490823745727539, "learning_rate": 4.528766329570536e-05, "loss": 1.706, "step": 7285 }, { "epoch": 0.18328489828640143, "grad_norm": 0.9884642958641052, "learning_rate": 4.523847434837447e-05, "loss": 1.7341, "step": 7316 }, { "epoch": 0.18406152921134383, "grad_norm": 0.9563024640083313, "learning_rate": 4.518905701261128e-05, "loss": 1.718, "step": 7347 }, { "epoch": 0.1848381601362862, "grad_norm": 1.177401065826416, "learning_rate": 4.5139411846083715e-05, "loss": 1.723, "step": 7378 }, { "epoch": 0.18561479106122858, "grad_norm": 0.9618046879768372, "learning_rate": 4.508953940903073e-05, "loss": 1.7309, "step": 7409 }, { "epoch": 0.18639142198617095, "grad_norm": 0.9730792045593262, "learning_rate": 4.5039440264255994e-05, "loss": 1.7236, "step": 7440 }, { "epoch": 0.18716805291111333, "grad_norm": 0.9472179412841797, "learning_rate": 4.498911497712155e-05, "loss": 1.7142, "step": 7471 }, { "epoch": 0.18794468383605573, "grad_norm": 0.9653865694999695, "learning_rate": 4.493856411554142e-05, "loss": 1.727, "step": 7502 }, { "epoch": 0.1887213147609981, "grad_norm": 0.9445356726646423, "learning_rate": 4.4887788249975206e-05, "loss": 1.7154, "step": 7533 }, { "epoch": 0.18949794568594047, "grad_norm": 1.1695305109024048, "learning_rate": 4.4836787953421656e-05, "loss": 1.7257, "step": 7564 }, { "epoch": 0.19027457661088285, "grad_norm": 0.9815401434898376, "learning_rate": 4.478556380141218e-05, "loss": 1.7237, "step": 7595 }, { "epoch": 0.19105120753582525, "grad_norm": 0.9725745916366577, "learning_rate": 4.4734116372004375e-05, "loss": 1.7362, "step": 7626 } ], "logging_steps": 31, "max_steps": 30517, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 7630, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 5.32921354882646e+18, "train_batch_size": 16, "trial_name": null, "trial_params": null }