{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.70578905630452, "eval_steps": 500, "global_step": 3600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01586042823156225, "grad_norm": 19.139528850030874, "learning_rate": 8.910891089108911e-07, "loss": 8.2466, "step": 10 }, { "epoch": 0.0317208564631245, "grad_norm": 17.8179869039751, "learning_rate": 1.8811881188118813e-06, "loss": 8.1206, "step": 20 }, { "epoch": 0.047581284694686754, "grad_norm": 9.164020050000067, "learning_rate": 2.8712871287128717e-06, "loss": 7.4762, "step": 30 }, { "epoch": 0.063441712926249, "grad_norm": 4.906293902424142, "learning_rate": 3.861386138613861e-06, "loss": 6.7446, "step": 40 }, { "epoch": 0.07930214115781126, "grad_norm": 3.052162672695787, "learning_rate": 4.851485148514852e-06, "loss": 6.2761, "step": 50 }, { "epoch": 0.09516256938937351, "grad_norm": 2.98736461961841, "learning_rate": 5.841584158415842e-06, "loss": 5.929, "step": 60 }, { "epoch": 0.11102299762093576, "grad_norm": 3.707337444231957, "learning_rate": 6.831683168316833e-06, "loss": 5.5255, "step": 70 }, { "epoch": 0.126883425852498, "grad_norm": 4.5149941785829, "learning_rate": 7.821782178217822e-06, "loss": 4.9205, "step": 80 }, { "epoch": 0.14274385408406026, "grad_norm": 4.194108732375239, "learning_rate": 8.811881188118812e-06, "loss": 4.2318, "step": 90 }, { "epoch": 0.1586042823156225, "grad_norm": 3.8369189131135757, "learning_rate": 9.801980198019804e-06, "loss": 3.6352, "step": 100 }, { "epoch": 0.17446471054718476, "grad_norm": 3.7340050812724255, "learning_rate": 1.0792079207920792e-05, "loss": 3.2605, "step": 110 }, { "epoch": 0.19032513877874702, "grad_norm": 3.9254417022343637, "learning_rate": 1.1782178217821782e-05, "loss": 3.0544, "step": 120 }, { "epoch": 0.20618556701030927, "grad_norm": 4.840686832835472, "learning_rate": 1.2772277227722773e-05, "loss": 2.9196, "step": 130 }, { "epoch": 0.22204599524187152, "grad_norm": 13.780201154926932, "learning_rate": 1.3762376237623763e-05, "loss": 2.8095, "step": 140 }, { "epoch": 0.23790642347343377, "grad_norm": 6.344054558352859, "learning_rate": 1.4752475247524752e-05, "loss": 2.7136, "step": 150 }, { "epoch": 0.253766851704996, "grad_norm": 4.982092617175093, "learning_rate": 1.5742574257425743e-05, "loss": 2.6392, "step": 160 }, { "epoch": 0.2696272799365583, "grad_norm": 8.162264297232719, "learning_rate": 1.6732673267326735e-05, "loss": 2.5676, "step": 170 }, { "epoch": 0.2854877081681205, "grad_norm": 9.068632822505595, "learning_rate": 1.7722772277227723e-05, "loss": 2.4886, "step": 180 }, { "epoch": 0.3013481363996828, "grad_norm": 21.522422147460635, "learning_rate": 1.8712871287128715e-05, "loss": 2.424, "step": 190 }, { "epoch": 0.317208564631245, "grad_norm": 20.83191234754218, "learning_rate": 1.9702970297029703e-05, "loss": 2.3979, "step": 200 }, { "epoch": 0.3330689928628073, "grad_norm": 11.966941640205993, "learning_rate": 2.069306930693069e-05, "loss": 2.3199, "step": 210 }, { "epoch": 0.34892942109436953, "grad_norm": 13.845469765092606, "learning_rate": 2.1683168316831683e-05, "loss": 2.2642, "step": 220 }, { "epoch": 0.3647898493259318, "grad_norm": 10.896989301572372, "learning_rate": 2.2673267326732675e-05, "loss": 2.1938, "step": 230 }, { "epoch": 0.38065027755749403, "grad_norm": 8.461441256784877, "learning_rate": 2.3663366336633663e-05, "loss": 2.1093, "step": 240 }, { "epoch": 0.3965107057890563, "grad_norm": 15.437949044441957, "learning_rate": 2.4653465346534655e-05, "loss": 2.0244, "step": 250 }, { "epoch": 0.41237113402061853, "grad_norm": 6.9324747811801215, "learning_rate": 2.5643564356435646e-05, "loss": 1.9328, "step": 260 }, { "epoch": 0.4282315622521808, "grad_norm": 6.539929054412363, "learning_rate": 2.6633663366336638e-05, "loss": 1.8107, "step": 270 }, { "epoch": 0.44409199048374304, "grad_norm": 9.546138483110752, "learning_rate": 2.7623762376237626e-05, "loss": 1.719, "step": 280 }, { "epoch": 0.4599524187153053, "grad_norm": 6.921145854402886, "learning_rate": 2.8613861386138614e-05, "loss": 1.64, "step": 290 }, { "epoch": 0.47581284694686754, "grad_norm": 5.464388935314663, "learning_rate": 2.9603960396039603e-05, "loss": 1.5848, "step": 300 }, { "epoch": 0.4916732751784298, "grad_norm": 5.644631505546815, "learning_rate": 3.0594059405940594e-05, "loss": 1.515, "step": 310 }, { "epoch": 0.507533703409992, "grad_norm": 7.749393965323654, "learning_rate": 3.158415841584158e-05, "loss": 1.4565, "step": 320 }, { "epoch": 0.5233941316415543, "grad_norm": 7.011857430438995, "learning_rate": 3.257425742574258e-05, "loss": 1.4069, "step": 330 }, { "epoch": 0.5392545598731165, "grad_norm": 4.774306275517458, "learning_rate": 3.3564356435643566e-05, "loss": 1.3559, "step": 340 }, { "epoch": 0.5551149881046789, "grad_norm": 4.827841991876933, "learning_rate": 3.4554455445544554e-05, "loss": 1.3113, "step": 350 }, { "epoch": 0.570975416336241, "grad_norm": 6.409703044827469, "learning_rate": 3.554455445544554e-05, "loss": 1.272, "step": 360 }, { "epoch": 0.5868358445678034, "grad_norm": 7.223403220564374, "learning_rate": 3.653465346534654e-05, "loss": 1.2188, "step": 370 }, { "epoch": 0.6026962727993656, "grad_norm": 5.777859827384273, "learning_rate": 3.7524752475247526e-05, "loss": 1.1884, "step": 380 }, { "epoch": 0.6185567010309279, "grad_norm": 6.4063926115137875, "learning_rate": 3.851485148514852e-05, "loss": 1.1581, "step": 390 }, { "epoch": 0.63441712926249, "grad_norm": 6.651129225778287, "learning_rate": 3.950495049504951e-05, "loss": 1.1047, "step": 400 }, { "epoch": 0.6502775574940524, "grad_norm": 5.6870828905793065, "learning_rate": 4.04950495049505e-05, "loss": 1.0823, "step": 410 }, { "epoch": 0.6661379857256146, "grad_norm": 5.667978471416249, "learning_rate": 4.1485148514851486e-05, "loss": 1.0494, "step": 420 }, { "epoch": 0.6819984139571769, "grad_norm": 4.237807026037709, "learning_rate": 4.2475247524752474e-05, "loss": 1.0155, "step": 430 }, { "epoch": 0.6978588421887391, "grad_norm": 4.255500663396079, "learning_rate": 4.346534653465347e-05, "loss": 0.9875, "step": 440 }, { "epoch": 0.7137192704203014, "grad_norm": 5.185306420438398, "learning_rate": 4.445544554455446e-05, "loss": 0.9639, "step": 450 }, { "epoch": 0.7295796986518636, "grad_norm": 5.272706809075813, "learning_rate": 4.544554455445545e-05, "loss": 0.9387, "step": 460 }, { "epoch": 0.7454401268834259, "grad_norm": 6.077622808418557, "learning_rate": 4.643564356435644e-05, "loss": 0.921, "step": 470 }, { "epoch": 0.7613005551149881, "grad_norm": 4.6482898197595235, "learning_rate": 4.742574257425743e-05, "loss": 0.8856, "step": 480 }, { "epoch": 0.7771609833465504, "grad_norm": 5.2219845727325955, "learning_rate": 4.841584158415842e-05, "loss": 0.8562, "step": 490 }, { "epoch": 0.7930214115781126, "grad_norm": 5.064442866871307, "learning_rate": 4.9405940594059405e-05, "loss": 0.8393, "step": 500 }, { "epoch": 0.8088818398096749, "grad_norm": 4.238944041111026, "learning_rate": 5.03960396039604e-05, "loss": 0.8133, "step": 510 }, { "epoch": 0.8247422680412371, "grad_norm": 5.703536274698318, "learning_rate": 5.138613861386139e-05, "loss": 0.8012, "step": 520 }, { "epoch": 0.8406026962727994, "grad_norm": 5.296419707622884, "learning_rate": 5.2376237623762384e-05, "loss": 0.767, "step": 530 }, { "epoch": 0.8564631245043616, "grad_norm": 5.699284324132107, "learning_rate": 5.336633663366337e-05, "loss": 0.7484, "step": 540 }, { "epoch": 0.8723235527359239, "grad_norm": 6.425639332496651, "learning_rate": 5.435643564356436e-05, "loss": 0.7292, "step": 550 }, { "epoch": 0.8881839809674861, "grad_norm": 5.045854763956847, "learning_rate": 5.5346534653465355e-05, "loss": 0.6976, "step": 560 }, { "epoch": 0.9040444091990484, "grad_norm": 5.0868187480748315, "learning_rate": 5.633663366336634e-05, "loss": 0.6719, "step": 570 }, { "epoch": 0.9199048374306106, "grad_norm": 6.760967897420004, "learning_rate": 5.7326732673267325e-05, "loss": 0.6573, "step": 580 }, { "epoch": 0.9357652656621729, "grad_norm": 4.427355231592498, "learning_rate": 5.831683168316831e-05, "loss": 0.6471, "step": 590 }, { "epoch": 0.9516256938937351, "grad_norm": 3.9839664702745634, "learning_rate": 5.930693069306931e-05, "loss": 0.6221, "step": 600 }, { "epoch": 0.9674861221252974, "grad_norm": 3.2513703063334196, "learning_rate": 6.02970297029703e-05, "loss": 0.5913, "step": 610 }, { "epoch": 0.9833465503568596, "grad_norm": 3.485916478339426, "learning_rate": 6.128712871287129e-05, "loss": 0.5775, "step": 620 }, { "epoch": 0.9992069785884219, "grad_norm": 4.08651811102019, "learning_rate": 6.227722772277228e-05, "loss": 0.5598, "step": 630 }, { "epoch": 1.014274385408406, "grad_norm": 3.438814479162103, "learning_rate": 6.326732673267327e-05, "loss": 0.5349, "step": 640 }, { "epoch": 1.0301348136399682, "grad_norm": 4.44087122057166, "learning_rate": 6.425742574257426e-05, "loss": 0.5194, "step": 650 }, { "epoch": 1.0459952418715306, "grad_norm": 3.5256251500611384, "learning_rate": 6.524752475247526e-05, "loss": 0.506, "step": 660 }, { "epoch": 1.0618556701030928, "grad_norm": 3.422611919607941, "learning_rate": 6.623762376237625e-05, "loss": 0.4861, "step": 670 }, { "epoch": 1.077716098334655, "grad_norm": 3.133948265271591, "learning_rate": 6.722772277227723e-05, "loss": 0.4602, "step": 680 }, { "epoch": 1.0935765265662174, "grad_norm": 3.6082454324392534, "learning_rate": 6.821782178217822e-05, "loss": 0.4496, "step": 690 }, { "epoch": 1.1094369547977796, "grad_norm": 2.9254028901121027, "learning_rate": 6.920792079207921e-05, "loss": 0.4271, "step": 700 }, { "epoch": 1.1252973830293418, "grad_norm": 2.873534663709151, "learning_rate": 7.01980198019802e-05, "loss": 0.408, "step": 710 }, { "epoch": 1.141157811260904, "grad_norm": 2.4876771741690122, "learning_rate": 7.118811881188119e-05, "loss": 0.3908, "step": 720 }, { "epoch": 1.1570182394924662, "grad_norm": 2.7097832052411737, "learning_rate": 7.217821782178218e-05, "loss": 0.382, "step": 730 }, { "epoch": 1.1728786677240286, "grad_norm": 2.9660438369371884, "learning_rate": 7.316831683168316e-05, "loss": 0.3582, "step": 740 }, { "epoch": 1.1887390959555908, "grad_norm": 2.5000910168051895, "learning_rate": 7.415841584158417e-05, "loss": 0.3497, "step": 750 }, { "epoch": 1.204599524187153, "grad_norm": 2.633285101346317, "learning_rate": 7.514851485148515e-05, "loss": 0.3334, "step": 760 }, { "epoch": 1.2204599524187154, "grad_norm": 2.60732404875358, "learning_rate": 7.613861386138614e-05, "loss": 0.3184, "step": 770 }, { "epoch": 1.2363203806502776, "grad_norm": 2.0629946739238005, "learning_rate": 7.712871287128713e-05, "loss": 0.3067, "step": 780 }, { "epoch": 1.2521808088818398, "grad_norm": 2.4100126998703253, "learning_rate": 7.811881188118812e-05, "loss": 0.2875, "step": 790 }, { "epoch": 1.268041237113402, "grad_norm": 2.798339817744955, "learning_rate": 7.910891089108912e-05, "loss": 0.277, "step": 800 }, { "epoch": 1.2839016653449642, "grad_norm": 2.806131384717819, "learning_rate": 8.009900990099011e-05, "loss": 0.2701, "step": 810 }, { "epoch": 1.2997620935765266, "grad_norm": 1.9986997398098798, "learning_rate": 8.10891089108911e-05, "loss": 0.2559, "step": 820 }, { "epoch": 1.3156225218080888, "grad_norm": 2.359590651524235, "learning_rate": 8.207920792079207e-05, "loss": 0.2419, "step": 830 }, { "epoch": 1.331482950039651, "grad_norm": 2.331111900194689, "learning_rate": 8.306930693069307e-05, "loss": 0.2294, "step": 840 }, { "epoch": 1.3473433782712134, "grad_norm": 1.8818075156301755, "learning_rate": 8.405940594059406e-05, "loss": 0.2141, "step": 850 }, { "epoch": 1.3632038065027756, "grad_norm": 1.634132799610872, "learning_rate": 8.504950495049505e-05, "loss": 0.2069, "step": 860 }, { "epoch": 1.3790642347343378, "grad_norm": 1.5120836080111373, "learning_rate": 8.603960396039604e-05, "loss": 0.1966, "step": 870 }, { "epoch": 1.3949246629659, "grad_norm": 1.6982638535321994, "learning_rate": 8.702970297029703e-05, "loss": 0.1882, "step": 880 }, { "epoch": 1.4107850911974622, "grad_norm": 1.7108735595543574, "learning_rate": 8.801980198019803e-05, "loss": 0.1779, "step": 890 }, { "epoch": 1.4266455194290246, "grad_norm": 1.7296122709014143, "learning_rate": 8.900990099009902e-05, "loss": 0.1676, "step": 900 }, { "epoch": 1.4425059476605868, "grad_norm": 1.8189109064576499, "learning_rate": 9e-05, "loss": 0.1601, "step": 910 }, { "epoch": 1.458366375892149, "grad_norm": 2.095375586550601, "learning_rate": 9.0990099009901e-05, "loss": 0.1499, "step": 920 }, { "epoch": 1.4742268041237114, "grad_norm": 2.6273043704027312, "learning_rate": 9.198019801980198e-05, "loss": 0.1455, "step": 930 }, { "epoch": 1.4900872323552736, "grad_norm": 1.1840652988818152, "learning_rate": 9.297029702970298e-05, "loss": 0.1434, "step": 940 }, { "epoch": 1.5059476605868358, "grad_norm": 1.102318462015262, "learning_rate": 9.396039603960396e-05, "loss": 0.1322, "step": 950 }, { "epoch": 1.521808088818398, "grad_norm": 1.249035070323803, "learning_rate": 9.495049504950495e-05, "loss": 0.1232, "step": 960 }, { "epoch": 1.5376685170499602, "grad_norm": 0.8585709469514784, "learning_rate": 9.594059405940594e-05, "loss": 0.1175, "step": 970 }, { "epoch": 1.5535289452815226, "grad_norm": 0.959556178843799, "learning_rate": 9.693069306930694e-05, "loss": 0.1119, "step": 980 }, { "epoch": 1.5693893735130848, "grad_norm": 0.9203530254113947, "learning_rate": 9.792079207920793e-05, "loss": 0.1083, "step": 990 }, { "epoch": 1.5852498017446472, "grad_norm": 0.8563247229051851, "learning_rate": 9.891089108910891e-05, "loss": 0.1009, "step": 1000 }, { "epoch": 1.6011102299762094, "grad_norm": 1.4810040972537613, "learning_rate": 9.99009900990099e-05, "loss": 0.0954, "step": 1010 }, { "epoch": 1.6169706582077716, "grad_norm": 0.6927338195573747, "learning_rate": 9.999975790882544e-05, "loss": 0.0907, "step": 1020 }, { "epoch": 1.6328310864393338, "grad_norm": 0.6353525161914889, "learning_rate": 9.999892105345399e-05, "loss": 0.0856, "step": 1030 }, { "epoch": 1.648691514670896, "grad_norm": 1.0066185794390339, "learning_rate": 9.999748645510806e-05, "loss": 0.0904, "step": 1040 }, { "epoch": 1.6645519429024582, "grad_norm": 0.5499242841223613, "learning_rate": 9.999545413093843e-05, "loss": 0.0817, "step": 1050 }, { "epoch": 1.6804123711340206, "grad_norm": 0.6026955934647209, "learning_rate": 9.999282410524176e-05, "loss": 0.076, "step": 1060 }, { "epoch": 1.6962727993655828, "grad_norm": 0.5189336537822474, "learning_rate": 9.998959640946033e-05, "loss": 0.0706, "step": 1070 }, { "epoch": 1.7121332275971453, "grad_norm": 0.5108915419488772, "learning_rate": 9.998577108218162e-05, "loss": 0.0685, "step": 1080 }, { "epoch": 1.7279936558287075, "grad_norm": 0.4759581343462929, "learning_rate": 9.998134816913788e-05, "loss": 0.0642, "step": 1090 }, { "epoch": 1.7438540840602696, "grad_norm": 0.44750114998963825, "learning_rate": 9.997632772320553e-05, "loss": 0.0615, "step": 1100 }, { "epoch": 1.7597145122918318, "grad_norm": 0.4682540236602841, "learning_rate": 9.997070980440462e-05, "loss": 0.0587, "step": 1110 }, { "epoch": 1.775574940523394, "grad_norm": 0.46100974574978826, "learning_rate": 9.9964494479898e-05, "loss": 0.0571, "step": 1120 }, { "epoch": 1.7914353687549562, "grad_norm": 0.4802771820307019, "learning_rate": 9.995768182399062e-05, "loss": 0.0542, "step": 1130 }, { "epoch": 1.8072957969865187, "grad_norm": 0.402517941066615, "learning_rate": 9.995027191812859e-05, "loss": 0.0526, "step": 1140 }, { "epoch": 1.8231562252180809, "grad_norm": 0.36529022302452335, "learning_rate": 9.99422648508982e-05, "loss": 0.0502, "step": 1150 }, { "epoch": 1.8390166534496433, "grad_norm": 0.43348415026389686, "learning_rate": 9.993366071802484e-05, "loss": 0.0478, "step": 1160 }, { "epoch": 1.8548770816812055, "grad_norm": 0.32832066422044764, "learning_rate": 9.9924459622372e-05, "loss": 0.0469, "step": 1170 }, { "epoch": 1.8707375099127677, "grad_norm": 0.36783738330763543, "learning_rate": 9.991466167393981e-05, "loss": 0.0458, "step": 1180 }, { "epoch": 1.8865979381443299, "grad_norm": 2.3188302609712563, "learning_rate": 9.99042669898639e-05, "loss": 0.0459, "step": 1190 }, { "epoch": 1.902458366375892, "grad_norm": 0.5436195698507995, "learning_rate": 9.989327569441394e-05, "loss": 0.0464, "step": 1200 }, { "epoch": 1.9183187946074542, "grad_norm": 0.3263229164097963, "learning_rate": 9.988168791899218e-05, "loss": 0.0436, "step": 1210 }, { "epoch": 1.9341792228390167, "grad_norm": 0.3022710473853306, "learning_rate": 9.986950380213182e-05, "loss": 0.0416, "step": 1220 }, { "epoch": 1.9500396510705789, "grad_norm": 0.30154108928053425, "learning_rate": 9.98567234894954e-05, "loss": 0.0406, "step": 1230 }, { "epoch": 1.9659000793021413, "grad_norm": 0.3196021212235642, "learning_rate": 9.984334713387308e-05, "loss": 0.0396, "step": 1240 }, { "epoch": 1.9817605075337035, "grad_norm": 0.3236037547731566, "learning_rate": 9.982937489518075e-05, "loss": 0.0389, "step": 1250 }, { "epoch": 1.9976209357652657, "grad_norm": 0.3711446498733101, "learning_rate": 9.981480694045816e-05, "loss": 0.038, "step": 1260 }, { "epoch": 2.0126883425852498, "grad_norm": 0.3063522932516602, "learning_rate": 9.979964344386692e-05, "loss": 0.0359, "step": 1270 }, { "epoch": 2.028548770816812, "grad_norm": 0.30361076290584094, "learning_rate": 9.978388458668842e-05, "loss": 0.0343, "step": 1280 }, { "epoch": 2.044409199048374, "grad_norm": 0.258513333686689, "learning_rate": 9.976753055732166e-05, "loss": 0.0338, "step": 1290 }, { "epoch": 2.0602696272799363, "grad_norm": 0.25186209885924893, "learning_rate": 9.975058155128097e-05, "loss": 0.0332, "step": 1300 }, { "epoch": 2.076130055511499, "grad_norm": 0.2667716434965371, "learning_rate": 9.97330377711937e-05, "loss": 0.0325, "step": 1310 }, { "epoch": 2.091990483743061, "grad_norm": 0.25831881157696407, "learning_rate": 9.97148994267978e-05, "loss": 0.0322, "step": 1320 }, { "epoch": 2.1078509119746234, "grad_norm": 0.2422521939116205, "learning_rate": 9.969616673493932e-05, "loss": 0.0312, "step": 1330 }, { "epoch": 2.1237113402061856, "grad_norm": 0.25167325235563537, "learning_rate": 9.96768399195698e-05, "loss": 0.0311, "step": 1340 }, { "epoch": 2.1395717684377478, "grad_norm": 0.2648060208843995, "learning_rate": 9.965691921174357e-05, "loss": 0.0308, "step": 1350 }, { "epoch": 2.15543219666931, "grad_norm": 0.26050946392333785, "learning_rate": 9.963640484961505e-05, "loss": 0.03, "step": 1360 }, { "epoch": 2.171292624900872, "grad_norm": 0.2384998360178266, "learning_rate": 9.961529707843583e-05, "loss": 0.0297, "step": 1370 }, { "epoch": 2.187153053132435, "grad_norm": 0.25739858905812224, "learning_rate": 9.95935961505518e-05, "loss": 0.029, "step": 1380 }, { "epoch": 2.203013481363997, "grad_norm": 0.23794124732997246, "learning_rate": 9.95713023254001e-05, "loss": 0.0286, "step": 1390 }, { "epoch": 2.218873909595559, "grad_norm": 0.2301971290512307, "learning_rate": 9.954841586950606e-05, "loss": 0.0286, "step": 1400 }, { "epoch": 2.2347343378271214, "grad_norm": 0.2290063026328564, "learning_rate": 9.95249370564799e-05, "loss": 0.0276, "step": 1410 }, { "epoch": 2.2505947660586836, "grad_norm": 0.23440055002640264, "learning_rate": 9.95008661670136e-05, "loss": 0.0273, "step": 1420 }, { "epoch": 2.266455194290246, "grad_norm": 0.34512157189164844, "learning_rate": 9.947620348887749e-05, "loss": 0.0266, "step": 1430 }, { "epoch": 2.282315622521808, "grad_norm": 0.25726085487236555, "learning_rate": 9.945094931691678e-05, "loss": 0.0268, "step": 1440 }, { "epoch": 2.29817605075337, "grad_norm": 0.3637610324377928, "learning_rate": 9.942510395304805e-05, "loss": 0.0259, "step": 1450 }, { "epoch": 2.3140364789849324, "grad_norm": 1.1472903509254984, "learning_rate": 9.939866770625567e-05, "loss": 0.0275, "step": 1460 }, { "epoch": 2.329896907216495, "grad_norm": 2.5053341106388856, "learning_rate": 9.937164089258809e-05, "loss": 0.0304, "step": 1470 }, { "epoch": 2.345757335448057, "grad_norm": 1.0767870929445287, "learning_rate": 9.9344023835154e-05, "loss": 0.0454, "step": 1480 }, { "epoch": 2.3616177636796194, "grad_norm": 0.43278952742259996, "learning_rate": 9.931581686411859e-05, "loss": 0.0362, "step": 1490 }, { "epoch": 2.3774781919111816, "grad_norm": 0.2745476890309345, "learning_rate": 9.928702031669954e-05, "loss": 0.0294, "step": 1500 }, { "epoch": 2.393338620142744, "grad_norm": 0.23151635915708174, "learning_rate": 9.92576345371629e-05, "loss": 0.0267, "step": 1510 }, { "epoch": 2.409199048374306, "grad_norm": 0.2528640123475777, "learning_rate": 9.922765987681917e-05, "loss": 0.0254, "step": 1520 }, { "epoch": 2.425059476605868, "grad_norm": 0.22322528832884078, "learning_rate": 9.919709669401891e-05, "loss": 0.0241, "step": 1530 }, { "epoch": 2.440919904837431, "grad_norm": 0.25767429518855794, "learning_rate": 9.916594535414856e-05, "loss": 0.0236, "step": 1540 }, { "epoch": 2.456780333068993, "grad_norm": 0.20859014169787804, "learning_rate": 9.913420622962606e-05, "loss": 0.0231, "step": 1550 }, { "epoch": 2.472640761300555, "grad_norm": 0.20097276712386156, "learning_rate": 9.910187969989635e-05, "loss": 0.0227, "step": 1560 }, { "epoch": 2.4885011895321174, "grad_norm": 0.19502715852546781, "learning_rate": 9.90689661514269e-05, "loss": 0.0223, "step": 1570 }, { "epoch": 2.5043616177636796, "grad_norm": 0.18926852564659236, "learning_rate": 9.903546597770305e-05, "loss": 0.0217, "step": 1580 }, { "epoch": 2.520222045995242, "grad_norm": 0.18977619403937718, "learning_rate": 9.900137957922333e-05, "loss": 0.0213, "step": 1590 }, { "epoch": 2.536082474226804, "grad_norm": 0.19098675458895795, "learning_rate": 9.896670736349462e-05, "loss": 0.0208, "step": 1600 }, { "epoch": 2.551942902458366, "grad_norm": 0.2009242073740019, "learning_rate": 9.893144974502733e-05, "loss": 0.0205, "step": 1610 }, { "epoch": 2.5678033306899284, "grad_norm": 0.1882743338134484, "learning_rate": 9.889560714533042e-05, "loss": 0.0209, "step": 1620 }, { "epoch": 2.583663758921491, "grad_norm": 0.20524223857112522, "learning_rate": 9.885917999290641e-05, "loss": 0.0202, "step": 1630 }, { "epoch": 2.5995241871530532, "grad_norm": 0.17581923873322422, "learning_rate": 9.882216872324617e-05, "loss": 0.02, "step": 1640 }, { "epoch": 2.6153846153846154, "grad_norm": 0.21569051031935538, "learning_rate": 9.878457377882376e-05, "loss": 0.0201, "step": 1650 }, { "epoch": 2.6312450436161776, "grad_norm": 0.1891563070911822, "learning_rate": 9.874639560909117e-05, "loss": 0.0196, "step": 1660 }, { "epoch": 2.64710547184774, "grad_norm": 0.19956230575208342, "learning_rate": 9.870763467047293e-05, "loss": 0.019, "step": 1670 }, { "epoch": 2.662965900079302, "grad_norm": 0.19799721546110283, "learning_rate": 9.866829142636058e-05, "loss": 0.0189, "step": 1680 }, { "epoch": 2.6788263283108646, "grad_norm": 0.19531667504057218, "learning_rate": 9.862836634710724e-05, "loss": 0.0186, "step": 1690 }, { "epoch": 2.694686756542427, "grad_norm": 0.18324610519548817, "learning_rate": 9.858785991002192e-05, "loss": 0.0185, "step": 1700 }, { "epoch": 2.710547184773989, "grad_norm": 0.19516552428750053, "learning_rate": 9.854677259936383e-05, "loss": 0.0179, "step": 1710 }, { "epoch": 2.7264076130055512, "grad_norm": 0.20561324061869957, "learning_rate": 9.85051049063366e-05, "loss": 0.0182, "step": 1720 }, { "epoch": 2.7422680412371134, "grad_norm": 0.1844230160943975, "learning_rate": 9.846285732908238e-05, "loss": 0.0177, "step": 1730 }, { "epoch": 2.7581284694686756, "grad_norm": 0.1890633342236241, "learning_rate": 9.842003037267593e-05, "loss": 0.0174, "step": 1740 }, { "epoch": 2.773988897700238, "grad_norm": 0.1661243506045367, "learning_rate": 9.837662454911855e-05, "loss": 0.0171, "step": 1750 }, { "epoch": 2.7898493259318, "grad_norm": 0.1603089791676492, "learning_rate": 9.833264037733198e-05, "loss": 0.0167, "step": 1760 }, { "epoch": 2.805709754163362, "grad_norm": 0.198488901552779, "learning_rate": 9.82880783831521e-05, "loss": 0.0167, "step": 1770 }, { "epoch": 2.8215701823949244, "grad_norm": 0.17631212946503003, "learning_rate": 9.824293909932285e-05, "loss": 0.0163, "step": 1780 }, { "epoch": 2.837430610626487, "grad_norm": 0.16861160104838285, "learning_rate": 9.819722306548962e-05, "loss": 0.0161, "step": 1790 }, { "epoch": 2.8532910388580492, "grad_norm": 0.19230483320622835, "learning_rate": 9.8150930828193e-05, "loss": 0.0158, "step": 1800 }, { "epoch": 2.8691514670896114, "grad_norm": 0.18577920780634982, "learning_rate": 9.81040629408621e-05, "loss": 0.0154, "step": 1810 }, { "epoch": 2.8850118953211736, "grad_norm": 0.1881494112800731, "learning_rate": 9.805661996380804e-05, "loss": 0.0153, "step": 1820 }, { "epoch": 2.900872323552736, "grad_norm": 0.17869253917833045, "learning_rate": 9.800860246421717e-05, "loss": 0.0151, "step": 1830 }, { "epoch": 2.916732751784298, "grad_norm": 0.17742762061027734, "learning_rate": 9.796001101614434e-05, "loss": 0.0152, "step": 1840 }, { "epoch": 2.9325931800158607, "grad_norm": 0.1830810064948476, "learning_rate": 9.791084620050602e-05, "loss": 0.0151, "step": 1850 }, { "epoch": 2.948453608247423, "grad_norm": 0.20147364949584862, "learning_rate": 9.786110860507336e-05, "loss": 0.0146, "step": 1860 }, { "epoch": 2.964314036478985, "grad_norm": 0.16997448856636277, "learning_rate": 9.781079882446514e-05, "loss": 0.0145, "step": 1870 }, { "epoch": 2.9801744647105473, "grad_norm": 0.1587095515375798, "learning_rate": 9.775991746014072e-05, "loss": 0.0139, "step": 1880 }, { "epoch": 2.9960348929421095, "grad_norm": 0.1983770059337939, "learning_rate": 9.770846512039278e-05, "loss": 0.0143, "step": 1890 }, { "epoch": 3.0111022997620935, "grad_norm": 0.15794198566462234, "learning_rate": 9.765644242034008e-05, "loss": 0.012, "step": 1900 }, { "epoch": 3.0269627279936557, "grad_norm": 0.1739431333762727, "learning_rate": 9.760384998192011e-05, "loss": 0.0109, "step": 1910 }, { "epoch": 3.042823156225218, "grad_norm": 0.14437644637053978, "learning_rate": 9.755068843388166e-05, "loss": 0.0108, "step": 1920 }, { "epoch": 3.05868358445678, "grad_norm": 0.1440694296478373, "learning_rate": 9.749695841177729e-05, "loss": 0.0104, "step": 1930 }, { "epoch": 3.0745440126883428, "grad_norm": 0.14923280981473364, "learning_rate": 9.744266055795568e-05, "loss": 0.0103, "step": 1940 }, { "epoch": 3.090404440919905, "grad_norm": 0.1518629106831049, "learning_rate": 9.738779552155409e-05, "loss": 0.0101, "step": 1950 }, { "epoch": 3.106264869151467, "grad_norm": 0.14823832101551415, "learning_rate": 9.733236395849048e-05, "loss": 0.01, "step": 1960 }, { "epoch": 3.1221252973830294, "grad_norm": 0.14119487110317194, "learning_rate": 9.727636653145567e-05, "loss": 0.0103, "step": 1970 }, { "epoch": 3.1379857256145915, "grad_norm": 0.14471599107467292, "learning_rate": 9.721980390990549e-05, "loss": 0.0099, "step": 1980 }, { "epoch": 3.1538461538461537, "grad_norm": 0.16131116027673068, "learning_rate": 9.716267677005273e-05, "loss": 0.0098, "step": 1990 }, { "epoch": 3.169706582077716, "grad_norm": 0.1524998515238758, "learning_rate": 9.710498579485907e-05, "loss": 0.0099, "step": 2000 }, { "epoch": 3.1855670103092786, "grad_norm": 0.15197353760818177, "learning_rate": 9.704673167402687e-05, "loss": 0.0096, "step": 2010 }, { "epoch": 3.2014274385408408, "grad_norm": 0.14615887528821866, "learning_rate": 9.6987915103991e-05, "loss": 0.0094, "step": 2020 }, { "epoch": 3.217287866772403, "grad_norm": 0.16757614542523475, "learning_rate": 9.692853678791044e-05, "loss": 0.0096, "step": 2030 }, { "epoch": 3.233148295003965, "grad_norm": 0.1563840538926366, "learning_rate": 9.686859743565997e-05, "loss": 0.0095, "step": 2040 }, { "epoch": 3.2490087232355274, "grad_norm": 0.15207509365465333, "learning_rate": 9.680809776382159e-05, "loss": 0.0095, "step": 2050 }, { "epoch": 3.2648691514670896, "grad_norm": 0.1408235208483165, "learning_rate": 9.674703849567594e-05, "loss": 0.0095, "step": 2060 }, { "epoch": 3.2807295796986518, "grad_norm": 0.13678320296028157, "learning_rate": 9.668542036119378e-05, "loss": 0.0094, "step": 2070 }, { "epoch": 3.296590007930214, "grad_norm": 0.16636115763625545, "learning_rate": 9.662324409702715e-05, "loss": 0.0091, "step": 2080 }, { "epoch": 3.312450436161776, "grad_norm": 0.13608061324123708, "learning_rate": 9.656051044650054e-05, "loss": 0.0089, "step": 2090 }, { "epoch": 3.328310864393339, "grad_norm": 0.1431792557439411, "learning_rate": 9.649722015960219e-05, "loss": 0.009, "step": 2100 }, { "epoch": 3.344171292624901, "grad_norm": 0.15687389279462885, "learning_rate": 9.643337399297484e-05, "loss": 0.009, "step": 2110 }, { "epoch": 3.360031720856463, "grad_norm": 0.14839646958379588, "learning_rate": 9.636897270990696e-05, "loss": 0.0087, "step": 2120 }, { "epoch": 3.3758921490880254, "grad_norm": 0.13745612916138747, "learning_rate": 9.630401708032343e-05, "loss": 0.0088, "step": 2130 }, { "epoch": 3.3917525773195876, "grad_norm": 0.15771151005385436, "learning_rate": 9.623850788077645e-05, "loss": 0.0087, "step": 2140 }, { "epoch": 3.4076130055511498, "grad_norm": 0.15078713122784224, "learning_rate": 9.617244589443619e-05, "loss": 0.0086, "step": 2150 }, { "epoch": 3.423473433782712, "grad_norm": 0.13928148814189775, "learning_rate": 9.610583191108145e-05, "loss": 0.0084, "step": 2160 }, { "epoch": 3.4393338620142746, "grad_norm": 0.13689800841443125, "learning_rate": 9.603866672709022e-05, "loss": 0.0084, "step": 2170 }, { "epoch": 3.455194290245837, "grad_norm": 0.13916459530391348, "learning_rate": 9.597095114543018e-05, "loss": 0.0083, "step": 2180 }, { "epoch": 3.471054718477399, "grad_norm": 0.15261756839835933, "learning_rate": 9.590268597564906e-05, "loss": 0.0083, "step": 2190 }, { "epoch": 3.486915146708961, "grad_norm": 0.13702247664859923, "learning_rate": 9.583387203386497e-05, "loss": 0.0081, "step": 2200 }, { "epoch": 3.5027755749405234, "grad_norm": 0.13505439254966808, "learning_rate": 9.576451014275669e-05, "loss": 0.0079, "step": 2210 }, { "epoch": 3.5186360031720856, "grad_norm": 0.13192729341816917, "learning_rate": 9.569460113155378e-05, "loss": 0.0081, "step": 2220 }, { "epoch": 3.5344964314036478, "grad_norm": 0.14259485452290382, "learning_rate": 9.562414583602664e-05, "loss": 0.0078, "step": 2230 }, { "epoch": 3.55035685963521, "grad_norm": 0.1380810668744061, "learning_rate": 9.555314509847663e-05, "loss": 0.0079, "step": 2240 }, { "epoch": 3.566217287866772, "grad_norm": 0.13586211454614464, "learning_rate": 9.548159976772592e-05, "loss": 0.0078, "step": 2250 }, { "epoch": 3.582077716098335, "grad_norm": 0.12201458768486265, "learning_rate": 9.540951069910733e-05, "loss": 0.0078, "step": 2260 }, { "epoch": 3.597938144329897, "grad_norm": 0.13844954643236915, "learning_rate": 9.533687875445414e-05, "loss": 0.0078, "step": 2270 }, { "epoch": 3.613798572561459, "grad_norm": 0.1425114414070632, "learning_rate": 9.526370480208979e-05, "loss": 0.0076, "step": 2280 }, { "epoch": 3.6296590007930214, "grad_norm": 0.2155707350379239, "learning_rate": 9.518998971681748e-05, "loss": 0.008, "step": 2290 }, { "epoch": 3.6455194290245836, "grad_norm": 0.13584009980221787, "learning_rate": 9.511573437990968e-05, "loss": 0.0078, "step": 2300 }, { "epoch": 3.661379857256146, "grad_norm": 0.12951200911833496, "learning_rate": 9.50409396790977e-05, "loss": 0.0076, "step": 2310 }, { "epoch": 3.6772402854877084, "grad_norm": 0.13780278708132593, "learning_rate": 9.496560650856097e-05, "loss": 0.0076, "step": 2320 }, { "epoch": 3.6931007137192706, "grad_norm": 0.14078358511236871, "learning_rate": 9.488973576891638e-05, "loss": 0.0075, "step": 2330 }, { "epoch": 3.708961141950833, "grad_norm": 0.13731645588921648, "learning_rate": 9.481332836720756e-05, "loss": 0.0073, "step": 2340 }, { "epoch": 3.724821570182395, "grad_norm": 0.14229326907743092, "learning_rate": 9.473638521689393e-05, "loss": 0.0073, "step": 2350 }, { "epoch": 3.740681998413957, "grad_norm": 0.1393168463393868, "learning_rate": 9.465890723783992e-05, "loss": 0.0074, "step": 2360 }, { "epoch": 3.7565424266455194, "grad_norm": 0.12400505280500868, "learning_rate": 9.458089535630387e-05, "loss": 0.007, "step": 2370 }, { "epoch": 3.7724028548770816, "grad_norm": 0.14228035248732068, "learning_rate": 9.4502350504927e-05, "loss": 0.0074, "step": 2380 }, { "epoch": 3.788263283108644, "grad_norm": 0.12229258730545413, "learning_rate": 9.44232736227222e-05, "loss": 0.0071, "step": 2390 }, { "epoch": 3.804123711340206, "grad_norm": 0.11833650135887812, "learning_rate": 9.434366565506292e-05, "loss": 0.0069, "step": 2400 }, { "epoch": 3.819984139571768, "grad_norm": 0.1459374639549126, "learning_rate": 9.426352755367174e-05, "loss": 0.0068, "step": 2410 }, { "epoch": 3.835844567803331, "grad_norm": 0.11935347161825668, "learning_rate": 9.418286027660908e-05, "loss": 0.0069, "step": 2420 }, { "epoch": 3.851704996034893, "grad_norm": 0.13102350817072028, "learning_rate": 9.410166478826172e-05, "loss": 0.0067, "step": 2430 }, { "epoch": 3.867565424266455, "grad_norm": 0.1299931124166466, "learning_rate": 9.401994205933127e-05, "loss": 0.0069, "step": 2440 }, { "epoch": 3.8834258524980174, "grad_norm": 0.12080186454827395, "learning_rate": 9.393769306682253e-05, "loss": 0.0064, "step": 2450 }, { "epoch": 3.8992862807295796, "grad_norm": 0.13858427536099355, "learning_rate": 9.385491879403189e-05, "loss": 0.0066, "step": 2460 }, { "epoch": 3.915146708961142, "grad_norm": 0.12403182365468098, "learning_rate": 9.377162023053549e-05, "loss": 0.0065, "step": 2470 }, { "epoch": 3.9310071371927044, "grad_norm": 0.1210866209740134, "learning_rate": 9.368779837217745e-05, "loss": 0.0066, "step": 2480 }, { "epoch": 3.9468675654242666, "grad_norm": 0.1318070654135075, "learning_rate": 9.360345422105793e-05, "loss": 0.0067, "step": 2490 }, { "epoch": 3.962727993655829, "grad_norm": 0.14258951615104107, "learning_rate": 9.351858878552116e-05, "loss": 0.0065, "step": 2500 }, { "epoch": 3.978588421887391, "grad_norm": 0.1204057759444754, "learning_rate": 9.343320308014341e-05, "loss": 0.0064, "step": 2510 }, { "epoch": 3.9944488501189532, "grad_norm": 0.11839457225594427, "learning_rate": 9.334729812572078e-05, "loss": 0.0064, "step": 2520 }, { "epoch": 4.009516256938937, "grad_norm": 0.08540322077120217, "learning_rate": 9.326087494925714e-05, "loss": 0.0053, "step": 2530 }, { "epoch": 4.0253766851704995, "grad_norm": 0.10112676530125538, "learning_rate": 9.317393458395168e-05, "loss": 0.0043, "step": 2540 }, { "epoch": 4.041237113402062, "grad_norm": 0.12529764169062654, "learning_rate": 9.308647806918669e-05, "loss": 0.0039, "step": 2550 }, { "epoch": 4.057097541633624, "grad_norm": 0.0955067824938099, "learning_rate": 9.299850645051506e-05, "loss": 0.0038, "step": 2560 }, { "epoch": 4.072957969865186, "grad_norm": 0.10874795377273988, "learning_rate": 9.291002077964788e-05, "loss": 0.0038, "step": 2570 }, { "epoch": 4.088818398096748, "grad_norm": 0.08668043825795246, "learning_rate": 9.282102211444168e-05, "loss": 0.0036, "step": 2580 }, { "epoch": 4.1046788263283105, "grad_norm": 0.09839554266178921, "learning_rate": 9.273151151888598e-05, "loss": 0.0035, "step": 2590 }, { "epoch": 4.120539254559873, "grad_norm": 0.1078946853176116, "learning_rate": 9.264149006309047e-05, "loss": 0.0036, "step": 2600 }, { "epoch": 4.136399682791436, "grad_norm": 0.08794520025183818, "learning_rate": 9.255095882327223e-05, "loss": 0.0038, "step": 2610 }, { "epoch": 4.152260111022998, "grad_norm": 0.09544438739347859, "learning_rate": 9.245991888174285e-05, "loss": 0.0035, "step": 2620 }, { "epoch": 4.16812053925456, "grad_norm": 0.09704914866906847, "learning_rate": 9.236837132689554e-05, "loss": 0.0036, "step": 2630 }, { "epoch": 4.183980967486122, "grad_norm": 0.09413701678761836, "learning_rate": 9.227631725319206e-05, "loss": 0.0036, "step": 2640 }, { "epoch": 4.1998413957176846, "grad_norm": 0.1249674941120182, "learning_rate": 9.21837577611497e-05, "loss": 0.0036, "step": 2650 }, { "epoch": 4.215701823949247, "grad_norm": 0.09320709700144189, "learning_rate": 9.209069395732802e-05, "loss": 0.0035, "step": 2660 }, { "epoch": 4.231562252180809, "grad_norm": 0.09816492498272372, "learning_rate": 9.199712695431577e-05, "loss": 0.0036, "step": 2670 }, { "epoch": 4.247422680412371, "grad_norm": 0.10786908595610735, "learning_rate": 9.190305787071742e-05, "loss": 0.0035, "step": 2680 }, { "epoch": 4.263283108643933, "grad_norm": 0.08480594239364594, "learning_rate": 9.180848783113996e-05, "loss": 0.0034, "step": 2690 }, { "epoch": 4.2791435368754955, "grad_norm": 0.09241037627689046, "learning_rate": 9.171341796617927e-05, "loss": 0.0035, "step": 2700 }, { "epoch": 4.295003965107058, "grad_norm": 0.10223555985966222, "learning_rate": 9.161784941240681e-05, "loss": 0.0035, "step": 2710 }, { "epoch": 4.31086439333862, "grad_norm": 0.12709742861011547, "learning_rate": 9.152178331235581e-05, "loss": 0.0036, "step": 2720 }, { "epoch": 4.326724821570182, "grad_norm": 0.10916240205541296, "learning_rate": 9.142522081450783e-05, "loss": 0.0036, "step": 2730 }, { "epoch": 4.342585249801744, "grad_norm": 0.1004166247257912, "learning_rate": 9.132816307327886e-05, "loss": 0.0035, "step": 2740 }, { "epoch": 4.3584456780333065, "grad_norm": 0.1053220173193627, "learning_rate": 9.123061124900556e-05, "loss": 0.0036, "step": 2750 }, { "epoch": 4.37430610626487, "grad_norm": 0.10781630634201299, "learning_rate": 9.113256650793149e-05, "loss": 0.0038, "step": 2760 }, { "epoch": 4.390166534496432, "grad_norm": 0.15441377221263897, "learning_rate": 9.103403002219305e-05, "loss": 0.0038, "step": 2770 }, { "epoch": 4.406026962727994, "grad_norm": 0.1145440846539534, "learning_rate": 9.093500296980548e-05, "loss": 0.0037, "step": 2780 }, { "epoch": 4.421887390959556, "grad_norm": 0.10014929941903501, "learning_rate": 9.083548653464884e-05, "loss": 0.0036, "step": 2790 }, { "epoch": 4.437747819191118, "grad_norm": 0.10575652642767745, "learning_rate": 9.073548190645378e-05, "loss": 0.0036, "step": 2800 }, { "epoch": 4.453608247422681, "grad_norm": 0.09967090608925282, "learning_rate": 9.063499028078741e-05, "loss": 0.0035, "step": 2810 }, { "epoch": 4.469468675654243, "grad_norm": 0.08849883488694847, "learning_rate": 9.053401285903889e-05, "loss": 0.0035, "step": 2820 }, { "epoch": 4.485329103885805, "grad_norm": 0.10136493808207836, "learning_rate": 9.043255084840517e-05, "loss": 0.0037, "step": 2830 }, { "epoch": 4.501189532117367, "grad_norm": 0.08898247112970178, "learning_rate": 9.03306054618765e-05, "loss": 0.0035, "step": 2840 }, { "epoch": 4.517049960348929, "grad_norm": 0.09208854129111659, "learning_rate": 9.022817791822198e-05, "loss": 0.0036, "step": 2850 }, { "epoch": 4.532910388580492, "grad_norm": 0.09961222712616437, "learning_rate": 9.012526944197488e-05, "loss": 0.0035, "step": 2860 }, { "epoch": 4.548770816812054, "grad_norm": 0.10356990211947537, "learning_rate": 9.002188126341815e-05, "loss": 0.0035, "step": 2870 }, { "epoch": 4.564631245043616, "grad_norm": 0.10880605758798846, "learning_rate": 8.991801461856961e-05, "loss": 0.0034, "step": 2880 }, { "epoch": 4.580491673275178, "grad_norm": 0.09025089948749608, "learning_rate": 8.98136707491672e-05, "loss": 0.0034, "step": 2890 }, { "epoch": 4.59635210150674, "grad_norm": 0.0948081759012918, "learning_rate": 8.970885090265413e-05, "loss": 0.0036, "step": 2900 }, { "epoch": 4.6122125297383025, "grad_norm": 0.10862619774623498, "learning_rate": 8.960355633216397e-05, "loss": 0.0035, "step": 2910 }, { "epoch": 4.628072957969865, "grad_norm": 0.0968778686048629, "learning_rate": 8.94977882965057e-05, "loss": 0.0036, "step": 2920 }, { "epoch": 4.643933386201428, "grad_norm": 0.09951637896006683, "learning_rate": 8.939154806014857e-05, "loss": 0.0035, "step": 2930 }, { "epoch": 4.65979381443299, "grad_norm": 0.10284890386755276, "learning_rate": 8.928483689320714e-05, "loss": 0.0035, "step": 2940 }, { "epoch": 4.675654242664552, "grad_norm": 0.12021152095203591, "learning_rate": 8.917765607142594e-05, "loss": 0.0036, "step": 2950 }, { "epoch": 4.691514670896114, "grad_norm": 0.10094042369158501, "learning_rate": 8.907000687616423e-05, "loss": 0.0037, "step": 2960 }, { "epoch": 4.707375099127677, "grad_norm": 0.12159048686884875, "learning_rate": 8.896189059438083e-05, "loss": 0.0035, "step": 2970 }, { "epoch": 4.723235527359239, "grad_norm": 0.09516680996052305, "learning_rate": 8.885330851861858e-05, "loss": 0.0035, "step": 2980 }, { "epoch": 4.739095955590801, "grad_norm": 0.10722002700044025, "learning_rate": 8.874426194698895e-05, "loss": 0.0036, "step": 2990 }, { "epoch": 4.754956383822363, "grad_norm": 0.09312639306042723, "learning_rate": 8.86347521831565e-05, "loss": 0.0034, "step": 3000 }, { "epoch": 4.770816812053925, "grad_norm": 0.10519488774048268, "learning_rate": 8.852478053632335e-05, "loss": 0.0035, "step": 3010 }, { "epoch": 4.786677240285488, "grad_norm": 0.09594602135358007, "learning_rate": 8.841434832121345e-05, "loss": 0.0036, "step": 3020 }, { "epoch": 4.80253766851705, "grad_norm": 0.08866775532281909, "learning_rate": 8.830345685805688e-05, "loss": 0.0035, "step": 3030 }, { "epoch": 4.818398096748612, "grad_norm": 0.09703766154369026, "learning_rate": 8.819210747257412e-05, "loss": 0.0033, "step": 3040 }, { "epoch": 4.834258524980174, "grad_norm": 0.09385784638715457, "learning_rate": 8.808030149596017e-05, "loss": 0.0034, "step": 3050 }, { "epoch": 4.850118953211736, "grad_norm": 0.10558045718553939, "learning_rate": 8.796804026486858e-05, "loss": 0.0034, "step": 3060 }, { "epoch": 4.8659793814432994, "grad_norm": 0.11749294827599736, "learning_rate": 8.785532512139558e-05, "loss": 0.0035, "step": 3070 }, { "epoch": 4.881839809674862, "grad_norm": 0.10210710172882062, "learning_rate": 8.774215741306395e-05, "loss": 0.0036, "step": 3080 }, { "epoch": 4.897700237906424, "grad_norm": 0.10464813148086784, "learning_rate": 8.762853849280693e-05, "loss": 0.0037, "step": 3090 }, { "epoch": 4.913560666137986, "grad_norm": 0.10471907357639558, "learning_rate": 8.751446971895206e-05, "loss": 0.0036, "step": 3100 }, { "epoch": 4.929421094369548, "grad_norm": 0.07894542756752126, "learning_rate": 8.739995245520492e-05, "loss": 0.0034, "step": 3110 }, { "epoch": 4.94528152260111, "grad_norm": 0.09286574927632184, "learning_rate": 8.728498807063288e-05, "loss": 0.0035, "step": 3120 }, { "epoch": 4.961141950832673, "grad_norm": 0.08571307419176223, "learning_rate": 8.716957793964864e-05, "loss": 0.0034, "step": 3130 }, { "epoch": 4.977002379064235, "grad_norm": 0.0965051873600371, "learning_rate": 8.705372344199387e-05, "loss": 0.0034, "step": 3140 }, { "epoch": 4.992862807295797, "grad_norm": 0.13496799817499566, "learning_rate": 8.69374259627227e-05, "loss": 0.0037, "step": 3150 }, { "epoch": 5.007930214115781, "grad_norm": 0.08289025036640724, "learning_rate": 8.682068689218517e-05, "loss": 0.0031, "step": 3160 }, { "epoch": 5.023790642347343, "grad_norm": 0.07226843684662153, "learning_rate": 8.670350762601059e-05, "loss": 0.0024, "step": 3170 }, { "epoch": 5.0396510705789055, "grad_norm": 0.06521417712763433, "learning_rate": 8.658588956509079e-05, "loss": 0.0021, "step": 3180 }, { "epoch": 5.055511498810468, "grad_norm": 0.07961399017197436, "learning_rate": 8.646783411556359e-05, "loss": 0.0018, "step": 3190 }, { "epoch": 5.07137192704203, "grad_norm": 0.08645502226538618, "learning_rate": 8.63493426887957e-05, "loss": 0.0017, "step": 3200 }, { "epoch": 5.087232355273592, "grad_norm": 0.07963006292300003, "learning_rate": 8.623041670136606e-05, "loss": 0.0016, "step": 3210 }, { "epoch": 5.103092783505154, "grad_norm": 0.06181791334855889, "learning_rate": 8.611105757504883e-05, "loss": 0.0017, "step": 3220 }, { "epoch": 5.1189532117367165, "grad_norm": 0.06988096800556821, "learning_rate": 8.599126673679636e-05, "loss": 0.0017, "step": 3230 }, { "epoch": 5.1348136399682796, "grad_norm": 0.08328659822255369, "learning_rate": 8.587104561872224e-05, "loss": 0.0017, "step": 3240 }, { "epoch": 5.150674068199842, "grad_norm": 0.11782439513762667, "learning_rate": 8.5750395658084e-05, "loss": 0.0017, "step": 3250 }, { "epoch": 5.166534496431404, "grad_norm": 0.09235663805764693, "learning_rate": 8.562931829726615e-05, "loss": 0.0018, "step": 3260 }, { "epoch": 5.182394924662966, "grad_norm": 0.07917233858457466, "learning_rate": 8.55078149837627e-05, "loss": 0.0018, "step": 3270 }, { "epoch": 5.198255352894528, "grad_norm": 0.07720468137565101, "learning_rate": 8.53858871701601e-05, "loss": 0.0018, "step": 3280 }, { "epoch": 5.2141157811260905, "grad_norm": 0.06460403408535213, "learning_rate": 8.526353631411965e-05, "loss": 0.0016, "step": 3290 }, { "epoch": 5.229976209357653, "grad_norm": 0.0696806022225143, "learning_rate": 8.514076387836021e-05, "loss": 0.0016, "step": 3300 }, { "epoch": 5.245836637589215, "grad_norm": 0.07170050913505419, "learning_rate": 8.501757133064065e-05, "loss": 0.0016, "step": 3310 }, { "epoch": 5.261697065820777, "grad_norm": 0.0661054241095149, "learning_rate": 8.489396014374237e-05, "loss": 0.0016, "step": 3320 }, { "epoch": 5.277557494052339, "grad_norm": 0.07387953260990546, "learning_rate": 8.476993179545166e-05, "loss": 0.0016, "step": 3330 }, { "epoch": 5.2934179222839015, "grad_norm": 0.06220099525799539, "learning_rate": 8.464548776854195e-05, "loss": 0.0017, "step": 3340 }, { "epoch": 5.309278350515464, "grad_norm": 0.06919342191387491, "learning_rate": 8.452062955075621e-05, "loss": 0.0016, "step": 3350 }, { "epoch": 5.325138778747026, "grad_norm": 0.069239564548577, "learning_rate": 8.43953586347891e-05, "loss": 0.0016, "step": 3360 }, { "epoch": 5.340999206978588, "grad_norm": 0.057485269571037244, "learning_rate": 8.426967651826914e-05, "loss": 0.0015, "step": 3370 }, { "epoch": 5.35685963521015, "grad_norm": 0.06475405169843909, "learning_rate": 8.41435847037408e-05, "loss": 0.0015, "step": 3380 }, { "epoch": 5.372720063441713, "grad_norm": 0.07618561528999164, "learning_rate": 8.401708469864653e-05, "loss": 0.0017, "step": 3390 }, { "epoch": 5.388580491673276, "grad_norm": 0.0754261896183142, "learning_rate": 8.389017801530875e-05, "loss": 0.0016, "step": 3400 }, { "epoch": 5.404440919904838, "grad_norm": 0.07800671155500213, "learning_rate": 8.376286617091178e-05, "loss": 0.0016, "step": 3410 }, { "epoch": 5.4203013481364, "grad_norm": 0.07636728277995097, "learning_rate": 8.363515068748364e-05, "loss": 0.0016, "step": 3420 }, { "epoch": 5.436161776367962, "grad_norm": 0.06974545329253266, "learning_rate": 8.350703309187798e-05, "loss": 0.0015, "step": 3430 }, { "epoch": 5.452022204599524, "grad_norm": 0.08486131169745545, "learning_rate": 8.337851491575568e-05, "loss": 0.0016, "step": 3440 }, { "epoch": 5.4678826328310866, "grad_norm": 0.10177268913062058, "learning_rate": 8.324959769556664e-05, "loss": 0.0017, "step": 3450 }, { "epoch": 5.483743061062649, "grad_norm": 0.07544977089684703, "learning_rate": 8.312028297253136e-05, "loss": 0.0017, "step": 3460 }, { "epoch": 5.499603489294211, "grad_norm": 0.08117648495668406, "learning_rate": 8.299057229262256e-05, "loss": 0.0017, "step": 3470 }, { "epoch": 5.515463917525773, "grad_norm": 0.07640679176251267, "learning_rate": 8.286046720654665e-05, "loss": 0.0017, "step": 3480 }, { "epoch": 5.531324345757335, "grad_norm": 0.079522193457805, "learning_rate": 8.27299692697252e-05, "loss": 0.0017, "step": 3490 }, { "epoch": 5.5471847739888975, "grad_norm": 0.07722026998309503, "learning_rate": 8.259908004227641e-05, "loss": 0.0018, "step": 3500 }, { "epoch": 5.56304520222046, "grad_norm": 0.08587811490541557, "learning_rate": 8.246780108899635e-05, "loss": 0.0019, "step": 3510 }, { "epoch": 5.578905630452022, "grad_norm": 0.21112988448424747, "learning_rate": 8.23361339793403e-05, "loss": 0.002, "step": 3520 }, { "epoch": 5.594766058683584, "grad_norm": 0.2731446862713363, "learning_rate": 8.220408028740407e-05, "loss": 0.0032, "step": 3530 }, { "epoch": 5.610626486915146, "grad_norm": 0.1379133248787839, "learning_rate": 8.207164159190503e-05, "loss": 0.0037, "step": 3540 }, { "epoch": 5.6264869151467085, "grad_norm": 0.09288443542654805, "learning_rate": 8.193881947616337e-05, "loss": 0.0024, "step": 3550 }, { "epoch": 5.642347343378272, "grad_norm": 0.1024679954754957, "learning_rate": 8.180561552808306e-05, "loss": 0.0021, "step": 3560 }, { "epoch": 5.658207771609834, "grad_norm": 0.08696933128166198, "learning_rate": 8.167203134013295e-05, "loss": 0.0021, "step": 3570 }, { "epoch": 5.674068199841396, "grad_norm": 0.07453735269493612, "learning_rate": 8.15380685093277e-05, "loss": 0.002, "step": 3580 }, { "epoch": 5.689928628072958, "grad_norm": 0.07288118742234356, "learning_rate": 8.140372863720868e-05, "loss": 0.0021, "step": 3590 }, { "epoch": 5.70578905630452, "grad_norm": 0.07358612936238743, "learning_rate": 8.126901332982486e-05, "loss": 0.0019, "step": 3600 } ], "logging_steps": 10, "max_steps": 10096, "num_input_tokens_seen": 0, "num_train_epochs": 16, "save_steps": 1800, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 258860064964608.0, "train_batch_size": 128, "trial_name": null, "trial_params": null }