diff --git "a/checkpoint-10000/trainer_state.json" "b/checkpoint-10000/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-10000/trainer_state.json" @@ -0,0 +1,6066 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.45320643553138457, + "eval_steps": 2000, + "global_step": 10000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.0000000000000003e-06, + "loss": 6.5194, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 4.000000000000001e-06, + "loss": 6.4472, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 6e-06, + "loss": 6.313, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 8.000000000000001e-06, + "loss": 6.188, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 1e-05, + "loss": 6.0095, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 1.2e-05, + "loss": 5.8336, + "step": 60 + }, + { + "epoch": 0.0, + "learning_rate": 1.4e-05, + "loss": 5.4948, + "step": 70 + }, + { + "epoch": 0.0, + "learning_rate": 1.6000000000000003e-05, + "loss": 5.2933, + "step": 80 + }, + { + "epoch": 0.0, + "learning_rate": 1.8e-05, + "loss": 4.908, + "step": 90 + }, + { + "epoch": 0.0, + "learning_rate": 2e-05, + "loss": 4.6039, + "step": 100 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999989771610435e-05, + "loss": 4.37, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 1.9999959086462666e-05, + "loss": 4.2062, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 1.999990794461946e-05, + "loss": 4.0018, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 1.999983634618544e-05, + "loss": 3.914, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 1.9999744291307077e-05, + "loss": 3.7417, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 1.9999631780172678e-05, + "loss": 3.652, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 1.999949881301241e-05, + "loss": 3.6293, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 1.9999345390098276e-05, + "loss": 3.5554, + "step": 180 + }, + { + "epoch": 0.01, + "learning_rate": 1.9999171511744134e-05, + "loss": 3.4717, + "step": 190 + }, + { + "epoch": 0.01, + "learning_rate": 1.9998977178305683e-05, + "loss": 3.3474, + "step": 200 + }, + { + "epoch": 0.01, + "learning_rate": 1.9998762390180467e-05, + "loss": 3.3879, + "step": 210 + }, + { + "epoch": 0.01, + "learning_rate": 1.999852714780787e-05, + "loss": 3.3087, + "step": 220 + }, + { + "epoch": 0.01, + "learning_rate": 1.9998271451669127e-05, + "loss": 3.2531, + "step": 230 + }, + { + "epoch": 0.01, + "learning_rate": 1.9997995302287306e-05, + "loss": 3.2259, + "step": 240 + }, + { + "epoch": 0.01, + "learning_rate": 1.999769870022732e-05, + "loss": 3.1982, + "step": 250 + }, + { + "epoch": 0.01, + "learning_rate": 1.9997381646095923e-05, + "loss": 3.2029, + "step": 260 + }, + { + "epoch": 0.01, + "learning_rate": 1.9997044140541704e-05, + "loss": 3.1327, + "step": 270 + }, + { + "epoch": 0.01, + "learning_rate": 1.9996686184255093e-05, + "loss": 3.1122, + "step": 280 + }, + { + "epoch": 0.01, + "learning_rate": 1.999630777796835e-05, + "loss": 3.0607, + "step": 290 + }, + { + "epoch": 0.01, + "learning_rate": 1.9995908922455574e-05, + "loss": 3.0865, + "step": 300 + }, + { + "epoch": 0.01, + "learning_rate": 1.9995489618532696e-05, + "loss": 3.0345, + "step": 310 + }, + { + "epoch": 0.01, + "learning_rate": 1.9995049867057475e-05, + "loss": 3.066, + "step": 320 + }, + { + "epoch": 0.01, + "learning_rate": 1.99945896689295e-05, + "loss": 3.0605, + "step": 330 + }, + { + "epoch": 0.02, + "learning_rate": 1.9994109025090193e-05, + "loss": 2.9867, + "step": 340 + }, + { + "epoch": 0.02, + "learning_rate": 1.9993607936522795e-05, + "loss": 2.9954, + "step": 350 + }, + { + "epoch": 0.02, + "learning_rate": 1.9993086404252368e-05, + "loss": 2.9902, + "step": 360 + }, + { + "epoch": 0.02, + "learning_rate": 1.99925444293458e-05, + "loss": 2.967, + "step": 370 + }, + { + "epoch": 0.02, + "learning_rate": 1.9991982012911796e-05, + "loss": 2.9373, + "step": 380 + }, + { + "epoch": 0.02, + "learning_rate": 1.9991399156100888e-05, + "loss": 2.9242, + "step": 390 + }, + { + "epoch": 0.02, + "learning_rate": 1.99907958601054e-05, + "loss": 2.8879, + "step": 400 + }, + { + "epoch": 0.02, + "learning_rate": 1.9990172126159493e-05, + "loss": 2.8951, + "step": 410 + }, + { + "epoch": 0.02, + "learning_rate": 1.9989527955539117e-05, + "loss": 2.9223, + "step": 420 + }, + { + "epoch": 0.02, + "learning_rate": 1.998886334956204e-05, + "loss": 2.9071, + "step": 430 + }, + { + "epoch": 0.02, + "learning_rate": 1.9988178309587834e-05, + "loss": 2.8767, + "step": 440 + }, + { + "epoch": 0.02, + "learning_rate": 1.9987472837017875e-05, + "loss": 2.8798, + "step": 450 + }, + { + "epoch": 0.02, + "learning_rate": 1.998674693329532e-05, + "loss": 2.8751, + "step": 460 + }, + { + "epoch": 0.02, + "learning_rate": 1.9986000599905144e-05, + "loss": 2.8694, + "step": 470 + }, + { + "epoch": 0.02, + "learning_rate": 1.9985233838374095e-05, + "loss": 2.8434, + "step": 480 + }, + { + "epoch": 0.02, + "learning_rate": 1.9984446650270735e-05, + "loss": 2.8669, + "step": 490 + }, + { + "epoch": 0.02, + "learning_rate": 1.9983639037205383e-05, + "loss": 2.8698, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 1.9982811000830168e-05, + "loss": 2.7942, + "step": 510 + }, + { + "epoch": 0.02, + "learning_rate": 1.9981962542838973e-05, + "loss": 2.8396, + "step": 520 + }, + { + "epoch": 0.02, + "learning_rate": 1.998109366496748e-05, + "loss": 2.8324, + "step": 530 + }, + { + "epoch": 0.02, + "learning_rate": 1.9980204368993125e-05, + "loss": 2.8112, + "step": 540 + }, + { + "epoch": 0.02, + "learning_rate": 1.9979294656735128e-05, + "loss": 2.789, + "step": 550 + }, + { + "epoch": 0.03, + "learning_rate": 1.9978364530054465e-05, + "loss": 2.7973, + "step": 560 + }, + { + "epoch": 0.03, + "learning_rate": 1.997741399085387e-05, + "loss": 2.7944, + "step": 570 + }, + { + "epoch": 0.03, + "learning_rate": 1.997644304107785e-05, + "loss": 2.8026, + "step": 580 + }, + { + "epoch": 0.03, + "learning_rate": 1.9975451682712653e-05, + "loss": 2.7717, + "step": 590 + }, + { + "epoch": 0.03, + "learning_rate": 1.997443991778627e-05, + "loss": 2.7765, + "step": 600 + }, + { + "epoch": 0.03, + "learning_rate": 1.9973407748368456e-05, + "loss": 2.7911, + "step": 610 + }, + { + "epoch": 0.03, + "learning_rate": 1.9972355176570695e-05, + "loss": 2.7744, + "step": 620 + }, + { + "epoch": 0.03, + "learning_rate": 1.9971282204546206e-05, + "loss": 2.7749, + "step": 630 + }, + { + "epoch": 0.03, + "learning_rate": 1.997018883448995e-05, + "loss": 2.7949, + "step": 640 + }, + { + "epoch": 0.03, + "learning_rate": 1.9969075068638603e-05, + "loss": 2.73, + "step": 650 + }, + { + "epoch": 0.03, + "learning_rate": 1.996794090927058e-05, + "loss": 2.7475, + "step": 660 + }, + { + "epoch": 0.03, + "learning_rate": 1.9966786358705997e-05, + "loss": 2.7215, + "step": 670 + }, + { + "epoch": 0.03, + "learning_rate": 1.9965611419306697e-05, + "loss": 2.7395, + "step": 680 + }, + { + "epoch": 0.03, + "learning_rate": 1.9964416093476227e-05, + "loss": 2.7544, + "step": 690 + }, + { + "epoch": 0.03, + "learning_rate": 1.996320038365984e-05, + "loss": 2.7504, + "step": 700 + }, + { + "epoch": 0.03, + "learning_rate": 1.9961964292344485e-05, + "loss": 2.7467, + "step": 710 + }, + { + "epoch": 0.03, + "learning_rate": 1.9960707822058807e-05, + "loss": 2.7522, + "step": 720 + }, + { + "epoch": 0.03, + "learning_rate": 1.995943097537314e-05, + "loss": 2.7601, + "step": 730 + }, + { + "epoch": 0.03, + "learning_rate": 1.99581337548995e-05, + "loss": 2.7437, + "step": 740 + }, + { + "epoch": 0.03, + "learning_rate": 1.9956816163291583e-05, + "loss": 2.7516, + "step": 750 + }, + { + "epoch": 0.03, + "learning_rate": 1.9955478203244758e-05, + "loss": 2.7282, + "step": 760 + }, + { + "epoch": 0.03, + "learning_rate": 1.9954119877496058e-05, + "loss": 2.7259, + "step": 770 + }, + { + "epoch": 0.04, + "learning_rate": 1.995274118882418e-05, + "loss": 2.7284, + "step": 780 + }, + { + "epoch": 0.04, + "learning_rate": 1.9951342140049483e-05, + "loss": 2.723, + "step": 790 + }, + { + "epoch": 0.04, + "learning_rate": 1.9949922734033958e-05, + "loss": 2.7367, + "step": 800 + }, + { + "epoch": 0.04, + "learning_rate": 1.9948482973681267e-05, + "loss": 2.7136, + "step": 810 + }, + { + "epoch": 0.04, + "learning_rate": 1.9947022861936686e-05, + "loss": 2.7344, + "step": 820 + }, + { + "epoch": 0.04, + "learning_rate": 1.9945542401787137e-05, + "loss": 2.7196, + "step": 830 + }, + { + "epoch": 0.04, + "learning_rate": 1.9944041596261162e-05, + "loss": 2.7228, + "step": 840 + }, + { + "epoch": 0.04, + "learning_rate": 1.994252044842893e-05, + "loss": 2.6978, + "step": 850 + }, + { + "epoch": 0.04, + "learning_rate": 1.9940978961402217e-05, + "loss": 2.7169, + "step": 860 + }, + { + "epoch": 0.04, + "learning_rate": 1.993941713833441e-05, + "loss": 2.7058, + "step": 870 + }, + { + "epoch": 0.04, + "learning_rate": 1.9937834982420492e-05, + "loss": 2.7083, + "step": 880 + }, + { + "epoch": 0.04, + "learning_rate": 1.993623249689705e-05, + "loss": 2.7348, + "step": 890 + }, + { + "epoch": 0.04, + "learning_rate": 1.9934609685042248e-05, + "loss": 2.7023, + "step": 900 + }, + { + "epoch": 0.04, + "learning_rate": 1.9932966550175842e-05, + "loss": 2.69, + "step": 910 + }, + { + "epoch": 0.04, + "learning_rate": 1.9931303095659153e-05, + "loss": 2.6818, + "step": 920 + }, + { + "epoch": 0.04, + "learning_rate": 1.9929619324895074e-05, + "loss": 2.724, + "step": 930 + }, + { + "epoch": 0.04, + "learning_rate": 1.9927915241328056e-05, + "loss": 2.6865, + "step": 940 + }, + { + "epoch": 0.04, + "learning_rate": 1.992619084844411e-05, + "loss": 2.6784, + "step": 950 + }, + { + "epoch": 0.04, + "learning_rate": 1.992444614977078e-05, + "loss": 2.6982, + "step": 960 + }, + { + "epoch": 0.04, + "learning_rate": 1.992268114887717e-05, + "loss": 2.698, + "step": 970 + }, + { + "epoch": 0.04, + "learning_rate": 1.992089584937389e-05, + "loss": 2.6747, + "step": 980 + }, + { + "epoch": 0.04, + "learning_rate": 1.9919090254913095e-05, + "loss": 2.6793, + "step": 990 + }, + { + "epoch": 0.05, + "learning_rate": 1.9917264369188453e-05, + "loss": 2.685, + "step": 1000 + }, + { + "epoch": 0.05, + "learning_rate": 1.9915418195935128e-05, + "loss": 2.6685, + "step": 1010 + }, + { + "epoch": 0.05, + "learning_rate": 1.9913551738929803e-05, + "loss": 2.672, + "step": 1020 + }, + { + "epoch": 0.05, + "learning_rate": 1.9911665001990648e-05, + "loss": 2.7005, + "step": 1030 + }, + { + "epoch": 0.05, + "learning_rate": 1.9909757988977315e-05, + "loss": 2.678, + "step": 1040 + }, + { + "epoch": 0.05, + "learning_rate": 1.9907830703790943e-05, + "loss": 2.6533, + "step": 1050 + }, + { + "epoch": 0.05, + "learning_rate": 1.9905883150374134e-05, + "loss": 2.6703, + "step": 1060 + }, + { + "epoch": 0.05, + "learning_rate": 1.9903915332710952e-05, + "loss": 2.6778, + "step": 1070 + }, + { + "epoch": 0.05, + "learning_rate": 1.990192725482693e-05, + "loss": 2.6672, + "step": 1080 + }, + { + "epoch": 0.05, + "learning_rate": 1.9899918920789017e-05, + "loss": 2.6442, + "step": 1090 + }, + { + "epoch": 0.05, + "learning_rate": 1.9897890334705636e-05, + "loss": 2.662, + "step": 1100 + }, + { + "epoch": 0.05, + "learning_rate": 1.9895841500726606e-05, + "loss": 2.6608, + "step": 1110 + }, + { + "epoch": 0.05, + "learning_rate": 1.9893772423043188e-05, + "loss": 2.6562, + "step": 1120 + }, + { + "epoch": 0.05, + "learning_rate": 1.9891683105888048e-05, + "loss": 2.6866, + "step": 1130 + }, + { + "epoch": 0.05, + "learning_rate": 1.9889573553535258e-05, + "loss": 2.6592, + "step": 1140 + }, + { + "epoch": 0.05, + "learning_rate": 1.988744377030028e-05, + "loss": 2.6526, + "step": 1150 + }, + { + "epoch": 0.05, + "learning_rate": 1.988529376053997e-05, + "loss": 2.644, + "step": 1160 + }, + { + "epoch": 0.05, + "learning_rate": 1.988312352865254e-05, + "loss": 2.6692, + "step": 1170 + }, + { + "epoch": 0.05, + "learning_rate": 1.9880933079077605e-05, + "loss": 2.663, + "step": 1180 + }, + { + "epoch": 0.05, + "learning_rate": 1.9878722416296104e-05, + "loss": 2.6357, + "step": 1190 + }, + { + "epoch": 0.05, + "learning_rate": 1.9876491544830352e-05, + "loss": 2.6277, + "step": 1200 + }, + { + "epoch": 0.05, + "learning_rate": 1.9874240469243987e-05, + "loss": 2.6691, + "step": 1210 + }, + { + "epoch": 0.06, + "learning_rate": 1.9871969194141985e-05, + "loss": 2.6788, + "step": 1220 + }, + { + "epoch": 0.06, + "learning_rate": 1.986967772417065e-05, + "loss": 2.6312, + "step": 1230 + }, + { + "epoch": 0.06, + "learning_rate": 1.9867366064017584e-05, + "loss": 2.6423, + "step": 1240 + }, + { + "epoch": 0.06, + "learning_rate": 1.9865034218411698e-05, + "loss": 2.6013, + "step": 1250 + }, + { + "epoch": 0.06, + "learning_rate": 1.9862682192123203e-05, + "loss": 2.6355, + "step": 1260 + }, + { + "epoch": 0.06, + "learning_rate": 1.9860309989963585e-05, + "loss": 2.6463, + "step": 1270 + }, + { + "epoch": 0.06, + "learning_rate": 1.9857917616785606e-05, + "loss": 2.6404, + "step": 1280 + }, + { + "epoch": 0.06, + "learning_rate": 1.9855505077483288e-05, + "loss": 2.6601, + "step": 1290 + }, + { + "epoch": 0.06, + "learning_rate": 1.9853072376991913e-05, + "loss": 2.6469, + "step": 1300 + }, + { + "epoch": 0.06, + "learning_rate": 1.9850619520288e-05, + "loss": 2.6393, + "step": 1310 + }, + { + "epoch": 0.06, + "learning_rate": 1.9848146512389305e-05, + "loss": 2.6231, + "step": 1320 + }, + { + "epoch": 0.06, + "learning_rate": 1.984565335835481e-05, + "loss": 2.6386, + "step": 1330 + }, + { + "epoch": 0.06, + "learning_rate": 1.9843140063284694e-05, + "loss": 2.6451, + "step": 1340 + }, + { + "epoch": 0.06, + "learning_rate": 1.9840606632320362e-05, + "loss": 2.6009, + "step": 1350 + }, + { + "epoch": 0.06, + "learning_rate": 1.9838053070644388e-05, + "loss": 2.621, + "step": 1360 + }, + { + "epoch": 0.06, + "learning_rate": 1.983547938348054e-05, + "loss": 2.633, + "step": 1370 + }, + { + "epoch": 0.06, + "learning_rate": 1.9832885576093755e-05, + "loss": 2.6157, + "step": 1380 + }, + { + "epoch": 0.06, + "learning_rate": 1.983027165379013e-05, + "loss": 2.6275, + "step": 1390 + }, + { + "epoch": 0.06, + "learning_rate": 1.9827637621916897e-05, + "loss": 2.6063, + "step": 1400 + }, + { + "epoch": 0.06, + "learning_rate": 1.9824983485862446e-05, + "loss": 2.6351, + "step": 1410 + }, + { + "epoch": 0.06, + "learning_rate": 1.9822309251056286e-05, + "loss": 2.6623, + "step": 1420 + }, + { + "epoch": 0.06, + "learning_rate": 1.981961492296903e-05, + "loss": 2.6489, + "step": 1430 + }, + { + "epoch": 0.07, + "learning_rate": 1.981690050711242e-05, + "loss": 2.6471, + "step": 1440 + }, + { + "epoch": 0.07, + "learning_rate": 1.9814166009039266e-05, + "loss": 2.6274, + "step": 1450 + }, + { + "epoch": 0.07, + "learning_rate": 1.9811411434343467e-05, + "loss": 2.633, + "step": 1460 + }, + { + "epoch": 0.07, + "learning_rate": 1.9808636788660008e-05, + "loss": 2.6094, + "step": 1470 + }, + { + "epoch": 0.07, + "learning_rate": 1.9805842077664913e-05, + "loss": 2.6053, + "step": 1480 + }, + { + "epoch": 0.07, + "learning_rate": 1.9803027307075258e-05, + "loss": 2.6303, + "step": 1490 + }, + { + "epoch": 0.07, + "learning_rate": 1.9800192482649164e-05, + "loss": 2.6214, + "step": 1500 + }, + { + "epoch": 0.07, + "learning_rate": 1.9797337610185763e-05, + "loss": 2.6238, + "step": 1510 + }, + { + "epoch": 0.07, + "learning_rate": 1.979446269552521e-05, + "loss": 2.6193, + "step": 1520 + }, + { + "epoch": 0.07, + "learning_rate": 1.9791567744548644e-05, + "loss": 2.6114, + "step": 1530 + }, + { + "epoch": 0.07, + "learning_rate": 1.9788652763178215e-05, + "loss": 2.6314, + "step": 1540 + }, + { + "epoch": 0.07, + "learning_rate": 1.9785717757377033e-05, + "loss": 2.6047, + "step": 1550 + }, + { + "epoch": 0.07, + "learning_rate": 1.9782762733149167e-05, + "loss": 2.6028, + "step": 1560 + }, + { + "epoch": 0.07, + "learning_rate": 1.977978769653965e-05, + "loss": 2.6117, + "step": 1570 + }, + { + "epoch": 0.07, + "learning_rate": 1.977679265363445e-05, + "loss": 2.603, + "step": 1580 + }, + { + "epoch": 0.07, + "learning_rate": 1.9773777610560458e-05, + "loss": 2.5901, + "step": 1590 + }, + { + "epoch": 0.07, + "learning_rate": 1.977074257348548e-05, + "loss": 2.6346, + "step": 1600 + }, + { + "epoch": 0.07, + "learning_rate": 1.9767687548618227e-05, + "loss": 2.5964, + "step": 1610 + }, + { + "epoch": 0.07, + "learning_rate": 1.9764612542208297e-05, + "loss": 2.6068, + "step": 1620 + }, + { + "epoch": 0.07, + "learning_rate": 1.976151756054616e-05, + "loss": 2.5897, + "step": 1630 + }, + { + "epoch": 0.07, + "learning_rate": 1.975840260996315e-05, + "loss": 2.6059, + "step": 1640 + }, + { + "epoch": 0.07, + "learning_rate": 1.9755267696831454e-05, + "loss": 2.6095, + "step": 1650 + }, + { + "epoch": 0.08, + "learning_rate": 1.9752112827564098e-05, + "loss": 2.6109, + "step": 1660 + }, + { + "epoch": 0.08, + "learning_rate": 1.9748938008614925e-05, + "loss": 2.6161, + "step": 1670 + }, + { + "epoch": 0.08, + "learning_rate": 1.974574324647859e-05, + "loss": 2.6231, + "step": 1680 + }, + { + "epoch": 0.08, + "learning_rate": 1.9742528547690554e-05, + "loss": 2.6016, + "step": 1690 + }, + { + "epoch": 0.08, + "learning_rate": 1.9739293918827047e-05, + "loss": 2.5802, + "step": 1700 + }, + { + "epoch": 0.08, + "learning_rate": 1.9736039366505087e-05, + "loss": 2.5746, + "step": 1710 + }, + { + "epoch": 0.08, + "learning_rate": 1.973276489738243e-05, + "loss": 2.6299, + "step": 1720 + }, + { + "epoch": 0.08, + "learning_rate": 1.9729470518157595e-05, + "loss": 2.5615, + "step": 1730 + }, + { + "epoch": 0.08, + "learning_rate": 1.972615623556981e-05, + "loss": 2.6017, + "step": 1740 + }, + { + "epoch": 0.08, + "learning_rate": 1.972282205639904e-05, + "loss": 2.5797, + "step": 1750 + }, + { + "epoch": 0.08, + "learning_rate": 1.9719467987465934e-05, + "loss": 2.5667, + "step": 1760 + }, + { + "epoch": 0.08, + "learning_rate": 1.9716094035631843e-05, + "loss": 2.5938, + "step": 1770 + }, + { + "epoch": 0.08, + "learning_rate": 1.9712700207798783e-05, + "loss": 2.5997, + "step": 1780 + }, + { + "epoch": 0.08, + "learning_rate": 1.970928651090943e-05, + "loss": 2.6088, + "step": 1790 + }, + { + "epoch": 0.08, + "learning_rate": 1.9705852951947115e-05, + "loss": 2.5769, + "step": 1800 + }, + { + "epoch": 0.08, + "learning_rate": 1.9702399537935785e-05, + "loss": 2.5784, + "step": 1810 + }, + { + "epoch": 0.08, + "learning_rate": 1.9698926275940017e-05, + "loss": 2.6015, + "step": 1820 + }, + { + "epoch": 0.08, + "learning_rate": 1.9695433173064987e-05, + "loss": 2.5902, + "step": 1830 + }, + { + "epoch": 0.08, + "learning_rate": 1.9691920236456462e-05, + "loss": 2.5692, + "step": 1840 + }, + { + "epoch": 0.08, + "learning_rate": 1.968838747330077e-05, + "loss": 2.6207, + "step": 1850 + }, + { + "epoch": 0.08, + "learning_rate": 1.9684834890824813e-05, + "loss": 2.5922, + "step": 1860 + }, + { + "epoch": 0.08, + "learning_rate": 1.9681262496296028e-05, + "loss": 2.5989, + "step": 1870 + }, + { + "epoch": 0.09, + "learning_rate": 1.9677670297022383e-05, + "loss": 2.5859, + "step": 1880 + }, + { + "epoch": 0.09, + "learning_rate": 1.9674058300352364e-05, + "loss": 2.5726, + "step": 1890 + }, + { + "epoch": 0.09, + "learning_rate": 1.9670426513674954e-05, + "loss": 2.6198, + "step": 1900 + }, + { + "epoch": 0.09, + "learning_rate": 1.9666774944419613e-05, + "loss": 2.5914, + "step": 1910 + }, + { + "epoch": 0.09, + "learning_rate": 1.9663103600056276e-05, + "loss": 2.6187, + "step": 1920 + }, + { + "epoch": 0.09, + "learning_rate": 1.965941248809534e-05, + "loss": 2.5771, + "step": 1930 + }, + { + "epoch": 0.09, + "learning_rate": 1.965570161608762e-05, + "loss": 2.5923, + "step": 1940 + }, + { + "epoch": 0.09, + "learning_rate": 1.965197099162437e-05, + "loss": 2.6079, + "step": 1950 + }, + { + "epoch": 0.09, + "learning_rate": 1.9648220622337245e-05, + "loss": 2.6138, + "step": 1960 + }, + { + "epoch": 0.09, + "learning_rate": 1.9644450515898293e-05, + "loss": 2.5875, + "step": 1970 + }, + { + "epoch": 0.09, + "learning_rate": 1.9640660680019938e-05, + "loss": 2.5786, + "step": 1980 + }, + { + "epoch": 0.09, + "learning_rate": 1.9636851122454965e-05, + "loss": 2.5824, + "step": 1990 + }, + { + "epoch": 0.09, + "learning_rate": 1.9633021850996496e-05, + "loss": 2.6021, + "step": 2000 + }, + { + "epoch": 0.09, + "eval_accuracy": 0.5305171973647798, + "eval_loss": 2.3284668922424316, + "eval_runtime": 9.9238, + "eval_samples_per_second": 137.749, + "eval_steps_per_second": 1.108, + "step": 2000 + }, + { + "epoch": 0.09, + "learning_rate": 1.9629172873477995e-05, + "loss": 2.5867, + "step": 2010 + }, + { + "epoch": 0.09, + "learning_rate": 1.9625304197773226e-05, + "loss": 2.5904, + "step": 2020 + }, + { + "epoch": 0.09, + "learning_rate": 1.962141583179625e-05, + "loss": 2.571, + "step": 2030 + }, + { + "epoch": 0.09, + "learning_rate": 1.9617507783501416e-05, + "loss": 2.5682, + "step": 2040 + }, + { + "epoch": 0.09, + "learning_rate": 1.9613580060883336e-05, + "loss": 2.5904, + "step": 2050 + }, + { + "epoch": 0.09, + "learning_rate": 1.960963267197686e-05, + "loss": 2.5614, + "step": 2060 + }, + { + "epoch": 0.09, + "learning_rate": 1.960566562485707e-05, + "loss": 2.5949, + "step": 2070 + }, + { + "epoch": 0.09, + "learning_rate": 1.9601678927639275e-05, + "loss": 2.555, + "step": 2080 + }, + { + "epoch": 0.09, + "learning_rate": 1.959767258847897e-05, + "loss": 2.5861, + "step": 2090 + }, + { + "epoch": 0.1, + "learning_rate": 1.9593646615571834e-05, + "loss": 2.5877, + "step": 2100 + }, + { + "epoch": 0.1, + "learning_rate": 1.958960101715371e-05, + "loss": 2.5815, + "step": 2110 + }, + { + "epoch": 0.1, + "learning_rate": 1.9585535801500593e-05, + "loss": 2.5512, + "step": 2120 + }, + { + "epoch": 0.1, + "learning_rate": 1.9581450976928603e-05, + "loss": 2.5319, + "step": 2130 + }, + { + "epoch": 0.1, + "learning_rate": 1.957734655179397e-05, + "loss": 2.5692, + "step": 2140 + }, + { + "epoch": 0.1, + "learning_rate": 1.9573222534493034e-05, + "loss": 2.5709, + "step": 2150 + }, + { + "epoch": 0.1, + "learning_rate": 1.9569078933462206e-05, + "loss": 2.5987, + "step": 2160 + }, + { + "epoch": 0.1, + "learning_rate": 1.9564915757177955e-05, + "loss": 2.5647, + "step": 2170 + }, + { + "epoch": 0.1, + "learning_rate": 1.9560733014156798e-05, + "loss": 2.5883, + "step": 2180 + }, + { + "epoch": 0.1, + "learning_rate": 1.9556530712955282e-05, + "loss": 2.5858, + "step": 2190 + }, + { + "epoch": 0.1, + "learning_rate": 1.9552308862169962e-05, + "loss": 2.5903, + "step": 2200 + }, + { + "epoch": 0.1, + "learning_rate": 1.9548067470437386e-05, + "loss": 2.5687, + "step": 2210 + }, + { + "epoch": 0.1, + "learning_rate": 1.9543806546434074e-05, + "loss": 2.5815, + "step": 2220 + }, + { + "epoch": 0.1, + "learning_rate": 1.95395260988765e-05, + "loss": 2.5657, + "step": 2230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9535226136521088e-05, + "loss": 2.5691, + "step": 2240 + }, + { + "epoch": 0.1, + "learning_rate": 1.9530906668164172e-05, + "loss": 2.5632, + "step": 2250 + }, + { + "epoch": 0.1, + "learning_rate": 1.9526567702642e-05, + "loss": 2.5308, + "step": 2260 + }, + { + "epoch": 0.1, + "learning_rate": 1.9522209248830686e-05, + "loss": 2.564, + "step": 2270 + }, + { + "epoch": 0.1, + "learning_rate": 1.951783131564623e-05, + "loss": 2.5459, + "step": 2280 + }, + { + "epoch": 0.1, + "learning_rate": 1.9513433912044473e-05, + "loss": 2.587, + "step": 2290 + }, + { + "epoch": 0.1, + "learning_rate": 1.9509017047021085e-05, + "loss": 2.5739, + "step": 2300 + }, + { + "epoch": 0.1, + "learning_rate": 1.950458072961155e-05, + "loss": 2.5777, + "step": 2310 + }, + { + "epoch": 0.11, + "learning_rate": 1.950012496889114e-05, + "loss": 2.5725, + "step": 2320 + }, + { + "epoch": 0.11, + "learning_rate": 1.9495649773974913e-05, + "loss": 2.5745, + "step": 2330 + }, + { + "epoch": 0.11, + "learning_rate": 1.9491155154017675e-05, + "loss": 2.5686, + "step": 2340 + }, + { + "epoch": 0.11, + "learning_rate": 1.948664111821397e-05, + "loss": 2.5904, + "step": 2350 + }, + { + "epoch": 0.11, + "learning_rate": 1.948210767579806e-05, + "loss": 2.5503, + "step": 2360 + }, + { + "epoch": 0.11, + "learning_rate": 1.9477554836043907e-05, + "loss": 2.5743, + "step": 2370 + }, + { + "epoch": 0.11, + "learning_rate": 1.947298260826516e-05, + "loss": 2.5746, + "step": 2380 + }, + { + "epoch": 0.11, + "learning_rate": 1.946839100181512e-05, + "loss": 2.5761, + "step": 2390 + }, + { + "epoch": 0.11, + "learning_rate": 1.9463780026086735e-05, + "loss": 2.5883, + "step": 2400 + }, + { + "epoch": 0.11, + "learning_rate": 1.945914969051258e-05, + "loss": 2.5673, + "step": 2410 + }, + { + "epoch": 0.11, + "learning_rate": 1.9454500004564825e-05, + "loss": 2.5564, + "step": 2420 + }, + { + "epoch": 0.11, + "learning_rate": 1.9449830977755234e-05, + "loss": 2.5568, + "step": 2430 + }, + { + "epoch": 0.11, + "learning_rate": 1.9445142619635127e-05, + "loss": 2.5582, + "step": 2440 + }, + { + "epoch": 0.11, + "learning_rate": 1.9440434939795382e-05, + "loss": 2.5595, + "step": 2450 + }, + { + "epoch": 0.11, + "learning_rate": 1.943570794786639e-05, + "loss": 2.5521, + "step": 2460 + }, + { + "epoch": 0.11, + "learning_rate": 1.9430961653518056e-05, + "loss": 2.5493, + "step": 2470 + }, + { + "epoch": 0.11, + "learning_rate": 1.9426196066459766e-05, + "loss": 2.5564, + "step": 2480 + }, + { + "epoch": 0.11, + "learning_rate": 1.942141119644038e-05, + "loss": 2.5652, + "step": 2490 + }, + { + "epoch": 0.11, + "learning_rate": 1.9416607053248203e-05, + "loss": 2.5486, + "step": 2500 + }, + { + "epoch": 0.11, + "learning_rate": 1.941178364671096e-05, + "loss": 2.5633, + "step": 2510 + }, + { + "epoch": 0.11, + "learning_rate": 1.940694098669579e-05, + "loss": 2.5736, + "step": 2520 + }, + { + "epoch": 0.11, + "learning_rate": 1.9402079083109217e-05, + "loss": 2.5312, + "step": 2530 + }, + { + "epoch": 0.12, + "learning_rate": 1.939719794589712e-05, + "loss": 2.5523, + "step": 2540 + }, + { + "epoch": 0.12, + "learning_rate": 1.9392297585044748e-05, + "loss": 2.5435, + "step": 2550 + }, + { + "epoch": 0.12, + "learning_rate": 1.9387378010576653e-05, + "loss": 2.5447, + "step": 2560 + }, + { + "epoch": 0.12, + "learning_rate": 1.9382439232556696e-05, + "loss": 2.5613, + "step": 2570 + }, + { + "epoch": 0.12, + "learning_rate": 1.9377481261088036e-05, + "loss": 2.5827, + "step": 2580 + }, + { + "epoch": 0.12, + "learning_rate": 1.937250410631308e-05, + "loss": 2.5472, + "step": 2590 + }, + { + "epoch": 0.12, + "learning_rate": 1.9367507778413483e-05, + "loss": 2.5242, + "step": 2600 + }, + { + "epoch": 0.12, + "learning_rate": 1.9362492287610126e-05, + "loss": 2.5497, + "step": 2610 + }, + { + "epoch": 0.12, + "learning_rate": 1.9357457644163086e-05, + "loss": 2.5683, + "step": 2620 + }, + { + "epoch": 0.12, + "learning_rate": 1.9352403858371618e-05, + "loss": 2.5524, + "step": 2630 + }, + { + "epoch": 0.12, + "learning_rate": 1.9347330940574145e-05, + "loss": 2.5521, + "step": 2640 + }, + { + "epoch": 0.12, + "learning_rate": 1.9342238901148222e-05, + "loss": 2.5512, + "step": 2650 + }, + { + "epoch": 0.12, + "learning_rate": 1.933712775051052e-05, + "loss": 2.5571, + "step": 2660 + }, + { + "epoch": 0.12, + "learning_rate": 1.933199749911681e-05, + "loss": 2.5624, + "step": 2670 + }, + { + "epoch": 0.12, + "learning_rate": 1.932684815746193e-05, + "loss": 2.5375, + "step": 2680 + }, + { + "epoch": 0.12, + "learning_rate": 1.9321679736079777e-05, + "loss": 2.5468, + "step": 2690 + }, + { + "epoch": 0.12, + "learning_rate": 1.9316492245543276e-05, + "loss": 2.5677, + "step": 2700 + }, + { + "epoch": 0.12, + "learning_rate": 1.9311285696464362e-05, + "loss": 2.5439, + "step": 2710 + }, + { + "epoch": 0.12, + "learning_rate": 1.9306060099493956e-05, + "loss": 2.5453, + "step": 2720 + }, + { + "epoch": 0.12, + "learning_rate": 1.930081546532195e-05, + "loss": 2.5596, + "step": 2730 + }, + { + "epoch": 0.12, + "learning_rate": 1.929555180467717e-05, + "loss": 2.5487, + "step": 2740 + }, + { + "epoch": 0.12, + "learning_rate": 1.9290269128327374e-05, + "loss": 2.567, + "step": 2750 + }, + { + "epoch": 0.13, + "learning_rate": 1.9284967447079218e-05, + "loss": 2.5375, + "step": 2760 + }, + { + "epoch": 0.13, + "learning_rate": 1.9279646771778234e-05, + "loss": 2.5614, + "step": 2770 + }, + { + "epoch": 0.13, + "learning_rate": 1.927430711330881e-05, + "loss": 2.5561, + "step": 2780 + }, + { + "epoch": 0.13, + "learning_rate": 1.926894848259416e-05, + "loss": 2.557, + "step": 2790 + }, + { + "epoch": 0.13, + "learning_rate": 1.9263570890596327e-05, + "loss": 2.5625, + "step": 2800 + }, + { + "epoch": 0.13, + "learning_rate": 1.9258174348316126e-05, + "loss": 2.514, + "step": 2810 + }, + { + "epoch": 0.13, + "learning_rate": 1.925275886679315e-05, + "loss": 2.5545, + "step": 2820 + }, + { + "epoch": 0.13, + "learning_rate": 1.924732445710572e-05, + "loss": 2.5612, + "step": 2830 + }, + { + "epoch": 0.13, + "learning_rate": 1.92418711303709e-05, + "loss": 2.5577, + "step": 2840 + }, + { + "epoch": 0.13, + "learning_rate": 1.923639889774443e-05, + "loss": 2.516, + "step": 2850 + }, + { + "epoch": 0.13, + "learning_rate": 1.9230907770420737e-05, + "loss": 2.536, + "step": 2860 + }, + { + "epoch": 0.13, + "learning_rate": 1.9225397759632905e-05, + "loss": 2.5547, + "step": 2870 + }, + { + "epoch": 0.13, + "learning_rate": 1.9219868876652637e-05, + "loss": 2.5592, + "step": 2880 + }, + { + "epoch": 0.13, + "learning_rate": 1.9214321132790247e-05, + "loss": 2.5764, + "step": 2890 + }, + { + "epoch": 0.13, + "learning_rate": 1.9208754539394632e-05, + "loss": 2.537, + "step": 2900 + }, + { + "epoch": 0.13, + "learning_rate": 1.920316910785325e-05, + "loss": 2.5297, + "step": 2910 + }, + { + "epoch": 0.13, + "learning_rate": 1.9197564849592093e-05, + "loss": 2.5446, + "step": 2920 + }, + { + "epoch": 0.13, + "learning_rate": 1.919194177607567e-05, + "loss": 2.5511, + "step": 2930 + }, + { + "epoch": 0.13, + "learning_rate": 1.9186299898806983e-05, + "loss": 2.5469, + "step": 2940 + }, + { + "epoch": 0.13, + "learning_rate": 1.9180639229327483e-05, + "loss": 2.5429, + "step": 2950 + }, + { + "epoch": 0.13, + "learning_rate": 1.9174959779217087e-05, + "loss": 2.5394, + "step": 2960 + }, + { + "epoch": 0.13, + "learning_rate": 1.9169261560094122e-05, + "loss": 2.5503, + "step": 2970 + }, + { + "epoch": 0.14, + "learning_rate": 1.9163544583615303e-05, + "loss": 2.5425, + "step": 2980 + }, + { + "epoch": 0.14, + "learning_rate": 1.9157808861475723e-05, + "loss": 2.5261, + "step": 2990 + }, + { + "epoch": 0.14, + "learning_rate": 1.9152054405408823e-05, + "loss": 2.5452, + "step": 3000 + }, + { + "epoch": 0.14, + "learning_rate": 1.914628122718637e-05, + "loss": 2.5342, + "step": 3010 + }, + { + "epoch": 0.14, + "learning_rate": 1.9140489338618423e-05, + "loss": 2.5413, + "step": 3020 + }, + { + "epoch": 0.14, + "learning_rate": 1.9134678751553325e-05, + "loss": 2.5623, + "step": 3030 + }, + { + "epoch": 0.14, + "learning_rate": 1.912884947787766e-05, + "loss": 2.5459, + "step": 3040 + }, + { + "epoch": 0.14, + "learning_rate": 1.9123001529516246e-05, + "loss": 2.524, + "step": 3050 + }, + { + "epoch": 0.14, + "learning_rate": 1.9117134918432106e-05, + "loss": 2.5516, + "step": 3060 + }, + { + "epoch": 0.14, + "learning_rate": 1.911124965662643e-05, + "loss": 2.5663, + "step": 3070 + }, + { + "epoch": 0.14, + "learning_rate": 1.9105345756138575e-05, + "loss": 2.5605, + "step": 3080 + }, + { + "epoch": 0.14, + "learning_rate": 1.9099423229046015e-05, + "loss": 2.5279, + "step": 3090 + }, + { + "epoch": 0.14, + "learning_rate": 1.909348208746433e-05, + "loss": 2.5512, + "step": 3100 + }, + { + "epoch": 0.14, + "learning_rate": 1.9087522343547195e-05, + "loss": 2.523, + "step": 3110 + }, + { + "epoch": 0.14, + "learning_rate": 1.9081544009486316e-05, + "loss": 2.5283, + "step": 3120 + }, + { + "epoch": 0.14, + "learning_rate": 1.9075547097511435e-05, + "loss": 2.5236, + "step": 3130 + }, + { + "epoch": 0.14, + "learning_rate": 1.9069531619890314e-05, + "loss": 2.5417, + "step": 3140 + }, + { + "epoch": 0.14, + "learning_rate": 1.9063497588928676e-05, + "loss": 2.5548, + "step": 3150 + }, + { + "epoch": 0.14, + "learning_rate": 1.90574450169702e-05, + "loss": 2.5413, + "step": 3160 + }, + { + "epoch": 0.14, + "learning_rate": 1.905137391639651e-05, + "loss": 2.5521, + "step": 3170 + }, + { + "epoch": 0.14, + "learning_rate": 1.904528429962712e-05, + "loss": 2.5547, + "step": 3180 + }, + { + "epoch": 0.14, + "learning_rate": 1.9039176179119418e-05, + "loss": 2.528, + "step": 3190 + }, + { + "epoch": 0.15, + "learning_rate": 1.9033049567368655e-05, + "loss": 2.5322, + "step": 3200 + }, + { + "epoch": 0.15, + "learning_rate": 1.90269044769079e-05, + "loss": 2.533, + "step": 3210 + }, + { + "epoch": 0.15, + "learning_rate": 1.902074092030804e-05, + "loss": 2.5438, + "step": 3220 + }, + { + "epoch": 0.15, + "learning_rate": 1.901455891017772e-05, + "loss": 2.5053, + "step": 3230 + }, + { + "epoch": 0.15, + "learning_rate": 1.900835845916334e-05, + "loss": 2.5348, + "step": 3240 + }, + { + "epoch": 0.15, + "learning_rate": 1.900213957994903e-05, + "loss": 2.5244, + "step": 3250 + }, + { + "epoch": 0.15, + "learning_rate": 1.899590228525661e-05, + "loss": 2.5434, + "step": 3260 + }, + { + "epoch": 0.15, + "learning_rate": 1.898964658784558e-05, + "loss": 2.5258, + "step": 3270 + }, + { + "epoch": 0.15, + "learning_rate": 1.8983372500513075e-05, + "loss": 2.5363, + "step": 3280 + }, + { + "epoch": 0.15, + "learning_rate": 1.8977080036093863e-05, + "loss": 2.5525, + "step": 3290 + }, + { + "epoch": 0.15, + "learning_rate": 1.89707692074603e-05, + "loss": 2.5336, + "step": 3300 + }, + { + "epoch": 0.15, + "learning_rate": 1.8964440027522306e-05, + "loss": 2.5109, + "step": 3310 + }, + { + "epoch": 0.15, + "learning_rate": 1.8958092509227347e-05, + "loss": 2.5359, + "step": 3320 + }, + { + "epoch": 0.15, + "learning_rate": 1.8951726665560395e-05, + "loss": 2.536, + "step": 3330 + }, + { + "epoch": 0.15, + "learning_rate": 1.8945342509543923e-05, + "loss": 2.5076, + "step": 3340 + }, + { + "epoch": 0.15, + "learning_rate": 1.8938940054237856e-05, + "loss": 2.5351, + "step": 3350 + }, + { + "epoch": 0.15, + "learning_rate": 1.8932519312739554e-05, + "loss": 2.5101, + "step": 3360 + }, + { + "epoch": 0.15, + "learning_rate": 1.8926080298183784e-05, + "loss": 2.5267, + "step": 3370 + }, + { + "epoch": 0.15, + "learning_rate": 1.89196230237427e-05, + "loss": 2.5512, + "step": 3380 + }, + { + "epoch": 0.15, + "learning_rate": 1.8913147502625802e-05, + "loss": 2.5042, + "step": 3390 + }, + { + "epoch": 0.15, + "learning_rate": 1.8906653748079927e-05, + "loss": 2.5479, + "step": 3400 + }, + { + "epoch": 0.15, + "learning_rate": 1.89001417733892e-05, + "loss": 2.5267, + "step": 3410 + }, + { + "epoch": 0.15, + "learning_rate": 1.889361159187502e-05, + "loss": 2.5475, + "step": 3420 + }, + { + "epoch": 0.16, + "learning_rate": 1.8887063216896043e-05, + "loss": 2.5353, + "step": 3430 + }, + { + "epoch": 0.16, + "learning_rate": 1.8880496661848132e-05, + "loss": 2.551, + "step": 3440 + }, + { + "epoch": 0.16, + "learning_rate": 1.8873911940164344e-05, + "loss": 2.5408, + "step": 3450 + }, + { + "epoch": 0.16, + "learning_rate": 1.88673090653149e-05, + "loss": 2.528, + "step": 3460 + }, + { + "epoch": 0.16, + "learning_rate": 1.886068805080715e-05, + "loss": 2.5241, + "step": 3470 + }, + { + "epoch": 0.16, + "learning_rate": 1.885404891018556e-05, + "loss": 2.5586, + "step": 3480 + }, + { + "epoch": 0.16, + "learning_rate": 1.8847391657031674e-05, + "loss": 2.5153, + "step": 3490 + }, + { + "epoch": 0.16, + "learning_rate": 1.884071630496409e-05, + "loss": 2.5022, + "step": 3500 + }, + { + "epoch": 0.16, + "learning_rate": 1.8834022867638423e-05, + "loss": 2.527, + "step": 3510 + }, + { + "epoch": 0.16, + "learning_rate": 1.8827311358747295e-05, + "loss": 2.512, + "step": 3520 + }, + { + "epoch": 0.16, + "learning_rate": 1.882058179202029e-05, + "loss": 2.5374, + "step": 3530 + }, + { + "epoch": 0.16, + "learning_rate": 1.8813834181223935e-05, + "loss": 2.5514, + "step": 3540 + }, + { + "epoch": 0.16, + "learning_rate": 1.880706854016166e-05, + "loss": 2.5169, + "step": 3550 + }, + { + "epoch": 0.16, + "learning_rate": 1.88002848826738e-05, + "loss": 2.4966, + "step": 3560 + }, + { + "epoch": 0.16, + "learning_rate": 1.8793483222637524e-05, + "loss": 2.5155, + "step": 3570 + }, + { + "epoch": 0.16, + "learning_rate": 1.8786663573966845e-05, + "loss": 2.509, + "step": 3580 + }, + { + "epoch": 0.16, + "learning_rate": 1.877982595061256e-05, + "loss": 2.5304, + "step": 3590 + }, + { + "epoch": 0.16, + "learning_rate": 1.877297036656225e-05, + "loss": 2.5268, + "step": 3600 + }, + { + "epoch": 0.16, + "learning_rate": 1.8766096835840226e-05, + "loss": 2.5605, + "step": 3610 + }, + { + "epoch": 0.16, + "learning_rate": 1.8759205372507528e-05, + "loss": 2.5112, + "step": 3620 + }, + { + "epoch": 0.16, + "learning_rate": 1.8752295990661857e-05, + "loss": 2.5627, + "step": 3630 + }, + { + "epoch": 0.16, + "learning_rate": 1.8745368704437594e-05, + "loss": 2.5212, + "step": 3640 + }, + { + "epoch": 0.17, + "learning_rate": 1.8738423528005733e-05, + "loss": 2.5379, + "step": 3650 + }, + { + "epoch": 0.17, + "learning_rate": 1.8731460475573864e-05, + "loss": 2.5574, + "step": 3660 + }, + { + "epoch": 0.17, + "learning_rate": 1.8724479561386152e-05, + "loss": 2.5381, + "step": 3670 + }, + { + "epoch": 0.17, + "learning_rate": 1.87174807997233e-05, + "loss": 2.5339, + "step": 3680 + }, + { + "epoch": 0.17, + "learning_rate": 1.871046420490252e-05, + "loss": 2.5476, + "step": 3690 + }, + { + "epoch": 0.17, + "learning_rate": 1.8703429791277502e-05, + "loss": 2.5304, + "step": 3700 + }, + { + "epoch": 0.17, + "learning_rate": 1.8696377573238393e-05, + "loss": 2.5252, + "step": 3710 + }, + { + "epoch": 0.17, + "learning_rate": 1.8689307565211757e-05, + "loss": 2.5276, + "step": 3720 + }, + { + "epoch": 0.17, + "learning_rate": 1.868221978166056e-05, + "loss": 2.5171, + "step": 3730 + }, + { + "epoch": 0.17, + "learning_rate": 1.8675114237084117e-05, + "loss": 2.5023, + "step": 3740 + }, + { + "epoch": 0.17, + "learning_rate": 1.8667990946018086e-05, + "loss": 2.5093, + "step": 3750 + }, + { + "epoch": 0.17, + "learning_rate": 1.866084992303443e-05, + "loss": 2.5555, + "step": 3760 + }, + { + "epoch": 0.17, + "learning_rate": 1.8653691182741374e-05, + "loss": 2.5282, + "step": 3770 + }, + { + "epoch": 0.17, + "learning_rate": 1.8646514739783404e-05, + "loss": 2.5215, + "step": 3780 + }, + { + "epoch": 0.17, + "learning_rate": 1.863932060884121e-05, + "loss": 2.5001, + "step": 3790 + }, + { + "epoch": 0.17, + "learning_rate": 1.8632108804631653e-05, + "loss": 2.4973, + "step": 3800 + }, + { + "epoch": 0.17, + "learning_rate": 1.862487934190778e-05, + "loss": 2.5067, + "step": 3810 + }, + { + "epoch": 0.17, + "learning_rate": 1.861763223545873e-05, + "loss": 2.517, + "step": 3820 + }, + { + "epoch": 0.17, + "learning_rate": 1.8610367500109757e-05, + "loss": 2.529, + "step": 3830 + }, + { + "epoch": 0.17, + "learning_rate": 1.8603085150722165e-05, + "loss": 2.5225, + "step": 3840 + }, + { + "epoch": 0.17, + "learning_rate": 1.8595785202193295e-05, + "loss": 2.5309, + "step": 3850 + }, + { + "epoch": 0.17, + "learning_rate": 1.8588467669456494e-05, + "loss": 2.5283, + "step": 3860 + }, + { + "epoch": 0.18, + "learning_rate": 1.8581132567481075e-05, + "loss": 2.5573, + "step": 3870 + }, + { + "epoch": 0.18, + "learning_rate": 1.8573779911272293e-05, + "loss": 2.5339, + "step": 3880 + }, + { + "epoch": 0.18, + "learning_rate": 1.856640971587132e-05, + "loss": 2.5111, + "step": 3890 + }, + { + "epoch": 0.18, + "learning_rate": 1.855902199635519e-05, + "loss": 2.5247, + "step": 3900 + }, + { + "epoch": 0.18, + "learning_rate": 1.855161676783681e-05, + "loss": 2.529, + "step": 3910 + }, + { + "epoch": 0.18, + "learning_rate": 1.8544194045464888e-05, + "loss": 2.5396, + "step": 3920 + }, + { + "epoch": 0.18, + "learning_rate": 1.8536753844423923e-05, + "loss": 2.5122, + "step": 3930 + }, + { + "epoch": 0.18, + "learning_rate": 1.8529296179934167e-05, + "loss": 2.5119, + "step": 3940 + }, + { + "epoch": 0.18, + "learning_rate": 1.8521821067251604e-05, + "loss": 2.5135, + "step": 3950 + }, + { + "epoch": 0.18, + "learning_rate": 1.8514328521667904e-05, + "loss": 2.5477, + "step": 3960 + }, + { + "epoch": 0.18, + "learning_rate": 1.8506818558510404e-05, + "loss": 2.5173, + "step": 3970 + }, + { + "epoch": 0.18, + "learning_rate": 1.8499291193142072e-05, + "loss": 2.5303, + "step": 3980 + }, + { + "epoch": 0.18, + "learning_rate": 1.8491746440961463e-05, + "loss": 2.5448, + "step": 3990 + }, + { + "epoch": 0.18, + "learning_rate": 1.8484184317402725e-05, + "loss": 2.5355, + "step": 4000 + }, + { + "epoch": 0.18, + "eval_accuracy": 0.5364902773874621, + "eval_loss": 2.274355888366699, + "eval_runtime": 9.8852, + "eval_samples_per_second": 138.288, + "eval_steps_per_second": 1.113, + "step": 4000 + }, + { + "epoch": 0.18, + "learning_rate": 1.8476604837935515e-05, + "loss": 2.5192, + "step": 4010 + }, + { + "epoch": 0.18, + "learning_rate": 1.846900801806501e-05, + "loss": 2.5216, + "step": 4020 + }, + { + "epoch": 0.18, + "learning_rate": 1.846139387333186e-05, + "loss": 2.5109, + "step": 4030 + }, + { + "epoch": 0.18, + "learning_rate": 1.845376241931215e-05, + "loss": 2.492, + "step": 4040 + }, + { + "epoch": 0.18, + "learning_rate": 1.8446113671617376e-05, + "loss": 2.4837, + "step": 4050 + }, + { + "epoch": 0.18, + "learning_rate": 1.843844764589441e-05, + "loss": 2.5299, + "step": 4060 + }, + { + "epoch": 0.18, + "learning_rate": 1.8430764357825482e-05, + "loss": 2.5008, + "step": 4070 + }, + { + "epoch": 0.18, + "learning_rate": 1.842306382312811e-05, + "loss": 2.4974, + "step": 4080 + }, + { + "epoch": 0.19, + "learning_rate": 1.8415346057555122e-05, + "loss": 2.5336, + "step": 4090 + }, + { + "epoch": 0.19, + "learning_rate": 1.8407611076894572e-05, + "loss": 2.524, + "step": 4100 + }, + { + "epoch": 0.19, + "learning_rate": 1.839985889696974e-05, + "loss": 2.5193, + "step": 4110 + }, + { + "epoch": 0.19, + "learning_rate": 1.839208953363909e-05, + "loss": 2.4849, + "step": 4120 + }, + { + "epoch": 0.19, + "learning_rate": 1.8384303002796236e-05, + "loss": 2.5555, + "step": 4130 + }, + { + "epoch": 0.19, + "learning_rate": 1.8376499320369917e-05, + "loss": 2.5041, + "step": 4140 + }, + { + "epoch": 0.19, + "learning_rate": 1.8368678502323947e-05, + "loss": 2.4856, + "step": 4150 + }, + { + "epoch": 0.19, + "learning_rate": 1.8360840564657202e-05, + "loss": 2.5083, + "step": 4160 + }, + { + "epoch": 0.19, + "learning_rate": 1.8352985523403584e-05, + "loss": 2.5207, + "step": 4170 + }, + { + "epoch": 0.19, + "learning_rate": 1.8345113394631973e-05, + "loss": 2.5169, + "step": 4180 + }, + { + "epoch": 0.19, + "learning_rate": 1.8337224194446205e-05, + "loss": 2.5269, + "step": 4190 + }, + { + "epoch": 0.19, + "learning_rate": 1.8329317938985052e-05, + "loss": 2.5056, + "step": 4200 + }, + { + "epoch": 0.19, + "learning_rate": 1.8321394644422155e-05, + "loss": 2.5142, + "step": 4210 + }, + { + "epoch": 0.19, + "learning_rate": 1.8313454326966035e-05, + "loss": 2.5418, + "step": 4220 + }, + { + "epoch": 0.19, + "learning_rate": 1.8305497002860015e-05, + "loss": 2.5119, + "step": 4230 + }, + { + "epoch": 0.19, + "learning_rate": 1.829752268838222e-05, + "loss": 2.5243, + "step": 4240 + }, + { + "epoch": 0.19, + "learning_rate": 1.8289531399845528e-05, + "loss": 2.4917, + "step": 4250 + }, + { + "epoch": 0.19, + "learning_rate": 1.8281523153597543e-05, + "loss": 2.4768, + "step": 4260 + }, + { + "epoch": 0.19, + "learning_rate": 1.8273497966020553e-05, + "loss": 2.4815, + "step": 4270 + }, + { + "epoch": 0.19, + "learning_rate": 1.8265455853531516e-05, + "loss": 2.5219, + "step": 4280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8257396832581997e-05, + "loss": 2.4825, + "step": 4290 + }, + { + "epoch": 0.19, + "learning_rate": 1.8249320919658158e-05, + "loss": 2.5093, + "step": 4300 + }, + { + "epoch": 0.2, + "learning_rate": 1.8241228131280716e-05, + "loss": 2.5584, + "step": 4310 + }, + { + "epoch": 0.2, + "learning_rate": 1.823311848400491e-05, + "loss": 2.5098, + "step": 4320 + }, + { + "epoch": 0.2, + "learning_rate": 1.8224991994420466e-05, + "loss": 2.5519, + "step": 4330 + }, + { + "epoch": 0.2, + "learning_rate": 1.8216848679151565e-05, + "loss": 2.4879, + "step": 4340 + }, + { + "epoch": 0.2, + "learning_rate": 1.820868855485681e-05, + "loss": 2.5185, + "step": 4350 + }, + { + "epoch": 0.2, + "learning_rate": 1.8200511638229178e-05, + "loss": 2.5258, + "step": 4360 + }, + { + "epoch": 0.2, + "learning_rate": 1.8192317945996016e-05, + "loss": 2.5009, + "step": 4370 + }, + { + "epoch": 0.2, + "learning_rate": 1.8184107494918976e-05, + "loss": 2.517, + "step": 4380 + }, + { + "epoch": 0.2, + "learning_rate": 1.8175880301793995e-05, + "loss": 2.4987, + "step": 4390 + }, + { + "epoch": 0.2, + "learning_rate": 1.816763638345126e-05, + "loss": 2.498, + "step": 4400 + }, + { + "epoch": 0.2, + "learning_rate": 1.815937575675518e-05, + "loss": 2.5115, + "step": 4410 + }, + { + "epoch": 0.2, + "learning_rate": 1.8151098438604323e-05, + "loss": 2.5069, + "step": 4420 + }, + { + "epoch": 0.2, + "learning_rate": 1.8142804445931425e-05, + "loss": 2.5153, + "step": 4430 + }, + { + "epoch": 0.2, + "learning_rate": 1.8134493795703325e-05, + "loss": 2.5119, + "step": 4440 + }, + { + "epoch": 0.2, + "learning_rate": 1.812616650492093e-05, + "loss": 2.5026, + "step": 4450 + }, + { + "epoch": 0.2, + "learning_rate": 1.81178225906192e-05, + "loss": 2.5119, + "step": 4460 + }, + { + "epoch": 0.2, + "learning_rate": 1.81094620698671e-05, + "loss": 2.5089, + "step": 4470 + }, + { + "epoch": 0.2, + "learning_rate": 1.810108495976755e-05, + "loss": 2.527, + "step": 4480 + }, + { + "epoch": 0.2, + "learning_rate": 1.8092691277457432e-05, + "loss": 2.4969, + "step": 4490 + }, + { + "epoch": 0.2, + "learning_rate": 1.8084281040107505e-05, + "loss": 2.5204, + "step": 4500 + }, + { + "epoch": 0.2, + "learning_rate": 1.8075854264922417e-05, + "loss": 2.5072, + "step": 4510 + }, + { + "epoch": 0.2, + "learning_rate": 1.8067410969140627e-05, + "loss": 2.524, + "step": 4520 + }, + { + "epoch": 0.21, + "learning_rate": 1.8058951170034407e-05, + "loss": 2.5161, + "step": 4530 + }, + { + "epoch": 0.21, + "learning_rate": 1.8050474884909772e-05, + "loss": 2.5365, + "step": 4540 + }, + { + "epoch": 0.21, + "learning_rate": 1.804198213110648e-05, + "loss": 2.4983, + "step": 4550 + }, + { + "epoch": 0.21, + "learning_rate": 1.8033472925997963e-05, + "loss": 2.498, + "step": 4560 + }, + { + "epoch": 0.21, + "learning_rate": 1.8024947286991316e-05, + "loss": 2.4998, + "step": 4570 + }, + { + "epoch": 0.21, + "learning_rate": 1.8016405231527253e-05, + "loss": 2.4966, + "step": 4580 + }, + { + "epoch": 0.21, + "learning_rate": 1.8007846777080064e-05, + "loss": 2.5147, + "step": 4590 + }, + { + "epoch": 0.21, + "learning_rate": 1.7999271941157596e-05, + "loss": 2.5035, + "step": 4600 + }, + { + "epoch": 0.21, + "learning_rate": 1.7990680741301195e-05, + "loss": 2.499, + "step": 4610 + }, + { + "epoch": 0.21, + "learning_rate": 1.7982073195085692e-05, + "loss": 2.4885, + "step": 4620 + }, + { + "epoch": 0.21, + "learning_rate": 1.7973449320119355e-05, + "loss": 2.5061, + "step": 4630 + }, + { + "epoch": 0.21, + "learning_rate": 1.796480913404385e-05, + "loss": 2.4925, + "step": 4640 + }, + { + "epoch": 0.21, + "learning_rate": 1.795615265453422e-05, + "loss": 2.4839, + "step": 4650 + }, + { + "epoch": 0.21, + "learning_rate": 1.7947479899298837e-05, + "loss": 2.5002, + "step": 4660 + }, + { + "epoch": 0.21, + "learning_rate": 1.7938790886079355e-05, + "loss": 2.5347, + "step": 4670 + }, + { + "epoch": 0.21, + "learning_rate": 1.7930085632650706e-05, + "loss": 2.5222, + "step": 4680 + }, + { + "epoch": 0.21, + "learning_rate": 1.7921364156821024e-05, + "loss": 2.5128, + "step": 4690 + }, + { + "epoch": 0.21, + "learning_rate": 1.7912626476431648e-05, + "loss": 2.5115, + "step": 4700 + }, + { + "epoch": 0.21, + "learning_rate": 1.7903872609357057e-05, + "loss": 2.5147, + "step": 4710 + }, + { + "epoch": 0.21, + "learning_rate": 1.7895102573504843e-05, + "loss": 2.5246, + "step": 4720 + }, + { + "epoch": 0.21, + "learning_rate": 1.788631638681567e-05, + "loss": 2.5282, + "step": 4730 + }, + { + "epoch": 0.21, + "learning_rate": 1.787751406726325e-05, + "loss": 2.4971, + "step": 4740 + }, + { + "epoch": 0.22, + "learning_rate": 1.7868695632854294e-05, + "loss": 2.4834, + "step": 4750 + }, + { + "epoch": 0.22, + "learning_rate": 1.785986110162848e-05, + "loss": 2.4973, + "step": 4760 + }, + { + "epoch": 0.22, + "learning_rate": 1.785101049165841e-05, + "loss": 2.5288, + "step": 4770 + }, + { + "epoch": 0.22, + "learning_rate": 1.784214382104958e-05, + "loss": 2.4988, + "step": 4780 + }, + { + "epoch": 0.22, + "learning_rate": 1.7833261107940347e-05, + "loss": 2.4955, + "step": 4790 + }, + { + "epoch": 0.22, + "learning_rate": 1.782436237050188e-05, + "loss": 2.5097, + "step": 4800 + }, + { + "epoch": 0.22, + "learning_rate": 1.7815447626938125e-05, + "loss": 2.5047, + "step": 4810 + }, + { + "epoch": 0.22, + "learning_rate": 1.780651689548578e-05, + "loss": 2.512, + "step": 4820 + }, + { + "epoch": 0.22, + "learning_rate": 1.7797570194414246e-05, + "loss": 2.4946, + "step": 4830 + }, + { + "epoch": 0.22, + "learning_rate": 1.7788607542025592e-05, + "loss": 2.476, + "step": 4840 + }, + { + "epoch": 0.22, + "learning_rate": 1.7779628956654513e-05, + "loss": 2.5146, + "step": 4850 + }, + { + "epoch": 0.22, + "learning_rate": 1.777063445666831e-05, + "loss": 2.5086, + "step": 4860 + }, + { + "epoch": 0.22, + "learning_rate": 1.7761624060466824e-05, + "loss": 2.4862, + "step": 4870 + }, + { + "epoch": 0.22, + "learning_rate": 1.775259778648243e-05, + "loss": 2.5173, + "step": 4880 + }, + { + "epoch": 0.22, + "learning_rate": 1.7743555653179978e-05, + "loss": 2.5241, + "step": 4890 + }, + { + "epoch": 0.22, + "learning_rate": 1.773449767905676e-05, + "loss": 2.5003, + "step": 4900 + }, + { + "epoch": 0.22, + "learning_rate": 1.7725423882642467e-05, + "loss": 2.5295, + "step": 4910 + }, + { + "epoch": 0.22, + "learning_rate": 1.771633428249917e-05, + "loss": 2.4967, + "step": 4920 + }, + { + "epoch": 0.22, + "learning_rate": 1.770722889722126e-05, + "loss": 2.5178, + "step": 4930 + }, + { + "epoch": 0.22, + "learning_rate": 1.769810774543543e-05, + "loss": 2.4951, + "step": 4940 + }, + { + "epoch": 0.22, + "learning_rate": 1.768897084580061e-05, + "loss": 2.4986, + "step": 4950 + }, + { + "epoch": 0.22, + "learning_rate": 1.767981821700796e-05, + "loss": 2.5109, + "step": 4960 + }, + { + "epoch": 0.23, + "learning_rate": 1.7670649877780803e-05, + "loss": 2.5234, + "step": 4970 + }, + { + "epoch": 0.23, + "learning_rate": 1.7661465846874618e-05, + "loss": 2.5029, + "step": 4980 + }, + { + "epoch": 0.23, + "learning_rate": 1.7652266143076964e-05, + "loss": 2.5181, + "step": 4990 + }, + { + "epoch": 0.23, + "learning_rate": 1.7643050785207478e-05, + "loss": 2.5092, + "step": 5000 + }, + { + "epoch": 0.23, + "learning_rate": 1.7633819792117815e-05, + "loss": 2.5061, + "step": 5010 + }, + { + "epoch": 0.23, + "learning_rate": 1.762457318269161e-05, + "loss": 2.5022, + "step": 5020 + }, + { + "epoch": 0.23, + "learning_rate": 1.7615310975844447e-05, + "loss": 2.5213, + "step": 5030 + }, + { + "epoch": 0.23, + "learning_rate": 1.7606033190523823e-05, + "loss": 2.507, + "step": 5040 + }, + { + "epoch": 0.23, + "learning_rate": 1.7596739845709096e-05, + "loss": 2.519, + "step": 5050 + }, + { + "epoch": 0.23, + "learning_rate": 1.7587430960411454e-05, + "loss": 2.5171, + "step": 5060 + }, + { + "epoch": 0.23, + "learning_rate": 1.757810655367388e-05, + "loss": 2.5059, + "step": 5070 + }, + { + "epoch": 0.23, + "learning_rate": 1.7568766644571108e-05, + "loss": 2.5114, + "step": 5080 + }, + { + "epoch": 0.23, + "learning_rate": 1.7559411252209583e-05, + "loss": 2.5041, + "step": 5090 + }, + { + "epoch": 0.23, + "learning_rate": 1.7550040395727422e-05, + "loss": 2.4847, + "step": 5100 + }, + { + "epoch": 0.23, + "learning_rate": 1.754065409429438e-05, + "loss": 2.5067, + "step": 5110 + }, + { + "epoch": 0.23, + "learning_rate": 1.7531252367111812e-05, + "loss": 2.4977, + "step": 5120 + }, + { + "epoch": 0.23, + "learning_rate": 1.752183523341262e-05, + "loss": 2.4925, + "step": 5130 + }, + { + "epoch": 0.23, + "learning_rate": 1.7512402712461222e-05, + "loss": 2.5229, + "step": 5140 + }, + { + "epoch": 0.23, + "learning_rate": 1.7502954823553522e-05, + "loss": 2.4954, + "step": 5150 + }, + { + "epoch": 0.23, + "learning_rate": 1.749349158601686e-05, + "loss": 2.4876, + "step": 5160 + }, + { + "epoch": 0.23, + "learning_rate": 1.7484013019209968e-05, + "loss": 2.4912, + "step": 5170 + }, + { + "epoch": 0.23, + "learning_rate": 1.7474519142522938e-05, + "loss": 2.5208, + "step": 5180 + }, + { + "epoch": 0.24, + "learning_rate": 1.7465009975377193e-05, + "loss": 2.4989, + "step": 5190 + }, + { + "epoch": 0.24, + "learning_rate": 1.745548553722542e-05, + "loss": 2.5165, + "step": 5200 + }, + { + "epoch": 0.24, + "learning_rate": 1.7445945847551553e-05, + "loss": 2.4886, + "step": 5210 + }, + { + "epoch": 0.24, + "learning_rate": 1.7436390925870722e-05, + "loss": 2.4798, + "step": 5220 + }, + { + "epoch": 0.24, + "learning_rate": 1.7426820791729223e-05, + "loss": 2.5086, + "step": 5230 + }, + { + "epoch": 0.24, + "learning_rate": 1.741723546470447e-05, + "loss": 2.4916, + "step": 5240 + }, + { + "epoch": 0.24, + "learning_rate": 1.740763496440495e-05, + "loss": 2.4957, + "step": 5250 + }, + { + "epoch": 0.24, + "learning_rate": 1.739801931047019e-05, + "loss": 2.5054, + "step": 5260 + }, + { + "epoch": 0.24, + "learning_rate": 1.7388388522570734e-05, + "loss": 2.4975, + "step": 5270 + }, + { + "epoch": 0.24, + "learning_rate": 1.737874262040806e-05, + "loss": 2.4723, + "step": 5280 + }, + { + "epoch": 0.24, + "learning_rate": 1.7369081623714582e-05, + "loss": 2.4917, + "step": 5290 + }, + { + "epoch": 0.24, + "learning_rate": 1.735940555225359e-05, + "loss": 2.5188, + "step": 5300 + }, + { + "epoch": 0.24, + "learning_rate": 1.7349714425819203e-05, + "loss": 2.5201, + "step": 5310 + }, + { + "epoch": 0.24, + "learning_rate": 1.7340008264236355e-05, + "loss": 2.4911, + "step": 5320 + }, + { + "epoch": 0.24, + "learning_rate": 1.7330287087360712e-05, + "loss": 2.5128, + "step": 5330 + }, + { + "epoch": 0.24, + "learning_rate": 1.7320550915078683e-05, + "loss": 2.4931, + "step": 5340 + }, + { + "epoch": 0.24, + "learning_rate": 1.7310799767307337e-05, + "loss": 2.4939, + "step": 5350 + }, + { + "epoch": 0.24, + "learning_rate": 1.730103366399438e-05, + "loss": 2.5136, + "step": 5360 + }, + { + "epoch": 0.24, + "learning_rate": 1.729125262511811e-05, + "loss": 2.5051, + "step": 5370 + }, + { + "epoch": 0.24, + "learning_rate": 1.728145667068739e-05, + "loss": 2.5114, + "step": 5380 + }, + { + "epoch": 0.24, + "learning_rate": 1.7271645820741586e-05, + "loss": 2.466, + "step": 5390 + }, + { + "epoch": 0.24, + "learning_rate": 1.7261820095350535e-05, + "loss": 2.5067, + "step": 5400 + }, + { + "epoch": 0.25, + "learning_rate": 1.7251979514614504e-05, + "loss": 2.514, + "step": 5410 + }, + { + "epoch": 0.25, + "learning_rate": 1.7242124098664157e-05, + "loss": 2.4983, + "step": 5420 + }, + { + "epoch": 0.25, + "learning_rate": 1.72322538676605e-05, + "loss": 2.4783, + "step": 5430 + }, + { + "epoch": 0.25, + "learning_rate": 1.722236884179484e-05, + "loss": 2.4695, + "step": 5440 + }, + { + "epoch": 0.25, + "learning_rate": 1.7212469041288763e-05, + "loss": 2.4844, + "step": 5450 + }, + { + "epoch": 0.25, + "learning_rate": 1.7202554486394068e-05, + "loss": 2.475, + "step": 5460 + }, + { + "epoch": 0.25, + "learning_rate": 1.7192625197392745e-05, + "loss": 2.5036, + "step": 5470 + }, + { + "epoch": 0.25, + "learning_rate": 1.718268119459692e-05, + "loss": 2.534, + "step": 5480 + }, + { + "epoch": 0.25, + "learning_rate": 1.717272249834882e-05, + "loss": 2.475, + "step": 5490 + }, + { + "epoch": 0.25, + "learning_rate": 1.7162749129020728e-05, + "loss": 2.4817, + "step": 5500 + }, + { + "epoch": 0.25, + "learning_rate": 1.7152761107014945e-05, + "loss": 2.5154, + "step": 5510 + }, + { + "epoch": 0.25, + "learning_rate": 1.714275845276375e-05, + "loss": 2.4787, + "step": 5520 + }, + { + "epoch": 0.25, + "learning_rate": 1.7132741186729347e-05, + "loss": 2.5196, + "step": 5530 + }, + { + "epoch": 0.25, + "learning_rate": 1.7122709329403845e-05, + "loss": 2.5128, + "step": 5540 + }, + { + "epoch": 0.25, + "learning_rate": 1.711266290130918e-05, + "loss": 2.5025, + "step": 5550 + }, + { + "epoch": 0.25, + "learning_rate": 1.7102601922997122e-05, + "loss": 2.5246, + "step": 5560 + }, + { + "epoch": 0.25, + "learning_rate": 1.709252641504918e-05, + "loss": 2.4984, + "step": 5570 + }, + { + "epoch": 0.25, + "learning_rate": 1.7082436398076608e-05, + "loss": 2.4903, + "step": 5580 + }, + { + "epoch": 0.25, + "learning_rate": 1.7072331892720323e-05, + "loss": 2.4873, + "step": 5590 + }, + { + "epoch": 0.25, + "learning_rate": 1.7062212919650895e-05, + "loss": 2.4894, + "step": 5600 + }, + { + "epoch": 0.25, + "learning_rate": 1.7052079499568477e-05, + "loss": 2.4858, + "step": 5610 + }, + { + "epoch": 0.25, + "learning_rate": 1.7041931653202788e-05, + "loss": 2.5158, + "step": 5620 + }, + { + "epoch": 0.26, + "learning_rate": 1.703176940131305e-05, + "loss": 2.4952, + "step": 5630 + }, + { + "epoch": 0.26, + "learning_rate": 1.702159276468796e-05, + "loss": 2.504, + "step": 5640 + }, + { + "epoch": 0.26, + "learning_rate": 1.7011401764145637e-05, + "loss": 2.4712, + "step": 5650 + }, + { + "epoch": 0.26, + "learning_rate": 1.7001196420533584e-05, + "loss": 2.503, + "step": 5660 + }, + { + "epoch": 0.26, + "learning_rate": 1.699097675472865e-05, + "loss": 2.4978, + "step": 5670 + }, + { + "epoch": 0.26, + "learning_rate": 1.6980742787636977e-05, + "loss": 2.5121, + "step": 5680 + }, + { + "epoch": 0.26, + "learning_rate": 1.697049454019397e-05, + "loss": 2.5233, + "step": 5690 + }, + { + "epoch": 0.26, + "learning_rate": 1.696023203336424e-05, + "loss": 2.5124, + "step": 5700 + }, + { + "epoch": 0.26, + "learning_rate": 1.6949955288141566e-05, + "loss": 2.5144, + "step": 5710 + }, + { + "epoch": 0.26, + "learning_rate": 1.6939664325548868e-05, + "loss": 2.4903, + "step": 5720 + }, + { + "epoch": 0.26, + "learning_rate": 1.6929359166638132e-05, + "loss": 2.4857, + "step": 5730 + }, + { + "epoch": 0.26, + "learning_rate": 1.69190398324904e-05, + "loss": 2.5045, + "step": 5740 + }, + { + "epoch": 0.26, + "learning_rate": 1.69087063442157e-05, + "loss": 2.4727, + "step": 5750 + }, + { + "epoch": 0.26, + "learning_rate": 1.6898358722953028e-05, + "loss": 2.4956, + "step": 5760 + }, + { + "epoch": 0.26, + "learning_rate": 1.688799698987028e-05, + "loss": 2.4701, + "step": 5770 + }, + { + "epoch": 0.26, + "learning_rate": 1.6877621166164222e-05, + "loss": 2.5074, + "step": 5780 + }, + { + "epoch": 0.26, + "learning_rate": 1.6867231273060452e-05, + "loss": 2.4902, + "step": 5790 + }, + { + "epoch": 0.26, + "learning_rate": 1.6856827331813344e-05, + "loss": 2.5153, + "step": 5800 + }, + { + "epoch": 0.26, + "learning_rate": 1.684640936370601e-05, + "loss": 2.5026, + "step": 5810 + }, + { + "epoch": 0.26, + "learning_rate": 1.6835977390050256e-05, + "loss": 2.4931, + "step": 5820 + }, + { + "epoch": 0.26, + "learning_rate": 1.6825531432186545e-05, + "loss": 2.5182, + "step": 5830 + }, + { + "epoch": 0.26, + "learning_rate": 1.6815071511483933e-05, + "loss": 2.4823, + "step": 5840 + }, + { + "epoch": 0.27, + "learning_rate": 1.680459764934006e-05, + "loss": 2.5198, + "step": 5850 + }, + { + "epoch": 0.27, + "learning_rate": 1.6794109867181066e-05, + "loss": 2.4722, + "step": 5860 + }, + { + "epoch": 0.27, + "learning_rate": 1.6783608186461576e-05, + "loss": 2.4904, + "step": 5870 + }, + { + "epoch": 0.27, + "learning_rate": 1.6773092628664654e-05, + "loss": 2.4845, + "step": 5880 + }, + { + "epoch": 0.27, + "learning_rate": 1.6762563215301735e-05, + "loss": 2.5111, + "step": 5890 + }, + { + "epoch": 0.27, + "learning_rate": 1.6752019967912613e-05, + "loss": 2.4876, + "step": 5900 + }, + { + "epoch": 0.27, + "learning_rate": 1.6741462908065373e-05, + "loss": 2.5221, + "step": 5910 + }, + { + "epoch": 0.27, + "learning_rate": 1.6730892057356363e-05, + "loss": 2.518, + "step": 5920 + }, + { + "epoch": 0.27, + "learning_rate": 1.6720307437410134e-05, + "loss": 2.4853, + "step": 5930 + }, + { + "epoch": 0.27, + "learning_rate": 1.6709709069879413e-05, + "loss": 2.5022, + "step": 5940 + }, + { + "epoch": 0.27, + "learning_rate": 1.6699096976445046e-05, + "loss": 2.5092, + "step": 5950 + }, + { + "epoch": 0.27, + "learning_rate": 1.668847117881596e-05, + "loss": 2.4856, + "step": 5960 + }, + { + "epoch": 0.27, + "learning_rate": 1.6677831698729106e-05, + "loss": 2.5005, + "step": 5970 + }, + { + "epoch": 0.27, + "learning_rate": 1.666717855794944e-05, + "loss": 2.5036, + "step": 5980 + }, + { + "epoch": 0.27, + "learning_rate": 1.6656511778269856e-05, + "loss": 2.4962, + "step": 5990 + }, + { + "epoch": 0.27, + "learning_rate": 1.664583138151115e-05, + "loss": 2.5063, + "step": 6000 + }, + { + "epoch": 0.27, + "eval_accuracy": 0.539072438522612, + "eval_loss": 2.253763437271118, + "eval_runtime": 9.8813, + "eval_samples_per_second": 138.342, + "eval_steps_per_second": 1.113, + "step": 6000 + }, + { + "epoch": 0.27, + "learning_rate": 1.663513738952198e-05, + "loss": 2.4694, + "step": 6010 + }, + { + "epoch": 0.27, + "learning_rate": 1.6624429824178794e-05, + "loss": 2.4673, + "step": 6020 + }, + { + "epoch": 0.27, + "learning_rate": 1.6613708707385832e-05, + "loss": 2.4789, + "step": 6030 + }, + { + "epoch": 0.27, + "learning_rate": 1.660297406107505e-05, + "loss": 2.495, + "step": 6040 + }, + { + "epoch": 0.27, + "learning_rate": 1.6592225907206065e-05, + "loss": 2.4933, + "step": 6050 + }, + { + "epoch": 0.27, + "learning_rate": 1.6581464267766144e-05, + "loss": 2.4915, + "step": 6060 + }, + { + "epoch": 0.28, + "learning_rate": 1.6570689164770138e-05, + "loss": 2.5032, + "step": 6070 + }, + { + "epoch": 0.28, + "learning_rate": 1.6559900620260435e-05, + "loss": 2.4912, + "step": 6080 + }, + { + "epoch": 0.28, + "learning_rate": 1.654909865630692e-05, + "loss": 2.5178, + "step": 6090 + }, + { + "epoch": 0.28, + "learning_rate": 1.6538283295006933e-05, + "loss": 2.4834, + "step": 6100 + }, + { + "epoch": 0.28, + "learning_rate": 1.6527454558485222e-05, + "loss": 2.4941, + "step": 6110 + }, + { + "epoch": 0.28, + "learning_rate": 1.6516612468893892e-05, + "loss": 2.5131, + "step": 6120 + }, + { + "epoch": 0.28, + "learning_rate": 1.650575704841237e-05, + "loss": 2.485, + "step": 6130 + }, + { + "epoch": 0.28, + "learning_rate": 1.6494888319247345e-05, + "loss": 2.5086, + "step": 6140 + }, + { + "epoch": 0.28, + "learning_rate": 1.648400630363274e-05, + "loss": 2.4829, + "step": 6150 + }, + { + "epoch": 0.28, + "learning_rate": 1.6473111023829646e-05, + "loss": 2.5099, + "step": 6160 + }, + { + "epoch": 0.28, + "learning_rate": 1.6462202502126307e-05, + "loss": 2.4983, + "step": 6170 + }, + { + "epoch": 0.28, + "learning_rate": 1.6451280760838036e-05, + "loss": 2.4665, + "step": 6180 + }, + { + "epoch": 0.28, + "learning_rate": 1.6440345822307204e-05, + "loss": 2.5018, + "step": 6190 + }, + { + "epoch": 0.28, + "learning_rate": 1.6429397708903172e-05, + "loss": 2.5068, + "step": 6200 + }, + { + "epoch": 0.28, + "learning_rate": 1.6418436443022254e-05, + "loss": 2.5092, + "step": 6210 + }, + { + "epoch": 0.28, + "learning_rate": 1.6407462047087667e-05, + "loss": 2.5059, + "step": 6220 + }, + { + "epoch": 0.28, + "learning_rate": 1.639647454354949e-05, + "loss": 2.4755, + "step": 6230 + }, + { + "epoch": 0.28, + "learning_rate": 1.638547395488462e-05, + "loss": 2.5195, + "step": 6240 + }, + { + "epoch": 0.28, + "learning_rate": 1.6374460303596718e-05, + "loss": 2.5125, + "step": 6250 + }, + { + "epoch": 0.28, + "learning_rate": 1.6363433612216163e-05, + "loss": 2.4828, + "step": 6260 + }, + { + "epoch": 0.28, + "learning_rate": 1.635239390330002e-05, + "loss": 2.4812, + "step": 6270 + }, + { + "epoch": 0.28, + "learning_rate": 1.6341341199431974e-05, + "loss": 2.5017, + "step": 6280 + }, + { + "epoch": 0.29, + "learning_rate": 1.6330275523222294e-05, + "loss": 2.5011, + "step": 6290 + }, + { + "epoch": 0.29, + "learning_rate": 1.6319196897307795e-05, + "loss": 2.4904, + "step": 6300 + }, + { + "epoch": 0.29, + "learning_rate": 1.6308105344351776e-05, + "loss": 2.4735, + "step": 6310 + }, + { + "epoch": 0.29, + "learning_rate": 1.6297000887043978e-05, + "loss": 2.5133, + "step": 6320 + }, + { + "epoch": 0.29, + "learning_rate": 1.6285883548100552e-05, + "loss": 2.4806, + "step": 6330 + }, + { + "epoch": 0.29, + "learning_rate": 1.6274753350263987e-05, + "loss": 2.4784, + "step": 6340 + }, + { + "epoch": 0.29, + "learning_rate": 1.6263610316303084e-05, + "loss": 2.4876, + "step": 6350 + }, + { + "epoch": 0.29, + "learning_rate": 1.62524544690129e-05, + "loss": 2.4851, + "step": 6360 + }, + { + "epoch": 0.29, + "learning_rate": 1.6241285831214707e-05, + "loss": 2.4619, + "step": 6370 + }, + { + "epoch": 0.29, + "learning_rate": 1.623010442575594e-05, + "loss": 2.4809, + "step": 6380 + }, + { + "epoch": 0.29, + "learning_rate": 1.621891027551015e-05, + "loss": 2.5083, + "step": 6390 + }, + { + "epoch": 0.29, + "learning_rate": 1.6207703403376973e-05, + "loss": 2.4874, + "step": 6400 + }, + { + "epoch": 0.29, + "learning_rate": 1.619648383228205e-05, + "loss": 2.489, + "step": 6410 + }, + { + "epoch": 0.29, + "learning_rate": 1.6185251585177013e-05, + "loss": 2.4943, + "step": 6420 + }, + { + "epoch": 0.29, + "learning_rate": 1.6174006685039425e-05, + "loss": 2.505, + "step": 6430 + }, + { + "epoch": 0.29, + "learning_rate": 1.6162749154872725e-05, + "loss": 2.4801, + "step": 6440 + }, + { + "epoch": 0.29, + "learning_rate": 1.6151479017706192e-05, + "loss": 2.5019, + "step": 6450 + }, + { + "epoch": 0.29, + "learning_rate": 1.6140196296594903e-05, + "loss": 2.508, + "step": 6460 + }, + { + "epoch": 0.29, + "learning_rate": 1.612890101461967e-05, + "loss": 2.4834, + "step": 6470 + }, + { + "epoch": 0.29, + "learning_rate": 1.6117593194886998e-05, + "loss": 2.4867, + "step": 6480 + }, + { + "epoch": 0.29, + "learning_rate": 1.6106272860529047e-05, + "loss": 2.5108, + "step": 6490 + }, + { + "epoch": 0.29, + "learning_rate": 1.6094940034703577e-05, + "loss": 2.4923, + "step": 6500 + }, + { + "epoch": 0.3, + "learning_rate": 1.6083594740593896e-05, + "loss": 2.5038, + "step": 6510 + }, + { + "epoch": 0.3, + "learning_rate": 1.6072237001408822e-05, + "loss": 2.5141, + "step": 6520 + }, + { + "epoch": 0.3, + "learning_rate": 1.6060866840382632e-05, + "loss": 2.5012, + "step": 6530 + }, + { + "epoch": 0.3, + "learning_rate": 1.6049484280775012e-05, + "loss": 2.4999, + "step": 6540 + }, + { + "epoch": 0.3, + "learning_rate": 1.6038089345871015e-05, + "loss": 2.4975, + "step": 6550 + }, + { + "epoch": 0.3, + "learning_rate": 1.6026682058981006e-05, + "loss": 2.5073, + "step": 6560 + }, + { + "epoch": 0.3, + "learning_rate": 1.6015262443440618e-05, + "loss": 2.4875, + "step": 6570 + }, + { + "epoch": 0.3, + "learning_rate": 1.6003830522610712e-05, + "loss": 2.5146, + "step": 6580 + }, + { + "epoch": 0.3, + "learning_rate": 1.599238631987731e-05, + "loss": 2.4881, + "step": 6590 + }, + { + "epoch": 0.3, + "learning_rate": 1.598092985865157e-05, + "loss": 2.481, + "step": 6600 + }, + { + "epoch": 0.3, + "learning_rate": 1.5969461162369718e-05, + "loss": 2.4918, + "step": 6610 + }, + { + "epoch": 0.3, + "learning_rate": 1.595798025449301e-05, + "loss": 2.4875, + "step": 6620 + }, + { + "epoch": 0.3, + "learning_rate": 1.5946487158507693e-05, + "loss": 2.4693, + "step": 6630 + }, + { + "epoch": 0.3, + "learning_rate": 1.5934981897924937e-05, + "loss": 2.5047, + "step": 6640 + }, + { + "epoch": 0.3, + "learning_rate": 1.5923464496280797e-05, + "loss": 2.5147, + "step": 6650 + }, + { + "epoch": 0.3, + "learning_rate": 1.5911934977136167e-05, + "loss": 2.4647, + "step": 6660 + }, + { + "epoch": 0.3, + "learning_rate": 1.5900393364076735e-05, + "loss": 2.4744, + "step": 6670 + }, + { + "epoch": 0.3, + "learning_rate": 1.5888839680712918e-05, + "loss": 2.4781, + "step": 6680 + }, + { + "epoch": 0.3, + "learning_rate": 1.587727395067983e-05, + "loss": 2.5232, + "step": 6690 + }, + { + "epoch": 0.3, + "learning_rate": 1.5865696197637234e-05, + "loss": 2.4996, + "step": 6700 + }, + { + "epoch": 0.3, + "learning_rate": 1.5854106445269483e-05, + "loss": 2.4779, + "step": 6710 + }, + { + "epoch": 0.3, + "learning_rate": 1.584250471728548e-05, + "loss": 2.5024, + "step": 6720 + }, + { + "epoch": 0.31, + "learning_rate": 1.5830891037418615e-05, + "loss": 2.4704, + "step": 6730 + }, + { + "epoch": 0.31, + "learning_rate": 1.5819265429426748e-05, + "loss": 2.5011, + "step": 6740 + }, + { + "epoch": 0.31, + "learning_rate": 1.5807627917092118e-05, + "loss": 2.4715, + "step": 6750 + }, + { + "epoch": 0.31, + "learning_rate": 1.579597852422133e-05, + "loss": 2.5069, + "step": 6760 + }, + { + "epoch": 0.31, + "learning_rate": 1.5784317274645294e-05, + "loss": 2.4801, + "step": 6770 + }, + { + "epoch": 0.31, + "learning_rate": 1.5772644192219164e-05, + "loss": 2.4633, + "step": 6780 + }, + { + "epoch": 0.31, + "learning_rate": 1.5760959300822313e-05, + "loss": 2.4838, + "step": 6790 + }, + { + "epoch": 0.31, + "learning_rate": 1.574926262435826e-05, + "loss": 2.4959, + "step": 6800 + }, + { + "epoch": 0.31, + "learning_rate": 1.573755418675464e-05, + "loss": 2.4952, + "step": 6810 + }, + { + "epoch": 0.31, + "learning_rate": 1.572583401196315e-05, + "loss": 2.4767, + "step": 6820 + }, + { + "epoch": 0.31, + "learning_rate": 1.5714102123959485e-05, + "loss": 2.4918, + "step": 6830 + }, + { + "epoch": 0.31, + "learning_rate": 1.5702358546743314e-05, + "loss": 2.5085, + "step": 6840 + }, + { + "epoch": 0.31, + "learning_rate": 1.569060330433821e-05, + "loss": 2.5108, + "step": 6850 + }, + { + "epoch": 0.31, + "learning_rate": 1.5678836420791618e-05, + "loss": 2.5056, + "step": 6860 + }, + { + "epoch": 0.31, + "learning_rate": 1.5667057920174785e-05, + "loss": 2.4979, + "step": 6870 + }, + { + "epoch": 0.31, + "learning_rate": 1.565526782658273e-05, + "loss": 2.5092, + "step": 6880 + }, + { + "epoch": 0.31, + "learning_rate": 1.5643466164134196e-05, + "loss": 2.4869, + "step": 6890 + }, + { + "epoch": 0.31, + "learning_rate": 1.5631652956971576e-05, + "loss": 2.4805, + "step": 6900 + }, + { + "epoch": 0.31, + "learning_rate": 1.561982822926089e-05, + "loss": 2.4754, + "step": 6910 + }, + { + "epoch": 0.31, + "learning_rate": 1.5607992005191717e-05, + "loss": 2.5099, + "step": 6920 + }, + { + "epoch": 0.31, + "learning_rate": 1.5596144308977167e-05, + "loss": 2.476, + "step": 6930 + }, + { + "epoch": 0.31, + "learning_rate": 1.5584285164853802e-05, + "loss": 2.5084, + "step": 6940 + }, + { + "epoch": 0.31, + "learning_rate": 1.5572414597081617e-05, + "loss": 2.4775, + "step": 6950 + }, + { + "epoch": 0.32, + "learning_rate": 1.5560532629943968e-05, + "loss": 2.4663, + "step": 6960 + }, + { + "epoch": 0.32, + "learning_rate": 1.5548639287747537e-05, + "loss": 2.4791, + "step": 6970 + }, + { + "epoch": 0.32, + "learning_rate": 1.5536734594822266e-05, + "loss": 2.4713, + "step": 6980 + }, + { + "epoch": 0.32, + "learning_rate": 1.552481857552132e-05, + "loss": 2.4699, + "step": 6990 + }, + { + "epoch": 0.32, + "learning_rate": 1.5512891254221046e-05, + "loss": 2.4678, + "step": 7000 + }, + { + "epoch": 0.32, + "learning_rate": 1.5500952655320892e-05, + "loss": 2.4733, + "step": 7010 + }, + { + "epoch": 0.32, + "learning_rate": 1.5489002803243396e-05, + "loss": 2.5095, + "step": 7020 + }, + { + "epoch": 0.32, + "learning_rate": 1.5477041722434096e-05, + "loss": 2.4851, + "step": 7030 + }, + { + "epoch": 0.32, + "learning_rate": 1.5465069437361516e-05, + "loss": 2.4988, + "step": 7040 + }, + { + "epoch": 0.32, + "learning_rate": 1.54530859725171e-05, + "loss": 2.4799, + "step": 7050 + }, + { + "epoch": 0.32, + "learning_rate": 1.5441091352415148e-05, + "loss": 2.4921, + "step": 7060 + }, + { + "epoch": 0.32, + "learning_rate": 1.5429085601592794e-05, + "loss": 2.5083, + "step": 7070 + }, + { + "epoch": 0.32, + "learning_rate": 1.541706874460994e-05, + "loss": 2.466, + "step": 7080 + }, + { + "epoch": 0.32, + "learning_rate": 1.5405040806049202e-05, + "loss": 2.4906, + "step": 7090 + }, + { + "epoch": 0.32, + "learning_rate": 1.5393001810515865e-05, + "loss": 2.4883, + "step": 7100 + }, + { + "epoch": 0.32, + "learning_rate": 1.538095178263784e-05, + "loss": 2.4842, + "step": 7110 + }, + { + "epoch": 0.32, + "learning_rate": 1.5368890747065604e-05, + "loss": 2.4967, + "step": 7120 + }, + { + "epoch": 0.32, + "learning_rate": 1.535681872847215e-05, + "loss": 2.4957, + "step": 7130 + }, + { + "epoch": 0.32, + "learning_rate": 1.5344735751552935e-05, + "loss": 2.5003, + "step": 7140 + }, + { + "epoch": 0.32, + "learning_rate": 1.533264184102585e-05, + "loss": 2.4989, + "step": 7150 + }, + { + "epoch": 0.32, + "learning_rate": 1.5320537021631126e-05, + "loss": 2.4865, + "step": 7160 + }, + { + "epoch": 0.32, + "learning_rate": 1.5308421318131333e-05, + "loss": 2.4966, + "step": 7170 + }, + { + "epoch": 0.33, + "learning_rate": 1.5296294755311295e-05, + "loss": 2.4821, + "step": 7180 + }, + { + "epoch": 0.33, + "learning_rate": 1.528415735797806e-05, + "loss": 2.4826, + "step": 7190 + }, + { + "epoch": 0.33, + "learning_rate": 1.5272009150960828e-05, + "loss": 2.4998, + "step": 7200 + }, + { + "epoch": 0.33, + "learning_rate": 1.5259850159110917e-05, + "loss": 2.4705, + "step": 7210 + }, + { + "epoch": 0.33, + "learning_rate": 1.5247680407301708e-05, + "loss": 2.4692, + "step": 7220 + }, + { + "epoch": 0.33, + "learning_rate": 1.52354999204286e-05, + "loss": 2.4782, + "step": 7230 + }, + { + "epoch": 0.33, + "learning_rate": 1.5223308723408936e-05, + "loss": 2.5029, + "step": 7240 + }, + { + "epoch": 0.33, + "learning_rate": 1.5211106841181988e-05, + "loss": 2.5012, + "step": 7250 + }, + { + "epoch": 0.33, + "learning_rate": 1.519889429870887e-05, + "loss": 2.4967, + "step": 7260 + }, + { + "epoch": 0.33, + "learning_rate": 1.5186671120972514e-05, + "loss": 2.469, + "step": 7270 + }, + { + "epoch": 0.33, + "learning_rate": 1.5174437332977606e-05, + "loss": 2.4666, + "step": 7280 + }, + { + "epoch": 0.33, + "learning_rate": 1.5162192959750532e-05, + "loss": 2.5038, + "step": 7290 + }, + { + "epoch": 0.33, + "learning_rate": 1.5149938026339341e-05, + "loss": 2.4995, + "step": 7300 + }, + { + "epoch": 0.33, + "learning_rate": 1.5137672557813672e-05, + "loss": 2.485, + "step": 7310 + }, + { + "epoch": 0.33, + "learning_rate": 1.5125396579264728e-05, + "loss": 2.4878, + "step": 7320 + }, + { + "epoch": 0.33, + "learning_rate": 1.5113110115805208e-05, + "loss": 2.5114, + "step": 7330 + }, + { + "epoch": 0.33, + "learning_rate": 1.5100813192569254e-05, + "loss": 2.4687, + "step": 7340 + }, + { + "epoch": 0.33, + "learning_rate": 1.5088505834712414e-05, + "loss": 2.521, + "step": 7350 + }, + { + "epoch": 0.33, + "learning_rate": 1.5076188067411582e-05, + "loss": 2.4765, + "step": 7360 + }, + { + "epoch": 0.33, + "learning_rate": 1.5063859915864936e-05, + "loss": 2.4709, + "step": 7370 + }, + { + "epoch": 0.33, + "learning_rate": 1.5051521405291905e-05, + "loss": 2.5008, + "step": 7380 + }, + { + "epoch": 0.33, + "learning_rate": 1.5039172560933109e-05, + "loss": 2.4881, + "step": 7390 + }, + { + "epoch": 0.34, + "learning_rate": 1.5026813408050305e-05, + "loss": 2.4938, + "step": 7400 + }, + { + "epoch": 0.34, + "learning_rate": 1.5014443971926338e-05, + "loss": 2.4877, + "step": 7410 + }, + { + "epoch": 0.34, + "learning_rate": 1.5002064277865094e-05, + "loss": 2.4864, + "step": 7420 + }, + { + "epoch": 0.34, + "learning_rate": 1.4989674351191436e-05, + "loss": 2.4753, + "step": 7430 + }, + { + "epoch": 0.34, + "learning_rate": 1.4977274217251166e-05, + "loss": 2.5124, + "step": 7440 + }, + { + "epoch": 0.34, + "learning_rate": 1.4964863901410962e-05, + "loss": 2.493, + "step": 7450 + }, + { + "epoch": 0.34, + "learning_rate": 1.4952443429058334e-05, + "loss": 2.4917, + "step": 7460 + }, + { + "epoch": 0.34, + "learning_rate": 1.4940012825601569e-05, + "loss": 2.4878, + "step": 7470 + }, + { + "epoch": 0.34, + "learning_rate": 1.4927572116469672e-05, + "loss": 2.4643, + "step": 7480 + }, + { + "epoch": 0.34, + "learning_rate": 1.4915121327112338e-05, + "loss": 2.4884, + "step": 7490 + }, + { + "epoch": 0.34, + "learning_rate": 1.4902660482999865e-05, + "loss": 2.4961, + "step": 7500 + }, + { + "epoch": 0.34, + "learning_rate": 1.4890189609623122e-05, + "loss": 2.4694, + "step": 7510 + }, + { + "epoch": 0.34, + "learning_rate": 1.4877708732493508e-05, + "loss": 2.471, + "step": 7520 + }, + { + "epoch": 0.34, + "learning_rate": 1.4865217877142872e-05, + "loss": 2.4625, + "step": 7530 + }, + { + "epoch": 0.34, + "learning_rate": 1.4852717069123483e-05, + "loss": 2.4878, + "step": 7540 + }, + { + "epoch": 0.34, + "learning_rate": 1.484020633400797e-05, + "loss": 2.4999, + "step": 7550 + }, + { + "epoch": 0.34, + "learning_rate": 1.4827685697389265e-05, + "loss": 2.4931, + "step": 7560 + }, + { + "epoch": 0.34, + "learning_rate": 1.4815155184880557e-05, + "loss": 2.4862, + "step": 7570 + }, + { + "epoch": 0.34, + "learning_rate": 1.4802614822115235e-05, + "loss": 2.496, + "step": 7580 + }, + { + "epoch": 0.34, + "learning_rate": 1.479006463474685e-05, + "loss": 2.4618, + "step": 7590 + }, + { + "epoch": 0.34, + "learning_rate": 1.4777504648449044e-05, + "loss": 2.4749, + "step": 7600 + }, + { + "epoch": 0.34, + "learning_rate": 1.4764934888915494e-05, + "loss": 2.4874, + "step": 7610 + }, + { + "epoch": 0.35, + "learning_rate": 1.4752355381859888e-05, + "loss": 2.4869, + "step": 7620 + }, + { + "epoch": 0.35, + "learning_rate": 1.4739766153015842e-05, + "loss": 2.473, + "step": 7630 + }, + { + "epoch": 0.35, + "learning_rate": 1.4727167228136862e-05, + "loss": 2.4901, + "step": 7640 + }, + { + "epoch": 0.35, + "learning_rate": 1.4714558632996297e-05, + "loss": 2.4881, + "step": 7650 + }, + { + "epoch": 0.35, + "learning_rate": 1.4701940393387264e-05, + "loss": 2.4849, + "step": 7660 + }, + { + "epoch": 0.35, + "learning_rate": 1.468931253512262e-05, + "loss": 2.4872, + "step": 7670 + }, + { + "epoch": 0.35, + "learning_rate": 1.4676675084034897e-05, + "loss": 2.4706, + "step": 7680 + }, + { + "epoch": 0.35, + "learning_rate": 1.4664028065976245e-05, + "loss": 2.4929, + "step": 7690 + }, + { + "epoch": 0.35, + "learning_rate": 1.4651371506818395e-05, + "loss": 2.5027, + "step": 7700 + }, + { + "epoch": 0.35, + "learning_rate": 1.463870543245259e-05, + "loss": 2.4725, + "step": 7710 + }, + { + "epoch": 0.35, + "learning_rate": 1.4626029868789535e-05, + "loss": 2.4946, + "step": 7720 + }, + { + "epoch": 0.35, + "learning_rate": 1.4613344841759354e-05, + "loss": 2.465, + "step": 7730 + }, + { + "epoch": 0.35, + "learning_rate": 1.4600650377311523e-05, + "loss": 2.4928, + "step": 7740 + }, + { + "epoch": 0.35, + "learning_rate": 1.4587946501414832e-05, + "loss": 2.4926, + "step": 7750 + }, + { + "epoch": 0.35, + "learning_rate": 1.4575233240057314e-05, + "loss": 2.4775, + "step": 7760 + }, + { + "epoch": 0.35, + "learning_rate": 1.4562510619246213e-05, + "loss": 2.4851, + "step": 7770 + }, + { + "epoch": 0.35, + "learning_rate": 1.454977866500791e-05, + "loss": 2.4875, + "step": 7780 + }, + { + "epoch": 0.35, + "learning_rate": 1.4537037403387882e-05, + "loss": 2.4923, + "step": 7790 + }, + { + "epoch": 0.35, + "learning_rate": 1.4524286860450646e-05, + "loss": 2.5041, + "step": 7800 + }, + { + "epoch": 0.35, + "learning_rate": 1.451152706227971e-05, + "loss": 2.4803, + "step": 7810 + }, + { + "epoch": 0.35, + "learning_rate": 1.4498758034977507e-05, + "loss": 2.4748, + "step": 7820 + }, + { + "epoch": 0.35, + "learning_rate": 1.4485979804665358e-05, + "loss": 2.473, + "step": 7830 + }, + { + "epoch": 0.36, + "learning_rate": 1.4473192397483403e-05, + "loss": 2.4936, + "step": 7840 + }, + { + "epoch": 0.36, + "learning_rate": 1.4460395839590563e-05, + "loss": 2.501, + "step": 7850 + }, + { + "epoch": 0.36, + "learning_rate": 1.4447590157164466e-05, + "loss": 2.5057, + "step": 7860 + }, + { + "epoch": 0.36, + "learning_rate": 1.4434775376401424e-05, + "loss": 2.4603, + "step": 7870 + }, + { + "epoch": 0.36, + "learning_rate": 1.442195152351634e-05, + "loss": 2.4675, + "step": 7880 + }, + { + "epoch": 0.36, + "learning_rate": 1.4409118624742696e-05, + "loss": 2.507, + "step": 7890 + }, + { + "epoch": 0.36, + "learning_rate": 1.4396276706332461e-05, + "loss": 2.4854, + "step": 7900 + }, + { + "epoch": 0.36, + "learning_rate": 1.4383425794556072e-05, + "loss": 2.4905, + "step": 7910 + }, + { + "epoch": 0.36, + "learning_rate": 1.437056591570235e-05, + "loss": 2.4925, + "step": 7920 + }, + { + "epoch": 0.36, + "learning_rate": 1.435769709607847e-05, + "loss": 2.4565, + "step": 7930 + }, + { + "epoch": 0.36, + "learning_rate": 1.4344819362009885e-05, + "loss": 2.4914, + "step": 7940 + }, + { + "epoch": 0.36, + "learning_rate": 1.4331932739840298e-05, + "loss": 2.4601, + "step": 7950 + }, + { + "epoch": 0.36, + "learning_rate": 1.4319037255931582e-05, + "loss": 2.4923, + "step": 7960 + }, + { + "epoch": 0.36, + "learning_rate": 1.4306132936663749e-05, + "loss": 2.4638, + "step": 7970 + }, + { + "epoch": 0.36, + "learning_rate": 1.4293219808434875e-05, + "loss": 2.4854, + "step": 7980 + }, + { + "epoch": 0.36, + "learning_rate": 1.4280297897661063e-05, + "loss": 2.5125, + "step": 7990 + }, + { + "epoch": 0.36, + "learning_rate": 1.4267367230776383e-05, + "loss": 2.4939, + "step": 8000 + }, + { + "epoch": 0.36, + "eval_accuracy": 0.5401815307188504, + "eval_loss": 2.244050979614258, + "eval_runtime": 9.925, + "eval_samples_per_second": 137.733, + "eval_steps_per_second": 1.108, + "step": 8000 + }, + { + "epoch": 0.36, + "learning_rate": 1.4254427834232811e-05, + "loss": 2.4725, + "step": 8010 + }, + { + "epoch": 0.36, + "learning_rate": 1.4241479734500187e-05, + "loss": 2.4881, + "step": 8020 + }, + { + "epoch": 0.36, + "learning_rate": 1.422852295806615e-05, + "loss": 2.4651, + "step": 8030 + }, + { + "epoch": 0.36, + "learning_rate": 1.4215557531436095e-05, + "loss": 2.5104, + "step": 8040 + }, + { + "epoch": 0.36, + "learning_rate": 1.4202583481133107e-05, + "loss": 2.4719, + "step": 8050 + }, + { + "epoch": 0.37, + "learning_rate": 1.418960083369791e-05, + "loss": 2.4504, + "step": 8060 + }, + { + "epoch": 0.37, + "learning_rate": 1.417660961568883e-05, + "loss": 2.4851, + "step": 8070 + }, + { + "epoch": 0.37, + "learning_rate": 1.4163609853681704e-05, + "loss": 2.4842, + "step": 8080 + }, + { + "epoch": 0.37, + "learning_rate": 1.4150601574269862e-05, + "loss": 2.4873, + "step": 8090 + }, + { + "epoch": 0.37, + "learning_rate": 1.4137584804064055e-05, + "loss": 2.4766, + "step": 8100 + }, + { + "epoch": 0.37, + "learning_rate": 1.41245595696924e-05, + "loss": 2.492, + "step": 8110 + }, + { + "epoch": 0.37, + "learning_rate": 1.4111525897800333e-05, + "loss": 2.4844, + "step": 8120 + }, + { + "epoch": 0.37, + "learning_rate": 1.4098483815050548e-05, + "loss": 2.4887, + "step": 8130 + }, + { + "epoch": 0.37, + "learning_rate": 1.4085433348122946e-05, + "loss": 2.4792, + "step": 8140 + }, + { + "epoch": 0.37, + "learning_rate": 1.4072374523714577e-05, + "loss": 2.4944, + "step": 8150 + }, + { + "epoch": 0.37, + "learning_rate": 1.4059307368539594e-05, + "loss": 2.4783, + "step": 8160 + }, + { + "epoch": 0.37, + "learning_rate": 1.4046231909329184e-05, + "loss": 2.4608, + "step": 8170 + }, + { + "epoch": 0.37, + "learning_rate": 1.4033148172831526e-05, + "loss": 2.4837, + "step": 8180 + }, + { + "epoch": 0.37, + "learning_rate": 1.402005618581173e-05, + "loss": 2.477, + "step": 8190 + }, + { + "epoch": 0.37, + "learning_rate": 1.4006955975051788e-05, + "loss": 2.4932, + "step": 8200 + }, + { + "epoch": 0.37, + "learning_rate": 1.399384756735051e-05, + "loss": 2.489, + "step": 8210 + }, + { + "epoch": 0.37, + "learning_rate": 1.3980730989523473e-05, + "loss": 2.4782, + "step": 8220 + }, + { + "epoch": 0.37, + "learning_rate": 1.3967606268402975e-05, + "loss": 2.4819, + "step": 8230 + }, + { + "epoch": 0.37, + "learning_rate": 1.3954473430837965e-05, + "loss": 2.4772, + "step": 8240 + }, + { + "epoch": 0.37, + "learning_rate": 1.3941332503694001e-05, + "loss": 2.4997, + "step": 8250 + }, + { + "epoch": 0.37, + "learning_rate": 1.3928183513853188e-05, + "loss": 2.4828, + "step": 8260 + }, + { + "epoch": 0.37, + "learning_rate": 1.3915026488214118e-05, + "loss": 2.5103, + "step": 8270 + }, + { + "epoch": 0.38, + "learning_rate": 1.3901861453691834e-05, + "loss": 2.503, + "step": 8280 + }, + { + "epoch": 0.38, + "learning_rate": 1.3888688437217757e-05, + "loss": 2.4911, + "step": 8290 + }, + { + "epoch": 0.38, + "learning_rate": 1.3875507465739633e-05, + "loss": 2.4989, + "step": 8300 + }, + { + "epoch": 0.38, + "learning_rate": 1.3862318566221481e-05, + "loss": 2.4716, + "step": 8310 + }, + { + "epoch": 0.38, + "learning_rate": 1.3849121765643549e-05, + "loss": 2.5075, + "step": 8320 + }, + { + "epoch": 0.38, + "learning_rate": 1.3835917091002236e-05, + "loss": 2.5114, + "step": 8330 + }, + { + "epoch": 0.38, + "learning_rate": 1.3822704569310053e-05, + "loss": 2.4933, + "step": 8340 + }, + { + "epoch": 0.38, + "learning_rate": 1.3809484227595564e-05, + "loss": 2.4884, + "step": 8350 + }, + { + "epoch": 0.38, + "learning_rate": 1.3796256092903333e-05, + "loss": 2.4812, + "step": 8360 + }, + { + "epoch": 0.38, + "learning_rate": 1.3783020192293858e-05, + "loss": 2.4746, + "step": 8370 + }, + { + "epoch": 0.38, + "learning_rate": 1.3769776552843532e-05, + "loss": 2.4646, + "step": 8380 + }, + { + "epoch": 0.38, + "learning_rate": 1.3756525201644577e-05, + "loss": 2.5032, + "step": 8390 + }, + { + "epoch": 0.38, + "learning_rate": 1.3743266165804983e-05, + "loss": 2.4692, + "step": 8400 + }, + { + "epoch": 0.38, + "learning_rate": 1.3729999472448474e-05, + "loss": 2.4748, + "step": 8410 + }, + { + "epoch": 0.38, + "learning_rate": 1.3716725148714429e-05, + "loss": 2.465, + "step": 8420 + }, + { + "epoch": 0.38, + "learning_rate": 1.3703443221757838e-05, + "loss": 2.4649, + "step": 8430 + }, + { + "epoch": 0.38, + "learning_rate": 1.3690153718749248e-05, + "loss": 2.4688, + "step": 8440 + }, + { + "epoch": 0.38, + "learning_rate": 1.36768566668747e-05, + "loss": 2.4741, + "step": 8450 + }, + { + "epoch": 0.38, + "learning_rate": 1.3663552093335676e-05, + "loss": 2.4869, + "step": 8460 + }, + { + "epoch": 0.38, + "learning_rate": 1.3650240025349055e-05, + "loss": 2.4578, + "step": 8470 + }, + { + "epoch": 0.38, + "learning_rate": 1.3636920490147034e-05, + "loss": 2.4768, + "step": 8480 + }, + { + "epoch": 0.38, + "learning_rate": 1.3623593514977098e-05, + "loss": 2.5064, + "step": 8490 + }, + { + "epoch": 0.39, + "learning_rate": 1.361025912710194e-05, + "loss": 2.4767, + "step": 8500 + }, + { + "epoch": 0.39, + "learning_rate": 1.3596917353799426e-05, + "loss": 2.475, + "step": 8510 + }, + { + "epoch": 0.39, + "learning_rate": 1.3583568222362526e-05, + "loss": 2.4926, + "step": 8520 + }, + { + "epoch": 0.39, + "learning_rate": 1.3570211760099265e-05, + "loss": 2.4748, + "step": 8530 + }, + { + "epoch": 0.39, + "learning_rate": 1.3556847994332662e-05, + "loss": 2.507, + "step": 8540 + }, + { + "epoch": 0.39, + "learning_rate": 1.3543476952400676e-05, + "loss": 2.491, + "step": 8550 + }, + { + "epoch": 0.39, + "learning_rate": 1.3530098661656155e-05, + "loss": 2.468, + "step": 8560 + }, + { + "epoch": 0.39, + "learning_rate": 1.351671314946677e-05, + "loss": 2.5024, + "step": 8570 + }, + { + "epoch": 0.39, + "learning_rate": 1.3503320443214968e-05, + "loss": 2.4747, + "step": 8580 + }, + { + "epoch": 0.39, + "learning_rate": 1.3489920570297916e-05, + "loss": 2.4857, + "step": 8590 + }, + { + "epoch": 0.39, + "learning_rate": 1.3476513558127433e-05, + "loss": 2.4804, + "step": 8600 + }, + { + "epoch": 0.39, + "learning_rate": 1.346309943412995e-05, + "loss": 2.4737, + "step": 8610 + }, + { + "epoch": 0.39, + "learning_rate": 1.3449678225746445e-05, + "loss": 2.4841, + "step": 8620 + }, + { + "epoch": 0.39, + "learning_rate": 1.3436249960432386e-05, + "loss": 2.4936, + "step": 8630 + }, + { + "epoch": 0.39, + "learning_rate": 1.3422814665657677e-05, + "loss": 2.5065, + "step": 8640 + }, + { + "epoch": 0.39, + "learning_rate": 1.340937236890661e-05, + "loss": 2.4979, + "step": 8650 + }, + { + "epoch": 0.39, + "learning_rate": 1.339592309767779e-05, + "loss": 2.4755, + "step": 8660 + }, + { + "epoch": 0.39, + "learning_rate": 1.3382466879484092e-05, + "loss": 2.4979, + "step": 8670 + }, + { + "epoch": 0.39, + "learning_rate": 1.336900374185261e-05, + "loss": 2.4854, + "step": 8680 + }, + { + "epoch": 0.39, + "learning_rate": 1.3355533712324586e-05, + "loss": 2.4722, + "step": 8690 + }, + { + "epoch": 0.39, + "learning_rate": 1.3342056818455359e-05, + "loss": 2.4854, + "step": 8700 + }, + { + "epoch": 0.39, + "learning_rate": 1.3328573087814314e-05, + "loss": 2.4955, + "step": 8710 + }, + { + "epoch": 0.4, + "learning_rate": 1.3315082547984819e-05, + "loss": 2.4944, + "step": 8720 + }, + { + "epoch": 0.4, + "learning_rate": 1.330158522656418e-05, + "loss": 2.5024, + "step": 8730 + }, + { + "epoch": 0.4, + "learning_rate": 1.328808115116356e-05, + "loss": 2.4808, + "step": 8740 + }, + { + "epoch": 0.4, + "learning_rate": 1.3274570349407956e-05, + "loss": 2.4916, + "step": 8750 + }, + { + "epoch": 0.4, + "learning_rate": 1.3261052848936116e-05, + "loss": 2.4632, + "step": 8760 + }, + { + "epoch": 0.4, + "learning_rate": 1.3247528677400486e-05, + "loss": 2.4657, + "step": 8770 + }, + { + "epoch": 0.4, + "learning_rate": 1.3233997862467169e-05, + "loss": 2.4718, + "step": 8780 + }, + { + "epoch": 0.4, + "learning_rate": 1.3220460431815859e-05, + "loss": 2.478, + "step": 8790 + }, + { + "epoch": 0.4, + "learning_rate": 1.320691641313977e-05, + "loss": 2.4887, + "step": 8800 + }, + { + "epoch": 0.4, + "learning_rate": 1.3193365834145606e-05, + "loss": 2.4611, + "step": 8810 + }, + { + "epoch": 0.4, + "learning_rate": 1.3179808722553486e-05, + "loss": 2.469, + "step": 8820 + }, + { + "epoch": 0.4, + "learning_rate": 1.31662451060969e-05, + "loss": 2.4403, + "step": 8830 + }, + { + "epoch": 0.4, + "learning_rate": 1.3152675012522629e-05, + "loss": 2.4769, + "step": 8840 + }, + { + "epoch": 0.4, + "learning_rate": 1.3139098469590716e-05, + "loss": 2.4568, + "step": 8850 + }, + { + "epoch": 0.4, + "learning_rate": 1.31255155050744e-05, + "loss": 2.4885, + "step": 8860 + }, + { + "epoch": 0.4, + "learning_rate": 1.3111926146760047e-05, + "loss": 2.4722, + "step": 8870 + }, + { + "epoch": 0.4, + "learning_rate": 1.309833042244711e-05, + "loss": 2.4638, + "step": 8880 + }, + { + "epoch": 0.4, + "learning_rate": 1.308472835994806e-05, + "loss": 2.4892, + "step": 8890 + }, + { + "epoch": 0.4, + "learning_rate": 1.3071119987088339e-05, + "loss": 2.4763, + "step": 8900 + }, + { + "epoch": 0.4, + "learning_rate": 1.3057505331706288e-05, + "loss": 2.494, + "step": 8910 + }, + { + "epoch": 0.4, + "learning_rate": 1.3043884421653115e-05, + "loss": 2.4811, + "step": 8920 + }, + { + "epoch": 0.4, + "learning_rate": 1.303025728479281e-05, + "loss": 2.4878, + "step": 8930 + }, + { + "epoch": 0.41, + "learning_rate": 1.3016623949002104e-05, + "loss": 2.4671, + "step": 8940 + }, + { + "epoch": 0.41, + "learning_rate": 1.3002984442170416e-05, + "loss": 2.4678, + "step": 8950 + }, + { + "epoch": 0.41, + "learning_rate": 1.2989338792199782e-05, + "loss": 2.4962, + "step": 8960 + }, + { + "epoch": 0.41, + "learning_rate": 1.2975687027004804e-05, + "loss": 2.4836, + "step": 8970 + }, + { + "epoch": 0.41, + "learning_rate": 1.29620291745126e-05, + "loss": 2.5108, + "step": 8980 + }, + { + "epoch": 0.41, + "learning_rate": 1.2948365262662734e-05, + "loss": 2.4853, + "step": 8990 + }, + { + "epoch": 0.41, + "learning_rate": 1.2934695319407176e-05, + "loss": 2.463, + "step": 9000 + }, + { + "epoch": 0.41, + "learning_rate": 1.2921019372710217e-05, + "loss": 2.4847, + "step": 9010 + }, + { + "epoch": 0.41, + "learning_rate": 1.2907337450548446e-05, + "loss": 2.4742, + "step": 9020 + }, + { + "epoch": 0.41, + "learning_rate": 1.289364958091067e-05, + "loss": 2.4816, + "step": 9030 + }, + { + "epoch": 0.41, + "learning_rate": 1.2879955791797853e-05, + "loss": 2.4556, + "step": 9040 + }, + { + "epoch": 0.41, + "learning_rate": 1.2866256111223085e-05, + "loss": 2.4868, + "step": 9050 + }, + { + "epoch": 0.41, + "learning_rate": 1.2852550567211498e-05, + "loss": 2.4913, + "step": 9060 + }, + { + "epoch": 0.41, + "learning_rate": 1.2838839187800218e-05, + "loss": 2.4818, + "step": 9070 + }, + { + "epoch": 0.41, + "learning_rate": 1.282512200103831e-05, + "loss": 2.5155, + "step": 9080 + }, + { + "epoch": 0.41, + "learning_rate": 1.2811399034986726e-05, + "loss": 2.4636, + "step": 9090 + }, + { + "epoch": 0.41, + "learning_rate": 1.2797670317718234e-05, + "loss": 2.47, + "step": 9100 + }, + { + "epoch": 0.41, + "learning_rate": 1.2783935877317362e-05, + "loss": 2.4984, + "step": 9110 + }, + { + "epoch": 0.41, + "learning_rate": 1.2770195741880356e-05, + "loss": 2.4898, + "step": 9120 + }, + { + "epoch": 0.41, + "learning_rate": 1.2756449939515107e-05, + "loss": 2.4708, + "step": 9130 + }, + { + "epoch": 0.41, + "learning_rate": 1.2742698498341098e-05, + "loss": 2.4779, + "step": 9140 + }, + { + "epoch": 0.41, + "learning_rate": 1.2728941446489347e-05, + "loss": 2.47, + "step": 9150 + }, + { + "epoch": 0.42, + "learning_rate": 1.2715178812102353e-05, + "loss": 2.4753, + "step": 9160 + }, + { + "epoch": 0.42, + "learning_rate": 1.2701410623334037e-05, + "loss": 2.5039, + "step": 9170 + }, + { + "epoch": 0.42, + "learning_rate": 1.2687636908349671e-05, + "loss": 2.4783, + "step": 9180 + }, + { + "epoch": 0.42, + "learning_rate": 1.2673857695325846e-05, + "loss": 2.4995, + "step": 9190 + }, + { + "epoch": 0.42, + "learning_rate": 1.2660073012450389e-05, + "loss": 2.4753, + "step": 9200 + }, + { + "epoch": 0.42, + "learning_rate": 1.2646282887922325e-05, + "loss": 2.4616, + "step": 9210 + }, + { + "epoch": 0.42, + "learning_rate": 1.2632487349951805e-05, + "loss": 2.4776, + "step": 9220 + }, + { + "epoch": 0.42, + "learning_rate": 1.2618686426760058e-05, + "loss": 2.4758, + "step": 9230 + }, + { + "epoch": 0.42, + "learning_rate": 1.2604880146579326e-05, + "loss": 2.4691, + "step": 9240 + }, + { + "epoch": 0.42, + "learning_rate": 1.2591068537652813e-05, + "loss": 2.4921, + "step": 9250 + }, + { + "epoch": 0.42, + "learning_rate": 1.257725162823462e-05, + "loss": 2.4803, + "step": 9260 + }, + { + "epoch": 0.42, + "learning_rate": 1.2563429446589695e-05, + "loss": 2.4763, + "step": 9270 + }, + { + "epoch": 0.42, + "learning_rate": 1.2549602020993769e-05, + "loss": 2.4785, + "step": 9280 + }, + { + "epoch": 0.42, + "learning_rate": 1.2535769379733305e-05, + "loss": 2.5066, + "step": 9290 + }, + { + "epoch": 0.42, + "learning_rate": 1.2521931551105427e-05, + "loss": 2.4683, + "step": 9300 + }, + { + "epoch": 0.42, + "learning_rate": 1.2508088563417875e-05, + "loss": 2.4796, + "step": 9310 + }, + { + "epoch": 0.42, + "learning_rate": 1.2494240444988943e-05, + "loss": 2.4638, + "step": 9320 + }, + { + "epoch": 0.42, + "learning_rate": 1.2480387224147426e-05, + "loss": 2.4631, + "step": 9330 + }, + { + "epoch": 0.42, + "learning_rate": 1.2466528929232548e-05, + "loss": 2.4953, + "step": 9340 + }, + { + "epoch": 0.42, + "learning_rate": 1.245266558859392e-05, + "loss": 2.4954, + "step": 9350 + }, + { + "epoch": 0.42, + "learning_rate": 1.2438797230591468e-05, + "loss": 2.481, + "step": 9360 + }, + { + "epoch": 0.42, + "learning_rate": 1.2424923883595389e-05, + "loss": 2.4852, + "step": 9370 + }, + { + "epoch": 0.43, + "learning_rate": 1.2411045575986079e-05, + "loss": 2.4744, + "step": 9380 + }, + { + "epoch": 0.43, + "learning_rate": 1.2397162336154085e-05, + "loss": 2.4688, + "step": 9390 + }, + { + "epoch": 0.43, + "learning_rate": 1.2383274192500048e-05, + "loss": 2.4656, + "step": 9400 + }, + { + "epoch": 0.43, + "learning_rate": 1.2369381173434636e-05, + "loss": 2.4552, + "step": 9410 + }, + { + "epoch": 0.43, + "learning_rate": 1.235548330737849e-05, + "loss": 2.4615, + "step": 9420 + }, + { + "epoch": 0.43, + "learning_rate": 1.2341580622762164e-05, + "loss": 2.4731, + "step": 9430 + }, + { + "epoch": 0.43, + "learning_rate": 1.2327673148026079e-05, + "loss": 2.4722, + "step": 9440 + }, + { + "epoch": 0.43, + "learning_rate": 1.2313760911620447e-05, + "loss": 2.4791, + "step": 9450 + }, + { + "epoch": 0.43, + "learning_rate": 1.229984394200522e-05, + "loss": 2.4814, + "step": 9460 + }, + { + "epoch": 0.43, + "learning_rate": 1.2285922267650038e-05, + "loss": 2.4528, + "step": 9470 + }, + { + "epoch": 0.43, + "learning_rate": 1.2271995917034166e-05, + "loss": 2.4879, + "step": 9480 + }, + { + "epoch": 0.43, + "learning_rate": 1.2258064918646424e-05, + "loss": 2.4689, + "step": 9490 + }, + { + "epoch": 0.43, + "learning_rate": 1.2244129300985153e-05, + "loss": 2.4963, + "step": 9500 + }, + { + "epoch": 0.43, + "learning_rate": 1.2230189092558138e-05, + "loss": 2.4701, + "step": 9510 + }, + { + "epoch": 0.43, + "learning_rate": 1.2216244321882553e-05, + "loss": 2.4841, + "step": 9520 + }, + { + "epoch": 0.43, + "learning_rate": 1.2202295017484911e-05, + "loss": 2.4951, + "step": 9530 + }, + { + "epoch": 0.43, + "learning_rate": 1.2188341207900991e-05, + "loss": 2.4291, + "step": 9540 + }, + { + "epoch": 0.43, + "learning_rate": 1.2174382921675799e-05, + "loss": 2.4742, + "step": 9550 + }, + { + "epoch": 0.43, + "learning_rate": 1.2160420187363484e-05, + "loss": 2.4867, + "step": 9560 + }, + { + "epoch": 0.43, + "learning_rate": 1.2146453033527315e-05, + "loss": 2.4603, + "step": 9570 + }, + { + "epoch": 0.43, + "learning_rate": 1.213248148873958e-05, + "loss": 2.4703, + "step": 9580 + }, + { + "epoch": 0.43, + "learning_rate": 1.2118505581581568e-05, + "loss": 2.4585, + "step": 9590 + }, + { + "epoch": 0.44, + "learning_rate": 1.2104525340643479e-05, + "loss": 2.4888, + "step": 9600 + }, + { + "epoch": 0.44, + "learning_rate": 1.2090540794524382e-05, + "loss": 2.4635, + "step": 9610 + }, + { + "epoch": 0.44, + "learning_rate": 1.2076551971832154e-05, + "loss": 2.4772, + "step": 9620 + }, + { + "epoch": 0.44, + "learning_rate": 1.2062558901183422e-05, + "loss": 2.4872, + "step": 9630 + }, + { + "epoch": 0.44, + "learning_rate": 1.2048561611203501e-05, + "loss": 2.4838, + "step": 9640 + }, + { + "epoch": 0.44, + "learning_rate": 1.2034560130526341e-05, + "loss": 2.4642, + "step": 9650 + }, + { + "epoch": 0.44, + "learning_rate": 1.2020554487794455e-05, + "loss": 2.5052, + "step": 9660 + }, + { + "epoch": 0.44, + "learning_rate": 1.2006544711658884e-05, + "loss": 2.4885, + "step": 9670 + }, + { + "epoch": 0.44, + "learning_rate": 1.1992530830779116e-05, + "loss": 2.4674, + "step": 9680 + }, + { + "epoch": 0.44, + "learning_rate": 1.1978512873823036e-05, + "loss": 2.4788, + "step": 9690 + }, + { + "epoch": 0.44, + "learning_rate": 1.1964490869466869e-05, + "loss": 2.4905, + "step": 9700 + }, + { + "epoch": 0.44, + "learning_rate": 1.1950464846395123e-05, + "loss": 2.5041, + "step": 9710 + }, + { + "epoch": 0.44, + "learning_rate": 1.1936434833300517e-05, + "loss": 2.4659, + "step": 9720 + }, + { + "epoch": 0.44, + "learning_rate": 1.1922400858883942e-05, + "loss": 2.4741, + "step": 9730 + }, + { + "epoch": 0.44, + "learning_rate": 1.1908362951854393e-05, + "loss": 2.4725, + "step": 9740 + }, + { + "epoch": 0.44, + "learning_rate": 1.1894321140928901e-05, + "loss": 2.478, + "step": 9750 + }, + { + "epoch": 0.44, + "learning_rate": 1.1880275454832493e-05, + "loss": 2.47, + "step": 9760 + }, + { + "epoch": 0.44, + "learning_rate": 1.1866225922298116e-05, + "loss": 2.474, + "step": 9770 + }, + { + "epoch": 0.44, + "learning_rate": 1.185217257206659e-05, + "loss": 2.4519, + "step": 9780 + }, + { + "epoch": 0.44, + "learning_rate": 1.183811543288654e-05, + "loss": 2.4818, + "step": 9790 + }, + { + "epoch": 0.44, + "learning_rate": 1.1824054533514349e-05, + "loss": 2.4663, + "step": 9800 + }, + { + "epoch": 0.44, + "learning_rate": 1.1809989902714085e-05, + "loss": 2.4877, + "step": 9810 + }, + { + "epoch": 0.45, + "learning_rate": 1.1795921569257456e-05, + "loss": 2.4713, + "step": 9820 + }, + { + "epoch": 0.45, + "learning_rate": 1.178184956192374e-05, + "loss": 2.4738, + "step": 9830 + }, + { + "epoch": 0.45, + "learning_rate": 1.1767773909499729e-05, + "loss": 2.457, + "step": 9840 + }, + { + "epoch": 0.45, + "learning_rate": 1.1753694640779677e-05, + "loss": 2.4695, + "step": 9850 + }, + { + "epoch": 0.45, + "learning_rate": 1.1739611784565232e-05, + "loss": 2.4408, + "step": 9860 + }, + { + "epoch": 0.45, + "learning_rate": 1.1725525369665383e-05, + "loss": 2.4893, + "step": 9870 + }, + { + "epoch": 0.45, + "learning_rate": 1.1711435424896395e-05, + "loss": 2.4603, + "step": 9880 + }, + { + "epoch": 0.45, + "learning_rate": 1.169734197908176e-05, + "loss": 2.4992, + "step": 9890 + }, + { + "epoch": 0.45, + "learning_rate": 1.1683245061052126e-05, + "loss": 2.4855, + "step": 9900 + }, + { + "epoch": 0.45, + "learning_rate": 1.1669144699645249e-05, + "loss": 2.4751, + "step": 9910 + }, + { + "epoch": 0.45, + "learning_rate": 1.1655040923705926e-05, + "loss": 2.4548, + "step": 9920 + }, + { + "epoch": 0.45, + "learning_rate": 1.1640933762085943e-05, + "loss": 2.4694, + "step": 9930 + }, + { + "epoch": 0.45, + "learning_rate": 1.1626823243644006e-05, + "loss": 2.469, + "step": 9940 + }, + { + "epoch": 0.45, + "learning_rate": 1.161270939724569e-05, + "loss": 2.5118, + "step": 9950 + }, + { + "epoch": 0.45, + "learning_rate": 1.1598592251763378e-05, + "loss": 2.4749, + "step": 9960 + }, + { + "epoch": 0.45, + "learning_rate": 1.1584471836076208e-05, + "loss": 2.4817, + "step": 9970 + }, + { + "epoch": 0.45, + "learning_rate": 1.1570348179069998e-05, + "loss": 2.4811, + "step": 9980 + }, + { + "epoch": 0.45, + "learning_rate": 1.1556221309637204e-05, + "loss": 2.4543, + "step": 9990 + }, + { + "epoch": 0.45, + "learning_rate": 1.1542091256676846e-05, + "loss": 2.463, + "step": 10000 + }, + { + "epoch": 0.45, + "eval_accuracy": 0.5409716963389947, + "eval_loss": 2.238548755645752, + "eval_runtime": 9.8782, + "eval_samples_per_second": 138.385, + "eval_steps_per_second": 1.114, + "step": 10000 + } + ], + "logging_steps": 10, + "max_steps": 22065, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 10000, + "total_flos": 5.66719860965376e+19, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +}