{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.457865168539326, "eval_steps": 500, "global_step": 3500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.988295880149813e-05, "loss": 1.7828, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.976591760299626e-05, "loss": 1.7581, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.964887640449438e-05, "loss": 1.7499, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.953183520599251e-05, "loss": 1.7351, "step": 40 }, { "epoch": 0.04, "learning_rate": 4.941479400749064e-05, "loss": 1.6748, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.929775280898877e-05, "loss": 1.6994, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.918071161048689e-05, "loss": 1.6761, "step": 70 }, { "epoch": 0.06, "learning_rate": 4.906367041198502e-05, "loss": 1.6459, "step": 80 }, { "epoch": 0.06, "learning_rate": 4.8946629213483144e-05, "loss": 1.6372, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.882958801498127e-05, "loss": 1.6715, "step": 100 }, { "epoch": 0.08, "learning_rate": 4.87125468164794e-05, "loss": 1.6141, "step": 110 }, { "epoch": 0.08, "learning_rate": 4.859550561797753e-05, "loss": 1.6354, "step": 120 }, { "epoch": 0.09, "learning_rate": 4.8478464419475654e-05, "loss": 1.6343, "step": 130 }, { "epoch": 0.1, "learning_rate": 4.836142322097378e-05, "loss": 1.6072, "step": 140 }, { "epoch": 0.11, "learning_rate": 4.824438202247191e-05, "loss": 1.6131, "step": 150 }, { "epoch": 0.11, "learning_rate": 4.812734082397004e-05, "loss": 1.6301, "step": 160 }, { "epoch": 0.12, "learning_rate": 4.801029962546817e-05, "loss": 1.597, "step": 170 }, { "epoch": 0.13, "learning_rate": 4.789325842696629e-05, "loss": 1.5489, "step": 180 }, { "epoch": 0.13, "learning_rate": 4.777621722846442e-05, "loss": 1.5998, "step": 190 }, { "epoch": 0.14, "learning_rate": 4.765917602996255e-05, "loss": 1.6023, "step": 200 }, { "epoch": 0.15, "learning_rate": 4.754213483146068e-05, "loss": 1.6847, "step": 210 }, { "epoch": 0.15, "learning_rate": 4.742509363295881e-05, "loss": 1.5816, "step": 220 }, { "epoch": 0.16, "learning_rate": 4.730805243445693e-05, "loss": 1.673, "step": 230 }, { "epoch": 0.17, "learning_rate": 4.719101123595506e-05, "loss": 1.6192, "step": 240 }, { "epoch": 0.18, "learning_rate": 4.707397003745318e-05, "loss": 1.6183, "step": 250 }, { "epoch": 0.18, "learning_rate": 4.695692883895131e-05, "loss": 1.6262, "step": 260 }, { "epoch": 0.19, "learning_rate": 4.683988764044944e-05, "loss": 1.5945, "step": 270 }, { "epoch": 0.2, "learning_rate": 4.6722846441947563e-05, "loss": 1.659, "step": 280 }, { "epoch": 0.2, "learning_rate": 4.660580524344569e-05, "loss": 1.6135, "step": 290 }, { "epoch": 0.21, "learning_rate": 4.648876404494382e-05, "loss": 1.6102, "step": 300 }, { "epoch": 0.22, "learning_rate": 4.637172284644195e-05, "loss": 1.6202, "step": 310 }, { "epoch": 0.22, "learning_rate": 4.625468164794008e-05, "loss": 1.6499, "step": 320 }, { "epoch": 0.23, "learning_rate": 4.61376404494382e-05, "loss": 1.656, "step": 330 }, { "epoch": 0.24, "learning_rate": 4.602059925093633e-05, "loss": 1.629, "step": 340 }, { "epoch": 0.25, "learning_rate": 4.590355805243446e-05, "loss": 1.6194, "step": 350 }, { "epoch": 0.25, "learning_rate": 4.578651685393259e-05, "loss": 1.6308, "step": 360 }, { "epoch": 0.26, "learning_rate": 4.566947565543072e-05, "loss": 1.6013, "step": 370 }, { "epoch": 0.27, "learning_rate": 4.555243445692884e-05, "loss": 1.6103, "step": 380 }, { "epoch": 0.27, "learning_rate": 4.543539325842697e-05, "loss": 1.6281, "step": 390 }, { "epoch": 0.28, "learning_rate": 4.531835205992509e-05, "loss": 1.5684, "step": 400 }, { "epoch": 0.29, "learning_rate": 4.520131086142322e-05, "loss": 1.6165, "step": 410 }, { "epoch": 0.29, "learning_rate": 4.508426966292135e-05, "loss": 1.6187, "step": 420 }, { "epoch": 0.3, "learning_rate": 4.496722846441947e-05, "loss": 1.6211, "step": 430 }, { "epoch": 0.31, "learning_rate": 4.48501872659176e-05, "loss": 1.6104, "step": 440 }, { "epoch": 0.32, "learning_rate": 4.473314606741573e-05, "loss": 1.6058, "step": 450 }, { "epoch": 0.32, "learning_rate": 4.461610486891386e-05, "loss": 1.5639, "step": 460 }, { "epoch": 0.33, "learning_rate": 4.449906367041199e-05, "loss": 1.5879, "step": 470 }, { "epoch": 0.34, "learning_rate": 4.438202247191011e-05, "loss": 1.5911, "step": 480 }, { "epoch": 0.34, "learning_rate": 4.426498127340824e-05, "loss": 1.6679, "step": 490 }, { "epoch": 0.35, "learning_rate": 4.414794007490637e-05, "loss": 1.578, "step": 500 }, { "epoch": 0.36, "learning_rate": 4.40308988764045e-05, "loss": 1.6275, "step": 510 }, { "epoch": 0.37, "learning_rate": 4.391385767790263e-05, "loss": 1.5811, "step": 520 }, { "epoch": 0.37, "learning_rate": 4.379681647940075e-05, "loss": 1.5688, "step": 530 }, { "epoch": 0.38, "learning_rate": 4.367977528089888e-05, "loss": 1.6364, "step": 540 }, { "epoch": 0.39, "learning_rate": 4.3562734082397e-05, "loss": 1.5866, "step": 550 }, { "epoch": 0.39, "learning_rate": 4.344569288389513e-05, "loss": 1.6161, "step": 560 }, { "epoch": 0.4, "learning_rate": 4.332865168539326e-05, "loss": 1.6424, "step": 570 }, { "epoch": 0.41, "learning_rate": 4.321161048689138e-05, "loss": 1.623, "step": 580 }, { "epoch": 0.41, "learning_rate": 4.309456928838951e-05, "loss": 1.5842, "step": 590 }, { "epoch": 0.42, "learning_rate": 4.297752808988764e-05, "loss": 1.6077, "step": 600 }, { "epoch": 0.43, "learning_rate": 4.286048689138577e-05, "loss": 1.6583, "step": 610 }, { "epoch": 0.44, "learning_rate": 4.27434456928839e-05, "loss": 1.6026, "step": 620 }, { "epoch": 0.44, "learning_rate": 4.262640449438202e-05, "loss": 1.6292, "step": 630 }, { "epoch": 0.45, "learning_rate": 4.250936329588015e-05, "loss": 1.6292, "step": 640 }, { "epoch": 0.46, "learning_rate": 4.239232209737828e-05, "loss": 1.5891, "step": 650 }, { "epoch": 0.46, "learning_rate": 4.227528089887641e-05, "loss": 1.6386, "step": 660 }, { "epoch": 0.47, "learning_rate": 4.215823970037454e-05, "loss": 1.6162, "step": 670 }, { "epoch": 0.48, "learning_rate": 4.204119850187267e-05, "loss": 1.5891, "step": 680 }, { "epoch": 0.48, "learning_rate": 4.192415730337079e-05, "loss": 1.614, "step": 690 }, { "epoch": 0.49, "learning_rate": 4.180711610486892e-05, "loss": 1.6487, "step": 700 }, { "epoch": 0.5, "learning_rate": 4.169007490636704e-05, "loss": 1.6591, "step": 710 }, { "epoch": 0.51, "learning_rate": 4.157303370786517e-05, "loss": 1.5986, "step": 720 }, { "epoch": 0.51, "learning_rate": 4.14559925093633e-05, "loss": 1.6107, "step": 730 }, { "epoch": 0.52, "learning_rate": 4.133895131086142e-05, "loss": 1.6195, "step": 740 }, { "epoch": 0.53, "learning_rate": 4.122191011235955e-05, "loss": 1.6278, "step": 750 }, { "epoch": 0.53, "learning_rate": 4.110486891385768e-05, "loss": 1.5987, "step": 760 }, { "epoch": 0.54, "learning_rate": 4.098782771535581e-05, "loss": 1.5816, "step": 770 }, { "epoch": 0.55, "learning_rate": 4.087078651685394e-05, "loss": 1.6183, "step": 780 }, { "epoch": 0.55, "learning_rate": 4.075374531835206e-05, "loss": 1.5796, "step": 790 }, { "epoch": 0.56, "learning_rate": 4.063670411985019e-05, "loss": 1.6078, "step": 800 }, { "epoch": 0.57, "learning_rate": 4.051966292134832e-05, "loss": 1.5659, "step": 810 }, { "epoch": 0.58, "learning_rate": 4.040262172284645e-05, "loss": 1.6024, "step": 820 }, { "epoch": 0.58, "learning_rate": 4.028558052434458e-05, "loss": 1.6321, "step": 830 }, { "epoch": 0.59, "learning_rate": 4.01685393258427e-05, "loss": 1.6139, "step": 840 }, { "epoch": 0.6, "learning_rate": 4.005149812734083e-05, "loss": 1.5753, "step": 850 }, { "epoch": 0.6, "learning_rate": 3.993445692883895e-05, "loss": 1.6109, "step": 860 }, { "epoch": 0.61, "learning_rate": 3.981741573033708e-05, "loss": 1.6098, "step": 870 }, { "epoch": 0.62, "learning_rate": 3.970037453183521e-05, "loss": 1.6277, "step": 880 }, { "epoch": 0.62, "learning_rate": 3.958333333333333e-05, "loss": 1.661, "step": 890 }, { "epoch": 0.63, "learning_rate": 3.946629213483146e-05, "loss": 1.6179, "step": 900 }, { "epoch": 0.64, "learning_rate": 3.934925093632959e-05, "loss": 1.6417, "step": 910 }, { "epoch": 0.65, "learning_rate": 3.923220973782772e-05, "loss": 1.622, "step": 920 }, { "epoch": 0.65, "learning_rate": 3.911516853932585e-05, "loss": 1.6275, "step": 930 }, { "epoch": 0.66, "learning_rate": 3.899812734082397e-05, "loss": 1.6297, "step": 940 }, { "epoch": 0.67, "learning_rate": 3.88810861423221e-05, "loss": 1.6049, "step": 950 }, { "epoch": 0.67, "learning_rate": 3.876404494382023e-05, "loss": 1.6347, "step": 960 }, { "epoch": 0.68, "learning_rate": 3.864700374531836e-05, "loss": 1.5998, "step": 970 }, { "epoch": 0.69, "learning_rate": 3.8529962546816486e-05, "loss": 1.6305, "step": 980 }, { "epoch": 0.7, "learning_rate": 3.841292134831461e-05, "loss": 1.6281, "step": 990 }, { "epoch": 0.7, "learning_rate": 3.829588014981274e-05, "loss": 1.6223, "step": 1000 }, { "epoch": 0.71, "learning_rate": 3.817883895131087e-05, "loss": 1.591, "step": 1010 }, { "epoch": 0.72, "learning_rate": 3.806179775280899e-05, "loss": 1.6133, "step": 1020 }, { "epoch": 0.72, "learning_rate": 3.794475655430712e-05, "loss": 1.6158, "step": 1030 }, { "epoch": 0.73, "learning_rate": 3.782771535580524e-05, "loss": 1.622, "step": 1040 }, { "epoch": 0.74, "learning_rate": 3.771067415730337e-05, "loss": 1.6461, "step": 1050 }, { "epoch": 0.74, "learning_rate": 3.75936329588015e-05, "loss": 1.6638, "step": 1060 }, { "epoch": 0.75, "learning_rate": 3.747659176029963e-05, "loss": 1.6071, "step": 1070 }, { "epoch": 0.76, "learning_rate": 3.735955056179776e-05, "loss": 1.6439, "step": 1080 }, { "epoch": 0.77, "learning_rate": 3.724250936329588e-05, "loss": 1.6111, "step": 1090 }, { "epoch": 0.77, "learning_rate": 3.712546816479401e-05, "loss": 1.5904, "step": 1100 }, { "epoch": 0.78, "learning_rate": 3.700842696629214e-05, "loss": 1.6312, "step": 1110 }, { "epoch": 0.79, "learning_rate": 3.689138576779027e-05, "loss": 1.6094, "step": 1120 }, { "epoch": 0.79, "learning_rate": 3.6774344569288396e-05, "loss": 1.5809, "step": 1130 }, { "epoch": 0.8, "learning_rate": 3.665730337078652e-05, "loss": 1.6235, "step": 1140 }, { "epoch": 0.81, "learning_rate": 3.654026217228465e-05, "loss": 1.6241, "step": 1150 }, { "epoch": 0.81, "learning_rate": 3.6423220973782776e-05, "loss": 1.594, "step": 1160 }, { "epoch": 0.82, "learning_rate": 3.63061797752809e-05, "loss": 1.6158, "step": 1170 }, { "epoch": 0.83, "learning_rate": 3.618913857677903e-05, "loss": 1.6182, "step": 1180 }, { "epoch": 0.84, "learning_rate": 3.607209737827715e-05, "loss": 1.6509, "step": 1190 }, { "epoch": 0.84, "learning_rate": 3.595505617977528e-05, "loss": 1.5991, "step": 1200 }, { "epoch": 0.85, "learning_rate": 3.583801498127341e-05, "loss": 1.6338, "step": 1210 }, { "epoch": 0.86, "learning_rate": 3.572097378277154e-05, "loss": 1.6244, "step": 1220 }, { "epoch": 0.86, "learning_rate": 3.560393258426967e-05, "loss": 1.5973, "step": 1230 }, { "epoch": 0.87, "learning_rate": 3.548689138576779e-05, "loss": 1.626, "step": 1240 }, { "epoch": 0.88, "learning_rate": 3.536985018726592e-05, "loss": 1.6008, "step": 1250 }, { "epoch": 0.88, "learning_rate": 3.525280898876405e-05, "loss": 1.6197, "step": 1260 }, { "epoch": 0.89, "learning_rate": 3.5135767790262176e-05, "loss": 1.5381, "step": 1270 }, { "epoch": 0.9, "learning_rate": 3.5018726591760305e-05, "loss": 1.6108, "step": 1280 }, { "epoch": 0.91, "learning_rate": 3.490168539325843e-05, "loss": 1.6042, "step": 1290 }, { "epoch": 0.91, "learning_rate": 3.478464419475656e-05, "loss": 1.5814, "step": 1300 }, { "epoch": 0.92, "learning_rate": 3.4667602996254686e-05, "loss": 1.614, "step": 1310 }, { "epoch": 0.93, "learning_rate": 3.455056179775281e-05, "loss": 1.5813, "step": 1320 }, { "epoch": 0.93, "learning_rate": 3.443352059925094e-05, "loss": 1.6115, "step": 1330 }, { "epoch": 0.94, "learning_rate": 3.431647940074906e-05, "loss": 1.5899, "step": 1340 }, { "epoch": 0.95, "learning_rate": 3.419943820224719e-05, "loss": 1.631, "step": 1350 }, { "epoch": 0.96, "learning_rate": 3.408239700374532e-05, "loss": 1.6057, "step": 1360 }, { "epoch": 0.96, "learning_rate": 3.396535580524345e-05, "loss": 1.5936, "step": 1370 }, { "epoch": 0.97, "learning_rate": 3.3848314606741576e-05, "loss": 1.6068, "step": 1380 }, { "epoch": 0.98, "learning_rate": 3.37312734082397e-05, "loss": 1.6029, "step": 1390 }, { "epoch": 0.98, "learning_rate": 3.361423220973783e-05, "loss": 1.6374, "step": 1400 }, { "epoch": 0.99, "learning_rate": 3.349719101123596e-05, "loss": 1.6115, "step": 1410 }, { "epoch": 1.0, "learning_rate": 3.3380149812734086e-05, "loss": 1.6287, "step": 1420 }, { "epoch": 1.0, "learning_rate": 3.3263108614232215e-05, "loss": 1.5845, "step": 1430 }, { "epoch": 1.01, "learning_rate": 3.314606741573034e-05, "loss": 1.5682, "step": 1440 }, { "epoch": 1.02, "learning_rate": 3.3029026217228467e-05, "loss": 1.5966, "step": 1450 }, { "epoch": 1.03, "learning_rate": 3.2911985018726596e-05, "loss": 1.6527, "step": 1460 }, { "epoch": 1.03, "learning_rate": 3.2794943820224725e-05, "loss": 1.5991, "step": 1470 }, { "epoch": 1.04, "learning_rate": 3.267790262172285e-05, "loss": 1.6472, "step": 1480 }, { "epoch": 1.05, "learning_rate": 3.2560861423220976e-05, "loss": 1.5972, "step": 1490 }, { "epoch": 1.05, "learning_rate": 3.24438202247191e-05, "loss": 1.5871, "step": 1500 }, { "epoch": 1.06, "learning_rate": 3.232677902621723e-05, "loss": 1.5687, "step": 1510 }, { "epoch": 1.07, "learning_rate": 3.220973782771536e-05, "loss": 1.6235, "step": 1520 }, { "epoch": 1.07, "learning_rate": 3.2092696629213486e-05, "loss": 1.6073, "step": 1530 }, { "epoch": 1.08, "learning_rate": 3.197565543071161e-05, "loss": 1.5895, "step": 1540 }, { "epoch": 1.09, "learning_rate": 3.185861423220974e-05, "loss": 1.6319, "step": 1550 }, { "epoch": 1.1, "learning_rate": 3.1741573033707866e-05, "loss": 1.5958, "step": 1560 }, { "epoch": 1.1, "learning_rate": 3.1624531835205996e-05, "loss": 1.6232, "step": 1570 }, { "epoch": 1.11, "learning_rate": 3.1507490636704125e-05, "loss": 1.6514, "step": 1580 }, { "epoch": 1.12, "learning_rate": 3.139044943820225e-05, "loss": 1.6175, "step": 1590 }, { "epoch": 1.12, "learning_rate": 3.1273408239700376e-05, "loss": 1.5959, "step": 1600 }, { "epoch": 1.13, "learning_rate": 3.1156367041198505e-05, "loss": 1.6223, "step": 1610 }, { "epoch": 1.14, "learning_rate": 3.1039325842696634e-05, "loss": 1.6289, "step": 1620 }, { "epoch": 1.14, "learning_rate": 3.092228464419476e-05, "loss": 1.6393, "step": 1630 }, { "epoch": 1.15, "learning_rate": 3.0805243445692886e-05, "loss": 1.5833, "step": 1640 }, { "epoch": 1.16, "learning_rate": 3.068820224719101e-05, "loss": 1.5563, "step": 1650 }, { "epoch": 1.17, "learning_rate": 3.057116104868914e-05, "loss": 1.6156, "step": 1660 }, { "epoch": 1.17, "learning_rate": 3.045411985018727e-05, "loss": 1.567, "step": 1670 }, { "epoch": 1.18, "learning_rate": 3.0337078651685396e-05, "loss": 1.5583, "step": 1680 }, { "epoch": 1.19, "learning_rate": 3.0220037453183518e-05, "loss": 1.6089, "step": 1690 }, { "epoch": 1.19, "learning_rate": 3.0102996254681647e-05, "loss": 1.6113, "step": 1700 }, { "epoch": 1.2, "learning_rate": 2.9985955056179776e-05, "loss": 1.6204, "step": 1710 }, { "epoch": 1.21, "learning_rate": 2.9868913857677905e-05, "loss": 1.6012, "step": 1720 }, { "epoch": 1.21, "learning_rate": 2.9751872659176034e-05, "loss": 1.61, "step": 1730 }, { "epoch": 1.22, "learning_rate": 2.9634831460674157e-05, "loss": 1.6197, "step": 1740 }, { "epoch": 1.23, "learning_rate": 2.9517790262172286e-05, "loss": 1.6477, "step": 1750 }, { "epoch": 1.24, "learning_rate": 2.940074906367041e-05, "loss": 1.6033, "step": 1760 }, { "epoch": 1.24, "learning_rate": 2.928370786516854e-05, "loss": 1.6398, "step": 1770 }, { "epoch": 1.25, "learning_rate": 2.916666666666667e-05, "loss": 1.5934, "step": 1780 }, { "epoch": 1.26, "learning_rate": 2.9049625468164792e-05, "loss": 1.6086, "step": 1790 }, { "epoch": 1.26, "learning_rate": 2.893258426966292e-05, "loss": 1.6349, "step": 1800 }, { "epoch": 1.27, "learning_rate": 2.881554307116105e-05, "loss": 1.5624, "step": 1810 }, { "epoch": 1.28, "learning_rate": 2.869850187265918e-05, "loss": 1.5814, "step": 1820 }, { "epoch": 1.29, "learning_rate": 2.8581460674157305e-05, "loss": 1.5955, "step": 1830 }, { "epoch": 1.29, "learning_rate": 2.846441947565543e-05, "loss": 1.6163, "step": 1840 }, { "epoch": 1.3, "learning_rate": 2.8347378277153557e-05, "loss": 1.6423, "step": 1850 }, { "epoch": 1.31, "learning_rate": 2.8230337078651686e-05, "loss": 1.5882, "step": 1860 }, { "epoch": 1.31, "learning_rate": 2.8113295880149815e-05, "loss": 1.5747, "step": 1870 }, { "epoch": 1.32, "learning_rate": 2.7996254681647944e-05, "loss": 1.6375, "step": 1880 }, { "epoch": 1.33, "learning_rate": 2.7879213483146066e-05, "loss": 1.577, "step": 1890 }, { "epoch": 1.33, "learning_rate": 2.7762172284644195e-05, "loss": 1.6285, "step": 1900 }, { "epoch": 1.34, "learning_rate": 2.7645131086142325e-05, "loss": 1.603, "step": 1910 }, { "epoch": 1.35, "learning_rate": 2.752808988764045e-05, "loss": 1.5859, "step": 1920 }, { "epoch": 1.36, "learning_rate": 2.741104868913858e-05, "loss": 1.5735, "step": 1930 }, { "epoch": 1.36, "learning_rate": 2.7294007490636702e-05, "loss": 1.5936, "step": 1940 }, { "epoch": 1.37, "learning_rate": 2.717696629213483e-05, "loss": 1.5934, "step": 1950 }, { "epoch": 1.38, "learning_rate": 2.705992509363296e-05, "loss": 1.5972, "step": 1960 }, { "epoch": 1.38, "learning_rate": 2.694288389513109e-05, "loss": 1.6575, "step": 1970 }, { "epoch": 1.39, "learning_rate": 2.6825842696629215e-05, "loss": 1.5937, "step": 1980 }, { "epoch": 1.4, "learning_rate": 2.670880149812734e-05, "loss": 1.5552, "step": 1990 }, { "epoch": 1.4, "learning_rate": 2.6591760299625466e-05, "loss": 1.6175, "step": 2000 }, { "epoch": 1.41, "learning_rate": 2.6474719101123595e-05, "loss": 1.58, "step": 2010 }, { "epoch": 1.42, "learning_rate": 2.6357677902621724e-05, "loss": 1.6338, "step": 2020 }, { "epoch": 1.43, "learning_rate": 2.6240636704119854e-05, "loss": 1.605, "step": 2030 }, { "epoch": 1.43, "learning_rate": 2.6123595505617983e-05, "loss": 1.6046, "step": 2040 }, { "epoch": 1.44, "learning_rate": 2.6006554307116105e-05, "loss": 1.6041, "step": 2050 }, { "epoch": 1.45, "learning_rate": 2.5889513108614234e-05, "loss": 1.594, "step": 2060 }, { "epoch": 1.45, "learning_rate": 2.577247191011236e-05, "loss": 1.5991, "step": 2070 }, { "epoch": 1.46, "learning_rate": 2.565543071161049e-05, "loss": 1.6344, "step": 2080 }, { "epoch": 1.47, "learning_rate": 2.5538389513108618e-05, "loss": 1.6152, "step": 2090 }, { "epoch": 1.47, "learning_rate": 2.542134831460674e-05, "loss": 1.5778, "step": 2100 }, { "epoch": 1.48, "learning_rate": 2.530430711610487e-05, "loss": 1.629, "step": 2110 }, { "epoch": 1.49, "learning_rate": 2.5187265917603e-05, "loss": 1.5921, "step": 2120 }, { "epoch": 1.5, "learning_rate": 2.5070224719101128e-05, "loss": 1.6092, "step": 2130 }, { "epoch": 1.5, "learning_rate": 2.4953183520599254e-05, "loss": 1.6009, "step": 2140 }, { "epoch": 1.51, "learning_rate": 2.483614232209738e-05, "loss": 1.601, "step": 2150 }, { "epoch": 1.52, "learning_rate": 2.4719101123595505e-05, "loss": 1.5833, "step": 2160 }, { "epoch": 1.52, "learning_rate": 2.4602059925093634e-05, "loss": 1.5711, "step": 2170 }, { "epoch": 1.53, "learning_rate": 2.448501872659176e-05, "loss": 1.599, "step": 2180 }, { "epoch": 1.54, "learning_rate": 2.436797752808989e-05, "loss": 1.599, "step": 2190 }, { "epoch": 1.54, "learning_rate": 2.4250936329588018e-05, "loss": 1.6161, "step": 2200 }, { "epoch": 1.55, "learning_rate": 2.4133895131086144e-05, "loss": 1.5779, "step": 2210 }, { "epoch": 1.56, "learning_rate": 2.401685393258427e-05, "loss": 1.6316, "step": 2220 }, { "epoch": 1.57, "learning_rate": 2.3899812734082395e-05, "loss": 1.5623, "step": 2230 }, { "epoch": 1.57, "learning_rate": 2.3782771535580524e-05, "loss": 1.6113, "step": 2240 }, { "epoch": 1.58, "learning_rate": 2.3665730337078653e-05, "loss": 1.5844, "step": 2250 }, { "epoch": 1.59, "learning_rate": 2.354868913857678e-05, "loss": 1.5771, "step": 2260 }, { "epoch": 1.59, "learning_rate": 2.3431647940074908e-05, "loss": 1.5795, "step": 2270 }, { "epoch": 1.6, "learning_rate": 2.3314606741573034e-05, "loss": 1.5784, "step": 2280 }, { "epoch": 1.61, "learning_rate": 2.3197565543071163e-05, "loss": 1.6204, "step": 2290 }, { "epoch": 1.62, "learning_rate": 2.308052434456929e-05, "loss": 1.5829, "step": 2300 }, { "epoch": 1.62, "learning_rate": 2.2963483146067415e-05, "loss": 1.5878, "step": 2310 }, { "epoch": 1.63, "learning_rate": 2.2846441947565544e-05, "loss": 1.5838, "step": 2320 }, { "epoch": 1.64, "learning_rate": 2.272940074906367e-05, "loss": 1.6049, "step": 2330 }, { "epoch": 1.64, "learning_rate": 2.26123595505618e-05, "loss": 1.602, "step": 2340 }, { "epoch": 1.65, "learning_rate": 2.2495318352059928e-05, "loss": 1.6357, "step": 2350 }, { "epoch": 1.66, "learning_rate": 2.2378277153558053e-05, "loss": 1.5882, "step": 2360 }, { "epoch": 1.66, "learning_rate": 2.2261235955056183e-05, "loss": 1.5904, "step": 2370 }, { "epoch": 1.67, "learning_rate": 2.2144194756554308e-05, "loss": 1.6046, "step": 2380 }, { "epoch": 1.68, "learning_rate": 2.2027153558052434e-05, "loss": 1.5691, "step": 2390 }, { "epoch": 1.69, "learning_rate": 2.1910112359550563e-05, "loss": 1.5727, "step": 2400 }, { "epoch": 1.69, "learning_rate": 2.179307116104869e-05, "loss": 1.5936, "step": 2410 }, { "epoch": 1.7, "learning_rate": 2.1676029962546818e-05, "loss": 1.6017, "step": 2420 }, { "epoch": 1.71, "learning_rate": 2.1558988764044947e-05, "loss": 1.6201, "step": 2430 }, { "epoch": 1.71, "learning_rate": 2.1441947565543073e-05, "loss": 1.6262, "step": 2440 }, { "epoch": 1.72, "learning_rate": 2.1324906367041202e-05, "loss": 1.5802, "step": 2450 }, { "epoch": 1.73, "learning_rate": 2.1207865168539328e-05, "loss": 1.5608, "step": 2460 }, { "epoch": 1.73, "learning_rate": 2.1090823970037453e-05, "loss": 1.6072, "step": 2470 }, { "epoch": 1.74, "learning_rate": 2.0973782771535582e-05, "loss": 1.6122, "step": 2480 }, { "epoch": 1.75, "learning_rate": 2.0856741573033708e-05, "loss": 1.6387, "step": 2490 }, { "epoch": 1.76, "learning_rate": 2.0739700374531837e-05, "loss": 1.5944, "step": 2500 }, { "epoch": 1.76, "learning_rate": 2.0622659176029963e-05, "loss": 1.623, "step": 2510 }, { "epoch": 1.77, "learning_rate": 2.0505617977528092e-05, "loss": 1.5679, "step": 2520 }, { "epoch": 1.78, "learning_rate": 2.0388576779026218e-05, "loss": 1.5833, "step": 2530 }, { "epoch": 1.78, "learning_rate": 2.0271535580524344e-05, "loss": 1.5898, "step": 2540 }, { "epoch": 1.79, "learning_rate": 2.0154494382022473e-05, "loss": 1.5832, "step": 2550 }, { "epoch": 1.8, "learning_rate": 2.00374531835206e-05, "loss": 1.6074, "step": 2560 }, { "epoch": 1.8, "learning_rate": 1.9920411985018728e-05, "loss": 1.5406, "step": 2570 }, { "epoch": 1.81, "learning_rate": 1.9803370786516857e-05, "loss": 1.5898, "step": 2580 }, { "epoch": 1.82, "learning_rate": 1.9686329588014982e-05, "loss": 1.6523, "step": 2590 }, { "epoch": 1.83, "learning_rate": 1.956928838951311e-05, "loss": 1.5475, "step": 2600 }, { "epoch": 1.83, "learning_rate": 1.9452247191011237e-05, "loss": 1.611, "step": 2610 }, { "epoch": 1.84, "learning_rate": 1.9335205992509363e-05, "loss": 1.644, "step": 2620 }, { "epoch": 1.85, "learning_rate": 1.9218164794007492e-05, "loss": 1.6512, "step": 2630 }, { "epoch": 1.85, "learning_rate": 1.9101123595505618e-05, "loss": 1.6181, "step": 2640 }, { "epoch": 1.86, "learning_rate": 1.8984082397003747e-05, "loss": 1.5943, "step": 2650 }, { "epoch": 1.87, "learning_rate": 1.8867041198501873e-05, "loss": 1.5644, "step": 2660 }, { "epoch": 1.88, "learning_rate": 1.8750000000000002e-05, "loss": 1.5931, "step": 2670 }, { "epoch": 1.88, "learning_rate": 1.863295880149813e-05, "loss": 1.5999, "step": 2680 }, { "epoch": 1.89, "learning_rate": 1.8515917602996257e-05, "loss": 1.6389, "step": 2690 }, { "epoch": 1.9, "learning_rate": 1.8398876404494382e-05, "loss": 1.6019, "step": 2700 }, { "epoch": 1.9, "learning_rate": 1.8281835205992508e-05, "loss": 1.6034, "step": 2710 }, { "epoch": 1.91, "learning_rate": 1.8164794007490637e-05, "loss": 1.6172, "step": 2720 }, { "epoch": 1.92, "learning_rate": 1.8047752808988766e-05, "loss": 1.584, "step": 2730 }, { "epoch": 1.92, "learning_rate": 1.7930711610486892e-05, "loss": 1.6288, "step": 2740 }, { "epoch": 1.93, "learning_rate": 1.781367041198502e-05, "loss": 1.6515, "step": 2750 }, { "epoch": 1.94, "learning_rate": 1.7696629213483147e-05, "loss": 1.6043, "step": 2760 }, { "epoch": 1.95, "learning_rate": 1.7579588014981273e-05, "loss": 1.6518, "step": 2770 }, { "epoch": 1.95, "learning_rate": 1.74625468164794e-05, "loss": 1.6164, "step": 2780 }, { "epoch": 1.96, "learning_rate": 1.7345505617977527e-05, "loss": 1.6004, "step": 2790 }, { "epoch": 1.97, "learning_rate": 1.7228464419475657e-05, "loss": 1.6178, "step": 2800 }, { "epoch": 1.97, "learning_rate": 1.7111423220973782e-05, "loss": 1.624, "step": 2810 }, { "epoch": 1.98, "learning_rate": 1.699438202247191e-05, "loss": 1.5782, "step": 2820 }, { "epoch": 1.99, "learning_rate": 1.687734082397004e-05, "loss": 1.6205, "step": 2830 }, { "epoch": 1.99, "learning_rate": 1.6760299625468166e-05, "loss": 1.5928, "step": 2840 }, { "epoch": 2.0, "learning_rate": 1.6643258426966292e-05, "loss": 1.6625, "step": 2850 }, { "epoch": 2.01, "learning_rate": 1.6526217228464418e-05, "loss": 1.5908, "step": 2860 }, { "epoch": 2.02, "learning_rate": 1.6409176029962547e-05, "loss": 1.6132, "step": 2870 }, { "epoch": 2.02, "learning_rate": 1.6292134831460676e-05, "loss": 1.6542, "step": 2880 }, { "epoch": 2.03, "learning_rate": 1.61750936329588e-05, "loss": 1.5836, "step": 2890 }, { "epoch": 2.04, "learning_rate": 1.605805243445693e-05, "loss": 1.581, "step": 2900 }, { "epoch": 2.04, "learning_rate": 1.5941011235955056e-05, "loss": 1.6075, "step": 2910 }, { "epoch": 2.05, "learning_rate": 1.5823970037453186e-05, "loss": 1.6246, "step": 2920 }, { "epoch": 2.06, "learning_rate": 1.570692883895131e-05, "loss": 1.589, "step": 2930 }, { "epoch": 2.06, "learning_rate": 1.5589887640449437e-05, "loss": 1.5989, "step": 2940 }, { "epoch": 2.07, "learning_rate": 1.5472846441947566e-05, "loss": 1.6443, "step": 2950 }, { "epoch": 2.08, "learning_rate": 1.5355805243445692e-05, "loss": 1.6154, "step": 2960 }, { "epoch": 2.09, "learning_rate": 1.5238764044943821e-05, "loss": 1.571, "step": 2970 }, { "epoch": 2.09, "learning_rate": 1.5121722846441948e-05, "loss": 1.6231, "step": 2980 }, { "epoch": 2.1, "learning_rate": 1.5004681647940074e-05, "loss": 1.595, "step": 2990 }, { "epoch": 2.11, "learning_rate": 1.4887640449438203e-05, "loss": 1.6098, "step": 3000 }, { "epoch": 2.11, "learning_rate": 1.4770599250936332e-05, "loss": 1.5654, "step": 3010 }, { "epoch": 2.12, "learning_rate": 1.4653558052434458e-05, "loss": 1.6087, "step": 3020 }, { "epoch": 2.13, "learning_rate": 1.4536516853932586e-05, "loss": 1.6169, "step": 3030 }, { "epoch": 2.13, "learning_rate": 1.4419475655430711e-05, "loss": 1.5326, "step": 3040 }, { "epoch": 2.14, "learning_rate": 1.430243445692884e-05, "loss": 1.5839, "step": 3050 }, { "epoch": 2.15, "learning_rate": 1.4185393258426968e-05, "loss": 1.6051, "step": 3060 }, { "epoch": 2.16, "learning_rate": 1.4068352059925093e-05, "loss": 1.595, "step": 3070 }, { "epoch": 2.16, "learning_rate": 1.3951310861423223e-05, "loss": 1.6497, "step": 3080 }, { "epoch": 2.17, "learning_rate": 1.3834269662921348e-05, "loss": 1.5961, "step": 3090 }, { "epoch": 2.18, "learning_rate": 1.3717228464419476e-05, "loss": 1.5774, "step": 3100 }, { "epoch": 2.18, "learning_rate": 1.3600187265917605e-05, "loss": 1.5494, "step": 3110 }, { "epoch": 2.19, "learning_rate": 1.348314606741573e-05, "loss": 1.6287, "step": 3120 }, { "epoch": 2.2, "learning_rate": 1.336610486891386e-05, "loss": 1.5876, "step": 3130 }, { "epoch": 2.21, "learning_rate": 1.3249063670411985e-05, "loss": 1.5899, "step": 3140 }, { "epoch": 2.21, "learning_rate": 1.3132022471910113e-05, "loss": 1.636, "step": 3150 }, { "epoch": 2.22, "learning_rate": 1.3014981273408242e-05, "loss": 1.5857, "step": 3160 }, { "epoch": 2.23, "learning_rate": 1.2897940074906368e-05, "loss": 1.5766, "step": 3170 }, { "epoch": 2.23, "learning_rate": 1.2780898876404495e-05, "loss": 1.5976, "step": 3180 }, { "epoch": 2.24, "learning_rate": 1.2663857677902621e-05, "loss": 1.6176, "step": 3190 }, { "epoch": 2.25, "learning_rate": 1.254681647940075e-05, "loss": 1.5601, "step": 3200 }, { "epoch": 2.25, "learning_rate": 1.2429775280898877e-05, "loss": 1.6138, "step": 3210 }, { "epoch": 2.26, "learning_rate": 1.2312734082397003e-05, "loss": 1.5693, "step": 3220 }, { "epoch": 2.27, "learning_rate": 1.2195692883895132e-05, "loss": 1.5975, "step": 3230 }, { "epoch": 2.28, "learning_rate": 1.207865168539326e-05, "loss": 1.5745, "step": 3240 }, { "epoch": 2.28, "learning_rate": 1.1961610486891387e-05, "loss": 1.5805, "step": 3250 }, { "epoch": 2.29, "learning_rate": 1.1844569288389513e-05, "loss": 1.5644, "step": 3260 }, { "epoch": 2.3, "learning_rate": 1.172752808988764e-05, "loss": 1.5996, "step": 3270 }, { "epoch": 2.3, "learning_rate": 1.161048689138577e-05, "loss": 1.5899, "step": 3280 }, { "epoch": 2.31, "learning_rate": 1.1493445692883897e-05, "loss": 1.5999, "step": 3290 }, { "epoch": 2.32, "learning_rate": 1.1376404494382022e-05, "loss": 1.5971, "step": 3300 }, { "epoch": 2.32, "learning_rate": 1.125936329588015e-05, "loss": 1.6169, "step": 3310 }, { "epoch": 2.33, "learning_rate": 1.1142322097378277e-05, "loss": 1.6032, "step": 3320 }, { "epoch": 2.34, "learning_rate": 1.1025280898876405e-05, "loss": 1.6395, "step": 3330 }, { "epoch": 2.35, "learning_rate": 1.0908239700374532e-05, "loss": 1.5836, "step": 3340 }, { "epoch": 2.35, "learning_rate": 1.079119850187266e-05, "loss": 1.6348, "step": 3350 }, { "epoch": 2.36, "learning_rate": 1.0674157303370787e-05, "loss": 1.6234, "step": 3360 }, { "epoch": 2.37, "learning_rate": 1.0557116104868914e-05, "loss": 1.5759, "step": 3370 }, { "epoch": 2.37, "learning_rate": 1.0440074906367042e-05, "loss": 1.5938, "step": 3380 }, { "epoch": 2.38, "learning_rate": 1.032303370786517e-05, "loss": 1.6115, "step": 3390 }, { "epoch": 2.39, "learning_rate": 1.0205992509363297e-05, "loss": 1.597, "step": 3400 }, { "epoch": 2.39, "learning_rate": 1.0088951310861424e-05, "loss": 1.6085, "step": 3410 }, { "epoch": 2.4, "learning_rate": 9.97191011235955e-06, "loss": 1.6232, "step": 3420 }, { "epoch": 2.41, "learning_rate": 9.854868913857679e-06, "loss": 1.5851, "step": 3430 }, { "epoch": 2.42, "learning_rate": 9.737827715355806e-06, "loss": 1.5964, "step": 3440 }, { "epoch": 2.42, "learning_rate": 9.620786516853934e-06, "loss": 1.6511, "step": 3450 }, { "epoch": 2.43, "learning_rate": 9.50374531835206e-06, "loss": 1.591, "step": 3460 }, { "epoch": 2.44, "learning_rate": 9.386704119850187e-06, "loss": 1.6433, "step": 3470 }, { "epoch": 2.44, "learning_rate": 9.269662921348316e-06, "loss": 1.5838, "step": 3480 }, { "epoch": 2.45, "learning_rate": 9.152621722846442e-06, "loss": 1.5905, "step": 3490 }, { "epoch": 2.46, "learning_rate": 9.03558052434457e-06, "loss": 1.5938, "step": 3500 } ], "logging_steps": 10, "max_steps": 4272, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.2114548519115162e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }