{ "best_metric": 0.6656151022527915, "best_model_checkpoint": "/efs/griadams/dsum/weights/perturber/ent_sample/checkpoint-92000", "epoch": 1.6339869281045751, "global_step": 100000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 0.0, "loss": 6.3471, "step": 1 }, { "epoch": 0.0, "learning_rate": 2.0000000000000003e-06, "loss": 6.3766, "step": 10 }, { "epoch": 0.0, "learning_rate": 4.5e-06, "loss": 5.4782, "step": 20 }, { "epoch": 0.0, "learning_rate": 7.000000000000001e-06, "loss": 4.9235, "step": 30 }, { "epoch": 0.0, "learning_rate": 9.25e-06, "loss": 4.5294, "step": 40 }, { "epoch": 0.0, "learning_rate": 1.175e-05, "loss": 4.415, "step": 50 }, { "epoch": 0.0, "learning_rate": 1.4249999999999999e-05, "loss": 4.1903, "step": 60 }, { "epoch": 0.0, "learning_rate": 1.675e-05, "loss": 4.077, "step": 70 }, { "epoch": 0.0, "learning_rate": 1.925e-05, "loss": 3.9311, "step": 80 }, { "epoch": 0.0, "learning_rate": 2.175e-05, "loss": 3.8825, "step": 90 }, { "epoch": 0.0, "learning_rate": 2.425e-05, "loss": 3.735, "step": 100 }, { "epoch": 0.0, "learning_rate": 2.6750000000000003e-05, "loss": 3.683, "step": 110 }, { "epoch": 0.0, "learning_rate": 2.925e-05, "loss": 3.684, "step": 120 }, { "epoch": 0.0, "learning_rate": 3.175e-05, "loss": 3.593, "step": 130 }, { "epoch": 0.0, "learning_rate": 3.4250000000000006e-05, "loss": 3.5485, "step": 140 }, { "epoch": 0.0, "learning_rate": 3.675e-05, "loss": 3.5382, "step": 150 }, { "epoch": 0.0, "learning_rate": 3.9250000000000005e-05, "loss": 3.5182, "step": 160 }, { "epoch": 0.0, "learning_rate": 4.175e-05, "loss": 3.4207, "step": 170 }, { "epoch": 0.0, "learning_rate": 4.4250000000000005e-05, "loss": 3.3964, "step": 180 }, { "epoch": 0.0, "learning_rate": 4.6750000000000005e-05, "loss": 3.3889, "step": 190 }, { "epoch": 0.0, "learning_rate": 4.9250000000000004e-05, "loss": 3.3242, "step": 200 }, { "epoch": 0.0, "learning_rate": 4.999649298597195e-05, "loss": 3.2921, "step": 210 }, { "epoch": 0.0, "learning_rate": 4.999148296593187e-05, "loss": 3.2607, "step": 220 }, { "epoch": 0.0, "learning_rate": 4.9986472945891785e-05, "loss": 3.2372, "step": 230 }, { "epoch": 0.0, "learning_rate": 4.9981462925851706e-05, "loss": 3.2513, "step": 240 }, { "epoch": 0.0, "learning_rate": 4.997645290581163e-05, "loss": 3.2169, "step": 250 }, { "epoch": 0.0, "learning_rate": 4.997144288577155e-05, "loss": 3.2379, "step": 260 }, { "epoch": 0.0, "learning_rate": 4.996643286573147e-05, "loss": 3.21, "step": 270 }, { "epoch": 0.0, "learning_rate": 4.996142284569139e-05, "loss": 3.1264, "step": 280 }, { "epoch": 0.0, "learning_rate": 4.99564128256513e-05, "loss": 3.1906, "step": 290 }, { "epoch": 0.0, "learning_rate": 4.995140280561122e-05, "loss": 3.1573, "step": 300 }, { "epoch": 0.01, "learning_rate": 4.9946392785571144e-05, "loss": 3.1467, "step": 310 }, { "epoch": 0.01, "learning_rate": 4.9941382765531064e-05, "loss": 3.1258, "step": 320 }, { "epoch": 0.01, "learning_rate": 4.9936873747494994e-05, "loss": 3.1294, "step": 330 }, { "epoch": 0.01, "learning_rate": 4.9931863727454915e-05, "loss": 3.0812, "step": 340 }, { "epoch": 0.01, "learning_rate": 4.9926853707414836e-05, "loss": 3.1266, "step": 350 }, { "epoch": 0.01, "learning_rate": 4.9921843687374756e-05, "loss": 3.0731, "step": 360 }, { "epoch": 0.01, "learning_rate": 4.991683366733467e-05, "loss": 3.0911, "step": 370 }, { "epoch": 0.01, "learning_rate": 4.991182364729459e-05, "loss": 3.0786, "step": 380 }, { "epoch": 0.01, "learning_rate": 4.990681362725451e-05, "loss": 3.0672, "step": 390 }, { "epoch": 0.01, "learning_rate": 4.990180360721443e-05, "loss": 3.0248, "step": 400 }, { "epoch": 0.01, "learning_rate": 4.989679358717435e-05, "loss": 2.9678, "step": 410 }, { "epoch": 0.01, "learning_rate": 4.989178356713427e-05, "loss": 2.9772, "step": 420 }, { "epoch": 0.01, "learning_rate": 4.988677354709419e-05, "loss": 2.9849, "step": 430 }, { "epoch": 0.01, "learning_rate": 4.988176352705411e-05, "loss": 3.0409, "step": 440 }, { "epoch": 0.01, "learning_rate": 4.987675350701403e-05, "loss": 2.9913, "step": 450 }, { "epoch": 0.01, "learning_rate": 4.987174348697395e-05, "loss": 2.9971, "step": 460 }, { "epoch": 0.01, "learning_rate": 4.986673346693387e-05, "loss": 3.0198, "step": 470 }, { "epoch": 0.01, "learning_rate": 4.986172344689379e-05, "loss": 2.9643, "step": 480 }, { "epoch": 0.01, "learning_rate": 4.9856713426853704e-05, "loss": 2.9001, "step": 490 }, { "epoch": 0.01, "learning_rate": 4.985170340681363e-05, "loss": 2.9734, "step": 500 }, { "epoch": 0.01, "learning_rate": 4.984669338677355e-05, "loss": 2.9855, "step": 510 }, { "epoch": 0.01, "learning_rate": 4.984168336673347e-05, "loss": 2.9572, "step": 520 }, { "epoch": 0.01, "learning_rate": 4.9837174348697396e-05, "loss": 2.9491, "step": 530 }, { "epoch": 0.01, "learning_rate": 4.983216432865732e-05, "loss": 2.9657, "step": 540 }, { "epoch": 0.01, "learning_rate": 4.982715430861724e-05, "loss": 2.9882, "step": 550 }, { "epoch": 0.01, "learning_rate": 4.982214428857716e-05, "loss": 2.9508, "step": 560 }, { "epoch": 0.01, "learning_rate": 4.981713426853707e-05, "loss": 2.9032, "step": 570 }, { "epoch": 0.01, "learning_rate": 4.981212424849699e-05, "loss": 2.9234, "step": 580 }, { "epoch": 0.01, "learning_rate": 4.980711422845691e-05, "loss": 2.8756, "step": 590 }, { "epoch": 0.01, "learning_rate": 4.980210420841684e-05, "loss": 2.9073, "step": 600 }, { "epoch": 0.01, "learning_rate": 4.979709418837676e-05, "loss": 2.9355, "step": 610 }, { "epoch": 0.01, "learning_rate": 4.9792084168336675e-05, "loss": 2.8714, "step": 620 }, { "epoch": 0.01, "learning_rate": 4.9787074148296596e-05, "loss": 2.8604, "step": 630 }, { "epoch": 0.01, "learning_rate": 4.9782064128256516e-05, "loss": 2.8803, "step": 640 }, { "epoch": 0.01, "learning_rate": 4.977705410821644e-05, "loss": 2.8607, "step": 650 }, { "epoch": 0.01, "learning_rate": 4.977204408817636e-05, "loss": 2.8159, "step": 660 }, { "epoch": 0.01, "learning_rate": 4.976703406813628e-05, "loss": 2.8828, "step": 670 }, { "epoch": 0.01, "learning_rate": 4.976202404809619e-05, "loss": 2.9074, "step": 680 }, { "epoch": 0.01, "learning_rate": 4.975701402805611e-05, "loss": 2.8989, "step": 690 }, { "epoch": 0.01, "learning_rate": 4.9752004008016033e-05, "loss": 2.8466, "step": 700 }, { "epoch": 0.01, "learning_rate": 4.9746993987975954e-05, "loss": 2.7704, "step": 710 }, { "epoch": 0.01, "learning_rate": 4.9741983967935875e-05, "loss": 2.8554, "step": 720 }, { "epoch": 0.01, "learning_rate": 4.9736973947895795e-05, "loss": 2.8319, "step": 730 }, { "epoch": 0.01, "learning_rate": 4.973196392785571e-05, "loss": 2.8339, "step": 740 }, { "epoch": 0.01, "learning_rate": 4.972695390781563e-05, "loss": 2.8475, "step": 750 }, { "epoch": 0.01, "learning_rate": 4.972194388777555e-05, "loss": 2.7966, "step": 760 }, { "epoch": 0.01, "learning_rate": 4.971693386773547e-05, "loss": 2.8454, "step": 770 }, { "epoch": 0.01, "learning_rate": 4.971192384769539e-05, "loss": 2.8631, "step": 780 }, { "epoch": 0.01, "learning_rate": 4.970691382765531e-05, "loss": 2.9026, "step": 790 }, { "epoch": 0.01, "learning_rate": 4.970190380761523e-05, "loss": 2.7814, "step": 800 }, { "epoch": 0.01, "learning_rate": 4.9696893787575154e-05, "loss": 2.7997, "step": 810 }, { "epoch": 0.01, "learning_rate": 4.9691883767535074e-05, "loss": 2.8223, "step": 820 }, { "epoch": 0.01, "learning_rate": 4.9686873747494995e-05, "loss": 2.7675, "step": 830 }, { "epoch": 0.01, "learning_rate": 4.9681863727454916e-05, "loss": 2.7768, "step": 840 }, { "epoch": 0.01, "learning_rate": 4.9676853707414836e-05, "loss": 2.8356, "step": 850 }, { "epoch": 0.01, "learning_rate": 4.967184368737475e-05, "loss": 2.8053, "step": 860 }, { "epoch": 0.01, "learning_rate": 4.966683366733467e-05, "loss": 2.7989, "step": 870 }, { "epoch": 0.01, "learning_rate": 4.966182364729459e-05, "loss": 2.8084, "step": 880 }, { "epoch": 0.01, "learning_rate": 4.965681362725451e-05, "loss": 2.8046, "step": 890 }, { "epoch": 0.01, "learning_rate": 4.965180360721443e-05, "loss": 2.81, "step": 900 }, { "epoch": 0.01, "learning_rate": 4.9646793587174353e-05, "loss": 2.786, "step": 910 }, { "epoch": 0.02, "learning_rate": 4.964178356713427e-05, "loss": 2.7894, "step": 920 }, { "epoch": 0.02, "learning_rate": 4.963677354709419e-05, "loss": 2.7866, "step": 930 }, { "epoch": 0.02, "learning_rate": 4.963176352705411e-05, "loss": 2.7215, "step": 940 }, { "epoch": 0.02, "learning_rate": 4.962675350701403e-05, "loss": 2.7597, "step": 950 }, { "epoch": 0.02, "learning_rate": 4.962174348697395e-05, "loss": 2.754, "step": 960 }, { "epoch": 0.02, "learning_rate": 4.961673346693387e-05, "loss": 2.7883, "step": 970 }, { "epoch": 0.02, "learning_rate": 4.9611723446893784e-05, "loss": 2.7492, "step": 980 }, { "epoch": 0.02, "learning_rate": 4.9606713426853705e-05, "loss": 2.7861, "step": 990 }, { "epoch": 0.02, "learning_rate": 4.960170340681363e-05, "loss": 2.7997, "step": 1000 }, { "epoch": 0.02, "eval_loss": 2.6530845165252686, "eval_mean_f1": 0.5713224313985495, "eval_rouge1_f1": 0.6492439087167909, "eval_rouge1_precision": 0.8017815050745305, "eval_rouge1_recall": 0.5775265345369596, "eval_rouge2_f1": 0.4552109870465224, "eval_rouge2_precision": 0.5627126372975984, "eval_rouge2_recall": 0.40590973789470236, "eval_rougeL_f1": 0.6095123984323353, "eval_rougeL_precision": 0.7483651405433052, "eval_rougeL_recall": 0.5437509762518895, "eval_runtime": 64.0166, "eval_samples_per_second": 15.996, "eval_steps_per_second": 1.999, "step": 1000 }, { "epoch": 0.02, "learning_rate": 4.959669338677355e-05, "loss": 2.7497, "step": 1010 }, { "epoch": 0.02, "learning_rate": 4.9591683366733474e-05, "loss": 2.7571, "step": 1020 }, { "epoch": 0.02, "learning_rate": 4.958667334669339e-05, "loss": 2.7699, "step": 1030 }, { "epoch": 0.02, "learning_rate": 4.958166332665331e-05, "loss": 2.6992, "step": 1040 }, { "epoch": 0.02, "learning_rate": 4.957665330661323e-05, "loss": 2.7276, "step": 1050 }, { "epoch": 0.02, "learning_rate": 4.957164328657315e-05, "loss": 2.7856, "step": 1060 }, { "epoch": 0.02, "learning_rate": 4.956663326653307e-05, "loss": 2.7535, "step": 1070 }, { "epoch": 0.02, "learning_rate": 4.956162324649299e-05, "loss": 2.6948, "step": 1080 }, { "epoch": 0.02, "learning_rate": 4.955661322645291e-05, "loss": 2.7577, "step": 1090 }, { "epoch": 0.02, "learning_rate": 4.9551603206412825e-05, "loss": 2.7859, "step": 1100 }, { "epoch": 0.02, "learning_rate": 4.9546593186372746e-05, "loss": 2.7631, "step": 1110 }, { "epoch": 0.02, "learning_rate": 4.9541583166332667e-05, "loss": 2.7541, "step": 1120 }, { "epoch": 0.02, "learning_rate": 4.953657314629259e-05, "loss": 2.745, "step": 1130 }, { "epoch": 0.02, "learning_rate": 4.953156312625251e-05, "loss": 2.7528, "step": 1140 }, { "epoch": 0.02, "learning_rate": 4.952655310621243e-05, "loss": 2.7382, "step": 1150 }, { "epoch": 0.02, "learning_rate": 4.952154308617234e-05, "loss": 2.751, "step": 1160 }, { "epoch": 0.02, "learning_rate": 4.951653306613226e-05, "loss": 2.7488, "step": 1170 }, { "epoch": 0.02, "learning_rate": 4.9511523046092184e-05, "loss": 2.7071, "step": 1180 }, { "epoch": 0.02, "learning_rate": 4.950651302605211e-05, "loss": 2.7711, "step": 1190 }, { "epoch": 0.02, "learning_rate": 4.950150300601203e-05, "loss": 2.6978, "step": 1200 }, { "epoch": 0.02, "learning_rate": 4.9496492985971946e-05, "loss": 2.725, "step": 1210 }, { "epoch": 0.02, "learning_rate": 4.9491482965931866e-05, "loss": 2.7137, "step": 1220 }, { "epoch": 0.02, "learning_rate": 4.948647294589179e-05, "loss": 2.7449, "step": 1230 }, { "epoch": 0.02, "learning_rate": 4.948146292585171e-05, "loss": 2.6845, "step": 1240 }, { "epoch": 0.02, "learning_rate": 4.947645290581163e-05, "loss": 2.7439, "step": 1250 }, { "epoch": 0.02, "learning_rate": 4.947144288577155e-05, "loss": 2.7289, "step": 1260 }, { "epoch": 0.02, "learning_rate": 4.946643286573146e-05, "loss": 2.6847, "step": 1270 }, { "epoch": 0.02, "learning_rate": 4.946142284569138e-05, "loss": 2.6286, "step": 1280 }, { "epoch": 0.02, "learning_rate": 4.9456412825651304e-05, "loss": 2.6806, "step": 1290 }, { "epoch": 0.02, "learning_rate": 4.9451402805611225e-05, "loss": 2.665, "step": 1300 }, { "epoch": 0.02, "learning_rate": 4.9446392785571145e-05, "loss": 2.7226, "step": 1310 }, { "epoch": 0.02, "learning_rate": 4.9441382765531066e-05, "loss": 2.6895, "step": 1320 }, { "epoch": 0.02, "learning_rate": 4.9436372745490986e-05, "loss": 2.6501, "step": 1330 }, { "epoch": 0.02, "learning_rate": 4.94313627254509e-05, "loss": 2.6997, "step": 1340 }, { "epoch": 0.02, "learning_rate": 4.942635270541082e-05, "loss": 2.7067, "step": 1350 }, { "epoch": 0.02, "learning_rate": 4.942134268537074e-05, "loss": 2.6565, "step": 1360 }, { "epoch": 0.02, "learning_rate": 4.941633266533066e-05, "loss": 2.7367, "step": 1370 }, { "epoch": 0.02, "learning_rate": 4.941132264529058e-05, "loss": 2.6609, "step": 1380 }, { "epoch": 0.02, "learning_rate": 4.9406312625250504e-05, "loss": 2.6411, "step": 1390 }, { "epoch": 0.02, "learning_rate": 4.9401302605210424e-05, "loss": 2.6956, "step": 1400 }, { "epoch": 0.02, "learning_rate": 4.9396292585170345e-05, "loss": 2.6094, "step": 1410 }, { "epoch": 0.02, "learning_rate": 4.9391282565130265e-05, "loss": 2.7477, "step": 1420 }, { "epoch": 0.02, "learning_rate": 4.9386272545090186e-05, "loss": 2.6843, "step": 1430 }, { "epoch": 0.02, "learning_rate": 4.938126252505011e-05, "loss": 2.601, "step": 1440 }, { "epoch": 0.02, "learning_rate": 4.937625250501002e-05, "loss": 2.6421, "step": 1450 }, { "epoch": 0.02, "learning_rate": 4.937124248496994e-05, "loss": 2.6896, "step": 1460 }, { "epoch": 0.02, "learning_rate": 4.936623246492986e-05, "loss": 2.6547, "step": 1470 }, { "epoch": 0.02, "learning_rate": 4.936122244488978e-05, "loss": 2.6523, "step": 1480 }, { "epoch": 0.02, "learning_rate": 4.93562124248497e-05, "loss": 2.6482, "step": 1490 }, { "epoch": 0.02, "learning_rate": 4.9351202404809624e-05, "loss": 2.6271, "step": 1500 }, { "epoch": 0.02, "learning_rate": 4.934619238476954e-05, "loss": 2.6563, "step": 1510 }, { "epoch": 0.02, "learning_rate": 4.934118236472946e-05, "loss": 2.6138, "step": 1520 }, { "epoch": 0.03, "learning_rate": 4.933617234468938e-05, "loss": 2.6253, "step": 1530 }, { "epoch": 0.03, "learning_rate": 4.93311623246493e-05, "loss": 2.6988, "step": 1540 }, { "epoch": 0.03, "learning_rate": 4.932615230460922e-05, "loss": 2.6876, "step": 1550 }, { "epoch": 0.03, "learning_rate": 4.932114228456914e-05, "loss": 2.6486, "step": 1560 }, { "epoch": 0.03, "learning_rate": 4.9316132264529055e-05, "loss": 2.6672, "step": 1570 }, { "epoch": 0.03, "learning_rate": 4.9311122244488975e-05, "loss": 2.6818, "step": 1580 }, { "epoch": 0.03, "learning_rate": 4.93061122244489e-05, "loss": 2.6502, "step": 1590 }, { "epoch": 0.03, "learning_rate": 4.9301102204408823e-05, "loss": 2.5772, "step": 1600 }, { "epoch": 0.03, "learning_rate": 4.9296092184368744e-05, "loss": 2.6212, "step": 1610 }, { "epoch": 0.03, "learning_rate": 4.929108216432866e-05, "loss": 2.6499, "step": 1620 }, { "epoch": 0.03, "learning_rate": 4.928607214428858e-05, "loss": 2.637, "step": 1630 }, { "epoch": 0.03, "learning_rate": 4.92810621242485e-05, "loss": 2.6565, "step": 1640 }, { "epoch": 0.03, "learning_rate": 4.927605210420842e-05, "loss": 2.6158, "step": 1650 }, { "epoch": 0.03, "learning_rate": 4.927104208416834e-05, "loss": 2.6403, "step": 1660 }, { "epoch": 0.03, "learning_rate": 4.926603206412826e-05, "loss": 2.5975, "step": 1670 }, { "epoch": 0.03, "learning_rate": 4.926102204408818e-05, "loss": 2.6224, "step": 1680 }, { "epoch": 0.03, "learning_rate": 4.9256012024048096e-05, "loss": 2.6021, "step": 1690 }, { "epoch": 0.03, "learning_rate": 4.9251002004008016e-05, "loss": 2.5727, "step": 1700 }, { "epoch": 0.03, "learning_rate": 4.924599198396794e-05, "loss": 2.6382, "step": 1710 }, { "epoch": 0.03, "learning_rate": 4.924098196392786e-05, "loss": 2.5363, "step": 1720 }, { "epoch": 0.03, "learning_rate": 4.923597194388778e-05, "loss": 2.6191, "step": 1730 }, { "epoch": 0.03, "learning_rate": 4.92309619238477e-05, "loss": 2.6715, "step": 1740 }, { "epoch": 0.03, "learning_rate": 4.922595190380761e-05, "loss": 2.6339, "step": 1750 }, { "epoch": 0.03, "learning_rate": 4.922094188376753e-05, "loss": 2.5665, "step": 1760 }, { "epoch": 0.03, "learning_rate": 4.9215931863727454e-05, "loss": 2.6916, "step": 1770 }, { "epoch": 0.03, "learning_rate": 4.921092184368738e-05, "loss": 2.6016, "step": 1780 }, { "epoch": 0.03, "learning_rate": 4.92059118236473e-05, "loss": 2.5762, "step": 1790 }, { "epoch": 0.03, "learning_rate": 4.9200901803607216e-05, "loss": 2.6151, "step": 1800 }, { "epoch": 0.03, "learning_rate": 4.9195891783567137e-05, "loss": 2.6187, "step": 1810 }, { "epoch": 0.03, "learning_rate": 4.919088176352706e-05, "loss": 2.5225, "step": 1820 }, { "epoch": 0.03, "learning_rate": 4.918587174348698e-05, "loss": 2.4727, "step": 1830 }, { "epoch": 0.03, "learning_rate": 4.91808617234469e-05, "loss": 2.6116, "step": 1840 }, { "epoch": 0.03, "learning_rate": 4.917585170340682e-05, "loss": 2.5779, "step": 1850 }, { "epoch": 0.03, "learning_rate": 4.917084168336673e-05, "loss": 2.6004, "step": 1860 }, { "epoch": 0.03, "learning_rate": 4.9165831663326654e-05, "loss": 2.5896, "step": 1870 }, { "epoch": 0.03, "learning_rate": 4.9160821643286574e-05, "loss": 2.5476, "step": 1880 }, { "epoch": 0.03, "learning_rate": 4.9155811623246495e-05, "loss": 2.6142, "step": 1890 }, { "epoch": 0.03, "learning_rate": 4.9150801603206416e-05, "loss": 2.5779, "step": 1900 }, { "epoch": 0.03, "learning_rate": 4.9145791583166336e-05, "loss": 2.5809, "step": 1910 }, { "epoch": 0.03, "learning_rate": 4.914078156312626e-05, "loss": 2.578, "step": 1920 }, { "epoch": 0.03, "learning_rate": 4.913577154308617e-05, "loss": 2.6081, "step": 1930 }, { "epoch": 0.03, "learning_rate": 4.913076152304609e-05, "loss": 2.572, "step": 1940 }, { "epoch": 0.03, "learning_rate": 4.912575150300601e-05, "loss": 2.6207, "step": 1950 }, { "epoch": 0.03, "learning_rate": 4.912074148296593e-05, "loss": 2.5693, "step": 1960 }, { "epoch": 0.03, "learning_rate": 4.911573146292585e-05, "loss": 2.6255, "step": 1970 }, { "epoch": 0.03, "learning_rate": 4.9110721442885774e-05, "loss": 2.5952, "step": 1980 }, { "epoch": 0.03, "learning_rate": 4.9105711422845695e-05, "loss": 2.588, "step": 1990 }, { "epoch": 0.03, "learning_rate": 4.9100701402805615e-05, "loss": 2.5732, "step": 2000 }, { "epoch": 0.03, "eval_loss": 2.4990265369415283, "eval_mean_f1": 0.5931649052192617, "eval_rouge1_f1": 0.6666923932688903, "eval_rouge1_precision": 0.8069188292304101, "eval_rouge1_recall": 0.5969988099377816, "eval_rouge2_f1": 0.48240575906082195, "eval_rouge2_precision": 0.5857352059561531, "eval_rouge2_recall": 0.4328954816909993, "eval_rougeL_f1": 0.6303965633280726, "eval_rougeL_precision": 0.7599600221300734, "eval_rougeL_recall": 0.5659934403515214, "eval_runtime": 65.1976, "eval_samples_per_second": 15.706, "eval_steps_per_second": 1.963, "step": 2000 }, { "epoch": 0.03, "learning_rate": 4.9095691382765536e-05, "loss": 2.5559, "step": 2010 }, { "epoch": 0.03, "learning_rate": 4.9090681362725456e-05, "loss": 2.5881, "step": 2020 }, { "epoch": 0.03, "learning_rate": 4.908567134268538e-05, "loss": 2.5294, "step": 2030 }, { "epoch": 0.03, "learning_rate": 4.908066132264529e-05, "loss": 2.6248, "step": 2040 }, { "epoch": 0.03, "learning_rate": 4.907565130260521e-05, "loss": 2.5895, "step": 2050 }, { "epoch": 0.03, "learning_rate": 4.907064128256513e-05, "loss": 2.5441, "step": 2060 }, { "epoch": 0.03, "learning_rate": 4.906563126252505e-05, "loss": 2.5827, "step": 2070 }, { "epoch": 0.03, "learning_rate": 4.9060621242484974e-05, "loss": 2.5459, "step": 2080 }, { "epoch": 0.03, "learning_rate": 4.9055611222444894e-05, "loss": 2.5731, "step": 2090 }, { "epoch": 0.03, "learning_rate": 4.905060120240481e-05, "loss": 2.4574, "step": 2100 }, { "epoch": 0.03, "learning_rate": 4.904559118236473e-05, "loss": 2.5949, "step": 2110 }, { "epoch": 0.03, "learning_rate": 4.904058116232465e-05, "loss": 2.5987, "step": 2120 }, { "epoch": 0.03, "learning_rate": 4.903557114228457e-05, "loss": 2.5092, "step": 2130 }, { "epoch": 0.03, "learning_rate": 4.903056112224449e-05, "loss": 2.5149, "step": 2140 }, { "epoch": 0.04, "learning_rate": 4.902555110220441e-05, "loss": 2.5617, "step": 2150 }, { "epoch": 0.04, "learning_rate": 4.9020541082164325e-05, "loss": 2.4967, "step": 2160 }, { "epoch": 0.04, "learning_rate": 4.901553106212425e-05, "loss": 2.5407, "step": 2170 }, { "epoch": 0.04, "learning_rate": 4.901052104208417e-05, "loss": 2.5444, "step": 2180 }, { "epoch": 0.04, "learning_rate": 4.9005511022044094e-05, "loss": 2.5828, "step": 2190 }, { "epoch": 0.04, "learning_rate": 4.9000501002004014e-05, "loss": 2.5085, "step": 2200 }, { "epoch": 0.04, "learning_rate": 4.8995490981963935e-05, "loss": 2.5603, "step": 2210 }, { "epoch": 0.04, "learning_rate": 4.899048096192385e-05, "loss": 2.5531, "step": 2220 }, { "epoch": 0.04, "learning_rate": 4.898547094188377e-05, "loss": 2.5834, "step": 2230 }, { "epoch": 0.04, "learning_rate": 4.898046092184369e-05, "loss": 2.5594, "step": 2240 }, { "epoch": 0.04, "learning_rate": 4.897545090180361e-05, "loss": 2.6081, "step": 2250 }, { "epoch": 0.04, "learning_rate": 4.897044088176353e-05, "loss": 2.5403, "step": 2260 }, { "epoch": 0.04, "learning_rate": 4.896543086172345e-05, "loss": 2.5534, "step": 2270 }, { "epoch": 0.04, "learning_rate": 4.8960420841683366e-05, "loss": 2.5582, "step": 2280 }, { "epoch": 0.04, "learning_rate": 4.895541082164329e-05, "loss": 2.5684, "step": 2290 }, { "epoch": 0.04, "learning_rate": 4.895040080160321e-05, "loss": 2.5611, "step": 2300 }, { "epoch": 0.04, "learning_rate": 4.894539078156313e-05, "loss": 2.593, "step": 2310 }, { "epoch": 0.04, "learning_rate": 4.894038076152305e-05, "loss": 2.5271, "step": 2320 }, { "epoch": 0.04, "learning_rate": 4.893537074148297e-05, "loss": 2.554, "step": 2330 }, { "epoch": 0.04, "learning_rate": 4.893036072144288e-05, "loss": 2.5506, "step": 2340 }, { "epoch": 0.04, "learning_rate": 4.8925350701402804e-05, "loss": 2.5659, "step": 2350 }, { "epoch": 0.04, "learning_rate": 4.8920340681362724e-05, "loss": 2.4876, "step": 2360 }, { "epoch": 0.04, "learning_rate": 4.891533066132265e-05, "loss": 2.5532, "step": 2370 }, { "epoch": 0.04, "learning_rate": 4.891032064128257e-05, "loss": 2.5765, "step": 2380 }, { "epoch": 0.04, "learning_rate": 4.8905310621242486e-05, "loss": 2.5659, "step": 2390 }, { "epoch": 0.04, "learning_rate": 4.890030060120241e-05, "loss": 2.5703, "step": 2400 }, { "epoch": 0.04, "learning_rate": 4.889529058116233e-05, "loss": 2.5233, "step": 2410 }, { "epoch": 0.04, "learning_rate": 4.889028056112225e-05, "loss": 2.5407, "step": 2420 }, { "epoch": 0.04, "learning_rate": 4.888527054108217e-05, "loss": 2.5288, "step": 2430 }, { "epoch": 0.04, "learning_rate": 4.888026052104209e-05, "loss": 2.5418, "step": 2440 }, { "epoch": 0.04, "learning_rate": 4.8875250501002003e-05, "loss": 2.5439, "step": 2450 }, { "epoch": 0.04, "learning_rate": 4.8870240480961924e-05, "loss": 2.5771, "step": 2460 }, { "epoch": 0.04, "learning_rate": 4.8865230460921845e-05, "loss": 2.5435, "step": 2470 }, { "epoch": 0.04, "learning_rate": 4.8860220440881765e-05, "loss": 2.5311, "step": 2480 }, { "epoch": 0.04, "learning_rate": 4.8855210420841686e-05, "loss": 2.5022, "step": 2490 }, { "epoch": 0.04, "learning_rate": 4.885020040080161e-05, "loss": 2.4917, "step": 2500 }, { "epoch": 0.04, "learning_rate": 4.884519038076153e-05, "loss": 2.5236, "step": 2510 }, { "epoch": 0.04, "learning_rate": 4.884018036072144e-05, "loss": 2.5778, "step": 2520 }, { "epoch": 0.04, "learning_rate": 4.883517034068136e-05, "loss": 2.5634, "step": 2530 }, { "epoch": 0.04, "learning_rate": 4.883016032064128e-05, "loss": 2.5494, "step": 2540 }, { "epoch": 0.04, "learning_rate": 4.88251503006012e-05, "loss": 2.5272, "step": 2550 }, { "epoch": 0.04, "learning_rate": 4.8820140280561124e-05, "loss": 2.5862, "step": 2560 }, { "epoch": 0.04, "learning_rate": 4.8815130260521044e-05, "loss": 2.5444, "step": 2570 }, { "epoch": 0.04, "learning_rate": 4.8810120240480965e-05, "loss": 2.4986, "step": 2580 }, { "epoch": 0.04, "learning_rate": 4.8805110220440886e-05, "loss": 2.5331, "step": 2590 }, { "epoch": 0.04, "learning_rate": 4.8800100200400806e-05, "loss": 2.5303, "step": 2600 }, { "epoch": 0.04, "learning_rate": 4.879509018036073e-05, "loss": 2.4569, "step": 2610 }, { "epoch": 0.04, "learning_rate": 4.879008016032065e-05, "loss": 2.5053, "step": 2620 }, { "epoch": 0.04, "learning_rate": 4.878507014028056e-05, "loss": 2.4949, "step": 2630 }, { "epoch": 0.04, "learning_rate": 4.878006012024048e-05, "loss": 2.5177, "step": 2640 }, { "epoch": 0.04, "learning_rate": 4.87750501002004e-05, "loss": 2.5402, "step": 2650 }, { "epoch": 0.04, "learning_rate": 4.877004008016032e-05, "loss": 2.5118, "step": 2660 }, { "epoch": 0.04, "learning_rate": 4.8765030060120244e-05, "loss": 2.5273, "step": 2670 }, { "epoch": 0.04, "learning_rate": 4.8760020040080165e-05, "loss": 2.4731, "step": 2680 }, { "epoch": 0.04, "learning_rate": 4.875501002004008e-05, "loss": 2.5448, "step": 2690 }, { "epoch": 0.04, "learning_rate": 4.875e-05, "loss": 2.5127, "step": 2700 }, { "epoch": 0.04, "learning_rate": 4.874498997995992e-05, "loss": 2.426, "step": 2710 }, { "epoch": 0.04, "learning_rate": 4.873997995991984e-05, "loss": 2.5731, "step": 2720 }, { "epoch": 0.04, "learning_rate": 4.873496993987976e-05, "loss": 2.5376, "step": 2730 }, { "epoch": 0.04, "learning_rate": 4.872995991983968e-05, "loss": 2.5037, "step": 2740 }, { "epoch": 0.04, "learning_rate": 4.87249498997996e-05, "loss": 2.5453, "step": 2750 }, { "epoch": 0.05, "learning_rate": 4.871993987975952e-05, "loss": 2.5002, "step": 2760 }, { "epoch": 0.05, "learning_rate": 4.8714929859719444e-05, "loss": 2.5095, "step": 2770 }, { "epoch": 0.05, "learning_rate": 4.8709919839679364e-05, "loss": 2.5442, "step": 2780 }, { "epoch": 0.05, "learning_rate": 4.8704909819639285e-05, "loss": 2.4832, "step": 2790 }, { "epoch": 0.05, "learning_rate": 4.8699899799599206e-05, "loss": 2.4002, "step": 2800 }, { "epoch": 0.05, "learning_rate": 4.869488977955912e-05, "loss": 2.4877, "step": 2810 }, { "epoch": 0.05, "learning_rate": 4.868987975951904e-05, "loss": 2.4646, "step": 2820 }, { "epoch": 0.05, "learning_rate": 4.868486973947896e-05, "loss": 2.5375, "step": 2830 }, { "epoch": 0.05, "learning_rate": 4.867985971943888e-05, "loss": 2.5557, "step": 2840 }, { "epoch": 0.05, "learning_rate": 4.86748496993988e-05, "loss": 2.5261, "step": 2850 }, { "epoch": 0.05, "learning_rate": 4.866983967935872e-05, "loss": 2.4479, "step": 2860 }, { "epoch": 0.05, "learning_rate": 4.8664829659318636e-05, "loss": 2.4658, "step": 2870 }, { "epoch": 0.05, "learning_rate": 4.865981963927856e-05, "loss": 2.5179, "step": 2880 }, { "epoch": 0.05, "learning_rate": 4.865480961923848e-05, "loss": 2.4667, "step": 2890 }, { "epoch": 0.05, "learning_rate": 4.86497995991984e-05, "loss": 2.5317, "step": 2900 }, { "epoch": 0.05, "learning_rate": 4.864478957915832e-05, "loss": 2.5563, "step": 2910 }, { "epoch": 0.05, "learning_rate": 4.863977955911824e-05, "loss": 2.509, "step": 2920 }, { "epoch": 0.05, "learning_rate": 4.8634769539078154e-05, "loss": 2.5324, "step": 2930 }, { "epoch": 0.05, "learning_rate": 4.8629759519038074e-05, "loss": 2.4551, "step": 2940 }, { "epoch": 0.05, "learning_rate": 4.8624749498997995e-05, "loss": 2.4951, "step": 2950 }, { "epoch": 0.05, "learning_rate": 4.861973947895792e-05, "loss": 2.5164, "step": 2960 }, { "epoch": 0.05, "learning_rate": 4.861472945891784e-05, "loss": 2.3969, "step": 2970 }, { "epoch": 0.05, "learning_rate": 4.860971943887776e-05, "loss": 2.4984, "step": 2980 }, { "epoch": 0.05, "learning_rate": 4.860470941883768e-05, "loss": 2.4109, "step": 2990 }, { "epoch": 0.05, "learning_rate": 4.85996993987976e-05, "loss": 2.4807, "step": 3000 }, { "epoch": 0.05, "eval_loss": 2.4130146503448486, "eval_mean_f1": 0.5982416580033957, "eval_rouge1_f1": 0.6709952978969673, "eval_rouge1_precision": 0.7936151969233021, "eval_rouge1_recall": 0.6116548702324334, "eval_rouge2_f1": 0.4929801641663879, "eval_rouge2_precision": 0.5845350023511644, "eval_rouge2_recall": 0.45035587385581044, "eval_rougeL_f1": 0.6307495119468316, "eval_rougeL_precision": 0.7429486062025692, "eval_rougeL_recall": 0.5768914058459984, "eval_runtime": 64.8756, "eval_samples_per_second": 15.784, "eval_steps_per_second": 1.973, "step": 3000 }, { "epoch": 0.05, "learning_rate": 4.859468937875752e-05, "loss": 2.5102, "step": 3010 }, { "epoch": 0.05, "learning_rate": 4.858967935871744e-05, "loss": 2.4631, "step": 3020 }, { "epoch": 0.05, "learning_rate": 4.858466933867736e-05, "loss": 2.5518, "step": 3030 }, { "epoch": 0.05, "learning_rate": 4.857965931863728e-05, "loss": 2.4395, "step": 3040 }, { "epoch": 0.05, "learning_rate": 4.8574649298597194e-05, "loss": 2.4699, "step": 3050 }, { "epoch": 0.05, "learning_rate": 4.8569639278557115e-05, "loss": 2.5168, "step": 3060 }, { "epoch": 0.05, "learning_rate": 4.8564629258517036e-05, "loss": 2.4881, "step": 3070 }, { "epoch": 0.05, "learning_rate": 4.8559619238476956e-05, "loss": 2.51, "step": 3080 }, { "epoch": 0.05, "learning_rate": 4.855460921843688e-05, "loss": 2.5015, "step": 3090 }, { "epoch": 0.05, "learning_rate": 4.85495991983968e-05, "loss": 2.5012, "step": 3100 }, { "epoch": 0.05, "learning_rate": 4.854458917835671e-05, "loss": 2.4816, "step": 3110 }, { "epoch": 0.05, "learning_rate": 4.853957915831663e-05, "loss": 2.5128, "step": 3120 }, { "epoch": 0.05, "learning_rate": 4.853456913827655e-05, "loss": 2.5405, "step": 3130 }, { "epoch": 0.05, "learning_rate": 4.8529559118236473e-05, "loss": 2.5088, "step": 3140 }, { "epoch": 0.05, "learning_rate": 4.8524549098196394e-05, "loss": 2.4689, "step": 3150 }, { "epoch": 0.05, "learning_rate": 4.8519539078156315e-05, "loss": 2.4856, "step": 3160 }, { "epoch": 0.05, "learning_rate": 4.8514529058116235e-05, "loss": 2.467, "step": 3170 }, { "epoch": 0.05, "learning_rate": 4.8509519038076156e-05, "loss": 2.4998, "step": 3180 }, { "epoch": 0.05, "learning_rate": 4.850450901803608e-05, "loss": 2.5032, "step": 3190 }, { "epoch": 0.05, "learning_rate": 4.8499498997996e-05, "loss": 2.5049, "step": 3200 }, { "epoch": 0.05, "learning_rate": 4.849448897795592e-05, "loss": 2.3898, "step": 3210 }, { "epoch": 0.05, "learning_rate": 4.848947895791583e-05, "loss": 2.4581, "step": 3220 }, { "epoch": 0.05, "learning_rate": 4.848446893787575e-05, "loss": 2.4814, "step": 3230 }, { "epoch": 0.05, "learning_rate": 4.847945891783567e-05, "loss": 2.4702, "step": 3240 }, { "epoch": 0.05, "learning_rate": 4.8474448897795594e-05, "loss": 2.4636, "step": 3250 }, { "epoch": 0.05, "learning_rate": 4.8469438877755514e-05, "loss": 2.4756, "step": 3260 }, { "epoch": 0.05, "learning_rate": 4.8464428857715435e-05, "loss": 2.4966, "step": 3270 }, { "epoch": 0.05, "learning_rate": 4.845941883767535e-05, "loss": 2.4525, "step": 3280 }, { "epoch": 0.05, "learning_rate": 4.845440881763527e-05, "loss": 2.459, "step": 3290 }, { "epoch": 0.05, "learning_rate": 4.844939879759519e-05, "loss": 2.4823, "step": 3300 }, { "epoch": 0.05, "learning_rate": 4.844438877755511e-05, "loss": 2.3936, "step": 3310 }, { "epoch": 0.05, "learning_rate": 4.843937875751503e-05, "loss": 2.5558, "step": 3320 }, { "epoch": 0.05, "learning_rate": 4.843436873747495e-05, "loss": 2.5138, "step": 3330 }, { "epoch": 0.05, "learning_rate": 4.842935871743487e-05, "loss": 2.4949, "step": 3340 }, { "epoch": 0.05, "learning_rate": 4.842434869739479e-05, "loss": 2.4753, "step": 3350 }, { "epoch": 0.05, "learning_rate": 4.8419338677354714e-05, "loss": 2.4329, "step": 3360 }, { "epoch": 0.06, "learning_rate": 4.8414328657314635e-05, "loss": 2.5122, "step": 3370 }, { "epoch": 0.06, "learning_rate": 4.8409318637274555e-05, "loss": 2.4628, "step": 3380 }, { "epoch": 0.06, "learning_rate": 4.8404308617234476e-05, "loss": 2.4799, "step": 3390 }, { "epoch": 0.06, "learning_rate": 4.839929859719439e-05, "loss": 2.4614, "step": 3400 }, { "epoch": 0.06, "learning_rate": 4.839428857715431e-05, "loss": 2.4327, "step": 3410 }, { "epoch": 0.06, "learning_rate": 4.838927855711423e-05, "loss": 2.5031, "step": 3420 }, { "epoch": 0.06, "learning_rate": 4.838426853707415e-05, "loss": 2.4433, "step": 3430 }, { "epoch": 0.06, "learning_rate": 4.837925851703407e-05, "loss": 2.4474, "step": 3440 }, { "epoch": 0.06, "learning_rate": 4.837424849699399e-05, "loss": 2.4642, "step": 3450 }, { "epoch": 0.06, "learning_rate": 4.836923847695391e-05, "loss": 2.4863, "step": 3460 }, { "epoch": 0.06, "learning_rate": 4.836422845691383e-05, "loss": 2.49, "step": 3470 }, { "epoch": 0.06, "learning_rate": 4.835921843687375e-05, "loss": 2.4462, "step": 3480 }, { "epoch": 0.06, "learning_rate": 4.835420841683367e-05, "loss": 2.4221, "step": 3490 }, { "epoch": 0.06, "learning_rate": 4.834919839679359e-05, "loss": 2.403, "step": 3500 }, { "epoch": 0.06, "learning_rate": 4.834418837675351e-05, "loss": 2.4557, "step": 3510 }, { "epoch": 0.06, "learning_rate": 4.8339178356713424e-05, "loss": 2.5178, "step": 3520 }, { "epoch": 0.06, "learning_rate": 4.8334168336673345e-05, "loss": 2.4574, "step": 3530 }, { "epoch": 0.06, "learning_rate": 4.8329158316633265e-05, "loss": 2.4695, "step": 3540 }, { "epoch": 0.06, "learning_rate": 4.832414829659319e-05, "loss": 2.4354, "step": 3550 }, { "epoch": 0.06, "learning_rate": 4.831913827655311e-05, "loss": 2.4857, "step": 3560 }, { "epoch": 0.06, "learning_rate": 4.831412825651303e-05, "loss": 2.4246, "step": 3570 }, { "epoch": 0.06, "learning_rate": 4.830911823647295e-05, "loss": 2.4608, "step": 3580 }, { "epoch": 0.06, "learning_rate": 4.830410821643287e-05, "loss": 2.4055, "step": 3590 }, { "epoch": 0.06, "learning_rate": 4.829909819639279e-05, "loss": 2.4416, "step": 3600 }, { "epoch": 0.06, "learning_rate": 4.829408817635271e-05, "loss": 2.4585, "step": 3610 }, { "epoch": 0.06, "learning_rate": 4.828907815631263e-05, "loss": 2.429, "step": 3620 }, { "epoch": 0.06, "learning_rate": 4.828406813627255e-05, "loss": 2.4596, "step": 3630 }, { "epoch": 0.06, "learning_rate": 4.8279058116232465e-05, "loss": 2.4549, "step": 3640 }, { "epoch": 0.06, "learning_rate": 4.8274048096192386e-05, "loss": 2.5268, "step": 3650 }, { "epoch": 0.06, "learning_rate": 4.8269038076152306e-05, "loss": 2.4719, "step": 3660 }, { "epoch": 0.06, "learning_rate": 4.826402805611223e-05, "loss": 2.4212, "step": 3670 }, { "epoch": 0.06, "learning_rate": 4.825901803607215e-05, "loss": 2.441, "step": 3680 }, { "epoch": 0.06, "learning_rate": 4.825400801603207e-05, "loss": 2.4399, "step": 3690 }, { "epoch": 0.06, "learning_rate": 4.824899799599198e-05, "loss": 2.4786, "step": 3700 }, { "epoch": 0.06, "learning_rate": 4.82439879759519e-05, "loss": 2.4063, "step": 3710 }, { "epoch": 0.06, "learning_rate": 4.823897795591182e-05, "loss": 2.4672, "step": 3720 }, { "epoch": 0.06, "learning_rate": 4.8233967935871744e-05, "loss": 2.4205, "step": 3730 }, { "epoch": 0.06, "learning_rate": 4.8228957915831664e-05, "loss": 2.3859, "step": 3740 }, { "epoch": 0.06, "learning_rate": 4.8223947895791585e-05, "loss": 2.3989, "step": 3750 }, { "epoch": 0.06, "learning_rate": 4.8218937875751506e-05, "loss": 2.5284, "step": 3760 }, { "epoch": 0.06, "learning_rate": 4.8213927855711426e-05, "loss": 2.4836, "step": 3770 }, { "epoch": 0.06, "learning_rate": 4.820891783567135e-05, "loss": 2.459, "step": 3780 }, { "epoch": 0.06, "learning_rate": 4.820390781563127e-05, "loss": 2.4517, "step": 3790 }, { "epoch": 0.06, "learning_rate": 4.819889779559119e-05, "loss": 2.4191, "step": 3800 }, { "epoch": 0.06, "learning_rate": 4.81938877755511e-05, "loss": 2.4303, "step": 3810 }, { "epoch": 0.06, "learning_rate": 4.818887775551102e-05, "loss": 2.4827, "step": 3820 }, { "epoch": 0.06, "learning_rate": 4.8183867735470943e-05, "loss": 2.4384, "step": 3830 }, { "epoch": 0.06, "learning_rate": 4.8178857715430864e-05, "loss": 2.4342, "step": 3840 }, { "epoch": 0.06, "learning_rate": 4.8173847695390785e-05, "loss": 2.4747, "step": 3850 }, { "epoch": 0.06, "learning_rate": 4.8168837675350705e-05, "loss": 2.4653, "step": 3860 }, { "epoch": 0.06, "learning_rate": 4.8163827655310626e-05, "loss": 2.4412, "step": 3870 }, { "epoch": 0.06, "learning_rate": 4.815881763527054e-05, "loss": 2.432, "step": 3880 }, { "epoch": 0.06, "learning_rate": 4.815380761523046e-05, "loss": 2.4508, "step": 3890 }, { "epoch": 0.06, "learning_rate": 4.814879759519038e-05, "loss": 2.4565, "step": 3900 }, { "epoch": 0.06, "learning_rate": 4.81437875751503e-05, "loss": 2.4462, "step": 3910 }, { "epoch": 0.06, "learning_rate": 4.813877755511022e-05, "loss": 2.4242, "step": 3920 }, { "epoch": 0.06, "learning_rate": 4.813376753507014e-05, "loss": 2.4416, "step": 3930 }, { "epoch": 0.06, "learning_rate": 4.8128757515030064e-05, "loss": 2.3934, "step": 3940 }, { "epoch": 0.06, "learning_rate": 4.8123747494989984e-05, "loss": 2.4117, "step": 3950 }, { "epoch": 0.06, "learning_rate": 4.8118737474949905e-05, "loss": 2.4418, "step": 3960 }, { "epoch": 0.06, "learning_rate": 4.8113727454909826e-05, "loss": 2.4251, "step": 3970 }, { "epoch": 0.07, "learning_rate": 4.8108717434869746e-05, "loss": 2.4815, "step": 3980 }, { "epoch": 0.07, "learning_rate": 4.810370741482966e-05, "loss": 2.3995, "step": 3990 }, { "epoch": 0.07, "learning_rate": 4.809869739478958e-05, "loss": 2.4042, "step": 4000 }, { "epoch": 0.07, "eval_loss": 2.357759952545166, "eval_mean_f1": 0.6059921217034665, "eval_rouge1_f1": 0.675753235522248, "eval_rouge1_precision": 0.7977177508714739, "eval_rouge1_recall": 0.6168099835899039, "eval_rouge2_f1": 0.5032966943059054, "eval_rouge2_precision": 0.5977353572263241, "eval_rouge2_recall": 0.45969802469597976, "eval_rougeL_f1": 0.6389264352822462, "eval_rougeL_precision": 0.7517844142603591, "eval_rougeL_recall": 0.5847067898728895, "eval_runtime": 65.0157, "eval_samples_per_second": 15.75, "eval_steps_per_second": 1.969, "step": 4000 }, { "epoch": 0.07, "learning_rate": 4.80936873747495e-05, "loss": 2.4178, "step": 4010 }, { "epoch": 0.07, "learning_rate": 4.808867735470942e-05, "loss": 2.472, "step": 4020 }, { "epoch": 0.07, "learning_rate": 4.808366733466934e-05, "loss": 2.4334, "step": 4030 }, { "epoch": 0.07, "learning_rate": 4.8078657314629263e-05, "loss": 2.4526, "step": 4040 }, { "epoch": 0.07, "learning_rate": 4.807364729458918e-05, "loss": 2.4614, "step": 4050 }, { "epoch": 0.07, "learning_rate": 4.80686372745491e-05, "loss": 2.4575, "step": 4060 }, { "epoch": 0.07, "learning_rate": 4.806362725450902e-05, "loss": 2.4271, "step": 4070 }, { "epoch": 0.07, "learning_rate": 4.805861723446894e-05, "loss": 2.4186, "step": 4080 }, { "epoch": 0.07, "learning_rate": 4.805360721442886e-05, "loss": 2.3904, "step": 4090 }, { "epoch": 0.07, "learning_rate": 4.804859719438878e-05, "loss": 2.3967, "step": 4100 }, { "epoch": 0.07, "learning_rate": 4.8043587174348694e-05, "loss": 2.4329, "step": 4110 }, { "epoch": 0.07, "learning_rate": 4.8038577154308615e-05, "loss": 2.4138, "step": 4120 }, { "epoch": 0.07, "learning_rate": 4.8033567134268536e-05, "loss": 2.3944, "step": 4130 }, { "epoch": 0.07, "learning_rate": 4.802855711422846e-05, "loss": 2.4378, "step": 4140 }, { "epoch": 0.07, "learning_rate": 4.8023547094188384e-05, "loss": 2.4613, "step": 4150 }, { "epoch": 0.07, "learning_rate": 4.80185370741483e-05, "loss": 2.4103, "step": 4160 }, { "epoch": 0.07, "learning_rate": 4.801352705410822e-05, "loss": 2.388, "step": 4170 }, { "epoch": 0.07, "learning_rate": 4.800851703406814e-05, "loss": 2.4049, "step": 4180 }, { "epoch": 0.07, "learning_rate": 4.800350701402806e-05, "loss": 2.3987, "step": 4190 }, { "epoch": 0.07, "learning_rate": 4.799849699398798e-05, "loss": 2.4223, "step": 4200 }, { "epoch": 0.07, "learning_rate": 4.79934869739479e-05, "loss": 2.4382, "step": 4210 }, { "epoch": 0.07, "learning_rate": 4.798847695390782e-05, "loss": 2.4383, "step": 4220 }, { "epoch": 0.07, "learning_rate": 4.7983466933867735e-05, "loss": 2.392, "step": 4230 }, { "epoch": 0.07, "learning_rate": 4.7978456913827656e-05, "loss": 2.4274, "step": 4240 }, { "epoch": 0.07, "learning_rate": 4.7973446893787577e-05, "loss": 2.4375, "step": 4250 }, { "epoch": 0.07, "learning_rate": 4.79684368737475e-05, "loss": 2.4222, "step": 4260 }, { "epoch": 0.07, "learning_rate": 4.796342685370742e-05, "loss": 2.4143, "step": 4270 }, { "epoch": 0.07, "learning_rate": 4.795841683366734e-05, "loss": 2.4395, "step": 4280 }, { "epoch": 0.07, "learning_rate": 4.795340681362725e-05, "loss": 2.4968, "step": 4290 }, { "epoch": 0.07, "learning_rate": 4.794839679358717e-05, "loss": 2.4348, "step": 4300 }, { "epoch": 0.07, "learning_rate": 4.7943386773547094e-05, "loss": 2.4002, "step": 4310 }, { "epoch": 0.07, "learning_rate": 4.7938376753507014e-05, "loss": 2.4624, "step": 4320 }, { "epoch": 0.07, "learning_rate": 4.7933366733466935e-05, "loss": 2.4808, "step": 4330 }, { "epoch": 0.07, "learning_rate": 4.7928356713426856e-05, "loss": 2.3858, "step": 4340 }, { "epoch": 0.07, "learning_rate": 4.7923346693386776e-05, "loss": 2.4232, "step": 4350 }, { "epoch": 0.07, "learning_rate": 4.79183366733467e-05, "loss": 2.4267, "step": 4360 }, { "epoch": 0.07, "learning_rate": 4.791332665330662e-05, "loss": 2.4362, "step": 4370 }, { "epoch": 0.07, "learning_rate": 4.790831663326654e-05, "loss": 2.4148, "step": 4380 }, { "epoch": 0.07, "learning_rate": 4.790330661322646e-05, "loss": 2.4135, "step": 4390 }, { "epoch": 0.07, "learning_rate": 4.789829659318637e-05, "loss": 2.4228, "step": 4400 }, { "epoch": 0.07, "learning_rate": 4.789328657314629e-05, "loss": 2.43, "step": 4410 }, { "epoch": 0.07, "learning_rate": 4.7888276553106214e-05, "loss": 2.4145, "step": 4420 }, { "epoch": 0.07, "learning_rate": 4.7883266533066135e-05, "loss": 2.3932, "step": 4430 }, { "epoch": 0.07, "learning_rate": 4.7878256513026055e-05, "loss": 2.3921, "step": 4440 }, { "epoch": 0.07, "learning_rate": 4.7873246492985976e-05, "loss": 2.4091, "step": 4450 }, { "epoch": 0.07, "learning_rate": 4.7868236472945896e-05, "loss": 2.4416, "step": 4460 }, { "epoch": 0.07, "learning_rate": 4.786322645290581e-05, "loss": 2.43, "step": 4470 }, { "epoch": 0.07, "learning_rate": 4.785821643286573e-05, "loss": 2.3768, "step": 4480 }, { "epoch": 0.07, "learning_rate": 4.785320641282565e-05, "loss": 2.3564, "step": 4490 }, { "epoch": 0.07, "learning_rate": 4.784819639278557e-05, "loss": 2.4113, "step": 4500 }, { "epoch": 0.07, "learning_rate": 4.784318637274549e-05, "loss": 2.3986, "step": 4510 }, { "epoch": 0.07, "learning_rate": 4.7838176352705414e-05, "loss": 2.4218, "step": 4520 }, { "epoch": 0.07, "learning_rate": 4.7833166332665334e-05, "loss": 2.413, "step": 4530 }, { "epoch": 0.07, "learning_rate": 4.7828156312625255e-05, "loss": 2.433, "step": 4540 }, { "epoch": 0.07, "learning_rate": 4.7823146292585175e-05, "loss": 2.4031, "step": 4550 }, { "epoch": 0.07, "learning_rate": 4.7818136272545096e-05, "loss": 2.4245, "step": 4560 }, { "epoch": 0.07, "learning_rate": 4.781312625250502e-05, "loss": 2.3851, "step": 4570 }, { "epoch": 0.07, "learning_rate": 4.780811623246493e-05, "loss": 2.4389, "step": 4580 }, { "epoch": 0.07, "learning_rate": 4.780310621242485e-05, "loss": 2.4145, "step": 4590 }, { "epoch": 0.08, "learning_rate": 4.779809619238477e-05, "loss": 2.4143, "step": 4600 }, { "epoch": 0.08, "learning_rate": 4.779308617234469e-05, "loss": 2.4583, "step": 4610 }, { "epoch": 0.08, "learning_rate": 4.778807615230461e-05, "loss": 2.4144, "step": 4620 }, { "epoch": 0.08, "learning_rate": 4.7783066132264534e-05, "loss": 2.4696, "step": 4630 }, { "epoch": 0.08, "learning_rate": 4.777805611222445e-05, "loss": 2.4284, "step": 4640 }, { "epoch": 0.08, "learning_rate": 4.777304609218437e-05, "loss": 2.3698, "step": 4650 }, { "epoch": 0.08, "learning_rate": 4.776803607214429e-05, "loss": 2.4549, "step": 4660 }, { "epoch": 0.08, "learning_rate": 4.776302605210421e-05, "loss": 2.458, "step": 4670 }, { "epoch": 0.08, "learning_rate": 4.775801603206413e-05, "loss": 2.367, "step": 4680 }, { "epoch": 0.08, "learning_rate": 4.775300601202405e-05, "loss": 2.3995, "step": 4690 }, { "epoch": 0.08, "learning_rate": 4.7747995991983965e-05, "loss": 2.3805, "step": 4700 }, { "epoch": 0.08, "learning_rate": 4.7742985971943885e-05, "loss": 2.4092, "step": 4710 }, { "epoch": 0.08, "learning_rate": 4.7737975951903806e-05, "loss": 2.4117, "step": 4720 }, { "epoch": 0.08, "learning_rate": 4.7732965931863733e-05, "loss": 2.3589, "step": 4730 }, { "epoch": 0.08, "learning_rate": 4.7727955911823654e-05, "loss": 2.3318, "step": 4740 }, { "epoch": 0.08, "learning_rate": 4.7722945891783575e-05, "loss": 2.3629, "step": 4750 }, { "epoch": 0.08, "learning_rate": 4.771793587174349e-05, "loss": 2.3941, "step": 4760 }, { "epoch": 0.08, "learning_rate": 4.771292585170341e-05, "loss": 2.38, "step": 4770 }, { "epoch": 0.08, "learning_rate": 4.770791583166333e-05, "loss": 2.3942, "step": 4780 }, { "epoch": 0.08, "learning_rate": 4.770290581162325e-05, "loss": 2.4225, "step": 4790 }, { "epoch": 0.08, "learning_rate": 4.769789579158317e-05, "loss": 2.3299, "step": 4800 }, { "epoch": 0.08, "learning_rate": 4.769288577154309e-05, "loss": 2.4128, "step": 4810 }, { "epoch": 0.08, "learning_rate": 4.7687875751503006e-05, "loss": 2.4015, "step": 4820 }, { "epoch": 0.08, "learning_rate": 4.7682865731462926e-05, "loss": 2.3897, "step": 4830 }, { "epoch": 0.08, "learning_rate": 4.767785571142285e-05, "loss": 2.4221, "step": 4840 }, { "epoch": 0.08, "learning_rate": 4.767284569138277e-05, "loss": 2.417, "step": 4850 }, { "epoch": 0.08, "learning_rate": 4.766783567134269e-05, "loss": 2.3757, "step": 4860 }, { "epoch": 0.08, "learning_rate": 4.766282565130261e-05, "loss": 2.4878, "step": 4870 }, { "epoch": 0.08, "learning_rate": 4.765781563126252e-05, "loss": 2.3801, "step": 4880 }, { "epoch": 0.08, "learning_rate": 4.765280561122244e-05, "loss": 2.3377, "step": 4890 }, { "epoch": 0.08, "learning_rate": 4.7647795591182364e-05, "loss": 2.3853, "step": 4900 }, { "epoch": 0.08, "learning_rate": 4.7642785571142285e-05, "loss": 2.3838, "step": 4910 }, { "epoch": 0.08, "learning_rate": 4.763777555110221e-05, "loss": 2.4186, "step": 4920 }, { "epoch": 0.08, "learning_rate": 4.7632765531062126e-05, "loss": 2.3797, "step": 4930 }, { "epoch": 0.08, "learning_rate": 4.7627755511022047e-05, "loss": 2.4675, "step": 4940 }, { "epoch": 0.08, "learning_rate": 4.762274549098197e-05, "loss": 2.362, "step": 4950 }, { "epoch": 0.08, "learning_rate": 4.761773547094189e-05, "loss": 2.3864, "step": 4960 }, { "epoch": 0.08, "learning_rate": 4.761272545090181e-05, "loss": 2.4123, "step": 4970 }, { "epoch": 0.08, "learning_rate": 4.760771543086173e-05, "loss": 2.4174, "step": 4980 }, { "epoch": 0.08, "learning_rate": 4.760270541082164e-05, "loss": 2.4277, "step": 4990 }, { "epoch": 0.08, "learning_rate": 4.7597695390781564e-05, "loss": 2.4079, "step": 5000 }, { "epoch": 0.08, "eval_loss": 2.3347973823547363, "eval_mean_f1": 0.6104320618080453, "eval_rouge1_f1": 0.678230713008188, "eval_rouge1_precision": 0.7982847274333231, "eval_rouge1_recall": 0.6190121410672462, "eval_rouge2_f1": 0.509728887971479, "eval_rouge2_precision": 0.601797673355291, "eval_rouge2_recall": 0.46591584725486707, "eval_rougeL_f1": 0.6433365844444688, "eval_rougeL_precision": 0.7553177949421779, "eval_rougeL_recall": 0.5885239726417933, "eval_runtime": 63.9601, "eval_samples_per_second": 16.01, "eval_steps_per_second": 2.001, "step": 5000 }, { "epoch": 0.08, "learning_rate": 4.7592685370741484e-05, "loss": 2.452, "step": 5010 }, { "epoch": 0.08, "learning_rate": 4.7587675350701405e-05, "loss": 2.4035, "step": 5020 }, { "epoch": 0.08, "learning_rate": 4.7582665330661326e-05, "loss": 2.3602, "step": 5030 }, { "epoch": 0.08, "learning_rate": 4.7577655310621246e-05, "loss": 2.4143, "step": 5040 }, { "epoch": 0.08, "learning_rate": 4.757264529058117e-05, "loss": 2.3963, "step": 5050 }, { "epoch": 0.08, "learning_rate": 4.756763527054108e-05, "loss": 2.4434, "step": 5060 }, { "epoch": 0.08, "learning_rate": 4.7562625250501e-05, "loss": 2.409, "step": 5070 }, { "epoch": 0.08, "learning_rate": 4.755761523046092e-05, "loss": 2.3944, "step": 5080 }, { "epoch": 0.08, "learning_rate": 4.755260521042084e-05, "loss": 2.3268, "step": 5090 }, { "epoch": 0.08, "learning_rate": 4.754759519038076e-05, "loss": 2.4097, "step": 5100 }, { "epoch": 0.08, "learning_rate": 4.7542585170340684e-05, "loss": 2.3888, "step": 5110 }, { "epoch": 0.08, "learning_rate": 4.7537575150300605e-05, "loss": 2.4137, "step": 5120 }, { "epoch": 0.08, "learning_rate": 4.7532565130260525e-05, "loss": 2.4235, "step": 5130 }, { "epoch": 0.08, "learning_rate": 4.7527555110220446e-05, "loss": 2.4075, "step": 5140 }, { "epoch": 0.08, "learning_rate": 4.7522545090180367e-05, "loss": 2.3796, "step": 5150 }, { "epoch": 0.08, "learning_rate": 4.751753507014029e-05, "loss": 2.3674, "step": 5160 }, { "epoch": 0.08, "learning_rate": 4.75125250501002e-05, "loss": 2.3957, "step": 5170 }, { "epoch": 0.08, "learning_rate": 4.750751503006012e-05, "loss": 2.3603, "step": 5180 }, { "epoch": 0.08, "learning_rate": 4.750250501002004e-05, "loss": 2.3989, "step": 5190 }, { "epoch": 0.08, "learning_rate": 4.749749498997996e-05, "loss": 2.3591, "step": 5200 }, { "epoch": 0.09, "learning_rate": 4.7492484969939884e-05, "loss": 2.3262, "step": 5210 }, { "epoch": 0.09, "learning_rate": 4.7487474949899804e-05, "loss": 2.3741, "step": 5220 }, { "epoch": 0.09, "learning_rate": 4.748246492985972e-05, "loss": 2.4285, "step": 5230 }, { "epoch": 0.09, "learning_rate": 4.747745490981964e-05, "loss": 2.3852, "step": 5240 }, { "epoch": 0.09, "learning_rate": 4.747244488977956e-05, "loss": 2.3482, "step": 5250 }, { "epoch": 0.09, "learning_rate": 4.746743486973948e-05, "loss": 2.3822, "step": 5260 }, { "epoch": 0.09, "learning_rate": 4.74624248496994e-05, "loss": 2.3962, "step": 5270 }, { "epoch": 0.09, "learning_rate": 4.745741482965932e-05, "loss": 2.3936, "step": 5280 }, { "epoch": 0.09, "learning_rate": 4.745240480961924e-05, "loss": 2.3426, "step": 5290 }, { "epoch": 0.09, "learning_rate": 4.7447394789579156e-05, "loss": 2.3973, "step": 5300 }, { "epoch": 0.09, "learning_rate": 4.7442384769539076e-05, "loss": 2.4154, "step": 5310 }, { "epoch": 0.09, "learning_rate": 4.7437374749499004e-05, "loss": 2.3704, "step": 5320 }, { "epoch": 0.09, "learning_rate": 4.7432364729458924e-05, "loss": 2.3578, "step": 5330 }, { "epoch": 0.09, "learning_rate": 4.7427354709418845e-05, "loss": 2.3808, "step": 5340 }, { "epoch": 0.09, "learning_rate": 4.742234468937876e-05, "loss": 2.369, "step": 5350 }, { "epoch": 0.09, "learning_rate": 4.741733466933868e-05, "loss": 2.3881, "step": 5360 }, { "epoch": 0.09, "learning_rate": 4.74123246492986e-05, "loss": 2.4227, "step": 5370 }, { "epoch": 0.09, "learning_rate": 4.740731462925852e-05, "loss": 2.3489, "step": 5380 }, { "epoch": 0.09, "learning_rate": 4.740230460921844e-05, "loss": 2.3474, "step": 5390 }, { "epoch": 0.09, "learning_rate": 4.739729458917836e-05, "loss": 2.3215, "step": 5400 }, { "epoch": 0.09, "learning_rate": 4.7392284569138276e-05, "loss": 2.3365, "step": 5410 }, { "epoch": 0.09, "learning_rate": 4.73872745490982e-05, "loss": 2.3951, "step": 5420 }, { "epoch": 0.09, "learning_rate": 4.738226452905812e-05, "loss": 2.4045, "step": 5430 }, { "epoch": 0.09, "learning_rate": 4.737725450901804e-05, "loss": 2.4672, "step": 5440 }, { "epoch": 0.09, "learning_rate": 4.737224448897796e-05, "loss": 2.3724, "step": 5450 }, { "epoch": 0.09, "learning_rate": 4.736723446893788e-05, "loss": 2.3928, "step": 5460 }, { "epoch": 0.09, "learning_rate": 4.736222444889779e-05, "loss": 2.3992, "step": 5470 }, { "epoch": 0.09, "learning_rate": 4.7357214428857714e-05, "loss": 2.3534, "step": 5480 }, { "epoch": 0.09, "learning_rate": 4.7352204408817634e-05, "loss": 2.3402, "step": 5490 }, { "epoch": 0.09, "learning_rate": 4.7347194388777555e-05, "loss": 2.4034, "step": 5500 }, { "epoch": 0.09, "learning_rate": 4.734218436873748e-05, "loss": 2.4062, "step": 5510 }, { "epoch": 0.09, "learning_rate": 4.7337174348697396e-05, "loss": 2.3196, "step": 5520 }, { "epoch": 0.09, "learning_rate": 4.733216432865732e-05, "loss": 2.3594, "step": 5530 }, { "epoch": 0.09, "learning_rate": 4.732715430861724e-05, "loss": 2.383, "step": 5540 }, { "epoch": 0.09, "learning_rate": 4.732214428857716e-05, "loss": 2.3452, "step": 5550 }, { "epoch": 0.09, "learning_rate": 4.731713426853708e-05, "loss": 2.3589, "step": 5560 }, { "epoch": 0.09, "learning_rate": 4.7312124248497e-05, "loss": 2.3315, "step": 5570 }, { "epoch": 0.09, "learning_rate": 4.730711422845692e-05, "loss": 2.3458, "step": 5580 }, { "epoch": 0.09, "learning_rate": 4.7302104208416834e-05, "loss": 2.3653, "step": 5590 }, { "epoch": 0.09, "learning_rate": 4.7297094188376755e-05, "loss": 2.3768, "step": 5600 }, { "epoch": 0.09, "learning_rate": 4.7292084168336675e-05, "loss": 2.3435, "step": 5610 }, { "epoch": 0.09, "learning_rate": 4.7287074148296596e-05, "loss": 2.4285, "step": 5620 }, { "epoch": 0.09, "learning_rate": 4.728206412825652e-05, "loss": 2.3881, "step": 5630 }, { "epoch": 0.09, "learning_rate": 4.727705410821644e-05, "loss": 2.3798, "step": 5640 }, { "epoch": 0.09, "learning_rate": 4.727204408817635e-05, "loss": 2.3774, "step": 5650 }, { "epoch": 0.09, "learning_rate": 4.726703406813627e-05, "loss": 2.3862, "step": 5660 }, { "epoch": 0.09, "learning_rate": 4.726202404809619e-05, "loss": 2.3818, "step": 5670 }, { "epoch": 0.09, "learning_rate": 4.725701402805611e-05, "loss": 2.3108, "step": 5680 }, { "epoch": 0.09, "learning_rate": 4.7252004008016034e-05, "loss": 2.3915, "step": 5690 }, { "epoch": 0.09, "learning_rate": 4.7246993987975954e-05, "loss": 2.378, "step": 5700 }, { "epoch": 0.09, "learning_rate": 4.7241983967935875e-05, "loss": 2.3891, "step": 5710 }, { "epoch": 0.09, "learning_rate": 4.7236973947895796e-05, "loss": 2.3549, "step": 5720 }, { "epoch": 0.09, "learning_rate": 4.7231963927855716e-05, "loss": 2.3583, "step": 5730 }, { "epoch": 0.09, "learning_rate": 4.722695390781564e-05, "loss": 2.3356, "step": 5740 }, { "epoch": 0.09, "learning_rate": 4.722194388777556e-05, "loss": 2.3655, "step": 5750 }, { "epoch": 0.09, "learning_rate": 4.721693386773547e-05, "loss": 2.3489, "step": 5760 }, { "epoch": 0.09, "learning_rate": 4.721192384769539e-05, "loss": 2.3858, "step": 5770 }, { "epoch": 0.09, "learning_rate": 4.720691382765531e-05, "loss": 2.3579, "step": 5780 }, { "epoch": 0.09, "learning_rate": 4.720190380761523e-05, "loss": 2.3849, "step": 5790 }, { "epoch": 0.09, "learning_rate": 4.7196893787575154e-05, "loss": 2.3611, "step": 5800 }, { "epoch": 0.09, "learning_rate": 4.7191883767535075e-05, "loss": 2.3806, "step": 5810 }, { "epoch": 0.1, "learning_rate": 4.718687374749499e-05, "loss": 2.385, "step": 5820 }, { "epoch": 0.1, "learning_rate": 4.718186372745491e-05, "loss": 2.3403, "step": 5830 }, { "epoch": 0.1, "learning_rate": 4.717685370741483e-05, "loss": 2.428, "step": 5840 }, { "epoch": 0.1, "learning_rate": 4.717184368737475e-05, "loss": 2.3313, "step": 5850 }, { "epoch": 0.1, "learning_rate": 4.716683366733467e-05, "loss": 2.3683, "step": 5860 }, { "epoch": 0.1, "learning_rate": 4.716182364729459e-05, "loss": 2.3749, "step": 5870 }, { "epoch": 0.1, "learning_rate": 4.715681362725451e-05, "loss": 2.3599, "step": 5880 }, { "epoch": 0.1, "learning_rate": 4.7151803607214426e-05, "loss": 2.3286, "step": 5890 }, { "epoch": 0.1, "learning_rate": 4.714679358717435e-05, "loss": 2.3166, "step": 5900 }, { "epoch": 0.1, "learning_rate": 4.7141783567134274e-05, "loss": 2.3183, "step": 5910 }, { "epoch": 0.1, "learning_rate": 4.7136773547094195e-05, "loss": 2.392, "step": 5920 }, { "epoch": 0.1, "learning_rate": 4.7131763527054116e-05, "loss": 2.3355, "step": 5930 }, { "epoch": 0.1, "learning_rate": 4.712675350701403e-05, "loss": 2.3891, "step": 5940 }, { "epoch": 0.1, "learning_rate": 4.712174348697395e-05, "loss": 2.3267, "step": 5950 }, { "epoch": 0.1, "learning_rate": 4.711673346693387e-05, "loss": 2.3455, "step": 5960 }, { "epoch": 0.1, "learning_rate": 4.711172344689379e-05, "loss": 2.31, "step": 5970 }, { "epoch": 0.1, "learning_rate": 4.710671342685371e-05, "loss": 2.3519, "step": 5980 }, { "epoch": 0.1, "learning_rate": 4.710170340681363e-05, "loss": 2.343, "step": 5990 }, { "epoch": 0.1, "learning_rate": 4.7096693386773546e-05, "loss": 2.3695, "step": 6000 }, { "epoch": 0.1, "eval_loss": 2.2929821014404297, "eval_mean_f1": 0.6126369696446977, "eval_rouge1_f1": 0.6783148516281083, "eval_rouge1_precision": 0.7909221736969763, "eval_rouge1_recall": 0.6266004861858132, "eval_rouge2_f1": 0.5160047473613254, "eval_rouge2_precision": 0.6048655588389467, "eval_rouge2_recall": 0.4767430958594298, "eval_rougeL_f1": 0.6435913099446594, "eval_rougeL_precision": 0.7481687584844181, "eval_rougeL_recall": 0.5953048058135428, "eval_runtime": 64.5368, "eval_samples_per_second": 15.867, "eval_steps_per_second": 1.983, "step": 6000 }, { "epoch": 0.1, "learning_rate": 4.709168336673347e-05, "loss": 2.2761, "step": 6010 }, { "epoch": 0.1, "learning_rate": 4.708667334669339e-05, "loss": 2.3466, "step": 6020 }, { "epoch": 0.1, "learning_rate": 4.708166332665331e-05, "loss": 2.3656, "step": 6030 }, { "epoch": 0.1, "learning_rate": 4.707665330661323e-05, "loss": 2.3551, "step": 6040 }, { "epoch": 0.1, "learning_rate": 4.707164328657315e-05, "loss": 2.3558, "step": 6050 }, { "epoch": 0.1, "learning_rate": 4.7066633266533064e-05, "loss": 2.3888, "step": 6060 }, { "epoch": 0.1, "learning_rate": 4.7061623246492984e-05, "loss": 2.3439, "step": 6070 }, { "epoch": 0.1, "learning_rate": 4.7056613226452905e-05, "loss": 2.3649, "step": 6080 }, { "epoch": 0.1, "learning_rate": 4.7051603206412825e-05, "loss": 2.3479, "step": 6090 }, { "epoch": 0.1, "learning_rate": 4.704659318637275e-05, "loss": 2.3581, "step": 6100 }, { "epoch": 0.1, "learning_rate": 4.704158316633267e-05, "loss": 2.3478, "step": 6110 }, { "epoch": 0.1, "learning_rate": 4.703657314629259e-05, "loss": 2.2943, "step": 6120 }, { "epoch": 0.1, "learning_rate": 4.703156312625251e-05, "loss": 2.3747, "step": 6130 }, { "epoch": 0.1, "learning_rate": 4.702655310621243e-05, "loss": 2.3579, "step": 6140 }, { "epoch": 0.1, "learning_rate": 4.702154308617235e-05, "loss": 2.3306, "step": 6150 }, { "epoch": 0.1, "learning_rate": 4.701653306613227e-05, "loss": 2.3428, "step": 6160 }, { "epoch": 0.1, "learning_rate": 4.701152304609219e-05, "loss": 2.3623, "step": 6170 }, { "epoch": 0.1, "learning_rate": 4.7006513026052104e-05, "loss": 2.3408, "step": 6180 }, { "epoch": 0.1, "learning_rate": 4.7001503006012025e-05, "loss": 2.3609, "step": 6190 }, { "epoch": 0.1, "learning_rate": 4.6996492985971946e-05, "loss": 2.335, "step": 6200 }, { "epoch": 0.1, "learning_rate": 4.6991482965931866e-05, "loss": 2.3496, "step": 6210 }, { "epoch": 0.1, "learning_rate": 4.698647294589179e-05, "loss": 2.3305, "step": 6220 }, { "epoch": 0.1, "learning_rate": 4.698146292585171e-05, "loss": 2.3413, "step": 6230 }, { "epoch": 0.1, "learning_rate": 4.697645290581162e-05, "loss": 2.3305, "step": 6240 }, { "epoch": 0.1, "learning_rate": 4.697144288577154e-05, "loss": 2.2859, "step": 6250 }, { "epoch": 0.1, "learning_rate": 4.696643286573146e-05, "loss": 2.3555, "step": 6260 }, { "epoch": 0.1, "learning_rate": 4.6961422845691383e-05, "loss": 2.3306, "step": 6270 }, { "epoch": 0.1, "learning_rate": 4.6956412825651304e-05, "loss": 2.3352, "step": 6280 }, { "epoch": 0.1, "learning_rate": 4.6951402805611225e-05, "loss": 2.3428, "step": 6290 }, { "epoch": 0.1, "learning_rate": 4.6946392785571145e-05, "loss": 2.374, "step": 6300 }, { "epoch": 0.1, "learning_rate": 4.6941382765531066e-05, "loss": 2.325, "step": 6310 }, { "epoch": 0.1, "learning_rate": 4.693637274549099e-05, "loss": 2.3237, "step": 6320 }, { "epoch": 0.1, "learning_rate": 4.693136272545091e-05, "loss": 2.3262, "step": 6330 }, { "epoch": 0.1, "learning_rate": 4.692635270541083e-05, "loss": 2.3576, "step": 6340 }, { "epoch": 0.1, "learning_rate": 4.692134268537074e-05, "loss": 2.3317, "step": 6350 }, { "epoch": 0.1, "learning_rate": 4.691633266533066e-05, "loss": 2.2936, "step": 6360 }, { "epoch": 0.1, "learning_rate": 4.691132264529058e-05, "loss": 2.3478, "step": 6370 }, { "epoch": 0.1, "learning_rate": 4.6906312625250504e-05, "loss": 2.33, "step": 6380 }, { "epoch": 0.1, "learning_rate": 4.6901302605210424e-05, "loss": 2.3438, "step": 6390 }, { "epoch": 0.1, "learning_rate": 4.6896292585170345e-05, "loss": 2.3079, "step": 6400 }, { "epoch": 0.1, "learning_rate": 4.6891282565130266e-05, "loss": 2.3738, "step": 6410 }, { "epoch": 0.1, "learning_rate": 4.688627254509018e-05, "loss": 2.3122, "step": 6420 }, { "epoch": 0.11, "learning_rate": 4.68812625250501e-05, "loss": 2.3504, "step": 6430 }, { "epoch": 0.11, "learning_rate": 4.687625250501002e-05, "loss": 2.2582, "step": 6440 }, { "epoch": 0.11, "learning_rate": 4.687124248496994e-05, "loss": 2.3279, "step": 6450 }, { "epoch": 0.11, "learning_rate": 4.686623246492986e-05, "loss": 2.3084, "step": 6460 }, { "epoch": 0.11, "learning_rate": 4.686122244488978e-05, "loss": 2.3173, "step": 6470 }, { "epoch": 0.11, "learning_rate": 4.6856212424849697e-05, "loss": 2.3728, "step": 6480 }, { "epoch": 0.11, "learning_rate": 4.685120240480962e-05, "loss": 2.3685, "step": 6490 }, { "epoch": 0.11, "learning_rate": 4.6846192384769545e-05, "loss": 2.3231, "step": 6500 }, { "epoch": 0.11, "learning_rate": 4.6841182364729465e-05, "loss": 2.3486, "step": 6510 }, { "epoch": 0.11, "learning_rate": 4.6836172344689386e-05, "loss": 2.3403, "step": 6520 }, { "epoch": 0.11, "learning_rate": 4.68311623246493e-05, "loss": 2.4257, "step": 6530 }, { "epoch": 0.11, "learning_rate": 4.682615230460922e-05, "loss": 2.3326, "step": 6540 }, { "epoch": 0.11, "learning_rate": 4.682114228456914e-05, "loss": 2.3949, "step": 6550 }, { "epoch": 0.11, "learning_rate": 4.681613226452906e-05, "loss": 2.3478, "step": 6560 }, { "epoch": 0.11, "learning_rate": 4.681112224448898e-05, "loss": 2.3363, "step": 6570 }, { "epoch": 0.11, "learning_rate": 4.68061122244489e-05, "loss": 2.3439, "step": 6580 }, { "epoch": 0.11, "learning_rate": 4.680110220440882e-05, "loss": 2.3165, "step": 6590 }, { "epoch": 0.11, "learning_rate": 4.679609218436874e-05, "loss": 2.3503, "step": 6600 }, { "epoch": 0.11, "learning_rate": 4.679108216432866e-05, "loss": 2.3322, "step": 6610 }, { "epoch": 0.11, "learning_rate": 4.678607214428858e-05, "loss": 2.3164, "step": 6620 }, { "epoch": 0.11, "learning_rate": 4.67810621242485e-05, "loss": 2.3614, "step": 6630 }, { "epoch": 0.11, "learning_rate": 4.677605210420842e-05, "loss": 2.3585, "step": 6640 }, { "epoch": 0.11, "learning_rate": 4.6771042084168334e-05, "loss": 2.3476, "step": 6650 }, { "epoch": 0.11, "learning_rate": 4.6766032064128255e-05, "loss": 2.3283, "step": 6660 }, { "epoch": 0.11, "learning_rate": 4.6761022044088175e-05, "loss": 2.3203, "step": 6670 }, { "epoch": 0.11, "learning_rate": 4.6756012024048096e-05, "loss": 2.3715, "step": 6680 }, { "epoch": 0.11, "learning_rate": 4.675100200400802e-05, "loss": 2.3674, "step": 6690 }, { "epoch": 0.11, "learning_rate": 4.6745991983967944e-05, "loss": 2.3381, "step": 6700 }, { "epoch": 0.11, "learning_rate": 4.674098196392786e-05, "loss": 2.3175, "step": 6710 }, { "epoch": 0.11, "learning_rate": 4.673597194388778e-05, "loss": 2.3729, "step": 6720 }, { "epoch": 0.11, "learning_rate": 4.67309619238477e-05, "loss": 2.3179, "step": 6730 }, { "epoch": 0.11, "learning_rate": 4.672595190380762e-05, "loss": 2.3611, "step": 6740 }, { "epoch": 0.11, "learning_rate": 4.672094188376754e-05, "loss": 2.3199, "step": 6750 }, { "epoch": 0.11, "learning_rate": 4.671593186372746e-05, "loss": 2.3422, "step": 6760 }, { "epoch": 0.11, "learning_rate": 4.6710921843687375e-05, "loss": 2.3364, "step": 6770 }, { "epoch": 0.11, "learning_rate": 4.6705911823647296e-05, "loss": 2.3396, "step": 6780 }, { "epoch": 0.11, "learning_rate": 4.6700901803607216e-05, "loss": 2.3404, "step": 6790 }, { "epoch": 0.11, "learning_rate": 4.669589178356714e-05, "loss": 2.3075, "step": 6800 }, { "epoch": 0.11, "learning_rate": 4.669088176352706e-05, "loss": 2.3529, "step": 6810 }, { "epoch": 0.11, "learning_rate": 4.668587174348698e-05, "loss": 2.3605, "step": 6820 }, { "epoch": 0.11, "learning_rate": 4.668086172344689e-05, "loss": 2.3934, "step": 6830 }, { "epoch": 0.11, "learning_rate": 4.667585170340681e-05, "loss": 2.3217, "step": 6840 }, { "epoch": 0.11, "learning_rate": 4.667084168336673e-05, "loss": 2.3353, "step": 6850 }, { "epoch": 0.11, "learning_rate": 4.6665831663326654e-05, "loss": 2.3192, "step": 6860 }, { "epoch": 0.11, "learning_rate": 4.6660821643286575e-05, "loss": 2.3512, "step": 6870 }, { "epoch": 0.11, "learning_rate": 4.6655811623246495e-05, "loss": 2.3266, "step": 6880 }, { "epoch": 0.11, "learning_rate": 4.6650801603206416e-05, "loss": 2.359, "step": 6890 }, { "epoch": 0.11, "learning_rate": 4.6645791583166336e-05, "loss": 2.3015, "step": 6900 }, { "epoch": 0.11, "learning_rate": 4.664078156312626e-05, "loss": 2.3817, "step": 6910 }, { "epoch": 0.11, "learning_rate": 4.663577154308618e-05, "loss": 2.2917, "step": 6920 }, { "epoch": 0.11, "learning_rate": 4.66307615230461e-05, "loss": 2.3206, "step": 6930 }, { "epoch": 0.11, "learning_rate": 4.662575150300601e-05, "loss": 2.2879, "step": 6940 }, { "epoch": 0.11, "learning_rate": 4.662074148296593e-05, "loss": 2.2666, "step": 6950 }, { "epoch": 0.11, "learning_rate": 4.6615731462925854e-05, "loss": 2.324, "step": 6960 }, { "epoch": 0.11, "learning_rate": 4.6610721442885774e-05, "loss": 2.3034, "step": 6970 }, { "epoch": 0.11, "learning_rate": 4.6605711422845695e-05, "loss": 2.3661, "step": 6980 }, { "epoch": 0.11, "learning_rate": 4.6600701402805615e-05, "loss": 2.2812, "step": 6990 }, { "epoch": 0.11, "learning_rate": 4.6595691382765536e-05, "loss": 2.3285, "step": 7000 }, { "epoch": 0.11, "eval_loss": 2.2694578170776367, "eval_mean_f1": 0.6153106023266459, "eval_rouge1_f1": 0.6811764959808995, "eval_rouge1_precision": 0.7969187531999885, "eval_rouge1_recall": 0.6261965485947253, "eval_rouge2_f1": 0.5184030214581669, "eval_rouge2_precision": 0.6083728554431687, "eval_rouge2_recall": 0.4769918452607389, "eval_rougeL_f1": 0.6463522895408714, "eval_rougeL_precision": 0.7527388130437018, "eval_rougeL_recall": 0.5954868614799846, "eval_runtime": 64.8057, "eval_samples_per_second": 15.801, "eval_steps_per_second": 1.975, "step": 7000 }, { "epoch": 0.11, "learning_rate": 4.659068136272545e-05, "loss": 2.3323, "step": 7010 }, { "epoch": 0.11, "learning_rate": 4.658567134268537e-05, "loss": 2.3087, "step": 7020 }, { "epoch": 0.11, "learning_rate": 4.658066132264529e-05, "loss": 2.2897, "step": 7030 }, { "epoch": 0.12, "learning_rate": 4.657565130260521e-05, "loss": 2.3483, "step": 7040 }, { "epoch": 0.12, "learning_rate": 4.657064128256513e-05, "loss": 2.3745, "step": 7050 }, { "epoch": 0.12, "learning_rate": 4.656563126252505e-05, "loss": 2.3626, "step": 7060 }, { "epoch": 0.12, "learning_rate": 4.656062124248497e-05, "loss": 2.3525, "step": 7070 }, { "epoch": 0.12, "learning_rate": 4.655561122244489e-05, "loss": 2.3348, "step": 7080 }, { "epoch": 0.12, "learning_rate": 4.6550601202404815e-05, "loss": 2.3315, "step": 7090 }, { "epoch": 0.12, "learning_rate": 4.6545591182364736e-05, "loss": 2.2752, "step": 7100 }, { "epoch": 0.12, "learning_rate": 4.6540581162324656e-05, "loss": 2.3386, "step": 7110 }, { "epoch": 0.12, "learning_rate": 4.653557114228457e-05, "loss": 2.301, "step": 7120 }, { "epoch": 0.12, "learning_rate": 4.653056112224449e-05, "loss": 2.3023, "step": 7130 }, { "epoch": 0.12, "learning_rate": 4.652555110220441e-05, "loss": 2.3002, "step": 7140 }, { "epoch": 0.12, "learning_rate": 4.652054108216433e-05, "loss": 2.2831, "step": 7150 }, { "epoch": 0.12, "learning_rate": 4.651553106212425e-05, "loss": 2.2733, "step": 7160 }, { "epoch": 0.12, "learning_rate": 4.6510521042084173e-05, "loss": 2.2993, "step": 7170 }, { "epoch": 0.12, "learning_rate": 4.650551102204409e-05, "loss": 2.293, "step": 7180 }, { "epoch": 0.12, "learning_rate": 4.650050100200401e-05, "loss": 2.3406, "step": 7190 }, { "epoch": 0.12, "learning_rate": 4.649549098196393e-05, "loss": 2.3021, "step": 7200 }, { "epoch": 0.12, "learning_rate": 4.649048096192385e-05, "loss": 2.3345, "step": 7210 }, { "epoch": 0.12, "learning_rate": 4.648547094188377e-05, "loss": 2.2601, "step": 7220 }, { "epoch": 0.12, "learning_rate": 4.648046092184369e-05, "loss": 2.3404, "step": 7230 }, { "epoch": 0.12, "learning_rate": 4.6475450901803604e-05, "loss": 2.2988, "step": 7240 }, { "epoch": 0.12, "learning_rate": 4.6470440881763525e-05, "loss": 2.2705, "step": 7250 }, { "epoch": 0.12, "learning_rate": 4.6465430861723446e-05, "loss": 2.3367, "step": 7260 }, { "epoch": 0.12, "learning_rate": 4.6460420841683366e-05, "loss": 2.3086, "step": 7270 }, { "epoch": 0.12, "learning_rate": 4.6455410821643294e-05, "loss": 2.3237, "step": 7280 }, { "epoch": 0.12, "learning_rate": 4.6450400801603214e-05, "loss": 2.3096, "step": 7290 }, { "epoch": 0.12, "learning_rate": 4.644539078156313e-05, "loss": 2.2612, "step": 7300 }, { "epoch": 0.12, "learning_rate": 4.644038076152305e-05, "loss": 2.2656, "step": 7310 }, { "epoch": 0.12, "learning_rate": 4.643537074148297e-05, "loss": 2.3513, "step": 7320 }, { "epoch": 0.12, "learning_rate": 4.643036072144289e-05, "loss": 2.3559, "step": 7330 }, { "epoch": 0.12, "learning_rate": 4.642535070140281e-05, "loss": 2.3415, "step": 7340 }, { "epoch": 0.12, "learning_rate": 4.642034068136273e-05, "loss": 2.3095, "step": 7350 }, { "epoch": 0.12, "learning_rate": 4.6415330661322645e-05, "loss": 2.3478, "step": 7360 }, { "epoch": 0.12, "learning_rate": 4.6410320641282566e-05, "loss": 2.3639, "step": 7370 }, { "epoch": 0.12, "learning_rate": 4.6405310621242487e-05, "loss": 2.3667, "step": 7380 }, { "epoch": 0.12, "learning_rate": 4.640030060120241e-05, "loss": 2.3318, "step": 7390 }, { "epoch": 0.12, "learning_rate": 4.639529058116233e-05, "loss": 2.3182, "step": 7400 }, { "epoch": 0.12, "learning_rate": 4.639028056112225e-05, "loss": 2.3124, "step": 7410 }, { "epoch": 0.12, "learning_rate": 4.638527054108216e-05, "loss": 2.3447, "step": 7420 }, { "epoch": 0.12, "learning_rate": 4.638026052104208e-05, "loss": 2.235, "step": 7430 }, { "epoch": 0.12, "learning_rate": 4.6375250501002004e-05, "loss": 2.3021, "step": 7440 }, { "epoch": 0.12, "learning_rate": 4.6370240480961924e-05, "loss": 2.3304, "step": 7450 }, { "epoch": 0.12, "learning_rate": 4.6365230460921845e-05, "loss": 2.3096, "step": 7460 }, { "epoch": 0.12, "learning_rate": 4.6360220440881766e-05, "loss": 2.3571, "step": 7470 }, { "epoch": 0.12, "learning_rate": 4.6355210420841686e-05, "loss": 2.2537, "step": 7480 }, { "epoch": 0.12, "learning_rate": 4.635020040080161e-05, "loss": 2.3473, "step": 7490 }, { "epoch": 0.12, "learning_rate": 4.634519038076153e-05, "loss": 2.3141, "step": 7500 }, { "epoch": 0.12, "learning_rate": 4.634018036072145e-05, "loss": 2.2689, "step": 7510 }, { "epoch": 0.12, "learning_rate": 4.633517034068137e-05, "loss": 2.2874, "step": 7520 }, { "epoch": 0.12, "learning_rate": 4.633016032064128e-05, "loss": 2.2945, "step": 7530 }, { "epoch": 0.12, "learning_rate": 4.63251503006012e-05, "loss": 2.2901, "step": 7540 }, { "epoch": 0.12, "learning_rate": 4.6320140280561124e-05, "loss": 2.3345, "step": 7550 }, { "epoch": 0.12, "learning_rate": 4.6315130260521045e-05, "loss": 2.3387, "step": 7560 }, { "epoch": 0.12, "learning_rate": 4.6310120240480965e-05, "loss": 2.3277, "step": 7570 }, { "epoch": 0.12, "learning_rate": 4.6305110220440886e-05, "loss": 2.3691, "step": 7580 }, { "epoch": 0.12, "learning_rate": 4.6300100200400806e-05, "loss": 2.363, "step": 7590 }, { "epoch": 0.12, "learning_rate": 4.629509018036072e-05, "loss": 2.3376, "step": 7600 }, { "epoch": 0.12, "learning_rate": 4.629008016032064e-05, "loss": 2.3234, "step": 7610 }, { "epoch": 0.12, "learning_rate": 4.628507014028056e-05, "loss": 2.3397, "step": 7620 }, { "epoch": 0.12, "learning_rate": 4.628006012024048e-05, "loss": 2.2969, "step": 7630 }, { "epoch": 0.12, "learning_rate": 4.62750501002004e-05, "loss": 2.3181, "step": 7640 }, { "epoch": 0.12, "learning_rate": 4.6270040080160324e-05, "loss": 2.3202, "step": 7650 }, { "epoch": 0.13, "learning_rate": 4.626503006012024e-05, "loss": 2.353, "step": 7660 }, { "epoch": 0.13, "learning_rate": 4.626002004008016e-05, "loss": 2.3126, "step": 7670 }, { "epoch": 0.13, "learning_rate": 4.6255010020040085e-05, "loss": 2.3107, "step": 7680 }, { "epoch": 0.13, "learning_rate": 4.6250000000000006e-05, "loss": 2.3142, "step": 7690 }, { "epoch": 0.13, "learning_rate": 4.624498997995993e-05, "loss": 2.3378, "step": 7700 }, { "epoch": 0.13, "learning_rate": 4.623997995991984e-05, "loss": 2.3019, "step": 7710 }, { "epoch": 0.13, "learning_rate": 4.623496993987976e-05, "loss": 2.3052, "step": 7720 }, { "epoch": 0.13, "learning_rate": 4.622995991983968e-05, "loss": 2.2953, "step": 7730 }, { "epoch": 0.13, "learning_rate": 4.62249498997996e-05, "loss": 2.2613, "step": 7740 }, { "epoch": 0.13, "learning_rate": 4.621993987975952e-05, "loss": 2.3464, "step": 7750 }, { "epoch": 0.13, "learning_rate": 4.6214929859719444e-05, "loss": 2.3117, "step": 7760 }, { "epoch": 0.13, "learning_rate": 4.620991983967936e-05, "loss": 2.324, "step": 7770 }, { "epoch": 0.13, "learning_rate": 4.620490981963928e-05, "loss": 2.2838, "step": 7780 }, { "epoch": 0.13, "learning_rate": 4.61998997995992e-05, "loss": 2.2614, "step": 7790 }, { "epoch": 0.13, "learning_rate": 4.619488977955912e-05, "loss": 2.279, "step": 7800 }, { "epoch": 0.13, "learning_rate": 4.618987975951904e-05, "loss": 2.2939, "step": 7810 }, { "epoch": 0.13, "learning_rate": 4.618486973947896e-05, "loss": 2.3164, "step": 7820 }, { "epoch": 0.13, "learning_rate": 4.617985971943888e-05, "loss": 2.3237, "step": 7830 }, { "epoch": 0.13, "learning_rate": 4.6174849699398795e-05, "loss": 2.3316, "step": 7840 }, { "epoch": 0.13, "learning_rate": 4.6169839679358716e-05, "loss": 2.2723, "step": 7850 }, { "epoch": 0.13, "learning_rate": 4.616482965931864e-05, "loss": 2.2731, "step": 7860 }, { "epoch": 0.13, "learning_rate": 4.6159819639278564e-05, "loss": 2.281, "step": 7870 }, { "epoch": 0.13, "learning_rate": 4.6154809619238485e-05, "loss": 2.3322, "step": 7880 }, { "epoch": 0.13, "learning_rate": 4.61497995991984e-05, "loss": 2.3329, "step": 7890 }, { "epoch": 0.13, "learning_rate": 4.614478957915832e-05, "loss": 2.2952, "step": 7900 }, { "epoch": 0.13, "learning_rate": 4.613977955911824e-05, "loss": 2.2984, "step": 7910 }, { "epoch": 0.13, "learning_rate": 4.613476953907816e-05, "loss": 2.2948, "step": 7920 }, { "epoch": 0.13, "learning_rate": 4.612975951903808e-05, "loss": 2.3393, "step": 7930 }, { "epoch": 0.13, "learning_rate": 4.6124749498998e-05, "loss": 2.3465, "step": 7940 }, { "epoch": 0.13, "learning_rate": 4.6120240480961925e-05, "loss": 2.2531, "step": 7950 }, { "epoch": 0.13, "learning_rate": 4.6115230460921846e-05, "loss": 2.2998, "step": 7960 }, { "epoch": 0.13, "learning_rate": 4.6110220440881766e-05, "loss": 2.2687, "step": 7970 }, { "epoch": 0.13, "learning_rate": 4.610521042084169e-05, "loss": 2.3162, "step": 7980 }, { "epoch": 0.13, "learning_rate": 4.610020040080161e-05, "loss": 2.2907, "step": 7990 }, { "epoch": 0.13, "learning_rate": 4.609519038076153e-05, "loss": 2.3114, "step": 8000 }, { "epoch": 0.13, "eval_loss": 2.245161294937134, "eval_mean_f1": 0.6200434186701758, "eval_rouge1_f1": 0.6871542582872169, "eval_rouge1_precision": 0.8011097401564431, "eval_rouge1_recall": 0.6331094857081246, "eval_rouge2_f1": 0.5228148148557075, "eval_rouge2_precision": 0.6131861892176824, "eval_rouge2_recall": 0.4824493052973433, "eval_rougeL_f1": 0.650161182867603, "eval_rougeL_precision": 0.7554431288878096, "eval_rougeL_recall": 0.6005554203833612, "eval_runtime": 66.2871, "eval_samples_per_second": 15.448, "eval_steps_per_second": 1.931, "step": 8000 }, { "epoch": 0.13, "learning_rate": 4.609018036072145e-05, "loss": 2.2968, "step": 8010 }, { "epoch": 0.13, "learning_rate": 4.608517034068137e-05, "loss": 2.2768, "step": 8020 }, { "epoch": 0.13, "learning_rate": 4.608016032064128e-05, "loss": 2.3095, "step": 8030 }, { "epoch": 0.13, "learning_rate": 4.6075150300601204e-05, "loss": 2.323, "step": 8040 }, { "epoch": 0.13, "learning_rate": 4.6070140280561125e-05, "loss": 2.3006, "step": 8050 }, { "epoch": 0.13, "learning_rate": 4.6065130260521045e-05, "loss": 2.3301, "step": 8060 }, { "epoch": 0.13, "learning_rate": 4.6060120240480966e-05, "loss": 2.2543, "step": 8070 }, { "epoch": 0.13, "learning_rate": 4.6055110220440887e-05, "loss": 2.2594, "step": 8080 }, { "epoch": 0.13, "learning_rate": 4.60501002004008e-05, "loss": 2.281, "step": 8090 }, { "epoch": 0.13, "learning_rate": 4.604509018036072e-05, "loss": 2.2573, "step": 8100 }, { "epoch": 0.13, "learning_rate": 4.604008016032064e-05, "loss": 2.3204, "step": 8110 }, { "epoch": 0.13, "learning_rate": 4.603507014028056e-05, "loss": 2.2749, "step": 8120 }, { "epoch": 0.13, "learning_rate": 4.603006012024048e-05, "loss": 2.341, "step": 8130 }, { "epoch": 0.13, "learning_rate": 4.6025050100200404e-05, "loss": 2.3123, "step": 8140 }, { "epoch": 0.13, "learning_rate": 4.602004008016032e-05, "loss": 2.2866, "step": 8150 }, { "epoch": 0.13, "learning_rate": 4.601503006012024e-05, "loss": 2.3152, "step": 8160 }, { "epoch": 0.13, "learning_rate": 4.6010020040080166e-05, "loss": 2.3158, "step": 8170 }, { "epoch": 0.13, "learning_rate": 4.6005010020040086e-05, "loss": 2.3124, "step": 8180 }, { "epoch": 0.13, "learning_rate": 4.600000000000001e-05, "loss": 2.2787, "step": 8190 }, { "epoch": 0.13, "learning_rate": 4.599498997995992e-05, "loss": 2.302, "step": 8200 }, { "epoch": 0.13, "learning_rate": 4.598997995991984e-05, "loss": 2.295, "step": 8210 }, { "epoch": 0.13, "learning_rate": 4.598496993987976e-05, "loss": 2.2869, "step": 8220 }, { "epoch": 0.13, "learning_rate": 4.597995991983968e-05, "loss": 2.3392, "step": 8230 }, { "epoch": 0.13, "learning_rate": 4.59749498997996e-05, "loss": 2.3032, "step": 8240 }, { "epoch": 0.13, "learning_rate": 4.5969939879759524e-05, "loss": 2.2261, "step": 8250 }, { "epoch": 0.13, "learning_rate": 4.596492985971944e-05, "loss": 2.2706, "step": 8260 }, { "epoch": 0.14, "learning_rate": 4.595991983967936e-05, "loss": 2.2969, "step": 8270 }, { "epoch": 0.14, "learning_rate": 4.595490981963928e-05, "loss": 2.3183, "step": 8280 }, { "epoch": 0.14, "learning_rate": 4.59498997995992e-05, "loss": 2.3236, "step": 8290 }, { "epoch": 0.14, "learning_rate": 4.594488977955912e-05, "loss": 2.2858, "step": 8300 }, { "epoch": 0.14, "learning_rate": 4.593987975951904e-05, "loss": 2.2675, "step": 8310 }, { "epoch": 0.14, "learning_rate": 4.593486973947896e-05, "loss": 2.2832, "step": 8320 }, { "epoch": 0.14, "learning_rate": 4.5929859719438875e-05, "loss": 2.3323, "step": 8330 }, { "epoch": 0.14, "learning_rate": 4.5924849699398796e-05, "loss": 2.2981, "step": 8340 }, { "epoch": 0.14, "learning_rate": 4.591983967935872e-05, "loss": 2.2876, "step": 8350 }, { "epoch": 0.14, "learning_rate": 4.5914829659318644e-05, "loss": 2.3088, "step": 8360 }, { "epoch": 0.14, "learning_rate": 4.5909819639278565e-05, "loss": 2.2901, "step": 8370 }, { "epoch": 0.14, "learning_rate": 4.590480961923848e-05, "loss": 2.3185, "step": 8380 }, { "epoch": 0.14, "learning_rate": 4.58997995991984e-05, "loss": 2.2738, "step": 8390 }, { "epoch": 0.14, "learning_rate": 4.589478957915832e-05, "loss": 2.3146, "step": 8400 }, { "epoch": 0.14, "learning_rate": 4.588977955911824e-05, "loss": 2.2584, "step": 8410 }, { "epoch": 0.14, "learning_rate": 4.588476953907816e-05, "loss": 2.2965, "step": 8420 }, { "epoch": 0.14, "learning_rate": 4.587975951903808e-05, "loss": 2.2898, "step": 8430 }, { "epoch": 0.14, "learning_rate": 4.5874749498997996e-05, "loss": 2.2832, "step": 8440 }, { "epoch": 0.14, "learning_rate": 4.5869739478957916e-05, "loss": 2.2994, "step": 8450 }, { "epoch": 0.14, "learning_rate": 4.586472945891784e-05, "loss": 2.282, "step": 8460 }, { "epoch": 0.14, "learning_rate": 4.585971943887776e-05, "loss": 2.3397, "step": 8470 }, { "epoch": 0.14, "learning_rate": 4.585470941883768e-05, "loss": 2.2468, "step": 8480 }, { "epoch": 0.14, "learning_rate": 4.58496993987976e-05, "loss": 2.2952, "step": 8490 }, { "epoch": 0.14, "learning_rate": 4.584468937875751e-05, "loss": 2.3213, "step": 8500 }, { "epoch": 0.14, "learning_rate": 4.5839679358717433e-05, "loss": 2.3186, "step": 8510 }, { "epoch": 0.14, "learning_rate": 4.5834669338677354e-05, "loss": 2.2917, "step": 8520 }, { "epoch": 0.14, "learning_rate": 4.5829659318637275e-05, "loss": 2.3455, "step": 8530 }, { "epoch": 0.14, "learning_rate": 4.5824649298597195e-05, "loss": 2.2504, "step": 8540 }, { "epoch": 0.14, "learning_rate": 4.5819639278557116e-05, "loss": 2.2307, "step": 8550 }, { "epoch": 0.14, "learning_rate": 4.581462925851704e-05, "loss": 2.3245, "step": 8560 }, { "epoch": 0.14, "learning_rate": 4.580961923847696e-05, "loss": 2.3037, "step": 8570 }, { "epoch": 0.14, "learning_rate": 4.580460921843688e-05, "loss": 2.273, "step": 8580 }, { "epoch": 0.14, "learning_rate": 4.57995991983968e-05, "loss": 2.3126, "step": 8590 }, { "epoch": 0.14, "learning_rate": 4.579458917835672e-05, "loss": 2.3033, "step": 8600 }, { "epoch": 0.14, "learning_rate": 4.578957915831664e-05, "loss": 2.3372, "step": 8610 }, { "epoch": 0.14, "learning_rate": 4.5784569138276554e-05, "loss": 2.273, "step": 8620 }, { "epoch": 0.14, "learning_rate": 4.5779559118236474e-05, "loss": 2.297, "step": 8630 }, { "epoch": 0.14, "learning_rate": 4.5774549098196395e-05, "loss": 2.315, "step": 8640 }, { "epoch": 0.14, "learning_rate": 4.5769539078156316e-05, "loss": 2.3097, "step": 8650 }, { "epoch": 0.14, "learning_rate": 4.5764529058116236e-05, "loss": 2.2545, "step": 8660 }, { "epoch": 0.14, "learning_rate": 4.575951903807616e-05, "loss": 2.2902, "step": 8670 }, { "epoch": 0.14, "learning_rate": 4.575450901803607e-05, "loss": 2.2215, "step": 8680 }, { "epoch": 0.14, "learning_rate": 4.574949899799599e-05, "loss": 2.3102, "step": 8690 }, { "epoch": 0.14, "learning_rate": 4.574448897795591e-05, "loss": 2.3148, "step": 8700 }, { "epoch": 0.14, "learning_rate": 4.573947895791583e-05, "loss": 2.272, "step": 8710 }, { "epoch": 0.14, "learning_rate": 4.573446893787575e-05, "loss": 2.2967, "step": 8720 }, { "epoch": 0.14, "learning_rate": 4.5729458917835674e-05, "loss": 2.3048, "step": 8730 }, { "epoch": 0.14, "learning_rate": 4.572444889779559e-05, "loss": 2.3254, "step": 8740 }, { "epoch": 0.14, "learning_rate": 4.571943887775551e-05, "loss": 2.3548, "step": 8750 }, { "epoch": 0.14, "learning_rate": 4.5714428857715436e-05, "loss": 2.2864, "step": 8760 }, { "epoch": 0.14, "learning_rate": 4.5709418837675357e-05, "loss": 2.2594, "step": 8770 }, { "epoch": 0.14, "learning_rate": 4.570440881763528e-05, "loss": 2.3162, "step": 8780 }, { "epoch": 0.14, "learning_rate": 4.569939879759519e-05, "loss": 2.3141, "step": 8790 }, { "epoch": 0.14, "learning_rate": 4.569438877755511e-05, "loss": 2.2836, "step": 8800 }, { "epoch": 0.14, "learning_rate": 4.568937875751503e-05, "loss": 2.3296, "step": 8810 }, { "epoch": 0.14, "learning_rate": 4.568436873747495e-05, "loss": 2.3294, "step": 8820 }, { "epoch": 0.14, "learning_rate": 4.5679358717434874e-05, "loss": 2.2749, "step": 8830 }, { "epoch": 0.14, "learning_rate": 4.5674348697394794e-05, "loss": 2.3026, "step": 8840 }, { "epoch": 0.14, "learning_rate": 4.5669338677354715e-05, "loss": 2.2602, "step": 8850 }, { "epoch": 0.14, "learning_rate": 4.566432865731463e-05, "loss": 2.2523, "step": 8860 }, { "epoch": 0.14, "learning_rate": 4.565931863727455e-05, "loss": 2.2837, "step": 8870 }, { "epoch": 0.15, "learning_rate": 4.565430861723447e-05, "loss": 2.2787, "step": 8880 }, { "epoch": 0.15, "learning_rate": 4.564929859719439e-05, "loss": 2.286, "step": 8890 }, { "epoch": 0.15, "learning_rate": 4.564428857715431e-05, "loss": 2.3127, "step": 8900 }, { "epoch": 0.15, "learning_rate": 4.563927855711423e-05, "loss": 2.2805, "step": 8910 }, { "epoch": 0.15, "learning_rate": 4.5634268537074146e-05, "loss": 2.2908, "step": 8920 }, { "epoch": 0.15, "learning_rate": 4.5629258517034067e-05, "loss": 2.3005, "step": 8930 }, { "epoch": 0.15, "learning_rate": 4.562424849699399e-05, "loss": 2.2958, "step": 8940 }, { "epoch": 0.15, "learning_rate": 4.5619238476953915e-05, "loss": 2.2722, "step": 8950 }, { "epoch": 0.15, "learning_rate": 4.5614228456913835e-05, "loss": 2.243, "step": 8960 }, { "epoch": 0.15, "learning_rate": 4.560921843687375e-05, "loss": 2.3226, "step": 8970 }, { "epoch": 0.15, "learning_rate": 4.560420841683367e-05, "loss": 2.248, "step": 8980 }, { "epoch": 0.15, "learning_rate": 4.559919839679359e-05, "loss": 2.1955, "step": 8990 }, { "epoch": 0.15, "learning_rate": 4.559418837675351e-05, "loss": 2.3061, "step": 9000 }, { "epoch": 0.15, "eval_loss": 2.2351810932159424, "eval_mean_f1": 0.6208511306331607, "eval_rouge1_f1": 0.6865252911838784, "eval_rouge1_precision": 0.7985588163448196, "eval_rouge1_recall": 0.6343975123889732, "eval_rouge2_f1": 0.5237017861723388, "eval_rouge2_precision": 0.6133080562829099, "eval_rouge2_recall": 0.48416682817690865, "eval_rougeL_f1": 0.652326314543265, "eval_rougeL_precision": 0.7570174180665767, "eval_rougeL_recall": 0.6041952257284291, "eval_runtime": 65.0767, "eval_samples_per_second": 15.735, "eval_steps_per_second": 1.967, "step": 9000 }, { "epoch": 0.15, "learning_rate": 4.558917835671343e-05, "loss": 2.3066, "step": 9010 }, { "epoch": 0.15, "learning_rate": 4.558416833667335e-05, "loss": 2.3117, "step": 9020 }, { "epoch": 0.15, "learning_rate": 4.5579158316633266e-05, "loss": 2.2574, "step": 9030 }, { "epoch": 0.15, "learning_rate": 4.557414829659319e-05, "loss": 2.3227, "step": 9040 }, { "epoch": 0.15, "learning_rate": 4.556913827655311e-05, "loss": 2.2913, "step": 9050 }, { "epoch": 0.15, "learning_rate": 4.556412825651303e-05, "loss": 2.2823, "step": 9060 }, { "epoch": 0.15, "learning_rate": 4.555911823647295e-05, "loss": 2.3108, "step": 9070 }, { "epoch": 0.15, "learning_rate": 4.555410821643287e-05, "loss": 2.2399, "step": 9080 }, { "epoch": 0.15, "learning_rate": 4.554909819639278e-05, "loss": 2.2512, "step": 9090 }, { "epoch": 0.15, "learning_rate": 4.5544088176352704e-05, "loss": 2.2414, "step": 9100 }, { "epoch": 0.15, "learning_rate": 4.5539078156312624e-05, "loss": 2.2861, "step": 9110 }, { "epoch": 0.15, "learning_rate": 4.5534068136272545e-05, "loss": 2.305, "step": 9120 }, { "epoch": 0.15, "learning_rate": 4.5529058116232466e-05, "loss": 2.2919, "step": 9130 }, { "epoch": 0.15, "learning_rate": 4.5524048096192386e-05, "loss": 2.2774, "step": 9140 }, { "epoch": 0.15, "learning_rate": 4.551903807615231e-05, "loss": 2.2471, "step": 9150 }, { "epoch": 0.15, "learning_rate": 4.551402805611223e-05, "loss": 2.3555, "step": 9160 }, { "epoch": 0.15, "learning_rate": 4.550901803607215e-05, "loss": 2.2814, "step": 9170 }, { "epoch": 0.15, "learning_rate": 4.550400801603207e-05, "loss": 2.342, "step": 9180 }, { "epoch": 0.15, "learning_rate": 4.549899799599199e-05, "loss": 2.2779, "step": 9190 }, { "epoch": 0.15, "learning_rate": 4.549398797595191e-05, "loss": 2.2888, "step": 9200 }, { "epoch": 0.15, "learning_rate": 4.5488977955911824e-05, "loss": 2.3219, "step": 9210 }, { "epoch": 0.15, "learning_rate": 4.5483967935871745e-05, "loss": 2.2804, "step": 9220 }, { "epoch": 0.15, "learning_rate": 4.5478957915831665e-05, "loss": 2.3152, "step": 9230 }, { "epoch": 0.15, "learning_rate": 4.5473947895791586e-05, "loss": 2.2588, "step": 9240 }, { "epoch": 0.15, "learning_rate": 4.546893787575151e-05, "loss": 2.2215, "step": 9250 }, { "epoch": 0.15, "learning_rate": 4.546392785571143e-05, "loss": 2.2599, "step": 9260 }, { "epoch": 0.15, "learning_rate": 4.545891783567134e-05, "loss": 2.3228, "step": 9270 }, { "epoch": 0.15, "learning_rate": 4.545390781563126e-05, "loss": 2.2997, "step": 9280 }, { "epoch": 0.15, "learning_rate": 4.544889779559118e-05, "loss": 2.2772, "step": 9290 }, { "epoch": 0.15, "learning_rate": 4.54438877755511e-05, "loss": 2.2645, "step": 9300 }, { "epoch": 0.15, "learning_rate": 4.5438877755511024e-05, "loss": 2.3179, "step": 9310 }, { "epoch": 0.15, "learning_rate": 4.5433867735470944e-05, "loss": 2.2413, "step": 9320 }, { "epoch": 0.15, "learning_rate": 4.542885771543086e-05, "loss": 2.2638, "step": 9330 }, { "epoch": 0.15, "learning_rate": 4.542384769539078e-05, "loss": 2.2939, "step": 9340 }, { "epoch": 0.15, "learning_rate": 4.5418837675350706e-05, "loss": 2.2773, "step": 9350 }, { "epoch": 0.15, "learning_rate": 4.541382765531063e-05, "loss": 2.2851, "step": 9360 }, { "epoch": 0.15, "learning_rate": 4.540881763527055e-05, "loss": 2.2859, "step": 9370 }, { "epoch": 0.15, "learning_rate": 4.540380761523046e-05, "loss": 2.2676, "step": 9380 }, { "epoch": 0.15, "learning_rate": 4.539879759519038e-05, "loss": 2.3137, "step": 9390 }, { "epoch": 0.15, "learning_rate": 4.53937875751503e-05, "loss": 2.328, "step": 9400 }, { "epoch": 0.15, "learning_rate": 4.5388777555110223e-05, "loss": 2.2443, "step": 9410 }, { "epoch": 0.15, "learning_rate": 4.5383767535070144e-05, "loss": 2.2882, "step": 9420 }, { "epoch": 0.15, "learning_rate": 4.5378757515030065e-05, "loss": 2.2408, "step": 9430 }, { "epoch": 0.15, "learning_rate": 4.5373747494989985e-05, "loss": 2.2597, "step": 9440 }, { "epoch": 0.15, "learning_rate": 4.53687374749499e-05, "loss": 2.2729, "step": 9450 }, { "epoch": 0.15, "learning_rate": 4.536372745490982e-05, "loss": 2.2863, "step": 9460 }, { "epoch": 0.15, "learning_rate": 4.535871743486974e-05, "loss": 2.3345, "step": 9470 }, { "epoch": 0.15, "learning_rate": 4.535370741482966e-05, "loss": 2.2942, "step": 9480 }, { "epoch": 0.16, "learning_rate": 4.534869739478958e-05, "loss": 2.2469, "step": 9490 }, { "epoch": 0.16, "learning_rate": 4.53436873747495e-05, "loss": 2.3059, "step": 9500 }, { "epoch": 0.16, "learning_rate": 4.5338677354709416e-05, "loss": 2.3076, "step": 9510 }, { "epoch": 0.16, "learning_rate": 4.533366733466934e-05, "loss": 2.2553, "step": 9520 }, { "epoch": 0.16, "learning_rate": 4.532865731462926e-05, "loss": 2.2857, "step": 9530 }, { "epoch": 0.16, "learning_rate": 4.5323647294589185e-05, "loss": 2.3054, "step": 9540 }, { "epoch": 0.16, "learning_rate": 4.5318637274549106e-05, "loss": 2.3031, "step": 9550 }, { "epoch": 0.16, "learning_rate": 4.531362725450902e-05, "loss": 2.2442, "step": 9560 }, { "epoch": 0.16, "learning_rate": 4.530861723446894e-05, "loss": 2.2132, "step": 9570 }, { "epoch": 0.16, "learning_rate": 4.530360721442886e-05, "loss": 2.3016, "step": 9580 }, { "epoch": 0.16, "learning_rate": 4.529859719438878e-05, "loss": 2.2825, "step": 9590 }, { "epoch": 0.16, "learning_rate": 4.52935871743487e-05, "loss": 2.299, "step": 9600 }, { "epoch": 0.16, "learning_rate": 4.528857715430862e-05, "loss": 2.3039, "step": 9610 }, { "epoch": 0.16, "learning_rate": 4.5283567134268537e-05, "loss": 2.2933, "step": 9620 }, { "epoch": 0.16, "learning_rate": 4.527855711422846e-05, "loss": 2.2903, "step": 9630 }, { "epoch": 0.16, "learning_rate": 4.527354709418838e-05, "loss": 2.2596, "step": 9640 }, { "epoch": 0.16, "learning_rate": 4.52685370741483e-05, "loss": 2.2857, "step": 9650 }, { "epoch": 0.16, "learning_rate": 4.526352705410822e-05, "loss": 2.2616, "step": 9660 }, { "epoch": 0.16, "learning_rate": 4.525851703406814e-05, "loss": 2.2558, "step": 9670 }, { "epoch": 0.16, "learning_rate": 4.525350701402806e-05, "loss": 2.2879, "step": 9680 }, { "epoch": 0.16, "learning_rate": 4.5248496993987974e-05, "loss": 2.2486, "step": 9690 }, { "epoch": 0.16, "learning_rate": 4.5243486973947895e-05, "loss": 2.248, "step": 9700 }, { "epoch": 0.16, "learning_rate": 4.5238476953907816e-05, "loss": 2.2358, "step": 9710 }, { "epoch": 0.16, "learning_rate": 4.5233466933867736e-05, "loss": 2.267, "step": 9720 }, { "epoch": 0.16, "learning_rate": 4.522845691382766e-05, "loss": 2.2737, "step": 9730 }, { "epoch": 0.16, "learning_rate": 4.522344689378758e-05, "loss": 2.2587, "step": 9740 }, { "epoch": 0.16, "learning_rate": 4.52184368737475e-05, "loss": 2.3353, "step": 9750 }, { "epoch": 0.16, "learning_rate": 4.521342685370742e-05, "loss": 2.2672, "step": 9760 }, { "epoch": 0.16, "learning_rate": 4.520841683366734e-05, "loss": 2.2721, "step": 9770 }, { "epoch": 0.16, "learning_rate": 4.520340681362726e-05, "loss": 2.2883, "step": 9780 }, { "epoch": 0.16, "learning_rate": 4.519839679358718e-05, "loss": 2.3366, "step": 9790 }, { "epoch": 0.16, "learning_rate": 4.5193386773547095e-05, "loss": 2.2548, "step": 9800 }, { "epoch": 0.16, "learning_rate": 4.5188376753507015e-05, "loss": 2.297, "step": 9810 }, { "epoch": 0.16, "learning_rate": 4.5183366733466936e-05, "loss": 2.2903, "step": 9820 }, { "epoch": 0.16, "learning_rate": 4.5178356713426856e-05, "loss": 2.2712, "step": 9830 }, { "epoch": 0.16, "learning_rate": 4.517334669338678e-05, "loss": 2.2874, "step": 9840 }, { "epoch": 0.16, "learning_rate": 4.51683366733467e-05, "loss": 2.2416, "step": 9850 }, { "epoch": 0.16, "learning_rate": 4.516332665330661e-05, "loss": 2.3075, "step": 9860 }, { "epoch": 0.16, "learning_rate": 4.515831663326653e-05, "loss": 2.2601, "step": 9870 }, { "epoch": 0.16, "learning_rate": 4.515330661322645e-05, "loss": 2.2668, "step": 9880 }, { "epoch": 0.16, "learning_rate": 4.5148296593186374e-05, "loss": 2.3356, "step": 9890 }, { "epoch": 0.16, "learning_rate": 4.5143286573146294e-05, "loss": 2.2858, "step": 9900 }, { "epoch": 0.16, "learning_rate": 4.5138276553106215e-05, "loss": 2.2626, "step": 9910 }, { "epoch": 0.16, "learning_rate": 4.513326653306613e-05, "loss": 2.2337, "step": 9920 }, { "epoch": 0.16, "learning_rate": 4.512825651302605e-05, "loss": 2.2402, "step": 9930 }, { "epoch": 0.16, "learning_rate": 4.512324649298598e-05, "loss": 2.3211, "step": 9940 }, { "epoch": 0.16, "learning_rate": 4.51182364729459e-05, "loss": 2.258, "step": 9950 }, { "epoch": 0.16, "learning_rate": 4.511322645290582e-05, "loss": 2.2816, "step": 9960 }, { "epoch": 0.16, "learning_rate": 4.510821643286574e-05, "loss": 2.2707, "step": 9970 }, { "epoch": 0.16, "learning_rate": 4.510320641282565e-05, "loss": 2.2743, "step": 9980 }, { "epoch": 0.16, "learning_rate": 4.509819639278557e-05, "loss": 2.2661, "step": 9990 }, { "epoch": 0.16, "learning_rate": 4.5093186372745494e-05, "loss": 2.306, "step": 10000 }, { "epoch": 0.16, "eval_loss": 2.2259774208068848, "eval_mean_f1": 0.6305767044181769, "eval_rouge1_f1": 0.6948989342450438, "eval_rouge1_precision": 0.8083830575795475, "eval_rouge1_recall": 0.6407090127174118, "eval_rouge2_f1": 0.5363204566591394, "eval_rouge2_precision": 0.625666403773093, "eval_rouge2_recall": 0.4950378685489028, "eval_rougeL_f1": 0.6605107223503477, "eval_rougeL_precision": 0.7655545534588217, "eval_rougeL_recall": 0.6102218203988903, "eval_runtime": 66.3596, "eval_samples_per_second": 15.431, "eval_steps_per_second": 1.929, "step": 10000 }, { "epoch": 0.16, "learning_rate": 4.5088176352705414e-05, "loss": 2.2683, "step": 10010 }, { "epoch": 0.16, "learning_rate": 4.5083166332665335e-05, "loss": 2.239, "step": 10020 }, { "epoch": 0.16, "learning_rate": 4.5078156312625256e-05, "loss": 2.2507, "step": 10030 }, { "epoch": 0.16, "learning_rate": 4.507314629258517e-05, "loss": 2.2651, "step": 10040 }, { "epoch": 0.16, "learning_rate": 4.506813627254509e-05, "loss": 2.2963, "step": 10050 }, { "epoch": 0.16, "learning_rate": 4.506312625250501e-05, "loss": 2.2254, "step": 10060 }, { "epoch": 0.16, "learning_rate": 4.505811623246493e-05, "loss": 2.3156, "step": 10070 }, { "epoch": 0.16, "learning_rate": 4.505310621242485e-05, "loss": 2.3267, "step": 10080 }, { "epoch": 0.16, "learning_rate": 4.504809619238477e-05, "loss": 2.3065, "step": 10090 }, { "epoch": 0.17, "learning_rate": 4.504308617234469e-05, "loss": 2.2612, "step": 10100 }, { "epoch": 0.17, "learning_rate": 4.503807615230461e-05, "loss": 2.2833, "step": 10110 }, { "epoch": 0.17, "learning_rate": 4.503306613226453e-05, "loss": 2.3181, "step": 10120 }, { "epoch": 0.17, "learning_rate": 4.5028056112224455e-05, "loss": 2.2358, "step": 10130 }, { "epoch": 0.17, "learning_rate": 4.5023046092184376e-05, "loss": 2.2749, "step": 10140 }, { "epoch": 0.17, "learning_rate": 4.501803607214429e-05, "loss": 2.3038, "step": 10150 }, { "epoch": 0.17, "learning_rate": 4.501302605210421e-05, "loss": 2.2652, "step": 10160 }, { "epoch": 0.17, "learning_rate": 4.500801603206413e-05, "loss": 2.2886, "step": 10170 }, { "epoch": 0.17, "learning_rate": 4.500300601202405e-05, "loss": 2.277, "step": 10180 }, { "epoch": 0.17, "learning_rate": 4.499799599198397e-05, "loss": 2.2766, "step": 10190 }, { "epoch": 0.17, "learning_rate": 4.499298597194389e-05, "loss": 2.3142, "step": 10200 }, { "epoch": 0.17, "learning_rate": 4.498797595190381e-05, "loss": 2.2288, "step": 10210 }, { "epoch": 0.17, "learning_rate": 4.498296593186373e-05, "loss": 2.2761, "step": 10220 }, { "epoch": 0.17, "learning_rate": 4.497795591182365e-05, "loss": 2.2712, "step": 10230 }, { "epoch": 0.17, "learning_rate": 4.497294589178357e-05, "loss": 2.2718, "step": 10240 }, { "epoch": 0.17, "learning_rate": 4.496793587174349e-05, "loss": 2.2953, "step": 10250 }, { "epoch": 0.17, "learning_rate": 4.496292585170341e-05, "loss": 2.2583, "step": 10260 }, { "epoch": 0.17, "learning_rate": 4.495791583166333e-05, "loss": 2.263, "step": 10270 }, { "epoch": 0.17, "learning_rate": 4.4952905811623245e-05, "loss": 2.2149, "step": 10280 }, { "epoch": 0.17, "learning_rate": 4.4947895791583165e-05, "loss": 2.2677, "step": 10290 }, { "epoch": 0.17, "learning_rate": 4.4942885771543086e-05, "loss": 2.2322, "step": 10300 }, { "epoch": 0.17, "learning_rate": 4.4937875751503007e-05, "loss": 2.2299, "step": 10310 }, { "epoch": 0.17, "learning_rate": 4.493286573146293e-05, "loss": 2.2357, "step": 10320 }, { "epoch": 0.17, "learning_rate": 4.492785571142285e-05, "loss": 2.3304, "step": 10330 }, { "epoch": 0.17, "learning_rate": 4.492284569138277e-05, "loss": 2.2477, "step": 10340 }, { "epoch": 0.17, "learning_rate": 4.491783567134269e-05, "loss": 2.296, "step": 10350 }, { "epoch": 0.17, "learning_rate": 4.491282565130261e-05, "loss": 2.2771, "step": 10360 }, { "epoch": 0.17, "learning_rate": 4.490781563126253e-05, "loss": 2.2131, "step": 10370 }, { "epoch": 0.17, "learning_rate": 4.490280561122245e-05, "loss": 2.2759, "step": 10380 }, { "epoch": 0.17, "learning_rate": 4.4897795591182365e-05, "loss": 2.2382, "step": 10390 }, { "epoch": 0.17, "learning_rate": 4.4892785571142286e-05, "loss": 2.2989, "step": 10400 }, { "epoch": 0.17, "learning_rate": 4.4887775551102206e-05, "loss": 2.2337, "step": 10410 }, { "epoch": 0.17, "learning_rate": 4.488276553106213e-05, "loss": 2.2833, "step": 10420 }, { "epoch": 0.17, "learning_rate": 4.487775551102205e-05, "loss": 2.2356, "step": 10430 }, { "epoch": 0.17, "learning_rate": 4.487274549098197e-05, "loss": 2.2689, "step": 10440 }, { "epoch": 0.17, "learning_rate": 4.486773547094188e-05, "loss": 2.2166, "step": 10450 }, { "epoch": 0.17, "learning_rate": 4.48627254509018e-05, "loss": 2.2324, "step": 10460 }, { "epoch": 0.17, "learning_rate": 4.485771543086172e-05, "loss": 2.2377, "step": 10470 }, { "epoch": 0.17, "learning_rate": 4.4852705410821644e-05, "loss": 2.2586, "step": 10480 }, { "epoch": 0.17, "learning_rate": 4.4847695390781565e-05, "loss": 2.265, "step": 10490 }, { "epoch": 0.17, "learning_rate": 4.4842685370741485e-05, "loss": 2.266, "step": 10500 }, { "epoch": 0.17, "learning_rate": 4.48376753507014e-05, "loss": 2.2384, "step": 10510 }, { "epoch": 0.17, "learning_rate": 4.4832665330661327e-05, "loss": 2.2733, "step": 10520 }, { "epoch": 0.17, "learning_rate": 4.482765531062125e-05, "loss": 2.2633, "step": 10530 }, { "epoch": 0.17, "learning_rate": 4.482264529058117e-05, "loss": 2.3203, "step": 10540 }, { "epoch": 0.17, "learning_rate": 4.481763527054109e-05, "loss": 2.277, "step": 10550 }, { "epoch": 0.17, "learning_rate": 4.481262525050101e-05, "loss": 2.2732, "step": 10560 }, { "epoch": 0.17, "learning_rate": 4.480761523046092e-05, "loss": 2.2408, "step": 10570 }, { "epoch": 0.17, "learning_rate": 4.4802605210420844e-05, "loss": 2.2703, "step": 10580 }, { "epoch": 0.17, "learning_rate": 4.4797595190380764e-05, "loss": 2.2518, "step": 10590 }, { "epoch": 0.17, "learning_rate": 4.4792585170340685e-05, "loss": 2.245, "step": 10600 }, { "epoch": 0.17, "learning_rate": 4.4787575150300605e-05, "loss": 2.2411, "step": 10610 }, { "epoch": 0.17, "learning_rate": 4.4782565130260526e-05, "loss": 2.2979, "step": 10620 }, { "epoch": 0.17, "learning_rate": 4.477755511022044e-05, "loss": 2.2661, "step": 10630 }, { "epoch": 0.17, "learning_rate": 4.477254509018036e-05, "loss": 2.251, "step": 10640 }, { "epoch": 0.17, "learning_rate": 4.476753507014028e-05, "loss": 2.2383, "step": 10650 }, { "epoch": 0.17, "learning_rate": 4.47625250501002e-05, "loss": 2.2522, "step": 10660 }, { "epoch": 0.17, "learning_rate": 4.475751503006012e-05, "loss": 2.2101, "step": 10670 }, { "epoch": 0.17, "learning_rate": 4.475250501002004e-05, "loss": 2.224, "step": 10680 }, { "epoch": 0.17, "learning_rate": 4.474749498997996e-05, "loss": 2.2329, "step": 10690 }, { "epoch": 0.17, "learning_rate": 4.474248496993988e-05, "loss": 2.2687, "step": 10700 }, { "epoch": 0.17, "learning_rate": 4.47374749498998e-05, "loss": 2.2843, "step": 10710 }, { "epoch": 0.18, "learning_rate": 4.4732464929859726e-05, "loss": 2.2809, "step": 10720 }, { "epoch": 0.18, "learning_rate": 4.4727454909819646e-05, "loss": 2.3166, "step": 10730 }, { "epoch": 0.18, "learning_rate": 4.472244488977956e-05, "loss": 2.2625, "step": 10740 }, { "epoch": 0.18, "learning_rate": 4.471743486973948e-05, "loss": 2.2539, "step": 10750 }, { "epoch": 0.18, "learning_rate": 4.47124248496994e-05, "loss": 2.1672, "step": 10760 }, { "epoch": 0.18, "learning_rate": 4.470741482965932e-05, "loss": 2.2726, "step": 10770 }, { "epoch": 0.18, "learning_rate": 4.470240480961924e-05, "loss": 2.2986, "step": 10780 }, { "epoch": 0.18, "learning_rate": 4.4697394789579163e-05, "loss": 2.2308, "step": 10790 }, { "epoch": 0.18, "learning_rate": 4.469238476953908e-05, "loss": 2.2717, "step": 10800 }, { "epoch": 0.18, "learning_rate": 4.4687374749499e-05, "loss": 2.2793, "step": 10810 }, { "epoch": 0.18, "learning_rate": 4.468236472945892e-05, "loss": 2.2545, "step": 10820 }, { "epoch": 0.18, "learning_rate": 4.467735470941884e-05, "loss": 2.2144, "step": 10830 }, { "epoch": 0.18, "learning_rate": 4.467234468937876e-05, "loss": 2.1916, "step": 10840 }, { "epoch": 0.18, "learning_rate": 4.466733466933868e-05, "loss": 2.2818, "step": 10850 }, { "epoch": 0.18, "learning_rate": 4.46623246492986e-05, "loss": 2.2411, "step": 10860 }, { "epoch": 0.18, "learning_rate": 4.4657314629258515e-05, "loss": 2.2517, "step": 10870 }, { "epoch": 0.18, "learning_rate": 4.4652304609218436e-05, "loss": 2.27, "step": 10880 }, { "epoch": 0.18, "learning_rate": 4.4647294589178356e-05, "loss": 2.3062, "step": 10890 }, { "epoch": 0.18, "learning_rate": 4.464228456913828e-05, "loss": 2.261, "step": 10900 }, { "epoch": 0.18, "learning_rate": 4.46372745490982e-05, "loss": 2.2555, "step": 10910 }, { "epoch": 0.18, "learning_rate": 4.463226452905812e-05, "loss": 2.2923, "step": 10920 }, { "epoch": 0.18, "learning_rate": 4.462725450901804e-05, "loss": 2.268, "step": 10930 }, { "epoch": 0.18, "learning_rate": 4.462224448897796e-05, "loss": 2.2307, "step": 10940 }, { "epoch": 0.18, "learning_rate": 4.461723446893788e-05, "loss": 2.2728, "step": 10950 }, { "epoch": 0.18, "learning_rate": 4.46122244488978e-05, "loss": 2.2139, "step": 10960 }, { "epoch": 0.18, "learning_rate": 4.460721442885772e-05, "loss": 2.2437, "step": 10970 }, { "epoch": 0.18, "learning_rate": 4.4602204408817635e-05, "loss": 2.2622, "step": 10980 }, { "epoch": 0.18, "learning_rate": 4.4597194388777556e-05, "loss": 2.253, "step": 10990 }, { "epoch": 0.18, "learning_rate": 4.459218436873748e-05, "loss": 2.2314, "step": 11000 }, { "epoch": 0.18, "eval_loss": 2.207533836364746, "eval_mean_f1": 0.6292511048458166, "eval_rouge1_f1": 0.6941017454197735, "eval_rouge1_precision": 0.8124948201037495, "eval_rouge1_recall": 0.6366505655118473, "eval_rouge2_f1": 0.5346652353796395, "eval_rouge2_precision": 0.6277681452119928, "eval_rouge2_recall": 0.4908260238505425, "eval_rougeL_f1": 0.6589863337380368, "eval_rougeL_precision": 0.7685202975432326, "eval_rougeL_recall": 0.6058162292780955, "eval_runtime": 63.481, "eval_samples_per_second": 16.131, "eval_steps_per_second": 2.016, "step": 11000 }, { "epoch": 0.18, "learning_rate": 4.45871743486974e-05, "loss": 2.2554, "step": 11010 }, { "epoch": 0.18, "learning_rate": 4.458216432865732e-05, "loss": 2.2377, "step": 11020 }, { "epoch": 0.18, "learning_rate": 4.457715430861724e-05, "loss": 2.2613, "step": 11030 }, { "epoch": 0.18, "learning_rate": 4.457214428857715e-05, "loss": 2.2603, "step": 11040 }, { "epoch": 0.18, "learning_rate": 4.456713426853707e-05, "loss": 2.2737, "step": 11050 }, { "epoch": 0.18, "learning_rate": 4.4562124248496994e-05, "loss": 2.2761, "step": 11060 }, { "epoch": 0.18, "learning_rate": 4.4557114228456914e-05, "loss": 2.2314, "step": 11070 }, { "epoch": 0.18, "learning_rate": 4.4552104208416835e-05, "loss": 2.3111, "step": 11080 }, { "epoch": 0.18, "learning_rate": 4.4547094188376756e-05, "loss": 2.2589, "step": 11090 }, { "epoch": 0.18, "learning_rate": 4.4542084168336676e-05, "loss": 2.2812, "step": 11100 }, { "epoch": 0.18, "learning_rate": 4.45370741482966e-05, "loss": 2.2917, "step": 11110 }, { "epoch": 0.18, "learning_rate": 4.453206412825652e-05, "loss": 2.2491, "step": 11120 }, { "epoch": 0.18, "learning_rate": 4.452705410821644e-05, "loss": 2.1732, "step": 11130 }, { "epoch": 0.18, "learning_rate": 4.452204408817636e-05, "loss": 2.2487, "step": 11140 }, { "epoch": 0.18, "learning_rate": 4.451703406813628e-05, "loss": 2.2516, "step": 11150 }, { "epoch": 0.18, "learning_rate": 4.451202404809619e-05, "loss": 2.2458, "step": 11160 }, { "epoch": 0.18, "learning_rate": 4.4507014028056114e-05, "loss": 2.2557, "step": 11170 }, { "epoch": 0.18, "learning_rate": 4.4502004008016035e-05, "loss": 2.2055, "step": 11180 }, { "epoch": 0.18, "learning_rate": 4.4496993987975955e-05, "loss": 2.2558, "step": 11190 }, { "epoch": 0.18, "learning_rate": 4.4491983967935876e-05, "loss": 2.2297, "step": 11200 }, { "epoch": 0.18, "learning_rate": 4.4486973947895797e-05, "loss": 2.2587, "step": 11210 }, { "epoch": 0.18, "learning_rate": 4.448196392785571e-05, "loss": 2.2552, "step": 11220 }, { "epoch": 0.18, "learning_rate": 4.447695390781563e-05, "loss": 2.2965, "step": 11230 }, { "epoch": 0.18, "learning_rate": 4.447194388777555e-05, "loss": 2.2532, "step": 11240 }, { "epoch": 0.18, "learning_rate": 4.446693386773547e-05, "loss": 2.2196, "step": 11250 }, { "epoch": 0.18, "learning_rate": 4.446192384769539e-05, "loss": 2.2819, "step": 11260 }, { "epoch": 0.18, "learning_rate": 4.4456913827655314e-05, "loss": 2.2644, "step": 11270 }, { "epoch": 0.18, "learning_rate": 4.445190380761523e-05, "loss": 2.2876, "step": 11280 }, { "epoch": 0.18, "learning_rate": 4.444689378757515e-05, "loss": 2.2647, "step": 11290 }, { "epoch": 0.18, "learning_rate": 4.444188376753507e-05, "loss": 2.2242, "step": 11300 }, { "epoch": 0.18, "learning_rate": 4.4436873747494996e-05, "loss": 2.241, "step": 11310 }, { "epoch": 0.18, "learning_rate": 4.443186372745492e-05, "loss": 2.2223, "step": 11320 }, { "epoch": 0.19, "learning_rate": 4.442685370741483e-05, "loss": 2.2406, "step": 11330 }, { "epoch": 0.19, "learning_rate": 4.442184368737475e-05, "loss": 2.2456, "step": 11340 }, { "epoch": 0.19, "learning_rate": 4.441683366733467e-05, "loss": 2.258, "step": 11350 }, { "epoch": 0.19, "learning_rate": 4.441182364729459e-05, "loss": 2.2612, "step": 11360 }, { "epoch": 0.19, "learning_rate": 4.440681362725451e-05, "loss": 2.2733, "step": 11370 }, { "epoch": 0.19, "learning_rate": 4.4401803607214434e-05, "loss": 2.276, "step": 11380 }, { "epoch": 0.19, "learning_rate": 4.4396793587174355e-05, "loss": 2.2117, "step": 11390 }, { "epoch": 0.19, "learning_rate": 4.439178356713427e-05, "loss": 2.2134, "step": 11400 }, { "epoch": 0.19, "learning_rate": 4.438677354709419e-05, "loss": 2.2272, "step": 11410 }, { "epoch": 0.19, "learning_rate": 4.438176352705411e-05, "loss": 2.2716, "step": 11420 }, { "epoch": 0.19, "learning_rate": 4.437675350701403e-05, "loss": 2.2717, "step": 11430 }, { "epoch": 0.19, "learning_rate": 4.437174348697395e-05, "loss": 2.2122, "step": 11440 }, { "epoch": 0.19, "learning_rate": 4.436673346693387e-05, "loss": 2.2551, "step": 11450 }, { "epoch": 0.19, "learning_rate": 4.4361723446893785e-05, "loss": 2.2244, "step": 11460 }, { "epoch": 0.19, "learning_rate": 4.4356713426853706e-05, "loss": 2.2041, "step": 11470 }, { "epoch": 0.19, "learning_rate": 4.435170340681363e-05, "loss": 2.237, "step": 11480 }, { "epoch": 0.19, "learning_rate": 4.434669338677355e-05, "loss": 2.2247, "step": 11490 }, { "epoch": 0.19, "learning_rate": 4.434168336673347e-05, "loss": 2.3052, "step": 11500 }, { "epoch": 0.19, "learning_rate": 4.433667334669339e-05, "loss": 2.179, "step": 11510 }, { "epoch": 0.19, "learning_rate": 4.433166332665331e-05, "loss": 2.2597, "step": 11520 }, { "epoch": 0.19, "learning_rate": 4.432665330661323e-05, "loss": 2.2693, "step": 11530 }, { "epoch": 0.19, "learning_rate": 4.432164328657315e-05, "loss": 2.2434, "step": 11540 }, { "epoch": 0.19, "learning_rate": 4.431663326653307e-05, "loss": 2.2531, "step": 11550 }, { "epoch": 0.19, "learning_rate": 4.431162324649299e-05, "loss": 2.2702, "step": 11560 }, { "epoch": 0.19, "learning_rate": 4.4306613226452906e-05, "loss": 2.2481, "step": 11570 }, { "epoch": 0.19, "learning_rate": 4.4301603206412826e-05, "loss": 2.228, "step": 11580 }, { "epoch": 0.19, "learning_rate": 4.429659318637275e-05, "loss": 2.2123, "step": 11590 }, { "epoch": 0.19, "learning_rate": 4.429158316633267e-05, "loss": 2.2288, "step": 11600 }, { "epoch": 0.19, "learning_rate": 4.428657314629259e-05, "loss": 2.2691, "step": 11610 }, { "epoch": 0.19, "learning_rate": 4.428156312625251e-05, "loss": 2.2173, "step": 11620 }, { "epoch": 0.19, "learning_rate": 4.427655310621242e-05, "loss": 2.2664, "step": 11630 }, { "epoch": 0.19, "learning_rate": 4.4271543086172343e-05, "loss": 2.2744, "step": 11640 }, { "epoch": 0.19, "learning_rate": 4.4266533066132264e-05, "loss": 2.3228, "step": 11650 }, { "epoch": 0.19, "learning_rate": 4.4261523046092185e-05, "loss": 2.2558, "step": 11660 }, { "epoch": 0.19, "learning_rate": 4.4256513026052105e-05, "loss": 2.2429, "step": 11670 }, { "epoch": 0.19, "learning_rate": 4.4251503006012026e-05, "loss": 2.2711, "step": 11680 }, { "epoch": 0.19, "learning_rate": 4.424649298597195e-05, "loss": 2.2086, "step": 11690 }, { "epoch": 0.19, "learning_rate": 4.424148296593187e-05, "loss": 2.2375, "step": 11700 }, { "epoch": 0.19, "learning_rate": 4.423647294589179e-05, "loss": 2.2339, "step": 11710 }, { "epoch": 0.19, "learning_rate": 4.423146292585171e-05, "loss": 2.2589, "step": 11720 }, { "epoch": 0.19, "learning_rate": 4.422645290581163e-05, "loss": 2.2661, "step": 11730 }, { "epoch": 0.19, "learning_rate": 4.422144288577155e-05, "loss": 2.268, "step": 11740 }, { "epoch": 0.19, "learning_rate": 4.4216432865731464e-05, "loss": 2.2471, "step": 11750 }, { "epoch": 0.19, "learning_rate": 4.4211422845691384e-05, "loss": 2.1826, "step": 11760 }, { "epoch": 0.19, "learning_rate": 4.4206412825651305e-05, "loss": 2.2044, "step": 11770 }, { "epoch": 0.19, "learning_rate": 4.4201402805611226e-05, "loss": 2.1963, "step": 11780 }, { "epoch": 0.19, "learning_rate": 4.4196392785571146e-05, "loss": 2.2794, "step": 11790 }, { "epoch": 0.19, "learning_rate": 4.419138276553107e-05, "loss": 2.1781, "step": 11800 }, { "epoch": 0.19, "learning_rate": 4.418637274549098e-05, "loss": 2.1863, "step": 11810 }, { "epoch": 0.19, "learning_rate": 4.41813627254509e-05, "loss": 2.241, "step": 11820 }, { "epoch": 0.19, "learning_rate": 4.417635270541082e-05, "loss": 2.2489, "step": 11830 }, { "epoch": 0.19, "learning_rate": 4.417134268537074e-05, "loss": 2.2406, "step": 11840 }, { "epoch": 0.19, "learning_rate": 4.416633266533066e-05, "loss": 2.2254, "step": 11850 }, { "epoch": 0.19, "learning_rate": 4.4161322645290584e-05, "loss": 2.2455, "step": 11860 }, { "epoch": 0.19, "learning_rate": 4.41563126252505e-05, "loss": 2.2167, "step": 11870 }, { "epoch": 0.19, "learning_rate": 4.415130260521042e-05, "loss": 2.2873, "step": 11880 }, { "epoch": 0.19, "learning_rate": 4.414629258517034e-05, "loss": 2.2929, "step": 11890 }, { "epoch": 0.19, "learning_rate": 4.4141282565130267e-05, "loss": 2.2732, "step": 11900 }, { "epoch": 0.19, "learning_rate": 4.413627254509019e-05, "loss": 2.2415, "step": 11910 }, { "epoch": 0.19, "learning_rate": 4.41312625250501e-05, "loss": 2.1995, "step": 11920 }, { "epoch": 0.19, "learning_rate": 4.412625250501002e-05, "loss": 2.2293, "step": 11930 }, { "epoch": 0.2, "learning_rate": 4.412124248496994e-05, "loss": 2.2513, "step": 11940 }, { "epoch": 0.2, "learning_rate": 4.411623246492986e-05, "loss": 2.2789, "step": 11950 }, { "epoch": 0.2, "learning_rate": 4.4111222444889784e-05, "loss": 2.2285, "step": 11960 }, { "epoch": 0.2, "learning_rate": 4.4106212424849704e-05, "loss": 2.251, "step": 11970 }, { "epoch": 0.2, "learning_rate": 4.4101202404809625e-05, "loss": 2.2657, "step": 11980 }, { "epoch": 0.2, "learning_rate": 4.409619238476954e-05, "loss": 2.1634, "step": 11990 }, { "epoch": 0.2, "learning_rate": 4.409118236472946e-05, "loss": 2.2035, "step": 12000 }, { "epoch": 0.2, "eval_loss": 2.197719097137451, "eval_mean_f1": 0.6279056029805172, "eval_rouge1_f1": 0.6914146932817765, "eval_rouge1_precision": 0.8029751832066137, "eval_rouge1_recall": 0.6383175038815738, "eval_rouge2_f1": 0.5345544599753311, "eval_rouge2_precision": 0.6225231128734552, "eval_rouge2_recall": 0.49406057529903646, "eval_rougeL_f1": 0.6577476556844443, "eval_rougeL_precision": 0.7606319907338116, "eval_rougeL_recall": 0.6088338070760053, "eval_runtime": 64.3818, "eval_samples_per_second": 15.905, "eval_steps_per_second": 1.988, "step": 12000 }, { "epoch": 0.2, "learning_rate": 4.408617234468938e-05, "loss": 2.2326, "step": 12010 }, { "epoch": 0.2, "learning_rate": 4.40811623246493e-05, "loss": 2.2138, "step": 12020 }, { "epoch": 0.2, "learning_rate": 4.407615230460922e-05, "loss": 2.2166, "step": 12030 }, { "epoch": 0.2, "learning_rate": 4.407114228456914e-05, "loss": 2.2762, "step": 12040 }, { "epoch": 0.2, "learning_rate": 4.4066132264529056e-05, "loss": 2.1643, "step": 12050 }, { "epoch": 0.2, "learning_rate": 4.4061122244488977e-05, "loss": 2.2944, "step": 12060 }, { "epoch": 0.2, "learning_rate": 4.40561122244489e-05, "loss": 2.2195, "step": 12070 }, { "epoch": 0.2, "learning_rate": 4.405110220440882e-05, "loss": 2.2421, "step": 12080 }, { "epoch": 0.2, "learning_rate": 4.404609218436874e-05, "loss": 2.2532, "step": 12090 }, { "epoch": 0.2, "learning_rate": 4.404108216432866e-05, "loss": 2.2244, "step": 12100 }, { "epoch": 0.2, "learning_rate": 4.403607214428858e-05, "loss": 2.2434, "step": 12110 }, { "epoch": 0.2, "learning_rate": 4.40310621242485e-05, "loss": 2.2238, "step": 12120 }, { "epoch": 0.2, "learning_rate": 4.402605210420842e-05, "loss": 2.2538, "step": 12130 }, { "epoch": 0.2, "learning_rate": 4.402104208416834e-05, "loss": 2.2439, "step": 12140 }, { "epoch": 0.2, "learning_rate": 4.401603206412826e-05, "loss": 2.2134, "step": 12150 }, { "epoch": 0.2, "learning_rate": 4.4011022044088176e-05, "loss": 2.26, "step": 12160 }, { "epoch": 0.2, "learning_rate": 4.40060120240481e-05, "loss": 2.2513, "step": 12170 }, { "epoch": 0.2, "learning_rate": 4.400100200400802e-05, "loss": 2.2422, "step": 12180 }, { "epoch": 0.2, "learning_rate": 4.399599198396794e-05, "loss": 2.1886, "step": 12190 }, { "epoch": 0.2, "learning_rate": 4.399098196392786e-05, "loss": 2.2439, "step": 12200 }, { "epoch": 0.2, "learning_rate": 4.398597194388778e-05, "loss": 2.1962, "step": 12210 }, { "epoch": 0.2, "learning_rate": 4.39809619238477e-05, "loss": 2.2847, "step": 12220 }, { "epoch": 0.2, "learning_rate": 4.3975951903807614e-05, "loss": 2.2285, "step": 12230 }, { "epoch": 0.2, "learning_rate": 4.3970941883767535e-05, "loss": 2.2382, "step": 12240 }, { "epoch": 0.2, "learning_rate": 4.3965931863727455e-05, "loss": 2.2624, "step": 12250 }, { "epoch": 0.2, "learning_rate": 4.3960921843687376e-05, "loss": 2.2374, "step": 12260 }, { "epoch": 0.2, "learning_rate": 4.3955911823647296e-05, "loss": 2.2095, "step": 12270 }, { "epoch": 0.2, "learning_rate": 4.395090180360722e-05, "loss": 2.2996, "step": 12280 }, { "epoch": 0.2, "learning_rate": 4.394589178356714e-05, "loss": 2.2663, "step": 12290 }, { "epoch": 0.2, "learning_rate": 4.394088176352706e-05, "loss": 2.2744, "step": 12300 }, { "epoch": 0.2, "learning_rate": 4.393587174348698e-05, "loss": 2.2811, "step": 12310 }, { "epoch": 0.2, "learning_rate": 4.39308617234469e-05, "loss": 2.2244, "step": 12320 }, { "epoch": 0.2, "learning_rate": 4.392585170340682e-05, "loss": 2.207, "step": 12330 }, { "epoch": 0.2, "learning_rate": 4.3920841683366734e-05, "loss": 2.1991, "step": 12340 }, { "epoch": 0.2, "learning_rate": 4.3915831663326655e-05, "loss": 2.2917, "step": 12350 }, { "epoch": 0.2, "learning_rate": 4.3910821643286575e-05, "loss": 2.2362, "step": 12360 }, { "epoch": 0.2, "learning_rate": 4.3905811623246496e-05, "loss": 2.2636, "step": 12370 }, { "epoch": 0.2, "learning_rate": 4.390080160320642e-05, "loss": 2.2178, "step": 12380 }, { "epoch": 0.2, "learning_rate": 4.389579158316634e-05, "loss": 2.2314, "step": 12390 }, { "epoch": 0.2, "learning_rate": 4.389078156312625e-05, "loss": 2.2409, "step": 12400 }, { "epoch": 0.2, "learning_rate": 4.388577154308617e-05, "loss": 2.1896, "step": 12410 }, { "epoch": 0.2, "learning_rate": 4.388076152304609e-05, "loss": 2.2349, "step": 12420 }, { "epoch": 0.2, "learning_rate": 4.387575150300601e-05, "loss": 2.2872, "step": 12430 }, { "epoch": 0.2, "learning_rate": 4.3870741482965934e-05, "loss": 2.2356, "step": 12440 }, { "epoch": 0.2, "learning_rate": 4.3865731462925854e-05, "loss": 2.2759, "step": 12450 }, { "epoch": 0.2, "learning_rate": 4.386072144288577e-05, "loss": 2.2561, "step": 12460 }, { "epoch": 0.2, "learning_rate": 4.385571142284569e-05, "loss": 2.238, "step": 12470 }, { "epoch": 0.2, "learning_rate": 4.385070140280561e-05, "loss": 2.251, "step": 12480 }, { "epoch": 0.2, "learning_rate": 4.384569138276554e-05, "loss": 2.2542, "step": 12490 }, { "epoch": 0.2, "learning_rate": 4.384068136272546e-05, "loss": 2.2416, "step": 12500 }, { "epoch": 0.2, "learning_rate": 4.383567134268538e-05, "loss": 2.1908, "step": 12510 }, { "epoch": 0.2, "learning_rate": 4.383066132264529e-05, "loss": 2.1981, "step": 12520 }, { "epoch": 0.2, "learning_rate": 4.382565130260521e-05, "loss": 2.2603, "step": 12530 }, { "epoch": 0.2, "learning_rate": 4.3820641282565133e-05, "loss": 2.2595, "step": 12540 }, { "epoch": 0.21, "learning_rate": 4.3815631262525054e-05, "loss": 2.2231, "step": 12550 }, { "epoch": 0.21, "learning_rate": 4.3810621242484975e-05, "loss": 2.3121, "step": 12560 }, { "epoch": 0.21, "learning_rate": 4.3805611222444895e-05, "loss": 2.2462, "step": 12570 }, { "epoch": 0.21, "learning_rate": 4.380060120240481e-05, "loss": 2.227, "step": 12580 }, { "epoch": 0.21, "learning_rate": 4.379559118236473e-05, "loss": 2.1811, "step": 12590 }, { "epoch": 0.21, "learning_rate": 4.379058116232465e-05, "loss": 2.2511, "step": 12600 }, { "epoch": 0.21, "learning_rate": 4.378557114228457e-05, "loss": 2.247, "step": 12610 }, { "epoch": 0.21, "learning_rate": 4.378056112224449e-05, "loss": 2.2934, "step": 12620 }, { "epoch": 0.21, "learning_rate": 4.377555110220441e-05, "loss": 2.2273, "step": 12630 }, { "epoch": 0.21, "learning_rate": 4.3770541082164326e-05, "loss": 2.2363, "step": 12640 }, { "epoch": 0.21, "learning_rate": 4.376553106212425e-05, "loss": 2.2283, "step": 12650 }, { "epoch": 0.21, "learning_rate": 4.376052104208417e-05, "loss": 2.2326, "step": 12660 }, { "epoch": 0.21, "learning_rate": 4.375551102204409e-05, "loss": 2.2245, "step": 12670 }, { "epoch": 0.21, "learning_rate": 4.375050100200401e-05, "loss": 2.2059, "step": 12680 }, { "epoch": 0.21, "learning_rate": 4.374549098196393e-05, "loss": 2.235, "step": 12690 }, { "epoch": 0.21, "learning_rate": 4.374048096192385e-05, "loss": 2.2268, "step": 12700 }, { "epoch": 0.21, "learning_rate": 4.373547094188377e-05, "loss": 2.2116, "step": 12710 }, { "epoch": 0.21, "learning_rate": 4.373046092184369e-05, "loss": 2.2199, "step": 12720 }, { "epoch": 0.21, "learning_rate": 4.372545090180361e-05, "loss": 2.2009, "step": 12730 }, { "epoch": 0.21, "learning_rate": 4.372044088176353e-05, "loss": 2.2088, "step": 12740 }, { "epoch": 0.21, "learning_rate": 4.3715430861723447e-05, "loss": 2.2104, "step": 12750 }, { "epoch": 0.21, "learning_rate": 4.371042084168337e-05, "loss": 2.2624, "step": 12760 }, { "epoch": 0.21, "learning_rate": 4.370541082164329e-05, "loss": 2.2121, "step": 12770 }, { "epoch": 0.21, "learning_rate": 4.370040080160321e-05, "loss": 2.2616, "step": 12780 }, { "epoch": 0.21, "learning_rate": 4.369539078156313e-05, "loss": 2.2708, "step": 12790 }, { "epoch": 0.21, "learning_rate": 4.369038076152305e-05, "loss": 2.2417, "step": 12800 }, { "epoch": 0.21, "learning_rate": 4.368537074148297e-05, "loss": 2.186, "step": 12810 }, { "epoch": 0.21, "learning_rate": 4.3680360721442884e-05, "loss": 2.2461, "step": 12820 }, { "epoch": 0.21, "learning_rate": 4.3675350701402805e-05, "loss": 2.2628, "step": 12830 }, { "epoch": 0.21, "learning_rate": 4.3670340681362726e-05, "loss": 2.2326, "step": 12840 }, { "epoch": 0.21, "learning_rate": 4.3665330661322646e-05, "loss": 2.2004, "step": 12850 }, { "epoch": 0.21, "learning_rate": 4.366032064128257e-05, "loss": 2.2375, "step": 12860 }, { "epoch": 0.21, "learning_rate": 4.365531062124249e-05, "loss": 2.1834, "step": 12870 }, { "epoch": 0.21, "learning_rate": 4.365030060120241e-05, "loss": 2.3011, "step": 12880 }, { "epoch": 0.21, "learning_rate": 4.364529058116233e-05, "loss": 2.1916, "step": 12890 }, { "epoch": 0.21, "learning_rate": 4.364028056112225e-05, "loss": 2.2622, "step": 12900 }, { "epoch": 0.21, "learning_rate": 4.363527054108217e-05, "loss": 2.216, "step": 12910 }, { "epoch": 0.21, "learning_rate": 4.363026052104209e-05, "loss": 2.2614, "step": 12920 }, { "epoch": 0.21, "learning_rate": 4.3625250501002005e-05, "loss": 2.2057, "step": 12930 }, { "epoch": 0.21, "learning_rate": 4.3620240480961925e-05, "loss": 2.2464, "step": 12940 }, { "epoch": 0.21, "learning_rate": 4.3615230460921846e-05, "loss": 2.2433, "step": 12950 }, { "epoch": 0.21, "learning_rate": 4.3610220440881766e-05, "loss": 2.2578, "step": 12960 }, { "epoch": 0.21, "learning_rate": 4.360521042084169e-05, "loss": 2.2266, "step": 12970 }, { "epoch": 0.21, "learning_rate": 4.360020040080161e-05, "loss": 2.2969, "step": 12980 }, { "epoch": 0.21, "learning_rate": 4.359519038076152e-05, "loss": 2.2199, "step": 12990 }, { "epoch": 0.21, "learning_rate": 4.359018036072144e-05, "loss": 2.245, "step": 13000 }, { "epoch": 0.21, "eval_loss": 2.186551094055176, "eval_mean_f1": 0.6337331207051832, "eval_rouge1_f1": 0.6964934622279331, "eval_rouge1_precision": 0.8136435003654816, "eval_rouge1_recall": 0.6404473544851934, "eval_rouge2_f1": 0.5400785246037043, "eval_rouge2_precision": 0.6336228956590282, "eval_rouge2_recall": 0.49693575329708484, "eval_rougeL_f1": 0.6646273752839122, "eval_rougeL_precision": 0.7733658366054391, "eval_rougeL_recall": 0.6124384396478418, "eval_runtime": 67.9923, "eval_samples_per_second": 15.061, "eval_steps_per_second": 1.883, "step": 13000 }, { "epoch": 0.21, "learning_rate": 4.358517034068136e-05, "loss": 2.2188, "step": 13010 }, { "epoch": 0.21, "learning_rate": 4.3580160320641284e-05, "loss": 2.1972, "step": 13020 }, { "epoch": 0.21, "learning_rate": 4.3575150300601204e-05, "loss": 2.2451, "step": 13030 }, { "epoch": 0.21, "learning_rate": 4.3570140280561125e-05, "loss": 2.2186, "step": 13040 }, { "epoch": 0.21, "learning_rate": 4.356513026052104e-05, "loss": 2.235, "step": 13050 }, { "epoch": 0.21, "learning_rate": 4.356012024048096e-05, "loss": 2.2498, "step": 13060 }, { "epoch": 0.21, "learning_rate": 4.355511022044088e-05, "loss": 2.2409, "step": 13070 }, { "epoch": 0.21, "learning_rate": 4.355010020040081e-05, "loss": 2.2083, "step": 13080 }, { "epoch": 0.21, "learning_rate": 4.354509018036073e-05, "loss": 2.2464, "step": 13090 }, { "epoch": 0.21, "learning_rate": 4.354008016032065e-05, "loss": 2.2615, "step": 13100 }, { "epoch": 0.21, "learning_rate": 4.353507014028056e-05, "loss": 2.1759, "step": 13110 }, { "epoch": 0.21, "learning_rate": 4.353006012024048e-05, "loss": 2.2021, "step": 13120 }, { "epoch": 0.21, "learning_rate": 4.3525050100200404e-05, "loss": 2.2158, "step": 13130 }, { "epoch": 0.21, "learning_rate": 4.3520040080160324e-05, "loss": 2.1982, "step": 13140 }, { "epoch": 0.21, "learning_rate": 4.3515030060120245e-05, "loss": 2.2175, "step": 13150 }, { "epoch": 0.22, "learning_rate": 4.3510020040080166e-05, "loss": 2.2542, "step": 13160 }, { "epoch": 0.22, "learning_rate": 4.350501002004008e-05, "loss": 2.2236, "step": 13170 }, { "epoch": 0.22, "learning_rate": 4.35e-05, "loss": 2.1831, "step": 13180 }, { "epoch": 0.22, "learning_rate": 4.349498997995992e-05, "loss": 2.2959, "step": 13190 }, { "epoch": 0.22, "learning_rate": 4.348997995991984e-05, "loss": 2.2527, "step": 13200 }, { "epoch": 0.22, "learning_rate": 4.348496993987976e-05, "loss": 2.2452, "step": 13210 }, { "epoch": 0.22, "learning_rate": 4.347995991983968e-05, "loss": 2.2426, "step": 13220 }, { "epoch": 0.22, "learning_rate": 4.34749498997996e-05, "loss": 2.2256, "step": 13230 }, { "epoch": 0.22, "learning_rate": 4.346993987975952e-05, "loss": 2.2419, "step": 13240 }, { "epoch": 0.22, "learning_rate": 4.346492985971944e-05, "loss": 2.2758, "step": 13250 }, { "epoch": 0.22, "learning_rate": 4.345991983967936e-05, "loss": 2.2931, "step": 13260 }, { "epoch": 0.22, "learning_rate": 4.345490981963928e-05, "loss": 2.2001, "step": 13270 }, { "epoch": 0.22, "learning_rate": 4.34498997995992e-05, "loss": 2.2188, "step": 13280 }, { "epoch": 0.22, "learning_rate": 4.344488977955912e-05, "loss": 2.1899, "step": 13290 }, { "epoch": 0.22, "learning_rate": 4.343987975951904e-05, "loss": 2.201, "step": 13300 }, { "epoch": 0.22, "learning_rate": 4.343486973947896e-05, "loss": 2.2313, "step": 13310 }, { "epoch": 0.22, "learning_rate": 4.342985971943888e-05, "loss": 2.2429, "step": 13320 }, { "epoch": 0.22, "learning_rate": 4.34248496993988e-05, "loss": 2.2173, "step": 13330 }, { "epoch": 0.22, "learning_rate": 4.341983967935872e-05, "loss": 2.2469, "step": 13340 }, { "epoch": 0.22, "learning_rate": 4.341482965931864e-05, "loss": 2.2158, "step": 13350 }, { "epoch": 0.22, "learning_rate": 4.340981963927856e-05, "loss": 2.2467, "step": 13360 }, { "epoch": 0.22, "learning_rate": 4.340480961923848e-05, "loss": 2.2198, "step": 13370 }, { "epoch": 0.22, "learning_rate": 4.33997995991984e-05, "loss": 2.238, "step": 13380 }, { "epoch": 0.22, "learning_rate": 4.339478957915832e-05, "loss": 2.2141, "step": 13390 }, { "epoch": 0.22, "learning_rate": 4.338977955911824e-05, "loss": 2.1827, "step": 13400 }, { "epoch": 0.22, "learning_rate": 4.3384769539078155e-05, "loss": 2.2197, "step": 13410 }, { "epoch": 0.22, "learning_rate": 4.3379759519038075e-05, "loss": 2.2841, "step": 13420 }, { "epoch": 0.22, "learning_rate": 4.3374749498997996e-05, "loss": 2.2154, "step": 13430 }, { "epoch": 0.22, "learning_rate": 4.3369739478957917e-05, "loss": 2.2502, "step": 13440 }, { "epoch": 0.22, "learning_rate": 4.336472945891784e-05, "loss": 2.2635, "step": 13450 }, { "epoch": 0.22, "learning_rate": 4.335971943887776e-05, "loss": 2.2274, "step": 13460 }, { "epoch": 0.22, "learning_rate": 4.335470941883768e-05, "loss": 2.1869, "step": 13470 }, { "epoch": 0.22, "learning_rate": 4.33496993987976e-05, "loss": 2.2295, "step": 13480 }, { "epoch": 0.22, "learning_rate": 4.334468937875752e-05, "loss": 2.2217, "step": 13490 }, { "epoch": 0.22, "learning_rate": 4.333967935871744e-05, "loss": 2.2204, "step": 13500 }, { "epoch": 0.22, "learning_rate": 4.333466933867736e-05, "loss": 2.2534, "step": 13510 }, { "epoch": 0.22, "learning_rate": 4.3329659318637275e-05, "loss": 2.2173, "step": 13520 }, { "epoch": 0.22, "learning_rate": 4.3324649298597196e-05, "loss": 2.2281, "step": 13530 }, { "epoch": 0.22, "learning_rate": 4.3319639278557116e-05, "loss": 2.2367, "step": 13540 }, { "epoch": 0.22, "learning_rate": 4.331462925851704e-05, "loss": 2.2455, "step": 13550 }, { "epoch": 0.22, "learning_rate": 4.330961923847696e-05, "loss": 2.1886, "step": 13560 }, { "epoch": 0.22, "learning_rate": 4.330460921843688e-05, "loss": 2.1991, "step": 13570 }, { "epoch": 0.22, "learning_rate": 4.329959919839679e-05, "loss": 2.1922, "step": 13580 }, { "epoch": 0.22, "learning_rate": 4.329458917835671e-05, "loss": 2.1406, "step": 13590 }, { "epoch": 0.22, "learning_rate": 4.328957915831663e-05, "loss": 2.2115, "step": 13600 }, { "epoch": 0.22, "learning_rate": 4.3284569138276554e-05, "loss": 2.2297, "step": 13610 }, { "epoch": 0.22, "learning_rate": 4.3279559118236475e-05, "loss": 2.2584, "step": 13620 }, { "epoch": 0.22, "learning_rate": 4.3274549098196395e-05, "loss": 2.2448, "step": 13630 }, { "epoch": 0.22, "learning_rate": 4.3269539078156316e-05, "loss": 2.1986, "step": 13640 }, { "epoch": 0.22, "learning_rate": 4.326452905811623e-05, "loss": 2.1928, "step": 13650 }, { "epoch": 0.22, "learning_rate": 4.325951903807615e-05, "loss": 2.1742, "step": 13660 }, { "epoch": 0.22, "learning_rate": 4.325450901803608e-05, "loss": 2.2676, "step": 13670 }, { "epoch": 0.22, "learning_rate": 4.3249498997996e-05, "loss": 2.2334, "step": 13680 }, { "epoch": 0.22, "learning_rate": 4.324448897795592e-05, "loss": 2.2075, "step": 13690 }, { "epoch": 0.22, "learning_rate": 4.323947895791583e-05, "loss": 2.2572, "step": 13700 }, { "epoch": 0.22, "learning_rate": 4.3234468937875754e-05, "loss": 2.226, "step": 13710 }, { "epoch": 0.22, "learning_rate": 4.3229458917835674e-05, "loss": 2.2448, "step": 13720 }, { "epoch": 0.22, "learning_rate": 4.3224448897795595e-05, "loss": 2.2204, "step": 13730 }, { "epoch": 0.22, "learning_rate": 4.3219438877755516e-05, "loss": 2.2487, "step": 13740 }, { "epoch": 0.22, "learning_rate": 4.3214428857715436e-05, "loss": 2.2543, "step": 13750 }, { "epoch": 0.22, "learning_rate": 4.320941883767535e-05, "loss": 2.2261, "step": 13760 }, { "epoch": 0.23, "learning_rate": 4.320440881763527e-05, "loss": 2.202, "step": 13770 }, { "epoch": 0.23, "learning_rate": 4.319939879759519e-05, "loss": 2.2253, "step": 13780 }, { "epoch": 0.23, "learning_rate": 4.319438877755511e-05, "loss": 2.2041, "step": 13790 }, { "epoch": 0.23, "learning_rate": 4.318937875751503e-05, "loss": 2.2622, "step": 13800 }, { "epoch": 0.23, "learning_rate": 4.318436873747495e-05, "loss": 2.2076, "step": 13810 }, { "epoch": 0.23, "learning_rate": 4.317935871743487e-05, "loss": 2.2141, "step": 13820 }, { "epoch": 0.23, "learning_rate": 4.317434869739479e-05, "loss": 2.2291, "step": 13830 }, { "epoch": 0.23, "learning_rate": 4.316933867735471e-05, "loss": 2.2412, "step": 13840 }, { "epoch": 0.23, "learning_rate": 4.316432865731463e-05, "loss": 2.1961, "step": 13850 }, { "epoch": 0.23, "learning_rate": 4.3159318637274556e-05, "loss": 2.203, "step": 13860 }, { "epoch": 0.23, "learning_rate": 4.315430861723447e-05, "loss": 2.2235, "step": 13870 }, { "epoch": 0.23, "learning_rate": 4.314929859719439e-05, "loss": 2.2029, "step": 13880 }, { "epoch": 0.23, "learning_rate": 4.314428857715431e-05, "loss": 2.226, "step": 13890 }, { "epoch": 0.23, "learning_rate": 4.313927855711423e-05, "loss": 2.2505, "step": 13900 }, { "epoch": 0.23, "learning_rate": 4.313426853707415e-05, "loss": 2.2717, "step": 13910 }, { "epoch": 0.23, "learning_rate": 4.3129258517034074e-05, "loss": 2.2129, "step": 13920 }, { "epoch": 0.23, "learning_rate": 4.3124248496993994e-05, "loss": 2.2243, "step": 13930 }, { "epoch": 0.23, "learning_rate": 4.311923847695391e-05, "loss": 2.1926, "step": 13940 }, { "epoch": 0.23, "learning_rate": 4.311422845691383e-05, "loss": 2.2236, "step": 13950 }, { "epoch": 0.23, "learning_rate": 4.310921843687375e-05, "loss": 2.1983, "step": 13960 }, { "epoch": 0.23, "learning_rate": 4.310420841683367e-05, "loss": 2.2174, "step": 13970 }, { "epoch": 0.23, "learning_rate": 4.309919839679359e-05, "loss": 2.2303, "step": 13980 }, { "epoch": 0.23, "learning_rate": 4.309418837675351e-05, "loss": 2.2222, "step": 13990 }, { "epoch": 0.23, "learning_rate": 4.3089178356713425e-05, "loss": 2.2368, "step": 14000 }, { "epoch": 0.23, "eval_loss": 2.174607753753662, "eval_mean_f1": 0.6353533230649896, "eval_rouge1_f1": 0.699177397952343, "eval_rouge1_precision": 0.8102939301813383, "eval_rouge1_recall": 0.6473838845121151, "eval_rouge2_f1": 0.5417272396684232, "eval_rouge2_precision": 0.6308664236154469, "eval_rouge2_recall": 0.5016466872999013, "eval_rougeL_f1": 0.6651553315742025, "eval_rougeL_precision": 0.7688915569038925, "eval_rougeL_recall": 0.617128696640123, "eval_runtime": 64.1886, "eval_samples_per_second": 15.953, "eval_steps_per_second": 1.994, "step": 14000 }, { "epoch": 0.23, "learning_rate": 4.3084168336673346e-05, "loss": 2.2045, "step": 14010 }, { "epoch": 0.23, "learning_rate": 4.3079158316633266e-05, "loss": 2.1709, "step": 14020 }, { "epoch": 0.23, "learning_rate": 4.307414829659319e-05, "loss": 2.205, "step": 14030 }, { "epoch": 0.23, "learning_rate": 4.306913827655311e-05, "loss": 2.2, "step": 14040 }, { "epoch": 0.23, "learning_rate": 4.306412825651303e-05, "loss": 2.2062, "step": 14050 }, { "epoch": 0.23, "learning_rate": 4.305911823647295e-05, "loss": 2.2042, "step": 14060 }, { "epoch": 0.23, "learning_rate": 4.305410821643287e-05, "loss": 2.2147, "step": 14070 }, { "epoch": 0.23, "learning_rate": 4.304909819639279e-05, "loss": 2.2046, "step": 14080 }, { "epoch": 0.23, "learning_rate": 4.304408817635271e-05, "loss": 2.1926, "step": 14090 }, { "epoch": 0.23, "learning_rate": 4.303907815631263e-05, "loss": 2.2095, "step": 14100 }, { "epoch": 0.23, "learning_rate": 4.3034068136272545e-05, "loss": 2.2484, "step": 14110 }, { "epoch": 0.23, "learning_rate": 4.3029058116232466e-05, "loss": 2.2307, "step": 14120 }, { "epoch": 0.23, "learning_rate": 4.302404809619239e-05, "loss": 2.1821, "step": 14130 }, { "epoch": 0.23, "learning_rate": 4.301903807615231e-05, "loss": 2.2197, "step": 14140 }, { "epoch": 0.23, "learning_rate": 4.301402805611223e-05, "loss": 2.1871, "step": 14150 }, { "epoch": 0.23, "learning_rate": 4.300901803607215e-05, "loss": 2.2026, "step": 14160 }, { "epoch": 0.23, "learning_rate": 4.300400801603206e-05, "loss": 2.2042, "step": 14170 }, { "epoch": 0.23, "learning_rate": 4.299899799599198e-05, "loss": 2.257, "step": 14180 }, { "epoch": 0.23, "learning_rate": 4.2993987975951904e-05, "loss": 2.1931, "step": 14190 }, { "epoch": 0.23, "learning_rate": 4.2988977955911824e-05, "loss": 2.1927, "step": 14200 }, { "epoch": 0.23, "learning_rate": 4.2983967935871745e-05, "loss": 2.1941, "step": 14210 }, { "epoch": 0.23, "learning_rate": 4.2978957915831666e-05, "loss": 2.238, "step": 14220 }, { "epoch": 0.23, "learning_rate": 4.2973947895791586e-05, "loss": 2.1937, "step": 14230 }, { "epoch": 0.23, "learning_rate": 4.29689378757515e-05, "loss": 2.2238, "step": 14240 }, { "epoch": 0.23, "learning_rate": 4.296392785571142e-05, "loss": 2.2447, "step": 14250 }, { "epoch": 0.23, "learning_rate": 4.295891783567135e-05, "loss": 2.2228, "step": 14260 }, { "epoch": 0.23, "learning_rate": 4.295390781563127e-05, "loss": 2.1911, "step": 14270 }, { "epoch": 0.23, "learning_rate": 4.294889779559119e-05, "loss": 2.2241, "step": 14280 }, { "epoch": 0.23, "learning_rate": 4.29438877755511e-05, "loss": 2.1711, "step": 14290 }, { "epoch": 0.23, "learning_rate": 4.2938877755511024e-05, "loss": 2.1803, "step": 14300 }, { "epoch": 0.23, "learning_rate": 4.2933867735470945e-05, "loss": 2.1955, "step": 14310 }, { "epoch": 0.23, "learning_rate": 4.2928857715430865e-05, "loss": 2.2129, "step": 14320 }, { "epoch": 0.23, "learning_rate": 4.2923847695390786e-05, "loss": 2.2189, "step": 14330 }, { "epoch": 0.23, "learning_rate": 4.2918837675350707e-05, "loss": 2.1907, "step": 14340 }, { "epoch": 0.23, "learning_rate": 4.291382765531062e-05, "loss": 2.2137, "step": 14350 }, { "epoch": 0.23, "learning_rate": 4.290881763527054e-05, "loss": 2.2914, "step": 14360 }, { "epoch": 0.23, "learning_rate": 4.290380761523046e-05, "loss": 2.2064, "step": 14370 }, { "epoch": 0.23, "learning_rate": 4.289879759519038e-05, "loss": 2.2296, "step": 14380 }, { "epoch": 0.24, "learning_rate": 4.28937875751503e-05, "loss": 2.2378, "step": 14390 }, { "epoch": 0.24, "learning_rate": 4.2888777555110224e-05, "loss": 2.2058, "step": 14400 }, { "epoch": 0.24, "learning_rate": 4.288376753507014e-05, "loss": 2.1753, "step": 14410 }, { "epoch": 0.24, "learning_rate": 4.287875751503006e-05, "loss": 2.1602, "step": 14420 }, { "epoch": 0.24, "learning_rate": 4.287374749498998e-05, "loss": 2.2638, "step": 14430 }, { "epoch": 0.24, "learning_rate": 4.28687374749499e-05, "loss": 2.2055, "step": 14440 }, { "epoch": 0.24, "learning_rate": 4.286372745490983e-05, "loss": 2.2081, "step": 14450 }, { "epoch": 0.24, "learning_rate": 4.285871743486974e-05, "loss": 2.2264, "step": 14460 }, { "epoch": 0.24, "learning_rate": 4.285370741482966e-05, "loss": 2.188, "step": 14470 }, { "epoch": 0.24, "learning_rate": 4.284869739478958e-05, "loss": 2.2252, "step": 14480 }, { "epoch": 0.24, "learning_rate": 4.28436873747495e-05, "loss": 2.2542, "step": 14490 }, { "epoch": 0.24, "learning_rate": 4.283867735470942e-05, "loss": 2.2201, "step": 14500 }, { "epoch": 0.24, "learning_rate": 4.2833667334669344e-05, "loss": 2.2469, "step": 14510 }, { "epoch": 0.24, "learning_rate": 4.2828657314629265e-05, "loss": 2.2305, "step": 14520 }, { "epoch": 0.24, "learning_rate": 4.282364729458918e-05, "loss": 2.2117, "step": 14530 }, { "epoch": 0.24, "learning_rate": 4.28186372745491e-05, "loss": 2.2662, "step": 14540 }, { "epoch": 0.24, "learning_rate": 4.281362725450902e-05, "loss": 2.1421, "step": 14550 }, { "epoch": 0.24, "learning_rate": 4.280861723446894e-05, "loss": 2.2392, "step": 14560 }, { "epoch": 0.24, "learning_rate": 4.280360721442886e-05, "loss": 2.2355, "step": 14570 }, { "epoch": 0.24, "learning_rate": 4.279859719438878e-05, "loss": 2.1689, "step": 14580 }, { "epoch": 0.24, "learning_rate": 4.279408817635271e-05, "loss": 2.2136, "step": 14590 }, { "epoch": 0.24, "learning_rate": 4.2789078156312625e-05, "loss": 2.2633, "step": 14600 }, { "epoch": 0.24, "learning_rate": 4.2784068136272546e-05, "loss": 2.2015, "step": 14610 }, { "epoch": 0.24, "learning_rate": 4.277905811623247e-05, "loss": 2.1737, "step": 14620 }, { "epoch": 0.24, "learning_rate": 4.277404809619239e-05, "loss": 2.2063, "step": 14630 }, { "epoch": 0.24, "learning_rate": 4.276903807615231e-05, "loss": 2.2128, "step": 14640 }, { "epoch": 0.24, "learning_rate": 4.276402805611223e-05, "loss": 2.2129, "step": 14650 }, { "epoch": 0.24, "learning_rate": 4.275901803607215e-05, "loss": 2.2093, "step": 14660 }, { "epoch": 0.24, "learning_rate": 4.275400801603206e-05, "loss": 2.2505, "step": 14670 }, { "epoch": 0.24, "learning_rate": 4.2748997995991984e-05, "loss": 2.217, "step": 14680 }, { "epoch": 0.24, "learning_rate": 4.2743987975951904e-05, "loss": 2.1838, "step": 14690 }, { "epoch": 0.24, "learning_rate": 4.2738977955911825e-05, "loss": 2.2223, "step": 14700 }, { "epoch": 0.24, "learning_rate": 4.2733967935871746e-05, "loss": 2.2638, "step": 14710 }, { "epoch": 0.24, "learning_rate": 4.2728957915831666e-05, "loss": 2.2484, "step": 14720 }, { "epoch": 0.24, "learning_rate": 4.272394789579158e-05, "loss": 2.1753, "step": 14730 }, { "epoch": 0.24, "learning_rate": 4.27189378757515e-05, "loss": 2.197, "step": 14740 }, { "epoch": 0.24, "learning_rate": 4.271392785571143e-05, "loss": 2.2016, "step": 14750 }, { "epoch": 0.24, "learning_rate": 4.270891783567135e-05, "loss": 2.2188, "step": 14760 }, { "epoch": 0.24, "learning_rate": 4.270390781563127e-05, "loss": 2.1434, "step": 14770 }, { "epoch": 0.24, "learning_rate": 4.2698897795591183e-05, "loss": 2.2379, "step": 14780 }, { "epoch": 0.24, "learning_rate": 4.2693887775551104e-05, "loss": 2.1779, "step": 14790 }, { "epoch": 0.24, "learning_rate": 4.2688877755511025e-05, "loss": 2.2378, "step": 14800 }, { "epoch": 0.24, "learning_rate": 4.2683867735470945e-05, "loss": 2.2135, "step": 14810 }, { "epoch": 0.24, "learning_rate": 4.2678857715430866e-05, "loss": 2.1748, "step": 14820 }, { "epoch": 0.24, "learning_rate": 4.267384769539079e-05, "loss": 2.2307, "step": 14830 }, { "epoch": 0.24, "learning_rate": 4.26688376753507e-05, "loss": 2.2057, "step": 14840 }, { "epoch": 0.24, "learning_rate": 4.266382765531062e-05, "loss": 2.2727, "step": 14850 }, { "epoch": 0.24, "learning_rate": 4.265881763527054e-05, "loss": 2.1915, "step": 14860 }, { "epoch": 0.24, "learning_rate": 4.265380761523046e-05, "loss": 2.14, "step": 14870 }, { "epoch": 0.24, "learning_rate": 4.264879759519038e-05, "loss": 2.1997, "step": 14880 }, { "epoch": 0.24, "learning_rate": 4.2643787575150304e-05, "loss": 2.146, "step": 14890 }, { "epoch": 0.24, "learning_rate": 4.263877755511022e-05, "loss": 2.1194, "step": 14900 }, { "epoch": 0.24, "learning_rate": 4.263376753507014e-05, "loss": 2.2166, "step": 14910 }, { "epoch": 0.24, "learning_rate": 4.262875751503006e-05, "loss": 2.2204, "step": 14920 }, { "epoch": 0.24, "learning_rate": 4.262374749498998e-05, "loss": 2.2303, "step": 14930 }, { "epoch": 0.24, "learning_rate": 4.26187374749499e-05, "loss": 2.2114, "step": 14940 }, { "epoch": 0.24, "learning_rate": 4.261372745490983e-05, "loss": 2.2209, "step": 14950 }, { "epoch": 0.24, "learning_rate": 4.260871743486974e-05, "loss": 2.2187, "step": 14960 }, { "epoch": 0.24, "learning_rate": 4.260370741482966e-05, "loss": 2.1553, "step": 14970 }, { "epoch": 0.24, "learning_rate": 4.259869739478958e-05, "loss": 2.2331, "step": 14980 }, { "epoch": 0.24, "learning_rate": 4.25936873747495e-05, "loss": 2.223, "step": 14990 }, { "epoch": 0.25, "learning_rate": 4.2588677354709424e-05, "loss": 2.1921, "step": 15000 }, { "epoch": 0.25, "eval_loss": 2.1691274642944336, "eval_mean_f1": 0.6351596512860495, "eval_rouge1_f1": 0.6966692893768138, "eval_rouge1_precision": 0.8109302393697495, "eval_rouge1_recall": 0.6415952771371278, "eval_rouge2_f1": 0.5443536946654719, "eval_rouge2_precision": 0.6380370592406726, "eval_rouge2_recall": 0.501549392027558, "eval_rougeL_f1": 0.6644559698158629, "eval_rougeL_precision": 0.7709993779868262, "eval_rougeL_recall": 0.6132239349724117, "eval_runtime": 64.227, "eval_samples_per_second": 15.943, "eval_steps_per_second": 1.993, "step": 15000 }, { "epoch": 0.25, "learning_rate": 4.2583667334669345e-05, "loss": 2.2089, "step": 15010 }, { "epoch": 0.25, "learning_rate": 4.257865731462926e-05, "loss": 2.1979, "step": 15020 }, { "epoch": 0.25, "learning_rate": 4.257364729458918e-05, "loss": 2.2376, "step": 15030 }, { "epoch": 0.25, "learning_rate": 4.25686372745491e-05, "loss": 2.1809, "step": 15040 }, { "epoch": 0.25, "learning_rate": 4.256362725450902e-05, "loss": 2.1998, "step": 15050 }, { "epoch": 0.25, "learning_rate": 4.255861723446894e-05, "loss": 2.2175, "step": 15060 }, { "epoch": 0.25, "learning_rate": 4.255360721442886e-05, "loss": 2.19, "step": 15070 }, { "epoch": 0.25, "learning_rate": 4.2548597194388776e-05, "loss": 2.2115, "step": 15080 }, { "epoch": 0.25, "learning_rate": 4.2543587174348696e-05, "loss": 2.2107, "step": 15090 }, { "epoch": 0.25, "learning_rate": 4.253857715430862e-05, "loss": 2.2271, "step": 15100 }, { "epoch": 0.25, "learning_rate": 4.253356713426854e-05, "loss": 2.1784, "step": 15110 }, { "epoch": 0.25, "learning_rate": 4.252855711422846e-05, "loss": 2.1676, "step": 15120 }, { "epoch": 0.25, "learning_rate": 4.252354709418838e-05, "loss": 2.2314, "step": 15130 }, { "epoch": 0.25, "learning_rate": 4.25185370741483e-05, "loss": 2.2373, "step": 15140 }, { "epoch": 0.25, "learning_rate": 4.251352705410822e-05, "loss": 2.2078, "step": 15150 }, { "epoch": 0.25, "learning_rate": 4.250851703406814e-05, "loss": 2.2265, "step": 15160 }, { "epoch": 0.25, "learning_rate": 4.250350701402806e-05, "loss": 2.2301, "step": 15170 }, { "epoch": 0.25, "learning_rate": 4.249849699398798e-05, "loss": 2.2208, "step": 15180 }, { "epoch": 0.25, "learning_rate": 4.2493486973947896e-05, "loss": 2.2361, "step": 15190 }, { "epoch": 0.25, "learning_rate": 4.2488476953907816e-05, "loss": 2.178, "step": 15200 }, { "epoch": 0.25, "learning_rate": 4.248346693386774e-05, "loss": 2.2014, "step": 15210 }, { "epoch": 0.25, "learning_rate": 4.247845691382766e-05, "loss": 2.2459, "step": 15220 }, { "epoch": 0.25, "learning_rate": 4.247344689378758e-05, "loss": 2.1824, "step": 15230 }, { "epoch": 0.25, "learning_rate": 4.24684368737475e-05, "loss": 2.2239, "step": 15240 }, { "epoch": 0.25, "learning_rate": 4.246342685370742e-05, "loss": 2.2266, "step": 15250 }, { "epoch": 0.25, "learning_rate": 4.2458416833667334e-05, "loss": 2.161, "step": 15260 }, { "epoch": 0.25, "learning_rate": 4.2453406813627254e-05, "loss": 2.1561, "step": 15270 }, { "epoch": 0.25, "learning_rate": 4.2448396793587175e-05, "loss": 2.2127, "step": 15280 }, { "epoch": 0.25, "learning_rate": 4.2443386773547095e-05, "loss": 2.1882, "step": 15290 }, { "epoch": 0.25, "learning_rate": 4.2438376753507016e-05, "loss": 2.1848, "step": 15300 }, { "epoch": 0.25, "learning_rate": 4.243336673346694e-05, "loss": 2.1558, "step": 15310 }, { "epoch": 0.25, "learning_rate": 4.242835671342685e-05, "loss": 2.2053, "step": 15320 }, { "epoch": 0.25, "learning_rate": 4.242334669338677e-05, "loss": 2.2363, "step": 15330 }, { "epoch": 0.25, "learning_rate": 4.24183366733467e-05, "loss": 2.1844, "step": 15340 }, { "epoch": 0.25, "learning_rate": 4.241332665330662e-05, "loss": 2.2207, "step": 15350 }, { "epoch": 0.25, "learning_rate": 4.240831663326654e-05, "loss": 2.2113, "step": 15360 }, { "epoch": 0.25, "learning_rate": 4.2403306613226454e-05, "loss": 2.1918, "step": 15370 }, { "epoch": 0.25, "learning_rate": 4.2398296593186374e-05, "loss": 2.1909, "step": 15380 }, { "epoch": 0.25, "learning_rate": 4.2393286573146295e-05, "loss": 2.2259, "step": 15390 }, { "epoch": 0.25, "learning_rate": 4.2388276553106216e-05, "loss": 2.1833, "step": 15400 }, { "epoch": 0.25, "learning_rate": 4.2383266533066136e-05, "loss": 2.252, "step": 15410 }, { "epoch": 0.25, "learning_rate": 4.237825651302606e-05, "loss": 2.2099, "step": 15420 }, { "epoch": 0.25, "learning_rate": 4.237324649298597e-05, "loss": 2.2481, "step": 15430 }, { "epoch": 0.25, "learning_rate": 4.236823647294589e-05, "loss": 2.2078, "step": 15440 }, { "epoch": 0.25, "learning_rate": 4.236322645290581e-05, "loss": 2.2239, "step": 15450 }, { "epoch": 0.25, "learning_rate": 4.235821643286573e-05, "loss": 2.1765, "step": 15460 }, { "epoch": 0.25, "learning_rate": 4.2353206412825653e-05, "loss": 2.2448, "step": 15470 }, { "epoch": 0.25, "learning_rate": 4.2348196392785574e-05, "loss": 2.2294, "step": 15480 }, { "epoch": 0.25, "learning_rate": 4.2343186372745495e-05, "loss": 2.2358, "step": 15490 }, { "epoch": 0.25, "learning_rate": 4.233817635270541e-05, "loss": 2.1856, "step": 15500 }, { "epoch": 0.25, "learning_rate": 4.233316633266533e-05, "loss": 2.2376, "step": 15510 }, { "epoch": 0.25, "learning_rate": 4.232815631262525e-05, "loss": 2.2018, "step": 15520 }, { "epoch": 0.25, "learning_rate": 4.232314629258517e-05, "loss": 2.1918, "step": 15530 }, { "epoch": 0.25, "learning_rate": 4.23181362725451e-05, "loss": 2.2002, "step": 15540 }, { "epoch": 0.25, "learning_rate": 4.231312625250501e-05, "loss": 2.2171, "step": 15550 }, { "epoch": 0.25, "learning_rate": 4.230811623246493e-05, "loss": 2.1909, "step": 15560 }, { "epoch": 0.25, "learning_rate": 4.230310621242485e-05, "loss": 2.2212, "step": 15570 }, { "epoch": 0.25, "learning_rate": 4.2298096192384774e-05, "loss": 2.1494, "step": 15580 }, { "epoch": 0.25, "learning_rate": 4.2293086172344694e-05, "loss": 2.2204, "step": 15590 }, { "epoch": 0.25, "learning_rate": 4.2288076152304615e-05, "loss": 2.221, "step": 15600 }, { "epoch": 0.26, "learning_rate": 4.228306613226453e-05, "loss": 2.1996, "step": 15610 }, { "epoch": 0.26, "learning_rate": 4.227805611222445e-05, "loss": 2.1941, "step": 15620 }, { "epoch": 0.26, "learning_rate": 4.227304609218437e-05, "loss": 2.2329, "step": 15630 }, { "epoch": 0.26, "learning_rate": 4.226803607214429e-05, "loss": 2.2066, "step": 15640 }, { "epoch": 0.26, "learning_rate": 4.226302605210421e-05, "loss": 2.2365, "step": 15650 }, { "epoch": 0.26, "learning_rate": 4.225801603206413e-05, "loss": 2.2184, "step": 15660 }, { "epoch": 0.26, "learning_rate": 4.2253006012024046e-05, "loss": 2.184, "step": 15670 }, { "epoch": 0.26, "learning_rate": 4.2247995991983967e-05, "loss": 2.1422, "step": 15680 }, { "epoch": 0.26, "learning_rate": 4.224298597194389e-05, "loss": 2.2204, "step": 15690 }, { "epoch": 0.26, "learning_rate": 4.223797595190381e-05, "loss": 2.1897, "step": 15700 }, { "epoch": 0.26, "learning_rate": 4.223296593186373e-05, "loss": 2.1288, "step": 15710 }, { "epoch": 0.26, "learning_rate": 4.222795591182365e-05, "loss": 2.2016, "step": 15720 }, { "epoch": 0.26, "learning_rate": 4.222294589178357e-05, "loss": 2.1889, "step": 15730 }, { "epoch": 0.26, "learning_rate": 4.221793587174349e-05, "loss": 2.1996, "step": 15740 }, { "epoch": 0.26, "learning_rate": 4.221292585170341e-05, "loss": 2.1563, "step": 15750 }, { "epoch": 0.26, "learning_rate": 4.220791583166333e-05, "loss": 2.2263, "step": 15760 }, { "epoch": 0.26, "learning_rate": 4.220290581162325e-05, "loss": 2.2162, "step": 15770 }, { "epoch": 0.26, "learning_rate": 4.219789579158317e-05, "loss": 2.2475, "step": 15780 }, { "epoch": 0.26, "learning_rate": 4.219288577154309e-05, "loss": 2.183, "step": 15790 }, { "epoch": 0.26, "learning_rate": 4.218787575150301e-05, "loss": 2.179, "step": 15800 }, { "epoch": 0.26, "learning_rate": 4.218286573146293e-05, "loss": 2.2452, "step": 15810 }, { "epoch": 0.26, "learning_rate": 4.217785571142285e-05, "loss": 2.174, "step": 15820 }, { "epoch": 0.26, "learning_rate": 4.217284569138277e-05, "loss": 2.1722, "step": 15830 }, { "epoch": 0.26, "learning_rate": 4.216783567134269e-05, "loss": 2.185, "step": 15840 }, { "epoch": 0.26, "learning_rate": 4.2162825651302604e-05, "loss": 2.2013, "step": 15850 }, { "epoch": 0.26, "learning_rate": 4.2157815631262525e-05, "loss": 2.2185, "step": 15860 }, { "epoch": 0.26, "learning_rate": 4.2152805611222445e-05, "loss": 2.1849, "step": 15870 }, { "epoch": 0.26, "learning_rate": 4.2147795591182366e-05, "loss": 2.206, "step": 15880 }, { "epoch": 0.26, "learning_rate": 4.2142785571142287e-05, "loss": 2.2225, "step": 15890 }, { "epoch": 0.26, "learning_rate": 4.213777555110221e-05, "loss": 2.1804, "step": 15900 }, { "epoch": 0.26, "learning_rate": 4.213276553106212e-05, "loss": 2.1628, "step": 15910 }, { "epoch": 0.26, "learning_rate": 4.212775551102204e-05, "loss": 2.1873, "step": 15920 }, { "epoch": 0.26, "learning_rate": 4.212274549098197e-05, "loss": 2.1904, "step": 15930 }, { "epoch": 0.26, "learning_rate": 4.211773547094189e-05, "loss": 2.2013, "step": 15940 }, { "epoch": 0.26, "learning_rate": 4.211272545090181e-05, "loss": 2.2459, "step": 15950 }, { "epoch": 0.26, "learning_rate": 4.2107715430861724e-05, "loss": 2.2267, "step": 15960 }, { "epoch": 0.26, "learning_rate": 4.2102705410821645e-05, "loss": 2.186, "step": 15970 }, { "epoch": 0.26, "learning_rate": 4.2097695390781565e-05, "loss": 2.1953, "step": 15980 }, { "epoch": 0.26, "learning_rate": 4.2092685370741486e-05, "loss": 2.1964, "step": 15990 }, { "epoch": 0.26, "learning_rate": 4.208767535070141e-05, "loss": 2.2238, "step": 16000 }, { "epoch": 0.26, "eval_loss": 2.168283462524414, "eval_mean_f1": 0.6306318221720145, "eval_rouge1_f1": 0.6932033368864258, "eval_rouge1_precision": 0.8046038852273776, "eval_rouge1_recall": 0.6414810314418826, "eval_rouge2_f1": 0.5382548354484037, "eval_rouge2_precision": 0.6277492709926803, "eval_rouge2_recall": 0.4979995586473147, "eval_rougeL_f1": 0.6604372941812142, "eval_rougeL_precision": 0.7644569119350832, "eval_rougeL_recall": 0.6122264443237784, "eval_runtime": 66.0304, "eval_samples_per_second": 15.508, "eval_steps_per_second": 1.939, "step": 16000 }, { "epoch": 0.26, "learning_rate": 4.208266533066133e-05, "loss": 2.2057, "step": 16010 }, { "epoch": 0.26, "learning_rate": 4.207765531062124e-05, "loss": 2.1834, "step": 16020 }, { "epoch": 0.26, "learning_rate": 4.207264529058116e-05, "loss": 2.2372, "step": 16030 }, { "epoch": 0.26, "learning_rate": 4.206763527054108e-05, "loss": 2.183, "step": 16040 }, { "epoch": 0.26, "learning_rate": 4.2062625250501e-05, "loss": 2.2119, "step": 16050 }, { "epoch": 0.26, "learning_rate": 4.2057615230460924e-05, "loss": 2.2067, "step": 16060 }, { "epoch": 0.26, "learning_rate": 4.2052605210420844e-05, "loss": 2.1546, "step": 16070 }, { "epoch": 0.26, "learning_rate": 4.2047595190380765e-05, "loss": 2.1998, "step": 16080 }, { "epoch": 0.26, "learning_rate": 4.204258517034068e-05, "loss": 2.2192, "step": 16090 }, { "epoch": 0.26, "learning_rate": 4.20375751503006e-05, "loss": 2.2141, "step": 16100 }, { "epoch": 0.26, "learning_rate": 4.203256513026052e-05, "loss": 2.2352, "step": 16110 }, { "epoch": 0.26, "learning_rate": 4.202755511022045e-05, "loss": 2.2221, "step": 16120 }, { "epoch": 0.26, "learning_rate": 4.202254509018037e-05, "loss": 2.2392, "step": 16130 }, { "epoch": 0.26, "learning_rate": 4.201753507014028e-05, "loss": 2.1908, "step": 16140 }, { "epoch": 0.26, "learning_rate": 4.20125250501002e-05, "loss": 2.2205, "step": 16150 }, { "epoch": 0.26, "learning_rate": 4.2007515030060123e-05, "loss": 2.1714, "step": 16160 }, { "epoch": 0.26, "learning_rate": 4.2002505010020044e-05, "loss": 2.1704, "step": 16170 }, { "epoch": 0.26, "learning_rate": 4.1997494989979965e-05, "loss": 2.1608, "step": 16180 }, { "epoch": 0.26, "learning_rate": 4.1992484969939885e-05, "loss": 2.1679, "step": 16190 }, { "epoch": 0.26, "learning_rate": 4.19874749498998e-05, "loss": 2.2039, "step": 16200 }, { "epoch": 0.26, "learning_rate": 4.198246492985972e-05, "loss": 2.206, "step": 16210 }, { "epoch": 0.27, "learning_rate": 4.197745490981964e-05, "loss": 2.1575, "step": 16220 }, { "epoch": 0.27, "learning_rate": 4.197244488977956e-05, "loss": 2.2048, "step": 16230 }, { "epoch": 0.27, "learning_rate": 4.196793587174349e-05, "loss": 2.2377, "step": 16240 }, { "epoch": 0.27, "learning_rate": 4.196292585170341e-05, "loss": 2.2165, "step": 16250 }, { "epoch": 0.27, "learning_rate": 4.195791583166333e-05, "loss": 2.2108, "step": 16260 }, { "epoch": 0.27, "learning_rate": 4.195290581162325e-05, "loss": 2.2024, "step": 16270 }, { "epoch": 0.27, "learning_rate": 4.194789579158317e-05, "loss": 2.1778, "step": 16280 }, { "epoch": 0.27, "learning_rate": 4.194288577154309e-05, "loss": 2.1899, "step": 16290 }, { "epoch": 0.27, "learning_rate": 4.193787575150301e-05, "loss": 2.1727, "step": 16300 }, { "epoch": 0.27, "learning_rate": 4.193286573146293e-05, "loss": 2.2141, "step": 16310 }, { "epoch": 0.27, "learning_rate": 4.192785571142285e-05, "loss": 2.2375, "step": 16320 }, { "epoch": 0.27, "learning_rate": 4.192284569138277e-05, "loss": 2.1885, "step": 16330 }, { "epoch": 0.27, "learning_rate": 4.1917835671342684e-05, "loss": 2.1648, "step": 16340 }, { "epoch": 0.27, "learning_rate": 4.1912825651302605e-05, "loss": 2.1472, "step": 16350 }, { "epoch": 0.27, "learning_rate": 4.1907815631262525e-05, "loss": 2.2599, "step": 16360 }, { "epoch": 0.27, "learning_rate": 4.1902805611222446e-05, "loss": 2.1941, "step": 16370 }, { "epoch": 0.27, "learning_rate": 4.1897795591182367e-05, "loss": 2.1996, "step": 16380 }, { "epoch": 0.27, "learning_rate": 4.189278557114229e-05, "loss": 2.2046, "step": 16390 }, { "epoch": 0.27, "learning_rate": 4.18877755511022e-05, "loss": 2.2268, "step": 16400 }, { "epoch": 0.27, "learning_rate": 4.188276553106212e-05, "loss": 2.2105, "step": 16410 }, { "epoch": 0.27, "learning_rate": 4.187775551102205e-05, "loss": 2.2097, "step": 16420 }, { "epoch": 0.27, "learning_rate": 4.187274549098197e-05, "loss": 2.2895, "step": 16430 }, { "epoch": 0.27, "learning_rate": 4.186773547094189e-05, "loss": 2.2034, "step": 16440 }, { "epoch": 0.27, "learning_rate": 4.1862725450901804e-05, "loss": 2.1979, "step": 16450 }, { "epoch": 0.27, "learning_rate": 4.1857715430861725e-05, "loss": 2.1827, "step": 16460 }, { "epoch": 0.27, "learning_rate": 4.1852705410821646e-05, "loss": 2.1444, "step": 16470 }, { "epoch": 0.27, "learning_rate": 4.1847695390781566e-05, "loss": 2.1751, "step": 16480 }, { "epoch": 0.27, "learning_rate": 4.184268537074149e-05, "loss": 2.2268, "step": 16490 }, { "epoch": 0.27, "learning_rate": 4.183767535070141e-05, "loss": 2.1813, "step": 16500 }, { "epoch": 0.27, "learning_rate": 4.183266533066133e-05, "loss": 2.2112, "step": 16510 }, { "epoch": 0.27, "learning_rate": 4.182765531062124e-05, "loss": 2.1975, "step": 16520 }, { "epoch": 0.27, "learning_rate": 4.182264529058116e-05, "loss": 2.2213, "step": 16530 }, { "epoch": 0.27, "learning_rate": 4.181763527054108e-05, "loss": 2.1988, "step": 16540 }, { "epoch": 0.27, "learning_rate": 4.1812625250501004e-05, "loss": 2.1845, "step": 16550 }, { "epoch": 0.27, "learning_rate": 4.1807615230460925e-05, "loss": 2.1951, "step": 16560 }, { "epoch": 0.27, "learning_rate": 4.1802605210420845e-05, "loss": 2.1732, "step": 16570 }, { "epoch": 0.27, "learning_rate": 4.179759519038076e-05, "loss": 2.1865, "step": 16580 }, { "epoch": 0.27, "learning_rate": 4.179258517034068e-05, "loss": 2.1492, "step": 16590 }, { "epoch": 0.27, "learning_rate": 4.17875751503006e-05, "loss": 2.2006, "step": 16600 }, { "epoch": 0.27, "learning_rate": 4.178256513026052e-05, "loss": 2.164, "step": 16610 }, { "epoch": 0.27, "learning_rate": 4.177755511022045e-05, "loss": 2.2174, "step": 16620 }, { "epoch": 0.27, "learning_rate": 4.177254509018036e-05, "loss": 2.2082, "step": 16630 }, { "epoch": 0.27, "learning_rate": 4.176753507014028e-05, "loss": 2.2331, "step": 16640 }, { "epoch": 0.27, "learning_rate": 4.1762525050100204e-05, "loss": 2.2246, "step": 16650 }, { "epoch": 0.27, "learning_rate": 4.1757515030060124e-05, "loss": 2.1883, "step": 16660 }, { "epoch": 0.27, "learning_rate": 4.1752505010020045e-05, "loss": 2.1849, "step": 16670 }, { "epoch": 0.27, "learning_rate": 4.1747494989979965e-05, "loss": 2.1427, "step": 16680 }, { "epoch": 0.27, "learning_rate": 4.174248496993988e-05, "loss": 2.1945, "step": 16690 }, { "epoch": 0.27, "learning_rate": 4.17374749498998e-05, "loss": 2.2231, "step": 16700 }, { "epoch": 0.27, "learning_rate": 4.173246492985972e-05, "loss": 2.2125, "step": 16710 }, { "epoch": 0.27, "learning_rate": 4.172745490981964e-05, "loss": 2.1532, "step": 16720 }, { "epoch": 0.27, "learning_rate": 4.172244488977956e-05, "loss": 2.2245, "step": 16730 }, { "epoch": 0.27, "learning_rate": 4.171743486973948e-05, "loss": 2.1865, "step": 16740 }, { "epoch": 0.27, "learning_rate": 4.171292585170341e-05, "loss": 2.2192, "step": 16750 }, { "epoch": 0.27, "learning_rate": 4.170791583166333e-05, "loss": 2.1731, "step": 16760 }, { "epoch": 0.27, "learning_rate": 4.170290581162325e-05, "loss": 2.1776, "step": 16770 }, { "epoch": 0.27, "learning_rate": 4.169789579158317e-05, "loss": 2.201, "step": 16780 }, { "epoch": 0.27, "learning_rate": 4.169288577154309e-05, "loss": 2.1446, "step": 16790 }, { "epoch": 0.27, "learning_rate": 4.168787575150301e-05, "loss": 2.1855, "step": 16800 }, { "epoch": 0.27, "learning_rate": 4.168286573146293e-05, "loss": 2.19, "step": 16810 }, { "epoch": 0.27, "learning_rate": 4.167785571142285e-05, "loss": 2.2245, "step": 16820 }, { "epoch": 0.28, "learning_rate": 4.1672845691382764e-05, "loss": 2.199, "step": 16830 }, { "epoch": 0.28, "learning_rate": 4.1667835671342685e-05, "loss": 2.1834, "step": 16840 }, { "epoch": 0.28, "learning_rate": 4.1662825651302605e-05, "loss": 2.2065, "step": 16850 }, { "epoch": 0.28, "learning_rate": 4.1657815631262526e-05, "loss": 2.1715, "step": 16860 }, { "epoch": 0.28, "learning_rate": 4.165280561122245e-05, "loss": 2.2016, "step": 16870 }, { "epoch": 0.28, "learning_rate": 4.164779559118237e-05, "loss": 2.2176, "step": 16880 }, { "epoch": 0.28, "learning_rate": 4.164278557114228e-05, "loss": 2.2243, "step": 16890 }, { "epoch": 0.28, "learning_rate": 4.16377755511022e-05, "loss": 2.1739, "step": 16900 }, { "epoch": 0.28, "learning_rate": 4.163276553106213e-05, "loss": 2.2083, "step": 16910 }, { "epoch": 0.28, "learning_rate": 4.162775551102205e-05, "loss": 2.1725, "step": 16920 }, { "epoch": 0.28, "learning_rate": 4.162274549098197e-05, "loss": 2.1766, "step": 16930 }, { "epoch": 0.28, "learning_rate": 4.1617735470941884e-05, "loss": 2.221, "step": 16940 }, { "epoch": 0.28, "learning_rate": 4.1612725450901805e-05, "loss": 2.2083, "step": 16950 }, { "epoch": 0.28, "learning_rate": 4.1607715430861726e-05, "loss": 2.1915, "step": 16960 }, { "epoch": 0.28, "learning_rate": 4.1602705410821646e-05, "loss": 2.2007, "step": 16970 }, { "epoch": 0.28, "learning_rate": 4.159769539078157e-05, "loss": 2.151, "step": 16980 }, { "epoch": 0.28, "learning_rate": 4.159268537074149e-05, "loss": 2.1754, "step": 16990 }, { "epoch": 0.28, "learning_rate": 4.158767535070141e-05, "loss": 2.1632, "step": 17000 }, { "epoch": 0.28, "eval_loss": 2.1566734313964844, "eval_mean_f1": 0.6367462938500134, "eval_rouge1_f1": 0.6982320738651453, "eval_rouge1_precision": 0.8122252782721391, "eval_rouge1_recall": 0.6438186482469835, "eval_rouge2_f1": 0.5452768723650028, "eval_rouge2_precision": 0.637637859238201, "eval_rouge2_recall": 0.5028942406401429, "eval_rougeL_f1": 0.6667299353198921, "eval_rougeL_precision": 0.7731233378995902, "eval_rougeL_recall": 0.6160813824174993, "eval_runtime": 65.2612, "eval_samples_per_second": 15.691, "eval_steps_per_second": 1.961, "step": 17000 }, { "epoch": 0.28, "learning_rate": 4.158266533066132e-05, "loss": 2.156, "step": 17010 }, { "epoch": 0.28, "learning_rate": 4.157765531062124e-05, "loss": 2.1894, "step": 17020 }, { "epoch": 0.28, "learning_rate": 4.157264529058116e-05, "loss": 2.2197, "step": 17030 }, { "epoch": 0.28, "learning_rate": 4.1567635270541084e-05, "loss": 2.1956, "step": 17040 }, { "epoch": 0.28, "learning_rate": 4.1562625250501005e-05, "loss": 2.1461, "step": 17050 }, { "epoch": 0.28, "learning_rate": 4.1557615230460925e-05, "loss": 2.1975, "step": 17060 }, { "epoch": 0.28, "learning_rate": 4.155260521042084e-05, "loss": 2.161, "step": 17070 }, { "epoch": 0.28, "learning_rate": 4.154759519038076e-05, "loss": 2.2012, "step": 17080 }, { "epoch": 0.28, "learning_rate": 4.154258517034068e-05, "loss": 2.2052, "step": 17090 }, { "epoch": 0.28, "learning_rate": 4.15375751503006e-05, "loss": 2.1685, "step": 17100 }, { "epoch": 0.28, "learning_rate": 4.153256513026053e-05, "loss": 2.1532, "step": 17110 }, { "epoch": 0.28, "learning_rate": 4.152755511022044e-05, "loss": 2.2013, "step": 17120 }, { "epoch": 0.28, "learning_rate": 4.152254509018036e-05, "loss": 2.2186, "step": 17130 }, { "epoch": 0.28, "learning_rate": 4.1517535070140284e-05, "loss": 2.2136, "step": 17140 }, { "epoch": 0.28, "learning_rate": 4.1512525050100204e-05, "loss": 2.173, "step": 17150 }, { "epoch": 0.28, "learning_rate": 4.1507515030060125e-05, "loss": 2.1569, "step": 17160 }, { "epoch": 0.28, "learning_rate": 4.1502505010020046e-05, "loss": 2.1837, "step": 17170 }, { "epoch": 0.28, "learning_rate": 4.149749498997996e-05, "loss": 2.2166, "step": 17180 }, { "epoch": 0.28, "learning_rate": 4.149248496993988e-05, "loss": 2.1768, "step": 17190 }, { "epoch": 0.28, "learning_rate": 4.14874749498998e-05, "loss": 2.21, "step": 17200 }, { "epoch": 0.28, "learning_rate": 4.148246492985972e-05, "loss": 2.192, "step": 17210 }, { "epoch": 0.28, "learning_rate": 4.147745490981964e-05, "loss": 2.1784, "step": 17220 }, { "epoch": 0.28, "learning_rate": 4.147244488977956e-05, "loss": 2.2218, "step": 17230 }, { "epoch": 0.28, "learning_rate": 4.146743486973948e-05, "loss": 2.2283, "step": 17240 }, { "epoch": 0.28, "learning_rate": 4.14624248496994e-05, "loss": 2.1539, "step": 17250 }, { "epoch": 0.28, "learning_rate": 4.145741482965932e-05, "loss": 2.165, "step": 17260 }, { "epoch": 0.28, "learning_rate": 4.145240480961924e-05, "loss": 2.1603, "step": 17270 }, { "epoch": 0.28, "learning_rate": 4.144739478957916e-05, "loss": 2.1486, "step": 17280 }, { "epoch": 0.28, "learning_rate": 4.144238476953908e-05, "loss": 2.2556, "step": 17290 }, { "epoch": 0.28, "learning_rate": 4.1437374749499e-05, "loss": 2.2201, "step": 17300 }, { "epoch": 0.28, "learning_rate": 4.143236472945892e-05, "loss": 2.1711, "step": 17310 }, { "epoch": 0.28, "learning_rate": 4.142735470941884e-05, "loss": 2.2204, "step": 17320 }, { "epoch": 0.28, "learning_rate": 4.142234468937876e-05, "loss": 2.1428, "step": 17330 }, { "epoch": 0.28, "learning_rate": 4.141733466933868e-05, "loss": 2.1832, "step": 17340 }, { "epoch": 0.28, "learning_rate": 4.1412324649298604e-05, "loss": 2.1708, "step": 17350 }, { "epoch": 0.28, "learning_rate": 4.140731462925852e-05, "loss": 2.1789, "step": 17360 }, { "epoch": 0.28, "learning_rate": 4.140230460921844e-05, "loss": 2.1745, "step": 17370 }, { "epoch": 0.28, "learning_rate": 4.139729458917836e-05, "loss": 2.1835, "step": 17380 }, { "epoch": 0.28, "learning_rate": 4.139228456913828e-05, "loss": 2.1772, "step": 17390 }, { "epoch": 0.28, "learning_rate": 4.13872745490982e-05, "loss": 2.201, "step": 17400 }, { "epoch": 0.28, "learning_rate": 4.138226452905812e-05, "loss": 2.231, "step": 17410 }, { "epoch": 0.28, "learning_rate": 4.1377254509018034e-05, "loss": 2.1875, "step": 17420 }, { "epoch": 0.28, "learning_rate": 4.1372244488977955e-05, "loss": 2.1682, "step": 17430 }, { "epoch": 0.28, "learning_rate": 4.1367234468937876e-05, "loss": 2.2226, "step": 17440 }, { "epoch": 0.29, "learning_rate": 4.1362224448897796e-05, "loss": 2.206, "step": 17450 }, { "epoch": 0.29, "learning_rate": 4.135721442885772e-05, "loss": 2.2199, "step": 17460 }, { "epoch": 0.29, "learning_rate": 4.135220440881764e-05, "loss": 2.2133, "step": 17470 }, { "epoch": 0.29, "learning_rate": 4.134719438877755e-05, "loss": 2.1391, "step": 17480 }, { "epoch": 0.29, "learning_rate": 4.134218436873747e-05, "loss": 2.1923, "step": 17490 }, { "epoch": 0.29, "learning_rate": 4.13371743486974e-05, "loss": 2.1781, "step": 17500 }, { "epoch": 0.29, "learning_rate": 4.133216432865732e-05, "loss": 2.1462, "step": 17510 }, { "epoch": 0.29, "learning_rate": 4.132715430861724e-05, "loss": 2.1848, "step": 17520 }, { "epoch": 0.29, "learning_rate": 4.132214428857716e-05, "loss": 2.1585, "step": 17530 }, { "epoch": 0.29, "learning_rate": 4.1317134268537075e-05, "loss": 2.2239, "step": 17540 }, { "epoch": 0.29, "learning_rate": 4.1312124248496996e-05, "loss": 2.193, "step": 17550 }, { "epoch": 0.29, "learning_rate": 4.130711422845692e-05, "loss": 2.1698, "step": 17560 }, { "epoch": 0.29, "learning_rate": 4.130210420841684e-05, "loss": 2.1784, "step": 17570 }, { "epoch": 0.29, "learning_rate": 4.129709418837676e-05, "loss": 2.1902, "step": 17580 }, { "epoch": 0.29, "learning_rate": 4.129208416833668e-05, "loss": 2.1567, "step": 17590 }, { "epoch": 0.29, "learning_rate": 4.128707414829659e-05, "loss": 2.1786, "step": 17600 }, { "epoch": 0.29, "learning_rate": 4.128206412825651e-05, "loss": 2.1762, "step": 17610 }, { "epoch": 0.29, "learning_rate": 4.1277054108216434e-05, "loss": 2.158, "step": 17620 }, { "epoch": 0.29, "learning_rate": 4.1272545090180364e-05, "loss": 2.1995, "step": 17630 }, { "epoch": 0.29, "learning_rate": 4.1267535070140284e-05, "loss": 2.232, "step": 17640 }, { "epoch": 0.29, "learning_rate": 4.1262525050100205e-05, "loss": 2.1786, "step": 17650 }, { "epoch": 0.29, "learning_rate": 4.1257515030060126e-05, "loss": 2.2392, "step": 17660 }, { "epoch": 0.29, "learning_rate": 4.125250501002004e-05, "loss": 2.2222, "step": 17670 }, { "epoch": 0.29, "learning_rate": 4.124749498997996e-05, "loss": 2.1865, "step": 17680 }, { "epoch": 0.29, "learning_rate": 4.124248496993988e-05, "loss": 2.1559, "step": 17690 }, { "epoch": 0.29, "learning_rate": 4.12374749498998e-05, "loss": 2.1931, "step": 17700 }, { "epoch": 0.29, "learning_rate": 4.123246492985972e-05, "loss": 2.2055, "step": 17710 }, { "epoch": 0.29, "learning_rate": 4.122745490981964e-05, "loss": 2.1988, "step": 17720 }, { "epoch": 0.29, "learning_rate": 4.122244488977956e-05, "loss": 2.2231, "step": 17730 }, { "epoch": 0.29, "learning_rate": 4.121743486973948e-05, "loss": 2.1176, "step": 17740 }, { "epoch": 0.29, "learning_rate": 4.12124248496994e-05, "loss": 2.1913, "step": 17750 }, { "epoch": 0.29, "learning_rate": 4.120741482965932e-05, "loss": 2.1747, "step": 17760 }, { "epoch": 0.29, "learning_rate": 4.120240480961924e-05, "loss": 2.1789, "step": 17770 }, { "epoch": 0.29, "learning_rate": 4.119739478957916e-05, "loss": 2.158, "step": 17780 }, { "epoch": 0.29, "learning_rate": 4.119238476953908e-05, "loss": 2.2251, "step": 17790 }, { "epoch": 0.29, "learning_rate": 4.1187374749499e-05, "loss": 2.1383, "step": 17800 }, { "epoch": 0.29, "learning_rate": 4.118236472945892e-05, "loss": 2.1767, "step": 17810 }, { "epoch": 0.29, "learning_rate": 4.117735470941884e-05, "loss": 2.1783, "step": 17820 }, { "epoch": 0.29, "learning_rate": 4.117234468937876e-05, "loss": 2.1956, "step": 17830 }, { "epoch": 0.29, "learning_rate": 4.1167334669338684e-05, "loss": 2.1508, "step": 17840 }, { "epoch": 0.29, "learning_rate": 4.11623246492986e-05, "loss": 2.1702, "step": 17850 }, { "epoch": 0.29, "learning_rate": 4.115731462925852e-05, "loss": 2.1639, "step": 17860 }, { "epoch": 0.29, "learning_rate": 4.115230460921844e-05, "loss": 2.2048, "step": 17870 }, { "epoch": 0.29, "learning_rate": 4.114729458917836e-05, "loss": 2.1555, "step": 17880 }, { "epoch": 0.29, "learning_rate": 4.114228456913828e-05, "loss": 2.1799, "step": 17890 }, { "epoch": 0.29, "learning_rate": 4.11372745490982e-05, "loss": 2.2054, "step": 17900 }, { "epoch": 0.29, "learning_rate": 4.1132264529058115e-05, "loss": 2.1754, "step": 17910 }, { "epoch": 0.29, "learning_rate": 4.1127254509018035e-05, "loss": 2.2306, "step": 17920 }, { "epoch": 0.29, "learning_rate": 4.1122244488977956e-05, "loss": 2.2311, "step": 17930 }, { "epoch": 0.29, "learning_rate": 4.1117234468937876e-05, "loss": 2.1459, "step": 17940 }, { "epoch": 0.29, "learning_rate": 4.11122244488978e-05, "loss": 2.1358, "step": 17950 }, { "epoch": 0.29, "learning_rate": 4.110721442885772e-05, "loss": 2.1661, "step": 17960 }, { "epoch": 0.29, "learning_rate": 4.110220440881764e-05, "loss": 2.1464, "step": 17970 }, { "epoch": 0.29, "learning_rate": 4.109719438877755e-05, "loss": 2.146, "step": 17980 }, { "epoch": 0.29, "learning_rate": 4.109218436873748e-05, "loss": 2.2355, "step": 17990 }, { "epoch": 0.29, "learning_rate": 4.10871743486974e-05, "loss": 2.161, "step": 18000 }, { "epoch": 0.29, "eval_loss": 2.144771099090576, "eval_mean_f1": 0.6323481498782902, "eval_rouge1_f1": 0.6946599070865043, "eval_rouge1_precision": 0.8068673867078338, "eval_rouge1_recall": 0.6423563374105746, "eval_rouge2_f1": 0.5407534580364295, "eval_rouge2_precision": 0.6302076978468578, "eval_rouge2_recall": 0.5003823173791764, "eval_rougeL_f1": 0.661631084511937, "eval_rougeL_precision": 0.7653712468151233, "eval_rougeL_recall": 0.6129923357320519, "eval_runtime": 63.8714, "eval_samples_per_second": 16.032, "eval_steps_per_second": 2.004, "step": 18000 }, { "epoch": 0.29, "learning_rate": 4.108216432865732e-05, "loss": 2.1843, "step": 18010 }, { "epoch": 0.29, "learning_rate": 4.107715430861724e-05, "loss": 2.1234, "step": 18020 }, { "epoch": 0.29, "learning_rate": 4.1072144288577155e-05, "loss": 2.1626, "step": 18030 }, { "epoch": 0.29, "learning_rate": 4.1067134268537076e-05, "loss": 2.1695, "step": 18040 }, { "epoch": 0.29, "learning_rate": 4.1062124248497e-05, "loss": 2.1542, "step": 18050 }, { "epoch": 0.3, "learning_rate": 4.105711422845692e-05, "loss": 2.1787, "step": 18060 }, { "epoch": 0.3, "learning_rate": 4.105210420841684e-05, "loss": 2.1397, "step": 18070 }, { "epoch": 0.3, "learning_rate": 4.104709418837676e-05, "loss": 2.2113, "step": 18080 }, { "epoch": 0.3, "learning_rate": 4.104208416833667e-05, "loss": 2.2227, "step": 18090 }, { "epoch": 0.3, "learning_rate": 4.103707414829659e-05, "loss": 2.1646, "step": 18100 }, { "epoch": 0.3, "learning_rate": 4.1032064128256514e-05, "loss": 2.2245, "step": 18110 }, { "epoch": 0.3, "learning_rate": 4.1027054108216434e-05, "loss": 2.2001, "step": 18120 }, { "epoch": 0.3, "learning_rate": 4.1022044088176355e-05, "loss": 2.1604, "step": 18130 }, { "epoch": 0.3, "learning_rate": 4.1017034068136276e-05, "loss": 2.1707, "step": 18140 }, { "epoch": 0.3, "learning_rate": 4.101202404809619e-05, "loss": 2.1196, "step": 18150 }, { "epoch": 0.3, "learning_rate": 4.100701402805611e-05, "loss": 2.1812, "step": 18160 }, { "epoch": 0.3, "learning_rate": 4.100200400801603e-05, "loss": 2.1968, "step": 18170 }, { "epoch": 0.3, "learning_rate": 4.099699398797595e-05, "loss": 2.1561, "step": 18180 }, { "epoch": 0.3, "learning_rate": 4.099198396793588e-05, "loss": 2.1625, "step": 18190 }, { "epoch": 0.3, "learning_rate": 4.098697394789579e-05, "loss": 2.2011, "step": 18200 }, { "epoch": 0.3, "learning_rate": 4.0981963927855713e-05, "loss": 2.1512, "step": 18210 }, { "epoch": 0.3, "learning_rate": 4.0976953907815634e-05, "loss": 2.1665, "step": 18220 }, { "epoch": 0.3, "learning_rate": 4.0971943887775555e-05, "loss": 2.1928, "step": 18230 }, { "epoch": 0.3, "learning_rate": 4.0966933867735475e-05, "loss": 2.1984, "step": 18240 }, { "epoch": 0.3, "learning_rate": 4.0961923847695396e-05, "loss": 2.1355, "step": 18250 }, { "epoch": 0.3, "learning_rate": 4.095691382765532e-05, "loss": 2.1254, "step": 18260 }, { "epoch": 0.3, "learning_rate": 4.095190380761523e-05, "loss": 2.1897, "step": 18270 }, { "epoch": 0.3, "learning_rate": 4.094689378757515e-05, "loss": 2.2167, "step": 18280 }, { "epoch": 0.3, "learning_rate": 4.094188376753507e-05, "loss": 2.1928, "step": 18290 }, { "epoch": 0.3, "learning_rate": 4.093687374749499e-05, "loss": 2.2314, "step": 18300 }, { "epoch": 0.3, "learning_rate": 4.093186372745491e-05, "loss": 2.1707, "step": 18310 }, { "epoch": 0.3, "learning_rate": 4.0926853707414834e-05, "loss": 2.1864, "step": 18320 }, { "epoch": 0.3, "learning_rate": 4.092184368737475e-05, "loss": 2.1689, "step": 18330 }, { "epoch": 0.3, "learning_rate": 4.091683366733467e-05, "loss": 2.1809, "step": 18340 }, { "epoch": 0.3, "learning_rate": 4.091182364729459e-05, "loss": 2.2278, "step": 18350 }, { "epoch": 0.3, "learning_rate": 4.090681362725451e-05, "loss": 2.171, "step": 18360 }, { "epoch": 0.3, "learning_rate": 4.090180360721443e-05, "loss": 2.1423, "step": 18370 }, { "epoch": 0.3, "learning_rate": 4.089679358717435e-05, "loss": 2.231, "step": 18380 }, { "epoch": 0.3, "learning_rate": 4.089178356713427e-05, "loss": 2.1548, "step": 18390 }, { "epoch": 0.3, "learning_rate": 4.088677354709419e-05, "loss": 2.1695, "step": 18400 }, { "epoch": 0.3, "learning_rate": 4.088176352705411e-05, "loss": 2.1777, "step": 18410 }, { "epoch": 0.3, "learning_rate": 4.087675350701403e-05, "loss": 2.1566, "step": 18420 }, { "epoch": 0.3, "learning_rate": 4.0871743486973954e-05, "loss": 2.1496, "step": 18430 }, { "epoch": 0.3, "learning_rate": 4.086673346693387e-05, "loss": 2.1627, "step": 18440 }, { "epoch": 0.3, "learning_rate": 4.086172344689379e-05, "loss": 2.2006, "step": 18450 }, { "epoch": 0.3, "learning_rate": 4.085671342685371e-05, "loss": 2.2313, "step": 18460 }, { "epoch": 0.3, "learning_rate": 4.085170340681363e-05, "loss": 2.2078, "step": 18470 }, { "epoch": 0.3, "learning_rate": 4.084669338677355e-05, "loss": 2.1814, "step": 18480 }, { "epoch": 0.3, "learning_rate": 4.084168336673347e-05, "loss": 2.1946, "step": 18490 }, { "epoch": 0.3, "learning_rate": 4.0836673346693385e-05, "loss": 2.1393, "step": 18500 }, { "epoch": 0.3, "learning_rate": 4.0831663326653306e-05, "loss": 2.1324, "step": 18510 }, { "epoch": 0.3, "learning_rate": 4.0826653306613226e-05, "loss": 2.245, "step": 18520 }, { "epoch": 0.3, "learning_rate": 4.082164328657315e-05, "loss": 2.2, "step": 18530 }, { "epoch": 0.3, "learning_rate": 4.081663326653307e-05, "loss": 2.1973, "step": 18540 }, { "epoch": 0.3, "learning_rate": 4.081162324649299e-05, "loss": 2.1748, "step": 18550 }, { "epoch": 0.3, "learning_rate": 4.080661322645291e-05, "loss": 2.1424, "step": 18560 }, { "epoch": 0.3, "learning_rate": 4.080160320641282e-05, "loss": 2.1653, "step": 18570 }, { "epoch": 0.3, "learning_rate": 4.079659318637275e-05, "loss": 2.1549, "step": 18580 }, { "epoch": 0.3, "learning_rate": 4.079158316633267e-05, "loss": 2.1672, "step": 18590 }, { "epoch": 0.3, "learning_rate": 4.078657314629259e-05, "loss": 2.1716, "step": 18600 }, { "epoch": 0.3, "learning_rate": 4.078156312625251e-05, "loss": 2.179, "step": 18610 }, { "epoch": 0.3, "learning_rate": 4.0776553106212426e-05, "loss": 2.1821, "step": 18620 }, { "epoch": 0.3, "learning_rate": 4.0771543086172346e-05, "loss": 2.2006, "step": 18630 }, { "epoch": 0.3, "learning_rate": 4.076653306613227e-05, "loss": 2.1987, "step": 18640 }, { "epoch": 0.3, "learning_rate": 4.076152304609219e-05, "loss": 2.1607, "step": 18650 }, { "epoch": 0.3, "learning_rate": 4.075651302605211e-05, "loss": 2.1647, "step": 18660 }, { "epoch": 0.31, "learning_rate": 4.075150300601203e-05, "loss": 2.1311, "step": 18670 }, { "epoch": 0.31, "learning_rate": 4.074649298597194e-05, "loss": 2.1434, "step": 18680 }, { "epoch": 0.31, "learning_rate": 4.0741482965931864e-05, "loss": 2.1752, "step": 18690 }, { "epoch": 0.31, "learning_rate": 4.0736472945891784e-05, "loss": 2.1693, "step": 18700 }, { "epoch": 0.31, "learning_rate": 4.0731462925851705e-05, "loss": 2.1721, "step": 18710 }, { "epoch": 0.31, "learning_rate": 4.0726452905811625e-05, "loss": 2.179, "step": 18720 }, { "epoch": 0.31, "learning_rate": 4.0721442885771546e-05, "loss": 2.1881, "step": 18730 }, { "epoch": 0.31, "learning_rate": 4.071643286573146e-05, "loss": 2.1662, "step": 18740 }, { "epoch": 0.31, "learning_rate": 4.071142284569138e-05, "loss": 2.1877, "step": 18750 }, { "epoch": 0.31, "learning_rate": 4.07064128256513e-05, "loss": 2.1257, "step": 18760 }, { "epoch": 0.31, "learning_rate": 4.070140280561122e-05, "loss": 2.2, "step": 18770 }, { "epoch": 0.31, "learning_rate": 4.069639278557115e-05, "loss": 2.1755, "step": 18780 }, { "epoch": 0.31, "learning_rate": 4.069138276553106e-05, "loss": 2.202, "step": 18790 }, { "epoch": 0.31, "learning_rate": 4.0686372745490984e-05, "loss": 2.1843, "step": 18800 }, { "epoch": 0.31, "learning_rate": 4.0681362725450904e-05, "loss": 2.2136, "step": 18810 }, { "epoch": 0.31, "learning_rate": 4.0676352705410825e-05, "loss": 2.1943, "step": 18820 }, { "epoch": 0.31, "learning_rate": 4.0671342685370746e-05, "loss": 2.1706, "step": 18830 }, { "epoch": 0.31, "learning_rate": 4.0666332665330666e-05, "loss": 2.1528, "step": 18840 }, { "epoch": 0.31, "learning_rate": 4.066132264529059e-05, "loss": 2.1981, "step": 18850 }, { "epoch": 0.31, "learning_rate": 4.06563126252505e-05, "loss": 2.1524, "step": 18860 }, { "epoch": 0.31, "learning_rate": 4.065130260521042e-05, "loss": 2.1673, "step": 18870 }, { "epoch": 0.31, "learning_rate": 4.064629258517034e-05, "loss": 2.2195, "step": 18880 }, { "epoch": 0.31, "learning_rate": 4.064128256513026e-05, "loss": 2.1942, "step": 18890 }, { "epoch": 0.31, "learning_rate": 4.0636272545090183e-05, "loss": 2.1536, "step": 18900 }, { "epoch": 0.31, "learning_rate": 4.0631262525050104e-05, "loss": 2.173, "step": 18910 }, { "epoch": 0.31, "learning_rate": 4.062625250501002e-05, "loss": 2.1223, "step": 18920 }, { "epoch": 0.31, "learning_rate": 4.062124248496994e-05, "loss": 2.1779, "step": 18930 }, { "epoch": 0.31, "learning_rate": 4.061623246492986e-05, "loss": 2.2253, "step": 18940 }, { "epoch": 0.31, "learning_rate": 4.061122244488978e-05, "loss": 2.1588, "step": 18950 }, { "epoch": 0.31, "learning_rate": 4.06062124248497e-05, "loss": 2.2122, "step": 18960 }, { "epoch": 0.31, "learning_rate": 4.060120240480962e-05, "loss": 2.2005, "step": 18970 }, { "epoch": 0.31, "learning_rate": 4.059619238476954e-05, "loss": 2.1936, "step": 18980 }, { "epoch": 0.31, "learning_rate": 4.059118236472946e-05, "loss": 2.1548, "step": 18990 }, { "epoch": 0.31, "learning_rate": 4.058617234468938e-05, "loss": 2.1495, "step": 19000 }, { "epoch": 0.31, "eval_loss": 2.1370577812194824, "eval_mean_f1": 0.6364745403286939, "eval_rouge1_f1": 0.6992210890492536, "eval_rouge1_precision": 0.8110389492825004, "eval_rouge1_recall": 0.6466329415019649, "eval_rouge2_f1": 0.5450674432006906, "eval_rouge2_precision": 0.6356470149316831, "eval_rouge2_recall": 0.5039331096401902, "eval_rougeL_f1": 0.6651350887361376, "eval_rougeL_precision": 0.7698307627542748, "eval_rougeL_recall": 0.6159610551260437, "eval_runtime": 66.2114, "eval_samples_per_second": 15.466, "eval_steps_per_second": 1.933, "step": 19000 }, { "epoch": 0.31, "learning_rate": 4.0581162324649304e-05, "loss": 2.1705, "step": 19010 }, { "epoch": 0.31, "learning_rate": 4.0576152304609224e-05, "loss": 2.1697, "step": 19020 }, { "epoch": 0.31, "learning_rate": 4.057114228456914e-05, "loss": 2.199, "step": 19030 }, { "epoch": 0.31, "learning_rate": 4.056613226452906e-05, "loss": 2.1832, "step": 19040 }, { "epoch": 0.31, "learning_rate": 4.056112224448898e-05, "loss": 2.1344, "step": 19050 }, { "epoch": 0.31, "learning_rate": 4.05561122244489e-05, "loss": 2.1876, "step": 19060 }, { "epoch": 0.31, "learning_rate": 4.055110220440882e-05, "loss": 2.1289, "step": 19070 }, { "epoch": 0.31, "learning_rate": 4.054609218436874e-05, "loss": 2.1461, "step": 19080 }, { "epoch": 0.31, "learning_rate": 4.0541082164328655e-05, "loss": 2.2054, "step": 19090 }, { "epoch": 0.31, "learning_rate": 4.0536072144288576e-05, "loss": 2.2084, "step": 19100 }, { "epoch": 0.31, "learning_rate": 4.0531062124248497e-05, "loss": 2.2387, "step": 19110 }, { "epoch": 0.31, "learning_rate": 4.052605210420842e-05, "loss": 2.1647, "step": 19120 }, { "epoch": 0.31, "learning_rate": 4.052104208416834e-05, "loss": 2.2059, "step": 19130 }, { "epoch": 0.31, "learning_rate": 4.051603206412826e-05, "loss": 2.1771, "step": 19140 }, { "epoch": 0.31, "learning_rate": 4.051102204408818e-05, "loss": 2.1781, "step": 19150 }, { "epoch": 0.31, "learning_rate": 4.050601202404809e-05, "loss": 2.1774, "step": 19160 }, { "epoch": 0.31, "learning_rate": 4.050100200400802e-05, "loss": 2.1845, "step": 19170 }, { "epoch": 0.31, "learning_rate": 4.049599198396794e-05, "loss": 2.1946, "step": 19180 }, { "epoch": 0.31, "learning_rate": 4.049098196392786e-05, "loss": 2.1736, "step": 19190 }, { "epoch": 0.31, "learning_rate": 4.048597194388778e-05, "loss": 2.1916, "step": 19200 }, { "epoch": 0.31, "learning_rate": 4.0480961923847696e-05, "loss": 2.1601, "step": 19210 }, { "epoch": 0.31, "learning_rate": 4.047595190380762e-05, "loss": 2.1727, "step": 19220 }, { "epoch": 0.31, "learning_rate": 4.047094188376754e-05, "loss": 2.183, "step": 19230 }, { "epoch": 0.31, "learning_rate": 4.046593186372746e-05, "loss": 2.1877, "step": 19240 }, { "epoch": 0.31, "learning_rate": 4.046092184368738e-05, "loss": 2.1689, "step": 19250 }, { "epoch": 0.31, "learning_rate": 4.04559118236473e-05, "loss": 2.1982, "step": 19260 }, { "epoch": 0.31, "learning_rate": 4.045090180360721e-05, "loss": 2.1585, "step": 19270 }, { "epoch": 0.32, "learning_rate": 4.0445891783567134e-05, "loss": 2.1981, "step": 19280 }, { "epoch": 0.32, "learning_rate": 4.0440881763527055e-05, "loss": 2.1633, "step": 19290 }, { "epoch": 0.32, "learning_rate": 4.0435871743486975e-05, "loss": 2.1808, "step": 19300 }, { "epoch": 0.32, "learning_rate": 4.0430861723446896e-05, "loss": 2.2116, "step": 19310 }, { "epoch": 0.32, "learning_rate": 4.0425851703406817e-05, "loss": 2.109, "step": 19320 }, { "epoch": 0.32, "learning_rate": 4.042084168336673e-05, "loss": 2.1541, "step": 19330 }, { "epoch": 0.32, "learning_rate": 4.041583166332665e-05, "loss": 2.2021, "step": 19340 }, { "epoch": 0.32, "learning_rate": 4.041082164328657e-05, "loss": 2.1438, "step": 19350 }, { "epoch": 0.32, "learning_rate": 4.040581162324649e-05, "loss": 2.1459, "step": 19360 }, { "epoch": 0.32, "learning_rate": 4.040080160320642e-05, "loss": 2.2016, "step": 19370 }, { "epoch": 0.32, "learning_rate": 4.0395791583166334e-05, "loss": 2.1295, "step": 19380 }, { "epoch": 0.32, "learning_rate": 4.0390781563126254e-05, "loss": 2.1941, "step": 19390 }, { "epoch": 0.32, "learning_rate": 4.0385771543086175e-05, "loss": 2.1545, "step": 19400 }, { "epoch": 0.32, "learning_rate": 4.0380761523046096e-05, "loss": 2.1587, "step": 19410 }, { "epoch": 0.32, "learning_rate": 4.0375751503006016e-05, "loss": 2.1629, "step": 19420 }, { "epoch": 0.32, "learning_rate": 4.037074148296594e-05, "loss": 2.1751, "step": 19430 }, { "epoch": 0.32, "learning_rate": 4.036573146292586e-05, "loss": 2.2222, "step": 19440 }, { "epoch": 0.32, "learning_rate": 4.036072144288577e-05, "loss": 2.1686, "step": 19450 }, { "epoch": 0.32, "learning_rate": 4.035571142284569e-05, "loss": 2.1456, "step": 19460 }, { "epoch": 0.32, "learning_rate": 4.035070140280561e-05, "loss": 2.1854, "step": 19470 }, { "epoch": 0.32, "learning_rate": 4.034569138276553e-05, "loss": 2.1715, "step": 19480 }, { "epoch": 0.32, "learning_rate": 4.0340681362725454e-05, "loss": 2.1928, "step": 19490 }, { "epoch": 0.32, "learning_rate": 4.0335671342685375e-05, "loss": 2.1796, "step": 19500 }, { "epoch": 0.32, "learning_rate": 4.033066132264529e-05, "loss": 2.1925, "step": 19510 }, { "epoch": 0.32, "learning_rate": 4.032565130260521e-05, "loss": 2.1757, "step": 19520 }, { "epoch": 0.32, "learning_rate": 4.032064128256513e-05, "loss": 2.1601, "step": 19530 }, { "epoch": 0.32, "learning_rate": 4.031563126252505e-05, "loss": 2.1715, "step": 19540 }, { "epoch": 0.32, "learning_rate": 4.031062124248497e-05, "loss": 2.1546, "step": 19550 }, { "epoch": 0.32, "learning_rate": 4.030561122244489e-05, "loss": 2.1836, "step": 19560 }, { "epoch": 0.32, "learning_rate": 4.030060120240481e-05, "loss": 2.1835, "step": 19570 }, { "epoch": 0.32, "learning_rate": 4.029559118236473e-05, "loss": 2.177, "step": 19580 }, { "epoch": 0.32, "learning_rate": 4.0290581162324654e-05, "loss": 2.1827, "step": 19590 }, { "epoch": 0.32, "learning_rate": 4.0285571142284574e-05, "loss": 2.1971, "step": 19600 }, { "epoch": 0.32, "learning_rate": 4.0280561122244495e-05, "loss": 2.1664, "step": 19610 }, { "epoch": 0.32, "learning_rate": 4.027555110220441e-05, "loss": 2.187, "step": 19620 }, { "epoch": 0.32, "learning_rate": 4.027054108216433e-05, "loss": 2.1833, "step": 19630 }, { "epoch": 0.32, "learning_rate": 4.026553106212425e-05, "loss": 2.1751, "step": 19640 }, { "epoch": 0.32, "learning_rate": 4.026052104208417e-05, "loss": 2.1791, "step": 19650 }, { "epoch": 0.32, "learning_rate": 4.025551102204409e-05, "loss": 2.176, "step": 19660 }, { "epoch": 0.32, "learning_rate": 4.025050100200401e-05, "loss": 2.1889, "step": 19670 }, { "epoch": 0.32, "learning_rate": 4.024549098196393e-05, "loss": 2.1561, "step": 19680 }, { "epoch": 0.32, "learning_rate": 4.0240480961923846e-05, "loss": 2.1457, "step": 19690 }, { "epoch": 0.32, "learning_rate": 4.023547094188377e-05, "loss": 2.1293, "step": 19700 }, { "epoch": 0.32, "learning_rate": 4.023046092184369e-05, "loss": 2.2018, "step": 19710 }, { "epoch": 0.32, "learning_rate": 4.022545090180361e-05, "loss": 2.1669, "step": 19720 }, { "epoch": 0.32, "learning_rate": 4.022044088176353e-05, "loss": 2.204, "step": 19730 }, { "epoch": 0.32, "learning_rate": 4.021543086172345e-05, "loss": 2.1802, "step": 19740 }, { "epoch": 0.32, "learning_rate": 4.0210420841683363e-05, "loss": 2.1861, "step": 19750 }, { "epoch": 0.32, "learning_rate": 4.020541082164329e-05, "loss": 2.1584, "step": 19760 }, { "epoch": 0.32, "learning_rate": 4.020040080160321e-05, "loss": 2.1621, "step": 19770 }, { "epoch": 0.32, "learning_rate": 4.019539078156313e-05, "loss": 2.1948, "step": 19780 }, { "epoch": 0.32, "learning_rate": 4.019038076152305e-05, "loss": 2.1965, "step": 19790 }, { "epoch": 0.32, "learning_rate": 4.018537074148297e-05, "loss": 2.1376, "step": 19800 }, { "epoch": 0.32, "learning_rate": 4.018036072144289e-05, "loss": 2.1909, "step": 19810 }, { "epoch": 0.32, "learning_rate": 4.017535070140281e-05, "loss": 2.2169, "step": 19820 }, { "epoch": 0.32, "learning_rate": 4.017034068136273e-05, "loss": 2.1604, "step": 19830 }, { "epoch": 0.32, "learning_rate": 4.016533066132265e-05, "loss": 2.1958, "step": 19840 }, { "epoch": 0.32, "learning_rate": 4.016032064128257e-05, "loss": 2.1647, "step": 19850 }, { "epoch": 0.32, "learning_rate": 4.0155310621242484e-05, "loss": 2.1687, "step": 19860 }, { "epoch": 0.32, "learning_rate": 4.0150300601202404e-05, "loss": 2.148, "step": 19870 }, { "epoch": 0.32, "learning_rate": 4.0145290581162325e-05, "loss": 2.1547, "step": 19880 }, { "epoch": 0.33, "learning_rate": 4.0140280561122246e-05, "loss": 2.146, "step": 19890 }, { "epoch": 0.33, "learning_rate": 4.0135270541082166e-05, "loss": 2.1352, "step": 19900 }, { "epoch": 0.33, "learning_rate": 4.013026052104209e-05, "loss": 2.1489, "step": 19910 }, { "epoch": 0.33, "learning_rate": 4.0125250501002e-05, "loss": 2.1078, "step": 19920 }, { "epoch": 0.33, "learning_rate": 4.012024048096192e-05, "loss": 2.1616, "step": 19930 }, { "epoch": 0.33, "learning_rate": 4.011523046092184e-05, "loss": 2.1403, "step": 19940 }, { "epoch": 0.33, "learning_rate": 4.011022044088176e-05, "loss": 2.2174, "step": 19950 }, { "epoch": 0.33, "learning_rate": 4.010521042084169e-05, "loss": 2.1498, "step": 19960 }, { "epoch": 0.33, "learning_rate": 4.010020040080161e-05, "loss": 2.1157, "step": 19970 }, { "epoch": 0.33, "learning_rate": 4.0095190380761525e-05, "loss": 2.2075, "step": 19980 }, { "epoch": 0.33, "learning_rate": 4.0090180360721445e-05, "loss": 2.1432, "step": 19990 }, { "epoch": 0.33, "learning_rate": 4.0085170340681366e-05, "loss": 2.1903, "step": 20000 }, { "epoch": 0.33, "eval_loss": 2.1355881690979004, "eval_mean_f1": 0.6379103955548543, "eval_rouge1_f1": 0.6995458046239631, "eval_rouge1_precision": 0.8088484801666236, "eval_rouge1_recall": 0.6488798618690657, "eval_rouge2_f1": 0.5485132800835562, "eval_rouge2_precision": 0.6384482128927929, "eval_rouge2_recall": 0.5084377909278343, "eval_rougeL_f1": 0.6656721019570437, "eval_rougeL_precision": 0.7680876257037357, "eval_rougeL_recall": 0.6186156211187646, "eval_runtime": 64.5433, "eval_samples_per_second": 15.865, "eval_steps_per_second": 1.983, "step": 20000 }, { "epoch": 0.33, "learning_rate": 4.0080160320641287e-05, "loss": 2.1459, "step": 20010 }, { "epoch": 0.33, "learning_rate": 4.007515030060121e-05, "loss": 2.1604, "step": 20020 }, { "epoch": 0.33, "learning_rate": 4.007014028056113e-05, "loss": 2.2034, "step": 20030 }, { "epoch": 0.33, "learning_rate": 4.006513026052104e-05, "loss": 2.156, "step": 20040 }, { "epoch": 0.33, "learning_rate": 4.006012024048096e-05, "loss": 2.1141, "step": 20050 }, { "epoch": 0.33, "learning_rate": 4.005511022044088e-05, "loss": 2.1411, "step": 20060 }, { "epoch": 0.33, "learning_rate": 4.0050100200400804e-05, "loss": 2.1748, "step": 20070 }, { "epoch": 0.33, "learning_rate": 4.0045090180360724e-05, "loss": 2.1882, "step": 20080 }, { "epoch": 0.33, "learning_rate": 4.0040080160320645e-05, "loss": 2.1988, "step": 20090 }, { "epoch": 0.33, "learning_rate": 4.003507014028056e-05, "loss": 2.1959, "step": 20100 }, { "epoch": 0.33, "learning_rate": 4.003006012024048e-05, "loss": 2.1865, "step": 20110 }, { "epoch": 0.33, "learning_rate": 4.00250501002004e-05, "loss": 2.1669, "step": 20120 }, { "epoch": 0.33, "learning_rate": 4.002004008016032e-05, "loss": 2.1499, "step": 20130 }, { "epoch": 0.33, "learning_rate": 4.001503006012024e-05, "loss": 2.1459, "step": 20140 }, { "epoch": 0.33, "learning_rate": 4.001002004008016e-05, "loss": 2.1316, "step": 20150 }, { "epoch": 0.33, "learning_rate": 4.000501002004008e-05, "loss": 2.1677, "step": 20160 }, { "epoch": 0.33, "learning_rate": 4e-05, "loss": 2.1762, "step": 20170 }, { "epoch": 0.33, "learning_rate": 3.9994989979959924e-05, "loss": 2.146, "step": 20180 }, { "epoch": 0.33, "learning_rate": 3.9989979959919845e-05, "loss": 2.2103, "step": 20190 }, { "epoch": 0.33, "learning_rate": 3.9984969939879765e-05, "loss": 2.1904, "step": 20200 }, { "epoch": 0.33, "learning_rate": 3.997995991983968e-05, "loss": 2.1177, "step": 20210 }, { "epoch": 0.33, "learning_rate": 3.99749498997996e-05, "loss": 2.1928, "step": 20220 }, { "epoch": 0.33, "learning_rate": 3.996993987975952e-05, "loss": 2.1532, "step": 20230 }, { "epoch": 0.33, "learning_rate": 3.996492985971944e-05, "loss": 2.1675, "step": 20240 }, { "epoch": 0.33, "learning_rate": 3.995991983967936e-05, "loss": 2.1224, "step": 20250 }, { "epoch": 0.33, "learning_rate": 3.995490981963928e-05, "loss": 2.1528, "step": 20260 }, { "epoch": 0.33, "learning_rate": 3.99498997995992e-05, "loss": 2.1862, "step": 20270 }, { "epoch": 0.33, "learning_rate": 3.994488977955912e-05, "loss": 2.1738, "step": 20280 }, { "epoch": 0.33, "learning_rate": 3.993987975951904e-05, "loss": 2.159, "step": 20290 }, { "epoch": 0.33, "learning_rate": 3.993486973947896e-05, "loss": 2.1707, "step": 20300 }, { "epoch": 0.33, "learning_rate": 3.992985971943888e-05, "loss": 2.1745, "step": 20310 }, { "epoch": 0.33, "learning_rate": 3.99248496993988e-05, "loss": 2.1674, "step": 20320 }, { "epoch": 0.33, "learning_rate": 3.991983967935872e-05, "loss": 2.1864, "step": 20330 }, { "epoch": 0.33, "learning_rate": 3.9914829659318634e-05, "loss": 2.2067, "step": 20340 }, { "epoch": 0.33, "learning_rate": 3.990981963927856e-05, "loss": 2.1751, "step": 20350 }, { "epoch": 0.33, "learning_rate": 3.990480961923848e-05, "loss": 2.1843, "step": 20360 }, { "epoch": 0.33, "learning_rate": 3.98997995991984e-05, "loss": 2.1785, "step": 20370 }, { "epoch": 0.33, "learning_rate": 3.989478957915832e-05, "loss": 2.1998, "step": 20380 }, { "epoch": 0.33, "learning_rate": 3.988977955911824e-05, "loss": 2.1749, "step": 20390 }, { "epoch": 0.33, "learning_rate": 3.988476953907816e-05, "loss": 2.1761, "step": 20400 }, { "epoch": 0.33, "learning_rate": 3.987975951903808e-05, "loss": 2.1488, "step": 20410 }, { "epoch": 0.33, "learning_rate": 3.9874749498998e-05, "loss": 2.1695, "step": 20420 }, { "epoch": 0.33, "learning_rate": 3.986973947895792e-05, "loss": 2.1653, "step": 20430 }, { "epoch": 0.33, "learning_rate": 3.986472945891784e-05, "loss": 2.1634, "step": 20440 }, { "epoch": 0.33, "learning_rate": 3.9859719438877754e-05, "loss": 2.1476, "step": 20450 }, { "epoch": 0.33, "learning_rate": 3.9854709418837675e-05, "loss": 2.1418, "step": 20460 }, { "epoch": 0.33, "learning_rate": 3.9849699398797595e-05, "loss": 2.1925, "step": 20470 }, { "epoch": 0.33, "learning_rate": 3.9844689378757516e-05, "loss": 2.1948, "step": 20480 }, { "epoch": 0.33, "learning_rate": 3.983967935871744e-05, "loss": 2.1652, "step": 20490 }, { "epoch": 0.33, "learning_rate": 3.983466933867736e-05, "loss": 2.1801, "step": 20500 }, { "epoch": 0.34, "learning_rate": 3.982965931863728e-05, "loss": 2.158, "step": 20510 }, { "epoch": 0.34, "learning_rate": 3.982464929859719e-05, "loss": 2.2024, "step": 20520 }, { "epoch": 0.34, "learning_rate": 3.981963927855711e-05, "loss": 2.1505, "step": 20530 }, { "epoch": 0.34, "learning_rate": 3.981462925851703e-05, "loss": 2.1926, "step": 20540 }, { "epoch": 0.34, "learning_rate": 3.980961923847696e-05, "loss": 2.1492, "step": 20550 }, { "epoch": 0.34, "learning_rate": 3.980460921843688e-05, "loss": 2.1664, "step": 20560 }, { "epoch": 0.34, "learning_rate": 3.9799599198396795e-05, "loss": 2.1715, "step": 20570 }, { "epoch": 0.34, "learning_rate": 3.9794589178356716e-05, "loss": 2.1676, "step": 20580 }, { "epoch": 0.34, "learning_rate": 3.9789579158316636e-05, "loss": 2.165, "step": 20590 }, { "epoch": 0.34, "learning_rate": 3.978456913827656e-05, "loss": 2.1667, "step": 20600 }, { "epoch": 0.34, "learning_rate": 3.977955911823648e-05, "loss": 2.1426, "step": 20610 }, { "epoch": 0.34, "learning_rate": 3.97745490981964e-05, "loss": 2.1433, "step": 20620 }, { "epoch": 0.34, "learning_rate": 3.976953907815631e-05, "loss": 2.1849, "step": 20630 }, { "epoch": 0.34, "learning_rate": 3.976452905811623e-05, "loss": 2.1689, "step": 20640 }, { "epoch": 0.34, "learning_rate": 3.9759519038076153e-05, "loss": 2.1208, "step": 20650 }, { "epoch": 0.34, "learning_rate": 3.9754509018036074e-05, "loss": 2.1619, "step": 20660 }, { "epoch": 0.34, "learning_rate": 3.9749498997995995e-05, "loss": 2.1274, "step": 20670 }, { "epoch": 0.34, "learning_rate": 3.9744488977955915e-05, "loss": 2.1517, "step": 20680 }, { "epoch": 0.34, "learning_rate": 3.973947895791583e-05, "loss": 2.1308, "step": 20690 }, { "epoch": 0.34, "learning_rate": 3.973446893787575e-05, "loss": 2.1777, "step": 20700 }, { "epoch": 0.34, "learning_rate": 3.972945891783567e-05, "loss": 2.1735, "step": 20710 }, { "epoch": 0.34, "learning_rate": 3.972444889779559e-05, "loss": 2.2122, "step": 20720 }, { "epoch": 0.34, "learning_rate": 3.971943887775551e-05, "loss": 2.1565, "step": 20730 }, { "epoch": 0.34, "learning_rate": 3.971442885771543e-05, "loss": 2.1538, "step": 20740 }, { "epoch": 0.34, "learning_rate": 3.970941883767535e-05, "loss": 2.153, "step": 20750 }, { "epoch": 0.34, "learning_rate": 3.9704408817635274e-05, "loss": 2.1718, "step": 20760 }, { "epoch": 0.34, "learning_rate": 3.9699398797595194e-05, "loss": 2.1988, "step": 20770 }, { "epoch": 0.34, "learning_rate": 3.9694388777555115e-05, "loss": 2.146, "step": 20780 }, { "epoch": 0.34, "learning_rate": 3.9689378757515036e-05, "loss": 2.1931, "step": 20790 }, { "epoch": 0.34, "learning_rate": 3.9684368737474956e-05, "loss": 2.1744, "step": 20800 }, { "epoch": 0.34, "learning_rate": 3.967935871743487e-05, "loss": 2.1329, "step": 20810 }, { "epoch": 0.34, "learning_rate": 3.967434869739479e-05, "loss": 2.1781, "step": 20820 }, { "epoch": 0.34, "learning_rate": 3.966933867735471e-05, "loss": 2.185, "step": 20830 }, { "epoch": 0.34, "learning_rate": 3.966432865731463e-05, "loss": 2.1842, "step": 20840 }, { "epoch": 0.34, "learning_rate": 3.965931863727455e-05, "loss": 2.1627, "step": 20850 }, { "epoch": 0.34, "learning_rate": 3.965430861723447e-05, "loss": 2.1914, "step": 20860 }, { "epoch": 0.34, "learning_rate": 3.964929859719439e-05, "loss": 2.2, "step": 20870 }, { "epoch": 0.34, "learning_rate": 3.964428857715431e-05, "loss": 2.1648, "step": 20880 }, { "epoch": 0.34, "learning_rate": 3.963927855711423e-05, "loss": 2.1666, "step": 20890 }, { "epoch": 0.34, "learning_rate": 3.963426853707415e-05, "loss": 2.1988, "step": 20900 }, { "epoch": 0.34, "learning_rate": 3.962925851703407e-05, "loss": 2.0956, "step": 20910 }, { "epoch": 0.34, "learning_rate": 3.962424849699399e-05, "loss": 2.1472, "step": 20920 }, { "epoch": 0.34, "learning_rate": 3.9619238476953904e-05, "loss": 2.1101, "step": 20930 }, { "epoch": 0.34, "learning_rate": 3.961422845691383e-05, "loss": 2.1854, "step": 20940 }, { "epoch": 0.34, "learning_rate": 3.960921843687375e-05, "loss": 2.1698, "step": 20950 }, { "epoch": 0.34, "learning_rate": 3.960420841683367e-05, "loss": 2.1537, "step": 20960 }, { "epoch": 0.34, "learning_rate": 3.9599198396793594e-05, "loss": 2.1635, "step": 20970 }, { "epoch": 0.34, "learning_rate": 3.959418837675351e-05, "loss": 2.1176, "step": 20980 }, { "epoch": 0.34, "learning_rate": 3.958917835671343e-05, "loss": 2.126, "step": 20990 }, { "epoch": 0.34, "learning_rate": 3.958416833667335e-05, "loss": 2.1517, "step": 21000 }, { "epoch": 0.34, "eval_loss": 2.131589889526367, "eval_mean_f1": 0.6407908635225552, "eval_rouge1_f1": 0.7024838834998607, "eval_rouge1_precision": 0.8143790672728509, "eval_rouge1_recall": 0.6497791755397393, "eval_rouge2_f1": 0.550902253807119, "eval_rouge2_precision": 0.6433670638443584, "eval_rouge2_recall": 0.5095151803104006, "eval_rougeL_f1": 0.6689864532606861, "eval_rougeL_precision": 0.7737727707644554, "eval_rougeL_recall": 0.6198582079664487, "eval_runtime": 64.1356, "eval_samples_per_second": 15.966, "eval_steps_per_second": 1.996, "step": 21000 }, { "epoch": 0.34, "learning_rate": 3.957915831663327e-05, "loss": 2.2043, "step": 21010 }, { "epoch": 0.34, "learning_rate": 3.957414829659319e-05, "loss": 2.1677, "step": 21020 }, { "epoch": 0.34, "learning_rate": 3.956913827655311e-05, "loss": 2.1402, "step": 21030 }, { "epoch": 0.34, "learning_rate": 3.9564128256513025e-05, "loss": 2.169, "step": 21040 }, { "epoch": 0.34, "learning_rate": 3.9559118236472945e-05, "loss": 2.1721, "step": 21050 }, { "epoch": 0.34, "learning_rate": 3.9554108216432866e-05, "loss": 2.1856, "step": 21060 }, { "epoch": 0.34, "learning_rate": 3.9549098196392786e-05, "loss": 2.1694, "step": 21070 }, { "epoch": 0.34, "learning_rate": 3.954408817635271e-05, "loss": 2.1232, "step": 21080 }, { "epoch": 0.34, "learning_rate": 3.953907815631263e-05, "loss": 2.1973, "step": 21090 }, { "epoch": 0.34, "learning_rate": 3.953406813627255e-05, "loss": 2.1499, "step": 21100 }, { "epoch": 0.34, "learning_rate": 3.952905811623246e-05, "loss": 2.1836, "step": 21110 }, { "epoch": 0.35, "learning_rate": 3.952404809619238e-05, "loss": 2.191, "step": 21120 }, { "epoch": 0.35, "learning_rate": 3.9519038076152304e-05, "loss": 2.1594, "step": 21130 }, { "epoch": 0.35, "learning_rate": 3.951402805611223e-05, "loss": 2.1936, "step": 21140 }, { "epoch": 0.35, "learning_rate": 3.950901803607215e-05, "loss": 2.1776, "step": 21150 }, { "epoch": 0.35, "learning_rate": 3.9504008016032065e-05, "loss": 2.1498, "step": 21160 }, { "epoch": 0.35, "learning_rate": 3.9498997995991986e-05, "loss": 2.147, "step": 21170 }, { "epoch": 0.35, "learning_rate": 3.949398797595191e-05, "loss": 2.154, "step": 21180 }, { "epoch": 0.35, "learning_rate": 3.948897795591183e-05, "loss": 2.1524, "step": 21190 }, { "epoch": 0.35, "learning_rate": 3.948396793587175e-05, "loss": 2.167, "step": 21200 }, { "epoch": 0.35, "learning_rate": 3.947895791583167e-05, "loss": 2.1697, "step": 21210 }, { "epoch": 0.35, "learning_rate": 3.947394789579158e-05, "loss": 2.1459, "step": 21220 }, { "epoch": 0.35, "learning_rate": 3.94689378757515e-05, "loss": 2.2155, "step": 21230 }, { "epoch": 0.35, "learning_rate": 3.9463927855711424e-05, "loss": 2.136, "step": 21240 }, { "epoch": 0.35, "learning_rate": 3.9458917835671344e-05, "loss": 2.1703, "step": 21250 }, { "epoch": 0.35, "learning_rate": 3.9453907815631265e-05, "loss": 2.1805, "step": 21260 }, { "epoch": 0.35, "learning_rate": 3.9448897795591186e-05, "loss": 2.1577, "step": 21270 }, { "epoch": 0.35, "learning_rate": 3.94438877755511e-05, "loss": 2.1619, "step": 21280 }, { "epoch": 0.35, "learning_rate": 3.943887775551102e-05, "loss": 2.2119, "step": 21290 }, { "epoch": 0.35, "learning_rate": 3.943386773547094e-05, "loss": 2.1946, "step": 21300 }, { "epoch": 0.35, "learning_rate": 3.942885771543086e-05, "loss": 2.1421, "step": 21310 }, { "epoch": 0.35, "learning_rate": 3.942384769539078e-05, "loss": 2.1832, "step": 21320 }, { "epoch": 0.35, "learning_rate": 3.94188376753507e-05, "loss": 2.1379, "step": 21330 }, { "epoch": 0.35, "learning_rate": 3.9413827655310623e-05, "loss": 2.1983, "step": 21340 }, { "epoch": 0.35, "learning_rate": 3.9408817635270544e-05, "loss": 2.1245, "step": 21350 }, { "epoch": 0.35, "learning_rate": 3.9403807615230465e-05, "loss": 2.1312, "step": 21360 }, { "epoch": 0.35, "learning_rate": 3.9398797595190385e-05, "loss": 2.1728, "step": 21370 }, { "epoch": 0.35, "learning_rate": 3.9393787575150306e-05, "loss": 2.1581, "step": 21380 }, { "epoch": 0.35, "learning_rate": 3.938877755511023e-05, "loss": 2.1852, "step": 21390 }, { "epoch": 0.35, "learning_rate": 3.938376753507014e-05, "loss": 2.171, "step": 21400 }, { "epoch": 0.35, "learning_rate": 3.937875751503006e-05, "loss": 2.1974, "step": 21410 }, { "epoch": 0.35, "learning_rate": 3.937374749498998e-05, "loss": 2.1821, "step": 21420 }, { "epoch": 0.35, "learning_rate": 3.93687374749499e-05, "loss": 2.1263, "step": 21430 }, { "epoch": 0.35, "learning_rate": 3.936372745490982e-05, "loss": 2.2384, "step": 21440 }, { "epoch": 0.35, "learning_rate": 3.9358717434869744e-05, "loss": 2.1912, "step": 21450 }, { "epoch": 0.35, "learning_rate": 3.935370741482966e-05, "loss": 2.1635, "step": 21460 }, { "epoch": 0.35, "learning_rate": 3.934869739478958e-05, "loss": 2.179, "step": 21470 }, { "epoch": 0.35, "learning_rate": 3.93436873747495e-05, "loss": 2.1754, "step": 21480 }, { "epoch": 0.35, "learning_rate": 3.933867735470942e-05, "loss": 2.1476, "step": 21490 }, { "epoch": 0.35, "learning_rate": 3.933366733466934e-05, "loss": 2.1525, "step": 21500 }, { "epoch": 0.35, "learning_rate": 3.932865731462926e-05, "loss": 2.1148, "step": 21510 }, { "epoch": 0.35, "learning_rate": 3.9323647294589175e-05, "loss": 2.1441, "step": 21520 }, { "epoch": 0.35, "learning_rate": 3.93186372745491e-05, "loss": 2.1896, "step": 21530 }, { "epoch": 0.35, "learning_rate": 3.931362725450902e-05, "loss": 2.174, "step": 21540 }, { "epoch": 0.35, "learning_rate": 3.930861723446894e-05, "loss": 2.1261, "step": 21550 }, { "epoch": 0.35, "learning_rate": 3.9303607214428864e-05, "loss": 2.1689, "step": 21560 }, { "epoch": 0.35, "learning_rate": 3.929859719438878e-05, "loss": 2.1541, "step": 21570 }, { "epoch": 0.35, "learning_rate": 3.92935871743487e-05, "loss": 2.1861, "step": 21580 }, { "epoch": 0.35, "learning_rate": 3.928857715430862e-05, "loss": 2.1574, "step": 21590 }, { "epoch": 0.35, "learning_rate": 3.928356713426854e-05, "loss": 2.175, "step": 21600 }, { "epoch": 0.35, "learning_rate": 3.927855711422846e-05, "loss": 2.1602, "step": 21610 }, { "epoch": 0.35, "learning_rate": 3.927354709418838e-05, "loss": 2.0764, "step": 21620 }, { "epoch": 0.35, "learning_rate": 3.9268537074148295e-05, "loss": 2.1626, "step": 21630 }, { "epoch": 0.35, "learning_rate": 3.9263527054108216e-05, "loss": 2.133, "step": 21640 }, { "epoch": 0.35, "learning_rate": 3.9258517034068136e-05, "loss": 2.1107, "step": 21650 }, { "epoch": 0.35, "learning_rate": 3.925350701402806e-05, "loss": 2.1579, "step": 21660 }, { "epoch": 0.35, "learning_rate": 3.924849699398798e-05, "loss": 2.1629, "step": 21670 }, { "epoch": 0.35, "learning_rate": 3.92434869739479e-05, "loss": 2.1611, "step": 21680 }, { "epoch": 0.35, "learning_rate": 3.923847695390782e-05, "loss": 2.1204, "step": 21690 }, { "epoch": 0.35, "learning_rate": 3.923346693386773e-05, "loss": 2.1219, "step": 21700 }, { "epoch": 0.35, "learning_rate": 3.922845691382765e-05, "loss": 2.1593, "step": 21710 }, { "epoch": 0.35, "learning_rate": 3.9223446893787574e-05, "loss": 2.1264, "step": 21720 }, { "epoch": 0.36, "learning_rate": 3.92184368737475e-05, "loss": 2.2259, "step": 21730 }, { "epoch": 0.36, "learning_rate": 3.921342685370742e-05, "loss": 2.1574, "step": 21740 }, { "epoch": 0.36, "learning_rate": 3.9208416833667336e-05, "loss": 2.126, "step": 21750 }, { "epoch": 0.36, "learning_rate": 3.9203406813627256e-05, "loss": 2.1846, "step": 21760 }, { "epoch": 0.36, "learning_rate": 3.919839679358718e-05, "loss": 2.1168, "step": 21770 }, { "epoch": 0.36, "learning_rate": 3.91933867735471e-05, "loss": 2.1934, "step": 21780 }, { "epoch": 0.36, "learning_rate": 3.918837675350702e-05, "loss": 2.1873, "step": 21790 }, { "epoch": 0.36, "learning_rate": 3.918336673346694e-05, "loss": 2.2042, "step": 21800 }, { "epoch": 0.36, "learning_rate": 3.917835671342685e-05, "loss": 2.1585, "step": 21810 }, { "epoch": 0.36, "learning_rate": 3.9173346693386774e-05, "loss": 2.2418, "step": 21820 }, { "epoch": 0.36, "learning_rate": 3.9168336673346694e-05, "loss": 2.1696, "step": 21830 }, { "epoch": 0.36, "learning_rate": 3.9163326653306615e-05, "loss": 2.1755, "step": 21840 }, { "epoch": 0.36, "learning_rate": 3.9158316633266535e-05, "loss": 2.1472, "step": 21850 }, { "epoch": 0.36, "learning_rate": 3.9153306613226456e-05, "loss": 2.1425, "step": 21860 }, { "epoch": 0.36, "learning_rate": 3.914829659318637e-05, "loss": 2.1866, "step": 21870 }, { "epoch": 0.36, "learning_rate": 3.914328657314629e-05, "loss": 2.1274, "step": 21880 }, { "epoch": 0.36, "learning_rate": 3.913827655310621e-05, "loss": 2.162, "step": 21890 }, { "epoch": 0.36, "learning_rate": 3.913326653306613e-05, "loss": 2.1939, "step": 21900 }, { "epoch": 0.36, "learning_rate": 3.912825651302605e-05, "loss": 2.1581, "step": 21910 }, { "epoch": 0.36, "learning_rate": 3.912324649298597e-05, "loss": 2.1546, "step": 21920 }, { "epoch": 0.36, "learning_rate": 3.9118236472945894e-05, "loss": 2.1455, "step": 21930 }, { "epoch": 0.36, "learning_rate": 3.9113226452905814e-05, "loss": 2.1364, "step": 21940 }, { "epoch": 0.36, "learning_rate": 3.9108216432865735e-05, "loss": 2.1442, "step": 21950 }, { "epoch": 0.36, "learning_rate": 3.9103206412825656e-05, "loss": 2.1179, "step": 21960 }, { "epoch": 0.36, "learning_rate": 3.9098196392785576e-05, "loss": 2.1784, "step": 21970 }, { "epoch": 0.36, "learning_rate": 3.90931863727455e-05, "loss": 2.158, "step": 21980 }, { "epoch": 0.36, "learning_rate": 3.908817635270541e-05, "loss": 2.186, "step": 21990 }, { "epoch": 0.36, "learning_rate": 3.908316633266533e-05, "loss": 2.1625, "step": 22000 }, { "epoch": 0.36, "eval_loss": 2.1210646629333496, "eval_mean_f1": 0.6371109999192885, "eval_rouge1_f1": 0.6983851620195074, "eval_rouge1_precision": 0.807436141085541, "eval_rouge1_recall": 0.6488319580470567, "eval_rouge2_f1": 0.5470288750307035, "eval_rouge2_precision": 0.6374447059017367, "eval_rouge2_recall": 0.5081575348230791, "eval_rougeL_f1": 0.6659189627076548, "eval_rougeL_precision": 0.7684171155976506, "eval_rougeL_recall": 0.6195746869733791, "eval_runtime": 65.6306, "eval_samples_per_second": 15.602, "eval_steps_per_second": 1.95, "step": 22000 }, { "epoch": 0.36, "learning_rate": 3.907815631262525e-05, "loss": 2.1719, "step": 22010 }, { "epoch": 0.36, "learning_rate": 3.907314629258517e-05, "loss": 2.1749, "step": 22020 }, { "epoch": 0.36, "learning_rate": 3.9068136272545093e-05, "loss": 2.1587, "step": 22030 }, { "epoch": 0.36, "learning_rate": 3.9063126252505014e-05, "loss": 2.151, "step": 22040 }, { "epoch": 0.36, "learning_rate": 3.905811623246493e-05, "loss": 2.1387, "step": 22050 }, { "epoch": 0.36, "learning_rate": 3.905310621242485e-05, "loss": 2.1698, "step": 22060 }, { "epoch": 0.36, "learning_rate": 3.904809619238477e-05, "loss": 2.1434, "step": 22070 }, { "epoch": 0.36, "learning_rate": 3.904308617234469e-05, "loss": 2.1773, "step": 22080 }, { "epoch": 0.36, "learning_rate": 3.903807615230461e-05, "loss": 2.1948, "step": 22090 }, { "epoch": 0.36, "learning_rate": 3.903306613226453e-05, "loss": 2.1788, "step": 22100 }, { "epoch": 0.36, "learning_rate": 3.9028056112224445e-05, "loss": 2.1754, "step": 22110 }, { "epoch": 0.36, "learning_rate": 3.902304609218437e-05, "loss": 2.1184, "step": 22120 }, { "epoch": 0.36, "learning_rate": 3.901803607214429e-05, "loss": 2.1062, "step": 22130 }, { "epoch": 0.36, "learning_rate": 3.9013026052104214e-05, "loss": 2.1425, "step": 22140 }, { "epoch": 0.36, "learning_rate": 3.9008016032064134e-05, "loss": 2.1735, "step": 22150 }, { "epoch": 0.36, "learning_rate": 3.900300601202405e-05, "loss": 2.127, "step": 22160 }, { "epoch": 0.36, "learning_rate": 3.899799599198397e-05, "loss": 2.1374, "step": 22170 }, { "epoch": 0.36, "learning_rate": 3.899298597194389e-05, "loss": 2.1531, "step": 22180 }, { "epoch": 0.36, "learning_rate": 3.898797595190381e-05, "loss": 2.1274, "step": 22190 }, { "epoch": 0.36, "learning_rate": 3.898296593186373e-05, "loss": 2.1651, "step": 22200 }, { "epoch": 0.36, "learning_rate": 3.897795591182365e-05, "loss": 2.1512, "step": 22210 }, { "epoch": 0.36, "learning_rate": 3.897294589178357e-05, "loss": 2.1096, "step": 22220 }, { "epoch": 0.36, "learning_rate": 3.8967935871743486e-05, "loss": 2.1722, "step": 22230 }, { "epoch": 0.36, "learning_rate": 3.896292585170341e-05, "loss": 2.1381, "step": 22240 }, { "epoch": 0.36, "learning_rate": 3.895791583166333e-05, "loss": 2.1831, "step": 22250 }, { "epoch": 0.36, "learning_rate": 3.895290581162325e-05, "loss": 2.1569, "step": 22260 }, { "epoch": 0.36, "learning_rate": 3.894789579158317e-05, "loss": 2.2053, "step": 22270 }, { "epoch": 0.36, "learning_rate": 3.894288577154309e-05, "loss": 2.1809, "step": 22280 }, { "epoch": 0.36, "learning_rate": 3.8937875751503e-05, "loss": 2.111, "step": 22290 }, { "epoch": 0.36, "learning_rate": 3.8932865731462924e-05, "loss": 2.1665, "step": 22300 }, { "epoch": 0.36, "learning_rate": 3.8927855711422844e-05, "loss": 2.1261, "step": 22310 }, { "epoch": 0.36, "learning_rate": 3.892284569138277e-05, "loss": 2.0773, "step": 22320 }, { "epoch": 0.36, "learning_rate": 3.891783567134269e-05, "loss": 2.0642, "step": 22330 }, { "epoch": 0.37, "learning_rate": 3.8912825651302606e-05, "loss": 2.1504, "step": 22340 }, { "epoch": 0.37, "learning_rate": 3.890781563126253e-05, "loss": 2.1709, "step": 22350 }, { "epoch": 0.37, "learning_rate": 3.890280561122245e-05, "loss": 2.1386, "step": 22360 }, { "epoch": 0.37, "learning_rate": 3.889779559118237e-05, "loss": 2.1859, "step": 22370 }, { "epoch": 0.37, "learning_rate": 3.889278557114229e-05, "loss": 2.2071, "step": 22380 }, { "epoch": 0.37, "learning_rate": 3.888777555110221e-05, "loss": 2.1375, "step": 22390 }, { "epoch": 0.37, "learning_rate": 3.888276553106212e-05, "loss": 2.1347, "step": 22400 }, { "epoch": 0.37, "learning_rate": 3.8877755511022044e-05, "loss": 2.1073, "step": 22410 }, { "epoch": 0.37, "learning_rate": 3.8872745490981965e-05, "loss": 2.1688, "step": 22420 }, { "epoch": 0.37, "learning_rate": 3.8867735470941885e-05, "loss": 2.1558, "step": 22430 }, { "epoch": 0.37, "learning_rate": 3.8862725450901806e-05, "loss": 2.117, "step": 22440 }, { "epoch": 0.37, "learning_rate": 3.8857715430861727e-05, "loss": 2.1189, "step": 22450 }, { "epoch": 0.37, "learning_rate": 3.885270541082164e-05, "loss": 2.1989, "step": 22460 }, { "epoch": 0.37, "learning_rate": 3.884769539078156e-05, "loss": 2.1053, "step": 22470 }, { "epoch": 0.37, "learning_rate": 3.884268537074148e-05, "loss": 2.1341, "step": 22480 }, { "epoch": 0.37, "learning_rate": 3.88376753507014e-05, "loss": 2.1096, "step": 22490 }, { "epoch": 0.37, "learning_rate": 3.883266533066132e-05, "loss": 2.1471, "step": 22500 }, { "epoch": 0.37, "learning_rate": 3.882765531062125e-05, "loss": 2.1297, "step": 22510 }, { "epoch": 0.37, "learning_rate": 3.8822645290581164e-05, "loss": 2.1452, "step": 22520 }, { "epoch": 0.37, "learning_rate": 3.8817635270541085e-05, "loss": 2.0971, "step": 22530 }, { "epoch": 0.37, "learning_rate": 3.8812625250501006e-05, "loss": 2.1508, "step": 22540 }, { "epoch": 0.37, "learning_rate": 3.8807615230460926e-05, "loss": 2.1554, "step": 22550 }, { "epoch": 0.37, "learning_rate": 3.880260521042085e-05, "loss": 2.1468, "step": 22560 }, { "epoch": 0.37, "learning_rate": 3.879759519038077e-05, "loss": 2.1664, "step": 22570 }, { "epoch": 0.37, "learning_rate": 3.879258517034068e-05, "loss": 2.1505, "step": 22580 }, { "epoch": 0.37, "learning_rate": 3.87875751503006e-05, "loss": 2.1569, "step": 22590 }, { "epoch": 0.37, "learning_rate": 3.878256513026052e-05, "loss": 2.1529, "step": 22600 }, { "epoch": 0.37, "learning_rate": 3.877755511022044e-05, "loss": 2.1574, "step": 22610 }, { "epoch": 0.37, "learning_rate": 3.8772545090180364e-05, "loss": 2.1429, "step": 22620 }, { "epoch": 0.37, "learning_rate": 3.8767535070140285e-05, "loss": 2.1352, "step": 22630 }, { "epoch": 0.37, "learning_rate": 3.87625250501002e-05, "loss": 2.1116, "step": 22640 }, { "epoch": 0.37, "learning_rate": 3.875751503006012e-05, "loss": 2.1745, "step": 22650 }, { "epoch": 0.37, "learning_rate": 3.875250501002004e-05, "loss": 2.1508, "step": 22660 }, { "epoch": 0.37, "learning_rate": 3.874749498997996e-05, "loss": 2.1548, "step": 22670 }, { "epoch": 0.37, "learning_rate": 3.874248496993988e-05, "loss": 2.1106, "step": 22680 }, { "epoch": 0.37, "learning_rate": 3.87374749498998e-05, "loss": 2.1333, "step": 22690 }, { "epoch": 0.37, "learning_rate": 3.8732464929859715e-05, "loss": 2.1343, "step": 22700 }, { "epoch": 0.37, "learning_rate": 3.872745490981964e-05, "loss": 2.1234, "step": 22710 }, { "epoch": 0.37, "learning_rate": 3.8722444889779564e-05, "loss": 2.1416, "step": 22720 }, { "epoch": 0.37, "learning_rate": 3.8717434869739484e-05, "loss": 2.1152, "step": 22730 }, { "epoch": 0.37, "learning_rate": 3.8712424849699405e-05, "loss": 2.1223, "step": 22740 }, { "epoch": 0.37, "learning_rate": 3.870741482965932e-05, "loss": 2.1714, "step": 22750 }, { "epoch": 0.37, "learning_rate": 3.870240480961924e-05, "loss": 2.1807, "step": 22760 }, { "epoch": 0.37, "learning_rate": 3.869739478957916e-05, "loss": 2.1387, "step": 22770 }, { "epoch": 0.37, "learning_rate": 3.869238476953908e-05, "loss": 2.1674, "step": 22780 }, { "epoch": 0.37, "learning_rate": 3.8687374749499e-05, "loss": 2.1242, "step": 22790 }, { "epoch": 0.37, "learning_rate": 3.868236472945892e-05, "loss": 2.1713, "step": 22800 }, { "epoch": 0.37, "learning_rate": 3.867735470941884e-05, "loss": 2.1514, "step": 22810 }, { "epoch": 0.37, "learning_rate": 3.8672344689378756e-05, "loss": 2.1522, "step": 22820 }, { "epoch": 0.37, "learning_rate": 3.866733466933868e-05, "loss": 2.1492, "step": 22830 }, { "epoch": 0.37, "learning_rate": 3.86623246492986e-05, "loss": 2.1657, "step": 22840 }, { "epoch": 0.37, "learning_rate": 3.865731462925852e-05, "loss": 2.1602, "step": 22850 }, { "epoch": 0.37, "learning_rate": 3.865230460921844e-05, "loss": 2.1513, "step": 22860 }, { "epoch": 0.37, "learning_rate": 3.864729458917836e-05, "loss": 2.2149, "step": 22870 }, { "epoch": 0.37, "learning_rate": 3.8642284569138273e-05, "loss": 2.1311, "step": 22880 }, { "epoch": 0.37, "learning_rate": 3.8637274549098194e-05, "loss": 2.1458, "step": 22890 }, { "epoch": 0.37, "learning_rate": 3.8632264529058115e-05, "loss": 2.1496, "step": 22900 }, { "epoch": 0.37, "learning_rate": 3.862725450901804e-05, "loss": 2.1653, "step": 22910 }, { "epoch": 0.37, "learning_rate": 3.862224448897796e-05, "loss": 2.1608, "step": 22920 }, { "epoch": 0.37, "learning_rate": 3.861723446893788e-05, "loss": 2.1911, "step": 22930 }, { "epoch": 0.37, "learning_rate": 3.86122244488978e-05, "loss": 2.1706, "step": 22940 }, { "epoch": 0.38, "learning_rate": 3.860721442885772e-05, "loss": 2.1877, "step": 22950 }, { "epoch": 0.38, "learning_rate": 3.860220440881764e-05, "loss": 2.1684, "step": 22960 }, { "epoch": 0.38, "learning_rate": 3.859719438877756e-05, "loss": 2.1398, "step": 22970 }, { "epoch": 0.38, "learning_rate": 3.859218436873748e-05, "loss": 2.178, "step": 22980 }, { "epoch": 0.38, "learning_rate": 3.8587174348697394e-05, "loss": 2.1309, "step": 22990 }, { "epoch": 0.38, "learning_rate": 3.8582164328657314e-05, "loss": 2.1769, "step": 23000 }, { "epoch": 0.38, "eval_loss": 2.1161437034606934, "eval_mean_f1": 0.6460485867410947, "eval_rouge1_f1": 0.7047563936925094, "eval_rouge1_precision": 0.8177037306991926, "eval_rouge1_recall": 0.652212606778458, "eval_rouge2_f1": 0.559707416445018, "eval_rouge2_precision": 0.6524088379068846, "eval_rouge2_recall": 0.5179253747066119, "eval_rougeL_f1": 0.6736819500857565, "eval_rougeL_precision": 0.7793380617847095, "eval_rougeL_recall": 0.6244703377919061, "eval_runtime": 64.8538, "eval_samples_per_second": 15.789, "eval_steps_per_second": 1.974, "step": 23000 }, { "epoch": 0.38, "learning_rate": 3.8577154308617235e-05, "loss": 2.1733, "step": 23010 }, { "epoch": 0.38, "learning_rate": 3.8572144288577156e-05, "loss": 2.1169, "step": 23020 }, { "epoch": 0.38, "learning_rate": 3.8567134268537076e-05, "loss": 2.1272, "step": 23030 }, { "epoch": 0.38, "learning_rate": 3.8562124248497e-05, "loss": 2.1892, "step": 23040 }, { "epoch": 0.38, "learning_rate": 3.855711422845692e-05, "loss": 2.1892, "step": 23050 }, { "epoch": 0.38, "learning_rate": 3.855210420841683e-05, "loss": 2.194, "step": 23060 }, { "epoch": 0.38, "learning_rate": 3.854709418837675e-05, "loss": 2.1349, "step": 23070 }, { "epoch": 0.38, "learning_rate": 3.854208416833667e-05, "loss": 2.1414, "step": 23080 }, { "epoch": 0.38, "learning_rate": 3.853707414829659e-05, "loss": 2.172, "step": 23090 }, { "epoch": 0.38, "learning_rate": 3.853206412825652e-05, "loss": 2.1516, "step": 23100 }, { "epoch": 0.38, "learning_rate": 3.8527054108216435e-05, "loss": 2.1546, "step": 23110 }, { "epoch": 0.38, "learning_rate": 3.8522044088176355e-05, "loss": 2.146, "step": 23120 }, { "epoch": 0.38, "learning_rate": 3.8517034068136276e-05, "loss": 2.1207, "step": 23130 }, { "epoch": 0.38, "learning_rate": 3.8512024048096197e-05, "loss": 2.1421, "step": 23140 }, { "epoch": 0.38, "learning_rate": 3.850701402805612e-05, "loss": 2.1509, "step": 23150 }, { "epoch": 0.38, "learning_rate": 3.850200400801604e-05, "loss": 2.1466, "step": 23160 }, { "epoch": 0.38, "learning_rate": 3.849699398797595e-05, "loss": 2.1422, "step": 23170 }, { "epoch": 0.38, "learning_rate": 3.849198396793587e-05, "loss": 2.1589, "step": 23180 }, { "epoch": 0.38, "learning_rate": 3.848697394789579e-05, "loss": 2.1086, "step": 23190 }, { "epoch": 0.38, "learning_rate": 3.8481963927855714e-05, "loss": 2.1434, "step": 23200 }, { "epoch": 0.38, "learning_rate": 3.8476953907815634e-05, "loss": 2.1545, "step": 23210 }, { "epoch": 0.38, "learning_rate": 3.8471943887775555e-05, "loss": 2.1138, "step": 23220 }, { "epoch": 0.38, "learning_rate": 3.846693386773547e-05, "loss": 2.1493, "step": 23230 }, { "epoch": 0.38, "learning_rate": 3.846192384769539e-05, "loss": 2.1593, "step": 23240 }, { "epoch": 0.38, "learning_rate": 3.845691382765531e-05, "loss": 2.1386, "step": 23250 }, { "epoch": 0.38, "learning_rate": 3.845190380761523e-05, "loss": 2.1547, "step": 23260 }, { "epoch": 0.38, "learning_rate": 3.844689378757515e-05, "loss": 2.1449, "step": 23270 }, { "epoch": 0.38, "learning_rate": 3.844188376753507e-05, "loss": 2.1356, "step": 23280 }, { "epoch": 0.38, "learning_rate": 3.8436873747494986e-05, "loss": 2.1531, "step": 23290 }, { "epoch": 0.38, "learning_rate": 3.843186372745491e-05, "loss": 2.1145, "step": 23300 }, { "epoch": 0.38, "learning_rate": 3.8426853707414834e-05, "loss": 2.1103, "step": 23310 }, { "epoch": 0.38, "learning_rate": 3.8421843687374755e-05, "loss": 2.1433, "step": 23320 }, { "epoch": 0.38, "learning_rate": 3.8416833667334675e-05, "loss": 2.1189, "step": 23330 }, { "epoch": 0.38, "learning_rate": 3.8411823647294596e-05, "loss": 2.0953, "step": 23340 }, { "epoch": 0.38, "learning_rate": 3.840681362725451e-05, "loss": 2.1719, "step": 23350 }, { "epoch": 0.38, "learning_rate": 3.840180360721443e-05, "loss": 2.159, "step": 23360 }, { "epoch": 0.38, "learning_rate": 3.839679358717435e-05, "loss": 2.1642, "step": 23370 }, { "epoch": 0.38, "learning_rate": 3.839178356713427e-05, "loss": 2.1507, "step": 23380 }, { "epoch": 0.38, "learning_rate": 3.838677354709419e-05, "loss": 2.1398, "step": 23390 }, { "epoch": 0.38, "learning_rate": 3.838176352705411e-05, "loss": 2.2067, "step": 23400 }, { "epoch": 0.38, "learning_rate": 3.837675350701403e-05, "loss": 2.1315, "step": 23410 }, { "epoch": 0.38, "learning_rate": 3.837174348697395e-05, "loss": 2.1331, "step": 23420 }, { "epoch": 0.38, "learning_rate": 3.836673346693387e-05, "loss": 2.1523, "step": 23430 }, { "epoch": 0.38, "learning_rate": 3.836172344689379e-05, "loss": 2.1795, "step": 23440 }, { "epoch": 0.38, "learning_rate": 3.835671342685371e-05, "loss": 2.1436, "step": 23450 }, { "epoch": 0.38, "learning_rate": 3.835170340681363e-05, "loss": 2.1571, "step": 23460 }, { "epoch": 0.38, "learning_rate": 3.8346693386773544e-05, "loss": 2.153, "step": 23470 }, { "epoch": 0.38, "learning_rate": 3.8341683366733464e-05, "loss": 2.1385, "step": 23480 }, { "epoch": 0.38, "learning_rate": 3.8336673346693385e-05, "loss": 2.1753, "step": 23490 }, { "epoch": 0.38, "learning_rate": 3.833166332665331e-05, "loss": 2.17, "step": 23500 }, { "epoch": 0.38, "learning_rate": 3.832665330661323e-05, "loss": 2.132, "step": 23510 }, { "epoch": 0.38, "learning_rate": 3.832164328657315e-05, "loss": 2.1394, "step": 23520 }, { "epoch": 0.38, "learning_rate": 3.831663326653307e-05, "loss": 2.1569, "step": 23530 }, { "epoch": 0.38, "learning_rate": 3.831162324649299e-05, "loss": 2.1557, "step": 23540 }, { "epoch": 0.38, "learning_rate": 3.830661322645291e-05, "loss": 2.1487, "step": 23550 }, { "epoch": 0.38, "learning_rate": 3.830160320641283e-05, "loss": 2.1297, "step": 23560 }, { "epoch": 0.39, "learning_rate": 3.829659318637275e-05, "loss": 2.1538, "step": 23570 }, { "epoch": 0.39, "learning_rate": 3.8291583166332664e-05, "loss": 2.1353, "step": 23580 }, { "epoch": 0.39, "learning_rate": 3.8286573146292585e-05, "loss": 2.1304, "step": 23590 }, { "epoch": 0.39, "learning_rate": 3.8281563126252505e-05, "loss": 2.1206, "step": 23600 }, { "epoch": 0.39, "learning_rate": 3.8276553106212426e-05, "loss": 2.1108, "step": 23610 }, { "epoch": 0.39, "learning_rate": 3.827154308617235e-05, "loss": 2.1083, "step": 23620 }, { "epoch": 0.39, "learning_rate": 3.826653306613227e-05, "loss": 2.2275, "step": 23630 }, { "epoch": 0.39, "learning_rate": 3.826152304609219e-05, "loss": 2.1535, "step": 23640 }, { "epoch": 0.39, "learning_rate": 3.82565130260521e-05, "loss": 2.1373, "step": 23650 }, { "epoch": 0.39, "learning_rate": 3.825150300601202e-05, "loss": 2.1068, "step": 23660 }, { "epoch": 0.39, "learning_rate": 3.824649298597194e-05, "loss": 2.1385, "step": 23670 }, { "epoch": 0.39, "learning_rate": 3.8241482965931864e-05, "loss": 2.1291, "step": 23680 }, { "epoch": 0.39, "learning_rate": 3.823647294589179e-05, "loss": 2.1484, "step": 23690 }, { "epoch": 0.39, "learning_rate": 3.8231462925851705e-05, "loss": 2.1655, "step": 23700 }, { "epoch": 0.39, "learning_rate": 3.8226452905811626e-05, "loss": 2.0807, "step": 23710 }, { "epoch": 0.39, "learning_rate": 3.8221442885771546e-05, "loss": 2.1407, "step": 23720 }, { "epoch": 0.39, "learning_rate": 3.821643286573147e-05, "loss": 2.1381, "step": 23730 }, { "epoch": 0.39, "learning_rate": 3.821142284569139e-05, "loss": 2.1518, "step": 23740 }, { "epoch": 0.39, "learning_rate": 3.820641282565131e-05, "loss": 2.1349, "step": 23750 }, { "epoch": 0.39, "learning_rate": 3.820140280561122e-05, "loss": 2.1619, "step": 23760 }, { "epoch": 0.39, "learning_rate": 3.819639278557114e-05, "loss": 2.1175, "step": 23770 }, { "epoch": 0.39, "learning_rate": 3.8191382765531063e-05, "loss": 2.0853, "step": 23780 }, { "epoch": 0.39, "learning_rate": 3.8186372745490984e-05, "loss": 2.153, "step": 23790 }, { "epoch": 0.39, "learning_rate": 3.8181362725450905e-05, "loss": 2.0941, "step": 23800 }, { "epoch": 0.39, "learning_rate": 3.8176352705410825e-05, "loss": 2.1036, "step": 23810 }, { "epoch": 0.39, "learning_rate": 3.817134268537074e-05, "loss": 2.168, "step": 23820 }, { "epoch": 0.39, "learning_rate": 3.816633266533066e-05, "loss": 2.1732, "step": 23830 }, { "epoch": 0.39, "learning_rate": 3.816132264529058e-05, "loss": 2.1353, "step": 23840 }, { "epoch": 0.39, "learning_rate": 3.81563126252505e-05, "loss": 2.1232, "step": 23850 }, { "epoch": 0.39, "learning_rate": 3.815130260521042e-05, "loss": 2.1621, "step": 23860 }, { "epoch": 0.39, "learning_rate": 3.814629258517034e-05, "loss": 2.1173, "step": 23870 }, { "epoch": 0.39, "learning_rate": 3.814128256513026e-05, "loss": 2.1081, "step": 23880 }, { "epoch": 0.39, "learning_rate": 3.8136272545090184e-05, "loss": 2.1509, "step": 23890 }, { "epoch": 0.39, "learning_rate": 3.8131262525050104e-05, "loss": 2.1081, "step": 23900 }, { "epoch": 0.39, "learning_rate": 3.8126252505010025e-05, "loss": 2.1179, "step": 23910 }, { "epoch": 0.39, "learning_rate": 3.8121242484969946e-05, "loss": 2.1588, "step": 23920 }, { "epoch": 0.39, "learning_rate": 3.8116232464929866e-05, "loss": 2.1217, "step": 23930 }, { "epoch": 0.39, "learning_rate": 3.811122244488978e-05, "loss": 2.1212, "step": 23940 }, { "epoch": 0.39, "learning_rate": 3.81062124248497e-05, "loss": 2.1152, "step": 23950 }, { "epoch": 0.39, "learning_rate": 3.810120240480962e-05, "loss": 2.136, "step": 23960 }, { "epoch": 0.39, "learning_rate": 3.809619238476954e-05, "loss": 2.1389, "step": 23970 }, { "epoch": 0.39, "learning_rate": 3.809118236472946e-05, "loss": 2.1434, "step": 23980 }, { "epoch": 0.39, "learning_rate": 3.808617234468938e-05, "loss": 2.13, "step": 23990 }, { "epoch": 0.39, "learning_rate": 3.80811623246493e-05, "loss": 2.1145, "step": 24000 }, { "epoch": 0.39, "eval_loss": 2.1111183166503906, "eval_mean_f1": 0.6407617048206519, "eval_rouge1_f1": 0.7022511982687872, "eval_rouge1_precision": 0.8115447275722002, "eval_rouge1_recall": 0.6519865216044664, "eval_rouge2_f1": 0.5512768178096796, "eval_rouge2_precision": 0.6416466745873485, "eval_rouge2_recall": 0.5115010622312486, "eval_rougeL_f1": 0.668757098383489, "eval_rougeL_precision": 0.7712488198586542, "eval_rougeL_recall": 0.6220092190134185, "eval_runtime": 66.2221, "eval_samples_per_second": 15.463, "eval_steps_per_second": 1.933, "step": 24000 }, { "epoch": 0.39, "learning_rate": 3.807615230460922e-05, "loss": 2.1078, "step": 24010 }, { "epoch": 0.39, "learning_rate": 3.807114228456914e-05, "loss": 2.1299, "step": 24020 }, { "epoch": 0.39, "learning_rate": 3.806613226452906e-05, "loss": 2.1957, "step": 24030 }, { "epoch": 0.39, "learning_rate": 3.806112224448898e-05, "loss": 2.1508, "step": 24040 }, { "epoch": 0.39, "learning_rate": 3.80561122244489e-05, "loss": 2.1398, "step": 24050 }, { "epoch": 0.39, "learning_rate": 3.8051102204408814e-05, "loss": 2.1483, "step": 24060 }, { "epoch": 0.39, "learning_rate": 3.8046092184368735e-05, "loss": 2.1344, "step": 24070 }, { "epoch": 0.39, "learning_rate": 3.804108216432866e-05, "loss": 2.1923, "step": 24080 }, { "epoch": 0.39, "learning_rate": 3.803607214428858e-05, "loss": 2.1479, "step": 24090 }, { "epoch": 0.39, "learning_rate": 3.8031062124248504e-05, "loss": 2.118, "step": 24100 }, { "epoch": 0.39, "learning_rate": 3.802605210420842e-05, "loss": 2.1407, "step": 24110 }, { "epoch": 0.39, "learning_rate": 3.802104208416834e-05, "loss": 2.1499, "step": 24120 }, { "epoch": 0.39, "learning_rate": 3.801603206412826e-05, "loss": 2.1437, "step": 24130 }, { "epoch": 0.39, "learning_rate": 3.801102204408818e-05, "loss": 2.1649, "step": 24140 }, { "epoch": 0.39, "learning_rate": 3.80060120240481e-05, "loss": 2.1536, "step": 24150 }, { "epoch": 0.39, "learning_rate": 3.800100200400802e-05, "loss": 2.1277, "step": 24160 }, { "epoch": 0.39, "learning_rate": 3.7995991983967935e-05, "loss": 2.1683, "step": 24170 }, { "epoch": 0.4, "learning_rate": 3.7990981963927855e-05, "loss": 2.1491, "step": 24180 }, { "epoch": 0.4, "learning_rate": 3.7985971943887776e-05, "loss": 2.1939, "step": 24190 }, { "epoch": 0.4, "learning_rate": 3.7980961923847696e-05, "loss": 2.1283, "step": 24200 }, { "epoch": 0.4, "learning_rate": 3.797595190380762e-05, "loss": 2.1533, "step": 24210 }, { "epoch": 0.4, "learning_rate": 3.797094188376754e-05, "loss": 2.1939, "step": 24220 }, { "epoch": 0.4, "learning_rate": 3.796593186372746e-05, "loss": 2.0965, "step": 24230 }, { "epoch": 0.4, "learning_rate": 3.796092184368737e-05, "loss": 2.1421, "step": 24240 }, { "epoch": 0.4, "learning_rate": 3.795591182364729e-05, "loss": 2.1239, "step": 24250 }, { "epoch": 0.4, "learning_rate": 3.7950901803607214e-05, "loss": 2.128, "step": 24260 }, { "epoch": 0.4, "learning_rate": 3.7945891783567134e-05, "loss": 2.1515, "step": 24270 }, { "epoch": 0.4, "learning_rate": 3.794088176352706e-05, "loss": 2.11, "step": 24280 }, { "epoch": 0.4, "learning_rate": 3.7935871743486975e-05, "loss": 2.0902, "step": 24290 }, { "epoch": 0.4, "learning_rate": 3.7930861723446896e-05, "loss": 2.1781, "step": 24300 }, { "epoch": 0.4, "learning_rate": 3.792585170340682e-05, "loss": 2.1308, "step": 24310 }, { "epoch": 0.4, "learning_rate": 3.792084168336674e-05, "loss": 2.0864, "step": 24320 }, { "epoch": 0.4, "learning_rate": 3.791583166332666e-05, "loss": 2.1825, "step": 24330 }, { "epoch": 0.4, "learning_rate": 3.791082164328658e-05, "loss": 2.1115, "step": 24340 }, { "epoch": 0.4, "learning_rate": 3.790581162324649e-05, "loss": 2.1653, "step": 24350 }, { "epoch": 0.4, "learning_rate": 3.790080160320641e-05, "loss": 2.1012, "step": 24360 }, { "epoch": 0.4, "learning_rate": 3.7895791583166334e-05, "loss": 2.1632, "step": 24370 }, { "epoch": 0.4, "learning_rate": 3.7890781563126254e-05, "loss": 2.187, "step": 24380 }, { "epoch": 0.4, "learning_rate": 3.7885771543086175e-05, "loss": 2.1438, "step": 24390 }, { "epoch": 0.4, "learning_rate": 3.7880761523046096e-05, "loss": 2.1653, "step": 24400 }, { "epoch": 0.4, "learning_rate": 3.787575150300601e-05, "loss": 2.1245, "step": 24410 }, { "epoch": 0.4, "learning_rate": 3.787074148296593e-05, "loss": 2.1783, "step": 24420 }, { "epoch": 0.4, "learning_rate": 3.786573146292585e-05, "loss": 2.136, "step": 24430 }, { "epoch": 0.4, "learning_rate": 3.786072144288577e-05, "loss": 2.1161, "step": 24440 }, { "epoch": 0.4, "learning_rate": 3.785571142284569e-05, "loss": 2.1201, "step": 24450 }, { "epoch": 0.4, "learning_rate": 3.785070140280561e-05, "loss": 2.1584, "step": 24460 }, { "epoch": 0.4, "learning_rate": 3.7845691382765533e-05, "loss": 2.1448, "step": 24470 }, { "epoch": 0.4, "learning_rate": 3.7840681362725454e-05, "loss": 2.1672, "step": 24480 }, { "epoch": 0.4, "learning_rate": 3.7835671342685375e-05, "loss": 2.133, "step": 24490 }, { "epoch": 0.4, "learning_rate": 3.7830661322645295e-05, "loss": 2.1425, "step": 24500 }, { "epoch": 0.4, "learning_rate": 3.7825651302605216e-05, "loss": 2.1483, "step": 24510 }, { "epoch": 0.4, "learning_rate": 3.782064128256514e-05, "loss": 2.1746, "step": 24520 }, { "epoch": 0.4, "learning_rate": 3.781563126252505e-05, "loss": 2.124, "step": 24530 }, { "epoch": 0.4, "learning_rate": 3.781062124248497e-05, "loss": 2.1437, "step": 24540 }, { "epoch": 0.4, "learning_rate": 3.780561122244489e-05, "loss": 2.1167, "step": 24550 }, { "epoch": 0.4, "learning_rate": 3.780060120240481e-05, "loss": 2.1495, "step": 24560 }, { "epoch": 0.4, "learning_rate": 3.779559118236473e-05, "loss": 2.1243, "step": 24570 }, { "epoch": 0.4, "learning_rate": 3.7790581162324654e-05, "loss": 2.1191, "step": 24580 }, { "epoch": 0.4, "learning_rate": 3.778557114228457e-05, "loss": 2.131, "step": 24590 }, { "epoch": 0.4, "learning_rate": 3.778056112224449e-05, "loss": 2.1357, "step": 24600 }, { "epoch": 0.4, "learning_rate": 3.777555110220441e-05, "loss": 2.1131, "step": 24610 }, { "epoch": 0.4, "learning_rate": 3.777054108216433e-05, "loss": 2.1676, "step": 24620 }, { "epoch": 0.4, "learning_rate": 3.776553106212425e-05, "loss": 2.1202, "step": 24630 }, { "epoch": 0.4, "learning_rate": 3.776052104208417e-05, "loss": 2.1428, "step": 24640 }, { "epoch": 0.4, "learning_rate": 3.7755511022044085e-05, "loss": 2.1153, "step": 24650 }, { "epoch": 0.4, "learning_rate": 3.7750501002004005e-05, "loss": 2.1031, "step": 24660 }, { "epoch": 0.4, "learning_rate": 3.774549098196393e-05, "loss": 2.1561, "step": 24670 }, { "epoch": 0.4, "learning_rate": 3.774048096192385e-05, "loss": 2.1609, "step": 24680 }, { "epoch": 0.4, "learning_rate": 3.7735470941883774e-05, "loss": 2.144, "step": 24690 }, { "epoch": 0.4, "learning_rate": 3.773046092184369e-05, "loss": 2.1672, "step": 24700 }, { "epoch": 0.4, "learning_rate": 3.772545090180361e-05, "loss": 2.1638, "step": 24710 }, { "epoch": 0.4, "learning_rate": 3.772044088176353e-05, "loss": 2.1068, "step": 24720 }, { "epoch": 0.4, "learning_rate": 3.771543086172345e-05, "loss": 2.1395, "step": 24730 }, { "epoch": 0.4, "learning_rate": 3.771042084168337e-05, "loss": 2.1725, "step": 24740 }, { "epoch": 0.4, "learning_rate": 3.770541082164329e-05, "loss": 2.1233, "step": 24750 }, { "epoch": 0.4, "learning_rate": 3.770040080160321e-05, "loss": 2.1253, "step": 24760 }, { "epoch": 0.4, "learning_rate": 3.7695390781563126e-05, "loss": 2.1262, "step": 24770 }, { "epoch": 0.4, "learning_rate": 3.7690380761523046e-05, "loss": 2.1374, "step": 24780 }, { "epoch": 0.41, "learning_rate": 3.768537074148297e-05, "loss": 2.1695, "step": 24790 }, { "epoch": 0.41, "learning_rate": 3.768036072144289e-05, "loss": 2.1476, "step": 24800 }, { "epoch": 0.41, "learning_rate": 3.767535070140281e-05, "loss": 2.0996, "step": 24810 }, { "epoch": 0.41, "learning_rate": 3.767034068136273e-05, "loss": 2.0894, "step": 24820 }, { "epoch": 0.41, "learning_rate": 3.766533066132264e-05, "loss": 2.1734, "step": 24830 }, { "epoch": 0.41, "learning_rate": 3.766032064128256e-05, "loss": 2.1281, "step": 24840 }, { "epoch": 0.41, "learning_rate": 3.7655310621242484e-05, "loss": 2.1682, "step": 24850 }, { "epoch": 0.41, "learning_rate": 3.7650300601202405e-05, "loss": 2.1572, "step": 24860 }, { "epoch": 0.41, "learning_rate": 3.764529058116233e-05, "loss": 2.1421, "step": 24870 }, { "epoch": 0.41, "learning_rate": 3.7640280561122246e-05, "loss": 2.1227, "step": 24880 }, { "epoch": 0.41, "learning_rate": 3.7635270541082167e-05, "loss": 2.1144, "step": 24890 }, { "epoch": 0.41, "learning_rate": 3.763026052104209e-05, "loss": 2.1571, "step": 24900 }, { "epoch": 0.41, "learning_rate": 3.762525050100201e-05, "loss": 2.1817, "step": 24910 }, { "epoch": 0.41, "learning_rate": 3.762024048096193e-05, "loss": 2.1462, "step": 24920 }, { "epoch": 0.41, "learning_rate": 3.761523046092185e-05, "loss": 2.1212, "step": 24930 }, { "epoch": 0.41, "learning_rate": 3.761022044088176e-05, "loss": 2.1356, "step": 24940 }, { "epoch": 0.41, "learning_rate": 3.7605210420841684e-05, "loss": 2.1236, "step": 24950 }, { "epoch": 0.41, "learning_rate": 3.7600200400801604e-05, "loss": 2.1694, "step": 24960 }, { "epoch": 0.41, "learning_rate": 3.7595190380761525e-05, "loss": 2.1903, "step": 24970 }, { "epoch": 0.41, "learning_rate": 3.7590180360721445e-05, "loss": 2.1868, "step": 24980 }, { "epoch": 0.41, "learning_rate": 3.7585170340681366e-05, "loss": 2.186, "step": 24990 }, { "epoch": 0.41, "learning_rate": 3.758016032064128e-05, "loss": 2.0946, "step": 25000 }, { "epoch": 0.41, "eval_loss": 2.110049247741699, "eval_mean_f1": 0.6468315534989829, "eval_rouge1_f1": 0.7058745082052802, "eval_rouge1_precision": 0.8159037661493436, "eval_rouge1_recall": 0.6537721255465581, "eval_rouge2_f1": 0.5591017309623313, "eval_rouge2_precision": 0.6493910786208149, "eval_rouge2_recall": 0.5181548279331835, "eval_rougeL_f1": 0.6755184213293375, "eval_rougeL_precision": 0.7785047051217784, "eval_rougeL_recall": 0.6271404359275319, "eval_runtime": 64.8983, "eval_samples_per_second": 15.779, "eval_steps_per_second": 1.972, "step": 25000 }, { "epoch": 0.41, "learning_rate": 3.75751503006012e-05, "loss": 2.1157, "step": 25010 }, { "epoch": 0.41, "learning_rate": 3.757014028056112e-05, "loss": 2.1289, "step": 25020 }, { "epoch": 0.41, "learning_rate": 3.756513026052104e-05, "loss": 2.112, "step": 25030 }, { "epoch": 0.41, "learning_rate": 3.756012024048096e-05, "loss": 2.1083, "step": 25040 }, { "epoch": 0.41, "learning_rate": 3.755511022044088e-05, "loss": 2.1522, "step": 25050 }, { "epoch": 0.41, "learning_rate": 3.7550100200400804e-05, "loss": 2.1217, "step": 25060 }, { "epoch": 0.41, "learning_rate": 3.7545090180360724e-05, "loss": 2.1229, "step": 25070 }, { "epoch": 0.41, "learning_rate": 3.7540080160320645e-05, "loss": 2.1088, "step": 25080 }, { "epoch": 0.41, "learning_rate": 3.7535070140280566e-05, "loss": 2.1321, "step": 25090 }, { "epoch": 0.41, "learning_rate": 3.7530060120240486e-05, "loss": 2.1579, "step": 25100 }, { "epoch": 0.41, "learning_rate": 3.752505010020041e-05, "loss": 2.1486, "step": 25110 }, { "epoch": 0.41, "learning_rate": 3.752004008016032e-05, "loss": 2.1512, "step": 25120 }, { "epoch": 0.41, "learning_rate": 3.751503006012024e-05, "loss": 2.1851, "step": 25130 }, { "epoch": 0.41, "learning_rate": 3.751002004008016e-05, "loss": 2.1348, "step": 25140 }, { "epoch": 0.41, "learning_rate": 3.750501002004008e-05, "loss": 2.1259, "step": 25150 }, { "epoch": 0.41, "learning_rate": 3.7500000000000003e-05, "loss": 2.1397, "step": 25160 }, { "epoch": 0.41, "learning_rate": 3.7494989979959924e-05, "loss": 2.1705, "step": 25170 }, { "epoch": 0.41, "learning_rate": 3.748997995991984e-05, "loss": 2.1227, "step": 25180 }, { "epoch": 0.41, "learning_rate": 3.748496993987976e-05, "loss": 2.1748, "step": 25190 }, { "epoch": 0.41, "learning_rate": 3.747995991983968e-05, "loss": 2.1699, "step": 25200 }, { "epoch": 0.41, "learning_rate": 3.74749498997996e-05, "loss": 2.148, "step": 25210 }, { "epoch": 0.41, "learning_rate": 3.746993987975952e-05, "loss": 2.1056, "step": 25220 }, { "epoch": 0.41, "learning_rate": 3.746492985971944e-05, "loss": 2.0949, "step": 25230 }, { "epoch": 0.41, "learning_rate": 3.7459919839679355e-05, "loss": 2.1368, "step": 25240 }, { "epoch": 0.41, "learning_rate": 3.7454909819639276e-05, "loss": 2.158, "step": 25250 }, { "epoch": 0.41, "learning_rate": 3.74498997995992e-05, "loss": 2.1625, "step": 25260 }, { "epoch": 0.41, "learning_rate": 3.7444889779559124e-05, "loss": 2.0995, "step": 25270 }, { "epoch": 0.41, "learning_rate": 3.7439879759519044e-05, "loss": 2.1348, "step": 25280 }, { "epoch": 0.41, "learning_rate": 3.743486973947896e-05, "loss": 2.1566, "step": 25290 }, { "epoch": 0.41, "learning_rate": 3.742985971943888e-05, "loss": 2.1449, "step": 25300 }, { "epoch": 0.41, "learning_rate": 3.74248496993988e-05, "loss": 2.1598, "step": 25310 }, { "epoch": 0.41, "learning_rate": 3.741983967935872e-05, "loss": 2.1509, "step": 25320 }, { "epoch": 0.41, "learning_rate": 3.741482965931864e-05, "loss": 2.2062, "step": 25330 }, { "epoch": 0.41, "learning_rate": 3.740981963927856e-05, "loss": 2.1232, "step": 25340 }, { "epoch": 0.41, "learning_rate": 3.740480961923848e-05, "loss": 2.1904, "step": 25350 }, { "epoch": 0.41, "learning_rate": 3.7399799599198396e-05, "loss": 2.151, "step": 25360 }, { "epoch": 0.41, "learning_rate": 3.739478957915832e-05, "loss": 2.1556, "step": 25370 }, { "epoch": 0.41, "learning_rate": 3.738977955911824e-05, "loss": 2.1041, "step": 25380 }, { "epoch": 0.41, "learning_rate": 3.738476953907816e-05, "loss": 2.1532, "step": 25390 }, { "epoch": 0.42, "learning_rate": 3.737975951903808e-05, "loss": 2.1693, "step": 25400 }, { "epoch": 0.42, "learning_rate": 3.7374749498998e-05, "loss": 2.1985, "step": 25410 }, { "epoch": 0.42, "learning_rate": 3.736973947895791e-05, "loss": 2.1525, "step": 25420 }, { "epoch": 0.42, "learning_rate": 3.7364729458917834e-05, "loss": 2.139, "step": 25430 }, { "epoch": 0.42, "learning_rate": 3.7359719438877754e-05, "loss": 2.1383, "step": 25440 }, { "epoch": 0.42, "learning_rate": 3.7354709418837675e-05, "loss": 2.1124, "step": 25450 }, { "epoch": 0.42, "learning_rate": 3.73496993987976e-05, "loss": 2.1311, "step": 25460 }, { "epoch": 0.42, "learning_rate": 3.7344689378757516e-05, "loss": 2.1054, "step": 25470 }, { "epoch": 0.42, "learning_rate": 3.733967935871744e-05, "loss": 2.2061, "step": 25480 }, { "epoch": 0.42, "learning_rate": 3.733466933867736e-05, "loss": 2.1314, "step": 25490 }, { "epoch": 0.42, "learning_rate": 3.732965931863728e-05, "loss": 2.1539, "step": 25500 }, { "epoch": 0.42, "learning_rate": 3.73246492985972e-05, "loss": 2.1218, "step": 25510 }, { "epoch": 0.42, "learning_rate": 3.731963927855712e-05, "loss": 2.1426, "step": 25520 }, { "epoch": 0.42, "learning_rate": 3.731462925851703e-05, "loss": 2.1914, "step": 25530 }, { "epoch": 0.42, "learning_rate": 3.7309619238476954e-05, "loss": 2.1246, "step": 25540 }, { "epoch": 0.42, "learning_rate": 3.7304609218436875e-05, "loss": 2.1601, "step": 25550 }, { "epoch": 0.42, "learning_rate": 3.7299599198396795e-05, "loss": 2.1427, "step": 25560 }, { "epoch": 0.42, "learning_rate": 3.7294589178356716e-05, "loss": 2.1486, "step": 25570 }, { "epoch": 0.42, "learning_rate": 3.7289579158316637e-05, "loss": 2.1317, "step": 25580 }, { "epoch": 0.42, "learning_rate": 3.728456913827656e-05, "loss": 2.1517, "step": 25590 }, { "epoch": 0.42, "learning_rate": 3.727955911823647e-05, "loss": 2.134, "step": 25600 }, { "epoch": 0.42, "learning_rate": 3.727454909819639e-05, "loss": 2.1882, "step": 25610 }, { "epoch": 0.42, "learning_rate": 3.726953907815631e-05, "loss": 2.1175, "step": 25620 }, { "epoch": 0.42, "learning_rate": 3.726452905811623e-05, "loss": 2.1204, "step": 25630 }, { "epoch": 0.42, "learning_rate": 3.7259519038076154e-05, "loss": 2.1032, "step": 25640 }, { "epoch": 0.42, "learning_rate": 3.7254509018036074e-05, "loss": 2.1621, "step": 25650 }, { "epoch": 0.42, "learning_rate": 3.7249498997995995e-05, "loss": 2.1265, "step": 25660 }, { "epoch": 0.42, "learning_rate": 3.7244488977955916e-05, "loss": 2.1297, "step": 25670 }, { "epoch": 0.42, "learning_rate": 3.7239478957915836e-05, "loss": 2.135, "step": 25680 }, { "epoch": 0.42, "learning_rate": 3.723446893787576e-05, "loss": 2.1081, "step": 25690 }, { "epoch": 0.42, "learning_rate": 3.722945891783568e-05, "loss": 2.1326, "step": 25700 }, { "epoch": 0.42, "learning_rate": 3.722444889779559e-05, "loss": 2.1326, "step": 25710 }, { "epoch": 0.42, "learning_rate": 3.721943887775551e-05, "loss": 2.1462, "step": 25720 }, { "epoch": 0.42, "learning_rate": 3.721442885771543e-05, "loss": 2.1663, "step": 25730 }, { "epoch": 0.42, "learning_rate": 3.720941883767535e-05, "loss": 2.1487, "step": 25740 }, { "epoch": 0.42, "learning_rate": 3.7204408817635274e-05, "loss": 2.1554, "step": 25750 }, { "epoch": 0.42, "learning_rate": 3.7199398797595195e-05, "loss": 2.1162, "step": 25760 }, { "epoch": 0.42, "learning_rate": 3.719438877755511e-05, "loss": 2.2003, "step": 25770 }, { "epoch": 0.42, "learning_rate": 3.718937875751503e-05, "loss": 2.1811, "step": 25780 }, { "epoch": 0.42, "learning_rate": 3.718436873747495e-05, "loss": 2.1249, "step": 25790 }, { "epoch": 0.42, "learning_rate": 3.717935871743487e-05, "loss": 2.1036, "step": 25800 }, { "epoch": 0.42, "learning_rate": 3.717434869739479e-05, "loss": 2.146, "step": 25810 }, { "epoch": 0.42, "learning_rate": 3.716933867735471e-05, "loss": 2.1445, "step": 25820 }, { "epoch": 0.42, "learning_rate": 3.7164328657314625e-05, "loss": 2.1268, "step": 25830 }, { "epoch": 0.42, "learning_rate": 3.7159318637274546e-05, "loss": 2.13, "step": 25840 }, { "epoch": 0.42, "learning_rate": 3.7154308617234474e-05, "loss": 2.1621, "step": 25850 }, { "epoch": 0.42, "learning_rate": 3.7149298597194394e-05, "loss": 2.1344, "step": 25860 }, { "epoch": 0.42, "learning_rate": 3.7144288577154315e-05, "loss": 2.1431, "step": 25870 }, { "epoch": 0.42, "learning_rate": 3.7139278557114235e-05, "loss": 2.1501, "step": 25880 }, { "epoch": 0.42, "learning_rate": 3.713426853707415e-05, "loss": 2.1599, "step": 25890 }, { "epoch": 0.42, "learning_rate": 3.712925851703407e-05, "loss": 2.1366, "step": 25900 }, { "epoch": 0.42, "learning_rate": 3.712424849699399e-05, "loss": 2.1333, "step": 25910 }, { "epoch": 0.42, "learning_rate": 3.711923847695391e-05, "loss": 2.1253, "step": 25920 }, { "epoch": 0.42, "learning_rate": 3.711422845691383e-05, "loss": 2.1571, "step": 25930 }, { "epoch": 0.42, "learning_rate": 3.710921843687375e-05, "loss": 2.1392, "step": 25940 }, { "epoch": 0.42, "learning_rate": 3.7104208416833666e-05, "loss": 2.1364, "step": 25950 }, { "epoch": 0.42, "learning_rate": 3.709919839679359e-05, "loss": 2.0831, "step": 25960 }, { "epoch": 0.42, "learning_rate": 3.709418837675351e-05, "loss": 2.1837, "step": 25970 }, { "epoch": 0.42, "learning_rate": 3.708917835671343e-05, "loss": 2.0969, "step": 25980 }, { "epoch": 0.42, "learning_rate": 3.708416833667335e-05, "loss": 2.1326, "step": 25990 }, { "epoch": 0.42, "learning_rate": 3.707915831663327e-05, "loss": 2.1569, "step": 26000 }, { "epoch": 0.42, "eval_loss": 2.108470916748047, "eval_mean_f1": 0.6410479343846661, "eval_rouge1_f1": 0.7012448274591256, "eval_rouge1_precision": 0.8116094701579817, "eval_rouge1_recall": 0.6504745337497533, "eval_rouge2_f1": 0.5523925084628363, "eval_rouge2_precision": 0.6431762397216496, "eval_rouge2_recall": 0.5121176533338975, "eval_rougeL_f1": 0.6695064672320366, "eval_rougeL_precision": 0.7724749198364063, "eval_rougeL_recall": 0.6222808838904252, "eval_runtime": 65.8314, "eval_samples_per_second": 15.555, "eval_steps_per_second": 1.944, "step": 26000 }, { "epoch": 0.42, "learning_rate": 3.7074148296593183e-05, "loss": 2.1543, "step": 26010 }, { "epoch": 0.43, "learning_rate": 3.7069138276553104e-05, "loss": 2.1149, "step": 26020 }, { "epoch": 0.43, "learning_rate": 3.7064128256513025e-05, "loss": 2.1486, "step": 26030 }, { "epoch": 0.43, "learning_rate": 3.7059118236472945e-05, "loss": 2.1027, "step": 26040 }, { "epoch": 0.43, "learning_rate": 3.705410821643287e-05, "loss": 2.1562, "step": 26050 }, { "epoch": 0.43, "learning_rate": 3.704909819639279e-05, "loss": 2.1404, "step": 26060 }, { "epoch": 0.43, "learning_rate": 3.704408817635271e-05, "loss": 2.149, "step": 26070 }, { "epoch": 0.43, "learning_rate": 3.703907815631263e-05, "loss": 2.1447, "step": 26080 }, { "epoch": 0.43, "learning_rate": 3.703406813627255e-05, "loss": 2.1569, "step": 26090 }, { "epoch": 0.43, "learning_rate": 3.702905811623247e-05, "loss": 2.1107, "step": 26100 }, { "epoch": 0.43, "learning_rate": 3.702404809619239e-05, "loss": 2.1637, "step": 26110 }, { "epoch": 0.43, "learning_rate": 3.7019038076152304e-05, "loss": 2.1393, "step": 26120 }, { "epoch": 0.43, "learning_rate": 3.7014028056112224e-05, "loss": 2.1914, "step": 26130 }, { "epoch": 0.43, "learning_rate": 3.7009018036072145e-05, "loss": 2.1512, "step": 26140 }, { "epoch": 0.43, "learning_rate": 3.7004008016032066e-05, "loss": 2.1603, "step": 26150 }, { "epoch": 0.43, "learning_rate": 3.6998997995991986e-05, "loss": 2.1787, "step": 26160 }, { "epoch": 0.43, "learning_rate": 3.699398797595191e-05, "loss": 2.0881, "step": 26170 }, { "epoch": 0.43, "learning_rate": 3.698897795591183e-05, "loss": 2.1053, "step": 26180 }, { "epoch": 0.43, "learning_rate": 3.698396793587174e-05, "loss": 2.1241, "step": 26190 }, { "epoch": 0.43, "learning_rate": 3.697895791583166e-05, "loss": 2.1243, "step": 26200 }, { "epoch": 0.43, "learning_rate": 3.697394789579158e-05, "loss": 2.1845, "step": 26210 }, { "epoch": 0.43, "learning_rate": 3.69689378757515e-05, "loss": 2.1272, "step": 26220 }, { "epoch": 0.43, "learning_rate": 3.6963927855711424e-05, "loss": 2.1641, "step": 26230 }, { "epoch": 0.43, "learning_rate": 3.6958917835671345e-05, "loss": 2.1266, "step": 26240 }, { "epoch": 0.43, "learning_rate": 3.6953907815631265e-05, "loss": 2.1379, "step": 26250 }, { "epoch": 0.43, "learning_rate": 3.6948897795591186e-05, "loss": 2.1396, "step": 26260 }, { "epoch": 0.43, "learning_rate": 3.6943887775551107e-05, "loss": 2.1312, "step": 26270 }, { "epoch": 0.43, "learning_rate": 3.693887775551103e-05, "loss": 2.1499, "step": 26280 }, { "epoch": 0.43, "learning_rate": 3.693386773547095e-05, "loss": 2.1618, "step": 26290 }, { "epoch": 0.43, "learning_rate": 3.692885771543086e-05, "loss": 2.1287, "step": 26300 }, { "epoch": 0.43, "learning_rate": 3.692384769539078e-05, "loss": 2.1248, "step": 26310 }, { "epoch": 0.43, "learning_rate": 3.69188376753507e-05, "loss": 2.1373, "step": 26320 }, { "epoch": 0.43, "learning_rate": 3.6913827655310624e-05, "loss": 2.1592, "step": 26330 }, { "epoch": 0.43, "learning_rate": 3.6908817635270544e-05, "loss": 2.1404, "step": 26340 }, { "epoch": 0.43, "learning_rate": 3.6903807615230465e-05, "loss": 2.1036, "step": 26350 }, { "epoch": 0.43, "learning_rate": 3.689879759519038e-05, "loss": 2.1714, "step": 26360 }, { "epoch": 0.43, "learning_rate": 3.68937875751503e-05, "loss": 2.096, "step": 26370 }, { "epoch": 0.43, "learning_rate": 3.688877755511022e-05, "loss": 2.1657, "step": 26380 }, { "epoch": 0.43, "learning_rate": 3.688376753507014e-05, "loss": 2.1415, "step": 26390 }, { "epoch": 0.43, "learning_rate": 3.687875751503006e-05, "loss": 2.1416, "step": 26400 }, { "epoch": 0.43, "learning_rate": 3.687374749498998e-05, "loss": 2.1133, "step": 26410 }, { "epoch": 0.43, "learning_rate": 3.68687374749499e-05, "loss": 2.1276, "step": 26420 }, { "epoch": 0.43, "learning_rate": 3.6863727454909817e-05, "loss": 2.1854, "step": 26430 }, { "epoch": 0.43, "learning_rate": 3.6858717434869744e-05, "loss": 2.1093, "step": 26440 }, { "epoch": 0.43, "learning_rate": 3.6853707414829665e-05, "loss": 2.1261, "step": 26450 }, { "epoch": 0.43, "learning_rate": 3.6848697394789585e-05, "loss": 2.1525, "step": 26460 }, { "epoch": 0.43, "learning_rate": 3.6843687374749506e-05, "loss": 2.0643, "step": 26470 }, { "epoch": 0.43, "learning_rate": 3.683867735470942e-05, "loss": 2.1698, "step": 26480 }, { "epoch": 0.43, "learning_rate": 3.683366733466934e-05, "loss": 2.1443, "step": 26490 }, { "epoch": 0.43, "learning_rate": 3.682865731462926e-05, "loss": 2.0868, "step": 26500 }, { "epoch": 0.43, "learning_rate": 3.682364729458918e-05, "loss": 2.1533, "step": 26510 }, { "epoch": 0.43, "learning_rate": 3.68186372745491e-05, "loss": 2.1228, "step": 26520 }, { "epoch": 0.43, "learning_rate": 3.681362725450902e-05, "loss": 2.134, "step": 26530 }, { "epoch": 0.43, "learning_rate": 3.680861723446894e-05, "loss": 2.104, "step": 26540 }, { "epoch": 0.43, "learning_rate": 3.680360721442886e-05, "loss": 2.1344, "step": 26550 }, { "epoch": 0.43, "learning_rate": 3.679859719438878e-05, "loss": 2.1239, "step": 26560 }, { "epoch": 0.43, "learning_rate": 3.67935871743487e-05, "loss": 2.0997, "step": 26570 }, { "epoch": 0.43, "learning_rate": 3.678857715430862e-05, "loss": 2.0634, "step": 26580 }, { "epoch": 0.43, "learning_rate": 3.678356713426854e-05, "loss": 2.1348, "step": 26590 }, { "epoch": 0.43, "learning_rate": 3.6778557114228454e-05, "loss": 2.1349, "step": 26600 }, { "epoch": 0.43, "learning_rate": 3.6773547094188375e-05, "loss": 2.1362, "step": 26610 }, { "epoch": 0.43, "learning_rate": 3.6768537074148295e-05, "loss": 2.0866, "step": 26620 }, { "epoch": 0.44, "learning_rate": 3.6763527054108216e-05, "loss": 2.1483, "step": 26630 }, { "epoch": 0.44, "learning_rate": 3.675851703406814e-05, "loss": 2.1726, "step": 26640 }, { "epoch": 0.44, "learning_rate": 3.675350701402806e-05, "loss": 2.1357, "step": 26650 }, { "epoch": 0.44, "learning_rate": 3.674849699398798e-05, "loss": 2.1254, "step": 26660 }, { "epoch": 0.44, "learning_rate": 3.67434869739479e-05, "loss": 2.1439, "step": 26670 }, { "epoch": 0.44, "learning_rate": 3.673847695390782e-05, "loss": 2.1582, "step": 26680 }, { "epoch": 0.44, "learning_rate": 3.673346693386774e-05, "loss": 2.1013, "step": 26690 }, { "epoch": 0.44, "learning_rate": 3.672845691382766e-05, "loss": 2.1645, "step": 26700 }, { "epoch": 0.44, "learning_rate": 3.6723446893787574e-05, "loss": 2.1417, "step": 26710 }, { "epoch": 0.44, "learning_rate": 3.6718436873747495e-05, "loss": 2.1372, "step": 26720 }, { "epoch": 0.44, "learning_rate": 3.6713426853707415e-05, "loss": 2.1268, "step": 26730 }, { "epoch": 0.44, "learning_rate": 3.6708416833667336e-05, "loss": 2.098, "step": 26740 }, { "epoch": 0.44, "learning_rate": 3.670340681362726e-05, "loss": 2.0637, "step": 26750 }, { "epoch": 0.44, "learning_rate": 3.669839679358718e-05, "loss": 2.0815, "step": 26760 }, { "epoch": 0.44, "learning_rate": 3.66933867735471e-05, "loss": 2.1204, "step": 26770 }, { "epoch": 0.44, "learning_rate": 3.668837675350701e-05, "loss": 2.155, "step": 26780 }, { "epoch": 0.44, "learning_rate": 3.668336673346693e-05, "loss": 2.091, "step": 26790 }, { "epoch": 0.44, "learning_rate": 3.667835671342685e-05, "loss": 2.1637, "step": 26800 }, { "epoch": 0.44, "learning_rate": 3.6673346693386774e-05, "loss": 2.1408, "step": 26810 }, { "epoch": 0.44, "learning_rate": 3.6668336673346694e-05, "loss": 2.1383, "step": 26820 }, { "epoch": 0.44, "learning_rate": 3.6663326653306615e-05, "loss": 2.1525, "step": 26830 }, { "epoch": 0.44, "learning_rate": 3.6658316633266536e-05, "loss": 2.1083, "step": 26840 }, { "epoch": 0.44, "learning_rate": 3.6653306613226456e-05, "loss": 2.1461, "step": 26850 }, { "epoch": 0.44, "learning_rate": 3.664829659318638e-05, "loss": 2.1787, "step": 26860 }, { "epoch": 0.44, "learning_rate": 3.66432865731463e-05, "loss": 2.1456, "step": 26870 }, { "epoch": 0.44, "learning_rate": 3.663827655310622e-05, "loss": 2.0898, "step": 26880 }, { "epoch": 0.44, "learning_rate": 3.663326653306613e-05, "loss": 2.1124, "step": 26890 }, { "epoch": 0.44, "learning_rate": 3.662825651302605e-05, "loss": 2.1281, "step": 26900 }, { "epoch": 0.44, "learning_rate": 3.6623246492985973e-05, "loss": 2.1258, "step": 26910 }, { "epoch": 0.44, "learning_rate": 3.6618236472945894e-05, "loss": 2.0819, "step": 26920 }, { "epoch": 0.44, "learning_rate": 3.6613226452905815e-05, "loss": 2.0969, "step": 26930 }, { "epoch": 0.44, "learning_rate": 3.6608216432865735e-05, "loss": 2.1152, "step": 26940 }, { "epoch": 0.44, "learning_rate": 3.660320641282565e-05, "loss": 2.1768, "step": 26950 }, { "epoch": 0.44, "learning_rate": 3.659819639278557e-05, "loss": 2.1359, "step": 26960 }, { "epoch": 0.44, "learning_rate": 3.659318637274549e-05, "loss": 2.1212, "step": 26970 }, { "epoch": 0.44, "learning_rate": 3.658817635270541e-05, "loss": 2.094, "step": 26980 }, { "epoch": 0.44, "learning_rate": 3.658316633266533e-05, "loss": 2.1362, "step": 26990 }, { "epoch": 0.44, "learning_rate": 3.657815631262525e-05, "loss": 2.0826, "step": 27000 }, { "epoch": 0.44, "eval_loss": 2.105740547180176, "eval_mean_f1": 0.647121812880819, "eval_rouge1_f1": 0.7066647105790819, "eval_rouge1_precision": 0.8158495288970492, "eval_rouge1_recall": 0.6555974520313362, "eval_rouge2_f1": 0.5606984140588908, "eval_rouge2_precision": 0.6499429464578389, "eval_rouge2_recall": 0.5207759434133872, "eval_rougeL_f1": 0.6740023140044844, "eval_rougeL_precision": 0.7758920795028459, "eval_rougeL_recall": 0.6265727554050042, "eval_runtime": 66.9816, "eval_samples_per_second": 15.288, "eval_steps_per_second": 1.911, "step": 27000 }, { "epoch": 0.44, "learning_rate": 3.657314629258517e-05, "loss": 2.1313, "step": 27010 }, { "epoch": 0.44, "learning_rate": 3.656813627254509e-05, "loss": 2.1475, "step": 27020 }, { "epoch": 0.44, "learning_rate": 3.6563126252505014e-05, "loss": 2.1274, "step": 27030 }, { "epoch": 0.44, "learning_rate": 3.6558116232464935e-05, "loss": 2.1352, "step": 27040 }, { "epoch": 0.44, "learning_rate": 3.6553106212424856e-05, "loss": 2.0861, "step": 27050 }, { "epoch": 0.44, "learning_rate": 3.6548096192384776e-05, "loss": 2.1126, "step": 27060 }, { "epoch": 0.44, "learning_rate": 3.654308617234469e-05, "loss": 2.0557, "step": 27070 }, { "epoch": 0.44, "learning_rate": 3.653807615230461e-05, "loss": 2.1245, "step": 27080 }, { "epoch": 0.44, "learning_rate": 3.653306613226453e-05, "loss": 2.1713, "step": 27090 }, { "epoch": 0.44, "learning_rate": 3.652805611222445e-05, "loss": 2.1103, "step": 27100 }, { "epoch": 0.44, "learning_rate": 3.652304609218437e-05, "loss": 2.0898, "step": 27110 }, { "epoch": 0.44, "learning_rate": 3.651803607214429e-05, "loss": 2.0629, "step": 27120 }, { "epoch": 0.44, "learning_rate": 3.651302605210421e-05, "loss": 2.1187, "step": 27130 }, { "epoch": 0.44, "learning_rate": 3.650801603206413e-05, "loss": 2.1699, "step": 27140 }, { "epoch": 0.44, "learning_rate": 3.650300601202405e-05, "loss": 2.1957, "step": 27150 }, { "epoch": 0.44, "learning_rate": 3.649799599198397e-05, "loss": 2.1195, "step": 27160 }, { "epoch": 0.44, "learning_rate": 3.649298597194389e-05, "loss": 2.1239, "step": 27170 }, { "epoch": 0.44, "learning_rate": 3.648797595190381e-05, "loss": 2.0979, "step": 27180 }, { "epoch": 0.44, "learning_rate": 3.6482965931863724e-05, "loss": 2.1949, "step": 27190 }, { "epoch": 0.44, "learning_rate": 3.6477955911823645e-05, "loss": 2.1522, "step": 27200 }, { "epoch": 0.44, "learning_rate": 3.6472945891783566e-05, "loss": 2.1514, "step": 27210 }, { "epoch": 0.44, "learning_rate": 3.6467935871743486e-05, "loss": 2.16, "step": 27220 }, { "epoch": 0.44, "learning_rate": 3.6462925851703414e-05, "loss": 2.1275, "step": 27230 }, { "epoch": 0.45, "learning_rate": 3.645791583166333e-05, "loss": 2.0875, "step": 27240 }, { "epoch": 0.45, "learning_rate": 3.645290581162325e-05, "loss": 2.1029, "step": 27250 }, { "epoch": 0.45, "learning_rate": 3.644839679358718e-05, "loss": 2.1441, "step": 27260 }, { "epoch": 0.45, "learning_rate": 3.644338677354709e-05, "loss": 2.1229, "step": 27270 }, { "epoch": 0.45, "learning_rate": 3.643837675350701e-05, "loss": 2.1349, "step": 27280 }, { "epoch": 0.45, "learning_rate": 3.643336673346693e-05, "loss": 2.0915, "step": 27290 }, { "epoch": 0.45, "learning_rate": 3.6428356713426854e-05, "loss": 2.1123, "step": 27300 }, { "epoch": 0.45, "learning_rate": 3.6423346693386774e-05, "loss": 2.1448, "step": 27310 }, { "epoch": 0.45, "learning_rate": 3.6418336673346695e-05, "loss": 2.1366, "step": 27320 }, { "epoch": 0.45, "learning_rate": 3.6413326653306616e-05, "loss": 2.0933, "step": 27330 }, { "epoch": 0.45, "learning_rate": 3.6408316633266536e-05, "loss": 2.0961, "step": 27340 }, { "epoch": 0.45, "learning_rate": 3.640330661322646e-05, "loss": 2.1183, "step": 27350 }, { "epoch": 0.45, "learning_rate": 3.639829659318638e-05, "loss": 2.095, "step": 27360 }, { "epoch": 0.45, "learning_rate": 3.63932865731463e-05, "loss": 2.1098, "step": 27370 }, { "epoch": 0.45, "learning_rate": 3.638827655310621e-05, "loss": 2.1538, "step": 27380 }, { "epoch": 0.45, "learning_rate": 3.638326653306613e-05, "loss": 2.1403, "step": 27390 }, { "epoch": 0.45, "learning_rate": 3.6378256513026053e-05, "loss": 2.1564, "step": 27400 }, { "epoch": 0.45, "learning_rate": 3.6373246492985974e-05, "loss": 2.0873, "step": 27410 }, { "epoch": 0.45, "learning_rate": 3.6368236472945895e-05, "loss": 2.1121, "step": 27420 }, { "epoch": 0.45, "learning_rate": 3.6363226452905815e-05, "loss": 2.122, "step": 27430 }, { "epoch": 0.45, "learning_rate": 3.635821643286573e-05, "loss": 2.1153, "step": 27440 }, { "epoch": 0.45, "learning_rate": 3.635320641282565e-05, "loss": 2.1121, "step": 27450 }, { "epoch": 0.45, "learning_rate": 3.634819639278557e-05, "loss": 2.0886, "step": 27460 }, { "epoch": 0.45, "learning_rate": 3.634318637274549e-05, "loss": 2.1751, "step": 27470 }, { "epoch": 0.45, "learning_rate": 3.633817635270541e-05, "loss": 2.1808, "step": 27480 }, { "epoch": 0.45, "learning_rate": 3.633316633266533e-05, "loss": 2.1322, "step": 27490 }, { "epoch": 0.45, "learning_rate": 3.632815631262525e-05, "loss": 2.1431, "step": 27500 }, { "epoch": 0.45, "learning_rate": 3.632314629258517e-05, "loss": 2.0956, "step": 27510 }, { "epoch": 0.45, "learning_rate": 3.6318136272545094e-05, "loss": 2.1177, "step": 27520 }, { "epoch": 0.45, "learning_rate": 3.6313126252505015e-05, "loss": 2.1004, "step": 27530 }, { "epoch": 0.45, "learning_rate": 3.6308116232464936e-05, "loss": 2.1445, "step": 27540 }, { "epoch": 0.45, "learning_rate": 3.6303106212424856e-05, "loss": 2.0975, "step": 27550 }, { "epoch": 0.45, "learning_rate": 3.629809619238477e-05, "loss": 2.1279, "step": 27560 }, { "epoch": 0.45, "learning_rate": 3.629308617234469e-05, "loss": 2.1431, "step": 27570 }, { "epoch": 0.45, "learning_rate": 3.628807615230461e-05, "loss": 2.1065, "step": 27580 }, { "epoch": 0.45, "learning_rate": 3.628306613226453e-05, "loss": 2.1123, "step": 27590 }, { "epoch": 0.45, "learning_rate": 3.627805611222445e-05, "loss": 2.1165, "step": 27600 }, { "epoch": 0.45, "learning_rate": 3.6273046092184373e-05, "loss": 2.1497, "step": 27610 }, { "epoch": 0.45, "learning_rate": 3.626803607214429e-05, "loss": 2.1348, "step": 27620 }, { "epoch": 0.45, "learning_rate": 3.626302605210421e-05, "loss": 2.1604, "step": 27630 }, { "epoch": 0.45, "learning_rate": 3.625801603206413e-05, "loss": 2.0692, "step": 27640 }, { "epoch": 0.45, "learning_rate": 3.625300601202405e-05, "loss": 2.1464, "step": 27650 }, { "epoch": 0.45, "learning_rate": 3.624799599198397e-05, "loss": 2.1148, "step": 27660 }, { "epoch": 0.45, "learning_rate": 3.624298597194389e-05, "loss": 2.0909, "step": 27670 }, { "epoch": 0.45, "learning_rate": 3.6237975951903804e-05, "loss": 2.106, "step": 27680 }, { "epoch": 0.45, "learning_rate": 3.6232965931863725e-05, "loss": 2.0982, "step": 27690 }, { "epoch": 0.45, "learning_rate": 3.6227955911823646e-05, "loss": 2.1309, "step": 27700 }, { "epoch": 0.45, "learning_rate": 3.6222945891783566e-05, "loss": 2.1764, "step": 27710 }, { "epoch": 0.45, "learning_rate": 3.6217935871743494e-05, "loss": 2.0806, "step": 27720 }, { "epoch": 0.45, "learning_rate": 3.621292585170341e-05, "loss": 2.1033, "step": 27730 }, { "epoch": 0.45, "learning_rate": 3.620791583166333e-05, "loss": 2.1464, "step": 27740 }, { "epoch": 0.45, "learning_rate": 3.620290581162325e-05, "loss": 2.1119, "step": 27750 }, { "epoch": 0.45, "learning_rate": 3.619789579158317e-05, "loss": 2.1296, "step": 27760 }, { "epoch": 0.45, "learning_rate": 3.619288577154309e-05, "loss": 2.1279, "step": 27770 }, { "epoch": 0.45, "learning_rate": 3.618787575150301e-05, "loss": 2.16, "step": 27780 }, { "epoch": 0.45, "learning_rate": 3.618286573146293e-05, "loss": 2.123, "step": 27790 }, { "epoch": 0.45, "learning_rate": 3.6177855711422845e-05, "loss": 2.1395, "step": 27800 }, { "epoch": 0.45, "learning_rate": 3.6172845691382766e-05, "loss": 2.0943, "step": 27810 }, { "epoch": 0.45, "learning_rate": 3.6167835671342687e-05, "loss": 2.1116, "step": 27820 }, { "epoch": 0.45, "learning_rate": 3.616282565130261e-05, "loss": 2.1309, "step": 27830 }, { "epoch": 0.45, "learning_rate": 3.615781563126253e-05, "loss": 2.0867, "step": 27840 }, { "epoch": 0.46, "learning_rate": 3.615280561122245e-05, "loss": 2.0649, "step": 27850 }, { "epoch": 0.46, "learning_rate": 3.614779559118236e-05, "loss": 2.1274, "step": 27860 }, { "epoch": 0.46, "learning_rate": 3.614278557114228e-05, "loss": 2.1268, "step": 27870 }, { "epoch": 0.46, "learning_rate": 3.6137775551102204e-05, "loss": 2.1142, "step": 27880 }, { "epoch": 0.46, "learning_rate": 3.6132765531062124e-05, "loss": 2.0961, "step": 27890 }, { "epoch": 0.46, "learning_rate": 3.6127755511022045e-05, "loss": 2.1064, "step": 27900 }, { "epoch": 0.46, "learning_rate": 3.6122745490981966e-05, "loss": 2.0838, "step": 27910 }, { "epoch": 0.46, "learning_rate": 3.6117735470941886e-05, "loss": 2.1187, "step": 27920 }, { "epoch": 0.46, "learning_rate": 3.611272545090181e-05, "loss": 2.1117, "step": 27930 }, { "epoch": 0.46, "learning_rate": 3.610771543086173e-05, "loss": 2.1526, "step": 27940 }, { "epoch": 0.46, "learning_rate": 3.610270541082165e-05, "loss": 2.1642, "step": 27950 }, { "epoch": 0.46, "learning_rate": 3.609769539078157e-05, "loss": 2.1381, "step": 27960 }, { "epoch": 0.46, "learning_rate": 3.609268537074148e-05, "loss": 2.126, "step": 27970 }, { "epoch": 0.46, "learning_rate": 3.60876753507014e-05, "loss": 2.0949, "step": 27980 }, { "epoch": 0.46, "learning_rate": 3.6082665330661324e-05, "loss": 2.1016, "step": 27990 }, { "epoch": 0.46, "learning_rate": 3.6077655310621245e-05, "loss": 2.1662, "step": 28000 }, { "epoch": 0.46, "eval_loss": 2.099177360534668, "eval_mean_f1": 0.6465921674692968, "eval_rouge1_f1": 0.7070786926550046, "eval_rouge1_precision": 0.8191896908047527, "eval_rouge1_recall": 0.6545284585948716, "eval_rouge2_f1": 0.5580950650484802, "eval_rouge2_precision": 0.6489793694261464, "eval_rouge2_recall": 0.5169534936799288, "eval_rougeL_f1": 0.6746027447044058, "eval_rougeL_precision": 0.7784606369682198, "eval_rougeL_recall": 0.6258859203859715, "eval_runtime": 67.05, "eval_samples_per_second": 15.272, "eval_steps_per_second": 1.909, "step": 28000 }, { "epoch": 0.46, "learning_rate": 3.6072645290581165e-05, "loss": 2.1364, "step": 28010 }, { "epoch": 0.46, "learning_rate": 3.6067635270541086e-05, "loss": 2.0665, "step": 28020 }, { "epoch": 0.46, "learning_rate": 3.6062625250501006e-05, "loss": 2.1397, "step": 28030 }, { "epoch": 0.46, "learning_rate": 3.605761523046092e-05, "loss": 2.1478, "step": 28040 }, { "epoch": 0.46, "learning_rate": 3.605260521042084e-05, "loss": 2.128, "step": 28050 }, { "epoch": 0.46, "learning_rate": 3.604759519038076e-05, "loss": 2.1955, "step": 28060 }, { "epoch": 0.46, "learning_rate": 3.604258517034068e-05, "loss": 2.1179, "step": 28070 }, { "epoch": 0.46, "learning_rate": 3.60375751503006e-05, "loss": 2.1427, "step": 28080 }, { "epoch": 0.46, "learning_rate": 3.6032565130260524e-05, "loss": 2.1182, "step": 28090 }, { "epoch": 0.46, "learning_rate": 3.602755511022044e-05, "loss": 2.1032, "step": 28100 }, { "epoch": 0.46, "learning_rate": 3.6022545090180365e-05, "loss": 2.0911, "step": 28110 }, { "epoch": 0.46, "learning_rate": 3.6017535070140285e-05, "loss": 2.1466, "step": 28120 }, { "epoch": 0.46, "learning_rate": 3.6012525050100206e-05, "loss": 2.1295, "step": 28130 }, { "epoch": 0.46, "learning_rate": 3.600751503006013e-05, "loss": 2.159, "step": 28140 }, { "epoch": 0.46, "learning_rate": 3.600250501002004e-05, "loss": 2.1286, "step": 28150 }, { "epoch": 0.46, "learning_rate": 3.599749498997996e-05, "loss": 2.1618, "step": 28160 }, { "epoch": 0.46, "learning_rate": 3.599248496993988e-05, "loss": 2.0925, "step": 28170 }, { "epoch": 0.46, "learning_rate": 3.59874749498998e-05, "loss": 2.1517, "step": 28180 }, { "epoch": 0.46, "learning_rate": 3.598246492985972e-05, "loss": 2.1261, "step": 28190 }, { "epoch": 0.46, "learning_rate": 3.5977454909819644e-05, "loss": 2.1269, "step": 28200 }, { "epoch": 0.46, "learning_rate": 3.597244488977956e-05, "loss": 2.1549, "step": 28210 }, { "epoch": 0.46, "learning_rate": 3.596743486973948e-05, "loss": 2.1127, "step": 28220 }, { "epoch": 0.46, "learning_rate": 3.59624248496994e-05, "loss": 2.1472, "step": 28230 }, { "epoch": 0.46, "learning_rate": 3.595741482965932e-05, "loss": 2.1517, "step": 28240 }, { "epoch": 0.46, "learning_rate": 3.595240480961924e-05, "loss": 2.1457, "step": 28250 }, { "epoch": 0.46, "learning_rate": 3.594739478957916e-05, "loss": 2.1493, "step": 28260 }, { "epoch": 0.46, "learning_rate": 3.5942384769539075e-05, "loss": 2.1126, "step": 28270 }, { "epoch": 0.46, "learning_rate": 3.5937374749498995e-05, "loss": 2.1479, "step": 28280 }, { "epoch": 0.46, "learning_rate": 3.5932364729458916e-05, "loss": 2.1356, "step": 28290 }, { "epoch": 0.46, "learning_rate": 3.592735470941884e-05, "loss": 2.1301, "step": 28300 }, { "epoch": 0.46, "learning_rate": 3.5922344689378764e-05, "loss": 2.1243, "step": 28310 }, { "epoch": 0.46, "learning_rate": 3.5917334669338685e-05, "loss": 2.1081, "step": 28320 }, { "epoch": 0.46, "learning_rate": 3.59123246492986e-05, "loss": 2.1163, "step": 28330 }, { "epoch": 0.46, "learning_rate": 3.590731462925852e-05, "loss": 2.1055, "step": 28340 }, { "epoch": 0.46, "learning_rate": 3.590230460921844e-05, "loss": 2.0994, "step": 28350 }, { "epoch": 0.46, "learning_rate": 3.589729458917836e-05, "loss": 2.1322, "step": 28360 }, { "epoch": 0.46, "learning_rate": 3.589228456913828e-05, "loss": 2.114, "step": 28370 }, { "epoch": 0.46, "learning_rate": 3.58872745490982e-05, "loss": 2.129, "step": 28380 }, { "epoch": 0.46, "learning_rate": 3.5882264529058116e-05, "loss": 2.076, "step": 28390 }, { "epoch": 0.46, "learning_rate": 3.5877254509018036e-05, "loss": 2.125, "step": 28400 }, { "epoch": 0.46, "learning_rate": 3.587224448897796e-05, "loss": 2.1073, "step": 28410 }, { "epoch": 0.46, "learning_rate": 3.586723446893788e-05, "loss": 2.1001, "step": 28420 }, { "epoch": 0.46, "learning_rate": 3.58622244488978e-05, "loss": 2.1596, "step": 28430 }, { "epoch": 0.46, "learning_rate": 3.585721442885772e-05, "loss": 2.1025, "step": 28440 }, { "epoch": 0.46, "learning_rate": 3.585220440881763e-05, "loss": 2.1329, "step": 28450 }, { "epoch": 0.47, "learning_rate": 3.584719438877755e-05, "loss": 2.1089, "step": 28460 }, { "epoch": 0.47, "learning_rate": 3.5842184368737474e-05, "loss": 2.0862, "step": 28470 }, { "epoch": 0.47, "learning_rate": 3.5837174348697395e-05, "loss": 2.1469, "step": 28480 }, { "epoch": 0.47, "learning_rate": 3.5832164328657315e-05, "loss": 2.1342, "step": 28490 }, { "epoch": 0.47, "learning_rate": 3.5827154308617236e-05, "loss": 2.1204, "step": 28500 }, { "epoch": 0.47, "learning_rate": 3.5822144288577157e-05, "loss": 2.1274, "step": 28510 }, { "epoch": 0.47, "learning_rate": 3.581713426853708e-05, "loss": 2.1115, "step": 28520 }, { "epoch": 0.47, "learning_rate": 3.5812124248497e-05, "loss": 2.1725, "step": 28530 }, { "epoch": 0.47, "learning_rate": 3.580711422845692e-05, "loss": 2.1106, "step": 28540 }, { "epoch": 0.47, "learning_rate": 3.580210420841684e-05, "loss": 2.1223, "step": 28550 }, { "epoch": 0.47, "learning_rate": 3.579709418837675e-05, "loss": 2.1244, "step": 28560 }, { "epoch": 0.47, "learning_rate": 3.5792084168336674e-05, "loss": 2.0776, "step": 28570 }, { "epoch": 0.47, "learning_rate": 3.5787074148296594e-05, "loss": 2.1055, "step": 28580 }, { "epoch": 0.47, "learning_rate": 3.5782064128256515e-05, "loss": 2.1273, "step": 28590 }, { "epoch": 0.47, "learning_rate": 3.5777054108216436e-05, "loss": 2.135, "step": 28600 }, { "epoch": 0.47, "learning_rate": 3.5772044088176356e-05, "loss": 2.064, "step": 28610 }, { "epoch": 0.47, "learning_rate": 3.576703406813628e-05, "loss": 2.1135, "step": 28620 }, { "epoch": 0.47, "learning_rate": 3.576202404809619e-05, "loss": 2.1404, "step": 28630 }, { "epoch": 0.47, "learning_rate": 3.575701402805611e-05, "loss": 2.1236, "step": 28640 }, { "epoch": 0.47, "learning_rate": 3.575200400801603e-05, "loss": 2.2224, "step": 28650 }, { "epoch": 0.47, "learning_rate": 3.574699398797595e-05, "loss": 2.1642, "step": 28660 }, { "epoch": 0.47, "learning_rate": 3.574198396793587e-05, "loss": 2.1326, "step": 28670 }, { "epoch": 0.47, "learning_rate": 3.5736973947895794e-05, "loss": 2.1265, "step": 28680 }, { "epoch": 0.47, "learning_rate": 3.573196392785571e-05, "loss": 2.126, "step": 28690 }, { "epoch": 0.47, "learning_rate": 3.5726953907815635e-05, "loss": 2.1175, "step": 28700 }, { "epoch": 0.47, "learning_rate": 3.5721943887775556e-05, "loss": 2.1106, "step": 28710 }, { "epoch": 0.47, "learning_rate": 3.5716933867735476e-05, "loss": 2.0882, "step": 28720 }, { "epoch": 0.47, "learning_rate": 3.57119238476954e-05, "loss": 2.1034, "step": 28730 }, { "epoch": 0.47, "learning_rate": 3.570691382765531e-05, "loss": 2.1353, "step": 28740 }, { "epoch": 0.47, "learning_rate": 3.570190380761523e-05, "loss": 2.1277, "step": 28750 }, { "epoch": 0.47, "learning_rate": 3.569689378757515e-05, "loss": 2.1529, "step": 28760 }, { "epoch": 0.47, "learning_rate": 3.569188376753507e-05, "loss": 2.1231, "step": 28770 }, { "epoch": 0.47, "learning_rate": 3.5686873747494994e-05, "loss": 2.0807, "step": 28780 }, { "epoch": 0.47, "learning_rate": 3.5681863727454914e-05, "loss": 2.1107, "step": 28790 }, { "epoch": 0.47, "learning_rate": 3.567685370741483e-05, "loss": 2.1489, "step": 28800 }, { "epoch": 0.47, "learning_rate": 3.567184368737475e-05, "loss": 2.1071, "step": 28810 }, { "epoch": 0.47, "learning_rate": 3.566683366733467e-05, "loss": 2.1288, "step": 28820 }, { "epoch": 0.47, "learning_rate": 3.566182364729459e-05, "loss": 2.1402, "step": 28830 }, { "epoch": 0.47, "learning_rate": 3.565681362725451e-05, "loss": 2.1384, "step": 28840 }, { "epoch": 0.47, "learning_rate": 3.565180360721443e-05, "loss": 2.1382, "step": 28850 }, { "epoch": 0.47, "learning_rate": 3.564679358717435e-05, "loss": 2.0927, "step": 28860 }, { "epoch": 0.47, "learning_rate": 3.5641783567134266e-05, "loss": 2.1174, "step": 28870 }, { "epoch": 0.47, "learning_rate": 3.5636773547094186e-05, "loss": 2.1313, "step": 28880 }, { "epoch": 0.47, "learning_rate": 3.563176352705411e-05, "loss": 2.136, "step": 28890 }, { "epoch": 0.47, "learning_rate": 3.5626753507014034e-05, "loss": 2.1058, "step": 28900 }, { "epoch": 0.47, "learning_rate": 3.5621743486973955e-05, "loss": 2.1223, "step": 28910 }, { "epoch": 0.47, "learning_rate": 3.561673346693387e-05, "loss": 2.0915, "step": 28920 }, { "epoch": 0.47, "learning_rate": 3.561172344689379e-05, "loss": 2.1568, "step": 28930 }, { "epoch": 0.47, "learning_rate": 3.560671342685371e-05, "loss": 2.1338, "step": 28940 }, { "epoch": 0.47, "learning_rate": 3.560170340681363e-05, "loss": 2.1349, "step": 28950 }, { "epoch": 0.47, "learning_rate": 3.559669338677355e-05, "loss": 2.0944, "step": 28960 }, { "epoch": 0.47, "learning_rate": 3.559168336673347e-05, "loss": 2.0851, "step": 28970 }, { "epoch": 0.47, "learning_rate": 3.5586673346693386e-05, "loss": 2.1115, "step": 28980 }, { "epoch": 0.47, "learning_rate": 3.558166332665331e-05, "loss": 2.121, "step": 28990 }, { "epoch": 0.47, "learning_rate": 3.557665330661323e-05, "loss": 2.1559, "step": 29000 }, { "epoch": 0.47, "eval_loss": 2.0950562953948975, "eval_mean_f1": 0.6423349827350336, "eval_rouge1_f1": 0.7028554923325747, "eval_rouge1_precision": 0.8124564601299437, "eval_rouge1_recall": 0.6524775663238491, "eval_rouge2_f1": 0.5535755950353596, "eval_rouge2_precision": 0.6443039077621595, "eval_rouge2_recall": 0.513659908830235, "eval_rougeL_f1": 0.6705738608371667, "eval_rougeL_precision": 0.7733463526044524, "eval_rougeL_recall": 0.6235423105906005, "eval_runtime": 66.6087, "eval_samples_per_second": 15.373, "eval_steps_per_second": 1.922, "step": 29000 }, { "epoch": 0.47, "learning_rate": 3.557164328657315e-05, "loss": 2.1361, "step": 29010 }, { "epoch": 0.47, "learning_rate": 3.556663326653307e-05, "loss": 2.1351, "step": 29020 }, { "epoch": 0.47, "learning_rate": 3.556162324649299e-05, "loss": 2.1124, "step": 29030 }, { "epoch": 0.47, "learning_rate": 3.55566132264529e-05, "loss": 2.1682, "step": 29040 }, { "epoch": 0.47, "learning_rate": 3.5551603206412824e-05, "loss": 2.1801, "step": 29050 }, { "epoch": 0.47, "learning_rate": 3.5546593186372744e-05, "loss": 2.078, "step": 29060 }, { "epoch": 0.47, "learning_rate": 3.5541583166332665e-05, "loss": 2.0791, "step": 29070 }, { "epoch": 0.48, "learning_rate": 3.5536573146292586e-05, "loss": 2.155, "step": 29080 }, { "epoch": 0.48, "learning_rate": 3.5531563126252506e-05, "loss": 2.1418, "step": 29090 }, { "epoch": 0.48, "learning_rate": 3.552655310621243e-05, "loss": 2.1138, "step": 29100 }, { "epoch": 0.48, "learning_rate": 3.552154308617235e-05, "loss": 2.1554, "step": 29110 }, { "epoch": 0.48, "learning_rate": 3.551653306613227e-05, "loss": 2.0621, "step": 29120 }, { "epoch": 0.48, "learning_rate": 3.551152304609219e-05, "loss": 2.1259, "step": 29130 }, { "epoch": 0.48, "learning_rate": 3.550651302605211e-05, "loss": 2.0845, "step": 29140 }, { "epoch": 0.48, "learning_rate": 3.550150300601203e-05, "loss": 2.1179, "step": 29150 }, { "epoch": 0.48, "learning_rate": 3.5496492985971944e-05, "loss": 2.1332, "step": 29160 }, { "epoch": 0.48, "learning_rate": 3.5491482965931865e-05, "loss": 2.111, "step": 29170 }, { "epoch": 0.48, "learning_rate": 3.5486472945891785e-05, "loss": 2.1302, "step": 29180 }, { "epoch": 0.48, "learning_rate": 3.5481462925851706e-05, "loss": 2.1396, "step": 29190 }, { "epoch": 0.48, "learning_rate": 3.547645290581163e-05, "loss": 2.1013, "step": 29200 }, { "epoch": 0.48, "learning_rate": 3.547144288577155e-05, "loss": 2.1272, "step": 29210 }, { "epoch": 0.48, "learning_rate": 3.546643286573146e-05, "loss": 2.1504, "step": 29220 }, { "epoch": 0.48, "learning_rate": 3.546142284569138e-05, "loss": 2.1173, "step": 29230 }, { "epoch": 0.48, "learning_rate": 3.54564128256513e-05, "loss": 2.1237, "step": 29240 }, { "epoch": 0.48, "learning_rate": 3.545140280561122e-05, "loss": 2.1224, "step": 29250 }, { "epoch": 0.48, "learning_rate": 3.5446392785571144e-05, "loss": 2.1389, "step": 29260 }, { "epoch": 0.48, "learning_rate": 3.5441382765531064e-05, "loss": 2.0838, "step": 29270 }, { "epoch": 0.48, "learning_rate": 3.543637274549098e-05, "loss": 2.111, "step": 29280 }, { "epoch": 0.48, "learning_rate": 3.5431362725450906e-05, "loss": 2.0998, "step": 29290 }, { "epoch": 0.48, "learning_rate": 3.5426352705410826e-05, "loss": 2.0972, "step": 29300 }, { "epoch": 0.48, "learning_rate": 3.542134268537075e-05, "loss": 2.0729, "step": 29310 }, { "epoch": 0.48, "learning_rate": 3.541633266533067e-05, "loss": 2.0847, "step": 29320 }, { "epoch": 0.48, "learning_rate": 3.541132264529058e-05, "loss": 2.0947, "step": 29330 }, { "epoch": 0.48, "learning_rate": 3.54063126252505e-05, "loss": 2.1094, "step": 29340 }, { "epoch": 0.48, "learning_rate": 3.540130260521042e-05, "loss": 2.1155, "step": 29350 }, { "epoch": 0.48, "learning_rate": 3.539629258517034e-05, "loss": 2.1246, "step": 29360 }, { "epoch": 0.48, "learning_rate": 3.5391282565130264e-05, "loss": 2.1067, "step": 29370 }, { "epoch": 0.48, "learning_rate": 3.5386272545090185e-05, "loss": 2.1154, "step": 29380 }, { "epoch": 0.48, "learning_rate": 3.53812625250501e-05, "loss": 2.1032, "step": 29390 }, { "epoch": 0.48, "learning_rate": 3.537625250501002e-05, "loss": 2.0831, "step": 29400 }, { "epoch": 0.48, "learning_rate": 3.537124248496994e-05, "loss": 2.0761, "step": 29410 }, { "epoch": 0.48, "learning_rate": 3.536623246492986e-05, "loss": 2.1347, "step": 29420 }, { "epoch": 0.48, "learning_rate": 3.536122244488978e-05, "loss": 2.112, "step": 29430 }, { "epoch": 0.48, "learning_rate": 3.53562124248497e-05, "loss": 2.1383, "step": 29440 }, { "epoch": 0.48, "learning_rate": 3.535120240480962e-05, "loss": 2.1146, "step": 29450 }, { "epoch": 0.48, "learning_rate": 3.5346192384769536e-05, "loss": 2.05, "step": 29460 }, { "epoch": 0.48, "learning_rate": 3.534118236472946e-05, "loss": 2.1523, "step": 29470 }, { "epoch": 0.48, "learning_rate": 3.533617234468938e-05, "loss": 2.1593, "step": 29480 }, { "epoch": 0.48, "learning_rate": 3.5331162324649305e-05, "loss": 2.0776, "step": 29490 }, { "epoch": 0.48, "learning_rate": 3.5326152304609226e-05, "loss": 2.1193, "step": 29500 }, { "epoch": 0.48, "learning_rate": 3.532114228456914e-05, "loss": 2.1155, "step": 29510 }, { "epoch": 0.48, "learning_rate": 3.531613226452906e-05, "loss": 2.161, "step": 29520 }, { "epoch": 0.48, "learning_rate": 3.531112224448898e-05, "loss": 2.1246, "step": 29530 }, { "epoch": 0.48, "learning_rate": 3.53061122244489e-05, "loss": 2.1324, "step": 29540 }, { "epoch": 0.48, "learning_rate": 3.530110220440882e-05, "loss": 2.138, "step": 29550 }, { "epoch": 0.48, "learning_rate": 3.529609218436874e-05, "loss": 2.0961, "step": 29560 }, { "epoch": 0.48, "learning_rate": 3.5291082164328656e-05, "loss": 2.1103, "step": 29570 }, { "epoch": 0.48, "learning_rate": 3.528607214428858e-05, "loss": 2.1152, "step": 29580 }, { "epoch": 0.48, "learning_rate": 3.52810621242485e-05, "loss": 2.1319, "step": 29590 }, { "epoch": 0.48, "learning_rate": 3.527605210420842e-05, "loss": 2.1061, "step": 29600 }, { "epoch": 0.48, "learning_rate": 3.527104208416834e-05, "loss": 2.1529, "step": 29610 }, { "epoch": 0.48, "learning_rate": 3.526603206412826e-05, "loss": 2.0344, "step": 29620 }, { "epoch": 0.48, "learning_rate": 3.5261022044088174e-05, "loss": 2.1171, "step": 29630 }, { "epoch": 0.48, "learning_rate": 3.5256012024048094e-05, "loss": 2.14, "step": 29640 }, { "epoch": 0.48, "learning_rate": 3.5251002004008015e-05, "loss": 2.0989, "step": 29650 }, { "epoch": 0.48, "learning_rate": 3.5245991983967935e-05, "loss": 2.1413, "step": 29660 }, { "epoch": 0.48, "learning_rate": 3.5240981963927856e-05, "loss": 2.0852, "step": 29670 }, { "epoch": 0.48, "learning_rate": 3.523597194388778e-05, "loss": 2.1233, "step": 29680 }, { "epoch": 0.49, "learning_rate": 3.52309619238477e-05, "loss": 2.1558, "step": 29690 }, { "epoch": 0.49, "learning_rate": 3.522595190380762e-05, "loss": 2.1314, "step": 29700 }, { "epoch": 0.49, "learning_rate": 3.522094188376754e-05, "loss": 2.1272, "step": 29710 }, { "epoch": 0.49, "learning_rate": 3.521593186372746e-05, "loss": 2.1207, "step": 29720 }, { "epoch": 0.49, "learning_rate": 3.521092184368738e-05, "loss": 2.1102, "step": 29730 }, { "epoch": 0.49, "learning_rate": 3.52059118236473e-05, "loss": 2.1319, "step": 29740 }, { "epoch": 0.49, "learning_rate": 3.5200901803607214e-05, "loss": 2.1214, "step": 29750 }, { "epoch": 0.49, "learning_rate": 3.5195891783567135e-05, "loss": 2.0906, "step": 29760 }, { "epoch": 0.49, "learning_rate": 3.5190881763527056e-05, "loss": 2.1236, "step": 29770 }, { "epoch": 0.49, "learning_rate": 3.5185871743486976e-05, "loss": 2.143, "step": 29780 }, { "epoch": 0.49, "learning_rate": 3.51808617234469e-05, "loss": 2.1273, "step": 29790 }, { "epoch": 0.49, "learning_rate": 3.517585170340682e-05, "loss": 2.1305, "step": 29800 }, { "epoch": 0.49, "learning_rate": 3.517084168336673e-05, "loss": 2.1532, "step": 29810 }, { "epoch": 0.49, "learning_rate": 3.516583166332665e-05, "loss": 2.1229, "step": 29820 }, { "epoch": 0.49, "learning_rate": 3.516082164328657e-05, "loss": 2.1443, "step": 29830 }, { "epoch": 0.49, "learning_rate": 3.5155811623246493e-05, "loss": 2.113, "step": 29840 }, { "epoch": 0.49, "learning_rate": 3.5150801603206414e-05, "loss": 2.1464, "step": 29850 }, { "epoch": 0.49, "learning_rate": 3.5145791583166335e-05, "loss": 2.1503, "step": 29860 }, { "epoch": 0.49, "learning_rate": 3.514078156312625e-05, "loss": 2.1785, "step": 29870 }, { "epoch": 0.49, "learning_rate": 3.5135771543086176e-05, "loss": 2.1176, "step": 29880 }, { "epoch": 0.49, "learning_rate": 3.51307615230461e-05, "loss": 2.136, "step": 29890 }, { "epoch": 0.49, "learning_rate": 3.512575150300602e-05, "loss": 2.1101, "step": 29900 }, { "epoch": 0.49, "learning_rate": 3.512074148296594e-05, "loss": 2.0985, "step": 29910 }, { "epoch": 0.49, "learning_rate": 3.511573146292585e-05, "loss": 2.0766, "step": 29920 }, { "epoch": 0.49, "learning_rate": 3.511072144288577e-05, "loss": 2.1218, "step": 29930 }, { "epoch": 0.49, "learning_rate": 3.510571142284569e-05, "loss": 2.0968, "step": 29940 }, { "epoch": 0.49, "learning_rate": 3.5100701402805614e-05, "loss": 2.1122, "step": 29950 }, { "epoch": 0.49, "learning_rate": 3.5095691382765534e-05, "loss": 2.1501, "step": 29960 }, { "epoch": 0.49, "learning_rate": 3.5090681362725455e-05, "loss": 2.1027, "step": 29970 }, { "epoch": 0.49, "learning_rate": 3.508567134268537e-05, "loss": 2.0767, "step": 29980 }, { "epoch": 0.49, "learning_rate": 3.508066132264529e-05, "loss": 2.1239, "step": 29990 }, { "epoch": 0.49, "learning_rate": 3.507565130260521e-05, "loss": 2.0698, "step": 30000 }, { "epoch": 0.49, "eval_loss": 2.090508222579956, "eval_mean_f1": 0.6445618540025623, "eval_rouge1_f1": 0.7055040822019061, "eval_rouge1_precision": 0.8142226785785058, "eval_rouge1_recall": 0.6557036792332558, "eval_rouge2_f1": 0.5566286189303873, "eval_rouge2_precision": 0.6478508524895241, "eval_rouge2_recall": 0.5170445672646129, "eval_rougeL_f1": 0.6715528608753933, "eval_rougeL_precision": 0.7740093468447523, "eval_rougeL_recall": 0.6249257397478476, "eval_runtime": 65.7969, "eval_samples_per_second": 15.563, "eval_steps_per_second": 1.945, "step": 30000 }, { "epoch": 0.49, "learning_rate": 3.507064128256513e-05, "loss": 2.1083, "step": 30010 }, { "epoch": 0.49, "learning_rate": 3.506563126252505e-05, "loss": 2.1133, "step": 30020 }, { "epoch": 0.49, "learning_rate": 3.506062124248497e-05, "loss": 2.1434, "step": 30030 }, { "epoch": 0.49, "learning_rate": 3.505561122244489e-05, "loss": 2.0765, "step": 30040 }, { "epoch": 0.49, "learning_rate": 3.5050601202404807e-05, "loss": 2.0888, "step": 30050 }, { "epoch": 0.49, "learning_rate": 3.504559118236473e-05, "loss": 2.1249, "step": 30060 }, { "epoch": 0.49, "learning_rate": 3.504058116232465e-05, "loss": 2.113, "step": 30070 }, { "epoch": 0.49, "learning_rate": 3.5035571142284575e-05, "loss": 2.1012, "step": 30080 }, { "epoch": 0.49, "learning_rate": 3.5030561122244496e-05, "loss": 2.1203, "step": 30090 }, { "epoch": 0.49, "learning_rate": 3.502555110220441e-05, "loss": 2.118, "step": 30100 }, { "epoch": 0.49, "learning_rate": 3.502054108216433e-05, "loss": 2.0671, "step": 30110 }, { "epoch": 0.49, "learning_rate": 3.501553106212425e-05, "loss": 2.0871, "step": 30120 }, { "epoch": 0.49, "learning_rate": 3.501052104208417e-05, "loss": 2.1144, "step": 30130 }, { "epoch": 0.49, "learning_rate": 3.500551102204409e-05, "loss": 2.129, "step": 30140 }, { "epoch": 0.49, "learning_rate": 3.500050100200401e-05, "loss": 2.1559, "step": 30150 }, { "epoch": 0.49, "learning_rate": 3.499549098196393e-05, "loss": 2.1386, "step": 30160 }, { "epoch": 0.49, "learning_rate": 3.499048096192385e-05, "loss": 2.1307, "step": 30170 }, { "epoch": 0.49, "learning_rate": 3.498547094188377e-05, "loss": 2.116, "step": 30180 }, { "epoch": 0.49, "learning_rate": 3.498046092184369e-05, "loss": 2.1178, "step": 30190 }, { "epoch": 0.49, "learning_rate": 3.497545090180361e-05, "loss": 2.1112, "step": 30200 }, { "epoch": 0.49, "learning_rate": 3.497044088176353e-05, "loss": 2.1092, "step": 30210 }, { "epoch": 0.49, "learning_rate": 3.4965430861723444e-05, "loss": 2.156, "step": 30220 }, { "epoch": 0.49, "learning_rate": 3.4960420841683365e-05, "loss": 2.1216, "step": 30230 }, { "epoch": 0.49, "learning_rate": 3.4955410821643285e-05, "loss": 2.1388, "step": 30240 }, { "epoch": 0.49, "learning_rate": 3.4950400801603206e-05, "loss": 2.0943, "step": 30250 }, { "epoch": 0.49, "learning_rate": 3.4945390781563127e-05, "loss": 2.0637, "step": 30260 }, { "epoch": 0.49, "learning_rate": 3.494038076152305e-05, "loss": 2.1576, "step": 30270 }, { "epoch": 0.49, "learning_rate": 3.493537074148297e-05, "loss": 2.0878, "step": 30280 }, { "epoch": 0.49, "learning_rate": 3.493036072144289e-05, "loss": 2.1143, "step": 30290 }, { "epoch": 0.5, "learning_rate": 3.492535070140281e-05, "loss": 2.0794, "step": 30300 }, { "epoch": 0.5, "learning_rate": 3.492034068136273e-05, "loss": 2.1369, "step": 30310 }, { "epoch": 0.5, "learning_rate": 3.491533066132265e-05, "loss": 2.0819, "step": 30320 }, { "epoch": 0.5, "learning_rate": 3.491032064128257e-05, "loss": 2.1058, "step": 30330 }, { "epoch": 0.5, "learning_rate": 3.4905310621242485e-05, "loss": 2.1196, "step": 30340 }, { "epoch": 0.5, "learning_rate": 3.4900300601202405e-05, "loss": 2.1457, "step": 30350 }, { "epoch": 0.5, "learning_rate": 3.4895290581162326e-05, "loss": 2.1084, "step": 30360 }, { "epoch": 0.5, "learning_rate": 3.489028056112225e-05, "loss": 2.1482, "step": 30370 }, { "epoch": 0.5, "learning_rate": 3.488527054108217e-05, "loss": 2.1177, "step": 30380 }, { "epoch": 0.5, "learning_rate": 3.488026052104209e-05, "loss": 2.1321, "step": 30390 }, { "epoch": 0.5, "learning_rate": 3.4875250501002e-05, "loss": 2.1185, "step": 30400 }, { "epoch": 0.5, "learning_rate": 3.487024048096192e-05, "loss": 2.0947, "step": 30410 }, { "epoch": 0.5, "learning_rate": 3.486523046092184e-05, "loss": 2.1387, "step": 30420 }, { "epoch": 0.5, "learning_rate": 3.4860220440881764e-05, "loss": 2.0996, "step": 30430 }, { "epoch": 0.5, "learning_rate": 3.4855210420841684e-05, "loss": 2.1169, "step": 30440 }, { "epoch": 0.5, "learning_rate": 3.4850200400801605e-05, "loss": 2.1401, "step": 30450 }, { "epoch": 0.5, "learning_rate": 3.484519038076152e-05, "loss": 2.123, "step": 30460 }, { "epoch": 0.5, "learning_rate": 3.4840180360721446e-05, "loss": 2.1373, "step": 30470 }, { "epoch": 0.5, "learning_rate": 3.483517034068137e-05, "loss": 2.1152, "step": 30480 }, { "epoch": 0.5, "learning_rate": 3.483016032064129e-05, "loss": 2.0963, "step": 30490 }, { "epoch": 0.5, "learning_rate": 3.482515030060121e-05, "loss": 2.1491, "step": 30500 }, { "epoch": 0.5, "learning_rate": 3.482014028056112e-05, "loss": 2.1189, "step": 30510 }, { "epoch": 0.5, "learning_rate": 3.481513026052104e-05, "loss": 2.1027, "step": 30520 }, { "epoch": 0.5, "learning_rate": 3.4810120240480963e-05, "loss": 2.1155, "step": 30530 }, { "epoch": 0.5, "learning_rate": 3.4805110220440884e-05, "loss": 2.1118, "step": 30540 }, { "epoch": 0.5, "learning_rate": 3.4800100200400805e-05, "loss": 2.0906, "step": 30550 }, { "epoch": 0.5, "learning_rate": 3.4795090180360725e-05, "loss": 2.1556, "step": 30560 }, { "epoch": 0.5, "learning_rate": 3.4790080160320646e-05, "loss": 2.1363, "step": 30570 }, { "epoch": 0.5, "learning_rate": 3.478507014028056e-05, "loss": 2.1286, "step": 30580 }, { "epoch": 0.5, "learning_rate": 3.478006012024048e-05, "loss": 2.1175, "step": 30590 }, { "epoch": 0.5, "learning_rate": 3.47750501002004e-05, "loss": 2.1211, "step": 30600 }, { "epoch": 0.5, "learning_rate": 3.477004008016032e-05, "loss": 2.0834, "step": 30610 }, { "epoch": 0.5, "learning_rate": 3.476503006012024e-05, "loss": 2.0793, "step": 30620 }, { "epoch": 0.5, "learning_rate": 3.476002004008016e-05, "loss": 2.0666, "step": 30630 }, { "epoch": 0.5, "learning_rate": 3.475501002004008e-05, "loss": 2.0948, "step": 30640 }, { "epoch": 0.5, "learning_rate": 3.475e-05, "loss": 2.1049, "step": 30650 }, { "epoch": 0.5, "learning_rate": 3.474498997995992e-05, "loss": 2.1431, "step": 30660 }, { "epoch": 0.5, "learning_rate": 3.4739979959919846e-05, "loss": 2.0777, "step": 30670 }, { "epoch": 0.5, "learning_rate": 3.4734969939879766e-05, "loss": 2.1668, "step": 30680 }, { "epoch": 0.5, "learning_rate": 3.472995991983968e-05, "loss": 2.0992, "step": 30690 }, { "epoch": 0.5, "learning_rate": 3.47249498997996e-05, "loss": 2.0747, "step": 30700 }, { "epoch": 0.5, "learning_rate": 3.471993987975952e-05, "loss": 2.1481, "step": 30710 }, { "epoch": 0.5, "learning_rate": 3.471492985971944e-05, "loss": 2.0783, "step": 30720 }, { "epoch": 0.5, "learning_rate": 3.470991983967936e-05, "loss": 2.1456, "step": 30730 }, { "epoch": 0.5, "learning_rate": 3.4704909819639283e-05, "loss": 2.0725, "step": 30740 }, { "epoch": 0.5, "learning_rate": 3.46998997995992e-05, "loss": 2.119, "step": 30750 }, { "epoch": 0.5, "learning_rate": 3.469488977955912e-05, "loss": 2.0931, "step": 30760 }, { "epoch": 0.5, "learning_rate": 3.468987975951904e-05, "loss": 2.1294, "step": 30770 }, { "epoch": 0.5, "learning_rate": 3.468486973947896e-05, "loss": 2.1104, "step": 30780 }, { "epoch": 0.5, "learning_rate": 3.467985971943888e-05, "loss": 2.1277, "step": 30790 }, { "epoch": 0.5, "learning_rate": 3.46748496993988e-05, "loss": 2.1138, "step": 30800 }, { "epoch": 0.5, "learning_rate": 3.4669839679358714e-05, "loss": 2.0876, "step": 30810 }, { "epoch": 0.5, "learning_rate": 3.4664829659318635e-05, "loss": 2.1645, "step": 30820 }, { "epoch": 0.5, "learning_rate": 3.4659819639278556e-05, "loss": 2.1168, "step": 30830 }, { "epoch": 0.5, "learning_rate": 3.4654809619238476e-05, "loss": 2.1475, "step": 30840 }, { "epoch": 0.5, "learning_rate": 3.46497995991984e-05, "loss": 2.141, "step": 30850 }, { "epoch": 0.5, "learning_rate": 3.4644789579158324e-05, "loss": 2.1184, "step": 30860 }, { "epoch": 0.5, "learning_rate": 3.463977955911824e-05, "loss": 2.1307, "step": 30870 }, { "epoch": 0.5, "learning_rate": 3.463476953907816e-05, "loss": 2.1491, "step": 30880 }, { "epoch": 0.5, "learning_rate": 3.462975951903808e-05, "loss": 2.1213, "step": 30890 }, { "epoch": 0.5, "learning_rate": 3.4624749498998e-05, "loss": 2.1531, "step": 30900 }, { "epoch": 0.51, "learning_rate": 3.461973947895792e-05, "loss": 2.1826, "step": 30910 }, { "epoch": 0.51, "learning_rate": 3.461472945891784e-05, "loss": 2.1217, "step": 30920 }, { "epoch": 0.51, "learning_rate": 3.4609719438877755e-05, "loss": 2.1335, "step": 30930 }, { "epoch": 0.51, "learning_rate": 3.4604709418837676e-05, "loss": 2.1211, "step": 30940 }, { "epoch": 0.51, "learning_rate": 3.4599699398797597e-05, "loss": 2.1096, "step": 30950 }, { "epoch": 0.51, "learning_rate": 3.459468937875752e-05, "loss": 2.1228, "step": 30960 }, { "epoch": 0.51, "learning_rate": 3.458967935871744e-05, "loss": 2.1489, "step": 30970 }, { "epoch": 0.51, "learning_rate": 3.458466933867736e-05, "loss": 2.0969, "step": 30980 }, { "epoch": 0.51, "learning_rate": 3.457965931863727e-05, "loss": 2.1285, "step": 30990 }, { "epoch": 0.51, "learning_rate": 3.457464929859719e-05, "loss": 2.1175, "step": 31000 }, { "epoch": 0.51, "eval_loss": 2.0864810943603516, "eval_mean_f1": 0.6456722073846488, "eval_rouge1_f1": 0.7053354981816645, "eval_rouge1_precision": 0.8142965679690884, "eval_rouge1_recall": 0.6551505275755943, "eval_rouge2_f1": 0.5581902820157445, "eval_rouge2_precision": 0.6475058788596386, "eval_rouge2_recall": 0.5187565312624494, "eval_rougeL_f1": 0.6734908419565375, "eval_rougeL_precision": 0.775114131115323, "eval_rougeL_recall": 0.6271247298515856, "eval_runtime": 65.4677, "eval_samples_per_second": 15.641, "eval_steps_per_second": 1.955, "step": 31000 }, { "epoch": 0.51, "learning_rate": 3.4569639278557114e-05, "loss": 2.0941, "step": 31010 }, { "epoch": 0.51, "learning_rate": 3.4564629258517034e-05, "loss": 2.1202, "step": 31020 }, { "epoch": 0.51, "learning_rate": 3.4560120240480964e-05, "loss": 2.1319, "step": 31030 }, { "epoch": 0.51, "learning_rate": 3.4555110220440885e-05, "loss": 2.0893, "step": 31040 }, { "epoch": 0.51, "learning_rate": 3.4550100200400805e-05, "loss": 2.1107, "step": 31050 }, { "epoch": 0.51, "learning_rate": 3.4545090180360726e-05, "loss": 2.1344, "step": 31060 }, { "epoch": 0.51, "learning_rate": 3.454008016032064e-05, "loss": 2.1336, "step": 31070 }, { "epoch": 0.51, "learning_rate": 3.453507014028056e-05, "loss": 2.096, "step": 31080 }, { "epoch": 0.51, "learning_rate": 3.453006012024048e-05, "loss": 2.142, "step": 31090 }, { "epoch": 0.51, "learning_rate": 3.45250501002004e-05, "loss": 2.1354, "step": 31100 }, { "epoch": 0.51, "learning_rate": 3.452004008016032e-05, "loss": 2.1223, "step": 31110 }, { "epoch": 0.51, "learning_rate": 3.451503006012024e-05, "loss": 2.0717, "step": 31120 }, { "epoch": 0.51, "learning_rate": 3.451002004008016e-05, "loss": 2.1158, "step": 31130 }, { "epoch": 0.51, "learning_rate": 3.450501002004008e-05, "loss": 2.0841, "step": 31140 }, { "epoch": 0.51, "learning_rate": 3.45e-05, "loss": 2.1358, "step": 31150 }, { "epoch": 0.51, "learning_rate": 3.4494989979959926e-05, "loss": 2.1123, "step": 31160 }, { "epoch": 0.51, "learning_rate": 3.4489979959919846e-05, "loss": 2.1184, "step": 31170 }, { "epoch": 0.51, "learning_rate": 3.448496993987976e-05, "loss": 2.0947, "step": 31180 }, { "epoch": 0.51, "learning_rate": 3.447995991983968e-05, "loss": 2.1162, "step": 31190 }, { "epoch": 0.51, "learning_rate": 3.44749498997996e-05, "loss": 2.1004, "step": 31200 }, { "epoch": 0.51, "learning_rate": 3.446993987975952e-05, "loss": 2.0727, "step": 31210 }, { "epoch": 0.51, "learning_rate": 3.446492985971944e-05, "loss": 2.1818, "step": 31220 }, { "epoch": 0.51, "learning_rate": 3.4459919839679363e-05, "loss": 2.0918, "step": 31230 }, { "epoch": 0.51, "learning_rate": 3.445490981963928e-05, "loss": 2.135, "step": 31240 }, { "epoch": 0.51, "learning_rate": 3.44498997995992e-05, "loss": 2.1696, "step": 31250 }, { "epoch": 0.51, "learning_rate": 3.444488977955912e-05, "loss": 2.1094, "step": 31260 }, { "epoch": 0.51, "learning_rate": 3.443987975951904e-05, "loss": 2.1231, "step": 31270 }, { "epoch": 0.51, "learning_rate": 3.443486973947896e-05, "loss": 2.0765, "step": 31280 }, { "epoch": 0.51, "learning_rate": 3.442985971943888e-05, "loss": 2.108, "step": 31290 }, { "epoch": 0.51, "learning_rate": 3.44248496993988e-05, "loss": 2.1163, "step": 31300 }, { "epoch": 0.51, "learning_rate": 3.4419839679358715e-05, "loss": 2.1004, "step": 31310 }, { "epoch": 0.51, "learning_rate": 3.4414829659318636e-05, "loss": 2.0866, "step": 31320 }, { "epoch": 0.51, "learning_rate": 3.4409819639278556e-05, "loss": 2.1038, "step": 31330 }, { "epoch": 0.51, "learning_rate": 3.440480961923848e-05, "loss": 2.1855, "step": 31340 }, { "epoch": 0.51, "learning_rate": 3.43997995991984e-05, "loss": 2.1105, "step": 31350 }, { "epoch": 0.51, "learning_rate": 3.439478957915832e-05, "loss": 2.1325, "step": 31360 }, { "epoch": 0.51, "learning_rate": 3.438977955911824e-05, "loss": 2.1189, "step": 31370 }, { "epoch": 0.51, "learning_rate": 3.438476953907816e-05, "loss": 2.1389, "step": 31380 }, { "epoch": 0.51, "learning_rate": 3.437975951903808e-05, "loss": 2.1753, "step": 31390 }, { "epoch": 0.51, "learning_rate": 3.4374749498998e-05, "loss": 2.1239, "step": 31400 }, { "epoch": 0.51, "learning_rate": 3.436973947895792e-05, "loss": 2.0802, "step": 31410 }, { "epoch": 0.51, "learning_rate": 3.4364729458917835e-05, "loss": 2.1257, "step": 31420 }, { "epoch": 0.51, "learning_rate": 3.4359719438877756e-05, "loss": 2.0422, "step": 31430 }, { "epoch": 0.51, "learning_rate": 3.4354709418837677e-05, "loss": 2.1179, "step": 31440 }, { "epoch": 0.51, "learning_rate": 3.43496993987976e-05, "loss": 2.106, "step": 31450 }, { "epoch": 0.51, "learning_rate": 3.434468937875752e-05, "loss": 2.152, "step": 31460 }, { "epoch": 0.51, "learning_rate": 3.433967935871744e-05, "loss": 2.0964, "step": 31470 }, { "epoch": 0.51, "learning_rate": 3.433466933867735e-05, "loss": 2.1029, "step": 31480 }, { "epoch": 0.51, "learning_rate": 3.432965931863727e-05, "loss": 2.0825, "step": 31490 }, { "epoch": 0.51, "learning_rate": 3.4324649298597194e-05, "loss": 2.0731, "step": 31500 }, { "epoch": 0.51, "learning_rate": 3.4319639278557114e-05, "loss": 2.1011, "step": 31510 }, { "epoch": 0.52, "learning_rate": 3.4314629258517035e-05, "loss": 2.0701, "step": 31520 }, { "epoch": 0.52, "learning_rate": 3.4309619238476956e-05, "loss": 2.1187, "step": 31530 }, { "epoch": 0.52, "learning_rate": 3.430460921843687e-05, "loss": 2.0798, "step": 31540 }, { "epoch": 0.52, "learning_rate": 3.42995991983968e-05, "loss": 2.0832, "step": 31550 }, { "epoch": 0.52, "learning_rate": 3.429458917835672e-05, "loss": 2.1127, "step": 31560 }, { "epoch": 0.52, "learning_rate": 3.428957915831664e-05, "loss": 2.0988, "step": 31570 }, { "epoch": 0.52, "learning_rate": 3.428456913827656e-05, "loss": 2.0822, "step": 31580 }, { "epoch": 0.52, "learning_rate": 3.427955911823648e-05, "loss": 2.0949, "step": 31590 }, { "epoch": 0.52, "learning_rate": 3.427454909819639e-05, "loss": 2.1019, "step": 31600 }, { "epoch": 0.52, "learning_rate": 3.4269539078156314e-05, "loss": 2.1339, "step": 31610 }, { "epoch": 0.52, "learning_rate": 3.4264529058116235e-05, "loss": 2.0939, "step": 31620 }, { "epoch": 0.52, "learning_rate": 3.4259519038076155e-05, "loss": 2.1601, "step": 31630 }, { "epoch": 0.52, "learning_rate": 3.4254509018036076e-05, "loss": 2.1188, "step": 31640 }, { "epoch": 0.52, "learning_rate": 3.4249498997995997e-05, "loss": 2.0898, "step": 31650 }, { "epoch": 0.52, "learning_rate": 3.424448897795591e-05, "loss": 2.0892, "step": 31660 }, { "epoch": 0.52, "learning_rate": 3.423947895791583e-05, "loss": 2.0714, "step": 31670 }, { "epoch": 0.52, "learning_rate": 3.423446893787575e-05, "loss": 2.0612, "step": 31680 }, { "epoch": 0.52, "learning_rate": 3.422945891783567e-05, "loss": 2.1237, "step": 31690 }, { "epoch": 0.52, "learning_rate": 3.422444889779559e-05, "loss": 2.1572, "step": 31700 }, { "epoch": 0.52, "learning_rate": 3.4219438877755514e-05, "loss": 2.1047, "step": 31710 }, { "epoch": 0.52, "learning_rate": 3.421442885771543e-05, "loss": 2.1223, "step": 31720 }, { "epoch": 0.52, "learning_rate": 3.420941883767535e-05, "loss": 2.0718, "step": 31730 }, { "epoch": 0.52, "learning_rate": 3.420440881763527e-05, "loss": 2.0997, "step": 31740 }, { "epoch": 0.52, "learning_rate": 3.4199398797595196e-05, "loss": 2.0966, "step": 31750 }, { "epoch": 0.52, "learning_rate": 3.419438877755512e-05, "loss": 2.1565, "step": 31760 }, { "epoch": 0.52, "learning_rate": 3.418937875751503e-05, "loss": 2.1104, "step": 31770 }, { "epoch": 0.52, "learning_rate": 3.418436873747495e-05, "loss": 2.0852, "step": 31780 }, { "epoch": 0.52, "learning_rate": 3.417935871743487e-05, "loss": 2.0655, "step": 31790 }, { "epoch": 0.52, "learning_rate": 3.417434869739479e-05, "loss": 2.1315, "step": 31800 }, { "epoch": 0.52, "learning_rate": 3.416933867735471e-05, "loss": 2.1215, "step": 31810 }, { "epoch": 0.52, "learning_rate": 3.4164328657314634e-05, "loss": 2.0879, "step": 31820 }, { "epoch": 0.52, "learning_rate": 3.415931863727455e-05, "loss": 2.1348, "step": 31830 }, { "epoch": 0.52, "learning_rate": 3.415430861723447e-05, "loss": 2.0809, "step": 31840 }, { "epoch": 0.52, "learning_rate": 3.414929859719439e-05, "loss": 2.0894, "step": 31850 }, { "epoch": 0.52, "learning_rate": 3.414428857715431e-05, "loss": 2.0993, "step": 31860 }, { "epoch": 0.52, "learning_rate": 3.413927855711423e-05, "loss": 2.1335, "step": 31870 }, { "epoch": 0.52, "learning_rate": 3.413426853707415e-05, "loss": 2.1047, "step": 31880 }, { "epoch": 0.52, "learning_rate": 3.412925851703407e-05, "loss": 2.0869, "step": 31890 }, { "epoch": 0.52, "learning_rate": 3.4124248496993985e-05, "loss": 2.1026, "step": 31900 }, { "epoch": 0.52, "learning_rate": 3.4119238476953906e-05, "loss": 2.1239, "step": 31910 }, { "epoch": 0.52, "learning_rate": 3.411422845691383e-05, "loss": 2.1618, "step": 31920 }, { "epoch": 0.52, "learning_rate": 3.410921843687375e-05, "loss": 2.0726, "step": 31930 }, { "epoch": 0.52, "learning_rate": 3.4104208416833675e-05, "loss": 2.1035, "step": 31940 }, { "epoch": 0.52, "learning_rate": 3.409919839679359e-05, "loss": 2.1473, "step": 31950 }, { "epoch": 0.52, "learning_rate": 3.409418837675351e-05, "loss": 2.0708, "step": 31960 }, { "epoch": 0.52, "learning_rate": 3.408917835671343e-05, "loss": 2.086, "step": 31970 }, { "epoch": 0.52, "learning_rate": 3.408416833667335e-05, "loss": 2.1214, "step": 31980 }, { "epoch": 0.52, "learning_rate": 3.407915831663327e-05, "loss": 2.1341, "step": 31990 }, { "epoch": 0.52, "learning_rate": 3.4074649298597194e-05, "loss": 2.0955, "step": 32000 }, { "epoch": 0.52, "eval_loss": 2.08701491355896, "eval_mean_f1": 0.6453411662148736, "eval_rouge1_f1": 0.704706741436578, "eval_rouge1_precision": 0.8157287810866629, "eval_rouge1_recall": 0.6533032978157087, "eval_rouge2_f1": 0.5576969588423255, "eval_rouge2_precision": 0.6495481399839311, "eval_rouge2_recall": 0.5169959133387316, "eval_rougeL_f1": 0.6736197983657173, "eval_rougeL_precision": 0.7771570689733318, "eval_rougeL_recall": 0.6252353718023722, "eval_runtime": 64.6591, "eval_samples_per_second": 15.837, "eval_steps_per_second": 1.98, "step": 32000 }, { "epoch": 0.52, "learning_rate": 3.4069639278557115e-05, "loss": 2.0868, "step": 32010 }, { "epoch": 0.52, "learning_rate": 3.4064629258517036e-05, "loss": 2.1474, "step": 32020 }, { "epoch": 0.52, "learning_rate": 3.4059619238476956e-05, "loss": 2.1444, "step": 32030 }, { "epoch": 0.52, "learning_rate": 3.405460921843688e-05, "loss": 2.1345, "step": 32040 }, { "epoch": 0.52, "learning_rate": 3.40495991983968e-05, "loss": 2.1466, "step": 32050 }, { "epoch": 0.52, "learning_rate": 3.404458917835672e-05, "loss": 2.1275, "step": 32060 }, { "epoch": 0.52, "learning_rate": 3.403957915831664e-05, "loss": 2.1084, "step": 32070 }, { "epoch": 0.52, "learning_rate": 3.403456913827656e-05, "loss": 2.1108, "step": 32080 }, { "epoch": 0.52, "learning_rate": 3.402955911823647e-05, "loss": 2.117, "step": 32090 }, { "epoch": 0.52, "learning_rate": 3.4024549098196394e-05, "loss": 2.0702, "step": 32100 }, { "epoch": 0.52, "learning_rate": 3.4019539078156315e-05, "loss": 2.1338, "step": 32110 }, { "epoch": 0.52, "learning_rate": 3.4014529058116235e-05, "loss": 2.0615, "step": 32120 }, { "epoch": 0.53, "learning_rate": 3.4009519038076156e-05, "loss": 2.1413, "step": 32130 }, { "epoch": 0.53, "learning_rate": 3.4004509018036077e-05, "loss": 2.1321, "step": 32140 }, { "epoch": 0.53, "learning_rate": 3.399949899799599e-05, "loss": 2.0721, "step": 32150 }, { "epoch": 0.53, "learning_rate": 3.399448897795591e-05, "loss": 2.136, "step": 32160 }, { "epoch": 0.53, "learning_rate": 3.398947895791583e-05, "loss": 2.0591, "step": 32170 }, { "epoch": 0.53, "learning_rate": 3.398446893787575e-05, "loss": 2.0701, "step": 32180 }, { "epoch": 0.53, "learning_rate": 3.397945891783567e-05, "loss": 2.0621, "step": 32190 }, { "epoch": 0.53, "learning_rate": 3.3974448897795594e-05, "loss": 2.0671, "step": 32200 }, { "epoch": 0.53, "learning_rate": 3.396943887775551e-05, "loss": 2.0925, "step": 32210 }, { "epoch": 0.53, "learning_rate": 3.396442885771543e-05, "loss": 2.0748, "step": 32220 }, { "epoch": 0.53, "learning_rate": 3.395941883767535e-05, "loss": 2.0949, "step": 32230 }, { "epoch": 0.53, "learning_rate": 3.3954408817635276e-05, "loss": 2.108, "step": 32240 }, { "epoch": 0.53, "learning_rate": 3.39493987975952e-05, "loss": 2.103, "step": 32250 }, { "epoch": 0.53, "learning_rate": 3.394438877755511e-05, "loss": 2.0942, "step": 32260 }, { "epoch": 0.53, "learning_rate": 3.393937875751503e-05, "loss": 2.1333, "step": 32270 }, { "epoch": 0.53, "learning_rate": 3.393436873747495e-05, "loss": 2.0748, "step": 32280 }, { "epoch": 0.53, "learning_rate": 3.392935871743487e-05, "loss": 2.11, "step": 32290 }, { "epoch": 0.53, "learning_rate": 3.392434869739479e-05, "loss": 2.1195, "step": 32300 }, { "epoch": 0.53, "learning_rate": 3.3919338677354714e-05, "loss": 2.0979, "step": 32310 }, { "epoch": 0.53, "learning_rate": 3.3914328657314635e-05, "loss": 2.1281, "step": 32320 }, { "epoch": 0.53, "learning_rate": 3.390931863727455e-05, "loss": 2.1252, "step": 32330 }, { "epoch": 0.53, "learning_rate": 3.390430861723447e-05, "loss": 2.132, "step": 32340 }, { "epoch": 0.53, "learning_rate": 3.389929859719439e-05, "loss": 2.0711, "step": 32350 }, { "epoch": 0.53, "learning_rate": 3.389428857715431e-05, "loss": 2.1397, "step": 32360 }, { "epoch": 0.53, "learning_rate": 3.388927855711423e-05, "loss": 2.0728, "step": 32370 }, { "epoch": 0.53, "learning_rate": 3.388426853707415e-05, "loss": 2.1192, "step": 32380 }, { "epoch": 0.53, "learning_rate": 3.3879258517034066e-05, "loss": 2.1252, "step": 32390 }, { "epoch": 0.53, "learning_rate": 3.3874248496993986e-05, "loss": 2.0896, "step": 32400 }, { "epoch": 0.53, "learning_rate": 3.386923847695391e-05, "loss": 2.1591, "step": 32410 }, { "epoch": 0.53, "learning_rate": 3.386422845691383e-05, "loss": 2.1038, "step": 32420 }, { "epoch": 0.53, "learning_rate": 3.385921843687375e-05, "loss": 2.1562, "step": 32430 }, { "epoch": 0.53, "learning_rate": 3.385420841683367e-05, "loss": 2.1808, "step": 32440 }, { "epoch": 0.53, "learning_rate": 3.384919839679359e-05, "loss": 2.0959, "step": 32450 }, { "epoch": 0.53, "learning_rate": 3.384418837675351e-05, "loss": 2.107, "step": 32460 }, { "epoch": 0.53, "learning_rate": 3.383917835671343e-05, "loss": 2.0861, "step": 32470 }, { "epoch": 0.53, "learning_rate": 3.383416833667335e-05, "loss": 2.1107, "step": 32480 }, { "epoch": 0.53, "learning_rate": 3.382915831663327e-05, "loss": 2.0897, "step": 32490 }, { "epoch": 0.53, "learning_rate": 3.3824148296593186e-05, "loss": 2.0714, "step": 32500 }, { "epoch": 0.53, "learning_rate": 3.3819138276553106e-05, "loss": 2.1533, "step": 32510 }, { "epoch": 0.53, "learning_rate": 3.381412825651303e-05, "loss": 2.0684, "step": 32520 }, { "epoch": 0.53, "learning_rate": 3.380911823647295e-05, "loss": 2.0857, "step": 32530 }, { "epoch": 0.53, "learning_rate": 3.380410821643287e-05, "loss": 2.0796, "step": 32540 }, { "epoch": 0.53, "learning_rate": 3.379909819639279e-05, "loss": 2.0972, "step": 32550 }, { "epoch": 0.53, "learning_rate": 3.37940881763527e-05, "loss": 2.1207, "step": 32560 }, { "epoch": 0.53, "learning_rate": 3.3789078156312623e-05, "loss": 2.0522, "step": 32570 }, { "epoch": 0.53, "learning_rate": 3.3784068136272544e-05, "loss": 2.1177, "step": 32580 }, { "epoch": 0.53, "learning_rate": 3.3779058116232465e-05, "loss": 2.1089, "step": 32590 }, { "epoch": 0.53, "learning_rate": 3.3774048096192385e-05, "loss": 2.0804, "step": 32600 }, { "epoch": 0.53, "learning_rate": 3.3769038076152306e-05, "loss": 2.1577, "step": 32610 }, { "epoch": 0.53, "learning_rate": 3.376402805611223e-05, "loss": 2.0921, "step": 32620 }, { "epoch": 0.53, "learning_rate": 3.375901803607215e-05, "loss": 2.1314, "step": 32630 }, { "epoch": 0.53, "learning_rate": 3.375400801603207e-05, "loss": 2.1221, "step": 32640 }, { "epoch": 0.53, "learning_rate": 3.374899799599199e-05, "loss": 2.0709, "step": 32650 }, { "epoch": 0.53, "learning_rate": 3.374398797595191e-05, "loss": 2.1308, "step": 32660 }, { "epoch": 0.53, "learning_rate": 3.373897795591183e-05, "loss": 2.142, "step": 32670 }, { "epoch": 0.53, "learning_rate": 3.3733967935871744e-05, "loss": 2.0912, "step": 32680 }, { "epoch": 0.53, "learning_rate": 3.3728957915831664e-05, "loss": 2.1199, "step": 32690 }, { "epoch": 0.53, "learning_rate": 3.3723947895791585e-05, "loss": 2.0952, "step": 32700 }, { "epoch": 0.53, "learning_rate": 3.3718937875751506e-05, "loss": 2.1062, "step": 32710 }, { "epoch": 0.53, "learning_rate": 3.3713927855711426e-05, "loss": 2.0831, "step": 32720 }, { "epoch": 0.53, "learning_rate": 3.370891783567135e-05, "loss": 2.1321, "step": 32730 }, { "epoch": 0.53, "learning_rate": 3.370390781563126e-05, "loss": 2.091, "step": 32740 }, { "epoch": 0.54, "learning_rate": 3.369889779559118e-05, "loss": 2.0341, "step": 32750 }, { "epoch": 0.54, "learning_rate": 3.36938877755511e-05, "loss": 2.1075, "step": 32760 }, { "epoch": 0.54, "learning_rate": 3.368887775551102e-05, "loss": 2.124, "step": 32770 }, { "epoch": 0.54, "learning_rate": 3.3683867735470943e-05, "loss": 2.1413, "step": 32780 }, { "epoch": 0.54, "learning_rate": 3.3678857715430864e-05, "loss": 2.1428, "step": 32790 }, { "epoch": 0.54, "learning_rate": 3.367384769539078e-05, "loss": 2.1104, "step": 32800 }, { "epoch": 0.54, "learning_rate": 3.36688376753507e-05, "loss": 2.134, "step": 32810 }, { "epoch": 0.54, "learning_rate": 3.366382765531062e-05, "loss": 2.0995, "step": 32820 }, { "epoch": 0.54, "learning_rate": 3.365881763527055e-05, "loss": 2.1535, "step": 32830 }, { "epoch": 0.54, "learning_rate": 3.365380761523047e-05, "loss": 2.0964, "step": 32840 }, { "epoch": 0.54, "learning_rate": 3.364879759519038e-05, "loss": 2.0894, "step": 32850 }, { "epoch": 0.54, "learning_rate": 3.36437875751503e-05, "loss": 2.1222, "step": 32860 }, { "epoch": 0.54, "learning_rate": 3.363877755511022e-05, "loss": 2.0657, "step": 32870 }, { "epoch": 0.54, "learning_rate": 3.363376753507014e-05, "loss": 2.1456, "step": 32880 }, { "epoch": 0.54, "learning_rate": 3.3628757515030064e-05, "loss": 2.0712, "step": 32890 }, { "epoch": 0.54, "learning_rate": 3.3623747494989984e-05, "loss": 2.1064, "step": 32900 }, { "epoch": 0.54, "learning_rate": 3.3618737474949905e-05, "loss": 2.0976, "step": 32910 }, { "epoch": 0.54, "learning_rate": 3.361372745490982e-05, "loss": 2.0936, "step": 32920 }, { "epoch": 0.54, "learning_rate": 3.360871743486974e-05, "loss": 2.0685, "step": 32930 }, { "epoch": 0.54, "learning_rate": 3.360370741482966e-05, "loss": 2.1153, "step": 32940 }, { "epoch": 0.54, "learning_rate": 3.359869739478958e-05, "loss": 2.0998, "step": 32950 }, { "epoch": 0.54, "learning_rate": 3.35936873747495e-05, "loss": 2.1042, "step": 32960 }, { "epoch": 0.54, "learning_rate": 3.358867735470942e-05, "loss": 2.1079, "step": 32970 }, { "epoch": 0.54, "learning_rate": 3.3583667334669336e-05, "loss": 2.0843, "step": 32980 }, { "epoch": 0.54, "learning_rate": 3.3578657314629257e-05, "loss": 2.0896, "step": 32990 }, { "epoch": 0.54, "learning_rate": 3.357364729458918e-05, "loss": 2.0754, "step": 33000 }, { "epoch": 0.54, "eval_loss": 2.0818724632263184, "eval_mean_f1": 0.6507317533237387, "eval_rouge1_f1": 0.7079765554320537, "eval_rouge1_precision": 0.8190865860134295, "eval_rouge1_recall": 0.6559954817454108, "eval_rouge2_f1": 0.5658156155569927, "eval_rouge2_precision": 0.6587923523958685, "eval_rouge2_recall": 0.5243908240928056, "eval_rougeL_f1": 0.6784030889821697, "eval_rougeL_precision": 0.7830469944695442, "eval_rougeL_recall": 0.6293913063034462, "eval_runtime": 65.5901, "eval_samples_per_second": 15.612, "eval_steps_per_second": 1.952, "step": 33000 }, { "epoch": 0.54, "learning_rate": 3.35686372745491e-05, "loss": 2.1028, "step": 33010 }, { "epoch": 0.54, "learning_rate": 3.356362725450902e-05, "loss": 2.1146, "step": 33020 }, { "epoch": 0.54, "learning_rate": 3.355861723446894e-05, "loss": 2.1152, "step": 33030 }, { "epoch": 0.54, "learning_rate": 3.355360721442886e-05, "loss": 2.0819, "step": 33040 }, { "epoch": 0.54, "learning_rate": 3.354859719438878e-05, "loss": 2.1205, "step": 33050 }, { "epoch": 0.54, "learning_rate": 3.35435871743487e-05, "loss": 2.1487, "step": 33060 }, { "epoch": 0.54, "learning_rate": 3.353857715430862e-05, "loss": 2.0636, "step": 33070 }, { "epoch": 0.54, "learning_rate": 3.353356713426854e-05, "loss": 2.1263, "step": 33080 }, { "epoch": 0.54, "learning_rate": 3.3528557114228456e-05, "loss": 2.0624, "step": 33090 }, { "epoch": 0.54, "learning_rate": 3.352354709418838e-05, "loss": 2.0921, "step": 33100 }, { "epoch": 0.54, "learning_rate": 3.35185370741483e-05, "loss": 2.0715, "step": 33110 }, { "epoch": 0.54, "learning_rate": 3.351352705410822e-05, "loss": 2.0791, "step": 33120 }, { "epoch": 0.54, "learning_rate": 3.350851703406814e-05, "loss": 2.1177, "step": 33130 }, { "epoch": 0.54, "learning_rate": 3.350350701402806e-05, "loss": 2.1052, "step": 33140 }, { "epoch": 0.54, "learning_rate": 3.349849699398798e-05, "loss": 2.0744, "step": 33150 }, { "epoch": 0.54, "learning_rate": 3.3493486973947894e-05, "loss": 2.1031, "step": 33160 }, { "epoch": 0.54, "learning_rate": 3.3488476953907815e-05, "loss": 2.0906, "step": 33170 }, { "epoch": 0.54, "learning_rate": 3.3483466933867735e-05, "loss": 2.0977, "step": 33180 }, { "epoch": 0.54, "learning_rate": 3.3478456913827656e-05, "loss": 2.1024, "step": 33190 }, { "epoch": 0.54, "learning_rate": 3.3473446893787576e-05, "loss": 2.1184, "step": 33200 }, { "epoch": 0.54, "learning_rate": 3.34684368737475e-05, "loss": 2.0757, "step": 33210 }, { "epoch": 0.54, "learning_rate": 3.346342685370742e-05, "loss": 2.0862, "step": 33220 }, { "epoch": 0.54, "learning_rate": 3.345841683366734e-05, "loss": 2.1178, "step": 33230 }, { "epoch": 0.54, "learning_rate": 3.345340681362726e-05, "loss": 2.0739, "step": 33240 }, { "epoch": 0.54, "learning_rate": 3.344839679358718e-05, "loss": 2.1149, "step": 33250 }, { "epoch": 0.54, "learning_rate": 3.34433867735471e-05, "loss": 2.1119, "step": 33260 }, { "epoch": 0.54, "learning_rate": 3.3438376753507014e-05, "loss": 2.0593, "step": 33270 }, { "epoch": 0.54, "learning_rate": 3.3433366733466935e-05, "loss": 2.0844, "step": 33280 }, { "epoch": 0.54, "learning_rate": 3.3428356713426855e-05, "loss": 2.069, "step": 33290 }, { "epoch": 0.54, "learning_rate": 3.3423346693386776e-05, "loss": 2.1496, "step": 33300 }, { "epoch": 0.54, "learning_rate": 3.34183366733467e-05, "loss": 2.1037, "step": 33310 }, { "epoch": 0.54, "learning_rate": 3.341332665330662e-05, "loss": 2.0921, "step": 33320 }, { "epoch": 0.54, "learning_rate": 3.340831663326653e-05, "loss": 2.0903, "step": 33330 }, { "epoch": 0.54, "learning_rate": 3.340330661322645e-05, "loss": 2.1248, "step": 33340 }, { "epoch": 0.54, "learning_rate": 3.339829659318637e-05, "loss": 2.1018, "step": 33350 }, { "epoch": 0.55, "learning_rate": 3.339328657314629e-05, "loss": 2.128, "step": 33360 }, { "epoch": 0.55, "learning_rate": 3.3388276553106214e-05, "loss": 2.0853, "step": 33370 }, { "epoch": 0.55, "learning_rate": 3.3383266533066134e-05, "loss": 2.0891, "step": 33380 }, { "epoch": 0.55, "learning_rate": 3.337825651302605e-05, "loss": 2.0995, "step": 33390 }, { "epoch": 0.55, "learning_rate": 3.337324649298597e-05, "loss": 2.0573, "step": 33400 }, { "epoch": 0.55, "learning_rate": 3.336823647294589e-05, "loss": 2.1019, "step": 33410 }, { "epoch": 0.55, "learning_rate": 3.336322645290582e-05, "loss": 2.1279, "step": 33420 }, { "epoch": 0.55, "learning_rate": 3.335821643286574e-05, "loss": 2.0865, "step": 33430 }, { "epoch": 0.55, "learning_rate": 3.335320641282566e-05, "loss": 2.1495, "step": 33440 }, { "epoch": 0.55, "learning_rate": 3.334819639278557e-05, "loss": 2.0634, "step": 33450 }, { "epoch": 0.55, "learning_rate": 3.334318637274549e-05, "loss": 2.1383, "step": 33460 }, { "epoch": 0.55, "learning_rate": 3.3338176352705413e-05, "loss": 2.1207, "step": 33470 }, { "epoch": 0.55, "learning_rate": 3.3333166332665334e-05, "loss": 2.0981, "step": 33480 }, { "epoch": 0.55, "learning_rate": 3.3328156312625255e-05, "loss": 2.1353, "step": 33490 }, { "epoch": 0.55, "learning_rate": 3.3323146292585175e-05, "loss": 2.1227, "step": 33500 }, { "epoch": 0.55, "learning_rate": 3.331813627254509e-05, "loss": 2.1016, "step": 33510 }, { "epoch": 0.55, "learning_rate": 3.331312625250501e-05, "loss": 2.0983, "step": 33520 }, { "epoch": 0.55, "learning_rate": 3.330811623246493e-05, "loss": 2.1145, "step": 33530 }, { "epoch": 0.55, "learning_rate": 3.330310621242485e-05, "loss": 2.1002, "step": 33540 }, { "epoch": 0.55, "learning_rate": 3.329809619238477e-05, "loss": 2.0716, "step": 33550 }, { "epoch": 0.55, "learning_rate": 3.329308617234469e-05, "loss": 2.1056, "step": 33560 }, { "epoch": 0.55, "learning_rate": 3.3288076152304606e-05, "loss": 2.0672, "step": 33570 }, { "epoch": 0.55, "learning_rate": 3.328306613226453e-05, "loss": 2.1325, "step": 33580 }, { "epoch": 0.55, "learning_rate": 3.327805611222445e-05, "loss": 2.0708, "step": 33590 }, { "epoch": 0.55, "learning_rate": 3.327304609218437e-05, "loss": 2.1298, "step": 33600 }, { "epoch": 0.55, "learning_rate": 3.326803607214429e-05, "loss": 2.122, "step": 33610 }, { "epoch": 0.55, "learning_rate": 3.326302605210421e-05, "loss": 2.162, "step": 33620 }, { "epoch": 0.55, "learning_rate": 3.325801603206413e-05, "loss": 2.0966, "step": 33630 }, { "epoch": 0.55, "learning_rate": 3.325300601202405e-05, "loss": 2.1215, "step": 33640 }, { "epoch": 0.55, "learning_rate": 3.324799599198397e-05, "loss": 2.1389, "step": 33650 }, { "epoch": 0.55, "learning_rate": 3.324298597194389e-05, "loss": 2.0868, "step": 33660 }, { "epoch": 0.55, "learning_rate": 3.323797595190381e-05, "loss": 2.1295, "step": 33670 }, { "epoch": 0.55, "learning_rate": 3.3232965931863727e-05, "loss": 2.1012, "step": 33680 }, { "epoch": 0.55, "learning_rate": 3.322795591182365e-05, "loss": 2.0973, "step": 33690 }, { "epoch": 0.55, "learning_rate": 3.322294589178357e-05, "loss": 2.1316, "step": 33700 }, { "epoch": 0.55, "learning_rate": 3.321793587174349e-05, "loss": 2.1208, "step": 33710 }, { "epoch": 0.55, "learning_rate": 3.321292585170341e-05, "loss": 2.097, "step": 33720 }, { "epoch": 0.55, "learning_rate": 3.320791583166333e-05, "loss": 2.0898, "step": 33730 }, { "epoch": 0.55, "learning_rate": 3.320290581162325e-05, "loss": 2.059, "step": 33740 }, { "epoch": 0.55, "learning_rate": 3.3197895791583164e-05, "loss": 2.1047, "step": 33750 }, { "epoch": 0.55, "learning_rate": 3.3192885771543085e-05, "loss": 2.1074, "step": 33760 }, { "epoch": 0.55, "learning_rate": 3.3187875751503006e-05, "loss": 2.111, "step": 33770 }, { "epoch": 0.55, "learning_rate": 3.3182865731462926e-05, "loss": 2.0889, "step": 33780 }, { "epoch": 0.55, "learning_rate": 3.317785571142285e-05, "loss": 2.0954, "step": 33790 }, { "epoch": 0.55, "learning_rate": 3.317284569138277e-05, "loss": 2.088, "step": 33800 }, { "epoch": 0.55, "learning_rate": 3.316783567134269e-05, "loss": 2.1486, "step": 33810 }, { "epoch": 0.55, "learning_rate": 3.316282565130261e-05, "loss": 2.0498, "step": 33820 }, { "epoch": 0.55, "learning_rate": 3.315781563126253e-05, "loss": 2.0885, "step": 33830 }, { "epoch": 0.55, "learning_rate": 3.315280561122245e-05, "loss": 2.1343, "step": 33840 }, { "epoch": 0.55, "learning_rate": 3.314779559118237e-05, "loss": 2.1042, "step": 33850 }, { "epoch": 0.55, "learning_rate": 3.3142785571142285e-05, "loss": 2.0982, "step": 33860 }, { "epoch": 0.55, "learning_rate": 3.3137775551102205e-05, "loss": 2.0886, "step": 33870 }, { "epoch": 0.55, "learning_rate": 3.3132765531062126e-05, "loss": 2.1072, "step": 33880 }, { "epoch": 0.55, "learning_rate": 3.3127755511022047e-05, "loss": 2.0903, "step": 33890 }, { "epoch": 0.55, "learning_rate": 3.312274549098197e-05, "loss": 2.1058, "step": 33900 }, { "epoch": 0.55, "learning_rate": 3.311773547094189e-05, "loss": 2.1209, "step": 33910 }, { "epoch": 0.55, "learning_rate": 3.31127254509018e-05, "loss": 2.1027, "step": 33920 }, { "epoch": 0.55, "learning_rate": 3.310771543086172e-05, "loss": 2.0806, "step": 33930 }, { "epoch": 0.55, "learning_rate": 3.310270541082164e-05, "loss": 2.1297, "step": 33940 }, { "epoch": 0.55, "learning_rate": 3.3097695390781564e-05, "loss": 2.0921, "step": 33950 }, { "epoch": 0.55, "learning_rate": 3.3092685370741484e-05, "loss": 2.0627, "step": 33960 }, { "epoch": 0.56, "learning_rate": 3.3087675350701405e-05, "loss": 2.1434, "step": 33970 }, { "epoch": 0.56, "learning_rate": 3.3082665330661326e-05, "loss": 2.0983, "step": 33980 }, { "epoch": 0.56, "learning_rate": 3.307765531062124e-05, "loss": 2.0846, "step": 33990 }, { "epoch": 0.56, "learning_rate": 3.307264529058116e-05, "loss": 2.1625, "step": 34000 }, { "epoch": 0.56, "eval_loss": 2.0767438411712646, "eval_mean_f1": 0.65292383423927, "eval_rouge1_f1": 0.7123634940701358, "eval_rouge1_precision": 0.8251213924629157, "eval_rouge1_recall": 0.659723901196057, "eval_rouge2_f1": 0.5663589435369628, "eval_rouge2_precision": 0.658423997199632, "eval_rouge2_recall": 0.5243410980627897, "eval_rougeL_f1": 0.6800490651107115, "eval_rougeL_precision": 0.7852720166979408, "eval_rougeL_recall": 0.6305592458847733, "eval_runtime": 65.6513, "eval_samples_per_second": 15.598, "eval_steps_per_second": 1.95, "step": 34000 }, { "epoch": 0.56, "learning_rate": 3.306763527054109e-05, "loss": 2.0936, "step": 34010 }, { "epoch": 0.56, "learning_rate": 3.306262525050101e-05, "loss": 2.0729, "step": 34020 }, { "epoch": 0.56, "learning_rate": 3.305761523046093e-05, "loss": 2.1076, "step": 34030 }, { "epoch": 0.56, "learning_rate": 3.305260521042084e-05, "loss": 2.079, "step": 34040 }, { "epoch": 0.56, "learning_rate": 3.304759519038076e-05, "loss": 2.13, "step": 34050 }, { "epoch": 0.56, "learning_rate": 3.3042585170340684e-05, "loss": 2.1439, "step": 34060 }, { "epoch": 0.56, "learning_rate": 3.3037575150300604e-05, "loss": 2.1155, "step": 34070 }, { "epoch": 0.56, "learning_rate": 3.3032565130260525e-05, "loss": 2.1243, "step": 34080 }, { "epoch": 0.56, "learning_rate": 3.3027555110220446e-05, "loss": 2.0884, "step": 34090 }, { "epoch": 0.56, "learning_rate": 3.302254509018036e-05, "loss": 2.0997, "step": 34100 }, { "epoch": 0.56, "learning_rate": 3.301753507014028e-05, "loss": 2.0669, "step": 34110 }, { "epoch": 0.56, "learning_rate": 3.30125250501002e-05, "loss": 2.1069, "step": 34120 }, { "epoch": 0.56, "learning_rate": 3.300751503006012e-05, "loss": 2.1049, "step": 34130 }, { "epoch": 0.56, "learning_rate": 3.300250501002004e-05, "loss": 2.0755, "step": 34140 }, { "epoch": 0.56, "learning_rate": 3.299749498997996e-05, "loss": 2.0733, "step": 34150 }, { "epoch": 0.56, "learning_rate": 3.299248496993988e-05, "loss": 2.0785, "step": 34160 }, { "epoch": 0.56, "learning_rate": 3.29874749498998e-05, "loss": 2.0854, "step": 34170 }, { "epoch": 0.56, "learning_rate": 3.298246492985972e-05, "loss": 2.0825, "step": 34180 }, { "epoch": 0.56, "learning_rate": 3.297745490981964e-05, "loss": 2.0848, "step": 34190 }, { "epoch": 0.56, "learning_rate": 3.297244488977956e-05, "loss": 2.1454, "step": 34200 }, { "epoch": 0.56, "learning_rate": 3.296743486973948e-05, "loss": 2.1074, "step": 34210 }, { "epoch": 0.56, "learning_rate": 3.29624248496994e-05, "loss": 2.1186, "step": 34220 }, { "epoch": 0.56, "learning_rate": 3.295741482965932e-05, "loss": 2.062, "step": 34230 }, { "epoch": 0.56, "learning_rate": 3.295240480961924e-05, "loss": 2.1382, "step": 34240 }, { "epoch": 0.56, "learning_rate": 3.294739478957916e-05, "loss": 2.1067, "step": 34250 }, { "epoch": 0.56, "learning_rate": 3.294238476953908e-05, "loss": 2.1069, "step": 34260 }, { "epoch": 0.56, "learning_rate": 3.2937374749499e-05, "loss": 2.1116, "step": 34270 }, { "epoch": 0.56, "learning_rate": 3.293236472945892e-05, "loss": 2.154, "step": 34280 }, { "epoch": 0.56, "learning_rate": 3.292735470941884e-05, "loss": 2.0873, "step": 34290 }, { "epoch": 0.56, "learning_rate": 3.292234468937876e-05, "loss": 2.1118, "step": 34300 }, { "epoch": 0.56, "learning_rate": 3.291733466933868e-05, "loss": 2.1766, "step": 34310 }, { "epoch": 0.56, "learning_rate": 3.29123246492986e-05, "loss": 2.0766, "step": 34320 }, { "epoch": 0.56, "learning_rate": 3.290731462925852e-05, "loss": 2.1266, "step": 34330 }, { "epoch": 0.56, "learning_rate": 3.2902304609218435e-05, "loss": 2.084, "step": 34340 }, { "epoch": 0.56, "learning_rate": 3.2897294589178355e-05, "loss": 2.1293, "step": 34350 }, { "epoch": 0.56, "learning_rate": 3.2892284569138276e-05, "loss": 2.0789, "step": 34360 }, { "epoch": 0.56, "learning_rate": 3.28872745490982e-05, "loss": 2.0953, "step": 34370 }, { "epoch": 0.56, "learning_rate": 3.288226452905812e-05, "loss": 2.0979, "step": 34380 }, { "epoch": 0.56, "learning_rate": 3.287725450901804e-05, "loss": 2.0979, "step": 34390 }, { "epoch": 0.56, "learning_rate": 3.287224448897796e-05, "loss": 2.133, "step": 34400 }, { "epoch": 0.56, "learning_rate": 3.286723446893788e-05, "loss": 2.1186, "step": 34410 }, { "epoch": 0.56, "learning_rate": 3.28622244488978e-05, "loss": 2.0938, "step": 34420 }, { "epoch": 0.56, "learning_rate": 3.285721442885772e-05, "loss": 2.1385, "step": 34430 }, { "epoch": 0.56, "learning_rate": 3.285220440881764e-05, "loss": 2.1173, "step": 34440 }, { "epoch": 0.56, "learning_rate": 3.2847194388777555e-05, "loss": 2.1026, "step": 34450 }, { "epoch": 0.56, "learning_rate": 3.2842184368737476e-05, "loss": 2.0766, "step": 34460 }, { "epoch": 0.56, "learning_rate": 3.2837174348697396e-05, "loss": 2.1396, "step": 34470 }, { "epoch": 0.56, "learning_rate": 3.283216432865732e-05, "loss": 2.0812, "step": 34480 }, { "epoch": 0.56, "learning_rate": 3.282715430861724e-05, "loss": 2.0947, "step": 34490 }, { "epoch": 0.56, "learning_rate": 3.282214428857716e-05, "loss": 2.0614, "step": 34500 }, { "epoch": 0.56, "learning_rate": 3.281713426853707e-05, "loss": 2.1258, "step": 34510 }, { "epoch": 0.56, "learning_rate": 3.281212424849699e-05, "loss": 2.1301, "step": 34520 }, { "epoch": 0.56, "learning_rate": 3.280711422845691e-05, "loss": 2.1084, "step": 34530 }, { "epoch": 0.56, "learning_rate": 3.2802104208416834e-05, "loss": 2.1076, "step": 34540 }, { "epoch": 0.56, "learning_rate": 3.2797094188376755e-05, "loss": 2.0826, "step": 34550 }, { "epoch": 0.56, "learning_rate": 3.2792084168336675e-05, "loss": 2.1043, "step": 34560 }, { "epoch": 0.56, "learning_rate": 3.2787074148296596e-05, "loss": 2.1056, "step": 34570 }, { "epoch": 0.57, "learning_rate": 3.278206412825651e-05, "loss": 2.1086, "step": 34580 }, { "epoch": 0.57, "learning_rate": 3.277705410821643e-05, "loss": 2.0986, "step": 34590 }, { "epoch": 0.57, "learning_rate": 3.277204408817636e-05, "loss": 2.0816, "step": 34600 }, { "epoch": 0.57, "learning_rate": 3.276703406813628e-05, "loss": 2.068, "step": 34610 }, { "epoch": 0.57, "learning_rate": 3.27620240480962e-05, "loss": 2.1151, "step": 34620 }, { "epoch": 0.57, "learning_rate": 3.275701402805611e-05, "loss": 2.1031, "step": 34630 }, { "epoch": 0.57, "learning_rate": 3.2752004008016034e-05, "loss": 2.0838, "step": 34640 }, { "epoch": 0.57, "learning_rate": 3.2746993987975954e-05, "loss": 2.1109, "step": 34650 }, { "epoch": 0.57, "learning_rate": 3.2741983967935875e-05, "loss": 2.058, "step": 34660 }, { "epoch": 0.57, "learning_rate": 3.2736973947895796e-05, "loss": 2.0676, "step": 34670 }, { "epoch": 0.57, "learning_rate": 3.2731963927855716e-05, "loss": 2.0392, "step": 34680 }, { "epoch": 0.57, "learning_rate": 3.272695390781563e-05, "loss": 2.0589, "step": 34690 }, { "epoch": 0.57, "learning_rate": 3.272194388777555e-05, "loss": 2.0946, "step": 34700 }, { "epoch": 0.57, "learning_rate": 3.271693386773547e-05, "loss": 2.0887, "step": 34710 }, { "epoch": 0.57, "learning_rate": 3.271192384769539e-05, "loss": 2.0367, "step": 34720 }, { "epoch": 0.57, "learning_rate": 3.270691382765531e-05, "loss": 2.1184, "step": 34730 }, { "epoch": 0.57, "learning_rate": 3.270190380761523e-05, "loss": 2.139, "step": 34740 }, { "epoch": 0.57, "learning_rate": 3.269689378757515e-05, "loss": 2.1069, "step": 34750 }, { "epoch": 0.57, "learning_rate": 3.269188376753507e-05, "loss": 2.1241, "step": 34760 }, { "epoch": 0.57, "learning_rate": 3.268687374749499e-05, "loss": 2.1044, "step": 34770 }, { "epoch": 0.57, "learning_rate": 3.268186372745491e-05, "loss": 2.112, "step": 34780 }, { "epoch": 0.57, "learning_rate": 3.2676853707414836e-05, "loss": 2.1094, "step": 34790 }, { "epoch": 0.57, "learning_rate": 3.267184368737475e-05, "loss": 2.0931, "step": 34800 }, { "epoch": 0.57, "learning_rate": 3.266683366733467e-05, "loss": 2.1239, "step": 34810 }, { "epoch": 0.57, "learning_rate": 3.266182364729459e-05, "loss": 2.1252, "step": 34820 }, { "epoch": 0.57, "learning_rate": 3.265681362725451e-05, "loss": 2.0937, "step": 34830 }, { "epoch": 0.57, "learning_rate": 3.265180360721443e-05, "loss": 2.1352, "step": 34840 }, { "epoch": 0.57, "learning_rate": 3.2646793587174354e-05, "loss": 2.1103, "step": 34850 }, { "epoch": 0.57, "learning_rate": 3.2641783567134274e-05, "loss": 2.1564, "step": 34860 }, { "epoch": 0.57, "learning_rate": 3.263677354709419e-05, "loss": 2.1017, "step": 34870 }, { "epoch": 0.57, "learning_rate": 3.263176352705411e-05, "loss": 2.0794, "step": 34880 }, { "epoch": 0.57, "learning_rate": 3.262675350701403e-05, "loss": 2.1077, "step": 34890 }, { "epoch": 0.57, "learning_rate": 3.262174348697395e-05, "loss": 2.067, "step": 34900 }, { "epoch": 0.57, "learning_rate": 3.261673346693387e-05, "loss": 2.0959, "step": 34910 }, { "epoch": 0.57, "learning_rate": 3.261172344689379e-05, "loss": 2.0546, "step": 34920 }, { "epoch": 0.57, "learning_rate": 3.2606713426853705e-05, "loss": 2.1071, "step": 34930 }, { "epoch": 0.57, "learning_rate": 3.2601703406813626e-05, "loss": 2.0568, "step": 34940 }, { "epoch": 0.57, "learning_rate": 3.2596693386773546e-05, "loss": 2.1209, "step": 34950 }, { "epoch": 0.57, "learning_rate": 3.259168336673347e-05, "loss": 2.0559, "step": 34960 }, { "epoch": 0.57, "learning_rate": 3.258667334669339e-05, "loss": 2.0824, "step": 34970 }, { "epoch": 0.57, "learning_rate": 3.258166332665331e-05, "loss": 2.1132, "step": 34980 }, { "epoch": 0.57, "learning_rate": 3.257665330661323e-05, "loss": 2.1412, "step": 34990 }, { "epoch": 0.57, "learning_rate": 3.257164328657315e-05, "loss": 2.1271, "step": 35000 }, { "epoch": 0.57, "eval_loss": 2.075010299682617, "eval_mean_f1": 0.6498320955344488, "eval_rouge1_f1": 0.7096708978573307, "eval_rouge1_precision": 0.8231067896261334, "eval_rouge1_recall": 0.655983499325138, "eval_rouge2_f1": 0.5632440004838919, "eval_rouge2_precision": 0.6569848310326829, "eval_rouge2_recall": 0.5210041315242915, "eval_rougeL_f1": 0.6765813882621237, "eval_rougeL_precision": 0.783253877557861, "eval_rougeL_recall": 0.6265881988123797, "eval_runtime": 66.064, "eval_samples_per_second": 15.5, "eval_steps_per_second": 1.938, "step": 35000 }, { "epoch": 0.57, "learning_rate": 3.256663326653307e-05, "loss": 2.1425, "step": 35010 }, { "epoch": 0.57, "learning_rate": 3.256162324649299e-05, "loss": 2.1618, "step": 35020 }, { "epoch": 0.57, "learning_rate": 3.255661322645291e-05, "loss": 2.106, "step": 35030 }, { "epoch": 0.57, "learning_rate": 3.2551603206412825e-05, "loss": 2.0871, "step": 35040 }, { "epoch": 0.57, "learning_rate": 3.2546593186372746e-05, "loss": 2.113, "step": 35050 }, { "epoch": 0.57, "learning_rate": 3.254158316633267e-05, "loss": 2.0963, "step": 35060 }, { "epoch": 0.57, "learning_rate": 3.253657314629259e-05, "loss": 2.1649, "step": 35070 }, { "epoch": 0.57, "learning_rate": 3.253156312625251e-05, "loss": 2.1185, "step": 35080 }, { "epoch": 0.57, "learning_rate": 3.252655310621243e-05, "loss": 2.0836, "step": 35090 }, { "epoch": 0.57, "learning_rate": 3.252154308617234e-05, "loss": 2.1017, "step": 35100 }, { "epoch": 0.57, "learning_rate": 3.251653306613226e-05, "loss": 2.112, "step": 35110 }, { "epoch": 0.57, "learning_rate": 3.2511523046092184e-05, "loss": 2.1327, "step": 35120 }, { "epoch": 0.57, "learning_rate": 3.2506513026052104e-05, "loss": 2.1175, "step": 35130 }, { "epoch": 0.57, "learning_rate": 3.2501503006012025e-05, "loss": 2.0436, "step": 35140 }, { "epoch": 0.57, "learning_rate": 3.2496492985971946e-05, "loss": 2.0822, "step": 35150 }, { "epoch": 0.57, "learning_rate": 3.2491482965931866e-05, "loss": 2.1042, "step": 35160 }, { "epoch": 0.57, "learning_rate": 3.248647294589178e-05, "loss": 2.1086, "step": 35170 }, { "epoch": 0.57, "learning_rate": 3.24814629258517e-05, "loss": 2.1305, "step": 35180 }, { "epoch": 0.57, "learning_rate": 3.247645290581163e-05, "loss": 2.1053, "step": 35190 }, { "epoch": 0.58, "learning_rate": 3.247144288577155e-05, "loss": 2.1137, "step": 35200 }, { "epoch": 0.58, "learning_rate": 3.246643286573147e-05, "loss": 2.1012, "step": 35210 }, { "epoch": 0.58, "learning_rate": 3.246142284569138e-05, "loss": 2.0894, "step": 35220 }, { "epoch": 0.58, "learning_rate": 3.2456412825651304e-05, "loss": 2.068, "step": 35230 }, { "epoch": 0.58, "learning_rate": 3.2451402805611225e-05, "loss": 2.1037, "step": 35240 }, { "epoch": 0.58, "learning_rate": 3.2446392785571145e-05, "loss": 2.0869, "step": 35250 }, { "epoch": 0.58, "learning_rate": 3.2441382765531066e-05, "loss": 2.1145, "step": 35260 }, { "epoch": 0.58, "learning_rate": 3.2436372745490987e-05, "loss": 2.1491, "step": 35270 }, { "epoch": 0.58, "learning_rate": 3.24313627254509e-05, "loss": 2.1593, "step": 35280 }, { "epoch": 0.58, "learning_rate": 3.242635270541082e-05, "loss": 2.1041, "step": 35290 }, { "epoch": 0.58, "learning_rate": 3.242134268537074e-05, "loss": 2.0896, "step": 35300 }, { "epoch": 0.58, "learning_rate": 3.241633266533066e-05, "loss": 2.0576, "step": 35310 }, { "epoch": 0.58, "learning_rate": 3.241132264529058e-05, "loss": 2.0968, "step": 35320 }, { "epoch": 0.58, "learning_rate": 3.2406312625250504e-05, "loss": 2.0829, "step": 35330 }, { "epoch": 0.58, "learning_rate": 3.240130260521042e-05, "loss": 2.1157, "step": 35340 }, { "epoch": 0.58, "learning_rate": 3.239629258517034e-05, "loss": 2.0969, "step": 35350 }, { "epoch": 0.58, "learning_rate": 3.239128256513026e-05, "loss": 2.0953, "step": 35360 }, { "epoch": 0.58, "learning_rate": 3.238627254509018e-05, "loss": 2.111, "step": 35370 }, { "epoch": 0.58, "learning_rate": 3.238126252505011e-05, "loss": 2.0932, "step": 35380 }, { "epoch": 0.58, "learning_rate": 3.237625250501002e-05, "loss": 2.1021, "step": 35390 }, { "epoch": 0.58, "learning_rate": 3.237124248496994e-05, "loss": 2.0539, "step": 35400 }, { "epoch": 0.58, "learning_rate": 3.236623246492986e-05, "loss": 2.0939, "step": 35410 }, { "epoch": 0.58, "learning_rate": 3.236122244488978e-05, "loss": 2.1428, "step": 35420 }, { "epoch": 0.58, "learning_rate": 3.23562124248497e-05, "loss": 2.1147, "step": 35430 }, { "epoch": 0.58, "learning_rate": 3.2351202404809624e-05, "loss": 2.1267, "step": 35440 }, { "epoch": 0.58, "learning_rate": 3.2346192384769545e-05, "loss": 2.0919, "step": 35450 }, { "epoch": 0.58, "learning_rate": 3.234118236472946e-05, "loss": 2.1231, "step": 35460 }, { "epoch": 0.58, "learning_rate": 3.233617234468938e-05, "loss": 2.1083, "step": 35470 }, { "epoch": 0.58, "learning_rate": 3.23311623246493e-05, "loss": 2.0553, "step": 35480 }, { "epoch": 0.58, "learning_rate": 3.232615230460922e-05, "loss": 2.1368, "step": 35490 }, { "epoch": 0.58, "learning_rate": 3.232114228456914e-05, "loss": 2.0957, "step": 35500 }, { "epoch": 0.58, "learning_rate": 3.231613226452906e-05, "loss": 2.1164, "step": 35510 }, { "epoch": 0.58, "learning_rate": 3.2311122244488976e-05, "loss": 2.1385, "step": 35520 }, { "epoch": 0.58, "learning_rate": 3.2306112224448896e-05, "loss": 2.1047, "step": 35530 }, { "epoch": 0.58, "learning_rate": 3.230110220440882e-05, "loss": 2.1074, "step": 35540 }, { "epoch": 0.58, "learning_rate": 3.229609218436874e-05, "loss": 2.0616, "step": 35550 }, { "epoch": 0.58, "learning_rate": 3.229108216432866e-05, "loss": 2.0726, "step": 35560 }, { "epoch": 0.58, "learning_rate": 3.228607214428858e-05, "loss": 2.1321, "step": 35570 }, { "epoch": 0.58, "learning_rate": 3.22810621242485e-05, "loss": 2.097, "step": 35580 }, { "epoch": 0.58, "learning_rate": 3.227605210420842e-05, "loss": 2.1164, "step": 35590 }, { "epoch": 0.58, "learning_rate": 3.227104208416834e-05, "loss": 2.1058, "step": 35600 }, { "epoch": 0.58, "learning_rate": 3.226603206412826e-05, "loss": 2.1332, "step": 35610 }, { "epoch": 0.58, "learning_rate": 3.226102204408818e-05, "loss": 2.1143, "step": 35620 }, { "epoch": 0.58, "learning_rate": 3.2256012024048096e-05, "loss": 2.1295, "step": 35630 }, { "epoch": 0.58, "learning_rate": 3.2251002004008016e-05, "loss": 2.0989, "step": 35640 }, { "epoch": 0.58, "learning_rate": 3.224599198396794e-05, "loss": 2.1408, "step": 35650 }, { "epoch": 0.58, "learning_rate": 3.224098196392786e-05, "loss": 2.0825, "step": 35660 }, { "epoch": 0.58, "learning_rate": 3.223597194388778e-05, "loss": 2.0698, "step": 35670 }, { "epoch": 0.58, "learning_rate": 3.22309619238477e-05, "loss": 2.1139, "step": 35680 }, { "epoch": 0.58, "learning_rate": 3.222595190380762e-05, "loss": 2.0991, "step": 35690 }, { "epoch": 0.58, "learning_rate": 3.2220941883767534e-05, "loss": 2.1317, "step": 35700 }, { "epoch": 0.58, "learning_rate": 3.2215931863727454e-05, "loss": 2.1155, "step": 35710 }, { "epoch": 0.58, "learning_rate": 3.2210921843687375e-05, "loss": 2.0852, "step": 35720 }, { "epoch": 0.58, "learning_rate": 3.2205911823647295e-05, "loss": 2.0745, "step": 35730 }, { "epoch": 0.58, "learning_rate": 3.2200901803607216e-05, "loss": 2.1595, "step": 35740 }, { "epoch": 0.58, "learning_rate": 3.219589178356714e-05, "loss": 2.0927, "step": 35750 }, { "epoch": 0.58, "learning_rate": 3.219088176352705e-05, "loss": 2.0984, "step": 35760 }, { "epoch": 0.58, "learning_rate": 3.218587174348697e-05, "loss": 2.1338, "step": 35770 }, { "epoch": 0.58, "learning_rate": 3.21808617234469e-05, "loss": 2.06, "step": 35780 }, { "epoch": 0.58, "learning_rate": 3.217585170340682e-05, "loss": 2.0988, "step": 35790 }, { "epoch": 0.58, "learning_rate": 3.217084168336674e-05, "loss": 2.0788, "step": 35800 }, { "epoch": 0.59, "learning_rate": 3.2165831663326654e-05, "loss": 2.0986, "step": 35810 }, { "epoch": 0.59, "learning_rate": 3.2160821643286574e-05, "loss": 2.0893, "step": 35820 }, { "epoch": 0.59, "learning_rate": 3.2155811623246495e-05, "loss": 2.0916, "step": 35830 }, { "epoch": 0.59, "learning_rate": 3.2150801603206416e-05, "loss": 2.0959, "step": 35840 }, { "epoch": 0.59, "learning_rate": 3.2145791583166336e-05, "loss": 2.106, "step": 35850 }, { "epoch": 0.59, "learning_rate": 3.214078156312626e-05, "loss": 2.0553, "step": 35860 }, { "epoch": 0.59, "learning_rate": 3.213577154308617e-05, "loss": 2.0767, "step": 35870 }, { "epoch": 0.59, "learning_rate": 3.213076152304609e-05, "loss": 2.1105, "step": 35880 }, { "epoch": 0.59, "learning_rate": 3.212575150300601e-05, "loss": 2.1156, "step": 35890 }, { "epoch": 0.59, "learning_rate": 3.212074148296593e-05, "loss": 2.0847, "step": 35900 }, { "epoch": 0.59, "learning_rate": 3.2115731462925853e-05, "loss": 2.0985, "step": 35910 }, { "epoch": 0.59, "learning_rate": 3.2110721442885774e-05, "loss": 2.0787, "step": 35920 }, { "epoch": 0.59, "learning_rate": 3.210571142284569e-05, "loss": 2.128, "step": 35930 }, { "epoch": 0.59, "learning_rate": 3.210070140280561e-05, "loss": 2.1083, "step": 35940 }, { "epoch": 0.59, "learning_rate": 3.209569138276553e-05, "loss": 2.0933, "step": 35950 }, { "epoch": 0.59, "learning_rate": 3.209068136272545e-05, "loss": 2.0684, "step": 35960 }, { "epoch": 0.59, "learning_rate": 3.208567134268538e-05, "loss": 2.0764, "step": 35970 }, { "epoch": 0.59, "learning_rate": 3.20806613226453e-05, "loss": 2.112, "step": 35980 }, { "epoch": 0.59, "learning_rate": 3.207615230460922e-05, "loss": 2.1404, "step": 35990 }, { "epoch": 0.59, "learning_rate": 3.207114228456914e-05, "loss": 2.0977, "step": 36000 }, { "epoch": 0.59, "eval_loss": 2.0731308460235596, "eval_mean_f1": 0.6499156774549094, "eval_rouge1_f1": 0.7082446245091145, "eval_rouge1_precision": 0.8176469841799716, "eval_rouge1_recall": 0.6574695550187739, "eval_rouge2_f1": 0.56376005966599, "eval_rouge2_precision": 0.6552943435145586, "eval_rouge2_recall": 0.5234617940159628, "eval_rougeL_f1": 0.6777423481896239, "eval_rougeL_precision": 0.7809416573472605, "eval_rougeL_recall": 0.6300018374053027, "eval_runtime": 64.5807, "eval_samples_per_second": 15.856, "eval_steps_per_second": 1.982, "step": 36000 }, { "epoch": 0.59, "learning_rate": 3.2066132264529056e-05, "loss": 2.1333, "step": 36010 }, { "epoch": 0.59, "learning_rate": 3.2061122244488976e-05, "loss": 2.1214, "step": 36020 }, { "epoch": 0.59, "learning_rate": 3.20561122244489e-05, "loss": 2.1389, "step": 36030 }, { "epoch": 0.59, "learning_rate": 3.205110220440882e-05, "loss": 2.1309, "step": 36040 }, { "epoch": 0.59, "learning_rate": 3.204609218436874e-05, "loss": 2.0747, "step": 36050 }, { "epoch": 0.59, "learning_rate": 3.204108216432866e-05, "loss": 2.1317, "step": 36060 }, { "epoch": 0.59, "learning_rate": 3.203607214428858e-05, "loss": 2.0753, "step": 36070 }, { "epoch": 0.59, "learning_rate": 3.20310621242485e-05, "loss": 2.1453, "step": 36080 }, { "epoch": 0.59, "learning_rate": 3.202605210420842e-05, "loss": 2.1283, "step": 36090 }, { "epoch": 0.59, "learning_rate": 3.202104208416834e-05, "loss": 2.0745, "step": 36100 }, { "epoch": 0.59, "learning_rate": 3.201603206412826e-05, "loss": 2.0718, "step": 36110 }, { "epoch": 0.59, "learning_rate": 3.2011022044088176e-05, "loss": 2.0962, "step": 36120 }, { "epoch": 0.59, "learning_rate": 3.2006012024048096e-05, "loss": 2.0699, "step": 36130 }, { "epoch": 0.59, "learning_rate": 3.200100200400802e-05, "loss": 2.0815, "step": 36140 }, { "epoch": 0.59, "learning_rate": 3.199599198396794e-05, "loss": 2.0275, "step": 36150 }, { "epoch": 0.59, "learning_rate": 3.199098196392786e-05, "loss": 2.0797, "step": 36160 }, { "epoch": 0.59, "learning_rate": 3.198597194388778e-05, "loss": 2.0605, "step": 36170 }, { "epoch": 0.59, "learning_rate": 3.19809619238477e-05, "loss": 2.1022, "step": 36180 }, { "epoch": 0.59, "learning_rate": 3.1975951903807614e-05, "loss": 2.0808, "step": 36190 }, { "epoch": 0.59, "learning_rate": 3.1970941883767534e-05, "loss": 2.0924, "step": 36200 }, { "epoch": 0.59, "learning_rate": 3.1965931863727455e-05, "loss": 2.1186, "step": 36210 }, { "epoch": 0.59, "learning_rate": 3.1960921843687375e-05, "loss": 2.0763, "step": 36220 }, { "epoch": 0.59, "learning_rate": 3.1955911823647296e-05, "loss": 2.1191, "step": 36230 }, { "epoch": 0.59, "learning_rate": 3.195090180360722e-05, "loss": 2.1035, "step": 36240 }, { "epoch": 0.59, "learning_rate": 3.194589178356713e-05, "loss": 2.122, "step": 36250 }, { "epoch": 0.59, "learning_rate": 3.194088176352705e-05, "loss": 2.1134, "step": 36260 }, { "epoch": 0.59, "learning_rate": 3.193587174348698e-05, "loss": 2.0817, "step": 36270 }, { "epoch": 0.59, "learning_rate": 3.19308617234469e-05, "loss": 2.0474, "step": 36280 }, { "epoch": 0.59, "learning_rate": 3.192585170340682e-05, "loss": 2.0838, "step": 36290 }, { "epoch": 0.59, "learning_rate": 3.1920841683366734e-05, "loss": 2.1026, "step": 36300 }, { "epoch": 0.59, "learning_rate": 3.1915831663326654e-05, "loss": 2.0591, "step": 36310 }, { "epoch": 0.59, "learning_rate": 3.1910821643286575e-05, "loss": 2.1111, "step": 36320 }, { "epoch": 0.59, "learning_rate": 3.1905811623246496e-05, "loss": 2.0809, "step": 36330 }, { "epoch": 0.59, "learning_rate": 3.1900801603206416e-05, "loss": 2.069, "step": 36340 }, { "epoch": 0.59, "learning_rate": 3.189579158316634e-05, "loss": 2.0781, "step": 36350 }, { "epoch": 0.59, "learning_rate": 3.189078156312625e-05, "loss": 2.1211, "step": 36360 }, { "epoch": 0.59, "learning_rate": 3.188577154308617e-05, "loss": 2.115, "step": 36370 }, { "epoch": 0.59, "learning_rate": 3.188076152304609e-05, "loss": 2.0761, "step": 36380 }, { "epoch": 0.59, "learning_rate": 3.187575150300601e-05, "loss": 2.0902, "step": 36390 }, { "epoch": 0.59, "learning_rate": 3.1870741482965933e-05, "loss": 2.0904, "step": 36400 }, { "epoch": 0.59, "learning_rate": 3.1865731462925854e-05, "loss": 2.0677, "step": 36410 }, { "epoch": 0.6, "learning_rate": 3.1860721442885775e-05, "loss": 2.0464, "step": 36420 }, { "epoch": 0.6, "learning_rate": 3.185571142284569e-05, "loss": 2.1498, "step": 36430 }, { "epoch": 0.6, "learning_rate": 3.185070140280561e-05, "loss": 2.0989, "step": 36440 }, { "epoch": 0.6, "learning_rate": 3.184569138276553e-05, "loss": 2.0459, "step": 36450 }, { "epoch": 0.6, "learning_rate": 3.184068136272545e-05, "loss": 2.1199, "step": 36460 }, { "epoch": 0.6, "learning_rate": 3.183567134268538e-05, "loss": 2.1109, "step": 36470 }, { "epoch": 0.6, "learning_rate": 3.183066132264529e-05, "loss": 2.0581, "step": 36480 }, { "epoch": 0.6, "learning_rate": 3.182565130260521e-05, "loss": 2.1281, "step": 36490 }, { "epoch": 0.6, "learning_rate": 3.182064128256513e-05, "loss": 2.119, "step": 36500 }, { "epoch": 0.6, "learning_rate": 3.1815631262525054e-05, "loss": 2.1234, "step": 36510 }, { "epoch": 0.6, "learning_rate": 3.1810621242484974e-05, "loss": 2.1035, "step": 36520 }, { "epoch": 0.6, "learning_rate": 3.1805611222444895e-05, "loss": 2.1218, "step": 36530 }, { "epoch": 0.6, "learning_rate": 3.180060120240481e-05, "loss": 2.1061, "step": 36540 }, { "epoch": 0.6, "learning_rate": 3.179559118236473e-05, "loss": 2.0976, "step": 36550 }, { "epoch": 0.6, "learning_rate": 3.179058116232465e-05, "loss": 2.0885, "step": 36560 }, { "epoch": 0.6, "learning_rate": 3.178557114228457e-05, "loss": 2.1076, "step": 36570 }, { "epoch": 0.6, "learning_rate": 3.178056112224449e-05, "loss": 2.0837, "step": 36580 }, { "epoch": 0.6, "learning_rate": 3.177555110220441e-05, "loss": 2.1544, "step": 36590 }, { "epoch": 0.6, "learning_rate": 3.1770541082164326e-05, "loss": 2.0758, "step": 36600 }, { "epoch": 0.6, "learning_rate": 3.176553106212425e-05, "loss": 2.0905, "step": 36610 }, { "epoch": 0.6, "learning_rate": 3.176052104208417e-05, "loss": 2.0982, "step": 36620 }, { "epoch": 0.6, "learning_rate": 3.175551102204409e-05, "loss": 2.1555, "step": 36630 }, { "epoch": 0.6, "learning_rate": 3.175050100200401e-05, "loss": 2.106, "step": 36640 }, { "epoch": 0.6, "learning_rate": 3.174549098196393e-05, "loss": 2.1328, "step": 36650 }, { "epoch": 0.6, "learning_rate": 3.174048096192385e-05, "loss": 2.0928, "step": 36660 }, { "epoch": 0.6, "learning_rate": 3.173547094188377e-05, "loss": 2.103, "step": 36670 }, { "epoch": 0.6, "learning_rate": 3.173046092184369e-05, "loss": 2.0709, "step": 36680 }, { "epoch": 0.6, "learning_rate": 3.172545090180361e-05, "loss": 2.0896, "step": 36690 }, { "epoch": 0.6, "learning_rate": 3.172044088176353e-05, "loss": 2.1126, "step": 36700 }, { "epoch": 0.6, "learning_rate": 3.171543086172345e-05, "loss": 2.0776, "step": 36710 }, { "epoch": 0.6, "learning_rate": 3.171042084168337e-05, "loss": 2.0972, "step": 36720 }, { "epoch": 0.6, "learning_rate": 3.170541082164329e-05, "loss": 2.0655, "step": 36730 }, { "epoch": 0.6, "learning_rate": 3.170040080160321e-05, "loss": 2.0975, "step": 36740 }, { "epoch": 0.6, "learning_rate": 3.169539078156313e-05, "loss": 2.0757, "step": 36750 }, { "epoch": 0.6, "learning_rate": 3.169038076152305e-05, "loss": 2.1097, "step": 36760 }, { "epoch": 0.6, "learning_rate": 3.168537074148297e-05, "loss": 2.0965, "step": 36770 }, { "epoch": 0.6, "learning_rate": 3.1680360721442884e-05, "loss": 2.0817, "step": 36780 }, { "epoch": 0.6, "learning_rate": 3.1675350701402805e-05, "loss": 2.1397, "step": 36790 }, { "epoch": 0.6, "learning_rate": 3.1670340681362725e-05, "loss": 2.1066, "step": 36800 }, { "epoch": 0.6, "learning_rate": 3.1665330661322646e-05, "loss": 2.0961, "step": 36810 }, { "epoch": 0.6, "learning_rate": 3.1660320641282567e-05, "loss": 2.076, "step": 36820 }, { "epoch": 0.6, "learning_rate": 3.165531062124249e-05, "loss": 2.1048, "step": 36830 }, { "epoch": 0.6, "learning_rate": 3.16503006012024e-05, "loss": 2.0658, "step": 36840 }, { "epoch": 0.6, "learning_rate": 3.164529058116232e-05, "loss": 2.0754, "step": 36850 }, { "epoch": 0.6, "learning_rate": 3.164028056112225e-05, "loss": 2.0811, "step": 36860 }, { "epoch": 0.6, "learning_rate": 3.163527054108217e-05, "loss": 2.0555, "step": 36870 }, { "epoch": 0.6, "learning_rate": 3.163026052104209e-05, "loss": 2.0529, "step": 36880 }, { "epoch": 0.6, "learning_rate": 3.1625250501002004e-05, "loss": 2.1322, "step": 36890 }, { "epoch": 0.6, "learning_rate": 3.1620240480961925e-05, "loss": 2.0332, "step": 36900 }, { "epoch": 0.6, "learning_rate": 3.1615230460921846e-05, "loss": 2.054, "step": 36910 }, { "epoch": 0.6, "learning_rate": 3.1610220440881766e-05, "loss": 2.08, "step": 36920 }, { "epoch": 0.6, "learning_rate": 3.160521042084169e-05, "loss": 2.04, "step": 36930 }, { "epoch": 0.6, "learning_rate": 3.160020040080161e-05, "loss": 2.0702, "step": 36940 }, { "epoch": 0.6, "learning_rate": 3.159519038076152e-05, "loss": 2.1215, "step": 36950 }, { "epoch": 0.6, "learning_rate": 3.159018036072144e-05, "loss": 2.0843, "step": 36960 }, { "epoch": 0.6, "learning_rate": 3.158517034068136e-05, "loss": 2.1396, "step": 36970 }, { "epoch": 0.6, "learning_rate": 3.158016032064128e-05, "loss": 2.1135, "step": 36980 }, { "epoch": 0.6, "learning_rate": 3.1575150300601204e-05, "loss": 2.0735, "step": 36990 }, { "epoch": 0.6, "learning_rate": 3.1570140280561125e-05, "loss": 2.082, "step": 37000 }, { "epoch": 0.6, "eval_loss": 2.0709290504455566, "eval_mean_f1": 0.6497338017768141, "eval_rouge1_f1": 0.7092649682145087, "eval_rouge1_precision": 0.8203657876491481, "eval_rouge1_recall": 0.6576445297727235, "eval_rouge2_f1": 0.5622993148683485, "eval_rouge2_precision": 0.6547770622660761, "eval_rouge2_recall": 0.5213872186389008, "eval_rougeL_f1": 0.6776371222475849, "eval_rougeL_precision": 0.7824073590797227, "eval_rougeL_recall": 0.6294235528111598, "eval_runtime": 66.1177, "eval_samples_per_second": 15.488, "eval_steps_per_second": 1.936, "step": 37000 }, { "epoch": 0.6, "learning_rate": 3.1565130260521045e-05, "loss": 2.1189, "step": 37010 }, { "epoch": 0.6, "learning_rate": 3.156012024048096e-05, "loss": 2.1195, "step": 37020 }, { "epoch": 0.61, "learning_rate": 3.155511022044088e-05, "loss": 2.1454, "step": 37030 }, { "epoch": 0.61, "learning_rate": 3.15501002004008e-05, "loss": 2.0883, "step": 37040 }, { "epoch": 0.61, "learning_rate": 3.154509018036073e-05, "loss": 2.0723, "step": 37050 }, { "epoch": 0.61, "learning_rate": 3.154008016032065e-05, "loss": 2.122, "step": 37060 }, { "epoch": 0.61, "learning_rate": 3.153507014028056e-05, "loss": 2.0906, "step": 37070 }, { "epoch": 0.61, "learning_rate": 3.153006012024048e-05, "loss": 2.0721, "step": 37080 }, { "epoch": 0.61, "learning_rate": 3.1525050100200404e-05, "loss": 2.0799, "step": 37090 }, { "epoch": 0.61, "learning_rate": 3.1520040080160324e-05, "loss": 2.0703, "step": 37100 }, { "epoch": 0.61, "learning_rate": 3.1515030060120245e-05, "loss": 2.1263, "step": 37110 }, { "epoch": 0.61, "learning_rate": 3.1510020040080165e-05, "loss": 2.0841, "step": 37120 }, { "epoch": 0.61, "learning_rate": 3.150501002004008e-05, "loss": 2.1519, "step": 37130 }, { "epoch": 0.61, "learning_rate": 3.15e-05, "loss": 2.057, "step": 37140 }, { "epoch": 0.61, "learning_rate": 3.149498997995992e-05, "loss": 2.0774, "step": 37150 }, { "epoch": 0.61, "learning_rate": 3.148997995991984e-05, "loss": 2.0998, "step": 37160 }, { "epoch": 0.61, "learning_rate": 3.148496993987976e-05, "loss": 2.0756, "step": 37170 }, { "epoch": 0.61, "learning_rate": 3.147995991983968e-05, "loss": 2.1143, "step": 37180 }, { "epoch": 0.61, "learning_rate": 3.1474949899799596e-05, "loss": 2.0981, "step": 37190 }, { "epoch": 0.61, "learning_rate": 3.146993987975952e-05, "loss": 2.0768, "step": 37200 }, { "epoch": 0.61, "learning_rate": 3.146492985971944e-05, "loss": 2.0951, "step": 37210 }, { "epoch": 0.61, "learning_rate": 3.145991983967936e-05, "loss": 2.0915, "step": 37220 }, { "epoch": 0.61, "learning_rate": 3.145490981963928e-05, "loss": 2.0791, "step": 37230 }, { "epoch": 0.61, "learning_rate": 3.14498997995992e-05, "loss": 2.0578, "step": 37240 }, { "epoch": 0.61, "learning_rate": 3.144488977955912e-05, "loss": 2.0803, "step": 37250 }, { "epoch": 0.61, "learning_rate": 3.143987975951904e-05, "loss": 2.084, "step": 37260 }, { "epoch": 0.61, "learning_rate": 3.143486973947896e-05, "loss": 2.0685, "step": 37270 }, { "epoch": 0.61, "learning_rate": 3.142985971943888e-05, "loss": 2.1189, "step": 37280 }, { "epoch": 0.61, "learning_rate": 3.14248496993988e-05, "loss": 2.0986, "step": 37290 }, { "epoch": 0.61, "learning_rate": 3.1419839679358723e-05, "loss": 2.1106, "step": 37300 }, { "epoch": 0.61, "learning_rate": 3.141482965931864e-05, "loss": 2.1243, "step": 37310 }, { "epoch": 0.61, "learning_rate": 3.140981963927856e-05, "loss": 2.132, "step": 37320 }, { "epoch": 0.61, "learning_rate": 3.140480961923848e-05, "loss": 2.1081, "step": 37330 }, { "epoch": 0.61, "learning_rate": 3.13997995991984e-05, "loss": 2.089, "step": 37340 }, { "epoch": 0.61, "learning_rate": 3.139478957915832e-05, "loss": 2.0783, "step": 37350 }, { "epoch": 0.61, "learning_rate": 3.138977955911824e-05, "loss": 2.0696, "step": 37360 }, { "epoch": 0.61, "learning_rate": 3.1384769539078154e-05, "loss": 2.0916, "step": 37370 }, { "epoch": 0.61, "learning_rate": 3.1379759519038075e-05, "loss": 2.0816, "step": 37380 }, { "epoch": 0.61, "learning_rate": 3.1374749498997996e-05, "loss": 2.1105, "step": 37390 }, { "epoch": 0.61, "learning_rate": 3.1369739478957916e-05, "loss": 2.1274, "step": 37400 }, { "epoch": 0.61, "learning_rate": 3.136472945891784e-05, "loss": 2.1024, "step": 37410 }, { "epoch": 0.61, "learning_rate": 3.135971943887776e-05, "loss": 2.1455, "step": 37420 }, { "epoch": 0.61, "learning_rate": 3.135470941883767e-05, "loss": 2.1322, "step": 37430 }, { "epoch": 0.61, "learning_rate": 3.134969939879759e-05, "loss": 2.0808, "step": 37440 }, { "epoch": 0.61, "learning_rate": 3.134468937875752e-05, "loss": 2.1076, "step": 37450 }, { "epoch": 0.61, "learning_rate": 3.133967935871744e-05, "loss": 2.0841, "step": 37460 }, { "epoch": 0.61, "learning_rate": 3.133466933867736e-05, "loss": 2.0833, "step": 37470 }, { "epoch": 0.61, "learning_rate": 3.1329659318637275e-05, "loss": 2.1088, "step": 37480 }, { "epoch": 0.61, "learning_rate": 3.1324649298597195e-05, "loss": 2.1094, "step": 37490 }, { "epoch": 0.61, "learning_rate": 3.1319639278557116e-05, "loss": 2.0695, "step": 37500 }, { "epoch": 0.61, "learning_rate": 3.1314629258517037e-05, "loss": 2.0529, "step": 37510 }, { "epoch": 0.61, "learning_rate": 3.130961923847696e-05, "loss": 2.082, "step": 37520 }, { "epoch": 0.61, "learning_rate": 3.130460921843688e-05, "loss": 2.0933, "step": 37530 }, { "epoch": 0.61, "learning_rate": 3.129959919839679e-05, "loss": 2.0575, "step": 37540 }, { "epoch": 0.61, "learning_rate": 3.129458917835671e-05, "loss": 2.0718, "step": 37550 }, { "epoch": 0.61, "learning_rate": 3.128957915831663e-05, "loss": 2.1133, "step": 37560 }, { "epoch": 0.61, "learning_rate": 3.1284569138276554e-05, "loss": 2.0733, "step": 37570 }, { "epoch": 0.61, "learning_rate": 3.1279559118236474e-05, "loss": 2.0779, "step": 37580 }, { "epoch": 0.61, "learning_rate": 3.1274549098196395e-05, "loss": 2.0881, "step": 37590 }, { "epoch": 0.61, "learning_rate": 3.1269539078156316e-05, "loss": 2.1139, "step": 37600 }, { "epoch": 0.61, "learning_rate": 3.126452905811623e-05, "loss": 2.0322, "step": 37610 }, { "epoch": 0.61, "learning_rate": 3.125951903807615e-05, "loss": 2.0658, "step": 37620 }, { "epoch": 0.61, "learning_rate": 3.125450901803607e-05, "loss": 1.9983, "step": 37630 }, { "epoch": 0.62, "learning_rate": 3.1249498997996e-05, "loss": 2.1082, "step": 37640 }, { "epoch": 0.62, "learning_rate": 3.124448897795592e-05, "loss": 2.1613, "step": 37650 }, { "epoch": 0.62, "learning_rate": 3.123947895791583e-05, "loss": 2.1395, "step": 37660 }, { "epoch": 0.62, "learning_rate": 3.123446893787575e-05, "loss": 2.1002, "step": 37670 }, { "epoch": 0.62, "learning_rate": 3.1229458917835674e-05, "loss": 2.1255, "step": 37680 }, { "epoch": 0.62, "learning_rate": 3.1224448897795595e-05, "loss": 2.0648, "step": 37690 }, { "epoch": 0.62, "learning_rate": 3.1219438877755515e-05, "loss": 2.0384, "step": 37700 }, { "epoch": 0.62, "learning_rate": 3.1214428857715436e-05, "loss": 2.075, "step": 37710 }, { "epoch": 0.62, "learning_rate": 3.120941883767535e-05, "loss": 2.0554, "step": 37720 }, { "epoch": 0.62, "learning_rate": 3.120440881763527e-05, "loss": 2.0612, "step": 37730 }, { "epoch": 0.62, "learning_rate": 3.119939879759519e-05, "loss": 2.1163, "step": 37740 }, { "epoch": 0.62, "learning_rate": 3.119438877755511e-05, "loss": 2.1173, "step": 37750 }, { "epoch": 0.62, "learning_rate": 3.118937875751503e-05, "loss": 2.0385, "step": 37760 }, { "epoch": 0.62, "learning_rate": 3.118436873747495e-05, "loss": 2.0967, "step": 37770 }, { "epoch": 0.62, "learning_rate": 3.117935871743487e-05, "loss": 2.1034, "step": 37780 }, { "epoch": 0.62, "learning_rate": 3.117434869739479e-05, "loss": 2.0989, "step": 37790 }, { "epoch": 0.62, "learning_rate": 3.116933867735471e-05, "loss": 2.1184, "step": 37800 }, { "epoch": 0.62, "learning_rate": 3.116432865731463e-05, "loss": 2.0592, "step": 37810 }, { "epoch": 0.62, "learning_rate": 3.115931863727455e-05, "loss": 2.1017, "step": 37820 }, { "epoch": 0.62, "learning_rate": 3.115430861723447e-05, "loss": 2.074, "step": 37830 }, { "epoch": 0.62, "learning_rate": 3.114929859719439e-05, "loss": 2.128, "step": 37840 }, { "epoch": 0.62, "learning_rate": 3.114428857715431e-05, "loss": 2.1009, "step": 37850 }, { "epoch": 0.62, "learning_rate": 3.113927855711423e-05, "loss": 2.0793, "step": 37860 }, { "epoch": 0.62, "learning_rate": 3.113426853707415e-05, "loss": 2.0785, "step": 37870 }, { "epoch": 0.62, "learning_rate": 3.112925851703407e-05, "loss": 2.1067, "step": 37880 }, { "epoch": 0.62, "learning_rate": 3.1124248496993994e-05, "loss": 2.0961, "step": 37890 }, { "epoch": 0.62, "learning_rate": 3.111923847695391e-05, "loss": 2.0896, "step": 37900 }, { "epoch": 0.62, "learning_rate": 3.111422845691383e-05, "loss": 2.1016, "step": 37910 }, { "epoch": 0.62, "learning_rate": 3.110921843687375e-05, "loss": 2.0555, "step": 37920 }, { "epoch": 0.62, "learning_rate": 3.110420841683367e-05, "loss": 2.0785, "step": 37930 }, { "epoch": 0.62, "learning_rate": 3.109919839679359e-05, "loss": 2.065, "step": 37940 }, { "epoch": 0.62, "learning_rate": 3.109418837675351e-05, "loss": 2.1177, "step": 37950 }, { "epoch": 0.62, "learning_rate": 3.1089178356713425e-05, "loss": 2.0932, "step": 37960 }, { "epoch": 0.62, "learning_rate": 3.1084168336673345e-05, "loss": 2.1047, "step": 37970 }, { "epoch": 0.62, "learning_rate": 3.1079158316633266e-05, "loss": 2.0748, "step": 37980 }, { "epoch": 0.62, "learning_rate": 3.107414829659319e-05, "loss": 2.0591, "step": 37990 }, { "epoch": 0.62, "learning_rate": 3.106913827655311e-05, "loss": 2.0599, "step": 38000 }, { "epoch": 0.62, "eval_loss": 2.0692901611328125, "eval_mean_f1": 0.6493804471285449, "eval_rouge1_f1": 0.7084959136535618, "eval_rouge1_precision": 0.8180512420107711, "eval_rouge1_recall": 0.6574651885122352, "eval_rouge2_f1": 0.56199201884594, "eval_rouge2_precision": 0.6511388872900098, "eval_rouge2_recall": 0.5220030032620451, "eval_rougeL_f1": 0.677653408886133, "eval_rougeL_precision": 0.7800716076968375, "eval_rougeL_recall": 0.6302574681447781, "eval_runtime": 66.3464, "eval_samples_per_second": 15.434, "eval_steps_per_second": 1.929, "step": 38000 }, { "epoch": 0.62, "learning_rate": 3.106412825651303e-05, "loss": 2.0884, "step": 38010 }, { "epoch": 0.62, "learning_rate": 3.105911823647294e-05, "loss": 2.0978, "step": 38020 }, { "epoch": 0.62, "learning_rate": 3.105410821643286e-05, "loss": 2.0726, "step": 38030 }, { "epoch": 0.62, "learning_rate": 3.104909819639279e-05, "loss": 2.0998, "step": 38040 }, { "epoch": 0.62, "learning_rate": 3.104408817635271e-05, "loss": 2.061, "step": 38050 }, { "epoch": 0.62, "learning_rate": 3.103907815631263e-05, "loss": 2.0934, "step": 38060 }, { "epoch": 0.62, "learning_rate": 3.1034068136272545e-05, "loss": 2.0789, "step": 38070 }, { "epoch": 0.62, "learning_rate": 3.1029058116232466e-05, "loss": 2.0913, "step": 38080 }, { "epoch": 0.62, "learning_rate": 3.1024048096192386e-05, "loss": 2.0941, "step": 38090 }, { "epoch": 0.62, "learning_rate": 3.101903807615231e-05, "loss": 2.0679, "step": 38100 }, { "epoch": 0.62, "learning_rate": 3.101402805611223e-05, "loss": 2.1538, "step": 38110 }, { "epoch": 0.62, "learning_rate": 3.100901803607215e-05, "loss": 2.062, "step": 38120 }, { "epoch": 0.62, "learning_rate": 3.100400801603207e-05, "loss": 2.0925, "step": 38130 }, { "epoch": 0.62, "learning_rate": 3.099899799599198e-05, "loss": 2.1304, "step": 38140 }, { "epoch": 0.62, "learning_rate": 3.0993987975951903e-05, "loss": 2.089, "step": 38150 }, { "epoch": 0.62, "learning_rate": 3.0988977955911824e-05, "loss": 2.0452, "step": 38160 }, { "epoch": 0.62, "learning_rate": 3.0983967935871745e-05, "loss": 2.0643, "step": 38170 }, { "epoch": 0.62, "learning_rate": 3.0978957915831665e-05, "loss": 2.0987, "step": 38180 }, { "epoch": 0.62, "learning_rate": 3.0973947895791586e-05, "loss": 2.1119, "step": 38190 }, { "epoch": 0.62, "learning_rate": 3.09689378757515e-05, "loss": 2.0743, "step": 38200 }, { "epoch": 0.62, "learning_rate": 3.096392785571142e-05, "loss": 2.0932, "step": 38210 }, { "epoch": 0.62, "learning_rate": 3.095891783567134e-05, "loss": 2.081, "step": 38220 }, { "epoch": 0.62, "learning_rate": 3.095390781563127e-05, "loss": 2.0414, "step": 38230 }, { "epoch": 0.62, "learning_rate": 3.094889779559119e-05, "loss": 2.1446, "step": 38240 }, { "epoch": 0.62, "learning_rate": 3.09438877755511e-05, "loss": 2.118, "step": 38250 }, { "epoch": 0.63, "learning_rate": 3.0938877755511024e-05, "loss": 2.0922, "step": 38260 }, { "epoch": 0.63, "learning_rate": 3.0933867735470944e-05, "loss": 2.0539, "step": 38270 }, { "epoch": 0.63, "learning_rate": 3.0928857715430865e-05, "loss": 2.1099, "step": 38280 }, { "epoch": 0.63, "learning_rate": 3.0923847695390786e-05, "loss": 2.1233, "step": 38290 }, { "epoch": 0.63, "learning_rate": 3.0918837675350706e-05, "loss": 2.1291, "step": 38300 }, { "epoch": 0.63, "learning_rate": 3.091382765531062e-05, "loss": 2.0763, "step": 38310 }, { "epoch": 0.63, "learning_rate": 3.090881763527054e-05, "loss": 2.1326, "step": 38320 }, { "epoch": 0.63, "learning_rate": 3.090380761523046e-05, "loss": 2.0622, "step": 38330 }, { "epoch": 0.63, "learning_rate": 3.089929859719439e-05, "loss": 2.0907, "step": 38340 }, { "epoch": 0.63, "learning_rate": 3.089428857715431e-05, "loss": 2.1479, "step": 38350 }, { "epoch": 0.63, "learning_rate": 3.088927855711423e-05, "loss": 2.0824, "step": 38360 }, { "epoch": 0.63, "learning_rate": 3.088426853707415e-05, "loss": 2.1312, "step": 38370 }, { "epoch": 0.63, "learning_rate": 3.0879258517034074e-05, "loss": 2.0891, "step": 38380 }, { "epoch": 0.63, "learning_rate": 3.087424849699399e-05, "loss": 2.0631, "step": 38390 }, { "epoch": 0.63, "learning_rate": 3.086923847695391e-05, "loss": 2.0983, "step": 38400 }, { "epoch": 0.63, "learning_rate": 3.086422845691383e-05, "loss": 2.0993, "step": 38410 }, { "epoch": 0.63, "learning_rate": 3.085921843687375e-05, "loss": 2.094, "step": 38420 }, { "epoch": 0.63, "learning_rate": 3.085420841683367e-05, "loss": 2.1178, "step": 38430 }, { "epoch": 0.63, "learning_rate": 3.084919839679359e-05, "loss": 2.0899, "step": 38440 }, { "epoch": 0.63, "learning_rate": 3.0844188376753505e-05, "loss": 2.0844, "step": 38450 }, { "epoch": 0.63, "learning_rate": 3.0839178356713425e-05, "loss": 2.0592, "step": 38460 }, { "epoch": 0.63, "learning_rate": 3.0834168336673346e-05, "loss": 2.1485, "step": 38470 }, { "epoch": 0.63, "learning_rate": 3.082915831663327e-05, "loss": 2.1484, "step": 38480 }, { "epoch": 0.63, "learning_rate": 3.082414829659319e-05, "loss": 2.1018, "step": 38490 }, { "epoch": 0.63, "learning_rate": 3.081913827655311e-05, "loss": 2.0729, "step": 38500 }, { "epoch": 0.63, "learning_rate": 3.081412825651302e-05, "loss": 2.1053, "step": 38510 }, { "epoch": 0.63, "learning_rate": 3.080911823647294e-05, "loss": 2.1057, "step": 38520 }, { "epoch": 0.63, "learning_rate": 3.080410821643287e-05, "loss": 2.0741, "step": 38530 }, { "epoch": 0.63, "learning_rate": 3.079909819639279e-05, "loss": 2.1294, "step": 38540 }, { "epoch": 0.63, "learning_rate": 3.079408817635271e-05, "loss": 2.0982, "step": 38550 }, { "epoch": 0.63, "learning_rate": 3.0789078156312625e-05, "loss": 2.0813, "step": 38560 }, { "epoch": 0.63, "learning_rate": 3.0784068136272546e-05, "loss": 2.0801, "step": 38570 }, { "epoch": 0.63, "learning_rate": 3.0779058116232466e-05, "loss": 2.0929, "step": 38580 }, { "epoch": 0.63, "learning_rate": 3.077404809619239e-05, "loss": 2.1392, "step": 38590 }, { "epoch": 0.63, "learning_rate": 3.076903807615231e-05, "loss": 2.1013, "step": 38600 }, { "epoch": 0.63, "learning_rate": 3.076402805611223e-05, "loss": 2.0711, "step": 38610 }, { "epoch": 0.63, "learning_rate": 3.075901803607215e-05, "loss": 2.0627, "step": 38620 }, { "epoch": 0.63, "learning_rate": 3.075400801603206e-05, "loss": 2.1067, "step": 38630 }, { "epoch": 0.63, "learning_rate": 3.0748997995991983e-05, "loss": 2.0385, "step": 38640 }, { "epoch": 0.63, "learning_rate": 3.0743987975951904e-05, "loss": 2.0847, "step": 38650 }, { "epoch": 0.63, "learning_rate": 3.0738977955911825e-05, "loss": 2.0471, "step": 38660 }, { "epoch": 0.63, "learning_rate": 3.0733967935871745e-05, "loss": 2.0345, "step": 38670 }, { "epoch": 0.63, "learning_rate": 3.0728957915831666e-05, "loss": 2.0735, "step": 38680 }, { "epoch": 0.63, "learning_rate": 3.072394789579158e-05, "loss": 2.1001, "step": 38690 }, { "epoch": 0.63, "learning_rate": 3.07189378757515e-05, "loss": 2.127, "step": 38700 }, { "epoch": 0.63, "learning_rate": 3.071392785571142e-05, "loss": 2.122, "step": 38710 }, { "epoch": 0.63, "learning_rate": 3.070891783567134e-05, "loss": 2.0623, "step": 38720 }, { "epoch": 0.63, "learning_rate": 3.070390781563127e-05, "loss": 2.0444, "step": 38730 }, { "epoch": 0.63, "learning_rate": 3.069889779559118e-05, "loss": 2.0758, "step": 38740 }, { "epoch": 0.63, "learning_rate": 3.0693887775551104e-05, "loss": 2.0669, "step": 38750 }, { "epoch": 0.63, "learning_rate": 3.0688877755511024e-05, "loss": 2.0913, "step": 38760 }, { "epoch": 0.63, "learning_rate": 3.0683867735470945e-05, "loss": 2.1193, "step": 38770 }, { "epoch": 0.63, "learning_rate": 3.0678857715430866e-05, "loss": 2.1076, "step": 38780 }, { "epoch": 0.63, "learning_rate": 3.0673847695390786e-05, "loss": 2.0673, "step": 38790 }, { "epoch": 0.63, "learning_rate": 3.06688376753507e-05, "loss": 2.0937, "step": 38800 }, { "epoch": 0.63, "learning_rate": 3.066382765531062e-05, "loss": 2.0906, "step": 38810 }, { "epoch": 0.63, "learning_rate": 3.065881763527054e-05, "loss": 2.0686, "step": 38820 }, { "epoch": 0.63, "learning_rate": 3.065380761523046e-05, "loss": 2.0906, "step": 38830 }, { "epoch": 0.63, "learning_rate": 3.064879759519038e-05, "loss": 2.0658, "step": 38840 }, { "epoch": 0.63, "learning_rate": 3.06437875751503e-05, "loss": 2.1092, "step": 38850 }, { "epoch": 0.63, "learning_rate": 3.0638777555110224e-05, "loss": 2.1059, "step": 38860 }, { "epoch": 0.64, "learning_rate": 3.063376753507014e-05, "loss": 2.0915, "step": 38870 }, { "epoch": 0.64, "learning_rate": 3.062875751503006e-05, "loss": 2.0709, "step": 38880 }, { "epoch": 0.64, "learning_rate": 3.062374749498998e-05, "loss": 2.0403, "step": 38890 }, { "epoch": 0.64, "learning_rate": 3.06187374749499e-05, "loss": 2.1247, "step": 38900 }, { "epoch": 0.64, "learning_rate": 3.061372745490982e-05, "loss": 2.0976, "step": 38910 }, { "epoch": 0.64, "learning_rate": 3.060871743486974e-05, "loss": 2.0737, "step": 38920 }, { "epoch": 0.64, "learning_rate": 3.060370741482966e-05, "loss": 2.1193, "step": 38930 }, { "epoch": 0.64, "learning_rate": 3.059869739478958e-05, "loss": 2.0669, "step": 38940 }, { "epoch": 0.64, "learning_rate": 3.05936873747495e-05, "loss": 2.0503, "step": 38950 }, { "epoch": 0.64, "learning_rate": 3.0588677354709424e-05, "loss": 2.093, "step": 38960 }, { "epoch": 0.64, "learning_rate": 3.0583667334669344e-05, "loss": 2.0606, "step": 38970 }, { "epoch": 0.64, "learning_rate": 3.057865731462926e-05, "loss": 2.092, "step": 38980 }, { "epoch": 0.64, "learning_rate": 3.057364729458918e-05, "loss": 2.0964, "step": 38990 }, { "epoch": 0.64, "learning_rate": 3.05686372745491e-05, "loss": 2.0953, "step": 39000 }, { "epoch": 0.64, "eval_loss": 2.066128730773926, "eval_mean_f1": 0.6510847932279477, "eval_rouge1_f1": 0.7107992830221952, "eval_rouge1_precision": 0.8224146629578041, "eval_rouge1_recall": 0.6577335326277893, "eval_rouge2_f1": 0.564555565934761, "eval_rouge2_precision": 0.6572203499083382, "eval_rouge2_recall": 0.5223085592123617, "eval_rougeL_f1": 0.6778995307268869, "eval_rougeL_precision": 0.7825305686928219, "eval_rougeL_recall": 0.6283981631749551, "eval_runtime": 67.0517, "eval_samples_per_second": 15.272, "eval_steps_per_second": 1.909, "step": 39000 }, { "epoch": 0.64, "learning_rate": 3.056362725450902e-05, "loss": 2.1004, "step": 39010 }, { "epoch": 0.64, "learning_rate": 3.055861723446894e-05, "loss": 2.1379, "step": 39020 }, { "epoch": 0.64, "learning_rate": 3.055360721442886e-05, "loss": 2.0963, "step": 39030 }, { "epoch": 0.64, "learning_rate": 3.0548597194388775e-05, "loss": 2.071, "step": 39040 }, { "epoch": 0.64, "learning_rate": 3.0543587174348696e-05, "loss": 2.0939, "step": 39050 }, { "epoch": 0.64, "learning_rate": 3.0538577154308617e-05, "loss": 2.1082, "step": 39060 }, { "epoch": 0.64, "learning_rate": 3.053356713426854e-05, "loss": 2.0728, "step": 39070 }, { "epoch": 0.64, "learning_rate": 3.052855711422846e-05, "loss": 2.1064, "step": 39080 }, { "epoch": 0.64, "learning_rate": 3.052354709418838e-05, "loss": 2.093, "step": 39090 }, { "epoch": 0.64, "learning_rate": 3.051853707414829e-05, "loss": 2.0788, "step": 39100 }, { "epoch": 0.64, "learning_rate": 3.0513527054108216e-05, "loss": 2.0923, "step": 39110 }, { "epoch": 0.64, "learning_rate": 3.050851703406814e-05, "loss": 2.0744, "step": 39120 }, { "epoch": 0.64, "learning_rate": 3.050350701402806e-05, "loss": 2.1166, "step": 39130 }, { "epoch": 0.64, "learning_rate": 3.0498496993987978e-05, "loss": 2.107, "step": 39140 }, { "epoch": 0.64, "learning_rate": 3.04934869739479e-05, "loss": 2.0559, "step": 39150 }, { "epoch": 0.64, "learning_rate": 3.048847695390782e-05, "loss": 2.0587, "step": 39160 }, { "epoch": 0.64, "learning_rate": 3.0483466933867737e-05, "loss": 2.0703, "step": 39170 }, { "epoch": 0.64, "learning_rate": 3.0478456913827657e-05, "loss": 2.1257, "step": 39180 }, { "epoch": 0.64, "learning_rate": 3.0473446893787578e-05, "loss": 2.0848, "step": 39190 }, { "epoch": 0.64, "learning_rate": 3.0468436873747495e-05, "loss": 2.1463, "step": 39200 }, { "epoch": 0.64, "learning_rate": 3.0463426853707416e-05, "loss": 2.0618, "step": 39210 }, { "epoch": 0.64, "learning_rate": 3.0458416833667337e-05, "loss": 2.1196, "step": 39220 }, { "epoch": 0.64, "learning_rate": 3.0453406813627254e-05, "loss": 2.1082, "step": 39230 }, { "epoch": 0.64, "learning_rate": 3.0448396793587175e-05, "loss": 2.0805, "step": 39240 }, { "epoch": 0.64, "learning_rate": 3.0443386773547095e-05, "loss": 2.0894, "step": 39250 }, { "epoch": 0.64, "learning_rate": 3.0438376753507016e-05, "loss": 2.1244, "step": 39260 }, { "epoch": 0.64, "learning_rate": 3.0433366733466933e-05, "loss": 2.0892, "step": 39270 }, { "epoch": 0.64, "learning_rate": 3.0428356713426854e-05, "loss": 2.0656, "step": 39280 }, { "epoch": 0.64, "learning_rate": 3.0423346693386774e-05, "loss": 2.0426, "step": 39290 }, { "epoch": 0.64, "learning_rate": 3.041833667334669e-05, "loss": 2.0824, "step": 39300 }, { "epoch": 0.64, "learning_rate": 3.041332665330662e-05, "loss": 2.0715, "step": 39310 }, { "epoch": 0.64, "learning_rate": 3.0408316633266536e-05, "loss": 2.1272, "step": 39320 }, { "epoch": 0.64, "learning_rate": 3.0403306613226457e-05, "loss": 2.1011, "step": 39330 }, { "epoch": 0.64, "learning_rate": 3.0398296593186378e-05, "loss": 2.1127, "step": 39340 }, { "epoch": 0.64, "learning_rate": 3.0393286573146295e-05, "loss": 2.0673, "step": 39350 }, { "epoch": 0.64, "learning_rate": 3.0388276553106215e-05, "loss": 2.1007, "step": 39360 }, { "epoch": 0.64, "learning_rate": 3.0383266533066136e-05, "loss": 2.0623, "step": 39370 }, { "epoch": 0.64, "learning_rate": 3.0378256513026053e-05, "loss": 2.0701, "step": 39380 }, { "epoch": 0.64, "learning_rate": 3.0373246492985974e-05, "loss": 2.0476, "step": 39390 }, { "epoch": 0.64, "learning_rate": 3.0368236472945895e-05, "loss": 2.1393, "step": 39400 }, { "epoch": 0.64, "learning_rate": 3.0363226452905812e-05, "loss": 2.0685, "step": 39410 }, { "epoch": 0.64, "learning_rate": 3.0358216432865733e-05, "loss": 2.1173, "step": 39420 }, { "epoch": 0.64, "learning_rate": 3.0353206412825653e-05, "loss": 2.0631, "step": 39430 }, { "epoch": 0.64, "learning_rate": 3.034819639278557e-05, "loss": 2.1172, "step": 39440 }, { "epoch": 0.64, "learning_rate": 3.034318637274549e-05, "loss": 2.116, "step": 39450 }, { "epoch": 0.64, "learning_rate": 3.033817635270541e-05, "loss": 2.1039, "step": 39460 }, { "epoch": 0.64, "learning_rate": 3.033316633266533e-05, "loss": 2.058, "step": 39470 }, { "epoch": 0.65, "learning_rate": 3.032815631262525e-05, "loss": 2.1008, "step": 39480 }, { "epoch": 0.65, "learning_rate": 3.032314629258517e-05, "loss": 2.0965, "step": 39490 }, { "epoch": 0.65, "learning_rate": 3.0318136272545087e-05, "loss": 2.0931, "step": 39500 }, { "epoch": 0.65, "learning_rate": 3.0313126252505015e-05, "loss": 2.1361, "step": 39510 }, { "epoch": 0.65, "learning_rate": 3.0308116232464932e-05, "loss": 2.1064, "step": 39520 }, { "epoch": 0.65, "learning_rate": 3.0303106212424853e-05, "loss": 2.0835, "step": 39530 }, { "epoch": 0.65, "learning_rate": 3.0298096192384773e-05, "loss": 2.0708, "step": 39540 }, { "epoch": 0.65, "learning_rate": 3.0293086172344694e-05, "loss": 2.1121, "step": 39550 }, { "epoch": 0.65, "learning_rate": 3.028807615230461e-05, "loss": 2.1439, "step": 39560 }, { "epoch": 0.65, "learning_rate": 3.0283066132264532e-05, "loss": 2.1026, "step": 39570 }, { "epoch": 0.65, "learning_rate": 3.0278056112224453e-05, "loss": 2.0838, "step": 39580 }, { "epoch": 0.65, "learning_rate": 3.027304609218437e-05, "loss": 2.0564, "step": 39590 }, { "epoch": 0.65, "learning_rate": 3.026803607214429e-05, "loss": 2.105, "step": 39600 }, { "epoch": 0.65, "learning_rate": 3.026302605210421e-05, "loss": 2.0932, "step": 39610 }, { "epoch": 0.65, "learning_rate": 3.025801603206413e-05, "loss": 2.1012, "step": 39620 }, { "epoch": 0.65, "learning_rate": 3.025300601202405e-05, "loss": 2.0772, "step": 39630 }, { "epoch": 0.65, "learning_rate": 3.024799599198397e-05, "loss": 2.0428, "step": 39640 }, { "epoch": 0.65, "learning_rate": 3.0242985971943887e-05, "loss": 2.1058, "step": 39650 }, { "epoch": 0.65, "learning_rate": 3.0237975951903808e-05, "loss": 2.0792, "step": 39660 }, { "epoch": 0.65, "learning_rate": 3.0232965931863728e-05, "loss": 2.0815, "step": 39670 }, { "epoch": 0.65, "learning_rate": 3.0227955911823645e-05, "loss": 2.0409, "step": 39680 }, { "epoch": 0.65, "learning_rate": 3.0222945891783566e-05, "loss": 2.1043, "step": 39690 }, { "epoch": 0.65, "learning_rate": 3.0217935871743487e-05, "loss": 2.1097, "step": 39700 }, { "epoch": 0.65, "learning_rate": 3.021292585170341e-05, "loss": 2.0468, "step": 39710 }, { "epoch": 0.65, "learning_rate": 3.020791583166333e-05, "loss": 2.0952, "step": 39720 }, { "epoch": 0.65, "learning_rate": 3.020290581162325e-05, "loss": 2.0741, "step": 39730 }, { "epoch": 0.65, "learning_rate": 3.019789579158317e-05, "loss": 2.1199, "step": 39740 }, { "epoch": 0.65, "learning_rate": 3.019288577154309e-05, "loss": 2.0846, "step": 39750 }, { "epoch": 0.65, "learning_rate": 3.0187875751503007e-05, "loss": 2.0561, "step": 39760 }, { "epoch": 0.65, "learning_rate": 3.0182865731462928e-05, "loss": 2.0662, "step": 39770 }, { "epoch": 0.65, "learning_rate": 3.017785571142285e-05, "loss": 2.0859, "step": 39780 }, { "epoch": 0.65, "learning_rate": 3.0172845691382766e-05, "loss": 2.1052, "step": 39790 }, { "epoch": 0.65, "learning_rate": 3.0167835671342686e-05, "loss": 2.1298, "step": 39800 }, { "epoch": 0.65, "learning_rate": 3.0162825651302607e-05, "loss": 2.1085, "step": 39810 }, { "epoch": 0.65, "learning_rate": 3.0157815631262524e-05, "loss": 2.0917, "step": 39820 }, { "epoch": 0.65, "learning_rate": 3.0152805611222445e-05, "loss": 2.0553, "step": 39830 }, { "epoch": 0.65, "learning_rate": 3.0147795591182366e-05, "loss": 2.1049, "step": 39840 }, { "epoch": 0.65, "learning_rate": 3.0142785571142286e-05, "loss": 2.109, "step": 39850 }, { "epoch": 0.65, "learning_rate": 3.0137775551102203e-05, "loss": 2.1082, "step": 39860 }, { "epoch": 0.65, "learning_rate": 3.0132765531062124e-05, "loss": 2.0842, "step": 39870 }, { "epoch": 0.65, "learning_rate": 3.0127755511022045e-05, "loss": 2.0543, "step": 39880 }, { "epoch": 0.65, "learning_rate": 3.0122745490981962e-05, "loss": 2.1243, "step": 39890 }, { "epoch": 0.65, "learning_rate": 3.011773547094189e-05, "loss": 2.0786, "step": 39900 }, { "epoch": 0.65, "learning_rate": 3.0112725450901807e-05, "loss": 2.1148, "step": 39910 }, { "epoch": 0.65, "learning_rate": 3.0107715430861727e-05, "loss": 2.1058, "step": 39920 }, { "epoch": 0.65, "learning_rate": 3.0102705410821648e-05, "loss": 2.0723, "step": 39930 }, { "epoch": 0.65, "learning_rate": 3.0097695390781565e-05, "loss": 2.0943, "step": 39940 }, { "epoch": 0.65, "learning_rate": 3.0092685370741486e-05, "loss": 2.0542, "step": 39950 }, { "epoch": 0.65, "learning_rate": 3.0087675350701406e-05, "loss": 2.0713, "step": 39960 }, { "epoch": 0.65, "learning_rate": 3.0082665330661324e-05, "loss": 2.0639, "step": 39970 }, { "epoch": 0.65, "learning_rate": 3.0077655310621244e-05, "loss": 2.0455, "step": 39980 }, { "epoch": 0.65, "learning_rate": 3.0072645290581165e-05, "loss": 2.0507, "step": 39990 }, { "epoch": 0.65, "learning_rate": 3.0067635270541082e-05, "loss": 2.0858, "step": 40000 }, { "epoch": 0.65, "eval_loss": 2.0627048015594482, "eval_mean_f1": 0.6493954310688724, "eval_rouge1_f1": 0.7105602674947658, "eval_rouge1_precision": 0.8219978988041803, "eval_rouge1_recall": 0.6577499942051261, "eval_rouge2_f1": 0.5613694632362091, "eval_rouge2_precision": 0.6533685722101252, "eval_rouge2_recall": 0.5200281533011908, "eval_rougeL_f1": 0.6762565624756424, "eval_rougeL_precision": 0.7806211344042366, "eval_rougeL_recall": 0.6273050837428086, "eval_runtime": 64.8825, "eval_samples_per_second": 15.782, "eval_steps_per_second": 1.973, "step": 40000 }, { "epoch": 0.65, "learning_rate": 3.0062625250501003e-05, "loss": 2.072, "step": 40010 }, { "epoch": 0.65, "learning_rate": 3.0057615230460924e-05, "loss": 2.0637, "step": 40020 }, { "epoch": 0.65, "learning_rate": 3.005260521042084e-05, "loss": 2.0745, "step": 40030 }, { "epoch": 0.65, "learning_rate": 3.004759519038076e-05, "loss": 2.0345, "step": 40040 }, { "epoch": 0.65, "learning_rate": 3.0042585170340682e-05, "loss": 2.0991, "step": 40050 }, { "epoch": 0.65, "learning_rate": 3.00375751503006e-05, "loss": 2.0391, "step": 40060 }, { "epoch": 0.65, "learning_rate": 3.003256513026052e-05, "loss": 2.0599, "step": 40070 }, { "epoch": 0.65, "learning_rate": 3.002755511022044e-05, "loss": 2.0916, "step": 40080 }, { "epoch": 0.66, "learning_rate": 3.0022545090180358e-05, "loss": 2.0714, "step": 40090 }, { "epoch": 0.66, "learning_rate": 3.0017535070140285e-05, "loss": 2.0861, "step": 40100 }, { "epoch": 0.66, "learning_rate": 3.0012525050100203e-05, "loss": 2.0838, "step": 40110 }, { "epoch": 0.66, "learning_rate": 3.0007515030060123e-05, "loss": 2.0458, "step": 40120 }, { "epoch": 0.66, "learning_rate": 3.0002505010020044e-05, "loss": 2.0762, "step": 40130 }, { "epoch": 0.66, "learning_rate": 2.9997494989979964e-05, "loss": 2.0902, "step": 40140 }, { "epoch": 0.66, "learning_rate": 2.9992484969939882e-05, "loss": 2.1071, "step": 40150 }, { "epoch": 0.66, "learning_rate": 2.9987474949899802e-05, "loss": 2.1088, "step": 40160 }, { "epoch": 0.66, "learning_rate": 2.9982464929859723e-05, "loss": 2.0782, "step": 40170 }, { "epoch": 0.66, "learning_rate": 2.997745490981964e-05, "loss": 2.0755, "step": 40180 }, { "epoch": 0.66, "learning_rate": 2.997244488977956e-05, "loss": 2.1196, "step": 40190 }, { "epoch": 0.66, "learning_rate": 2.996743486973948e-05, "loss": 2.0679, "step": 40200 }, { "epoch": 0.66, "learning_rate": 2.99624248496994e-05, "loss": 2.116, "step": 40210 }, { "epoch": 0.66, "learning_rate": 2.995741482965932e-05, "loss": 2.0563, "step": 40220 }, { "epoch": 0.66, "learning_rate": 2.995240480961924e-05, "loss": 2.0922, "step": 40230 }, { "epoch": 0.66, "learning_rate": 2.9947394789579157e-05, "loss": 2.1411, "step": 40240 }, { "epoch": 0.66, "learning_rate": 2.9942384769539078e-05, "loss": 2.1159, "step": 40250 }, { "epoch": 0.66, "learning_rate": 2.9937374749499e-05, "loss": 2.0761, "step": 40260 }, { "epoch": 0.66, "learning_rate": 2.9932364729458916e-05, "loss": 2.1147, "step": 40270 }, { "epoch": 0.66, "learning_rate": 2.9927354709418837e-05, "loss": 2.1008, "step": 40280 }, { "epoch": 0.66, "learning_rate": 2.9922344689378757e-05, "loss": 2.1084, "step": 40290 }, { "epoch": 0.66, "learning_rate": 2.991733466933868e-05, "loss": 2.0268, "step": 40300 }, { "epoch": 0.66, "learning_rate": 2.9912324649298602e-05, "loss": 2.0969, "step": 40310 }, { "epoch": 0.66, "learning_rate": 2.990731462925852e-05, "loss": 2.0894, "step": 40320 }, { "epoch": 0.66, "learning_rate": 2.990230460921844e-05, "loss": 2.1006, "step": 40330 }, { "epoch": 0.66, "learning_rate": 2.989729458917836e-05, "loss": 2.1159, "step": 40340 }, { "epoch": 0.66, "learning_rate": 2.9892284569138278e-05, "loss": 2.0833, "step": 40350 }, { "epoch": 0.66, "learning_rate": 2.9887274549098198e-05, "loss": 2.1035, "step": 40360 }, { "epoch": 0.66, "learning_rate": 2.988226452905812e-05, "loss": 2.0498, "step": 40370 }, { "epoch": 0.66, "learning_rate": 2.9877254509018036e-05, "loss": 2.0703, "step": 40380 }, { "epoch": 0.66, "learning_rate": 2.9872244488977957e-05, "loss": 2.063, "step": 40390 }, { "epoch": 0.66, "learning_rate": 2.9867234468937877e-05, "loss": 2.0832, "step": 40400 }, { "epoch": 0.66, "learning_rate": 2.9862224448897798e-05, "loss": 2.112, "step": 40410 }, { "epoch": 0.66, "learning_rate": 2.9857214428857715e-05, "loss": 2.0891, "step": 40420 }, { "epoch": 0.66, "learning_rate": 2.9852204408817636e-05, "loss": 2.1118, "step": 40430 }, { "epoch": 0.66, "learning_rate": 2.9847194388777557e-05, "loss": 2.1079, "step": 40440 }, { "epoch": 0.66, "learning_rate": 2.9842184368737474e-05, "loss": 2.0749, "step": 40450 }, { "epoch": 0.66, "learning_rate": 2.9837174348697394e-05, "loss": 2.0815, "step": 40460 }, { "epoch": 0.66, "learning_rate": 2.9832164328657315e-05, "loss": 2.0599, "step": 40470 }, { "epoch": 0.66, "learning_rate": 2.9827154308617232e-05, "loss": 2.1309, "step": 40480 }, { "epoch": 0.66, "learning_rate": 2.982214428857716e-05, "loss": 2.068, "step": 40490 }, { "epoch": 0.66, "learning_rate": 2.9817134268537077e-05, "loss": 2.0912, "step": 40500 }, { "epoch": 0.66, "learning_rate": 2.9812124248496998e-05, "loss": 2.1007, "step": 40510 }, { "epoch": 0.66, "learning_rate": 2.980711422845692e-05, "loss": 2.1638, "step": 40520 }, { "epoch": 0.66, "learning_rate": 2.9802104208416836e-05, "loss": 2.0567, "step": 40530 }, { "epoch": 0.66, "learning_rate": 2.9797094188376756e-05, "loss": 2.0796, "step": 40540 }, { "epoch": 0.66, "learning_rate": 2.9792084168336677e-05, "loss": 2.0865, "step": 40550 }, { "epoch": 0.66, "learning_rate": 2.9787074148296594e-05, "loss": 2.1121, "step": 40560 }, { "epoch": 0.66, "learning_rate": 2.9782064128256515e-05, "loss": 2.1029, "step": 40570 }, { "epoch": 0.66, "learning_rate": 2.9777054108216435e-05, "loss": 2.0885, "step": 40580 }, { "epoch": 0.66, "learning_rate": 2.9772044088176353e-05, "loss": 2.0852, "step": 40590 }, { "epoch": 0.66, "learning_rate": 2.9767034068136273e-05, "loss": 2.074, "step": 40600 }, { "epoch": 0.66, "learning_rate": 2.9762024048096194e-05, "loss": 2.048, "step": 40610 }, { "epoch": 0.66, "learning_rate": 2.975701402805611e-05, "loss": 2.0816, "step": 40620 }, { "epoch": 0.66, "learning_rate": 2.9752004008016032e-05, "loss": 2.0681, "step": 40630 }, { "epoch": 0.66, "learning_rate": 2.9746993987975952e-05, "loss": 2.0672, "step": 40640 }, { "epoch": 0.66, "learning_rate": 2.974198396793587e-05, "loss": 2.1159, "step": 40650 }, { "epoch": 0.66, "learning_rate": 2.973697394789579e-05, "loss": 2.115, "step": 40660 }, { "epoch": 0.66, "learning_rate": 2.973196392785571e-05, "loss": 2.0839, "step": 40670 }, { "epoch": 0.66, "learning_rate": 2.972695390781563e-05, "loss": 2.0132, "step": 40680 }, { "epoch": 0.66, "learning_rate": 2.9721943887775556e-05, "loss": 2.0863, "step": 40690 }, { "epoch": 0.67, "learning_rate": 2.9716933867735476e-05, "loss": 2.0549, "step": 40700 }, { "epoch": 0.67, "learning_rate": 2.9711923847695394e-05, "loss": 2.0785, "step": 40710 }, { "epoch": 0.67, "learning_rate": 2.9706913827655314e-05, "loss": 2.0981, "step": 40720 }, { "epoch": 0.67, "learning_rate": 2.9701903807615235e-05, "loss": 2.1353, "step": 40730 }, { "epoch": 0.67, "learning_rate": 2.9696893787575152e-05, "loss": 2.0782, "step": 40740 }, { "epoch": 0.67, "learning_rate": 2.9691883767535073e-05, "loss": 2.1602, "step": 40750 }, { "epoch": 0.67, "learning_rate": 2.9686873747494993e-05, "loss": 2.0561, "step": 40760 }, { "epoch": 0.67, "learning_rate": 2.968186372745491e-05, "loss": 2.0708, "step": 40770 }, { "epoch": 0.67, "learning_rate": 2.967685370741483e-05, "loss": 2.0536, "step": 40780 }, { "epoch": 0.67, "learning_rate": 2.9671843687374752e-05, "loss": 2.1265, "step": 40790 }, { "epoch": 0.67, "learning_rate": 2.966683366733467e-05, "loss": 2.0639, "step": 40800 }, { "epoch": 0.67, "learning_rate": 2.966182364729459e-05, "loss": 2.0825, "step": 40810 }, { "epoch": 0.67, "learning_rate": 2.965681362725451e-05, "loss": 2.1059, "step": 40820 }, { "epoch": 0.67, "learning_rate": 2.9651803607214428e-05, "loss": 2.0715, "step": 40830 }, { "epoch": 0.67, "learning_rate": 2.964679358717435e-05, "loss": 2.0802, "step": 40840 }, { "epoch": 0.67, "learning_rate": 2.964178356713427e-05, "loss": 2.0542, "step": 40850 }, { "epoch": 0.67, "learning_rate": 2.9636773547094186e-05, "loss": 2.0681, "step": 40860 }, { "epoch": 0.67, "learning_rate": 2.9631763527054107e-05, "loss": 2.0553, "step": 40870 }, { "epoch": 0.67, "learning_rate": 2.9626753507014028e-05, "loss": 2.0973, "step": 40880 }, { "epoch": 0.67, "learning_rate": 2.962174348697395e-05, "loss": 2.1302, "step": 40890 }, { "epoch": 0.67, "learning_rate": 2.9616733466933872e-05, "loss": 2.0847, "step": 40900 }, { "epoch": 0.67, "learning_rate": 2.961172344689379e-05, "loss": 2.0891, "step": 40910 }, { "epoch": 0.67, "learning_rate": 2.960671342685371e-05, "loss": 2.0744, "step": 40920 }, { "epoch": 0.67, "learning_rate": 2.960170340681363e-05, "loss": 2.0923, "step": 40930 }, { "epoch": 0.67, "learning_rate": 2.9596693386773548e-05, "loss": 2.0633, "step": 40940 }, { "epoch": 0.67, "learning_rate": 2.959168336673347e-05, "loss": 2.1068, "step": 40950 }, { "epoch": 0.67, "learning_rate": 2.958667334669339e-05, "loss": 2.0669, "step": 40960 }, { "epoch": 0.67, "learning_rate": 2.958166332665331e-05, "loss": 2.1189, "step": 40970 }, { "epoch": 0.67, "learning_rate": 2.9576653306613227e-05, "loss": 2.0919, "step": 40980 }, { "epoch": 0.67, "learning_rate": 2.9571643286573148e-05, "loss": 2.1114, "step": 40990 }, { "epoch": 0.67, "learning_rate": 2.956663326653307e-05, "loss": 2.1284, "step": 41000 }, { "epoch": 0.67, "eval_loss": 2.05977725982666, "eval_mean_f1": 0.6511203169869278, "eval_rouge1_f1": 0.7110321142945386, "eval_rouge1_precision": 0.8222095262417956, "eval_rouge1_recall": 0.6584928389491955, "eval_rouge2_f1": 0.5634961687906419, "eval_rouge2_precision": 0.6554597285310174, "eval_rouge2_recall": 0.521829289079037, "eval_rougeL_f1": 0.678832667875603, "eval_rougeL_precision": 0.7838653899014083, "eval_rougeL_recall": 0.629532995168675, "eval_runtime": 65.5703, "eval_samples_per_second": 15.617, "eval_steps_per_second": 1.952, "step": 41000 }, { "epoch": 0.67, "learning_rate": 2.9561623246492986e-05, "loss": 2.0617, "step": 41010 }, { "epoch": 0.67, "learning_rate": 2.9556613226452906e-05, "loss": 2.0363, "step": 41020 }, { "epoch": 0.67, "learning_rate": 2.9551603206412827e-05, "loss": 2.0574, "step": 41030 }, { "epoch": 0.67, "learning_rate": 2.9546593186372744e-05, "loss": 2.103, "step": 41040 }, { "epoch": 0.67, "learning_rate": 2.9541583166332665e-05, "loss": 2.0551, "step": 41050 }, { "epoch": 0.67, "learning_rate": 2.9536573146292586e-05, "loss": 2.061, "step": 41060 }, { "epoch": 0.67, "learning_rate": 2.9531563126252503e-05, "loss": 2.0892, "step": 41070 }, { "epoch": 0.67, "learning_rate": 2.952655310621243e-05, "loss": 2.0695, "step": 41080 }, { "epoch": 0.67, "learning_rate": 2.9521543086172347e-05, "loss": 2.066, "step": 41090 }, { "epoch": 0.67, "learning_rate": 2.9516533066132268e-05, "loss": 2.0896, "step": 41100 }, { "epoch": 0.67, "learning_rate": 2.951152304609219e-05, "loss": 2.0989, "step": 41110 }, { "epoch": 0.67, "learning_rate": 2.9506513026052106e-05, "loss": 2.0869, "step": 41120 }, { "epoch": 0.67, "learning_rate": 2.9501503006012027e-05, "loss": 2.058, "step": 41130 }, { "epoch": 0.67, "learning_rate": 2.9496492985971947e-05, "loss": 2.0183, "step": 41140 }, { "epoch": 0.67, "learning_rate": 2.9491482965931865e-05, "loss": 2.0319, "step": 41150 }, { "epoch": 0.67, "learning_rate": 2.9486472945891785e-05, "loss": 2.0938, "step": 41160 }, { "epoch": 0.67, "learning_rate": 2.9481462925851706e-05, "loss": 2.0541, "step": 41170 }, { "epoch": 0.67, "learning_rate": 2.9476452905811623e-05, "loss": 2.1308, "step": 41180 }, { "epoch": 0.67, "learning_rate": 2.9471442885771544e-05, "loss": 2.0927, "step": 41190 }, { "epoch": 0.67, "learning_rate": 2.9466432865731464e-05, "loss": 2.058, "step": 41200 }, { "epoch": 0.67, "learning_rate": 2.946142284569138e-05, "loss": 2.0554, "step": 41210 }, { "epoch": 0.67, "learning_rate": 2.9456412825651302e-05, "loss": 2.1141, "step": 41220 }, { "epoch": 0.67, "learning_rate": 2.9451402805611223e-05, "loss": 2.1039, "step": 41230 }, { "epoch": 0.67, "learning_rate": 2.9446392785571144e-05, "loss": 2.0645, "step": 41240 }, { "epoch": 0.67, "learning_rate": 2.944138276553106e-05, "loss": 2.1119, "step": 41250 }, { "epoch": 0.67, "learning_rate": 2.943637274549098e-05, "loss": 2.0774, "step": 41260 }, { "epoch": 0.67, "learning_rate": 2.9431362725450902e-05, "loss": 2.0491, "step": 41270 }, { "epoch": 0.67, "learning_rate": 2.9426352705410826e-05, "loss": 2.0856, "step": 41280 }, { "epoch": 0.67, "learning_rate": 2.9421342685370747e-05, "loss": 2.0473, "step": 41290 }, { "epoch": 0.67, "learning_rate": 2.9416332665330664e-05, "loss": 2.0733, "step": 41300 }, { "epoch": 0.68, "learning_rate": 2.9411322645290585e-05, "loss": 2.12, "step": 41310 }, { "epoch": 0.68, "learning_rate": 2.9406312625250505e-05, "loss": 2.0725, "step": 41320 }, { "epoch": 0.68, "learning_rate": 2.9401302605210423e-05, "loss": 2.0618, "step": 41330 }, { "epoch": 0.68, "learning_rate": 2.9396292585170343e-05, "loss": 2.0381, "step": 41340 }, { "epoch": 0.68, "learning_rate": 2.9391282565130264e-05, "loss": 2.0454, "step": 41350 }, { "epoch": 0.68, "learning_rate": 2.938627254509018e-05, "loss": 2.0621, "step": 41360 }, { "epoch": 0.68, "learning_rate": 2.9381262525050102e-05, "loss": 2.0677, "step": 41370 }, { "epoch": 0.68, "learning_rate": 2.9376252505010022e-05, "loss": 2.046, "step": 41380 }, { "epoch": 0.68, "learning_rate": 2.937124248496994e-05, "loss": 2.0991, "step": 41390 }, { "epoch": 0.68, "learning_rate": 2.936623246492986e-05, "loss": 2.087, "step": 41400 }, { "epoch": 0.68, "learning_rate": 2.936122244488978e-05, "loss": 2.0851, "step": 41410 }, { "epoch": 0.68, "learning_rate": 2.9356212424849698e-05, "loss": 2.055, "step": 41420 }, { "epoch": 0.68, "learning_rate": 2.935120240480962e-05, "loss": 2.0696, "step": 41430 }, { "epoch": 0.68, "learning_rate": 2.934619238476954e-05, "loss": 2.114, "step": 41440 }, { "epoch": 0.68, "learning_rate": 2.9341182364729457e-05, "loss": 2.0382, "step": 41450 }, { "epoch": 0.68, "learning_rate": 2.9336172344689377e-05, "loss": 2.1014, "step": 41460 }, { "epoch": 0.68, "learning_rate": 2.9331162324649298e-05, "loss": 2.0853, "step": 41470 }, { "epoch": 0.68, "learning_rate": 2.9326152304609222e-05, "loss": 2.0752, "step": 41480 }, { "epoch": 0.68, "learning_rate": 2.9321142284569143e-05, "loss": 2.1071, "step": 41490 }, { "epoch": 0.68, "learning_rate": 2.931613226452906e-05, "loss": 2.0611, "step": 41500 }, { "epoch": 0.68, "learning_rate": 2.931112224448898e-05, "loss": 2.124, "step": 41510 }, { "epoch": 0.68, "learning_rate": 2.93061122244489e-05, "loss": 2.0705, "step": 41520 }, { "epoch": 0.68, "learning_rate": 2.9301102204408822e-05, "loss": 2.044, "step": 41530 }, { "epoch": 0.68, "learning_rate": 2.929609218436874e-05, "loss": 2.0708, "step": 41540 }, { "epoch": 0.68, "learning_rate": 2.929108216432866e-05, "loss": 2.0809, "step": 41550 }, { "epoch": 0.68, "learning_rate": 2.928607214428858e-05, "loss": 2.0775, "step": 41560 }, { "epoch": 0.68, "learning_rate": 2.9281062124248498e-05, "loss": 2.0542, "step": 41570 }, { "epoch": 0.68, "learning_rate": 2.9276052104208418e-05, "loss": 2.0528, "step": 41580 }, { "epoch": 0.68, "learning_rate": 2.927104208416834e-05, "loss": 2.0503, "step": 41590 }, { "epoch": 0.68, "learning_rate": 2.9266032064128256e-05, "loss": 2.0953, "step": 41600 }, { "epoch": 0.68, "learning_rate": 2.9261022044088177e-05, "loss": 2.0818, "step": 41610 }, { "epoch": 0.68, "learning_rate": 2.9256012024048097e-05, "loss": 2.072, "step": 41620 }, { "epoch": 0.68, "learning_rate": 2.9251002004008015e-05, "loss": 2.0766, "step": 41630 }, { "epoch": 0.68, "learning_rate": 2.9245991983967935e-05, "loss": 2.0831, "step": 41640 }, { "epoch": 0.68, "learning_rate": 2.9240981963927856e-05, "loss": 2.0659, "step": 41650 }, { "epoch": 0.68, "learning_rate": 2.9235971943887773e-05, "loss": 2.0742, "step": 41660 }, { "epoch": 0.68, "learning_rate": 2.92309619238477e-05, "loss": 2.0448, "step": 41670 }, { "epoch": 0.68, "learning_rate": 2.9225951903807618e-05, "loss": 2.0789, "step": 41680 }, { "epoch": 0.68, "learning_rate": 2.922094188376754e-05, "loss": 2.0601, "step": 41690 }, { "epoch": 0.68, "learning_rate": 2.921593186372746e-05, "loss": 2.0636, "step": 41700 }, { "epoch": 0.68, "learning_rate": 2.9210921843687376e-05, "loss": 2.1077, "step": 41710 }, { "epoch": 0.68, "learning_rate": 2.9205911823647297e-05, "loss": 2.0592, "step": 41720 }, { "epoch": 0.68, "learning_rate": 2.9200901803607218e-05, "loss": 2.0919, "step": 41730 }, { "epoch": 0.68, "learning_rate": 2.9195891783567135e-05, "loss": 2.1002, "step": 41740 }, { "epoch": 0.68, "learning_rate": 2.9190881763527056e-05, "loss": 2.1087, "step": 41750 }, { "epoch": 0.68, "learning_rate": 2.9185871743486976e-05, "loss": 2.0741, "step": 41760 }, { "epoch": 0.68, "learning_rate": 2.9180861723446893e-05, "loss": 2.0814, "step": 41770 }, { "epoch": 0.68, "learning_rate": 2.9175851703406814e-05, "loss": 2.016, "step": 41780 }, { "epoch": 0.68, "learning_rate": 2.9170841683366735e-05, "loss": 2.1073, "step": 41790 }, { "epoch": 0.68, "learning_rate": 2.9165831663326655e-05, "loss": 2.0315, "step": 41800 }, { "epoch": 0.68, "learning_rate": 2.9160821643286573e-05, "loss": 2.0656, "step": 41810 }, { "epoch": 0.68, "learning_rate": 2.9155811623246493e-05, "loss": 2.0789, "step": 41820 }, { "epoch": 0.68, "learning_rate": 2.9150801603206414e-05, "loss": 2.0887, "step": 41830 }, { "epoch": 0.68, "learning_rate": 2.914579158316633e-05, "loss": 2.1086, "step": 41840 }, { "epoch": 0.68, "learning_rate": 2.9140781563126252e-05, "loss": 2.113, "step": 41850 }, { "epoch": 0.68, "learning_rate": 2.9135771543086172e-05, "loss": 2.0843, "step": 41860 }, { "epoch": 0.68, "learning_rate": 2.9130761523046097e-05, "loss": 2.0672, "step": 41870 }, { "epoch": 0.68, "learning_rate": 2.9125751503006017e-05, "loss": 2.0608, "step": 41880 }, { "epoch": 0.68, "learning_rate": 2.9120741482965934e-05, "loss": 2.052, "step": 41890 }, { "epoch": 0.68, "learning_rate": 2.9115731462925855e-05, "loss": 2.0672, "step": 41900 }, { "epoch": 0.68, "learning_rate": 2.9110721442885776e-05, "loss": 2.0527, "step": 41910 }, { "epoch": 0.68, "learning_rate": 2.9105711422845693e-05, "loss": 2.0736, "step": 41920 }, { "epoch": 0.69, "learning_rate": 2.9100701402805614e-05, "loss": 2.0301, "step": 41930 }, { "epoch": 0.69, "learning_rate": 2.9095691382765534e-05, "loss": 2.0799, "step": 41940 }, { "epoch": 0.69, "learning_rate": 2.909068136272545e-05, "loss": 2.1106, "step": 41950 }, { "epoch": 0.69, "learning_rate": 2.9085671342685372e-05, "loss": 2.1383, "step": 41960 }, { "epoch": 0.69, "learning_rate": 2.9080661322645293e-05, "loss": 2.0622, "step": 41970 }, { "epoch": 0.69, "learning_rate": 2.907565130260521e-05, "loss": 2.0665, "step": 41980 }, { "epoch": 0.69, "learning_rate": 2.907064128256513e-05, "loss": 2.0755, "step": 41990 }, { "epoch": 0.69, "learning_rate": 2.906563126252505e-05, "loss": 2.0845, "step": 42000 }, { "epoch": 0.69, "eval_loss": 2.0594496726989746, "eval_mean_f1": 0.6452487574166067, "eval_rouge1_f1": 0.7051012828220258, "eval_rouge1_precision": 0.8148008273241645, "eval_rouge1_recall": 0.6540123281168523, "eval_rouge2_f1": 0.5574235556078606, "eval_rouge2_precision": 0.6473573742067391, "eval_rouge2_recall": 0.5172799180609575, "eval_rougeL_f1": 0.6732214338199336, "eval_rougeL_precision": 0.7762919220456703, "eval_rougeL_recall": 0.6257200999891025, "eval_runtime": 66.1844, "eval_samples_per_second": 15.472, "eval_steps_per_second": 1.934, "step": 42000 }, { "epoch": 0.69, "learning_rate": 2.906062124248497e-05, "loss": 2.099, "step": 42010 }, { "epoch": 0.69, "learning_rate": 2.905561122244489e-05, "loss": 2.1094, "step": 42020 }, { "epoch": 0.69, "learning_rate": 2.905060120240481e-05, "loss": 2.0966, "step": 42030 }, { "epoch": 0.69, "learning_rate": 2.9045591182364727e-05, "loss": 2.0951, "step": 42040 }, { "epoch": 0.69, "learning_rate": 2.9040581162324648e-05, "loss": 2.0643, "step": 42050 }, { "epoch": 0.69, "learning_rate": 2.903557114228457e-05, "loss": 2.0519, "step": 42060 }, { "epoch": 0.69, "learning_rate": 2.9030561122244492e-05, "loss": 2.0822, "step": 42070 }, { "epoch": 0.69, "learning_rate": 2.9025551102204413e-05, "loss": 2.054, "step": 42080 }, { "epoch": 0.69, "learning_rate": 2.9020541082164334e-05, "loss": 2.0588, "step": 42090 }, { "epoch": 0.69, "learning_rate": 2.901553106212425e-05, "loss": 2.0373, "step": 42100 }, { "epoch": 0.69, "learning_rate": 2.901052104208417e-05, "loss": 2.063, "step": 42110 }, { "epoch": 0.69, "learning_rate": 2.9005511022044092e-05, "loss": 2.0843, "step": 42120 }, { "epoch": 0.69, "learning_rate": 2.900050100200401e-05, "loss": 2.1105, "step": 42130 }, { "epoch": 0.69, "learning_rate": 2.899549098196393e-05, "loss": 2.1097, "step": 42140 }, { "epoch": 0.69, "learning_rate": 2.899048096192385e-05, "loss": 2.0817, "step": 42150 }, { "epoch": 0.69, "learning_rate": 2.8985470941883768e-05, "loss": 2.0631, "step": 42160 }, { "epoch": 0.69, "learning_rate": 2.898046092184369e-05, "loss": 2.0837, "step": 42170 }, { "epoch": 0.69, "learning_rate": 2.897545090180361e-05, "loss": 2.0788, "step": 42180 }, { "epoch": 0.69, "learning_rate": 2.8970440881763527e-05, "loss": 2.0799, "step": 42190 }, { "epoch": 0.69, "learning_rate": 2.8965430861723447e-05, "loss": 2.0873, "step": 42200 }, { "epoch": 0.69, "learning_rate": 2.8960420841683368e-05, "loss": 2.0327, "step": 42210 }, { "epoch": 0.69, "learning_rate": 2.8955410821643285e-05, "loss": 2.091, "step": 42220 }, { "epoch": 0.69, "learning_rate": 2.8950400801603206e-05, "loss": 2.0649, "step": 42230 }, { "epoch": 0.69, "learning_rate": 2.8945390781563126e-05, "loss": 2.0626, "step": 42240 }, { "epoch": 0.69, "learning_rate": 2.8940380761523044e-05, "loss": 2.0904, "step": 42250 }, { "epoch": 0.69, "learning_rate": 2.893537074148297e-05, "loss": 2.1012, "step": 42260 }, { "epoch": 0.69, "learning_rate": 2.8930360721442888e-05, "loss": 2.0781, "step": 42270 }, { "epoch": 0.69, "learning_rate": 2.892535070140281e-05, "loss": 2.0362, "step": 42280 }, { "epoch": 0.69, "learning_rate": 2.892034068136273e-05, "loss": 2.0611, "step": 42290 }, { "epoch": 0.69, "learning_rate": 2.8915330661322647e-05, "loss": 2.0467, "step": 42300 }, { "epoch": 0.69, "learning_rate": 2.8910320641282567e-05, "loss": 2.1043, "step": 42310 }, { "epoch": 0.69, "learning_rate": 2.8905310621242488e-05, "loss": 2.0956, "step": 42320 }, { "epoch": 0.69, "learning_rate": 2.8900300601202405e-05, "loss": 2.0687, "step": 42330 }, { "epoch": 0.69, "learning_rate": 2.8895290581162326e-05, "loss": 2.0995, "step": 42340 }, { "epoch": 0.69, "learning_rate": 2.8890280561122247e-05, "loss": 2.0875, "step": 42350 }, { "epoch": 0.69, "learning_rate": 2.8885270541082164e-05, "loss": 2.1204, "step": 42360 }, { "epoch": 0.69, "learning_rate": 2.8880260521042085e-05, "loss": 2.0593, "step": 42370 }, { "epoch": 0.69, "learning_rate": 2.8875250501002005e-05, "loss": 2.063, "step": 42380 }, { "epoch": 0.69, "learning_rate": 2.8870240480961926e-05, "loss": 2.1083, "step": 42390 }, { "epoch": 0.69, "learning_rate": 2.8865230460921843e-05, "loss": 2.0861, "step": 42400 }, { "epoch": 0.69, "learning_rate": 2.8860220440881764e-05, "loss": 2.0973, "step": 42410 }, { "epoch": 0.69, "learning_rate": 2.8855210420841684e-05, "loss": 2.0931, "step": 42420 }, { "epoch": 0.69, "learning_rate": 2.88502004008016e-05, "loss": 2.1059, "step": 42430 }, { "epoch": 0.69, "learning_rate": 2.8845190380761522e-05, "loss": 2.0608, "step": 42440 }, { "epoch": 0.69, "learning_rate": 2.8840180360721443e-05, "loss": 2.0924, "step": 42450 }, { "epoch": 0.69, "learning_rate": 2.8835170340681367e-05, "loss": 2.0915, "step": 42460 }, { "epoch": 0.69, "learning_rate": 2.8830160320641288e-05, "loss": 2.1214, "step": 42470 }, { "epoch": 0.69, "learning_rate": 2.8825150300601205e-05, "loss": 2.0953, "step": 42480 }, { "epoch": 0.69, "learning_rate": 2.8820140280561125e-05, "loss": 2.0937, "step": 42490 }, { "epoch": 0.69, "learning_rate": 2.8815130260521046e-05, "loss": 2.0949, "step": 42500 }, { "epoch": 0.69, "learning_rate": 2.8810120240480963e-05, "loss": 2.132, "step": 42510 }, { "epoch": 0.69, "learning_rate": 2.8805110220440884e-05, "loss": 2.0535, "step": 42520 }, { "epoch": 0.69, "learning_rate": 2.8800100200400805e-05, "loss": 2.0513, "step": 42530 }, { "epoch": 0.7, "learning_rate": 2.8795090180360722e-05, "loss": 2.0753, "step": 42540 }, { "epoch": 0.7, "learning_rate": 2.8790080160320643e-05, "loss": 2.0405, "step": 42550 }, { "epoch": 0.7, "learning_rate": 2.8785070140280563e-05, "loss": 2.0639, "step": 42560 }, { "epoch": 0.7, "learning_rate": 2.878006012024048e-05, "loss": 2.1247, "step": 42570 }, { "epoch": 0.7, "learning_rate": 2.87750501002004e-05, "loss": 2.0988, "step": 42580 }, { "epoch": 0.7, "learning_rate": 2.877004008016032e-05, "loss": 2.1049, "step": 42590 }, { "epoch": 0.7, "learning_rate": 2.876503006012024e-05, "loss": 2.1004, "step": 42600 }, { "epoch": 0.7, "learning_rate": 2.876002004008016e-05, "loss": 2.0882, "step": 42610 }, { "epoch": 0.7, "learning_rate": 2.875501002004008e-05, "loss": 2.1347, "step": 42620 }, { "epoch": 0.7, "learning_rate": 2.8749999999999997e-05, "loss": 2.0847, "step": 42630 }, { "epoch": 0.7, "learning_rate": 2.8744989979959918e-05, "loss": 2.116, "step": 42640 }, { "epoch": 0.7, "learning_rate": 2.8739979959919842e-05, "loss": 2.0659, "step": 42650 }, { "epoch": 0.7, "learning_rate": 2.8734969939879763e-05, "loss": 2.0622, "step": 42660 }, { "epoch": 0.7, "learning_rate": 2.8729959919839683e-05, "loss": 2.0789, "step": 42670 }, { "epoch": 0.7, "learning_rate": 2.8724949899799604e-05, "loss": 2.0715, "step": 42680 }, { "epoch": 0.7, "learning_rate": 2.871993987975952e-05, "loss": 2.0815, "step": 42690 }, { "epoch": 0.7, "learning_rate": 2.8714929859719442e-05, "loss": 2.0988, "step": 42700 }, { "epoch": 0.7, "learning_rate": 2.8709919839679363e-05, "loss": 2.0929, "step": 42710 }, { "epoch": 0.7, "learning_rate": 2.870490981963928e-05, "loss": 2.0509, "step": 42720 }, { "epoch": 0.7, "learning_rate": 2.86998997995992e-05, "loss": 2.0648, "step": 42730 }, { "epoch": 0.7, "learning_rate": 2.869488977955912e-05, "loss": 2.0773, "step": 42740 }, { "epoch": 0.7, "learning_rate": 2.868987975951904e-05, "loss": 2.0866, "step": 42750 }, { "epoch": 0.7, "learning_rate": 2.868486973947896e-05, "loss": 2.1074, "step": 42760 }, { "epoch": 0.7, "learning_rate": 2.867985971943888e-05, "loss": 2.1199, "step": 42770 }, { "epoch": 0.7, "learning_rate": 2.8674849699398797e-05, "loss": 2.11, "step": 42780 }, { "epoch": 0.7, "learning_rate": 2.8669839679358718e-05, "loss": 2.0812, "step": 42790 }, { "epoch": 0.7, "learning_rate": 2.8664829659318638e-05, "loss": 2.0892, "step": 42800 }, { "epoch": 0.7, "learning_rate": 2.8659819639278555e-05, "loss": 2.0938, "step": 42810 }, { "epoch": 0.7, "learning_rate": 2.8654809619238476e-05, "loss": 2.0707, "step": 42820 }, { "epoch": 0.7, "learning_rate": 2.8649799599198397e-05, "loss": 2.0892, "step": 42830 }, { "epoch": 0.7, "learning_rate": 2.8644789579158314e-05, "loss": 2.0663, "step": 42840 }, { "epoch": 0.7, "learning_rate": 2.863977955911824e-05, "loss": 2.0711, "step": 42850 }, { "epoch": 0.7, "learning_rate": 2.863476953907816e-05, "loss": 2.1051, "step": 42860 }, { "epoch": 0.7, "learning_rate": 2.862975951903808e-05, "loss": 2.0984, "step": 42870 }, { "epoch": 0.7, "learning_rate": 2.8624749498998e-05, "loss": 2.0726, "step": 42880 }, { "epoch": 0.7, "learning_rate": 2.8619739478957917e-05, "loss": 2.0777, "step": 42890 }, { "epoch": 0.7, "learning_rate": 2.8614729458917838e-05, "loss": 2.0513, "step": 42900 }, { "epoch": 0.7, "learning_rate": 2.860971943887776e-05, "loss": 2.0847, "step": 42910 }, { "epoch": 0.7, "learning_rate": 2.8604709418837676e-05, "loss": 2.1225, "step": 42920 }, { "epoch": 0.7, "learning_rate": 2.8599699398797596e-05, "loss": 2.1191, "step": 42930 }, { "epoch": 0.7, "learning_rate": 2.8594689378757517e-05, "loss": 2.036, "step": 42940 }, { "epoch": 0.7, "learning_rate": 2.8589679358717438e-05, "loss": 2.0838, "step": 42950 }, { "epoch": 0.7, "learning_rate": 2.8584669338677355e-05, "loss": 2.0452, "step": 42960 }, { "epoch": 0.7, "learning_rate": 2.8579659318637276e-05, "loss": 2.0891, "step": 42970 }, { "epoch": 0.7, "learning_rate": 2.8574649298597196e-05, "loss": 2.0876, "step": 42980 }, { "epoch": 0.7, "learning_rate": 2.8569639278557113e-05, "loss": 2.0605, "step": 42990 }, { "epoch": 0.7, "learning_rate": 2.8564629258517034e-05, "loss": 2.073, "step": 43000 }, { "epoch": 0.7, "eval_loss": 2.053649425506592, "eval_mean_f1": 0.653020716679353, "eval_rouge1_f1": 0.7122731045919543, "eval_rouge1_precision": 0.8270648106122453, "eval_rouge1_recall": 0.6575396771152361, "eval_rouge2_f1": 0.5669763484745322, "eval_rouge2_precision": 0.66295662345467, "eval_rouge2_recall": 0.5233169880111034, "eval_rougeL_f1": 0.6798126969715725, "eval_rougeL_precision": 0.7872789632896338, "eval_rougeL_recall": 0.6288172979767241, "eval_runtime": 64.3756, "eval_samples_per_second": 15.907, "eval_steps_per_second": 1.988, "step": 43000 }, { "epoch": 0.7, "learning_rate": 2.8559619238476955e-05, "loss": 2.0899, "step": 43010 }, { "epoch": 0.7, "learning_rate": 2.8554609218436872e-05, "loss": 2.1059, "step": 43020 }, { "epoch": 0.7, "learning_rate": 2.8549599198396793e-05, "loss": 2.0707, "step": 43030 }, { "epoch": 0.7, "learning_rate": 2.8544589178356713e-05, "loss": 2.0794, "step": 43040 }, { "epoch": 0.7, "learning_rate": 2.8539579158316637e-05, "loss": 2.1045, "step": 43050 }, { "epoch": 0.7, "learning_rate": 2.8534569138276558e-05, "loss": 2.0575, "step": 43060 }, { "epoch": 0.7, "learning_rate": 2.8529559118236475e-05, "loss": 2.0588, "step": 43070 }, { "epoch": 0.7, "learning_rate": 2.8524549098196396e-05, "loss": 1.9997, "step": 43080 }, { "epoch": 0.7, "learning_rate": 2.8519539078156316e-05, "loss": 2.0889, "step": 43090 }, { "epoch": 0.7, "learning_rate": 2.8514529058116234e-05, "loss": 2.026, "step": 43100 }, { "epoch": 0.7, "learning_rate": 2.8509519038076154e-05, "loss": 2.0721, "step": 43110 }, { "epoch": 0.7, "learning_rate": 2.8504509018036075e-05, "loss": 2.0728, "step": 43120 }, { "epoch": 0.7, "learning_rate": 2.8499498997995992e-05, "loss": 2.0389, "step": 43130 }, { "epoch": 0.7, "learning_rate": 2.8494488977955913e-05, "loss": 2.0487, "step": 43140 }, { "epoch": 0.71, "learning_rate": 2.8489478957915834e-05, "loss": 2.0543, "step": 43150 }, { "epoch": 0.71, "learning_rate": 2.848446893787575e-05, "loss": 2.0644, "step": 43160 }, { "epoch": 0.71, "learning_rate": 2.847945891783567e-05, "loss": 2.0372, "step": 43170 }, { "epoch": 0.71, "learning_rate": 2.8474448897795592e-05, "loss": 2.0542, "step": 43180 }, { "epoch": 0.71, "learning_rate": 2.846943887775551e-05, "loss": 2.0952, "step": 43190 }, { "epoch": 0.71, "learning_rate": 2.846442885771543e-05, "loss": 2.1084, "step": 43200 }, { "epoch": 0.71, "learning_rate": 2.845941883767535e-05, "loss": 2.1026, "step": 43210 }, { "epoch": 0.71, "learning_rate": 2.845440881763527e-05, "loss": 2.1011, "step": 43220 }, { "epoch": 0.71, "learning_rate": 2.844939879759519e-05, "loss": 2.0851, "step": 43230 }, { "epoch": 0.71, "learning_rate": 2.8444388777555116e-05, "loss": 2.0656, "step": 43240 }, { "epoch": 0.71, "learning_rate": 2.8439378757515033e-05, "loss": 2.071, "step": 43250 }, { "epoch": 0.71, "learning_rate": 2.8434368737474954e-05, "loss": 2.034, "step": 43260 }, { "epoch": 0.71, "learning_rate": 2.8429358717434874e-05, "loss": 2.0411, "step": 43270 }, { "epoch": 0.71, "learning_rate": 2.8424348697394792e-05, "loss": 2.0541, "step": 43280 }, { "epoch": 0.71, "learning_rate": 2.8419839679358718e-05, "loss": 2.0915, "step": 43290 }, { "epoch": 0.71, "learning_rate": 2.8414829659318636e-05, "loss": 2.1382, "step": 43300 }, { "epoch": 0.71, "learning_rate": 2.8409819639278556e-05, "loss": 2.0762, "step": 43310 }, { "epoch": 0.71, "learning_rate": 2.8404809619238477e-05, "loss": 2.0765, "step": 43320 }, { "epoch": 0.71, "learning_rate": 2.8399799599198394e-05, "loss": 2.093, "step": 43330 }, { "epoch": 0.71, "learning_rate": 2.839478957915832e-05, "loss": 2.0783, "step": 43340 }, { "epoch": 0.71, "learning_rate": 2.838977955911824e-05, "loss": 2.0376, "step": 43350 }, { "epoch": 0.71, "learning_rate": 2.838476953907816e-05, "loss": 2.0975, "step": 43360 }, { "epoch": 0.71, "learning_rate": 2.837975951903808e-05, "loss": 2.1159, "step": 43370 }, { "epoch": 0.71, "learning_rate": 2.8374749498997997e-05, "loss": 2.0749, "step": 43380 }, { "epoch": 0.71, "learning_rate": 2.8369739478957918e-05, "loss": 2.0291, "step": 43390 }, { "epoch": 0.71, "learning_rate": 2.836472945891784e-05, "loss": 2.0752, "step": 43400 }, { "epoch": 0.71, "learning_rate": 2.835971943887776e-05, "loss": 2.0691, "step": 43410 }, { "epoch": 0.71, "learning_rate": 2.8354709418837676e-05, "loss": 2.0472, "step": 43420 }, { "epoch": 0.71, "learning_rate": 2.8349699398797597e-05, "loss": 2.0857, "step": 43430 }, { "epoch": 0.71, "learning_rate": 2.8344689378757518e-05, "loss": 2.0631, "step": 43440 }, { "epoch": 0.71, "learning_rate": 2.8339679358717435e-05, "loss": 2.0923, "step": 43450 }, { "epoch": 0.71, "learning_rate": 2.8334669338677356e-05, "loss": 2.1074, "step": 43460 }, { "epoch": 0.71, "learning_rate": 2.8329659318637276e-05, "loss": 2.0931, "step": 43470 }, { "epoch": 0.71, "learning_rate": 2.8324649298597194e-05, "loss": 2.0283, "step": 43480 }, { "epoch": 0.71, "learning_rate": 2.8319639278557114e-05, "loss": 2.1054, "step": 43490 }, { "epoch": 0.71, "learning_rate": 2.8314629258517035e-05, "loss": 2.1, "step": 43500 }, { "epoch": 0.71, "learning_rate": 2.8309619238476952e-05, "loss": 2.0712, "step": 43510 }, { "epoch": 0.71, "learning_rate": 2.8304609218436873e-05, "loss": 2.0736, "step": 43520 }, { "epoch": 0.71, "learning_rate": 2.8299599198396793e-05, "loss": 2.1188, "step": 43530 }, { "epoch": 0.71, "learning_rate": 2.8294589178356717e-05, "loss": 2.1111, "step": 43540 }, { "epoch": 0.71, "learning_rate": 2.8289579158316638e-05, "loss": 2.0568, "step": 43550 }, { "epoch": 0.71, "learning_rate": 2.8284569138276555e-05, "loss": 2.096, "step": 43560 }, { "epoch": 0.71, "learning_rate": 2.8279559118236476e-05, "loss": 2.1145, "step": 43570 }, { "epoch": 0.71, "learning_rate": 2.8274549098196397e-05, "loss": 2.0679, "step": 43580 }, { "epoch": 0.71, "learning_rate": 2.8269539078156314e-05, "loss": 2.0422, "step": 43590 }, { "epoch": 0.71, "learning_rate": 2.8264529058116234e-05, "loss": 2.099, "step": 43600 }, { "epoch": 0.71, "learning_rate": 2.8259519038076155e-05, "loss": 2.0438, "step": 43610 }, { "epoch": 0.71, "learning_rate": 2.8254509018036072e-05, "loss": 2.086, "step": 43620 }, { "epoch": 0.71, "learning_rate": 2.8249498997995993e-05, "loss": 2.0464, "step": 43630 }, { "epoch": 0.71, "learning_rate": 2.8244488977955914e-05, "loss": 2.0528, "step": 43640 }, { "epoch": 0.71, "learning_rate": 2.823947895791583e-05, "loss": 2.0375, "step": 43650 }, { "epoch": 0.71, "learning_rate": 2.823446893787575e-05, "loss": 2.0324, "step": 43660 }, { "epoch": 0.71, "learning_rate": 2.8229458917835672e-05, "loss": 2.0449, "step": 43670 }, { "epoch": 0.71, "learning_rate": 2.8224448897795593e-05, "loss": 2.1077, "step": 43680 }, { "epoch": 0.71, "learning_rate": 2.821943887775551e-05, "loss": 2.0832, "step": 43690 }, { "epoch": 0.71, "learning_rate": 2.821442885771543e-05, "loss": 2.135, "step": 43700 }, { "epoch": 0.71, "learning_rate": 2.820941883767535e-05, "loss": 2.0581, "step": 43710 }, { "epoch": 0.71, "learning_rate": 2.820440881763527e-05, "loss": 2.0775, "step": 43720 }, { "epoch": 0.71, "learning_rate": 2.819939879759519e-05, "loss": 2.0584, "step": 43730 }, { "epoch": 0.71, "learning_rate": 2.8194388777555113e-05, "loss": 2.0865, "step": 43740 }, { "epoch": 0.71, "learning_rate": 2.8189378757515034e-05, "loss": 2.1281, "step": 43750 }, { "epoch": 0.72, "learning_rate": 2.8184368737474955e-05, "loss": 2.0802, "step": 43760 }, { "epoch": 0.72, "learning_rate": 2.8179358717434872e-05, "loss": 2.038, "step": 43770 }, { "epoch": 0.72, "learning_rate": 2.8174348697394792e-05, "loss": 2.1079, "step": 43780 }, { "epoch": 0.72, "learning_rate": 2.8169338677354713e-05, "loss": 2.0799, "step": 43790 }, { "epoch": 0.72, "learning_rate": 2.816432865731463e-05, "loss": 2.0693, "step": 43800 }, { "epoch": 0.72, "learning_rate": 2.815931863727455e-05, "loss": 2.0475, "step": 43810 }, { "epoch": 0.72, "learning_rate": 2.815430861723447e-05, "loss": 2.0867, "step": 43820 }, { "epoch": 0.72, "learning_rate": 2.814929859719439e-05, "loss": 2.1012, "step": 43830 }, { "epoch": 0.72, "learning_rate": 2.814428857715431e-05, "loss": 2.0766, "step": 43840 }, { "epoch": 0.72, "learning_rate": 2.813927855711423e-05, "loss": 2.0944, "step": 43850 }, { "epoch": 0.72, "learning_rate": 2.8134268537074147e-05, "loss": 2.0437, "step": 43860 }, { "epoch": 0.72, "learning_rate": 2.8129258517034068e-05, "loss": 2.0646, "step": 43870 }, { "epoch": 0.72, "learning_rate": 2.812424849699399e-05, "loss": 2.1342, "step": 43880 }, { "epoch": 0.72, "learning_rate": 2.8119238476953906e-05, "loss": 2.0935, "step": 43890 }, { "epoch": 0.72, "learning_rate": 2.8114228456913827e-05, "loss": 2.0866, "step": 43900 }, { "epoch": 0.72, "learning_rate": 2.8109218436873747e-05, "loss": 2.0534, "step": 43910 }, { "epoch": 0.72, "learning_rate": 2.8104208416833664e-05, "loss": 2.0868, "step": 43920 }, { "epoch": 0.72, "learning_rate": 2.8099198396793592e-05, "loss": 2.0393, "step": 43930 }, { "epoch": 0.72, "learning_rate": 2.809418837675351e-05, "loss": 2.0784, "step": 43940 }, { "epoch": 0.72, "learning_rate": 2.808917835671343e-05, "loss": 2.0273, "step": 43950 }, { "epoch": 0.72, "learning_rate": 2.808416833667335e-05, "loss": 2.0463, "step": 43960 }, { "epoch": 0.72, "learning_rate": 2.807915831663327e-05, "loss": 2.0625, "step": 43970 }, { "epoch": 0.72, "learning_rate": 2.807414829659319e-05, "loss": 2.0613, "step": 43980 }, { "epoch": 0.72, "learning_rate": 2.806913827655311e-05, "loss": 2.1092, "step": 43990 }, { "epoch": 0.72, "learning_rate": 2.806412825651303e-05, "loss": 2.0848, "step": 44000 }, { "epoch": 0.72, "eval_loss": 2.050408363342285, "eval_mean_f1": 0.6552984245746374, "eval_rouge1_f1": 0.7137089257506426, "eval_rouge1_precision": 0.8254276052834904, "eval_rouge1_recall": 0.660504262045914, "eval_rouge2_f1": 0.5699500361788316, "eval_rouge2_precision": 0.663345577084591, "eval_rouge2_recall": 0.5273972497255643, "eval_rougeL_f1": 0.6822363117944379, "eval_rougeL_precision": 0.7880638497818814, "eval_rougeL_recall": 0.6323582140983954, "eval_runtime": 65.1279, "eval_samples_per_second": 15.723, "eval_steps_per_second": 1.965, "step": 44000 }, { "epoch": 0.72, "learning_rate": 2.8059118236472947e-05, "loss": 2.0651, "step": 44010 }, { "epoch": 0.72, "learning_rate": 2.8054108216432867e-05, "loss": 2.0478, "step": 44020 }, { "epoch": 0.72, "learning_rate": 2.8049098196392788e-05, "loss": 2.0606, "step": 44030 }, { "epoch": 0.72, "learning_rate": 2.8044088176352705e-05, "loss": 2.1041, "step": 44040 }, { "epoch": 0.72, "learning_rate": 2.8039078156312626e-05, "loss": 2.0535, "step": 44050 }, { "epoch": 0.72, "learning_rate": 2.8034068136272547e-05, "loss": 2.13, "step": 44060 }, { "epoch": 0.72, "learning_rate": 2.8029058116232464e-05, "loss": 2.0452, "step": 44070 }, { "epoch": 0.72, "learning_rate": 2.8024048096192385e-05, "loss": 2.0634, "step": 44080 }, { "epoch": 0.72, "learning_rate": 2.8019038076152305e-05, "loss": 2.0888, "step": 44090 }, { "epoch": 0.72, "learning_rate": 2.8014028056112222e-05, "loss": 2.0529, "step": 44100 }, { "epoch": 0.72, "learning_rate": 2.8009018036072143e-05, "loss": 2.0716, "step": 44110 }, { "epoch": 0.72, "learning_rate": 2.8004008016032064e-05, "loss": 2.0666, "step": 44120 }, { "epoch": 0.72, "learning_rate": 2.7998997995991988e-05, "loss": 2.0478, "step": 44130 }, { "epoch": 0.72, "learning_rate": 2.799398797595191e-05, "loss": 2.0586, "step": 44140 }, { "epoch": 0.72, "learning_rate": 2.7988977955911826e-05, "loss": 2.0786, "step": 44150 }, { "epoch": 0.72, "learning_rate": 2.7983967935871746e-05, "loss": 2.094, "step": 44160 }, { "epoch": 0.72, "learning_rate": 2.7978957915831667e-05, "loss": 2.0948, "step": 44170 }, { "epoch": 0.72, "learning_rate": 2.7973947895791584e-05, "loss": 2.0874, "step": 44180 }, { "epoch": 0.72, "learning_rate": 2.7968937875751505e-05, "loss": 2.033, "step": 44190 }, { "epoch": 0.72, "learning_rate": 2.7963927855711425e-05, "loss": 2.0547, "step": 44200 }, { "epoch": 0.72, "learning_rate": 2.7958917835671343e-05, "loss": 2.1057, "step": 44210 }, { "epoch": 0.72, "learning_rate": 2.7953907815631263e-05, "loss": 2.042, "step": 44220 }, { "epoch": 0.72, "learning_rate": 2.7948897795591184e-05, "loss": 2.0281, "step": 44230 }, { "epoch": 0.72, "learning_rate": 2.7943887775551105e-05, "loss": 2.0596, "step": 44240 }, { "epoch": 0.72, "learning_rate": 2.7938877755511022e-05, "loss": 2.0601, "step": 44250 }, { "epoch": 0.72, "learning_rate": 2.7933867735470943e-05, "loss": 2.0654, "step": 44260 }, { "epoch": 0.72, "learning_rate": 2.7928857715430863e-05, "loss": 2.0989, "step": 44270 }, { "epoch": 0.72, "learning_rate": 2.792384769539078e-05, "loss": 2.0628, "step": 44280 }, { "epoch": 0.72, "learning_rate": 2.79188376753507e-05, "loss": 2.0754, "step": 44290 }, { "epoch": 0.72, "learning_rate": 2.7913827655310622e-05, "loss": 2.0912, "step": 44300 }, { "epoch": 0.72, "learning_rate": 2.790881763527054e-05, "loss": 2.0437, "step": 44310 }, { "epoch": 0.72, "learning_rate": 2.790380761523046e-05, "loss": 2.0916, "step": 44320 }, { "epoch": 0.72, "learning_rate": 2.7898797595190384e-05, "loss": 2.0947, "step": 44330 }, { "epoch": 0.72, "learning_rate": 2.7893787575150304e-05, "loss": 2.0628, "step": 44340 }, { "epoch": 0.72, "learning_rate": 2.7888777555110225e-05, "loss": 2.0848, "step": 44350 }, { "epoch": 0.72, "learning_rate": 2.7883767535070142e-05, "loss": 2.0874, "step": 44360 }, { "epoch": 0.72, "learning_rate": 2.7878757515030063e-05, "loss": 2.0661, "step": 44370 }, { "epoch": 0.73, "learning_rate": 2.7873747494989983e-05, "loss": 2.1148, "step": 44380 }, { "epoch": 0.73, "learning_rate": 2.78687374749499e-05, "loss": 2.0656, "step": 44390 }, { "epoch": 0.73, "learning_rate": 2.786372745490982e-05, "loss": 2.0835, "step": 44400 }, { "epoch": 0.73, "learning_rate": 2.7858717434869742e-05, "loss": 2.1143, "step": 44410 }, { "epoch": 0.73, "learning_rate": 2.785370741482966e-05, "loss": 2.0972, "step": 44420 }, { "epoch": 0.73, "learning_rate": 2.784869739478958e-05, "loss": 2.0772, "step": 44430 }, { "epoch": 0.73, "learning_rate": 2.78436873747495e-05, "loss": 2.1125, "step": 44440 }, { "epoch": 0.73, "learning_rate": 2.7838677354709418e-05, "loss": 2.0629, "step": 44450 }, { "epoch": 0.73, "learning_rate": 2.783366733466934e-05, "loss": 2.128, "step": 44460 }, { "epoch": 0.73, "learning_rate": 2.782865731462926e-05, "loss": 2.0905, "step": 44470 }, { "epoch": 0.73, "learning_rate": 2.7823647294589176e-05, "loss": 2.1103, "step": 44480 }, { "epoch": 0.73, "learning_rate": 2.7818637274549097e-05, "loss": 2.0806, "step": 44490 }, { "epoch": 0.73, "learning_rate": 2.7813627254509018e-05, "loss": 2.0914, "step": 44500 }, { "epoch": 0.73, "learning_rate": 2.7808617234468938e-05, "loss": 2.0441, "step": 44510 }, { "epoch": 0.73, "learning_rate": 2.7803607214428862e-05, "loss": 2.0226, "step": 44520 }, { "epoch": 0.73, "learning_rate": 2.7798597194388783e-05, "loss": 2.0709, "step": 44530 }, { "epoch": 0.73, "learning_rate": 2.77935871743487e-05, "loss": 2.0339, "step": 44540 }, { "epoch": 0.73, "learning_rate": 2.778857715430862e-05, "loss": 2.0929, "step": 44550 }, { "epoch": 0.73, "learning_rate": 2.778356713426854e-05, "loss": 2.1084, "step": 44560 }, { "epoch": 0.73, "learning_rate": 2.777855711422846e-05, "loss": 2.1092, "step": 44570 }, { "epoch": 0.73, "learning_rate": 2.777354709418838e-05, "loss": 2.0974, "step": 44580 }, { "epoch": 0.73, "learning_rate": 2.77685370741483e-05, "loss": 2.0745, "step": 44590 }, { "epoch": 0.73, "learning_rate": 2.7763527054108217e-05, "loss": 2.0612, "step": 44600 }, { "epoch": 0.73, "learning_rate": 2.7758517034068138e-05, "loss": 2.092, "step": 44610 }, { "epoch": 0.73, "learning_rate": 2.775350701402806e-05, "loss": 2.0714, "step": 44620 }, { "epoch": 0.73, "learning_rate": 2.7748496993987976e-05, "loss": 2.0801, "step": 44630 }, { "epoch": 0.73, "learning_rate": 2.7743486973947896e-05, "loss": 2.0836, "step": 44640 }, { "epoch": 0.73, "learning_rate": 2.7738476953907817e-05, "loss": 2.0639, "step": 44650 }, { "epoch": 0.73, "learning_rate": 2.7733466933867734e-05, "loss": 2.0769, "step": 44660 }, { "epoch": 0.73, "learning_rate": 2.7728456913827655e-05, "loss": 2.0989, "step": 44670 }, { "epoch": 0.73, "learning_rate": 2.7723446893787576e-05, "loss": 2.0061, "step": 44680 }, { "epoch": 0.73, "learning_rate": 2.7718436873747493e-05, "loss": 2.0655, "step": 44690 }, { "epoch": 0.73, "learning_rate": 2.7713426853707414e-05, "loss": 2.0952, "step": 44700 }, { "epoch": 0.73, "learning_rate": 2.7708416833667334e-05, "loss": 2.0541, "step": 44710 }, { "epoch": 0.73, "learning_rate": 2.7703406813627258e-05, "loss": 2.0665, "step": 44720 }, { "epoch": 0.73, "learning_rate": 2.769839679358718e-05, "loss": 2.0375, "step": 44730 }, { "epoch": 0.73, "learning_rate": 2.7693386773547096e-05, "loss": 2.0903, "step": 44740 }, { "epoch": 0.73, "learning_rate": 2.7688376753507017e-05, "loss": 2.0593, "step": 44750 }, { "epoch": 0.73, "learning_rate": 2.7683366733466937e-05, "loss": 2.0918, "step": 44760 }, { "epoch": 0.73, "learning_rate": 2.7678356713426855e-05, "loss": 2.0839, "step": 44770 }, { "epoch": 0.73, "learning_rate": 2.7673346693386775e-05, "loss": 2.0189, "step": 44780 }, { "epoch": 0.73, "learning_rate": 2.7668336673346696e-05, "loss": 2.0703, "step": 44790 }, { "epoch": 0.73, "learning_rate": 2.7663326653306617e-05, "loss": 2.0897, "step": 44800 }, { "epoch": 0.73, "learning_rate": 2.7658316633266534e-05, "loss": 2.0567, "step": 44810 }, { "epoch": 0.73, "learning_rate": 2.7653306613226454e-05, "loss": 2.0517, "step": 44820 }, { "epoch": 0.73, "learning_rate": 2.7648296593186375e-05, "loss": 2.0277, "step": 44830 }, { "epoch": 0.73, "learning_rate": 2.7643286573146292e-05, "loss": 2.0433, "step": 44840 }, { "epoch": 0.73, "learning_rate": 2.7638276553106213e-05, "loss": 2.0865, "step": 44850 }, { "epoch": 0.73, "learning_rate": 2.7633266533066134e-05, "loss": 2.0262, "step": 44860 }, { "epoch": 0.73, "learning_rate": 2.762825651302605e-05, "loss": 2.1117, "step": 44870 }, { "epoch": 0.73, "learning_rate": 2.762324649298597e-05, "loss": 2.0972, "step": 44880 }, { "epoch": 0.73, "learning_rate": 2.7618236472945892e-05, "loss": 2.0835, "step": 44890 }, { "epoch": 0.73, "learning_rate": 2.761322645290581e-05, "loss": 2.0693, "step": 44900 }, { "epoch": 0.73, "learning_rate": 2.7608216432865737e-05, "loss": 2.0713, "step": 44910 }, { "epoch": 0.73, "learning_rate": 2.7603206412825654e-05, "loss": 2.0709, "step": 44920 }, { "epoch": 0.73, "learning_rate": 2.7598196392785575e-05, "loss": 2.1231, "step": 44930 }, { "epoch": 0.73, "learning_rate": 2.7593186372745495e-05, "loss": 2.0744, "step": 44940 }, { "epoch": 0.73, "learning_rate": 2.7588176352705413e-05, "loss": 2.0858, "step": 44950 }, { "epoch": 0.73, "learning_rate": 2.7583166332665333e-05, "loss": 2.0239, "step": 44960 }, { "epoch": 0.73, "learning_rate": 2.7578156312625254e-05, "loss": 2.0563, "step": 44970 }, { "epoch": 0.73, "learning_rate": 2.757314629258517e-05, "loss": 2.0632, "step": 44980 }, { "epoch": 0.74, "learning_rate": 2.7568136272545092e-05, "loss": 2.0825, "step": 44990 }, { "epoch": 0.74, "learning_rate": 2.7563126252505012e-05, "loss": 2.0359, "step": 45000 }, { "epoch": 0.74, "eval_loss": 2.0516469478607178, "eval_mean_f1": 0.6512713423145312, "eval_rouge1_f1": 0.7098663499200935, "eval_rouge1_precision": 0.8213687169795709, "eval_rouge1_recall": 0.6577383982554998, "eval_rouge2_f1": 0.566077090800365, "eval_rouge2_precision": 0.6570118263355567, "eval_rouge2_recall": 0.5250170299841488, "eval_rougeL_f1": 0.6778705862231352, "eval_rougeL_precision": 0.781780139228942, "eval_rougeL_recall": 0.6291960617220494, "eval_runtime": 62.1329, "eval_samples_per_second": 16.481, "eval_steps_per_second": 2.06, "step": 45000 }, { "epoch": 0.74, "learning_rate": 2.755811623246493e-05, "loss": 2.0736, "step": 45010 }, { "epoch": 0.74, "learning_rate": 2.755310621242485e-05, "loss": 2.0552, "step": 45020 }, { "epoch": 0.74, "learning_rate": 2.754809619238477e-05, "loss": 2.1301, "step": 45030 }, { "epoch": 0.74, "learning_rate": 2.7543086172344688e-05, "loss": 2.0862, "step": 45040 }, { "epoch": 0.74, "learning_rate": 2.753807615230461e-05, "loss": 2.0584, "step": 45050 }, { "epoch": 0.74, "learning_rate": 2.753306613226453e-05, "loss": 2.0809, "step": 45060 }, { "epoch": 0.74, "learning_rate": 2.752805611222445e-05, "loss": 2.018, "step": 45070 }, { "epoch": 0.74, "learning_rate": 2.7523046092184367e-05, "loss": 2.0817, "step": 45080 }, { "epoch": 0.74, "learning_rate": 2.7518036072144288e-05, "loss": 2.0555, "step": 45090 }, { "epoch": 0.74, "learning_rate": 2.751302605210421e-05, "loss": 2.0433, "step": 45100 }, { "epoch": 0.74, "learning_rate": 2.7508016032064133e-05, "loss": 2.0341, "step": 45110 }, { "epoch": 0.74, "learning_rate": 2.7503006012024053e-05, "loss": 2.0724, "step": 45120 }, { "epoch": 0.74, "learning_rate": 2.749799599198397e-05, "loss": 2.1137, "step": 45130 }, { "epoch": 0.74, "learning_rate": 2.749298597194389e-05, "loss": 2.0775, "step": 45140 }, { "epoch": 0.74, "learning_rate": 2.7487975951903812e-05, "loss": 2.0559, "step": 45150 }, { "epoch": 0.74, "learning_rate": 2.748296593186373e-05, "loss": 2.0772, "step": 45160 }, { "epoch": 0.74, "learning_rate": 2.747795591182365e-05, "loss": 2.0821, "step": 45170 }, { "epoch": 0.74, "learning_rate": 2.747294589178357e-05, "loss": 2.0392, "step": 45180 }, { "epoch": 0.74, "learning_rate": 2.7467935871743488e-05, "loss": 2.0769, "step": 45190 }, { "epoch": 0.74, "learning_rate": 2.7462925851703408e-05, "loss": 2.0665, "step": 45200 }, { "epoch": 0.74, "learning_rate": 2.745791583166333e-05, "loss": 2.0592, "step": 45210 }, { "epoch": 0.74, "learning_rate": 2.7452905811623246e-05, "loss": 2.1075, "step": 45220 }, { "epoch": 0.74, "learning_rate": 2.7447895791583167e-05, "loss": 2.0325, "step": 45230 }, { "epoch": 0.74, "learning_rate": 2.7442885771543087e-05, "loss": 2.0759, "step": 45240 }, { "epoch": 0.74, "learning_rate": 2.7437875751503005e-05, "loss": 2.0679, "step": 45250 }, { "epoch": 0.74, "learning_rate": 2.7432865731462925e-05, "loss": 2.0409, "step": 45260 }, { "epoch": 0.74, "learning_rate": 2.7427855711422846e-05, "loss": 2.1031, "step": 45270 }, { "epoch": 0.74, "learning_rate": 2.7422845691382763e-05, "loss": 2.0567, "step": 45280 }, { "epoch": 0.74, "learning_rate": 2.7417835671342684e-05, "loss": 2.0781, "step": 45290 }, { "epoch": 0.74, "learning_rate": 2.7412825651302605e-05, "loss": 2.0643, "step": 45300 }, { "epoch": 0.74, "learning_rate": 2.740781563126253e-05, "loss": 2.0624, "step": 45310 }, { "epoch": 0.74, "learning_rate": 2.740280561122245e-05, "loss": 2.0246, "step": 45320 }, { "epoch": 0.74, "learning_rate": 2.7397795591182366e-05, "loss": 2.0515, "step": 45330 }, { "epoch": 0.74, "learning_rate": 2.7392785571142287e-05, "loss": 2.0872, "step": 45340 }, { "epoch": 0.74, "learning_rate": 2.7387775551102208e-05, "loss": 2.0591, "step": 45350 }, { "epoch": 0.74, "learning_rate": 2.738276553106213e-05, "loss": 2.0605, "step": 45360 }, { "epoch": 0.74, "learning_rate": 2.7377755511022046e-05, "loss": 2.0611, "step": 45370 }, { "epoch": 0.74, "learning_rate": 2.7372745490981966e-05, "loss": 2.0861, "step": 45380 }, { "epoch": 0.74, "learning_rate": 2.7367735470941887e-05, "loss": 2.0676, "step": 45390 }, { "epoch": 0.74, "learning_rate": 2.7362725450901804e-05, "loss": 2.0987, "step": 45400 }, { "epoch": 0.74, "learning_rate": 2.7357715430861725e-05, "loss": 2.0246, "step": 45410 }, { "epoch": 0.74, "learning_rate": 2.7352705410821645e-05, "loss": 2.0689, "step": 45420 }, { "epoch": 0.74, "learning_rate": 2.7347695390781563e-05, "loss": 2.0309, "step": 45430 }, { "epoch": 0.74, "learning_rate": 2.7342685370741483e-05, "loss": 2.062, "step": 45440 }, { "epoch": 0.74, "learning_rate": 2.7337675350701404e-05, "loss": 2.1397, "step": 45450 }, { "epoch": 0.74, "learning_rate": 2.733266533066132e-05, "loss": 2.0681, "step": 45460 }, { "epoch": 0.74, "learning_rate": 2.7327655310621242e-05, "loss": 2.0375, "step": 45470 }, { "epoch": 0.74, "learning_rate": 2.7322645290581163e-05, "loss": 2.0528, "step": 45480 }, { "epoch": 0.74, "learning_rate": 2.731763527054108e-05, "loss": 2.0389, "step": 45490 }, { "epoch": 0.74, "learning_rate": 2.7312625250501007e-05, "loss": 2.0751, "step": 45500 }, { "epoch": 0.74, "learning_rate": 2.7307615230460924e-05, "loss": 2.0248, "step": 45510 }, { "epoch": 0.74, "learning_rate": 2.7302605210420845e-05, "loss": 2.0741, "step": 45520 }, { "epoch": 0.74, "learning_rate": 2.7297595190380766e-05, "loss": 2.1086, "step": 45530 }, { "epoch": 0.74, "learning_rate": 2.7292585170340683e-05, "loss": 2.0596, "step": 45540 }, { "epoch": 0.74, "learning_rate": 2.7287575150300604e-05, "loss": 2.1011, "step": 45550 }, { "epoch": 0.74, "learning_rate": 2.7282565130260524e-05, "loss": 2.0388, "step": 45560 }, { "epoch": 0.74, "learning_rate": 2.727755511022044e-05, "loss": 2.1162, "step": 45570 }, { "epoch": 0.74, "learning_rate": 2.7272545090180362e-05, "loss": 2.0538, "step": 45580 }, { "epoch": 0.74, "learning_rate": 2.7267535070140283e-05, "loss": 2.0674, "step": 45590 }, { "epoch": 0.75, "learning_rate": 2.72625250501002e-05, "loss": 2.0439, "step": 45600 }, { "epoch": 0.75, "learning_rate": 2.725751503006012e-05, "loss": 2.0762, "step": 45610 }, { "epoch": 0.75, "learning_rate": 2.725250501002004e-05, "loss": 2.0593, "step": 45620 }, { "epoch": 0.75, "learning_rate": 2.7247494989979962e-05, "loss": 2.0849, "step": 45630 }, { "epoch": 0.75, "learning_rate": 2.724248496993988e-05, "loss": 2.047, "step": 45640 }, { "epoch": 0.75, "learning_rate": 2.72374749498998e-05, "loss": 2.0873, "step": 45650 }, { "epoch": 0.75, "learning_rate": 2.723246492985972e-05, "loss": 2.0658, "step": 45660 }, { "epoch": 0.75, "learning_rate": 2.7227454909819638e-05, "loss": 2.1228, "step": 45670 }, { "epoch": 0.75, "learning_rate": 2.722244488977956e-05, "loss": 2.0547, "step": 45680 }, { "epoch": 0.75, "learning_rate": 2.721743486973948e-05, "loss": 2.1203, "step": 45690 }, { "epoch": 0.75, "learning_rate": 2.7212424849699403e-05, "loss": 2.0715, "step": 45700 }, { "epoch": 0.75, "learning_rate": 2.7207414829659324e-05, "loss": 2.0817, "step": 45710 }, { "epoch": 0.75, "learning_rate": 2.720240480961924e-05, "loss": 2.0469, "step": 45720 }, { "epoch": 0.75, "learning_rate": 2.719739478957916e-05, "loss": 2.0793, "step": 45730 }, { "epoch": 0.75, "learning_rate": 2.7192384769539082e-05, "loss": 2.0911, "step": 45740 }, { "epoch": 0.75, "learning_rate": 2.7187374749499e-05, "loss": 2.0505, "step": 45750 }, { "epoch": 0.75, "learning_rate": 2.718236472945892e-05, "loss": 2.0444, "step": 45760 }, { "epoch": 0.75, "learning_rate": 2.717735470941884e-05, "loss": 2.0863, "step": 45770 }, { "epoch": 0.75, "learning_rate": 2.7172344689378758e-05, "loss": 2.0865, "step": 45780 }, { "epoch": 0.75, "learning_rate": 2.716733466933868e-05, "loss": 2.0814, "step": 45790 }, { "epoch": 0.75, "learning_rate": 2.71623246492986e-05, "loss": 2.0602, "step": 45800 }, { "epoch": 0.75, "learning_rate": 2.7157314629258517e-05, "loss": 2.1011, "step": 45810 }, { "epoch": 0.75, "learning_rate": 2.7152304609218437e-05, "loss": 2.0948, "step": 45820 }, { "epoch": 0.75, "learning_rate": 2.7147294589178358e-05, "loss": 2.0546, "step": 45830 }, { "epoch": 0.75, "learning_rate": 2.7142284569138275e-05, "loss": 2.088, "step": 45840 }, { "epoch": 0.75, "learning_rate": 2.7137274549098196e-05, "loss": 2.0644, "step": 45850 }, { "epoch": 0.75, "learning_rate": 2.7132264529058116e-05, "loss": 2.0768, "step": 45860 }, { "epoch": 0.75, "learning_rate": 2.7127254509018034e-05, "loss": 2.078, "step": 45870 }, { "epoch": 0.75, "learning_rate": 2.7122244488977954e-05, "loss": 2.0854, "step": 45880 }, { "epoch": 0.75, "learning_rate": 2.7117234468937875e-05, "loss": 2.0583, "step": 45890 }, { "epoch": 0.75, "learning_rate": 2.71122244488978e-05, "loss": 2.0487, "step": 45900 }, { "epoch": 0.75, "learning_rate": 2.710721442885772e-05, "loss": 2.061, "step": 45910 }, { "epoch": 0.75, "learning_rate": 2.7102204408817637e-05, "loss": 2.0992, "step": 45920 }, { "epoch": 0.75, "learning_rate": 2.7097194388777558e-05, "loss": 2.0607, "step": 45930 }, { "epoch": 0.75, "learning_rate": 2.7092184368737478e-05, "loss": 2.0651, "step": 45940 }, { "epoch": 0.75, "learning_rate": 2.70871743486974e-05, "loss": 2.048, "step": 45950 }, { "epoch": 0.75, "learning_rate": 2.7082164328657316e-05, "loss": 2.0345, "step": 45960 }, { "epoch": 0.75, "learning_rate": 2.7077154308617237e-05, "loss": 2.1368, "step": 45970 }, { "epoch": 0.75, "learning_rate": 2.7072144288577157e-05, "loss": 2.0637, "step": 45980 }, { "epoch": 0.75, "learning_rate": 2.7067134268537075e-05, "loss": 2.0564, "step": 45990 }, { "epoch": 0.75, "learning_rate": 2.7062124248496995e-05, "loss": 2.0556, "step": 46000 }, { "epoch": 0.75, "eval_loss": 2.0515968799591064, "eval_mean_f1": 0.6531848532603469, "eval_rouge1_f1": 0.7129995900945297, "eval_rouge1_precision": 0.8234628356494016, "eval_rouge1_recall": 0.6614655259125168, "eval_rouge2_f1": 0.566538417420368, "eval_rouge2_precision": 0.6582944724546286, "eval_rouge2_recall": 0.5257397243729645, "eval_rougeL_f1": 0.6800165522661432, "eval_rougeL_precision": 0.7828863261448133, "eval_rougeL_recall": 0.6323308379042885, "eval_runtime": 63.4965, "eval_samples_per_second": 16.127, "eval_steps_per_second": 2.016, "step": 46000 }, { "epoch": 0.75, "learning_rate": 2.7057114228456916e-05, "loss": 2.0548, "step": 46010 }, { "epoch": 0.75, "learning_rate": 2.7052104208416833e-05, "loss": 2.0239, "step": 46020 }, { "epoch": 0.75, "learning_rate": 2.7047094188376754e-05, "loss": 2.0681, "step": 46030 }, { "epoch": 0.75, "learning_rate": 2.7042084168336674e-05, "loss": 2.1066, "step": 46040 }, { "epoch": 0.75, "learning_rate": 2.703707414829659e-05, "loss": 2.09, "step": 46050 }, { "epoch": 0.75, "learning_rate": 2.7032064128256512e-05, "loss": 2.0479, "step": 46060 }, { "epoch": 0.75, "learning_rate": 2.7027054108216433e-05, "loss": 2.0609, "step": 46070 }, { "epoch": 0.75, "learning_rate": 2.702204408817635e-05, "loss": 2.0804, "step": 46080 }, { "epoch": 0.75, "learning_rate": 2.7017034068136278e-05, "loss": 2.0247, "step": 46090 }, { "epoch": 0.75, "learning_rate": 2.7012024048096195e-05, "loss": 2.0653, "step": 46100 }, { "epoch": 0.75, "learning_rate": 2.7007014028056116e-05, "loss": 2.0768, "step": 46110 }, { "epoch": 0.75, "learning_rate": 2.7002004008016036e-05, "loss": 2.0206, "step": 46120 }, { "epoch": 0.75, "learning_rate": 2.6996993987975953e-05, "loss": 2.0983, "step": 46130 }, { "epoch": 0.75, "learning_rate": 2.6991983967935874e-05, "loss": 2.0088, "step": 46140 }, { "epoch": 0.75, "learning_rate": 2.6986973947895795e-05, "loss": 2.0884, "step": 46150 }, { "epoch": 0.75, "learning_rate": 2.6981963927855712e-05, "loss": 2.0767, "step": 46160 }, { "epoch": 0.75, "learning_rate": 2.6976953907815633e-05, "loss": 2.042, "step": 46170 }, { "epoch": 0.75, "learning_rate": 2.6971943887775553e-05, "loss": 2.087, "step": 46180 }, { "epoch": 0.75, "learning_rate": 2.696693386773547e-05, "loss": 2.0841, "step": 46190 }, { "epoch": 0.75, "learning_rate": 2.696192384769539e-05, "loss": 2.0891, "step": 46200 }, { "epoch": 0.76, "learning_rate": 2.6956913827655312e-05, "loss": 2.0542, "step": 46210 }, { "epoch": 0.76, "learning_rate": 2.6951903807615232e-05, "loss": 2.0538, "step": 46220 }, { "epoch": 0.76, "learning_rate": 2.694689378757515e-05, "loss": 2.0348, "step": 46230 }, { "epoch": 0.76, "learning_rate": 2.694188376753507e-05, "loss": 2.0771, "step": 46240 }, { "epoch": 0.76, "learning_rate": 2.693687374749499e-05, "loss": 2.1046, "step": 46250 }, { "epoch": 0.76, "learning_rate": 2.6931863727454908e-05, "loss": 2.0791, "step": 46260 }, { "epoch": 0.76, "learning_rate": 2.692685370741483e-05, "loss": 2.1153, "step": 46270 }, { "epoch": 0.76, "learning_rate": 2.692184368737475e-05, "loss": 2.0696, "step": 46280 }, { "epoch": 0.76, "learning_rate": 2.6916833667334674e-05, "loss": 2.1122, "step": 46290 }, { "epoch": 0.76, "learning_rate": 2.6911823647294594e-05, "loss": 2.0564, "step": 46300 }, { "epoch": 0.76, "learning_rate": 2.690681362725451e-05, "loss": 2.0306, "step": 46310 }, { "epoch": 0.76, "learning_rate": 2.6901803607214432e-05, "loss": 2.0714, "step": 46320 }, { "epoch": 0.76, "learning_rate": 2.6896793587174353e-05, "loss": 2.0871, "step": 46330 }, { "epoch": 0.76, "learning_rate": 2.689178356713427e-05, "loss": 2.0661, "step": 46340 }, { "epoch": 0.76, "learning_rate": 2.688677354709419e-05, "loss": 2.0547, "step": 46350 }, { "epoch": 0.76, "learning_rate": 2.688176352705411e-05, "loss": 2.0397, "step": 46360 }, { "epoch": 0.76, "learning_rate": 2.687675350701403e-05, "loss": 2.0635, "step": 46370 }, { "epoch": 0.76, "learning_rate": 2.687174348697395e-05, "loss": 2.0559, "step": 46380 }, { "epoch": 0.76, "learning_rate": 2.686673346693387e-05, "loss": 2.0973, "step": 46390 }, { "epoch": 0.76, "learning_rate": 2.6861723446893787e-05, "loss": 2.0611, "step": 46400 }, { "epoch": 0.76, "learning_rate": 2.6856713426853708e-05, "loss": 2.0627, "step": 46410 }, { "epoch": 0.76, "learning_rate": 2.6851703406813628e-05, "loss": 2.0366, "step": 46420 }, { "epoch": 0.76, "learning_rate": 2.6846693386773546e-05, "loss": 2.1085, "step": 46430 }, { "epoch": 0.76, "learning_rate": 2.6841683366733466e-05, "loss": 2.0917, "step": 46440 }, { "epoch": 0.76, "learning_rate": 2.6836673346693387e-05, "loss": 2.0403, "step": 46450 }, { "epoch": 0.76, "learning_rate": 2.6831663326653304e-05, "loss": 2.0649, "step": 46460 }, { "epoch": 0.76, "learning_rate": 2.6826653306613225e-05, "loss": 2.0909, "step": 46470 }, { "epoch": 0.76, "learning_rate": 2.6821643286573145e-05, "loss": 2.0855, "step": 46480 }, { "epoch": 0.76, "learning_rate": 2.681663326653307e-05, "loss": 2.0556, "step": 46490 }, { "epoch": 0.76, "learning_rate": 2.681162324649299e-05, "loss": 2.0764, "step": 46500 }, { "epoch": 0.76, "learning_rate": 2.680661322645291e-05, "loss": 2.0891, "step": 46510 }, { "epoch": 0.76, "learning_rate": 2.6801603206412828e-05, "loss": 2.0726, "step": 46520 }, { "epoch": 0.76, "learning_rate": 2.679659318637275e-05, "loss": 2.0815, "step": 46530 }, { "epoch": 0.76, "learning_rate": 2.679158316633267e-05, "loss": 2.0909, "step": 46540 }, { "epoch": 0.76, "learning_rate": 2.6786573146292586e-05, "loss": 2.1129, "step": 46550 }, { "epoch": 0.76, "learning_rate": 2.6781563126252507e-05, "loss": 2.058, "step": 46560 }, { "epoch": 0.76, "learning_rate": 2.6776553106212428e-05, "loss": 2.0302, "step": 46570 }, { "epoch": 0.76, "learning_rate": 2.6771543086172345e-05, "loss": 2.0958, "step": 46580 }, { "epoch": 0.76, "learning_rate": 2.6766533066132266e-05, "loss": 2.0946, "step": 46590 }, { "epoch": 0.76, "learning_rate": 2.6761523046092186e-05, "loss": 2.0682, "step": 46600 }, { "epoch": 0.76, "learning_rate": 2.6756513026052104e-05, "loss": 2.0602, "step": 46610 }, { "epoch": 0.76, "learning_rate": 2.6751503006012024e-05, "loss": 2.0769, "step": 46620 }, { "epoch": 0.76, "learning_rate": 2.6746492985971945e-05, "loss": 2.1162, "step": 46630 }, { "epoch": 0.76, "learning_rate": 2.6741482965931862e-05, "loss": 2.0885, "step": 46640 }, { "epoch": 0.76, "learning_rate": 2.6736472945891783e-05, "loss": 2.0634, "step": 46650 }, { "epoch": 0.76, "learning_rate": 2.6731462925851703e-05, "loss": 2.0584, "step": 46660 }, { "epoch": 0.76, "learning_rate": 2.672645290581162e-05, "loss": 2.0657, "step": 46670 }, { "epoch": 0.76, "learning_rate": 2.6721442885771548e-05, "loss": 2.0773, "step": 46680 }, { "epoch": 0.76, "learning_rate": 2.6716432865731465e-05, "loss": 2.1203, "step": 46690 }, { "epoch": 0.76, "learning_rate": 2.6711422845691386e-05, "loss": 2.0606, "step": 46700 }, { "epoch": 0.76, "learning_rate": 2.6706412825651307e-05, "loss": 2.0157, "step": 46710 }, { "epoch": 0.76, "learning_rate": 2.6701402805611224e-05, "loss": 2.1231, "step": 46720 }, { "epoch": 0.76, "learning_rate": 2.6696392785571144e-05, "loss": 2.0751, "step": 46730 }, { "epoch": 0.76, "learning_rate": 2.6691382765531065e-05, "loss": 2.074, "step": 46740 }, { "epoch": 0.76, "learning_rate": 2.6686372745490982e-05, "loss": 2.0866, "step": 46750 }, { "epoch": 0.76, "learning_rate": 2.6681362725450903e-05, "loss": 2.0437, "step": 46760 }, { "epoch": 0.76, "learning_rate": 2.6676352705410824e-05, "loss": 2.0849, "step": 46770 }, { "epoch": 0.76, "learning_rate": 2.6671342685370744e-05, "loss": 2.0729, "step": 46780 }, { "epoch": 0.76, "learning_rate": 2.666633266533066e-05, "loss": 2.088, "step": 46790 }, { "epoch": 0.76, "learning_rate": 2.6661322645290582e-05, "loss": 2.0521, "step": 46800 }, { "epoch": 0.76, "learning_rate": 2.6656312625250503e-05, "loss": 2.0791, "step": 46810 }, { "epoch": 0.77, "learning_rate": 2.665130260521042e-05, "loss": 2.0358, "step": 46820 }, { "epoch": 0.77, "learning_rate": 2.664629258517034e-05, "loss": 2.1227, "step": 46830 }, { "epoch": 0.77, "learning_rate": 2.664128256513026e-05, "loss": 2.0462, "step": 46840 }, { "epoch": 0.77, "learning_rate": 2.663627254509018e-05, "loss": 2.0354, "step": 46850 }, { "epoch": 0.77, "learning_rate": 2.66312625250501e-05, "loss": 2.0424, "step": 46860 }, { "epoch": 0.77, "learning_rate": 2.662625250501002e-05, "loss": 2.0993, "step": 46870 }, { "epoch": 0.77, "learning_rate": 2.6621242484969944e-05, "loss": 2.0602, "step": 46880 }, { "epoch": 0.77, "learning_rate": 2.6616232464929865e-05, "loss": 2.0572, "step": 46890 }, { "epoch": 0.77, "learning_rate": 2.6611222444889782e-05, "loss": 2.0998, "step": 46900 }, { "epoch": 0.77, "learning_rate": 2.6606212424849702e-05, "loss": 2.0602, "step": 46910 }, { "epoch": 0.77, "learning_rate": 2.6601202404809623e-05, "loss": 2.1037, "step": 46920 }, { "epoch": 0.77, "learning_rate": 2.659619238476954e-05, "loss": 2.0778, "step": 46930 }, { "epoch": 0.77, "learning_rate": 2.659118236472946e-05, "loss": 2.0358, "step": 46940 }, { "epoch": 0.77, "learning_rate": 2.658617234468938e-05, "loss": 2.0565, "step": 46950 }, { "epoch": 0.77, "learning_rate": 2.65811623246493e-05, "loss": 2.1042, "step": 46960 }, { "epoch": 0.77, "learning_rate": 2.657615230460922e-05, "loss": 2.0399, "step": 46970 }, { "epoch": 0.77, "learning_rate": 2.657114228456914e-05, "loss": 2.0937, "step": 46980 }, { "epoch": 0.77, "learning_rate": 2.6566132264529057e-05, "loss": 2.074, "step": 46990 }, { "epoch": 0.77, "learning_rate": 2.6561122244488978e-05, "loss": 2.098, "step": 47000 }, { "epoch": 0.77, "eval_loss": 2.0469627380371094, "eval_mean_f1": 0.6529706291330638, "eval_rouge1_f1": 0.7130414112114682, "eval_rouge1_precision": 0.8251310752427329, "eval_rouge1_recall": 0.6605731294796259, "eval_rouge2_f1": 0.5661289403615325, "eval_rouge2_precision": 0.6593553365037741, "eval_rouge2_recall": 0.5244389411092789, "eval_rougeL_f1": 0.6797415358261909, "eval_rougeL_precision": 0.7845403251182914, "eval_rougeL_recall": 0.6304908573132534, "eval_runtime": 68.1381, "eval_samples_per_second": 15.028, "eval_steps_per_second": 1.879, "step": 47000 }, { "epoch": 0.77, "learning_rate": 2.65561122244489e-05, "loss": 2.0171, "step": 47010 }, { "epoch": 0.77, "learning_rate": 2.6551102204408816e-05, "loss": 2.0498, "step": 47020 }, { "epoch": 0.77, "learning_rate": 2.6546092184368737e-05, "loss": 2.06, "step": 47030 }, { "epoch": 0.77, "learning_rate": 2.6541082164328657e-05, "loss": 2.0647, "step": 47040 }, { "epoch": 0.77, "learning_rate": 2.6536072144288578e-05, "loss": 2.0414, "step": 47050 }, { "epoch": 0.77, "learning_rate": 2.6531062124248495e-05, "loss": 2.1021, "step": 47060 }, { "epoch": 0.77, "learning_rate": 2.6526052104208416e-05, "loss": 2.0962, "step": 47070 }, { "epoch": 0.77, "learning_rate": 2.652104208416834e-05, "loss": 2.0873, "step": 47080 }, { "epoch": 0.77, "learning_rate": 2.651603206412826e-05, "loss": 2.0785, "step": 47090 }, { "epoch": 0.77, "learning_rate": 2.651102204408818e-05, "loss": 2.0647, "step": 47100 }, { "epoch": 0.77, "learning_rate": 2.65060120240481e-05, "loss": 2.0435, "step": 47110 }, { "epoch": 0.77, "learning_rate": 2.650100200400802e-05, "loss": 2.0991, "step": 47120 }, { "epoch": 0.77, "learning_rate": 2.649599198396794e-05, "loss": 2.0564, "step": 47130 }, { "epoch": 0.77, "learning_rate": 2.6490981963927857e-05, "loss": 2.0762, "step": 47140 }, { "epoch": 0.77, "learning_rate": 2.6485971943887778e-05, "loss": 2.0391, "step": 47150 }, { "epoch": 0.77, "learning_rate": 2.6480961923847698e-05, "loss": 2.0515, "step": 47160 }, { "epoch": 0.77, "learning_rate": 2.6475951903807615e-05, "loss": 2.0889, "step": 47170 }, { "epoch": 0.77, "learning_rate": 2.6470941883767536e-05, "loss": 2.0748, "step": 47180 }, { "epoch": 0.77, "learning_rate": 2.6465931863727457e-05, "loss": 2.114, "step": 47190 }, { "epoch": 0.77, "learning_rate": 2.6460921843687374e-05, "loss": 2.0821, "step": 47200 }, { "epoch": 0.77, "learning_rate": 2.6455911823647295e-05, "loss": 2.0856, "step": 47210 }, { "epoch": 0.77, "learning_rate": 2.6450901803607215e-05, "loss": 2.0753, "step": 47220 }, { "epoch": 0.77, "learning_rate": 2.6445891783567132e-05, "loss": 2.0653, "step": 47230 }, { "epoch": 0.77, "learning_rate": 2.6440881763527053e-05, "loss": 2.0283, "step": 47240 }, { "epoch": 0.77, "learning_rate": 2.6435871743486974e-05, "loss": 2.0339, "step": 47250 }, { "epoch": 0.77, "learning_rate": 2.643086172344689e-05, "loss": 2.0581, "step": 47260 }, { "epoch": 0.77, "learning_rate": 2.642585170340682e-05, "loss": 2.0769, "step": 47270 }, { "epoch": 0.77, "learning_rate": 2.6420841683366736e-05, "loss": 2.0897, "step": 47280 }, { "epoch": 0.77, "learning_rate": 2.6415831663326656e-05, "loss": 2.1116, "step": 47290 }, { "epoch": 0.77, "learning_rate": 2.6410821643286577e-05, "loss": 2.0398, "step": 47300 }, { "epoch": 0.77, "learning_rate": 2.6405811623246494e-05, "loss": 2.0647, "step": 47310 }, { "epoch": 0.77, "learning_rate": 2.6400801603206415e-05, "loss": 2.0621, "step": 47320 }, { "epoch": 0.77, "learning_rate": 2.6395791583166335e-05, "loss": 2.1019, "step": 47330 }, { "epoch": 0.77, "learning_rate": 2.6390781563126256e-05, "loss": 2.0443, "step": 47340 }, { "epoch": 0.77, "learning_rate": 2.6385771543086173e-05, "loss": 2.0439, "step": 47350 }, { "epoch": 0.77, "learning_rate": 2.6380761523046094e-05, "loss": 2.1271, "step": 47360 }, { "epoch": 0.77, "learning_rate": 2.6375751503006015e-05, "loss": 2.0483, "step": 47370 }, { "epoch": 0.77, "learning_rate": 2.6370741482965932e-05, "loss": 2.0706, "step": 47380 }, { "epoch": 0.77, "learning_rate": 2.6365731462925853e-05, "loss": 2.0529, "step": 47390 }, { "epoch": 0.77, "learning_rate": 2.6360721442885773e-05, "loss": 2.0258, "step": 47400 }, { "epoch": 0.77, "learning_rate": 2.635571142284569e-05, "loss": 2.0147, "step": 47410 }, { "epoch": 0.77, "learning_rate": 2.635070140280561e-05, "loss": 2.037, "step": 47420 }, { "epoch": 0.78, "learning_rate": 2.6345691382765532e-05, "loss": 2.0895, "step": 47430 }, { "epoch": 0.78, "learning_rate": 2.634068136272545e-05, "loss": 2.0178, "step": 47440 }, { "epoch": 0.78, "learning_rate": 2.633567134268537e-05, "loss": 2.0591, "step": 47450 }, { "epoch": 0.78, "learning_rate": 2.633066132264529e-05, "loss": 2.075, "step": 47460 }, { "epoch": 0.78, "learning_rate": 2.6325651302605214e-05, "loss": 2.1096, "step": 47470 }, { "epoch": 0.78, "learning_rate": 2.6320641282565135e-05, "loss": 2.0633, "step": 47480 }, { "epoch": 0.78, "learning_rate": 2.6315631262525052e-05, "loss": 2.099, "step": 47490 }, { "epoch": 0.78, "learning_rate": 2.6310621242484973e-05, "loss": 2.06, "step": 47500 }, { "epoch": 0.78, "learning_rate": 2.6305611222444893e-05, "loss": 2.0467, "step": 47510 }, { "epoch": 0.78, "learning_rate": 2.630060120240481e-05, "loss": 2.0433, "step": 47520 }, { "epoch": 0.78, "learning_rate": 2.629559118236473e-05, "loss": 2.0437, "step": 47530 }, { "epoch": 0.78, "learning_rate": 2.6290581162324652e-05, "loss": 2.0575, "step": 47540 }, { "epoch": 0.78, "learning_rate": 2.628557114228457e-05, "loss": 2.1205, "step": 47550 }, { "epoch": 0.78, "learning_rate": 2.6281062124248496e-05, "loss": 2.0823, "step": 47560 }, { "epoch": 0.78, "learning_rate": 2.627605210420842e-05, "loss": 2.0993, "step": 47570 }, { "epoch": 0.78, "learning_rate": 2.627104208416834e-05, "loss": 2.0631, "step": 47580 }, { "epoch": 0.78, "learning_rate": 2.626603206412826e-05, "loss": 2.0497, "step": 47590 }, { "epoch": 0.78, "learning_rate": 2.626102204408818e-05, "loss": 2.0814, "step": 47600 }, { "epoch": 0.78, "learning_rate": 2.62560120240481e-05, "loss": 2.0906, "step": 47610 }, { "epoch": 0.78, "learning_rate": 2.625100200400802e-05, "loss": 2.0237, "step": 47620 }, { "epoch": 0.78, "learning_rate": 2.6245991983967937e-05, "loss": 2.0792, "step": 47630 }, { "epoch": 0.78, "learning_rate": 2.6240981963927858e-05, "loss": 2.0639, "step": 47640 }, { "epoch": 0.78, "learning_rate": 2.6235971943887778e-05, "loss": 2.0988, "step": 47650 }, { "epoch": 0.78, "learning_rate": 2.6230961923847695e-05, "loss": 2.0627, "step": 47660 }, { "epoch": 0.78, "learning_rate": 2.6225951903807616e-05, "loss": 2.061, "step": 47670 }, { "epoch": 0.78, "learning_rate": 2.6220941883767537e-05, "loss": 2.0279, "step": 47680 }, { "epoch": 0.78, "learning_rate": 2.6215931863727454e-05, "loss": 2.0184, "step": 47690 }, { "epoch": 0.78, "learning_rate": 2.6210921843687375e-05, "loss": 2.035, "step": 47700 }, { "epoch": 0.78, "learning_rate": 2.6205911823647295e-05, "loss": 2.0624, "step": 47710 }, { "epoch": 0.78, "learning_rate": 2.6200901803607213e-05, "loss": 2.1261, "step": 47720 }, { "epoch": 0.78, "learning_rate": 2.6195891783567133e-05, "loss": 2.0212, "step": 47730 }, { "epoch": 0.78, "learning_rate": 2.6190881763527054e-05, "loss": 2.0544, "step": 47740 }, { "epoch": 0.78, "learning_rate": 2.618587174348697e-05, "loss": 2.0377, "step": 47750 }, { "epoch": 0.78, "learning_rate": 2.61808617234469e-05, "loss": 2.0484, "step": 47760 }, { "epoch": 0.78, "learning_rate": 2.6175851703406816e-05, "loss": 2.0638, "step": 47770 }, { "epoch": 0.78, "learning_rate": 2.6170841683366736e-05, "loss": 2.0398, "step": 47780 }, { "epoch": 0.78, "learning_rate": 2.6165831663326657e-05, "loss": 2.0599, "step": 47790 }, { "epoch": 0.78, "learning_rate": 2.6160821643286578e-05, "loss": 2.0757, "step": 47800 }, { "epoch": 0.78, "learning_rate": 2.6155811623246495e-05, "loss": 2.0872, "step": 47810 }, { "epoch": 0.78, "learning_rate": 2.6150801603206416e-05, "loss": 2.0772, "step": 47820 }, { "epoch": 0.78, "learning_rate": 2.6145791583166336e-05, "loss": 2.0611, "step": 47830 }, { "epoch": 0.78, "learning_rate": 2.6140781563126253e-05, "loss": 2.1066, "step": 47840 }, { "epoch": 0.78, "learning_rate": 2.6135771543086174e-05, "loss": 2.0564, "step": 47850 }, { "epoch": 0.78, "learning_rate": 2.6130761523046095e-05, "loss": 2.0565, "step": 47860 }, { "epoch": 0.78, "learning_rate": 2.6125751503006012e-05, "loss": 2.0566, "step": 47870 }, { "epoch": 0.78, "learning_rate": 2.6120741482965933e-05, "loss": 2.0497, "step": 47880 }, { "epoch": 0.78, "learning_rate": 2.6115731462925853e-05, "loss": 2.0521, "step": 47890 }, { "epoch": 0.78, "learning_rate": 2.611072144288577e-05, "loss": 2.0662, "step": 47900 }, { "epoch": 0.78, "learning_rate": 2.610571142284569e-05, "loss": 2.0725, "step": 47910 }, { "epoch": 0.78, "learning_rate": 2.6100701402805612e-05, "loss": 2.0939, "step": 47920 }, { "epoch": 0.78, "learning_rate": 2.609569138276553e-05, "loss": 2.0794, "step": 47930 }, { "epoch": 0.78, "learning_rate": 2.609068136272545e-05, "loss": 2.1216, "step": 47940 }, { "epoch": 0.78, "learning_rate": 2.608567134268537e-05, "loss": 2.0426, "step": 47950 }, { "epoch": 0.78, "learning_rate": 2.6080661322645294e-05, "loss": 2.0615, "step": 47960 }, { "epoch": 0.78, "learning_rate": 2.6075651302605215e-05, "loss": 2.0273, "step": 47970 }, { "epoch": 0.78, "learning_rate": 2.6070641282565132e-05, "loss": 2.0149, "step": 47980 }, { "epoch": 0.78, "learning_rate": 2.6065631262525053e-05, "loss": 2.035, "step": 47990 }, { "epoch": 0.78, "learning_rate": 2.6060621242484974e-05, "loss": 2.0701, "step": 48000 }, { "epoch": 0.78, "eval_loss": 2.0467443466186523, "eval_mean_f1": 0.6541639695608028, "eval_rouge1_f1": 0.711609362161274, "eval_rouge1_precision": 0.8225152621087672, "eval_rouge1_recall": 0.6598138317119766, "eval_rouge2_f1": 0.5691038261701922, "eval_rouge2_precision": 0.6619822445078801, "eval_rouge2_recall": 0.5278432564814128, "eval_rougeL_f1": 0.6817787203509422, "eval_rougeL_precision": 0.7862445537860577, "eval_rougeL_recall": 0.6332604043193641, "eval_runtime": 65.4019, "eval_samples_per_second": 15.657, "eval_steps_per_second": 1.957, "step": 48000 }, { "epoch": 0.78, "learning_rate": 2.605561122244489e-05, "loss": 2.0846, "step": 48010 }, { "epoch": 0.78, "learning_rate": 2.605060120240481e-05, "loss": 2.0627, "step": 48020 }, { "epoch": 0.78, "learning_rate": 2.6045591182364732e-05, "loss": 2.0491, "step": 48030 }, { "epoch": 0.78, "learning_rate": 2.604058116232465e-05, "loss": 2.0214, "step": 48040 }, { "epoch": 0.79, "learning_rate": 2.603557114228457e-05, "loss": 2.1099, "step": 48050 }, { "epoch": 0.79, "learning_rate": 2.603056112224449e-05, "loss": 2.0608, "step": 48060 }, { "epoch": 0.79, "learning_rate": 2.602555110220441e-05, "loss": 2.0962, "step": 48070 }, { "epoch": 0.79, "learning_rate": 2.602054108216433e-05, "loss": 2.1142, "step": 48080 }, { "epoch": 0.79, "learning_rate": 2.601553106212425e-05, "loss": 2.1064, "step": 48090 }, { "epoch": 0.79, "learning_rate": 2.601052104208417e-05, "loss": 2.0657, "step": 48100 }, { "epoch": 0.79, "learning_rate": 2.6005511022044087e-05, "loss": 2.0956, "step": 48110 }, { "epoch": 0.79, "learning_rate": 2.6000501002004008e-05, "loss": 2.0662, "step": 48120 }, { "epoch": 0.79, "learning_rate": 2.599549098196393e-05, "loss": 2.0226, "step": 48130 }, { "epoch": 0.79, "learning_rate": 2.5990480961923846e-05, "loss": 2.0153, "step": 48140 }, { "epoch": 0.79, "learning_rate": 2.5985470941883766e-05, "loss": 2.0564, "step": 48150 }, { "epoch": 0.79, "learning_rate": 2.598046092184369e-05, "loss": 2.0626, "step": 48160 }, { "epoch": 0.79, "learning_rate": 2.597545090180361e-05, "loss": 2.06, "step": 48170 }, { "epoch": 0.79, "learning_rate": 2.597044088176353e-05, "loss": 2.0841, "step": 48180 }, { "epoch": 0.79, "learning_rate": 2.596543086172345e-05, "loss": 2.1073, "step": 48190 }, { "epoch": 0.79, "learning_rate": 2.596042084168337e-05, "loss": 2.1652, "step": 48200 }, { "epoch": 0.79, "learning_rate": 2.595541082164329e-05, "loss": 2.0662, "step": 48210 }, { "epoch": 0.79, "learning_rate": 2.5950400801603207e-05, "loss": 2.0965, "step": 48220 }, { "epoch": 0.79, "learning_rate": 2.5945390781563128e-05, "loss": 2.0773, "step": 48230 }, { "epoch": 0.79, "learning_rate": 2.594038076152305e-05, "loss": 2.0866, "step": 48240 }, { "epoch": 0.79, "learning_rate": 2.5935370741482966e-05, "loss": 2.0534, "step": 48250 }, { "epoch": 0.79, "learning_rate": 2.5930360721442887e-05, "loss": 1.9966, "step": 48260 }, { "epoch": 0.79, "learning_rate": 2.5925350701402807e-05, "loss": 2.0498, "step": 48270 }, { "epoch": 0.79, "learning_rate": 2.5920340681362724e-05, "loss": 2.0948, "step": 48280 }, { "epoch": 0.79, "learning_rate": 2.5915330661322645e-05, "loss": 2.0691, "step": 48290 }, { "epoch": 0.79, "learning_rate": 2.5910320641282566e-05, "loss": 2.0862, "step": 48300 }, { "epoch": 0.79, "learning_rate": 2.5905310621242483e-05, "loss": 2.057, "step": 48310 }, { "epoch": 0.79, "learning_rate": 2.5900300601202404e-05, "loss": 2.0636, "step": 48320 }, { "epoch": 0.79, "learning_rate": 2.5895290581162324e-05, "loss": 2.0531, "step": 48330 }, { "epoch": 0.79, "learning_rate": 2.5890280561122245e-05, "loss": 2.0566, "step": 48340 }, { "epoch": 0.79, "learning_rate": 2.588527054108217e-05, "loss": 2.0673, "step": 48350 }, { "epoch": 0.79, "learning_rate": 2.588026052104209e-05, "loss": 2.0728, "step": 48360 }, { "epoch": 0.79, "learning_rate": 2.5875250501002007e-05, "loss": 2.0517, "step": 48370 }, { "epoch": 0.79, "learning_rate": 2.5870240480961927e-05, "loss": 2.0559, "step": 48380 }, { "epoch": 0.79, "learning_rate": 2.5865230460921848e-05, "loss": 2.0561, "step": 48390 }, { "epoch": 0.79, "learning_rate": 2.5860220440881765e-05, "loss": 2.018, "step": 48400 }, { "epoch": 0.79, "learning_rate": 2.5855210420841686e-05, "loss": 2.0928, "step": 48410 }, { "epoch": 0.79, "learning_rate": 2.5850200400801607e-05, "loss": 2.0696, "step": 48420 }, { "epoch": 0.79, "learning_rate": 2.5845190380761524e-05, "loss": 2.0825, "step": 48430 }, { "epoch": 0.79, "learning_rate": 2.5840180360721444e-05, "loss": 2.1111, "step": 48440 }, { "epoch": 0.79, "learning_rate": 2.5835170340681365e-05, "loss": 2.0573, "step": 48450 }, { "epoch": 0.79, "learning_rate": 2.5830160320641282e-05, "loss": 2.0322, "step": 48460 }, { "epoch": 0.79, "learning_rate": 2.5825150300601203e-05, "loss": 2.0636, "step": 48470 }, { "epoch": 0.79, "learning_rate": 2.5820140280561124e-05, "loss": 2.0572, "step": 48480 }, { "epoch": 0.79, "learning_rate": 2.581513026052104e-05, "loss": 2.0624, "step": 48490 }, { "epoch": 0.79, "learning_rate": 2.581012024048096e-05, "loss": 2.0513, "step": 48500 }, { "epoch": 0.79, "learning_rate": 2.5805110220440882e-05, "loss": 2.0784, "step": 48510 }, { "epoch": 0.79, "learning_rate": 2.58001002004008e-05, "loss": 2.0598, "step": 48520 }, { "epoch": 0.79, "learning_rate": 2.579509018036072e-05, "loss": 2.0302, "step": 48530 }, { "epoch": 0.79, "learning_rate": 2.579008016032064e-05, "loss": 2.0715, "step": 48540 }, { "epoch": 0.79, "learning_rate": 2.5785070140280565e-05, "loss": 2.08, "step": 48550 }, { "epoch": 0.79, "learning_rate": 2.5780060120240485e-05, "loss": 2.0254, "step": 48560 }, { "epoch": 0.79, "learning_rate": 2.5775050100200403e-05, "loss": 2.0237, "step": 48570 }, { "epoch": 0.79, "learning_rate": 2.5770040080160323e-05, "loss": 2.0391, "step": 48580 }, { "epoch": 0.79, "learning_rate": 2.5765030060120244e-05, "loss": 2.0895, "step": 48590 }, { "epoch": 0.79, "learning_rate": 2.576002004008016e-05, "loss": 2.0177, "step": 48600 }, { "epoch": 0.79, "learning_rate": 2.5755010020040082e-05, "loss": 2.1278, "step": 48610 }, { "epoch": 0.79, "learning_rate": 2.5750000000000002e-05, "loss": 2.0509, "step": 48620 }, { "epoch": 0.79, "learning_rate": 2.5744989979959923e-05, "loss": 2.076, "step": 48630 }, { "epoch": 0.79, "learning_rate": 2.573997995991984e-05, "loss": 2.0517, "step": 48640 }, { "epoch": 0.79, "learning_rate": 2.573496993987976e-05, "loss": 2.0973, "step": 48650 }, { "epoch": 0.8, "learning_rate": 2.572995991983968e-05, "loss": 2.051, "step": 48660 }, { "epoch": 0.8, "learning_rate": 2.57249498997996e-05, "loss": 2.0275, "step": 48670 }, { "epoch": 0.8, "learning_rate": 2.571993987975952e-05, "loss": 2.0283, "step": 48680 }, { "epoch": 0.8, "learning_rate": 2.571492985971944e-05, "loss": 2.0361, "step": 48690 }, { "epoch": 0.8, "learning_rate": 2.5709919839679357e-05, "loss": 2.0884, "step": 48700 }, { "epoch": 0.8, "learning_rate": 2.5704909819639278e-05, "loss": 2.0766, "step": 48710 }, { "epoch": 0.8, "learning_rate": 2.56998997995992e-05, "loss": 2.0518, "step": 48720 }, { "epoch": 0.8, "learning_rate": 2.5694889779559116e-05, "loss": 2.0251, "step": 48730 }, { "epoch": 0.8, "learning_rate": 2.5689879759519037e-05, "loss": 2.0472, "step": 48740 }, { "epoch": 0.8, "learning_rate": 2.568486973947896e-05, "loss": 2.0306, "step": 48750 }, { "epoch": 0.8, "learning_rate": 2.567985971943888e-05, "loss": 2.0613, "step": 48760 }, { "epoch": 0.8, "learning_rate": 2.5674849699398802e-05, "loss": 2.0321, "step": 48770 }, { "epoch": 0.8, "learning_rate": 2.566983967935872e-05, "loss": 2.0655, "step": 48780 }, { "epoch": 0.8, "learning_rate": 2.566482965931864e-05, "loss": 2.0573, "step": 48790 }, { "epoch": 0.8, "learning_rate": 2.565981963927856e-05, "loss": 2.0789, "step": 48800 }, { "epoch": 0.8, "learning_rate": 2.5654809619238478e-05, "loss": 2.0088, "step": 48810 }, { "epoch": 0.8, "learning_rate": 2.56497995991984e-05, "loss": 2.0957, "step": 48820 }, { "epoch": 0.8, "learning_rate": 2.564478957915832e-05, "loss": 2.079, "step": 48830 }, { "epoch": 0.8, "learning_rate": 2.5639779559118236e-05, "loss": 2.1247, "step": 48840 }, { "epoch": 0.8, "learning_rate": 2.5634769539078157e-05, "loss": 2.0617, "step": 48850 }, { "epoch": 0.8, "learning_rate": 2.5629759519038078e-05, "loss": 2.0875, "step": 48860 }, { "epoch": 0.8, "learning_rate": 2.5624749498997995e-05, "loss": 2.0644, "step": 48870 }, { "epoch": 0.8, "learning_rate": 2.5619739478957915e-05, "loss": 2.0753, "step": 48880 }, { "epoch": 0.8, "learning_rate": 2.5614729458917836e-05, "loss": 2.0445, "step": 48890 }, { "epoch": 0.8, "learning_rate": 2.5609719438877757e-05, "loss": 2.0916, "step": 48900 }, { "epoch": 0.8, "learning_rate": 2.5604709418837674e-05, "loss": 2.086, "step": 48910 }, { "epoch": 0.8, "learning_rate": 2.5599699398797595e-05, "loss": 2.0646, "step": 48920 }, { "epoch": 0.8, "learning_rate": 2.5594689378757515e-05, "loss": 2.1406, "step": 48930 }, { "epoch": 0.8, "learning_rate": 2.558967935871744e-05, "loss": 2.0771, "step": 48940 }, { "epoch": 0.8, "learning_rate": 2.558466933867736e-05, "loss": 2.0223, "step": 48950 }, { "epoch": 0.8, "learning_rate": 2.5579659318637277e-05, "loss": 2.0474, "step": 48960 }, { "epoch": 0.8, "learning_rate": 2.5574649298597198e-05, "loss": 2.0535, "step": 48970 }, { "epoch": 0.8, "learning_rate": 2.556963927855712e-05, "loss": 2.1003, "step": 48980 }, { "epoch": 0.8, "learning_rate": 2.5564629258517036e-05, "loss": 2.0568, "step": 48990 }, { "epoch": 0.8, "learning_rate": 2.5559619238476956e-05, "loss": 2.0845, "step": 49000 }, { "epoch": 0.8, "eval_loss": 2.0490756034851074, "eval_mean_f1": 0.6522679672748332, "eval_rouge1_f1": 0.7114277078154432, "eval_rouge1_precision": 0.8234753006054263, "eval_rouge1_recall": 0.6587193044537969, "eval_rouge2_f1": 0.5666596755010374, "eval_rouge2_precision": 0.6592132856293013, "eval_rouge2_recall": 0.5252449450321462, "eval_rougeL_f1": 0.6787165185080188, "eval_rougeL_precision": 0.7831826993663507, "eval_rougeL_recall": 0.6298566737792115, "eval_runtime": 63.6805, "eval_samples_per_second": 16.08, "eval_steps_per_second": 2.01, "step": 49000 }, { "epoch": 0.8, "learning_rate": 2.5554609218436877e-05, "loss": 2.0628, "step": 49010 }, { "epoch": 0.8, "learning_rate": 2.5549599198396794e-05, "loss": 2.0363, "step": 49020 }, { "epoch": 0.8, "learning_rate": 2.5544589178356715e-05, "loss": 2.0529, "step": 49030 }, { "epoch": 0.8, "learning_rate": 2.5539579158316636e-05, "loss": 2.1134, "step": 49040 }, { "epoch": 0.8, "learning_rate": 2.5534569138276553e-05, "loss": 2.0766, "step": 49050 }, { "epoch": 0.8, "learning_rate": 2.5529559118236473e-05, "loss": 2.0594, "step": 49060 }, { "epoch": 0.8, "learning_rate": 2.5524549098196394e-05, "loss": 1.993, "step": 49070 }, { "epoch": 0.8, "learning_rate": 2.551953907815631e-05, "loss": 2.0093, "step": 49080 }, { "epoch": 0.8, "learning_rate": 2.5514529058116232e-05, "loss": 2.0887, "step": 49090 }, { "epoch": 0.8, "learning_rate": 2.5509519038076153e-05, "loss": 2.0557, "step": 49100 }, { "epoch": 0.8, "learning_rate": 2.550450901803607e-05, "loss": 2.1032, "step": 49110 }, { "epoch": 0.8, "learning_rate": 2.549949899799599e-05, "loss": 2.0555, "step": 49120 }, { "epoch": 0.8, "learning_rate": 2.549448897795591e-05, "loss": 2.0327, "step": 49130 }, { "epoch": 0.8, "learning_rate": 2.5489478957915835e-05, "loss": 2.0735, "step": 49140 }, { "epoch": 0.8, "learning_rate": 2.5484468937875756e-05, "loss": 2.0482, "step": 49150 }, { "epoch": 0.8, "learning_rate": 2.5479458917835673e-05, "loss": 2.0887, "step": 49160 }, { "epoch": 0.8, "learning_rate": 2.5474448897795594e-05, "loss": 2.1099, "step": 49170 }, { "epoch": 0.8, "learning_rate": 2.5469438877755514e-05, "loss": 2.0579, "step": 49180 }, { "epoch": 0.8, "learning_rate": 2.546442885771543e-05, "loss": 2.0561, "step": 49190 }, { "epoch": 0.8, "learning_rate": 2.5459418837675352e-05, "loss": 2.1094, "step": 49200 }, { "epoch": 0.8, "learning_rate": 2.5454408817635273e-05, "loss": 2.0389, "step": 49210 }, { "epoch": 0.8, "learning_rate": 2.5449398797595194e-05, "loss": 2.0475, "step": 49220 }, { "epoch": 0.8, "learning_rate": 2.544438877755511e-05, "loss": 2.0773, "step": 49230 }, { "epoch": 0.8, "learning_rate": 2.543937875751503e-05, "loss": 2.0929, "step": 49240 }, { "epoch": 0.8, "learning_rate": 2.5434368737474952e-05, "loss": 2.0743, "step": 49250 }, { "epoch": 0.8, "learning_rate": 2.542935871743487e-05, "loss": 2.0872, "step": 49260 }, { "epoch": 0.81, "learning_rate": 2.542434869739479e-05, "loss": 2.028, "step": 49270 }, { "epoch": 0.81, "learning_rate": 2.541933867735471e-05, "loss": 2.0692, "step": 49280 }, { "epoch": 0.81, "learning_rate": 2.5414328657314628e-05, "loss": 2.0389, "step": 49290 }, { "epoch": 0.81, "learning_rate": 2.5409819639278558e-05, "loss": 2.0938, "step": 49300 }, { "epoch": 0.81, "learning_rate": 2.540480961923848e-05, "loss": 2.0062, "step": 49310 }, { "epoch": 0.81, "learning_rate": 2.53997995991984e-05, "loss": 2.0413, "step": 49320 }, { "epoch": 0.81, "learning_rate": 2.5394789579158316e-05, "loss": 2.02, "step": 49330 }, { "epoch": 0.81, "learning_rate": 2.5389779559118237e-05, "loss": 2.0361, "step": 49340 }, { "epoch": 0.81, "learning_rate": 2.5384769539078158e-05, "loss": 2.0959, "step": 49350 }, { "epoch": 0.81, "learning_rate": 2.5379759519038078e-05, "loss": 2.0674, "step": 49360 }, { "epoch": 0.81, "learning_rate": 2.5374749498997996e-05, "loss": 2.054, "step": 49370 }, { "epoch": 0.81, "learning_rate": 2.5369739478957916e-05, "loss": 2.0655, "step": 49380 }, { "epoch": 0.81, "learning_rate": 2.5364729458917837e-05, "loss": 2.0595, "step": 49390 }, { "epoch": 0.81, "learning_rate": 2.5359719438877754e-05, "loss": 2.067, "step": 49400 }, { "epoch": 0.81, "learning_rate": 2.5354709418837675e-05, "loss": 2.0155, "step": 49410 }, { "epoch": 0.81, "learning_rate": 2.5349699398797595e-05, "loss": 2.0673, "step": 49420 }, { "epoch": 0.81, "learning_rate": 2.5344689378757513e-05, "loss": 2.0987, "step": 49430 }, { "epoch": 0.81, "learning_rate": 2.533967935871744e-05, "loss": 2.1098, "step": 49440 }, { "epoch": 0.81, "learning_rate": 2.5334669338677357e-05, "loss": 2.0326, "step": 49450 }, { "epoch": 0.81, "learning_rate": 2.5329659318637278e-05, "loss": 2.0693, "step": 49460 }, { "epoch": 0.81, "learning_rate": 2.53246492985972e-05, "loss": 2.1074, "step": 49470 }, { "epoch": 0.81, "learning_rate": 2.5319639278557116e-05, "loss": 2.0766, "step": 49480 }, { "epoch": 0.81, "learning_rate": 2.5314629258517036e-05, "loss": 2.0157, "step": 49490 }, { "epoch": 0.81, "learning_rate": 2.5309619238476957e-05, "loss": 2.0513, "step": 49500 }, { "epoch": 0.81, "learning_rate": 2.5304609218436874e-05, "loss": 2.0535, "step": 49510 }, { "epoch": 0.81, "learning_rate": 2.5299599198396795e-05, "loss": 2.0561, "step": 49520 }, { "epoch": 0.81, "learning_rate": 2.5294589178356716e-05, "loss": 2.0404, "step": 49530 }, { "epoch": 0.81, "learning_rate": 2.5289579158316633e-05, "loss": 2.1186, "step": 49540 }, { "epoch": 0.81, "learning_rate": 2.5284569138276553e-05, "loss": 2.0697, "step": 49550 }, { "epoch": 0.81, "learning_rate": 2.5279559118236474e-05, "loss": 2.0535, "step": 49560 }, { "epoch": 0.81, "learning_rate": 2.527454909819639e-05, "loss": 2.0598, "step": 49570 }, { "epoch": 0.81, "learning_rate": 2.5269539078156312e-05, "loss": 2.0683, "step": 49580 }, { "epoch": 0.81, "learning_rate": 2.5264529058116233e-05, "loss": 2.0883, "step": 49590 }, { "epoch": 0.81, "learning_rate": 2.525951903807615e-05, "loss": 2.0738, "step": 49600 }, { "epoch": 0.81, "learning_rate": 2.525450901803607e-05, "loss": 2.0287, "step": 49610 }, { "epoch": 0.81, "learning_rate": 2.524949899799599e-05, "loss": 2.0358, "step": 49620 }, { "epoch": 0.81, "learning_rate": 2.5244488977955915e-05, "loss": 2.0373, "step": 49630 }, { "epoch": 0.81, "learning_rate": 2.5239478957915836e-05, "loss": 2.0373, "step": 49640 }, { "epoch": 0.81, "learning_rate": 2.5234468937875757e-05, "loss": 2.0791, "step": 49650 }, { "epoch": 0.81, "learning_rate": 2.5229458917835674e-05, "loss": 2.1166, "step": 49660 }, { "epoch": 0.81, "learning_rate": 2.5224448897795594e-05, "loss": 2.0662, "step": 49670 }, { "epoch": 0.81, "learning_rate": 2.5219438877755515e-05, "loss": 2.0993, "step": 49680 }, { "epoch": 0.81, "learning_rate": 2.5214428857715432e-05, "loss": 2.0239, "step": 49690 }, { "epoch": 0.81, "learning_rate": 2.5209418837675353e-05, "loss": 2.056, "step": 49700 }, { "epoch": 0.81, "learning_rate": 2.5204408817635274e-05, "loss": 2.0835, "step": 49710 }, { "epoch": 0.81, "learning_rate": 2.519939879759519e-05, "loss": 2.0789, "step": 49720 }, { "epoch": 0.81, "learning_rate": 2.519438877755511e-05, "loss": 2.0457, "step": 49730 }, { "epoch": 0.81, "learning_rate": 2.5189378757515032e-05, "loss": 2.0429, "step": 49740 }, { "epoch": 0.81, "learning_rate": 2.518436873747495e-05, "loss": 2.0257, "step": 49750 }, { "epoch": 0.81, "learning_rate": 2.517935871743487e-05, "loss": 2.0724, "step": 49760 }, { "epoch": 0.81, "learning_rate": 2.517434869739479e-05, "loss": 2.0444, "step": 49770 }, { "epoch": 0.81, "learning_rate": 2.5169338677354708e-05, "loss": 2.1059, "step": 49780 }, { "epoch": 0.81, "learning_rate": 2.516432865731463e-05, "loss": 2.0411, "step": 49790 }, { "epoch": 0.81, "learning_rate": 2.515931863727455e-05, "loss": 2.0527, "step": 49800 }, { "epoch": 0.81, "learning_rate": 2.5154308617234466e-05, "loss": 2.1083, "step": 49810 }, { "epoch": 0.81, "learning_rate": 2.5149298597194387e-05, "loss": 2.0298, "step": 49820 }, { "epoch": 0.81, "learning_rate": 2.514428857715431e-05, "loss": 2.0394, "step": 49830 }, { "epoch": 0.81, "learning_rate": 2.5139278557114232e-05, "loss": 2.0165, "step": 49840 }, { "epoch": 0.81, "learning_rate": 2.5134268537074152e-05, "loss": 2.0434, "step": 49850 }, { "epoch": 0.81, "learning_rate": 2.512925851703407e-05, "loss": 2.0915, "step": 49860 }, { "epoch": 0.81, "learning_rate": 2.512424849699399e-05, "loss": 2.084, "step": 49870 }, { "epoch": 0.82, "learning_rate": 2.511923847695391e-05, "loss": 2.0387, "step": 49880 }, { "epoch": 0.82, "learning_rate": 2.5114228456913828e-05, "loss": 2.04, "step": 49890 }, { "epoch": 0.82, "learning_rate": 2.510921843687375e-05, "loss": 2.0333, "step": 49900 }, { "epoch": 0.82, "learning_rate": 2.510420841683367e-05, "loss": 2.0637, "step": 49910 }, { "epoch": 0.82, "learning_rate": 2.5099198396793587e-05, "loss": 2.0161, "step": 49920 }, { "epoch": 0.82, "learning_rate": 2.5094188376753507e-05, "loss": 2.068, "step": 49930 }, { "epoch": 0.82, "learning_rate": 2.5089178356713428e-05, "loss": 2.0859, "step": 49940 }, { "epoch": 0.82, "learning_rate": 2.508416833667335e-05, "loss": 2.0848, "step": 49950 }, { "epoch": 0.82, "learning_rate": 2.5079158316633266e-05, "loss": 2.1128, "step": 49960 }, { "epoch": 0.82, "learning_rate": 2.5074148296593187e-05, "loss": 2.0668, "step": 49970 }, { "epoch": 0.82, "learning_rate": 2.5069138276553107e-05, "loss": 2.0457, "step": 49980 }, { "epoch": 0.82, "learning_rate": 2.5064128256513024e-05, "loss": 2.0511, "step": 49990 }, { "epoch": 0.82, "learning_rate": 2.5059118236472945e-05, "loss": 2.059, "step": 50000 }, { "epoch": 0.82, "eval_loss": 2.043787956237793, "eval_mean_f1": 0.653625219322008, "eval_rouge1_f1": 0.7135068095643484, "eval_rouge1_precision": 0.8236863963322337, "eval_rouge1_recall": 0.6626429430496149, "eval_rouge2_f1": 0.567514231424776, "eval_rouge2_precision": 0.6581759833590888, "eval_rouge2_recall": 0.5277032243585049, "eval_rougeL_f1": 0.6798546169768995, "eval_rougeL_precision": 0.783246234105393, "eval_rougeL_recall": 0.6328446688203617, "eval_runtime": 64.1616, "eval_samples_per_second": 15.96, "eval_steps_per_second": 1.995, "step": 50000 }, { "epoch": 0.82, "learning_rate": 2.5054108216432866e-05, "loss": 2.0525, "step": 50010 }, { "epoch": 0.82, "learning_rate": 2.504909819639279e-05, "loss": 2.0533, "step": 50020 }, { "epoch": 0.82, "learning_rate": 2.504408817635271e-05, "loss": 2.0946, "step": 50030 }, { "epoch": 0.82, "learning_rate": 2.5039078156312628e-05, "loss": 2.0416, "step": 50040 }, { "epoch": 0.82, "learning_rate": 2.5034068136272548e-05, "loss": 2.0565, "step": 50050 }, { "epoch": 0.82, "learning_rate": 2.502905811623247e-05, "loss": 2.0907, "step": 50060 }, { "epoch": 0.82, "learning_rate": 2.5024048096192386e-05, "loss": 2.0908, "step": 50070 }, { "epoch": 0.82, "learning_rate": 2.5019038076152307e-05, "loss": 2.0397, "step": 50080 }, { "epoch": 0.82, "learning_rate": 2.5014028056112227e-05, "loss": 2.0521, "step": 50090 }, { "epoch": 0.82, "learning_rate": 2.5009018036072145e-05, "loss": 2.0809, "step": 50100 }, { "epoch": 0.82, "learning_rate": 2.5004008016032065e-05, "loss": 2.0365, "step": 50110 }, { "epoch": 0.82, "learning_rate": 2.4998997995991986e-05, "loss": 2.0301, "step": 50120 }, { "epoch": 0.82, "learning_rate": 2.4993987975951903e-05, "loss": 2.0743, "step": 50130 }, { "epoch": 0.82, "learning_rate": 2.4988977955911824e-05, "loss": 2.0837, "step": 50140 }, { "epoch": 0.82, "learning_rate": 2.4983967935871745e-05, "loss": 2.085, "step": 50150 }, { "epoch": 0.82, "learning_rate": 2.4978957915831662e-05, "loss": 2.032, "step": 50160 }, { "epoch": 0.82, "learning_rate": 2.4973947895791586e-05, "loss": 2.0656, "step": 50170 }, { "epoch": 0.82, "learning_rate": 2.4968937875751506e-05, "loss": 2.0899, "step": 50180 }, { "epoch": 0.82, "learning_rate": 2.4963927855711424e-05, "loss": 2.0528, "step": 50190 }, { "epoch": 0.82, "learning_rate": 2.4958917835671344e-05, "loss": 2.0414, "step": 50200 }, { "epoch": 0.82, "learning_rate": 2.4953907815631265e-05, "loss": 2.107, "step": 50210 }, { "epoch": 0.82, "learning_rate": 2.4948897795591182e-05, "loss": 2.0586, "step": 50220 }, { "epoch": 0.82, "learning_rate": 2.4943887775551103e-05, "loss": 2.0338, "step": 50230 }, { "epoch": 0.82, "learning_rate": 2.4938877755511024e-05, "loss": 2.083, "step": 50240 }, { "epoch": 0.82, "learning_rate": 2.493386773547094e-05, "loss": 2.0611, "step": 50250 }, { "epoch": 0.82, "learning_rate": 2.492885771543086e-05, "loss": 2.0683, "step": 50260 }, { "epoch": 0.82, "learning_rate": 2.4923847695390785e-05, "loss": 2.0906, "step": 50270 }, { "epoch": 0.82, "learning_rate": 2.4918837675350703e-05, "loss": 2.0943, "step": 50280 }, { "epoch": 0.82, "learning_rate": 2.4913827655310623e-05, "loss": 2.0366, "step": 50290 }, { "epoch": 0.82, "learning_rate": 2.4908817635270544e-05, "loss": 2.066, "step": 50300 }, { "epoch": 0.82, "learning_rate": 2.490380761523046e-05, "loss": 2.0934, "step": 50310 }, { "epoch": 0.82, "learning_rate": 2.4898797595190382e-05, "loss": 2.0685, "step": 50320 }, { "epoch": 0.82, "learning_rate": 2.4893787575150303e-05, "loss": 2.1091, "step": 50330 }, { "epoch": 0.82, "learning_rate": 2.488877755511022e-05, "loss": 2.0699, "step": 50340 }, { "epoch": 0.82, "learning_rate": 2.488376753507014e-05, "loss": 2.0929, "step": 50350 }, { "epoch": 0.82, "learning_rate": 2.487875751503006e-05, "loss": 2.0366, "step": 50360 }, { "epoch": 0.82, "learning_rate": 2.4873747494989982e-05, "loss": 2.0441, "step": 50370 }, { "epoch": 0.82, "learning_rate": 2.4868737474949902e-05, "loss": 2.0474, "step": 50380 }, { "epoch": 0.82, "learning_rate": 2.4863727454909823e-05, "loss": 2.0946, "step": 50390 }, { "epoch": 0.82, "learning_rate": 2.485871743486974e-05, "loss": 2.0822, "step": 50400 }, { "epoch": 0.82, "learning_rate": 2.485370741482966e-05, "loss": 2.0968, "step": 50410 }, { "epoch": 0.82, "learning_rate": 2.484869739478958e-05, "loss": 2.0388, "step": 50420 }, { "epoch": 0.82, "learning_rate": 2.48436873747495e-05, "loss": 2.0789, "step": 50430 }, { "epoch": 0.82, "learning_rate": 2.483867735470942e-05, "loss": 2.0761, "step": 50440 }, { "epoch": 0.82, "learning_rate": 2.483366733466934e-05, "loss": 2.053, "step": 50450 }, { "epoch": 0.82, "learning_rate": 2.4828657314629257e-05, "loss": 2.0526, "step": 50460 }, { "epoch": 0.82, "learning_rate": 2.482364729458918e-05, "loss": 2.0567, "step": 50470 }, { "epoch": 0.82, "learning_rate": 2.48186372745491e-05, "loss": 2.0725, "step": 50480 }, { "epoch": 0.82, "learning_rate": 2.481362725450902e-05, "loss": 2.1127, "step": 50490 }, { "epoch": 0.83, "learning_rate": 2.480861723446894e-05, "loss": 2.0716, "step": 50500 }, { "epoch": 0.83, "learning_rate": 2.480360721442886e-05, "loss": 2.0881, "step": 50510 }, { "epoch": 0.83, "learning_rate": 2.4798597194388778e-05, "loss": 2.053, "step": 50520 }, { "epoch": 0.83, "learning_rate": 2.47935871743487e-05, "loss": 2.0671, "step": 50530 }, { "epoch": 0.83, "learning_rate": 2.478857715430862e-05, "loss": 2.0931, "step": 50540 }, { "epoch": 0.83, "learning_rate": 2.4783567134268536e-05, "loss": 2.0532, "step": 50550 }, { "epoch": 0.83, "learning_rate": 2.4778557114228457e-05, "loss": 2.0575, "step": 50560 }, { "epoch": 0.83, "learning_rate": 2.4773547094188378e-05, "loss": 2.0955, "step": 50570 }, { "epoch": 0.83, "learning_rate": 2.4768537074148298e-05, "loss": 2.0564, "step": 50580 }, { "epoch": 0.83, "learning_rate": 2.476352705410822e-05, "loss": 2.0312, "step": 50590 }, { "epoch": 0.83, "learning_rate": 2.4758517034068136e-05, "loss": 2.0157, "step": 50600 }, { "epoch": 0.83, "learning_rate": 2.4753507014028057e-05, "loss": 2.0623, "step": 50610 }, { "epoch": 0.83, "learning_rate": 2.4748496993987977e-05, "loss": 2.0689, "step": 50620 }, { "epoch": 0.83, "learning_rate": 2.4743486973947898e-05, "loss": 2.0642, "step": 50630 }, { "epoch": 0.83, "learning_rate": 2.4738476953907815e-05, "loss": 2.0931, "step": 50640 }, { "epoch": 0.83, "learning_rate": 2.4733466933867736e-05, "loss": 2.0654, "step": 50650 }, { "epoch": 0.83, "learning_rate": 2.4728456913827657e-05, "loss": 2.0292, "step": 50660 }, { "epoch": 0.83, "learning_rate": 2.4723446893787577e-05, "loss": 2.0428, "step": 50670 }, { "epoch": 0.83, "learning_rate": 2.4718436873747498e-05, "loss": 2.0386, "step": 50680 }, { "epoch": 0.83, "learning_rate": 2.4713426853707415e-05, "loss": 2.0491, "step": 50690 }, { "epoch": 0.83, "learning_rate": 2.4708416833667336e-05, "loss": 2.0599, "step": 50700 }, { "epoch": 0.83, "learning_rate": 2.4703406813627256e-05, "loss": 2.0272, "step": 50710 }, { "epoch": 0.83, "learning_rate": 2.4698396793587174e-05, "loss": 2.0347, "step": 50720 }, { "epoch": 0.83, "learning_rate": 2.4693386773547094e-05, "loss": 2.0708, "step": 50730 }, { "epoch": 0.83, "learning_rate": 2.4688376753507015e-05, "loss": 2.0043, "step": 50740 }, { "epoch": 0.83, "learning_rate": 2.4683366733466932e-05, "loss": 2.0956, "step": 50750 }, { "epoch": 0.83, "learning_rate": 2.4678356713426856e-05, "loss": 2.0603, "step": 50760 }, { "epoch": 0.83, "learning_rate": 2.4673346693386777e-05, "loss": 2.0397, "step": 50770 }, { "epoch": 0.83, "learning_rate": 2.4668336673346694e-05, "loss": 2.0504, "step": 50780 }, { "epoch": 0.83, "learning_rate": 2.4663326653306615e-05, "loss": 2.0643, "step": 50790 }, { "epoch": 0.83, "learning_rate": 2.4658316633266535e-05, "loss": 2.0645, "step": 50800 }, { "epoch": 0.83, "learning_rate": 2.4653306613226453e-05, "loss": 2.0397, "step": 50810 }, { "epoch": 0.83, "learning_rate": 2.4648296593186373e-05, "loss": 2.0393, "step": 50820 }, { "epoch": 0.83, "learning_rate": 2.4643286573146294e-05, "loss": 2.1067, "step": 50830 }, { "epoch": 0.83, "learning_rate": 2.463827655310621e-05, "loss": 2.0836, "step": 50840 }, { "epoch": 0.83, "learning_rate": 2.4633266533066132e-05, "loss": 2.0421, "step": 50850 }, { "epoch": 0.83, "learning_rate": 2.4628256513026056e-05, "loss": 1.9994, "step": 50860 }, { "epoch": 0.83, "learning_rate": 2.4623246492985973e-05, "loss": 2.0427, "step": 50870 }, { "epoch": 0.83, "learning_rate": 2.4618236472945894e-05, "loss": 2.0712, "step": 50880 }, { "epoch": 0.83, "learning_rate": 2.4613226452905814e-05, "loss": 2.0798, "step": 50890 }, { "epoch": 0.83, "learning_rate": 2.460821643286573e-05, "loss": 2.0695, "step": 50900 }, { "epoch": 0.83, "learning_rate": 2.4603206412825652e-05, "loss": 2.042, "step": 50910 }, { "epoch": 0.83, "learning_rate": 2.4598196392785573e-05, "loss": 2.0892, "step": 50920 }, { "epoch": 0.83, "learning_rate": 2.459318637274549e-05, "loss": 2.0889, "step": 50930 }, { "epoch": 0.83, "learning_rate": 2.458817635270541e-05, "loss": 2.0709, "step": 50940 }, { "epoch": 0.83, "learning_rate": 2.458316633266533e-05, "loss": 2.052, "step": 50950 }, { "epoch": 0.83, "learning_rate": 2.4578156312625252e-05, "loss": 2.0707, "step": 50960 }, { "epoch": 0.83, "learning_rate": 2.4573146292585173e-05, "loss": 2.0436, "step": 50970 }, { "epoch": 0.83, "learning_rate": 2.4568136272545093e-05, "loss": 2.0503, "step": 50980 }, { "epoch": 0.83, "learning_rate": 2.456312625250501e-05, "loss": 2.0542, "step": 50990 }, { "epoch": 0.83, "learning_rate": 2.455811623246493e-05, "loss": 2.0583, "step": 51000 }, { "epoch": 0.83, "eval_loss": 2.0365843772888184, "eval_mean_f1": 0.6523375344065092, "eval_rouge1_f1": 0.7112144248925013, "eval_rouge1_precision": 0.8218652423773632, "eval_rouge1_recall": 0.6598292974407394, "eval_rouge2_f1": 0.5667658412518727, "eval_rouge2_precision": 0.6600449321457632, "eval_rouge2_recall": 0.5252212793363122, "eval_rougeL_f1": 0.6790323370751536, "eval_rougeL_precision": 0.7833492505040781, "eval_rougeL_recall": 0.6305367837980339, "eval_runtime": 64.492, "eval_samples_per_second": 15.878, "eval_steps_per_second": 1.985, "step": 51000 }, { "epoch": 0.83, "learning_rate": 2.4553106212424852e-05, "loss": 2.0501, "step": 51010 }, { "epoch": 0.83, "learning_rate": 2.454809619238477e-05, "loss": 2.0525, "step": 51020 }, { "epoch": 0.83, "learning_rate": 2.454308617234469e-05, "loss": 2.033, "step": 51030 }, { "epoch": 0.83, "learning_rate": 2.453807615230461e-05, "loss": 2.0914, "step": 51040 }, { "epoch": 0.83, "learning_rate": 2.4533066132264528e-05, "loss": 2.0371, "step": 51050 }, { "epoch": 0.83, "learning_rate": 2.4528056112224452e-05, "loss": 2.0878, "step": 51060 }, { "epoch": 0.83, "learning_rate": 2.4523046092184372e-05, "loss": 2.0925, "step": 51070 }, { "epoch": 0.83, "learning_rate": 2.451803607214429e-05, "loss": 2.0392, "step": 51080 }, { "epoch": 0.83, "learning_rate": 2.451302605210421e-05, "loss": 2.055, "step": 51090 }, { "epoch": 0.83, "learning_rate": 2.450801603206413e-05, "loss": 2.0235, "step": 51100 }, { "epoch": 0.84, "learning_rate": 2.4503006012024048e-05, "loss": 2.0769, "step": 51110 }, { "epoch": 0.84, "learning_rate": 2.449799599198397e-05, "loss": 2.0692, "step": 51120 }, { "epoch": 0.84, "learning_rate": 2.449298597194389e-05, "loss": 2.0433, "step": 51130 }, { "epoch": 0.84, "learning_rate": 2.4487975951903807e-05, "loss": 2.0603, "step": 51140 }, { "epoch": 0.84, "learning_rate": 2.448296593186373e-05, "loss": 2.0121, "step": 51150 }, { "epoch": 0.84, "learning_rate": 2.4477955911823648e-05, "loss": 2.0446, "step": 51160 }, { "epoch": 0.84, "learning_rate": 2.447294589178357e-05, "loss": 2.0619, "step": 51170 }, { "epoch": 0.84, "learning_rate": 2.446793587174349e-05, "loss": 2.0343, "step": 51180 }, { "epoch": 0.84, "learning_rate": 2.4462925851703407e-05, "loss": 2.0581, "step": 51190 }, { "epoch": 0.84, "learning_rate": 2.4457915831663327e-05, "loss": 2.0936, "step": 51200 }, { "epoch": 0.84, "learning_rate": 2.4452905811623248e-05, "loss": 2.0714, "step": 51210 }, { "epoch": 0.84, "learning_rate": 2.444789579158317e-05, "loss": 2.0948, "step": 51220 }, { "epoch": 0.84, "learning_rate": 2.4442885771543086e-05, "loss": 2.0854, "step": 51230 }, { "epoch": 0.84, "learning_rate": 2.4437875751503006e-05, "loss": 2.0966, "step": 51240 }, { "epoch": 0.84, "learning_rate": 2.4432865731462927e-05, "loss": 2.0641, "step": 51250 }, { "epoch": 0.84, "learning_rate": 2.4427855711422848e-05, "loss": 2.0397, "step": 51260 }, { "epoch": 0.84, "learning_rate": 2.4422845691382768e-05, "loss": 2.061, "step": 51270 }, { "epoch": 0.84, "learning_rate": 2.4417835671342686e-05, "loss": 2.107, "step": 51280 }, { "epoch": 0.84, "learning_rate": 2.4412825651302606e-05, "loss": 2.0596, "step": 51290 }, { "epoch": 0.84, "learning_rate": 2.4407815631262527e-05, "loss": 2.006, "step": 51300 }, { "epoch": 0.84, "learning_rate": 2.4402805611222444e-05, "loss": 2.0696, "step": 51310 }, { "epoch": 0.84, "learning_rate": 2.4397795591182365e-05, "loss": 1.9953, "step": 51320 }, { "epoch": 0.84, "learning_rate": 2.4392785571142285e-05, "loss": 2.0624, "step": 51330 }, { "epoch": 0.84, "learning_rate": 2.4387775551102206e-05, "loss": 2.0414, "step": 51340 }, { "epoch": 0.84, "learning_rate": 2.4382765531062127e-05, "loss": 2.0795, "step": 51350 }, { "epoch": 0.84, "learning_rate": 2.4377755511022047e-05, "loss": 2.0288, "step": 51360 }, { "epoch": 0.84, "learning_rate": 2.4372745490981965e-05, "loss": 2.073, "step": 51370 }, { "epoch": 0.84, "learning_rate": 2.4367735470941885e-05, "loss": 2.0382, "step": 51380 }, { "epoch": 0.84, "learning_rate": 2.4362725450901806e-05, "loss": 2.037, "step": 51390 }, { "epoch": 0.84, "learning_rate": 2.4357715430861723e-05, "loss": 2.0588, "step": 51400 }, { "epoch": 0.84, "learning_rate": 2.4352705410821644e-05, "loss": 2.0501, "step": 51410 }, { "epoch": 0.84, "learning_rate": 2.4347695390781564e-05, "loss": 2.0906, "step": 51420 }, { "epoch": 0.84, "learning_rate": 2.434268537074148e-05, "loss": 2.0419, "step": 51430 }, { "epoch": 0.84, "learning_rate": 2.4337675350701402e-05, "loss": 2.0957, "step": 51440 }, { "epoch": 0.84, "learning_rate": 2.4332665330661326e-05, "loss": 2.0618, "step": 51450 }, { "epoch": 0.84, "learning_rate": 2.4327655310621244e-05, "loss": 2.0545, "step": 51460 }, { "epoch": 0.84, "learning_rate": 2.4322645290581164e-05, "loss": 2.102, "step": 51470 }, { "epoch": 0.84, "learning_rate": 2.4317635270541085e-05, "loss": 2.0744, "step": 51480 }, { "epoch": 0.84, "learning_rate": 2.4312625250501002e-05, "loss": 2.0609, "step": 51490 }, { "epoch": 0.84, "learning_rate": 2.4307615230460923e-05, "loss": 2.093, "step": 51500 }, { "epoch": 0.84, "learning_rate": 2.4302605210420843e-05, "loss": 2.0274, "step": 51510 }, { "epoch": 0.84, "learning_rate": 2.429759519038076e-05, "loss": 2.0726, "step": 51520 }, { "epoch": 0.84, "learning_rate": 2.429258517034068e-05, "loss": 2.0792, "step": 51530 }, { "epoch": 0.84, "learning_rate": 2.4287575150300602e-05, "loss": 2.0686, "step": 51540 }, { "epoch": 0.84, "learning_rate": 2.4282565130260523e-05, "loss": 2.0821, "step": 51550 }, { "epoch": 0.84, "learning_rate": 2.4277555110220443e-05, "loss": 2.0537, "step": 51560 }, { "epoch": 0.84, "learning_rate": 2.4272545090180364e-05, "loss": 2.0672, "step": 51570 }, { "epoch": 0.84, "learning_rate": 2.426753507014028e-05, "loss": 2.0532, "step": 51580 }, { "epoch": 0.84, "learning_rate": 2.42625250501002e-05, "loss": 2.0715, "step": 51590 }, { "epoch": 0.84, "learning_rate": 2.4257515030060122e-05, "loss": 2.1111, "step": 51600 }, { "epoch": 0.84, "learning_rate": 2.425250501002004e-05, "loss": 2.0805, "step": 51610 }, { "epoch": 0.84, "learning_rate": 2.424749498997996e-05, "loss": 2.0828, "step": 51620 }, { "epoch": 0.84, "learning_rate": 2.424248496993988e-05, "loss": 2.0654, "step": 51630 }, { "epoch": 0.84, "learning_rate": 2.4237474949899798e-05, "loss": 2.0334, "step": 51640 }, { "epoch": 0.84, "learning_rate": 2.4232464929859722e-05, "loss": 2.0913, "step": 51650 }, { "epoch": 0.84, "learning_rate": 2.4227454909819643e-05, "loss": 2.0634, "step": 51660 }, { "epoch": 0.84, "learning_rate": 2.422244488977956e-05, "loss": 2.0096, "step": 51670 }, { "epoch": 0.84, "learning_rate": 2.421743486973948e-05, "loss": 2.051, "step": 51680 }, { "epoch": 0.84, "learning_rate": 2.42124248496994e-05, "loss": 2.0535, "step": 51690 }, { "epoch": 0.84, "learning_rate": 2.420741482965932e-05, "loss": 2.0284, "step": 51700 }, { "epoch": 0.84, "learning_rate": 2.420240480961924e-05, "loss": 2.0447, "step": 51710 }, { "epoch": 0.85, "learning_rate": 2.419739478957916e-05, "loss": 2.0284, "step": 51720 }, { "epoch": 0.85, "learning_rate": 2.4192384769539077e-05, "loss": 2.0963, "step": 51730 }, { "epoch": 0.85, "learning_rate": 2.4187374749499e-05, "loss": 2.0233, "step": 51740 }, { "epoch": 0.85, "learning_rate": 2.418236472945892e-05, "loss": 2.0595, "step": 51750 }, { "epoch": 0.85, "learning_rate": 2.417735470941884e-05, "loss": 2.0387, "step": 51760 }, { "epoch": 0.85, "learning_rate": 2.417234468937876e-05, "loss": 2.0426, "step": 51770 }, { "epoch": 0.85, "learning_rate": 2.416733466933868e-05, "loss": 2.0357, "step": 51780 }, { "epoch": 0.85, "learning_rate": 2.4162324649298598e-05, "loss": 2.056, "step": 51790 }, { "epoch": 0.85, "learning_rate": 2.4157314629258518e-05, "loss": 2.0331, "step": 51800 }, { "epoch": 0.85, "learning_rate": 2.415230460921844e-05, "loss": 2.0437, "step": 51810 }, { "epoch": 0.85, "learning_rate": 2.4147294589178356e-05, "loss": 2.048, "step": 51820 }, { "epoch": 0.85, "learning_rate": 2.4142284569138277e-05, "loss": 2.0833, "step": 51830 }, { "epoch": 0.85, "learning_rate": 2.4137274549098197e-05, "loss": 2.0644, "step": 51840 }, { "epoch": 0.85, "learning_rate": 2.4132264529058118e-05, "loss": 2.0618, "step": 51850 }, { "epoch": 0.85, "learning_rate": 2.412725450901804e-05, "loss": 2.0468, "step": 51860 }, { "epoch": 0.85, "learning_rate": 2.4122244488977956e-05, "loss": 2.0588, "step": 51870 }, { "epoch": 0.85, "learning_rate": 2.4117234468937877e-05, "loss": 2.0295, "step": 51880 }, { "epoch": 0.85, "learning_rate": 2.4112224448897797e-05, "loss": 2.0659, "step": 51890 }, { "epoch": 0.85, "learning_rate": 2.4107214428857718e-05, "loss": 2.0723, "step": 51900 }, { "epoch": 0.85, "learning_rate": 2.4102204408817635e-05, "loss": 2.0629, "step": 51910 }, { "epoch": 0.85, "learning_rate": 2.4097194388777556e-05, "loss": 2.0536, "step": 51920 }, { "epoch": 0.85, "learning_rate": 2.4092184368737476e-05, "loss": 2.0782, "step": 51930 }, { "epoch": 0.85, "learning_rate": 2.4087174348697397e-05, "loss": 2.0501, "step": 51940 }, { "epoch": 0.85, "learning_rate": 2.4082164328657318e-05, "loss": 2.0407, "step": 51950 }, { "epoch": 0.85, "learning_rate": 2.4077154308617235e-05, "loss": 2.0479, "step": 51960 }, { "epoch": 0.85, "learning_rate": 2.4072144288577156e-05, "loss": 2.1122, "step": 51970 }, { "epoch": 0.85, "learning_rate": 2.4067134268537076e-05, "loss": 2.0829, "step": 51980 }, { "epoch": 0.85, "learning_rate": 2.4062124248496993e-05, "loss": 2.0735, "step": 51990 }, { "epoch": 0.85, "learning_rate": 2.4057114228456914e-05, "loss": 2.0925, "step": 52000 }, { "epoch": 0.85, "eval_loss": 2.03641414642334, "eval_mean_f1": 0.6558958453041359, "eval_rouge1_f1": 0.7130939467852919, "eval_rouge1_precision": 0.8223956015915892, "eval_rouge1_recall": 0.6631245113294724, "eval_rouge2_f1": 0.57216956599189, "eval_rouge2_precision": 0.6641576353063171, "eval_rouge2_recall": 0.5320803343542053, "eval_rougeL_f1": 0.6824240231352259, "eval_rougeL_precision": 0.7845769475271713, "eval_rougeL_recall": 0.6354282505909598, "eval_runtime": 63.5695, "eval_samples_per_second": 16.108, "eval_steps_per_second": 2.014, "step": 52000 }, { "epoch": 0.85, "learning_rate": 2.4052104208416835e-05, "loss": 2.0396, "step": 52010 }, { "epoch": 0.85, "learning_rate": 2.4047094188376752e-05, "loss": 2.1498, "step": 52020 }, { "epoch": 0.85, "learning_rate": 2.4042084168336673e-05, "loss": 2.0451, "step": 52030 }, { "epoch": 0.85, "learning_rate": 2.4037074148296597e-05, "loss": 2.0823, "step": 52040 }, { "epoch": 0.85, "learning_rate": 2.4032064128256514e-05, "loss": 2.0166, "step": 52050 }, { "epoch": 0.85, "learning_rate": 2.4027054108216435e-05, "loss": 2.0789, "step": 52060 }, { "epoch": 0.85, "learning_rate": 2.4022044088176355e-05, "loss": 2.0865, "step": 52070 }, { "epoch": 0.85, "learning_rate": 2.4017034068136272e-05, "loss": 2.0483, "step": 52080 }, { "epoch": 0.85, "learning_rate": 2.4012024048096193e-05, "loss": 2.021, "step": 52090 }, { "epoch": 0.85, "learning_rate": 2.4007014028056114e-05, "loss": 2.0527, "step": 52100 }, { "epoch": 0.85, "learning_rate": 2.400200400801603e-05, "loss": 2.0444, "step": 52110 }, { "epoch": 0.85, "learning_rate": 2.399699398797595e-05, "loss": 2.0858, "step": 52120 }, { "epoch": 0.85, "learning_rate": 2.3991983967935872e-05, "loss": 2.0488, "step": 52130 }, { "epoch": 0.85, "learning_rate": 2.3986973947895793e-05, "loss": 2.0623, "step": 52140 }, { "epoch": 0.85, "learning_rate": 2.3981963927855714e-05, "loss": 2.0224, "step": 52150 }, { "epoch": 0.85, "learning_rate": 2.3976953907815634e-05, "loss": 2.0381, "step": 52160 }, { "epoch": 0.85, "learning_rate": 2.397194388777555e-05, "loss": 2.0571, "step": 52170 }, { "epoch": 0.85, "learning_rate": 2.3966933867735472e-05, "loss": 2.0688, "step": 52180 }, { "epoch": 0.85, "learning_rate": 2.3961923847695393e-05, "loss": 2.0579, "step": 52190 }, { "epoch": 0.85, "learning_rate": 2.395691382765531e-05, "loss": 2.1044, "step": 52200 }, { "epoch": 0.85, "learning_rate": 2.395190380761523e-05, "loss": 2.068, "step": 52210 }, { "epoch": 0.85, "learning_rate": 2.394689378757515e-05, "loss": 2.0312, "step": 52220 }, { "epoch": 0.85, "learning_rate": 2.3941883767535072e-05, "loss": 2.1323, "step": 52230 }, { "epoch": 0.85, "learning_rate": 2.3936873747494993e-05, "loss": 2.0579, "step": 52240 }, { "epoch": 0.85, "learning_rate": 2.3931863727454913e-05, "loss": 2.0756, "step": 52250 }, { "epoch": 0.85, "learning_rate": 2.392685370741483e-05, "loss": 2.0617, "step": 52260 }, { "epoch": 0.85, "learning_rate": 2.392184368737475e-05, "loss": 2.0905, "step": 52270 }, { "epoch": 0.85, "learning_rate": 2.3916833667334672e-05, "loss": 2.0498, "step": 52280 }, { "epoch": 0.85, "learning_rate": 2.391182364729459e-05, "loss": 2.0977, "step": 52290 }, { "epoch": 0.85, "learning_rate": 2.390681362725451e-05, "loss": 2.0771, "step": 52300 }, { "epoch": 0.85, "learning_rate": 2.390180360721443e-05, "loss": 2.0336, "step": 52310 }, { "epoch": 0.85, "learning_rate": 2.3896793587174348e-05, "loss": 2.0634, "step": 52320 }, { "epoch": 0.86, "learning_rate": 2.389178356713427e-05, "loss": 2.0276, "step": 52330 }, { "epoch": 0.86, "learning_rate": 2.3886773547094192e-05, "loss": 2.0452, "step": 52340 }, { "epoch": 0.86, "learning_rate": 2.388176352705411e-05, "loss": 2.0693, "step": 52350 }, { "epoch": 0.86, "learning_rate": 2.387675350701403e-05, "loss": 2.0206, "step": 52360 }, { "epoch": 0.86, "learning_rate": 2.387174348697395e-05, "loss": 2.0621, "step": 52370 }, { "epoch": 0.86, "learning_rate": 2.3866733466933868e-05, "loss": 2.1181, "step": 52380 }, { "epoch": 0.86, "learning_rate": 2.386172344689379e-05, "loss": 2.0399, "step": 52390 }, { "epoch": 0.86, "learning_rate": 2.385671342685371e-05, "loss": 2.0509, "step": 52400 }, { "epoch": 0.86, "learning_rate": 2.3851703406813627e-05, "loss": 2.0339, "step": 52410 }, { "epoch": 0.86, "learning_rate": 2.3846693386773547e-05, "loss": 2.0394, "step": 52420 }, { "epoch": 0.86, "learning_rate": 2.3841683366733468e-05, "loss": 2.0376, "step": 52430 }, { "epoch": 0.86, "learning_rate": 2.383667334669339e-05, "loss": 2.07, "step": 52440 }, { "epoch": 0.86, "learning_rate": 2.383166332665331e-05, "loss": 2.0343, "step": 52450 }, { "epoch": 0.86, "learning_rate": 2.382665330661323e-05, "loss": 2.0515, "step": 52460 }, { "epoch": 0.86, "learning_rate": 2.3821643286573147e-05, "loss": 2.0665, "step": 52470 }, { "epoch": 0.86, "learning_rate": 2.3816633266533068e-05, "loss": 2.0751, "step": 52480 }, { "epoch": 0.86, "learning_rate": 2.3811623246492988e-05, "loss": 2.0503, "step": 52490 }, { "epoch": 0.86, "learning_rate": 2.3806613226452906e-05, "loss": 2.0321, "step": 52500 }, { "epoch": 0.86, "learning_rate": 2.3801603206412826e-05, "loss": 2.1084, "step": 52510 }, { "epoch": 0.86, "learning_rate": 2.3796593186372747e-05, "loss": 2.0837, "step": 52520 }, { "epoch": 0.86, "learning_rate": 2.3791583166332667e-05, "loss": 2.0343, "step": 52530 }, { "epoch": 0.86, "learning_rate": 2.3786573146292588e-05, "loss": 2.0853, "step": 52540 }, { "epoch": 0.86, "learning_rate": 2.3781563126252505e-05, "loss": 2.0741, "step": 52550 }, { "epoch": 0.86, "learning_rate": 2.3776553106212426e-05, "loss": 2.0907, "step": 52560 }, { "epoch": 0.86, "learning_rate": 2.3771543086172347e-05, "loss": 2.0517, "step": 52570 }, { "epoch": 0.86, "learning_rate": 2.3766533066132264e-05, "loss": 2.0423, "step": 52580 }, { "epoch": 0.86, "learning_rate": 2.3761523046092185e-05, "loss": 2.037, "step": 52590 }, { "epoch": 0.86, "learning_rate": 2.3756513026052105e-05, "loss": 2.097, "step": 52600 }, { "epoch": 0.86, "learning_rate": 2.3751503006012026e-05, "loss": 2.054, "step": 52610 }, { "epoch": 0.86, "learning_rate": 2.3746492985971943e-05, "loss": 2.0777, "step": 52620 }, { "epoch": 0.86, "learning_rate": 2.3741482965931867e-05, "loss": 2.0873, "step": 52630 }, { "epoch": 0.86, "learning_rate": 2.3736472945891784e-05, "loss": 2.0616, "step": 52640 }, { "epoch": 0.86, "learning_rate": 2.3731462925851705e-05, "loss": 2.0416, "step": 52650 }, { "epoch": 0.86, "learning_rate": 2.3726452905811626e-05, "loss": 2.0604, "step": 52660 }, { "epoch": 0.86, "learning_rate": 2.3721442885771543e-05, "loss": 2.0956, "step": 52670 }, { "epoch": 0.86, "learning_rate": 2.3716432865731464e-05, "loss": 2.0607, "step": 52680 }, { "epoch": 0.86, "learning_rate": 2.3711422845691384e-05, "loss": 2.0585, "step": 52690 }, { "epoch": 0.86, "learning_rate": 2.37064128256513e-05, "loss": 2.109, "step": 52700 }, { "epoch": 0.86, "learning_rate": 2.3701402805611222e-05, "loss": 2.0701, "step": 52710 }, { "epoch": 0.86, "learning_rate": 2.3696392785571143e-05, "loss": 2.0387, "step": 52720 }, { "epoch": 0.86, "learning_rate": 2.3691382765531063e-05, "loss": 2.0306, "step": 52730 }, { "epoch": 0.86, "learning_rate": 2.3686372745490984e-05, "loss": 2.0884, "step": 52740 }, { "epoch": 0.86, "learning_rate": 2.3681362725450905e-05, "loss": 2.0589, "step": 52750 }, { "epoch": 0.86, "learning_rate": 2.3676352705410822e-05, "loss": 2.0427, "step": 52760 }, { "epoch": 0.86, "learning_rate": 2.3671342685370743e-05, "loss": 2.0177, "step": 52770 }, { "epoch": 0.86, "learning_rate": 2.3666332665330663e-05, "loss": 2.0324, "step": 52780 }, { "epoch": 0.86, "learning_rate": 2.366132264529058e-05, "loss": 2.0473, "step": 52790 }, { "epoch": 0.86, "learning_rate": 2.36563126252505e-05, "loss": 2.1038, "step": 52800 }, { "epoch": 0.86, "learning_rate": 2.365130260521042e-05, "loss": 2.0709, "step": 52810 }, { "epoch": 0.86, "learning_rate": 2.3646292585170342e-05, "loss": 2.0716, "step": 52820 }, { "epoch": 0.86, "learning_rate": 2.3641282565130263e-05, "loss": 2.0009, "step": 52830 }, { "epoch": 0.86, "learning_rate": 2.3636272545090184e-05, "loss": 2.0493, "step": 52840 }, { "epoch": 0.86, "learning_rate": 2.36312625250501e-05, "loss": 2.049, "step": 52850 }, { "epoch": 0.86, "learning_rate": 2.362625250501002e-05, "loss": 2.048, "step": 52860 }, { "epoch": 0.86, "learning_rate": 2.3621242484969942e-05, "loss": 2.0416, "step": 52870 }, { "epoch": 0.86, "learning_rate": 2.361623246492986e-05, "loss": 2.0728, "step": 52880 }, { "epoch": 0.86, "learning_rate": 2.361122244488978e-05, "loss": 2.0394, "step": 52890 }, { "epoch": 0.86, "learning_rate": 2.36062124248497e-05, "loss": 2.0376, "step": 52900 }, { "epoch": 0.86, "learning_rate": 2.3601202404809618e-05, "loss": 2.0423, "step": 52910 }, { "epoch": 0.86, "learning_rate": 2.3596192384769542e-05, "loss": 2.0296, "step": 52920 }, { "epoch": 0.86, "learning_rate": 2.3591182364729463e-05, "loss": 2.0809, "step": 52930 }, { "epoch": 0.87, "learning_rate": 2.358617234468938e-05, "loss": 2.0628, "step": 52940 }, { "epoch": 0.87, "learning_rate": 2.35811623246493e-05, "loss": 2.0196, "step": 52950 }, { "epoch": 0.87, "learning_rate": 2.357615230460922e-05, "loss": 2.0703, "step": 52960 }, { "epoch": 0.87, "learning_rate": 2.357114228456914e-05, "loss": 2.0538, "step": 52970 }, { "epoch": 0.87, "learning_rate": 2.356613226452906e-05, "loss": 2.0544, "step": 52980 }, { "epoch": 0.87, "learning_rate": 2.356112224448898e-05, "loss": 2.0666, "step": 52990 }, { "epoch": 0.87, "learning_rate": 2.3556112224448897e-05, "loss": 2.0446, "step": 53000 }, { "epoch": 0.87, "eval_loss": 2.037872314453125, "eval_mean_f1": 0.6548418685090246, "eval_rouge1_f1": 0.7131843580147572, "eval_rouge1_precision": 0.822499879757318, "eval_rouge1_recall": 0.6622425955755619, "eval_rouge2_f1": 0.5697996564730001, "eval_rouge2_precision": 0.6612729237179917, "eval_rouge2_recall": 0.5288781485131318, "eval_rougeL_f1": 0.6815415910393166, "eval_rougeL_precision": 0.7843279489336614, "eval_rougeL_recall": 0.6337286394400157, "eval_runtime": 64.7934, "eval_samples_per_second": 15.804, "eval_steps_per_second": 1.976, "step": 53000 }, { "epoch": 0.87, "learning_rate": 2.3551102204408818e-05, "loss": 2.0714, "step": 53010 }, { "epoch": 0.87, "learning_rate": 2.3546092184368738e-05, "loss": 2.0609, "step": 53020 }, { "epoch": 0.87, "learning_rate": 2.354108216432866e-05, "loss": 2.0605, "step": 53030 }, { "epoch": 0.87, "learning_rate": 2.353607214428858e-05, "loss": 2.0588, "step": 53040 }, { "epoch": 0.87, "learning_rate": 2.35310621242485e-05, "loss": 2.0115, "step": 53050 }, { "epoch": 0.87, "learning_rate": 2.3526052104208417e-05, "loss": 2.0655, "step": 53060 }, { "epoch": 0.87, "learning_rate": 2.3521042084168338e-05, "loss": 2.0407, "step": 53070 }, { "epoch": 0.87, "learning_rate": 2.351603206412826e-05, "loss": 1.9978, "step": 53080 }, { "epoch": 0.87, "learning_rate": 2.3511022044088176e-05, "loss": 2.0656, "step": 53090 }, { "epoch": 0.87, "learning_rate": 2.3506012024048097e-05, "loss": 2.0496, "step": 53100 }, { "epoch": 0.87, "learning_rate": 2.3501002004008017e-05, "loss": 2.1032, "step": 53110 }, { "epoch": 0.87, "learning_rate": 2.3495991983967938e-05, "loss": 2.0317, "step": 53120 }, { "epoch": 0.87, "learning_rate": 2.349098196392786e-05, "loss": 2.0505, "step": 53130 }, { "epoch": 0.87, "learning_rate": 2.3485971943887776e-05, "loss": 2.0616, "step": 53140 }, { "epoch": 0.87, "learning_rate": 2.3480961923847696e-05, "loss": 2.0363, "step": 53150 }, { "epoch": 0.87, "learning_rate": 2.3475951903807617e-05, "loss": 2.0199, "step": 53160 }, { "epoch": 0.87, "learning_rate": 2.3470941883767538e-05, "loss": 2.0906, "step": 53170 }, { "epoch": 0.87, "learning_rate": 2.3465931863727455e-05, "loss": 2.0971, "step": 53180 }, { "epoch": 0.87, "learning_rate": 2.3460921843687376e-05, "loss": 2.0671, "step": 53190 }, { "epoch": 0.87, "learning_rate": 2.3455911823647296e-05, "loss": 2.0555, "step": 53200 }, { "epoch": 0.87, "learning_rate": 2.3450901803607213e-05, "loss": 2.0231, "step": 53210 }, { "epoch": 0.87, "learning_rate": 2.3445891783567137e-05, "loss": 2.0196, "step": 53220 }, { "epoch": 0.87, "learning_rate": 2.3440881763527055e-05, "loss": 2.0088, "step": 53230 }, { "epoch": 0.87, "learning_rate": 2.3435871743486975e-05, "loss": 2.0405, "step": 53240 }, { "epoch": 0.87, "learning_rate": 2.3430861723446896e-05, "loss": 2.0545, "step": 53250 }, { "epoch": 0.87, "learning_rate": 2.3425851703406813e-05, "loss": 2.0735, "step": 53260 }, { "epoch": 0.87, "learning_rate": 2.3420841683366734e-05, "loss": 2.0292, "step": 53270 }, { "epoch": 0.87, "learning_rate": 2.3415831663326655e-05, "loss": 2.0424, "step": 53280 }, { "epoch": 0.87, "learning_rate": 2.3410821643286572e-05, "loss": 2.043, "step": 53290 }, { "epoch": 0.87, "learning_rate": 2.3405811623246492e-05, "loss": 2.0984, "step": 53300 }, { "epoch": 0.87, "learning_rate": 2.3400801603206413e-05, "loss": 2.0445, "step": 53310 }, { "epoch": 0.87, "learning_rate": 2.3395791583166334e-05, "loss": 2.0455, "step": 53320 }, { "epoch": 0.87, "learning_rate": 2.3390781563126254e-05, "loss": 2.0246, "step": 53330 }, { "epoch": 0.87, "learning_rate": 2.3385771543086175e-05, "loss": 2.0315, "step": 53340 }, { "epoch": 0.87, "learning_rate": 2.3380761523046092e-05, "loss": 2.0793, "step": 53350 }, { "epoch": 0.87, "learning_rate": 2.3375751503006013e-05, "loss": 2.0438, "step": 53360 }, { "epoch": 0.87, "learning_rate": 2.3370741482965934e-05, "loss": 2.0754, "step": 53370 }, { "epoch": 0.87, "learning_rate": 2.336573146292585e-05, "loss": 2.0651, "step": 53380 }, { "epoch": 0.87, "learning_rate": 2.336072144288577e-05, "loss": 2.0725, "step": 53390 }, { "epoch": 0.87, "learning_rate": 2.3355711422845692e-05, "loss": 2.0611, "step": 53400 }, { "epoch": 0.87, "learning_rate": 2.3350701402805613e-05, "loss": 2.0562, "step": 53410 }, { "epoch": 0.87, "learning_rate": 2.3345691382765533e-05, "loss": 2.0917, "step": 53420 }, { "epoch": 0.87, "learning_rate": 2.3340681362725454e-05, "loss": 2.0509, "step": 53430 }, { "epoch": 0.87, "learning_rate": 2.333567134268537e-05, "loss": 2.0347, "step": 53440 }, { "epoch": 0.87, "learning_rate": 2.3330661322645292e-05, "loss": 2.0791, "step": 53450 }, { "epoch": 0.87, "learning_rate": 2.3325651302605213e-05, "loss": 2.041, "step": 53460 }, { "epoch": 0.87, "learning_rate": 2.332064128256513e-05, "loss": 2.079, "step": 53470 }, { "epoch": 0.87, "learning_rate": 2.331563126252505e-05, "loss": 2.0988, "step": 53480 }, { "epoch": 0.87, "learning_rate": 2.331062124248497e-05, "loss": 2.0098, "step": 53490 }, { "epoch": 0.87, "learning_rate": 2.330561122244489e-05, "loss": 2.0714, "step": 53500 }, { "epoch": 0.87, "learning_rate": 2.3300601202404812e-05, "loss": 2.0584, "step": 53510 }, { "epoch": 0.87, "learning_rate": 2.3295591182364733e-05, "loss": 2.0624, "step": 53520 }, { "epoch": 0.87, "learning_rate": 2.329058116232465e-05, "loss": 2.0878, "step": 53530 }, { "epoch": 0.87, "learning_rate": 2.328557114228457e-05, "loss": 2.0549, "step": 53540 }, { "epoch": 0.88, "learning_rate": 2.328056112224449e-05, "loss": 2.0317, "step": 53550 }, { "epoch": 0.88, "learning_rate": 2.327555110220441e-05, "loss": 2.033, "step": 53560 }, { "epoch": 0.88, "learning_rate": 2.327054108216433e-05, "loss": 2.0504, "step": 53570 }, { "epoch": 0.88, "learning_rate": 2.326553106212425e-05, "loss": 2.0749, "step": 53580 }, { "epoch": 0.88, "learning_rate": 2.3260521042084167e-05, "loss": 2.0498, "step": 53590 }, { "epoch": 0.88, "learning_rate": 2.3255511022044088e-05, "loss": 2.0945, "step": 53600 }, { "epoch": 0.88, "learning_rate": 2.3250501002004012e-05, "loss": 2.0782, "step": 53610 }, { "epoch": 0.88, "learning_rate": 2.324549098196393e-05, "loss": 2.0508, "step": 53620 }, { "epoch": 0.88, "learning_rate": 2.324048096192385e-05, "loss": 2.063, "step": 53630 }, { "epoch": 0.88, "learning_rate": 2.323547094188377e-05, "loss": 2.0858, "step": 53640 }, { "epoch": 0.88, "learning_rate": 2.3230460921843688e-05, "loss": 2.0237, "step": 53650 }, { "epoch": 0.88, "learning_rate": 2.322545090180361e-05, "loss": 2.0801, "step": 53660 }, { "epoch": 0.88, "learning_rate": 2.322044088176353e-05, "loss": 2.0422, "step": 53670 }, { "epoch": 0.88, "learning_rate": 2.3215430861723446e-05, "loss": 2.0576, "step": 53680 }, { "epoch": 0.88, "learning_rate": 2.3210420841683367e-05, "loss": 2.0858, "step": 53690 }, { "epoch": 0.88, "learning_rate": 2.3205410821643288e-05, "loss": 2.0698, "step": 53700 }, { "epoch": 0.88, "learning_rate": 2.3200400801603208e-05, "loss": 2.0574, "step": 53710 }, { "epoch": 0.88, "learning_rate": 2.319539078156313e-05, "loss": 2.034, "step": 53720 }, { "epoch": 0.88, "learning_rate": 2.319038076152305e-05, "loss": 2.0787, "step": 53730 }, { "epoch": 0.88, "learning_rate": 2.3185370741482967e-05, "loss": 2.1152, "step": 53740 }, { "epoch": 0.88, "learning_rate": 2.3180360721442887e-05, "loss": 2.0583, "step": 53750 }, { "epoch": 0.88, "learning_rate": 2.3175350701402808e-05, "loss": 2.0685, "step": 53760 }, { "epoch": 0.88, "learning_rate": 2.3170340681362725e-05, "loss": 2.0744, "step": 53770 }, { "epoch": 0.88, "learning_rate": 2.3165330661322646e-05, "loss": 2.0096, "step": 53780 }, { "epoch": 0.88, "learning_rate": 2.3160320641282567e-05, "loss": 2.0373, "step": 53790 }, { "epoch": 0.88, "learning_rate": 2.3155310621242484e-05, "loss": 2.0403, "step": 53800 }, { "epoch": 0.88, "learning_rate": 2.3150300601202408e-05, "loss": 2.0425, "step": 53810 }, { "epoch": 0.88, "learning_rate": 2.3145290581162325e-05, "loss": 2.0817, "step": 53820 }, { "epoch": 0.88, "learning_rate": 2.3140280561122246e-05, "loss": 2.0809, "step": 53830 }, { "epoch": 0.88, "learning_rate": 2.3135270541082166e-05, "loss": 2.0276, "step": 53840 }, { "epoch": 0.88, "learning_rate": 2.3130260521042084e-05, "loss": 2.0716, "step": 53850 }, { "epoch": 0.88, "learning_rate": 2.3125250501002004e-05, "loss": 2.0394, "step": 53860 }, { "epoch": 0.88, "learning_rate": 2.3120240480961925e-05, "loss": 2.0706, "step": 53870 }, { "epoch": 0.88, "learning_rate": 2.3115230460921846e-05, "loss": 2.0462, "step": 53880 }, { "epoch": 0.88, "learning_rate": 2.3110220440881763e-05, "loss": 2.028, "step": 53890 }, { "epoch": 0.88, "learning_rate": 2.3105210420841687e-05, "loss": 2.0532, "step": 53900 }, { "epoch": 0.88, "learning_rate": 2.3100200400801604e-05, "loss": 2.0911, "step": 53910 }, { "epoch": 0.88, "learning_rate": 2.3095190380761525e-05, "loss": 2.0763, "step": 53920 }, { "epoch": 0.88, "learning_rate": 2.3090180360721445e-05, "loss": 2.0395, "step": 53930 }, { "epoch": 0.88, "learning_rate": 2.3085170340681363e-05, "loss": 2.075, "step": 53940 }, { "epoch": 0.88, "learning_rate": 2.3080160320641283e-05, "loss": 2.0659, "step": 53950 }, { "epoch": 0.88, "learning_rate": 2.3075150300601204e-05, "loss": 2.0648, "step": 53960 }, { "epoch": 0.88, "learning_rate": 2.307014028056112e-05, "loss": 2.108, "step": 53970 }, { "epoch": 0.88, "learning_rate": 2.3065130260521042e-05, "loss": 2.0281, "step": 53980 }, { "epoch": 0.88, "learning_rate": 2.3060120240480962e-05, "loss": 2.0653, "step": 53990 }, { "epoch": 0.88, "learning_rate": 2.3055110220440883e-05, "loss": 2.0795, "step": 54000 }, { "epoch": 0.88, "eval_loss": 2.039398431777954, "eval_mean_f1": 0.6584058741270623, "eval_rouge1_f1": 0.7160197257741983, "eval_rouge1_precision": 0.8268189692060894, "eval_rouge1_recall": 0.6639290763615486, "eval_rouge2_f1": 0.574544879410437, "eval_rouge2_precision": 0.6678313040312551, "eval_rouge2_recall": 0.5325767784426996, "eval_rougeL_f1": 0.6846530171965517, "eval_rougeL_precision": 0.7883390532456336, "eval_rougeL_recall": 0.6359906668884192, "eval_runtime": 61.8962, "eval_samples_per_second": 16.544, "eval_steps_per_second": 2.068, "step": 54000 }, { "epoch": 0.88, "learning_rate": 2.3050100200400804e-05, "loss": 2.0494, "step": 54010 }, { "epoch": 0.88, "learning_rate": 2.3045090180360724e-05, "loss": 2.1139, "step": 54020 }, { "epoch": 0.88, "learning_rate": 2.304008016032064e-05, "loss": 2.0462, "step": 54030 }, { "epoch": 0.88, "learning_rate": 2.3035070140280562e-05, "loss": 2.0557, "step": 54040 }, { "epoch": 0.88, "learning_rate": 2.3030060120240483e-05, "loss": 2.071, "step": 54050 }, { "epoch": 0.88, "learning_rate": 2.30250501002004e-05, "loss": 2.0522, "step": 54060 }, { "epoch": 0.88, "learning_rate": 2.302004008016032e-05, "loss": 2.007, "step": 54070 }, { "epoch": 0.88, "learning_rate": 2.301503006012024e-05, "loss": 2.022, "step": 54080 }, { "epoch": 0.88, "learning_rate": 2.301002004008016e-05, "loss": 2.0425, "step": 54090 }, { "epoch": 0.88, "learning_rate": 2.3005010020040083e-05, "loss": 2.0202, "step": 54100 }, { "epoch": 0.88, "learning_rate": 2.3000000000000003e-05, "loss": 2.0581, "step": 54110 }, { "epoch": 0.88, "learning_rate": 2.299498997995992e-05, "loss": 2.0489, "step": 54120 }, { "epoch": 0.88, "learning_rate": 2.298997995991984e-05, "loss": 2.0451, "step": 54130 }, { "epoch": 0.88, "learning_rate": 2.2984969939879762e-05, "loss": 2.0568, "step": 54140 }, { "epoch": 0.88, "learning_rate": 2.297995991983968e-05, "loss": 2.0785, "step": 54150 }, { "epoch": 0.88, "learning_rate": 2.29749498997996e-05, "loss": 2.1092, "step": 54160 }, { "epoch": 0.89, "learning_rate": 2.296993987975952e-05, "loss": 2.0989, "step": 54170 }, { "epoch": 0.89, "learning_rate": 2.2964929859719438e-05, "loss": 2.0362, "step": 54180 }, { "epoch": 0.89, "learning_rate": 2.295991983967936e-05, "loss": 2.0103, "step": 54190 }, { "epoch": 0.89, "learning_rate": 2.2954909819639282e-05, "loss": 2.0104, "step": 54200 }, { "epoch": 0.89, "learning_rate": 2.29498997995992e-05, "loss": 2.0416, "step": 54210 }, { "epoch": 0.89, "learning_rate": 2.294488977955912e-05, "loss": 2.0503, "step": 54220 }, { "epoch": 0.89, "learning_rate": 2.293987975951904e-05, "loss": 2.0486, "step": 54230 }, { "epoch": 0.89, "learning_rate": 2.2934869739478958e-05, "loss": 2.0706, "step": 54240 }, { "epoch": 0.89, "learning_rate": 2.292985971943888e-05, "loss": 2.0067, "step": 54250 }, { "epoch": 0.89, "learning_rate": 2.29248496993988e-05, "loss": 2.0464, "step": 54260 }, { "epoch": 0.89, "learning_rate": 2.2919839679358717e-05, "loss": 2.0583, "step": 54270 }, { "epoch": 0.89, "learning_rate": 2.2914829659318637e-05, "loss": 2.063, "step": 54280 }, { "epoch": 0.89, "learning_rate": 2.2909819639278558e-05, "loss": 2.0761, "step": 54290 }, { "epoch": 0.89, "learning_rate": 2.290480961923848e-05, "loss": 2.001, "step": 54300 }, { "epoch": 0.89, "learning_rate": 2.28997995991984e-05, "loss": 2.0199, "step": 54310 }, { "epoch": 0.89, "learning_rate": 2.289478957915832e-05, "loss": 2.057, "step": 54320 }, { "epoch": 0.89, "learning_rate": 2.2889779559118237e-05, "loss": 2.0476, "step": 54330 }, { "epoch": 0.89, "learning_rate": 2.2884769539078158e-05, "loss": 2.1066, "step": 54340 }, { "epoch": 0.89, "learning_rate": 2.287975951903808e-05, "loss": 2.0787, "step": 54350 }, { "epoch": 0.89, "learning_rate": 2.2874749498997996e-05, "loss": 2.0602, "step": 54360 }, { "epoch": 0.89, "learning_rate": 2.2869739478957916e-05, "loss": 2.071, "step": 54370 }, { "epoch": 0.89, "learning_rate": 2.2864729458917837e-05, "loss": 1.9902, "step": 54380 }, { "epoch": 0.89, "learning_rate": 2.2859719438877754e-05, "loss": 2.0355, "step": 54390 }, { "epoch": 0.89, "learning_rate": 2.2854709418837678e-05, "loss": 2.0151, "step": 54400 }, { "epoch": 0.89, "learning_rate": 2.2849699398797596e-05, "loss": 2.0409, "step": 54410 }, { "epoch": 0.89, "learning_rate": 2.2844689378757516e-05, "loss": 2.0212, "step": 54420 }, { "epoch": 0.89, "learning_rate": 2.2839679358717437e-05, "loss": 2.111, "step": 54430 }, { "epoch": 0.89, "learning_rate": 2.2834669338677357e-05, "loss": 2.0763, "step": 54440 }, { "epoch": 0.89, "learning_rate": 2.2829659318637275e-05, "loss": 1.9982, "step": 54450 }, { "epoch": 0.89, "learning_rate": 2.2824649298597195e-05, "loss": 2.0586, "step": 54460 }, { "epoch": 0.89, "learning_rate": 2.2819639278557116e-05, "loss": 2.0471, "step": 54470 }, { "epoch": 0.89, "learning_rate": 2.2814629258517033e-05, "loss": 2.0541, "step": 54480 }, { "epoch": 0.89, "learning_rate": 2.2809619238476957e-05, "loss": 2.0403, "step": 54490 }, { "epoch": 0.89, "learning_rate": 2.2804609218436875e-05, "loss": 2.0094, "step": 54500 }, { "epoch": 0.89, "learning_rate": 2.2799599198396795e-05, "loss": 2.0688, "step": 54510 }, { "epoch": 0.89, "learning_rate": 2.2794589178356716e-05, "loss": 2.0724, "step": 54520 }, { "epoch": 0.89, "learning_rate": 2.2789579158316633e-05, "loss": 2.0722, "step": 54530 }, { "epoch": 0.89, "learning_rate": 2.2784569138276554e-05, "loss": 2.0264, "step": 54540 }, { "epoch": 0.89, "learning_rate": 2.2779559118236474e-05, "loss": 2.0599, "step": 54550 }, { "epoch": 0.89, "learning_rate": 2.277454909819639e-05, "loss": 2.0215, "step": 54560 }, { "epoch": 0.89, "learning_rate": 2.2769539078156312e-05, "loss": 2.0794, "step": 54570 }, { "epoch": 0.89, "learning_rate": 2.2764529058116233e-05, "loss": 2.0316, "step": 54580 }, { "epoch": 0.89, "learning_rate": 2.2759519038076154e-05, "loss": 2.0845, "step": 54590 }, { "epoch": 0.89, "learning_rate": 2.2754509018036074e-05, "loss": 2.0444, "step": 54600 }, { "epoch": 0.89, "learning_rate": 2.2749498997995995e-05, "loss": 2.054, "step": 54610 }, { "epoch": 0.89, "learning_rate": 2.2744488977955912e-05, "loss": 2.0091, "step": 54620 }, { "epoch": 0.89, "learning_rate": 2.2739478957915833e-05, "loss": 2.0093, "step": 54630 }, { "epoch": 0.89, "learning_rate": 2.2734468937875753e-05, "loss": 2.0593, "step": 54640 }, { "epoch": 0.89, "learning_rate": 2.272945891783567e-05, "loss": 2.0839, "step": 54650 }, { "epoch": 0.89, "learning_rate": 2.272444889779559e-05, "loss": 2.028, "step": 54660 }, { "epoch": 0.89, "learning_rate": 2.2719438877755512e-05, "loss": 2.0154, "step": 54670 }, { "epoch": 0.89, "learning_rate": 2.271442885771543e-05, "loss": 2.048, "step": 54680 }, { "epoch": 0.89, "learning_rate": 2.2709418837675353e-05, "loss": 2.0435, "step": 54690 }, { "epoch": 0.89, "learning_rate": 2.2704408817635274e-05, "loss": 2.027, "step": 54700 }, { "epoch": 0.89, "learning_rate": 2.269939879759519e-05, "loss": 2.0797, "step": 54710 }, { "epoch": 0.89, "learning_rate": 2.2694388777555112e-05, "loss": 2.0195, "step": 54720 }, { "epoch": 0.89, "learning_rate": 2.2689378757515032e-05, "loss": 2.0279, "step": 54730 }, { "epoch": 0.89, "learning_rate": 2.268436873747495e-05, "loss": 2.0191, "step": 54740 }, { "epoch": 0.89, "learning_rate": 2.267935871743487e-05, "loss": 2.0572, "step": 54750 }, { "epoch": 0.89, "learning_rate": 2.267434869739479e-05, "loss": 2.0442, "step": 54760 }, { "epoch": 0.89, "learning_rate": 2.2669338677354708e-05, "loss": 2.0346, "step": 54770 }, { "epoch": 0.9, "learning_rate": 2.266432865731463e-05, "loss": 2.0738, "step": 54780 }, { "epoch": 0.9, "learning_rate": 2.2659318637274553e-05, "loss": 2.0342, "step": 54790 }, { "epoch": 0.9, "learning_rate": 2.265430861723447e-05, "loss": 2.0518, "step": 54800 }, { "epoch": 0.9, "learning_rate": 2.264929859719439e-05, "loss": 2.0387, "step": 54810 }, { "epoch": 0.9, "learning_rate": 2.264428857715431e-05, "loss": 2.0498, "step": 54820 }, { "epoch": 0.9, "learning_rate": 2.263927855711423e-05, "loss": 2.0356, "step": 54830 }, { "epoch": 0.9, "learning_rate": 2.263426853707415e-05, "loss": 2.0389, "step": 54840 }, { "epoch": 0.9, "learning_rate": 2.262925851703407e-05, "loss": 2.049, "step": 54850 }, { "epoch": 0.9, "learning_rate": 2.2624248496993987e-05, "loss": 2.0639, "step": 54860 }, { "epoch": 0.9, "learning_rate": 2.2619238476953908e-05, "loss": 2.0447, "step": 54870 }, { "epoch": 0.9, "learning_rate": 2.261422845691383e-05, "loss": 2.0502, "step": 54880 }, { "epoch": 0.9, "learning_rate": 2.260921843687375e-05, "loss": 2.0754, "step": 54890 }, { "epoch": 0.9, "learning_rate": 2.260420841683367e-05, "loss": 2.0677, "step": 54900 }, { "epoch": 0.9, "learning_rate": 2.259919839679359e-05, "loss": 2.0906, "step": 54910 }, { "epoch": 0.9, "learning_rate": 2.2594188376753508e-05, "loss": 2.0678, "step": 54920 }, { "epoch": 0.9, "learning_rate": 2.2589178356713428e-05, "loss": 2.0896, "step": 54930 }, { "epoch": 0.9, "learning_rate": 2.258416833667335e-05, "loss": 2.0287, "step": 54940 }, { "epoch": 0.9, "learning_rate": 2.2579158316633266e-05, "loss": 2.0263, "step": 54950 }, { "epoch": 0.9, "learning_rate": 2.2574148296593187e-05, "loss": 2.0497, "step": 54960 }, { "epoch": 0.9, "learning_rate": 2.2569138276553107e-05, "loss": 2.0458, "step": 54970 }, { "epoch": 0.9, "learning_rate": 2.2564128256513025e-05, "loss": 2.0644, "step": 54980 }, { "epoch": 0.9, "learning_rate": 2.255911823647295e-05, "loss": 2.0406, "step": 54990 }, { "epoch": 0.9, "learning_rate": 2.255410821643287e-05, "loss": 2.0491, "step": 55000 }, { "epoch": 0.9, "eval_loss": 2.031282424926758, "eval_mean_f1": 0.6551106917864101, "eval_rouge1_f1": 0.7126769990703794, "eval_rouge1_precision": 0.8229023042578585, "eval_rouge1_recall": 0.6613612047973556, "eval_rouge2_f1": 0.5712983044050421, "eval_rouge2_precision": 0.6648528608977828, "eval_rouge2_recall": 0.5299709315612956, "eval_rougeL_f1": 0.6813567718838089, "eval_rougeL_precision": 0.7849068309237486, "eval_rougeL_recall": 0.6333431160953729, "eval_runtime": 63.4635, "eval_samples_per_second": 16.135, "eval_steps_per_second": 2.017, "step": 55000 }, { "epoch": 0.9, "learning_rate": 2.2549098196392787e-05, "loss": 2.0575, "step": 55010 }, { "epoch": 0.9, "learning_rate": 2.2544088176352707e-05, "loss": 2.0563, "step": 55020 }, { "epoch": 0.9, "learning_rate": 2.2539078156312628e-05, "loss": 2.0732, "step": 55030 }, { "epoch": 0.9, "learning_rate": 2.2534068136272545e-05, "loss": 2.0915, "step": 55040 }, { "epoch": 0.9, "learning_rate": 2.2529058116232466e-05, "loss": 2.0725, "step": 55050 }, { "epoch": 0.9, "learning_rate": 2.2524048096192386e-05, "loss": 2.0402, "step": 55060 }, { "epoch": 0.9, "learning_rate": 2.2519038076152304e-05, "loss": 2.0956, "step": 55070 }, { "epoch": 0.9, "learning_rate": 2.2514028056112228e-05, "loss": 2.0395, "step": 55080 }, { "epoch": 0.9, "learning_rate": 2.2509018036072145e-05, "loss": 2.0383, "step": 55090 }, { "epoch": 0.9, "learning_rate": 2.2504008016032066e-05, "loss": 2.0291, "step": 55100 }, { "epoch": 0.9, "learning_rate": 2.2498997995991986e-05, "loss": 2.0689, "step": 55110 }, { "epoch": 0.9, "learning_rate": 2.2493987975951903e-05, "loss": 2.0207, "step": 55120 }, { "epoch": 0.9, "learning_rate": 2.2488977955911824e-05, "loss": 2.0602, "step": 55130 }, { "epoch": 0.9, "learning_rate": 2.2483967935871745e-05, "loss": 2.0381, "step": 55140 }, { "epoch": 0.9, "learning_rate": 2.2478957915831665e-05, "loss": 2.0166, "step": 55150 }, { "epoch": 0.9, "learning_rate": 2.2473947895791583e-05, "loss": 2.0868, "step": 55160 }, { "epoch": 0.9, "learning_rate": 2.2468937875751503e-05, "loss": 2.0878, "step": 55170 }, { "epoch": 0.9, "learning_rate": 2.2463927855711424e-05, "loss": 2.0898, "step": 55180 }, { "epoch": 0.9, "learning_rate": 2.2458917835671345e-05, "loss": 2.0758, "step": 55190 }, { "epoch": 0.9, "learning_rate": 2.2453907815631265e-05, "loss": 2.0247, "step": 55200 }, { "epoch": 0.9, "learning_rate": 2.2448897795591182e-05, "loss": 2.0242, "step": 55210 }, { "epoch": 0.9, "learning_rate": 2.2443887775551103e-05, "loss": 2.0292, "step": 55220 }, { "epoch": 0.9, "learning_rate": 2.2438877755511024e-05, "loss": 2.0488, "step": 55230 }, { "epoch": 0.9, "learning_rate": 2.243386773547094e-05, "loss": 2.0522, "step": 55240 }, { "epoch": 0.9, "learning_rate": 2.242885771543086e-05, "loss": 2.0408, "step": 55250 }, { "epoch": 0.9, "learning_rate": 2.2423847695390782e-05, "loss": 2.1005, "step": 55260 }, { "epoch": 0.9, "learning_rate": 2.24188376753507e-05, "loss": 2.0102, "step": 55270 }, { "epoch": 0.9, "learning_rate": 2.2413827655310624e-05, "loss": 2.0331, "step": 55280 }, { "epoch": 0.9, "learning_rate": 2.2408817635270544e-05, "loss": 2.0743, "step": 55290 }, { "epoch": 0.9, "learning_rate": 2.240380761523046e-05, "loss": 2.0393, "step": 55300 }, { "epoch": 0.9, "learning_rate": 2.2398797595190382e-05, "loss": 2.0593, "step": 55310 }, { "epoch": 0.9, "learning_rate": 2.2393787575150303e-05, "loss": 2.0709, "step": 55320 }, { "epoch": 0.9, "learning_rate": 2.238877755511022e-05, "loss": 2.0335, "step": 55330 }, { "epoch": 0.9, "learning_rate": 2.238376753507014e-05, "loss": 2.0632, "step": 55340 }, { "epoch": 0.9, "learning_rate": 2.237875751503006e-05, "loss": 2.0569, "step": 55350 }, { "epoch": 0.9, "learning_rate": 2.237374749498998e-05, "loss": 2.034, "step": 55360 }, { "epoch": 0.9, "learning_rate": 2.23687374749499e-05, "loss": 2.0351, "step": 55370 }, { "epoch": 0.9, "learning_rate": 2.2363727454909823e-05, "loss": 2.1072, "step": 55380 }, { "epoch": 0.91, "learning_rate": 2.235871743486974e-05, "loss": 2.0945, "step": 55390 }, { "epoch": 0.91, "learning_rate": 2.235370741482966e-05, "loss": 2.0301, "step": 55400 }, { "epoch": 0.91, "learning_rate": 2.2348697394789582e-05, "loss": 2.1077, "step": 55410 }, { "epoch": 0.91, "learning_rate": 2.23436873747495e-05, "loss": 2.0521, "step": 55420 }, { "epoch": 0.91, "learning_rate": 2.233867735470942e-05, "loss": 2.0478, "step": 55430 }, { "epoch": 0.91, "learning_rate": 2.233366733466934e-05, "loss": 2.0288, "step": 55440 }, { "epoch": 0.91, "learning_rate": 2.2328657314629258e-05, "loss": 2.0281, "step": 55450 }, { "epoch": 0.91, "learning_rate": 2.2323647294589178e-05, "loss": 2.0681, "step": 55460 }, { "epoch": 0.91, "learning_rate": 2.23186372745491e-05, "loss": 2.0871, "step": 55470 }, { "epoch": 0.91, "learning_rate": 2.231362725450902e-05, "loss": 2.0472, "step": 55480 }, { "epoch": 0.91, "learning_rate": 2.230861723446894e-05, "loss": 2.0327, "step": 55490 }, { "epoch": 0.91, "learning_rate": 2.230360721442886e-05, "loss": 2.0732, "step": 55500 }, { "epoch": 0.91, "learning_rate": 2.2298597194388778e-05, "loss": 2.0222, "step": 55510 }, { "epoch": 0.91, "learning_rate": 2.22935871743487e-05, "loss": 1.9776, "step": 55520 }, { "epoch": 0.91, "learning_rate": 2.228857715430862e-05, "loss": 2.0411, "step": 55530 }, { "epoch": 0.91, "learning_rate": 2.2283567134268537e-05, "loss": 2.0584, "step": 55540 }, { "epoch": 0.91, "learning_rate": 2.2278557114228457e-05, "loss": 2.0021, "step": 55550 }, { "epoch": 0.91, "learning_rate": 2.2273547094188378e-05, "loss": 2.0581, "step": 55560 }, { "epoch": 0.91, "learning_rate": 2.22685370741483e-05, "loss": 2.0713, "step": 55570 }, { "epoch": 0.91, "learning_rate": 2.226352705410822e-05, "loss": 2.0293, "step": 55580 }, { "epoch": 0.91, "learning_rate": 2.225851703406814e-05, "loss": 2.0552, "step": 55590 }, { "epoch": 0.91, "learning_rate": 2.2253507014028057e-05, "loss": 2.059, "step": 55600 }, { "epoch": 0.91, "learning_rate": 2.2248496993987978e-05, "loss": 2.0001, "step": 55610 }, { "epoch": 0.91, "learning_rate": 2.2243486973947898e-05, "loss": 2.059, "step": 55620 }, { "epoch": 0.91, "learning_rate": 2.2238476953907816e-05, "loss": 2.1041, "step": 55630 }, { "epoch": 0.91, "learning_rate": 2.2233466933867736e-05, "loss": 2.0256, "step": 55640 }, { "epoch": 0.91, "learning_rate": 2.2228456913827657e-05, "loss": 2.0588, "step": 55650 }, { "epoch": 0.91, "learning_rate": 2.2223446893787574e-05, "loss": 2.0984, "step": 55660 }, { "epoch": 0.91, "learning_rate": 2.2218436873747498e-05, "loss": 2.0019, "step": 55670 }, { "epoch": 0.91, "learning_rate": 2.2213426853707415e-05, "loss": 2.0617, "step": 55680 }, { "epoch": 0.91, "learning_rate": 2.2208416833667336e-05, "loss": 2.054, "step": 55690 }, { "epoch": 0.91, "learning_rate": 2.2203406813627257e-05, "loss": 2.0376, "step": 55700 }, { "epoch": 0.91, "learning_rate": 2.2198396793587177e-05, "loss": 2.1324, "step": 55710 }, { "epoch": 0.91, "learning_rate": 2.2193386773547095e-05, "loss": 2.0488, "step": 55720 }, { "epoch": 0.91, "learning_rate": 2.2188376753507015e-05, "loss": 2.0291, "step": 55730 }, { "epoch": 0.91, "learning_rate": 2.2183366733466936e-05, "loss": 2.0897, "step": 55740 }, { "epoch": 0.91, "learning_rate": 2.2178356713426853e-05, "loss": 2.0486, "step": 55750 }, { "epoch": 0.91, "learning_rate": 2.2173346693386774e-05, "loss": 2.0352, "step": 55760 }, { "epoch": 0.91, "learning_rate": 2.2168336673346694e-05, "loss": 2.1141, "step": 55770 }, { "epoch": 0.91, "learning_rate": 2.2163326653306615e-05, "loss": 2.0538, "step": 55780 }, { "epoch": 0.91, "learning_rate": 2.2158316633266536e-05, "loss": 2.0205, "step": 55790 }, { "epoch": 0.91, "learning_rate": 2.2153306613226453e-05, "loss": 2.0582, "step": 55800 }, { "epoch": 0.91, "learning_rate": 2.2148296593186374e-05, "loss": 2.0589, "step": 55810 }, { "epoch": 0.91, "learning_rate": 2.2143286573146294e-05, "loss": 2.0309, "step": 55820 }, { "epoch": 0.91, "learning_rate": 2.213827655310621e-05, "loss": 2.0052, "step": 55830 }, { "epoch": 0.91, "learning_rate": 2.2133266533066132e-05, "loss": 2.058, "step": 55840 }, { "epoch": 0.91, "learning_rate": 2.2128256513026053e-05, "loss": 2.0399, "step": 55850 }, { "epoch": 0.91, "learning_rate": 2.2123246492985973e-05, "loss": 2.0397, "step": 55860 }, { "epoch": 0.91, "learning_rate": 2.2118236472945894e-05, "loss": 2.06, "step": 55870 }, { "epoch": 0.91, "learning_rate": 2.2113226452905815e-05, "loss": 2.0569, "step": 55880 }, { "epoch": 0.91, "learning_rate": 2.2108216432865732e-05, "loss": 2.0641, "step": 55890 }, { "epoch": 0.91, "learning_rate": 2.2103206412825653e-05, "loss": 2.0709, "step": 55900 }, { "epoch": 0.91, "learning_rate": 2.2098196392785573e-05, "loss": 2.0168, "step": 55910 }, { "epoch": 0.91, "learning_rate": 2.209318637274549e-05, "loss": 2.0584, "step": 55920 }, { "epoch": 0.91, "learning_rate": 2.208817635270541e-05, "loss": 2.0388, "step": 55930 }, { "epoch": 0.91, "learning_rate": 2.208316633266533e-05, "loss": 2.0546, "step": 55940 }, { "epoch": 0.91, "learning_rate": 2.207815631262525e-05, "loss": 2.0522, "step": 55950 }, { "epoch": 0.91, "learning_rate": 2.207314629258517e-05, "loss": 2.0664, "step": 55960 }, { "epoch": 0.91, "learning_rate": 2.2068136272545094e-05, "loss": 2.0605, "step": 55970 }, { "epoch": 0.91, "learning_rate": 2.206312625250501e-05, "loss": 2.0548, "step": 55980 }, { "epoch": 0.91, "learning_rate": 2.205811623246493e-05, "loss": 2.0539, "step": 55990 }, { "epoch": 0.92, "learning_rate": 2.2053106212424852e-05, "loss": 2.0543, "step": 56000 }, { "epoch": 0.92, "eval_loss": 2.034615993499756, "eval_mean_f1": 0.6529564515932559, "eval_rouge1_f1": 0.7103575916347395, "eval_rouge1_precision": 0.8227183950856252, "eval_rouge1_recall": 0.6589791561962737, "eval_rouge2_f1": 0.569002100033589, "eval_rouge2_precision": 0.663384082958058, "eval_rouge2_recall": 0.5273724240282344, "eval_rougeL_f1": 0.679509663111439, "eval_rougeL_precision": 0.7844424262866931, "eval_rougeL_recall": 0.6314634411225444, "eval_runtime": 63.6507, "eval_samples_per_second": 16.088, "eval_steps_per_second": 2.011, "step": 56000 }, { "epoch": 0.92, "learning_rate": 2.204809619238477e-05, "loss": 2.0517, "step": 56010 }, { "epoch": 0.92, "learning_rate": 2.204308617234469e-05, "loss": 2.0621, "step": 56020 }, { "epoch": 0.92, "learning_rate": 2.203807615230461e-05, "loss": 2.0454, "step": 56030 }, { "epoch": 0.92, "learning_rate": 2.2033066132264528e-05, "loss": 2.098, "step": 56040 }, { "epoch": 0.92, "learning_rate": 2.202805611222445e-05, "loss": 2.0779, "step": 56050 }, { "epoch": 0.92, "learning_rate": 2.202304609218437e-05, "loss": 2.0929, "step": 56060 }, { "epoch": 0.92, "learning_rate": 2.201803607214429e-05, "loss": 2.0467, "step": 56070 }, { "epoch": 0.92, "learning_rate": 2.201302605210421e-05, "loss": 2.0649, "step": 56080 }, { "epoch": 0.92, "learning_rate": 2.2008517034068137e-05, "loss": 2.0912, "step": 56090 }, { "epoch": 0.92, "learning_rate": 2.2003507014028058e-05, "loss": 2.0195, "step": 56100 }, { "epoch": 0.92, "learning_rate": 2.199849699398798e-05, "loss": 2.0179, "step": 56110 }, { "epoch": 0.92, "learning_rate": 2.1993486973947896e-05, "loss": 2.0125, "step": 56120 }, { "epoch": 0.92, "learning_rate": 2.1988476953907816e-05, "loss": 2.0102, "step": 56130 }, { "epoch": 0.92, "learning_rate": 2.1983466933867737e-05, "loss": 2.0553, "step": 56140 }, { "epoch": 0.92, "learning_rate": 2.1978456913827654e-05, "loss": 2.0466, "step": 56150 }, { "epoch": 0.92, "learning_rate": 2.1973446893787575e-05, "loss": 2.065, "step": 56160 }, { "epoch": 0.92, "learning_rate": 2.19684368737475e-05, "loss": 2.0398, "step": 56170 }, { "epoch": 0.92, "learning_rate": 2.1963426853707416e-05, "loss": 2.0439, "step": 56180 }, { "epoch": 0.92, "learning_rate": 2.1958416833667337e-05, "loss": 2.097, "step": 56190 }, { "epoch": 0.92, "learning_rate": 2.1953406813627257e-05, "loss": 2.0934, "step": 56200 }, { "epoch": 0.92, "learning_rate": 2.1948396793587175e-05, "loss": 2.0784, "step": 56210 }, { "epoch": 0.92, "learning_rate": 2.1943386773547095e-05, "loss": 2.0824, "step": 56220 }, { "epoch": 0.92, "learning_rate": 2.1938376753507016e-05, "loss": 2.0923, "step": 56230 }, { "epoch": 0.92, "learning_rate": 2.1933366733466933e-05, "loss": 2.0557, "step": 56240 }, { "epoch": 0.92, "learning_rate": 2.1928356713426854e-05, "loss": 2.0424, "step": 56250 }, { "epoch": 0.92, "learning_rate": 2.1923346693386774e-05, "loss": 2.0717, "step": 56260 }, { "epoch": 0.92, "learning_rate": 2.1918336673346695e-05, "loss": 2.0558, "step": 56270 }, { "epoch": 0.92, "learning_rate": 2.1913326653306616e-05, "loss": 2.1002, "step": 56280 }, { "epoch": 0.92, "learning_rate": 2.1908316633266533e-05, "loss": 2.0688, "step": 56290 }, { "epoch": 0.92, "learning_rate": 2.1903306613226454e-05, "loss": 2.0633, "step": 56300 }, { "epoch": 0.92, "learning_rate": 2.1898296593186374e-05, "loss": 2.0674, "step": 56310 }, { "epoch": 0.92, "learning_rate": 2.1893286573146295e-05, "loss": 2.0303, "step": 56320 }, { "epoch": 0.92, "learning_rate": 2.1888276553106212e-05, "loss": 2.0415, "step": 56330 }, { "epoch": 0.92, "learning_rate": 2.1883266533066133e-05, "loss": 2.0324, "step": 56340 }, { "epoch": 0.92, "learning_rate": 2.1878256513026053e-05, "loss": 2.0426, "step": 56350 }, { "epoch": 0.92, "learning_rate": 2.1873246492985974e-05, "loss": 2.1147, "step": 56360 }, { "epoch": 0.92, "learning_rate": 2.1868236472945895e-05, "loss": 2.0345, "step": 56370 }, { "epoch": 0.92, "learning_rate": 2.1863226452905812e-05, "loss": 2.0323, "step": 56380 }, { "epoch": 0.92, "learning_rate": 2.1858216432865733e-05, "loss": 2.057, "step": 56390 }, { "epoch": 0.92, "learning_rate": 2.1853206412825653e-05, "loss": 2.0865, "step": 56400 }, { "epoch": 0.92, "learning_rate": 2.184819639278557e-05, "loss": 2.064, "step": 56410 }, { "epoch": 0.92, "learning_rate": 2.184318637274549e-05, "loss": 2.0618, "step": 56420 }, { "epoch": 0.92, "learning_rate": 2.1838176352705412e-05, "loss": 2.0525, "step": 56430 }, { "epoch": 0.92, "learning_rate": 2.1833166332665332e-05, "loss": 2.0411, "step": 56440 }, { "epoch": 0.92, "learning_rate": 2.182815631262525e-05, "loss": 2.0329, "step": 56450 }, { "epoch": 0.92, "learning_rate": 2.1823146292585174e-05, "loss": 2.0646, "step": 56460 }, { "epoch": 0.92, "learning_rate": 2.181813627254509e-05, "loss": 2.0045, "step": 56470 }, { "epoch": 0.92, "learning_rate": 2.181312625250501e-05, "loss": 2.096, "step": 56480 }, { "epoch": 0.92, "learning_rate": 2.1808116232464932e-05, "loss": 2.0366, "step": 56490 }, { "epoch": 0.92, "learning_rate": 2.180310621242485e-05, "loss": 2.0567, "step": 56500 }, { "epoch": 0.92, "learning_rate": 2.179809619238477e-05, "loss": 2.0932, "step": 56510 }, { "epoch": 0.92, "learning_rate": 2.179308617234469e-05, "loss": 2.0062, "step": 56520 }, { "epoch": 0.92, "learning_rate": 2.1788076152304608e-05, "loss": 2.0333, "step": 56530 }, { "epoch": 0.92, "learning_rate": 2.178306613226453e-05, "loss": 2.0506, "step": 56540 }, { "epoch": 0.92, "learning_rate": 2.177805611222445e-05, "loss": 2.0839, "step": 56550 }, { "epoch": 0.92, "learning_rate": 2.177304609218437e-05, "loss": 2.0673, "step": 56560 }, { "epoch": 0.92, "learning_rate": 2.176803607214429e-05, "loss": 2.074, "step": 56570 }, { "epoch": 0.92, "learning_rate": 2.176302605210421e-05, "loss": 2.0363, "step": 56580 }, { "epoch": 0.92, "learning_rate": 2.175801603206413e-05, "loss": 2.0437, "step": 56590 }, { "epoch": 0.92, "learning_rate": 2.175300601202405e-05, "loss": 2.0458, "step": 56600 }, { "epoch": 0.93, "learning_rate": 2.174799599198397e-05, "loss": 2.0332, "step": 56610 }, { "epoch": 0.93, "learning_rate": 2.1742985971943887e-05, "loss": 2.0428, "step": 56620 }, { "epoch": 0.93, "learning_rate": 2.1737975951903808e-05, "loss": 2.0319, "step": 56630 }, { "epoch": 0.93, "learning_rate": 2.1732965931863728e-05, "loss": 2.0361, "step": 56640 }, { "epoch": 0.93, "learning_rate": 2.1727955911823646e-05, "loss": 2.0021, "step": 56650 }, { "epoch": 0.93, "learning_rate": 2.172294589178357e-05, "loss": 2.0402, "step": 56660 }, { "epoch": 0.93, "learning_rate": 2.171793587174349e-05, "loss": 2.0142, "step": 56670 }, { "epoch": 0.93, "learning_rate": 2.1712925851703407e-05, "loss": 2.0653, "step": 56680 }, { "epoch": 0.93, "learning_rate": 2.1707915831663328e-05, "loss": 2.1148, "step": 56690 }, { "epoch": 0.93, "learning_rate": 2.170290581162325e-05, "loss": 2.0262, "step": 56700 }, { "epoch": 0.93, "learning_rate": 2.1697895791583166e-05, "loss": 2.0286, "step": 56710 }, { "epoch": 0.93, "learning_rate": 2.1692885771543087e-05, "loss": 2.0541, "step": 56720 }, { "epoch": 0.93, "learning_rate": 2.1687875751503007e-05, "loss": 2.0153, "step": 56730 }, { "epoch": 0.93, "learning_rate": 2.1682865731462925e-05, "loss": 2.0536, "step": 56740 }, { "epoch": 0.93, "learning_rate": 2.167785571142285e-05, "loss": 2.0712, "step": 56750 }, { "epoch": 0.93, "learning_rate": 2.167284569138277e-05, "loss": 2.097, "step": 56760 }, { "epoch": 0.93, "learning_rate": 2.1667835671342686e-05, "loss": 2.0564, "step": 56770 }, { "epoch": 0.93, "learning_rate": 2.1662825651302607e-05, "loss": 2.0735, "step": 56780 }, { "epoch": 0.93, "learning_rate": 2.1657815631262528e-05, "loss": 2.0857, "step": 56790 }, { "epoch": 0.93, "learning_rate": 2.1652805611222445e-05, "loss": 2.0409, "step": 56800 }, { "epoch": 0.93, "learning_rate": 2.1647795591182366e-05, "loss": 2.0354, "step": 56810 }, { "epoch": 0.93, "learning_rate": 2.1642785571142286e-05, "loss": 2.0017, "step": 56820 }, { "epoch": 0.93, "learning_rate": 2.1637775551102204e-05, "loss": 2.0492, "step": 56830 }, { "epoch": 0.93, "learning_rate": 2.1632765531062124e-05, "loss": 2.0318, "step": 56840 }, { "epoch": 0.93, "learning_rate": 2.1627755511022045e-05, "loss": 2.0721, "step": 56850 }, { "epoch": 0.93, "learning_rate": 2.1622745490981965e-05, "loss": 2.068, "step": 56860 }, { "epoch": 0.93, "learning_rate": 2.1617735470941886e-05, "loss": 2.0209, "step": 56870 }, { "epoch": 0.93, "learning_rate": 2.1612725450901807e-05, "loss": 2.01, "step": 56880 }, { "epoch": 0.93, "learning_rate": 2.1607715430861724e-05, "loss": 2.0659, "step": 56890 }, { "epoch": 0.93, "learning_rate": 2.1602705410821645e-05, "loss": 2.0166, "step": 56900 }, { "epoch": 0.93, "learning_rate": 2.1597695390781565e-05, "loss": 2.0631, "step": 56910 }, { "epoch": 0.93, "learning_rate": 2.1592685370741483e-05, "loss": 2.0742, "step": 56920 }, { "epoch": 0.93, "learning_rate": 2.1587675350701403e-05, "loss": 2.0533, "step": 56930 }, { "epoch": 0.93, "learning_rate": 2.1582665330661324e-05, "loss": 2.1189, "step": 56940 }, { "epoch": 0.93, "learning_rate": 2.1577655310621244e-05, "loss": 2.0308, "step": 56950 }, { "epoch": 0.93, "learning_rate": 2.1572645290581165e-05, "loss": 1.9985, "step": 56960 }, { "epoch": 0.93, "learning_rate": 2.1567635270541082e-05, "loss": 2.0206, "step": 56970 }, { "epoch": 0.93, "learning_rate": 2.1562625250501003e-05, "loss": 2.0604, "step": 56980 }, { "epoch": 0.93, "learning_rate": 2.1557615230460924e-05, "loss": 2.0436, "step": 56990 }, { "epoch": 0.93, "learning_rate": 2.1552605210420844e-05, "loss": 2.0321, "step": 57000 }, { "epoch": 0.93, "eval_loss": 2.028777599334717, "eval_mean_f1": 0.6576629670720414, "eval_rouge1_f1": 0.715502579254162, "eval_rouge1_precision": 0.8265555521314365, "eval_rouge1_recall": 0.6644665117461674, "eval_rouge2_f1": 0.5739499882834602, "eval_rouge2_precision": 0.6660913197046011, "eval_rouge2_recall": 0.5333788855336672, "eval_rougeL_f1": 0.6835363336785022, "eval_rougeL_precision": 0.7876761432931723, "eval_rougeL_recall": 0.6360858763028368, "eval_runtime": 62.8307, "eval_samples_per_second": 16.298, "eval_steps_per_second": 2.037, "step": 57000 }, { "epoch": 0.93, "learning_rate": 2.154759519038076e-05, "loss": 2.0524, "step": 57010 }, { "epoch": 0.93, "learning_rate": 2.1542585170340682e-05, "loss": 2.0664, "step": 57020 }, { "epoch": 0.93, "learning_rate": 2.1537575150300603e-05, "loss": 2.0262, "step": 57030 }, { "epoch": 0.93, "learning_rate": 2.153256513026052e-05, "loss": 2.029, "step": 57040 }, { "epoch": 0.93, "learning_rate": 2.1527555110220444e-05, "loss": 2.046, "step": 57050 }, { "epoch": 0.93, "learning_rate": 2.152254509018036e-05, "loss": 2.0442, "step": 57060 }, { "epoch": 0.93, "learning_rate": 2.1517535070140282e-05, "loss": 2.0235, "step": 57070 }, { "epoch": 0.93, "learning_rate": 2.1512525050100203e-05, "loss": 2.064, "step": 57080 }, { "epoch": 0.93, "learning_rate": 2.150751503006012e-05, "loss": 2.044, "step": 57090 }, { "epoch": 0.93, "learning_rate": 2.150250501002004e-05, "loss": 2.0454, "step": 57100 }, { "epoch": 0.93, "learning_rate": 2.149749498997996e-05, "loss": 2.0539, "step": 57110 }, { "epoch": 0.93, "learning_rate": 2.149248496993988e-05, "loss": 2.0552, "step": 57120 }, { "epoch": 0.93, "learning_rate": 2.14874749498998e-05, "loss": 2.0788, "step": 57130 }, { "epoch": 0.93, "learning_rate": 2.148246492985972e-05, "loss": 2.0754, "step": 57140 }, { "epoch": 0.93, "learning_rate": 2.147745490981964e-05, "loss": 2.051, "step": 57150 }, { "epoch": 0.93, "learning_rate": 2.147244488977956e-05, "loss": 2.1006, "step": 57160 }, { "epoch": 0.93, "learning_rate": 2.146743486973948e-05, "loss": 2.082, "step": 57170 }, { "epoch": 0.93, "learning_rate": 2.14624248496994e-05, "loss": 2.0497, "step": 57180 }, { "epoch": 0.93, "learning_rate": 2.145741482965932e-05, "loss": 2.0664, "step": 57190 }, { "epoch": 0.93, "learning_rate": 2.145240480961924e-05, "loss": 2.0204, "step": 57200 }, { "epoch": 0.93, "learning_rate": 2.1447394789579157e-05, "loss": 2.0414, "step": 57210 }, { "epoch": 0.93, "learning_rate": 2.1442384769539078e-05, "loss": 2.0411, "step": 57220 }, { "epoch": 0.94, "learning_rate": 2.1437374749499e-05, "loss": 2.045, "step": 57230 }, { "epoch": 0.94, "learning_rate": 2.1432364729458916e-05, "loss": 2.0413, "step": 57240 }, { "epoch": 0.94, "learning_rate": 2.142735470941884e-05, "loss": 2.0989, "step": 57250 }, { "epoch": 0.94, "learning_rate": 2.142234468937876e-05, "loss": 2.0681, "step": 57260 }, { "epoch": 0.94, "learning_rate": 2.1417334669338678e-05, "loss": 2.0593, "step": 57270 }, { "epoch": 0.94, "learning_rate": 2.14123246492986e-05, "loss": 2.0298, "step": 57280 }, { "epoch": 0.94, "learning_rate": 2.140731462925852e-05, "loss": 2.0848, "step": 57290 }, { "epoch": 0.94, "learning_rate": 2.1402304609218436e-05, "loss": 2.0433, "step": 57300 }, { "epoch": 0.94, "learning_rate": 2.1397294589178357e-05, "loss": 2.0692, "step": 57310 }, { "epoch": 0.94, "learning_rate": 2.1392284569138278e-05, "loss": 2.0599, "step": 57320 }, { "epoch": 0.94, "learning_rate": 2.1387274549098195e-05, "loss": 2.0257, "step": 57330 }, { "epoch": 0.94, "learning_rate": 2.138226452905812e-05, "loss": 2.0534, "step": 57340 }, { "epoch": 0.94, "learning_rate": 2.137725450901804e-05, "loss": 2.0598, "step": 57350 }, { "epoch": 0.94, "learning_rate": 2.1372244488977957e-05, "loss": 2.0289, "step": 57360 }, { "epoch": 0.94, "learning_rate": 2.1367234468937877e-05, "loss": 2.0168, "step": 57370 }, { "epoch": 0.94, "learning_rate": 2.1362224448897798e-05, "loss": 2.0519, "step": 57380 }, { "epoch": 0.94, "learning_rate": 2.1357214428857715e-05, "loss": 2.0607, "step": 57390 }, { "epoch": 0.94, "learning_rate": 2.1352204408817636e-05, "loss": 2.037, "step": 57400 }, { "epoch": 0.94, "learning_rate": 2.1347194388777557e-05, "loss": 2.0344, "step": 57410 }, { "epoch": 0.94, "learning_rate": 2.1342184368737474e-05, "loss": 2.0312, "step": 57420 }, { "epoch": 0.94, "learning_rate": 2.1337174348697395e-05, "loss": 2.08, "step": 57430 }, { "epoch": 0.94, "learning_rate": 2.133216432865732e-05, "loss": 2.0726, "step": 57440 }, { "epoch": 0.94, "learning_rate": 2.1327154308617236e-05, "loss": 2.0203, "step": 57450 }, { "epoch": 0.94, "learning_rate": 2.1322144288577156e-05, "loss": 2.0524, "step": 57460 }, { "epoch": 0.94, "learning_rate": 2.1317134268537077e-05, "loss": 2.0061, "step": 57470 }, { "epoch": 0.94, "learning_rate": 2.1312124248496994e-05, "loss": 2.0302, "step": 57480 }, { "epoch": 0.94, "learning_rate": 2.1307114228456915e-05, "loss": 2.0476, "step": 57490 }, { "epoch": 0.94, "learning_rate": 2.1302104208416836e-05, "loss": 2.051, "step": 57500 }, { "epoch": 0.94, "learning_rate": 2.1297094188376753e-05, "loss": 2.0553, "step": 57510 }, { "epoch": 0.94, "learning_rate": 2.1292084168336674e-05, "loss": 2.1005, "step": 57520 }, { "epoch": 0.94, "learning_rate": 2.1287074148296594e-05, "loss": 2.0463, "step": 57530 }, { "epoch": 0.94, "learning_rate": 2.1282064128256515e-05, "loss": 2.0353, "step": 57540 }, { "epoch": 0.94, "learning_rate": 2.1277054108216435e-05, "loss": 2.0723, "step": 57550 }, { "epoch": 0.94, "learning_rate": 2.1272044088176353e-05, "loss": 2.065, "step": 57560 }, { "epoch": 0.94, "learning_rate": 2.1267034068136273e-05, "loss": 2.0961, "step": 57570 }, { "epoch": 0.94, "learning_rate": 2.1262024048096194e-05, "loss": 2.0302, "step": 57580 }, { "epoch": 0.94, "learning_rate": 2.1257014028056115e-05, "loss": 2.0435, "step": 57590 }, { "epoch": 0.94, "learning_rate": 2.1252004008016032e-05, "loss": 2.0018, "step": 57600 }, { "epoch": 0.94, "learning_rate": 2.1246993987975953e-05, "loss": 2.0659, "step": 57610 }, { "epoch": 0.94, "learning_rate": 2.1241983967935873e-05, "loss": 2.0185, "step": 57620 }, { "epoch": 0.94, "learning_rate": 2.123697394789579e-05, "loss": 2.0503, "step": 57630 }, { "epoch": 0.94, "learning_rate": 2.1231963927855714e-05, "loss": 2.0178, "step": 57640 }, { "epoch": 0.94, "learning_rate": 2.1226953907815632e-05, "loss": 2.0126, "step": 57650 }, { "epoch": 0.94, "learning_rate": 2.1221943887775552e-05, "loss": 2.0885, "step": 57660 }, { "epoch": 0.94, "learning_rate": 2.1216933867735473e-05, "loss": 2.0451, "step": 57670 }, { "epoch": 0.94, "learning_rate": 2.121192384769539e-05, "loss": 2.0654, "step": 57680 }, { "epoch": 0.94, "learning_rate": 2.120691382765531e-05, "loss": 2.0795, "step": 57690 }, { "epoch": 0.94, "learning_rate": 2.120190380761523e-05, "loss": 2.0488, "step": 57700 }, { "epoch": 0.94, "learning_rate": 2.1196893787575152e-05, "loss": 2.0781, "step": 57710 }, { "epoch": 0.94, "learning_rate": 2.119188376753507e-05, "loss": 2.0429, "step": 57720 }, { "epoch": 0.94, "learning_rate": 2.118687374749499e-05, "loss": 2.066, "step": 57730 }, { "epoch": 0.94, "learning_rate": 2.118186372745491e-05, "loss": 2.0284, "step": 57740 }, { "epoch": 0.94, "learning_rate": 2.117685370741483e-05, "loss": 2.0624, "step": 57750 }, { "epoch": 0.94, "learning_rate": 2.1171843687374752e-05, "loss": 2.0549, "step": 57760 }, { "epoch": 0.94, "learning_rate": 2.116683366733467e-05, "loss": 2.0471, "step": 57770 }, { "epoch": 0.94, "learning_rate": 2.116182364729459e-05, "loss": 2.0457, "step": 57780 }, { "epoch": 0.94, "learning_rate": 2.115681362725451e-05, "loss": 2.0245, "step": 57790 }, { "epoch": 0.94, "learning_rate": 2.1151803607214428e-05, "loss": 2.0272, "step": 57800 }, { "epoch": 0.94, "learning_rate": 2.114679358717435e-05, "loss": 2.0798, "step": 57810 }, { "epoch": 0.94, "learning_rate": 2.114178356713427e-05, "loss": 2.0145, "step": 57820 }, { "epoch": 0.94, "learning_rate": 2.113677354709419e-05, "loss": 2.0766, "step": 57830 }, { "epoch": 0.95, "learning_rate": 2.113176352705411e-05, "loss": 2.0096, "step": 57840 }, { "epoch": 0.95, "learning_rate": 2.112675350701403e-05, "loss": 2.0842, "step": 57850 }, { "epoch": 0.95, "learning_rate": 2.1121743486973948e-05, "loss": 2.0219, "step": 57860 }, { "epoch": 0.95, "learning_rate": 2.111673346693387e-05, "loss": 2.0031, "step": 57870 }, { "epoch": 0.95, "learning_rate": 2.111172344689379e-05, "loss": 2.0363, "step": 57880 }, { "epoch": 0.95, "learning_rate": 2.1106713426853707e-05, "loss": 2.0475, "step": 57890 }, { "epoch": 0.95, "learning_rate": 2.1101703406813627e-05, "loss": 2.0671, "step": 57900 }, { "epoch": 0.95, "learning_rate": 2.1096693386773548e-05, "loss": 2.045, "step": 57910 }, { "epoch": 0.95, "learning_rate": 2.1091683366733465e-05, "loss": 2.0108, "step": 57920 }, { "epoch": 0.95, "learning_rate": 2.108667334669339e-05, "loss": 2.0406, "step": 57930 }, { "epoch": 0.95, "learning_rate": 2.108166332665331e-05, "loss": 2.0586, "step": 57940 }, { "epoch": 0.95, "learning_rate": 2.1076653306613227e-05, "loss": 2.068, "step": 57950 }, { "epoch": 0.95, "learning_rate": 2.1071643286573148e-05, "loss": 2.0282, "step": 57960 }, { "epoch": 0.95, "learning_rate": 2.106663326653307e-05, "loss": 2.0618, "step": 57970 }, { "epoch": 0.95, "learning_rate": 2.1061623246492986e-05, "loss": 2.0753, "step": 57980 }, { "epoch": 0.95, "learning_rate": 2.1056613226452906e-05, "loss": 2.0488, "step": 57990 }, { "epoch": 0.95, "learning_rate": 2.1051603206412827e-05, "loss": 2.0679, "step": 58000 }, { "epoch": 0.95, "eval_loss": 2.026101589202881, "eval_mean_f1": 0.6589331657451146, "eval_rouge1_f1": 0.7170010835240004, "eval_rouge1_precision": 0.8288110069726278, "eval_rouge1_recall": 0.6651095409697599, "eval_rouge2_f1": 0.5741982896536094, "eval_rouge2_precision": 0.6668904019428921, "eval_rouge2_recall": 0.5328398967711281, "eval_rougeL_f1": 0.685600124057734, "eval_rougeL_precision": 0.7904419583748055, "eval_rougeL_recall": 0.6373525268569158, "eval_runtime": 62.9335, "eval_samples_per_second": 16.271, "eval_steps_per_second": 2.034, "step": 58000 }, { "epoch": 0.95, "learning_rate": 2.1046593186372744e-05, "loss": 2.0199, "step": 58010 }, { "epoch": 0.95, "learning_rate": 2.1041583166332665e-05, "loss": 2.0414, "step": 58020 }, { "epoch": 0.95, "learning_rate": 2.103657314629259e-05, "loss": 2.0197, "step": 58030 }, { "epoch": 0.95, "learning_rate": 2.1031563126252506e-05, "loss": 2.0592, "step": 58040 }, { "epoch": 0.95, "learning_rate": 2.1026553106212427e-05, "loss": 2.0237, "step": 58050 }, { "epoch": 0.95, "learning_rate": 2.1021543086172348e-05, "loss": 2.0783, "step": 58060 }, { "epoch": 0.95, "learning_rate": 2.1016533066132265e-05, "loss": 2.0352, "step": 58070 }, { "epoch": 0.95, "learning_rate": 2.1011523046092185e-05, "loss": 2.068, "step": 58080 }, { "epoch": 0.95, "learning_rate": 2.1006513026052106e-05, "loss": 2.0571, "step": 58090 }, { "epoch": 0.95, "learning_rate": 2.1001503006012023e-05, "loss": 2.0542, "step": 58100 }, { "epoch": 0.95, "learning_rate": 2.0996492985971944e-05, "loss": 2.0268, "step": 58110 }, { "epoch": 0.95, "learning_rate": 2.0991482965931865e-05, "loss": 2.0278, "step": 58120 }, { "epoch": 0.95, "learning_rate": 2.0986472945891785e-05, "loss": 2.034, "step": 58130 }, { "epoch": 0.95, "learning_rate": 2.0981462925851706e-05, "loss": 2.0226, "step": 58140 }, { "epoch": 0.95, "learning_rate": 2.0976452905811627e-05, "loss": 2.0402, "step": 58150 }, { "epoch": 0.95, "learning_rate": 2.0971442885771544e-05, "loss": 2.0908, "step": 58160 }, { "epoch": 0.95, "learning_rate": 2.0966432865731464e-05, "loss": 2.0461, "step": 58170 }, { "epoch": 0.95, "learning_rate": 2.0961422845691385e-05, "loss": 2.0351, "step": 58180 }, { "epoch": 0.95, "learning_rate": 2.0956412825651302e-05, "loss": 2.057, "step": 58190 }, { "epoch": 0.95, "learning_rate": 2.0951402805611223e-05, "loss": 2.0462, "step": 58200 }, { "epoch": 0.95, "learning_rate": 2.0946392785571144e-05, "loss": 2.042, "step": 58210 }, { "epoch": 0.95, "learning_rate": 2.094138276553106e-05, "loss": 2.069, "step": 58220 }, { "epoch": 0.95, "learning_rate": 2.0936372745490985e-05, "loss": 2.0319, "step": 58230 }, { "epoch": 0.95, "learning_rate": 2.0931362725450902e-05, "loss": 2.0662, "step": 58240 }, { "epoch": 0.95, "learning_rate": 2.0926352705410823e-05, "loss": 2.0189, "step": 58250 }, { "epoch": 0.95, "learning_rate": 2.0921342685370743e-05, "loss": 2.0042, "step": 58260 }, { "epoch": 0.95, "learning_rate": 2.0916332665330664e-05, "loss": 2.0547, "step": 58270 }, { "epoch": 0.95, "learning_rate": 2.091132264529058e-05, "loss": 2.0043, "step": 58280 }, { "epoch": 0.95, "learning_rate": 2.0906312625250502e-05, "loss": 2.041, "step": 58290 }, { "epoch": 0.95, "learning_rate": 2.0901302605210423e-05, "loss": 2.0685, "step": 58300 }, { "epoch": 0.95, "learning_rate": 2.089629258517034e-05, "loss": 2.0405, "step": 58310 }, { "epoch": 0.95, "learning_rate": 2.089128256513026e-05, "loss": 2.0156, "step": 58320 }, { "epoch": 0.95, "learning_rate": 2.088627254509018e-05, "loss": 2.0537, "step": 58330 }, { "epoch": 0.95, "learning_rate": 2.0881262525050102e-05, "loss": 2.0679, "step": 58340 }, { "epoch": 0.95, "learning_rate": 2.0876252505010022e-05, "loss": 2.0252, "step": 58350 }, { "epoch": 0.95, "learning_rate": 2.087124248496994e-05, "loss": 2.0566, "step": 58360 }, { "epoch": 0.95, "learning_rate": 2.086623246492986e-05, "loss": 2.0441, "step": 58370 }, { "epoch": 0.95, "learning_rate": 2.086122244488978e-05, "loss": 2.0665, "step": 58380 }, { "epoch": 0.95, "learning_rate": 2.0856212424849698e-05, "loss": 2.0714, "step": 58390 }, { "epoch": 0.95, "learning_rate": 2.085120240480962e-05, "loss": 2.0343, "step": 58400 }, { "epoch": 0.95, "learning_rate": 2.084619238476954e-05, "loss": 2.0669, "step": 58410 }, { "epoch": 0.95, "learning_rate": 2.084118236472946e-05, "loss": 2.0599, "step": 58420 }, { "epoch": 0.95, "learning_rate": 2.083617234468938e-05, "loss": 2.0491, "step": 58430 }, { "epoch": 0.95, "learning_rate": 2.08311623246493e-05, "loss": 2.0407, "step": 58440 }, { "epoch": 0.96, "learning_rate": 2.082615230460922e-05, "loss": 2.0225, "step": 58450 }, { "epoch": 0.96, "learning_rate": 2.082114228456914e-05, "loss": 2.0173, "step": 58460 }, { "epoch": 0.96, "learning_rate": 2.081613226452906e-05, "loss": 2.0477, "step": 58470 }, { "epoch": 0.96, "learning_rate": 2.0811122244488977e-05, "loss": 2.0421, "step": 58480 }, { "epoch": 0.96, "learning_rate": 2.0806112224448898e-05, "loss": 2.0585, "step": 58490 }, { "epoch": 0.96, "learning_rate": 2.080110220440882e-05, "loss": 2.0399, "step": 58500 }, { "epoch": 0.96, "learning_rate": 2.0796092184368736e-05, "loss": 2.007, "step": 58510 }, { "epoch": 0.96, "learning_rate": 2.079108216432866e-05, "loss": 2.0636, "step": 58520 }, { "epoch": 0.96, "learning_rate": 2.078607214428858e-05, "loss": 2.0237, "step": 58530 }, { "epoch": 0.96, "learning_rate": 2.0781062124248498e-05, "loss": 2.0211, "step": 58540 }, { "epoch": 0.96, "learning_rate": 2.0776052104208418e-05, "loss": 2.1173, "step": 58550 }, { "epoch": 0.96, "learning_rate": 2.077104208416834e-05, "loss": 2.0689, "step": 58560 }, { "epoch": 0.96, "learning_rate": 2.0766032064128256e-05, "loss": 2.0612, "step": 58570 }, { "epoch": 0.96, "learning_rate": 2.0761022044088177e-05, "loss": 2.029, "step": 58580 }, { "epoch": 0.96, "learning_rate": 2.0756012024048097e-05, "loss": 2.0697, "step": 58590 }, { "epoch": 0.96, "learning_rate": 2.0751002004008015e-05, "loss": 2.0973, "step": 58600 }, { "epoch": 0.96, "learning_rate": 2.0745991983967935e-05, "loss": 2.0443, "step": 58610 }, { "epoch": 0.96, "learning_rate": 2.074098196392786e-05, "loss": 2.0661, "step": 58620 }, { "epoch": 0.96, "learning_rate": 2.0735971943887777e-05, "loss": 2.0285, "step": 58630 }, { "epoch": 0.96, "learning_rate": 2.0730961923847697e-05, "loss": 2.0761, "step": 58640 }, { "epoch": 0.96, "learning_rate": 2.0725951903807618e-05, "loss": 2.0833, "step": 58650 }, { "epoch": 0.96, "learning_rate": 2.0720941883767535e-05, "loss": 2.081, "step": 58660 }, { "epoch": 0.96, "learning_rate": 2.0715931863727456e-05, "loss": 2.0598, "step": 58670 }, { "epoch": 0.96, "learning_rate": 2.0710921843687376e-05, "loss": 2.0923, "step": 58680 }, { "epoch": 0.96, "learning_rate": 2.0705911823647294e-05, "loss": 2.0526, "step": 58690 }, { "epoch": 0.96, "learning_rate": 2.0700901803607214e-05, "loss": 2.0375, "step": 58700 }, { "epoch": 0.96, "learning_rate": 2.0695891783567135e-05, "loss": 2.0393, "step": 58710 }, { "epoch": 0.96, "learning_rate": 2.0690881763527056e-05, "loss": 2.0379, "step": 58720 }, { "epoch": 0.96, "learning_rate": 2.0685871743486976e-05, "loss": 2.0296, "step": 58730 }, { "epoch": 0.96, "learning_rate": 2.0680861723446897e-05, "loss": 2.044, "step": 58740 }, { "epoch": 0.96, "learning_rate": 2.0675851703406814e-05, "loss": 2.0453, "step": 58750 }, { "epoch": 0.96, "learning_rate": 2.0670841683366735e-05, "loss": 2.0685, "step": 58760 }, { "epoch": 0.96, "learning_rate": 2.0665831663326655e-05, "loss": 2.0201, "step": 58770 }, { "epoch": 0.96, "learning_rate": 2.0660821643286573e-05, "loss": 2.0082, "step": 58780 }, { "epoch": 0.96, "learning_rate": 2.0655811623246493e-05, "loss": 2.0065, "step": 58790 }, { "epoch": 0.96, "learning_rate": 2.0650801603206414e-05, "loss": 2.0539, "step": 58800 }, { "epoch": 0.96, "learning_rate": 2.064579158316633e-05, "loss": 2.0134, "step": 58810 }, { "epoch": 0.96, "learning_rate": 2.0640781563126255e-05, "loss": 2.0345, "step": 58820 }, { "epoch": 0.96, "learning_rate": 2.0635771543086173e-05, "loss": 2.0535, "step": 58830 }, { "epoch": 0.96, "learning_rate": 2.0630761523046093e-05, "loss": 2.038, "step": 58840 }, { "epoch": 0.96, "learning_rate": 2.0625751503006014e-05, "loss": 2.0302, "step": 58850 }, { "epoch": 0.96, "learning_rate": 2.0620741482965934e-05, "loss": 2.0649, "step": 58860 }, { "epoch": 0.96, "learning_rate": 2.0615731462925852e-05, "loss": 2.077, "step": 58870 }, { "epoch": 0.96, "learning_rate": 2.0610721442885772e-05, "loss": 2.0329, "step": 58880 }, { "epoch": 0.96, "learning_rate": 2.0605711422845693e-05, "loss": 2.0103, "step": 58890 }, { "epoch": 0.96, "learning_rate": 2.060070140280561e-05, "loss": 2.0503, "step": 58900 }, { "epoch": 0.96, "learning_rate": 2.059569138276553e-05, "loss": 2.0479, "step": 58910 }, { "epoch": 0.96, "learning_rate": 2.059068136272545e-05, "loss": 2.009, "step": 58920 }, { "epoch": 0.96, "learning_rate": 2.0585671342685372e-05, "loss": 2.084, "step": 58930 }, { "epoch": 0.96, "learning_rate": 2.0580661322645293e-05, "loss": 2.0202, "step": 58940 }, { "epoch": 0.96, "learning_rate": 2.057565130260521e-05, "loss": 2.0461, "step": 58950 }, { "epoch": 0.96, "learning_rate": 2.057064128256513e-05, "loss": 2.0006, "step": 58960 }, { "epoch": 0.96, "learning_rate": 2.056563126252505e-05, "loss": 2.0346, "step": 58970 }, { "epoch": 0.96, "learning_rate": 2.0560621242484972e-05, "loss": 2.0552, "step": 58980 }, { "epoch": 0.96, "learning_rate": 2.055561122244489e-05, "loss": 2.0322, "step": 58990 }, { "epoch": 0.96, "learning_rate": 2.055060120240481e-05, "loss": 2.0801, "step": 59000 }, { "epoch": 0.96, "eval_loss": 2.0285139083862305, "eval_mean_f1": 0.6529782827005596, "eval_rouge1_f1": 0.7122025838844022, "eval_rouge1_precision": 0.8240973486101444, "eval_rouge1_recall": 0.6602801673579326, "eval_rouge2_f1": 0.5674009549371912, "eval_rouge2_precision": 0.6606846048374369, "eval_rouge2_recall": 0.5260822910850792, "eval_rougeL_f1": 0.6793313092800852, "eval_rougeL_precision": 0.7840482833952076, "eval_rougeL_recall": 0.6310083577377059, "eval_runtime": 63.2568, "eval_samples_per_second": 16.188, "eval_steps_per_second": 2.023, "step": 59000 }, { "epoch": 0.96, "learning_rate": 2.054559118236473e-05, "loss": 2.0283, "step": 59010 }, { "epoch": 0.96, "learning_rate": 2.054058116232465e-05, "loss": 2.0461, "step": 59020 }, { "epoch": 0.96, "learning_rate": 2.0535571142284572e-05, "loss": 2.0454, "step": 59030 }, { "epoch": 0.96, "learning_rate": 2.053056112224449e-05, "loss": 2.0412, "step": 59040 }, { "epoch": 0.96, "learning_rate": 2.052555110220441e-05, "loss": 2.0434, "step": 59050 }, { "epoch": 0.97, "learning_rate": 2.052054108216433e-05, "loss": 2.0581, "step": 59060 }, { "epoch": 0.97, "learning_rate": 2.0515531062124248e-05, "loss": 1.9973, "step": 59070 }, { "epoch": 0.97, "learning_rate": 2.0510521042084168e-05, "loss": 2.0373, "step": 59080 }, { "epoch": 0.97, "learning_rate": 2.050551102204409e-05, "loss": 2.0766, "step": 59090 }, { "epoch": 0.97, "learning_rate": 2.0500501002004006e-05, "loss": 2.0227, "step": 59100 }, { "epoch": 0.97, "learning_rate": 2.049549098196393e-05, "loss": 2.0263, "step": 59110 }, { "epoch": 0.97, "learning_rate": 2.049048096192385e-05, "loss": 2.0673, "step": 59120 }, { "epoch": 0.97, "learning_rate": 2.0485470941883768e-05, "loss": 2.0846, "step": 59130 }, { "epoch": 0.97, "learning_rate": 2.048046092184369e-05, "loss": 2.0262, "step": 59140 }, { "epoch": 0.97, "learning_rate": 2.047545090180361e-05, "loss": 2.1036, "step": 59150 }, { "epoch": 0.97, "learning_rate": 2.0470440881763527e-05, "loss": 2.0188, "step": 59160 }, { "epoch": 0.97, "learning_rate": 2.0465430861723447e-05, "loss": 2.076, "step": 59170 }, { "epoch": 0.97, "learning_rate": 2.0460420841683368e-05, "loss": 2.0392, "step": 59180 }, { "epoch": 0.97, "learning_rate": 2.0455410821643285e-05, "loss": 2.0074, "step": 59190 }, { "epoch": 0.97, "learning_rate": 2.0450400801603206e-05, "loss": 2.0406, "step": 59200 }, { "epoch": 0.97, "learning_rate": 2.044539078156313e-05, "loss": 2.0733, "step": 59210 }, { "epoch": 0.97, "learning_rate": 2.0440380761523047e-05, "loss": 2.0668, "step": 59220 }, { "epoch": 0.97, "learning_rate": 2.0435370741482968e-05, "loss": 2.0142, "step": 59230 }, { "epoch": 0.97, "learning_rate": 2.043036072144289e-05, "loss": 2.0625, "step": 59240 }, { "epoch": 0.97, "learning_rate": 2.0425350701402806e-05, "loss": 2.0225, "step": 59250 }, { "epoch": 0.97, "learning_rate": 2.0420340681362726e-05, "loss": 2.0098, "step": 59260 }, { "epoch": 0.97, "learning_rate": 2.0415330661322647e-05, "loss": 2.0042, "step": 59270 }, { "epoch": 0.97, "learning_rate": 2.0410320641282564e-05, "loss": 1.9776, "step": 59280 }, { "epoch": 0.97, "learning_rate": 2.0405310621242485e-05, "loss": 2.0116, "step": 59290 }, { "epoch": 0.97, "learning_rate": 2.0400300601202405e-05, "loss": 2.0617, "step": 59300 }, { "epoch": 0.97, "learning_rate": 2.0395290581162326e-05, "loss": 2.0421, "step": 59310 }, { "epoch": 0.97, "learning_rate": 2.0390280561122247e-05, "loss": 2.0229, "step": 59320 }, { "epoch": 0.97, "learning_rate": 2.0385270541082167e-05, "loss": 2.0687, "step": 59330 }, { "epoch": 0.97, "learning_rate": 2.0380260521042085e-05, "loss": 2.0084, "step": 59340 }, { "epoch": 0.97, "learning_rate": 2.0375250501002005e-05, "loss": 2.0681, "step": 59350 }, { "epoch": 0.97, "learning_rate": 2.0370240480961926e-05, "loss": 2.0745, "step": 59360 }, { "epoch": 0.97, "learning_rate": 2.0365230460921843e-05, "loss": 2.0904, "step": 59370 }, { "epoch": 0.97, "learning_rate": 2.0360220440881764e-05, "loss": 2.0102, "step": 59380 }, { "epoch": 0.97, "learning_rate": 2.0355210420841684e-05, "loss": 2.0862, "step": 59390 }, { "epoch": 0.97, "learning_rate": 2.03502004008016e-05, "loss": 2.0636, "step": 59400 }, { "epoch": 0.97, "learning_rate": 2.0345190380761526e-05, "loss": 2.0425, "step": 59410 }, { "epoch": 0.97, "learning_rate": 2.0340180360721446e-05, "loss": 2.0924, "step": 59420 }, { "epoch": 0.97, "learning_rate": 2.0335170340681364e-05, "loss": 2.0082, "step": 59430 }, { "epoch": 0.97, "learning_rate": 2.0330160320641284e-05, "loss": 2.0206, "step": 59440 }, { "epoch": 0.97, "learning_rate": 2.0325150300601205e-05, "loss": 2.0621, "step": 59450 }, { "epoch": 0.97, "learning_rate": 2.0320140280561122e-05, "loss": 2.0793, "step": 59460 }, { "epoch": 0.97, "learning_rate": 2.0315130260521043e-05, "loss": 2.0474, "step": 59470 }, { "epoch": 0.97, "learning_rate": 2.0310120240480963e-05, "loss": 2.0788, "step": 59480 }, { "epoch": 0.97, "learning_rate": 2.030511022044088e-05, "loss": 2.0681, "step": 59490 }, { "epoch": 0.97, "learning_rate": 2.0300100200400805e-05, "loss": 2.0502, "step": 59500 }, { "epoch": 0.97, "learning_rate": 2.0295090180360722e-05, "loss": 2.0241, "step": 59510 }, { "epoch": 0.97, "learning_rate": 2.0290080160320643e-05, "loss": 2.0129, "step": 59520 }, { "epoch": 0.97, "learning_rate": 2.0285070140280563e-05, "loss": 2.0482, "step": 59530 }, { "epoch": 0.97, "learning_rate": 2.0280060120240484e-05, "loss": 2.083, "step": 59540 }, { "epoch": 0.97, "learning_rate": 2.02750501002004e-05, "loss": 2.0362, "step": 59550 }, { "epoch": 0.97, "learning_rate": 2.0270040080160322e-05, "loss": 2.0341, "step": 59560 }, { "epoch": 0.97, "learning_rate": 2.0265030060120242e-05, "loss": 2.021, "step": 59570 }, { "epoch": 0.97, "learning_rate": 2.026002004008016e-05, "loss": 2.078, "step": 59580 }, { "epoch": 0.97, "learning_rate": 2.025501002004008e-05, "loss": 2.0482, "step": 59590 }, { "epoch": 0.97, "learning_rate": 2.025e-05, "loss": 2.0184, "step": 59600 }, { "epoch": 0.97, "learning_rate": 2.024498997995992e-05, "loss": 2.0315, "step": 59610 }, { "epoch": 0.97, "learning_rate": 2.0239979959919842e-05, "loss": 2.0673, "step": 59620 }, { "epoch": 0.97, "learning_rate": 2.023496993987976e-05, "loss": 2.0855, "step": 59630 }, { "epoch": 0.97, "learning_rate": 2.022995991983968e-05, "loss": 2.0531, "step": 59640 }, { "epoch": 0.97, "learning_rate": 2.02249498997996e-05, "loss": 2.0604, "step": 59650 }, { "epoch": 0.97, "learning_rate": 2.0219939879759518e-05, "loss": 2.0267, "step": 59660 }, { "epoch": 0.97, "learning_rate": 2.021492985971944e-05, "loss": 2.059, "step": 59670 }, { "epoch": 0.98, "learning_rate": 2.020991983967936e-05, "loss": 2.0296, "step": 59680 }, { "epoch": 0.98, "learning_rate": 2.020490981963928e-05, "loss": 2.0361, "step": 59690 }, { "epoch": 0.98, "learning_rate": 2.01998997995992e-05, "loss": 2.0458, "step": 59700 }, { "epoch": 0.98, "learning_rate": 2.019488977955912e-05, "loss": 2.0175, "step": 59710 }, { "epoch": 0.98, "learning_rate": 2.018987975951904e-05, "loss": 2.0371, "step": 59720 }, { "epoch": 0.98, "learning_rate": 2.018486973947896e-05, "loss": 2.065, "step": 59730 }, { "epoch": 0.98, "learning_rate": 2.017985971943888e-05, "loss": 2.0047, "step": 59740 }, { "epoch": 0.98, "learning_rate": 2.0174849699398797e-05, "loss": 2.0353, "step": 59750 }, { "epoch": 0.98, "learning_rate": 2.0169839679358718e-05, "loss": 2.0686, "step": 59760 }, { "epoch": 0.98, "learning_rate": 2.0164829659318638e-05, "loss": 2.0313, "step": 59770 }, { "epoch": 0.98, "learning_rate": 2.0159819639278556e-05, "loss": 2.0226, "step": 59780 }, { "epoch": 0.98, "learning_rate": 2.0154809619238476e-05, "loss": 2.0465, "step": 59790 }, { "epoch": 0.98, "learning_rate": 2.01497995991984e-05, "loss": 2.0574, "step": 59800 }, { "epoch": 0.98, "learning_rate": 2.0144789579158317e-05, "loss": 2.076, "step": 59810 }, { "epoch": 0.98, "learning_rate": 2.0139779559118238e-05, "loss": 2.0415, "step": 59820 }, { "epoch": 0.98, "learning_rate": 2.013476953907816e-05, "loss": 2.0541, "step": 59830 }, { "epoch": 0.98, "learning_rate": 2.0129759519038076e-05, "loss": 2.007, "step": 59840 }, { "epoch": 0.98, "learning_rate": 2.0124749498997997e-05, "loss": 2.0223, "step": 59850 }, { "epoch": 0.98, "learning_rate": 2.0119739478957917e-05, "loss": 2.0307, "step": 59860 }, { "epoch": 0.98, "learning_rate": 2.0114729458917835e-05, "loss": 2.0002, "step": 59870 }, { "epoch": 0.98, "learning_rate": 2.0109719438877755e-05, "loss": 2.01, "step": 59880 }, { "epoch": 0.98, "learning_rate": 2.0104709418837676e-05, "loss": 2.0663, "step": 59890 }, { "epoch": 0.98, "learning_rate": 2.0099699398797596e-05, "loss": 2.0196, "step": 59900 }, { "epoch": 0.98, "learning_rate": 2.0094689378757517e-05, "loss": 2.0434, "step": 59910 }, { "epoch": 0.98, "learning_rate": 2.0089679358717438e-05, "loss": 2.0224, "step": 59920 }, { "epoch": 0.98, "learning_rate": 2.0084669338677355e-05, "loss": 2.0622, "step": 59930 }, { "epoch": 0.98, "learning_rate": 2.0079659318637276e-05, "loss": 2.0378, "step": 59940 }, { "epoch": 0.98, "learning_rate": 2.0074649298597196e-05, "loss": 2.0441, "step": 59950 }, { "epoch": 0.98, "learning_rate": 2.0069639278557114e-05, "loss": 2.0518, "step": 59960 }, { "epoch": 0.98, "learning_rate": 2.0064629258517034e-05, "loss": 2.0217, "step": 59970 }, { "epoch": 0.98, "learning_rate": 2.0059619238476955e-05, "loss": 2.0724, "step": 59980 }, { "epoch": 0.98, "learning_rate": 2.0054609218436872e-05, "loss": 2.0281, "step": 59990 }, { "epoch": 0.98, "learning_rate": 2.0049599198396796e-05, "loss": 2.1049, "step": 60000 }, { "epoch": 0.98, "eval_loss": 2.0262234210968018, "eval_mean_f1": 0.6638383546591248, "eval_rouge1_f1": 0.7209874789987027, "eval_rouge1_precision": 0.8334680217945099, "eval_rouge1_recall": 0.6682811636790069, "eval_rouge2_f1": 0.5794271131746523, "eval_rouge2_precision": 0.6747357006329179, "eval_rouge2_recall": 0.5366041783416331, "eval_rougeL_f1": 0.6911004718040191, "eval_rougeL_precision": 0.7973926291201392, "eval_rougeL_recall": 0.6414782031579176, "eval_runtime": 63.7956, "eval_samples_per_second": 16.051, "eval_steps_per_second": 2.006, "step": 60000 }, { "epoch": 0.98, "learning_rate": 2.0044589178356717e-05, "loss": 2.0003, "step": 60010 }, { "epoch": 0.98, "learning_rate": 2.0039579158316634e-05, "loss": 1.999, "step": 60020 }, { "epoch": 0.98, "learning_rate": 2.0034569138276555e-05, "loss": 2.0021, "step": 60030 }, { "epoch": 0.98, "learning_rate": 2.0029559118236475e-05, "loss": 2.0626, "step": 60040 }, { "epoch": 0.98, "learning_rate": 2.0024549098196393e-05, "loss": 2.0725, "step": 60050 }, { "epoch": 0.98, "learning_rate": 2.0019539078156313e-05, "loss": 2.068, "step": 60060 }, { "epoch": 0.98, "learning_rate": 2.0014529058116234e-05, "loss": 2.0505, "step": 60070 }, { "epoch": 0.98, "learning_rate": 2.000951903807615e-05, "loss": 2.0235, "step": 60080 }, { "epoch": 0.98, "learning_rate": 2.0004509018036075e-05, "loss": 2.0685, "step": 60090 }, { "epoch": 0.98, "learning_rate": 1.9999498997995992e-05, "loss": 2.0389, "step": 60100 }, { "epoch": 0.98, "learning_rate": 1.9994488977955913e-05, "loss": 2.0311, "step": 60110 }, { "epoch": 0.98, "learning_rate": 1.9989478957915834e-05, "loss": 2.0655, "step": 60120 }, { "epoch": 0.98, "learning_rate": 1.9984468937875754e-05, "loss": 2.0864, "step": 60130 }, { "epoch": 0.98, "learning_rate": 1.997945891783567e-05, "loss": 2.0267, "step": 60140 }, { "epoch": 0.98, "learning_rate": 1.9974448897795592e-05, "loss": 2.0711, "step": 60150 }, { "epoch": 0.98, "learning_rate": 1.9969438877755513e-05, "loss": 2.0276, "step": 60160 }, { "epoch": 0.98, "learning_rate": 1.996442885771543e-05, "loss": 2.0671, "step": 60170 }, { "epoch": 0.98, "learning_rate": 1.995941883767535e-05, "loss": 2.0455, "step": 60180 }, { "epoch": 0.98, "learning_rate": 1.995440881763527e-05, "loss": 2.0431, "step": 60190 }, { "epoch": 0.98, "learning_rate": 1.9949398797595192e-05, "loss": 2.0191, "step": 60200 }, { "epoch": 0.98, "learning_rate": 1.9944388777555113e-05, "loss": 2.081, "step": 60210 }, { "epoch": 0.98, "learning_rate": 1.993937875751503e-05, "loss": 2.0301, "step": 60220 }, { "epoch": 0.98, "learning_rate": 1.993436873747495e-05, "loss": 2.0675, "step": 60230 }, { "epoch": 0.98, "learning_rate": 1.992935871743487e-05, "loss": 2.0301, "step": 60240 }, { "epoch": 0.98, "learning_rate": 1.9924348697394792e-05, "loss": 2.0332, "step": 60250 }, { "epoch": 0.98, "learning_rate": 1.991933867735471e-05, "loss": 2.0409, "step": 60260 }, { "epoch": 0.98, "learning_rate": 1.991432865731463e-05, "loss": 2.0468, "step": 60270 }, { "epoch": 0.98, "learning_rate": 1.990931863727455e-05, "loss": 2.0306, "step": 60280 }, { "epoch": 0.99, "learning_rate": 1.990430861723447e-05, "loss": 2.0441, "step": 60290 }, { "epoch": 0.99, "learning_rate": 1.989929859719439e-05, "loss": 2.0509, "step": 60300 }, { "epoch": 0.99, "learning_rate": 1.989428857715431e-05, "loss": 2.0305, "step": 60310 }, { "epoch": 0.99, "learning_rate": 1.988927855711423e-05, "loss": 2.0475, "step": 60320 }, { "epoch": 0.99, "learning_rate": 1.988426853707415e-05, "loss": 2.0489, "step": 60330 }, { "epoch": 0.99, "learning_rate": 1.9879258517034067e-05, "loss": 2.0492, "step": 60340 }, { "epoch": 0.99, "learning_rate": 1.9874248496993988e-05, "loss": 2.0687, "step": 60350 }, { "epoch": 0.99, "learning_rate": 1.986923847695391e-05, "loss": 2.0588, "step": 60360 }, { "epoch": 0.99, "learning_rate": 1.9864228456913826e-05, "loss": 2.0366, "step": 60370 }, { "epoch": 0.99, "learning_rate": 1.9859218436873747e-05, "loss": 2.0486, "step": 60380 }, { "epoch": 0.99, "learning_rate": 1.985420841683367e-05, "loss": 2.0325, "step": 60390 }, { "epoch": 0.99, "learning_rate": 1.9849198396793588e-05, "loss": 2.0924, "step": 60400 }, { "epoch": 0.99, "learning_rate": 1.984418837675351e-05, "loss": 2.0779, "step": 60410 }, { "epoch": 0.99, "learning_rate": 1.983917835671343e-05, "loss": 2.02, "step": 60420 }, { "epoch": 0.99, "learning_rate": 1.9834168336673346e-05, "loss": 2.0924, "step": 60430 }, { "epoch": 0.99, "learning_rate": 1.9829158316633267e-05, "loss": 2.0538, "step": 60440 }, { "epoch": 0.99, "learning_rate": 1.9824148296593188e-05, "loss": 2.0423, "step": 60450 }, { "epoch": 0.99, "learning_rate": 1.9819138276553105e-05, "loss": 2.0506, "step": 60460 }, { "epoch": 0.99, "learning_rate": 1.9814128256513026e-05, "loss": 2.0211, "step": 60470 }, { "epoch": 0.99, "learning_rate": 1.9809118236472946e-05, "loss": 2.0541, "step": 60480 }, { "epoch": 0.99, "learning_rate": 1.9804108216432867e-05, "loss": 2.0407, "step": 60490 }, { "epoch": 0.99, "learning_rate": 1.9799098196392788e-05, "loss": 2.0733, "step": 60500 }, { "epoch": 0.99, "learning_rate": 1.9794088176352708e-05, "loss": 2.0407, "step": 60510 }, { "epoch": 0.99, "learning_rate": 1.9789078156312625e-05, "loss": 1.997, "step": 60520 }, { "epoch": 0.99, "learning_rate": 1.9784068136272546e-05, "loss": 2.0557, "step": 60530 }, { "epoch": 0.99, "learning_rate": 1.9779058116232467e-05, "loss": 1.9877, "step": 60540 }, { "epoch": 0.99, "learning_rate": 1.9774048096192384e-05, "loss": 2.0608, "step": 60550 }, { "epoch": 0.99, "learning_rate": 1.9769038076152305e-05, "loss": 2.0792, "step": 60560 }, { "epoch": 0.99, "learning_rate": 1.9764028056112225e-05, "loss": 2.0224, "step": 60570 }, { "epoch": 0.99, "learning_rate": 1.9759018036072142e-05, "loss": 2.0587, "step": 60580 }, { "epoch": 0.99, "learning_rate": 1.9754008016032067e-05, "loss": 2.051, "step": 60590 }, { "epoch": 0.99, "learning_rate": 1.9748997995991987e-05, "loss": 2.0055, "step": 60600 }, { "epoch": 0.99, "learning_rate": 1.9743987975951904e-05, "loss": 2.043, "step": 60610 }, { "epoch": 0.99, "learning_rate": 1.9738977955911825e-05, "loss": 2.0146, "step": 60620 }, { "epoch": 0.99, "learning_rate": 1.9733967935871746e-05, "loss": 2.0134, "step": 60630 }, { "epoch": 0.99, "learning_rate": 1.9728957915831663e-05, "loss": 2.0466, "step": 60640 }, { "epoch": 0.99, "learning_rate": 1.9723947895791584e-05, "loss": 2.0424, "step": 60650 }, { "epoch": 0.99, "learning_rate": 1.9718937875751504e-05, "loss": 2.0229, "step": 60660 }, { "epoch": 0.99, "learning_rate": 1.971392785571142e-05, "loss": 1.9904, "step": 60670 }, { "epoch": 0.99, "learning_rate": 1.9708917835671345e-05, "loss": 2.0764, "step": 60680 }, { "epoch": 0.99, "learning_rate": 1.9703907815631266e-05, "loss": 2.0009, "step": 60690 }, { "epoch": 0.99, "learning_rate": 1.9698897795591183e-05, "loss": 2.0225, "step": 60700 }, { "epoch": 0.99, "learning_rate": 1.9693887775551104e-05, "loss": 2.0412, "step": 60710 }, { "epoch": 0.99, "learning_rate": 1.9688877755511025e-05, "loss": 2.01, "step": 60720 }, { "epoch": 0.99, "learning_rate": 1.9683867735470942e-05, "loss": 2.0355, "step": 60730 }, { "epoch": 0.99, "learning_rate": 1.9678857715430863e-05, "loss": 2.0367, "step": 60740 }, { "epoch": 0.99, "learning_rate": 1.9673847695390783e-05, "loss": 2.0354, "step": 60750 }, { "epoch": 0.99, "learning_rate": 1.96688376753507e-05, "loss": 2.0102, "step": 60760 }, { "epoch": 0.99, "learning_rate": 1.966382765531062e-05, "loss": 2.0594, "step": 60770 }, { "epoch": 0.99, "learning_rate": 1.9658817635270542e-05, "loss": 2.0065, "step": 60780 }, { "epoch": 0.99, "learning_rate": 1.9653807615230462e-05, "loss": 2.0379, "step": 60790 }, { "epoch": 0.99, "learning_rate": 1.9648797595190383e-05, "loss": 2.0471, "step": 60800 }, { "epoch": 0.99, "learning_rate": 1.9643787575150304e-05, "loss": 2.07, "step": 60810 }, { "epoch": 0.99, "learning_rate": 1.963877755511022e-05, "loss": 2.045, "step": 60820 }, { "epoch": 0.99, "learning_rate": 1.963376753507014e-05, "loss": 2.0542, "step": 60830 }, { "epoch": 0.99, "learning_rate": 1.9628757515030062e-05, "loss": 2.044, "step": 60840 }, { "epoch": 0.99, "learning_rate": 1.962374749498998e-05, "loss": 2.0339, "step": 60850 }, { "epoch": 0.99, "learning_rate": 1.96187374749499e-05, "loss": 2.035, "step": 60860 }, { "epoch": 0.99, "learning_rate": 1.961372745490982e-05, "loss": 2.0062, "step": 60870 }, { "epoch": 0.99, "learning_rate": 1.960871743486974e-05, "loss": 2.0197, "step": 60880 }, { "epoch": 0.99, "learning_rate": 1.9603707414829662e-05, "loss": 2.0292, "step": 60890 }, { "epoch": 1.0, "learning_rate": 1.959869739478958e-05, "loss": 2.0673, "step": 60900 }, { "epoch": 1.0, "learning_rate": 1.95936873747495e-05, "loss": 2.0337, "step": 60910 }, { "epoch": 1.0, "learning_rate": 1.958867735470942e-05, "loss": 2.0039, "step": 60920 }, { "epoch": 1.0, "learning_rate": 1.9583667334669338e-05, "loss": 2.0467, "step": 60930 }, { "epoch": 1.0, "learning_rate": 1.957865731462926e-05, "loss": 2.0389, "step": 60940 }, { "epoch": 1.0, "learning_rate": 1.957364729458918e-05, "loss": 2.0335, "step": 60950 }, { "epoch": 1.0, "learning_rate": 1.95686372745491e-05, "loss": 2.0048, "step": 60960 }, { "epoch": 1.0, "learning_rate": 1.9563627254509017e-05, "loss": 2.0533, "step": 60970 }, { "epoch": 1.0, "learning_rate": 1.955861723446894e-05, "loss": 2.0532, "step": 60980 }, { "epoch": 1.0, "learning_rate": 1.9553607214428858e-05, "loss": 2.0662, "step": 60990 }, { "epoch": 1.0, "learning_rate": 1.954859719438878e-05, "loss": 2.0261, "step": 61000 }, { "epoch": 1.0, "eval_loss": 2.0228652954101562, "eval_mean_f1": 0.658628072371272, "eval_rouge1_f1": 0.7170303966766032, "eval_rouge1_precision": 0.8300513007038022, "eval_rouge1_recall": 0.6639252454600441, "eval_rouge2_f1": 0.5735734348407131, "eval_rouge2_precision": 0.6684767150709535, "eval_rouge2_recall": 0.5311146435355416, "eval_rougeL_f1": 0.6852803855964996, "eval_rougeL_precision": 0.7913162451729496, "eval_rougeL_recall": 0.6357468301831932, "eval_runtime": 63.1691, "eval_samples_per_second": 16.21, "eval_steps_per_second": 2.026, "step": 61000 }, { "epoch": 1.0, "learning_rate": 1.95435871743487e-05, "loss": 2.0356, "step": 61010 }, { "epoch": 1.0, "learning_rate": 1.9538577154308617e-05, "loss": 2.0395, "step": 61020 }, { "epoch": 1.0, "learning_rate": 1.9533567134268537e-05, "loss": 2.0297, "step": 61030 }, { "epoch": 1.0, "learning_rate": 1.9528557114228458e-05, "loss": 2.044, "step": 61040 }, { "epoch": 1.0, "learning_rate": 1.9524048096192385e-05, "loss": 2.01, "step": 61050 }, { "epoch": 1.0, "learning_rate": 1.9519038076152305e-05, "loss": 2.0196, "step": 61060 }, { "epoch": 1.0, "learning_rate": 1.9514028056112223e-05, "loss": 1.9885, "step": 61070 }, { "epoch": 1.0, "learning_rate": 1.9509018036072147e-05, "loss": 2.0116, "step": 61080 }, { "epoch": 1.0, "learning_rate": 1.9504008016032067e-05, "loss": 2.0185, "step": 61090 }, { "epoch": 1.0, "learning_rate": 1.9498997995991984e-05, "loss": 2.1061, "step": 61100 }, { "epoch": 1.0, "learning_rate": 1.9493987975951905e-05, "loss": 2.0225, "step": 61110 }, { "epoch": 1.0, "learning_rate": 1.9488977955911826e-05, "loss": 2.0499, "step": 61120 }, { "epoch": 1.0, "learning_rate": 1.9483967935871743e-05, "loss": 2.0428, "step": 61130 }, { "epoch": 1.0, "learning_rate": 1.9478957915831664e-05, "loss": 1.9944, "step": 61140 }, { "epoch": 1.0, "learning_rate": 1.9473947895791584e-05, "loss": 2.0005, "step": 61150 }, { "epoch": 1.0, "learning_rate": 1.94689378757515e-05, "loss": 2.0283, "step": 61160 }, { "epoch": 1.0, "learning_rate": 1.9463927855711422e-05, "loss": 2.0886, "step": 61170 }, { "epoch": 1.0, "learning_rate": 1.9458917835671346e-05, "loss": 2.0844, "step": 61180 }, { "epoch": 1.0, "learning_rate": 1.9453907815631263e-05, "loss": 2.0382, "step": 61190 }, { "epoch": 1.0, "learning_rate": 1.9448897795591184e-05, "loss": 2.0782, "step": 61200 }, { "epoch": 1.0, "learning_rate": 1.9443887775551105e-05, "loss": 1.9905, "step": 61210 }, { "epoch": 1.0, "learning_rate": 1.9438877755511022e-05, "loss": 2.0058, "step": 61220 }, { "epoch": 1.0, "learning_rate": 1.9433867735470943e-05, "loss": 2.0261, "step": 61230 }, { "epoch": 1.0, "learning_rate": 1.9428857715430863e-05, "loss": 2.0752, "step": 61240 }, { "epoch": 1.0, "learning_rate": 1.942384769539078e-05, "loss": 2.0762, "step": 61250 }, { "epoch": 1.0, "learning_rate": 1.94188376753507e-05, "loss": 2.0474, "step": 61260 }, { "epoch": 1.0, "learning_rate": 1.9413827655310625e-05, "loss": 2.0559, "step": 61270 }, { "epoch": 1.0, "learning_rate": 1.9408817635270542e-05, "loss": 2.0161, "step": 61280 }, { "epoch": 1.0, "learning_rate": 1.9403807615230463e-05, "loss": 2.075, "step": 61290 }, { "epoch": 1.0, "learning_rate": 1.9398797595190384e-05, "loss": 2.0362, "step": 61300 }, { "epoch": 1.0, "learning_rate": 1.93937875751503e-05, "loss": 2.0461, "step": 61310 }, { "epoch": 1.0, "learning_rate": 1.938877755511022e-05, "loss": 2.0239, "step": 61320 }, { "epoch": 1.0, "learning_rate": 1.9383767535070142e-05, "loss": 1.9952, "step": 61330 }, { "epoch": 1.0, "learning_rate": 1.937875751503006e-05, "loss": 2.0009, "step": 61340 }, { "epoch": 1.0, "learning_rate": 1.937374749498998e-05, "loss": 2.0138, "step": 61350 }, { "epoch": 1.0, "learning_rate": 1.93687374749499e-05, "loss": 2.0362, "step": 61360 }, { "epoch": 1.0, "learning_rate": 1.936372745490982e-05, "loss": 2.0476, "step": 61370 }, { "epoch": 1.0, "learning_rate": 1.9358717434869742e-05, "loss": 2.0494, "step": 61380 }, { "epoch": 1.0, "learning_rate": 1.935370741482966e-05, "loss": 2.0422, "step": 61390 }, { "epoch": 1.0, "learning_rate": 1.934869739478958e-05, "loss": 2.0358, "step": 61400 }, { "epoch": 1.0, "learning_rate": 1.93436873747495e-05, "loss": 2.0361, "step": 61410 }, { "epoch": 1.0, "learning_rate": 1.933867735470942e-05, "loss": 2.0322, "step": 61420 }, { "epoch": 1.0, "learning_rate": 1.933366733466934e-05, "loss": 2.0073, "step": 61430 }, { "epoch": 1.0, "learning_rate": 1.932865731462926e-05, "loss": 2.0462, "step": 61440 }, { "epoch": 1.0, "learning_rate": 1.932364729458918e-05, "loss": 2.0546, "step": 61450 }, { "epoch": 1.0, "learning_rate": 1.9318637274549097e-05, "loss": 1.9838, "step": 61460 }, { "epoch": 1.0, "learning_rate": 1.931362725450902e-05, "loss": 2.0284, "step": 61470 }, { "epoch": 1.0, "learning_rate": 1.930861723446894e-05, "loss": 2.0478, "step": 61480 }, { "epoch": 1.0, "learning_rate": 1.930360721442886e-05, "loss": 2.0291, "step": 61490 }, { "epoch": 1.0, "learning_rate": 1.929859719438878e-05, "loss": 2.0226, "step": 61500 }, { "epoch": 1.01, "learning_rate": 1.9293587174348697e-05, "loss": 2.0234, "step": 61510 }, { "epoch": 1.01, "learning_rate": 1.9288577154308618e-05, "loss": 2.0597, "step": 61520 }, { "epoch": 1.01, "learning_rate": 1.9283567134268538e-05, "loss": 2.0537, "step": 61530 }, { "epoch": 1.01, "learning_rate": 1.927855711422846e-05, "loss": 2.0166, "step": 61540 }, { "epoch": 1.01, "learning_rate": 1.9273547094188376e-05, "loss": 2.0328, "step": 61550 }, { "epoch": 1.01, "learning_rate": 1.9268537074148297e-05, "loss": 2.0677, "step": 61560 }, { "epoch": 1.01, "learning_rate": 1.9263527054108217e-05, "loss": 2.0098, "step": 61570 }, { "epoch": 1.01, "learning_rate": 1.9258517034068138e-05, "loss": 2.0098, "step": 61580 }, { "epoch": 1.01, "learning_rate": 1.925350701402806e-05, "loss": 2.0629, "step": 61590 }, { "epoch": 1.01, "learning_rate": 1.9248496993987976e-05, "loss": 2.0409, "step": 61600 }, { "epoch": 1.01, "learning_rate": 1.9243486973947897e-05, "loss": 2.0213, "step": 61610 }, { "epoch": 1.01, "learning_rate": 1.9238476953907817e-05, "loss": 2.0508, "step": 61620 }, { "epoch": 1.01, "learning_rate": 1.9233466933867734e-05, "loss": 2.0556, "step": 61630 }, { "epoch": 1.01, "learning_rate": 1.9228456913827655e-05, "loss": 1.9885, "step": 61640 }, { "epoch": 1.01, "learning_rate": 1.9223446893787576e-05, "loss": 2.044, "step": 61650 }, { "epoch": 1.01, "learning_rate": 1.9218436873747493e-05, "loss": 2.0691, "step": 61660 }, { "epoch": 1.01, "learning_rate": 1.9213426853707417e-05, "loss": 2.0252, "step": 61670 }, { "epoch": 1.01, "learning_rate": 1.9208416833667338e-05, "loss": 2.0122, "step": 61680 }, { "epoch": 1.01, "learning_rate": 1.9203406813627255e-05, "loss": 2.0252, "step": 61690 }, { "epoch": 1.01, "learning_rate": 1.9198396793587175e-05, "loss": 1.9992, "step": 61700 }, { "epoch": 1.01, "learning_rate": 1.9193386773547096e-05, "loss": 2.0436, "step": 61710 }, { "epoch": 1.01, "learning_rate": 1.9188376753507013e-05, "loss": 2.0891, "step": 61720 }, { "epoch": 1.01, "learning_rate": 1.9183366733466934e-05, "loss": 1.9931, "step": 61730 }, { "epoch": 1.01, "learning_rate": 1.9178356713426855e-05, "loss": 2.0262, "step": 61740 }, { "epoch": 1.01, "learning_rate": 1.9173346693386772e-05, "loss": 2.051, "step": 61750 }, { "epoch": 1.01, "learning_rate": 1.9168336673346693e-05, "loss": 2.0329, "step": 61760 }, { "epoch": 1.01, "learning_rate": 1.9163326653306617e-05, "loss": 2.0091, "step": 61770 }, { "epoch": 1.01, "learning_rate": 1.9158316633266534e-05, "loss": 2.033, "step": 61780 }, { "epoch": 1.01, "learning_rate": 1.9153306613226454e-05, "loss": 2.0123, "step": 61790 }, { "epoch": 1.01, "learning_rate": 1.9148296593186375e-05, "loss": 2.0675, "step": 61800 }, { "epoch": 1.01, "learning_rate": 1.9143286573146292e-05, "loss": 2.0318, "step": 61810 }, { "epoch": 1.01, "learning_rate": 1.9138276553106213e-05, "loss": 2.0129, "step": 61820 }, { "epoch": 1.01, "learning_rate": 1.9133266533066134e-05, "loss": 2.054, "step": 61830 }, { "epoch": 1.01, "learning_rate": 1.912825651302605e-05, "loss": 2.0619, "step": 61840 }, { "epoch": 1.01, "learning_rate": 1.912324649298597e-05, "loss": 2.0732, "step": 61850 }, { "epoch": 1.01, "learning_rate": 1.9118236472945896e-05, "loss": 2.0064, "step": 61860 }, { "epoch": 1.01, "learning_rate": 1.9113226452905813e-05, "loss": 2.078, "step": 61870 }, { "epoch": 1.01, "learning_rate": 1.9108216432865733e-05, "loss": 1.9888, "step": 61880 }, { "epoch": 1.01, "learning_rate": 1.9103206412825654e-05, "loss": 2.0196, "step": 61890 }, { "epoch": 1.01, "learning_rate": 1.909819639278557e-05, "loss": 2.0305, "step": 61900 }, { "epoch": 1.01, "learning_rate": 1.9093186372745492e-05, "loss": 2.0136, "step": 61910 }, { "epoch": 1.01, "learning_rate": 1.9088176352705413e-05, "loss": 2.0475, "step": 61920 }, { "epoch": 1.01, "learning_rate": 1.908316633266533e-05, "loss": 2.013, "step": 61930 }, { "epoch": 1.01, "learning_rate": 1.907815631262525e-05, "loss": 2.0556, "step": 61940 }, { "epoch": 1.01, "learning_rate": 1.907314629258517e-05, "loss": 2.0642, "step": 61950 }, { "epoch": 1.01, "learning_rate": 1.9068136272545092e-05, "loss": 2.0462, "step": 61960 }, { "epoch": 1.01, "learning_rate": 1.9063126252505012e-05, "loss": 2.019, "step": 61970 }, { "epoch": 1.01, "learning_rate": 1.9058116232464933e-05, "loss": 2.0531, "step": 61980 }, { "epoch": 1.01, "learning_rate": 1.905310621242485e-05, "loss": 2.0518, "step": 61990 }, { "epoch": 1.01, "learning_rate": 1.904809619238477e-05, "loss": 1.9907, "step": 62000 }, { "epoch": 1.01, "eval_loss": 2.0268232822418213, "eval_mean_f1": 0.6556268931855719, "eval_rouge1_f1": 0.7151856655282798, "eval_rouge1_precision": 0.8263223702806082, "eval_rouge1_recall": 0.6636527798931096, "eval_rouge2_f1": 0.5679038830403514, "eval_rouge2_precision": 0.6612931149796386, "eval_rouge2_recall": 0.5269766692504119, "eval_rougeL_f1": 0.6837911309880842, "eval_rougeL_precision": 0.7886363758311996, "eval_rougeL_recall": 0.6356075963449088, "eval_runtime": 63.4762, "eval_samples_per_second": 16.132, "eval_steps_per_second": 2.017, "step": 62000 }, { "epoch": 1.01, "learning_rate": 1.904308617234469e-05, "loss": 2.0175, "step": 62010 }, { "epoch": 1.01, "learning_rate": 1.903807615230461e-05, "loss": 2.0361, "step": 62020 }, { "epoch": 1.01, "learning_rate": 1.903306613226453e-05, "loss": 2.0201, "step": 62030 }, { "epoch": 1.01, "learning_rate": 1.902805611222445e-05, "loss": 2.0322, "step": 62040 }, { "epoch": 1.01, "learning_rate": 1.9023046092184367e-05, "loss": 1.9868, "step": 62050 }, { "epoch": 1.01, "learning_rate": 1.901803607214429e-05, "loss": 2.0155, "step": 62060 }, { "epoch": 1.01, "learning_rate": 1.901302605210421e-05, "loss": 2.043, "step": 62070 }, { "epoch": 1.01, "learning_rate": 1.900801603206413e-05, "loss": 2.0528, "step": 62080 }, { "epoch": 1.01, "learning_rate": 1.900300601202405e-05, "loss": 1.9967, "step": 62090 }, { "epoch": 1.01, "learning_rate": 1.8997995991983967e-05, "loss": 2.0845, "step": 62100 }, { "epoch": 1.01, "learning_rate": 1.8992985971943888e-05, "loss": 2.0076, "step": 62110 }, { "epoch": 1.02, "learning_rate": 1.898797595190381e-05, "loss": 2.0993, "step": 62120 }, { "epoch": 1.02, "learning_rate": 1.898296593186373e-05, "loss": 2.0378, "step": 62130 }, { "epoch": 1.02, "learning_rate": 1.8977955911823646e-05, "loss": 2.0151, "step": 62140 }, { "epoch": 1.02, "learning_rate": 1.8972945891783567e-05, "loss": 2.0113, "step": 62150 }, { "epoch": 1.02, "learning_rate": 1.8967935871743488e-05, "loss": 2.063, "step": 62160 }, { "epoch": 1.02, "learning_rate": 1.896292585170341e-05, "loss": 2.0205, "step": 62170 }, { "epoch": 1.02, "learning_rate": 1.895791583166333e-05, "loss": 2.023, "step": 62180 }, { "epoch": 1.02, "learning_rate": 1.8952905811623246e-05, "loss": 2.0403, "step": 62190 }, { "epoch": 1.02, "learning_rate": 1.8947895791583167e-05, "loss": 2.0115, "step": 62200 }, { "epoch": 1.02, "learning_rate": 1.8942885771543088e-05, "loss": 2.0314, "step": 62210 }, { "epoch": 1.02, "learning_rate": 1.8937875751503005e-05, "loss": 2.0331, "step": 62220 }, { "epoch": 1.02, "learning_rate": 1.8932865731462925e-05, "loss": 2.0359, "step": 62230 }, { "epoch": 1.02, "learning_rate": 1.8927855711422846e-05, "loss": 2.0401, "step": 62240 }, { "epoch": 1.02, "learning_rate": 1.8922845691382767e-05, "loss": 2.0716, "step": 62250 }, { "epoch": 1.02, "learning_rate": 1.8917835671342687e-05, "loss": 2.0347, "step": 62260 }, { "epoch": 1.02, "learning_rate": 1.8912825651302608e-05, "loss": 2.0703, "step": 62270 }, { "epoch": 1.02, "learning_rate": 1.8907815631262525e-05, "loss": 2.0676, "step": 62280 }, { "epoch": 1.02, "learning_rate": 1.8902805611222446e-05, "loss": 2.0707, "step": 62290 }, { "epoch": 1.02, "learning_rate": 1.8897795591182367e-05, "loss": 2.0112, "step": 62300 }, { "epoch": 1.02, "learning_rate": 1.8892785571142284e-05, "loss": 2.0866, "step": 62310 }, { "epoch": 1.02, "learning_rate": 1.8887775551102204e-05, "loss": 2.0429, "step": 62320 }, { "epoch": 1.02, "learning_rate": 1.8882765531062125e-05, "loss": 2.0054, "step": 62330 }, { "epoch": 1.02, "learning_rate": 1.8877755511022042e-05, "loss": 2.0313, "step": 62340 }, { "epoch": 1.02, "learning_rate": 1.8872745490981966e-05, "loss": 2.0206, "step": 62350 }, { "epoch": 1.02, "learning_rate": 1.8867735470941887e-05, "loss": 2.0457, "step": 62360 }, { "epoch": 1.02, "learning_rate": 1.8862725450901804e-05, "loss": 2.0454, "step": 62370 }, { "epoch": 1.02, "learning_rate": 1.8857715430861725e-05, "loss": 2.0671, "step": 62380 }, { "epoch": 1.02, "learning_rate": 1.8852705410821646e-05, "loss": 2.0653, "step": 62390 }, { "epoch": 1.02, "learning_rate": 1.8847695390781563e-05, "loss": 2.0348, "step": 62400 }, { "epoch": 1.02, "learning_rate": 1.8842685370741483e-05, "loss": 2.0208, "step": 62410 }, { "epoch": 1.02, "learning_rate": 1.8837675350701404e-05, "loss": 2.0264, "step": 62420 }, { "epoch": 1.02, "learning_rate": 1.883266533066132e-05, "loss": 2.0693, "step": 62430 }, { "epoch": 1.02, "learning_rate": 1.8827655310621242e-05, "loss": 2.014, "step": 62440 }, { "epoch": 1.02, "learning_rate": 1.8822645290581166e-05, "loss": 2.0047, "step": 62450 }, { "epoch": 1.02, "learning_rate": 1.8817635270541083e-05, "loss": 1.9981, "step": 62460 }, { "epoch": 1.02, "learning_rate": 1.8812625250501004e-05, "loss": 1.9896, "step": 62470 }, { "epoch": 1.02, "learning_rate": 1.8807615230460925e-05, "loss": 1.9779, "step": 62480 }, { "epoch": 1.02, "learning_rate": 1.8802605210420842e-05, "loss": 2.0706, "step": 62490 }, { "epoch": 1.02, "learning_rate": 1.8797595190380762e-05, "loss": 2.0417, "step": 62500 }, { "epoch": 1.02, "learning_rate": 1.8792585170340683e-05, "loss": 2.0323, "step": 62510 }, { "epoch": 1.02, "learning_rate": 1.87875751503006e-05, "loss": 2.0185, "step": 62520 }, { "epoch": 1.02, "learning_rate": 1.878256513026052e-05, "loss": 2.0216, "step": 62530 }, { "epoch": 1.02, "learning_rate": 1.877755511022044e-05, "loss": 2.0091, "step": 62540 }, { "epoch": 1.02, "learning_rate": 1.8772545090180362e-05, "loss": 2.042, "step": 62550 }, { "epoch": 1.02, "learning_rate": 1.8767535070140283e-05, "loss": 2.0554, "step": 62560 }, { "epoch": 1.02, "learning_rate": 1.8762525050100204e-05, "loss": 2.0394, "step": 62570 }, { "epoch": 1.02, "learning_rate": 1.875751503006012e-05, "loss": 2.0511, "step": 62580 }, { "epoch": 1.02, "learning_rate": 1.875250501002004e-05, "loss": 1.9914, "step": 62590 }, { "epoch": 1.02, "learning_rate": 1.8747494989979962e-05, "loss": 2.0455, "step": 62600 }, { "epoch": 1.02, "learning_rate": 1.874248496993988e-05, "loss": 2.0257, "step": 62610 }, { "epoch": 1.02, "learning_rate": 1.87374749498998e-05, "loss": 1.9958, "step": 62620 }, { "epoch": 1.02, "learning_rate": 1.873246492985972e-05, "loss": 2.0274, "step": 62630 }, { "epoch": 1.02, "learning_rate": 1.8727454909819638e-05, "loss": 2.0488, "step": 62640 }, { "epoch": 1.02, "learning_rate": 1.8722444889779562e-05, "loss": 2.0109, "step": 62650 }, { "epoch": 1.02, "learning_rate": 1.871743486973948e-05, "loss": 2.0322, "step": 62660 }, { "epoch": 1.02, "learning_rate": 1.87124248496994e-05, "loss": 2.0513, "step": 62670 }, { "epoch": 1.02, "learning_rate": 1.870741482965932e-05, "loss": 2.0632, "step": 62680 }, { "epoch": 1.02, "learning_rate": 1.870240480961924e-05, "loss": 1.9942, "step": 62690 }, { "epoch": 1.02, "learning_rate": 1.869739478957916e-05, "loss": 2.0733, "step": 62700 }, { "epoch": 1.02, "learning_rate": 1.869238476953908e-05, "loss": 2.027, "step": 62710 }, { "epoch": 1.02, "learning_rate": 1.8687374749499e-05, "loss": 2.0777, "step": 62720 }, { "epoch": 1.02, "learning_rate": 1.8682364729458917e-05, "loss": 1.991, "step": 62730 }, { "epoch": 1.03, "learning_rate": 1.8677354709418837e-05, "loss": 2.0229, "step": 62740 }, { "epoch": 1.03, "learning_rate": 1.8672344689378758e-05, "loss": 1.9971, "step": 62750 }, { "epoch": 1.03, "learning_rate": 1.866733466933868e-05, "loss": 2.0706, "step": 62760 }, { "epoch": 1.03, "learning_rate": 1.86623246492986e-05, "loss": 1.9915, "step": 62770 }, { "epoch": 1.03, "learning_rate": 1.8657314629258517e-05, "loss": 2.0486, "step": 62780 }, { "epoch": 1.03, "learning_rate": 1.8652304609218437e-05, "loss": 2.0348, "step": 62790 }, { "epoch": 1.03, "learning_rate": 1.8647294589178358e-05, "loss": 1.9889, "step": 62800 }, { "epoch": 1.03, "learning_rate": 1.864228456913828e-05, "loss": 2.0069, "step": 62810 }, { "epoch": 1.03, "learning_rate": 1.8637274549098196e-05, "loss": 2.0381, "step": 62820 }, { "epoch": 1.03, "learning_rate": 1.8632264529058116e-05, "loss": 2.0272, "step": 62830 }, { "epoch": 1.03, "learning_rate": 1.8627254509018037e-05, "loss": 1.9535, "step": 62840 }, { "epoch": 1.03, "learning_rate": 1.8622244488977958e-05, "loss": 2.0243, "step": 62850 }, { "epoch": 1.03, "learning_rate": 1.861723446893788e-05, "loss": 2.0253, "step": 62860 }, { "epoch": 1.03, "learning_rate": 1.8612224448897796e-05, "loss": 2.0861, "step": 62870 }, { "epoch": 1.03, "learning_rate": 1.8607214428857716e-05, "loss": 2.0666, "step": 62880 }, { "epoch": 1.03, "learning_rate": 1.8602204408817637e-05, "loss": 2.0673, "step": 62890 }, { "epoch": 1.03, "learning_rate": 1.8597194388777554e-05, "loss": 2.0421, "step": 62900 }, { "epoch": 1.03, "learning_rate": 1.8592184368737475e-05, "loss": 2.0106, "step": 62910 }, { "epoch": 1.03, "learning_rate": 1.8587174348697395e-05, "loss": 2.0543, "step": 62920 }, { "epoch": 1.03, "learning_rate": 1.8582164328657313e-05, "loss": 2.0808, "step": 62930 }, { "epoch": 1.03, "learning_rate": 1.8577154308617237e-05, "loss": 2.0377, "step": 62940 }, { "epoch": 1.03, "learning_rate": 1.8572144288577157e-05, "loss": 2.0063, "step": 62950 }, { "epoch": 1.03, "learning_rate": 1.8567134268537075e-05, "loss": 2.0529, "step": 62960 }, { "epoch": 1.03, "learning_rate": 1.8562124248496995e-05, "loss": 2.0221, "step": 62970 }, { "epoch": 1.03, "learning_rate": 1.8557114228456916e-05, "loss": 1.9935, "step": 62980 }, { "epoch": 1.03, "learning_rate": 1.8552104208416833e-05, "loss": 2.009, "step": 62990 }, { "epoch": 1.03, "learning_rate": 1.8547094188376754e-05, "loss": 2.0011, "step": 63000 }, { "epoch": 1.03, "eval_loss": 2.023871421813965, "eval_mean_f1": 0.6580133141003552, "eval_rouge1_f1": 0.7155093299217488, "eval_rouge1_precision": 0.8260721447909087, "eval_rouge1_recall": 0.6649150859882346, "eval_rouge2_f1": 0.5742224666288712, "eval_rouge2_precision": 0.6672442459612873, "eval_rouge2_recall": 0.5337293493907328, "eval_rougeL_f1": 0.6843081457504459, "eval_rougeL_precision": 0.7885666939779991, "eval_rougeL_recall": 0.636870053167141, "eval_runtime": 64.7543, "eval_samples_per_second": 15.814, "eval_steps_per_second": 1.977, "step": 63000 }, { "epoch": 1.03, "learning_rate": 1.8542084168336674e-05, "loss": 2.028, "step": 63010 }, { "epoch": 1.03, "learning_rate": 1.8537074148296592e-05, "loss": 2.0419, "step": 63020 }, { "epoch": 1.03, "learning_rate": 1.8532064128256512e-05, "loss": 2.0431, "step": 63030 }, { "epoch": 1.03, "learning_rate": 1.8527054108216436e-05, "loss": 2.0379, "step": 63040 }, { "epoch": 1.03, "learning_rate": 1.8522044088176354e-05, "loss": 2.0473, "step": 63050 }, { "epoch": 1.03, "learning_rate": 1.8517034068136274e-05, "loss": 2.0389, "step": 63060 }, { "epoch": 1.03, "learning_rate": 1.8512024048096195e-05, "loss": 2.0305, "step": 63070 }, { "epoch": 1.03, "learning_rate": 1.8507014028056112e-05, "loss": 2.0221, "step": 63080 }, { "epoch": 1.03, "learning_rate": 1.8502004008016033e-05, "loss": 2.0416, "step": 63090 }, { "epoch": 1.03, "learning_rate": 1.8496993987975953e-05, "loss": 2.0506, "step": 63100 }, { "epoch": 1.03, "learning_rate": 1.849198396793587e-05, "loss": 2.0061, "step": 63110 }, { "epoch": 1.03, "learning_rate": 1.848697394789579e-05, "loss": 1.9875, "step": 63120 }, { "epoch": 1.03, "learning_rate": 1.8481963927855712e-05, "loss": 2.0287, "step": 63130 }, { "epoch": 1.03, "learning_rate": 1.8476953907815633e-05, "loss": 2.0436, "step": 63140 }, { "epoch": 1.03, "learning_rate": 1.8471943887775553e-05, "loss": 2.0572, "step": 63150 }, { "epoch": 1.03, "learning_rate": 1.8466933867735474e-05, "loss": 2.0402, "step": 63160 }, { "epoch": 1.03, "learning_rate": 1.846192384769539e-05, "loss": 2.0259, "step": 63170 }, { "epoch": 1.03, "learning_rate": 1.8456913827655312e-05, "loss": 2.0552, "step": 63180 }, { "epoch": 1.03, "learning_rate": 1.8451903807615232e-05, "loss": 2.0292, "step": 63190 }, { "epoch": 1.03, "learning_rate": 1.844689378757515e-05, "loss": 2.0107, "step": 63200 }, { "epoch": 1.03, "learning_rate": 1.844188376753507e-05, "loss": 2.0131, "step": 63210 }, { "epoch": 1.03, "learning_rate": 1.843687374749499e-05, "loss": 2.0544, "step": 63220 }, { "epoch": 1.03, "learning_rate": 1.8431863727454908e-05, "loss": 2.0122, "step": 63230 }, { "epoch": 1.03, "learning_rate": 1.8426853707414832e-05, "loss": 2.0458, "step": 63240 }, { "epoch": 1.03, "learning_rate": 1.8421843687374753e-05, "loss": 2.0193, "step": 63250 }, { "epoch": 1.03, "learning_rate": 1.841683366733467e-05, "loss": 2.0049, "step": 63260 }, { "epoch": 1.03, "learning_rate": 1.841182364729459e-05, "loss": 2.0457, "step": 63270 }, { "epoch": 1.03, "learning_rate": 1.840681362725451e-05, "loss": 2.0419, "step": 63280 }, { "epoch": 1.03, "learning_rate": 1.840180360721443e-05, "loss": 2.0267, "step": 63290 }, { "epoch": 1.03, "learning_rate": 1.839679358717435e-05, "loss": 2.0147, "step": 63300 }, { "epoch": 1.03, "learning_rate": 1.839178356713427e-05, "loss": 2.0775, "step": 63310 }, { "epoch": 1.03, "learning_rate": 1.8386773547094187e-05, "loss": 1.9995, "step": 63320 }, { "epoch": 1.03, "learning_rate": 1.8381763527054108e-05, "loss": 1.9972, "step": 63330 }, { "epoch": 1.03, "learning_rate": 1.837675350701403e-05, "loss": 2.0361, "step": 63340 }, { "epoch": 1.04, "learning_rate": 1.837174348697395e-05, "loss": 2.0079, "step": 63350 }, { "epoch": 1.04, "learning_rate": 1.836673346693387e-05, "loss": 2.0212, "step": 63360 }, { "epoch": 1.04, "learning_rate": 1.8361723446893787e-05, "loss": 2.0339, "step": 63370 }, { "epoch": 1.04, "learning_rate": 1.8356713426853708e-05, "loss": 2.033, "step": 63380 }, { "epoch": 1.04, "learning_rate": 1.835170340681363e-05, "loss": 2.0345, "step": 63390 }, { "epoch": 1.04, "learning_rate": 1.834669338677355e-05, "loss": 2.0296, "step": 63400 }, { "epoch": 1.04, "learning_rate": 1.8341683366733466e-05, "loss": 2.0109, "step": 63410 }, { "epoch": 1.04, "learning_rate": 1.8336673346693387e-05, "loss": 2.0513, "step": 63420 }, { "epoch": 1.04, "learning_rate": 1.8331663326653308e-05, "loss": 2.0707, "step": 63430 }, { "epoch": 1.04, "learning_rate": 1.8326653306613228e-05, "loss": 2.0032, "step": 63440 }, { "epoch": 1.04, "learning_rate": 1.832164328657315e-05, "loss": 2.0322, "step": 63450 }, { "epoch": 1.04, "learning_rate": 1.8316633266533066e-05, "loss": 2.0308, "step": 63460 }, { "epoch": 1.04, "learning_rate": 1.8311623246492987e-05, "loss": 1.9814, "step": 63470 }, { "epoch": 1.04, "learning_rate": 1.8306613226452907e-05, "loss": 2.0751, "step": 63480 }, { "epoch": 1.04, "learning_rate": 1.8301603206412825e-05, "loss": 2.0133, "step": 63490 }, { "epoch": 1.04, "learning_rate": 1.8296593186372745e-05, "loss": 2.0585, "step": 63500 }, { "epoch": 1.04, "learning_rate": 1.8291583166332666e-05, "loss": 2.0321, "step": 63510 }, { "epoch": 1.04, "learning_rate": 1.8286573146292587e-05, "loss": 2.0381, "step": 63520 }, { "epoch": 1.04, "learning_rate": 1.8281563126252507e-05, "loss": 2.0365, "step": 63530 }, { "epoch": 1.04, "learning_rate": 1.8276553106212428e-05, "loss": 2.0317, "step": 63540 }, { "epoch": 1.04, "learning_rate": 1.8271543086172345e-05, "loss": 2.06, "step": 63550 }, { "epoch": 1.04, "learning_rate": 1.8266533066132266e-05, "loss": 2.0008, "step": 63560 }, { "epoch": 1.04, "learning_rate": 1.8261523046092186e-05, "loss": 2.0051, "step": 63570 }, { "epoch": 1.04, "learning_rate": 1.8256513026052104e-05, "loss": 2.0369, "step": 63580 }, { "epoch": 1.04, "learning_rate": 1.8251503006012024e-05, "loss": 2.0235, "step": 63590 }, { "epoch": 1.04, "learning_rate": 1.8246492985971945e-05, "loss": 2.0097, "step": 63600 }, { "epoch": 1.04, "learning_rate": 1.8241482965931862e-05, "loss": 2.0381, "step": 63610 }, { "epoch": 1.04, "learning_rate": 1.8236472945891783e-05, "loss": 2.0113, "step": 63620 }, { "epoch": 1.04, "learning_rate": 1.8231462925851707e-05, "loss": 2.0267, "step": 63630 }, { "epoch": 1.04, "learning_rate": 1.8226452905811624e-05, "loss": 1.9919, "step": 63640 }, { "epoch": 1.04, "learning_rate": 1.8221442885771545e-05, "loss": 1.992, "step": 63650 }, { "epoch": 1.04, "learning_rate": 1.8216432865731465e-05, "loss": 2.0591, "step": 63660 }, { "epoch": 1.04, "learning_rate": 1.8211422845691383e-05, "loss": 2.0125, "step": 63670 }, { "epoch": 1.04, "learning_rate": 1.8206412825651303e-05, "loss": 2.0242, "step": 63680 }, { "epoch": 1.04, "learning_rate": 1.8201402805611224e-05, "loss": 2.0454, "step": 63690 }, { "epoch": 1.04, "learning_rate": 1.819639278557114e-05, "loss": 2.0582, "step": 63700 }, { "epoch": 1.04, "learning_rate": 1.8191382765531062e-05, "loss": 2.0017, "step": 63710 }, { "epoch": 1.04, "learning_rate": 1.8186372745490982e-05, "loss": 2.0113, "step": 63720 }, { "epoch": 1.04, "learning_rate": 1.8181362725450903e-05, "loss": 2.0276, "step": 63730 }, { "epoch": 1.04, "learning_rate": 1.8176352705410824e-05, "loss": 2.0268, "step": 63740 }, { "epoch": 1.04, "learning_rate": 1.8171342685370744e-05, "loss": 2.0085, "step": 63750 }, { "epoch": 1.04, "learning_rate": 1.816633266533066e-05, "loss": 2.0379, "step": 63760 }, { "epoch": 1.04, "learning_rate": 1.8161322645290582e-05, "loss": 2.0366, "step": 63770 }, { "epoch": 1.04, "learning_rate": 1.8156312625250503e-05, "loss": 1.9913, "step": 63780 }, { "epoch": 1.04, "learning_rate": 1.815130260521042e-05, "loss": 2.0277, "step": 63790 }, { "epoch": 1.04, "learning_rate": 1.814629258517034e-05, "loss": 2.0617, "step": 63800 }, { "epoch": 1.04, "learning_rate": 1.814128256513026e-05, "loss": 2.0167, "step": 63810 }, { "epoch": 1.04, "learning_rate": 1.813627254509018e-05, "loss": 1.9739, "step": 63820 }, { "epoch": 1.04, "learning_rate": 1.8131262525050103e-05, "loss": 2.0224, "step": 63830 }, { "epoch": 1.04, "learning_rate": 1.8126252505010023e-05, "loss": 1.9798, "step": 63840 }, { "epoch": 1.04, "learning_rate": 1.812124248496994e-05, "loss": 2.0426, "step": 63850 }, { "epoch": 1.04, "learning_rate": 1.811623246492986e-05, "loss": 2.0002, "step": 63860 }, { "epoch": 1.04, "learning_rate": 1.8111222444889782e-05, "loss": 2.0474, "step": 63870 }, { "epoch": 1.04, "learning_rate": 1.81062124248497e-05, "loss": 2.0472, "step": 63880 }, { "epoch": 1.04, "learning_rate": 1.810120240480962e-05, "loss": 2.0178, "step": 63890 }, { "epoch": 1.04, "learning_rate": 1.809619238476954e-05, "loss": 2.0169, "step": 63900 }, { "epoch": 1.04, "learning_rate": 1.8091182364729458e-05, "loss": 2.0599, "step": 63910 }, { "epoch": 1.04, "learning_rate": 1.8086673346693388e-05, "loss": 2.0234, "step": 63920 }, { "epoch": 1.04, "learning_rate": 1.8081663326653308e-05, "loss": 2.0184, "step": 63930 }, { "epoch": 1.04, "learning_rate": 1.807665330661323e-05, "loss": 1.9914, "step": 63940 }, { "epoch": 1.04, "learning_rate": 1.8071643286573146e-05, "loss": 2.0242, "step": 63950 }, { "epoch": 1.05, "learning_rate": 1.8066633266533067e-05, "loss": 2.0249, "step": 63960 }, { "epoch": 1.05, "learning_rate": 1.8061623246492987e-05, "loss": 2.0199, "step": 63970 }, { "epoch": 1.05, "learning_rate": 1.8056613226452908e-05, "loss": 2.0345, "step": 63980 }, { "epoch": 1.05, "learning_rate": 1.8051603206412825e-05, "loss": 2.0112, "step": 63990 }, { "epoch": 1.05, "learning_rate": 1.8046593186372746e-05, "loss": 2.0286, "step": 64000 }, { "epoch": 1.05, "eval_loss": 2.02164363861084, "eval_mean_f1": 0.661556131633727, "eval_rouge1_f1": 0.7184106621752178, "eval_rouge1_precision": 0.8315781281371806, "eval_rouge1_recall": 0.6647763972147012, "eval_rouge2_f1": 0.5775213973812036, "eval_rouge2_precision": 0.6722554687337403, "eval_rouge2_recall": 0.5348636317494568, "eval_rougeL_f1": 0.6887363353447595, "eval_rougeL_precision": 0.7950740880388885, "eval_rougeL_recall": 0.6386915399786732, "eval_runtime": 63.2328, "eval_samples_per_second": 16.194, "eval_steps_per_second": 2.024, "step": 64000 }, { "epoch": 1.05, "learning_rate": 1.8041583166332667e-05, "loss": 2.0151, "step": 64010 }, { "epoch": 1.05, "learning_rate": 1.8036573146292584e-05, "loss": 2.0017, "step": 64020 }, { "epoch": 1.05, "learning_rate": 1.8031563126252508e-05, "loss": 2.0037, "step": 64030 }, { "epoch": 1.05, "learning_rate": 1.8026553106212425e-05, "loss": 1.9988, "step": 64040 }, { "epoch": 1.05, "learning_rate": 1.8021543086172346e-05, "loss": 2.057, "step": 64050 }, { "epoch": 1.05, "learning_rate": 1.8016533066132266e-05, "loss": 2.015, "step": 64060 }, { "epoch": 1.05, "learning_rate": 1.8011523046092184e-05, "loss": 2.0803, "step": 64070 }, { "epoch": 1.05, "learning_rate": 1.8006513026052104e-05, "loss": 2.0517, "step": 64080 }, { "epoch": 1.05, "learning_rate": 1.8001503006012025e-05, "loss": 2.0078, "step": 64090 }, { "epoch": 1.05, "learning_rate": 1.7996492985971942e-05, "loss": 2.0603, "step": 64100 }, { "epoch": 1.05, "learning_rate": 1.7991482965931863e-05, "loss": 2.0367, "step": 64110 }, { "epoch": 1.05, "learning_rate": 1.7986472945891787e-05, "loss": 2.0496, "step": 64120 }, { "epoch": 1.05, "learning_rate": 1.7981462925851704e-05, "loss": 2.0492, "step": 64130 }, { "epoch": 1.05, "learning_rate": 1.7976452905811625e-05, "loss": 2.026, "step": 64140 }, { "epoch": 1.05, "learning_rate": 1.7971442885771545e-05, "loss": 2.0481, "step": 64150 }, { "epoch": 1.05, "learning_rate": 1.7966432865731463e-05, "loss": 2.0013, "step": 64160 }, { "epoch": 1.05, "learning_rate": 1.7961422845691383e-05, "loss": 2.0624, "step": 64170 }, { "epoch": 1.05, "learning_rate": 1.7956412825651304e-05, "loss": 2.0586, "step": 64180 }, { "epoch": 1.05, "learning_rate": 1.795140280561122e-05, "loss": 2.0279, "step": 64190 }, { "epoch": 1.05, "learning_rate": 1.7946392785571142e-05, "loss": 2.0436, "step": 64200 }, { "epoch": 1.05, "learning_rate": 1.7941382765531062e-05, "loss": 1.9796, "step": 64210 }, { "epoch": 1.05, "learning_rate": 1.7936372745490983e-05, "loss": 2.0148, "step": 64220 }, { "epoch": 1.05, "learning_rate": 1.7931362725450904e-05, "loss": 2.0389, "step": 64230 }, { "epoch": 1.05, "learning_rate": 1.7926352705410824e-05, "loss": 2.0454, "step": 64240 }, { "epoch": 1.05, "learning_rate": 1.792134268537074e-05, "loss": 2.0322, "step": 64250 }, { "epoch": 1.05, "learning_rate": 1.7916332665330662e-05, "loss": 2.0394, "step": 64260 }, { "epoch": 1.05, "learning_rate": 1.7911322645290583e-05, "loss": 2.0502, "step": 64270 }, { "epoch": 1.05, "learning_rate": 1.79063126252505e-05, "loss": 2.0217, "step": 64280 }, { "epoch": 1.05, "learning_rate": 1.790130260521042e-05, "loss": 1.9892, "step": 64290 }, { "epoch": 1.05, "learning_rate": 1.789629258517034e-05, "loss": 2.0767, "step": 64300 }, { "epoch": 1.05, "learning_rate": 1.789128256513026e-05, "loss": 2.0636, "step": 64310 }, { "epoch": 1.05, "learning_rate": 1.7886272545090183e-05, "loss": 2.0253, "step": 64320 }, { "epoch": 1.05, "learning_rate": 1.7881262525050103e-05, "loss": 2.0804, "step": 64330 }, { "epoch": 1.05, "learning_rate": 1.787625250501002e-05, "loss": 2.0326, "step": 64340 }, { "epoch": 1.05, "learning_rate": 1.787124248496994e-05, "loss": 2.0089, "step": 64350 }, { "epoch": 1.05, "learning_rate": 1.7866232464929862e-05, "loss": 1.9954, "step": 64360 }, { "epoch": 1.05, "learning_rate": 1.786122244488978e-05, "loss": 2.0445, "step": 64370 }, { "epoch": 1.05, "learning_rate": 1.78562124248497e-05, "loss": 2.0306, "step": 64380 }, { "epoch": 1.05, "learning_rate": 1.785120240480962e-05, "loss": 2.0229, "step": 64390 }, { "epoch": 1.05, "learning_rate": 1.7846192384769538e-05, "loss": 2.0466, "step": 64400 }, { "epoch": 1.05, "learning_rate": 1.784118236472946e-05, "loss": 2.0427, "step": 64410 }, { "epoch": 1.05, "learning_rate": 1.7836172344689382e-05, "loss": 2.0414, "step": 64420 }, { "epoch": 1.05, "learning_rate": 1.78311623246493e-05, "loss": 1.995, "step": 64430 }, { "epoch": 1.05, "learning_rate": 1.782615230460922e-05, "loss": 1.9859, "step": 64440 }, { "epoch": 1.05, "learning_rate": 1.782114228456914e-05, "loss": 2.0503, "step": 64450 }, { "epoch": 1.05, "learning_rate": 1.7816132264529058e-05, "loss": 2.0483, "step": 64460 }, { "epoch": 1.05, "learning_rate": 1.781112224448898e-05, "loss": 2.0271, "step": 64470 }, { "epoch": 1.05, "learning_rate": 1.78061122244489e-05, "loss": 2.0432, "step": 64480 }, { "epoch": 1.05, "learning_rate": 1.7801102204408817e-05, "loss": 2.0149, "step": 64490 }, { "epoch": 1.05, "learning_rate": 1.7796092184368737e-05, "loss": 2.0287, "step": 64500 }, { "epoch": 1.05, "learning_rate": 1.7791082164328658e-05, "loss": 1.9929, "step": 64510 }, { "epoch": 1.05, "learning_rate": 1.778607214428858e-05, "loss": 2.0684, "step": 64520 }, { "epoch": 1.05, "learning_rate": 1.77810621242485e-05, "loss": 2.0454, "step": 64530 }, { "epoch": 1.05, "learning_rate": 1.777605210420842e-05, "loss": 2.003, "step": 64540 }, { "epoch": 1.05, "learning_rate": 1.7771042084168337e-05, "loss": 2.0498, "step": 64550 }, { "epoch": 1.05, "learning_rate": 1.7766032064128258e-05, "loss": 2.0121, "step": 64560 }, { "epoch": 1.06, "learning_rate": 1.776102204408818e-05, "loss": 2.0484, "step": 64570 }, { "epoch": 1.06, "learning_rate": 1.7756012024048096e-05, "loss": 2.033, "step": 64580 }, { "epoch": 1.06, "learning_rate": 1.7751002004008016e-05, "loss": 2.0394, "step": 64590 }, { "epoch": 1.06, "learning_rate": 1.7745991983967937e-05, "loss": 2.0297, "step": 64600 }, { "epoch": 1.06, "learning_rate": 1.7740981963927858e-05, "loss": 2.0071, "step": 64610 }, { "epoch": 1.06, "learning_rate": 1.7735971943887778e-05, "loss": 2.03, "step": 64620 }, { "epoch": 1.06, "learning_rate": 1.7730961923847696e-05, "loss": 2.0478, "step": 64630 }, { "epoch": 1.06, "learning_rate": 1.7725951903807616e-05, "loss": 2.0021, "step": 64640 }, { "epoch": 1.06, "learning_rate": 1.7720941883767537e-05, "loss": 2.112, "step": 64650 }, { "epoch": 1.06, "learning_rate": 1.7715931863727454e-05, "loss": 2.0543, "step": 64660 }, { "epoch": 1.06, "learning_rate": 1.7710921843687375e-05, "loss": 2.0307, "step": 64670 }, { "epoch": 1.06, "learning_rate": 1.7705911823647295e-05, "loss": 2.0366, "step": 64680 }, { "epoch": 1.06, "learning_rate": 1.7700901803607216e-05, "loss": 2.0692, "step": 64690 }, { "epoch": 1.06, "learning_rate": 1.7695891783567133e-05, "loss": 2.0556, "step": 64700 }, { "epoch": 1.06, "learning_rate": 1.7690881763527057e-05, "loss": 2.0755, "step": 64710 }, { "epoch": 1.06, "learning_rate": 1.7685871743486975e-05, "loss": 2.0371, "step": 64720 }, { "epoch": 1.06, "learning_rate": 1.7680861723446895e-05, "loss": 2.0021, "step": 64730 }, { "epoch": 1.06, "learning_rate": 1.7675851703406816e-05, "loss": 2.0635, "step": 64740 }, { "epoch": 1.06, "learning_rate": 1.7670841683366733e-05, "loss": 2.0527, "step": 64750 }, { "epoch": 1.06, "learning_rate": 1.7665831663326654e-05, "loss": 2.053, "step": 64760 }, { "epoch": 1.06, "learning_rate": 1.7660821643286574e-05, "loss": 2.0344, "step": 64770 }, { "epoch": 1.06, "learning_rate": 1.765581162324649e-05, "loss": 2.0165, "step": 64780 }, { "epoch": 1.06, "learning_rate": 1.7650801603206412e-05, "loss": 2.0139, "step": 64790 }, { "epoch": 1.06, "learning_rate": 1.7645791583166333e-05, "loss": 2.0152, "step": 64800 }, { "epoch": 1.06, "learning_rate": 1.7640781563126254e-05, "loss": 2.0052, "step": 64810 }, { "epoch": 1.06, "learning_rate": 1.7635771543086174e-05, "loss": 2.0366, "step": 64820 }, { "epoch": 1.06, "learning_rate": 1.7630761523046095e-05, "loss": 2.0112, "step": 64830 }, { "epoch": 1.06, "learning_rate": 1.7625751503006012e-05, "loss": 2.034, "step": 64840 }, { "epoch": 1.06, "learning_rate": 1.7620741482965933e-05, "loss": 2.0442, "step": 64850 }, { "epoch": 1.06, "learning_rate": 1.7615731462925853e-05, "loss": 2.0833, "step": 64860 }, { "epoch": 1.06, "learning_rate": 1.761072144288577e-05, "loss": 2.0447, "step": 64870 }, { "epoch": 1.06, "learning_rate": 1.760571142284569e-05, "loss": 2.006, "step": 64880 }, { "epoch": 1.06, "learning_rate": 1.7600701402805612e-05, "loss": 2.0621, "step": 64890 }, { "epoch": 1.06, "learning_rate": 1.759569138276553e-05, "loss": 2.0603, "step": 64900 }, { "epoch": 1.06, "learning_rate": 1.7590681362725453e-05, "loss": 2.0647, "step": 64910 }, { "epoch": 1.06, "learning_rate": 1.7585671342685374e-05, "loss": 2.099, "step": 64920 }, { "epoch": 1.06, "learning_rate": 1.758066132264529e-05, "loss": 2.0274, "step": 64930 }, { "epoch": 1.06, "learning_rate": 1.757565130260521e-05, "loss": 2.027, "step": 64940 }, { "epoch": 1.06, "learning_rate": 1.7570641282565132e-05, "loss": 2.0241, "step": 64950 }, { "epoch": 1.06, "learning_rate": 1.756563126252505e-05, "loss": 2.0141, "step": 64960 }, { "epoch": 1.06, "learning_rate": 1.756062124248497e-05, "loss": 1.996, "step": 64970 }, { "epoch": 1.06, "learning_rate": 1.755561122244489e-05, "loss": 2.0276, "step": 64980 }, { "epoch": 1.06, "learning_rate": 1.7550601202404808e-05, "loss": 1.9915, "step": 64990 }, { "epoch": 1.06, "learning_rate": 1.754559118236473e-05, "loss": 2.0302, "step": 65000 }, { "epoch": 1.06, "eval_loss": 2.0233283042907715, "eval_mean_f1": 0.6538283296660675, "eval_rouge1_f1": 0.7121917242472225, "eval_rouge1_precision": 0.8228276853291205, "eval_rouge1_recall": 0.6612554775094344, "eval_rouge2_f1": 0.5694257848479303, "eval_rouge2_precision": 0.662483928560589, "eval_rouge2_recall": 0.5282373667001543, "eval_rougeL_f1": 0.6798674799030495, "eval_rougeL_precision": 0.7844179109990803, "eval_rougeL_recall": 0.6317189696067561, "eval_runtime": 62.3174, "eval_samples_per_second": 16.432, "eval_steps_per_second": 2.054, "step": 65000 }, { "epoch": 1.06, "learning_rate": 1.7540581162324653e-05, "loss": 1.969, "step": 65010 }, { "epoch": 1.06, "learning_rate": 1.753557114228457e-05, "loss": 2.0294, "step": 65020 }, { "epoch": 1.06, "learning_rate": 1.753056112224449e-05, "loss": 2.0097, "step": 65030 }, { "epoch": 1.06, "learning_rate": 1.752555110220441e-05, "loss": 2.0344, "step": 65040 }, { "epoch": 1.06, "learning_rate": 1.752054108216433e-05, "loss": 2.0679, "step": 65050 }, { "epoch": 1.06, "learning_rate": 1.751553106212425e-05, "loss": 2.0405, "step": 65060 }, { "epoch": 1.06, "learning_rate": 1.751052104208417e-05, "loss": 2.0498, "step": 65070 }, { "epoch": 1.06, "learning_rate": 1.7505511022044087e-05, "loss": 2.0527, "step": 65080 }, { "epoch": 1.06, "learning_rate": 1.7500501002004008e-05, "loss": 2.0295, "step": 65090 }, { "epoch": 1.06, "learning_rate": 1.749549098196393e-05, "loss": 2.0372, "step": 65100 }, { "epoch": 1.06, "learning_rate": 1.749048096192385e-05, "loss": 2.0119, "step": 65110 }, { "epoch": 1.06, "learning_rate": 1.748547094188377e-05, "loss": 2.0397, "step": 65120 }, { "epoch": 1.06, "learning_rate": 1.748046092184369e-05, "loss": 2.0611, "step": 65130 }, { "epoch": 1.06, "learning_rate": 1.7475450901803608e-05, "loss": 2.0128, "step": 65140 }, { "epoch": 1.06, "learning_rate": 1.7470440881763528e-05, "loss": 2.0363, "step": 65150 }, { "epoch": 1.06, "learning_rate": 1.746543086172345e-05, "loss": 2.014, "step": 65160 }, { "epoch": 1.06, "learning_rate": 1.7460420841683366e-05, "loss": 2.0176, "step": 65170 }, { "epoch": 1.07, "learning_rate": 1.7455410821643287e-05, "loss": 2.0631, "step": 65180 }, { "epoch": 1.07, "learning_rate": 1.7450400801603207e-05, "loss": 2.0072, "step": 65190 }, { "epoch": 1.07, "learning_rate": 1.7445390781563128e-05, "loss": 2.0165, "step": 65200 }, { "epoch": 1.07, "learning_rate": 1.744038076152305e-05, "loss": 2.0269, "step": 65210 }, { "epoch": 1.07, "learning_rate": 1.7435370741482966e-05, "loss": 2.0435, "step": 65220 }, { "epoch": 1.07, "learning_rate": 1.7430360721442887e-05, "loss": 2.0696, "step": 65230 }, { "epoch": 1.07, "learning_rate": 1.7425350701402807e-05, "loss": 2.0566, "step": 65240 }, { "epoch": 1.07, "learning_rate": 1.7420340681362728e-05, "loss": 2.0363, "step": 65250 }, { "epoch": 1.07, "learning_rate": 1.7415330661322645e-05, "loss": 2.0384, "step": 65260 }, { "epoch": 1.07, "learning_rate": 1.7410320641282566e-05, "loss": 2.0326, "step": 65270 }, { "epoch": 1.07, "learning_rate": 1.7405310621242486e-05, "loss": 2.0191, "step": 65280 }, { "epoch": 1.07, "learning_rate": 1.7400300601202404e-05, "loss": 1.999, "step": 65290 }, { "epoch": 1.07, "learning_rate": 1.7395290581162328e-05, "loss": 2.0311, "step": 65300 }, { "epoch": 1.07, "learning_rate": 1.7390280561122245e-05, "loss": 2.024, "step": 65310 }, { "epoch": 1.07, "learning_rate": 1.7385270541082166e-05, "loss": 2.0119, "step": 65320 }, { "epoch": 1.07, "learning_rate": 1.7380260521042086e-05, "loss": 2.0387, "step": 65330 }, { "epoch": 1.07, "learning_rate": 1.7375250501002003e-05, "loss": 2.0616, "step": 65340 }, { "epoch": 1.07, "learning_rate": 1.7370240480961924e-05, "loss": 2.0382, "step": 65350 }, { "epoch": 1.07, "learning_rate": 1.7365230460921845e-05, "loss": 2.0124, "step": 65360 }, { "epoch": 1.07, "learning_rate": 1.7360220440881762e-05, "loss": 2.0192, "step": 65370 }, { "epoch": 1.07, "learning_rate": 1.7355210420841683e-05, "loss": 2.0645, "step": 65380 }, { "epoch": 1.07, "learning_rate": 1.7350200400801603e-05, "loss": 2.0268, "step": 65390 }, { "epoch": 1.07, "learning_rate": 1.7345190380761524e-05, "loss": 2.0333, "step": 65400 }, { "epoch": 1.07, "learning_rate": 1.7340180360721445e-05, "loss": 2.0003, "step": 65410 }, { "epoch": 1.07, "learning_rate": 1.733567134268537e-05, "loss": 2.0607, "step": 65420 }, { "epoch": 1.07, "learning_rate": 1.7330661322645292e-05, "loss": 2.0807, "step": 65430 }, { "epoch": 1.07, "learning_rate": 1.7325651302605212e-05, "loss": 1.9848, "step": 65440 }, { "epoch": 1.07, "learning_rate": 1.732064128256513e-05, "loss": 2.0084, "step": 65450 }, { "epoch": 1.07, "learning_rate": 1.731563126252505e-05, "loss": 2.0373, "step": 65460 }, { "epoch": 1.07, "learning_rate": 1.731062124248497e-05, "loss": 2.0558, "step": 65470 }, { "epoch": 1.07, "learning_rate": 1.7305611222444888e-05, "loss": 2.0555, "step": 65480 }, { "epoch": 1.07, "learning_rate": 1.730060120240481e-05, "loss": 2.0096, "step": 65490 }, { "epoch": 1.07, "learning_rate": 1.7295591182364733e-05, "loss": 2.0117, "step": 65500 }, { "epoch": 1.07, "learning_rate": 1.729058116232465e-05, "loss": 2.0647, "step": 65510 }, { "epoch": 1.07, "learning_rate": 1.728557114228457e-05, "loss": 2.0081, "step": 65520 }, { "epoch": 1.07, "learning_rate": 1.728056112224449e-05, "loss": 2.0835, "step": 65530 }, { "epoch": 1.07, "learning_rate": 1.727555110220441e-05, "loss": 2.0323, "step": 65540 }, { "epoch": 1.07, "learning_rate": 1.727054108216433e-05, "loss": 1.9885, "step": 65550 }, { "epoch": 1.07, "learning_rate": 1.726553106212425e-05, "loss": 2.0277, "step": 65560 }, { "epoch": 1.07, "learning_rate": 1.7260521042084167e-05, "loss": 2.0761, "step": 65570 }, { "epoch": 1.07, "learning_rate": 1.7255511022044088e-05, "loss": 2.0334, "step": 65580 }, { "epoch": 1.07, "learning_rate": 1.725050100200401e-05, "loss": 2.0441, "step": 65590 }, { "epoch": 1.07, "learning_rate": 1.724549098196393e-05, "loss": 2.0092, "step": 65600 }, { "epoch": 1.07, "learning_rate": 1.724048096192385e-05, "loss": 2.041, "step": 65610 }, { "epoch": 1.07, "learning_rate": 1.723547094188377e-05, "loss": 2.0106, "step": 65620 }, { "epoch": 1.07, "learning_rate": 1.7230460921843688e-05, "loss": 2.0338, "step": 65630 }, { "epoch": 1.07, "learning_rate": 1.7225450901803608e-05, "loss": 2.0152, "step": 65640 }, { "epoch": 1.07, "learning_rate": 1.722044088176353e-05, "loss": 2.0316, "step": 65650 }, { "epoch": 1.07, "learning_rate": 1.7215430861723446e-05, "loss": 2.0313, "step": 65660 }, { "epoch": 1.07, "learning_rate": 1.7210420841683367e-05, "loss": 2.0056, "step": 65670 }, { "epoch": 1.07, "learning_rate": 1.7205410821643287e-05, "loss": 2.0815, "step": 65680 }, { "epoch": 1.07, "learning_rate": 1.7200400801603205e-05, "loss": 2.0269, "step": 65690 }, { "epoch": 1.07, "learning_rate": 1.719539078156313e-05, "loss": 2.0545, "step": 65700 }, { "epoch": 1.07, "learning_rate": 1.719038076152305e-05, "loss": 1.994, "step": 65710 }, { "epoch": 1.07, "learning_rate": 1.7185370741482967e-05, "loss": 2.0364, "step": 65720 }, { "epoch": 1.07, "learning_rate": 1.7180360721442887e-05, "loss": 2.042, "step": 65730 }, { "epoch": 1.07, "learning_rate": 1.7175350701402808e-05, "loss": 2.0522, "step": 65740 }, { "epoch": 1.07, "learning_rate": 1.7170340681362725e-05, "loss": 2.0389, "step": 65750 }, { "epoch": 1.07, "learning_rate": 1.7165330661322646e-05, "loss": 2.0153, "step": 65760 }, { "epoch": 1.07, "learning_rate": 1.7160320641282566e-05, "loss": 2.0361, "step": 65770 }, { "epoch": 1.07, "learning_rate": 1.7155310621242484e-05, "loss": 2.0563, "step": 65780 }, { "epoch": 1.07, "learning_rate": 1.7150300601202408e-05, "loss": 1.9987, "step": 65790 }, { "epoch": 1.08, "learning_rate": 1.7145290581162325e-05, "loss": 2.0069, "step": 65800 }, { "epoch": 1.08, "learning_rate": 1.7140280561122246e-05, "loss": 2.0369, "step": 65810 }, { "epoch": 1.08, "learning_rate": 1.7135270541082166e-05, "loss": 2.0401, "step": 65820 }, { "epoch": 1.08, "learning_rate": 1.7130260521042087e-05, "loss": 2.0694, "step": 65830 }, { "epoch": 1.08, "learning_rate": 1.7125250501002004e-05, "loss": 1.9969, "step": 65840 }, { "epoch": 1.08, "learning_rate": 1.7120240480961925e-05, "loss": 2.0474, "step": 65850 }, { "epoch": 1.08, "learning_rate": 1.7115230460921845e-05, "loss": 2.066, "step": 65860 }, { "epoch": 1.08, "learning_rate": 1.7110220440881763e-05, "loss": 2.0505, "step": 65870 }, { "epoch": 1.08, "learning_rate": 1.7105210420841683e-05, "loss": 2.0075, "step": 65880 }, { "epoch": 1.08, "learning_rate": 1.7100200400801604e-05, "loss": 1.9968, "step": 65890 }, { "epoch": 1.08, "learning_rate": 1.7095190380761525e-05, "loss": 2.0526, "step": 65900 }, { "epoch": 1.08, "learning_rate": 1.7090180360721445e-05, "loss": 2.0756, "step": 65910 }, { "epoch": 1.08, "learning_rate": 1.7085170340681363e-05, "loss": 1.9791, "step": 65920 }, { "epoch": 1.08, "learning_rate": 1.7080160320641283e-05, "loss": 2.0535, "step": 65930 }, { "epoch": 1.08, "learning_rate": 1.7075150300601204e-05, "loss": 2.0531, "step": 65940 }, { "epoch": 1.08, "learning_rate": 1.707014028056112e-05, "loss": 2.0179, "step": 65950 }, { "epoch": 1.08, "learning_rate": 1.706513026052104e-05, "loss": 2.0043, "step": 65960 }, { "epoch": 1.08, "learning_rate": 1.7060120240480962e-05, "loss": 2.0874, "step": 65970 }, { "epoch": 1.08, "learning_rate": 1.7055110220440883e-05, "loss": 2.0044, "step": 65980 }, { "epoch": 1.08, "learning_rate": 1.7050100200400804e-05, "loss": 2.0181, "step": 65990 }, { "epoch": 1.08, "learning_rate": 1.7045090180360724e-05, "loss": 2.0286, "step": 66000 }, { "epoch": 1.08, "eval_loss": 2.0187978744506836, "eval_mean_f1": 0.6576881171685175, "eval_rouge1_f1": 0.7172405878620806, "eval_rouge1_precision": 0.8269649771854206, "eval_rouge1_recall": 0.6664674040716576, "eval_rouge2_f1": 0.5722576997358138, "eval_rouge2_precision": 0.6638485239803601, "eval_rouge2_recall": 0.5313473831593829, "eval_rougeL_f1": 0.683566063907658, "eval_rougeL_precision": 0.7861401846372835, "eval_rougeL_recall": 0.6363679749768865, "eval_runtime": 63.4297, "eval_samples_per_second": 16.144, "eval_steps_per_second": 2.018, "step": 66000 }, { "epoch": 1.08, "learning_rate": 1.704008016032064e-05, "loss": 2.062, "step": 66010 }, { "epoch": 1.08, "learning_rate": 1.7035070140280562e-05, "loss": 2.0009, "step": 66020 }, { "epoch": 1.08, "learning_rate": 1.7030060120240483e-05, "loss": 2.0335, "step": 66030 }, { "epoch": 1.08, "learning_rate": 1.70250501002004e-05, "loss": 2.0294, "step": 66040 }, { "epoch": 1.08, "learning_rate": 1.702004008016032e-05, "loss": 2.0378, "step": 66050 }, { "epoch": 1.08, "learning_rate": 1.701503006012024e-05, "loss": 2.0094, "step": 66060 }, { "epoch": 1.08, "learning_rate": 1.701002004008016e-05, "loss": 2.0325, "step": 66070 }, { "epoch": 1.08, "learning_rate": 1.700501002004008e-05, "loss": 1.9722, "step": 66080 }, { "epoch": 1.08, "learning_rate": 1.7000000000000003e-05, "loss": 2.0624, "step": 66090 }, { "epoch": 1.08, "learning_rate": 1.699498997995992e-05, "loss": 2.0438, "step": 66100 }, { "epoch": 1.08, "learning_rate": 1.698997995991984e-05, "loss": 2.0245, "step": 66110 }, { "epoch": 1.08, "learning_rate": 1.6984969939879762e-05, "loss": 2.0117, "step": 66120 }, { "epoch": 1.08, "learning_rate": 1.697995991983968e-05, "loss": 2.026, "step": 66130 }, { "epoch": 1.08, "learning_rate": 1.69749498997996e-05, "loss": 2.009, "step": 66140 }, { "epoch": 1.08, "learning_rate": 1.696993987975952e-05, "loss": 2.0509, "step": 66150 }, { "epoch": 1.08, "learning_rate": 1.6964929859719438e-05, "loss": 2.0, "step": 66160 }, { "epoch": 1.08, "learning_rate": 1.6959919839679358e-05, "loss": 2.0346, "step": 66170 }, { "epoch": 1.08, "learning_rate": 1.695490981963928e-05, "loss": 1.9739, "step": 66180 }, { "epoch": 1.08, "learning_rate": 1.69498997995992e-05, "loss": 2.0651, "step": 66190 }, { "epoch": 1.08, "learning_rate": 1.694488977955912e-05, "loss": 2.069, "step": 66200 }, { "epoch": 1.08, "learning_rate": 1.693987975951904e-05, "loss": 1.9981, "step": 66210 }, { "epoch": 1.08, "learning_rate": 1.6934869739478958e-05, "loss": 2.0302, "step": 66220 }, { "epoch": 1.08, "learning_rate": 1.692985971943888e-05, "loss": 2.0692, "step": 66230 }, { "epoch": 1.08, "learning_rate": 1.69248496993988e-05, "loss": 2.0452, "step": 66240 }, { "epoch": 1.08, "learning_rate": 1.6919839679358717e-05, "loss": 2.028, "step": 66250 }, { "epoch": 1.08, "learning_rate": 1.6914829659318637e-05, "loss": 2.0577, "step": 66260 }, { "epoch": 1.08, "learning_rate": 1.6909819639278558e-05, "loss": 2.0232, "step": 66270 }, { "epoch": 1.08, "learning_rate": 1.6904809619238475e-05, "loss": 2.0538, "step": 66280 }, { "epoch": 1.08, "learning_rate": 1.68997995991984e-05, "loss": 2.0567, "step": 66290 }, { "epoch": 1.08, "learning_rate": 1.689478957915832e-05, "loss": 2.0155, "step": 66300 }, { "epoch": 1.08, "learning_rate": 1.6889779559118237e-05, "loss": 2.0281, "step": 66310 }, { "epoch": 1.08, "learning_rate": 1.6884769539078158e-05, "loss": 2.023, "step": 66320 }, { "epoch": 1.08, "learning_rate": 1.687975951903808e-05, "loss": 2.0156, "step": 66330 }, { "epoch": 1.08, "learning_rate": 1.6874749498997996e-05, "loss": 2.0297, "step": 66340 }, { "epoch": 1.08, "learning_rate": 1.6869739478957916e-05, "loss": 2.0663, "step": 66350 }, { "epoch": 1.08, "learning_rate": 1.6864729458917837e-05, "loss": 2.0491, "step": 66360 }, { "epoch": 1.08, "learning_rate": 1.6859719438877754e-05, "loss": 2.0316, "step": 66370 }, { "epoch": 1.08, "learning_rate": 1.6854709418837678e-05, "loss": 2.0028, "step": 66380 }, { "epoch": 1.08, "learning_rate": 1.6849699398797595e-05, "loss": 2.1224, "step": 66390 }, { "epoch": 1.08, "learning_rate": 1.6844689378757516e-05, "loss": 1.999, "step": 66400 }, { "epoch": 1.09, "learning_rate": 1.6839679358717437e-05, "loss": 2.0238, "step": 66410 }, { "epoch": 1.09, "learning_rate": 1.6834669338677357e-05, "loss": 2.0057, "step": 66420 }, { "epoch": 1.09, "learning_rate": 1.6829659318637275e-05, "loss": 2.0065, "step": 66430 }, { "epoch": 1.09, "learning_rate": 1.6824649298597195e-05, "loss": 2.0107, "step": 66440 }, { "epoch": 1.09, "learning_rate": 1.6819639278557116e-05, "loss": 2.0231, "step": 66450 }, { "epoch": 1.09, "learning_rate": 1.6814629258517033e-05, "loss": 2.0194, "step": 66460 }, { "epoch": 1.09, "learning_rate": 1.6809619238476954e-05, "loss": 2.0577, "step": 66470 }, { "epoch": 1.09, "learning_rate": 1.6804609218436874e-05, "loss": 2.0298, "step": 66480 }, { "epoch": 1.09, "learning_rate": 1.6799599198396795e-05, "loss": 2.0298, "step": 66490 }, { "epoch": 1.09, "learning_rate": 1.6794589178356716e-05, "loss": 1.9909, "step": 66500 }, { "epoch": 1.09, "learning_rate": 1.6789579158316633e-05, "loss": 2.0143, "step": 66510 }, { "epoch": 1.09, "learning_rate": 1.6784569138276554e-05, "loss": 1.9716, "step": 66520 }, { "epoch": 1.09, "learning_rate": 1.6779559118236474e-05, "loss": 2.0333, "step": 66530 }, { "epoch": 1.09, "learning_rate": 1.6774549098196395e-05, "loss": 2.0499, "step": 66540 }, { "epoch": 1.09, "learning_rate": 1.6769539078156312e-05, "loss": 2.0279, "step": 66550 }, { "epoch": 1.09, "learning_rate": 1.6764529058116233e-05, "loss": 1.9788, "step": 66560 }, { "epoch": 1.09, "learning_rate": 1.6759519038076153e-05, "loss": 2.0603, "step": 66570 }, { "epoch": 1.09, "learning_rate": 1.6754509018036074e-05, "loss": 2.0199, "step": 66580 }, { "epoch": 1.09, "learning_rate": 1.6749498997995995e-05, "loss": 1.9927, "step": 66590 }, { "epoch": 1.09, "learning_rate": 1.6744488977955912e-05, "loss": 2.0195, "step": 66600 }, { "epoch": 1.09, "learning_rate": 1.6739478957915833e-05, "loss": 2.0696, "step": 66610 }, { "epoch": 1.09, "learning_rate": 1.6734468937875753e-05, "loss": 2.0434, "step": 66620 }, { "epoch": 1.09, "learning_rate": 1.672945891783567e-05, "loss": 2.0356, "step": 66630 }, { "epoch": 1.09, "learning_rate": 1.672444889779559e-05, "loss": 2.0603, "step": 66640 }, { "epoch": 1.09, "learning_rate": 1.6719438877755512e-05, "loss": 2.0555, "step": 66650 }, { "epoch": 1.09, "learning_rate": 1.671442885771543e-05, "loss": 2.0508, "step": 66660 }, { "epoch": 1.09, "learning_rate": 1.670941883767535e-05, "loss": 2.002, "step": 66670 }, { "epoch": 1.09, "learning_rate": 1.6704408817635274e-05, "loss": 2.0496, "step": 66680 }, { "epoch": 1.09, "learning_rate": 1.669939879759519e-05, "loss": 2.0611, "step": 66690 }, { "epoch": 1.09, "learning_rate": 1.669438877755511e-05, "loss": 2.0431, "step": 66700 }, { "epoch": 1.09, "learning_rate": 1.6689378757515032e-05, "loss": 2.0383, "step": 66710 }, { "epoch": 1.09, "learning_rate": 1.668436873747495e-05, "loss": 2.0299, "step": 66720 }, { "epoch": 1.09, "learning_rate": 1.667935871743487e-05, "loss": 2.0073, "step": 66730 }, { "epoch": 1.09, "learning_rate": 1.667434869739479e-05, "loss": 2.0142, "step": 66740 }, { "epoch": 1.09, "learning_rate": 1.6669338677354708e-05, "loss": 2.0089, "step": 66750 }, { "epoch": 1.09, "learning_rate": 1.666432865731463e-05, "loss": 2.0056, "step": 66760 }, { "epoch": 1.09, "learning_rate": 1.665931863727455e-05, "loss": 2.0341, "step": 66770 }, { "epoch": 1.09, "learning_rate": 1.665430861723447e-05, "loss": 2.0126, "step": 66780 }, { "epoch": 1.09, "learning_rate": 1.664929859719439e-05, "loss": 2.0479, "step": 66790 }, { "epoch": 1.09, "learning_rate": 1.664428857715431e-05, "loss": 2.0215, "step": 66800 }, { "epoch": 1.09, "learning_rate": 1.663927855711423e-05, "loss": 2.0497, "step": 66810 }, { "epoch": 1.09, "learning_rate": 1.663426853707415e-05, "loss": 2.0622, "step": 66820 }, { "epoch": 1.09, "learning_rate": 1.662925851703407e-05, "loss": 2.0667, "step": 66830 }, { "epoch": 1.09, "learning_rate": 1.6624248496993987e-05, "loss": 2.0014, "step": 66840 }, { "epoch": 1.09, "learning_rate": 1.6619238476953908e-05, "loss": 2.0333, "step": 66850 }, { "epoch": 1.09, "learning_rate": 1.6614228456913828e-05, "loss": 2.0433, "step": 66860 }, { "epoch": 1.09, "learning_rate": 1.660921843687375e-05, "loss": 2.0129, "step": 66870 }, { "epoch": 1.09, "learning_rate": 1.660420841683367e-05, "loss": 1.9968, "step": 66880 }, { "epoch": 1.09, "learning_rate": 1.659919839679359e-05, "loss": 2.0417, "step": 66890 }, { "epoch": 1.09, "learning_rate": 1.6594188376753507e-05, "loss": 2.0286, "step": 66900 }, { "epoch": 1.09, "learning_rate": 1.6589178356713428e-05, "loss": 2.0626, "step": 66910 }, { "epoch": 1.09, "learning_rate": 1.658416833667335e-05, "loss": 2.0378, "step": 66920 }, { "epoch": 1.09, "learning_rate": 1.6579158316633266e-05, "loss": 2.0255, "step": 66930 }, { "epoch": 1.09, "learning_rate": 1.6574148296593187e-05, "loss": 2.021, "step": 66940 }, { "epoch": 1.09, "learning_rate": 1.6569138276553107e-05, "loss": 2.0281, "step": 66950 }, { "epoch": 1.09, "learning_rate": 1.6564128256513025e-05, "loss": 2.0258, "step": 66960 }, { "epoch": 1.09, "learning_rate": 1.655911823647295e-05, "loss": 2.0374, "step": 66970 }, { "epoch": 1.09, "learning_rate": 1.655410821643287e-05, "loss": 2.0098, "step": 66980 }, { "epoch": 1.09, "learning_rate": 1.6549098196392786e-05, "loss": 2.0243, "step": 66990 }, { "epoch": 1.09, "learning_rate": 1.6544088176352707e-05, "loss": 2.0346, "step": 67000 }, { "epoch": 1.09, "eval_loss": 2.0171127319335938, "eval_mean_f1": 0.6625066897011602, "eval_rouge1_f1": 0.7188945736417758, "eval_rouge1_precision": 0.8309641753916652, "eval_rouge1_recall": 0.6665208540455202, "eval_rouge2_f1": 0.5802655515938607, "eval_rouge2_precision": 0.6748511308569904, "eval_rouge2_recall": 0.537888473293715, "eval_rougeL_f1": 0.688359943867844, "eval_rougeL_precision": 0.7941530805508579, "eval_rougeL_recall": 0.6394277590268188, "eval_runtime": 64.5564, "eval_samples_per_second": 15.862, "eval_steps_per_second": 1.983, "step": 67000 }, { "epoch": 1.09, "learning_rate": 1.6539078156312628e-05, "loss": 2.0439, "step": 67010 }, { "epoch": 1.1, "learning_rate": 1.6534068136272545e-05, "loss": 2.026, "step": 67020 }, { "epoch": 1.1, "learning_rate": 1.6529058116232466e-05, "loss": 2.0442, "step": 67030 }, { "epoch": 1.1, "learning_rate": 1.6524048096192386e-05, "loss": 2.0544, "step": 67040 }, { "epoch": 1.1, "learning_rate": 1.6519038076152304e-05, "loss": 2.0621, "step": 67050 }, { "epoch": 1.1, "learning_rate": 1.6514028056112224e-05, "loss": 2.0386, "step": 67060 }, { "epoch": 1.1, "learning_rate": 1.6509018036072145e-05, "loss": 2.0227, "step": 67070 }, { "epoch": 1.1, "learning_rate": 1.6504008016032065e-05, "loss": 2.0252, "step": 67080 }, { "epoch": 1.1, "learning_rate": 1.6498997995991986e-05, "loss": 2.0052, "step": 67090 }, { "epoch": 1.1, "learning_rate": 1.6493987975951907e-05, "loss": 2.0083, "step": 67100 }, { "epoch": 1.1, "learning_rate": 1.6488977955911824e-05, "loss": 2.0721, "step": 67110 }, { "epoch": 1.1, "learning_rate": 1.6483967935871745e-05, "loss": 2.0478, "step": 67120 }, { "epoch": 1.1, "learning_rate": 1.6478957915831665e-05, "loss": 2.0627, "step": 67130 }, { "epoch": 1.1, "learning_rate": 1.6473947895791583e-05, "loss": 1.9772, "step": 67140 }, { "epoch": 1.1, "learning_rate": 1.6468937875751503e-05, "loss": 1.9977, "step": 67150 }, { "epoch": 1.1, "learning_rate": 1.6463927855711424e-05, "loss": 2.0117, "step": 67160 }, { "epoch": 1.1, "learning_rate": 1.6458917835671344e-05, "loss": 2.0458, "step": 67170 }, { "epoch": 1.1, "learning_rate": 1.6453907815631265e-05, "loss": 2.021, "step": 67180 }, { "epoch": 1.1, "learning_rate": 1.6448897795591182e-05, "loss": 2.0659, "step": 67190 }, { "epoch": 1.1, "learning_rate": 1.6443887775551103e-05, "loss": 2.0351, "step": 67200 }, { "epoch": 1.1, "learning_rate": 1.6438877755511024e-05, "loss": 2.0312, "step": 67210 }, { "epoch": 1.1, "learning_rate": 1.643386773547094e-05, "loss": 2.0454, "step": 67220 }, { "epoch": 1.1, "learning_rate": 1.642885771543086e-05, "loss": 2.0061, "step": 67230 }, { "epoch": 1.1, "learning_rate": 1.6423847695390782e-05, "loss": 1.9707, "step": 67240 }, { "epoch": 1.1, "learning_rate": 1.6418837675350703e-05, "loss": 2.0095, "step": 67250 }, { "epoch": 1.1, "learning_rate": 1.641382765531062e-05, "loss": 2.0428, "step": 67260 }, { "epoch": 1.1, "learning_rate": 1.6408817635270544e-05, "loss": 2.0006, "step": 67270 }, { "epoch": 1.1, "learning_rate": 1.640380761523046e-05, "loss": 2.0287, "step": 67280 }, { "epoch": 1.1, "learning_rate": 1.6398797595190382e-05, "loss": 2.0407, "step": 67290 }, { "epoch": 1.1, "learning_rate": 1.6393787575150303e-05, "loss": 2.0597, "step": 67300 }, { "epoch": 1.1, "learning_rate": 1.638877755511022e-05, "loss": 2.0335, "step": 67310 }, { "epoch": 1.1, "learning_rate": 1.638376753507014e-05, "loss": 1.9909, "step": 67320 }, { "epoch": 1.1, "learning_rate": 1.637875751503006e-05, "loss": 1.9691, "step": 67330 }, { "epoch": 1.1, "learning_rate": 1.637374749498998e-05, "loss": 2.0461, "step": 67340 }, { "epoch": 1.1, "learning_rate": 1.63687374749499e-05, "loss": 2.0256, "step": 67350 }, { "epoch": 1.1, "learning_rate": 1.636372745490982e-05, "loss": 2.0606, "step": 67360 }, { "epoch": 1.1, "learning_rate": 1.635871743486974e-05, "loss": 2.0267, "step": 67370 }, { "epoch": 1.1, "learning_rate": 1.635370741482966e-05, "loss": 2.0907, "step": 67380 }, { "epoch": 1.1, "learning_rate": 1.634869739478958e-05, "loss": 1.9947, "step": 67390 }, { "epoch": 1.1, "learning_rate": 1.63436873747495e-05, "loss": 2.0006, "step": 67400 }, { "epoch": 1.1, "learning_rate": 1.633867735470942e-05, "loss": 2.032, "step": 67410 }, { "epoch": 1.1, "learning_rate": 1.633366733466934e-05, "loss": 2.0048, "step": 67420 }, { "epoch": 1.1, "learning_rate": 1.6328657314629257e-05, "loss": 1.9874, "step": 67430 }, { "epoch": 1.1, "learning_rate": 1.6323647294589178e-05, "loss": 2.0109, "step": 67440 }, { "epoch": 1.1, "learning_rate": 1.63186372745491e-05, "loss": 2.0506, "step": 67450 }, { "epoch": 1.1, "learning_rate": 1.631362725450902e-05, "loss": 2.0059, "step": 67460 }, { "epoch": 1.1, "learning_rate": 1.630861723446894e-05, "loss": 2.0192, "step": 67470 }, { "epoch": 1.1, "learning_rate": 1.630360721442886e-05, "loss": 2.0056, "step": 67480 }, { "epoch": 1.1, "learning_rate": 1.6298597194388778e-05, "loss": 2.028, "step": 67490 }, { "epoch": 1.1, "learning_rate": 1.62935871743487e-05, "loss": 2.0276, "step": 67500 }, { "epoch": 1.1, "learning_rate": 1.628857715430862e-05, "loss": 2.0441, "step": 67510 }, { "epoch": 1.1, "learning_rate": 1.6283567134268536e-05, "loss": 2.0484, "step": 67520 }, { "epoch": 1.1, "learning_rate": 1.6278557114228457e-05, "loss": 1.9753, "step": 67530 }, { "epoch": 1.1, "learning_rate": 1.6273547094188378e-05, "loss": 2.025, "step": 67540 }, { "epoch": 1.1, "learning_rate": 1.6268537074148295e-05, "loss": 2.0723, "step": 67550 }, { "epoch": 1.1, "learning_rate": 1.626352705410822e-05, "loss": 2.017, "step": 67560 }, { "epoch": 1.1, "learning_rate": 1.625851703406814e-05, "loss": 2.0277, "step": 67570 }, { "epoch": 1.1, "learning_rate": 1.6253507014028057e-05, "loss": 2.0714, "step": 67580 }, { "epoch": 1.1, "learning_rate": 1.6248496993987977e-05, "loss": 2.0172, "step": 67590 }, { "epoch": 1.1, "learning_rate": 1.6243486973947898e-05, "loss": 2.0416, "step": 67600 }, { "epoch": 1.1, "learning_rate": 1.6238476953907815e-05, "loss": 2.0216, "step": 67610 }, { "epoch": 1.1, "learning_rate": 1.6233466933867736e-05, "loss": 2.0835, "step": 67620 }, { "epoch": 1.11, "learning_rate": 1.6228456913827657e-05, "loss": 2.0173, "step": 67630 }, { "epoch": 1.11, "learning_rate": 1.6223446893787574e-05, "loss": 2.0471, "step": 67640 }, { "epoch": 1.11, "learning_rate": 1.6218436873747495e-05, "loss": 2.0183, "step": 67650 }, { "epoch": 1.11, "learning_rate": 1.6213426853707415e-05, "loss": 2.0266, "step": 67660 }, { "epoch": 1.11, "learning_rate": 1.6208416833667336e-05, "loss": 2.0111, "step": 67670 }, { "epoch": 1.11, "learning_rate": 1.6203406813627256e-05, "loss": 2.0246, "step": 67680 }, { "epoch": 1.11, "learning_rate": 1.6198396793587177e-05, "loss": 2.0249, "step": 67690 }, { "epoch": 1.11, "learning_rate": 1.6193386773547094e-05, "loss": 2.0585, "step": 67700 }, { "epoch": 1.11, "learning_rate": 1.6188376753507015e-05, "loss": 1.9979, "step": 67710 }, { "epoch": 1.11, "learning_rate": 1.6183366733466936e-05, "loss": 2.0011, "step": 67720 }, { "epoch": 1.11, "learning_rate": 1.6178356713426853e-05, "loss": 2.0609, "step": 67730 }, { "epoch": 1.11, "learning_rate": 1.6173346693386774e-05, "loss": 2.0641, "step": 67740 }, { "epoch": 1.11, "learning_rate": 1.6168336673346694e-05, "loss": 1.9908, "step": 67750 }, { "epoch": 1.11, "learning_rate": 1.6163326653306615e-05, "loss": 2.0227, "step": 67760 }, { "epoch": 1.11, "learning_rate": 1.6158316633266535e-05, "loss": 2.0411, "step": 67770 }, { "epoch": 1.11, "learning_rate": 1.6153306613226453e-05, "loss": 2.0393, "step": 67780 }, { "epoch": 1.11, "learning_rate": 1.6148296593186373e-05, "loss": 2.0537, "step": 67790 }, { "epoch": 1.11, "learning_rate": 1.6143286573146294e-05, "loss": 1.9738, "step": 67800 }, { "epoch": 1.11, "learning_rate": 1.6138276553106215e-05, "loss": 2.0334, "step": 67810 }, { "epoch": 1.11, "learning_rate": 1.6133266533066132e-05, "loss": 2.0188, "step": 67820 }, { "epoch": 1.11, "learning_rate": 1.6128256513026053e-05, "loss": 1.9761, "step": 67830 }, { "epoch": 1.11, "learning_rate": 1.6123246492985973e-05, "loss": 2.0422, "step": 67840 }, { "epoch": 1.11, "learning_rate": 1.611823647294589e-05, "loss": 2.0452, "step": 67850 }, { "epoch": 1.11, "learning_rate": 1.6113226452905814e-05, "loss": 2.0346, "step": 67860 }, { "epoch": 1.11, "learning_rate": 1.6108216432865732e-05, "loss": 2.0378, "step": 67870 }, { "epoch": 1.11, "learning_rate": 1.6103206412825652e-05, "loss": 2.0066, "step": 67880 }, { "epoch": 1.11, "learning_rate": 1.6098196392785573e-05, "loss": 2.0425, "step": 67890 }, { "epoch": 1.11, "learning_rate": 1.609318637274549e-05, "loss": 2.0098, "step": 67900 }, { "epoch": 1.11, "learning_rate": 1.608817635270541e-05, "loss": 2.0083, "step": 67910 }, { "epoch": 1.11, "learning_rate": 1.608316633266533e-05, "loss": 2.0279, "step": 67920 }, { "epoch": 1.11, "learning_rate": 1.607815631262525e-05, "loss": 2.0626, "step": 67930 }, { "epoch": 1.11, "learning_rate": 1.607314629258517e-05, "loss": 2.0826, "step": 67940 }, { "epoch": 1.11, "learning_rate": 1.606813627254509e-05, "loss": 1.9853, "step": 67950 }, { "epoch": 1.11, "learning_rate": 1.606312625250501e-05, "loss": 2.0287, "step": 67960 }, { "epoch": 1.11, "learning_rate": 1.605811623246493e-05, "loss": 2.029, "step": 67970 }, { "epoch": 1.11, "learning_rate": 1.6053106212424852e-05, "loss": 2.0199, "step": 67980 }, { "epoch": 1.11, "learning_rate": 1.604809619238477e-05, "loss": 2.0037, "step": 67990 }, { "epoch": 1.11, "learning_rate": 1.604308617234469e-05, "loss": 1.981, "step": 68000 }, { "epoch": 1.11, "eval_loss": 2.0123586654663086, "eval_mean_f1": 0.6603870704634741, "eval_rouge1_f1": 0.7190083881195559, "eval_rouge1_precision": 0.8296761434191059, "eval_rouge1_recall": 0.6671499385111209, "eval_rouge2_f1": 0.5759104674951114, "eval_rouge2_precision": 0.670649305799452, "eval_rouge2_recall": 0.5340743518561002, "eval_rougeL_f1": 0.686242355775755, "eval_rougeL_precision": 0.7911553812127543, "eval_rougeL_recall": 0.6379345282823101, "eval_runtime": 64.0437, "eval_samples_per_second": 15.989, "eval_steps_per_second": 1.999, "step": 68000 }, { "epoch": 1.11, "learning_rate": 1.603807615230461e-05, "loss": 2.0306, "step": 68010 }, { "epoch": 1.11, "learning_rate": 1.6033066132264528e-05, "loss": 1.9923, "step": 68020 }, { "epoch": 1.11, "learning_rate": 1.602805611222445e-05, "loss": 2.0841, "step": 68030 }, { "epoch": 1.11, "learning_rate": 1.602304609218437e-05, "loss": 2.0309, "step": 68040 }, { "epoch": 1.11, "learning_rate": 1.601803607214429e-05, "loss": 2.0487, "step": 68050 }, { "epoch": 1.11, "learning_rate": 1.601302605210421e-05, "loss": 1.9978, "step": 68060 }, { "epoch": 1.11, "learning_rate": 1.600801603206413e-05, "loss": 1.9912, "step": 68070 }, { "epoch": 1.11, "learning_rate": 1.6003006012024048e-05, "loss": 2.0329, "step": 68080 }, { "epoch": 1.11, "learning_rate": 1.599799599198397e-05, "loss": 2.0065, "step": 68090 }, { "epoch": 1.11, "learning_rate": 1.599298597194389e-05, "loss": 2.0069, "step": 68100 }, { "epoch": 1.11, "learning_rate": 1.5987975951903807e-05, "loss": 2.0073, "step": 68110 }, { "epoch": 1.11, "learning_rate": 1.5982965931863727e-05, "loss": 2.0587, "step": 68120 }, { "epoch": 1.11, "learning_rate": 1.5977955911823648e-05, "loss": 2.032, "step": 68130 }, { "epoch": 1.11, "learning_rate": 1.5972945891783565e-05, "loss": 2.0551, "step": 68140 }, { "epoch": 1.11, "learning_rate": 1.596793587174349e-05, "loss": 2.0662, "step": 68150 }, { "epoch": 1.11, "learning_rate": 1.596292585170341e-05, "loss": 2.0156, "step": 68160 }, { "epoch": 1.11, "learning_rate": 1.5957915831663327e-05, "loss": 2.0185, "step": 68170 }, { "epoch": 1.11, "learning_rate": 1.5952905811623248e-05, "loss": 1.9949, "step": 68180 }, { "epoch": 1.11, "learning_rate": 1.594789579158317e-05, "loss": 1.9926, "step": 68190 }, { "epoch": 1.11, "learning_rate": 1.5942885771543086e-05, "loss": 2.0131, "step": 68200 }, { "epoch": 1.11, "learning_rate": 1.5937875751503006e-05, "loss": 2.015, "step": 68210 }, { "epoch": 1.11, "learning_rate": 1.5932865731462927e-05, "loss": 2.0013, "step": 68220 }, { "epoch": 1.11, "learning_rate": 1.5927855711422844e-05, "loss": 2.0056, "step": 68230 }, { "epoch": 1.12, "learning_rate": 1.5922845691382765e-05, "loss": 2.0264, "step": 68240 }, { "epoch": 1.12, "learning_rate": 1.591783567134269e-05, "loss": 2.0512, "step": 68250 }, { "epoch": 1.12, "learning_rate": 1.5912825651302606e-05, "loss": 2.0587, "step": 68260 }, { "epoch": 1.12, "learning_rate": 1.5907815631262527e-05, "loss": 2.0603, "step": 68270 }, { "epoch": 1.12, "learning_rate": 1.5902805611222448e-05, "loss": 2.0076, "step": 68280 }, { "epoch": 1.12, "learning_rate": 1.5897795591182365e-05, "loss": 2.0576, "step": 68290 }, { "epoch": 1.12, "learning_rate": 1.5892785571142285e-05, "loss": 2.031, "step": 68300 }, { "epoch": 1.12, "learning_rate": 1.5887775551102206e-05, "loss": 2.0611, "step": 68310 }, { "epoch": 1.12, "learning_rate": 1.5882765531062123e-05, "loss": 2.0297, "step": 68320 }, { "epoch": 1.12, "learning_rate": 1.5878256513026053e-05, "loss": 2.0193, "step": 68330 }, { "epoch": 1.12, "learning_rate": 1.587324649298597e-05, "loss": 2.0202, "step": 68340 }, { "epoch": 1.12, "learning_rate": 1.5868236472945895e-05, "loss": 2.0017, "step": 68350 }, { "epoch": 1.12, "learning_rate": 1.5863226452905812e-05, "loss": 2.0527, "step": 68360 }, { "epoch": 1.12, "learning_rate": 1.5858216432865732e-05, "loss": 2.0342, "step": 68370 }, { "epoch": 1.12, "learning_rate": 1.5853206412825653e-05, "loss": 1.985, "step": 68380 }, { "epoch": 1.12, "learning_rate": 1.584819639278557e-05, "loss": 2.0479, "step": 68390 }, { "epoch": 1.12, "learning_rate": 1.584318637274549e-05, "loss": 1.9856, "step": 68400 }, { "epoch": 1.12, "learning_rate": 1.583817635270541e-05, "loss": 2.0283, "step": 68410 }, { "epoch": 1.12, "learning_rate": 1.5833166332665332e-05, "loss": 2.0244, "step": 68420 }, { "epoch": 1.12, "learning_rate": 1.582815631262525e-05, "loss": 2.0273, "step": 68430 }, { "epoch": 1.12, "learning_rate": 1.582314629258517e-05, "loss": 2.0232, "step": 68440 }, { "epoch": 1.12, "learning_rate": 1.581813627254509e-05, "loss": 1.9997, "step": 68450 }, { "epoch": 1.12, "learning_rate": 1.581312625250501e-05, "loss": 2.0165, "step": 68460 }, { "epoch": 1.12, "learning_rate": 1.5808116232464932e-05, "loss": 1.9689, "step": 68470 }, { "epoch": 1.12, "learning_rate": 1.580310621242485e-05, "loss": 2.0352, "step": 68480 }, { "epoch": 1.12, "learning_rate": 1.579809619238477e-05, "loss": 2.0334, "step": 68490 }, { "epoch": 1.12, "learning_rate": 1.579308617234469e-05, "loss": 2.0048, "step": 68500 }, { "epoch": 1.12, "learning_rate": 1.5788076152304608e-05, "loss": 1.9984, "step": 68510 }, { "epoch": 1.12, "learning_rate": 1.578306613226453e-05, "loss": 2.0234, "step": 68520 }, { "epoch": 1.12, "learning_rate": 1.577805611222445e-05, "loss": 2.0324, "step": 68530 }, { "epoch": 1.12, "learning_rate": 1.577304609218437e-05, "loss": 2.0077, "step": 68540 }, { "epoch": 1.12, "learning_rate": 1.576803607214429e-05, "loss": 2.0443, "step": 68550 }, { "epoch": 1.12, "learning_rate": 1.576302605210421e-05, "loss": 2.0382, "step": 68560 }, { "epoch": 1.12, "learning_rate": 1.5758016032064128e-05, "loss": 2.0424, "step": 68570 }, { "epoch": 1.12, "learning_rate": 1.575300601202405e-05, "loss": 2.0351, "step": 68580 }, { "epoch": 1.12, "learning_rate": 1.574799599198397e-05, "loss": 2.0238, "step": 68590 }, { "epoch": 1.12, "learning_rate": 1.5742985971943887e-05, "loss": 2.0437, "step": 68600 }, { "epoch": 1.12, "learning_rate": 1.5737975951903807e-05, "loss": 2.0179, "step": 68610 }, { "epoch": 1.12, "learning_rate": 1.5732965931863728e-05, "loss": 1.9737, "step": 68620 }, { "epoch": 1.12, "learning_rate": 1.5727955911823645e-05, "loss": 2.0408, "step": 68630 }, { "epoch": 1.12, "learning_rate": 1.572294589178357e-05, "loss": 1.9792, "step": 68640 }, { "epoch": 1.12, "learning_rate": 1.571793587174349e-05, "loss": 2.0354, "step": 68650 }, { "epoch": 1.12, "learning_rate": 1.5712925851703407e-05, "loss": 2.0296, "step": 68660 }, { "epoch": 1.12, "learning_rate": 1.5707915831663328e-05, "loss": 2.0466, "step": 68670 }, { "epoch": 1.12, "learning_rate": 1.570290581162325e-05, "loss": 2.0441, "step": 68680 }, { "epoch": 1.12, "learning_rate": 1.5697895791583166e-05, "loss": 2.0183, "step": 68690 }, { "epoch": 1.12, "learning_rate": 1.5692885771543086e-05, "loss": 2.0434, "step": 68700 }, { "epoch": 1.12, "learning_rate": 1.5687875751503007e-05, "loss": 2.0696, "step": 68710 }, { "epoch": 1.12, "learning_rate": 1.5682865731462924e-05, "loss": 2.0402, "step": 68720 }, { "epoch": 1.12, "learning_rate": 1.5677855711422845e-05, "loss": 2.0487, "step": 68730 }, { "epoch": 1.12, "learning_rate": 1.567284569138277e-05, "loss": 2.0098, "step": 68740 }, { "epoch": 1.12, "learning_rate": 1.5667835671342686e-05, "loss": 2.0053, "step": 68750 }, { "epoch": 1.12, "learning_rate": 1.5662825651302607e-05, "loss": 2.0067, "step": 68760 }, { "epoch": 1.12, "learning_rate": 1.5657815631262528e-05, "loss": 2.055, "step": 68770 }, { "epoch": 1.12, "learning_rate": 1.5652805611222445e-05, "loss": 2.0267, "step": 68780 }, { "epoch": 1.12, "learning_rate": 1.5647795591182365e-05, "loss": 1.9865, "step": 68790 }, { "epoch": 1.12, "learning_rate": 1.5642785571142286e-05, "loss": 2.0343, "step": 68800 }, { "epoch": 1.12, "learning_rate": 1.5637775551102203e-05, "loss": 2.0812, "step": 68810 }, { "epoch": 1.12, "learning_rate": 1.5632765531062124e-05, "loss": 2.0442, "step": 68820 }, { "epoch": 1.12, "learning_rate": 1.5627755511022045e-05, "loss": 2.0398, "step": 68830 }, { "epoch": 1.12, "learning_rate": 1.5622745490981965e-05, "loss": 2.0012, "step": 68840 }, { "epoch": 1.12, "learning_rate": 1.5617735470941886e-05, "loss": 2.001, "step": 68850 }, { "epoch": 1.13, "learning_rate": 1.5612725450901807e-05, "loss": 2.0194, "step": 68860 }, { "epoch": 1.13, "learning_rate": 1.5607715430861724e-05, "loss": 2.0522, "step": 68870 }, { "epoch": 1.13, "learning_rate": 1.5602705410821644e-05, "loss": 2.0508, "step": 68880 }, { "epoch": 1.13, "learning_rate": 1.5597695390781565e-05, "loss": 2.049, "step": 68890 }, { "epoch": 1.13, "learning_rate": 1.5592685370741482e-05, "loss": 1.9896, "step": 68900 }, { "epoch": 1.13, "learning_rate": 1.5587675350701403e-05, "loss": 2.0289, "step": 68910 }, { "epoch": 1.13, "learning_rate": 1.5582665330661324e-05, "loss": 2.0134, "step": 68920 }, { "epoch": 1.13, "learning_rate": 1.557765531062124e-05, "loss": 1.9844, "step": 68930 }, { "epoch": 1.13, "learning_rate": 1.5572645290581165e-05, "loss": 1.9771, "step": 68940 }, { "epoch": 1.13, "learning_rate": 1.5567635270541082e-05, "loss": 2.0089, "step": 68950 }, { "epoch": 1.13, "learning_rate": 1.5562625250501003e-05, "loss": 1.9984, "step": 68960 }, { "epoch": 1.13, "learning_rate": 1.5557615230460923e-05, "loss": 1.9848, "step": 68970 }, { "epoch": 1.13, "learning_rate": 1.5552605210420844e-05, "loss": 2.0067, "step": 68980 }, { "epoch": 1.13, "learning_rate": 1.554759519038076e-05, "loss": 2.0273, "step": 68990 }, { "epoch": 1.13, "learning_rate": 1.5542585170340682e-05, "loss": 2.0261, "step": 69000 }, { "epoch": 1.13, "eval_loss": 2.017897605895996, "eval_mean_f1": 0.6594191353454065, "eval_rouge1_f1": 0.7167876475215014, "eval_rouge1_precision": 0.8263915401897934, "eval_rouge1_recall": 0.6656729464766591, "eval_rouge2_f1": 0.5757929926024121, "eval_rouge2_precision": 0.6681809936753784, "eval_rouge2_recall": 0.5341103237364895, "eval_rougeL_f1": 0.6856767659123062, "eval_rougeL_precision": 0.7890469762123593, "eval_rougeL_recall": 0.6378198044949612, "eval_runtime": 63.4177, "eval_samples_per_second": 16.147, "eval_steps_per_second": 2.018, "step": 69000 }, { "epoch": 1.13, "learning_rate": 1.5537575150300603e-05, "loss": 2.0825, "step": 69010 }, { "epoch": 1.13, "learning_rate": 1.553256513026052e-05, "loss": 2.0141, "step": 69020 }, { "epoch": 1.13, "learning_rate": 1.552755511022044e-05, "loss": 2.0047, "step": 69030 }, { "epoch": 1.13, "learning_rate": 1.552254509018036e-05, "loss": 2.0137, "step": 69040 }, { "epoch": 1.13, "learning_rate": 1.5517535070140282e-05, "loss": 2.0374, "step": 69050 }, { "epoch": 1.13, "learning_rate": 1.5512525050100202e-05, "loss": 2.0142, "step": 69060 }, { "epoch": 1.13, "learning_rate": 1.550751503006012e-05, "loss": 1.991, "step": 69070 }, { "epoch": 1.13, "learning_rate": 1.550250501002004e-05, "loss": 2.0015, "step": 69080 }, { "epoch": 1.13, "learning_rate": 1.549749498997996e-05, "loss": 2.0499, "step": 69090 }, { "epoch": 1.13, "learning_rate": 1.549248496993988e-05, "loss": 2.0114, "step": 69100 }, { "epoch": 1.13, "learning_rate": 1.54874749498998e-05, "loss": 2.0334, "step": 69110 }, { "epoch": 1.13, "learning_rate": 1.548246492985972e-05, "loss": 2.0031, "step": 69120 }, { "epoch": 1.13, "learning_rate": 1.547745490981964e-05, "loss": 2.0193, "step": 69130 }, { "epoch": 1.13, "learning_rate": 1.547244488977956e-05, "loss": 2.0213, "step": 69140 }, { "epoch": 1.13, "learning_rate": 1.546743486973948e-05, "loss": 2.0109, "step": 69150 }, { "epoch": 1.13, "learning_rate": 1.54624248496994e-05, "loss": 2.0299, "step": 69160 }, { "epoch": 1.13, "learning_rate": 1.545741482965932e-05, "loss": 1.9907, "step": 69170 }, { "epoch": 1.13, "learning_rate": 1.545240480961924e-05, "loss": 2.0141, "step": 69180 }, { "epoch": 1.13, "learning_rate": 1.5447394789579157e-05, "loss": 2.0678, "step": 69190 }, { "epoch": 1.13, "learning_rate": 1.5442384769539078e-05, "loss": 2.0394, "step": 69200 }, { "epoch": 1.13, "learning_rate": 1.5437374749499e-05, "loss": 2.0062, "step": 69210 }, { "epoch": 1.13, "learning_rate": 1.5432364729458916e-05, "loss": 2.0444, "step": 69220 }, { "epoch": 1.13, "learning_rate": 1.542735470941884e-05, "loss": 2.0054, "step": 69230 }, { "epoch": 1.13, "learning_rate": 1.542234468937876e-05, "loss": 2.0059, "step": 69240 }, { "epoch": 1.13, "learning_rate": 1.5417334669338678e-05, "loss": 2.0441, "step": 69250 }, { "epoch": 1.13, "learning_rate": 1.54123246492986e-05, "loss": 2.0249, "step": 69260 }, { "epoch": 1.13, "learning_rate": 1.540731462925852e-05, "loss": 2.0366, "step": 69270 }, { "epoch": 1.13, "learning_rate": 1.5402304609218436e-05, "loss": 2.012, "step": 69280 }, { "epoch": 1.13, "learning_rate": 1.5397294589178357e-05, "loss": 2.0055, "step": 69290 }, { "epoch": 1.13, "learning_rate": 1.5392284569138278e-05, "loss": 2.0495, "step": 69300 }, { "epoch": 1.13, "learning_rate": 1.5387274549098195e-05, "loss": 2.0403, "step": 69310 }, { "epoch": 1.13, "learning_rate": 1.5382264529058115e-05, "loss": 2.033, "step": 69320 }, { "epoch": 1.13, "learning_rate": 1.537725450901804e-05, "loss": 2.038, "step": 69330 }, { "epoch": 1.13, "learning_rate": 1.5372244488977957e-05, "loss": 2.0539, "step": 69340 }, { "epoch": 1.13, "learning_rate": 1.5367234468937877e-05, "loss": 1.9878, "step": 69350 }, { "epoch": 1.13, "learning_rate": 1.5362224448897798e-05, "loss": 2.0376, "step": 69360 }, { "epoch": 1.13, "learning_rate": 1.5357214428857715e-05, "loss": 2.0454, "step": 69370 }, { "epoch": 1.13, "learning_rate": 1.5352204408817636e-05, "loss": 2.0232, "step": 69380 }, { "epoch": 1.13, "learning_rate": 1.5347194388777557e-05, "loss": 2.0285, "step": 69390 }, { "epoch": 1.13, "learning_rate": 1.5342184368737474e-05, "loss": 2.0212, "step": 69400 }, { "epoch": 1.13, "learning_rate": 1.5337174348697394e-05, "loss": 2.0338, "step": 69410 }, { "epoch": 1.13, "learning_rate": 1.5332164328657315e-05, "loss": 1.9952, "step": 69420 }, { "epoch": 1.13, "learning_rate": 1.5327154308617236e-05, "loss": 2.0274, "step": 69430 }, { "epoch": 1.13, "learning_rate": 1.5322144288577156e-05, "loss": 2.0133, "step": 69440 }, { "epoch": 1.13, "learning_rate": 1.5317134268537077e-05, "loss": 2.0183, "step": 69450 }, { "epoch": 1.13, "learning_rate": 1.5312124248496994e-05, "loss": 2.0287, "step": 69460 }, { "epoch": 1.14, "learning_rate": 1.5307114228456915e-05, "loss": 1.9923, "step": 69470 }, { "epoch": 1.14, "learning_rate": 1.5302104208416836e-05, "loss": 2.0841, "step": 69480 }, { "epoch": 1.14, "learning_rate": 1.5297094188376753e-05, "loss": 2.0485, "step": 69490 }, { "epoch": 1.14, "learning_rate": 1.5292084168336673e-05, "loss": 2.0743, "step": 69500 }, { "epoch": 1.14, "learning_rate": 1.5287074148296594e-05, "loss": 2.0464, "step": 69510 }, { "epoch": 1.14, "learning_rate": 1.528206412825651e-05, "loss": 2.0344, "step": 69520 }, { "epoch": 1.14, "learning_rate": 1.5277054108216435e-05, "loss": 2.019, "step": 69530 }, { "epoch": 1.14, "learning_rate": 1.5272044088176356e-05, "loss": 2.0188, "step": 69540 }, { "epoch": 1.14, "learning_rate": 1.5267034068136273e-05, "loss": 2.0364, "step": 69550 }, { "epoch": 1.14, "learning_rate": 1.5262024048096194e-05, "loss": 2.014, "step": 69560 }, { "epoch": 1.14, "learning_rate": 1.5257014028056113e-05, "loss": 2.01, "step": 69570 }, { "epoch": 1.14, "learning_rate": 1.5252004008016032e-05, "loss": 2.0044, "step": 69580 }, { "epoch": 1.14, "learning_rate": 1.5246993987975952e-05, "loss": 2.0312, "step": 69590 }, { "epoch": 1.14, "learning_rate": 1.5241983967935871e-05, "loss": 2.0259, "step": 69600 }, { "epoch": 1.14, "learning_rate": 1.5236973947895792e-05, "loss": 2.0047, "step": 69610 }, { "epoch": 1.14, "learning_rate": 1.5231963927855711e-05, "loss": 2.0259, "step": 69620 }, { "epoch": 1.14, "learning_rate": 1.5226953907815633e-05, "loss": 1.9997, "step": 69630 }, { "epoch": 1.14, "learning_rate": 1.5221943887775552e-05, "loss": 2.043, "step": 69640 }, { "epoch": 1.14, "learning_rate": 1.5216933867735473e-05, "loss": 2.0267, "step": 69650 }, { "epoch": 1.14, "learning_rate": 1.5211923847695392e-05, "loss": 1.9859, "step": 69660 }, { "epoch": 1.14, "learning_rate": 1.520691382765531e-05, "loss": 1.9884, "step": 69670 }, { "epoch": 1.14, "learning_rate": 1.5201903807615231e-05, "loss": 2.0281, "step": 69680 }, { "epoch": 1.14, "learning_rate": 1.519689378757515e-05, "loss": 2.0382, "step": 69690 }, { "epoch": 1.14, "learning_rate": 1.519188376753507e-05, "loss": 2.0253, "step": 69700 }, { "epoch": 1.14, "learning_rate": 1.518687374749499e-05, "loss": 2.0363, "step": 69710 }, { "epoch": 1.14, "learning_rate": 1.5181863727454912e-05, "loss": 2.022, "step": 69720 }, { "epoch": 1.14, "learning_rate": 1.5176853707414831e-05, "loss": 2.0118, "step": 69730 }, { "epoch": 1.14, "learning_rate": 1.5171843687374752e-05, "loss": 2.0305, "step": 69740 }, { "epoch": 1.14, "learning_rate": 1.516683366733467e-05, "loss": 2.0316, "step": 69750 }, { "epoch": 1.14, "learning_rate": 1.516182364729459e-05, "loss": 2.0173, "step": 69760 }, { "epoch": 1.14, "learning_rate": 1.515681362725451e-05, "loss": 2.0254, "step": 69770 }, { "epoch": 1.14, "learning_rate": 1.515180360721443e-05, "loss": 2.0393, "step": 69780 }, { "epoch": 1.14, "learning_rate": 1.5146793587174348e-05, "loss": 2.047, "step": 69790 }, { "epoch": 1.14, "learning_rate": 1.5141783567134269e-05, "loss": 2.0382, "step": 69800 }, { "epoch": 1.14, "learning_rate": 1.5136773547094188e-05, "loss": 2.0149, "step": 69810 }, { "epoch": 1.14, "learning_rate": 1.513176352705411e-05, "loss": 2.0028, "step": 69820 }, { "epoch": 1.14, "learning_rate": 1.512675350701403e-05, "loss": 2.0027, "step": 69830 }, { "epoch": 1.14, "learning_rate": 1.512174348697395e-05, "loss": 2.0409, "step": 69840 }, { "epoch": 1.14, "learning_rate": 1.5116733466933869e-05, "loss": 1.9719, "step": 69850 }, { "epoch": 1.14, "learning_rate": 1.5111723446893788e-05, "loss": 2.0417, "step": 69860 }, { "epoch": 1.14, "learning_rate": 1.5106713426853708e-05, "loss": 2.0594, "step": 69870 }, { "epoch": 1.14, "learning_rate": 1.5101703406813627e-05, "loss": 2.0416, "step": 69880 }, { "epoch": 1.14, "learning_rate": 1.5096693386773548e-05, "loss": 2.0225, "step": 69890 }, { "epoch": 1.14, "learning_rate": 1.5091683366733467e-05, "loss": 2.0458, "step": 69900 }, { "epoch": 1.14, "learning_rate": 1.5086673346693386e-05, "loss": 1.9733, "step": 69910 }, { "epoch": 1.14, "learning_rate": 1.5081663326653308e-05, "loss": 2.0133, "step": 69920 }, { "epoch": 1.14, "learning_rate": 1.5076653306613229e-05, "loss": 2.0638, "step": 69930 }, { "epoch": 1.14, "learning_rate": 1.5071643286573148e-05, "loss": 2.0116, "step": 69940 }, { "epoch": 1.14, "learning_rate": 1.5066633266533067e-05, "loss": 2.0546, "step": 69950 }, { "epoch": 1.14, "learning_rate": 1.5061623246492987e-05, "loss": 2.0165, "step": 69960 }, { "epoch": 1.14, "learning_rate": 1.5056613226452906e-05, "loss": 1.976, "step": 69970 }, { "epoch": 1.14, "learning_rate": 1.5051603206412825e-05, "loss": 2.0271, "step": 69980 }, { "epoch": 1.14, "learning_rate": 1.5046593186372746e-05, "loss": 2.045, "step": 69990 }, { "epoch": 1.14, "learning_rate": 1.5041583166332665e-05, "loss": 2.0236, "step": 70000 }, { "epoch": 1.14, "eval_loss": 2.009993553161621, "eval_mean_f1": 0.6601036283450965, "eval_rouge1_f1": 0.7174788554919043, "eval_rouge1_precision": 0.828433834032912, "eval_rouge1_recall": 0.6654997003681027, "eval_rouge2_f1": 0.5760624196575814, "eval_rouge2_precision": 0.6700092659077037, "eval_rouge2_recall": 0.5340651387457865, "eval_rougeL_f1": 0.6867696098858038, "eval_rougeL_precision": 0.7916512254930652, "eval_rougeL_recall": 0.6380802558261014, "eval_runtime": 63.7406, "eval_samples_per_second": 16.065, "eval_steps_per_second": 2.008, "step": 70000 }, { "epoch": 1.14, "learning_rate": 1.5036573146292585e-05, "loss": 2.0025, "step": 70010 }, { "epoch": 1.14, "learning_rate": 1.5031563126252508e-05, "loss": 2.0115, "step": 70020 }, { "epoch": 1.14, "learning_rate": 1.5026553106212427e-05, "loss": 1.9687, "step": 70030 }, { "epoch": 1.14, "learning_rate": 1.5021543086172346e-05, "loss": 2.032, "step": 70040 }, { "epoch": 1.14, "learning_rate": 1.5016533066132266e-05, "loss": 2.0256, "step": 70050 }, { "epoch": 1.14, "learning_rate": 1.5011523046092185e-05, "loss": 2.0132, "step": 70060 }, { "epoch": 1.14, "learning_rate": 1.5006513026052104e-05, "loss": 1.9911, "step": 70070 }, { "epoch": 1.15, "learning_rate": 1.5001503006012025e-05, "loss": 2.0298, "step": 70080 }, { "epoch": 1.15, "learning_rate": 1.4996492985971944e-05, "loss": 2.016, "step": 70090 }, { "epoch": 1.15, "learning_rate": 1.4991482965931863e-05, "loss": 2.0438, "step": 70100 }, { "epoch": 1.15, "learning_rate": 1.4986472945891783e-05, "loss": 1.9987, "step": 70110 }, { "epoch": 1.15, "learning_rate": 1.4981462925851706e-05, "loss": 1.998, "step": 70120 }, { "epoch": 1.15, "learning_rate": 1.4976452905811625e-05, "loss": 2.0177, "step": 70130 }, { "epoch": 1.15, "learning_rate": 1.4971442885771544e-05, "loss": 2.0171, "step": 70140 }, { "epoch": 1.15, "learning_rate": 1.4966432865731464e-05, "loss": 2.0221, "step": 70150 }, { "epoch": 1.15, "learning_rate": 1.4961422845691383e-05, "loss": 2.0111, "step": 70160 }, { "epoch": 1.15, "learning_rate": 1.4956412825651304e-05, "loss": 2.0286, "step": 70170 }, { "epoch": 1.15, "learning_rate": 1.4951402805611223e-05, "loss": 2.0049, "step": 70180 }, { "epoch": 1.15, "learning_rate": 1.4946392785571142e-05, "loss": 2.0375, "step": 70190 }, { "epoch": 1.15, "learning_rate": 1.4941382765531062e-05, "loss": 2.0051, "step": 70200 }, { "epoch": 1.15, "learning_rate": 1.4936372745490981e-05, "loss": 1.993, "step": 70210 }, { "epoch": 1.15, "learning_rate": 1.4931362725450904e-05, "loss": 2.0107, "step": 70220 }, { "epoch": 1.15, "learning_rate": 1.4926352705410823e-05, "loss": 2.0387, "step": 70230 }, { "epoch": 1.15, "learning_rate": 1.4921342685370743e-05, "loss": 1.9985, "step": 70240 }, { "epoch": 1.15, "learning_rate": 1.4916332665330662e-05, "loss": 2.0219, "step": 70250 }, { "epoch": 1.15, "learning_rate": 1.4911322645290581e-05, "loss": 2.0147, "step": 70260 }, { "epoch": 1.15, "learning_rate": 1.4906312625250502e-05, "loss": 2.0409, "step": 70270 }, { "epoch": 1.15, "learning_rate": 1.490130260521042e-05, "loss": 2.0015, "step": 70280 }, { "epoch": 1.15, "learning_rate": 1.489629258517034e-05, "loss": 2.053, "step": 70290 }, { "epoch": 1.15, "learning_rate": 1.489128256513026e-05, "loss": 2.0123, "step": 70300 }, { "epoch": 1.15, "learning_rate": 1.4886272545090183e-05, "loss": 2.0206, "step": 70310 }, { "epoch": 1.15, "learning_rate": 1.4881262525050102e-05, "loss": 2.0034, "step": 70320 }, { "epoch": 1.15, "learning_rate": 1.4876252505010022e-05, "loss": 2.0523, "step": 70330 }, { "epoch": 1.15, "learning_rate": 1.4871242484969941e-05, "loss": 2.0225, "step": 70340 }, { "epoch": 1.15, "learning_rate": 1.486623246492986e-05, "loss": 2.0661, "step": 70350 }, { "epoch": 1.15, "learning_rate": 1.486122244488978e-05, "loss": 2.0173, "step": 70360 }, { "epoch": 1.15, "learning_rate": 1.48562124248497e-05, "loss": 2.0464, "step": 70370 }, { "epoch": 1.15, "learning_rate": 1.4851202404809619e-05, "loss": 2.0228, "step": 70380 }, { "epoch": 1.15, "learning_rate": 1.484619238476954e-05, "loss": 2.023, "step": 70390 }, { "epoch": 1.15, "learning_rate": 1.4841182364729458e-05, "loss": 2.0272, "step": 70400 }, { "epoch": 1.15, "learning_rate": 1.483617234468938e-05, "loss": 1.9965, "step": 70410 }, { "epoch": 1.15, "learning_rate": 1.48311623246493e-05, "loss": 2.0288, "step": 70420 }, { "epoch": 1.15, "learning_rate": 1.482615230460922e-05, "loss": 2.0398, "step": 70430 }, { "epoch": 1.15, "learning_rate": 1.482114228456914e-05, "loss": 2.0486, "step": 70440 }, { "epoch": 1.15, "learning_rate": 1.481613226452906e-05, "loss": 2.0361, "step": 70450 }, { "epoch": 1.15, "learning_rate": 1.4811122244488979e-05, "loss": 2.0641, "step": 70460 }, { "epoch": 1.15, "learning_rate": 1.4806112224448898e-05, "loss": 2.0499, "step": 70470 }, { "epoch": 1.15, "learning_rate": 1.4801102204408818e-05, "loss": 2.0607, "step": 70480 }, { "epoch": 1.15, "learning_rate": 1.4796092184368737e-05, "loss": 1.9998, "step": 70490 }, { "epoch": 1.15, "learning_rate": 1.4791082164328656e-05, "loss": 2.046, "step": 70500 }, { "epoch": 1.15, "learning_rate": 1.4786573146292588e-05, "loss": 2.0311, "step": 70510 }, { "epoch": 1.15, "learning_rate": 1.4781563126252507e-05, "loss": 2.031, "step": 70520 }, { "epoch": 1.15, "learning_rate": 1.4776553106212426e-05, "loss": 2.0036, "step": 70530 }, { "epoch": 1.15, "learning_rate": 1.4771543086172346e-05, "loss": 2.0062, "step": 70540 }, { "epoch": 1.15, "learning_rate": 1.4766533066132265e-05, "loss": 1.9962, "step": 70550 }, { "epoch": 1.15, "learning_rate": 1.4761523046092184e-05, "loss": 2.0657, "step": 70560 }, { "epoch": 1.15, "learning_rate": 1.4756513026052105e-05, "loss": 2.0137, "step": 70570 }, { "epoch": 1.15, "learning_rate": 1.4751503006012024e-05, "loss": 2.0356, "step": 70580 }, { "epoch": 1.15, "learning_rate": 1.4746492985971943e-05, "loss": 2.0167, "step": 70590 }, { "epoch": 1.15, "learning_rate": 1.4741482965931863e-05, "loss": 2.0102, "step": 70600 }, { "epoch": 1.15, "learning_rate": 1.4736472945891786e-05, "loss": 1.9901, "step": 70610 }, { "epoch": 1.15, "learning_rate": 1.4731462925851705e-05, "loss": 2.0333, "step": 70620 }, { "epoch": 1.15, "learning_rate": 1.4726452905811625e-05, "loss": 2.0251, "step": 70630 }, { "epoch": 1.15, "learning_rate": 1.4721442885771544e-05, "loss": 2.0878, "step": 70640 }, { "epoch": 1.15, "learning_rate": 1.4716432865731463e-05, "loss": 2.0454, "step": 70650 }, { "epoch": 1.15, "learning_rate": 1.4711422845691384e-05, "loss": 2.0184, "step": 70660 }, { "epoch": 1.15, "learning_rate": 1.4706412825651303e-05, "loss": 1.9961, "step": 70670 }, { "epoch": 1.15, "learning_rate": 1.4701402805611222e-05, "loss": 2.0155, "step": 70680 }, { "epoch": 1.16, "learning_rate": 1.4696392785571142e-05, "loss": 2.0391, "step": 70690 }, { "epoch": 1.16, "learning_rate": 1.4691382765531061e-05, "loss": 2.0192, "step": 70700 }, { "epoch": 1.16, "learning_rate": 1.4686372745490984e-05, "loss": 2.0232, "step": 70710 }, { "epoch": 1.16, "learning_rate": 1.4681362725450903e-05, "loss": 1.9928, "step": 70720 }, { "epoch": 1.16, "learning_rate": 1.4676352705410823e-05, "loss": 2.0463, "step": 70730 }, { "epoch": 1.16, "learning_rate": 1.4671342685370742e-05, "loss": 1.9953, "step": 70740 }, { "epoch": 1.16, "learning_rate": 1.4666332665330663e-05, "loss": 2.0251, "step": 70750 }, { "epoch": 1.16, "learning_rate": 1.4661322645290582e-05, "loss": 2.0295, "step": 70760 }, { "epoch": 1.16, "learning_rate": 1.46563126252505e-05, "loss": 2.0441, "step": 70770 }, { "epoch": 1.16, "learning_rate": 1.4651302605210421e-05, "loss": 2.0095, "step": 70780 }, { "epoch": 1.16, "learning_rate": 1.464629258517034e-05, "loss": 2.0469, "step": 70790 }, { "epoch": 1.16, "learning_rate": 1.464128256513026e-05, "loss": 2.0388, "step": 70800 }, { "epoch": 1.16, "learning_rate": 1.4636272545090182e-05, "loss": 2.0186, "step": 70810 }, { "epoch": 1.16, "learning_rate": 1.4631262525050102e-05, "loss": 2.0406, "step": 70820 }, { "epoch": 1.16, "learning_rate": 1.4626252505010021e-05, "loss": 2.0384, "step": 70830 }, { "epoch": 1.16, "learning_rate": 1.462124248496994e-05, "loss": 2.0286, "step": 70840 }, { "epoch": 1.16, "learning_rate": 1.4616232464929861e-05, "loss": 2.0304, "step": 70850 }, { "epoch": 1.16, "learning_rate": 1.461122244488978e-05, "loss": 2.0144, "step": 70860 }, { "epoch": 1.16, "learning_rate": 1.4606212424849699e-05, "loss": 1.9993, "step": 70870 }, { "epoch": 1.16, "learning_rate": 1.460120240480962e-05, "loss": 1.9991, "step": 70880 }, { "epoch": 1.16, "learning_rate": 1.4596192384769538e-05, "loss": 1.9903, "step": 70890 }, { "epoch": 1.16, "learning_rate": 1.459118236472946e-05, "loss": 2.0083, "step": 70900 }, { "epoch": 1.16, "learning_rate": 1.4586172344689381e-05, "loss": 2.0101, "step": 70910 }, { "epoch": 1.16, "learning_rate": 1.45811623246493e-05, "loss": 2.0502, "step": 70920 }, { "epoch": 1.16, "learning_rate": 1.457615230460922e-05, "loss": 2.0742, "step": 70930 }, { "epoch": 1.16, "learning_rate": 1.457114228456914e-05, "loss": 2.0121, "step": 70940 }, { "epoch": 1.16, "learning_rate": 1.4566132264529059e-05, "loss": 2.0535, "step": 70950 }, { "epoch": 1.16, "learning_rate": 1.4561122244488978e-05, "loss": 2.0159, "step": 70960 }, { "epoch": 1.16, "learning_rate": 1.4556112224448898e-05, "loss": 1.9869, "step": 70970 }, { "epoch": 1.16, "learning_rate": 1.4551102204408817e-05, "loss": 2.0421, "step": 70980 }, { "epoch": 1.16, "learning_rate": 1.4546092184368736e-05, "loss": 2.0056, "step": 70990 }, { "epoch": 1.16, "learning_rate": 1.4541082164328659e-05, "loss": 2.0178, "step": 71000 }, { "epoch": 1.16, "eval_loss": 2.0138649940490723, "eval_mean_f1": 0.661017397131326, "eval_rouge1_f1": 0.7189036352259678, "eval_rouge1_precision": 0.8289294556578272, "eval_rouge1_recall": 0.6674130512913348, "eval_rouge2_f1": 0.5773405459564755, "eval_rouge2_precision": 0.6706031476661366, "eval_rouge2_recall": 0.5357320629392252, "eval_rougeL_f1": 0.6868080102115346, "eval_rougeL_precision": 0.790094638992416, "eval_rougeL_recall": 0.6384645879175006, "eval_runtime": 64.7049, "eval_samples_per_second": 15.826, "eval_steps_per_second": 1.978, "step": 71000 }, { "epoch": 1.16, "learning_rate": 1.453607214428858e-05, "loss": 2.0834, "step": 71010 }, { "epoch": 1.16, "learning_rate": 1.4531062124248498e-05, "loss": 2.0217, "step": 71020 }, { "epoch": 1.16, "learning_rate": 1.4526052104208417e-05, "loss": 2.0314, "step": 71030 }, { "epoch": 1.16, "learning_rate": 1.4521042084168338e-05, "loss": 2.0046, "step": 71040 }, { "epoch": 1.16, "learning_rate": 1.4516032064128257e-05, "loss": 2.0581, "step": 71050 }, { "epoch": 1.16, "learning_rate": 1.4511022044088177e-05, "loss": 1.9722, "step": 71060 }, { "epoch": 1.16, "learning_rate": 1.4506012024048096e-05, "loss": 2.0182, "step": 71070 }, { "epoch": 1.16, "learning_rate": 1.4501002004008015e-05, "loss": 1.9972, "step": 71080 }, { "epoch": 1.16, "learning_rate": 1.4495991983967936e-05, "loss": 2.0296, "step": 71090 }, { "epoch": 1.16, "learning_rate": 1.4490981963927858e-05, "loss": 2.0207, "step": 71100 }, { "epoch": 1.16, "learning_rate": 1.4485971943887777e-05, "loss": 2.0619, "step": 71110 }, { "epoch": 1.16, "learning_rate": 1.4480961923847696e-05, "loss": 1.9892, "step": 71120 }, { "epoch": 1.16, "learning_rate": 1.4475951903807617e-05, "loss": 2.0064, "step": 71130 }, { "epoch": 1.16, "learning_rate": 1.4470941883767536e-05, "loss": 2.0268, "step": 71140 }, { "epoch": 1.16, "learning_rate": 1.4465931863727455e-05, "loss": 2.032, "step": 71150 }, { "epoch": 1.16, "learning_rate": 1.4460921843687375e-05, "loss": 1.991, "step": 71160 }, { "epoch": 1.16, "learning_rate": 1.4455911823647294e-05, "loss": 1.9818, "step": 71170 }, { "epoch": 1.16, "learning_rate": 1.4450901803607215e-05, "loss": 2.0287, "step": 71180 }, { "epoch": 1.16, "learning_rate": 1.4445891783567134e-05, "loss": 2.0041, "step": 71190 }, { "epoch": 1.16, "learning_rate": 1.4440881763527056e-05, "loss": 1.9964, "step": 71200 }, { "epoch": 1.16, "learning_rate": 1.4435871743486975e-05, "loss": 2.0223, "step": 71210 }, { "epoch": 1.16, "learning_rate": 1.4430861723446896e-05, "loss": 2.0707, "step": 71220 }, { "epoch": 1.16, "learning_rate": 1.4425851703406815e-05, "loss": 2.0024, "step": 71230 }, { "epoch": 1.16, "learning_rate": 1.4420841683366734e-05, "loss": 2.0141, "step": 71240 }, { "epoch": 1.16, "learning_rate": 1.4415831663326654e-05, "loss": 1.9943, "step": 71250 }, { "epoch": 1.16, "learning_rate": 1.4410821643286573e-05, "loss": 2.0117, "step": 71260 }, { "epoch": 1.16, "learning_rate": 1.4405811623246492e-05, "loss": 2.0077, "step": 71270 }, { "epoch": 1.16, "learning_rate": 1.4400801603206413e-05, "loss": 1.9838, "step": 71280 }, { "epoch": 1.16, "learning_rate": 1.4395791583166332e-05, "loss": 2.0336, "step": 71290 }, { "epoch": 1.17, "learning_rate": 1.4390781563126254e-05, "loss": 2.039, "step": 71300 }, { "epoch": 1.17, "learning_rate": 1.4385771543086173e-05, "loss": 2.0241, "step": 71310 }, { "epoch": 1.17, "learning_rate": 1.4380761523046094e-05, "loss": 2.0342, "step": 71320 }, { "epoch": 1.17, "learning_rate": 1.4375751503006013e-05, "loss": 2.0202, "step": 71330 }, { "epoch": 1.17, "learning_rate": 1.4370741482965933e-05, "loss": 2.0128, "step": 71340 }, { "epoch": 1.17, "learning_rate": 1.4365731462925852e-05, "loss": 1.9741, "step": 71350 }, { "epoch": 1.17, "learning_rate": 1.4360721442885771e-05, "loss": 1.9987, "step": 71360 }, { "epoch": 1.17, "learning_rate": 1.4355711422845692e-05, "loss": 1.9843, "step": 71370 }, { "epoch": 1.17, "learning_rate": 1.435070140280561e-05, "loss": 2.0675, "step": 71380 }, { "epoch": 1.17, "learning_rate": 1.434569138276553e-05, "loss": 1.9716, "step": 71390 }, { "epoch": 1.17, "learning_rate": 1.4340681362725452e-05, "loss": 1.9768, "step": 71400 }, { "epoch": 1.17, "learning_rate": 1.4335671342685373e-05, "loss": 2.0226, "step": 71410 }, { "epoch": 1.17, "learning_rate": 1.4330661322645292e-05, "loss": 1.9879, "step": 71420 }, { "epoch": 1.17, "learning_rate": 1.432565130260521e-05, "loss": 1.998, "step": 71430 }, { "epoch": 1.17, "learning_rate": 1.4320641282565131e-05, "loss": 2.0195, "step": 71440 }, { "epoch": 1.17, "learning_rate": 1.431563126252505e-05, "loss": 2.0346, "step": 71450 }, { "epoch": 1.17, "learning_rate": 1.4310621242484971e-05, "loss": 2.0624, "step": 71460 }, { "epoch": 1.17, "learning_rate": 1.430561122244489e-05, "loss": 2.0101, "step": 71470 }, { "epoch": 1.17, "learning_rate": 1.4300601202404809e-05, "loss": 2.0175, "step": 71480 }, { "epoch": 1.17, "learning_rate": 1.4295591182364731e-05, "loss": 1.9908, "step": 71490 }, { "epoch": 1.17, "learning_rate": 1.4290581162324652e-05, "loss": 2.0261, "step": 71500 }, { "epoch": 1.17, "learning_rate": 1.428557114228457e-05, "loss": 2.0675, "step": 71510 }, { "epoch": 1.17, "learning_rate": 1.428056112224449e-05, "loss": 2.034, "step": 71520 }, { "epoch": 1.17, "learning_rate": 1.427555110220441e-05, "loss": 2.0303, "step": 71530 }, { "epoch": 1.17, "learning_rate": 1.427054108216433e-05, "loss": 2.058, "step": 71540 }, { "epoch": 1.17, "learning_rate": 1.4265531062124248e-05, "loss": 2.0198, "step": 71550 }, { "epoch": 1.17, "learning_rate": 1.4260521042084169e-05, "loss": 2.0434, "step": 71560 }, { "epoch": 1.17, "learning_rate": 1.4255511022044088e-05, "loss": 2.0575, "step": 71570 }, { "epoch": 1.17, "learning_rate": 1.4250501002004007e-05, "loss": 1.9986, "step": 71580 }, { "epoch": 1.17, "learning_rate": 1.4245490981963929e-05, "loss": 2.0201, "step": 71590 }, { "epoch": 1.17, "learning_rate": 1.424048096192385e-05, "loss": 2.0099, "step": 71600 }, { "epoch": 1.17, "learning_rate": 1.4235470941883769e-05, "loss": 1.9697, "step": 71610 }, { "epoch": 1.17, "learning_rate": 1.423046092184369e-05, "loss": 1.9925, "step": 71620 }, { "epoch": 1.17, "learning_rate": 1.4225450901803608e-05, "loss": 2.0784, "step": 71630 }, { "epoch": 1.17, "learning_rate": 1.4220440881763527e-05, "loss": 1.9956, "step": 71640 }, { "epoch": 1.17, "learning_rate": 1.4215430861723448e-05, "loss": 1.9809, "step": 71650 }, { "epoch": 1.17, "learning_rate": 1.4210420841683367e-05, "loss": 2.0068, "step": 71660 }, { "epoch": 1.17, "learning_rate": 1.4205410821643286e-05, "loss": 2.0248, "step": 71670 }, { "epoch": 1.17, "learning_rate": 1.4200400801603206e-05, "loss": 2.0582, "step": 71680 }, { "epoch": 1.17, "learning_rate": 1.4195390781563129e-05, "loss": 2.0319, "step": 71690 }, { "epoch": 1.17, "learning_rate": 1.4190380761523048e-05, "loss": 1.9881, "step": 71700 }, { "epoch": 1.17, "learning_rate": 1.4185370741482967e-05, "loss": 2.0149, "step": 71710 }, { "epoch": 1.17, "learning_rate": 1.4180360721442887e-05, "loss": 2.0858, "step": 71720 }, { "epoch": 1.17, "learning_rate": 1.4175350701402806e-05, "loss": 2.0286, "step": 71730 }, { "epoch": 1.17, "learning_rate": 1.4170340681362727e-05, "loss": 2.0249, "step": 71740 }, { "epoch": 1.17, "learning_rate": 1.4165330661322646e-05, "loss": 2.0348, "step": 71750 }, { "epoch": 1.17, "learning_rate": 1.4160320641282565e-05, "loss": 2.0579, "step": 71760 }, { "epoch": 1.17, "learning_rate": 1.4155310621242485e-05, "loss": 1.9969, "step": 71770 }, { "epoch": 1.17, "learning_rate": 1.4150300601202404e-05, "loss": 2.0411, "step": 71780 }, { "epoch": 1.17, "learning_rate": 1.4145290581162327e-05, "loss": 2.0032, "step": 71790 }, { "epoch": 1.17, "learning_rate": 1.4140280561122246e-05, "loss": 2.0278, "step": 71800 }, { "epoch": 1.17, "learning_rate": 1.4135270541082166e-05, "loss": 2.0114, "step": 71810 }, { "epoch": 1.17, "learning_rate": 1.4130260521042085e-05, "loss": 1.9751, "step": 71820 }, { "epoch": 1.17, "learning_rate": 1.4125250501002004e-05, "loss": 2.0292, "step": 71830 }, { "epoch": 1.17, "learning_rate": 1.4120240480961925e-05, "loss": 2.0414, "step": 71840 }, { "epoch": 1.17, "learning_rate": 1.4115230460921844e-05, "loss": 2.0412, "step": 71850 }, { "epoch": 1.17, "learning_rate": 1.4110220440881763e-05, "loss": 2.0345, "step": 71860 }, { "epoch": 1.17, "learning_rate": 1.4105210420841683e-05, "loss": 1.9763, "step": 71870 }, { "epoch": 1.17, "learning_rate": 1.4100200400801602e-05, "loss": 2.0425, "step": 71880 }, { "epoch": 1.17, "learning_rate": 1.4095190380761525e-05, "loss": 1.9915, "step": 71890 }, { "epoch": 1.17, "learning_rate": 1.4090180360721445e-05, "loss": 2.0721, "step": 71900 }, { "epoch": 1.18, "learning_rate": 1.4085170340681364e-05, "loss": 2.0167, "step": 71910 }, { "epoch": 1.18, "learning_rate": 1.4080160320641283e-05, "loss": 2.0503, "step": 71920 }, { "epoch": 1.18, "learning_rate": 1.4075150300601204e-05, "loss": 2.0195, "step": 71930 }, { "epoch": 1.18, "learning_rate": 1.4070140280561123e-05, "loss": 1.9905, "step": 71940 }, { "epoch": 1.18, "learning_rate": 1.4065130260521042e-05, "loss": 2.0603, "step": 71950 }, { "epoch": 1.18, "learning_rate": 1.4060120240480962e-05, "loss": 2.004, "step": 71960 }, { "epoch": 1.18, "learning_rate": 1.4055110220440881e-05, "loss": 1.9963, "step": 71970 }, { "epoch": 1.18, "learning_rate": 1.4050100200400804e-05, "loss": 2.0158, "step": 71980 }, { "epoch": 1.18, "learning_rate": 1.4045090180360722e-05, "loss": 1.9822, "step": 71990 }, { "epoch": 1.18, "learning_rate": 1.4040080160320643e-05, "loss": 2.0196, "step": 72000 }, { "epoch": 1.18, "eval_loss": 2.0100769996643066, "eval_mean_f1": 0.660179378009313, "eval_rouge1_f1": 0.7195892134535127, "eval_rouge1_precision": 0.8306550159638539, "eval_rouge1_recall": 0.6675566317329433, "eval_rouge2_f1": 0.5745901396995847, "eval_rouge2_precision": 0.667885379323367, "eval_rouge2_recall": 0.5333758661014698, "eval_rougeL_f1": 0.6863587808748417, "eval_rougeL_precision": 0.791117923776399, "eval_rougeL_recall": 0.6378107957852461, "eval_runtime": 63.6381, "eval_samples_per_second": 16.091, "eval_steps_per_second": 2.011, "step": 72000 }, { "epoch": 1.18, "learning_rate": 1.4035070140280562e-05, "loss": 2.0099, "step": 72010 }, { "epoch": 1.18, "learning_rate": 1.4030060120240483e-05, "loss": 2.0414, "step": 72020 }, { "epoch": 1.18, "learning_rate": 1.4025050100200402e-05, "loss": 2.0376, "step": 72030 }, { "epoch": 1.18, "learning_rate": 1.402004008016032e-05, "loss": 2.0035, "step": 72040 }, { "epoch": 1.18, "learning_rate": 1.4015030060120241e-05, "loss": 2.0064, "step": 72050 }, { "epoch": 1.18, "learning_rate": 1.401002004008016e-05, "loss": 2.0415, "step": 72060 }, { "epoch": 1.18, "learning_rate": 1.4005010020040079e-05, "loss": 2.087, "step": 72070 }, { "epoch": 1.18, "learning_rate": 1.4000000000000001e-05, "loss": 2.0238, "step": 72080 }, { "epoch": 1.18, "learning_rate": 1.3994989979959922e-05, "loss": 2.0535, "step": 72090 }, { "epoch": 1.18, "learning_rate": 1.3989979959919841e-05, "loss": 2.0447, "step": 72100 }, { "epoch": 1.18, "learning_rate": 1.398496993987976e-05, "loss": 2.0027, "step": 72110 }, { "epoch": 1.18, "learning_rate": 1.397995991983968e-05, "loss": 2.0512, "step": 72120 }, { "epoch": 1.18, "learning_rate": 1.39749498997996e-05, "loss": 2.0265, "step": 72130 }, { "epoch": 1.18, "learning_rate": 1.3969939879759519e-05, "loss": 1.9977, "step": 72140 }, { "epoch": 1.18, "learning_rate": 1.396492985971944e-05, "loss": 2.0239, "step": 72150 }, { "epoch": 1.18, "learning_rate": 1.3959919839679358e-05, "loss": 1.9873, "step": 72160 }, { "epoch": 1.18, "learning_rate": 1.3954909819639279e-05, "loss": 2.0272, "step": 72170 }, { "epoch": 1.18, "learning_rate": 1.3949899799599201e-05, "loss": 2.0429, "step": 72180 }, { "epoch": 1.18, "learning_rate": 1.394488977955912e-05, "loss": 2.0295, "step": 72190 }, { "epoch": 1.18, "learning_rate": 1.3939879759519039e-05, "loss": 2.0273, "step": 72200 }, { "epoch": 1.18, "learning_rate": 1.393486973947896e-05, "loss": 2.0349, "step": 72210 }, { "epoch": 1.18, "learning_rate": 1.3929859719438879e-05, "loss": 2.0337, "step": 72220 }, { "epoch": 1.18, "learning_rate": 1.3924849699398798e-05, "loss": 2.0563, "step": 72230 }, { "epoch": 1.18, "learning_rate": 1.3919839679358718e-05, "loss": 2.0523, "step": 72240 }, { "epoch": 1.18, "learning_rate": 1.3914829659318637e-05, "loss": 2.0338, "step": 72250 }, { "epoch": 1.18, "learning_rate": 1.3909819639278556e-05, "loss": 2.0011, "step": 72260 }, { "epoch": 1.18, "learning_rate": 1.3904809619238477e-05, "loss": 2.0396, "step": 72270 }, { "epoch": 1.18, "learning_rate": 1.3899799599198399e-05, "loss": 1.9975, "step": 72280 }, { "epoch": 1.18, "learning_rate": 1.3894789579158318e-05, "loss": 2.0094, "step": 72290 }, { "epoch": 1.18, "learning_rate": 1.3889779559118239e-05, "loss": 2.0356, "step": 72300 }, { "epoch": 1.18, "learning_rate": 1.3884769539078158e-05, "loss": 1.9836, "step": 72310 }, { "epoch": 1.18, "learning_rate": 1.3879759519038077e-05, "loss": 2.046, "step": 72320 }, { "epoch": 1.18, "learning_rate": 1.3874749498997997e-05, "loss": 2.0114, "step": 72330 }, { "epoch": 1.18, "learning_rate": 1.3869739478957916e-05, "loss": 1.9882, "step": 72340 }, { "epoch": 1.18, "learning_rate": 1.3864729458917835e-05, "loss": 1.9991, "step": 72350 }, { "epoch": 1.18, "learning_rate": 1.3859719438877756e-05, "loss": 1.9915, "step": 72360 }, { "epoch": 1.18, "learning_rate": 1.3854709418837675e-05, "loss": 2.0038, "step": 72370 }, { "epoch": 1.18, "learning_rate": 1.3849699398797597e-05, "loss": 2.0445, "step": 72380 }, { "epoch": 1.18, "learning_rate": 1.3844689378757516e-05, "loss": 2.0256, "step": 72390 }, { "epoch": 1.18, "learning_rate": 1.3839679358717437e-05, "loss": 2.0491, "step": 72400 }, { "epoch": 1.18, "learning_rate": 1.3834669338677356e-05, "loss": 2.0234, "step": 72410 }, { "epoch": 1.18, "learning_rate": 1.3829659318637274e-05, "loss": 2.032, "step": 72420 }, { "epoch": 1.18, "learning_rate": 1.3824649298597195e-05, "loss": 1.975, "step": 72430 }, { "epoch": 1.18, "learning_rate": 1.3819639278557114e-05, "loss": 1.9611, "step": 72440 }, { "epoch": 1.18, "learning_rate": 1.3814629258517035e-05, "loss": 2.0289, "step": 72450 }, { "epoch": 1.18, "learning_rate": 1.3809619238476954e-05, "loss": 2.0258, "step": 72460 }, { "epoch": 1.18, "learning_rate": 1.3804609218436873e-05, "loss": 2.0435, "step": 72470 }, { "epoch": 1.18, "learning_rate": 1.3799599198396795e-05, "loss": 2.0111, "step": 72480 }, { "epoch": 1.18, "learning_rate": 1.3794589178356716e-05, "loss": 2.0584, "step": 72490 }, { "epoch": 1.18, "learning_rate": 1.3789579158316635e-05, "loss": 2.0215, "step": 72500 }, { "epoch": 1.18, "learning_rate": 1.3784569138276553e-05, "loss": 2.0154, "step": 72510 }, { "epoch": 1.18, "learning_rate": 1.3779559118236474e-05, "loss": 2.0178, "step": 72520 }, { "epoch": 1.19, "learning_rate": 1.3774549098196393e-05, "loss": 2.0258, "step": 72530 }, { "epoch": 1.19, "learning_rate": 1.3769539078156312e-05, "loss": 2.0667, "step": 72540 }, { "epoch": 1.19, "learning_rate": 1.3764529058116233e-05, "loss": 2.0645, "step": 72550 }, { "epoch": 1.19, "learning_rate": 1.3759519038076152e-05, "loss": 2.0011, "step": 72560 }, { "epoch": 1.19, "learning_rate": 1.3754509018036074e-05, "loss": 2.0369, "step": 72570 }, { "epoch": 1.19, "learning_rate": 1.3749498997995993e-05, "loss": 1.9801, "step": 72580 }, { "epoch": 1.19, "learning_rate": 1.3744488977955914e-05, "loss": 2.0042, "step": 72590 }, { "epoch": 1.19, "learning_rate": 1.3739478957915832e-05, "loss": 1.9794, "step": 72600 }, { "epoch": 1.19, "learning_rate": 1.3734468937875753e-05, "loss": 1.9838, "step": 72610 }, { "epoch": 1.19, "learning_rate": 1.3729458917835672e-05, "loss": 2.0258, "step": 72620 }, { "epoch": 1.19, "learning_rate": 1.3724448897795591e-05, "loss": 1.9914, "step": 72630 }, { "epoch": 1.19, "learning_rate": 1.3719438877755512e-05, "loss": 2.0051, "step": 72640 }, { "epoch": 1.19, "learning_rate": 1.371442885771543e-05, "loss": 2.0064, "step": 72650 }, { "epoch": 1.19, "learning_rate": 1.370941883767535e-05, "loss": 2.0355, "step": 72660 }, { "epoch": 1.19, "learning_rate": 1.3704408817635272e-05, "loss": 2.0547, "step": 72670 }, { "epoch": 1.19, "learning_rate": 1.3699398797595193e-05, "loss": 2.0176, "step": 72680 }, { "epoch": 1.19, "learning_rate": 1.3694388777555111e-05, "loss": 1.9885, "step": 72690 }, { "epoch": 1.19, "learning_rate": 1.368937875751503e-05, "loss": 1.9826, "step": 72700 }, { "epoch": 1.19, "learning_rate": 1.3684368737474951e-05, "loss": 2.0453, "step": 72710 }, { "epoch": 1.19, "learning_rate": 1.367935871743487e-05, "loss": 2.016, "step": 72720 }, { "epoch": 1.19, "learning_rate": 1.367434869739479e-05, "loss": 2.0111, "step": 72730 }, { "epoch": 1.19, "learning_rate": 1.366933867735471e-05, "loss": 2.019, "step": 72740 }, { "epoch": 1.19, "learning_rate": 1.3664328657314629e-05, "loss": 2.0397, "step": 72750 }, { "epoch": 1.19, "learning_rate": 1.365931863727455e-05, "loss": 2.0125, "step": 72760 }, { "epoch": 1.19, "learning_rate": 1.3654308617234472e-05, "loss": 2.0341, "step": 72770 }, { "epoch": 1.19, "learning_rate": 1.364929859719439e-05, "loss": 2.0137, "step": 72780 }, { "epoch": 1.19, "learning_rate": 1.364428857715431e-05, "loss": 2.0206, "step": 72790 }, { "epoch": 1.19, "learning_rate": 1.363927855711423e-05, "loss": 1.9922, "step": 72800 }, { "epoch": 1.19, "learning_rate": 1.3634268537074149e-05, "loss": 1.994, "step": 72810 }, { "epoch": 1.19, "learning_rate": 1.3629258517034068e-05, "loss": 2.0281, "step": 72820 }, { "epoch": 1.19, "learning_rate": 1.3624248496993989e-05, "loss": 2.0335, "step": 72830 }, { "epoch": 1.19, "learning_rate": 1.3619238476953908e-05, "loss": 2.0499, "step": 72840 }, { "epoch": 1.19, "learning_rate": 1.3614228456913826e-05, "loss": 2.0425, "step": 72850 }, { "epoch": 1.19, "learning_rate": 1.3609218436873747e-05, "loss": 2.0061, "step": 72860 }, { "epoch": 1.19, "learning_rate": 1.360420841683367e-05, "loss": 2.0051, "step": 72870 }, { "epoch": 1.19, "learning_rate": 1.3599198396793588e-05, "loss": 1.9917, "step": 72880 }, { "epoch": 1.19, "learning_rate": 1.3594188376753509e-05, "loss": 2.0372, "step": 72890 }, { "epoch": 1.19, "learning_rate": 1.3589178356713428e-05, "loss": 2.0021, "step": 72900 }, { "epoch": 1.19, "learning_rate": 1.3584168336673347e-05, "loss": 2.0607, "step": 72910 }, { "epoch": 1.19, "learning_rate": 1.3579158316633268e-05, "loss": 2.0867, "step": 72920 }, { "epoch": 1.19, "learning_rate": 1.3574148296593187e-05, "loss": 2.0467, "step": 72930 }, { "epoch": 1.19, "learning_rate": 1.3569138276553105e-05, "loss": 2.0553, "step": 72940 }, { "epoch": 1.19, "learning_rate": 1.3564128256513026e-05, "loss": 2.0216, "step": 72950 }, { "epoch": 1.19, "learning_rate": 1.3559118236472945e-05, "loss": 2.01, "step": 72960 }, { "epoch": 1.19, "learning_rate": 1.3554108216432867e-05, "loss": 2.016, "step": 72970 }, { "epoch": 1.19, "learning_rate": 1.3549098196392786e-05, "loss": 2.0118, "step": 72980 }, { "epoch": 1.19, "learning_rate": 1.3544088176352707e-05, "loss": 2.0339, "step": 72990 }, { "epoch": 1.19, "learning_rate": 1.3539078156312626e-05, "loss": 2.0146, "step": 73000 }, { "epoch": 1.19, "eval_loss": 2.0130953788757324, "eval_mean_f1": 0.6597163951699218, "eval_rouge1_f1": 0.7195384151366655, "eval_rouge1_precision": 0.829722533055052, "eval_rouge1_recall": 0.667761868685794, "eval_rouge2_f1": 0.5731860550826382, "eval_rouge2_precision": 0.6668970298364825, "eval_rouge2_recall": 0.5316143949080989, "eval_rougeL_f1": 0.6864247152904617, "eval_rougeL_precision": 0.7899602871645184, "eval_rougeL_recall": 0.6379079823690005, "eval_runtime": 63.2865, "eval_samples_per_second": 16.18, "eval_steps_per_second": 2.023, "step": 73000 }, { "epoch": 1.19, "learning_rate": 1.3534068136272547e-05, "loss": 1.9985, "step": 73010 }, { "epoch": 1.19, "learning_rate": 1.3529058116232466e-05, "loss": 1.9611, "step": 73020 }, { "epoch": 1.19, "learning_rate": 1.3524048096192384e-05, "loss": 2.0399, "step": 73030 }, { "epoch": 1.19, "learning_rate": 1.3519038076152305e-05, "loss": 2.0054, "step": 73040 }, { "epoch": 1.19, "learning_rate": 1.3514028056112224e-05, "loss": 2.0507, "step": 73050 }, { "epoch": 1.19, "learning_rate": 1.3509018036072143e-05, "loss": 1.968, "step": 73060 }, { "epoch": 1.19, "learning_rate": 1.3504008016032065e-05, "loss": 2.021, "step": 73070 }, { "epoch": 1.19, "learning_rate": 1.3498997995991986e-05, "loss": 2.0386, "step": 73080 }, { "epoch": 1.19, "learning_rate": 1.3493987975951905e-05, "loss": 2.0211, "step": 73090 }, { "epoch": 1.19, "learning_rate": 1.3488977955911824e-05, "loss": 2.0127, "step": 73100 }, { "epoch": 1.19, "learning_rate": 1.3483967935871745e-05, "loss": 2.0451, "step": 73110 }, { "epoch": 1.19, "learning_rate": 1.3478957915831663e-05, "loss": 1.9997, "step": 73120 }, { "epoch": 1.19, "learning_rate": 1.3473947895791582e-05, "loss": 1.9787, "step": 73130 }, { "epoch": 1.2, "learning_rate": 1.3468937875751503e-05, "loss": 2.0286, "step": 73140 }, { "epoch": 1.2, "learning_rate": 1.3463927855711422e-05, "loss": 2.0126, "step": 73150 }, { "epoch": 1.2, "learning_rate": 1.3458917835671344e-05, "loss": 2.0416, "step": 73160 }, { "epoch": 1.2, "learning_rate": 1.3453907815631265e-05, "loss": 1.999, "step": 73170 }, { "epoch": 1.2, "learning_rate": 1.3448897795591184e-05, "loss": 2.0008, "step": 73180 }, { "epoch": 1.2, "learning_rate": 1.3443887775551103e-05, "loss": 2.0124, "step": 73190 }, { "epoch": 1.2, "learning_rate": 1.3438877755511024e-05, "loss": 2.0502, "step": 73200 }, { "epoch": 1.2, "learning_rate": 1.3433867735470942e-05, "loss": 2.0296, "step": 73210 }, { "epoch": 1.2, "learning_rate": 1.3428857715430861e-05, "loss": 2.0133, "step": 73220 }, { "epoch": 1.2, "learning_rate": 1.3423847695390782e-05, "loss": 1.9994, "step": 73230 }, { "epoch": 1.2, "learning_rate": 1.3418837675350701e-05, "loss": 2.0009, "step": 73240 }, { "epoch": 1.2, "learning_rate": 1.341382765531062e-05, "loss": 1.9738, "step": 73250 }, { "epoch": 1.2, "learning_rate": 1.3408817635270542e-05, "loss": 2.0323, "step": 73260 }, { "epoch": 1.2, "learning_rate": 1.3403807615230463e-05, "loss": 2.0677, "step": 73270 }, { "epoch": 1.2, "learning_rate": 1.3398797595190382e-05, "loss": 2.0252, "step": 73280 }, { "epoch": 1.2, "learning_rate": 1.3393787575150303e-05, "loss": 1.9956, "step": 73290 }, { "epoch": 1.2, "learning_rate": 1.3388777555110221e-05, "loss": 2.0492, "step": 73300 }, { "epoch": 1.2, "learning_rate": 1.338376753507014e-05, "loss": 2.0328, "step": 73310 }, { "epoch": 1.2, "learning_rate": 1.3378757515030061e-05, "loss": 1.9786, "step": 73320 }, { "epoch": 1.2, "learning_rate": 1.337374749498998e-05, "loss": 2.0465, "step": 73330 }, { "epoch": 1.2, "learning_rate": 1.3368737474949899e-05, "loss": 2.0503, "step": 73340 }, { "epoch": 1.2, "learning_rate": 1.336372745490982e-05, "loss": 2.0497, "step": 73350 }, { "epoch": 1.2, "learning_rate": 1.3358717434869742e-05, "loss": 2.0012, "step": 73360 }, { "epoch": 1.2, "learning_rate": 1.3353707414829661e-05, "loss": 2.0607, "step": 73370 }, { "epoch": 1.2, "learning_rate": 1.334869739478958e-05, "loss": 2.0719, "step": 73380 }, { "epoch": 1.2, "learning_rate": 1.33436873747495e-05, "loss": 2.0347, "step": 73390 }, { "epoch": 1.2, "learning_rate": 1.333867735470942e-05, "loss": 2.0168, "step": 73400 }, { "epoch": 1.2, "learning_rate": 1.3333667334669338e-05, "loss": 2.0322, "step": 73410 }, { "epoch": 1.2, "learning_rate": 1.3328657314629259e-05, "loss": 2.0013, "step": 73420 }, { "epoch": 1.2, "learning_rate": 1.3323647294589178e-05, "loss": 2.0158, "step": 73430 }, { "epoch": 1.2, "learning_rate": 1.3318637274549099e-05, "loss": 2.0404, "step": 73440 }, { "epoch": 1.2, "learning_rate": 1.3313627254509018e-05, "loss": 2.035, "step": 73450 }, { "epoch": 1.2, "learning_rate": 1.330861723446894e-05, "loss": 2.0184, "step": 73460 }, { "epoch": 1.2, "learning_rate": 1.3303607214428859e-05, "loss": 2.0027, "step": 73470 }, { "epoch": 1.2, "learning_rate": 1.329859719438878e-05, "loss": 2.0269, "step": 73480 }, { "epoch": 1.2, "learning_rate": 1.3293587174348698e-05, "loss": 2.0376, "step": 73490 }, { "epoch": 1.2, "learning_rate": 1.3288577154308617e-05, "loss": 2.0625, "step": 73500 }, { "epoch": 1.2, "learning_rate": 1.3283567134268538e-05, "loss": 2.0388, "step": 73510 }, { "epoch": 1.2, "learning_rate": 1.3278557114228457e-05, "loss": 1.9997, "step": 73520 }, { "epoch": 1.2, "learning_rate": 1.3273547094188376e-05, "loss": 2.0285, "step": 73530 }, { "epoch": 1.2, "learning_rate": 1.3268537074148297e-05, "loss": 2.0335, "step": 73540 }, { "epoch": 1.2, "learning_rate": 1.3263527054108215e-05, "loss": 2.0404, "step": 73550 }, { "epoch": 1.2, "learning_rate": 1.3258517034068138e-05, "loss": 2.0614, "step": 73560 }, { "epoch": 1.2, "learning_rate": 1.3253507014028058e-05, "loss": 2.0171, "step": 73570 }, { "epoch": 1.2, "learning_rate": 1.3248496993987977e-05, "loss": 2.0395, "step": 73580 }, { "epoch": 1.2, "learning_rate": 1.3243486973947896e-05, "loss": 2.0221, "step": 73590 }, { "epoch": 1.2, "learning_rate": 1.3238476953907817e-05, "loss": 2.0012, "step": 73600 }, { "epoch": 1.2, "learning_rate": 1.3233466933867736e-05, "loss": 2.0147, "step": 73610 }, { "epoch": 1.2, "learning_rate": 1.3228456913827655e-05, "loss": 2.0116, "step": 73620 }, { "epoch": 1.2, "learning_rate": 1.3223446893787576e-05, "loss": 2.0065, "step": 73630 }, { "epoch": 1.2, "learning_rate": 1.3218436873747494e-05, "loss": 2.0514, "step": 73640 }, { "epoch": 1.2, "learning_rate": 1.3213426853707417e-05, "loss": 2.058, "step": 73650 }, { "epoch": 1.2, "learning_rate": 1.3208416833667336e-05, "loss": 2.0539, "step": 73660 }, { "epoch": 1.2, "learning_rate": 1.3203406813627256e-05, "loss": 2.0492, "step": 73670 }, { "epoch": 1.2, "learning_rate": 1.3198396793587175e-05, "loss": 1.9917, "step": 73680 }, { "epoch": 1.2, "learning_rate": 1.3193386773547094e-05, "loss": 1.9698, "step": 73690 }, { "epoch": 1.2, "learning_rate": 1.3188376753507015e-05, "loss": 2.0609, "step": 73700 }, { "epoch": 1.2, "learning_rate": 1.3183366733466934e-05, "loss": 2.0287, "step": 73710 }, { "epoch": 1.2, "learning_rate": 1.3178356713426855e-05, "loss": 2.035, "step": 73720 }, { "epoch": 1.2, "learning_rate": 1.3173346693386773e-05, "loss": 2.0131, "step": 73730 }, { "epoch": 1.2, "learning_rate": 1.3168336673346692e-05, "loss": 2.0165, "step": 73740 }, { "epoch": 1.21, "learning_rate": 1.3163326653306615e-05, "loss": 2.0004, "step": 73750 }, { "epoch": 1.21, "learning_rate": 1.3158316633266535e-05, "loss": 2.0214, "step": 73760 }, { "epoch": 1.21, "learning_rate": 1.3153306613226454e-05, "loss": 2.0344, "step": 73770 }, { "epoch": 1.21, "learning_rate": 1.3148296593186373e-05, "loss": 2.0019, "step": 73780 }, { "epoch": 1.21, "learning_rate": 1.3143286573146294e-05, "loss": 2.0506, "step": 73790 }, { "epoch": 1.21, "learning_rate": 1.3138276553106213e-05, "loss": 2.0506, "step": 73800 }, { "epoch": 1.21, "learning_rate": 1.3133266533066132e-05, "loss": 2.0312, "step": 73810 }, { "epoch": 1.21, "learning_rate": 1.3128256513026052e-05, "loss": 2.007, "step": 73820 }, { "epoch": 1.21, "learning_rate": 1.3123246492985971e-05, "loss": 2.0208, "step": 73830 }, { "epoch": 1.21, "learning_rate": 1.311823647294589e-05, "loss": 2.005, "step": 73840 }, { "epoch": 1.21, "learning_rate": 1.3113226452905813e-05, "loss": 2.0108, "step": 73850 }, { "epoch": 1.21, "learning_rate": 1.3108216432865733e-05, "loss": 2.0096, "step": 73860 }, { "epoch": 1.21, "learning_rate": 1.3103206412825652e-05, "loss": 2.0095, "step": 73870 }, { "epoch": 1.21, "learning_rate": 1.3098196392785573e-05, "loss": 2.0253, "step": 73880 }, { "epoch": 1.21, "learning_rate": 1.3093186372745492e-05, "loss": 2.0057, "step": 73890 }, { "epoch": 1.21, "learning_rate": 1.308817635270541e-05, "loss": 2.0322, "step": 73900 }, { "epoch": 1.21, "learning_rate": 1.3083166332665331e-05, "loss": 2.0542, "step": 73910 }, { "epoch": 1.21, "learning_rate": 1.307815631262525e-05, "loss": 1.9822, "step": 73920 }, { "epoch": 1.21, "learning_rate": 1.307314629258517e-05, "loss": 2.0021, "step": 73930 }, { "epoch": 1.21, "learning_rate": 1.306813627254509e-05, "loss": 2.038, "step": 73940 }, { "epoch": 1.21, "learning_rate": 1.3063126252505012e-05, "loss": 2.0088, "step": 73950 }, { "epoch": 1.21, "learning_rate": 1.3058116232464931e-05, "loss": 2.0151, "step": 73960 }, { "epoch": 1.21, "learning_rate": 1.305310621242485e-05, "loss": 1.9822, "step": 73970 }, { "epoch": 1.21, "learning_rate": 1.3048096192384771e-05, "loss": 2.0232, "step": 73980 }, { "epoch": 1.21, "learning_rate": 1.304308617234469e-05, "loss": 2.0349, "step": 73990 }, { "epoch": 1.21, "learning_rate": 1.303807615230461e-05, "loss": 2.0184, "step": 74000 }, { "epoch": 1.21, "eval_loss": 2.0097692012786865, "eval_mean_f1": 0.6646216192498834, "eval_rouge1_f1": 0.7220185608438462, "eval_rouge1_precision": 0.8346161447601874, "eval_rouge1_recall": 0.6690054456467927, "eval_rouge2_f1": 0.5807248431435668, "eval_rouge2_precision": 0.6764173407972236, "eval_rouge2_recall": 0.5385376304132905, "eval_rougeL_f1": 0.6911214537622372, "eval_rougeL_precision": 0.7960359419720775, "eval_rougeL_recall": 0.6413354514471254, "eval_runtime": 64.307, "eval_samples_per_second": 15.924, "eval_steps_per_second": 1.99, "step": 74000 }, { "epoch": 1.21, "learning_rate": 1.303306613226453e-05, "loss": 2.0378, "step": 74010 }, { "epoch": 1.21, "learning_rate": 1.3028056112224448e-05, "loss": 2.0014, "step": 74020 }, { "epoch": 1.21, "learning_rate": 1.3023046092184369e-05, "loss": 1.9869, "step": 74030 }, { "epoch": 1.21, "learning_rate": 1.3018036072144288e-05, "loss": 2.0394, "step": 74040 }, { "epoch": 1.21, "learning_rate": 1.301302605210421e-05, "loss": 1.9859, "step": 74050 }, { "epoch": 1.21, "learning_rate": 1.300801603206413e-05, "loss": 2.0218, "step": 74060 }, { "epoch": 1.21, "learning_rate": 1.300300601202405e-05, "loss": 1.9998, "step": 74070 }, { "epoch": 1.21, "learning_rate": 1.2997995991983969e-05, "loss": 1.9743, "step": 74080 }, { "epoch": 1.21, "learning_rate": 1.2992985971943888e-05, "loss": 2.0281, "step": 74090 }, { "epoch": 1.21, "learning_rate": 1.2987975951903808e-05, "loss": 1.9929, "step": 74100 }, { "epoch": 1.21, "learning_rate": 1.2982965931863727e-05, "loss": 1.9933, "step": 74110 }, { "epoch": 1.21, "learning_rate": 1.2977955911823646e-05, "loss": 2.0092, "step": 74120 }, { "epoch": 1.21, "learning_rate": 1.2972945891783567e-05, "loss": 2.0039, "step": 74130 }, { "epoch": 1.21, "learning_rate": 1.2967935871743486e-05, "loss": 2.0079, "step": 74140 }, { "epoch": 1.21, "learning_rate": 1.2962925851703408e-05, "loss": 2.0131, "step": 74150 }, { "epoch": 1.21, "learning_rate": 1.2957915831663329e-05, "loss": 2.0148, "step": 74160 }, { "epoch": 1.21, "learning_rate": 1.2952905811623248e-05, "loss": 2.0532, "step": 74170 }, { "epoch": 1.21, "learning_rate": 1.2947895791583167e-05, "loss": 2.041, "step": 74180 }, { "epoch": 1.21, "learning_rate": 1.2942885771543087e-05, "loss": 1.9858, "step": 74190 }, { "epoch": 1.21, "learning_rate": 1.2937875751503006e-05, "loss": 2.0046, "step": 74200 }, { "epoch": 1.21, "learning_rate": 1.2932865731462925e-05, "loss": 2.0014, "step": 74210 }, { "epoch": 1.21, "learning_rate": 1.2927855711422846e-05, "loss": 2.0453, "step": 74220 }, { "epoch": 1.21, "learning_rate": 1.2922845691382765e-05, "loss": 2.0163, "step": 74230 }, { "epoch": 1.21, "learning_rate": 1.2917835671342687e-05, "loss": 1.9922, "step": 74240 }, { "epoch": 1.21, "learning_rate": 1.2912825651302606e-05, "loss": 2.0112, "step": 74250 }, { "epoch": 1.21, "learning_rate": 1.2907815631262527e-05, "loss": 1.9961, "step": 74260 }, { "epoch": 1.21, "learning_rate": 1.2902805611222446e-05, "loss": 1.9936, "step": 74270 }, { "epoch": 1.21, "learning_rate": 1.2897795591182366e-05, "loss": 2.0054, "step": 74280 }, { "epoch": 1.21, "learning_rate": 1.2892785571142285e-05, "loss": 2.0445, "step": 74290 }, { "epoch": 1.21, "learning_rate": 1.2887775551102204e-05, "loss": 2.0526, "step": 74300 }, { "epoch": 1.21, "learning_rate": 1.2882765531062125e-05, "loss": 2.0886, "step": 74310 }, { "epoch": 1.21, "learning_rate": 1.2877755511022044e-05, "loss": 1.9884, "step": 74320 }, { "epoch": 1.21, "learning_rate": 1.2872745490981963e-05, "loss": 2.0283, "step": 74330 }, { "epoch": 1.21, "learning_rate": 1.2867735470941885e-05, "loss": 1.999, "step": 74340 }, { "epoch": 1.21, "learning_rate": 1.2862725450901806e-05, "loss": 2.0157, "step": 74350 }, { "epoch": 1.22, "learning_rate": 1.2857715430861725e-05, "loss": 2.0357, "step": 74360 }, { "epoch": 1.22, "learning_rate": 1.2852705410821644e-05, "loss": 1.9832, "step": 74370 }, { "epoch": 1.22, "learning_rate": 1.2847695390781564e-05, "loss": 2.0501, "step": 74380 }, { "epoch": 1.22, "learning_rate": 1.2842685370741483e-05, "loss": 2.0131, "step": 74390 }, { "epoch": 1.22, "learning_rate": 1.2837675350701402e-05, "loss": 2.0545, "step": 74400 }, { "epoch": 1.22, "learning_rate": 1.2832665330661323e-05, "loss": 2.0421, "step": 74410 }, { "epoch": 1.22, "learning_rate": 1.2827655310621242e-05, "loss": 2.0114, "step": 74420 }, { "epoch": 1.22, "learning_rate": 1.2822645290581162e-05, "loss": 1.997, "step": 74430 }, { "epoch": 1.22, "learning_rate": 1.2817635270541085e-05, "loss": 2.0083, "step": 74440 }, { "epoch": 1.22, "learning_rate": 1.2812625250501004e-05, "loss": 1.9843, "step": 74450 }, { "epoch": 1.22, "learning_rate": 1.2807615230460923e-05, "loss": 2.0023, "step": 74460 }, { "epoch": 1.22, "learning_rate": 1.2802605210420843e-05, "loss": 1.9887, "step": 74470 }, { "epoch": 1.22, "learning_rate": 1.2797595190380762e-05, "loss": 1.9906, "step": 74480 }, { "epoch": 1.22, "learning_rate": 1.2792585170340681e-05, "loss": 2.0327, "step": 74490 }, { "epoch": 1.22, "learning_rate": 1.2787575150300602e-05, "loss": 1.9836, "step": 74500 }, { "epoch": 1.22, "learning_rate": 1.278256513026052e-05, "loss": 2.0309, "step": 74510 }, { "epoch": 1.22, "learning_rate": 1.277755511022044e-05, "loss": 1.9643, "step": 74520 }, { "epoch": 1.22, "learning_rate": 1.277254509018036e-05, "loss": 2.021, "step": 74530 }, { "epoch": 1.22, "learning_rate": 1.2767535070140283e-05, "loss": 1.9715, "step": 74540 }, { "epoch": 1.22, "learning_rate": 1.276302605210421e-05, "loss": 2.0013, "step": 74550 }, { "epoch": 1.22, "learning_rate": 1.275801603206413e-05, "loss": 2.0488, "step": 74560 }, { "epoch": 1.22, "learning_rate": 1.2753006012024049e-05, "loss": 2.0383, "step": 74570 }, { "epoch": 1.22, "learning_rate": 1.2747995991983968e-05, "loss": 2.0294, "step": 74580 }, { "epoch": 1.22, "learning_rate": 1.2742985971943888e-05, "loss": 2.0025, "step": 74590 }, { "epoch": 1.22, "learning_rate": 1.2737975951903807e-05, "loss": 1.9957, "step": 74600 }, { "epoch": 1.22, "learning_rate": 1.2732965931863728e-05, "loss": 2.0353, "step": 74610 }, { "epoch": 1.22, "learning_rate": 1.2727955911823647e-05, "loss": 2.0156, "step": 74620 }, { "epoch": 1.22, "learning_rate": 1.2722945891783566e-05, "loss": 2.0192, "step": 74630 }, { "epoch": 1.22, "learning_rate": 1.2717935871743488e-05, "loss": 2.0049, "step": 74640 }, { "epoch": 1.22, "learning_rate": 1.2712925851703409e-05, "loss": 2.0149, "step": 74650 }, { "epoch": 1.22, "learning_rate": 1.2707915831663328e-05, "loss": 2.0612, "step": 74660 }, { "epoch": 1.22, "learning_rate": 1.2702905811623247e-05, "loss": 2.0054, "step": 74670 }, { "epoch": 1.22, "learning_rate": 1.2697895791583167e-05, "loss": 2.0343, "step": 74680 }, { "epoch": 1.22, "learning_rate": 1.2692885771543086e-05, "loss": 2.0124, "step": 74690 }, { "epoch": 1.22, "learning_rate": 1.2687875751503005e-05, "loss": 2.0772, "step": 74700 }, { "epoch": 1.22, "learning_rate": 1.2682865731462926e-05, "loss": 2.0281, "step": 74710 }, { "epoch": 1.22, "learning_rate": 1.2677855711422845e-05, "loss": 2.0485, "step": 74720 }, { "epoch": 1.22, "learning_rate": 1.2672845691382766e-05, "loss": 2.0211, "step": 74730 }, { "epoch": 1.22, "learning_rate": 1.2667835671342688e-05, "loss": 2.0645, "step": 74740 }, { "epoch": 1.22, "learning_rate": 1.2662825651302607e-05, "loss": 2.0354, "step": 74750 }, { "epoch": 1.22, "learning_rate": 1.2657815631262526e-05, "loss": 2.0478, "step": 74760 }, { "epoch": 1.22, "learning_rate": 1.2652805611222446e-05, "loss": 2.0146, "step": 74770 }, { "epoch": 1.22, "learning_rate": 1.2647795591182365e-05, "loss": 2.0462, "step": 74780 }, { "epoch": 1.22, "learning_rate": 1.2642785571142284e-05, "loss": 2.031, "step": 74790 }, { "epoch": 1.22, "learning_rate": 1.2637775551102205e-05, "loss": 2.0008, "step": 74800 }, { "epoch": 1.22, "learning_rate": 1.2632765531062124e-05, "loss": 2.0312, "step": 74810 }, { "epoch": 1.22, "learning_rate": 1.2627755511022043e-05, "loss": 2.0158, "step": 74820 }, { "epoch": 1.22, "learning_rate": 1.2622745490981965e-05, "loss": 2.0357, "step": 74830 }, { "epoch": 1.22, "learning_rate": 1.2617735470941886e-05, "loss": 2.0333, "step": 74840 }, { "epoch": 1.22, "learning_rate": 1.2612725450901805e-05, "loss": 2.0292, "step": 74850 }, { "epoch": 1.22, "learning_rate": 1.2607715430861724e-05, "loss": 2.038, "step": 74860 }, { "epoch": 1.22, "learning_rate": 1.2602705410821644e-05, "loss": 2.0125, "step": 74870 }, { "epoch": 1.22, "learning_rate": 1.2597695390781563e-05, "loss": 2.0249, "step": 74880 }, { "epoch": 1.22, "learning_rate": 1.2592685370741484e-05, "loss": 2.0119, "step": 74890 }, { "epoch": 1.22, "learning_rate": 1.2587675350701403e-05, "loss": 1.9928, "step": 74900 }, { "epoch": 1.22, "learning_rate": 1.2582665330661322e-05, "loss": 2.0219, "step": 74910 }, { "epoch": 1.22, "learning_rate": 1.2577655310621243e-05, "loss": 1.9712, "step": 74920 }, { "epoch": 1.22, "learning_rate": 1.2572645290581165e-05, "loss": 1.9882, "step": 74930 }, { "epoch": 1.22, "learning_rate": 1.2567635270541084e-05, "loss": 2.0165, "step": 74940 }, { "epoch": 1.22, "learning_rate": 1.2562625250501003e-05, "loss": 2.0289, "step": 74950 }, { "epoch": 1.22, "learning_rate": 1.2557615230460923e-05, "loss": 2.0067, "step": 74960 }, { "epoch": 1.23, "learning_rate": 1.2552605210420842e-05, "loss": 2.0264, "step": 74970 }, { "epoch": 1.23, "learning_rate": 1.2547595190380761e-05, "loss": 2.0038, "step": 74980 }, { "epoch": 1.23, "learning_rate": 1.2542585170340682e-05, "loss": 2.0125, "step": 74990 }, { "epoch": 1.23, "learning_rate": 1.2537575150300601e-05, "loss": 2.037, "step": 75000 }, { "epoch": 1.23, "eval_loss": 2.0087814331054688, "eval_mean_f1": 0.6624429764979736, "eval_rouge1_f1": 0.7192070809019897, "eval_rouge1_precision": 0.8306453229818196, "eval_rouge1_recall": 0.6671097897717384, "eval_rouge2_f1": 0.5802219441285945, "eval_rouge2_precision": 0.6750288780501188, "eval_rouge2_recall": 0.538212569903114, "eval_rougeL_f1": 0.6878999044633364, "eval_rougeL_precision": 0.7930406249311346, "eval_rougeL_recall": 0.6391202734899332, "eval_runtime": 63.5689, "eval_samples_per_second": 16.109, "eval_steps_per_second": 2.014, "step": 75000 }, { "epoch": 1.23, "learning_rate": 1.2532565130260522e-05, "loss": 1.9964, "step": 75010 }, { "epoch": 1.23, "learning_rate": 1.252755511022044e-05, "loss": 1.9848, "step": 75020 }, { "epoch": 1.23, "learning_rate": 1.2522545090180363e-05, "loss": 1.9951, "step": 75030 }, { "epoch": 1.23, "learning_rate": 1.2517535070140282e-05, "loss": 1.9885, "step": 75040 }, { "epoch": 1.23, "learning_rate": 1.2512525050100202e-05, "loss": 2.017, "step": 75050 }, { "epoch": 1.23, "learning_rate": 1.2507515030060121e-05, "loss": 2.0381, "step": 75060 }, { "epoch": 1.23, "learning_rate": 1.250250501002004e-05, "loss": 2.0144, "step": 75070 }, { "epoch": 1.23, "learning_rate": 1.2497494989979961e-05, "loss": 2.0078, "step": 75080 }, { "epoch": 1.23, "learning_rate": 1.249248496993988e-05, "loss": 2.0355, "step": 75090 }, { "epoch": 1.23, "learning_rate": 1.24874749498998e-05, "loss": 2.0406, "step": 75100 }, { "epoch": 1.23, "learning_rate": 1.2482464929859721e-05, "loss": 2.0201, "step": 75110 }, { "epoch": 1.23, "learning_rate": 1.247745490981964e-05, "loss": 2.0377, "step": 75120 }, { "epoch": 1.23, "learning_rate": 1.2472444889779559e-05, "loss": 2.04, "step": 75130 }, { "epoch": 1.23, "learning_rate": 1.246743486973948e-05, "loss": 2.024, "step": 75140 }, { "epoch": 1.23, "learning_rate": 1.24624248496994e-05, "loss": 2.0205, "step": 75150 }, { "epoch": 1.23, "learning_rate": 1.245741482965932e-05, "loss": 2.0126, "step": 75160 }, { "epoch": 1.23, "learning_rate": 1.245240480961924e-05, "loss": 2.0165, "step": 75170 }, { "epoch": 1.23, "learning_rate": 1.2447394789579159e-05, "loss": 2.0473, "step": 75180 }, { "epoch": 1.23, "learning_rate": 1.2442384769539078e-05, "loss": 1.9959, "step": 75190 }, { "epoch": 1.23, "learning_rate": 1.2437374749498998e-05, "loss": 2.0235, "step": 75200 }, { "epoch": 1.23, "learning_rate": 1.2432364729458919e-05, "loss": 2.0269, "step": 75210 }, { "epoch": 1.23, "learning_rate": 1.2427354709418838e-05, "loss": 2.0032, "step": 75220 }, { "epoch": 1.23, "learning_rate": 1.2422344689378759e-05, "loss": 2.0127, "step": 75230 }, { "epoch": 1.23, "learning_rate": 1.2417334669338678e-05, "loss": 2.0028, "step": 75240 }, { "epoch": 1.23, "learning_rate": 1.2412324649298598e-05, "loss": 2.0005, "step": 75250 }, { "epoch": 1.23, "learning_rate": 1.2407314629258517e-05, "loss": 2.026, "step": 75260 }, { "epoch": 1.23, "learning_rate": 1.2402304609218438e-05, "loss": 1.9974, "step": 75270 }, { "epoch": 1.23, "learning_rate": 1.2397294589178357e-05, "loss": 2.0285, "step": 75280 }, { "epoch": 1.23, "learning_rate": 1.2392284569138277e-05, "loss": 2.024, "step": 75290 }, { "epoch": 1.23, "learning_rate": 1.2387274549098198e-05, "loss": 2.051, "step": 75300 }, { "epoch": 1.23, "learning_rate": 1.2382264529058117e-05, "loss": 1.9863, "step": 75310 }, { "epoch": 1.23, "learning_rate": 1.2377254509018036e-05, "loss": 2.0035, "step": 75320 }, { "epoch": 1.23, "learning_rate": 1.2372244488977957e-05, "loss": 1.9825, "step": 75330 }, { "epoch": 1.23, "learning_rate": 1.2367234468937876e-05, "loss": 2.0185, "step": 75340 }, { "epoch": 1.23, "learning_rate": 1.2362224448897796e-05, "loss": 2.0173, "step": 75350 }, { "epoch": 1.23, "learning_rate": 1.2357214428857717e-05, "loss": 1.9937, "step": 75360 }, { "epoch": 1.23, "learning_rate": 1.2352204408817636e-05, "loss": 1.9895, "step": 75370 }, { "epoch": 1.23, "learning_rate": 1.2347194388777555e-05, "loss": 2.035, "step": 75380 }, { "epoch": 1.23, "learning_rate": 1.2342184368737475e-05, "loss": 2.0186, "step": 75390 }, { "epoch": 1.23, "learning_rate": 1.2337174348697396e-05, "loss": 2.009, "step": 75400 }, { "epoch": 1.23, "learning_rate": 1.2332164328657315e-05, "loss": 2.0107, "step": 75410 }, { "epoch": 1.23, "learning_rate": 1.2327154308617236e-05, "loss": 2.008, "step": 75420 }, { "epoch": 1.23, "learning_rate": 1.2322144288577155e-05, "loss": 2.0032, "step": 75430 }, { "epoch": 1.23, "learning_rate": 1.2317134268537074e-05, "loss": 1.9989, "step": 75440 }, { "epoch": 1.23, "learning_rate": 1.2312124248496996e-05, "loss": 1.9925, "step": 75450 }, { "epoch": 1.23, "learning_rate": 1.2307114228456915e-05, "loss": 2.0371, "step": 75460 }, { "epoch": 1.23, "learning_rate": 1.2302104208416834e-05, "loss": 2.046, "step": 75470 }, { "epoch": 1.23, "learning_rate": 1.2297094188376754e-05, "loss": 2.0183, "step": 75480 }, { "epoch": 1.23, "learning_rate": 1.2292084168336673e-05, "loss": 2.0119, "step": 75490 }, { "epoch": 1.23, "learning_rate": 1.2287074148296594e-05, "loss": 2.0021, "step": 75500 }, { "epoch": 1.23, "learning_rate": 1.2282064128256515e-05, "loss": 2.0158, "step": 75510 }, { "epoch": 1.23, "learning_rate": 1.2277054108216434e-05, "loss": 2.0317, "step": 75520 }, { "epoch": 1.23, "learning_rate": 1.2272044088176353e-05, "loss": 1.9941, "step": 75530 }, { "epoch": 1.23, "learning_rate": 1.2267034068136273e-05, "loss": 2.0064, "step": 75540 }, { "epoch": 1.23, "learning_rate": 1.2262024048096194e-05, "loss": 2.0594, "step": 75550 }, { "epoch": 1.23, "learning_rate": 1.2257014028056113e-05, "loss": 2.0563, "step": 75560 }, { "epoch": 1.23, "learning_rate": 1.2252004008016033e-05, "loss": 1.9952, "step": 75570 }, { "epoch": 1.23, "learning_rate": 1.2246993987975952e-05, "loss": 1.9835, "step": 75580 }, { "epoch": 1.24, "learning_rate": 1.2241983967935871e-05, "loss": 2.0286, "step": 75590 }, { "epoch": 1.24, "learning_rate": 1.2236973947895792e-05, "loss": 2.0202, "step": 75600 }, { "epoch": 1.24, "learning_rate": 1.2231963927855713e-05, "loss": 2.0563, "step": 75610 }, { "epoch": 1.24, "learning_rate": 1.2226953907815632e-05, "loss": 2.0367, "step": 75620 }, { "epoch": 1.24, "learning_rate": 1.222194388777555e-05, "loss": 2.02, "step": 75630 }, { "epoch": 1.24, "learning_rate": 1.2216933867735473e-05, "loss": 1.9753, "step": 75640 }, { "epoch": 1.24, "learning_rate": 1.2211923847695392e-05, "loss": 2.0239, "step": 75650 }, { "epoch": 1.24, "learning_rate": 1.220691382765531e-05, "loss": 2.0327, "step": 75660 }, { "epoch": 1.24, "learning_rate": 1.2201903807615231e-05, "loss": 2.0021, "step": 75670 }, { "epoch": 1.24, "learning_rate": 1.219689378757515e-05, "loss": 2.0546, "step": 75680 }, { "epoch": 1.24, "learning_rate": 1.2191883767535071e-05, "loss": 2.0234, "step": 75690 }, { "epoch": 1.24, "learning_rate": 1.2186873747494992e-05, "loss": 2.0088, "step": 75700 }, { "epoch": 1.24, "learning_rate": 1.218186372745491e-05, "loss": 1.9871, "step": 75710 }, { "epoch": 1.24, "learning_rate": 1.217685370741483e-05, "loss": 2.0047, "step": 75720 }, { "epoch": 1.24, "learning_rate": 1.217184368737475e-05, "loss": 2.0307, "step": 75730 }, { "epoch": 1.24, "learning_rate": 1.216683366733467e-05, "loss": 2.0124, "step": 75740 }, { "epoch": 1.24, "learning_rate": 1.216182364729459e-05, "loss": 1.9964, "step": 75750 }, { "epoch": 1.24, "learning_rate": 1.215681362725451e-05, "loss": 2.0445, "step": 75760 }, { "epoch": 1.24, "learning_rate": 1.215180360721443e-05, "loss": 2.0019, "step": 75770 }, { "epoch": 1.24, "learning_rate": 1.2146793587174348e-05, "loss": 2.0135, "step": 75780 }, { "epoch": 1.24, "learning_rate": 1.214178356713427e-05, "loss": 2.0295, "step": 75790 }, { "epoch": 1.24, "learning_rate": 1.213677354709419e-05, "loss": 1.9936, "step": 75800 }, { "epoch": 1.24, "learning_rate": 1.2131763527054108e-05, "loss": 2.0311, "step": 75810 }, { "epoch": 1.24, "learning_rate": 1.2126753507014029e-05, "loss": 2.0554, "step": 75820 }, { "epoch": 1.24, "learning_rate": 1.2121743486973948e-05, "loss": 2.0084, "step": 75830 }, { "epoch": 1.24, "learning_rate": 1.2116733466933869e-05, "loss": 1.9924, "step": 75840 }, { "epoch": 1.24, "learning_rate": 1.2111723446893788e-05, "loss": 2.0461, "step": 75850 }, { "epoch": 1.24, "learning_rate": 1.2106713426853708e-05, "loss": 1.9905, "step": 75860 }, { "epoch": 1.24, "learning_rate": 1.2101703406813627e-05, "loss": 1.9835, "step": 75870 }, { "epoch": 1.24, "learning_rate": 1.2096693386773548e-05, "loss": 1.9994, "step": 75880 }, { "epoch": 1.24, "learning_rate": 1.2091683366733468e-05, "loss": 2.045, "step": 75890 }, { "epoch": 1.24, "learning_rate": 1.2086673346693387e-05, "loss": 1.9868, "step": 75900 }, { "epoch": 1.24, "learning_rate": 1.2081663326653306e-05, "loss": 2.0059, "step": 75910 }, { "epoch": 1.24, "learning_rate": 1.2076653306613227e-05, "loss": 2.0016, "step": 75920 }, { "epoch": 1.24, "learning_rate": 1.2071643286573146e-05, "loss": 2.0312, "step": 75930 }, { "epoch": 1.24, "learning_rate": 1.2066633266533067e-05, "loss": 2.0243, "step": 75940 }, { "epoch": 1.24, "learning_rate": 1.2061623246492987e-05, "loss": 2.0048, "step": 75950 }, { "epoch": 1.24, "learning_rate": 1.2056613226452906e-05, "loss": 1.998, "step": 75960 }, { "epoch": 1.24, "learning_rate": 1.2051603206412825e-05, "loss": 1.9944, "step": 75970 }, { "epoch": 1.24, "learning_rate": 1.2046593186372746e-05, "loss": 2.024, "step": 75980 }, { "epoch": 1.24, "learning_rate": 1.2041583166332666e-05, "loss": 2.054, "step": 75990 }, { "epoch": 1.24, "learning_rate": 1.2036573146292585e-05, "loss": 2.0223, "step": 76000 }, { "epoch": 1.24, "eval_loss": 2.0063748359680176, "eval_mean_f1": 0.6598910981081781, "eval_rouge1_f1": 0.7168399139946303, "eval_rouge1_precision": 0.8281507901262471, "eval_rouge1_recall": 0.6650763549284331, "eval_rouge2_f1": 0.5762890559869195, "eval_rouge2_precision": 0.6697518193611945, "eval_rouge2_recall": 0.5349740733201613, "eval_rougeL_f1": 0.6865443243429845, "eval_rougeL_precision": 0.7910047833121991, "eval_rougeL_recall": 0.6383016437745748, "eval_runtime": 63.7859, "eval_samples_per_second": 16.054, "eval_steps_per_second": 2.007, "step": 76000 }, { "epoch": 1.24, "learning_rate": 1.2031563126252506e-05, "loss": 2.004, "step": 76010 }, { "epoch": 1.24, "learning_rate": 1.2026553106212425e-05, "loss": 1.9899, "step": 76020 }, { "epoch": 1.24, "learning_rate": 1.2021543086172344e-05, "loss": 1.9757, "step": 76030 }, { "epoch": 1.24, "learning_rate": 1.2016533066132266e-05, "loss": 2.0368, "step": 76040 }, { "epoch": 1.24, "learning_rate": 1.2011523046092185e-05, "loss": 2.0404, "step": 76050 }, { "epoch": 1.24, "learning_rate": 1.2006513026052104e-05, "loss": 1.9797, "step": 76060 }, { "epoch": 1.24, "learning_rate": 1.2001503006012025e-05, "loss": 1.9915, "step": 76070 }, { "epoch": 1.24, "learning_rate": 1.1996492985971944e-05, "loss": 2.0114, "step": 76080 }, { "epoch": 1.24, "learning_rate": 1.1991482965931864e-05, "loss": 2.0076, "step": 76090 }, { "epoch": 1.24, "learning_rate": 1.1986472945891785e-05, "loss": 1.984, "step": 76100 }, { "epoch": 1.24, "learning_rate": 1.1981462925851704e-05, "loss": 2.0247, "step": 76110 }, { "epoch": 1.24, "learning_rate": 1.1976452905811623e-05, "loss": 1.9672, "step": 76120 }, { "epoch": 1.24, "learning_rate": 1.1971442885771544e-05, "loss": 1.9801, "step": 76130 }, { "epoch": 1.24, "learning_rate": 1.1966432865731464e-05, "loss": 1.9932, "step": 76140 }, { "epoch": 1.24, "learning_rate": 1.1961422845691383e-05, "loss": 2.0451, "step": 76150 }, { "epoch": 1.24, "learning_rate": 1.1956412825651304e-05, "loss": 2.0365, "step": 76160 }, { "epoch": 1.24, "learning_rate": 1.1951402805611223e-05, "loss": 2.0024, "step": 76170 }, { "epoch": 1.24, "learning_rate": 1.1946392785571142e-05, "loss": 2.0046, "step": 76180 }, { "epoch": 1.24, "learning_rate": 1.1941382765531062e-05, "loss": 2.0172, "step": 76190 }, { "epoch": 1.25, "learning_rate": 1.1936372745490983e-05, "loss": 2.0082, "step": 76200 }, { "epoch": 1.25, "learning_rate": 1.1931362725450902e-05, "loss": 2.0345, "step": 76210 }, { "epoch": 1.25, "learning_rate": 1.1926352705410823e-05, "loss": 2.0329, "step": 76220 }, { "epoch": 1.25, "learning_rate": 1.1921342685370743e-05, "loss": 2.0354, "step": 76230 }, { "epoch": 1.25, "learning_rate": 1.1916332665330662e-05, "loss": 2.0103, "step": 76240 }, { "epoch": 1.25, "learning_rate": 1.1911322645290581e-05, "loss": 2.0086, "step": 76250 }, { "epoch": 1.25, "learning_rate": 1.1906312625250502e-05, "loss": 2.0517, "step": 76260 }, { "epoch": 1.25, "learning_rate": 1.190130260521042e-05, "loss": 2.0679, "step": 76270 }, { "epoch": 1.25, "learning_rate": 1.1896292585170341e-05, "loss": 2.0108, "step": 76280 }, { "epoch": 1.25, "learning_rate": 1.1891282565130262e-05, "loss": 2.0172, "step": 76290 }, { "epoch": 1.25, "learning_rate": 1.1886272545090181e-05, "loss": 2.0336, "step": 76300 }, { "epoch": 1.25, "learning_rate": 1.18812625250501e-05, "loss": 1.9936, "step": 76310 }, { "epoch": 1.25, "learning_rate": 1.187625250501002e-05, "loss": 2.0269, "step": 76320 }, { "epoch": 1.25, "learning_rate": 1.1871242484969941e-05, "loss": 2.0108, "step": 76330 }, { "epoch": 1.25, "learning_rate": 1.186623246492986e-05, "loss": 1.9831, "step": 76340 }, { "epoch": 1.25, "learning_rate": 1.186122244488978e-05, "loss": 2.056, "step": 76350 }, { "epoch": 1.25, "learning_rate": 1.18562124248497e-05, "loss": 1.995, "step": 76360 }, { "epoch": 1.25, "learning_rate": 1.1851202404809619e-05, "loss": 2.0215, "step": 76370 }, { "epoch": 1.25, "learning_rate": 1.1846192384769541e-05, "loss": 2.0379, "step": 76380 }, { "epoch": 1.25, "learning_rate": 1.184118236472946e-05, "loss": 2.0291, "step": 76390 }, { "epoch": 1.25, "learning_rate": 1.1836172344689379e-05, "loss": 2.0053, "step": 76400 }, { "epoch": 1.25, "learning_rate": 1.18311623246493e-05, "loss": 2.0166, "step": 76410 }, { "epoch": 1.25, "learning_rate": 1.1826152304609218e-05, "loss": 1.9981, "step": 76420 }, { "epoch": 1.25, "learning_rate": 1.1821142284569139e-05, "loss": 2.0034, "step": 76430 }, { "epoch": 1.25, "learning_rate": 1.181613226452906e-05, "loss": 2.0407, "step": 76440 }, { "epoch": 1.25, "learning_rate": 1.1811122244488979e-05, "loss": 2.0196, "step": 76450 }, { "epoch": 1.25, "learning_rate": 1.1806112224448898e-05, "loss": 2.0075, "step": 76460 }, { "epoch": 1.25, "learning_rate": 1.1801102204408818e-05, "loss": 2.045, "step": 76470 }, { "epoch": 1.25, "learning_rate": 1.1796092184368739e-05, "loss": 2.0033, "step": 76480 }, { "epoch": 1.25, "learning_rate": 1.1791082164328658e-05, "loss": 1.9705, "step": 76490 }, { "epoch": 1.25, "learning_rate": 1.1786072144288578e-05, "loss": 2.0553, "step": 76500 }, { "epoch": 1.25, "learning_rate": 1.1781062124248497e-05, "loss": 2.0751, "step": 76510 }, { "epoch": 1.25, "learning_rate": 1.1776052104208416e-05, "loss": 1.9834, "step": 76520 }, { "epoch": 1.25, "learning_rate": 1.1771042084168337e-05, "loss": 2.0238, "step": 76530 }, { "epoch": 1.25, "learning_rate": 1.1766032064128258e-05, "loss": 2.0227, "step": 76540 }, { "epoch": 1.25, "learning_rate": 1.1761022044088177e-05, "loss": 2.0063, "step": 76550 }, { "epoch": 1.25, "learning_rate": 1.1756012024048097e-05, "loss": 2.0223, "step": 76560 }, { "epoch": 1.25, "learning_rate": 1.1751002004008016e-05, "loss": 2.0207, "step": 76570 }, { "epoch": 1.25, "learning_rate": 1.1745991983967937e-05, "loss": 1.9986, "step": 76580 }, { "epoch": 1.25, "learning_rate": 1.1740981963927856e-05, "loss": 2.0376, "step": 76590 }, { "epoch": 1.25, "learning_rate": 1.1735971943887776e-05, "loss": 2.04, "step": 76600 }, { "epoch": 1.25, "learning_rate": 1.1730961923847695e-05, "loss": 1.975, "step": 76610 }, { "epoch": 1.25, "learning_rate": 1.1725951903807614e-05, "loss": 2.0233, "step": 76620 }, { "epoch": 1.25, "learning_rate": 1.1720941883767537e-05, "loss": 2.057, "step": 76630 }, { "epoch": 1.25, "learning_rate": 1.1715931863727456e-05, "loss": 2.0101, "step": 76640 }, { "epoch": 1.25, "learning_rate": 1.1710921843687375e-05, "loss": 2.0341, "step": 76650 }, { "epoch": 1.25, "learning_rate": 1.1705911823647295e-05, "loss": 2.0286, "step": 76660 }, { "epoch": 1.25, "learning_rate": 1.1700901803607214e-05, "loss": 2.0404, "step": 76670 }, { "epoch": 1.25, "learning_rate": 1.1695891783567135e-05, "loss": 2.0128, "step": 76680 }, { "epoch": 1.25, "learning_rate": 1.1690881763527055e-05, "loss": 2.0487, "step": 76690 }, { "epoch": 1.25, "learning_rate": 1.1685871743486974e-05, "loss": 2.004, "step": 76700 }, { "epoch": 1.25, "learning_rate": 1.1680861723446893e-05, "loss": 2.0418, "step": 76710 }, { "epoch": 1.25, "learning_rate": 1.1675851703406814e-05, "loss": 2.0401, "step": 76720 }, { "epoch": 1.25, "learning_rate": 1.1670841683366735e-05, "loss": 2.0067, "step": 76730 }, { "epoch": 1.25, "learning_rate": 1.1665831663326654e-05, "loss": 2.0292, "step": 76740 }, { "epoch": 1.25, "learning_rate": 1.1660821643286574e-05, "loss": 2.0352, "step": 76750 }, { "epoch": 1.25, "learning_rate": 1.1655811623246493e-05, "loss": 2.0288, "step": 76760 }, { "epoch": 1.25, "learning_rate": 1.1650801603206414e-05, "loss": 2.0407, "step": 76770 }, { "epoch": 1.25, "learning_rate": 1.1645791583166334e-05, "loss": 1.9983, "step": 76780 }, { "epoch": 1.25, "learning_rate": 1.1640781563126253e-05, "loss": 2.0057, "step": 76790 }, { "epoch": 1.25, "learning_rate": 1.1635771543086172e-05, "loss": 2.0233, "step": 76800 }, { "epoch": 1.26, "learning_rate": 1.1630761523046093e-05, "loss": 1.979, "step": 76810 }, { "epoch": 1.26, "learning_rate": 1.1625751503006014e-05, "loss": 1.9742, "step": 76820 }, { "epoch": 1.26, "learning_rate": 1.1620741482965933e-05, "loss": 2.0386, "step": 76830 }, { "epoch": 1.26, "learning_rate": 1.1615731462925853e-05, "loss": 1.9984, "step": 76840 }, { "epoch": 1.26, "learning_rate": 1.1610721442885772e-05, "loss": 2.0188, "step": 76850 }, { "epoch": 1.26, "learning_rate": 1.1605711422845691e-05, "loss": 2.0228, "step": 76860 }, { "epoch": 1.26, "learning_rate": 1.1600701402805612e-05, "loss": 2.0251, "step": 76870 }, { "epoch": 1.26, "learning_rate": 1.1595691382765532e-05, "loss": 2.0379, "step": 76880 }, { "epoch": 1.26, "learning_rate": 1.1590681362725451e-05, "loss": 2.0074, "step": 76890 }, { "epoch": 1.26, "learning_rate": 1.158567134268537e-05, "loss": 1.9929, "step": 76900 }, { "epoch": 1.26, "learning_rate": 1.1580661322645291e-05, "loss": 2.014, "step": 76910 }, { "epoch": 1.26, "learning_rate": 1.1575651302605212e-05, "loss": 2.0724, "step": 76920 }, { "epoch": 1.26, "learning_rate": 1.157064128256513e-05, "loss": 2.0429, "step": 76930 }, { "epoch": 1.26, "learning_rate": 1.1565631262525051e-05, "loss": 1.9879, "step": 76940 }, { "epoch": 1.26, "learning_rate": 1.156062124248497e-05, "loss": 2.0082, "step": 76950 }, { "epoch": 1.26, "learning_rate": 1.1555611222444889e-05, "loss": 1.9966, "step": 76960 }, { "epoch": 1.26, "learning_rate": 1.1550601202404811e-05, "loss": 1.9917, "step": 76970 }, { "epoch": 1.26, "learning_rate": 1.154559118236473e-05, "loss": 1.9988, "step": 76980 }, { "epoch": 1.26, "learning_rate": 1.154058116232465e-05, "loss": 2.0611, "step": 76990 }, { "epoch": 1.26, "learning_rate": 1.153557114228457e-05, "loss": 2.0409, "step": 77000 }, { "epoch": 1.26, "eval_loss": 2.0054054260253906, "eval_mean_f1": 0.6597843912898711, "eval_rouge1_f1": 0.7171436216227876, "eval_rouge1_precision": 0.8284198482691991, "eval_rouge1_recall": 0.665091937472452, "eval_rouge2_f1": 0.576217765547294, "eval_rouge2_precision": 0.6706476764338094, "eval_rouge2_recall": 0.5340005360930797, "eval_rougeL_f1": 0.6859917866995318, "eval_rougeL_precision": 0.7909898548796616, "eval_rougeL_recall": 0.6375688048428655, "eval_runtime": 64.38, "eval_samples_per_second": 15.906, "eval_steps_per_second": 1.988, "step": 77000 }, { "epoch": 1.26, "learning_rate": 1.1530561122244489e-05, "loss": 1.9888, "step": 77010 }, { "epoch": 1.26, "learning_rate": 1.152555110220441e-05, "loss": 2.0421, "step": 77020 }, { "epoch": 1.26, "learning_rate": 1.152054108216433e-05, "loss": 2.0471, "step": 77030 }, { "epoch": 1.26, "learning_rate": 1.1515531062124249e-05, "loss": 2.0386, "step": 77040 }, { "epoch": 1.26, "learning_rate": 1.1510521042084168e-05, "loss": 2.0026, "step": 77050 }, { "epoch": 1.26, "learning_rate": 1.1505511022044089e-05, "loss": 2.0352, "step": 77060 }, { "epoch": 1.26, "learning_rate": 1.150050100200401e-05, "loss": 2.0101, "step": 77070 }, { "epoch": 1.26, "learning_rate": 1.1495490981963928e-05, "loss": 2.0407, "step": 77080 }, { "epoch": 1.26, "learning_rate": 1.1490480961923849e-05, "loss": 1.9975, "step": 77090 }, { "epoch": 1.26, "learning_rate": 1.1485470941883768e-05, "loss": 1.9926, "step": 77100 }, { "epoch": 1.26, "learning_rate": 1.1480460921843687e-05, "loss": 2.0136, "step": 77110 }, { "epoch": 1.26, "learning_rate": 1.1475450901803607e-05, "loss": 2.0074, "step": 77120 }, { "epoch": 1.26, "learning_rate": 1.1470440881763528e-05, "loss": 2.0348, "step": 77130 }, { "epoch": 1.26, "learning_rate": 1.1465430861723447e-05, "loss": 1.9801, "step": 77140 }, { "epoch": 1.26, "learning_rate": 1.1460420841683368e-05, "loss": 2.0423, "step": 77150 }, { "epoch": 1.26, "learning_rate": 1.1455410821643287e-05, "loss": 2.0092, "step": 77160 }, { "epoch": 1.26, "learning_rate": 1.1450400801603207e-05, "loss": 1.9859, "step": 77170 }, { "epoch": 1.26, "learning_rate": 1.1445390781563126e-05, "loss": 1.9953, "step": 77180 }, { "epoch": 1.26, "learning_rate": 1.1440380761523047e-05, "loss": 2.0152, "step": 77190 }, { "epoch": 1.26, "learning_rate": 1.1435370741482966e-05, "loss": 1.979, "step": 77200 }, { "epoch": 1.26, "learning_rate": 1.1430360721442886e-05, "loss": 2.023, "step": 77210 }, { "epoch": 1.26, "learning_rate": 1.1425350701402807e-05, "loss": 2.0063, "step": 77220 }, { "epoch": 1.26, "learning_rate": 1.1420340681362726e-05, "loss": 2.0159, "step": 77230 }, { "epoch": 1.26, "learning_rate": 1.1415330661322645e-05, "loss": 2.0476, "step": 77240 }, { "epoch": 1.26, "learning_rate": 1.1410320641282566e-05, "loss": 2.0013, "step": 77250 }, { "epoch": 1.26, "learning_rate": 1.1405310621242485e-05, "loss": 2.045, "step": 77260 }, { "epoch": 1.26, "learning_rate": 1.1400300601202405e-05, "loss": 2.0235, "step": 77270 }, { "epoch": 1.26, "learning_rate": 1.1395290581162326e-05, "loss": 1.9869, "step": 77280 }, { "epoch": 1.26, "learning_rate": 1.1390280561122245e-05, "loss": 1.9933, "step": 77290 }, { "epoch": 1.26, "learning_rate": 1.1385270541082164e-05, "loss": 2.0208, "step": 77300 }, { "epoch": 1.26, "learning_rate": 1.1380260521042086e-05, "loss": 1.9951, "step": 77310 }, { "epoch": 1.26, "learning_rate": 1.1375250501002005e-05, "loss": 2.0057, "step": 77320 }, { "epoch": 1.26, "learning_rate": 1.1370240480961924e-05, "loss": 1.9841, "step": 77330 }, { "epoch": 1.26, "learning_rate": 1.1365230460921845e-05, "loss": 2.0372, "step": 77340 }, { "epoch": 1.26, "learning_rate": 1.1360220440881764e-05, "loss": 2.0165, "step": 77350 }, { "epoch": 1.26, "learning_rate": 1.1355210420841684e-05, "loss": 2.0302, "step": 77360 }, { "epoch": 1.26, "learning_rate": 1.1350200400801605e-05, "loss": 2.0493, "step": 77370 }, { "epoch": 1.26, "learning_rate": 1.1345190380761524e-05, "loss": 1.979, "step": 77380 }, { "epoch": 1.26, "learning_rate": 1.1340180360721443e-05, "loss": 1.9842, "step": 77390 }, { "epoch": 1.26, "learning_rate": 1.1335170340681363e-05, "loss": 2.0002, "step": 77400 }, { "epoch": 1.26, "learning_rate": 1.1330160320641284e-05, "loss": 2.0349, "step": 77410 }, { "epoch": 1.27, "learning_rate": 1.1325150300601203e-05, "loss": 2.0205, "step": 77420 }, { "epoch": 1.27, "learning_rate": 1.1320140280561124e-05, "loss": 2.0152, "step": 77430 }, { "epoch": 1.27, "learning_rate": 1.1315130260521043e-05, "loss": 2.0379, "step": 77440 }, { "epoch": 1.27, "learning_rate": 1.1310120240480961e-05, "loss": 2.0549, "step": 77450 }, { "epoch": 1.27, "learning_rate": 1.1305110220440882e-05, "loss": 2.058, "step": 77460 }, { "epoch": 1.27, "learning_rate": 1.1300100200400803e-05, "loss": 2.0227, "step": 77470 }, { "epoch": 1.27, "learning_rate": 1.1295090180360722e-05, "loss": 2.0245, "step": 77480 }, { "epoch": 1.27, "learning_rate": 1.1290080160320642e-05, "loss": 2.0117, "step": 77490 }, { "epoch": 1.27, "learning_rate": 1.1285070140280561e-05, "loss": 1.9698, "step": 77500 }, { "epoch": 1.27, "learning_rate": 1.1280060120240482e-05, "loss": 2.0282, "step": 77510 }, { "epoch": 1.27, "learning_rate": 1.1275050100200401e-05, "loss": 2.0192, "step": 77520 }, { "epoch": 1.27, "learning_rate": 1.1270040080160322e-05, "loss": 2.0172, "step": 77530 }, { "epoch": 1.27, "learning_rate": 1.126503006012024e-05, "loss": 1.9809, "step": 77540 }, { "epoch": 1.27, "learning_rate": 1.1260020040080161e-05, "loss": 2.0277, "step": 77550 }, { "epoch": 1.27, "learning_rate": 1.1255010020040082e-05, "loss": 2.0226, "step": 77560 }, { "epoch": 1.27, "learning_rate": 1.125e-05, "loss": 2.0286, "step": 77570 }, { "epoch": 1.27, "learning_rate": 1.124498997995992e-05, "loss": 2.0143, "step": 77580 }, { "epoch": 1.27, "learning_rate": 1.123997995991984e-05, "loss": 2.0377, "step": 77590 }, { "epoch": 1.27, "learning_rate": 1.123496993987976e-05, "loss": 2.0225, "step": 77600 }, { "epoch": 1.27, "learning_rate": 1.122995991983968e-05, "loss": 2.029, "step": 77610 }, { "epoch": 1.27, "learning_rate": 1.12249498997996e-05, "loss": 2.0559, "step": 77620 }, { "epoch": 1.27, "learning_rate": 1.121993987975952e-05, "loss": 2.0321, "step": 77630 }, { "epoch": 1.27, "learning_rate": 1.1214929859719438e-05, "loss": 1.9994, "step": 77640 }, { "epoch": 1.27, "learning_rate": 1.1209919839679359e-05, "loss": 2.0159, "step": 77650 }, { "epoch": 1.27, "learning_rate": 1.120490981963928e-05, "loss": 2.017, "step": 77660 }, { "epoch": 1.27, "learning_rate": 1.1199899799599199e-05, "loss": 2.0068, "step": 77670 }, { "epoch": 1.27, "learning_rate": 1.119488977955912e-05, "loss": 1.9611, "step": 77680 }, { "epoch": 1.27, "learning_rate": 1.1189879759519038e-05, "loss": 2.0295, "step": 77690 }, { "epoch": 1.27, "learning_rate": 1.1185370741482966e-05, "loss": 1.9956, "step": 77700 }, { "epoch": 1.27, "learning_rate": 1.1180360721442887e-05, "loss": 2.0201, "step": 77710 }, { "epoch": 1.27, "learning_rate": 1.1175350701402806e-05, "loss": 2.0621, "step": 77720 }, { "epoch": 1.27, "learning_rate": 1.1170340681362727e-05, "loss": 2.067, "step": 77730 }, { "epoch": 1.27, "learning_rate": 1.1165330661322646e-05, "loss": 2.0343, "step": 77740 }, { "epoch": 1.27, "learning_rate": 1.1160320641282565e-05, "loss": 2.0136, "step": 77750 }, { "epoch": 1.27, "learning_rate": 1.1155310621242485e-05, "loss": 1.976, "step": 77760 }, { "epoch": 1.27, "learning_rate": 1.1150300601202406e-05, "loss": 1.9964, "step": 77770 }, { "epoch": 1.27, "learning_rate": 1.1145290581162325e-05, "loss": 1.9865, "step": 77780 }, { "epoch": 1.27, "learning_rate": 1.1140280561122245e-05, "loss": 2.0034, "step": 77790 }, { "epoch": 1.27, "learning_rate": 1.1135270541082164e-05, "loss": 1.9875, "step": 77800 }, { "epoch": 1.27, "learning_rate": 1.1130260521042085e-05, "loss": 2.0377, "step": 77810 }, { "epoch": 1.27, "learning_rate": 1.1125250501002004e-05, "loss": 2.0059, "step": 77820 }, { "epoch": 1.27, "learning_rate": 1.1120240480961925e-05, "loss": 1.9961, "step": 77830 }, { "epoch": 1.27, "learning_rate": 1.1115230460921844e-05, "loss": 2.0296, "step": 77840 }, { "epoch": 1.27, "learning_rate": 1.1110220440881763e-05, "loss": 2.026, "step": 77850 }, { "epoch": 1.27, "learning_rate": 1.1105210420841685e-05, "loss": 2.0001, "step": 77860 }, { "epoch": 1.27, "learning_rate": 1.1100200400801604e-05, "loss": 2.0252, "step": 77870 }, { "epoch": 1.27, "learning_rate": 1.1095190380761523e-05, "loss": 2.0045, "step": 77880 }, { "epoch": 1.27, "learning_rate": 1.1090180360721443e-05, "loss": 1.9987, "step": 77890 }, { "epoch": 1.27, "learning_rate": 1.1085170340681362e-05, "loss": 2.0423, "step": 77900 }, { "epoch": 1.27, "learning_rate": 1.1080160320641283e-05, "loss": 2.0169, "step": 77910 }, { "epoch": 1.27, "learning_rate": 1.1075150300601204e-05, "loss": 2.0273, "step": 77920 }, { "epoch": 1.27, "learning_rate": 1.1070140280561123e-05, "loss": 1.9831, "step": 77930 }, { "epoch": 1.27, "learning_rate": 1.1065130260521042e-05, "loss": 2.0469, "step": 77940 }, { "epoch": 1.27, "learning_rate": 1.1060120240480964e-05, "loss": 1.9887, "step": 77950 }, { "epoch": 1.27, "learning_rate": 1.1055110220440883e-05, "loss": 2.0419, "step": 77960 }, { "epoch": 1.27, "learning_rate": 1.1050100200400802e-05, "loss": 2.0012, "step": 77970 }, { "epoch": 1.27, "learning_rate": 1.1045090180360722e-05, "loss": 2.0199, "step": 77980 }, { "epoch": 1.27, "learning_rate": 1.1040080160320641e-05, "loss": 1.9659, "step": 77990 }, { "epoch": 1.27, "learning_rate": 1.1035070140280562e-05, "loss": 1.9837, "step": 78000 }, { "epoch": 1.27, "eval_loss": 2.005821704864502, "eval_mean_f1": 0.6625363014309303, "eval_rouge1_f1": 0.7187468413077766, "eval_rouge1_precision": 0.8287650912615007, "eval_rouge1_recall": 0.6683415328345699, "eval_rouge2_f1": 0.5814401522351863, "eval_rouge2_precision": 0.6743206832501266, "eval_rouge2_recall": 0.5408492019917465, "eval_rougeL_f1": 0.6874219107498281, "eval_rougeL_precision": 0.7907988522181713, "eval_rougeL_recall": 0.640168027190372, "eval_runtime": 63.2066, "eval_samples_per_second": 16.201, "eval_steps_per_second": 2.025, "step": 78000 }, { "epoch": 1.27, "learning_rate": 1.1030060120240483e-05, "loss": 2.0318, "step": 78010 }, { "epoch": 1.27, "learning_rate": 1.1025050100200402e-05, "loss": 1.9776, "step": 78020 }, { "epoch": 1.27, "learning_rate": 1.102004008016032e-05, "loss": 1.9777, "step": 78030 }, { "epoch": 1.28, "learning_rate": 1.1015030060120241e-05, "loss": 1.9707, "step": 78040 }, { "epoch": 1.28, "learning_rate": 1.1010020040080162e-05, "loss": 2.0371, "step": 78050 }, { "epoch": 1.28, "learning_rate": 1.100501002004008e-05, "loss": 1.9926, "step": 78060 }, { "epoch": 1.28, "learning_rate": 1.1000000000000001e-05, "loss": 2.0084, "step": 78070 }, { "epoch": 1.28, "learning_rate": 1.099498997995992e-05, "loss": 2.005, "step": 78080 }, { "epoch": 1.28, "learning_rate": 1.098997995991984e-05, "loss": 2.0227, "step": 78090 }, { "epoch": 1.28, "learning_rate": 1.098496993987976e-05, "loss": 1.9935, "step": 78100 }, { "epoch": 1.28, "learning_rate": 1.097995991983968e-05, "loss": 2.0138, "step": 78110 }, { "epoch": 1.28, "learning_rate": 1.09749498997996e-05, "loss": 2.0236, "step": 78120 }, { "epoch": 1.28, "learning_rate": 1.0969939879759518e-05, "loss": 2.0187, "step": 78130 }, { "epoch": 1.28, "learning_rate": 1.0964929859719439e-05, "loss": 2.0269, "step": 78140 }, { "epoch": 1.28, "learning_rate": 1.095991983967936e-05, "loss": 2.044, "step": 78150 }, { "epoch": 1.28, "learning_rate": 1.0954909819639279e-05, "loss": 2.0074, "step": 78160 }, { "epoch": 1.28, "learning_rate": 1.09498997995992e-05, "loss": 2.0155, "step": 78170 }, { "epoch": 1.28, "learning_rate": 1.0944889779559118e-05, "loss": 1.9888, "step": 78180 }, { "epoch": 1.28, "learning_rate": 1.0939879759519037e-05, "loss": 2.0241, "step": 78190 }, { "epoch": 1.28, "learning_rate": 1.093486973947896e-05, "loss": 2.05, "step": 78200 }, { "epoch": 1.28, "learning_rate": 1.0929859719438879e-05, "loss": 1.9957, "step": 78210 }, { "epoch": 1.28, "learning_rate": 1.0924849699398797e-05, "loss": 2.0224, "step": 78220 }, { "epoch": 1.28, "learning_rate": 1.0919839679358718e-05, "loss": 1.9686, "step": 78230 }, { "epoch": 1.28, "learning_rate": 1.0914829659318637e-05, "loss": 2.0182, "step": 78240 }, { "epoch": 1.28, "learning_rate": 1.0909819639278558e-05, "loss": 2.0218, "step": 78250 }, { "epoch": 1.28, "learning_rate": 1.0904809619238478e-05, "loss": 1.9807, "step": 78260 }, { "epoch": 1.28, "learning_rate": 1.0899799599198397e-05, "loss": 1.9964, "step": 78270 }, { "epoch": 1.28, "learning_rate": 1.0894789579158316e-05, "loss": 2.0577, "step": 78280 }, { "epoch": 1.28, "learning_rate": 1.0889779559118237e-05, "loss": 2.0228, "step": 78290 }, { "epoch": 1.28, "learning_rate": 1.0884769539078158e-05, "loss": 2.012, "step": 78300 }, { "epoch": 1.28, "learning_rate": 1.0879759519038076e-05, "loss": 1.9791, "step": 78310 }, { "epoch": 1.28, "learning_rate": 1.0874749498997997e-05, "loss": 1.9822, "step": 78320 }, { "epoch": 1.28, "learning_rate": 1.0869739478957916e-05, "loss": 2.0344, "step": 78330 }, { "epoch": 1.28, "learning_rate": 1.0864729458917835e-05, "loss": 2.0226, "step": 78340 }, { "epoch": 1.28, "learning_rate": 1.0859719438877757e-05, "loss": 2.0065, "step": 78350 }, { "epoch": 1.28, "learning_rate": 1.0854709418837676e-05, "loss": 2.0167, "step": 78360 }, { "epoch": 1.28, "learning_rate": 1.0849699398797595e-05, "loss": 2.0633, "step": 78370 }, { "epoch": 1.28, "learning_rate": 1.0844689378757516e-05, "loss": 1.973, "step": 78380 }, { "epoch": 1.28, "learning_rate": 1.0839679358717435e-05, "loss": 1.9522, "step": 78390 }, { "epoch": 1.28, "learning_rate": 1.0834669338677355e-05, "loss": 2.0025, "step": 78400 }, { "epoch": 1.28, "learning_rate": 1.0829659318637274e-05, "loss": 2.0305, "step": 78410 }, { "epoch": 1.28, "learning_rate": 1.0824649298597195e-05, "loss": 2.0259, "step": 78420 }, { "epoch": 1.28, "learning_rate": 1.0819639278557114e-05, "loss": 2.0416, "step": 78430 }, { "epoch": 1.28, "learning_rate": 1.0814629258517035e-05, "loss": 1.9864, "step": 78440 }, { "epoch": 1.28, "learning_rate": 1.0809619238476955e-05, "loss": 2.0785, "step": 78450 }, { "epoch": 1.28, "learning_rate": 1.0804609218436874e-05, "loss": 2.0118, "step": 78460 }, { "epoch": 1.28, "learning_rate": 1.0799599198396793e-05, "loss": 2.0861, "step": 78470 }, { "epoch": 1.28, "learning_rate": 1.0794589178356714e-05, "loss": 1.969, "step": 78480 }, { "epoch": 1.28, "learning_rate": 1.0789579158316634e-05, "loss": 2.0499, "step": 78490 }, { "epoch": 1.28, "learning_rate": 1.0784569138276553e-05, "loss": 2.0294, "step": 78500 }, { "epoch": 1.28, "learning_rate": 1.0779559118236474e-05, "loss": 2.0472, "step": 78510 }, { "epoch": 1.28, "learning_rate": 1.0774549098196393e-05, "loss": 1.9994, "step": 78520 }, { "epoch": 1.28, "learning_rate": 1.0769539078156312e-05, "loss": 2.0143, "step": 78530 }, { "epoch": 1.28, "learning_rate": 1.0764529058116234e-05, "loss": 2.0061, "step": 78540 }, { "epoch": 1.28, "learning_rate": 1.0759519038076153e-05, "loss": 2.0157, "step": 78550 }, { "epoch": 1.28, "learning_rate": 1.0754509018036072e-05, "loss": 2.0135, "step": 78560 }, { "epoch": 1.28, "learning_rate": 1.0749498997995993e-05, "loss": 2.0295, "step": 78570 }, { "epoch": 1.28, "learning_rate": 1.0744488977955912e-05, "loss": 2.0055, "step": 78580 }, { "epoch": 1.28, "learning_rate": 1.0739478957915832e-05, "loss": 2.0409, "step": 78590 }, { "epoch": 1.28, "learning_rate": 1.0734468937875753e-05, "loss": 2.0096, "step": 78600 }, { "epoch": 1.28, "learning_rate": 1.0729458917835672e-05, "loss": 1.982, "step": 78610 }, { "epoch": 1.28, "learning_rate": 1.0724448897795591e-05, "loss": 2.0395, "step": 78620 }, { "epoch": 1.28, "learning_rate": 1.0719438877755512e-05, "loss": 1.9928, "step": 78630 }, { "epoch": 1.28, "learning_rate": 1.0714428857715432e-05, "loss": 2.0143, "step": 78640 }, { "epoch": 1.29, "learning_rate": 1.0709418837675351e-05, "loss": 1.9921, "step": 78650 }, { "epoch": 1.29, "learning_rate": 1.0704408817635272e-05, "loss": 1.9859, "step": 78660 }, { "epoch": 1.29, "learning_rate": 1.069939879759519e-05, "loss": 1.9838, "step": 78670 }, { "epoch": 1.29, "learning_rate": 1.069438877755511e-05, "loss": 2.0053, "step": 78680 }, { "epoch": 1.29, "learning_rate": 1.068937875751503e-05, "loss": 2.0529, "step": 78690 }, { "epoch": 1.29, "learning_rate": 1.0684368737474951e-05, "loss": 1.9817, "step": 78700 }, { "epoch": 1.29, "learning_rate": 1.067935871743487e-05, "loss": 2.0321, "step": 78710 }, { "epoch": 1.29, "learning_rate": 1.067434869739479e-05, "loss": 1.9861, "step": 78720 }, { "epoch": 1.29, "learning_rate": 1.066933867735471e-05, "loss": 2.0292, "step": 78730 }, { "epoch": 1.29, "learning_rate": 1.066432865731463e-05, "loss": 1.9923, "step": 78740 }, { "epoch": 1.29, "learning_rate": 1.0659318637274549e-05, "loss": 2.014, "step": 78750 }, { "epoch": 1.29, "learning_rate": 1.065430861723447e-05, "loss": 1.9964, "step": 78760 }, { "epoch": 1.29, "learning_rate": 1.0649298597194389e-05, "loss": 2.0131, "step": 78770 }, { "epoch": 1.29, "learning_rate": 1.064428857715431e-05, "loss": 2.063, "step": 78780 }, { "epoch": 1.29, "learning_rate": 1.063927855711423e-05, "loss": 2.026, "step": 78790 }, { "epoch": 1.29, "learning_rate": 1.0634268537074149e-05, "loss": 2.0828, "step": 78800 }, { "epoch": 1.29, "learning_rate": 1.0629258517034068e-05, "loss": 2.0102, "step": 78810 }, { "epoch": 1.29, "learning_rate": 1.0624248496993989e-05, "loss": 2.0419, "step": 78820 }, { "epoch": 1.29, "learning_rate": 1.0619238476953907e-05, "loss": 1.994, "step": 78830 }, { "epoch": 1.29, "learning_rate": 1.0614228456913828e-05, "loss": 2.0101, "step": 78840 }, { "epoch": 1.29, "learning_rate": 1.0609218436873749e-05, "loss": 2.0208, "step": 78850 }, { "epoch": 1.29, "learning_rate": 1.0604208416833668e-05, "loss": 2.0031, "step": 78860 }, { "epoch": 1.29, "learning_rate": 1.0599198396793587e-05, "loss": 2.0193, "step": 78870 }, { "epoch": 1.29, "learning_rate": 1.0594188376753507e-05, "loss": 1.98, "step": 78880 }, { "epoch": 1.29, "learning_rate": 1.0589178356713428e-05, "loss": 2.0045, "step": 78890 }, { "epoch": 1.29, "learning_rate": 1.0584168336673347e-05, "loss": 2.0049, "step": 78900 }, { "epoch": 1.29, "learning_rate": 1.0579158316633268e-05, "loss": 2.037, "step": 78910 }, { "epoch": 1.29, "learning_rate": 1.0574148296593186e-05, "loss": 2.0537, "step": 78920 }, { "epoch": 1.29, "learning_rate": 1.0569138276553105e-05, "loss": 2.0098, "step": 78930 }, { "epoch": 1.29, "learning_rate": 1.0564128256513028e-05, "loss": 2.014, "step": 78940 }, { "epoch": 1.29, "learning_rate": 1.0559118236472947e-05, "loss": 1.9971, "step": 78950 }, { "epoch": 1.29, "learning_rate": 1.0554108216432866e-05, "loss": 1.9927, "step": 78960 }, { "epoch": 1.29, "learning_rate": 1.0549098196392786e-05, "loss": 1.973, "step": 78970 }, { "epoch": 1.29, "learning_rate": 1.0544088176352705e-05, "loss": 2.0357, "step": 78980 }, { "epoch": 1.29, "learning_rate": 1.0539078156312626e-05, "loss": 2.0101, "step": 78990 }, { "epoch": 1.29, "learning_rate": 1.0534068136272547e-05, "loss": 1.9939, "step": 79000 }, { "epoch": 1.29, "eval_loss": 2.005432605743408, "eval_mean_f1": 0.6624140067277632, "eval_rouge1_f1": 0.7193921151762919, "eval_rouge1_precision": 0.8293968276652242, "eval_rouge1_recall": 0.6676959091736536, "eval_rouge2_f1": 0.5789617417980103, "eval_rouge2_precision": 0.6713331190565082, "eval_rouge2_recall": 0.5371206744576562, "eval_rougeL_f1": 0.6888881632089874, "eval_rougeL_precision": 0.7926026909400211, "eval_rougeL_recall": 0.6405056627404218, "eval_runtime": 64.3011, "eval_samples_per_second": 15.925, "eval_steps_per_second": 1.991, "step": 79000 }, { "epoch": 1.29, "learning_rate": 1.0529058116232465e-05, "loss": 2.027, "step": 79010 }, { "epoch": 1.29, "learning_rate": 1.0524048096192384e-05, "loss": 2.0151, "step": 79020 }, { "epoch": 1.29, "learning_rate": 1.0519038076152305e-05, "loss": 2.0118, "step": 79030 }, { "epoch": 1.29, "learning_rate": 1.0514028056112226e-05, "loss": 2.0393, "step": 79040 }, { "epoch": 1.29, "learning_rate": 1.0509018036072145e-05, "loss": 2.0157, "step": 79050 }, { "epoch": 1.29, "learning_rate": 1.0504008016032065e-05, "loss": 2.0632, "step": 79060 }, { "epoch": 1.29, "learning_rate": 1.0498997995991984e-05, "loss": 2.0378, "step": 79070 }, { "epoch": 1.29, "learning_rate": 1.0493987975951905e-05, "loss": 2.0345, "step": 79080 }, { "epoch": 1.29, "learning_rate": 1.0488977955911824e-05, "loss": 2.0252, "step": 79090 }, { "epoch": 1.29, "learning_rate": 1.0483967935871744e-05, "loss": 1.9991, "step": 79100 }, { "epoch": 1.29, "learning_rate": 1.0478957915831663e-05, "loss": 2.0457, "step": 79110 }, { "epoch": 1.29, "learning_rate": 1.0473947895791584e-05, "loss": 2.0135, "step": 79120 }, { "epoch": 1.29, "learning_rate": 1.0468937875751505e-05, "loss": 2.0194, "step": 79130 }, { "epoch": 1.29, "learning_rate": 1.0463927855711424e-05, "loss": 2.0601, "step": 79140 }, { "epoch": 1.29, "learning_rate": 1.0458917835671343e-05, "loss": 2.0097, "step": 79150 }, { "epoch": 1.29, "learning_rate": 1.0453907815631263e-05, "loss": 2.0093, "step": 79160 }, { "epoch": 1.29, "learning_rate": 1.0448897795591182e-05, "loss": 2.0288, "step": 79170 }, { "epoch": 1.29, "learning_rate": 1.0443887775551103e-05, "loss": 2.0235, "step": 79180 }, { "epoch": 1.29, "learning_rate": 1.0438877755511023e-05, "loss": 1.9586, "step": 79190 }, { "epoch": 1.29, "learning_rate": 1.0433867735470942e-05, "loss": 2.0172, "step": 79200 }, { "epoch": 1.29, "learning_rate": 1.0428857715430861e-05, "loss": 2.0046, "step": 79210 }, { "epoch": 1.29, "learning_rate": 1.0423847695390782e-05, "loss": 1.9899, "step": 79220 }, { "epoch": 1.29, "learning_rate": 1.0418837675350703e-05, "loss": 2.0018, "step": 79230 }, { "epoch": 1.29, "learning_rate": 1.0413827655310622e-05, "loss": 2.0077, "step": 79240 }, { "epoch": 1.29, "learning_rate": 1.0408817635270542e-05, "loss": 2.0398, "step": 79250 }, { "epoch": 1.3, "learning_rate": 1.0403807615230461e-05, "loss": 2.0128, "step": 79260 }, { "epoch": 1.3, "learning_rate": 1.039879759519038e-05, "loss": 2.0664, "step": 79270 }, { "epoch": 1.3, "learning_rate": 1.0393787575150302e-05, "loss": 2.0102, "step": 79280 }, { "epoch": 1.3, "learning_rate": 1.0388777555110221e-05, "loss": 2.0023, "step": 79290 }, { "epoch": 1.3, "learning_rate": 1.038376753507014e-05, "loss": 2.0059, "step": 79300 }, { "epoch": 1.3, "learning_rate": 1.0378757515030061e-05, "loss": 2.0291, "step": 79310 }, { "epoch": 1.3, "learning_rate": 1.037374749498998e-05, "loss": 2.0124, "step": 79320 }, { "epoch": 1.3, "learning_rate": 1.03687374749499e-05, "loss": 1.9875, "step": 79330 }, { "epoch": 1.3, "learning_rate": 1.0363727454909821e-05, "loss": 2.0392, "step": 79340 }, { "epoch": 1.3, "learning_rate": 1.035871743486974e-05, "loss": 2.0458, "step": 79350 }, { "epoch": 1.3, "learning_rate": 1.0353707414829659e-05, "loss": 1.9915, "step": 79360 }, { "epoch": 1.3, "learning_rate": 1.034869739478958e-05, "loss": 1.9907, "step": 79370 }, { "epoch": 1.3, "learning_rate": 1.03436873747495e-05, "loss": 2.0179, "step": 79380 }, { "epoch": 1.3, "learning_rate": 1.033867735470942e-05, "loss": 2.0314, "step": 79390 }, { "epoch": 1.3, "learning_rate": 1.0333667334669338e-05, "loss": 2.002, "step": 79400 }, { "epoch": 1.3, "learning_rate": 1.0328657314629259e-05, "loss": 1.9614, "step": 79410 }, { "epoch": 1.3, "learning_rate": 1.0323647294589178e-05, "loss": 2.0501, "step": 79420 }, { "epoch": 1.3, "learning_rate": 1.0318637274549099e-05, "loss": 2.0204, "step": 79430 }, { "epoch": 1.3, "learning_rate": 1.031362725450902e-05, "loss": 2.0285, "step": 79440 }, { "epoch": 1.3, "learning_rate": 1.0308617234468938e-05, "loss": 1.985, "step": 79450 }, { "epoch": 1.3, "learning_rate": 1.0303607214428857e-05, "loss": 2.0359, "step": 79460 }, { "epoch": 1.3, "learning_rate": 1.0298597194388778e-05, "loss": 2.016, "step": 79470 }, { "epoch": 1.3, "learning_rate": 1.0293587174348698e-05, "loss": 2.0253, "step": 79480 }, { "epoch": 1.3, "learning_rate": 1.0288577154308617e-05, "loss": 1.9856, "step": 79490 }, { "epoch": 1.3, "learning_rate": 1.0283567134268538e-05, "loss": 2.0503, "step": 79500 }, { "epoch": 1.3, "learning_rate": 1.0278557114228457e-05, "loss": 2.0168, "step": 79510 }, { "epoch": 1.3, "learning_rate": 1.0273547094188376e-05, "loss": 2.0374, "step": 79520 }, { "epoch": 1.3, "learning_rate": 1.0268537074148298e-05, "loss": 1.991, "step": 79530 }, { "epoch": 1.3, "learning_rate": 1.0263527054108217e-05, "loss": 1.9781, "step": 79540 }, { "epoch": 1.3, "learning_rate": 1.0258517034068136e-05, "loss": 2.0082, "step": 79550 }, { "epoch": 1.3, "learning_rate": 1.0253507014028057e-05, "loss": 2.0354, "step": 79560 }, { "epoch": 1.3, "learning_rate": 1.0248496993987977e-05, "loss": 2.034, "step": 79570 }, { "epoch": 1.3, "learning_rate": 1.0243486973947896e-05, "loss": 2.0215, "step": 79580 }, { "epoch": 1.3, "learning_rate": 1.0238977955911825e-05, "loss": 2.0407, "step": 79590 }, { "epoch": 1.3, "learning_rate": 1.0233967935871743e-05, "loss": 2.0105, "step": 79600 }, { "epoch": 1.3, "learning_rate": 1.0228957915831664e-05, "loss": 1.9907, "step": 79610 }, { "epoch": 1.3, "learning_rate": 1.0223947895791583e-05, "loss": 2.0462, "step": 79620 }, { "epoch": 1.3, "learning_rate": 1.0218937875751504e-05, "loss": 2.0289, "step": 79630 }, { "epoch": 1.3, "learning_rate": 1.0213927855711423e-05, "loss": 2.0144, "step": 79640 }, { "epoch": 1.3, "learning_rate": 1.0208917835671343e-05, "loss": 2.0238, "step": 79650 }, { "epoch": 1.3, "learning_rate": 1.0203907815631262e-05, "loss": 2.0174, "step": 79660 }, { "epoch": 1.3, "learning_rate": 1.0198897795591183e-05, "loss": 2.0428, "step": 79670 }, { "epoch": 1.3, "learning_rate": 1.0193887775551104e-05, "loss": 2.015, "step": 79680 }, { "epoch": 1.3, "learning_rate": 1.0188877755511022e-05, "loss": 2.0006, "step": 79690 }, { "epoch": 1.3, "learning_rate": 1.0183867735470941e-05, "loss": 2.0111, "step": 79700 }, { "epoch": 1.3, "learning_rate": 1.0178857715430862e-05, "loss": 1.9851, "step": 79710 }, { "epoch": 1.3, "learning_rate": 1.0173847695390783e-05, "loss": 2.0262, "step": 79720 }, { "epoch": 1.3, "learning_rate": 1.0168837675350702e-05, "loss": 1.9933, "step": 79730 }, { "epoch": 1.3, "learning_rate": 1.0163827655310622e-05, "loss": 1.9916, "step": 79740 }, { "epoch": 1.3, "learning_rate": 1.0158817635270541e-05, "loss": 1.9936, "step": 79750 }, { "epoch": 1.3, "learning_rate": 1.015380761523046e-05, "loss": 2.0088, "step": 79760 }, { "epoch": 1.3, "learning_rate": 1.0148797595190383e-05, "loss": 1.9926, "step": 79770 }, { "epoch": 1.3, "learning_rate": 1.0143787575150301e-05, "loss": 1.994, "step": 79780 }, { "epoch": 1.3, "learning_rate": 1.013877755511022e-05, "loss": 2.0112, "step": 79790 }, { "epoch": 1.3, "learning_rate": 1.0133767535070141e-05, "loss": 1.9918, "step": 79800 }, { "epoch": 1.3, "learning_rate": 1.012875751503006e-05, "loss": 2.033, "step": 79810 }, { "epoch": 1.3, "learning_rate": 1.012374749498998e-05, "loss": 2.0004, "step": 79820 }, { "epoch": 1.3, "learning_rate": 1.0118737474949901e-05, "loss": 1.9829, "step": 79830 }, { "epoch": 1.3, "learning_rate": 1.011372745490982e-05, "loss": 2.003, "step": 79840 }, { "epoch": 1.3, "learning_rate": 1.010871743486974e-05, "loss": 2.0028, "step": 79850 }, { "epoch": 1.3, "learning_rate": 1.010370741482966e-05, "loss": 2.0148, "step": 79860 }, { "epoch": 1.31, "learning_rate": 1.009869739478958e-05, "loss": 1.9918, "step": 79870 }, { "epoch": 1.31, "learning_rate": 1.00936873747495e-05, "loss": 2.0063, "step": 79880 }, { "epoch": 1.31, "learning_rate": 1.008867735470942e-05, "loss": 1.9999, "step": 79890 }, { "epoch": 1.31, "learning_rate": 1.0083667334669339e-05, "loss": 2.0238, "step": 79900 }, { "epoch": 1.31, "learning_rate": 1.0078657314629258e-05, "loss": 2.0023, "step": 79910 }, { "epoch": 1.31, "learning_rate": 1.0073647294589179e-05, "loss": 1.9871, "step": 79920 }, { "epoch": 1.31, "learning_rate": 1.00686372745491e-05, "loss": 2.0522, "step": 79930 }, { "epoch": 1.31, "learning_rate": 1.0063627254509018e-05, "loss": 1.9569, "step": 79940 }, { "epoch": 1.31, "learning_rate": 1.0058617234468939e-05, "loss": 2.012, "step": 79950 }, { "epoch": 1.31, "learning_rate": 1.0053607214428858e-05, "loss": 2.0384, "step": 79960 }, { "epoch": 1.31, "learning_rate": 1.0048597194388778e-05, "loss": 2.0155, "step": 79970 }, { "epoch": 1.31, "learning_rate": 1.0043587174348697e-05, "loss": 2.0276, "step": 79980 }, { "epoch": 1.31, "learning_rate": 1.0038577154308618e-05, "loss": 1.9962, "step": 79990 }, { "epoch": 1.31, "learning_rate": 1.0033567134268537e-05, "loss": 2.0739, "step": 80000 }, { "epoch": 1.31, "eval_loss": 2.0038297176361084, "eval_mean_f1": 0.6640382289815016, "eval_rouge1_f1": 0.7190551179948592, "eval_rouge1_precision": 0.8293271271610965, "eval_rouge1_recall": 0.668028178445772, "eval_rouge2_f1": 0.5830302075316567, "eval_rouge2_precision": 0.676122393773761, "eval_rouge2_recall": 0.54159290355806, "eval_rougeL_f1": 0.6900293614179889, "eval_rougeL_precision": 0.7943715877492741, "eval_rougeL_recall": 0.641738228261399, "eval_runtime": 66.1616, "eval_samples_per_second": 15.477, "eval_steps_per_second": 1.935, "step": 80000 }, { "epoch": 1.31, "learning_rate": 1.0028557114228458e-05, "loss": 2.0432, "step": 80010 }, { "epoch": 1.31, "learning_rate": 1.0023547094188378e-05, "loss": 2.0097, "step": 80020 }, { "epoch": 1.31, "learning_rate": 1.0018537074148297e-05, "loss": 2.0063, "step": 80030 }, { "epoch": 1.31, "learning_rate": 1.0013527054108216e-05, "loss": 2.0003, "step": 80040 }, { "epoch": 1.31, "learning_rate": 1.0008517034068137e-05, "loss": 1.9757, "step": 80050 }, { "epoch": 1.31, "learning_rate": 1.0003507014028056e-05, "loss": 2.0039, "step": 80060 }, { "epoch": 1.31, "learning_rate": 9.998496993987976e-06, "loss": 2.0379, "step": 80070 }, { "epoch": 1.31, "learning_rate": 9.993486973947897e-06, "loss": 1.9795, "step": 80080 }, { "epoch": 1.31, "learning_rate": 9.988476953907816e-06, "loss": 1.9905, "step": 80090 }, { "epoch": 1.31, "learning_rate": 9.983466933867735e-06, "loss": 1.9918, "step": 80100 }, { "epoch": 1.31, "learning_rate": 9.978456913827656e-06, "loss": 2.0296, "step": 80110 }, { "epoch": 1.31, "learning_rate": 9.973446893787576e-06, "loss": 2.0225, "step": 80120 }, { "epoch": 1.31, "learning_rate": 9.968436873747495e-06, "loss": 1.9622, "step": 80130 }, { "epoch": 1.31, "learning_rate": 9.963426853707416e-06, "loss": 2.0106, "step": 80140 }, { "epoch": 1.31, "learning_rate": 9.958416833667335e-06, "loss": 2.0089, "step": 80150 }, { "epoch": 1.31, "learning_rate": 9.953406813627254e-06, "loss": 1.9722, "step": 80160 }, { "epoch": 1.31, "learning_rate": 9.948396793587176e-06, "loss": 2.0397, "step": 80170 }, { "epoch": 1.31, "learning_rate": 9.943386773547095e-06, "loss": 2.0122, "step": 80180 }, { "epoch": 1.31, "learning_rate": 9.938376753507014e-06, "loss": 2.0366, "step": 80190 }, { "epoch": 1.31, "learning_rate": 9.933366733466935e-06, "loss": 2.0376, "step": 80200 }, { "epoch": 1.31, "learning_rate": 9.928356713426855e-06, "loss": 2.0484, "step": 80210 }, { "epoch": 1.31, "learning_rate": 9.923346693386774e-06, "loss": 1.9893, "step": 80220 }, { "epoch": 1.31, "learning_rate": 9.918336673346695e-06, "loss": 1.991, "step": 80230 }, { "epoch": 1.31, "learning_rate": 9.913326653306614e-06, "loss": 2.0518, "step": 80240 }, { "epoch": 1.31, "learning_rate": 9.908316633266533e-06, "loss": 2.0342, "step": 80250 }, { "epoch": 1.31, "learning_rate": 9.903306613226453e-06, "loss": 2.0104, "step": 80260 }, { "epoch": 1.31, "learning_rate": 9.898296593186374e-06, "loss": 2.0235, "step": 80270 }, { "epoch": 1.31, "learning_rate": 9.893286573146293e-06, "loss": 2.0317, "step": 80280 }, { "epoch": 1.31, "learning_rate": 9.888276553106214e-06, "loss": 1.9917, "step": 80290 }, { "epoch": 1.31, "learning_rate": 9.883266533066132e-06, "loss": 1.9925, "step": 80300 }, { "epoch": 1.31, "learning_rate": 9.878256513026053e-06, "loss": 2.0132, "step": 80310 }, { "epoch": 1.31, "learning_rate": 9.873246492985972e-06, "loss": 2.0325, "step": 80320 }, { "epoch": 1.31, "learning_rate": 9.868236472945893e-06, "loss": 2.0285, "step": 80330 }, { "epoch": 1.31, "learning_rate": 9.863226452905812e-06, "loss": 2.0041, "step": 80340 }, { "epoch": 1.31, "learning_rate": 9.858216432865732e-06, "loss": 2.0018, "step": 80350 }, { "epoch": 1.31, "learning_rate": 9.853206412825653e-06, "loss": 1.9786, "step": 80360 }, { "epoch": 1.31, "learning_rate": 9.848196392785572e-06, "loss": 1.9945, "step": 80370 }, { "epoch": 1.31, "learning_rate": 9.84318637274549e-06, "loss": 2.0015, "step": 80380 }, { "epoch": 1.31, "learning_rate": 9.838176352705411e-06, "loss": 2.0148, "step": 80390 }, { "epoch": 1.31, "learning_rate": 9.83316633266533e-06, "loss": 1.9909, "step": 80400 }, { "epoch": 1.31, "learning_rate": 9.828156312625251e-06, "loss": 2.0451, "step": 80410 }, { "epoch": 1.31, "learning_rate": 9.823146292585172e-06, "loss": 1.9693, "step": 80420 }, { "epoch": 1.31, "learning_rate": 9.81813627254509e-06, "loss": 1.9791, "step": 80430 }, { "epoch": 1.31, "learning_rate": 9.81312625250501e-06, "loss": 1.9844, "step": 80440 }, { "epoch": 1.31, "learning_rate": 9.80811623246493e-06, "loss": 2.018, "step": 80450 }, { "epoch": 1.31, "learning_rate": 9.803106212424851e-06, "loss": 2.0029, "step": 80460 }, { "epoch": 1.31, "learning_rate": 9.79809619238477e-06, "loss": 2.0032, "step": 80470 }, { "epoch": 1.32, "learning_rate": 9.79308617234469e-06, "loss": 2.0032, "step": 80480 }, { "epoch": 1.32, "learning_rate": 9.78807615230461e-06, "loss": 2.0325, "step": 80490 }, { "epoch": 1.32, "learning_rate": 9.783066132264528e-06, "loss": 2.0087, "step": 80500 }, { "epoch": 1.32, "learning_rate": 9.77805611222445e-06, "loss": 1.9928, "step": 80510 }, { "epoch": 1.32, "learning_rate": 9.77304609218437e-06, "loss": 2.0257, "step": 80520 }, { "epoch": 1.32, "learning_rate": 9.768036072144289e-06, "loss": 1.9743, "step": 80530 }, { "epoch": 1.32, "learning_rate": 9.76302605210421e-06, "loss": 2.0371, "step": 80540 }, { "epoch": 1.32, "learning_rate": 9.758016032064128e-06, "loss": 2.0252, "step": 80550 }, { "epoch": 1.32, "learning_rate": 9.753006012024049e-06, "loss": 2.066, "step": 80560 }, { "epoch": 1.32, "learning_rate": 9.74799599198397e-06, "loss": 2.032, "step": 80570 }, { "epoch": 1.32, "learning_rate": 9.742985971943888e-06, "loss": 2.0224, "step": 80580 }, { "epoch": 1.32, "learning_rate": 9.737975951903807e-06, "loss": 2.0155, "step": 80590 }, { "epoch": 1.32, "learning_rate": 9.732965931863728e-06, "loss": 2.0187, "step": 80600 }, { "epoch": 1.32, "learning_rate": 9.727955911823649e-06, "loss": 2.0069, "step": 80610 }, { "epoch": 1.32, "learning_rate": 9.722945891783568e-06, "loss": 2.0236, "step": 80620 }, { "epoch": 1.32, "learning_rate": 9.717935871743487e-06, "loss": 1.9943, "step": 80630 }, { "epoch": 1.32, "learning_rate": 9.712925851703407e-06, "loss": 2.0094, "step": 80640 }, { "epoch": 1.32, "learning_rate": 9.707915831663326e-06, "loss": 2.0067, "step": 80650 }, { "epoch": 1.32, "learning_rate": 9.702905811623247e-06, "loss": 1.9988, "step": 80660 }, { "epoch": 1.32, "learning_rate": 9.697895791583167e-06, "loss": 2.0291, "step": 80670 }, { "epoch": 1.32, "learning_rate": 9.692885771543086e-06, "loss": 1.9932, "step": 80680 }, { "epoch": 1.32, "learning_rate": 9.687875751503005e-06, "loss": 2.0205, "step": 80690 }, { "epoch": 1.32, "learning_rate": 9.682865731462926e-06, "loss": 2.0348, "step": 80700 }, { "epoch": 1.32, "learning_rate": 9.677855711422847e-06, "loss": 1.985, "step": 80710 }, { "epoch": 1.32, "learning_rate": 9.672845691382766e-06, "loss": 1.9906, "step": 80720 }, { "epoch": 1.32, "learning_rate": 9.667835671342686e-06, "loss": 1.9609, "step": 80730 }, { "epoch": 1.32, "learning_rate": 9.662825651302605e-06, "loss": 1.9891, "step": 80740 }, { "epoch": 1.32, "learning_rate": 9.657815631262526e-06, "loss": 2.0382, "step": 80750 }, { "epoch": 1.32, "learning_rate": 9.652805611222446e-06, "loss": 2.0058, "step": 80760 }, { "epoch": 1.32, "learning_rate": 9.647795591182365e-06, "loss": 2.0527, "step": 80770 }, { "epoch": 1.32, "learning_rate": 9.642785571142284e-06, "loss": 1.9951, "step": 80780 }, { "epoch": 1.32, "learning_rate": 9.637775551102205e-06, "loss": 1.9744, "step": 80790 }, { "epoch": 1.32, "learning_rate": 9.632765531062126e-06, "loss": 2.0299, "step": 80800 }, { "epoch": 1.32, "learning_rate": 9.627755511022044e-06, "loss": 1.9946, "step": 80810 }, { "epoch": 1.32, "learning_rate": 9.622745490981965e-06, "loss": 2.0118, "step": 80820 }, { "epoch": 1.32, "learning_rate": 9.617735470941884e-06, "loss": 2.006, "step": 80830 }, { "epoch": 1.32, "learning_rate": 9.612725450901803e-06, "loss": 1.9974, "step": 80840 }, { "epoch": 1.32, "learning_rate": 9.607715430861725e-06, "loss": 2.0012, "step": 80850 }, { "epoch": 1.32, "learning_rate": 9.602705410821644e-06, "loss": 2.029, "step": 80860 }, { "epoch": 1.32, "learning_rate": 9.597695390781563e-06, "loss": 1.9937, "step": 80870 }, { "epoch": 1.32, "learning_rate": 9.592685370741484e-06, "loss": 2.0406, "step": 80880 }, { "epoch": 1.32, "learning_rate": 9.587675350701403e-06, "loss": 1.9724, "step": 80890 }, { "epoch": 1.32, "learning_rate": 9.582665330661323e-06, "loss": 2.0051, "step": 80900 }, { "epoch": 1.32, "learning_rate": 9.577655310621242e-06, "loss": 1.9938, "step": 80910 }, { "epoch": 1.32, "learning_rate": 9.572645290581163e-06, "loss": 2.0194, "step": 80920 }, { "epoch": 1.32, "learning_rate": 9.567635270541082e-06, "loss": 2.0231, "step": 80930 }, { "epoch": 1.32, "learning_rate": 9.562625250501003e-06, "loss": 2.0152, "step": 80940 }, { "epoch": 1.32, "learning_rate": 9.557615230460923e-06, "loss": 2.0127, "step": 80950 }, { "epoch": 1.32, "learning_rate": 9.552605210420842e-06, "loss": 2.0066, "step": 80960 }, { "epoch": 1.32, "learning_rate": 9.547595190380761e-06, "loss": 2.0342, "step": 80970 }, { "epoch": 1.32, "learning_rate": 9.542585170340682e-06, "loss": 2.0078, "step": 80980 }, { "epoch": 1.32, "learning_rate": 9.5375751503006e-06, "loss": 2.0093, "step": 80990 }, { "epoch": 1.32, "learning_rate": 9.532565130260521e-06, "loss": 2.0699, "step": 81000 }, { "epoch": 1.32, "eval_loss": 2.0032448768615723, "eval_mean_f1": 0.6640865721717489, "eval_rouge1_f1": 0.7210205855736603, "eval_rouge1_precision": 0.8321823181988046, "eval_rouge1_recall": 0.6682634881217329, "eval_rouge2_f1": 0.5810863868515999, "eval_rouge2_precision": 0.6747723793133953, "eval_rouge2_recall": 0.5386908740299655, "eval_rougeL_f1": 0.6901527440899868, "eval_rougeL_precision": 0.7949762241179974, "eval_rougeL_recall": 0.6409391980126156, "eval_runtime": 69.3103, "eval_samples_per_second": 14.774, "eval_steps_per_second": 1.847, "step": 81000 }, { "epoch": 1.32, "learning_rate": 9.527555110220442e-06, "loss": 2.0138, "step": 81010 }, { "epoch": 1.32, "learning_rate": 9.522545090180361e-06, "loss": 1.9913, "step": 81020 }, { "epoch": 1.32, "learning_rate": 9.51753507014028e-06, "loss": 2.0449, "step": 81030 }, { "epoch": 1.32, "learning_rate": 9.5125250501002e-06, "loss": 2.012, "step": 81040 }, { "epoch": 1.32, "learning_rate": 9.507515030060121e-06, "loss": 2.0828, "step": 81050 }, { "epoch": 1.32, "learning_rate": 9.50250501002004e-06, "loss": 2.0139, "step": 81060 }, { "epoch": 1.32, "learning_rate": 9.49749498997996e-06, "loss": 2.0092, "step": 81070 }, { "epoch": 1.32, "learning_rate": 9.49248496993988e-06, "loss": 2.0443, "step": 81080 }, { "epoch": 1.32, "learning_rate": 9.487474949899799e-06, "loss": 2.0305, "step": 81090 }, { "epoch": 1.33, "learning_rate": 9.482464929859721e-06, "loss": 1.9854, "step": 81100 }, { "epoch": 1.33, "learning_rate": 9.47745490981964e-06, "loss": 2.0098, "step": 81110 }, { "epoch": 1.33, "learning_rate": 9.472444889779559e-06, "loss": 2.0207, "step": 81120 }, { "epoch": 1.33, "learning_rate": 9.46743486973948e-06, "loss": 1.9561, "step": 81130 }, { "epoch": 1.33, "learning_rate": 9.462424849699399e-06, "loss": 2.01, "step": 81140 }, { "epoch": 1.33, "learning_rate": 9.45741482965932e-06, "loss": 1.9777, "step": 81150 }, { "epoch": 1.33, "learning_rate": 9.45240480961924e-06, "loss": 1.9858, "step": 81160 }, { "epoch": 1.33, "learning_rate": 9.447394789579159e-06, "loss": 1.9639, "step": 81170 }, { "epoch": 1.33, "learning_rate": 9.442384769539078e-06, "loss": 1.9873, "step": 81180 }, { "epoch": 1.33, "learning_rate": 9.437374749498998e-06, "loss": 2.015, "step": 81190 }, { "epoch": 1.33, "learning_rate": 9.432364729458919e-06, "loss": 2.0281, "step": 81200 }, { "epoch": 1.33, "learning_rate": 9.427354709418838e-06, "loss": 2.0213, "step": 81210 }, { "epoch": 1.33, "learning_rate": 9.422344689378759e-06, "loss": 2.0126, "step": 81220 }, { "epoch": 1.33, "learning_rate": 9.417334669338678e-06, "loss": 2.0017, "step": 81230 }, { "epoch": 1.33, "learning_rate": 9.412324649298596e-06, "loss": 2.0466, "step": 81240 }, { "epoch": 1.33, "learning_rate": 9.407314629258517e-06, "loss": 1.9877, "step": 81250 }, { "epoch": 1.33, "learning_rate": 9.402304609218438e-06, "loss": 1.9705, "step": 81260 }, { "epoch": 1.33, "learning_rate": 9.397294589178357e-06, "loss": 1.9981, "step": 81270 }, { "epoch": 1.33, "learning_rate": 9.392284569138277e-06, "loss": 2.0205, "step": 81280 }, { "epoch": 1.33, "learning_rate": 9.387274549098198e-06, "loss": 1.998, "step": 81290 }, { "epoch": 1.33, "learning_rate": 9.382264529058117e-06, "loss": 2.003, "step": 81300 }, { "epoch": 1.33, "learning_rate": 9.377254509018036e-06, "loss": 1.9629, "step": 81310 }, { "epoch": 1.33, "learning_rate": 9.372244488977957e-06, "loss": 2.0098, "step": 81320 }, { "epoch": 1.33, "learning_rate": 9.367234468937875e-06, "loss": 1.9938, "step": 81330 }, { "epoch": 1.33, "learning_rate": 9.362224448897796e-06, "loss": 2.0011, "step": 81340 }, { "epoch": 1.33, "learning_rate": 9.357214428857717e-06, "loss": 2.0172, "step": 81350 }, { "epoch": 1.33, "learning_rate": 9.352204408817636e-06, "loss": 2.0545, "step": 81360 }, { "epoch": 1.33, "learning_rate": 9.347194388777555e-06, "loss": 1.9918, "step": 81370 }, { "epoch": 1.33, "learning_rate": 9.342184368737475e-06, "loss": 2.0137, "step": 81380 }, { "epoch": 1.33, "learning_rate": 9.337174348697396e-06, "loss": 2.0233, "step": 81390 }, { "epoch": 1.33, "learning_rate": 9.332164328657315e-06, "loss": 2.0389, "step": 81400 }, { "epoch": 1.33, "learning_rate": 9.327154308617236e-06, "loss": 1.982, "step": 81410 }, { "epoch": 1.33, "learning_rate": 9.322144288577154e-06, "loss": 2.0463, "step": 81420 }, { "epoch": 1.33, "learning_rate": 9.317134268537073e-06, "loss": 2.0327, "step": 81430 }, { "epoch": 1.33, "learning_rate": 9.312124248496996e-06, "loss": 2.0226, "step": 81440 }, { "epoch": 1.33, "learning_rate": 9.307114228456915e-06, "loss": 2.0065, "step": 81450 }, { "epoch": 1.33, "learning_rate": 9.302104208416834e-06, "loss": 2.0352, "step": 81460 }, { "epoch": 1.33, "learning_rate": 9.297094188376754e-06, "loss": 2.023, "step": 81470 }, { "epoch": 1.33, "learning_rate": 9.292084168336673e-06, "loss": 2.0069, "step": 81480 }, { "epoch": 1.33, "learning_rate": 9.287074148296594e-06, "loss": 2.0275, "step": 81490 }, { "epoch": 1.33, "learning_rate": 9.282064128256515e-06, "loss": 2.0168, "step": 81500 }, { "epoch": 1.33, "learning_rate": 9.277054108216433e-06, "loss": 1.9932, "step": 81510 }, { "epoch": 1.33, "learning_rate": 9.272044088176352e-06, "loss": 1.9952, "step": 81520 }, { "epoch": 1.33, "learning_rate": 9.267034068136273e-06, "loss": 2.0126, "step": 81530 }, { "epoch": 1.33, "learning_rate": 9.262024048096194e-06, "loss": 2.0359, "step": 81540 }, { "epoch": 1.33, "learning_rate": 9.257014028056113e-06, "loss": 2.0171, "step": 81550 }, { "epoch": 1.33, "learning_rate": 9.252004008016033e-06, "loss": 2.0138, "step": 81560 }, { "epoch": 1.33, "learning_rate": 9.246993987975952e-06, "loss": 1.9925, "step": 81570 }, { "epoch": 1.33, "learning_rate": 9.241983967935871e-06, "loss": 2.0458, "step": 81580 }, { "epoch": 1.33, "learning_rate": 9.236973947895792e-06, "loss": 2.0005, "step": 81590 }, { "epoch": 1.33, "learning_rate": 9.231963927855712e-06, "loss": 2.0113, "step": 81600 }, { "epoch": 1.33, "learning_rate": 9.226953907815631e-06, "loss": 2.0303, "step": 81610 }, { "epoch": 1.33, "learning_rate": 9.221943887775552e-06, "loss": 2.021, "step": 81620 }, { "epoch": 1.33, "learning_rate": 9.216933867735471e-06, "loss": 1.9622, "step": 81630 }, { "epoch": 1.33, "learning_rate": 9.211923847695392e-06, "loss": 2.024, "step": 81640 }, { "epoch": 1.33, "learning_rate": 9.20691382765531e-06, "loss": 2.0131, "step": 81650 }, { "epoch": 1.33, "learning_rate": 9.201903807615231e-06, "loss": 2.0125, "step": 81660 }, { "epoch": 1.33, "learning_rate": 9.19689378757515e-06, "loss": 1.9934, "step": 81670 }, { "epoch": 1.33, "learning_rate": 9.191883767535069e-06, "loss": 1.9978, "step": 81680 }, { "epoch": 1.33, "learning_rate": 9.186873747494991e-06, "loss": 2.0138, "step": 81690 }, { "epoch": 1.33, "learning_rate": 9.18186372745491e-06, "loss": 2.0098, "step": 81700 }, { "epoch": 1.34, "learning_rate": 9.17685370741483e-06, "loss": 2.055, "step": 81710 }, { "epoch": 1.34, "learning_rate": 9.17184368737475e-06, "loss": 1.9633, "step": 81720 }, { "epoch": 1.34, "learning_rate": 9.166833667334669e-06, "loss": 2.0085, "step": 81730 }, { "epoch": 1.34, "learning_rate": 9.16182364729459e-06, "loss": 2.0368, "step": 81740 }, { "epoch": 1.34, "learning_rate": 9.15681362725451e-06, "loss": 2.0264, "step": 81750 }, { "epoch": 1.34, "learning_rate": 9.15180360721443e-06, "loss": 1.9932, "step": 81760 }, { "epoch": 1.34, "learning_rate": 9.146793587174348e-06, "loss": 1.9718, "step": 81770 }, { "epoch": 1.34, "learning_rate": 9.141783567134269e-06, "loss": 2.0045, "step": 81780 }, { "epoch": 1.34, "learning_rate": 9.13677354709419e-06, "loss": 2.0053, "step": 81790 }, { "epoch": 1.34, "learning_rate": 9.131763527054108e-06, "loss": 2.0052, "step": 81800 }, { "epoch": 1.34, "learning_rate": 9.126753507014029e-06, "loss": 2.0376, "step": 81810 }, { "epoch": 1.34, "learning_rate": 9.121743486973948e-06, "loss": 2.0235, "step": 81820 }, { "epoch": 1.34, "learning_rate": 9.116733466933867e-06, "loss": 1.9697, "step": 81830 }, { "epoch": 1.34, "learning_rate": 9.11172344689379e-06, "loss": 2.018, "step": 81840 }, { "epoch": 1.34, "learning_rate": 9.106713426853708e-06, "loss": 2.0115, "step": 81850 }, { "epoch": 1.34, "learning_rate": 9.101703406813627e-06, "loss": 2.0369, "step": 81860 }, { "epoch": 1.34, "learning_rate": 9.096693386773548e-06, "loss": 2.0164, "step": 81870 }, { "epoch": 1.34, "learning_rate": 9.091683366733468e-06, "loss": 2.0358, "step": 81880 }, { "epoch": 1.34, "learning_rate": 9.086673346693387e-06, "loss": 2.032, "step": 81890 }, { "epoch": 1.34, "learning_rate": 9.081663326653308e-06, "loss": 2.0314, "step": 81900 }, { "epoch": 1.34, "learning_rate": 9.076653306613227e-06, "loss": 2.0177, "step": 81910 }, { "epoch": 1.34, "learning_rate": 9.071643286573146e-06, "loss": 2.0031, "step": 81920 }, { "epoch": 1.34, "learning_rate": 9.066633266533067e-06, "loss": 1.9878, "step": 81930 }, { "epoch": 1.34, "learning_rate": 9.061623246492987e-06, "loss": 2.0116, "step": 81940 }, { "epoch": 1.34, "learning_rate": 9.057114228456914e-06, "loss": 1.9995, "step": 81950 }, { "epoch": 1.34, "learning_rate": 9.052104208416834e-06, "loss": 2.0496, "step": 81960 }, { "epoch": 1.34, "learning_rate": 9.047094188376753e-06, "loss": 2.0201, "step": 81970 }, { "epoch": 1.34, "learning_rate": 9.042084168336674e-06, "loss": 2.0208, "step": 81980 }, { "epoch": 1.34, "learning_rate": 9.037074148296595e-06, "loss": 2.023, "step": 81990 }, { "epoch": 1.34, "learning_rate": 9.032064128256514e-06, "loss": 1.975, "step": 82000 }, { "epoch": 1.34, "eval_loss": 2.004032611846924, "eval_mean_f1": 0.6568997667408865, "eval_rouge1_f1": 0.7150581266230047, "eval_rouge1_precision": 0.8253557782150953, "eval_rouge1_recall": 0.6636577776812191, "eval_rouge2_f1": 0.5721947477122453, "eval_rouge2_precision": 0.6650406058242972, "eval_rouge2_recall": 0.5309910759568397, "eval_rougeL_f1": 0.6834464258874093, "eval_rougeL_precision": 0.7877775484192073, "eval_rougeL_recall": 0.6352585899034581, "eval_runtime": 66.0291, "eval_samples_per_second": 15.508, "eval_steps_per_second": 1.939, "step": 82000 }, { "epoch": 1.34, "learning_rate": 9.027054108216432e-06, "loss": 2.0136, "step": 82010 }, { "epoch": 1.34, "learning_rate": 9.022044088176353e-06, "loss": 2.0103, "step": 82020 }, { "epoch": 1.34, "learning_rate": 9.017034068136274e-06, "loss": 2.0601, "step": 82030 }, { "epoch": 1.34, "learning_rate": 9.012024048096193e-06, "loss": 2.0534, "step": 82040 }, { "epoch": 1.34, "learning_rate": 9.007014028056113e-06, "loss": 2.0198, "step": 82050 }, { "epoch": 1.34, "learning_rate": 9.002004008016032e-06, "loss": 2.0118, "step": 82060 }, { "epoch": 1.34, "learning_rate": 8.996993987975951e-06, "loss": 2.0713, "step": 82070 }, { "epoch": 1.34, "learning_rate": 8.991983967935874e-06, "loss": 2.0275, "step": 82080 }, { "epoch": 1.34, "learning_rate": 8.986973947895793e-06, "loss": 2.0122, "step": 82090 }, { "epoch": 1.34, "learning_rate": 8.981963927855711e-06, "loss": 1.9918, "step": 82100 }, { "epoch": 1.34, "learning_rate": 8.976953907815632e-06, "loss": 1.9868, "step": 82110 }, { "epoch": 1.34, "learning_rate": 8.971943887775551e-06, "loss": 2.0276, "step": 82120 }, { "epoch": 1.34, "learning_rate": 8.966933867735472e-06, "loss": 1.9883, "step": 82130 }, { "epoch": 1.34, "learning_rate": 8.96192384769539e-06, "loss": 1.9719, "step": 82140 }, { "epoch": 1.34, "learning_rate": 8.956913827655311e-06, "loss": 2.0298, "step": 82150 }, { "epoch": 1.34, "learning_rate": 8.95190380761523e-06, "loss": 2.0146, "step": 82160 }, { "epoch": 1.34, "learning_rate": 8.946893787575151e-06, "loss": 2.0239, "step": 82170 }, { "epoch": 1.34, "learning_rate": 8.941883767535072e-06, "loss": 2.001, "step": 82180 }, { "epoch": 1.34, "learning_rate": 8.93687374749499e-06, "loss": 2.0275, "step": 82190 }, { "epoch": 1.34, "learning_rate": 8.93186372745491e-06, "loss": 2.0088, "step": 82200 }, { "epoch": 1.34, "learning_rate": 8.92685370741483e-06, "loss": 2.0332, "step": 82210 }, { "epoch": 1.34, "learning_rate": 8.921843687374749e-06, "loss": 1.9844, "step": 82220 }, { "epoch": 1.34, "learning_rate": 8.91683366733467e-06, "loss": 1.9798, "step": 82230 }, { "epoch": 1.34, "learning_rate": 8.91182364729459e-06, "loss": 2.0126, "step": 82240 }, { "epoch": 1.34, "learning_rate": 8.90681362725451e-06, "loss": 2.0331, "step": 82250 }, { "epoch": 1.34, "learning_rate": 8.901803607214428e-06, "loss": 1.9813, "step": 82260 }, { "epoch": 1.34, "learning_rate": 8.896793587174349e-06, "loss": 2.0092, "step": 82270 }, { "epoch": 1.34, "learning_rate": 8.89178356713427e-06, "loss": 2.0412, "step": 82280 }, { "epoch": 1.34, "learning_rate": 8.886773547094188e-06, "loss": 1.966, "step": 82290 }, { "epoch": 1.34, "learning_rate": 8.881763527054109e-06, "loss": 2.0081, "step": 82300 }, { "epoch": 1.34, "learning_rate": 8.876753507014028e-06, "loss": 1.9741, "step": 82310 }, { "epoch": 1.35, "learning_rate": 8.871743486973947e-06, "loss": 2.013, "step": 82320 }, { "epoch": 1.35, "learning_rate": 8.86673346693387e-06, "loss": 2.0264, "step": 82330 }, { "epoch": 1.35, "learning_rate": 8.861723446893788e-06, "loss": 2.0275, "step": 82340 }, { "epoch": 1.35, "learning_rate": 8.856713426853707e-06, "loss": 2.062, "step": 82350 }, { "epoch": 1.35, "learning_rate": 8.851703406813628e-06, "loss": 2.0392, "step": 82360 }, { "epoch": 1.35, "learning_rate": 8.846693386773547e-06, "loss": 1.9468, "step": 82370 }, { "epoch": 1.35, "learning_rate": 8.841683366733467e-06, "loss": 1.9795, "step": 82380 }, { "epoch": 1.35, "learning_rate": 8.836673346693388e-06, "loss": 2.0488, "step": 82390 }, { "epoch": 1.35, "learning_rate": 8.831663326653307e-06, "loss": 2.0222, "step": 82400 }, { "epoch": 1.35, "learning_rate": 8.826653306613226e-06, "loss": 2.0548, "step": 82410 }, { "epoch": 1.35, "learning_rate": 8.821643286573147e-06, "loss": 2.0448, "step": 82420 }, { "epoch": 1.35, "learning_rate": 8.816633266533067e-06, "loss": 2.0248, "step": 82430 }, { "epoch": 1.35, "learning_rate": 8.811623246492986e-06, "loss": 2.0245, "step": 82440 }, { "epoch": 1.35, "learning_rate": 8.806613226452907e-06, "loss": 1.9921, "step": 82450 }, { "epoch": 1.35, "learning_rate": 8.801603206412826e-06, "loss": 1.9949, "step": 82460 }, { "epoch": 1.35, "learning_rate": 8.796593186372746e-06, "loss": 2.033, "step": 82470 }, { "epoch": 1.35, "learning_rate": 8.791583166332665e-06, "loss": 1.9741, "step": 82480 }, { "epoch": 1.35, "learning_rate": 8.786573146292586e-06, "loss": 1.9743, "step": 82490 }, { "epoch": 1.35, "learning_rate": 8.781563126252505e-06, "loss": 2.0078, "step": 82500 }, { "epoch": 1.35, "learning_rate": 8.776553106212426e-06, "loss": 2.0091, "step": 82510 }, { "epoch": 1.35, "learning_rate": 8.771543086172346e-06, "loss": 1.9808, "step": 82520 }, { "epoch": 1.35, "learning_rate": 8.766533066132265e-06, "loss": 2.0269, "step": 82530 }, { "epoch": 1.35, "learning_rate": 8.761523046092184e-06, "loss": 1.9899, "step": 82540 }, { "epoch": 1.35, "learning_rate": 8.756513026052105e-06, "loss": 1.997, "step": 82550 }, { "epoch": 1.35, "learning_rate": 8.751503006012024e-06, "loss": 1.9795, "step": 82560 }, { "epoch": 1.35, "learning_rate": 8.746492985971944e-06, "loss": 1.9976, "step": 82570 }, { "epoch": 1.35, "learning_rate": 8.741482965931865e-06, "loss": 2.0082, "step": 82580 }, { "epoch": 1.35, "learning_rate": 8.736472945891784e-06, "loss": 2.002, "step": 82590 }, { "epoch": 1.35, "learning_rate": 8.731462925851703e-06, "loss": 2.0353, "step": 82600 }, { "epoch": 1.35, "learning_rate": 8.726452905811624e-06, "loss": 1.9905, "step": 82610 }, { "epoch": 1.35, "learning_rate": 8.721442885771544e-06, "loss": 1.9935, "step": 82620 }, { "epoch": 1.35, "learning_rate": 8.716432865731463e-06, "loss": 2.013, "step": 82630 }, { "epoch": 1.35, "learning_rate": 8.711422845691384e-06, "loss": 1.975, "step": 82640 }, { "epoch": 1.35, "learning_rate": 8.706412825651303e-06, "loss": 2.033, "step": 82650 }, { "epoch": 1.35, "learning_rate": 8.701402805611222e-06, "loss": 2.0306, "step": 82660 }, { "epoch": 1.35, "learning_rate": 8.696392785571144e-06, "loss": 2.0618, "step": 82670 }, { "epoch": 1.35, "learning_rate": 8.691382765531063e-06, "loss": 2.0428, "step": 82680 }, { "epoch": 1.35, "learning_rate": 8.686372745490982e-06, "loss": 1.9744, "step": 82690 }, { "epoch": 1.35, "learning_rate": 8.681362725450903e-06, "loss": 2.0396, "step": 82700 }, { "epoch": 1.35, "learning_rate": 8.676352705410821e-06, "loss": 1.999, "step": 82710 }, { "epoch": 1.35, "learning_rate": 8.671342685370742e-06, "loss": 2.0366, "step": 82720 }, { "epoch": 1.35, "learning_rate": 8.666332665330663e-06, "loss": 2.0031, "step": 82730 }, { "epoch": 1.35, "learning_rate": 8.661322645290582e-06, "loss": 2.0061, "step": 82740 }, { "epoch": 1.35, "learning_rate": 8.6563126252505e-06, "loss": 1.9436, "step": 82750 }, { "epoch": 1.35, "learning_rate": 8.651302605210421e-06, "loss": 2.0172, "step": 82760 }, { "epoch": 1.35, "learning_rate": 8.646292585170342e-06, "loss": 1.9938, "step": 82770 }, { "epoch": 1.35, "learning_rate": 8.641282565130261e-06, "loss": 2.0267, "step": 82780 }, { "epoch": 1.35, "learning_rate": 8.636272545090182e-06, "loss": 2.0072, "step": 82790 }, { "epoch": 1.35, "learning_rate": 8.6312625250501e-06, "loss": 1.9649, "step": 82800 }, { "epoch": 1.35, "learning_rate": 8.62625250501002e-06, "loss": 1.9927, "step": 82810 }, { "epoch": 1.35, "learning_rate": 8.62124248496994e-06, "loss": 2.0313, "step": 82820 }, { "epoch": 1.35, "learning_rate": 8.61623246492986e-06, "loss": 2.0184, "step": 82830 }, { "epoch": 1.35, "learning_rate": 8.61122244488978e-06, "loss": 1.9759, "step": 82840 }, { "epoch": 1.35, "learning_rate": 8.6062124248497e-06, "loss": 1.9817, "step": 82850 }, { "epoch": 1.35, "learning_rate": 8.60120240480962e-06, "loss": 2.0147, "step": 82860 }, { "epoch": 1.35, "learning_rate": 8.59619238476954e-06, "loss": 2.0318, "step": 82870 }, { "epoch": 1.35, "learning_rate": 8.591182364729459e-06, "loss": 2.0187, "step": 82880 }, { "epoch": 1.35, "learning_rate": 8.58617234468938e-06, "loss": 2.0072, "step": 82890 }, { "epoch": 1.35, "learning_rate": 8.581162324649298e-06, "loss": 2.0473, "step": 82900 }, { "epoch": 1.35, "learning_rate": 8.576152304609217e-06, "loss": 1.9608, "step": 82910 }, { "epoch": 1.35, "learning_rate": 8.57114228456914e-06, "loss": 1.994, "step": 82920 }, { "epoch": 1.36, "learning_rate": 8.566132264529059e-06, "loss": 1.9987, "step": 82930 }, { "epoch": 1.36, "learning_rate": 8.561122244488978e-06, "loss": 1.9787, "step": 82940 }, { "epoch": 1.36, "learning_rate": 8.556112224448898e-06, "loss": 1.9967, "step": 82950 }, { "epoch": 1.36, "learning_rate": 8.551102204408817e-06, "loss": 2.0056, "step": 82960 }, { "epoch": 1.36, "learning_rate": 8.546092184368738e-06, "loss": 2.007, "step": 82970 }, { "epoch": 1.36, "learning_rate": 8.541082164328658e-06, "loss": 2.017, "step": 82980 }, { "epoch": 1.36, "learning_rate": 8.536072144288577e-06, "loss": 2.0104, "step": 82990 }, { "epoch": 1.36, "learning_rate": 8.531062124248496e-06, "loss": 1.9915, "step": 83000 }, { "epoch": 1.36, "eval_loss": 2.005157947540283, "eval_mean_f1": 0.6619423051998229, "eval_rouge1_f1": 0.7178919518147202, "eval_rouge1_precision": 0.8280265244642254, "eval_rouge1_recall": 0.666659793336547, "eval_rouge2_f1": 0.5796294168938703, "eval_rouge2_precision": 0.6725216508480668, "eval_rouge2_recall": 0.5384267063142059, "eval_rougeL_f1": 0.6883055468908781, "eval_rougeL_precision": 0.7923907646093562, "eval_rougeL_recall": 0.6399493277947866, "eval_runtime": 65.1052, "eval_samples_per_second": 15.728, "eval_steps_per_second": 1.966, "step": 83000 }, { "epoch": 1.36, "learning_rate": 8.526052104208419e-06, "loss": 2.0063, "step": 83010 }, { "epoch": 1.36, "learning_rate": 8.521042084168338e-06, "loss": 1.9982, "step": 83020 }, { "epoch": 1.36, "learning_rate": 8.516032064128257e-06, "loss": 2.0137, "step": 83030 }, { "epoch": 1.36, "learning_rate": 8.511022044088177e-06, "loss": 2.0381, "step": 83040 }, { "epoch": 1.36, "learning_rate": 8.506012024048096e-06, "loss": 2.0139, "step": 83050 }, { "epoch": 1.36, "learning_rate": 8.501002004008017e-06, "loss": 1.9847, "step": 83060 }, { "epoch": 1.36, "learning_rate": 8.495991983967937e-06, "loss": 2.0082, "step": 83070 }, { "epoch": 1.36, "learning_rate": 8.490981963927856e-06, "loss": 2.0169, "step": 83080 }, { "epoch": 1.36, "learning_rate": 8.485971943887775e-06, "loss": 2.0382, "step": 83090 }, { "epoch": 1.36, "learning_rate": 8.480961923847696e-06, "loss": 1.9601, "step": 83100 }, { "epoch": 1.36, "learning_rate": 8.475951903807617e-06, "loss": 2.0171, "step": 83110 }, { "epoch": 1.36, "learning_rate": 8.470941883767536e-06, "loss": 2.0302, "step": 83120 }, { "epoch": 1.36, "learning_rate": 8.465931863727456e-06, "loss": 2.0295, "step": 83130 }, { "epoch": 1.36, "learning_rate": 8.460921843687375e-06, "loss": 2.0233, "step": 83140 }, { "epoch": 1.36, "learning_rate": 8.455911823647294e-06, "loss": 2.0274, "step": 83150 }, { "epoch": 1.36, "learning_rate": 8.450901803607215e-06, "loss": 2.003, "step": 83160 }, { "epoch": 1.36, "learning_rate": 8.445891783567135e-06, "loss": 1.9936, "step": 83170 }, { "epoch": 1.36, "learning_rate": 8.440881763527054e-06, "loss": 1.996, "step": 83180 }, { "epoch": 1.36, "learning_rate": 8.435871743486973e-06, "loss": 2.0273, "step": 83190 }, { "epoch": 1.36, "learning_rate": 8.430861723446894e-06, "loss": 2.0641, "step": 83200 }, { "epoch": 1.36, "learning_rate": 8.425851703406815e-06, "loss": 1.9979, "step": 83210 }, { "epoch": 1.36, "learning_rate": 8.420841683366734e-06, "loss": 1.9979, "step": 83220 }, { "epoch": 1.36, "learning_rate": 8.415831663326654e-06, "loss": 2.0108, "step": 83230 }, { "epoch": 1.36, "learning_rate": 8.410821643286573e-06, "loss": 2.0665, "step": 83240 }, { "epoch": 1.36, "learning_rate": 8.405811623246492e-06, "loss": 2.0189, "step": 83250 }, { "epoch": 1.36, "learning_rate": 8.400801603206414e-06, "loss": 2.0725, "step": 83260 }, { "epoch": 1.36, "learning_rate": 8.395791583166333e-06, "loss": 1.9799, "step": 83270 }, { "epoch": 1.36, "learning_rate": 8.390781563126252e-06, "loss": 1.9994, "step": 83280 }, { "epoch": 1.36, "learning_rate": 8.385771543086173e-06, "loss": 2.0022, "step": 83290 }, { "epoch": 1.36, "learning_rate": 8.380761523046092e-06, "loss": 1.9872, "step": 83300 }, { "epoch": 1.36, "learning_rate": 8.375751503006013e-06, "loss": 1.996, "step": 83310 }, { "epoch": 1.36, "learning_rate": 8.370741482965933e-06, "loss": 2.0357, "step": 83320 }, { "epoch": 1.36, "learning_rate": 8.365731462925852e-06, "loss": 2.0074, "step": 83330 }, { "epoch": 1.36, "learning_rate": 8.360721442885771e-06, "loss": 2.0137, "step": 83340 }, { "epoch": 1.36, "learning_rate": 8.355711422845692e-06, "loss": 2.0401, "step": 83350 }, { "epoch": 1.36, "learning_rate": 8.350701402805612e-06, "loss": 2.0391, "step": 83360 }, { "epoch": 1.36, "learning_rate": 8.345691382765531e-06, "loss": 2.0261, "step": 83370 }, { "epoch": 1.36, "learning_rate": 8.340681362725452e-06, "loss": 2.0217, "step": 83380 }, { "epoch": 1.36, "learning_rate": 8.335671342685371e-06, "loss": 2.0023, "step": 83390 }, { "epoch": 1.36, "learning_rate": 8.33066132264529e-06, "loss": 2.009, "step": 83400 }, { "epoch": 1.36, "learning_rate": 8.32565130260521e-06, "loss": 2.0404, "step": 83410 }, { "epoch": 1.36, "learning_rate": 8.320641282565131e-06, "loss": 2.0142, "step": 83420 }, { "epoch": 1.36, "learning_rate": 8.31563126252505e-06, "loss": 2.0212, "step": 83430 }, { "epoch": 1.36, "learning_rate": 8.31062124248497e-06, "loss": 2.0254, "step": 83440 }, { "epoch": 1.36, "learning_rate": 8.30561122244489e-06, "loss": 2.0099, "step": 83450 }, { "epoch": 1.36, "learning_rate": 8.30060120240481e-06, "loss": 2.0036, "step": 83460 }, { "epoch": 1.36, "learning_rate": 8.29559118236473e-06, "loss": 2.0497, "step": 83470 }, { "epoch": 1.36, "learning_rate": 8.29058116232465e-06, "loss": 2.0151, "step": 83480 }, { "epoch": 1.36, "learning_rate": 8.285571142284569e-06, "loss": 1.9629, "step": 83490 }, { "epoch": 1.36, "learning_rate": 8.28056112224449e-06, "loss": 1.9581, "step": 83500 }, { "epoch": 1.36, "learning_rate": 8.27555110220441e-06, "loss": 1.9872, "step": 83510 }, { "epoch": 1.36, "learning_rate": 8.270541082164329e-06, "loss": 2.0212, "step": 83520 }, { "epoch": 1.36, "learning_rate": 8.265531062124248e-06, "loss": 1.9911, "step": 83530 }, { "epoch": 1.37, "learning_rate": 8.260521042084169e-06, "loss": 1.9908, "step": 83540 }, { "epoch": 1.37, "learning_rate": 8.255511022044088e-06, "loss": 2.0107, "step": 83550 }, { "epoch": 1.37, "learning_rate": 8.250501002004008e-06, "loss": 1.9777, "step": 83560 }, { "epoch": 1.37, "learning_rate": 8.245490981963929e-06, "loss": 2.0175, "step": 83570 }, { "epoch": 1.37, "learning_rate": 8.240480961923848e-06, "loss": 2.0411, "step": 83580 }, { "epoch": 1.37, "learning_rate": 8.235470941883767e-06, "loss": 2.0013, "step": 83590 }, { "epoch": 1.37, "learning_rate": 8.230460921843689e-06, "loss": 2.0514, "step": 83600 }, { "epoch": 1.37, "learning_rate": 8.225450901803608e-06, "loss": 2.0384, "step": 83610 }, { "epoch": 1.37, "learning_rate": 8.220440881763527e-06, "loss": 2.0073, "step": 83620 }, { "epoch": 1.37, "learning_rate": 8.215430861723448e-06, "loss": 2.0412, "step": 83630 }, { "epoch": 1.37, "learning_rate": 8.210420841683367e-06, "loss": 2.0176, "step": 83640 }, { "epoch": 1.37, "learning_rate": 8.205410821643287e-06, "loss": 1.998, "step": 83650 }, { "epoch": 1.37, "learning_rate": 8.200400801603208e-06, "loss": 1.9674, "step": 83660 }, { "epoch": 1.37, "learning_rate": 8.195390781563127e-06, "loss": 2.0026, "step": 83670 }, { "epoch": 1.37, "learning_rate": 8.190380761523046e-06, "loss": 2.0165, "step": 83680 }, { "epoch": 1.37, "learning_rate": 8.185370741482966e-06, "loss": 2.0094, "step": 83690 }, { "epoch": 1.37, "learning_rate": 8.180360721442887e-06, "loss": 2.0056, "step": 83700 }, { "epoch": 1.37, "learning_rate": 8.175350701402806e-06, "loss": 1.9764, "step": 83710 }, { "epoch": 1.37, "learning_rate": 8.170340681362727e-06, "loss": 2.0036, "step": 83720 }, { "epoch": 1.37, "learning_rate": 8.165330661322646e-06, "loss": 1.9919, "step": 83730 }, { "epoch": 1.37, "learning_rate": 8.160320641282565e-06, "loss": 1.9913, "step": 83740 }, { "epoch": 1.37, "learning_rate": 8.155310621242485e-06, "loss": 2.0052, "step": 83750 }, { "epoch": 1.37, "learning_rate": 8.150300601202406e-06, "loss": 2.0113, "step": 83760 }, { "epoch": 1.37, "learning_rate": 8.145290581162325e-06, "loss": 2.0169, "step": 83770 }, { "epoch": 1.37, "learning_rate": 8.140280561122245e-06, "loss": 1.9866, "step": 83780 }, { "epoch": 1.37, "learning_rate": 8.135270541082164e-06, "loss": 2.0333, "step": 83790 }, { "epoch": 1.37, "learning_rate": 8.130260521042085e-06, "loss": 2.0306, "step": 83800 }, { "epoch": 1.37, "learning_rate": 8.125250501002004e-06, "loss": 1.9867, "step": 83810 }, { "epoch": 1.37, "learning_rate": 8.120240480961925e-06, "loss": 2.0484, "step": 83820 }, { "epoch": 1.37, "learning_rate": 8.115230460921844e-06, "loss": 1.9891, "step": 83830 }, { "epoch": 1.37, "learning_rate": 8.110220440881764e-06, "loss": 1.9553, "step": 83840 }, { "epoch": 1.37, "learning_rate": 8.105210420841685e-06, "loss": 2.0015, "step": 83850 }, { "epoch": 1.37, "learning_rate": 8.100200400801604e-06, "loss": 2.0072, "step": 83860 }, { "epoch": 1.37, "learning_rate": 8.095190380761523e-06, "loss": 1.987, "step": 83870 }, { "epoch": 1.37, "learning_rate": 8.090180360721443e-06, "loss": 2.005, "step": 83880 }, { "epoch": 1.37, "learning_rate": 8.085170340681362e-06, "loss": 2.0034, "step": 83890 }, { "epoch": 1.37, "learning_rate": 8.080160320641283e-06, "loss": 2.0129, "step": 83900 }, { "epoch": 1.37, "learning_rate": 8.075150300601204e-06, "loss": 2.0466, "step": 83910 }, { "epoch": 1.37, "learning_rate": 8.070140280561123e-06, "loss": 2.0526, "step": 83920 }, { "epoch": 1.37, "learning_rate": 8.065130260521041e-06, "loss": 2.0264, "step": 83930 }, { "epoch": 1.37, "learning_rate": 8.060120240480962e-06, "loss": 2.0138, "step": 83940 }, { "epoch": 1.37, "learning_rate": 8.055110220440883e-06, "loss": 2.017, "step": 83950 }, { "epoch": 1.37, "learning_rate": 8.050100200400802e-06, "loss": 1.9899, "step": 83960 }, { "epoch": 1.37, "learning_rate": 8.045090180360722e-06, "loss": 2.0536, "step": 83970 }, { "epoch": 1.37, "learning_rate": 8.040080160320641e-06, "loss": 2.0004, "step": 83980 }, { "epoch": 1.37, "learning_rate": 8.03507014028056e-06, "loss": 2.0014, "step": 83990 }, { "epoch": 1.37, "learning_rate": 8.030060120240483e-06, "loss": 2.035, "step": 84000 }, { "epoch": 1.37, "eval_loss": 2.0019044876098633, "eval_mean_f1": 0.662538630694277, "eval_rouge1_f1": 0.7200841047773315, "eval_rouge1_precision": 0.8325290428637309, "eval_rouge1_recall": 0.667806350400854, "eval_rouge2_f1": 0.5778400921343703, "eval_rouge2_precision": 0.6725563051856998, "eval_rouge2_recall": 0.5360981968766413, "eval_rougeL_f1": 0.6896916951711292, "eval_rougeL_precision": 0.7955780538411372, "eval_rougeL_recall": 0.6406166043975448, "eval_runtime": 69.4285, "eval_samples_per_second": 14.749, "eval_steps_per_second": 1.844, "step": 84000 }, { "epoch": 1.37, "learning_rate": 8.025050100200402e-06, "loss": 1.9849, "step": 84010 }, { "epoch": 1.37, "learning_rate": 8.02004008016032e-06, "loss": 1.989, "step": 84020 }, { "epoch": 1.37, "learning_rate": 8.015030060120241e-06, "loss": 2.006, "step": 84030 }, { "epoch": 1.37, "learning_rate": 8.01002004008016e-06, "loss": 2.0184, "step": 84040 }, { "epoch": 1.37, "learning_rate": 8.00501002004008e-06, "loss": 2.0155, "step": 84050 }, { "epoch": 1.37, "learning_rate": 8.000000000000001e-06, "loss": 1.9349, "step": 84060 }, { "epoch": 1.37, "learning_rate": 7.99498997995992e-06, "loss": 2.0134, "step": 84070 }, { "epoch": 1.37, "learning_rate": 7.98997995991984e-06, "loss": 2.0191, "step": 84080 }, { "epoch": 1.37, "learning_rate": 7.98496993987976e-06, "loss": 2.0415, "step": 84090 }, { "epoch": 1.37, "learning_rate": 7.97995991983968e-06, "loss": 2.0365, "step": 84100 }, { "epoch": 1.37, "learning_rate": 7.9749498997996e-06, "loss": 2.0311, "step": 84110 }, { "epoch": 1.37, "learning_rate": 7.96993987975952e-06, "loss": 2.0036, "step": 84120 }, { "epoch": 1.37, "learning_rate": 7.964929859719439e-06, "loss": 1.9809, "step": 84130 }, { "epoch": 1.37, "learning_rate": 7.95991983967936e-06, "loss": 2.0276, "step": 84140 }, { "epoch": 1.38, "learning_rate": 7.954909819639279e-06, "loss": 1.9436, "step": 84150 }, { "epoch": 1.38, "learning_rate": 7.9498997995992e-06, "loss": 2.0027, "step": 84160 }, { "epoch": 1.38, "learning_rate": 7.944889779559118e-06, "loss": 1.9901, "step": 84170 }, { "epoch": 1.38, "learning_rate": 7.939879759519037e-06, "loss": 2.0055, "step": 84180 }, { "epoch": 1.38, "learning_rate": 7.93486973947896e-06, "loss": 2.0485, "step": 84190 }, { "epoch": 1.38, "learning_rate": 7.929859719438878e-06, "loss": 2.0199, "step": 84200 }, { "epoch": 1.38, "learning_rate": 7.924849699398797e-06, "loss": 2.0105, "step": 84210 }, { "epoch": 1.38, "learning_rate": 7.919839679358718e-06, "loss": 2.0325, "step": 84220 }, { "epoch": 1.38, "learning_rate": 7.914829659318637e-06, "loss": 2.0027, "step": 84230 }, { "epoch": 1.38, "learning_rate": 7.909819639278558e-06, "loss": 2.0469, "step": 84240 }, { "epoch": 1.38, "learning_rate": 7.904809619238478e-06, "loss": 2.0012, "step": 84250 }, { "epoch": 1.38, "learning_rate": 7.899799599198397e-06, "loss": 2.0643, "step": 84260 }, { "epoch": 1.38, "learning_rate": 7.894789579158316e-06, "loss": 2.0537, "step": 84270 }, { "epoch": 1.38, "learning_rate": 7.889779559118237e-06, "loss": 2.0271, "step": 84280 }, { "epoch": 1.38, "learning_rate": 7.884769539078157e-06, "loss": 1.9808, "step": 84290 }, { "epoch": 1.38, "learning_rate": 7.879759519038076e-06, "loss": 2.0267, "step": 84300 }, { "epoch": 1.38, "learning_rate": 7.874749498997997e-06, "loss": 2.0103, "step": 84310 }, { "epoch": 1.38, "learning_rate": 7.869739478957916e-06, "loss": 1.988, "step": 84320 }, { "epoch": 1.38, "learning_rate": 7.864729458917835e-06, "loss": 2.0131, "step": 84330 }, { "epoch": 1.38, "learning_rate": 7.859719438877757e-06, "loss": 2.0273, "step": 84340 }, { "epoch": 1.38, "learning_rate": 7.854709418837676e-06, "loss": 1.9651, "step": 84350 }, { "epoch": 1.38, "learning_rate": 7.849699398797595e-06, "loss": 2.0389, "step": 84360 }, { "epoch": 1.38, "learning_rate": 7.844689378757516e-06, "loss": 1.9708, "step": 84370 }, { "epoch": 1.38, "learning_rate": 7.839679358717435e-06, "loss": 2.0479, "step": 84380 }, { "epoch": 1.38, "learning_rate": 7.834669338677355e-06, "loss": 2.0337, "step": 84390 }, { "epoch": 1.38, "learning_rate": 7.829659318637276e-06, "loss": 2.0013, "step": 84400 }, { "epoch": 1.38, "learning_rate": 7.824649298597195e-06, "loss": 2.0059, "step": 84410 }, { "epoch": 1.38, "learning_rate": 7.819639278557114e-06, "loss": 1.9919, "step": 84420 }, { "epoch": 1.38, "learning_rate": 7.814629258517035e-06, "loss": 2.0041, "step": 84430 }, { "epoch": 1.38, "learning_rate": 7.809619238476955e-06, "loss": 1.9966, "step": 84440 }, { "epoch": 1.38, "learning_rate": 7.804609218436874e-06, "loss": 1.9921, "step": 84450 }, { "epoch": 1.38, "learning_rate": 7.799599198396793e-06, "loss": 2.0322, "step": 84460 }, { "epoch": 1.38, "learning_rate": 7.794589178356714e-06, "loss": 2.0282, "step": 84470 }, { "epoch": 1.38, "learning_rate": 7.789579158316633e-06, "loss": 1.9609, "step": 84480 }, { "epoch": 1.38, "learning_rate": 7.784569138276553e-06, "loss": 2.0325, "step": 84490 }, { "epoch": 1.38, "learning_rate": 7.779559118236474e-06, "loss": 2.037, "step": 84500 }, { "epoch": 1.38, "learning_rate": 7.774549098196393e-06, "loss": 1.9704, "step": 84510 }, { "epoch": 1.38, "learning_rate": 7.769539078156312e-06, "loss": 1.9945, "step": 84520 }, { "epoch": 1.38, "learning_rate": 7.764529058116233e-06, "loss": 1.979, "step": 84530 }, { "epoch": 1.38, "learning_rate": 7.759519038076153e-06, "loss": 2.0309, "step": 84540 }, { "epoch": 1.38, "learning_rate": 7.754509018036072e-06, "loss": 2.0225, "step": 84550 }, { "epoch": 1.38, "learning_rate": 7.749498997995993e-06, "loss": 2.0214, "step": 84560 }, { "epoch": 1.38, "learning_rate": 7.744488977955912e-06, "loss": 2.0176, "step": 84570 }, { "epoch": 1.38, "learning_rate": 7.73947895791583e-06, "loss": 1.9949, "step": 84580 }, { "epoch": 1.38, "learning_rate": 7.734468937875753e-06, "loss": 2.0259, "step": 84590 }, { "epoch": 1.38, "learning_rate": 7.729458917835672e-06, "loss": 2.0096, "step": 84600 }, { "epoch": 1.38, "learning_rate": 7.724448897795591e-06, "loss": 1.9954, "step": 84610 }, { "epoch": 1.38, "learning_rate": 7.719438877755512e-06, "loss": 1.9858, "step": 84620 }, { "epoch": 1.38, "learning_rate": 7.71442885771543e-06, "loss": 2.0086, "step": 84630 }, { "epoch": 1.38, "learning_rate": 7.709418837675351e-06, "loss": 2.0377, "step": 84640 }, { "epoch": 1.38, "learning_rate": 7.704408817635272e-06, "loss": 1.9844, "step": 84650 }, { "epoch": 1.38, "learning_rate": 7.69939879759519e-06, "loss": 2.0371, "step": 84660 }, { "epoch": 1.38, "learning_rate": 7.69438877755511e-06, "loss": 2.0435, "step": 84670 }, { "epoch": 1.38, "learning_rate": 7.68937875751503e-06, "loss": 2.01, "step": 84680 }, { "epoch": 1.38, "learning_rate": 7.684368737474951e-06, "loss": 2.032, "step": 84690 }, { "epoch": 1.38, "learning_rate": 7.67935871743487e-06, "loss": 2.0148, "step": 84700 }, { "epoch": 1.38, "learning_rate": 7.67434869739479e-06, "loss": 2.0247, "step": 84710 }, { "epoch": 1.38, "learning_rate": 7.66933867735471e-06, "loss": 2.0487, "step": 84720 }, { "epoch": 1.38, "learning_rate": 7.66432865731463e-06, "loss": 1.9869, "step": 84730 }, { "epoch": 1.38, "learning_rate": 7.659318637274549e-06, "loss": 2.0452, "step": 84740 }, { "epoch": 1.38, "learning_rate": 7.65430861723447e-06, "loss": 1.9813, "step": 84750 }, { "epoch": 1.38, "learning_rate": 7.649298597194389e-06, "loss": 1.9581, "step": 84760 }, { "epoch": 1.39, "learning_rate": 7.64428857715431e-06, "loss": 2.023, "step": 84770 }, { "epoch": 1.39, "learning_rate": 7.63927855711423e-06, "loss": 2.0118, "step": 84780 }, { "epoch": 1.39, "learning_rate": 7.634268537074149e-06, "loss": 1.9581, "step": 84790 }, { "epoch": 1.39, "learning_rate": 7.629258517034069e-06, "loss": 2.0084, "step": 84800 }, { "epoch": 1.39, "learning_rate": 7.6242484969939884e-06, "loss": 2.0128, "step": 84810 }, { "epoch": 1.39, "learning_rate": 7.619238476953907e-06, "loss": 2.014, "step": 84820 }, { "epoch": 1.39, "learning_rate": 7.614228456913829e-06, "loss": 2.0174, "step": 84830 }, { "epoch": 1.39, "learning_rate": 7.609218436873748e-06, "loss": 1.9849, "step": 84840 }, { "epoch": 1.39, "learning_rate": 7.604208416833668e-06, "loss": 2.0135, "step": 84850 }, { "epoch": 1.39, "learning_rate": 7.599198396793587e-06, "loss": 1.9641, "step": 84860 }, { "epoch": 1.39, "learning_rate": 7.594188376753507e-06, "loss": 2.0123, "step": 84870 }, { "epoch": 1.39, "learning_rate": 7.589178356713428e-06, "loss": 2.0038, "step": 84880 }, { "epoch": 1.39, "learning_rate": 7.584168336673348e-06, "loss": 1.9842, "step": 84890 }, { "epoch": 1.39, "learning_rate": 7.579158316633267e-06, "loss": 2.0055, "step": 84900 }, { "epoch": 1.39, "learning_rate": 7.574148296593186e-06, "loss": 2.043, "step": 84910 }, { "epoch": 1.39, "learning_rate": 7.569138276553106e-06, "loss": 2.0134, "step": 84920 }, { "epoch": 1.39, "learning_rate": 7.564128256513027e-06, "loss": 1.9879, "step": 84930 }, { "epoch": 1.39, "learning_rate": 7.559118236472947e-06, "loss": 2.026, "step": 84940 }, { "epoch": 1.39, "learning_rate": 7.554108216432866e-06, "loss": 2.0192, "step": 84950 }, { "epoch": 1.39, "learning_rate": 7.549098196392785e-06, "loss": 2.0471, "step": 84960 }, { "epoch": 1.39, "learning_rate": 7.544088176352705e-06, "loss": 2.0261, "step": 84970 }, { "epoch": 1.39, "learning_rate": 7.539078156312626e-06, "loss": 2.0207, "step": 84980 }, { "epoch": 1.39, "learning_rate": 7.534068136272546e-06, "loss": 1.9909, "step": 84990 }, { "epoch": 1.39, "learning_rate": 7.529058116232465e-06, "loss": 2.0138, "step": 85000 }, { "epoch": 1.39, "eval_loss": 1.9994696378707886, "eval_mean_f1": 0.6608597055494537, "eval_rouge1_f1": 0.7163381930314877, "eval_rouge1_precision": 0.8260069983806919, "eval_rouge1_recall": 0.6659768922527499, "eval_rouge2_f1": 0.57872789398058, "eval_rouge2_precision": 0.6719582548256869, "eval_rouge2_recall": 0.5377881719179971, "eval_rougeL_f1": 0.6875130296362935, "eval_rougeL_precision": 0.7917367793642355, "eval_rougeL_recall": 0.6398866799801359, "eval_runtime": 64.8326, "eval_samples_per_second": 15.795, "eval_steps_per_second": 1.974, "step": 85000 }, { "epoch": 1.39, "learning_rate": 7.524048096192385e-06, "loss": 1.9988, "step": 85010 }, { "epoch": 1.39, "learning_rate": 7.519038076152304e-06, "loss": 1.9971, "step": 85020 }, { "epoch": 1.39, "learning_rate": 7.514028056112226e-06, "loss": 1.9972, "step": 85030 }, { "epoch": 1.39, "learning_rate": 7.5090180360721446e-06, "loss": 1.9894, "step": 85040 }, { "epoch": 1.39, "learning_rate": 7.504008016032064e-06, "loss": 2.022, "step": 85050 }, { "epoch": 1.39, "learning_rate": 7.498997995991984e-06, "loss": 1.9641, "step": 85060 }, { "epoch": 1.39, "learning_rate": 7.493987975951904e-06, "loss": 1.9945, "step": 85070 }, { "epoch": 1.39, "learning_rate": 7.488977955911825e-06, "loss": 2.0626, "step": 85080 }, { "epoch": 1.39, "learning_rate": 7.483967935871744e-06, "loss": 1.9841, "step": 85090 }, { "epoch": 1.39, "learning_rate": 7.478957915831663e-06, "loss": 1.9884, "step": 85100 }, { "epoch": 1.39, "learning_rate": 7.473947895791583e-06, "loss": 1.9877, "step": 85110 }, { "epoch": 1.39, "learning_rate": 7.468937875751503e-06, "loss": 1.9995, "step": 85120 }, { "epoch": 1.39, "learning_rate": 7.4639278557114236e-06, "loss": 2.0422, "step": 85130 }, { "epoch": 1.39, "learning_rate": 7.458917835671343e-06, "loss": 2.0037, "step": 85140 }, { "epoch": 1.39, "learning_rate": 7.453907815631263e-06, "loss": 1.9846, "step": 85150 }, { "epoch": 1.39, "learning_rate": 7.448897795591182e-06, "loss": 2.0564, "step": 85160 }, { "epoch": 1.39, "learning_rate": 7.443887775551102e-06, "loss": 1.9754, "step": 85170 }, { "epoch": 1.39, "learning_rate": 7.4388777555110225e-06, "loss": 2.0114, "step": 85180 }, { "epoch": 1.39, "learning_rate": 7.433867735470942e-06, "loss": 2.0398, "step": 85190 }, { "epoch": 1.39, "learning_rate": 7.428857715430862e-06, "loss": 2.0233, "step": 85200 }, { "epoch": 1.39, "learning_rate": 7.423847695390782e-06, "loss": 2.0043, "step": 85210 }, { "epoch": 1.39, "learning_rate": 7.418837675350701e-06, "loss": 1.9993, "step": 85220 }, { "epoch": 1.39, "learning_rate": 7.413827655310622e-06, "loss": 2.0059, "step": 85230 }, { "epoch": 1.39, "learning_rate": 7.408817635270541e-06, "loss": 1.9866, "step": 85240 }, { "epoch": 1.39, "learning_rate": 7.403807615230461e-06, "loss": 1.9974, "step": 85250 }, { "epoch": 1.39, "learning_rate": 7.398797595190381e-06, "loss": 1.9858, "step": 85260 }, { "epoch": 1.39, "learning_rate": 7.3937875751503015e-06, "loss": 2.0475, "step": 85270 }, { "epoch": 1.39, "learning_rate": 7.388777555110221e-06, "loss": 2.0266, "step": 85280 }, { "epoch": 1.39, "learning_rate": 7.383767535070141e-06, "loss": 2.0088, "step": 85290 }, { "epoch": 1.39, "learning_rate": 7.37875751503006e-06, "loss": 2.0535, "step": 85300 }, { "epoch": 1.39, "learning_rate": 7.37374749498998e-06, "loss": 2.0499, "step": 85310 }, { "epoch": 1.39, "learning_rate": 7.3687374749499005e-06, "loss": 1.98, "step": 85320 }, { "epoch": 1.39, "learning_rate": 7.36372745490982e-06, "loss": 1.9861, "step": 85330 }, { "epoch": 1.39, "learning_rate": 7.35871743486974e-06, "loss": 1.999, "step": 85340 }, { "epoch": 1.39, "learning_rate": 7.35370741482966e-06, "loss": 2.037, "step": 85350 }, { "epoch": 1.39, "learning_rate": 7.348697394789579e-06, "loss": 2.0006, "step": 85360 }, { "epoch": 1.39, "learning_rate": 7.3436873747495e-06, "loss": 2.0518, "step": 85370 }, { "epoch": 1.4, "learning_rate": 7.338677354709419e-06, "loss": 2.0036, "step": 85380 }, { "epoch": 1.4, "learning_rate": 7.333667334669339e-06, "loss": 2.0413, "step": 85390 }, { "epoch": 1.4, "learning_rate": 7.328657314629259e-06, "loss": 2.0401, "step": 85400 }, { "epoch": 1.4, "learning_rate": 7.323647294589178e-06, "loss": 2.0412, "step": 85410 }, { "epoch": 1.4, "learning_rate": 7.318637274549099e-06, "loss": 2.0131, "step": 85420 }, { "epoch": 1.4, "learning_rate": 7.313627254509019e-06, "loss": 2.0279, "step": 85430 }, { "epoch": 1.4, "learning_rate": 7.308617234468938e-06, "loss": 2.0158, "step": 85440 }, { "epoch": 1.4, "learning_rate": 7.303607214428858e-06, "loss": 1.989, "step": 85450 }, { "epoch": 1.4, "learning_rate": 7.298597194388778e-06, "loss": 2.0264, "step": 85460 }, { "epoch": 1.4, "learning_rate": 7.293587174348698e-06, "loss": 2.0206, "step": 85470 }, { "epoch": 1.4, "learning_rate": 7.288577154308618e-06, "loss": 2.0018, "step": 85480 }, { "epoch": 1.4, "learning_rate": 7.283567134268538e-06, "loss": 2.0075, "step": 85490 }, { "epoch": 1.4, "learning_rate": 7.278557114228457e-06, "loss": 2.0452, "step": 85500 }, { "epoch": 1.4, "learning_rate": 7.273547094188377e-06, "loss": 2.0006, "step": 85510 }, { "epoch": 1.4, "learning_rate": 7.268537074148297e-06, "loss": 2.0078, "step": 85520 }, { "epoch": 1.4, "learning_rate": 7.263527054108217e-06, "loss": 1.9951, "step": 85530 }, { "epoch": 1.4, "learning_rate": 7.258517034068137e-06, "loss": 2.0212, "step": 85540 }, { "epoch": 1.4, "learning_rate": 7.253507014028056e-06, "loss": 2.0203, "step": 85550 }, { "epoch": 1.4, "learning_rate": 7.2484969939879756e-06, "loss": 2.0247, "step": 85560 }, { "epoch": 1.4, "learning_rate": 7.243486973947897e-06, "loss": 2.0114, "step": 85570 }, { "epoch": 1.4, "learning_rate": 7.238476953907816e-06, "loss": 2.0157, "step": 85580 }, { "epoch": 1.4, "learning_rate": 7.233466933867736e-06, "loss": 2.0112, "step": 85590 }, { "epoch": 1.4, "learning_rate": 7.228456913827656e-06, "loss": 1.984, "step": 85600 }, { "epoch": 1.4, "learning_rate": 7.2234468937875745e-06, "loss": 2.0165, "step": 85610 }, { "epoch": 1.4, "learning_rate": 7.218436873747496e-06, "loss": 1.9714, "step": 85620 }, { "epoch": 1.4, "learning_rate": 7.213426853707416e-06, "loss": 1.9748, "step": 85630 }, { "epoch": 1.4, "learning_rate": 7.208416833667335e-06, "loss": 1.9865, "step": 85640 }, { "epoch": 1.4, "learning_rate": 7.2034068136272546e-06, "loss": 1.9786, "step": 85650 }, { "epoch": 1.4, "learning_rate": 7.198396793587174e-06, "loss": 1.9754, "step": 85660 }, { "epoch": 1.4, "learning_rate": 7.193386773547095e-06, "loss": 1.9642, "step": 85670 }, { "epoch": 1.4, "learning_rate": 7.188376753507015e-06, "loss": 1.9835, "step": 85680 }, { "epoch": 1.4, "learning_rate": 7.183366733466934e-06, "loss": 1.9955, "step": 85690 }, { "epoch": 1.4, "learning_rate": 7.1783567134268535e-06, "loss": 1.9968, "step": 85700 }, { "epoch": 1.4, "learning_rate": 7.173346693386773e-06, "loss": 1.9733, "step": 85710 }, { "epoch": 1.4, "learning_rate": 7.168336673346694e-06, "loss": 1.9845, "step": 85720 }, { "epoch": 1.4, "learning_rate": 7.163326653306614e-06, "loss": 1.9929, "step": 85730 }, { "epoch": 1.4, "learning_rate": 7.1583166332665335e-06, "loss": 2.0354, "step": 85740 }, { "epoch": 1.4, "learning_rate": 7.1533066132264525e-06, "loss": 1.9898, "step": 85750 }, { "epoch": 1.4, "learning_rate": 7.148296593186372e-06, "loss": 2.0375, "step": 85760 }, { "epoch": 1.4, "learning_rate": 7.143286573146293e-06, "loss": 2.0084, "step": 85770 }, { "epoch": 1.4, "learning_rate": 7.138276553106213e-06, "loss": 1.9929, "step": 85780 }, { "epoch": 1.4, "learning_rate": 7.1332665330661325e-06, "loss": 1.998, "step": 85790 }, { "epoch": 1.4, "learning_rate": 7.128256513026052e-06, "loss": 1.9616, "step": 85800 }, { "epoch": 1.4, "learning_rate": 7.123246492985973e-06, "loss": 1.9978, "step": 85810 }, { "epoch": 1.4, "learning_rate": 7.118236472945893e-06, "loss": 1.9716, "step": 85820 }, { "epoch": 1.4, "learning_rate": 7.113226452905812e-06, "loss": 2.0078, "step": 85830 }, { "epoch": 1.4, "learning_rate": 7.1082164328657315e-06, "loss": 2.03, "step": 85840 }, { "epoch": 1.4, "learning_rate": 7.103206412825651e-06, "loss": 2.0144, "step": 85850 }, { "epoch": 1.4, "learning_rate": 7.098196392785572e-06, "loss": 2.01, "step": 85860 }, { "epoch": 1.4, "learning_rate": 7.093186372745492e-06, "loss": 2.044, "step": 85870 }, { "epoch": 1.4, "learning_rate": 7.0881763527054115e-06, "loss": 2.0119, "step": 85880 }, { "epoch": 1.4, "learning_rate": 7.0831663326653305e-06, "loss": 1.999, "step": 85890 }, { "epoch": 1.4, "learning_rate": 7.07815631262525e-06, "loss": 2.0142, "step": 85900 }, { "epoch": 1.4, "learning_rate": 7.073146292585171e-06, "loss": 2.0056, "step": 85910 }, { "epoch": 1.4, "learning_rate": 7.068136272545091e-06, "loss": 2.0208, "step": 85920 }, { "epoch": 1.4, "learning_rate": 7.0631262525050105e-06, "loss": 2.0088, "step": 85930 }, { "epoch": 1.4, "learning_rate": 7.05811623246493e-06, "loss": 2.0332, "step": 85940 }, { "epoch": 1.4, "learning_rate": 7.053106212424849e-06, "loss": 2.015, "step": 85950 }, { "epoch": 1.4, "learning_rate": 7.048096192384771e-06, "loss": 2.0132, "step": 85960 }, { "epoch": 1.4, "learning_rate": 7.04308617234469e-06, "loss": 2.0181, "step": 85970 }, { "epoch": 1.4, "learning_rate": 7.0380761523046095e-06, "loss": 2.0222, "step": 85980 }, { "epoch": 1.41, "learning_rate": 7.033066132264529e-06, "loss": 2.0188, "step": 85990 }, { "epoch": 1.41, "learning_rate": 7.028056112224449e-06, "loss": 1.9961, "step": 86000 }, { "epoch": 1.41, "eval_loss": 2.000519037246704, "eval_mean_f1": 0.6611620696689152, "eval_rouge1_f1": 0.7180860862635214, "eval_rouge1_precision": 0.8284601341902578, "eval_rouge1_recall": 0.6665222326801143, "eval_rouge2_f1": 0.5777141115873012, "eval_rouge2_precision": 0.6713677225823225, "eval_rouge2_recall": 0.53616571275799, "eval_rougeL_f1": 0.6876860111559232, "eval_rougeL_precision": 0.7918068973223213, "eval_rougeL_recall": 0.639484032918731, "eval_runtime": 70.327, "eval_samples_per_second": 14.561, "eval_steps_per_second": 1.82, "step": 86000 }, { "epoch": 1.41, "learning_rate": 7.02304609218437e-06, "loss": 2.0147, "step": 86010 }, { "epoch": 1.41, "learning_rate": 7.0180360721442895e-06, "loss": 2.0497, "step": 86020 }, { "epoch": 1.41, "learning_rate": 7.0130260521042084e-06, "loss": 2.0529, "step": 86030 }, { "epoch": 1.41, "learning_rate": 7.008016032064128e-06, "loss": 2.0238, "step": 86040 }, { "epoch": 1.41, "learning_rate": 7.003006012024048e-06, "loss": 2.0215, "step": 86050 }, { "epoch": 1.41, "learning_rate": 6.997995991983969e-06, "loss": 2.0036, "step": 86060 }, { "epoch": 1.41, "learning_rate": 6.9929859719438885e-06, "loss": 1.9851, "step": 86070 }, { "epoch": 1.41, "learning_rate": 6.987975951903808e-06, "loss": 2.0076, "step": 86080 }, { "epoch": 1.41, "learning_rate": 6.982965931863727e-06, "loss": 2.0412, "step": 86090 }, { "epoch": 1.41, "learning_rate": 6.977955911823647e-06, "loss": 1.9618, "step": 86100 }, { "epoch": 1.41, "learning_rate": 6.972945891783568e-06, "loss": 1.9722, "step": 86110 }, { "epoch": 1.41, "learning_rate": 6.9679358717434874e-06, "loss": 2.0583, "step": 86120 }, { "epoch": 1.41, "learning_rate": 6.962925851703407e-06, "loss": 1.9874, "step": 86130 }, { "epoch": 1.41, "learning_rate": 6.957915831663327e-06, "loss": 2.0094, "step": 86140 }, { "epoch": 1.41, "learning_rate": 6.952905811623246e-06, "loss": 2.0032, "step": 86150 }, { "epoch": 1.41, "learning_rate": 6.9478957915831674e-06, "loss": 2.0088, "step": 86160 }, { "epoch": 1.41, "learning_rate": 6.942885771543086e-06, "loss": 2.0326, "step": 86170 }, { "epoch": 1.41, "learning_rate": 6.938376753507015e-06, "loss": 1.9989, "step": 86180 }, { "epoch": 1.41, "learning_rate": 6.933366733466934e-06, "loss": 2.0612, "step": 86190 }, { "epoch": 1.41, "learning_rate": 6.928356713426853e-06, "loss": 2.0229, "step": 86200 }, { "epoch": 1.41, "learning_rate": 6.923346693386774e-06, "loss": 2.0166, "step": 86210 }, { "epoch": 1.41, "learning_rate": 6.918336673346694e-06, "loss": 1.9963, "step": 86220 }, { "epoch": 1.41, "learning_rate": 6.913326653306614e-06, "loss": 1.9798, "step": 86230 }, { "epoch": 1.41, "learning_rate": 6.908316633266533e-06, "loss": 2.0146, "step": 86240 }, { "epoch": 1.41, "learning_rate": 6.903306613226452e-06, "loss": 2.0319, "step": 86250 }, { "epoch": 1.41, "learning_rate": 6.898296593186374e-06, "loss": 2.0524, "step": 86260 }, { "epoch": 1.41, "learning_rate": 6.893286573146293e-06, "loss": 2.0107, "step": 86270 }, { "epoch": 1.41, "learning_rate": 6.888276553106213e-06, "loss": 1.9753, "step": 86280 }, { "epoch": 1.41, "learning_rate": 6.883266533066132e-06, "loss": 1.9913, "step": 86290 }, { "epoch": 1.41, "learning_rate": 6.878256513026052e-06, "loss": 2.0237, "step": 86300 }, { "epoch": 1.41, "learning_rate": 6.873246492985973e-06, "loss": 1.9805, "step": 86310 }, { "epoch": 1.41, "learning_rate": 6.868236472945893e-06, "loss": 2.0174, "step": 86320 }, { "epoch": 1.41, "learning_rate": 6.8632264529058115e-06, "loss": 1.9803, "step": 86330 }, { "epoch": 1.41, "learning_rate": 6.858216432865731e-06, "loss": 1.9921, "step": 86340 }, { "epoch": 1.41, "learning_rate": 6.853206412825651e-06, "loss": 2.0004, "step": 86350 }, { "epoch": 1.41, "learning_rate": 6.848196392785572e-06, "loss": 2.0405, "step": 86360 }, { "epoch": 1.41, "learning_rate": 6.8431863727454916e-06, "loss": 2.0154, "step": 86370 }, { "epoch": 1.41, "learning_rate": 6.838176352705411e-06, "loss": 2.0263, "step": 86380 }, { "epoch": 1.41, "learning_rate": 6.83316633266533e-06, "loss": 2.0483, "step": 86390 }, { "epoch": 1.41, "learning_rate": 6.828156312625252e-06, "loss": 2.0341, "step": 86400 }, { "epoch": 1.41, "learning_rate": 6.823146292585171e-06, "loss": 2.0034, "step": 86410 }, { "epoch": 1.41, "learning_rate": 6.8181362725450905e-06, "loss": 1.9962, "step": 86420 }, { "epoch": 1.41, "learning_rate": 6.81312625250501e-06, "loss": 2.0508, "step": 86430 }, { "epoch": 1.41, "learning_rate": 6.80811623246493e-06, "loss": 1.9893, "step": 86440 }, { "epoch": 1.41, "learning_rate": 6.803106212424851e-06, "loss": 2.0333, "step": 86450 }, { "epoch": 1.41, "learning_rate": 6.798597194388778e-06, "loss": 2.0003, "step": 86460 }, { "epoch": 1.41, "learning_rate": 6.793587174348698e-06, "loss": 2.0169, "step": 86470 }, { "epoch": 1.41, "learning_rate": 6.788577154308618e-06, "loss": 2.0263, "step": 86480 }, { "epoch": 1.41, "learning_rate": 6.783567134268537e-06, "loss": 2.0104, "step": 86490 }, { "epoch": 1.41, "learning_rate": 6.778557114228458e-06, "loss": 1.9754, "step": 86500 }, { "epoch": 1.41, "learning_rate": 6.773547094188377e-06, "loss": 1.99, "step": 86510 }, { "epoch": 1.41, "learning_rate": 6.768537074148297e-06, "loss": 1.9891, "step": 86520 }, { "epoch": 1.41, "learning_rate": 6.763527054108217e-06, "loss": 2.0008, "step": 86530 }, { "epoch": 1.41, "learning_rate": 6.7585170340681365e-06, "loss": 2.0469, "step": 86540 }, { "epoch": 1.41, "learning_rate": 6.753507014028057e-06, "loss": 1.9963, "step": 86550 }, { "epoch": 1.41, "learning_rate": 6.748496993987977e-06, "loss": 1.9716, "step": 86560 }, { "epoch": 1.41, "learning_rate": 6.743486973947896e-06, "loss": 1.9537, "step": 86570 }, { "epoch": 1.41, "learning_rate": 6.738476953907816e-06, "loss": 1.9958, "step": 86580 }, { "epoch": 1.41, "learning_rate": 6.7334669338677355e-06, "loss": 2.0173, "step": 86590 }, { "epoch": 1.42, "learning_rate": 6.728456913827656e-06, "loss": 2.0475, "step": 86600 }, { "epoch": 1.42, "learning_rate": 6.723446893787576e-06, "loss": 2.0521, "step": 86610 }, { "epoch": 1.42, "learning_rate": 6.718436873747496e-06, "loss": 1.978, "step": 86620 }, { "epoch": 1.42, "learning_rate": 6.713426853707415e-06, "loss": 2.0162, "step": 86630 }, { "epoch": 1.42, "learning_rate": 6.7084168336673345e-06, "loss": 2.0117, "step": 86640 }, { "epoch": 1.42, "learning_rate": 6.703406813627255e-06, "loss": 2.076, "step": 86650 }, { "epoch": 1.42, "learning_rate": 6.698396793587175e-06, "loss": 2.0392, "step": 86660 }, { "epoch": 1.42, "learning_rate": 6.693386773547095e-06, "loss": 2.0028, "step": 86670 }, { "epoch": 1.42, "learning_rate": 6.6883767535070145e-06, "loss": 1.9765, "step": 86680 }, { "epoch": 1.42, "learning_rate": 6.6833667334669334e-06, "loss": 2.032, "step": 86690 }, { "epoch": 1.42, "learning_rate": 6.678356713426855e-06, "loss": 1.9801, "step": 86700 }, { "epoch": 1.42, "learning_rate": 6.673346693386774e-06, "loss": 1.9566, "step": 86710 }, { "epoch": 1.42, "learning_rate": 6.668336673346694e-06, "loss": 2.0304, "step": 86720 }, { "epoch": 1.42, "learning_rate": 6.6633266533066135e-06, "loss": 2.0128, "step": 86730 }, { "epoch": 1.42, "learning_rate": 6.658316633266532e-06, "loss": 2.0371, "step": 86740 }, { "epoch": 1.42, "learning_rate": 6.653306613226454e-06, "loss": 1.9987, "step": 86750 }, { "epoch": 1.42, "learning_rate": 6.648296593186374e-06, "loss": 2.0289, "step": 86760 }, { "epoch": 1.42, "learning_rate": 6.643286573146293e-06, "loss": 2.031, "step": 86770 }, { "epoch": 1.42, "learning_rate": 6.6382765531062124e-06, "loss": 1.9613, "step": 86780 }, { "epoch": 1.42, "learning_rate": 6.633266533066132e-06, "loss": 2.0526, "step": 86790 }, { "epoch": 1.42, "learning_rate": 6.628256513026053e-06, "loss": 2.0225, "step": 86800 }, { "epoch": 1.42, "learning_rate": 6.623246492985973e-06, "loss": 1.9846, "step": 86810 }, { "epoch": 1.42, "learning_rate": 6.6182364729458925e-06, "loss": 1.9744, "step": 86820 }, { "epoch": 1.42, "learning_rate": 6.613226452905811e-06, "loss": 1.9838, "step": 86830 }, { "epoch": 1.42, "learning_rate": 6.608216432865731e-06, "loss": 2.0398, "step": 86840 }, { "epoch": 1.42, "learning_rate": 6.603206412825652e-06, "loss": 2.0204, "step": 86850 }, { "epoch": 1.42, "learning_rate": 6.598196392785572e-06, "loss": 2.0013, "step": 86860 }, { "epoch": 1.42, "learning_rate": 6.5931863727454914e-06, "loss": 1.9778, "step": 86870 }, { "epoch": 1.42, "learning_rate": 6.58817635270541e-06, "loss": 1.9974, "step": 86880 }, { "epoch": 1.42, "learning_rate": 6.58316633266533e-06, "loss": 1.9995, "step": 86890 }, { "epoch": 1.42, "learning_rate": 6.578156312625252e-06, "loss": 1.9957, "step": 86900 }, { "epoch": 1.42, "learning_rate": 6.573146292585171e-06, "loss": 1.9886, "step": 86910 }, { "epoch": 1.42, "learning_rate": 6.56813627254509e-06, "loss": 2.029, "step": 86920 }, { "epoch": 1.42, "learning_rate": 6.56312625250501e-06, "loss": 1.9775, "step": 86930 }, { "epoch": 1.42, "learning_rate": 6.558116232464929e-06, "loss": 1.9929, "step": 86940 }, { "epoch": 1.42, "learning_rate": 6.553106212424851e-06, "loss": 2.009, "step": 86950 }, { "epoch": 1.42, "learning_rate": 6.54809619238477e-06, "loss": 1.9791, "step": 86960 }, { "epoch": 1.42, "learning_rate": 6.543086172344689e-06, "loss": 2.0219, "step": 86970 }, { "epoch": 1.42, "learning_rate": 6.538076152304609e-06, "loss": 2.0143, "step": 86980 }, { "epoch": 1.42, "learning_rate": 6.533066132264529e-06, "loss": 1.9539, "step": 86990 }, { "epoch": 1.42, "learning_rate": 6.52805611222445e-06, "loss": 2.0198, "step": 87000 }, { "epoch": 1.42, "eval_loss": 1.9978625774383545, "eval_mean_f1": 0.6611026101329572, "eval_rouge1_f1": 0.7166707302122317, "eval_rouge1_precision": 0.8287856297173126, "eval_rouge1_recall": 0.6653029717938838, "eval_rouge2_f1": 0.5790905156930479, "eval_rouge2_precision": 0.6747323795724677, "eval_rouge2_recall": 0.5374492858904447, "eval_rougeL_f1": 0.6875465844935921, "eval_rougeL_precision": 0.7941146010596831, "eval_rougeL_recall": 0.6389193664103159, "eval_runtime": 70.4598, "eval_samples_per_second": 14.533, "eval_steps_per_second": 1.817, "step": 87000 }, { "epoch": 1.42, "learning_rate": 6.523046092184369e-06, "loss": 1.975, "step": 87010 }, { "epoch": 1.42, "learning_rate": 6.518036072144288e-06, "loss": 2.0249, "step": 87020 }, { "epoch": 1.42, "learning_rate": 6.513026052104208e-06, "loss": 2.0248, "step": 87030 }, { "epoch": 1.42, "learning_rate": 6.50801603206413e-06, "loss": 1.9885, "step": 87040 }, { "epoch": 1.42, "learning_rate": 6.5030060120240486e-06, "loss": 2.0351, "step": 87050 }, { "epoch": 1.42, "learning_rate": 6.497995991983968e-06, "loss": 2.0242, "step": 87060 }, { "epoch": 1.42, "learning_rate": 6.492985971943888e-06, "loss": 1.9807, "step": 87070 }, { "epoch": 1.42, "learning_rate": 6.487975951903807e-06, "loss": 1.9785, "step": 87080 }, { "epoch": 1.42, "learning_rate": 6.482965931863729e-06, "loss": 1.9819, "step": 87090 }, { "epoch": 1.42, "learning_rate": 6.477955911823648e-06, "loss": 2.0316, "step": 87100 }, { "epoch": 1.42, "learning_rate": 6.472945891783567e-06, "loss": 1.9617, "step": 87110 }, { "epoch": 1.42, "learning_rate": 6.467935871743487e-06, "loss": 1.9679, "step": 87120 }, { "epoch": 1.42, "learning_rate": 6.462925851703407e-06, "loss": 2.0188, "step": 87130 }, { "epoch": 1.42, "learning_rate": 6.4579158316633276e-06, "loss": 2.0107, "step": 87140 }, { "epoch": 1.42, "learning_rate": 6.452905811623247e-06, "loss": 2.0022, "step": 87150 }, { "epoch": 1.42, "learning_rate": 6.447895791583166e-06, "loss": 2.0262, "step": 87160 }, { "epoch": 1.42, "learning_rate": 6.442885771543086e-06, "loss": 1.9981, "step": 87170 }, { "epoch": 1.42, "learning_rate": 6.437875751503006e-06, "loss": 2.0067, "step": 87180 }, { "epoch": 1.42, "learning_rate": 6.4328657314629265e-06, "loss": 1.9842, "step": 87190 }, { "epoch": 1.42, "learning_rate": 6.427855711422846e-06, "loss": 1.9946, "step": 87200 }, { "epoch": 1.43, "learning_rate": 6.422845691382766e-06, "loss": 1.9959, "step": 87210 }, { "epoch": 1.43, "learning_rate": 6.417835671342685e-06, "loss": 2.0126, "step": 87220 }, { "epoch": 1.43, "learning_rate": 6.412825651302605e-06, "loss": 1.9697, "step": 87230 }, { "epoch": 1.43, "learning_rate": 6.4078156312625255e-06, "loss": 2.0346, "step": 87240 }, { "epoch": 1.43, "learning_rate": 6.402805611222445e-06, "loss": 2.0084, "step": 87250 }, { "epoch": 1.43, "learning_rate": 6.397795591182365e-06, "loss": 1.9998, "step": 87260 }, { "epoch": 1.43, "learning_rate": 6.392785571142285e-06, "loss": 1.989, "step": 87270 }, { "epoch": 1.43, "learning_rate": 6.387775551102204e-06, "loss": 2.0506, "step": 87280 }, { "epoch": 1.43, "learning_rate": 6.382765531062125e-06, "loss": 2.0225, "step": 87290 }, { "epoch": 1.43, "learning_rate": 6.377755511022044e-06, "loss": 2.0026, "step": 87300 }, { "epoch": 1.43, "learning_rate": 6.372745490981964e-06, "loss": 2.0174, "step": 87310 }, { "epoch": 1.43, "learning_rate": 6.367735470941884e-06, "loss": 2.0377, "step": 87320 }, { "epoch": 1.43, "learning_rate": 6.362725450901804e-06, "loss": 1.9972, "step": 87330 }, { "epoch": 1.43, "learning_rate": 6.357715430861724e-06, "loss": 2.0271, "step": 87340 }, { "epoch": 1.43, "learning_rate": 6.352705410821644e-06, "loss": 1.9702, "step": 87350 }, { "epoch": 1.43, "learning_rate": 6.347695390781563e-06, "loss": 2.0129, "step": 87360 }, { "epoch": 1.43, "learning_rate": 6.342685370741483e-06, "loss": 1.9486, "step": 87370 }, { "epoch": 1.43, "learning_rate": 6.337675350701403e-06, "loss": 1.9617, "step": 87380 }, { "epoch": 1.43, "learning_rate": 6.332665330661323e-06, "loss": 2.053, "step": 87390 }, { "epoch": 1.43, "learning_rate": 6.327655310621243e-06, "loss": 1.9669, "step": 87400 }, { "epoch": 1.43, "learning_rate": 6.322645290581163e-06, "loss": 1.9842, "step": 87410 }, { "epoch": 1.43, "learning_rate": 6.317635270541082e-06, "loss": 1.9827, "step": 87420 }, { "epoch": 1.43, "learning_rate": 6.312625250501002e-06, "loss": 2.0195, "step": 87430 }, { "epoch": 1.43, "learning_rate": 6.307615230460922e-06, "loss": 2.0087, "step": 87440 }, { "epoch": 1.43, "learning_rate": 6.302605210420842e-06, "loss": 2.0422, "step": 87450 }, { "epoch": 1.43, "learning_rate": 6.297595190380762e-06, "loss": 2.0137, "step": 87460 }, { "epoch": 1.43, "learning_rate": 6.292585170340682e-06, "loss": 1.9935, "step": 87470 }, { "epoch": 1.43, "learning_rate": 6.2875751503006006e-06, "loss": 2.0188, "step": 87480 }, { "epoch": 1.43, "learning_rate": 6.282565130260522e-06, "loss": 1.9713, "step": 87490 }, { "epoch": 1.43, "learning_rate": 6.277555110220441e-06, "loss": 2.0497, "step": 87500 }, { "epoch": 1.43, "learning_rate": 6.272545090180361e-06, "loss": 2.0252, "step": 87510 }, { "epoch": 1.43, "learning_rate": 6.267535070140281e-06, "loss": 2.011, "step": 87520 }, { "epoch": 1.43, "learning_rate": 6.2625250501002e-06, "loss": 2.0245, "step": 87530 }, { "epoch": 1.43, "learning_rate": 6.257515030060121e-06, "loss": 2.0053, "step": 87540 }, { "epoch": 1.43, "learning_rate": 6.252505010020041e-06, "loss": 1.961, "step": 87550 }, { "epoch": 1.43, "learning_rate": 6.24749498997996e-06, "loss": 1.9996, "step": 87560 }, { "epoch": 1.43, "learning_rate": 6.24248496993988e-06, "loss": 2.0393, "step": 87570 }, { "epoch": 1.43, "learning_rate": 6.2374749498998e-06, "loss": 1.9692, "step": 87580 }, { "epoch": 1.43, "learning_rate": 6.232464929859719e-06, "loss": 1.9999, "step": 87590 }, { "epoch": 1.43, "learning_rate": 6.22745490981964e-06, "loss": 2.0401, "step": 87600 }, { "epoch": 1.43, "learning_rate": 6.22244488977956e-06, "loss": 1.9982, "step": 87610 }, { "epoch": 1.43, "learning_rate": 6.217434869739479e-06, "loss": 1.9982, "step": 87620 }, { "epoch": 1.43, "learning_rate": 6.212424849699399e-06, "loss": 1.9937, "step": 87630 }, { "epoch": 1.43, "learning_rate": 6.207414829659319e-06, "loss": 2.0179, "step": 87640 }, { "epoch": 1.43, "learning_rate": 6.202404809619239e-06, "loss": 2.0097, "step": 87650 }, { "epoch": 1.43, "learning_rate": 6.1973947895791586e-06, "loss": 1.9935, "step": 87660 }, { "epoch": 1.43, "learning_rate": 6.192384769539078e-06, "loss": 1.9957, "step": 87670 }, { "epoch": 1.43, "learning_rate": 6.187374749498998e-06, "loss": 2.0191, "step": 87680 }, { "epoch": 1.43, "learning_rate": 6.182364729458918e-06, "loss": 2.0146, "step": 87690 }, { "epoch": 1.43, "learning_rate": 6.177354709418838e-06, "loss": 1.9724, "step": 87700 }, { "epoch": 1.43, "learning_rate": 6.1723446893787575e-06, "loss": 1.9754, "step": 87710 }, { "epoch": 1.43, "learning_rate": 6.167334669338678e-06, "loss": 2.0084, "step": 87720 }, { "epoch": 1.43, "learning_rate": 6.162324649298597e-06, "loss": 1.9748, "step": 87730 }, { "epoch": 1.43, "learning_rate": 6.157314629258518e-06, "loss": 2.0272, "step": 87740 }, { "epoch": 1.43, "learning_rate": 6.1523046092184376e-06, "loss": 2.0012, "step": 87750 }, { "epoch": 1.43, "learning_rate": 6.1472945891783565e-06, "loss": 2.0079, "step": 87760 }, { "epoch": 1.43, "learning_rate": 6.142284569138277e-06, "loss": 1.9695, "step": 87770 }, { "epoch": 1.43, "learning_rate": 6.137274549098197e-06, "loss": 2.0334, "step": 87780 }, { "epoch": 1.43, "learning_rate": 6.132264529058117e-06, "loss": 2.0017, "step": 87790 }, { "epoch": 1.43, "learning_rate": 6.1272545090180365e-06, "loss": 1.9713, "step": 87800 }, { "epoch": 1.43, "learning_rate": 6.122244488977956e-06, "loss": 2.027, "step": 87810 }, { "epoch": 1.43, "learning_rate": 6.117234468937876e-06, "loss": 2.0144, "step": 87820 }, { "epoch": 1.44, "learning_rate": 6.112224448897796e-06, "loss": 2.0096, "step": 87830 }, { "epoch": 1.44, "learning_rate": 6.107214428857716e-06, "loss": 1.9853, "step": 87840 }, { "epoch": 1.44, "learning_rate": 6.1022044088176355e-06, "loss": 2.0319, "step": 87850 }, { "epoch": 1.44, "learning_rate": 6.097194388777555e-06, "loss": 2.0027, "step": 87860 }, { "epoch": 1.44, "learning_rate": 6.092184368737475e-06, "loss": 1.9869, "step": 87870 }, { "epoch": 1.44, "learning_rate": 6.087174348697395e-06, "loss": 2.0392, "step": 87880 }, { "epoch": 1.44, "learning_rate": 6.0821643286573155e-06, "loss": 2.0481, "step": 87890 }, { "epoch": 1.44, "learning_rate": 6.0771543086172345e-06, "loss": 1.9865, "step": 87900 }, { "epoch": 1.44, "learning_rate": 6.072144288577154e-06, "loss": 2.0176, "step": 87910 }, { "epoch": 1.44, "learning_rate": 6.067134268537075e-06, "loss": 1.9719, "step": 87920 }, { "epoch": 1.44, "learning_rate": 6.062124248496994e-06, "loss": 1.9902, "step": 87930 }, { "epoch": 1.44, "learning_rate": 6.0571142284569145e-06, "loss": 2.0055, "step": 87940 }, { "epoch": 1.44, "learning_rate": 6.052104208416834e-06, "loss": 1.9987, "step": 87950 }, { "epoch": 1.44, "learning_rate": 6.047094188376753e-06, "loss": 1.9607, "step": 87960 }, { "epoch": 1.44, "learning_rate": 6.042084168336674e-06, "loss": 2.0066, "step": 87970 }, { "epoch": 1.44, "learning_rate": 6.037074148296594e-06, "loss": 1.9761, "step": 87980 }, { "epoch": 1.44, "learning_rate": 6.0320641282565135e-06, "loss": 2.0265, "step": 87990 }, { "epoch": 1.44, "learning_rate": 6.027054108216433e-06, "loss": 1.9974, "step": 88000 }, { "epoch": 1.44, "eval_loss": 1.998486876487732, "eval_mean_f1": 0.6645416544882184, "eval_rouge1_f1": 0.7214817162844733, "eval_rouge1_precision": 0.8319411865899112, "eval_rouge1_recall": 0.670119056163645, "eval_rouge2_f1": 0.5817105355003667, "eval_rouge2_precision": 0.675534395346407, "eval_rouge2_recall": 0.5402540624128692, "eval_rougeL_f1": 0.6904327116798155, "eval_rougeL_precision": 0.7946825753265319, "eval_rougeL_recall": 0.6419600278089258, "eval_runtime": 65.3063, "eval_samples_per_second": 15.68, "eval_steps_per_second": 1.96, "step": 88000 }, { "epoch": 1.44, "learning_rate": 6.022044088176353e-06, "loss": 1.9986, "step": 88010 }, { "epoch": 1.44, "learning_rate": 6.017034068136273e-06, "loss": 1.9941, "step": 88020 }, { "epoch": 1.44, "learning_rate": 6.012024048096193e-06, "loss": 1.9915, "step": 88030 }, { "epoch": 1.44, "learning_rate": 6.0070140280561124e-06, "loss": 1.964, "step": 88040 }, { "epoch": 1.44, "learning_rate": 6.002004008016032e-06, "loss": 2.0075, "step": 88050 }, { "epoch": 1.44, "learning_rate": 5.996993987975953e-06, "loss": 2.003, "step": 88060 }, { "epoch": 1.44, "learning_rate": 5.991983967935872e-06, "loss": 2.011, "step": 88070 }, { "epoch": 1.44, "learning_rate": 5.986973947895792e-06, "loss": 2.0315, "step": 88080 }, { "epoch": 1.44, "learning_rate": 5.981963927855712e-06, "loss": 1.9995, "step": 88090 }, { "epoch": 1.44, "learning_rate": 5.976953907815631e-06, "loss": 2.0067, "step": 88100 }, { "epoch": 1.44, "learning_rate": 5.971943887775552e-06, "loss": 2.0074, "step": 88110 }, { "epoch": 1.44, "learning_rate": 5.966933867735472e-06, "loss": 2.053, "step": 88120 }, { "epoch": 1.44, "learning_rate": 5.961923847695391e-06, "loss": 2.0104, "step": 88130 }, { "epoch": 1.44, "learning_rate": 5.956913827655311e-06, "loss": 1.9745, "step": 88140 }, { "epoch": 1.44, "learning_rate": 5.95190380761523e-06, "loss": 1.9318, "step": 88150 }, { "epoch": 1.44, "learning_rate": 5.946893787575151e-06, "loss": 2.0101, "step": 88160 }, { "epoch": 1.44, "learning_rate": 5.941883767535071e-06, "loss": 2.0021, "step": 88170 }, { "epoch": 1.44, "learning_rate": 5.9368737474949896e-06, "loss": 1.9867, "step": 88180 }, { "epoch": 1.44, "learning_rate": 5.93186372745491e-06, "loss": 2.0059, "step": 88190 }, { "epoch": 1.44, "learning_rate": 5.92685370741483e-06, "loss": 1.97, "step": 88200 }, { "epoch": 1.44, "learning_rate": 5.92184368737475e-06, "loss": 1.9782, "step": 88210 }, { "epoch": 1.44, "learning_rate": 5.91683366733467e-06, "loss": 2.0235, "step": 88220 }, { "epoch": 1.44, "learning_rate": 5.911823647294589e-06, "loss": 2.0273, "step": 88230 }, { "epoch": 1.44, "learning_rate": 5.906813627254509e-06, "loss": 1.9982, "step": 88240 }, { "epoch": 1.44, "learning_rate": 5.901803607214429e-06, "loss": 2.0001, "step": 88250 }, { "epoch": 1.44, "learning_rate": 5.896793587174349e-06, "loss": 2.0241, "step": 88260 }, { "epoch": 1.44, "learning_rate": 5.8917835671342686e-06, "loss": 2.0119, "step": 88270 }, { "epoch": 1.44, "learning_rate": 5.886773547094189e-06, "loss": 2.0198, "step": 88280 }, { "epoch": 1.44, "learning_rate": 5.881763527054108e-06, "loss": 2.032, "step": 88290 }, { "epoch": 1.44, "learning_rate": 5.876753507014028e-06, "loss": 1.9906, "step": 88300 }, { "epoch": 1.44, "learning_rate": 5.871743486973949e-06, "loss": 1.9848, "step": 88310 }, { "epoch": 1.44, "learning_rate": 5.8667334669338675e-06, "loss": 2.0315, "step": 88320 }, { "epoch": 1.44, "learning_rate": 5.861723446893788e-06, "loss": 1.9866, "step": 88330 }, { "epoch": 1.44, "learning_rate": 5.856713426853708e-06, "loss": 1.9621, "step": 88340 }, { "epoch": 1.44, "learning_rate": 5.851703406813627e-06, "loss": 2.0335, "step": 88350 }, { "epoch": 1.44, "learning_rate": 5.8466933867735476e-06, "loss": 1.9907, "step": 88360 }, { "epoch": 1.44, "learning_rate": 5.841683366733467e-06, "loss": 1.9912, "step": 88370 }, { "epoch": 1.44, "learning_rate": 5.836673346693387e-06, "loss": 2.0173, "step": 88380 }, { "epoch": 1.44, "learning_rate": 5.831663326653307e-06, "loss": 2.0064, "step": 88390 }, { "epoch": 1.44, "learning_rate": 5.826653306613227e-06, "loss": 2.0095, "step": 88400 }, { "epoch": 1.44, "learning_rate": 5.8216432865731465e-06, "loss": 1.9924, "step": 88410 }, { "epoch": 1.44, "learning_rate": 5.816633266533066e-06, "loss": 1.991, "step": 88420 }, { "epoch": 1.44, "learning_rate": 5.811623246492986e-06, "loss": 1.9906, "step": 88430 }, { "epoch": 1.45, "learning_rate": 5.806613226452906e-06, "loss": 2.0351, "step": 88440 }, { "epoch": 1.45, "learning_rate": 5.801603206412826e-06, "loss": 1.985, "step": 88450 }, { "epoch": 1.45, "learning_rate": 5.7965931863727455e-06, "loss": 1.9751, "step": 88460 }, { "epoch": 1.45, "learning_rate": 5.791583166332665e-06, "loss": 2.019, "step": 88470 }, { "epoch": 1.45, "learning_rate": 5.786573146292586e-06, "loss": 1.9944, "step": 88480 }, { "epoch": 1.45, "learning_rate": 5.781563126252505e-06, "loss": 2.0342, "step": 88490 }, { "epoch": 1.45, "learning_rate": 5.776553106212425e-06, "loss": 1.9886, "step": 88500 }, { "epoch": 1.45, "learning_rate": 5.771543086172345e-06, "loss": 2.0091, "step": 88510 }, { "epoch": 1.45, "learning_rate": 5.766533066132264e-06, "loss": 2.0085, "step": 88520 }, { "epoch": 1.45, "learning_rate": 5.761523046092185e-06, "loss": 2.0126, "step": 88530 }, { "epoch": 1.45, "learning_rate": 5.756513026052105e-06, "loss": 2.028, "step": 88540 }, { "epoch": 1.45, "learning_rate": 5.7515030060120245e-06, "loss": 2.0287, "step": 88550 }, { "epoch": 1.45, "learning_rate": 5.746492985971944e-06, "loss": 1.9942, "step": 88560 }, { "epoch": 1.45, "learning_rate": 5.741482965931864e-06, "loss": 2.0066, "step": 88570 }, { "epoch": 1.45, "learning_rate": 5.736472945891784e-06, "loss": 1.9813, "step": 88580 }, { "epoch": 1.45, "learning_rate": 5.731462925851704e-06, "loss": 2.0442, "step": 88590 }, { "epoch": 1.45, "learning_rate": 5.7264529058116235e-06, "loss": 1.9865, "step": 88600 }, { "epoch": 1.45, "learning_rate": 5.721442885771543e-06, "loss": 1.9917, "step": 88610 }, { "epoch": 1.45, "learning_rate": 5.716432865731463e-06, "loss": 2.027, "step": 88620 }, { "epoch": 1.45, "learning_rate": 5.711422845691383e-06, "loss": 1.9634, "step": 88630 }, { "epoch": 1.45, "learning_rate": 5.706412825651303e-06, "loss": 2.0194, "step": 88640 }, { "epoch": 1.45, "learning_rate": 5.701402805611223e-06, "loss": 2.0221, "step": 88650 }, { "epoch": 1.45, "learning_rate": 5.696392785571142e-06, "loss": 2.0133, "step": 88660 }, { "epoch": 1.45, "learning_rate": 5.691382765531062e-06, "loss": 1.9774, "step": 88670 }, { "epoch": 1.45, "learning_rate": 5.686372745490983e-06, "loss": 1.9692, "step": 88680 }, { "epoch": 1.45, "learning_rate": 5.681362725450902e-06, "loss": 2.0014, "step": 88690 }, { "epoch": 1.45, "learning_rate": 5.676352705410822e-06, "loss": 2.001, "step": 88700 }, { "epoch": 1.45, "learning_rate": 5.671342685370742e-06, "loss": 2.0178, "step": 88710 }, { "epoch": 1.45, "learning_rate": 5.666332665330661e-06, "loss": 2.0047, "step": 88720 }, { "epoch": 1.45, "learning_rate": 5.661322645290582e-06, "loss": 2.0071, "step": 88730 }, { "epoch": 1.45, "learning_rate": 5.6563126252505014e-06, "loss": 2.0012, "step": 88740 }, { "epoch": 1.45, "learning_rate": 5.651302605210421e-06, "loss": 2.0478, "step": 88750 }, { "epoch": 1.45, "learning_rate": 5.646292585170341e-06, "loss": 2.0234, "step": 88760 }, { "epoch": 1.45, "learning_rate": 5.641282565130261e-06, "loss": 2.0072, "step": 88770 }, { "epoch": 1.45, "learning_rate": 5.636272545090181e-06, "loss": 1.9943, "step": 88780 }, { "epoch": 1.45, "learning_rate": 5.6312625250501e-06, "loss": 1.9747, "step": 88790 }, { "epoch": 1.45, "learning_rate": 5.62625250501002e-06, "loss": 1.9904, "step": 88800 }, { "epoch": 1.45, "learning_rate": 5.62124248496994e-06, "loss": 2.007, "step": 88810 }, { "epoch": 1.45, "learning_rate": 5.616232464929861e-06, "loss": 1.9865, "step": 88820 }, { "epoch": 1.45, "learning_rate": 5.61122244488978e-06, "loss": 2.0194, "step": 88830 }, { "epoch": 1.45, "learning_rate": 5.606212424849699e-06, "loss": 1.96, "step": 88840 }, { "epoch": 1.45, "learning_rate": 5.60120240480962e-06, "loss": 1.9775, "step": 88850 }, { "epoch": 1.45, "learning_rate": 5.596192384769539e-06, "loss": 2.0058, "step": 88860 }, { "epoch": 1.45, "learning_rate": 5.59118236472946e-06, "loss": 2.0148, "step": 88870 }, { "epoch": 1.45, "learning_rate": 5.586172344689379e-06, "loss": 1.9354, "step": 88880 }, { "epoch": 1.45, "learning_rate": 5.581162324649298e-06, "loss": 2.0094, "step": 88890 }, { "epoch": 1.45, "learning_rate": 5.576152304609219e-06, "loss": 1.9984, "step": 88900 }, { "epoch": 1.45, "learning_rate": 5.571142284569139e-06, "loss": 1.9754, "step": 88910 }, { "epoch": 1.45, "learning_rate": 5.5661322645290586e-06, "loss": 2.0099, "step": 88920 }, { "epoch": 1.45, "learning_rate": 5.561122244488978e-06, "loss": 2.007, "step": 88930 }, { "epoch": 1.45, "learning_rate": 5.556112224448898e-06, "loss": 2.0105, "step": 88940 }, { "epoch": 1.45, "learning_rate": 5.551102204408818e-06, "loss": 1.9635, "step": 88950 }, { "epoch": 1.45, "learning_rate": 5.546092184368738e-06, "loss": 2.0151, "step": 88960 }, { "epoch": 1.45, "learning_rate": 5.5410821643286575e-06, "loss": 2.0106, "step": 88970 }, { "epoch": 1.45, "learning_rate": 5.536072144288577e-06, "loss": 1.9817, "step": 88980 }, { "epoch": 1.45, "learning_rate": 5.531062124248497e-06, "loss": 2.0353, "step": 88990 }, { "epoch": 1.45, "learning_rate": 5.526052104208417e-06, "loss": 2.0204, "step": 89000 }, { "epoch": 1.45, "eval_loss": 1.9968440532684326, "eval_mean_f1": 0.660168076848111, "eval_rouge1_f1": 0.7172202105688676, "eval_rouge1_precision": 0.8266562144484654, "eval_rouge1_recall": 0.6663666187107287, "eval_rouge2_f1": 0.57743603703047, "eval_rouge2_precision": 0.6687696065869897, "eval_rouge2_recall": 0.5368916110832322, "eval_rougeL_f1": 0.6858479829449949, "eval_rougeL_precision": 0.7888009245847595, "eval_rougeL_recall": 0.6380789988075195, "eval_runtime": 67.971, "eval_samples_per_second": 15.065, "eval_steps_per_second": 1.883, "step": 89000 }, { "epoch": 1.45, "learning_rate": 5.521042084168337e-06, "loss": 2.0379, "step": 89010 }, { "epoch": 1.45, "learning_rate": 5.516032064128257e-06, "loss": 2.0047, "step": 89020 }, { "epoch": 1.45, "learning_rate": 5.511022044088176e-06, "loss": 2.0329, "step": 89030 }, { "epoch": 1.45, "learning_rate": 5.506012024048096e-06, "loss": 1.9777, "step": 89040 }, { "epoch": 1.46, "learning_rate": 5.501002004008017e-06, "loss": 2.0249, "step": 89050 }, { "epoch": 1.46, "learning_rate": 5.495991983967936e-06, "loss": 1.9924, "step": 89060 }, { "epoch": 1.46, "learning_rate": 5.490981963927856e-06, "loss": 1.9901, "step": 89070 }, { "epoch": 1.46, "learning_rate": 5.485971943887776e-06, "loss": 1.9663, "step": 89080 }, { "epoch": 1.46, "learning_rate": 5.480961923847696e-06, "loss": 2.0118, "step": 89090 }, { "epoch": 1.46, "learning_rate": 5.475951903807616e-06, "loss": 1.9954, "step": 89100 }, { "epoch": 1.46, "learning_rate": 5.4709418837675355e-06, "loss": 2.0096, "step": 89110 }, { "epoch": 1.46, "learning_rate": 5.465931863727455e-06, "loss": 2.0052, "step": 89120 }, { "epoch": 1.46, "learning_rate": 5.460921843687375e-06, "loss": 2.0148, "step": 89130 }, { "epoch": 1.46, "learning_rate": 5.455911823647295e-06, "loss": 2.0305, "step": 89140 }, { "epoch": 1.46, "learning_rate": 5.450901803607215e-06, "loss": 2.0608, "step": 89150 }, { "epoch": 1.46, "learning_rate": 5.4458917835671345e-06, "loss": 1.9752, "step": 89160 }, { "epoch": 1.46, "learning_rate": 5.440881763527054e-06, "loss": 2.0001, "step": 89170 }, { "epoch": 1.46, "learning_rate": 5.435871743486974e-06, "loss": 1.9809, "step": 89180 }, { "epoch": 1.46, "learning_rate": 5.430861723446895e-06, "loss": 2.0545, "step": 89190 }, { "epoch": 1.46, "learning_rate": 5.425851703406814e-06, "loss": 1.989, "step": 89200 }, { "epoch": 1.46, "learning_rate": 5.4208416833667335e-06, "loss": 1.9707, "step": 89210 }, { "epoch": 1.46, "learning_rate": 5.415831663326654e-06, "loss": 2.0089, "step": 89220 }, { "epoch": 1.46, "learning_rate": 5.410821643286573e-06, "loss": 2.0297, "step": 89230 }, { "epoch": 1.46, "learning_rate": 5.405811623246494e-06, "loss": 1.9429, "step": 89240 }, { "epoch": 1.46, "learning_rate": 5.4008016032064135e-06, "loss": 2.0367, "step": 89250 }, { "epoch": 1.46, "learning_rate": 5.3957915831663324e-06, "loss": 2.0118, "step": 89260 }, { "epoch": 1.46, "learning_rate": 5.390781563126253e-06, "loss": 1.991, "step": 89270 }, { "epoch": 1.46, "learning_rate": 5.385771543086172e-06, "loss": 1.9959, "step": 89280 }, { "epoch": 1.46, "learning_rate": 5.380761523046093e-06, "loss": 2.0345, "step": 89290 }, { "epoch": 1.46, "learning_rate": 5.3757515030060124e-06, "loss": 2.0433, "step": 89300 }, { "epoch": 1.46, "learning_rate": 5.370741482965931e-06, "loss": 1.9646, "step": 89310 }, { "epoch": 1.46, "learning_rate": 5.365731462925852e-06, "loss": 2.0016, "step": 89320 }, { "epoch": 1.46, "learning_rate": 5.360721442885772e-06, "loss": 2.0361, "step": 89330 }, { "epoch": 1.46, "learning_rate": 5.355711422845692e-06, "loss": 2.0294, "step": 89340 }, { "epoch": 1.46, "learning_rate": 5.350701402805611e-06, "loss": 2.0023, "step": 89350 }, { "epoch": 1.46, "learning_rate": 5.345691382765532e-06, "loss": 1.9886, "step": 89360 }, { "epoch": 1.46, "learning_rate": 5.340681362725451e-06, "loss": 2.0012, "step": 89370 }, { "epoch": 1.46, "learning_rate": 5.335671342685371e-06, "loss": 2.0424, "step": 89380 }, { "epoch": 1.46, "learning_rate": 5.3306613226452914e-06, "loss": 2.0294, "step": 89390 }, { "epoch": 1.46, "learning_rate": 5.32565130260521e-06, "loss": 1.9925, "step": 89400 }, { "epoch": 1.46, "learning_rate": 5.320641282565131e-06, "loss": 1.9989, "step": 89410 }, { "epoch": 1.46, "learning_rate": 5.31563126252505e-06, "loss": 2.047, "step": 89420 }, { "epoch": 1.46, "learning_rate": 5.31062124248497e-06, "loss": 1.9896, "step": 89430 }, { "epoch": 1.46, "learning_rate": 5.30561122244489e-06, "loss": 1.991, "step": 89440 }, { "epoch": 1.46, "learning_rate": 5.300601202404809e-06, "loss": 2.0018, "step": 89450 }, { "epoch": 1.46, "learning_rate": 5.29559118236473e-06, "loss": 1.9898, "step": 89460 }, { "epoch": 1.46, "learning_rate": 5.29058116232465e-06, "loss": 2.0047, "step": 89470 }, { "epoch": 1.46, "learning_rate": 5.285571142284569e-06, "loss": 1.9852, "step": 89480 }, { "epoch": 1.46, "learning_rate": 5.280561122244489e-06, "loss": 2.0049, "step": 89490 }, { "epoch": 1.46, "learning_rate": 5.275551102204409e-06, "loss": 1.9965, "step": 89500 }, { "epoch": 1.46, "learning_rate": 5.270541082164329e-06, "loss": 2.019, "step": 89510 }, { "epoch": 1.46, "learning_rate": 5.265531062124249e-06, "loss": 1.9929, "step": 89520 }, { "epoch": 1.46, "learning_rate": 5.2605210420841686e-06, "loss": 2.0012, "step": 89530 }, { "epoch": 1.46, "learning_rate": 5.255511022044088e-06, "loss": 1.9842, "step": 89540 }, { "epoch": 1.46, "learning_rate": 5.250501002004008e-06, "loss": 1.9952, "step": 89550 }, { "epoch": 1.46, "learning_rate": 5.245490981963928e-06, "loss": 2.0143, "step": 89560 }, { "epoch": 1.46, "learning_rate": 5.240480961923848e-06, "loss": 2.0136, "step": 89570 }, { "epoch": 1.46, "learning_rate": 5.2354709418837675e-06, "loss": 1.9934, "step": 89580 }, { "epoch": 1.46, "learning_rate": 5.230460921843687e-06, "loss": 1.9931, "step": 89590 }, { "epoch": 1.46, "learning_rate": 5.225450901803607e-06, "loss": 2.0125, "step": 89600 }, { "epoch": 1.46, "learning_rate": 5.220440881763528e-06, "loss": 2.008, "step": 89610 }, { "epoch": 1.46, "learning_rate": 5.215430861723447e-06, "loss": 2.0138, "step": 89620 }, { "epoch": 1.46, "learning_rate": 5.2104208416833665e-06, "loss": 2.0275, "step": 89630 }, { "epoch": 1.46, "learning_rate": 5.205410821643287e-06, "loss": 2.0286, "step": 89640 }, { "epoch": 1.46, "learning_rate": 5.200400801603206e-06, "loss": 2.0376, "step": 89650 }, { "epoch": 1.47, "learning_rate": 5.195390781563127e-06, "loss": 1.9926, "step": 89660 }, { "epoch": 1.47, "learning_rate": 5.1903807615230465e-06, "loss": 1.9936, "step": 89670 }, { "epoch": 1.47, "learning_rate": 5.185370741482966e-06, "loss": 2.0035, "step": 89680 }, { "epoch": 1.47, "learning_rate": 5.180360721442886e-06, "loss": 1.9783, "step": 89690 }, { "epoch": 1.47, "learning_rate": 5.175350701402806e-06, "loss": 1.9625, "step": 89700 }, { "epoch": 1.47, "learning_rate": 5.170340681362726e-06, "loss": 2.0021, "step": 89710 }, { "epoch": 1.47, "learning_rate": 5.1653306613226455e-06, "loss": 1.9799, "step": 89720 }, { "epoch": 1.47, "learning_rate": 5.160320641282565e-06, "loss": 2.0046, "step": 89730 }, { "epoch": 1.47, "learning_rate": 5.155310621242485e-06, "loss": 1.9931, "step": 89740 }, { "epoch": 1.47, "learning_rate": 5.150300601202405e-06, "loss": 1.9917, "step": 89750 }, { "epoch": 1.47, "learning_rate": 5.145290581162325e-06, "loss": 2.087, "step": 89760 }, { "epoch": 1.47, "learning_rate": 5.1402805611222445e-06, "loss": 1.9945, "step": 89770 }, { "epoch": 1.47, "learning_rate": 5.135270541082165e-06, "loss": 2.0015, "step": 89780 }, { "epoch": 1.47, "learning_rate": 5.130260521042084e-06, "loss": 2.0275, "step": 89790 }, { "epoch": 1.47, "learning_rate": 5.125250501002004e-06, "loss": 1.9599, "step": 89800 }, { "epoch": 1.47, "learning_rate": 5.1202404809619245e-06, "loss": 1.9958, "step": 89810 }, { "epoch": 1.47, "learning_rate": 5.1152304609218434e-06, "loss": 2.0018, "step": 89820 }, { "epoch": 1.47, "learning_rate": 5.110220440881764e-06, "loss": 2.0171, "step": 89830 }, { "epoch": 1.47, "learning_rate": 5.105210420841684e-06, "loss": 1.9814, "step": 89840 }, { "epoch": 1.47, "learning_rate": 5.100200400801603e-06, "loss": 2.0002, "step": 89850 }, { "epoch": 1.47, "learning_rate": 5.0951903807615235e-06, "loss": 2.0094, "step": 89860 }, { "epoch": 1.47, "learning_rate": 5.090180360721443e-06, "loss": 2.0062, "step": 89870 }, { "epoch": 1.47, "learning_rate": 5.085170340681363e-06, "loss": 2.0188, "step": 89880 }, { "epoch": 1.47, "learning_rate": 5.080160320641283e-06, "loss": 1.9748, "step": 89890 }, { "epoch": 1.47, "learning_rate": 5.075150300601203e-06, "loss": 2.0094, "step": 89900 }, { "epoch": 1.47, "learning_rate": 5.0701402805611224e-06, "loss": 1.9747, "step": 89910 }, { "epoch": 1.47, "learning_rate": 5.065130260521042e-06, "loss": 1.9861, "step": 89920 }, { "epoch": 1.47, "learning_rate": 5.060120240480962e-06, "loss": 1.9772, "step": 89930 }, { "epoch": 1.47, "learning_rate": 5.055110220440882e-06, "loss": 2.0162, "step": 89940 }, { "epoch": 1.47, "learning_rate": 5.0501002004008025e-06, "loss": 2.0075, "step": 89950 }, { "epoch": 1.47, "learning_rate": 5.045090180360721e-06, "loss": 2.0001, "step": 89960 }, { "epoch": 1.47, "learning_rate": 5.040080160320641e-06, "loss": 2.0081, "step": 89970 }, { "epoch": 1.47, "learning_rate": 5.035070140280562e-06, "loss": 2.064, "step": 89980 }, { "epoch": 1.47, "learning_rate": 5.030060120240481e-06, "loss": 1.9558, "step": 89990 }, { "epoch": 1.47, "learning_rate": 5.0250501002004014e-06, "loss": 2.0015, "step": 90000 }, { "epoch": 1.47, "eval_loss": 1.9956731796264648, "eval_mean_f1": 0.6630853634178254, "eval_rouge1_f1": 0.7182504826030642, "eval_rouge1_precision": 0.8287558157334258, "eval_rouge1_recall": 0.6668291066511817, "eval_rouge2_f1": 0.5818782383989516, "eval_rouge2_precision": 0.6763441080945963, "eval_rouge2_recall": 0.5394914623167393, "eval_rougeL_f1": 0.6891273692514606, "eval_rougeL_precision": 0.7930093049248033, "eval_rougeL_recall": 0.6407401732559822, "eval_runtime": 66.7176, "eval_samples_per_second": 15.348, "eval_steps_per_second": 1.919, "step": 90000 }, { "epoch": 1.47, "learning_rate": 5.020040080160321e-06, "loss": 1.9976, "step": 90010 }, { "epoch": 1.47, "learning_rate": 5.01503006012024e-06, "loss": 2.0241, "step": 90020 }, { "epoch": 1.47, "learning_rate": 5.010020040080161e-06, "loss": 1.9797, "step": 90030 }, { "epoch": 1.47, "learning_rate": 5.005010020040081e-06, "loss": 2.0142, "step": 90040 }, { "epoch": 1.47, "learning_rate": 5e-06, "loss": 2.0488, "step": 90050 }, { "epoch": 1.47, "learning_rate": 4.99498997995992e-06, "loss": 1.9725, "step": 90060 }, { "epoch": 1.47, "learning_rate": 4.98997995991984e-06, "loss": 1.961, "step": 90070 }, { "epoch": 1.47, "learning_rate": 4.98496993987976e-06, "loss": 2.0083, "step": 90080 }, { "epoch": 1.47, "learning_rate": 4.97995991983968e-06, "loss": 2.0263, "step": 90090 }, { "epoch": 1.47, "learning_rate": 4.974949899799599e-06, "loss": 2.0025, "step": 90100 }, { "epoch": 1.47, "learning_rate": 4.969939879759519e-06, "loss": 2.0128, "step": 90110 }, { "epoch": 1.47, "learning_rate": 4.964929859719439e-06, "loss": 2.022, "step": 90120 }, { "epoch": 1.47, "learning_rate": 4.959919839679359e-06, "loss": 1.9966, "step": 90130 }, { "epoch": 1.47, "learning_rate": 4.9549098196392786e-06, "loss": 1.9936, "step": 90140 }, { "epoch": 1.47, "learning_rate": 4.949899799599199e-06, "loss": 1.9807, "step": 90150 }, { "epoch": 1.47, "learning_rate": 4.944889779559118e-06, "loss": 2.0096, "step": 90160 }, { "epoch": 1.47, "learning_rate": 4.939879759519038e-06, "loss": 2.0425, "step": 90170 }, { "epoch": 1.47, "learning_rate": 4.934869739478959e-06, "loss": 2.0084, "step": 90180 }, { "epoch": 1.47, "learning_rate": 4.9298597194388775e-06, "loss": 2.0393, "step": 90190 }, { "epoch": 1.47, "learning_rate": 4.924849699398798e-06, "loss": 1.9963, "step": 90200 }, { "epoch": 1.47, "learning_rate": 4.919839679358718e-06, "loss": 2.0023, "step": 90210 }, { "epoch": 1.47, "learning_rate": 4.914829659318638e-06, "loss": 2.0116, "step": 90220 }, { "epoch": 1.47, "learning_rate": 4.9098196392785576e-06, "loss": 2.0037, "step": 90230 }, { "epoch": 1.47, "learning_rate": 4.904809619238477e-06, "loss": 1.9787, "step": 90240 }, { "epoch": 1.47, "learning_rate": 4.899799599198397e-06, "loss": 2.0785, "step": 90250 }, { "epoch": 1.47, "learning_rate": 4.894789579158317e-06, "loss": 1.9648, "step": 90260 }, { "epoch": 1.48, "learning_rate": 4.889779559118237e-06, "loss": 2.0168, "step": 90270 }, { "epoch": 1.48, "learning_rate": 4.8847695390781565e-06, "loss": 1.9955, "step": 90280 }, { "epoch": 1.48, "learning_rate": 4.879759519038076e-06, "loss": 1.9791, "step": 90290 }, { "epoch": 1.48, "learning_rate": 4.874749498997996e-06, "loss": 1.9587, "step": 90300 }, { "epoch": 1.48, "learning_rate": 4.869739478957916e-06, "loss": 1.9953, "step": 90310 }, { "epoch": 1.48, "learning_rate": 4.8647294589178365e-06, "loss": 1.9798, "step": 90320 }, { "epoch": 1.48, "learning_rate": 4.8597194388777555e-06, "loss": 1.9637, "step": 90330 }, { "epoch": 1.48, "learning_rate": 4.854709418837675e-06, "loss": 2.0093, "step": 90340 }, { "epoch": 1.48, "learning_rate": 4.849699398797596e-06, "loss": 1.9799, "step": 90350 }, { "epoch": 1.48, "learning_rate": 4.844689378757515e-06, "loss": 1.9828, "step": 90360 }, { "epoch": 1.48, "learning_rate": 4.8396793587174355e-06, "loss": 2.0166, "step": 90370 }, { "epoch": 1.48, "learning_rate": 4.834669338677355e-06, "loss": 1.9963, "step": 90380 }, { "epoch": 1.48, "learning_rate": 4.829659318637274e-06, "loss": 1.9816, "step": 90390 }, { "epoch": 1.48, "learning_rate": 4.824649298597195e-06, "loss": 1.9986, "step": 90400 }, { "epoch": 1.48, "learning_rate": 4.819639278557115e-06, "loss": 2.0397, "step": 90410 }, { "epoch": 1.48, "learning_rate": 4.8146292585170345e-06, "loss": 2.0132, "step": 90420 }, { "epoch": 1.48, "learning_rate": 4.809619238476954e-06, "loss": 1.9995, "step": 90430 }, { "epoch": 1.48, "learning_rate": 4.804609218436873e-06, "loss": 1.9786, "step": 90440 }, { "epoch": 1.48, "learning_rate": 4.799599198396794e-06, "loss": 2.0032, "step": 90450 }, { "epoch": 1.48, "learning_rate": 4.794589178356714e-06, "loss": 1.9743, "step": 90460 }, { "epoch": 1.48, "learning_rate": 4.7895791583166335e-06, "loss": 1.9926, "step": 90470 }, { "epoch": 1.48, "learning_rate": 4.784569138276553e-06, "loss": 2.0125, "step": 90480 }, { "epoch": 1.48, "learning_rate": 4.779559118236474e-06, "loss": 2.0358, "step": 90490 }, { "epoch": 1.48, "learning_rate": 4.774549098196393e-06, "loss": 1.9834, "step": 90500 }, { "epoch": 1.48, "learning_rate": 4.769539078156313e-06, "loss": 2.0323, "step": 90510 }, { "epoch": 1.48, "learning_rate": 4.764529058116233e-06, "loss": 1.9462, "step": 90520 }, { "epoch": 1.48, "learning_rate": 4.759519038076152e-06, "loss": 1.9625, "step": 90530 }, { "epoch": 1.48, "learning_rate": 4.754509018036073e-06, "loss": 2.0161, "step": 90540 }, { "epoch": 1.48, "learning_rate": 4.749498997995992e-06, "loss": 1.9969, "step": 90550 }, { "epoch": 1.48, "learning_rate": 4.744488977955912e-06, "loss": 1.9737, "step": 90560 }, { "epoch": 1.48, "learning_rate": 4.739478957915832e-06, "loss": 1.9886, "step": 90570 }, { "epoch": 1.48, "learning_rate": 4.734468937875751e-06, "loss": 2.024, "step": 90580 }, { "epoch": 1.48, "learning_rate": 4.729458917835672e-06, "loss": 2.0194, "step": 90590 }, { "epoch": 1.48, "learning_rate": 4.724448897795592e-06, "loss": 2.0049, "step": 90600 }, { "epoch": 1.48, "learning_rate": 4.719438877755511e-06, "loss": 2.0401, "step": 90610 }, { "epoch": 1.48, "learning_rate": 4.714428857715431e-06, "loss": 2.0075, "step": 90620 }, { "epoch": 1.48, "learning_rate": 4.709418837675351e-06, "loss": 2.0528, "step": 90630 }, { "epoch": 1.48, "learning_rate": 4.704408817635271e-06, "loss": 2.0314, "step": 90640 }, { "epoch": 1.48, "learning_rate": 4.699398797595191e-06, "loss": 1.9702, "step": 90650 }, { "epoch": 1.48, "learning_rate": 4.69438877755511e-06, "loss": 2.0051, "step": 90660 }, { "epoch": 1.48, "learning_rate": 4.68937875751503e-06, "loss": 2.022, "step": 90670 }, { "epoch": 1.48, "learning_rate": 4.68436873747495e-06, "loss": 1.9795, "step": 90680 }, { "epoch": 1.48, "learning_rate": 4.67935871743487e-06, "loss": 2.0333, "step": 90690 }, { "epoch": 1.48, "learning_rate": 4.67434869739479e-06, "loss": 2.0051, "step": 90700 }, { "epoch": 1.48, "learning_rate": 4.669338677354709e-06, "loss": 2.028, "step": 90710 }, { "epoch": 1.48, "learning_rate": 4.664328657314629e-06, "loss": 1.9784, "step": 90720 }, { "epoch": 1.48, "learning_rate": 4.659318637274549e-06, "loss": 1.9911, "step": 90730 }, { "epoch": 1.48, "learning_rate": 4.65430861723447e-06, "loss": 2.0148, "step": 90740 }, { "epoch": 1.48, "learning_rate": 4.6492985971943886e-06, "loss": 2.0192, "step": 90750 }, { "epoch": 1.48, "learning_rate": 4.644288577154309e-06, "loss": 2.0104, "step": 90760 }, { "epoch": 1.48, "learning_rate": 4.639278557114229e-06, "loss": 2.0113, "step": 90770 }, { "epoch": 1.48, "learning_rate": 4.634268537074148e-06, "loss": 1.9841, "step": 90780 }, { "epoch": 1.48, "learning_rate": 4.6292585170340686e-06, "loss": 2.018, "step": 90790 }, { "epoch": 1.48, "learning_rate": 4.624248496993988e-06, "loss": 2.0387, "step": 90800 }, { "epoch": 1.48, "learning_rate": 4.619739478957917e-06, "loss": 2.0544, "step": 90810 }, { "epoch": 1.48, "learning_rate": 4.6147294589178356e-06, "loss": 1.9478, "step": 90820 }, { "epoch": 1.48, "learning_rate": 4.609719438877755e-06, "loss": 2.004, "step": 90830 }, { "epoch": 1.48, "learning_rate": 4.604709418837676e-06, "loss": 1.9873, "step": 90840 }, { "epoch": 1.48, "learning_rate": 4.599699398797595e-06, "loss": 1.9857, "step": 90850 }, { "epoch": 1.48, "learning_rate": 4.594689378757516e-06, "loss": 2.0096, "step": 90860 }, { "epoch": 1.48, "learning_rate": 4.589679358717435e-06, "loss": 2.0123, "step": 90870 }, { "epoch": 1.48, "learning_rate": 4.584669338677354e-06, "loss": 2.0316, "step": 90880 }, { "epoch": 1.49, "learning_rate": 4.579659318637275e-06, "loss": 2.0161, "step": 90890 }, { "epoch": 1.49, "learning_rate": 4.574649298597195e-06, "loss": 1.9908, "step": 90900 }, { "epoch": 1.49, "learning_rate": 4.5696392785571145e-06, "loss": 1.9892, "step": 90910 }, { "epoch": 1.49, "learning_rate": 4.564629258517034e-06, "loss": 2.0265, "step": 90920 }, { "epoch": 1.49, "learning_rate": 4.559619238476954e-06, "loss": 2.003, "step": 90930 }, { "epoch": 1.49, "learning_rate": 4.554609218436874e-06, "loss": 1.9944, "step": 90940 }, { "epoch": 1.49, "learning_rate": 4.549599198396794e-06, "loss": 1.9509, "step": 90950 }, { "epoch": 1.49, "learning_rate": 4.5445891783567135e-06, "loss": 2.0528, "step": 90960 }, { "epoch": 1.49, "learning_rate": 4.539579158316633e-06, "loss": 1.9743, "step": 90970 }, { "epoch": 1.49, "learning_rate": 4.534569138276553e-06, "loss": 2.0222, "step": 90980 }, { "epoch": 1.49, "learning_rate": 4.529559118236473e-06, "loss": 1.9877, "step": 90990 }, { "epoch": 1.49, "learning_rate": 4.524549098196393e-06, "loss": 2.0433, "step": 91000 }, { "epoch": 1.49, "eval_loss": 1.996866226196289, "eval_mean_f1": 0.6645997460497206, "eval_rouge1_f1": 0.7208930413573693, "eval_rouge1_precision": 0.8314245315422932, "eval_rouge1_recall": 0.6690912650094403, "eval_rouge2_f1": 0.5829738786343963, "eval_rouge2_precision": 0.6779332355199055, "eval_rouge2_recall": 0.5412853212904001, "eval_rougeL_f1": 0.6899323181573962, "eval_rougeL_precision": 0.7946165638002725, "eval_rougeL_recall": 0.641339279082475, "eval_runtime": 67.3974, "eval_samples_per_second": 15.193, "eval_steps_per_second": 1.899, "step": 91000 }, { "epoch": 1.49, "learning_rate": 4.519539078156313e-06, "loss": 1.9764, "step": 91010 }, { "epoch": 1.49, "learning_rate": 4.514529058116232e-06, "loss": 1.9971, "step": 91020 }, { "epoch": 1.49, "learning_rate": 4.509519038076152e-06, "loss": 1.9907, "step": 91030 }, { "epoch": 1.49, "learning_rate": 4.504509018036073e-06, "loss": 2.0295, "step": 91040 }, { "epoch": 1.49, "learning_rate": 4.499498997995992e-06, "loss": 1.994, "step": 91050 }, { "epoch": 1.49, "learning_rate": 4.494488977955912e-06, "loss": 1.9696, "step": 91060 }, { "epoch": 1.49, "learning_rate": 4.489478957915832e-06, "loss": 2.0047, "step": 91070 }, { "epoch": 1.49, "learning_rate": 4.484468937875752e-06, "loss": 1.9755, "step": 91080 }, { "epoch": 1.49, "learning_rate": 4.479458917835672e-06, "loss": 2.0017, "step": 91090 }, { "epoch": 1.49, "learning_rate": 4.4744488977955915e-06, "loss": 1.9782, "step": 91100 }, { "epoch": 1.49, "learning_rate": 4.469438877755511e-06, "loss": 1.9897, "step": 91110 }, { "epoch": 1.49, "learning_rate": 4.464428857715431e-06, "loss": 1.9797, "step": 91120 }, { "epoch": 1.49, "learning_rate": 4.459418837675351e-06, "loss": 2.0091, "step": 91130 }, { "epoch": 1.49, "learning_rate": 4.454408817635271e-06, "loss": 2.0136, "step": 91140 }, { "epoch": 1.49, "learning_rate": 4.4493987975951905e-06, "loss": 2.0099, "step": 91150 }, { "epoch": 1.49, "learning_rate": 4.44438877755511e-06, "loss": 1.9796, "step": 91160 }, { "epoch": 1.49, "learning_rate": 4.43937875751503e-06, "loss": 2.0379, "step": 91170 }, { "epoch": 1.49, "learning_rate": 4.434368737474951e-06, "loss": 1.9862, "step": 91180 }, { "epoch": 1.49, "learning_rate": 4.42935871743487e-06, "loss": 2.0076, "step": 91190 }, { "epoch": 1.49, "learning_rate": 4.4243486973947894e-06, "loss": 2.0665, "step": 91200 }, { "epoch": 1.49, "learning_rate": 4.41933867735471e-06, "loss": 1.9851, "step": 91210 }, { "epoch": 1.49, "learning_rate": 4.414328657314629e-06, "loss": 2.03, "step": 91220 }, { "epoch": 1.49, "learning_rate": 4.40931863727455e-06, "loss": 1.9872, "step": 91230 }, { "epoch": 1.49, "learning_rate": 4.4043086172344695e-06, "loss": 1.9966, "step": 91240 }, { "epoch": 1.49, "learning_rate": 4.399298597194388e-06, "loss": 1.9795, "step": 91250 }, { "epoch": 1.49, "learning_rate": 4.394288577154309e-06, "loss": 1.9915, "step": 91260 }, { "epoch": 1.49, "learning_rate": 4.389278557114229e-06, "loss": 2.0312, "step": 91270 }, { "epoch": 1.49, "learning_rate": 4.384268537074149e-06, "loss": 2.0347, "step": 91280 }, { "epoch": 1.49, "learning_rate": 4.3792585170340684e-06, "loss": 2.0187, "step": 91290 }, { "epoch": 1.49, "learning_rate": 4.374248496993988e-06, "loss": 2.0015, "step": 91300 }, { "epoch": 1.49, "learning_rate": 4.369238476953908e-06, "loss": 2.0146, "step": 91310 }, { "epoch": 1.49, "learning_rate": 4.364228456913828e-06, "loss": 2.0247, "step": 91320 }, { "epoch": 1.49, "learning_rate": 4.359218436873748e-06, "loss": 1.9734, "step": 91330 }, { "epoch": 1.49, "learning_rate": 4.354208416833667e-06, "loss": 1.9794, "step": 91340 }, { "epoch": 1.49, "learning_rate": 4.349198396793587e-06, "loss": 2.0579, "step": 91350 }, { "epoch": 1.49, "learning_rate": 4.344188376753507e-06, "loss": 2.0431, "step": 91360 }, { "epoch": 1.49, "learning_rate": 4.339178356713427e-06, "loss": 2.0063, "step": 91370 }, { "epoch": 1.49, "learning_rate": 4.334168336673347e-06, "loss": 1.9698, "step": 91380 }, { "epoch": 1.49, "learning_rate": 4.329158316633266e-06, "loss": 1.9924, "step": 91390 }, { "epoch": 1.49, "learning_rate": 4.324148296593187e-06, "loss": 2.0179, "step": 91400 }, { "epoch": 1.49, "learning_rate": 4.319138276553107e-06, "loss": 2.024, "step": 91410 }, { "epoch": 1.49, "learning_rate": 4.314128256513026e-06, "loss": 1.999, "step": 91420 }, { "epoch": 1.49, "learning_rate": 4.309118236472946e-06, "loss": 1.997, "step": 91430 }, { "epoch": 1.49, "learning_rate": 4.304108216432866e-06, "loss": 1.9958, "step": 91440 }, { "epoch": 1.49, "learning_rate": 4.299098196392786e-06, "loss": 2.0154, "step": 91450 }, { "epoch": 1.49, "learning_rate": 4.294088176352706e-06, "loss": 2.0155, "step": 91460 }, { "epoch": 1.49, "learning_rate": 4.2890781563126256e-06, "loss": 2.0061, "step": 91470 }, { "epoch": 1.49, "learning_rate": 4.284068136272545e-06, "loss": 2.0218, "step": 91480 }, { "epoch": 1.49, "learning_rate": 4.279058116232465e-06, "loss": 1.9932, "step": 91490 }, { "epoch": 1.5, "learning_rate": 4.274048096192385e-06, "loss": 1.9997, "step": 91500 }, { "epoch": 1.5, "learning_rate": 4.269038076152305e-06, "loss": 2.0455, "step": 91510 }, { "epoch": 1.5, "learning_rate": 4.2640280561122245e-06, "loss": 2.0057, "step": 91520 }, { "epoch": 1.5, "learning_rate": 4.259018036072144e-06, "loss": 2.0073, "step": 91530 }, { "epoch": 1.5, "learning_rate": 4.254008016032064e-06, "loss": 1.9678, "step": 91540 }, { "epoch": 1.5, "learning_rate": 4.248997995991985e-06, "loss": 2.0319, "step": 91550 }, { "epoch": 1.5, "learning_rate": 4.243987975951904e-06, "loss": 2.0242, "step": 91560 }, { "epoch": 1.5, "learning_rate": 4.2389779559118235e-06, "loss": 2.0436, "step": 91570 }, { "epoch": 1.5, "learning_rate": 4.233967935871744e-06, "loss": 1.9765, "step": 91580 }, { "epoch": 1.5, "learning_rate": 4.228957915831663e-06, "loss": 1.9913, "step": 91590 }, { "epoch": 1.5, "learning_rate": 4.223947895791584e-06, "loss": 2.0228, "step": 91600 }, { "epoch": 1.5, "learning_rate": 4.2189378757515035e-06, "loss": 1.9845, "step": 91610 }, { "epoch": 1.5, "learning_rate": 4.2139278557114225e-06, "loss": 2.0067, "step": 91620 }, { "epoch": 1.5, "learning_rate": 4.208917835671343e-06, "loss": 2.0089, "step": 91630 }, { "epoch": 1.5, "learning_rate": 4.203907815631263e-06, "loss": 2.0001, "step": 91640 }, { "epoch": 1.5, "learning_rate": 4.198897795591183e-06, "loss": 2.009, "step": 91650 }, { "epoch": 1.5, "learning_rate": 4.1938877755511025e-06, "loss": 2.0363, "step": 91660 }, { "epoch": 1.5, "learning_rate": 4.188877755511022e-06, "loss": 2.0133, "step": 91670 }, { "epoch": 1.5, "learning_rate": 4.183867735470942e-06, "loss": 2.0218, "step": 91680 }, { "epoch": 1.5, "learning_rate": 4.178857715430862e-06, "loss": 1.9908, "step": 91690 }, { "epoch": 1.5, "learning_rate": 4.173847695390782e-06, "loss": 2.0061, "step": 91700 }, { "epoch": 1.5, "learning_rate": 4.1688376753507015e-06, "loss": 1.9943, "step": 91710 }, { "epoch": 1.5, "learning_rate": 4.163827655310622e-06, "loss": 1.9967, "step": 91720 }, { "epoch": 1.5, "learning_rate": 4.158817635270541e-06, "loss": 1.9847, "step": 91730 }, { "epoch": 1.5, "learning_rate": 4.153807615230461e-06, "loss": 2.013, "step": 91740 }, { "epoch": 1.5, "learning_rate": 4.149298597194389e-06, "loss": 2.0007, "step": 91750 }, { "epoch": 1.5, "learning_rate": 4.144288577154309e-06, "loss": 2.0207, "step": 91760 }, { "epoch": 1.5, "learning_rate": 4.139278557114229e-06, "loss": 1.98, "step": 91770 }, { "epoch": 1.5, "learning_rate": 4.1342685370741485e-06, "loss": 1.9915, "step": 91780 }, { "epoch": 1.5, "learning_rate": 4.129258517034068e-06, "loss": 2.0233, "step": 91790 }, { "epoch": 1.5, "learning_rate": 4.124248496993988e-06, "loss": 2.019, "step": 91800 }, { "epoch": 1.5, "learning_rate": 4.119238476953908e-06, "loss": 2.0102, "step": 91810 }, { "epoch": 1.5, "learning_rate": 4.1142284569138285e-06, "loss": 2.0424, "step": 91820 }, { "epoch": 1.5, "learning_rate": 4.1092184368737475e-06, "loss": 1.9985, "step": 91830 }, { "epoch": 1.5, "learning_rate": 4.104208416833667e-06, "loss": 1.987, "step": 91840 }, { "epoch": 1.5, "learning_rate": 4.099198396793588e-06, "loss": 2.0203, "step": 91850 }, { "epoch": 1.5, "learning_rate": 4.094188376753507e-06, "loss": 1.9615, "step": 91860 }, { "epoch": 1.5, "learning_rate": 4.0891783567134275e-06, "loss": 1.9537, "step": 91870 }, { "epoch": 1.5, "learning_rate": 4.084168336673347e-06, "loss": 2.0027, "step": 91880 }, { "epoch": 1.5, "learning_rate": 4.079158316633266e-06, "loss": 1.9898, "step": 91890 }, { "epoch": 1.5, "learning_rate": 4.074148296593187e-06, "loss": 2.0436, "step": 91900 }, { "epoch": 1.5, "learning_rate": 4.069138276553106e-06, "loss": 2.0015, "step": 91910 }, { "epoch": 1.5, "learning_rate": 4.0641282565130265e-06, "loss": 1.9989, "step": 91920 }, { "epoch": 1.5, "learning_rate": 4.059118236472946e-06, "loss": 1.9816, "step": 91930 }, { "epoch": 1.5, "learning_rate": 4.054108216432865e-06, "loss": 1.9918, "step": 91940 }, { "epoch": 1.5, "learning_rate": 4.049098196392786e-06, "loss": 2.0417, "step": 91950 }, { "epoch": 1.5, "learning_rate": 4.044088176352706e-06, "loss": 2.001, "step": 91960 }, { "epoch": 1.5, "learning_rate": 4.0390781563126254e-06, "loss": 2.0134, "step": 91970 }, { "epoch": 1.5, "learning_rate": 4.034068136272545e-06, "loss": 2.0165, "step": 91980 }, { "epoch": 1.5, "learning_rate": 4.029058116232466e-06, "loss": 2.0132, "step": 91990 }, { "epoch": 1.5, "learning_rate": 4.024048096192385e-06, "loss": 1.9963, "step": 92000 }, { "epoch": 1.5, "eval_loss": 1.9947196245193481, "eval_mean_f1": 0.6656151022527915, "eval_rouge1_f1": 0.7220269747307874, "eval_rouge1_precision": 0.8321603540629987, "eval_rouge1_recall": 0.6708527734849448, "eval_rouge2_f1": 0.5835671720413983, "eval_rouge2_precision": 0.676702239952973, "eval_rouge2_recall": 0.5424815673811381, "eval_rougeL_f1": 0.691251159986189, "eval_rougeL_precision": 0.794378449576491, "eval_rougeL_recall": 0.6435046193080634, "eval_runtime": 65.3365, "eval_samples_per_second": 15.673, "eval_steps_per_second": 1.959, "step": 92000 }, { "epoch": 1.5, "learning_rate": 4.019038076152305e-06, "loss": 1.9907, "step": 92010 }, { "epoch": 1.5, "learning_rate": 4.014028056112225e-06, "loss": 2.0122, "step": 92020 }, { "epoch": 1.5, "learning_rate": 4.009018036072144e-06, "loss": 2.057, "step": 92030 }, { "epoch": 1.5, "learning_rate": 4.004008016032065e-06, "loss": 1.9829, "step": 92040 }, { "epoch": 1.5, "learning_rate": 3.998997995991984e-06, "loss": 1.9997, "step": 92050 }, { "epoch": 1.5, "learning_rate": 3.9939879759519036e-06, "loss": 2.0242, "step": 92060 }, { "epoch": 1.5, "learning_rate": 3.988977955911824e-06, "loss": 1.9762, "step": 92070 }, { "epoch": 1.5, "learning_rate": 3.983967935871743e-06, "loss": 2.0199, "step": 92080 }, { "epoch": 1.5, "learning_rate": 3.978957915831664e-06, "loss": 2.0273, "step": 92090 }, { "epoch": 1.5, "learning_rate": 3.973947895791584e-06, "loss": 2.022, "step": 92100 }, { "epoch": 1.51, "learning_rate": 3.9689378757515025e-06, "loss": 1.9967, "step": 92110 }, { "epoch": 1.51, "learning_rate": 3.963927855711423e-06, "loss": 1.9787, "step": 92120 }, { "epoch": 1.51, "learning_rate": 3.958917835671343e-06, "loss": 1.9787, "step": 92130 }, { "epoch": 1.51, "learning_rate": 3.953907815631263e-06, "loss": 1.9943, "step": 92140 }, { "epoch": 1.51, "learning_rate": 3.9488977955911826e-06, "loss": 2.0648, "step": 92150 }, { "epoch": 1.51, "learning_rate": 3.943887775551102e-06, "loss": 1.9917, "step": 92160 }, { "epoch": 1.51, "learning_rate": 3.938877755511022e-06, "loss": 1.9908, "step": 92170 }, { "epoch": 1.51, "learning_rate": 3.933867735470942e-06, "loss": 2.0036, "step": 92180 }, { "epoch": 1.51, "learning_rate": 3.928857715430862e-06, "loss": 1.9759, "step": 92190 }, { "epoch": 1.51, "learning_rate": 3.9238476953907815e-06, "loss": 2.0243, "step": 92200 }, { "epoch": 1.51, "learning_rate": 3.918837675350701e-06, "loss": 1.9986, "step": 92210 }, { "epoch": 1.51, "learning_rate": 3.913827655310621e-06, "loss": 1.9605, "step": 92220 }, { "epoch": 1.51, "learning_rate": 3.908817635270541e-06, "loss": 2.0401, "step": 92230 }, { "epoch": 1.51, "learning_rate": 3.9038076152304616e-06, "loss": 2.0375, "step": 92240 }, { "epoch": 1.51, "learning_rate": 3.8987975951903805e-06, "loss": 1.9969, "step": 92250 }, { "epoch": 1.51, "learning_rate": 3.893787575150301e-06, "loss": 2.0314, "step": 92260 }, { "epoch": 1.51, "learning_rate": 3.888777555110221e-06, "loss": 2.0023, "step": 92270 }, { "epoch": 1.51, "learning_rate": 3.88376753507014e-06, "loss": 2.0283, "step": 92280 }, { "epoch": 1.51, "learning_rate": 3.8787575150300605e-06, "loss": 2.0119, "step": 92290 }, { "epoch": 1.51, "learning_rate": 3.87374749498998e-06, "loss": 2.0069, "step": 92300 }, { "epoch": 1.51, "learning_rate": 3.8687374749499e-06, "loss": 2.0128, "step": 92310 }, { "epoch": 1.51, "learning_rate": 3.86372745490982e-06, "loss": 1.9893, "step": 92320 }, { "epoch": 1.51, "learning_rate": 3.85871743486974e-06, "loss": 2.0506, "step": 92330 }, { "epoch": 1.51, "learning_rate": 3.8537074148296595e-06, "loss": 2.0309, "step": 92340 }, { "epoch": 1.51, "learning_rate": 3.848697394789579e-06, "loss": 2.0087, "step": 92350 }, { "epoch": 1.51, "learning_rate": 3.843687374749499e-06, "loss": 2.0158, "step": 92360 }, { "epoch": 1.51, "learning_rate": 3.838677354709419e-06, "loss": 1.9857, "step": 92370 }, { "epoch": 1.51, "learning_rate": 3.833667334669339e-06, "loss": 2.0091, "step": 92380 }, { "epoch": 1.51, "learning_rate": 3.8286573146292585e-06, "loss": 1.9988, "step": 92390 }, { "epoch": 1.51, "learning_rate": 3.823647294589178e-06, "loss": 2.0624, "step": 92400 }, { "epoch": 1.51, "learning_rate": 3.818637274549099e-06, "loss": 2.0063, "step": 92410 }, { "epoch": 1.51, "learning_rate": 3.8136272545090183e-06, "loss": 2.0315, "step": 92420 }, { "epoch": 1.51, "learning_rate": 3.8086172344689377e-06, "loss": 2.0409, "step": 92430 }, { "epoch": 1.51, "learning_rate": 3.803607214428858e-06, "loss": 2.0073, "step": 92440 }, { "epoch": 1.51, "learning_rate": 3.7985971943887777e-06, "loss": 1.985, "step": 92450 }, { "epoch": 1.51, "learning_rate": 3.793587174348698e-06, "loss": 2.0071, "step": 92460 }, { "epoch": 1.51, "learning_rate": 3.7885771543086173e-06, "loss": 2.0069, "step": 92470 }, { "epoch": 1.51, "learning_rate": 3.783567134268537e-06, "loss": 2.0497, "step": 92480 }, { "epoch": 1.51, "learning_rate": 3.7785571142284573e-06, "loss": 2.0144, "step": 92490 }, { "epoch": 1.51, "learning_rate": 3.7735470941883766e-06, "loss": 1.9992, "step": 92500 }, { "epoch": 1.51, "learning_rate": 3.768537074148297e-06, "loss": 1.9842, "step": 92510 }, { "epoch": 1.51, "learning_rate": 3.7635270541082167e-06, "loss": 1.9905, "step": 92520 }, { "epoch": 1.51, "learning_rate": 3.758517034068137e-06, "loss": 2.0253, "step": 92530 }, { "epoch": 1.51, "learning_rate": 3.7535070140280562e-06, "loss": 2.0558, "step": 92540 }, { "epoch": 1.51, "learning_rate": 3.748496993987976e-06, "loss": 2.0059, "step": 92550 }, { "epoch": 1.51, "learning_rate": 3.7434869739478963e-06, "loss": 1.9834, "step": 92560 }, { "epoch": 1.51, "learning_rate": 3.7384769539078156e-06, "loss": 1.9701, "step": 92570 }, { "epoch": 1.51, "learning_rate": 3.733466933867736e-06, "loss": 1.9685, "step": 92580 }, { "epoch": 1.51, "learning_rate": 3.7284569138276556e-06, "loss": 2.0175, "step": 92590 }, { "epoch": 1.51, "learning_rate": 3.723446893787575e-06, "loss": 2.002, "step": 92600 }, { "epoch": 1.51, "learning_rate": 3.7184368737474952e-06, "loss": 1.98, "step": 92610 }, { "epoch": 1.51, "learning_rate": 3.713426853707415e-06, "loss": 1.9956, "step": 92620 }, { "epoch": 1.51, "learning_rate": 3.7084168336673352e-06, "loss": 2.0021, "step": 92630 }, { "epoch": 1.51, "learning_rate": 3.7034068136272546e-06, "loss": 2.0032, "step": 92640 }, { "epoch": 1.51, "learning_rate": 3.6983967935871744e-06, "loss": 1.9777, "step": 92650 }, { "epoch": 1.51, "learning_rate": 3.6933867735470946e-06, "loss": 1.967, "step": 92660 }, { "epoch": 1.51, "learning_rate": 3.688376753507014e-06, "loss": 1.9875, "step": 92670 }, { "epoch": 1.51, "learning_rate": 3.683366733466934e-06, "loss": 1.9575, "step": 92680 }, { "epoch": 1.51, "learning_rate": 3.678356713426854e-06, "loss": 1.9993, "step": 92690 }, { "epoch": 1.51, "learning_rate": 3.6733466933867734e-06, "loss": 1.9857, "step": 92700 }, { "epoch": 1.51, "learning_rate": 3.6683366733466936e-06, "loss": 1.9828, "step": 92710 }, { "epoch": 1.52, "learning_rate": 3.6633266533066134e-06, "loss": 2.006, "step": 92720 }, { "epoch": 1.52, "learning_rate": 3.6583166332665336e-06, "loss": 1.9979, "step": 92730 }, { "epoch": 1.52, "learning_rate": 3.653306613226453e-06, "loss": 2.0287, "step": 92740 }, { "epoch": 1.52, "learning_rate": 3.6482965931863728e-06, "loss": 2.0031, "step": 92750 }, { "epoch": 1.52, "learning_rate": 3.643286573146293e-06, "loss": 1.9931, "step": 92760 }, { "epoch": 1.52, "learning_rate": 3.6382765531062124e-06, "loss": 2.0288, "step": 92770 }, { "epoch": 1.52, "learning_rate": 3.6332665330661326e-06, "loss": 2.0198, "step": 92780 }, { "epoch": 1.52, "learning_rate": 3.6282565130260524e-06, "loss": 2.0354, "step": 92790 }, { "epoch": 1.52, "learning_rate": 3.6232464929859726e-06, "loss": 2.0185, "step": 92800 }, { "epoch": 1.52, "learning_rate": 3.618236472945892e-06, "loss": 2.0016, "step": 92810 }, { "epoch": 1.52, "learning_rate": 3.6132264529058117e-06, "loss": 2.0198, "step": 92820 }, { "epoch": 1.52, "learning_rate": 3.608216432865732e-06, "loss": 2.0079, "step": 92830 }, { "epoch": 1.52, "learning_rate": 3.6032064128256513e-06, "loss": 1.9762, "step": 92840 }, { "epoch": 1.52, "learning_rate": 3.5981963927855716e-06, "loss": 1.9866, "step": 92850 }, { "epoch": 1.52, "learning_rate": 3.5931863727454914e-06, "loss": 1.9733, "step": 92860 }, { "epoch": 1.52, "learning_rate": 3.5881763527054107e-06, "loss": 2.0185, "step": 92870 }, { "epoch": 1.52, "learning_rate": 3.583166332665331e-06, "loss": 1.9792, "step": 92880 }, { "epoch": 1.52, "learning_rate": 3.5781563126252507e-06, "loss": 1.9929, "step": 92890 }, { "epoch": 1.52, "learning_rate": 3.573146292585171e-06, "loss": 1.981, "step": 92900 }, { "epoch": 1.52, "learning_rate": 3.5681362725450903e-06, "loss": 1.9941, "step": 92910 }, { "epoch": 1.52, "learning_rate": 3.56312625250501e-06, "loss": 1.9588, "step": 92920 }, { "epoch": 1.52, "learning_rate": 3.5581162324649303e-06, "loss": 1.9739, "step": 92930 }, { "epoch": 1.52, "learning_rate": 3.5531062124248497e-06, "loss": 1.9912, "step": 92940 }, { "epoch": 1.52, "learning_rate": 3.54809619238477e-06, "loss": 2.0065, "step": 92950 }, { "epoch": 1.52, "learning_rate": 3.5430861723446897e-06, "loss": 1.9771, "step": 92960 }, { "epoch": 1.52, "learning_rate": 3.538076152304609e-06, "loss": 2.0317, "step": 92970 }, { "epoch": 1.52, "learning_rate": 3.5330661322645293e-06, "loss": 2.013, "step": 92980 }, { "epoch": 1.52, "learning_rate": 3.528056112224449e-06, "loss": 2.0034, "step": 92990 }, { "epoch": 1.52, "learning_rate": 3.5230460921843693e-06, "loss": 1.9785, "step": 93000 }, { "epoch": 1.52, "eval_loss": 1.9932501316070557, "eval_mean_f1": 0.6650219336869383, "eval_rouge1_f1": 0.7218187905043821, "eval_rouge1_precision": 0.8312884951133166, "eval_rouge1_recall": 0.6712236106252782, "eval_rouge2_f1": 0.5831531722259728, "eval_rouge2_precision": 0.6758785661495623, "eval_rouge2_recall": 0.5427573991339374, "eval_rougeL_f1": 0.6900938383304598, "eval_rougeL_precision": 0.7936867724831591, "eval_rougeL_recall": 0.6428618101097485, "eval_runtime": 64.9058, "eval_samples_per_second": 15.777, "eval_steps_per_second": 1.972, "step": 93000 }, { "epoch": 1.52, "learning_rate": 3.5180360721442887e-06, "loss": 2.0083, "step": 93010 }, { "epoch": 1.52, "learning_rate": 3.513026052104208e-06, "loss": 1.9309, "step": 93020 }, { "epoch": 1.52, "learning_rate": 3.5080160320641287e-06, "loss": 1.985, "step": 93030 }, { "epoch": 1.52, "learning_rate": 3.503006012024048e-06, "loss": 2.0216, "step": 93040 }, { "epoch": 1.52, "learning_rate": 3.4979959919839683e-06, "loss": 2.0159, "step": 93050 }, { "epoch": 1.52, "learning_rate": 3.492985971943888e-06, "loss": 2.0075, "step": 93060 }, { "epoch": 1.52, "learning_rate": 3.4879759519038075e-06, "loss": 2.0242, "step": 93070 }, { "epoch": 1.52, "learning_rate": 3.4829659318637277e-06, "loss": 1.9745, "step": 93080 }, { "epoch": 1.52, "learning_rate": 3.477955911823647e-06, "loss": 1.9817, "step": 93090 }, { "epoch": 1.52, "learning_rate": 3.4729458917835677e-06, "loss": 1.9794, "step": 93100 }, { "epoch": 1.52, "learning_rate": 3.467935871743487e-06, "loss": 2.03, "step": 93110 }, { "epoch": 1.52, "learning_rate": 3.4629258517034073e-06, "loss": 1.9729, "step": 93120 }, { "epoch": 1.52, "learning_rate": 3.457915831663327e-06, "loss": 2.0448, "step": 93130 }, { "epoch": 1.52, "learning_rate": 3.4529058116232464e-06, "loss": 1.9664, "step": 93140 }, { "epoch": 1.52, "learning_rate": 3.4478957915831667e-06, "loss": 1.9937, "step": 93150 }, { "epoch": 1.52, "learning_rate": 3.442885771543086e-06, "loss": 2.0004, "step": 93160 }, { "epoch": 1.52, "learning_rate": 3.4378757515030067e-06, "loss": 2.0056, "step": 93170 }, { "epoch": 1.52, "learning_rate": 3.432865731462926e-06, "loss": 2.0246, "step": 93180 }, { "epoch": 1.52, "learning_rate": 3.4278557114228454e-06, "loss": 2.0404, "step": 93190 }, { "epoch": 1.52, "learning_rate": 3.422845691382766e-06, "loss": 1.9487, "step": 93200 }, { "epoch": 1.52, "learning_rate": 3.4178356713426854e-06, "loss": 1.9994, "step": 93210 }, { "epoch": 1.52, "learning_rate": 3.4128256513026056e-06, "loss": 2.0094, "step": 93220 }, { "epoch": 1.52, "learning_rate": 3.407815631262525e-06, "loss": 2.0231, "step": 93230 }, { "epoch": 1.52, "learning_rate": 3.402805611222445e-06, "loss": 1.9653, "step": 93240 }, { "epoch": 1.52, "learning_rate": 3.397795591182365e-06, "loss": 2.0037, "step": 93250 }, { "epoch": 1.52, "learning_rate": 3.3927855711422844e-06, "loss": 2.0037, "step": 93260 }, { "epoch": 1.52, "learning_rate": 3.3877755511022046e-06, "loss": 2.0087, "step": 93270 }, { "epoch": 1.52, "learning_rate": 3.3827655310621244e-06, "loss": 1.9796, "step": 93280 }, { "epoch": 1.52, "learning_rate": 3.3777555110220438e-06, "loss": 2.0394, "step": 93290 }, { "epoch": 1.52, "learning_rate": 3.372745490981964e-06, "loss": 2.0294, "step": 93300 }, { "epoch": 1.52, "learning_rate": 3.3677354709418838e-06, "loss": 1.9965, "step": 93310 }, { "epoch": 1.52, "learning_rate": 3.362725450901804e-06, "loss": 1.9659, "step": 93320 }, { "epoch": 1.52, "learning_rate": 3.3577154308617234e-06, "loss": 2.0254, "step": 93330 }, { "epoch": 1.53, "learning_rate": 3.352705410821643e-06, "loss": 2.0025, "step": 93340 }, { "epoch": 1.53, "learning_rate": 3.3476953907815634e-06, "loss": 2.0364, "step": 93350 }, { "epoch": 1.53, "learning_rate": 3.3426853707414828e-06, "loss": 2.0079, "step": 93360 }, { "epoch": 1.53, "learning_rate": 3.337675350701403e-06, "loss": 1.9684, "step": 93370 }, { "epoch": 1.53, "learning_rate": 3.3326653306613228e-06, "loss": 2.0175, "step": 93380 }, { "epoch": 1.53, "learning_rate": 3.327655310621243e-06, "loss": 1.9823, "step": 93390 }, { "epoch": 1.53, "learning_rate": 3.3226452905811624e-06, "loss": 1.9756, "step": 93400 }, { "epoch": 1.53, "learning_rate": 3.317635270541082e-06, "loss": 1.996, "step": 93410 }, { "epoch": 1.53, "learning_rate": 3.3126252505010024e-06, "loss": 1.9979, "step": 93420 }, { "epoch": 1.53, "learning_rate": 3.3076152304609217e-06, "loss": 1.9395, "step": 93430 }, { "epoch": 1.53, "learning_rate": 3.302605210420842e-06, "loss": 1.9895, "step": 93440 }, { "epoch": 1.53, "learning_rate": 3.2975951903807618e-06, "loss": 2.0206, "step": 93450 }, { "epoch": 1.53, "learning_rate": 3.292585170340681e-06, "loss": 2.0127, "step": 93460 }, { "epoch": 1.53, "learning_rate": 3.2875751503006013e-06, "loss": 1.9811, "step": 93470 }, { "epoch": 1.53, "learning_rate": 3.282565130260521e-06, "loss": 2.0141, "step": 93480 }, { "epoch": 1.53, "learning_rate": 3.2775551102204414e-06, "loss": 2.0072, "step": 93490 }, { "epoch": 1.53, "learning_rate": 3.2725450901803607e-06, "loss": 2.0131, "step": 93500 }, { "epoch": 1.53, "learning_rate": 3.2675350701402805e-06, "loss": 1.9588, "step": 93510 }, { "epoch": 1.53, "learning_rate": 3.2625250501002007e-06, "loss": 2.0176, "step": 93520 }, { "epoch": 1.53, "learning_rate": 3.25751503006012e-06, "loss": 2.0154, "step": 93530 }, { "epoch": 1.53, "learning_rate": 3.2525050100200403e-06, "loss": 2.0312, "step": 93540 }, { "epoch": 1.53, "learning_rate": 3.24749498997996e-06, "loss": 2.0433, "step": 93550 }, { "epoch": 1.53, "learning_rate": 3.2424849699398795e-06, "loss": 2.0097, "step": 93560 }, { "epoch": 1.53, "learning_rate": 3.2374749498997997e-06, "loss": 2.0329, "step": 93570 }, { "epoch": 1.53, "learning_rate": 3.2324649298597195e-06, "loss": 1.997, "step": 93580 }, { "epoch": 1.53, "learning_rate": 3.2274549098196397e-06, "loss": 1.9502, "step": 93590 }, { "epoch": 1.53, "learning_rate": 3.222444889779559e-06, "loss": 2.0195, "step": 93600 }, { "epoch": 1.53, "learning_rate": 3.217434869739479e-06, "loss": 2.0417, "step": 93610 }, { "epoch": 1.53, "learning_rate": 3.212424849699399e-06, "loss": 2.0221, "step": 93620 }, { "epoch": 1.53, "learning_rate": 3.2074148296593185e-06, "loss": 1.938, "step": 93630 }, { "epoch": 1.53, "learning_rate": 3.2024048096192387e-06, "loss": 2.011, "step": 93640 }, { "epoch": 1.53, "learning_rate": 3.1973947895791585e-06, "loss": 1.9747, "step": 93650 }, { "epoch": 1.53, "learning_rate": 3.1923847695390787e-06, "loss": 2.0243, "step": 93660 }, { "epoch": 1.53, "learning_rate": 3.187374749498998e-06, "loss": 1.9956, "step": 93670 }, { "epoch": 1.53, "learning_rate": 3.182364729458918e-06, "loss": 2.009, "step": 93680 }, { "epoch": 1.53, "learning_rate": 3.177354709418838e-06, "loss": 1.9962, "step": 93690 }, { "epoch": 1.53, "learning_rate": 3.1723446893787575e-06, "loss": 2.0091, "step": 93700 }, { "epoch": 1.53, "learning_rate": 3.1673346693386777e-06, "loss": 1.9865, "step": 93710 }, { "epoch": 1.53, "learning_rate": 3.1623246492985975e-06, "loss": 2.0115, "step": 93720 }, { "epoch": 1.53, "learning_rate": 3.157314629258517e-06, "loss": 2.0304, "step": 93730 }, { "epoch": 1.53, "learning_rate": 3.152304609218437e-06, "loss": 1.9564, "step": 93740 }, { "epoch": 1.53, "learning_rate": 3.147294589178357e-06, "loss": 1.9695, "step": 93750 }, { "epoch": 1.53, "learning_rate": 3.142284569138277e-06, "loss": 2.0142, "step": 93760 }, { "epoch": 1.53, "learning_rate": 3.1372745490981964e-06, "loss": 1.9946, "step": 93770 }, { "epoch": 1.53, "learning_rate": 3.1322645290581162e-06, "loss": 2.0419, "step": 93780 }, { "epoch": 1.53, "learning_rate": 3.1272545090180365e-06, "loss": 2.0221, "step": 93790 }, { "epoch": 1.53, "learning_rate": 3.122244488977956e-06, "loss": 1.9598, "step": 93800 }, { "epoch": 1.53, "learning_rate": 3.1172344689378756e-06, "loss": 2.0014, "step": 93810 }, { "epoch": 1.53, "learning_rate": 3.112224448897796e-06, "loss": 2.0484, "step": 93820 }, { "epoch": 1.53, "learning_rate": 3.1072144288577156e-06, "loss": 2.016, "step": 93830 }, { "epoch": 1.53, "learning_rate": 3.1022044088176354e-06, "loss": 1.9305, "step": 93840 }, { "epoch": 1.53, "learning_rate": 3.0971943887775552e-06, "loss": 1.9853, "step": 93850 }, { "epoch": 1.53, "learning_rate": 3.092685370741483e-06, "loss": 2.0091, "step": 93860 }, { "epoch": 1.53, "learning_rate": 3.087675350701403e-06, "loss": 1.9955, "step": 93870 }, { "epoch": 1.53, "learning_rate": 3.0826653306613226e-06, "loss": 2.0153, "step": 93880 }, { "epoch": 1.53, "learning_rate": 3.077655310621243e-06, "loss": 1.9988, "step": 93890 }, { "epoch": 1.53, "learning_rate": 3.0726452905811626e-06, "loss": 1.9922, "step": 93900 }, { "epoch": 1.53, "learning_rate": 3.067635270541082e-06, "loss": 2.02, "step": 93910 }, { "epoch": 1.53, "learning_rate": 3.0626252505010022e-06, "loss": 1.9524, "step": 93920 }, { "epoch": 1.53, "learning_rate": 3.057615230460922e-06, "loss": 2.009, "step": 93930 }, { "epoch": 1.53, "learning_rate": 3.052605210420842e-06, "loss": 2.0489, "step": 93940 }, { "epoch": 1.54, "learning_rate": 3.0475951903807616e-06, "loss": 2.0007, "step": 93950 }, { "epoch": 1.54, "learning_rate": 3.0425851703406814e-06, "loss": 2.0002, "step": 93960 }, { "epoch": 1.54, "learning_rate": 3.037575150300601e-06, "loss": 2.0206, "step": 93970 }, { "epoch": 1.54, "learning_rate": 3.032565130260521e-06, "loss": 1.9991, "step": 93980 }, { "epoch": 1.54, "learning_rate": 3.027555110220441e-06, "loss": 1.9992, "step": 93990 }, { "epoch": 1.54, "learning_rate": 3.022545090180361e-06, "loss": 2.0199, "step": 94000 }, { "epoch": 1.54, "eval_loss": 1.9947196245193481, "eval_mean_f1": 0.6608476268846778, "eval_rouge1_f1": 0.718566925061981, "eval_rouge1_precision": 0.8294998914484197, "eval_rouge1_recall": 0.6675928423150275, "eval_rouge2_f1": 0.5777095245499453, "eval_rouge2_precision": 0.6710934668087991, "eval_rouge2_recall": 0.536806018848079, "eval_rougeL_f1": 0.6862664310421069, "eval_rougeL_precision": 0.7905007823601289, "eval_rougeL_recall": 0.6385323109600188, "eval_runtime": 67.1837, "eval_samples_per_second": 15.242, "eval_steps_per_second": 1.905, "step": 94000 }, { "epoch": 1.54, "learning_rate": 3.0175350701402804e-06, "loss": 1.99, "step": 94010 }, { "epoch": 1.54, "learning_rate": 3.0125250501002006e-06, "loss": 1.9806, "step": 94020 }, { "epoch": 1.54, "learning_rate": 3.0075150300601204e-06, "loss": 1.9916, "step": 94030 }, { "epoch": 1.54, "learning_rate": 3.00250501002004e-06, "loss": 1.9971, "step": 94040 }, { "epoch": 1.54, "learning_rate": 2.99749498997996e-06, "loss": 2.009, "step": 94050 }, { "epoch": 1.54, "learning_rate": 2.99248496993988e-06, "loss": 1.9793, "step": 94060 }, { "epoch": 1.54, "learning_rate": 2.9874749498997996e-06, "loss": 2.0096, "step": 94070 }, { "epoch": 1.54, "learning_rate": 2.9824649298597194e-06, "loss": 2.0305, "step": 94080 }, { "epoch": 1.54, "learning_rate": 2.9774549098196396e-06, "loss": 1.9896, "step": 94090 }, { "epoch": 1.54, "learning_rate": 2.9724448897795594e-06, "loss": 2.0135, "step": 94100 }, { "epoch": 1.54, "learning_rate": 2.967434869739479e-06, "loss": 2.0003, "step": 94110 }, { "epoch": 1.54, "learning_rate": 2.962424849699399e-06, "loss": 2.0033, "step": 94120 }, { "epoch": 1.54, "learning_rate": 2.9574148296593188e-06, "loss": 1.9972, "step": 94130 }, { "epoch": 1.54, "learning_rate": 2.9524048096192385e-06, "loss": 2.008, "step": 94140 }, { "epoch": 1.54, "learning_rate": 2.9473947895791583e-06, "loss": 2.001, "step": 94150 }, { "epoch": 1.54, "learning_rate": 2.9423847695390786e-06, "loss": 1.9811, "step": 94160 }, { "epoch": 1.54, "learning_rate": 2.9373747494989984e-06, "loss": 1.9848, "step": 94170 }, { "epoch": 1.54, "learning_rate": 2.9323647294589177e-06, "loss": 2.0009, "step": 94180 }, { "epoch": 1.54, "learning_rate": 2.927354709418838e-06, "loss": 1.975, "step": 94190 }, { "epoch": 1.54, "learning_rate": 2.9223446893787577e-06, "loss": 2.0433, "step": 94200 }, { "epoch": 1.54, "learning_rate": 2.9173346693386775e-06, "loss": 1.9898, "step": 94210 }, { "epoch": 1.54, "learning_rate": 2.9123246492985973e-06, "loss": 1.9779, "step": 94220 }, { "epoch": 1.54, "learning_rate": 2.907314629258517e-06, "loss": 1.9739, "step": 94230 }, { "epoch": 1.54, "learning_rate": 2.902304609218437e-06, "loss": 1.9549, "step": 94240 }, { "epoch": 1.54, "learning_rate": 2.8972945891783567e-06, "loss": 2.0227, "step": 94250 }, { "epoch": 1.54, "learning_rate": 2.892284569138277e-06, "loss": 1.9801, "step": 94260 }, { "epoch": 1.54, "learning_rate": 2.8872745490981967e-06, "loss": 1.9443, "step": 94270 }, { "epoch": 1.54, "learning_rate": 2.882264529058116e-06, "loss": 1.9919, "step": 94280 }, { "epoch": 1.54, "learning_rate": 2.8772545090180363e-06, "loss": 1.9834, "step": 94290 }, { "epoch": 1.54, "learning_rate": 2.872244488977956e-06, "loss": 2.013, "step": 94300 }, { "epoch": 1.54, "learning_rate": 2.867234468937876e-06, "loss": 1.9805, "step": 94310 }, { "epoch": 1.54, "learning_rate": 2.8622244488977957e-06, "loss": 1.9831, "step": 94320 }, { "epoch": 1.54, "learning_rate": 2.857214428857716e-06, "loss": 2.0305, "step": 94330 }, { "epoch": 1.54, "learning_rate": 2.8522044088176353e-06, "loss": 2.0171, "step": 94340 }, { "epoch": 1.54, "learning_rate": 2.847194388777555e-06, "loss": 1.9783, "step": 94350 }, { "epoch": 1.54, "learning_rate": 2.8421843687374753e-06, "loss": 2.0299, "step": 94360 }, { "epoch": 1.54, "learning_rate": 2.837174348697395e-06, "loss": 2.0295, "step": 94370 }, { "epoch": 1.54, "learning_rate": 2.832164328657315e-06, "loss": 2.0026, "step": 94380 }, { "epoch": 1.54, "learning_rate": 2.8271543086172342e-06, "loss": 1.9849, "step": 94390 }, { "epoch": 1.54, "learning_rate": 2.8221442885771545e-06, "loss": 1.9872, "step": 94400 }, { "epoch": 1.54, "learning_rate": 2.8171342685370743e-06, "loss": 1.9758, "step": 94410 }, { "epoch": 1.54, "learning_rate": 2.812124248496994e-06, "loss": 2.0223, "step": 94420 }, { "epoch": 1.54, "learning_rate": 2.8071142284569143e-06, "loss": 1.9881, "step": 94430 }, { "epoch": 1.54, "learning_rate": 2.8021042084168336e-06, "loss": 2.0008, "step": 94440 }, { "epoch": 1.54, "learning_rate": 2.7970941883767534e-06, "loss": 2.0105, "step": 94450 }, { "epoch": 1.54, "learning_rate": 2.7920841683366732e-06, "loss": 1.9965, "step": 94460 }, { "epoch": 1.54, "learning_rate": 2.7870741482965935e-06, "loss": 1.9891, "step": 94470 }, { "epoch": 1.54, "learning_rate": 2.7820641282565132e-06, "loss": 2.0294, "step": 94480 }, { "epoch": 1.54, "learning_rate": 2.777054108216433e-06, "loss": 2.0131, "step": 94490 }, { "epoch": 1.54, "learning_rate": 2.772044088176353e-06, "loss": 2.0478, "step": 94500 }, { "epoch": 1.54, "learning_rate": 2.7670340681362726e-06, "loss": 1.9712, "step": 94510 }, { "epoch": 1.54, "learning_rate": 2.7620240480961924e-06, "loss": 2.0376, "step": 94520 }, { "epoch": 1.54, "learning_rate": 2.7570140280561122e-06, "loss": 1.9937, "step": 94530 }, { "epoch": 1.54, "learning_rate": 2.7520040080160324e-06, "loss": 2.0129, "step": 94540 }, { "epoch": 1.54, "learning_rate": 2.746993987975952e-06, "loss": 1.9859, "step": 94550 }, { "epoch": 1.55, "learning_rate": 2.7419839679358716e-06, "loss": 1.9898, "step": 94560 }, { "epoch": 1.55, "learning_rate": 2.736973947895792e-06, "loss": 2.0291, "step": 94570 }, { "epoch": 1.55, "learning_rate": 2.7319639278557116e-06, "loss": 2.0468, "step": 94580 }, { "epoch": 1.55, "learning_rate": 2.7269539078156314e-06, "loss": 2.067, "step": 94590 }, { "epoch": 1.55, "learning_rate": 2.721943887775551e-06, "loss": 1.9831, "step": 94600 }, { "epoch": 1.55, "learning_rate": 2.716933867735471e-06, "loss": 2.0141, "step": 94610 }, { "epoch": 1.55, "learning_rate": 2.711923847695391e-06, "loss": 1.9471, "step": 94620 }, { "epoch": 1.55, "learning_rate": 2.7069138276553106e-06, "loss": 1.9729, "step": 94630 }, { "epoch": 1.55, "learning_rate": 2.701903807615231e-06, "loss": 2.0134, "step": 94640 }, { "epoch": 1.55, "learning_rate": 2.6968937875751506e-06, "loss": 1.9914, "step": 94650 }, { "epoch": 1.55, "learning_rate": 2.69188376753507e-06, "loss": 1.9879, "step": 94660 }, { "epoch": 1.55, "learning_rate": 2.68687374749499e-06, "loss": 1.997, "step": 94670 }, { "epoch": 1.55, "learning_rate": 2.68186372745491e-06, "loss": 2.0455, "step": 94680 }, { "epoch": 1.55, "learning_rate": 2.6768537074148298e-06, "loss": 2.0054, "step": 94690 }, { "epoch": 1.55, "learning_rate": 2.6718436873747496e-06, "loss": 2.0206, "step": 94700 }, { "epoch": 1.55, "learning_rate": 2.6668336673346694e-06, "loss": 1.9974, "step": 94710 }, { "epoch": 1.55, "learning_rate": 2.661823647294589e-06, "loss": 2.0248, "step": 94720 }, { "epoch": 1.55, "learning_rate": 2.656813627254509e-06, "loss": 2.0054, "step": 94730 }, { "epoch": 1.55, "learning_rate": 2.651803607214429e-06, "loss": 2.014, "step": 94740 }, { "epoch": 1.55, "learning_rate": 2.646793587174349e-06, "loss": 2.0049, "step": 94750 }, { "epoch": 1.55, "learning_rate": 2.6417835671342688e-06, "loss": 1.9651, "step": 94760 }, { "epoch": 1.55, "learning_rate": 2.6367735470941885e-06, "loss": 2.022, "step": 94770 }, { "epoch": 1.55, "learning_rate": 2.6317635270541083e-06, "loss": 2.0186, "step": 94780 }, { "epoch": 1.55, "learning_rate": 2.626753507014028e-06, "loss": 1.9913, "step": 94790 }, { "epoch": 1.55, "learning_rate": 2.621743486973948e-06, "loss": 2.0128, "step": 94800 }, { "epoch": 1.55, "learning_rate": 2.616733466933868e-06, "loss": 2.0291, "step": 94810 }, { "epoch": 1.55, "learning_rate": 2.6117234468937875e-06, "loss": 1.9934, "step": 94820 }, { "epoch": 1.55, "learning_rate": 2.6067134268537073e-06, "loss": 1.9811, "step": 94830 }, { "epoch": 1.55, "learning_rate": 2.6017034068136275e-06, "loss": 1.9676, "step": 94840 }, { "epoch": 1.55, "learning_rate": 2.5966933867735473e-06, "loss": 1.9933, "step": 94850 }, { "epoch": 1.55, "learning_rate": 2.591683366733467e-06, "loss": 2.0021, "step": 94860 }, { "epoch": 1.55, "learning_rate": 2.586673346693387e-06, "loss": 2.0308, "step": 94870 }, { "epoch": 1.55, "learning_rate": 2.5816633266533067e-06, "loss": 1.9734, "step": 94880 }, { "epoch": 1.55, "learning_rate": 2.5766533066132265e-06, "loss": 2.0036, "step": 94890 }, { "epoch": 1.55, "learning_rate": 2.5716432865731463e-06, "loss": 1.9794, "step": 94900 }, { "epoch": 1.55, "learning_rate": 2.5666332665330665e-06, "loss": 2.0614, "step": 94910 }, { "epoch": 1.55, "learning_rate": 2.5616232464929863e-06, "loss": 1.9859, "step": 94920 }, { "epoch": 1.55, "learning_rate": 2.5566132264529057e-06, "loss": 1.9925, "step": 94930 }, { "epoch": 1.55, "learning_rate": 2.551603206412826e-06, "loss": 2.036, "step": 94940 }, { "epoch": 1.55, "learning_rate": 2.5465931863727457e-06, "loss": 2.0281, "step": 94950 }, { "epoch": 1.55, "learning_rate": 2.5415831663326655e-06, "loss": 2.0117, "step": 94960 }, { "epoch": 1.55, "learning_rate": 2.5365731462925853e-06, "loss": 2.0113, "step": 94970 }, { "epoch": 1.55, "learning_rate": 2.531563126252505e-06, "loss": 1.9934, "step": 94980 }, { "epoch": 1.55, "learning_rate": 2.526553106212425e-06, "loss": 2.0303, "step": 94990 }, { "epoch": 1.55, "learning_rate": 2.5215430861723447e-06, "loss": 2.0166, "step": 95000 }, { "epoch": 1.55, "eval_loss": 1.9964184761047363, "eval_mean_f1": 0.6598198576682425, "eval_rouge1_f1": 0.7161114319719639, "eval_rouge1_precision": 0.8265025922683324, "eval_rouge1_recall": 0.6654065161220235, "eval_rouge2_f1": 0.5771589784513302, "eval_rouge2_precision": 0.671570884492027, "eval_rouge2_recall": 0.5358356011921468, "eval_rougeL_f1": 0.6861891625814335, "eval_rougeL_precision": 0.7908202966387416, "eval_rougeL_recall": 0.6385846009468739, "eval_runtime": 63.8101, "eval_samples_per_second": 16.048, "eval_steps_per_second": 2.006, "step": 95000 }, { "epoch": 1.55, "learning_rate": 2.516533066132265e-06, "loss": 1.9746, "step": 95010 }, { "epoch": 1.55, "learning_rate": 2.5115230460921847e-06, "loss": 1.9848, "step": 95020 }, { "epoch": 1.55, "learning_rate": 2.5065130260521045e-06, "loss": 1.9984, "step": 95030 }, { "epoch": 1.55, "learning_rate": 2.501503006012024e-06, "loss": 1.9703, "step": 95040 }, { "epoch": 1.55, "learning_rate": 2.496492985971944e-06, "loss": 1.9988, "step": 95050 }, { "epoch": 1.55, "learning_rate": 2.491482965931864e-06, "loss": 1.958, "step": 95060 }, { "epoch": 1.55, "learning_rate": 2.4864729458917836e-06, "loss": 1.9889, "step": 95070 }, { "epoch": 1.55, "learning_rate": 2.481462925851704e-06, "loss": 1.9768, "step": 95080 }, { "epoch": 1.55, "learning_rate": 2.4764529058116232e-06, "loss": 1.9866, "step": 95090 }, { "epoch": 1.55, "learning_rate": 2.471442885771543e-06, "loss": 2.0196, "step": 95100 }, { "epoch": 1.55, "learning_rate": 2.466432865731463e-06, "loss": 2.0557, "step": 95110 }, { "epoch": 1.55, "learning_rate": 2.461422845691383e-06, "loss": 1.9837, "step": 95120 }, { "epoch": 1.55, "learning_rate": 2.456412825651303e-06, "loss": 1.9532, "step": 95130 }, { "epoch": 1.55, "learning_rate": 2.451402805611222e-06, "loss": 2.0125, "step": 95140 }, { "epoch": 1.55, "learning_rate": 2.4463927855711424e-06, "loss": 2.0026, "step": 95150 }, { "epoch": 1.55, "learning_rate": 2.4413827655310622e-06, "loss": 1.9825, "step": 95160 }, { "epoch": 1.56, "learning_rate": 2.436372745490982e-06, "loss": 1.9745, "step": 95170 }, { "epoch": 1.56, "learning_rate": 2.431362725450902e-06, "loss": 1.9885, "step": 95180 }, { "epoch": 1.56, "learning_rate": 2.426352705410822e-06, "loss": 2.005, "step": 95190 }, { "epoch": 1.56, "learning_rate": 2.4213426853707414e-06, "loss": 2.0551, "step": 95200 }, { "epoch": 1.56, "learning_rate": 2.416332665330661e-06, "loss": 2.031, "step": 95210 }, { "epoch": 1.56, "learning_rate": 2.4113226452905814e-06, "loss": 2.0385, "step": 95220 }, { "epoch": 1.56, "learning_rate": 2.406312625250501e-06, "loss": 2.0287, "step": 95230 }, { "epoch": 1.56, "learning_rate": 2.401302605210421e-06, "loss": 1.9979, "step": 95240 }, { "epoch": 1.56, "learning_rate": 2.396292585170341e-06, "loss": 1.9652, "step": 95250 }, { "epoch": 1.56, "learning_rate": 2.3912825651302606e-06, "loss": 2.0012, "step": 95260 }, { "epoch": 1.56, "learning_rate": 2.3862725450901804e-06, "loss": 1.9436, "step": 95270 }, { "epoch": 1.56, "learning_rate": 2.3812625250501e-06, "loss": 2.0109, "step": 95280 }, { "epoch": 1.56, "learning_rate": 2.3762525050100204e-06, "loss": 2.0525, "step": 95290 }, { "epoch": 1.56, "learning_rate": 2.37124248496994e-06, "loss": 2.0323, "step": 95300 }, { "epoch": 1.56, "learning_rate": 2.3662324649298596e-06, "loss": 2.0286, "step": 95310 }, { "epoch": 1.56, "learning_rate": 2.3612224448897798e-06, "loss": 1.9627, "step": 95320 }, { "epoch": 1.56, "learning_rate": 2.3562124248496996e-06, "loss": 1.9592, "step": 95330 }, { "epoch": 1.56, "learning_rate": 2.3512024048096194e-06, "loss": 1.9569, "step": 95340 }, { "epoch": 1.56, "learning_rate": 2.346192384769539e-06, "loss": 1.9714, "step": 95350 }, { "epoch": 1.56, "learning_rate": 2.341182364729459e-06, "loss": 1.9951, "step": 95360 }, { "epoch": 1.56, "learning_rate": 2.3361723446893787e-06, "loss": 2.0075, "step": 95370 }, { "epoch": 1.56, "learning_rate": 2.3311623246492985e-06, "loss": 2.1021, "step": 95380 }, { "epoch": 1.56, "learning_rate": 2.3261523046092188e-06, "loss": 1.9999, "step": 95390 }, { "epoch": 1.56, "learning_rate": 2.3211422845691386e-06, "loss": 1.9772, "step": 95400 }, { "epoch": 1.56, "learning_rate": 2.316132264529058e-06, "loss": 1.9883, "step": 95410 }, { "epoch": 1.56, "learning_rate": 2.311122244488978e-06, "loss": 1.956, "step": 95420 }, { "epoch": 1.56, "learning_rate": 2.306112224448898e-06, "loss": 1.986, "step": 95430 }, { "epoch": 1.56, "learning_rate": 2.3011022044088177e-06, "loss": 1.9989, "step": 95440 }, { "epoch": 1.56, "learning_rate": 2.2960921843687375e-06, "loss": 1.961, "step": 95450 }, { "epoch": 1.56, "learning_rate": 2.2910821643286577e-06, "loss": 2.0264, "step": 95460 }, { "epoch": 1.56, "learning_rate": 2.286072144288577e-06, "loss": 1.9837, "step": 95470 }, { "epoch": 1.56, "learning_rate": 2.281062124248497e-06, "loss": 2.0541, "step": 95480 }, { "epoch": 1.56, "learning_rate": 2.276052104208417e-06, "loss": 2.0331, "step": 95490 }, { "epoch": 1.56, "learning_rate": 2.271042084168337e-06, "loss": 2.0087, "step": 95500 }, { "epoch": 1.56, "learning_rate": 2.2660320641282567e-06, "loss": 2.0341, "step": 95510 }, { "epoch": 1.56, "learning_rate": 2.2610220440881765e-06, "loss": 1.9875, "step": 95520 }, { "epoch": 1.56, "learning_rate": 2.2560120240480963e-06, "loss": 2.0025, "step": 95530 }, { "epoch": 1.56, "learning_rate": 2.251002004008016e-06, "loss": 2.0285, "step": 95540 }, { "epoch": 1.56, "learning_rate": 2.245991983967936e-06, "loss": 2.0239, "step": 95550 }, { "epoch": 1.56, "learning_rate": 2.240981963927856e-06, "loss": 2.0324, "step": 95560 }, { "epoch": 1.56, "learning_rate": 2.235971943887776e-06, "loss": 1.9759, "step": 95570 }, { "epoch": 1.56, "learning_rate": 2.2309619238476953e-06, "loss": 2.0075, "step": 95580 }, { "epoch": 1.56, "learning_rate": 2.2259519038076155e-06, "loss": 2.015, "step": 95590 }, { "epoch": 1.56, "learning_rate": 2.2209418837675353e-06, "loss": 1.9817, "step": 95600 }, { "epoch": 1.56, "learning_rate": 2.215931863727455e-06, "loss": 1.9866, "step": 95610 }, { "epoch": 1.56, "learning_rate": 2.210921843687375e-06, "loss": 1.9673, "step": 95620 }, { "epoch": 1.56, "learning_rate": 2.2059118236472947e-06, "loss": 2.0248, "step": 95630 }, { "epoch": 1.56, "learning_rate": 2.2009018036072145e-06, "loss": 1.9622, "step": 95640 }, { "epoch": 1.56, "learning_rate": 2.1958917835671343e-06, "loss": 2.014, "step": 95650 }, { "epoch": 1.56, "learning_rate": 2.1908817635270545e-06, "loss": 1.9722, "step": 95660 }, { "epoch": 1.56, "learning_rate": 2.1858717434869743e-06, "loss": 1.9737, "step": 95670 }, { "epoch": 1.56, "learning_rate": 2.1808617234468936e-06, "loss": 2.0366, "step": 95680 }, { "epoch": 1.56, "learning_rate": 2.1758517034068134e-06, "loss": 1.9709, "step": 95690 }, { "epoch": 1.56, "learning_rate": 2.1708416833667337e-06, "loss": 1.9801, "step": 95700 }, { "epoch": 1.56, "learning_rate": 2.1658316633266534e-06, "loss": 2.0092, "step": 95710 }, { "epoch": 1.56, "learning_rate": 2.1608216432865732e-06, "loss": 1.9979, "step": 95720 }, { "epoch": 1.56, "learning_rate": 2.155811623246493e-06, "loss": 1.9985, "step": 95730 }, { "epoch": 1.56, "learning_rate": 2.150801603206413e-06, "loss": 2.0019, "step": 95740 }, { "epoch": 1.56, "learning_rate": 2.1457915831663326e-06, "loss": 1.9922, "step": 95750 }, { "epoch": 1.56, "learning_rate": 2.1407815631262524e-06, "loss": 1.9924, "step": 95760 }, { "epoch": 1.56, "learning_rate": 2.1357715430861726e-06, "loss": 2.0368, "step": 95770 }, { "epoch": 1.57, "learning_rate": 2.1307615230460924e-06, "loss": 2.0304, "step": 95780 }, { "epoch": 1.57, "learning_rate": 2.125751503006012e-06, "loss": 2.0175, "step": 95790 }, { "epoch": 1.57, "learning_rate": 2.120741482965932e-06, "loss": 2.0306, "step": 95800 }, { "epoch": 1.57, "learning_rate": 2.115731462925852e-06, "loss": 2.0065, "step": 95810 }, { "epoch": 1.57, "learning_rate": 2.1107214428857716e-06, "loss": 1.9812, "step": 95820 }, { "epoch": 1.57, "learning_rate": 2.1057114228456914e-06, "loss": 2.0374, "step": 95830 }, { "epoch": 1.57, "learning_rate": 2.1007014028056116e-06, "loss": 1.9879, "step": 95840 }, { "epoch": 1.57, "learning_rate": 2.095691382765531e-06, "loss": 2.0281, "step": 95850 }, { "epoch": 1.57, "learning_rate": 2.0906813627254508e-06, "loss": 2.0422, "step": 95860 }, { "epoch": 1.57, "learning_rate": 2.085671342685371e-06, "loss": 2.0045, "step": 95870 }, { "epoch": 1.57, "learning_rate": 2.080661322645291e-06, "loss": 2.0089, "step": 95880 }, { "epoch": 1.57, "learning_rate": 2.0756513026052106e-06, "loss": 2.0725, "step": 95890 }, { "epoch": 1.57, "learning_rate": 2.0706412825651304e-06, "loss": 1.9947, "step": 95900 }, { "epoch": 1.57, "learning_rate": 2.06563126252505e-06, "loss": 1.9943, "step": 95910 }, { "epoch": 1.57, "learning_rate": 2.06062124248497e-06, "loss": 2.0381, "step": 95920 }, { "epoch": 1.57, "learning_rate": 2.0556112224448898e-06, "loss": 1.9968, "step": 95930 }, { "epoch": 1.57, "learning_rate": 2.05060120240481e-06, "loss": 1.9742, "step": 95940 }, { "epoch": 1.57, "learning_rate": 2.0455911823647294e-06, "loss": 1.9915, "step": 95950 }, { "epoch": 1.57, "learning_rate": 2.040581162324649e-06, "loss": 1.9514, "step": 95960 }, { "epoch": 1.57, "learning_rate": 2.0355711422845694e-06, "loss": 2.0067, "step": 95970 }, { "epoch": 1.57, "learning_rate": 2.030561122244489e-06, "loss": 1.9995, "step": 95980 }, { "epoch": 1.57, "learning_rate": 2.025551102204409e-06, "loss": 2.0278, "step": 95990 }, { "epoch": 1.57, "learning_rate": 2.0205410821643288e-06, "loss": 2.0057, "step": 96000 }, { "epoch": 1.57, "eval_loss": 1.992992639541626, "eval_mean_f1": 0.6636944235639751, "eval_rouge1_f1": 0.7200675430539134, "eval_rouge1_precision": 0.8308226313600993, "eval_rouge1_recall": 0.6687874942841078, "eval_rouge2_f1": 0.5810019369371768, "eval_rouge2_precision": 0.6747001824943719, "eval_rouge2_recall": 0.5394175782091444, "eval_rougeL_f1": 0.6900137907008352, "eval_rougeL_precision": 0.7944500766655097, "eval_rougeL_recall": 0.6419247296454305, "eval_runtime": 66.7702, "eval_samples_per_second": 15.336, "eval_steps_per_second": 1.917, "step": 96000 }, { "epoch": 1.57, "learning_rate": 2.0155310621242485e-06, "loss": 2.0075, "step": 96010 }, { "epoch": 1.57, "learning_rate": 2.0105210420841683e-06, "loss": 1.976, "step": 96020 }, { "epoch": 1.57, "learning_rate": 2.005511022044088e-06, "loss": 1.9936, "step": 96030 }, { "epoch": 1.57, "learning_rate": 2.0005010020040084e-06, "loss": 1.9848, "step": 96040 }, { "epoch": 1.57, "learning_rate": 1.995490981963928e-06, "loss": 2.0173, "step": 96050 }, { "epoch": 1.57, "learning_rate": 1.9904809619238475e-06, "loss": 2.0342, "step": 96060 }, { "epoch": 1.57, "learning_rate": 1.9854709418837677e-06, "loss": 2.0073, "step": 96070 }, { "epoch": 1.57, "learning_rate": 1.9804609218436875e-06, "loss": 1.9843, "step": 96080 }, { "epoch": 1.57, "learning_rate": 1.9754509018036073e-06, "loss": 2.0025, "step": 96090 }, { "epoch": 1.57, "learning_rate": 1.970440881763527e-06, "loss": 1.9752, "step": 96100 }, { "epoch": 1.57, "learning_rate": 1.965430861723447e-06, "loss": 2.0113, "step": 96110 }, { "epoch": 1.57, "learning_rate": 1.9604208416833667e-06, "loss": 1.9669, "step": 96120 }, { "epoch": 1.57, "learning_rate": 1.9554108216432865e-06, "loss": 1.9979, "step": 96130 }, { "epoch": 1.57, "learning_rate": 1.9504008016032067e-06, "loss": 2.0254, "step": 96140 }, { "epoch": 1.57, "learning_rate": 1.9453907815631265e-06, "loss": 2.0138, "step": 96150 }, { "epoch": 1.57, "learning_rate": 1.9403807615230463e-06, "loss": 1.999, "step": 96160 }, { "epoch": 1.57, "learning_rate": 1.9353707414829657e-06, "loss": 2.0177, "step": 96170 }, { "epoch": 1.57, "learning_rate": 1.930360721442886e-06, "loss": 2.0262, "step": 96180 }, { "epoch": 1.57, "learning_rate": 1.9253507014028057e-06, "loss": 2.0224, "step": 96190 }, { "epoch": 1.57, "learning_rate": 1.9203406813627255e-06, "loss": 2.0138, "step": 96200 }, { "epoch": 1.57, "learning_rate": 1.9153306613226457e-06, "loss": 2.0464, "step": 96210 }, { "epoch": 1.57, "learning_rate": 1.910320641282565e-06, "loss": 1.9822, "step": 96220 }, { "epoch": 1.57, "learning_rate": 1.9053106212424849e-06, "loss": 1.9927, "step": 96230 }, { "epoch": 1.57, "learning_rate": 1.9003006012024049e-06, "loss": 1.9889, "step": 96240 }, { "epoch": 1.57, "learning_rate": 1.8952905811623247e-06, "loss": 2.0126, "step": 96250 }, { "epoch": 1.57, "learning_rate": 1.8902805611222447e-06, "loss": 2.0279, "step": 96260 }, { "epoch": 1.57, "learning_rate": 1.8852705410821647e-06, "loss": 2.0021, "step": 96270 }, { "epoch": 1.57, "learning_rate": 1.880260521042084e-06, "loss": 2.0241, "step": 96280 }, { "epoch": 1.57, "learning_rate": 1.875250501002004e-06, "loss": 1.9688, "step": 96290 }, { "epoch": 1.57, "learning_rate": 1.8702404809619239e-06, "loss": 2.013, "step": 96300 }, { "epoch": 1.57, "learning_rate": 1.8652304609218439e-06, "loss": 1.9966, "step": 96310 }, { "epoch": 1.57, "learning_rate": 1.8602204408817637e-06, "loss": 1.9625, "step": 96320 }, { "epoch": 1.57, "learning_rate": 1.8552104208416832e-06, "loss": 1.9552, "step": 96330 }, { "epoch": 1.57, "learning_rate": 1.8502004008016032e-06, "loss": 1.9814, "step": 96340 }, { "epoch": 1.57, "learning_rate": 1.845190380761523e-06, "loss": 1.9632, "step": 96350 }, { "epoch": 1.57, "learning_rate": 1.840180360721443e-06, "loss": 2.02, "step": 96360 }, { "epoch": 1.57, "learning_rate": 1.8351703406813628e-06, "loss": 2.0038, "step": 96370 }, { "epoch": 1.57, "learning_rate": 1.8301603206412824e-06, "loss": 1.9824, "step": 96380 }, { "epoch": 1.57, "learning_rate": 1.8251503006012024e-06, "loss": 1.9797, "step": 96390 }, { "epoch": 1.58, "learning_rate": 1.8201402805611222e-06, "loss": 1.9765, "step": 96400 }, { "epoch": 1.58, "learning_rate": 1.8151302605210422e-06, "loss": 1.9834, "step": 96410 }, { "epoch": 1.58, "learning_rate": 1.810120240480962e-06, "loss": 2.0261, "step": 96420 }, { "epoch": 1.58, "learning_rate": 1.805110220440882e-06, "loss": 2.0012, "step": 96430 }, { "epoch": 1.58, "learning_rate": 1.8001002004008016e-06, "loss": 2.0384, "step": 96440 }, { "epoch": 1.58, "learning_rate": 1.7950901803607214e-06, "loss": 2.0299, "step": 96450 }, { "epoch": 1.58, "learning_rate": 1.7900801603206414e-06, "loss": 1.9678, "step": 96460 }, { "epoch": 1.58, "learning_rate": 1.7850701402805612e-06, "loss": 1.9754, "step": 96470 }, { "epoch": 1.58, "learning_rate": 1.7800601202404812e-06, "loss": 2.0273, "step": 96480 }, { "epoch": 1.58, "learning_rate": 1.7750501002004008e-06, "loss": 1.9662, "step": 96490 }, { "epoch": 1.58, "learning_rate": 1.7700400801603206e-06, "loss": 2.0354, "step": 96500 }, { "epoch": 1.58, "learning_rate": 1.7650300601202406e-06, "loss": 2.0087, "step": 96510 }, { "epoch": 1.58, "learning_rate": 1.7600200400801604e-06, "loss": 1.9939, "step": 96520 }, { "epoch": 1.58, "learning_rate": 1.7550100200400804e-06, "loss": 2.0254, "step": 96530 }, { "epoch": 1.58, "learning_rate": 1.7500000000000002e-06, "loss": 1.9901, "step": 96540 }, { "epoch": 1.58, "learning_rate": 1.7449899799599198e-06, "loss": 1.9985, "step": 96550 }, { "epoch": 1.58, "learning_rate": 1.7399799599198398e-06, "loss": 1.9695, "step": 96560 }, { "epoch": 1.58, "learning_rate": 1.7349699398797596e-06, "loss": 2.0065, "step": 96570 }, { "epoch": 1.58, "learning_rate": 1.7299599198396796e-06, "loss": 1.9571, "step": 96580 }, { "epoch": 1.58, "learning_rate": 1.7249498997995994e-06, "loss": 2.0175, "step": 96590 }, { "epoch": 1.58, "learning_rate": 1.719939879759519e-06, "loss": 2.0345, "step": 96600 }, { "epoch": 1.58, "learning_rate": 1.714929859719439e-06, "loss": 1.9824, "step": 96610 }, { "epoch": 1.58, "learning_rate": 1.7099198396793588e-06, "loss": 2.0397, "step": 96620 }, { "epoch": 1.58, "learning_rate": 1.7049098196392788e-06, "loss": 1.9805, "step": 96630 }, { "epoch": 1.58, "learning_rate": 1.6998997995991986e-06, "loss": 2.0018, "step": 96640 }, { "epoch": 1.58, "learning_rate": 1.6948897795591181e-06, "loss": 1.9919, "step": 96650 }, { "epoch": 1.58, "learning_rate": 1.6898797595190381e-06, "loss": 1.9929, "step": 96660 }, { "epoch": 1.58, "learning_rate": 1.684869739478958e-06, "loss": 1.9682, "step": 96670 }, { "epoch": 1.58, "learning_rate": 1.679859719438878e-06, "loss": 1.9945, "step": 96680 }, { "epoch": 1.58, "learning_rate": 1.6748496993987977e-06, "loss": 2.001, "step": 96690 }, { "epoch": 1.58, "learning_rate": 1.6698396793587177e-06, "loss": 1.9713, "step": 96700 }, { "epoch": 1.58, "learning_rate": 1.6648296593186373e-06, "loss": 2.0165, "step": 96710 }, { "epoch": 1.58, "learning_rate": 1.6598196392785571e-06, "loss": 2.0081, "step": 96720 }, { "epoch": 1.58, "learning_rate": 1.6548096192384771e-06, "loss": 2.0168, "step": 96730 }, { "epoch": 1.58, "learning_rate": 1.649799599198397e-06, "loss": 1.9835, "step": 96740 }, { "epoch": 1.58, "learning_rate": 1.644789579158317e-06, "loss": 2.0086, "step": 96750 }, { "epoch": 1.58, "learning_rate": 1.6397795591182363e-06, "loss": 1.9741, "step": 96760 }, { "epoch": 1.58, "learning_rate": 1.6347695390781563e-06, "loss": 2.0046, "step": 96770 }, { "epoch": 1.58, "learning_rate": 1.6297595190380763e-06, "loss": 2.004, "step": 96780 }, { "epoch": 1.58, "learning_rate": 1.624749498997996e-06, "loss": 1.9938, "step": 96790 }, { "epoch": 1.58, "learning_rate": 1.6197394789579161e-06, "loss": 2.0107, "step": 96800 }, { "epoch": 1.58, "learning_rate": 1.614729458917836e-06, "loss": 2.0415, "step": 96810 }, { "epoch": 1.58, "learning_rate": 1.6097194388777555e-06, "loss": 2.0447, "step": 96820 }, { "epoch": 1.58, "learning_rate": 1.6047094188376753e-06, "loss": 2.0236, "step": 96830 }, { "epoch": 1.58, "learning_rate": 1.5996993987975953e-06, "loss": 2.023, "step": 96840 }, { "epoch": 1.58, "learning_rate": 1.5946893787575153e-06, "loss": 1.9735, "step": 96850 }, { "epoch": 1.58, "learning_rate": 1.590180360721443e-06, "loss": 2.004, "step": 96860 }, { "epoch": 1.58, "learning_rate": 1.5851703406813627e-06, "loss": 2.0052, "step": 96870 }, { "epoch": 1.58, "learning_rate": 1.5801603206412827e-06, "loss": 2.0061, "step": 96880 }, { "epoch": 1.58, "learning_rate": 1.5751503006012025e-06, "loss": 1.9852, "step": 96890 }, { "epoch": 1.58, "learning_rate": 1.5701402805611225e-06, "loss": 2.0043, "step": 96900 }, { "epoch": 1.58, "learning_rate": 1.5651302605210423e-06, "loss": 2.0211, "step": 96910 }, { "epoch": 1.58, "learning_rate": 1.560120240480962e-06, "loss": 2.029, "step": 96920 }, { "epoch": 1.58, "learning_rate": 1.5551102204408817e-06, "loss": 2.0225, "step": 96930 }, { "epoch": 1.58, "learning_rate": 1.5501002004008017e-06, "loss": 1.9864, "step": 96940 }, { "epoch": 1.58, "learning_rate": 1.5450901803607217e-06, "loss": 1.9852, "step": 96950 }, { "epoch": 1.58, "learning_rate": 1.5400801603206413e-06, "loss": 2.0122, "step": 96960 }, { "epoch": 1.58, "learning_rate": 1.5350701402805613e-06, "loss": 2.0233, "step": 96970 }, { "epoch": 1.58, "learning_rate": 1.530060120240481e-06, "loss": 2.0318, "step": 96980 }, { "epoch": 1.58, "learning_rate": 1.5250501002004009e-06, "loss": 2.023, "step": 96990 }, { "epoch": 1.58, "learning_rate": 1.5200400801603206e-06, "loss": 2.0005, "step": 97000 }, { "epoch": 1.58, "eval_loss": 1.9932299852371216, "eval_mean_f1": 0.6654753430517379, "eval_rouge1_f1": 0.7210326572527466, "eval_rouge1_precision": 0.8319960580135499, "eval_rouge1_recall": 0.669563622636528, "eval_rouge2_f1": 0.5832287899342181, "eval_rouge2_precision": 0.6773626736761507, "eval_rouge2_recall": 0.54165797007084, "eval_rougeL_f1": 0.6921645819682491, "eval_rougeL_precision": 0.7962864676699546, "eval_rougeL_recall": 0.6438868802514791, "eval_runtime": 67.1777, "eval_samples_per_second": 15.243, "eval_steps_per_second": 1.905, "step": 97000 }, { "epoch": 1.59, "learning_rate": 1.5150300601202404e-06, "loss": 2.0576, "step": 97010 }, { "epoch": 1.59, "learning_rate": 1.5100200400801604e-06, "loss": 2.0292, "step": 97020 }, { "epoch": 1.59, "learning_rate": 1.5050100200400802e-06, "loss": 2.0287, "step": 97030 }, { "epoch": 1.59, "learning_rate": 1.5e-06, "loss": 1.9789, "step": 97040 }, { "epoch": 1.59, "learning_rate": 1.4949899799599198e-06, "loss": 1.9954, "step": 97050 }, { "epoch": 1.59, "learning_rate": 1.4899799599198398e-06, "loss": 1.9793, "step": 97060 }, { "epoch": 1.59, "learning_rate": 1.4849699398797596e-06, "loss": 1.9965, "step": 97070 }, { "epoch": 1.59, "learning_rate": 1.4799599198396794e-06, "loss": 1.9886, "step": 97080 }, { "epoch": 1.59, "learning_rate": 1.4749498997995992e-06, "loss": 1.9724, "step": 97090 }, { "epoch": 1.59, "learning_rate": 1.469939879759519e-06, "loss": 2.0197, "step": 97100 }, { "epoch": 1.59, "learning_rate": 1.464929859719439e-06, "loss": 1.9737, "step": 97110 }, { "epoch": 1.59, "learning_rate": 1.4599198396793588e-06, "loss": 1.9707, "step": 97120 }, { "epoch": 1.59, "learning_rate": 1.4549098196392786e-06, "loss": 2.0024, "step": 97130 }, { "epoch": 1.59, "learning_rate": 1.4498997995991986e-06, "loss": 1.9525, "step": 97140 }, { "epoch": 1.59, "learning_rate": 1.4448897795591182e-06, "loss": 1.9783, "step": 97150 }, { "epoch": 1.59, "learning_rate": 1.4398797595190382e-06, "loss": 2.0269, "step": 97160 }, { "epoch": 1.59, "learning_rate": 1.434869739478958e-06, "loss": 1.9878, "step": 97170 }, { "epoch": 1.59, "learning_rate": 1.4298597194388778e-06, "loss": 1.9655, "step": 97180 }, { "epoch": 1.59, "learning_rate": 1.4248496993987978e-06, "loss": 2.0182, "step": 97190 }, { "epoch": 1.59, "learning_rate": 1.4198396793587174e-06, "loss": 1.995, "step": 97200 }, { "epoch": 1.59, "learning_rate": 1.4148296593186374e-06, "loss": 1.9972, "step": 97210 }, { "epoch": 1.59, "learning_rate": 1.4098196392785572e-06, "loss": 1.9903, "step": 97220 }, { "epoch": 1.59, "learning_rate": 1.404809619238477e-06, "loss": 2.0348, "step": 97230 }, { "epoch": 1.59, "learning_rate": 1.399799599198397e-06, "loss": 1.9806, "step": 97240 }, { "epoch": 1.59, "learning_rate": 1.3947895791583168e-06, "loss": 1.9729, "step": 97250 }, { "epoch": 1.59, "learning_rate": 1.3897795591182366e-06, "loss": 1.9826, "step": 97260 }, { "epoch": 1.59, "learning_rate": 1.3847695390781564e-06, "loss": 1.984, "step": 97270 }, { "epoch": 1.59, "learning_rate": 1.3797595190380762e-06, "loss": 2.0031, "step": 97280 }, { "epoch": 1.59, "learning_rate": 1.374749498997996e-06, "loss": 1.9743, "step": 97290 }, { "epoch": 1.59, "learning_rate": 1.369739478957916e-06, "loss": 1.9727, "step": 97300 }, { "epoch": 1.59, "learning_rate": 1.3647294589178358e-06, "loss": 2.0512, "step": 97310 }, { "epoch": 1.59, "learning_rate": 1.3597194388777555e-06, "loss": 1.9575, "step": 97320 }, { "epoch": 1.59, "learning_rate": 1.3547094188376756e-06, "loss": 1.9812, "step": 97330 }, { "epoch": 1.59, "learning_rate": 1.3496993987975951e-06, "loss": 1.9885, "step": 97340 }, { "epoch": 1.59, "learning_rate": 1.3446893787575151e-06, "loss": 1.9533, "step": 97350 }, { "epoch": 1.59, "learning_rate": 1.339679358717435e-06, "loss": 1.9986, "step": 97360 }, { "epoch": 1.59, "learning_rate": 1.3346693386773547e-06, "loss": 2.0179, "step": 97370 }, { "epoch": 1.59, "learning_rate": 1.3296593186372747e-06, "loss": 2.0056, "step": 97380 }, { "epoch": 1.59, "learning_rate": 1.3246492985971943e-06, "loss": 2.0452, "step": 97390 }, { "epoch": 1.59, "learning_rate": 1.3196392785571143e-06, "loss": 2.0033, "step": 97400 }, { "epoch": 1.59, "learning_rate": 1.3146292585170341e-06, "loss": 1.9943, "step": 97410 }, { "epoch": 1.59, "learning_rate": 1.309619238476954e-06, "loss": 1.9876, "step": 97420 }, { "epoch": 1.59, "learning_rate": 1.304609218436874e-06, "loss": 2.0517, "step": 97430 }, { "epoch": 1.59, "learning_rate": 1.2995991983967935e-06, "loss": 2.0197, "step": 97440 }, { "epoch": 1.59, "learning_rate": 1.2945891783567135e-06, "loss": 1.9619, "step": 97450 }, { "epoch": 1.59, "learning_rate": 1.2895791583166333e-06, "loss": 2.0461, "step": 97460 }, { "epoch": 1.59, "learning_rate": 1.284569138276553e-06, "loss": 2.0495, "step": 97470 }, { "epoch": 1.59, "learning_rate": 1.279559118236473e-06, "loss": 2.0392, "step": 97480 }, { "epoch": 1.59, "learning_rate": 1.274549098196393e-06, "loss": 2.0247, "step": 97490 }, { "epoch": 1.59, "learning_rate": 1.2695390781563127e-06, "loss": 2.0064, "step": 97500 }, { "epoch": 1.59, "learning_rate": 1.2645290581162325e-06, "loss": 2.009, "step": 97510 }, { "epoch": 1.59, "learning_rate": 1.2595190380761525e-06, "loss": 1.9786, "step": 97520 }, { "epoch": 1.59, "learning_rate": 1.254509018036072e-06, "loss": 1.9977, "step": 97530 }, { "epoch": 1.59, "learning_rate": 1.249498997995992e-06, "loss": 1.9993, "step": 97540 }, { "epoch": 1.59, "learning_rate": 1.2444889779559119e-06, "loss": 2.0087, "step": 97550 }, { "epoch": 1.59, "learning_rate": 1.2394789579158317e-06, "loss": 2.035, "step": 97560 }, { "epoch": 1.59, "learning_rate": 1.2344689378757517e-06, "loss": 1.9772, "step": 97570 }, { "epoch": 1.59, "learning_rate": 1.2294589178356713e-06, "loss": 1.9569, "step": 97580 }, { "epoch": 1.59, "learning_rate": 1.2244488977955913e-06, "loss": 2.029, "step": 97590 }, { "epoch": 1.59, "learning_rate": 1.219438877755511e-06, "loss": 2.0113, "step": 97600 }, { "epoch": 1.59, "learning_rate": 1.2144288577154309e-06, "loss": 2.044, "step": 97610 }, { "epoch": 1.6, "learning_rate": 1.2094188376753509e-06, "loss": 2.0065, "step": 97620 }, { "epoch": 1.6, "learning_rate": 1.2044088176352704e-06, "loss": 2.0347, "step": 97630 }, { "epoch": 1.6, "learning_rate": 1.1993987975951904e-06, "loss": 2.0273, "step": 97640 }, { "epoch": 1.6, "learning_rate": 1.1943887775551102e-06, "loss": 2.005, "step": 97650 }, { "epoch": 1.6, "learning_rate": 1.18937875751503e-06, "loss": 1.9886, "step": 97660 }, { "epoch": 1.6, "learning_rate": 1.18436873747495e-06, "loss": 2.0056, "step": 97670 }, { "epoch": 1.6, "learning_rate": 1.1793587174348698e-06, "loss": 2.0379, "step": 97680 }, { "epoch": 1.6, "learning_rate": 1.1743486973947896e-06, "loss": 1.9926, "step": 97690 }, { "epoch": 1.6, "learning_rate": 1.1693386773547094e-06, "loss": 2.0129, "step": 97700 }, { "epoch": 1.6, "learning_rate": 1.1643286573146292e-06, "loss": 2.0357, "step": 97710 }, { "epoch": 1.6, "learning_rate": 1.1593186372745492e-06, "loss": 1.9944, "step": 97720 }, { "epoch": 1.6, "learning_rate": 1.154308617234469e-06, "loss": 1.9689, "step": 97730 }, { "epoch": 1.6, "learning_rate": 1.1492985971943888e-06, "loss": 2.0072, "step": 97740 }, { "epoch": 1.6, "learning_rate": 1.1442885771543086e-06, "loss": 1.9795, "step": 97750 }, { "epoch": 1.6, "learning_rate": 1.1392785571142286e-06, "loss": 2.0202, "step": 97760 }, { "epoch": 1.6, "learning_rate": 1.1342685370741484e-06, "loss": 2.0012, "step": 97770 }, { "epoch": 1.6, "learning_rate": 1.1292585170340682e-06, "loss": 1.9934, "step": 97780 }, { "epoch": 1.6, "learning_rate": 1.124248496993988e-06, "loss": 1.9609, "step": 97790 }, { "epoch": 1.6, "learning_rate": 1.1192384769539078e-06, "loss": 2.0356, "step": 97800 }, { "epoch": 1.6, "learning_rate": 1.1142284569138278e-06, "loss": 2.0333, "step": 97810 }, { "epoch": 1.6, "learning_rate": 1.1092184368737474e-06, "loss": 2.018, "step": 97820 }, { "epoch": 1.6, "learning_rate": 1.1042084168336674e-06, "loss": 2.0224, "step": 97830 }, { "epoch": 1.6, "learning_rate": 1.0991983967935874e-06, "loss": 1.9729, "step": 97840 }, { "epoch": 1.6, "learning_rate": 1.094188376753507e-06, "loss": 1.9803, "step": 97850 }, { "epoch": 1.6, "learning_rate": 1.089178356713427e-06, "loss": 1.9733, "step": 97860 }, { "epoch": 1.6, "learning_rate": 1.0841683366733468e-06, "loss": 2.0664, "step": 97870 }, { "epoch": 1.6, "learning_rate": 1.0791583166332666e-06, "loss": 2.0223, "step": 97880 }, { "epoch": 1.6, "learning_rate": 1.0741482965931864e-06, "loss": 2.0114, "step": 97890 }, { "epoch": 1.6, "learning_rate": 1.0691382765531062e-06, "loss": 2.0233, "step": 97900 }, { "epoch": 1.6, "learning_rate": 1.0641282565130262e-06, "loss": 2.0044, "step": 97910 }, { "epoch": 1.6, "learning_rate": 1.059118236472946e-06, "loss": 1.9719, "step": 97920 }, { "epoch": 1.6, "learning_rate": 1.0541082164328658e-06, "loss": 1.9735, "step": 97930 }, { "epoch": 1.6, "learning_rate": 1.0490981963927855e-06, "loss": 2.0407, "step": 97940 }, { "epoch": 1.6, "learning_rate": 1.0440881763527056e-06, "loss": 2.0053, "step": 97950 }, { "epoch": 1.6, "learning_rate": 1.0390781563126253e-06, "loss": 1.9955, "step": 97960 }, { "epoch": 1.6, "learning_rate": 1.0340681362725451e-06, "loss": 1.9849, "step": 97970 }, { "epoch": 1.6, "learning_rate": 1.029058116232465e-06, "loss": 1.9569, "step": 97980 }, { "epoch": 1.6, "learning_rate": 1.0240480961923847e-06, "loss": 1.9929, "step": 97990 }, { "epoch": 1.6, "learning_rate": 1.0190380761523047e-06, "loss": 1.9855, "step": 98000 }, { "epoch": 1.6, "eval_loss": 1.9949144124984741, "eval_mean_f1": 0.6626251238389674, "eval_rouge1_f1": 0.7190849274488224, "eval_rouge1_precision": 0.8299391043032611, "eval_rouge1_recall": 0.6677549561176952, "eval_rouge2_f1": 0.5807450148351756, "eval_rouge2_precision": 0.6751261372904442, "eval_rouge2_recall": 0.5392048589503582, "eval_rougeL_f1": 0.6880454292329043, "eval_rougeL_precision": 0.7929236595525087, "eval_rougeL_recall": 0.6399228618079786, "eval_runtime": 68.1984, "eval_samples_per_second": 15.015, "eval_steps_per_second": 1.877, "step": 98000 }, { "epoch": 1.6, "learning_rate": 1.0140280561122245e-06, "loss": 1.963, "step": 98010 }, { "epoch": 1.6, "learning_rate": 1.0090180360721443e-06, "loss": 1.9727, "step": 98020 }, { "epoch": 1.6, "learning_rate": 1.0040080160320643e-06, "loss": 2.0141, "step": 98030 }, { "epoch": 1.6, "learning_rate": 9.98997995991984e-07, "loss": 1.9846, "step": 98040 }, { "epoch": 1.6, "learning_rate": 9.93987975951904e-07, "loss": 1.9708, "step": 98050 }, { "epoch": 1.6, "learning_rate": 9.889779559118237e-07, "loss": 1.9818, "step": 98060 }, { "epoch": 1.6, "learning_rate": 9.839679358717435e-07, "loss": 2.0254, "step": 98070 }, { "epoch": 1.6, "learning_rate": 9.789579158316635e-07, "loss": 2.0015, "step": 98080 }, { "epoch": 1.6, "learning_rate": 9.73947895791583e-07, "loss": 2.0323, "step": 98090 }, { "epoch": 1.6, "learning_rate": 9.68937875751503e-07, "loss": 2.0327, "step": 98100 }, { "epoch": 1.6, "learning_rate": 9.63927855711423e-07, "loss": 1.9807, "step": 98110 }, { "epoch": 1.6, "learning_rate": 9.589178356713427e-07, "loss": 2.0193, "step": 98120 }, { "epoch": 1.6, "learning_rate": 9.539078156312627e-07, "loss": 1.9903, "step": 98130 }, { "epoch": 1.6, "learning_rate": 9.488977955911823e-07, "loss": 1.9947, "step": 98140 }, { "epoch": 1.6, "learning_rate": 9.438877755511022e-07, "loss": 2.0266, "step": 98150 }, { "epoch": 1.6, "learning_rate": 9.388777555110221e-07, "loss": 2.0284, "step": 98160 }, { "epoch": 1.6, "learning_rate": 9.338677354709419e-07, "loss": 1.9738, "step": 98170 }, { "epoch": 1.6, "learning_rate": 9.288577154308618e-07, "loss": 2.0173, "step": 98180 }, { "epoch": 1.6, "learning_rate": 9.238476953907817e-07, "loss": 1.9909, "step": 98190 }, { "epoch": 1.6, "learning_rate": 9.188376753507014e-07, "loss": 1.969, "step": 98200 }, { "epoch": 1.6, "learning_rate": 9.138276553106213e-07, "loss": 1.9742, "step": 98210 }, { "epoch": 1.6, "learning_rate": 9.088176352705412e-07, "loss": 1.983, "step": 98220 }, { "epoch": 1.61, "learning_rate": 9.03807615230461e-07, "loss": 1.9864, "step": 98230 }, { "epoch": 1.61, "learning_rate": 8.987975951903809e-07, "loss": 2.0123, "step": 98240 }, { "epoch": 1.61, "learning_rate": 8.937875751503005e-07, "loss": 2.0253, "step": 98250 }, { "epoch": 1.61, "learning_rate": 8.887775551102204e-07, "loss": 2.0442, "step": 98260 }, { "epoch": 1.61, "learning_rate": 8.837675350701403e-07, "loss": 2.014, "step": 98270 }, { "epoch": 1.61, "learning_rate": 8.787575150300601e-07, "loss": 2.0485, "step": 98280 }, { "epoch": 1.61, "learning_rate": 8.7374749498998e-07, "loss": 1.992, "step": 98290 }, { "epoch": 1.61, "learning_rate": 8.687374749498999e-07, "loss": 2.0053, "step": 98300 }, { "epoch": 1.61, "learning_rate": 8.637274549098196e-07, "loss": 2.0002, "step": 98310 }, { "epoch": 1.61, "learning_rate": 8.587174348697395e-07, "loss": 1.9619, "step": 98320 }, { "epoch": 1.61, "learning_rate": 8.537074148296593e-07, "loss": 1.9949, "step": 98330 }, { "epoch": 1.61, "learning_rate": 8.486973947895792e-07, "loss": 2.0145, "step": 98340 }, { "epoch": 1.61, "learning_rate": 8.436873747494991e-07, "loss": 2.0128, "step": 98350 }, { "epoch": 1.61, "learning_rate": 8.386773547094188e-07, "loss": 1.9786, "step": 98360 }, { "epoch": 1.61, "learning_rate": 8.336673346693387e-07, "loss": 2.0039, "step": 98370 }, { "epoch": 1.61, "learning_rate": 8.286573146292586e-07, "loss": 1.9835, "step": 98380 }, { "epoch": 1.61, "learning_rate": 8.236472945891784e-07, "loss": 2.008, "step": 98390 }, { "epoch": 1.61, "learning_rate": 8.186372745490983e-07, "loss": 2.0034, "step": 98400 }, { "epoch": 1.61, "learning_rate": 8.13627254509018e-07, "loss": 1.9578, "step": 98410 }, { "epoch": 1.61, "learning_rate": 8.086172344689379e-07, "loss": 1.9928, "step": 98420 }, { "epoch": 1.61, "learning_rate": 8.036072144288578e-07, "loss": 1.9756, "step": 98430 }, { "epoch": 1.61, "learning_rate": 7.985971943887775e-07, "loss": 1.9992, "step": 98440 }, { "epoch": 1.61, "learning_rate": 7.935871743486974e-07, "loss": 2.0169, "step": 98450 }, { "epoch": 1.61, "learning_rate": 7.885771543086174e-07, "loss": 2.0016, "step": 98460 }, { "epoch": 1.61, "learning_rate": 7.835671342685371e-07, "loss": 2.0018, "step": 98470 }, { "epoch": 1.61, "learning_rate": 7.78557114228457e-07, "loss": 2.0152, "step": 98480 }, { "epoch": 1.61, "learning_rate": 7.735470941883768e-07, "loss": 1.9849, "step": 98490 }, { "epoch": 1.61, "learning_rate": 7.685370741482966e-07, "loss": 2.0027, "step": 98500 }, { "epoch": 1.61, "learning_rate": 7.635270541082165e-07, "loss": 2.0275, "step": 98510 }, { "epoch": 1.61, "learning_rate": 7.585170340681364e-07, "loss": 1.9659, "step": 98520 }, { "epoch": 1.61, "learning_rate": 7.535070140280562e-07, "loss": 1.9828, "step": 98530 }, { "epoch": 1.61, "learning_rate": 7.48496993987976e-07, "loss": 2.037, "step": 98540 }, { "epoch": 1.61, "learning_rate": 7.434869739478959e-07, "loss": 1.997, "step": 98550 }, { "epoch": 1.61, "learning_rate": 7.384769539078157e-07, "loss": 1.9742, "step": 98560 }, { "epoch": 1.61, "learning_rate": 7.334669338677356e-07, "loss": 2.0328, "step": 98570 }, { "epoch": 1.61, "learning_rate": 7.284569138276553e-07, "loss": 1.9746, "step": 98580 }, { "epoch": 1.61, "learning_rate": 7.234468937875752e-07, "loss": 1.961, "step": 98590 }, { "epoch": 1.61, "learning_rate": 7.18436873747495e-07, "loss": 2.0292, "step": 98600 }, { "epoch": 1.61, "learning_rate": 7.134268537074148e-07, "loss": 2.0439, "step": 98610 }, { "epoch": 1.61, "learning_rate": 7.084168336673346e-07, "loss": 1.983, "step": 98620 }, { "epoch": 1.61, "learning_rate": 7.034068136272545e-07, "loss": 2.0024, "step": 98630 }, { "epoch": 1.61, "learning_rate": 6.983967935871744e-07, "loss": 1.9736, "step": 98640 }, { "epoch": 1.61, "learning_rate": 6.933867735470942e-07, "loss": 2.0099, "step": 98650 }, { "epoch": 1.61, "learning_rate": 6.88376753507014e-07, "loss": 2.0086, "step": 98660 }, { "epoch": 1.61, "learning_rate": 6.833667334669339e-07, "loss": 2.0191, "step": 98670 }, { "epoch": 1.61, "learning_rate": 6.783567134268537e-07, "loss": 1.9753, "step": 98680 }, { "epoch": 1.61, "learning_rate": 6.733466933867736e-07, "loss": 1.9606, "step": 98690 }, { "epoch": 1.61, "learning_rate": 6.683366733466934e-07, "loss": 1.9995, "step": 98700 }, { "epoch": 1.61, "learning_rate": 6.633266533066133e-07, "loss": 1.992, "step": 98710 }, { "epoch": 1.61, "learning_rate": 6.583166332665331e-07, "loss": 2.0159, "step": 98720 }, { "epoch": 1.61, "learning_rate": 6.533066132264529e-07, "loss": 1.9248, "step": 98730 }, { "epoch": 1.61, "learning_rate": 6.482965931863727e-07, "loss": 2.0634, "step": 98740 }, { "epoch": 1.61, "learning_rate": 6.432865731462926e-07, "loss": 2.0262, "step": 98750 }, { "epoch": 1.61, "learning_rate": 6.382765531062125e-07, "loss": 1.9635, "step": 98760 }, { "epoch": 1.61, "learning_rate": 6.332665330661323e-07, "loss": 2.0255, "step": 98770 }, { "epoch": 1.61, "learning_rate": 6.282565130260521e-07, "loss": 2.0208, "step": 98780 }, { "epoch": 1.61, "learning_rate": 6.23246492985972e-07, "loss": 1.9927, "step": 98790 }, { "epoch": 1.61, "learning_rate": 6.182364729458918e-07, "loss": 2.0367, "step": 98800 }, { "epoch": 1.61, "learning_rate": 6.132264529058117e-07, "loss": 1.9928, "step": 98810 }, { "epoch": 1.61, "learning_rate": 6.082164328657316e-07, "loss": 1.9938, "step": 98820 }, { "epoch": 1.61, "learning_rate": 6.032064128256514e-07, "loss": 1.9669, "step": 98830 }, { "epoch": 1.62, "learning_rate": 5.981963927855712e-07, "loss": 2.0049, "step": 98840 }, { "epoch": 1.62, "learning_rate": 5.93186372745491e-07, "loss": 1.9824, "step": 98850 }, { "epoch": 1.62, "learning_rate": 5.881763527054109e-07, "loss": 2.059, "step": 98860 }, { "epoch": 1.62, "learning_rate": 5.831663326653308e-07, "loss": 2.0222, "step": 98870 }, { "epoch": 1.62, "learning_rate": 5.781563126252506e-07, "loss": 2.0141, "step": 98880 }, { "epoch": 1.62, "learning_rate": 5.731462925851703e-07, "loss": 2.0031, "step": 98890 }, { "epoch": 1.62, "learning_rate": 5.681362725450902e-07, "loss": 2.0099, "step": 98900 }, { "epoch": 1.62, "learning_rate": 5.6312625250501e-07, "loss": 1.9949, "step": 98910 }, { "epoch": 1.62, "learning_rate": 5.581162324649298e-07, "loss": 1.9709, "step": 98920 }, { "epoch": 1.62, "learning_rate": 5.531062124248497e-07, "loss": 1.9999, "step": 98930 }, { "epoch": 1.62, "learning_rate": 5.480961923847696e-07, "loss": 1.9894, "step": 98940 }, { "epoch": 1.62, "learning_rate": 5.430861723446894e-07, "loss": 1.9928, "step": 98950 }, { "epoch": 1.62, "learning_rate": 5.380761523046092e-07, "loss": 1.9764, "step": 98960 }, { "epoch": 1.62, "learning_rate": 5.33066132264529e-07, "loss": 2.0088, "step": 98970 }, { "epoch": 1.62, "learning_rate": 5.280561122244489e-07, "loss": 2.0422, "step": 98980 }, { "epoch": 1.62, "learning_rate": 5.230460921843688e-07, "loss": 1.9521, "step": 98990 }, { "epoch": 1.62, "learning_rate": 5.180360721442886e-07, "loss": 2.0376, "step": 99000 }, { "epoch": 1.62, "eval_loss": 1.9938691854476929, "eval_mean_f1": 0.6635736309099306, "eval_rouge1_f1": 0.7189597725238965, "eval_rouge1_precision": 0.8287971868753692, "eval_rouge1_recall": 0.66783343648339, "eval_rouge2_f1": 0.5831538633509141, "eval_rouge2_precision": 0.6772712029181756, "eval_rouge2_recall": 0.5413375036055245, "eval_rougeL_f1": 0.688607256854981, "eval_rougeL_precision": 0.7918696507549329, "eval_rougeL_recall": 0.6406328068654875, "eval_runtime": 67.7667, "eval_samples_per_second": 15.111, "eval_steps_per_second": 1.889, "step": 99000 }, { "epoch": 1.62, "learning_rate": 5.130260521042084e-07, "loss": 2.0292, "step": 99010 }, { "epoch": 1.62, "learning_rate": 5.080160320641283e-07, "loss": 1.981, "step": 99020 }, { "epoch": 1.62, "learning_rate": 5.030060120240481e-07, "loss": 1.9961, "step": 99030 }, { "epoch": 1.62, "learning_rate": 4.979959919839679e-07, "loss": 2.0346, "step": 99040 }, { "epoch": 1.62, "learning_rate": 4.929859719438878e-07, "loss": 2.0104, "step": 99050 }, { "epoch": 1.62, "learning_rate": 4.879759519038077e-07, "loss": 2.043, "step": 99060 }, { "epoch": 1.62, "learning_rate": 4.829659318637275e-07, "loss": 1.9665, "step": 99070 }, { "epoch": 1.62, "learning_rate": 4.779559118236473e-07, "loss": 2.0013, "step": 99080 }, { "epoch": 1.62, "learning_rate": 4.7294589178356713e-07, "loss": 2.0292, "step": 99090 }, { "epoch": 1.62, "learning_rate": 4.6793587174348703e-07, "loss": 2.0275, "step": 99100 }, { "epoch": 1.62, "learning_rate": 4.629258517034068e-07, "loss": 2.0241, "step": 99110 }, { "epoch": 1.62, "learning_rate": 4.5791583166332667e-07, "loss": 2.0103, "step": 99120 }, { "epoch": 1.62, "learning_rate": 4.5290581162324657e-07, "loss": 1.985, "step": 99130 }, { "epoch": 1.62, "learning_rate": 4.4789579158316637e-07, "loss": 1.954, "step": 99140 }, { "epoch": 1.62, "learning_rate": 4.428857715430862e-07, "loss": 1.9866, "step": 99150 }, { "epoch": 1.62, "learning_rate": 4.37875751503006e-07, "loss": 2.0196, "step": 99160 }, { "epoch": 1.62, "learning_rate": 4.328657314629259e-07, "loss": 2.0118, "step": 99170 }, { "epoch": 1.62, "learning_rate": 4.2785571142284576e-07, "loss": 1.9775, "step": 99180 }, { "epoch": 1.62, "learning_rate": 4.2284569138276555e-07, "loss": 2.0211, "step": 99190 }, { "epoch": 1.62, "learning_rate": 4.1783567134268534e-07, "loss": 1.9964, "step": 99200 }, { "epoch": 1.62, "learning_rate": 4.1282565130260524e-07, "loss": 1.9858, "step": 99210 }, { "epoch": 1.62, "learning_rate": 4.078156312625251e-07, "loss": 2.0035, "step": 99220 }, { "epoch": 1.62, "learning_rate": 4.028056112224449e-07, "loss": 2.0137, "step": 99230 }, { "epoch": 1.62, "learning_rate": 3.9779559118236473e-07, "loss": 1.9748, "step": 99240 }, { "epoch": 1.62, "learning_rate": 3.9278557114228463e-07, "loss": 2.003, "step": 99250 }, { "epoch": 1.62, "learning_rate": 3.8777555110220443e-07, "loss": 2.0058, "step": 99260 }, { "epoch": 1.62, "learning_rate": 3.827655310621243e-07, "loss": 2.0153, "step": 99270 }, { "epoch": 1.62, "learning_rate": 3.777555110220441e-07, "loss": 1.9976, "step": 99280 }, { "epoch": 1.62, "learning_rate": 3.727454909819639e-07, "loss": 1.9947, "step": 99290 }, { "epoch": 1.62, "learning_rate": 3.677354709418838e-07, "loss": 2.0311, "step": 99300 }, { "epoch": 1.62, "learning_rate": 3.627254509018036e-07, "loss": 2.0265, "step": 99310 }, { "epoch": 1.62, "learning_rate": 3.5771543086172346e-07, "loss": 1.9841, "step": 99320 }, { "epoch": 1.62, "learning_rate": 3.527054108216433e-07, "loss": 1.9888, "step": 99330 }, { "epoch": 1.62, "learning_rate": 3.4769539078156315e-07, "loss": 1.9593, "step": 99340 }, { "epoch": 1.62, "learning_rate": 3.4268537074148295e-07, "loss": 1.9659, "step": 99350 }, { "epoch": 1.62, "learning_rate": 3.3767535070140285e-07, "loss": 1.9824, "step": 99360 }, { "epoch": 1.62, "learning_rate": 3.3266533066132264e-07, "loss": 2.0003, "step": 99370 }, { "epoch": 1.62, "learning_rate": 3.276553106212425e-07, "loss": 2.0005, "step": 99380 }, { "epoch": 1.62, "learning_rate": 3.2264529058116234e-07, "loss": 1.9694, "step": 99390 }, { "epoch": 1.62, "learning_rate": 3.176352705410822e-07, "loss": 1.9661, "step": 99400 }, { "epoch": 1.62, "learning_rate": 3.12625250501002e-07, "loss": 2.0016, "step": 99410 }, { "epoch": 1.62, "learning_rate": 3.076152304609219e-07, "loss": 2.0108, "step": 99420 }, { "epoch": 1.62, "learning_rate": 3.0260521042084167e-07, "loss": 1.9903, "step": 99430 }, { "epoch": 1.62, "learning_rate": 2.975951903807615e-07, "loss": 2.0031, "step": 99440 }, { "epoch": 1.62, "learning_rate": 2.9258517034068137e-07, "loss": 1.9914, "step": 99450 }, { "epoch": 1.63, "learning_rate": 2.875751503006012e-07, "loss": 2.0457, "step": 99460 }, { "epoch": 1.63, "learning_rate": 2.8256513026052106e-07, "loss": 2.0091, "step": 99470 }, { "epoch": 1.63, "learning_rate": 2.775551102204409e-07, "loss": 2.0117, "step": 99480 }, { "epoch": 1.63, "learning_rate": 2.7254509018036076e-07, "loss": 1.9779, "step": 99490 }, { "epoch": 1.63, "learning_rate": 2.6753507014028055e-07, "loss": 1.991, "step": 99500 }, { "epoch": 1.63, "learning_rate": 2.6252505010020045e-07, "loss": 2.0018, "step": 99510 }, { "epoch": 1.63, "learning_rate": 2.5751503006012024e-07, "loss": 2.0118, "step": 99520 }, { "epoch": 1.63, "learning_rate": 2.525050100200401e-07, "loss": 2.0445, "step": 99530 }, { "epoch": 1.63, "learning_rate": 2.4749498997995994e-07, "loss": 2.0184, "step": 99540 }, { "epoch": 1.63, "learning_rate": 2.424849699398798e-07, "loss": 1.9904, "step": 99550 }, { "epoch": 1.63, "learning_rate": 2.374749498997996e-07, "loss": 1.9635, "step": 99560 }, { "epoch": 1.63, "learning_rate": 2.3246492985971945e-07, "loss": 1.9856, "step": 99570 }, { "epoch": 1.63, "learning_rate": 2.2745490981963927e-07, "loss": 1.9958, "step": 99580 }, { "epoch": 1.63, "learning_rate": 2.2244488977955915e-07, "loss": 1.979, "step": 99590 }, { "epoch": 1.63, "learning_rate": 2.1743486973947897e-07, "loss": 2.048, "step": 99600 }, { "epoch": 1.63, "learning_rate": 2.1242484969939882e-07, "loss": 2.0154, "step": 99610 }, { "epoch": 1.63, "learning_rate": 2.0741482965931864e-07, "loss": 1.9447, "step": 99620 }, { "epoch": 1.63, "learning_rate": 2.0240480961923848e-07, "loss": 2.0394, "step": 99630 }, { "epoch": 1.63, "learning_rate": 1.973947895791583e-07, "loss": 1.9923, "step": 99640 }, { "epoch": 1.63, "learning_rate": 1.9238476953907818e-07, "loss": 2.0409, "step": 99650 }, { "epoch": 1.63, "learning_rate": 1.87374749498998e-07, "loss": 1.9931, "step": 99660 }, { "epoch": 1.63, "learning_rate": 1.8236472945891785e-07, "loss": 1.9701, "step": 99670 }, { "epoch": 1.63, "learning_rate": 1.773547094188377e-07, "loss": 1.9483, "step": 99680 }, { "epoch": 1.63, "learning_rate": 1.7234468937875754e-07, "loss": 1.9693, "step": 99690 }, { "epoch": 1.63, "learning_rate": 1.6733466933867736e-07, "loss": 1.996, "step": 99700 }, { "epoch": 1.63, "learning_rate": 1.623246492985972e-07, "loss": 2.0013, "step": 99710 }, { "epoch": 1.63, "learning_rate": 1.5731462925851706e-07, "loss": 1.982, "step": 99720 }, { "epoch": 1.63, "learning_rate": 1.5230460921843688e-07, "loss": 1.9723, "step": 99730 }, { "epoch": 1.63, "learning_rate": 1.4729458917835672e-07, "loss": 2.0082, "step": 99740 }, { "epoch": 1.63, "learning_rate": 1.4228456913827657e-07, "loss": 1.9828, "step": 99750 }, { "epoch": 1.63, "learning_rate": 1.372745490981964e-07, "loss": 1.9823, "step": 99760 }, { "epoch": 1.63, "learning_rate": 1.3226452905811624e-07, "loss": 2.0065, "step": 99770 }, { "epoch": 1.63, "learning_rate": 1.272545090180361e-07, "loss": 1.9948, "step": 99780 }, { "epoch": 1.63, "learning_rate": 1.222444889779559e-07, "loss": 2.0128, "step": 99790 }, { "epoch": 1.63, "learning_rate": 1.1723446893787575e-07, "loss": 2.0086, "step": 99800 }, { "epoch": 1.63, "learning_rate": 1.1222444889779559e-07, "loss": 1.9794, "step": 99810 }, { "epoch": 1.63, "learning_rate": 1.0721442885771544e-07, "loss": 1.9945, "step": 99820 }, { "epoch": 1.63, "learning_rate": 1.0220440881763527e-07, "loss": 1.9813, "step": 99830 }, { "epoch": 1.63, "learning_rate": 9.71943887775551e-08, "loss": 2.0264, "step": 99840 }, { "epoch": 1.63, "learning_rate": 9.218436873747495e-08, "loss": 1.9712, "step": 99850 }, { "epoch": 1.63, "learning_rate": 8.71743486973948e-08, "loss": 1.9949, "step": 99860 }, { "epoch": 1.63, "learning_rate": 8.216432865731463e-08, "loss": 1.9847, "step": 99870 }, { "epoch": 1.63, "learning_rate": 7.715430861723448e-08, "loss": 2.0006, "step": 99880 }, { "epoch": 1.63, "learning_rate": 7.214428857715431e-08, "loss": 2.0155, "step": 99890 }, { "epoch": 1.63, "learning_rate": 6.713426853707415e-08, "loss": 1.9755, "step": 99900 }, { "epoch": 1.63, "learning_rate": 6.2124248496994e-08, "loss": 2.0257, "step": 99910 }, { "epoch": 1.63, "learning_rate": 5.711422845691383e-08, "loss": 1.9129, "step": 99920 }, { "epoch": 1.63, "learning_rate": 5.210420841683367e-08, "loss": 1.9931, "step": 99930 }, { "epoch": 1.63, "learning_rate": 4.709418837675351e-08, "loss": 1.9965, "step": 99940 }, { "epoch": 1.63, "learning_rate": 4.208416833667335e-08, "loss": 1.9778, "step": 99950 }, { "epoch": 1.63, "learning_rate": 3.7074148296593185e-08, "loss": 2.0083, "step": 99960 }, { "epoch": 1.63, "learning_rate": 3.2064128256513025e-08, "loss": 1.9866, "step": 99970 }, { "epoch": 1.63, "learning_rate": 2.705410821643287e-08, "loss": 1.991, "step": 99980 }, { "epoch": 1.63, "learning_rate": 2.2044088176352707e-08, "loss": 2.0239, "step": 99990 }, { "epoch": 1.63, "learning_rate": 1.7034068136272547e-08, "loss": 2.0199, "step": 100000 }, { "epoch": 1.63, "eval_loss": 1.9908442497253418, "eval_mean_f1": 0.6624991301340465, "eval_rouge1_f1": 0.7193555126699296, "eval_rouge1_precision": 0.8293535459989108, "eval_rouge1_recall": 0.6684357744148894, "eval_rouge2_f1": 0.5799189602045164, "eval_rouge2_precision": 0.6730413507391055, "eval_rouge2_recall": 0.5388152328652429, "eval_rougeL_f1": 0.6882229175276937, "eval_rougeL_precision": 0.7918367834390643, "eval_rougeL_recall": 0.6407495561321894, "eval_runtime": 67.9188, "eval_samples_per_second": 15.077, "eval_steps_per_second": 1.885, "step": 100000 } ], "max_steps": 100000, "num_train_epochs": 2, "total_flos": 1.9099925872324116e+18, "trial_name": null, "trial_params": null }