{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.6061057334326136, "eval_steps": 500, "global_step": 3500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.98758997269794e-05, "loss": 1.8077, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.97517994539588e-05, "loss": 1.7919, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.96276991809382e-05, "loss": 1.7931, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.95035989079176e-05, "loss": 1.7427, "step": 40 }, { "epoch": 0.04, "learning_rate": 4.9379498634897e-05, "loss": 1.7361, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.92553983618764e-05, "loss": 1.7501, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.91312980888558e-05, "loss": 1.6787, "step": 70 }, { "epoch": 0.06, "learning_rate": 4.90071978158352e-05, "loss": 1.7201, "step": 80 }, { "epoch": 0.07, "learning_rate": 4.88830975428146e-05, "loss": 1.6944, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.875899726979399e-05, "loss": 1.6702, "step": 100 }, { "epoch": 0.08, "learning_rate": 4.86348969967734e-05, "loss": 1.6788, "step": 110 }, { "epoch": 0.09, "learning_rate": 4.8510796723752796e-05, "loss": 1.7192, "step": 120 }, { "epoch": 0.1, "learning_rate": 4.8386696450732196e-05, "loss": 1.6632, "step": 130 }, { "epoch": 0.1, "learning_rate": 4.8262596177711595e-05, "loss": 1.6643, "step": 140 }, { "epoch": 0.11, "learning_rate": 4.8138495904690995e-05, "loss": 1.6802, "step": 150 }, { "epoch": 0.12, "learning_rate": 4.8014395631670394e-05, "loss": 1.7225, "step": 160 }, { "epoch": 0.13, "learning_rate": 4.789029535864979e-05, "loss": 1.6649, "step": 170 }, { "epoch": 0.13, "learning_rate": 4.7766195085629186e-05, "loss": 1.6951, "step": 180 }, { "epoch": 0.14, "learning_rate": 4.764209481260859e-05, "loss": 1.6736, "step": 190 }, { "epoch": 0.15, "learning_rate": 4.751799453958799e-05, "loss": 1.6874, "step": 200 }, { "epoch": 0.16, "learning_rate": 4.739389426656739e-05, "loss": 1.6894, "step": 210 }, { "epoch": 0.16, "learning_rate": 4.726979399354679e-05, "loss": 1.682, "step": 220 }, { "epoch": 0.17, "learning_rate": 4.7145693720526184e-05, "loss": 1.6885, "step": 230 }, { "epoch": 0.18, "learning_rate": 4.702159344750558e-05, "loss": 1.7011, "step": 240 }, { "epoch": 0.19, "learning_rate": 4.689749317448498e-05, "loss": 1.6548, "step": 250 }, { "epoch": 0.19, "learning_rate": 4.677339290146439e-05, "loss": 1.7147, "step": 260 }, { "epoch": 0.2, "learning_rate": 4.664929262844379e-05, "loss": 1.6414, "step": 270 }, { "epoch": 0.21, "learning_rate": 4.652519235542319e-05, "loss": 1.6986, "step": 280 }, { "epoch": 0.22, "learning_rate": 4.640109208240258e-05, "loss": 1.676, "step": 290 }, { "epoch": 0.22, "learning_rate": 4.627699180938198e-05, "loss": 1.7008, "step": 300 }, { "epoch": 0.23, "learning_rate": 4.615289153636138e-05, "loss": 1.697, "step": 310 }, { "epoch": 0.24, "learning_rate": 4.602879126334078e-05, "loss": 1.6687, "step": 320 }, { "epoch": 0.25, "learning_rate": 4.590469099032018e-05, "loss": 1.6386, "step": 330 }, { "epoch": 0.25, "learning_rate": 4.5780590717299585e-05, "loss": 1.7363, "step": 340 }, { "epoch": 0.26, "learning_rate": 4.5656490444278984e-05, "loss": 1.6989, "step": 350 }, { "epoch": 0.27, "learning_rate": 4.553239017125838e-05, "loss": 1.6976, "step": 360 }, { "epoch": 0.28, "learning_rate": 4.5408289898237776e-05, "loss": 1.6699, "step": 370 }, { "epoch": 0.28, "learning_rate": 4.5284189625217176e-05, "loss": 1.6899, "step": 380 }, { "epoch": 0.29, "learning_rate": 4.5160089352196575e-05, "loss": 1.6911, "step": 390 }, { "epoch": 0.3, "learning_rate": 4.5035989079175975e-05, "loss": 1.6817, "step": 400 }, { "epoch": 0.31, "learning_rate": 4.491188880615538e-05, "loss": 1.6754, "step": 410 }, { "epoch": 0.31, "learning_rate": 4.4787788533134774e-05, "loss": 1.6631, "step": 420 }, { "epoch": 0.32, "learning_rate": 4.466368826011417e-05, "loss": 1.67, "step": 430 }, { "epoch": 0.33, "learning_rate": 4.453958798709357e-05, "loss": 1.6579, "step": 440 }, { "epoch": 0.34, "learning_rate": 4.441548771407297e-05, "loss": 1.7106, "step": 450 }, { "epoch": 0.34, "learning_rate": 4.429138744105237e-05, "loss": 1.6756, "step": 460 }, { "epoch": 0.35, "learning_rate": 4.416728716803177e-05, "loss": 1.6315, "step": 470 }, { "epoch": 0.36, "learning_rate": 4.404318689501117e-05, "loss": 1.6599, "step": 480 }, { "epoch": 0.36, "learning_rate": 4.391908662199057e-05, "loss": 1.6958, "step": 490 }, { "epoch": 0.37, "learning_rate": 4.379498634896997e-05, "loss": 1.6641, "step": 500 }, { "epoch": 0.38, "learning_rate": 4.367088607594937e-05, "loss": 1.6882, "step": 510 }, { "epoch": 0.39, "learning_rate": 4.354678580292877e-05, "loss": 1.674, "step": 520 }, { "epoch": 0.39, "learning_rate": 4.342268552990817e-05, "loss": 1.6857, "step": 530 }, { "epoch": 0.4, "learning_rate": 4.329858525688757e-05, "loss": 1.6924, "step": 540 }, { "epoch": 0.41, "learning_rate": 4.317448498386697e-05, "loss": 1.6747, "step": 550 }, { "epoch": 0.42, "learning_rate": 4.3050384710846366e-05, "loss": 1.6745, "step": 560 }, { "epoch": 0.42, "learning_rate": 4.2926284437825766e-05, "loss": 1.6719, "step": 570 }, { "epoch": 0.43, "learning_rate": 4.2802184164805165e-05, "loss": 1.6876, "step": 580 }, { "epoch": 0.44, "learning_rate": 4.2678083891784565e-05, "loss": 1.6586, "step": 590 }, { "epoch": 0.45, "learning_rate": 4.2553983618763964e-05, "loss": 1.6897, "step": 600 }, { "epoch": 0.45, "learning_rate": 4.2429883345743364e-05, "loss": 1.6563, "step": 610 }, { "epoch": 0.46, "learning_rate": 4.2305783072722757e-05, "loss": 1.6897, "step": 620 }, { "epoch": 0.47, "learning_rate": 4.218168279970216e-05, "loss": 1.6692, "step": 630 }, { "epoch": 0.48, "learning_rate": 4.205758252668156e-05, "loss": 1.6706, "step": 640 }, { "epoch": 0.48, "learning_rate": 4.193348225366096e-05, "loss": 1.6651, "step": 650 }, { "epoch": 0.49, "learning_rate": 4.180938198064036e-05, "loss": 1.6825, "step": 660 }, { "epoch": 0.5, "learning_rate": 4.168528170761976e-05, "loss": 1.6498, "step": 670 }, { "epoch": 0.51, "learning_rate": 4.1561181434599153e-05, "loss": 1.6936, "step": 680 }, { "epoch": 0.51, "learning_rate": 4.143708116157855e-05, "loss": 1.7123, "step": 690 }, { "epoch": 0.52, "learning_rate": 4.131298088855796e-05, "loss": 1.6691, "step": 700 }, { "epoch": 0.53, "learning_rate": 4.118888061553736e-05, "loss": 1.7012, "step": 710 }, { "epoch": 0.54, "learning_rate": 4.106478034251676e-05, "loss": 1.6674, "step": 720 }, { "epoch": 0.54, "learning_rate": 4.094068006949616e-05, "loss": 1.6844, "step": 730 }, { "epoch": 0.55, "learning_rate": 4.081657979647556e-05, "loss": 1.6373, "step": 740 }, { "epoch": 0.56, "learning_rate": 4.069247952345495e-05, "loss": 1.6868, "step": 750 }, { "epoch": 0.57, "learning_rate": 4.056837925043435e-05, "loss": 1.6604, "step": 760 }, { "epoch": 0.57, "learning_rate": 4.044427897741375e-05, "loss": 1.6834, "step": 770 }, { "epoch": 0.58, "learning_rate": 4.0320178704393155e-05, "loss": 1.6587, "step": 780 }, { "epoch": 0.59, "learning_rate": 4.0196078431372555e-05, "loss": 1.7264, "step": 790 }, { "epoch": 0.6, "learning_rate": 4.0071978158351954e-05, "loss": 1.6618, "step": 800 }, { "epoch": 0.6, "learning_rate": 3.994787788533135e-05, "loss": 1.6448, "step": 810 }, { "epoch": 0.61, "learning_rate": 3.9823777612310746e-05, "loss": 1.6918, "step": 820 }, { "epoch": 0.62, "learning_rate": 3.9699677339290146e-05, "loss": 1.6985, "step": 830 }, { "epoch": 0.63, "learning_rate": 3.9575577066269545e-05, "loss": 1.6774, "step": 840 }, { "epoch": 0.63, "learning_rate": 3.945147679324895e-05, "loss": 1.6627, "step": 850 }, { "epoch": 0.64, "learning_rate": 3.932737652022835e-05, "loss": 1.6789, "step": 860 }, { "epoch": 0.65, "learning_rate": 3.9203276247207744e-05, "loss": 1.6428, "step": 870 }, { "epoch": 0.66, "learning_rate": 3.907917597418714e-05, "loss": 1.6933, "step": 880 }, { "epoch": 0.66, "learning_rate": 3.895507570116654e-05, "loss": 1.7061, "step": 890 }, { "epoch": 0.67, "learning_rate": 3.883097542814594e-05, "loss": 1.6626, "step": 900 }, { "epoch": 0.68, "learning_rate": 3.870687515512534e-05, "loss": 1.6478, "step": 910 }, { "epoch": 0.69, "learning_rate": 3.858277488210474e-05, "loss": 1.6741, "step": 920 }, { "epoch": 0.69, "learning_rate": 3.845867460908415e-05, "loss": 1.6474, "step": 930 }, { "epoch": 0.7, "learning_rate": 3.833457433606354e-05, "loss": 1.6721, "step": 940 }, { "epoch": 0.71, "learning_rate": 3.821047406304294e-05, "loss": 1.6692, "step": 950 }, { "epoch": 0.71, "learning_rate": 3.808637379002234e-05, "loss": 1.6877, "step": 960 }, { "epoch": 0.72, "learning_rate": 3.796227351700174e-05, "loss": 1.6902, "step": 970 }, { "epoch": 0.73, "learning_rate": 3.783817324398114e-05, "loss": 1.67, "step": 980 }, { "epoch": 0.74, "learning_rate": 3.771407297096054e-05, "loss": 1.6489, "step": 990 }, { "epoch": 0.74, "learning_rate": 3.758997269793994e-05, "loss": 1.6152, "step": 1000 }, { "epoch": 0.75, "learning_rate": 3.7465872424919336e-05, "loss": 1.6342, "step": 1010 }, { "epoch": 0.76, "learning_rate": 3.7341772151898736e-05, "loss": 1.7007, "step": 1020 }, { "epoch": 0.77, "learning_rate": 3.7217671878878135e-05, "loss": 1.6869, "step": 1030 }, { "epoch": 0.77, "learning_rate": 3.7093571605857535e-05, "loss": 1.6739, "step": 1040 }, { "epoch": 0.78, "learning_rate": 3.6969471332836934e-05, "loss": 1.6451, "step": 1050 }, { "epoch": 0.79, "learning_rate": 3.6845371059816334e-05, "loss": 1.7087, "step": 1060 }, { "epoch": 0.8, "learning_rate": 3.672127078679573e-05, "loss": 1.6473, "step": 1070 }, { "epoch": 0.8, "learning_rate": 3.659717051377513e-05, "loss": 1.6848, "step": 1080 }, { "epoch": 0.81, "learning_rate": 3.647307024075453e-05, "loss": 1.7159, "step": 1090 }, { "epoch": 0.82, "learning_rate": 3.634896996773393e-05, "loss": 1.6728, "step": 1100 }, { "epoch": 0.83, "learning_rate": 3.622486969471333e-05, "loss": 1.6719, "step": 1110 }, { "epoch": 0.83, "learning_rate": 3.610076942169273e-05, "loss": 1.6785, "step": 1120 }, { "epoch": 0.84, "learning_rate": 3.597666914867212e-05, "loss": 1.6803, "step": 1130 }, { "epoch": 0.85, "learning_rate": 3.585256887565153e-05, "loss": 1.6699, "step": 1140 }, { "epoch": 0.86, "learning_rate": 3.572846860263093e-05, "loss": 1.7113, "step": 1150 }, { "epoch": 0.86, "learning_rate": 3.560436832961033e-05, "loss": 1.6633, "step": 1160 }, { "epoch": 0.87, "learning_rate": 3.548026805658973e-05, "loss": 1.682, "step": 1170 }, { "epoch": 0.88, "learning_rate": 3.535616778356913e-05, "loss": 1.6666, "step": 1180 }, { "epoch": 0.89, "learning_rate": 3.523206751054853e-05, "loss": 1.6731, "step": 1190 }, { "epoch": 0.89, "learning_rate": 3.510796723752792e-05, "loss": 1.6593, "step": 1200 }, { "epoch": 0.9, "learning_rate": 3.498386696450732e-05, "loss": 1.6447, "step": 1210 }, { "epoch": 0.91, "learning_rate": 3.4859766691486725e-05, "loss": 1.5988, "step": 1220 }, { "epoch": 0.92, "learning_rate": 3.4735666418466125e-05, "loss": 1.6807, "step": 1230 }, { "epoch": 0.92, "learning_rate": 3.4611566145445524e-05, "loss": 1.713, "step": 1240 }, { "epoch": 0.93, "learning_rate": 3.4487465872424924e-05, "loss": 1.6622, "step": 1250 }, { "epoch": 0.94, "learning_rate": 3.4363365599404317e-05, "loss": 1.7027, "step": 1260 }, { "epoch": 0.95, "learning_rate": 3.4239265326383716e-05, "loss": 1.6428, "step": 1270 }, { "epoch": 0.95, "learning_rate": 3.4115165053363115e-05, "loss": 1.6927, "step": 1280 }, { "epoch": 0.96, "learning_rate": 3.399106478034252e-05, "loss": 1.6833, "step": 1290 }, { "epoch": 0.97, "learning_rate": 3.386696450732192e-05, "loss": 1.6675, "step": 1300 }, { "epoch": 0.98, "learning_rate": 3.374286423430132e-05, "loss": 1.6862, "step": 1310 }, { "epoch": 0.98, "learning_rate": 3.3618763961280713e-05, "loss": 1.6729, "step": 1320 }, { "epoch": 0.99, "learning_rate": 3.349466368826011e-05, "loss": 1.6459, "step": 1330 }, { "epoch": 1.0, "learning_rate": 3.337056341523951e-05, "loss": 1.7022, "step": 1340 }, { "epoch": 1.01, "learning_rate": 3.324646314221891e-05, "loss": 1.6457, "step": 1350 }, { "epoch": 1.01, "learning_rate": 3.312236286919831e-05, "loss": 1.6501, "step": 1360 }, { "epoch": 1.02, "learning_rate": 3.299826259617772e-05, "loss": 1.6801, "step": 1370 }, { "epoch": 1.03, "learning_rate": 3.287416232315712e-05, "loss": 1.6756, "step": 1380 }, { "epoch": 1.03, "learning_rate": 3.275006205013651e-05, "loss": 1.6152, "step": 1390 }, { "epoch": 1.04, "learning_rate": 3.262596177711591e-05, "loss": 1.6636, "step": 1400 }, { "epoch": 1.05, "learning_rate": 3.250186150409531e-05, "loss": 1.6726, "step": 1410 }, { "epoch": 1.06, "learning_rate": 3.237776123107471e-05, "loss": 1.617, "step": 1420 }, { "epoch": 1.06, "learning_rate": 3.225366095805411e-05, "loss": 1.6792, "step": 1430 }, { "epoch": 1.07, "learning_rate": 3.2129560685033514e-05, "loss": 1.6745, "step": 1440 }, { "epoch": 1.08, "learning_rate": 3.200546041201291e-05, "loss": 1.6935, "step": 1450 }, { "epoch": 1.09, "learning_rate": 3.1881360138992306e-05, "loss": 1.6966, "step": 1460 }, { "epoch": 1.09, "learning_rate": 3.1757259865971706e-05, "loss": 1.6419, "step": 1470 }, { "epoch": 1.1, "learning_rate": 3.1633159592951105e-05, "loss": 1.662, "step": 1480 }, { "epoch": 1.11, "learning_rate": 3.1509059319930505e-05, "loss": 1.6341, "step": 1490 }, { "epoch": 1.12, "learning_rate": 3.1384959046909904e-05, "loss": 1.6635, "step": 1500 }, { "epoch": 1.12, "learning_rate": 3.1260858773889304e-05, "loss": 1.7295, "step": 1510 }, { "epoch": 1.13, "learning_rate": 3.11367585008687e-05, "loss": 1.6808, "step": 1520 }, { "epoch": 1.14, "learning_rate": 3.10126582278481e-05, "loss": 1.6468, "step": 1530 }, { "epoch": 1.15, "learning_rate": 3.08885579548275e-05, "loss": 1.691, "step": 1540 }, { "epoch": 1.15, "learning_rate": 3.07644576818069e-05, "loss": 1.6552, "step": 1550 }, { "epoch": 1.16, "learning_rate": 3.06403574087863e-05, "loss": 1.6505, "step": 1560 }, { "epoch": 1.17, "learning_rate": 3.0516257135765704e-05, "loss": 1.688, "step": 1570 }, { "epoch": 1.18, "learning_rate": 3.0392156862745097e-05, "loss": 1.6815, "step": 1580 }, { "epoch": 1.18, "learning_rate": 3.0268056589724496e-05, "loss": 1.636, "step": 1590 }, { "epoch": 1.19, "learning_rate": 3.01439563167039e-05, "loss": 1.6722, "step": 1600 }, { "epoch": 1.2, "learning_rate": 3.00198560436833e-05, "loss": 1.6699, "step": 1610 }, { "epoch": 1.21, "learning_rate": 2.9895755770662698e-05, "loss": 1.6866, "step": 1620 }, { "epoch": 1.21, "learning_rate": 2.9771655497642097e-05, "loss": 1.6608, "step": 1630 }, { "epoch": 1.22, "learning_rate": 2.9647555224621497e-05, "loss": 1.6178, "step": 1640 }, { "epoch": 1.23, "learning_rate": 2.9523454951600893e-05, "loss": 1.6967, "step": 1650 }, { "epoch": 1.24, "learning_rate": 2.9399354678580292e-05, "loss": 1.6463, "step": 1660 }, { "epoch": 1.24, "learning_rate": 2.9275254405559692e-05, "loss": 1.658, "step": 1670 }, { "epoch": 1.25, "learning_rate": 2.9151154132539095e-05, "loss": 1.6781, "step": 1680 }, { "epoch": 1.26, "learning_rate": 2.9027053859518494e-05, "loss": 1.6673, "step": 1690 }, { "epoch": 1.27, "learning_rate": 2.8902953586497894e-05, "loss": 1.6404, "step": 1700 }, { "epoch": 1.27, "learning_rate": 2.877885331347729e-05, "loss": 1.7009, "step": 1710 }, { "epoch": 1.28, "learning_rate": 2.865475304045669e-05, "loss": 1.6635, "step": 1720 }, { "epoch": 1.29, "learning_rate": 2.853065276743609e-05, "loss": 1.6714, "step": 1730 }, { "epoch": 1.3, "learning_rate": 2.8406552494415488e-05, "loss": 1.6603, "step": 1740 }, { "epoch": 1.3, "learning_rate": 2.828245222139489e-05, "loss": 1.6324, "step": 1750 }, { "epoch": 1.31, "learning_rate": 2.815835194837429e-05, "loss": 1.6442, "step": 1760 }, { "epoch": 1.32, "learning_rate": 2.8034251675353683e-05, "loss": 1.6276, "step": 1770 }, { "epoch": 1.33, "learning_rate": 2.7910151402333086e-05, "loss": 1.6726, "step": 1780 }, { "epoch": 1.33, "learning_rate": 2.7786051129312486e-05, "loss": 1.7454, "step": 1790 }, { "epoch": 1.34, "learning_rate": 2.7661950856291885e-05, "loss": 1.6872, "step": 1800 }, { "epoch": 1.35, "learning_rate": 2.7537850583271285e-05, "loss": 1.6247, "step": 1810 }, { "epoch": 1.36, "learning_rate": 2.7413750310250684e-05, "loss": 1.6809, "step": 1820 }, { "epoch": 1.36, "learning_rate": 2.7289650037230087e-05, "loss": 1.6463, "step": 1830 }, { "epoch": 1.37, "learning_rate": 2.716554976420948e-05, "loss": 1.6471, "step": 1840 }, { "epoch": 1.38, "learning_rate": 2.704144949118888e-05, "loss": 1.6207, "step": 1850 }, { "epoch": 1.38, "learning_rate": 2.6917349218168282e-05, "loss": 1.6446, "step": 1860 }, { "epoch": 1.39, "learning_rate": 2.679324894514768e-05, "loss": 1.6531, "step": 1870 }, { "epoch": 1.4, "learning_rate": 2.666914867212708e-05, "loss": 1.7086, "step": 1880 }, { "epoch": 1.41, "learning_rate": 2.654504839910648e-05, "loss": 1.6952, "step": 1890 }, { "epoch": 1.41, "learning_rate": 2.6420948126085876e-05, "loss": 1.7021, "step": 1900 }, { "epoch": 1.42, "learning_rate": 2.6296847853065276e-05, "loss": 1.675, "step": 1910 }, { "epoch": 1.43, "learning_rate": 2.6172747580044675e-05, "loss": 1.704, "step": 1920 }, { "epoch": 1.44, "learning_rate": 2.6048647307024078e-05, "loss": 1.6771, "step": 1930 }, { "epoch": 1.44, "learning_rate": 2.5924547034003478e-05, "loss": 1.6419, "step": 1940 }, { "epoch": 1.45, "learning_rate": 2.5800446760982877e-05, "loss": 1.6895, "step": 1950 }, { "epoch": 1.46, "learning_rate": 2.5676346487962277e-05, "loss": 1.6553, "step": 1960 }, { "epoch": 1.47, "learning_rate": 2.5552246214941673e-05, "loss": 1.6813, "step": 1970 }, { "epoch": 1.47, "learning_rate": 2.5428145941921072e-05, "loss": 1.7266, "step": 1980 }, { "epoch": 1.48, "learning_rate": 2.5304045668900472e-05, "loss": 1.6449, "step": 1990 }, { "epoch": 1.49, "learning_rate": 2.517994539587987e-05, "loss": 1.6844, "step": 2000 }, { "epoch": 1.5, "learning_rate": 2.5055845122859274e-05, "loss": 1.6786, "step": 2010 }, { "epoch": 1.5, "learning_rate": 2.493174484983867e-05, "loss": 1.7249, "step": 2020 }, { "epoch": 1.51, "learning_rate": 2.480764457681807e-05, "loss": 1.6894, "step": 2030 }, { "epoch": 1.52, "learning_rate": 2.468354430379747e-05, "loss": 1.6378, "step": 2040 }, { "epoch": 1.53, "learning_rate": 2.455944403077687e-05, "loss": 1.6217, "step": 2050 }, { "epoch": 1.53, "learning_rate": 2.4435343757756268e-05, "loss": 1.6994, "step": 2060 }, { "epoch": 1.54, "learning_rate": 2.4311243484735668e-05, "loss": 1.6395, "step": 2070 }, { "epoch": 1.55, "learning_rate": 2.4187143211715067e-05, "loss": 1.681, "step": 2080 }, { "epoch": 1.56, "learning_rate": 2.4063042938694467e-05, "loss": 1.6679, "step": 2090 }, { "epoch": 1.56, "learning_rate": 2.3938942665673866e-05, "loss": 1.6626, "step": 2100 }, { "epoch": 1.57, "learning_rate": 2.3814842392653262e-05, "loss": 1.6688, "step": 2110 }, { "epoch": 1.58, "learning_rate": 2.3690742119632665e-05, "loss": 1.6993, "step": 2120 }, { "epoch": 1.59, "learning_rate": 2.3566641846612065e-05, "loss": 1.6653, "step": 2130 }, { "epoch": 1.59, "learning_rate": 2.3442541573591464e-05, "loss": 1.6902, "step": 2140 }, { "epoch": 1.6, "learning_rate": 2.3318441300570863e-05, "loss": 1.6639, "step": 2150 }, { "epoch": 1.61, "learning_rate": 2.3194341027550263e-05, "loss": 1.6497, "step": 2160 }, { "epoch": 1.62, "learning_rate": 2.3070240754529662e-05, "loss": 1.6298, "step": 2170 }, { "epoch": 1.62, "learning_rate": 2.294614048150906e-05, "loss": 1.6438, "step": 2180 }, { "epoch": 1.63, "learning_rate": 2.282204020848846e-05, "loss": 1.6262, "step": 2190 }, { "epoch": 1.64, "learning_rate": 2.269793993546786e-05, "loss": 1.6852, "step": 2200 }, { "epoch": 1.65, "learning_rate": 2.2573839662447257e-05, "loss": 1.6822, "step": 2210 }, { "epoch": 1.65, "learning_rate": 2.2449739389426656e-05, "loss": 1.6899, "step": 2220 }, { "epoch": 1.66, "learning_rate": 2.232563911640606e-05, "loss": 1.626, "step": 2230 }, { "epoch": 1.67, "learning_rate": 2.2201538843385455e-05, "loss": 1.6789, "step": 2240 }, { "epoch": 1.68, "learning_rate": 2.2077438570364855e-05, "loss": 1.6565, "step": 2250 }, { "epoch": 1.68, "learning_rate": 2.1953338297344254e-05, "loss": 1.6891, "step": 2260 }, { "epoch": 1.69, "learning_rate": 2.1829238024323654e-05, "loss": 1.6958, "step": 2270 }, { "epoch": 1.7, "learning_rate": 2.1705137751303053e-05, "loss": 1.631, "step": 2280 }, { "epoch": 1.71, "learning_rate": 2.1581037478282453e-05, "loss": 1.6186, "step": 2290 }, { "epoch": 1.71, "learning_rate": 2.1456937205261852e-05, "loss": 1.6403, "step": 2300 }, { "epoch": 1.72, "learning_rate": 2.1332836932241252e-05, "loss": 1.6636, "step": 2310 }, { "epoch": 1.73, "learning_rate": 2.120873665922065e-05, "loss": 1.7027, "step": 2320 }, { "epoch": 1.73, "learning_rate": 2.108463638620005e-05, "loss": 1.6916, "step": 2330 }, { "epoch": 1.74, "learning_rate": 2.096053611317945e-05, "loss": 1.6643, "step": 2340 }, { "epoch": 1.75, "learning_rate": 2.083643584015885e-05, "loss": 1.6531, "step": 2350 }, { "epoch": 1.76, "learning_rate": 2.071233556713825e-05, "loss": 1.6272, "step": 2360 }, { "epoch": 1.76, "learning_rate": 2.058823529411765e-05, "loss": 1.6251, "step": 2370 }, { "epoch": 1.77, "learning_rate": 2.0464135021097048e-05, "loss": 1.6679, "step": 2380 }, { "epoch": 1.78, "learning_rate": 2.0340034748076448e-05, "loss": 1.6414, "step": 2390 }, { "epoch": 1.79, "learning_rate": 2.0215934475055844e-05, "loss": 1.6384, "step": 2400 }, { "epoch": 1.79, "learning_rate": 2.0091834202035247e-05, "loss": 1.6612, "step": 2410 }, { "epoch": 1.8, "learning_rate": 1.9967733929014646e-05, "loss": 1.6294, "step": 2420 }, { "epoch": 1.81, "learning_rate": 1.9843633655994042e-05, "loss": 1.7111, "step": 2430 }, { "epoch": 1.82, "learning_rate": 1.971953338297344e-05, "loss": 1.6443, "step": 2440 }, { "epoch": 1.82, "learning_rate": 1.9595433109952844e-05, "loss": 1.6743, "step": 2450 }, { "epoch": 1.83, "learning_rate": 1.9471332836932244e-05, "loss": 1.6503, "step": 2460 }, { "epoch": 1.84, "learning_rate": 1.934723256391164e-05, "loss": 1.635, "step": 2470 }, { "epoch": 1.85, "learning_rate": 1.922313229089104e-05, "loss": 1.6268, "step": 2480 }, { "epoch": 1.85, "learning_rate": 1.9099032017870442e-05, "loss": 1.6998, "step": 2490 }, { "epoch": 1.86, "learning_rate": 1.897493174484984e-05, "loss": 1.6196, "step": 2500 }, { "epoch": 1.87, "learning_rate": 1.8850831471829238e-05, "loss": 1.6758, "step": 2510 }, { "epoch": 1.88, "learning_rate": 1.8726731198808637e-05, "loss": 1.6605, "step": 2520 }, { "epoch": 1.88, "learning_rate": 1.8602630925788037e-05, "loss": 1.6611, "step": 2530 }, { "epoch": 1.89, "learning_rate": 1.8478530652767436e-05, "loss": 1.6922, "step": 2540 }, { "epoch": 1.9, "learning_rate": 1.8354430379746836e-05, "loss": 1.6888, "step": 2550 }, { "epoch": 1.91, "learning_rate": 1.8230330106726235e-05, "loss": 1.6768, "step": 2560 }, { "epoch": 1.91, "learning_rate": 1.8106229833705635e-05, "loss": 1.6707, "step": 2570 }, { "epoch": 1.92, "learning_rate": 1.7982129560685034e-05, "loss": 1.6322, "step": 2580 }, { "epoch": 1.93, "learning_rate": 1.7858029287664434e-05, "loss": 1.7273, "step": 2590 }, { "epoch": 1.94, "learning_rate": 1.7733929014643833e-05, "loss": 1.657, "step": 2600 }, { "epoch": 1.94, "learning_rate": 1.7609828741623233e-05, "loss": 1.6675, "step": 2610 }, { "epoch": 1.95, "learning_rate": 1.7485728468602632e-05, "loss": 1.6635, "step": 2620 }, { "epoch": 1.96, "learning_rate": 1.7361628195582032e-05, "loss": 1.7096, "step": 2630 }, { "epoch": 1.97, "learning_rate": 1.723752792256143e-05, "loss": 1.6372, "step": 2640 }, { "epoch": 1.97, "learning_rate": 1.711342764954083e-05, "loss": 1.6543, "step": 2650 }, { "epoch": 1.98, "learning_rate": 1.6989327376520227e-05, "loss": 1.6279, "step": 2660 }, { "epoch": 1.99, "learning_rate": 1.686522710349963e-05, "loss": 1.6361, "step": 2670 }, { "epoch": 2.0, "learning_rate": 1.674112683047903e-05, "loss": 1.6577, "step": 2680 }, { "epoch": 2.0, "learning_rate": 1.6617026557458425e-05, "loss": 1.6519, "step": 2690 }, { "epoch": 2.01, "learning_rate": 1.6492926284437825e-05, "loss": 1.6885, "step": 2700 }, { "epoch": 2.02, "learning_rate": 1.6368826011417228e-05, "loss": 1.6314, "step": 2710 }, { "epoch": 2.03, "learning_rate": 1.6244725738396624e-05, "loss": 1.7008, "step": 2720 }, { "epoch": 2.03, "learning_rate": 1.6120625465376023e-05, "loss": 1.6638, "step": 2730 }, { "epoch": 2.04, "learning_rate": 1.5996525192355426e-05, "loss": 1.6488, "step": 2740 }, { "epoch": 2.05, "learning_rate": 1.5872424919334825e-05, "loss": 1.6602, "step": 2750 }, { "epoch": 2.06, "learning_rate": 1.574832464631422e-05, "loss": 1.671, "step": 2760 }, { "epoch": 2.06, "learning_rate": 1.562422437329362e-05, "loss": 1.7074, "step": 2770 }, { "epoch": 2.07, "learning_rate": 1.5500124100273024e-05, "loss": 1.7044, "step": 2780 }, { "epoch": 2.08, "learning_rate": 1.537602382725242e-05, "loss": 1.6499, "step": 2790 }, { "epoch": 2.08, "learning_rate": 1.525192355423182e-05, "loss": 1.6293, "step": 2800 }, { "epoch": 2.09, "learning_rate": 1.512782328121122e-05, "loss": 1.6543, "step": 2810 }, { "epoch": 2.1, "learning_rate": 1.5003723008190618e-05, "loss": 1.6497, "step": 2820 }, { "epoch": 2.11, "learning_rate": 1.4879622735170018e-05, "loss": 1.6494, "step": 2830 }, { "epoch": 2.11, "learning_rate": 1.4755522462149417e-05, "loss": 1.6416, "step": 2840 }, { "epoch": 2.12, "learning_rate": 1.4631422189128815e-05, "loss": 1.6681, "step": 2850 }, { "epoch": 2.13, "learning_rate": 1.4507321916108216e-05, "loss": 1.651, "step": 2860 }, { "epoch": 2.14, "learning_rate": 1.4383221643087616e-05, "loss": 1.6304, "step": 2870 }, { "epoch": 2.14, "learning_rate": 1.4259121370067017e-05, "loss": 1.6882, "step": 2880 }, { "epoch": 2.15, "learning_rate": 1.4135021097046413e-05, "loss": 1.6731, "step": 2890 }, { "epoch": 2.16, "learning_rate": 1.4010920824025814e-05, "loss": 1.6352, "step": 2900 }, { "epoch": 2.17, "learning_rate": 1.3886820551005214e-05, "loss": 1.6431, "step": 2910 }, { "epoch": 2.17, "learning_rate": 1.3762720277984612e-05, "loss": 1.6861, "step": 2920 }, { "epoch": 2.18, "learning_rate": 1.3638620004964011e-05, "loss": 1.6547, "step": 2930 }, { "epoch": 2.19, "learning_rate": 1.3514519731943412e-05, "loss": 1.6977, "step": 2940 }, { "epoch": 2.2, "learning_rate": 1.339041945892281e-05, "loss": 1.6685, "step": 2950 }, { "epoch": 2.2, "learning_rate": 1.326631918590221e-05, "loss": 1.6431, "step": 2960 }, { "epoch": 2.21, "learning_rate": 1.3142218912881609e-05, "loss": 1.6643, "step": 2970 }, { "epoch": 2.22, "learning_rate": 1.3018118639861007e-05, "loss": 1.6742, "step": 2980 }, { "epoch": 2.23, "learning_rate": 1.2894018366840408e-05, "loss": 1.6792, "step": 2990 }, { "epoch": 2.23, "learning_rate": 1.2769918093819807e-05, "loss": 1.646, "step": 3000 }, { "epoch": 2.24, "learning_rate": 1.2645817820799205e-05, "loss": 1.6429, "step": 3010 }, { "epoch": 2.25, "learning_rate": 1.2521717547778605e-05, "loss": 1.6593, "step": 3020 }, { "epoch": 2.26, "learning_rate": 1.2397617274758006e-05, "loss": 1.6614, "step": 3030 }, { "epoch": 2.26, "learning_rate": 1.2273517001737404e-05, "loss": 1.6751, "step": 3040 }, { "epoch": 2.27, "learning_rate": 1.2149416728716803e-05, "loss": 1.6603, "step": 3050 }, { "epoch": 2.28, "learning_rate": 1.2025316455696203e-05, "loss": 1.6363, "step": 3060 }, { "epoch": 2.29, "learning_rate": 1.1901216182675602e-05, "loss": 1.6295, "step": 3070 }, { "epoch": 2.29, "learning_rate": 1.1777115909655002e-05, "loss": 1.6173, "step": 3080 }, { "epoch": 2.3, "learning_rate": 1.1653015636634401e-05, "loss": 1.6602, "step": 3090 }, { "epoch": 2.31, "learning_rate": 1.15289153636138e-05, "loss": 1.6252, "step": 3100 }, { "epoch": 2.32, "learning_rate": 1.14048150905932e-05, "loss": 1.5957, "step": 3110 }, { "epoch": 2.32, "learning_rate": 1.12807148175726e-05, "loss": 1.6549, "step": 3120 }, { "epoch": 2.33, "learning_rate": 1.1156614544551997e-05, "loss": 1.679, "step": 3130 }, { "epoch": 2.34, "learning_rate": 1.1032514271531398e-05, "loss": 1.6924, "step": 3140 }, { "epoch": 2.35, "learning_rate": 1.0908413998510796e-05, "loss": 1.7333, "step": 3150 }, { "epoch": 2.35, "learning_rate": 1.0784313725490197e-05, "loss": 1.6296, "step": 3160 }, { "epoch": 2.36, "learning_rate": 1.0660213452469595e-05, "loss": 1.6571, "step": 3170 }, { "epoch": 2.37, "learning_rate": 1.0536113179448995e-05, "loss": 1.6586, "step": 3180 }, { "epoch": 2.38, "learning_rate": 1.0412012906428396e-05, "loss": 1.6801, "step": 3190 }, { "epoch": 2.38, "learning_rate": 1.0287912633407794e-05, "loss": 1.6578, "step": 3200 }, { "epoch": 2.39, "learning_rate": 1.0163812360387195e-05, "loss": 1.651, "step": 3210 }, { "epoch": 2.4, "learning_rate": 1.0039712087366593e-05, "loss": 1.6463, "step": 3220 }, { "epoch": 2.41, "learning_rate": 9.915611814345992e-06, "loss": 1.6758, "step": 3230 }, { "epoch": 2.41, "learning_rate": 9.791511541325392e-06, "loss": 1.6101, "step": 3240 }, { "epoch": 2.42, "learning_rate": 9.667411268304791e-06, "loss": 1.6287, "step": 3250 }, { "epoch": 2.43, "learning_rate": 9.543310995284189e-06, "loss": 1.6586, "step": 3260 }, { "epoch": 2.43, "learning_rate": 9.41921072226359e-06, "loss": 1.671, "step": 3270 }, { "epoch": 2.44, "learning_rate": 9.295110449242988e-06, "loss": 1.6542, "step": 3280 }, { "epoch": 2.45, "learning_rate": 9.171010176222389e-06, "loss": 1.6366, "step": 3290 }, { "epoch": 2.46, "learning_rate": 9.046909903201788e-06, "loss": 1.6178, "step": 3300 }, { "epoch": 2.46, "learning_rate": 8.922809630181186e-06, "loss": 1.6397, "step": 3310 }, { "epoch": 2.47, "learning_rate": 8.798709357160587e-06, "loss": 1.6754, "step": 3320 }, { "epoch": 2.48, "learning_rate": 8.674609084139985e-06, "loss": 1.6704, "step": 3330 }, { "epoch": 2.49, "learning_rate": 8.550508811119385e-06, "loss": 1.6644, "step": 3340 }, { "epoch": 2.49, "learning_rate": 8.426408538098784e-06, "loss": 1.6371, "step": 3350 }, { "epoch": 2.5, "learning_rate": 8.302308265078184e-06, "loss": 1.6559, "step": 3360 }, { "epoch": 2.51, "learning_rate": 8.178207992057583e-06, "loss": 1.64, "step": 3370 }, { "epoch": 2.52, "learning_rate": 8.054107719036983e-06, "loss": 1.6312, "step": 3380 }, { "epoch": 2.52, "learning_rate": 7.93000744601638e-06, "loss": 1.6663, "step": 3390 }, { "epoch": 2.53, "learning_rate": 7.805907172995782e-06, "loss": 1.6617, "step": 3400 }, { "epoch": 2.54, "learning_rate": 7.681806899975181e-06, "loss": 1.6976, "step": 3410 }, { "epoch": 2.55, "learning_rate": 7.557706626954579e-06, "loss": 1.6472, "step": 3420 }, { "epoch": 2.55, "learning_rate": 7.433606353933979e-06, "loss": 1.6116, "step": 3430 }, { "epoch": 2.56, "learning_rate": 7.309506080913378e-06, "loss": 1.65, "step": 3440 }, { "epoch": 2.57, "learning_rate": 7.185405807892778e-06, "loss": 1.6776, "step": 3450 }, { "epoch": 2.58, "learning_rate": 7.061305534872177e-06, "loss": 1.6506, "step": 3460 }, { "epoch": 2.58, "learning_rate": 6.937205261851576e-06, "loss": 1.6523, "step": 3470 }, { "epoch": 2.59, "learning_rate": 6.8131049888309765e-06, "loss": 1.6785, "step": 3480 }, { "epoch": 2.6, "learning_rate": 6.689004715810375e-06, "loss": 1.6364, "step": 3490 }, { "epoch": 2.61, "learning_rate": 6.564904442789774e-06, "loss": 1.6569, "step": 3500 } ], "logging_steps": 10, "max_steps": 4029, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.21208687673344e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }