{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.8229775327133569, "eval_steps": 500, "global_step": 10000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 5.0453611334320685e-06, "loss": 0.3087, "step": 25 }, { "epoch": 0.0, "learning_rate": 6.229195710491767e-06, "loss": 0.3064, "step": 50 }, { "epoch": 0.01, "learning_rate": 6.903829450223392e-06, "loss": 0.3032, "step": 75 }, { "epoch": 0.01, "learning_rate": 7.377725845391017e-06, "loss": 0.2897, "step": 100 }, { "epoch": 0.01, "learning_rate": 7.743343231239583e-06, "loss": 0.2752, "step": 125 }, { "epoch": 0.01, "learning_rate": 8.041073861170494e-06, "loss": 0.2695, "step": 150 }, { "epoch": 0.01, "learning_rate": 8.292222957399574e-06, "loss": 0.2657, "step": 175 }, { "epoch": 0.02, "learning_rate": 8.509413541357755e-06, "loss": 0.2567, "step": 200 }, { "epoch": 0.02, "learning_rate": 8.700744577655557e-06, "loss": 0.2824, "step": 225 }, { "epoch": 0.02, "learning_rate": 8.871723942761204e-06, "loss": 0.266, "step": 250 }, { "epoch": 0.02, "learning_rate": 9.026267958246849e-06, "loss": 0.2634, "step": 275 }, { "epoch": 0.02, "learning_rate": 9.16726106663399e-06, "loss": 0.2691, "step": 300 }, { "epoch": 0.03, "learning_rate": 9.296889251455016e-06, "loss": 0.256, "step": 325 }, { "epoch": 0.03, "learning_rate": 9.416848797368692e-06, "loss": 0.2534, "step": 350 }, { "epoch": 0.03, "learning_rate": 9.528482449516371e-06, "loss": 0.2719, "step": 375 }, { "epoch": 0.03, "learning_rate": 9.632871309784314e-06, "loss": 0.2646, "step": 400 }, { "epoch": 0.03, "learning_rate": 9.73089868785391e-06, "loss": 0.2508, "step": 425 }, { "epoch": 0.04, "learning_rate": 9.823295589572114e-06, "loss": 0.2521, "step": 450 }, { "epoch": 0.04, "learning_rate": 9.910673836465484e-06, "loss": 0.2381, "step": 475 }, { "epoch": 0.04, "learning_rate": 9.993550644973805e-06, "loss": 0.2728, "step": 500 }, { "epoch": 0.04, "learning_rate": 9.976842105263158e-06, "loss": 0.2246, "step": 525 }, { "epoch": 0.05, "learning_rate": 9.950526315789475e-06, "loss": 0.2373, "step": 550 }, { "epoch": 0.05, "learning_rate": 9.92421052631579e-06, "loss": 0.2511, "step": 575 }, { "epoch": 0.05, "learning_rate": 9.897894736842107e-06, "loss": 0.246, "step": 600 }, { "epoch": 0.05, "learning_rate": 9.871578947368422e-06, "loss": 0.2273, "step": 625 }, { "epoch": 0.05, "learning_rate": 9.845263157894738e-06, "loss": 0.2509, "step": 650 }, { "epoch": 0.06, "learning_rate": 9.818947368421053e-06, "loss": 0.2126, "step": 675 }, { "epoch": 0.06, "learning_rate": 9.79263157894737e-06, "loss": 0.2007, "step": 700 }, { "epoch": 0.06, "learning_rate": 9.766315789473685e-06, "loss": 0.248, "step": 725 }, { "epoch": 0.06, "learning_rate": 9.74e-06, "loss": 0.2357, "step": 750 }, { "epoch": 0.06, "learning_rate": 9.713684210526317e-06, "loss": 0.2349, "step": 775 }, { "epoch": 0.07, "learning_rate": 9.687368421052632e-06, "loss": 0.2388, "step": 800 }, { "epoch": 0.07, "learning_rate": 9.661052631578948e-06, "loss": 0.2527, "step": 825 }, { "epoch": 0.07, "learning_rate": 9.634736842105265e-06, "loss": 0.2283, "step": 850 }, { "epoch": 0.07, "learning_rate": 9.60842105263158e-06, "loss": 0.2347, "step": 875 }, { "epoch": 0.07, "learning_rate": 9.582105263157897e-06, "loss": 0.2423, "step": 900 }, { "epoch": 0.08, "learning_rate": 9.555789473684211e-06, "loss": 0.2306, "step": 925 }, { "epoch": 0.08, "learning_rate": 9.529473684210528e-06, "loss": 0.2452, "step": 950 }, { "epoch": 0.08, "learning_rate": 9.503157894736843e-06, "loss": 0.2157, "step": 975 }, { "epoch": 0.08, "learning_rate": 9.476842105263158e-06, "loss": 0.2229, "step": 1000 }, { "epoch": 0.08, "learning_rate": 9.452631578947368e-06, "loss": 0.2176, "step": 1025 }, { "epoch": 0.09, "learning_rate": 9.426315789473685e-06, "loss": 0.2204, "step": 1050 }, { "epoch": 0.09, "learning_rate": 9.4e-06, "loss": 0.2197, "step": 1075 }, { "epoch": 0.09, "learning_rate": 9.373684210526316e-06, "loss": 0.2192, "step": 1100 }, { "epoch": 0.09, "learning_rate": 9.347368421052633e-06, "loss": 0.2084, "step": 1125 }, { "epoch": 0.09, "learning_rate": 9.321052631578948e-06, "loss": 0.2202, "step": 1150 }, { "epoch": 0.1, "learning_rate": 9.294736842105265e-06, "loss": 0.2066, "step": 1175 }, { "epoch": 0.1, "learning_rate": 9.26842105263158e-06, "loss": 0.1891, "step": 1200 }, { "epoch": 0.1, "learning_rate": 9.242105263157896e-06, "loss": 0.2137, "step": 1225 }, { "epoch": 0.1, "learning_rate": 9.215789473684211e-06, "loss": 0.2114, "step": 1250 }, { "epoch": 0.1, "learning_rate": 9.189473684210526e-06, "loss": 0.2036, "step": 1275 }, { "epoch": 0.11, "learning_rate": 9.163157894736843e-06, "loss": 0.2245, "step": 1300 }, { "epoch": 0.11, "learning_rate": 9.136842105263158e-06, "loss": 0.206, "step": 1325 }, { "epoch": 0.11, "learning_rate": 9.110526315789475e-06, "loss": 0.2267, "step": 1350 }, { "epoch": 0.11, "learning_rate": 9.08421052631579e-06, "loss": 0.2308, "step": 1375 }, { "epoch": 0.12, "learning_rate": 9.057894736842106e-06, "loss": 0.1975, "step": 1400 }, { "epoch": 0.12, "learning_rate": 9.031578947368423e-06, "loss": 0.206, "step": 1425 }, { "epoch": 0.12, "learning_rate": 9.005263157894738e-06, "loss": 0.1878, "step": 1450 }, { "epoch": 0.12, "learning_rate": 8.978947368421055e-06, "loss": 0.2008, "step": 1475 }, { "epoch": 0.12, "learning_rate": 8.95263157894737e-06, "loss": 0.2034, "step": 1500 }, { "epoch": 0.13, "learning_rate": 8.926315789473685e-06, "loss": 0.2075, "step": 1525 }, { "epoch": 0.13, "learning_rate": 8.900000000000001e-06, "loss": 0.2086, "step": 1550 }, { "epoch": 0.13, "learning_rate": 8.873684210526316e-06, "loss": 0.1993, "step": 1575 }, { "epoch": 0.13, "learning_rate": 8.847368421052633e-06, "loss": 0.204, "step": 1600 }, { "epoch": 0.13, "learning_rate": 8.821052631578948e-06, "loss": 0.1998, "step": 1625 }, { "epoch": 0.14, "learning_rate": 8.794736842105264e-06, "loss": 0.222, "step": 1650 }, { "epoch": 0.14, "learning_rate": 8.76842105263158e-06, "loss": 0.2151, "step": 1675 }, { "epoch": 0.14, "learning_rate": 8.742105263157894e-06, "loss": 0.1854, "step": 1700 }, { "epoch": 0.14, "learning_rate": 8.715789473684211e-06, "loss": 0.2148, "step": 1725 }, { "epoch": 0.14, "learning_rate": 8.689473684210526e-06, "loss": 0.1965, "step": 1750 }, { "epoch": 0.15, "learning_rate": 8.663157894736843e-06, "loss": 0.216, "step": 1775 }, { "epoch": 0.15, "learning_rate": 8.63684210526316e-06, "loss": 0.2021, "step": 1800 }, { "epoch": 0.15, "learning_rate": 8.610526315789474e-06, "loss": 0.1922, "step": 1825 }, { "epoch": 0.15, "learning_rate": 8.584210526315791e-06, "loss": 0.2068, "step": 1850 }, { "epoch": 0.15, "learning_rate": 8.557894736842106e-06, "loss": 0.2174, "step": 1875 }, { "epoch": 0.16, "learning_rate": 8.531578947368423e-06, "loss": 0.1834, "step": 1900 }, { "epoch": 0.16, "learning_rate": 8.505263157894738e-06, "loss": 0.1714, "step": 1925 }, { "epoch": 0.16, "learning_rate": 8.478947368421053e-06, "loss": 0.2106, "step": 1950 }, { "epoch": 0.16, "learning_rate": 8.45263157894737e-06, "loss": 0.2222, "step": 1975 }, { "epoch": 0.16, "learning_rate": 8.426315789473684e-06, "loss": 0.1911, "step": 2000 }, { "epoch": 0.17, "learning_rate": 8.402105263157896e-06, "loss": 0.1918, "step": 2025 }, { "epoch": 0.17, "learning_rate": 8.375789473684211e-06, "loss": 0.1831, "step": 2050 }, { "epoch": 0.17, "learning_rate": 8.349473684210528e-06, "loss": 0.1808, "step": 2075 }, { "epoch": 0.17, "learning_rate": 8.323157894736843e-06, "loss": 0.1833, "step": 2100 }, { "epoch": 0.17, "learning_rate": 8.29684210526316e-06, "loss": 0.1929, "step": 2125 }, { "epoch": 0.18, "learning_rate": 8.270526315789474e-06, "loss": 0.1846, "step": 2150 }, { "epoch": 0.18, "learning_rate": 8.244210526315791e-06, "loss": 0.1921, "step": 2175 }, { "epoch": 0.18, "learning_rate": 8.217894736842106e-06, "loss": 0.1928, "step": 2200 }, { "epoch": 0.18, "learning_rate": 8.19157894736842e-06, "loss": 0.1808, "step": 2225 }, { "epoch": 0.19, "learning_rate": 8.165263157894737e-06, "loss": 0.191, "step": 2250 }, { "epoch": 0.19, "learning_rate": 8.138947368421052e-06, "loss": 0.1832, "step": 2275 }, { "epoch": 0.19, "learning_rate": 8.112631578947369e-06, "loss": 0.2098, "step": 2300 }, { "epoch": 0.19, "learning_rate": 8.086315789473684e-06, "loss": 0.2125, "step": 2325 }, { "epoch": 0.19, "learning_rate": 8.06e-06, "loss": 0.1671, "step": 2350 }, { "epoch": 0.2, "learning_rate": 8.033684210526317e-06, "loss": 0.185, "step": 2375 }, { "epoch": 0.2, "learning_rate": 8.007368421052632e-06, "loss": 0.1963, "step": 2400 }, { "epoch": 0.2, "learning_rate": 7.981052631578949e-06, "loss": 0.1847, "step": 2425 }, { "epoch": 0.2, "learning_rate": 7.954736842105264e-06, "loss": 0.1862, "step": 2450 }, { "epoch": 0.2, "learning_rate": 7.928421052631579e-06, "loss": 0.1555, "step": 2475 }, { "epoch": 0.21, "learning_rate": 7.902105263157896e-06, "loss": 0.1682, "step": 2500 }, { "epoch": 0.21, "learning_rate": 7.87578947368421e-06, "loss": 0.1705, "step": 2525 }, { "epoch": 0.21, "learning_rate": 7.849473684210527e-06, "loss": 0.1983, "step": 2550 }, { "epoch": 0.21, "learning_rate": 7.823157894736842e-06, "loss": 0.1762, "step": 2575 }, { "epoch": 0.21, "learning_rate": 7.796842105263159e-06, "loss": 0.1835, "step": 2600 }, { "epoch": 0.22, "learning_rate": 7.770526315789474e-06, "loss": 0.1887, "step": 2625 }, { "epoch": 0.22, "learning_rate": 7.744210526315789e-06, "loss": 0.1724, "step": 2650 }, { "epoch": 0.22, "learning_rate": 7.717894736842107e-06, "loss": 0.1937, "step": 2675 }, { "epoch": 0.22, "learning_rate": 7.691578947368422e-06, "loss": 0.1886, "step": 2700 }, { "epoch": 0.22, "learning_rate": 7.665263157894737e-06, "loss": 0.2126, "step": 2725 }, { "epoch": 0.23, "learning_rate": 7.638947368421054e-06, "loss": 0.2043, "step": 2750 }, { "epoch": 0.23, "learning_rate": 7.61263157894737e-06, "loss": 0.1705, "step": 2775 }, { "epoch": 0.23, "learning_rate": 7.586315789473685e-06, "loss": 0.1581, "step": 2800 }, { "epoch": 0.23, "learning_rate": 7.5600000000000005e-06, "loss": 0.1699, "step": 2825 }, { "epoch": 0.23, "learning_rate": 7.533684210526316e-06, "loss": 0.1801, "step": 2850 }, { "epoch": 0.24, "learning_rate": 7.507368421052632e-06, "loss": 0.1732, "step": 2875 }, { "epoch": 0.24, "learning_rate": 7.481052631578948e-06, "loss": 0.1846, "step": 2900 }, { "epoch": 0.24, "learning_rate": 7.454736842105264e-06, "loss": 0.1832, "step": 2925 }, { "epoch": 0.24, "learning_rate": 7.4284210526315796e-06, "loss": 0.1581, "step": 2950 }, { "epoch": 0.24, "learning_rate": 7.4021052631578945e-06, "loss": 0.1744, "step": 2975 }, { "epoch": 0.25, "learning_rate": 7.37578947368421e-06, "loss": 0.1718, "step": 3000 }, { "epoch": 0.25, "learning_rate": 7.351578947368422e-06, "loss": 0.181, "step": 3025 }, { "epoch": 0.25, "learning_rate": 7.325263157894738e-06, "loss": 0.1563, "step": 3050 }, { "epoch": 0.25, "learning_rate": 7.298947368421053e-06, "loss": 0.1821, "step": 3075 }, { "epoch": 0.26, "learning_rate": 7.272631578947369e-06, "loss": 0.1635, "step": 3100 }, { "epoch": 0.26, "learning_rate": 7.2463157894736845e-06, "loss": 0.1922, "step": 3125 }, { "epoch": 0.26, "learning_rate": 7.22e-06, "loss": 0.1771, "step": 3150 }, { "epoch": 0.26, "learning_rate": 7.193684210526316e-06, "loss": 0.1721, "step": 3175 }, { "epoch": 0.26, "learning_rate": 7.167368421052632e-06, "loss": 0.1518, "step": 3200 }, { "epoch": 0.27, "learning_rate": 7.141052631578948e-06, "loss": 0.1621, "step": 3225 }, { "epoch": 0.27, "learning_rate": 7.1147368421052645e-06, "loss": 0.1771, "step": 3250 }, { "epoch": 0.27, "learning_rate": 7.08842105263158e-06, "loss": 0.1703, "step": 3275 }, { "epoch": 0.27, "learning_rate": 7.062105263157896e-06, "loss": 0.1775, "step": 3300 }, { "epoch": 0.27, "learning_rate": 7.035789473684211e-06, "loss": 0.1826, "step": 3325 }, { "epoch": 0.28, "learning_rate": 7.009473684210527e-06, "loss": 0.156, "step": 3350 }, { "epoch": 0.28, "learning_rate": 6.983157894736843e-06, "loss": 0.1743, "step": 3375 }, { "epoch": 0.28, "learning_rate": 6.9568421052631585e-06, "loss": 0.1821, "step": 3400 }, { "epoch": 0.28, "learning_rate": 6.930526315789474e-06, "loss": 0.1784, "step": 3425 }, { "epoch": 0.28, "learning_rate": 6.90421052631579e-06, "loss": 0.1634, "step": 3450 }, { "epoch": 0.29, "learning_rate": 6.877894736842106e-06, "loss": 0.1824, "step": 3475 }, { "epoch": 0.29, "learning_rate": 6.851578947368421e-06, "loss": 0.1852, "step": 3500 }, { "epoch": 0.29, "learning_rate": 6.825263157894737e-06, "loss": 0.1851, "step": 3525 }, { "epoch": 0.29, "learning_rate": 6.798947368421053e-06, "loss": 0.1754, "step": 3550 }, { "epoch": 0.29, "learning_rate": 6.772631578947368e-06, "loss": 0.1805, "step": 3575 }, { "epoch": 0.3, "learning_rate": 6.746315789473685e-06, "loss": 0.1773, "step": 3600 }, { "epoch": 0.3, "learning_rate": 6.720000000000001e-06, "loss": 0.167, "step": 3625 }, { "epoch": 0.3, "learning_rate": 6.693684210526317e-06, "loss": 0.1657, "step": 3650 }, { "epoch": 0.3, "learning_rate": 6.6673684210526325e-06, "loss": 0.2064, "step": 3675 }, { "epoch": 0.3, "learning_rate": 6.641052631578948e-06, "loss": 0.1741, "step": 3700 }, { "epoch": 0.31, "learning_rate": 6.614736842105264e-06, "loss": 0.1899, "step": 3725 }, { "epoch": 0.31, "learning_rate": 6.588421052631579e-06, "loss": 0.1531, "step": 3750 }, { "epoch": 0.31, "learning_rate": 6.562105263157895e-06, "loss": 0.1637, "step": 3775 }, { "epoch": 0.31, "learning_rate": 6.535789473684211e-06, "loss": 0.1386, "step": 3800 }, { "epoch": 0.31, "learning_rate": 6.509473684210527e-06, "loss": 0.1668, "step": 3825 }, { "epoch": 0.32, "learning_rate": 6.483157894736842e-06, "loss": 0.166, "step": 3850 }, { "epoch": 0.32, "learning_rate": 6.456842105263158e-06, "loss": 0.1653, "step": 3875 }, { "epoch": 0.32, "learning_rate": 6.430526315789474e-06, "loss": 0.161, "step": 3900 }, { "epoch": 0.32, "learning_rate": 6.404210526315791e-06, "loss": 0.172, "step": 3925 }, { "epoch": 0.33, "learning_rate": 6.3778947368421065e-06, "loss": 0.1625, "step": 3950 }, { "epoch": 0.33, "learning_rate": 6.351578947368422e-06, "loss": 0.1595, "step": 3975 }, { "epoch": 0.33, "learning_rate": 6.325263157894737e-06, "loss": 0.1513, "step": 4000 }, { "epoch": 0.33, "learning_rate": 6.301052631578947e-06, "loss": 0.1762, "step": 4025 }, { "epoch": 0.33, "learning_rate": 6.274736842105263e-06, "loss": 0.1448, "step": 4050 }, { "epoch": 0.34, "learning_rate": 6.248421052631579e-06, "loss": 0.1773, "step": 4075 }, { "epoch": 0.34, "learning_rate": 6.222105263157895e-06, "loss": 0.1507, "step": 4100 }, { "epoch": 0.34, "learning_rate": 6.195789473684211e-06, "loss": 0.1508, "step": 4125 }, { "epoch": 0.34, "learning_rate": 6.1694736842105265e-06, "loss": 0.1587, "step": 4150 }, { "epoch": 0.34, "learning_rate": 6.143157894736843e-06, "loss": 0.1707, "step": 4175 }, { "epoch": 0.35, "learning_rate": 6.116842105263159e-06, "loss": 0.1648, "step": 4200 }, { "epoch": 0.35, "learning_rate": 6.090526315789475e-06, "loss": 0.165, "step": 4225 }, { "epoch": 0.35, "learning_rate": 6.0642105263157906e-06, "loss": 0.1892, "step": 4250 }, { "epoch": 0.35, "learning_rate": 6.0378947368421055e-06, "loss": 0.1698, "step": 4275 }, { "epoch": 0.35, "learning_rate": 6.011578947368421e-06, "loss": 0.1692, "step": 4300 }, { "epoch": 0.36, "learning_rate": 5.985263157894737e-06, "loss": 0.1504, "step": 4325 }, { "epoch": 0.36, "learning_rate": 5.958947368421053e-06, "loss": 0.1435, "step": 4350 }, { "epoch": 0.36, "learning_rate": 5.932631578947369e-06, "loss": 0.1532, "step": 4375 }, { "epoch": 0.36, "learning_rate": 5.906315789473685e-06, "loss": 0.1575, "step": 4400 }, { "epoch": 0.36, "learning_rate": 5.8800000000000005e-06, "loss": 0.163, "step": 4425 }, { "epoch": 0.37, "learning_rate": 5.853684210526316e-06, "loss": 0.1524, "step": 4450 }, { "epoch": 0.37, "learning_rate": 5.827368421052631e-06, "loss": 0.157, "step": 4475 }, { "epoch": 0.37, "learning_rate": 5.801052631578949e-06, "loss": 0.1593, "step": 4500 }, { "epoch": 0.37, "learning_rate": 5.774736842105264e-06, "loss": 0.1696, "step": 4525 }, { "epoch": 0.37, "learning_rate": 5.7484210526315795e-06, "loss": 0.1472, "step": 4550 }, { "epoch": 0.38, "learning_rate": 5.722105263157895e-06, "loss": 0.1534, "step": 4575 }, { "epoch": 0.38, "learning_rate": 5.695789473684211e-06, "loss": 0.1552, "step": 4600 }, { "epoch": 0.38, "learning_rate": 5.669473684210527e-06, "loss": 0.1661, "step": 4625 }, { "epoch": 0.38, "learning_rate": 5.643157894736843e-06, "loss": 0.1526, "step": 4650 }, { "epoch": 0.38, "learning_rate": 5.616842105263159e-06, "loss": 0.1454, "step": 4675 }, { "epoch": 0.39, "learning_rate": 5.590526315789474e-06, "loss": 0.1505, "step": 4700 }, { "epoch": 0.39, "learning_rate": 5.5642105263157894e-06, "loss": 0.1593, "step": 4725 }, { "epoch": 0.39, "learning_rate": 5.537894736842105e-06, "loss": 0.1653, "step": 4750 }, { "epoch": 0.39, "learning_rate": 5.511578947368421e-06, "loss": 0.1298, "step": 4775 }, { "epoch": 0.4, "learning_rate": 5.485263157894737e-06, "loss": 0.157, "step": 4800 }, { "epoch": 0.4, "learning_rate": 5.458947368421053e-06, "loss": 0.1549, "step": 4825 }, { "epoch": 0.4, "learning_rate": 5.432631578947369e-06, "loss": 0.1516, "step": 4850 }, { "epoch": 0.4, "learning_rate": 5.406315789473685e-06, "loss": 0.1511, "step": 4875 }, { "epoch": 0.4, "learning_rate": 5.380000000000001e-06, "loss": 0.136, "step": 4900 }, { "epoch": 0.41, "learning_rate": 5.353684210526317e-06, "loss": 0.1558, "step": 4925 }, { "epoch": 0.41, "learning_rate": 5.327368421052632e-06, "loss": 0.1546, "step": 4950 }, { "epoch": 0.41, "learning_rate": 5.301052631578948e-06, "loss": 0.1524, "step": 4975 }, { "epoch": 0.41, "learning_rate": 5.2747368421052634e-06, "loss": 0.1531, "step": 5000 }, { "epoch": 0.41, "learning_rate": 5.2505263157894735e-06, "loss": 0.1541, "step": 5025 }, { "epoch": 0.42, "learning_rate": 5.224210526315789e-06, "loss": 0.1515, "step": 5050 }, { "epoch": 0.42, "learning_rate": 5.197894736842106e-06, "loss": 0.1483, "step": 5075 }, { "epoch": 0.42, "learning_rate": 5.171578947368422e-06, "loss": 0.1495, "step": 5100 }, { "epoch": 0.42, "learning_rate": 5.145263157894738e-06, "loss": 0.1593, "step": 5125 }, { "epoch": 0.42, "learning_rate": 5.118947368421053e-06, "loss": 0.1507, "step": 5150 }, { "epoch": 0.43, "learning_rate": 5.092631578947369e-06, "loss": 0.1458, "step": 5175 }, { "epoch": 0.43, "learning_rate": 5.066315789473685e-06, "loss": 0.1426, "step": 5200 }, { "epoch": 0.43, "learning_rate": 5.04e-06, "loss": 0.1422, "step": 5225 }, { "epoch": 0.43, "learning_rate": 5.013684210526316e-06, "loss": 0.1586, "step": 5250 }, { "epoch": 0.43, "learning_rate": 4.987368421052632e-06, "loss": 0.1416, "step": 5275 }, { "epoch": 0.44, "learning_rate": 4.9610526315789475e-06, "loss": 0.1757, "step": 5300 }, { "epoch": 0.44, "learning_rate": 4.934736842105264e-06, "loss": 0.1338, "step": 5325 }, { "epoch": 0.44, "learning_rate": 4.908421052631579e-06, "loss": 0.1545, "step": 5350 }, { "epoch": 0.44, "learning_rate": 4.882105263157895e-06, "loss": 0.1494, "step": 5375 }, { "epoch": 0.44, "learning_rate": 4.855789473684211e-06, "loss": 0.1627, "step": 5400 }, { "epoch": 0.45, "learning_rate": 4.8294736842105266e-06, "loss": 0.1554, "step": 5425 }, { "epoch": 0.45, "learning_rate": 4.803157894736842e-06, "loss": 0.1487, "step": 5450 }, { "epoch": 0.45, "learning_rate": 4.776842105263158e-06, "loss": 0.1472, "step": 5475 }, { "epoch": 0.45, "learning_rate": 4.750526315789474e-06, "loss": 0.1345, "step": 5500 }, { "epoch": 0.45, "learning_rate": 4.72421052631579e-06, "loss": 0.1513, "step": 5525 }, { "epoch": 0.46, "learning_rate": 4.697894736842106e-06, "loss": 0.1376, "step": 5550 }, { "epoch": 0.46, "learning_rate": 4.6715789473684215e-06, "loss": 0.1554, "step": 5575 }, { "epoch": 0.46, "learning_rate": 4.645263157894737e-06, "loss": 0.1475, "step": 5600 }, { "epoch": 0.46, "learning_rate": 4.618947368421053e-06, "loss": 0.1449, "step": 5625 }, { "epoch": 0.46, "learning_rate": 4.592631578947369e-06, "loss": 0.128, "step": 5650 }, { "epoch": 0.47, "learning_rate": 4.566315789473685e-06, "loss": 0.1386, "step": 5675 }, { "epoch": 0.47, "learning_rate": 4.540000000000001e-06, "loss": 0.1701, "step": 5700 }, { "epoch": 0.47, "learning_rate": 4.513684210526316e-06, "loss": 0.1492, "step": 5725 }, { "epoch": 0.47, "learning_rate": 4.487368421052632e-06, "loss": 0.1476, "step": 5750 }, { "epoch": 0.48, "learning_rate": 4.461052631578948e-06, "loss": 0.146, "step": 5775 }, { "epoch": 0.48, "learning_rate": 4.434736842105263e-06, "loss": 0.1399, "step": 5800 }, { "epoch": 0.48, "learning_rate": 4.408421052631579e-06, "loss": 0.1462, "step": 5825 }, { "epoch": 0.48, "learning_rate": 4.3821052631578955e-06, "loss": 0.1369, "step": 5850 }, { "epoch": 0.48, "learning_rate": 4.355789473684211e-06, "loss": 0.1576, "step": 5875 }, { "epoch": 0.49, "learning_rate": 4.329473684210527e-06, "loss": 0.1639, "step": 5900 }, { "epoch": 0.49, "learning_rate": 4.303157894736842e-06, "loss": 0.1439, "step": 5925 }, { "epoch": 0.49, "learning_rate": 4.276842105263158e-06, "loss": 0.1548, "step": 5950 }, { "epoch": 0.49, "learning_rate": 4.250526315789474e-06, "loss": 0.1377, "step": 5975 }, { "epoch": 0.49, "learning_rate": 4.22421052631579e-06, "loss": 0.1455, "step": 6000 }, { "epoch": 0.5, "learning_rate": 4.2000000000000004e-06, "loss": 0.1581, "step": 6025 }, { "epoch": 0.5, "learning_rate": 4.173684210526316e-06, "loss": 0.1463, "step": 6050 }, { "epoch": 0.5, "learning_rate": 4.147368421052632e-06, "loss": 0.1524, "step": 6075 }, { "epoch": 0.5, "learning_rate": 4.121052631578948e-06, "loss": 0.1262, "step": 6100 }, { "epoch": 0.5, "learning_rate": 4.094736842105264e-06, "loss": 0.1492, "step": 6125 }, { "epoch": 0.51, "learning_rate": 4.0684210526315795e-06, "loss": 0.1378, "step": 6150 }, { "epoch": 0.51, "learning_rate": 4.042105263157895e-06, "loss": 0.1508, "step": 6175 }, { "epoch": 0.51, "learning_rate": 4.01578947368421e-06, "loss": 0.1329, "step": 6200 }, { "epoch": 0.51, "learning_rate": 3.989473684210526e-06, "loss": 0.1342, "step": 6225 }, { "epoch": 0.51, "learning_rate": 3.963157894736843e-06, "loss": 0.1336, "step": 6250 }, { "epoch": 0.52, "learning_rate": 3.936842105263159e-06, "loss": 0.1259, "step": 6275 }, { "epoch": 0.52, "learning_rate": 3.9105263157894744e-06, "loss": 0.1402, "step": 6300 }, { "epoch": 0.52, "learning_rate": 3.884210526315789e-06, "loss": 0.1361, "step": 6325 }, { "epoch": 0.52, "learning_rate": 3.857894736842105e-06, "loss": 0.149, "step": 6350 }, { "epoch": 0.52, "learning_rate": 3.831578947368421e-06, "loss": 0.1471, "step": 6375 }, { "epoch": 0.53, "learning_rate": 3.805263157894737e-06, "loss": 0.1264, "step": 6400 }, { "epoch": 0.53, "learning_rate": 3.778947368421053e-06, "loss": 0.1329, "step": 6425 }, { "epoch": 0.53, "learning_rate": 3.752631578947369e-06, "loss": 0.1643, "step": 6450 }, { "epoch": 0.53, "learning_rate": 3.7263157894736848e-06, "loss": 0.1489, "step": 6475 }, { "epoch": 0.53, "learning_rate": 3.7e-06, "loss": 0.1234, "step": 6500 }, { "epoch": 0.54, "learning_rate": 3.673684210526316e-06, "loss": 0.1318, "step": 6525 }, { "epoch": 0.54, "learning_rate": 3.6473684210526318e-06, "loss": 0.1481, "step": 6550 }, { "epoch": 0.54, "learning_rate": 3.621052631578948e-06, "loss": 0.1454, "step": 6575 }, { "epoch": 0.54, "learning_rate": 3.5947368421052634e-06, "loss": 0.1493, "step": 6600 }, { "epoch": 0.55, "learning_rate": 3.5684210526315792e-06, "loss": 0.1371, "step": 6625 }, { "epoch": 0.55, "learning_rate": 3.542105263157895e-06, "loss": 0.1435, "step": 6650 }, { "epoch": 0.55, "learning_rate": 3.515789473684211e-06, "loss": 0.1475, "step": 6675 }, { "epoch": 0.55, "learning_rate": 3.4894736842105263e-06, "loss": 0.1509, "step": 6700 }, { "epoch": 0.55, "learning_rate": 3.463157894736842e-06, "loss": 0.1512, "step": 6725 }, { "epoch": 0.56, "learning_rate": 3.4368421052631583e-06, "loss": 0.1376, "step": 6750 }, { "epoch": 0.56, "learning_rate": 3.410526315789474e-06, "loss": 0.1333, "step": 6775 }, { "epoch": 0.56, "learning_rate": 3.38421052631579e-06, "loss": 0.1355, "step": 6800 }, { "epoch": 0.56, "learning_rate": 3.3578947368421054e-06, "loss": 0.1577, "step": 6825 }, { "epoch": 0.56, "learning_rate": 3.331578947368421e-06, "loss": 0.1315, "step": 6850 }, { "epoch": 0.57, "learning_rate": 3.305263157894737e-06, "loss": 0.1328, "step": 6875 }, { "epoch": 0.57, "learning_rate": 3.278947368421053e-06, "loss": 0.1445, "step": 6900 }, { "epoch": 0.57, "learning_rate": 3.252631578947369e-06, "loss": 0.1373, "step": 6925 }, { "epoch": 0.57, "learning_rate": 3.2263157894736845e-06, "loss": 0.1347, "step": 6950 }, { "epoch": 0.57, "learning_rate": 3.2000000000000003e-06, "loss": 0.1323, "step": 6975 }, { "epoch": 0.58, "learning_rate": 3.173684210526316e-06, "loss": 0.1406, "step": 7000 }, { "epoch": 0.58, "learning_rate": 3.1494736842105266e-06, "loss": 0.1225, "step": 7025 }, { "epoch": 0.58, "learning_rate": 3.1231578947368424e-06, "loss": 0.1459, "step": 7050 }, { "epoch": 0.58, "learning_rate": 3.096842105263158e-06, "loss": 0.1315, "step": 7075 }, { "epoch": 0.58, "learning_rate": 3.0705263157894736e-06, "loss": 0.1233, "step": 7100 }, { "epoch": 0.59, "learning_rate": 3.0442105263157894e-06, "loss": 0.1328, "step": 7125 }, { "epoch": 0.59, "learning_rate": 3.0178947368421057e-06, "loss": 0.1374, "step": 7150 }, { "epoch": 0.59, "learning_rate": 2.9915789473684215e-06, "loss": 0.1323, "step": 7175 }, { "epoch": 0.59, "learning_rate": 2.9652631578947373e-06, "loss": 0.1576, "step": 7200 }, { "epoch": 0.59, "learning_rate": 2.9389473684210527e-06, "loss": 0.1365, "step": 7225 }, { "epoch": 0.6, "learning_rate": 2.9126315789473685e-06, "loss": 0.1519, "step": 7250 }, { "epoch": 0.6, "learning_rate": 2.8863157894736843e-06, "loss": 0.1446, "step": 7275 }, { "epoch": 0.6, "learning_rate": 2.86e-06, "loss": 0.1529, "step": 7300 }, { "epoch": 0.6, "learning_rate": 2.8336842105263164e-06, "loss": 0.1426, "step": 7325 }, { "epoch": 0.6, "learning_rate": 2.8073684210526318e-06, "loss": 0.1352, "step": 7350 }, { "epoch": 0.61, "learning_rate": 2.7810526315789476e-06, "loss": 0.1391, "step": 7375 }, { "epoch": 0.61, "learning_rate": 2.7547368421052634e-06, "loss": 0.1369, "step": 7400 }, { "epoch": 0.61, "learning_rate": 2.7284210526315792e-06, "loss": 0.1361, "step": 7425 }, { "epoch": 0.61, "learning_rate": 2.7021052631578946e-06, "loss": 0.1319, "step": 7450 }, { "epoch": 0.62, "learning_rate": 2.6757894736842105e-06, "loss": 0.1236, "step": 7475 }, { "epoch": 0.62, "learning_rate": 2.6494736842105267e-06, "loss": 0.1349, "step": 7500 }, { "epoch": 0.62, "learning_rate": 2.6231578947368425e-06, "loss": 0.1438, "step": 7525 }, { "epoch": 0.62, "learning_rate": 2.5968421052631583e-06, "loss": 0.1203, "step": 7550 }, { "epoch": 0.62, "learning_rate": 2.5705263157894737e-06, "loss": 0.1335, "step": 7575 }, { "epoch": 0.63, "learning_rate": 2.5442105263157895e-06, "loss": 0.1609, "step": 7600 }, { "epoch": 0.63, "learning_rate": 2.5178947368421054e-06, "loss": 0.1199, "step": 7625 }, { "epoch": 0.63, "learning_rate": 2.491578947368421e-06, "loss": 0.135, "step": 7650 }, { "epoch": 0.63, "learning_rate": 2.465263157894737e-06, "loss": 0.1355, "step": 7675 }, { "epoch": 0.63, "learning_rate": 2.438947368421053e-06, "loss": 0.1429, "step": 7700 }, { "epoch": 0.64, "learning_rate": 2.4126315789473686e-06, "loss": 0.1199, "step": 7725 }, { "epoch": 0.64, "learning_rate": 2.3863157894736845e-06, "loss": 0.1185, "step": 7750 }, { "epoch": 0.64, "learning_rate": 2.3600000000000003e-06, "loss": 0.158, "step": 7775 }, { "epoch": 0.64, "learning_rate": 2.333684210526316e-06, "loss": 0.1367, "step": 7800 }, { "epoch": 0.64, "learning_rate": 2.307368421052632e-06, "loss": 0.1454, "step": 7825 }, { "epoch": 0.65, "learning_rate": 2.2810526315789473e-06, "loss": 0.1239, "step": 7850 }, { "epoch": 0.65, "learning_rate": 2.2547368421052635e-06, "loss": 0.116, "step": 7875 }, { "epoch": 0.65, "learning_rate": 2.228421052631579e-06, "loss": 0.1256, "step": 7900 }, { "epoch": 0.65, "learning_rate": 2.2021052631578948e-06, "loss": 0.1233, "step": 7925 }, { "epoch": 0.65, "learning_rate": 2.175789473684211e-06, "loss": 0.1435, "step": 7950 }, { "epoch": 0.66, "learning_rate": 2.1494736842105264e-06, "loss": 0.126, "step": 7975 }, { "epoch": 0.66, "learning_rate": 2.1231578947368422e-06, "loss": 0.1343, "step": 8000 }, { "epoch": 0.66, "learning_rate": 2.098947368421053e-06, "loss": 0.1192, "step": 8025 }, { "epoch": 0.66, "learning_rate": 2.0726315789473685e-06, "loss": 0.1582, "step": 8050 }, { "epoch": 0.66, "learning_rate": 2.0463157894736843e-06, "loss": 0.1336, "step": 8075 }, { "epoch": 0.67, "learning_rate": 2.02e-06, "loss": 0.133, "step": 8100 }, { "epoch": 0.67, "learning_rate": 1.993684210526316e-06, "loss": 0.1092, "step": 8125 }, { "epoch": 0.67, "learning_rate": 1.9673684210526318e-06, "loss": 0.1518, "step": 8150 }, { "epoch": 0.67, "learning_rate": 1.9410526315789476e-06, "loss": 0.1223, "step": 8175 }, { "epoch": 0.67, "learning_rate": 1.9147368421052634e-06, "loss": 0.138, "step": 8200 }, { "epoch": 0.68, "learning_rate": 1.888421052631579e-06, "loss": 0.1348, "step": 8225 }, { "epoch": 0.68, "learning_rate": 1.8621052631578948e-06, "loss": 0.1182, "step": 8250 }, { "epoch": 0.68, "learning_rate": 1.8357894736842109e-06, "loss": 0.1305, "step": 8275 }, { "epoch": 0.68, "learning_rate": 1.8094736842105265e-06, "loss": 0.1389, "step": 8300 }, { "epoch": 0.69, "learning_rate": 1.7831578947368423e-06, "loss": 0.1275, "step": 8325 }, { "epoch": 0.69, "learning_rate": 1.756842105263158e-06, "loss": 0.1443, "step": 8350 }, { "epoch": 0.69, "learning_rate": 1.730526315789474e-06, "loss": 0.1134, "step": 8375 }, { "epoch": 0.69, "learning_rate": 1.7042105263157895e-06, "loss": 0.1122, "step": 8400 }, { "epoch": 0.69, "learning_rate": 1.6778947368421054e-06, "loss": 0.1451, "step": 8425 }, { "epoch": 0.7, "learning_rate": 1.6515789473684212e-06, "loss": 0.1204, "step": 8450 }, { "epoch": 0.7, "learning_rate": 1.625263157894737e-06, "loss": 0.121, "step": 8475 }, { "epoch": 0.7, "learning_rate": 1.5989473684210526e-06, "loss": 0.1289, "step": 8500 }, { "epoch": 0.7, "learning_rate": 1.5726315789473686e-06, "loss": 0.1388, "step": 8525 }, { "epoch": 0.7, "learning_rate": 1.5463157894736845e-06, "loss": 0.1316, "step": 8550 }, { "epoch": 0.71, "learning_rate": 1.52e-06, "loss": 0.1396, "step": 8575 }, { "epoch": 0.71, "learning_rate": 1.4936842105263159e-06, "loss": 0.1206, "step": 8600 }, { "epoch": 0.71, "learning_rate": 1.4673684210526317e-06, "loss": 0.1362, "step": 8625 }, { "epoch": 0.71, "learning_rate": 1.4410526315789475e-06, "loss": 0.1213, "step": 8650 }, { "epoch": 0.71, "learning_rate": 1.4147368421052631e-06, "loss": 0.1398, "step": 8675 }, { "epoch": 0.72, "learning_rate": 1.3884210526315792e-06, "loss": 0.1446, "step": 8700 }, { "epoch": 0.72, "learning_rate": 1.362105263157895e-06, "loss": 0.1098, "step": 8725 }, { "epoch": 0.72, "learning_rate": 1.3357894736842106e-06, "loss": 0.1352, "step": 8750 }, { "epoch": 0.72, "learning_rate": 1.3094736842105262e-06, "loss": 0.1295, "step": 8775 }, { "epoch": 0.72, "learning_rate": 1.2831578947368422e-06, "loss": 0.1309, "step": 8800 }, { "epoch": 0.73, "learning_rate": 1.256842105263158e-06, "loss": 0.1492, "step": 8825 }, { "epoch": 0.73, "learning_rate": 1.2305263157894739e-06, "loss": 0.1489, "step": 8850 }, { "epoch": 0.73, "learning_rate": 1.2042105263157895e-06, "loss": 0.1187, "step": 8875 }, { "epoch": 0.73, "learning_rate": 1.1778947368421053e-06, "loss": 0.144, "step": 8900 }, { "epoch": 0.73, "learning_rate": 1.1515789473684213e-06, "loss": 0.1201, "step": 8925 }, { "epoch": 0.74, "learning_rate": 1.125263157894737e-06, "loss": 0.11, "step": 8950 }, { "epoch": 0.74, "learning_rate": 1.0989473684210527e-06, "loss": 0.1476, "step": 8975 }, { "epoch": 0.74, "learning_rate": 1.0726315789473685e-06, "loss": 0.1462, "step": 9000 }, { "epoch": 0.74, "learning_rate": 1.048421052631579e-06, "loss": 0.1503, "step": 9025 }, { "epoch": 0.74, "learning_rate": 1.0221052631578948e-06, "loss": 0.1338, "step": 9050 }, { "epoch": 0.75, "learning_rate": 9.957894736842107e-07, "loss": 0.1339, "step": 9075 }, { "epoch": 0.75, "learning_rate": 9.694736842105265e-07, "loss": 0.1322, "step": 9100 }, { "epoch": 0.75, "learning_rate": 9.431578947368422e-07, "loss": 0.1316, "step": 9125 }, { "epoch": 0.75, "learning_rate": 9.168421052631579e-07, "loss": 0.1234, "step": 9150 }, { "epoch": 0.76, "learning_rate": 8.905263157894737e-07, "loss": 0.1297, "step": 9175 }, { "epoch": 0.76, "learning_rate": 8.642105263157896e-07, "loss": 0.1218, "step": 9200 }, { "epoch": 0.76, "learning_rate": 8.378947368421054e-07, "loss": 0.124, "step": 9225 }, { "epoch": 0.76, "learning_rate": 8.115789473684212e-07, "loss": 0.1271, "step": 9250 }, { "epoch": 0.76, "learning_rate": 7.852631578947369e-07, "loss": 0.1196, "step": 9275 }, { "epoch": 0.77, "learning_rate": 7.589473684210527e-07, "loss": 0.1296, "step": 9300 }, { "epoch": 0.77, "learning_rate": 7.326315789473684e-07, "loss": 0.1182, "step": 9325 }, { "epoch": 0.77, "learning_rate": 7.063157894736842e-07, "loss": 0.1213, "step": 9350 }, { "epoch": 0.77, "learning_rate": 6.800000000000001e-07, "loss": 0.1302, "step": 9375 }, { "epoch": 0.77, "learning_rate": 6.536842105263158e-07, "loss": 0.133, "step": 9400 }, { "epoch": 0.78, "learning_rate": 6.273684210526317e-07, "loss": 0.1202, "step": 9425 }, { "epoch": 0.78, "learning_rate": 6.010526315789474e-07, "loss": 0.1293, "step": 9450 }, { "epoch": 0.78, "learning_rate": 5.747368421052632e-07, "loss": 0.1416, "step": 9475 }, { "epoch": 0.78, "learning_rate": 5.484210526315789e-07, "loss": 0.1398, "step": 9500 }, { "epoch": 0.78, "learning_rate": 5.221052631578948e-07, "loss": 0.1314, "step": 9525 }, { "epoch": 0.79, "learning_rate": 4.957894736842106e-07, "loss": 0.1301, "step": 9550 }, { "epoch": 0.79, "learning_rate": 4.694736842105264e-07, "loss": 0.1242, "step": 9575 }, { "epoch": 0.79, "learning_rate": 4.4315789473684216e-07, "loss": 0.1194, "step": 9600 }, { "epoch": 0.79, "learning_rate": 4.168421052631579e-07, "loss": 0.1313, "step": 9625 }, { "epoch": 0.79, "learning_rate": 3.905263157894737e-07, "loss": 0.1379, "step": 9650 }, { "epoch": 0.8, "learning_rate": 3.6421052631578945e-07, "loss": 0.1469, "step": 9675 }, { "epoch": 0.8, "learning_rate": 3.378947368421053e-07, "loss": 0.1472, "step": 9700 }, { "epoch": 0.8, "learning_rate": 3.115789473684211e-07, "loss": 0.1312, "step": 9725 }, { "epoch": 0.8, "learning_rate": 2.8526315789473686e-07, "loss": 0.1152, "step": 9750 }, { "epoch": 0.8, "learning_rate": 2.589473684210526e-07, "loss": 0.1024, "step": 9775 }, { "epoch": 0.81, "learning_rate": 2.3263157894736844e-07, "loss": 0.1194, "step": 9800 }, { "epoch": 0.81, "learning_rate": 2.0631578947368423e-07, "loss": 0.1304, "step": 9825 }, { "epoch": 0.81, "learning_rate": 1.8e-07, "loss": 0.1289, "step": 9850 }, { "epoch": 0.81, "learning_rate": 1.536842105263158e-07, "loss": 0.1305, "step": 9875 }, { "epoch": 0.81, "learning_rate": 1.2736842105263158e-07, "loss": 0.1182, "step": 9900 }, { "epoch": 0.82, "learning_rate": 1.0105263157894737e-07, "loss": 0.11, "step": 9925 }, { "epoch": 0.82, "learning_rate": 7.473684210526317e-08, "loss": 0.1196, "step": 9950 }, { "epoch": 0.82, "learning_rate": 4.842105263157895e-08, "loss": 0.1286, "step": 9975 }, { "epoch": 0.82, "learning_rate": 2.2105263157894736e-08, "loss": 0.1367, "step": 10000 }, { "epoch": 0.82, "step": 10000, "total_flos": 5.4359970325966356e+20, "train_loss": 0.16558935852050782, "train_runtime": 67809.1634, "train_samples_per_second": 2.36, "train_steps_per_second": 0.147 } ], "logging_steps": 25, "max_steps": 10000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "total_flos": 5.4359970325966356e+20, "train_batch_size": 16, "trial_name": null, "trial_params": null }