{ "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": 4.82046852530342e-06, "loss": 0.5469, "step": 25 }, { "epoch": 0.0, "learning_rate": 6.125346006511307e-06, "loss": 0.4394, "step": 50 }, { "epoch": 0.01, "learning_rate": 6.836304357032582e-06, "loss": 0.4163, "step": 75 }, { "epoch": 0.01, "learning_rate": 7.327697610983243e-06, "loss": 0.4264, "step": 100 }, { "epoch": 0.01, "learning_rate": 7.703610053862492e-06, "loss": 0.3874, "step": 125 }, { "epoch": 0.01, "learning_rate": 8.008121612180345e-06, "loss": 0.3768, "step": 150 }, { "epoch": 0.01, "learning_rate": 8.26407450914592e-06, "loss": 0.3651, "step": 175 }, { "epoch": 0.02, "learning_rate": 8.484846469888412e-06, "loss": 0.3504, "step": 200 }, { "epoch": 0.02, "learning_rate": 8.678950403520593e-06, "loss": 0.3711, "step": 225 }, { "epoch": 0.02, "learning_rate": 8.852140188761744e-06, "loss": 0.318, "step": 250 }, { "epoch": 0.02, "learning_rate": 9.00848753507038e-06, "loss": 0.3269, "step": 275 }, { "epoch": 0.02, "learning_rate": 9.150979862726452e-06, "loss": 0.3084, "step": 300 }, { "epoch": 0.03, "learning_rate": 9.281874101213678e-06, "loss": 0.3411, "step": 325 }, { "epoch": 0.03, "learning_rate": 9.402917005361869e-06, "loss": 0.3206, "step": 350 }, { "epoch": 0.03, "learning_rate": 9.51548820454122e-06, "loss": 0.3215, "step": 375 }, { "epoch": 0.03, "learning_rate": 9.620696382156558e-06, "loss": 0.3363, "step": 400 }, { "epoch": 0.03, "learning_rate": 9.719445885591654e-06, "loss": 0.3179, "step": 425 }, { "epoch": 0.04, "learning_rate": 9.812484046603779e-06, "loss": 0.3186, "step": 450 }, { "epoch": 0.04, "learning_rate": 9.900435550016748e-06, "loss": 0.3006, "step": 475 }, { "epoch": 0.04, "learning_rate": 9.98382788472848e-06, "loss": 0.2693, "step": 500 }, { "epoch": 0.04, "learning_rate": 9.980000000000001e-06, "loss": 0.2941, "step": 525 }, { "epoch": 0.05, "learning_rate": 9.953684210526316e-06, "loss": 0.2931, "step": 550 }, { "epoch": 0.05, "learning_rate": 9.927368421052633e-06, "loss": 0.2925, "step": 575 }, { "epoch": 0.05, "learning_rate": 9.901052631578948e-06, "loss": 0.2543, "step": 600 }, { "epoch": 0.05, "learning_rate": 9.874736842105264e-06, "loss": 0.2909, "step": 625 }, { "epoch": 0.05, "learning_rate": 9.84842105263158e-06, "loss": 0.2799, "step": 650 }, { "epoch": 0.06, "learning_rate": 9.822105263157894e-06, "loss": 0.2774, "step": 675 }, { "epoch": 0.06, "learning_rate": 9.795789473684213e-06, "loss": 0.295, "step": 700 }, { "epoch": 0.06, "learning_rate": 9.769473684210528e-06, "loss": 0.2689, "step": 725 }, { "epoch": 0.06, "learning_rate": 9.743157894736843e-06, "loss": 0.2659, "step": 750 }, { "epoch": 0.06, "learning_rate": 9.71684210526316e-06, "loss": 0.295, "step": 775 }, { "epoch": 0.07, "learning_rate": 9.690526315789474e-06, "loss": 0.2693, "step": 800 }, { "epoch": 0.07, "learning_rate": 9.66421052631579e-06, "loss": 0.242, "step": 825 }, { "epoch": 0.07, "learning_rate": 9.637894736842106e-06, "loss": 0.2385, "step": 850 }, { "epoch": 0.07, "learning_rate": 9.611578947368422e-06, "loss": 0.2691, "step": 875 }, { "epoch": 0.07, "learning_rate": 9.585263157894737e-06, "loss": 0.2681, "step": 900 }, { "epoch": 0.08, "learning_rate": 9.558947368421052e-06, "loss": 0.2691, "step": 925 }, { "epoch": 0.08, "learning_rate": 9.532631578947369e-06, "loss": 0.2578, "step": 950 }, { "epoch": 0.08, "learning_rate": 9.506315789473684e-06, "loss": 0.2689, "step": 975 }, { "epoch": 0.08, "learning_rate": 9.48e-06, "loss": 0.2727, "step": 1000 }, { "epoch": 0.08, "learning_rate": 9.453684210526316e-06, "loss": 0.2546, "step": 1025 }, { "epoch": 0.09, "learning_rate": 9.427368421052632e-06, "loss": 0.2599, "step": 1050 }, { "epoch": 0.09, "learning_rate": 9.401052631578949e-06, "loss": 0.2273, "step": 1075 }, { "epoch": 0.09, "learning_rate": 9.374736842105264e-06, "loss": 0.2298, "step": 1100 }, { "epoch": 0.09, "learning_rate": 9.34842105263158e-06, "loss": 0.2264, "step": 1125 }, { "epoch": 0.09, "learning_rate": 9.322105263157896e-06, "loss": 0.231, "step": 1150 }, { "epoch": 0.1, "learning_rate": 9.29578947368421e-06, "loss": 0.2432, "step": 1175 }, { "epoch": 0.1, "learning_rate": 9.269473684210527e-06, "loss": 0.247, "step": 1200 }, { "epoch": 0.1, "learning_rate": 9.243157894736842e-06, "loss": 0.2326, "step": 1225 }, { "epoch": 0.1, "learning_rate": 9.216842105263159e-06, "loss": 0.2482, "step": 1250 }, { "epoch": 0.1, "learning_rate": 9.190526315789474e-06, "loss": 0.2336, "step": 1275 }, { "epoch": 0.11, "learning_rate": 9.16421052631579e-06, "loss": 0.2762, "step": 1300 }, { "epoch": 0.11, "learning_rate": 9.137894736842106e-06, "loss": 0.2373, "step": 1325 }, { "epoch": 0.11, "learning_rate": 9.11157894736842e-06, "loss": 0.2476, "step": 1350 }, { "epoch": 0.11, "learning_rate": 9.085263157894739e-06, "loss": 0.2279, "step": 1375 }, { "epoch": 0.12, "learning_rate": 9.058947368421054e-06, "loss": 0.2435, "step": 1400 }, { "epoch": 0.12, "learning_rate": 9.032631578947369e-06, "loss": 0.2171, "step": 1425 }, { "epoch": 0.12, "learning_rate": 9.006315789473685e-06, "loss": 0.2227, "step": 1450 }, { "epoch": 0.12, "learning_rate": 8.98e-06, "loss": 0.2297, "step": 1475 }, { "epoch": 0.12, "learning_rate": 8.953684210526317e-06, "loss": 0.2338, "step": 1500 }, { "epoch": 0.13, "learning_rate": 8.927368421052632e-06, "loss": 0.2433, "step": 1525 }, { "epoch": 0.13, "learning_rate": 8.901052631578949e-06, "loss": 0.218, "step": 1550 }, { "epoch": 0.13, "learning_rate": 8.874736842105264e-06, "loss": 0.2204, "step": 1575 }, { "epoch": 0.13, "learning_rate": 8.848421052631579e-06, "loss": 0.2382, "step": 1600 }, { "epoch": 0.13, "learning_rate": 8.822105263157895e-06, "loss": 0.2299, "step": 1625 }, { "epoch": 0.14, "learning_rate": 8.79578947368421e-06, "loss": 0.2461, "step": 1650 }, { "epoch": 0.14, "learning_rate": 8.769473684210527e-06, "loss": 0.2114, "step": 1675 }, { "epoch": 0.14, "learning_rate": 8.743157894736842e-06, "loss": 0.2126, "step": 1700 }, { "epoch": 0.14, "learning_rate": 8.716842105263159e-06, "loss": 0.2323, "step": 1725 }, { "epoch": 0.14, "learning_rate": 8.690526315789475e-06, "loss": 0.2217, "step": 1750 }, { "epoch": 0.15, "learning_rate": 8.66421052631579e-06, "loss": 0.2226, "step": 1775 }, { "epoch": 0.15, "learning_rate": 8.637894736842107e-06, "loss": 0.2191, "step": 1800 }, { "epoch": 0.15, "learning_rate": 8.611578947368422e-06, "loss": 0.212, "step": 1825 }, { "epoch": 0.15, "learning_rate": 8.585263157894737e-06, "loss": 0.2129, "step": 1850 }, { "epoch": 0.15, "learning_rate": 8.558947368421054e-06, "loss": 0.2331, "step": 1875 }, { "epoch": 0.16, "learning_rate": 8.532631578947368e-06, "loss": 0.2119, "step": 1900 }, { "epoch": 0.16, "learning_rate": 8.506315789473685e-06, "loss": 0.2111, "step": 1925 }, { "epoch": 0.16, "learning_rate": 8.48e-06, "loss": 0.2231, "step": 1950 }, { "epoch": 0.16, "learning_rate": 8.453684210526317e-06, "loss": 0.2194, "step": 1975 }, { "epoch": 0.16, "learning_rate": 8.427368421052632e-06, "loss": 0.2099, "step": 2000 }, { "epoch": 0.17, "learning_rate": 8.401052631578947e-06, "loss": 0.2141, "step": 2025 }, { "epoch": 0.17, "learning_rate": 8.374736842105265e-06, "loss": 0.217, "step": 2050 }, { "epoch": 0.17, "learning_rate": 8.34842105263158e-06, "loss": 0.2309, "step": 2075 }, { "epoch": 0.17, "learning_rate": 8.322105263157895e-06, "loss": 0.2121, "step": 2100 }, { "epoch": 0.17, "learning_rate": 8.295789473684212e-06, "loss": 0.2191, "step": 2125 }, { "epoch": 0.18, "learning_rate": 8.269473684210527e-06, "loss": 0.209, "step": 2150 }, { "epoch": 0.18, "learning_rate": 8.243157894736843e-06, "loss": 0.2211, "step": 2175 }, { "epoch": 0.18, "learning_rate": 8.216842105263158e-06, "loss": 0.2301, "step": 2200 }, { "epoch": 0.18, "learning_rate": 8.190526315789475e-06, "loss": 0.1991, "step": 2225 }, { "epoch": 0.19, "learning_rate": 8.16421052631579e-06, "loss": 0.1973, "step": 2250 }, { "epoch": 0.19, "learning_rate": 8.137894736842105e-06, "loss": 0.2089, "step": 2275 }, { "epoch": 0.19, "learning_rate": 8.111578947368422e-06, "loss": 0.1904, "step": 2300 }, { "epoch": 0.19, "learning_rate": 8.085263157894737e-06, "loss": 0.1915, "step": 2325 }, { "epoch": 0.19, "learning_rate": 8.058947368421053e-06, "loss": 0.1758, "step": 2350 }, { "epoch": 0.2, "learning_rate": 8.032631578947368e-06, "loss": 0.1883, "step": 2375 }, { "epoch": 0.2, "learning_rate": 8.006315789473685e-06, "loss": 0.23, "step": 2400 }, { "epoch": 0.2, "learning_rate": 7.980000000000002e-06, "loss": 0.2007, "step": 2425 }, { "epoch": 0.2, "learning_rate": 7.953684210526316e-06, "loss": 0.2222, "step": 2450 }, { "epoch": 0.2, "learning_rate": 7.927368421052633e-06, "loss": 0.1969, "step": 2475 }, { "epoch": 0.21, "learning_rate": 7.901052631578948e-06, "loss": 0.2097, "step": 2500 }, { "epoch": 0.21, "learning_rate": 7.874736842105263e-06, "loss": 0.198, "step": 2525 }, { "epoch": 0.21, "learning_rate": 7.84842105263158e-06, "loss": 0.2219, "step": 2550 }, { "epoch": 0.21, "learning_rate": 7.822105263157895e-06, "loss": 0.208, "step": 2575 }, { "epoch": 0.21, "learning_rate": 7.795789473684211e-06, "loss": 0.1917, "step": 2600 }, { "epoch": 0.22, "learning_rate": 7.769473684210526e-06, "loss": 0.2206, "step": 2625 }, { "epoch": 0.22, "learning_rate": 7.743157894736843e-06, "loss": 0.2014, "step": 2650 }, { "epoch": 0.22, "learning_rate": 7.716842105263158e-06, "loss": 0.2113, "step": 2675 }, { "epoch": 0.22, "learning_rate": 7.690526315789475e-06, "loss": 0.1928, "step": 2700 }, { "epoch": 0.22, "learning_rate": 7.664210526315791e-06, "loss": 0.2032, "step": 2725 }, { "epoch": 0.23, "learning_rate": 7.637894736842106e-06, "loss": 0.1708, "step": 2750 }, { "epoch": 0.23, "learning_rate": 7.611578947368422e-06, "loss": 0.1783, "step": 2775 }, { "epoch": 0.23, "learning_rate": 7.585263157894738e-06, "loss": 0.1862, "step": 2800 }, { "epoch": 0.23, "learning_rate": 7.558947368421054e-06, "loss": 0.2024, "step": 2825 }, { "epoch": 0.23, "learning_rate": 7.53263157894737e-06, "loss": 0.1881, "step": 2850 }, { "epoch": 0.24, "learning_rate": 7.5063157894736846e-06, "loss": 0.1982, "step": 2875 }, { "epoch": 0.24, "learning_rate": 7.48e-06, "loss": 0.196, "step": 2900 }, { "epoch": 0.24, "learning_rate": 7.453684210526316e-06, "loss": 0.1881, "step": 2925 }, { "epoch": 0.24, "learning_rate": 7.427368421052632e-06, "loss": 0.1852, "step": 2950 }, { "epoch": 0.24, "learning_rate": 7.401052631578948e-06, "loss": 0.2046, "step": 2975 }, { "epoch": 0.25, "learning_rate": 7.374736842105264e-06, "loss": 0.1943, "step": 3000 }, { "epoch": 0.25, "learning_rate": 7.3484210526315795e-06, "loss": 0.1893, "step": 3025 }, { "epoch": 0.25, "learning_rate": 7.3221052631578944e-06, "loss": 0.2071, "step": 3050 }, { "epoch": 0.25, "learning_rate": 7.295789473684212e-06, "loss": 0.2122, "step": 3075 }, { "epoch": 0.26, "learning_rate": 7.269473684210527e-06, "loss": 0.1924, "step": 3100 }, { "epoch": 0.26, "learning_rate": 7.243157894736843e-06, "loss": 0.165, "step": 3125 }, { "epoch": 0.26, "learning_rate": 7.2168421052631586e-06, "loss": 0.1923, "step": 3150 }, { "epoch": 0.26, "learning_rate": 7.190526315789474e-06, "loss": 0.1806, "step": 3175 }, { "epoch": 0.26, "learning_rate": 7.16421052631579e-06, "loss": 0.1812, "step": 3200 }, { "epoch": 0.27, "learning_rate": 7.137894736842106e-06, "loss": 0.2111, "step": 3225 }, { "epoch": 0.27, "learning_rate": 7.111578947368422e-06, "loss": 0.1902, "step": 3250 }, { "epoch": 0.27, "learning_rate": 7.085263157894738e-06, "loss": 0.1828, "step": 3275 }, { "epoch": 0.27, "learning_rate": 7.058947368421053e-06, "loss": 0.1958, "step": 3300 }, { "epoch": 0.27, "learning_rate": 7.0326315789473684e-06, "loss": 0.1899, "step": 3325 }, { "epoch": 0.28, "learning_rate": 7.006315789473684e-06, "loss": 0.1821, "step": 3350 }, { "epoch": 0.28, "learning_rate": 6.98e-06, "loss": 0.2074, "step": 3375 }, { "epoch": 0.28, "learning_rate": 6.953684210526316e-06, "loss": 0.1887, "step": 3400 }, { "epoch": 0.28, "learning_rate": 6.9273684210526326e-06, "loss": 0.1778, "step": 3425 }, { "epoch": 0.28, "learning_rate": 6.901052631578948e-06, "loss": 0.178, "step": 3450 }, { "epoch": 0.29, "learning_rate": 6.874736842105264e-06, "loss": 0.1766, "step": 3475 }, { "epoch": 0.29, "learning_rate": 6.84842105263158e-06, "loss": 0.1753, "step": 3500 }, { "epoch": 0.29, "learning_rate": 6.822105263157896e-06, "loss": 0.1853, "step": 3525 }, { "epoch": 0.29, "learning_rate": 6.795789473684211e-06, "loss": 0.1782, "step": 3550 }, { "epoch": 0.29, "learning_rate": 6.769473684210527e-06, "loss": 0.1753, "step": 3575 }, { "epoch": 0.3, "learning_rate": 6.7431578947368425e-06, "loss": 0.1934, "step": 3600 }, { "epoch": 0.3, "learning_rate": 6.716842105263158e-06, "loss": 0.1882, "step": 3625 }, { "epoch": 0.3, "learning_rate": 6.690526315789474e-06, "loss": 0.2041, "step": 3650 }, { "epoch": 0.3, "learning_rate": 6.66421052631579e-06, "loss": 0.1924, "step": 3675 }, { "epoch": 0.3, "learning_rate": 6.637894736842106e-06, "loss": 0.1808, "step": 3700 }, { "epoch": 0.31, "learning_rate": 6.611578947368421e-06, "loss": 0.1902, "step": 3725 }, { "epoch": 0.31, "learning_rate": 6.585263157894738e-06, "loss": 0.1834, "step": 3750 }, { "epoch": 0.31, "learning_rate": 6.558947368421054e-06, "loss": 0.1919, "step": 3775 }, { "epoch": 0.31, "learning_rate": 6.532631578947369e-06, "loss": 0.1861, "step": 3800 }, { "epoch": 0.31, "learning_rate": 6.506315789473685e-06, "loss": 0.1678, "step": 3825 }, { "epoch": 0.32, "learning_rate": 6.480000000000001e-06, "loss": 0.1784, "step": 3850 }, { "epoch": 0.32, "learning_rate": 6.4536842105263165e-06, "loss": 0.1737, "step": 3875 }, { "epoch": 0.32, "learning_rate": 6.427368421052632e-06, "loss": 0.1793, "step": 3900 }, { "epoch": 0.32, "learning_rate": 6.401052631578948e-06, "loss": 0.1797, "step": 3925 }, { "epoch": 0.33, "learning_rate": 6.374736842105264e-06, "loss": 0.1787, "step": 3950 }, { "epoch": 0.33, "learning_rate": 6.348421052631579e-06, "loss": 0.1534, "step": 3975 }, { "epoch": 0.33, "learning_rate": 6.322105263157895e-06, "loss": 0.1612, "step": 4000 }, { "epoch": 0.33, "learning_rate": 6.2978947368421064e-06, "loss": 0.1924, "step": 4025 }, { "epoch": 0.33, "learning_rate": 6.271578947368422e-06, "loss": 0.1692, "step": 4050 }, { "epoch": 0.34, "learning_rate": 6.245263157894737e-06, "loss": 0.1549, "step": 4075 }, { "epoch": 0.34, "learning_rate": 6.218947368421053e-06, "loss": 0.1908, "step": 4100 }, { "epoch": 0.34, "learning_rate": 6.192631578947369e-06, "loss": 0.1811, "step": 4125 }, { "epoch": 0.34, "learning_rate": 6.166315789473685e-06, "loss": 0.1903, "step": 4150 }, { "epoch": 0.34, "learning_rate": 6.1400000000000005e-06, "loss": 0.1854, "step": 4175 }, { "epoch": 0.35, "learning_rate": 6.113684210526316e-06, "loss": 0.1732, "step": 4200 }, { "epoch": 0.35, "learning_rate": 6.087368421052632e-06, "loss": 0.1649, "step": 4225 }, { "epoch": 0.35, "learning_rate": 6.061052631578947e-06, "loss": 0.1591, "step": 4250 }, { "epoch": 0.35, "learning_rate": 6.034736842105263e-06, "loss": 0.1927, "step": 4275 }, { "epoch": 0.35, "learning_rate": 6.008421052631579e-06, "loss": 0.202, "step": 4300 }, { "epoch": 0.36, "learning_rate": 5.982105263157895e-06, "loss": 0.1684, "step": 4325 }, { "epoch": 0.36, "learning_rate": 5.956842105263159e-06, "loss": 0.1743, "step": 4350 }, { "epoch": 0.36, "learning_rate": 5.930526315789475e-06, "loss": 0.1665, "step": 4375 }, { "epoch": 0.36, "learning_rate": 5.90421052631579e-06, "loss": 0.1837, "step": 4400 }, { "epoch": 0.36, "learning_rate": 5.877894736842105e-06, "loss": 0.1713, "step": 4425 }, { "epoch": 0.37, "learning_rate": 5.851578947368421e-06, "loss": 0.1656, "step": 4450 }, { "epoch": 0.37, "learning_rate": 5.825263157894737e-06, "loss": 0.1796, "step": 4475 }, { "epoch": 0.37, "learning_rate": 5.798947368421053e-06, "loss": 0.1611, "step": 4500 }, { "epoch": 0.37, "learning_rate": 5.772631578947369e-06, "loss": 0.1834, "step": 4525 }, { "epoch": 0.37, "learning_rate": 5.7463157894736845e-06, "loss": 0.1746, "step": 4550 }, { "epoch": 0.38, "learning_rate": 5.72e-06, "loss": 0.1662, "step": 4575 }, { "epoch": 0.38, "learning_rate": 5.693684210526316e-06, "loss": 0.1764, "step": 4600 }, { "epoch": 0.38, "learning_rate": 5.667368421052633e-06, "loss": 0.166, "step": 4625 }, { "epoch": 0.38, "learning_rate": 5.641052631578949e-06, "loss": 0.1717, "step": 4650 }, { "epoch": 0.38, "learning_rate": 5.6147368421052636e-06, "loss": 0.1577, "step": 4675 }, { "epoch": 0.39, "learning_rate": 5.588421052631579e-06, "loss": 0.1805, "step": 4700 }, { "epoch": 0.39, "learning_rate": 5.562105263157895e-06, "loss": 0.1781, "step": 4725 }, { "epoch": 0.39, "learning_rate": 5.535789473684211e-06, "loss": 0.167, "step": 4750 }, { "epoch": 0.39, "learning_rate": 5.509473684210527e-06, "loss": 0.1571, "step": 4775 }, { "epoch": 0.4, "learning_rate": 5.483157894736843e-06, "loss": 0.1768, "step": 4800 }, { "epoch": 0.4, "learning_rate": 5.4568421052631585e-06, "loss": 0.152, "step": 4825 }, { "epoch": 0.4, "learning_rate": 5.4305263157894734e-06, "loss": 0.1908, "step": 4850 }, { "epoch": 0.4, "learning_rate": 5.404210526315789e-06, "loss": 0.168, "step": 4875 }, { "epoch": 0.4, "learning_rate": 5.377894736842105e-06, "loss": 0.1749, "step": 4900 }, { "epoch": 0.41, "learning_rate": 5.351578947368421e-06, "loss": 0.1698, "step": 4925 }, { "epoch": 0.41, "learning_rate": 5.3252631578947376e-06, "loss": 0.1823, "step": 4950 }, { "epoch": 0.41, "learning_rate": 5.298947368421053e-06, "loss": 0.1577, "step": 4975 }, { "epoch": 0.41, "learning_rate": 5.272631578947369e-06, "loss": 0.1795, "step": 5000 }, { "epoch": 0.41, "learning_rate": 5.246315789473685e-06, "loss": 0.2045, "step": 5025 }, { "epoch": 0.42, "learning_rate": 5.220000000000001e-06, "loss": 0.1642, "step": 5050 }, { "epoch": 0.42, "learning_rate": 5.193684210526317e-06, "loss": 0.1638, "step": 5075 }, { "epoch": 0.42, "learning_rate": 5.167368421052632e-06, "loss": 0.1822, "step": 5100 }, { "epoch": 0.42, "learning_rate": 5.1410526315789475e-06, "loss": 0.2059, "step": 5125 }, { "epoch": 0.42, "learning_rate": 5.114736842105263e-06, "loss": 0.1766, "step": 5150 }, { "epoch": 0.43, "learning_rate": 5.088421052631579e-06, "loss": 0.1574, "step": 5175 }, { "epoch": 0.43, "learning_rate": 5.062105263157895e-06, "loss": 0.1774, "step": 5200 }, { "epoch": 0.43, "learning_rate": 5.035789473684211e-06, "loss": 0.1848, "step": 5225 }, { "epoch": 0.43, "learning_rate": 5.0094736842105265e-06, "loss": 0.1751, "step": 5250 }, { "epoch": 0.43, "learning_rate": 4.983157894736842e-06, "loss": 0.1736, "step": 5275 }, { "epoch": 0.44, "learning_rate": 4.956842105263158e-06, "loss": 0.1678, "step": 5300 }, { "epoch": 0.44, "learning_rate": 4.930526315789474e-06, "loss": 0.1767, "step": 5325 }, { "epoch": 0.44, "learning_rate": 4.90421052631579e-06, "loss": 0.1652, "step": 5350 }, { "epoch": 0.44, "learning_rate": 4.877894736842106e-06, "loss": 0.1542, "step": 5375 }, { "epoch": 0.44, "learning_rate": 4.8515789473684215e-06, "loss": 0.1715, "step": 5400 }, { "epoch": 0.45, "learning_rate": 4.825263157894737e-06, "loss": 0.1696, "step": 5425 }, { "epoch": 0.45, "learning_rate": 4.798947368421053e-06, "loss": 0.1568, "step": 5450 }, { "epoch": 0.45, "learning_rate": 4.772631578947369e-06, "loss": 0.1777, "step": 5475 }, { "epoch": 0.45, "learning_rate": 4.746315789473685e-06, "loss": 0.1677, "step": 5500 }, { "epoch": 0.45, "learning_rate": 4.7200000000000005e-06, "loss": 0.1792, "step": 5525 }, { "epoch": 0.46, "learning_rate": 4.693684210526316e-06, "loss": 0.1673, "step": 5550 }, { "epoch": 0.46, "learning_rate": 4.667368421052632e-06, "loss": 0.1467, "step": 5575 }, { "epoch": 0.46, "learning_rate": 4.641052631578948e-06, "loss": 0.1769, "step": 5600 }, { "epoch": 0.46, "learning_rate": 4.614736842105264e-06, "loss": 0.1913, "step": 5625 }, { "epoch": 0.46, "learning_rate": 4.58842105263158e-06, "loss": 0.1662, "step": 5650 }, { "epoch": 0.47, "learning_rate": 4.562105263157895e-06, "loss": 0.177, "step": 5675 }, { "epoch": 0.47, "learning_rate": 4.5357894736842104e-06, "loss": 0.1723, "step": 5700 }, { "epoch": 0.47, "learning_rate": 4.509473684210527e-06, "loss": 0.1511, "step": 5725 }, { "epoch": 0.47, "learning_rate": 4.483157894736843e-06, "loss": 0.1459, "step": 5750 }, { "epoch": 0.48, "learning_rate": 4.456842105263158e-06, "loss": 0.1764, "step": 5775 }, { "epoch": 0.48, "learning_rate": 4.430526315789474e-06, "loss": 0.1642, "step": 5800 }, { "epoch": 0.48, "learning_rate": 4.4042105263157895e-06, "loss": 0.1519, "step": 5825 }, { "epoch": 0.48, "learning_rate": 4.377894736842105e-06, "loss": 0.1642, "step": 5850 }, { "epoch": 0.48, "learning_rate": 4.351578947368422e-06, "loss": 0.1493, "step": 5875 }, { "epoch": 0.49, "learning_rate": 4.325263157894737e-06, "loss": 0.1718, "step": 5900 }, { "epoch": 0.49, "learning_rate": 4.298947368421053e-06, "loss": 0.1723, "step": 5925 }, { "epoch": 0.49, "learning_rate": 4.272631578947369e-06, "loss": 0.171, "step": 5950 }, { "epoch": 0.49, "learning_rate": 4.2463157894736844e-06, "loss": 0.1662, "step": 5975 }, { "epoch": 0.49, "learning_rate": 4.22e-06, "loss": 0.1536, "step": 6000 }, { "epoch": 0.5, "learning_rate": 4.193684210526316e-06, "loss": 0.1537, "step": 6025 }, { "epoch": 0.5, "learning_rate": 4.167368421052632e-06, "loss": 0.1512, "step": 6050 }, { "epoch": 0.5, "learning_rate": 4.141052631578948e-06, "loss": 0.1502, "step": 6075 }, { "epoch": 0.5, "learning_rate": 4.1147368421052635e-06, "loss": 0.1521, "step": 6100 }, { "epoch": 0.5, "learning_rate": 4.088421052631579e-06, "loss": 0.1552, "step": 6125 }, { "epoch": 0.51, "learning_rate": 4.062105263157895e-06, "loss": 0.1776, "step": 6150 }, { "epoch": 0.51, "learning_rate": 4.035789473684211e-06, "loss": 0.1772, "step": 6175 }, { "epoch": 0.51, "learning_rate": 4.009473684210527e-06, "loss": 0.1607, "step": 6200 }, { "epoch": 0.51, "learning_rate": 3.983157894736843e-06, "loss": 0.1604, "step": 6225 }, { "epoch": 0.51, "learning_rate": 3.9568421052631584e-06, "loss": 0.1609, "step": 6250 }, { "epoch": 0.52, "learning_rate": 3.930526315789474e-06, "loss": 0.1597, "step": 6275 }, { "epoch": 0.52, "learning_rate": 3.90421052631579e-06, "loss": 0.1756, "step": 6300 }, { "epoch": 0.52, "learning_rate": 3.877894736842106e-06, "loss": 0.161, "step": 6325 }, { "epoch": 0.52, "learning_rate": 3.853684210526316e-06, "loss": 0.1425, "step": 6350 }, { "epoch": 0.52, "learning_rate": 3.827368421052632e-06, "loss": 0.1473, "step": 6375 }, { "epoch": 0.53, "learning_rate": 3.8010526315789476e-06, "loss": 0.159, "step": 6400 }, { "epoch": 0.53, "learning_rate": 3.7747368421052634e-06, "loss": 0.1495, "step": 6425 }, { "epoch": 0.53, "learning_rate": 3.7484210526315796e-06, "loss": 0.1442, "step": 6450 }, { "epoch": 0.53, "learning_rate": 3.722105263157895e-06, "loss": 0.1502, "step": 6475 }, { "epoch": 0.53, "learning_rate": 3.695789473684211e-06, "loss": 0.1386, "step": 6500 }, { "epoch": 0.54, "learning_rate": 3.6694736842105267e-06, "loss": 0.1308, "step": 6525 }, { "epoch": 0.54, "learning_rate": 3.6431578947368425e-06, "loss": 0.1712, "step": 6550 }, { "epoch": 0.54, "learning_rate": 3.616842105263158e-06, "loss": 0.1381, "step": 6575 }, { "epoch": 0.54, "learning_rate": 3.5905263157894737e-06, "loss": 0.1593, "step": 6600 }, { "epoch": 0.55, "learning_rate": 3.56421052631579e-06, "loss": 0.1319, "step": 6625 }, { "epoch": 0.55, "learning_rate": 3.5378947368421058e-06, "loss": 0.1616, "step": 6650 }, { "epoch": 0.55, "learning_rate": 3.5115789473684216e-06, "loss": 0.1447, "step": 6675 }, { "epoch": 0.55, "learning_rate": 3.485263157894737e-06, "loss": 0.1483, "step": 6700 }, { "epoch": 0.55, "learning_rate": 3.458947368421053e-06, "loss": 0.159, "step": 6725 }, { "epoch": 0.56, "learning_rate": 3.4326315789473686e-06, "loss": 0.1446, "step": 6750 }, { "epoch": 0.56, "learning_rate": 3.4063157894736844e-06, "loss": 0.1346, "step": 6775 }, { "epoch": 0.56, "learning_rate": 3.3800000000000007e-06, "loss": 0.1317, "step": 6800 }, { "epoch": 0.56, "learning_rate": 3.353684210526316e-06, "loss": 0.1797, "step": 6825 }, { "epoch": 0.56, "learning_rate": 3.327368421052632e-06, "loss": 0.1423, "step": 6850 }, { "epoch": 0.57, "learning_rate": 3.3010526315789477e-06, "loss": 0.1513, "step": 6875 }, { "epoch": 0.57, "learning_rate": 3.2747368421052635e-06, "loss": 0.1373, "step": 6900 }, { "epoch": 0.57, "learning_rate": 3.248421052631579e-06, "loss": 0.1682, "step": 6925 }, { "epoch": 0.57, "learning_rate": 3.2221052631578947e-06, "loss": 0.1371, "step": 6950 }, { "epoch": 0.57, "learning_rate": 3.195789473684211e-06, "loss": 0.1455, "step": 6975 }, { "epoch": 0.58, "learning_rate": 3.169473684210527e-06, "loss": 0.1612, "step": 7000 }, { "epoch": 0.58, "learning_rate": 3.1431578947368426e-06, "loss": 0.1471, "step": 7025 }, { "epoch": 0.58, "learning_rate": 3.116842105263158e-06, "loss": 0.1644, "step": 7050 }, { "epoch": 0.58, "learning_rate": 3.090526315789474e-06, "loss": 0.1533, "step": 7075 }, { "epoch": 0.58, "learning_rate": 3.0642105263157896e-06, "loss": 0.1433, "step": 7100 }, { "epoch": 0.59, "learning_rate": 3.037894736842106e-06, "loss": 0.1489, "step": 7125 }, { "epoch": 0.59, "learning_rate": 3.0115789473684213e-06, "loss": 0.1391, "step": 7150 }, { "epoch": 0.59, "learning_rate": 2.985263157894737e-06, "loss": 0.1559, "step": 7175 }, { "epoch": 0.59, "learning_rate": 2.958947368421053e-06, "loss": 0.1429, "step": 7200 }, { "epoch": 0.59, "learning_rate": 2.9326315789473687e-06, "loss": 0.1544, "step": 7225 }, { "epoch": 0.6, "learning_rate": 2.906315789473684e-06, "loss": 0.16, "step": 7250 }, { "epoch": 0.6, "learning_rate": 2.88e-06, "loss": 0.1565, "step": 7275 }, { "epoch": 0.6, "learning_rate": 2.853684210526316e-06, "loss": 0.1495, "step": 7300 }, { "epoch": 0.6, "learning_rate": 2.827368421052632e-06, "loss": 0.1547, "step": 7325 }, { "epoch": 0.6, "learning_rate": 2.803157894736842e-06, "loss": 0.1352, "step": 7350 }, { "epoch": 0.61, "learning_rate": 2.7768421052631583e-06, "loss": 0.133, "step": 7375 }, { "epoch": 0.61, "learning_rate": 2.750526315789474e-06, "loss": 0.1475, "step": 7400 }, { "epoch": 0.61, "learning_rate": 2.72421052631579e-06, "loss": 0.1651, "step": 7425 }, { "epoch": 0.61, "learning_rate": 2.6978947368421053e-06, "loss": 0.1632, "step": 7450 }, { "epoch": 0.62, "learning_rate": 2.671578947368421e-06, "loss": 0.1552, "step": 7475 }, { "epoch": 0.62, "learning_rate": 2.645263157894737e-06, "loss": 0.1717, "step": 7500 }, { "epoch": 0.62, "learning_rate": 2.6189473684210524e-06, "loss": 0.1572, "step": 7525 }, { "epoch": 0.62, "learning_rate": 2.592631578947369e-06, "loss": 0.1404, "step": 7550 }, { "epoch": 0.62, "learning_rate": 2.5663157894736844e-06, "loss": 0.1733, "step": 7575 }, { "epoch": 0.63, "learning_rate": 2.5400000000000002e-06, "loss": 0.1477, "step": 7600 }, { "epoch": 0.63, "learning_rate": 2.513684210526316e-06, "loss": 0.1338, "step": 7625 }, { "epoch": 0.63, "learning_rate": 2.4873684210526315e-06, "loss": 0.1583, "step": 7650 }, { "epoch": 0.63, "learning_rate": 2.4610526315789477e-06, "loss": 0.1441, "step": 7675 }, { "epoch": 0.63, "learning_rate": 2.4347368421052635e-06, "loss": 0.1373, "step": 7700 }, { "epoch": 0.64, "learning_rate": 2.408421052631579e-06, "loss": 0.1375, "step": 7725 }, { "epoch": 0.64, "learning_rate": 2.382105263157895e-06, "loss": 0.1528, "step": 7750 }, { "epoch": 0.64, "learning_rate": 2.3557894736842106e-06, "loss": 0.1546, "step": 7775 }, { "epoch": 0.64, "learning_rate": 2.3294736842105264e-06, "loss": 0.144, "step": 7800 }, { "epoch": 0.64, "learning_rate": 2.3031578947368426e-06, "loss": 0.1565, "step": 7825 }, { "epoch": 0.65, "learning_rate": 2.276842105263158e-06, "loss": 0.1229, "step": 7850 }, { "epoch": 0.65, "learning_rate": 2.250526315789474e-06, "loss": 0.1581, "step": 7875 }, { "epoch": 0.65, "learning_rate": 2.2242105263157896e-06, "loss": 0.151, "step": 7900 }, { "epoch": 0.65, "learning_rate": 2.1978947368421055e-06, "loss": 0.1452, "step": 7925 }, { "epoch": 0.65, "learning_rate": 2.1715789473684213e-06, "loss": 0.1436, "step": 7950 }, { "epoch": 0.66, "learning_rate": 2.145263157894737e-06, "loss": 0.1494, "step": 7975 }, { "epoch": 0.66, "learning_rate": 2.118947368421053e-06, "loss": 0.1231, "step": 8000 }, { "epoch": 0.66, "learning_rate": 2.0926315789473687e-06, "loss": 0.1412, "step": 8025 }, { "epoch": 0.66, "learning_rate": 2.066315789473684e-06, "loss": 0.1504, "step": 8050 }, { "epoch": 0.66, "learning_rate": 2.04e-06, "loss": 0.1624, "step": 8075 }, { "epoch": 0.67, "learning_rate": 2.013684210526316e-06, "loss": 0.1534, "step": 8100 }, { "epoch": 0.67, "learning_rate": 1.9873684210526316e-06, "loss": 0.1649, "step": 8125 }, { "epoch": 0.67, "learning_rate": 1.9610526315789474e-06, "loss": 0.1369, "step": 8150 }, { "epoch": 0.67, "learning_rate": 1.9347368421052632e-06, "loss": 0.1546, "step": 8175 }, { "epoch": 0.67, "learning_rate": 1.908421052631579e-06, "loss": 0.1417, "step": 8200 }, { "epoch": 0.68, "learning_rate": 1.8821052631578949e-06, "loss": 0.1491, "step": 8225 }, { "epoch": 0.68, "learning_rate": 1.8557894736842109e-06, "loss": 0.1449, "step": 8250 }, { "epoch": 0.68, "learning_rate": 1.8294736842105265e-06, "loss": 0.1387, "step": 8275 }, { "epoch": 0.68, "learning_rate": 1.8031578947368423e-06, "loss": 0.1542, "step": 8300 }, { "epoch": 0.69, "learning_rate": 1.776842105263158e-06, "loss": 0.1619, "step": 8325 }, { "epoch": 0.69, "learning_rate": 1.7526315789473686e-06, "loss": 0.1582, "step": 8350 }, { "epoch": 0.69, "learning_rate": 1.7263157894736842e-06, "loss": 0.1565, "step": 8375 }, { "epoch": 0.69, "learning_rate": 1.7000000000000002e-06, "loss": 0.1709, "step": 8400 }, { "epoch": 0.69, "learning_rate": 1.673684210526316e-06, "loss": 0.1424, "step": 8425 }, { "epoch": 0.7, "learning_rate": 1.6473684210526317e-06, "loss": 0.1545, "step": 8450 }, { "epoch": 0.7, "learning_rate": 1.6210526315789473e-06, "loss": 0.1424, "step": 8475 }, { "epoch": 0.7, "learning_rate": 1.5947368421052633e-06, "loss": 0.1401, "step": 8500 }, { "epoch": 0.7, "learning_rate": 1.5684210526315791e-06, "loss": 0.1512, "step": 8525 }, { "epoch": 0.7, "learning_rate": 1.5421052631578947e-06, "loss": 0.1362, "step": 8550 }, { "epoch": 0.71, "learning_rate": 1.5157894736842108e-06, "loss": 0.1393, "step": 8575 }, { "epoch": 0.71, "learning_rate": 1.4894736842105264e-06, "loss": 0.1213, "step": 8600 }, { "epoch": 0.71, "learning_rate": 1.4631578947368422e-06, "loss": 0.1462, "step": 8625 }, { "epoch": 0.71, "learning_rate": 1.4368421052631582e-06, "loss": 0.158, "step": 8650 }, { "epoch": 0.71, "learning_rate": 1.4105263157894738e-06, "loss": 0.1468, "step": 8675 }, { "epoch": 0.72, "learning_rate": 1.3842105263157896e-06, "loss": 0.1469, "step": 8700 }, { "epoch": 0.72, "learning_rate": 1.3578947368421052e-06, "loss": 0.1569, "step": 8725 }, { "epoch": 0.72, "learning_rate": 1.3315789473684213e-06, "loss": 0.1538, "step": 8750 }, { "epoch": 0.72, "learning_rate": 1.3052631578947369e-06, "loss": 0.1332, "step": 8775 }, { "epoch": 0.72, "learning_rate": 1.2789473684210527e-06, "loss": 0.1378, "step": 8800 }, { "epoch": 0.73, "learning_rate": 1.2526315789473687e-06, "loss": 0.1386, "step": 8825 }, { "epoch": 0.73, "learning_rate": 1.2263157894736843e-06, "loss": 0.1675, "step": 8850 }, { "epoch": 0.73, "learning_rate": 1.2000000000000002e-06, "loss": 0.1457, "step": 8875 }, { "epoch": 0.73, "learning_rate": 1.173684210526316e-06, "loss": 0.1262, "step": 8900 }, { "epoch": 0.73, "learning_rate": 1.1473684210526316e-06, "loss": 0.148, "step": 8925 }, { "epoch": 0.74, "learning_rate": 1.1210526315789474e-06, "loss": 0.1413, "step": 8950 }, { "epoch": 0.74, "learning_rate": 1.0947368421052632e-06, "loss": 0.1326, "step": 8975 }, { "epoch": 0.74, "learning_rate": 1.068421052631579e-06, "loss": 0.1484, "step": 9000 }, { "epoch": 0.74, "learning_rate": 1.0421052631578949e-06, "loss": 0.1705, "step": 9025 }, { "epoch": 0.74, "learning_rate": 1.0157894736842105e-06, "loss": 0.1248, "step": 9050 }, { "epoch": 0.75, "learning_rate": 9.905263157894738e-07, "loss": 0.1554, "step": 9075 }, { "epoch": 0.75, "learning_rate": 9.642105263157896e-07, "loss": 0.122, "step": 9100 }, { "epoch": 0.75, "learning_rate": 9.378947368421052e-07, "loss": 0.1566, "step": 9125 }, { "epoch": 0.75, "learning_rate": 9.115789473684212e-07, "loss": 0.1434, "step": 9150 }, { "epoch": 0.76, "learning_rate": 8.85263157894737e-07, "loss": 0.1372, "step": 9175 }, { "epoch": 0.76, "learning_rate": 8.589473684210527e-07, "loss": 0.1456, "step": 9200 }, { "epoch": 0.76, "learning_rate": 8.326315789473685e-07, "loss": 0.1436, "step": 9225 }, { "epoch": 0.76, "learning_rate": 8.063157894736842e-07, "loss": 0.1533, "step": 9250 }, { "epoch": 0.76, "learning_rate": 7.8e-07, "loss": 0.1324, "step": 9275 }, { "epoch": 0.77, "learning_rate": 7.536842105263159e-07, "loss": 0.1397, "step": 9300 }, { "epoch": 0.77, "learning_rate": 7.273684210526316e-07, "loss": 0.1477, "step": 9325 }, { "epoch": 0.77, "learning_rate": 7.010526315789475e-07, "loss": 0.1387, "step": 9350 }, { "epoch": 0.77, "learning_rate": 6.747368421052631e-07, "loss": 0.1722, "step": 9375 }, { "epoch": 0.77, "learning_rate": 6.48421052631579e-07, "loss": 0.1504, "step": 9400 }, { "epoch": 0.78, "learning_rate": 6.221052631578947e-07, "loss": 0.1554, "step": 9425 }, { "epoch": 0.78, "learning_rate": 5.957894736842106e-07, "loss": 0.1516, "step": 9450 }, { "epoch": 0.78, "learning_rate": 5.694736842105263e-07, "loss": 0.1518, "step": 9475 }, { "epoch": 0.78, "learning_rate": 5.431578947368422e-07, "loss": 0.1288, "step": 9500 }, { "epoch": 0.78, "learning_rate": 5.168421052631579e-07, "loss": 0.1361, "step": 9525 }, { "epoch": 0.79, "learning_rate": 4.905263157894737e-07, "loss": 0.1501, "step": 9550 }, { "epoch": 0.79, "learning_rate": 4.642105263157895e-07, "loss": 0.135, "step": 9575 }, { "epoch": 0.79, "learning_rate": 4.3789473684210527e-07, "loss": 0.1452, "step": 9600 }, { "epoch": 0.79, "learning_rate": 4.1157894736842114e-07, "loss": 0.1251, "step": 9625 }, { "epoch": 0.79, "learning_rate": 3.852631578947369e-07, "loss": 0.1374, "step": 9650 }, { "epoch": 0.8, "learning_rate": 3.5894736842105267e-07, "loss": 0.147, "step": 9675 }, { "epoch": 0.8, "learning_rate": 3.3263157894736843e-07, "loss": 0.1457, "step": 9700 }, { "epoch": 0.8, "learning_rate": 3.063157894736842e-07, "loss": 0.1587, "step": 9725 }, { "epoch": 0.8, "learning_rate": 2.8e-07, "loss": 0.1388, "step": 9750 }, { "epoch": 0.8, "learning_rate": 2.536842105263158e-07, "loss": 0.1554, "step": 9775 }, { "epoch": 0.81, "learning_rate": 2.273684210526316e-07, "loss": 0.1495, "step": 9800 }, { "epoch": 0.81, "learning_rate": 2.010526315789474e-07, "loss": 0.1596, "step": 9825 }, { "epoch": 0.81, "learning_rate": 1.7473684210526316e-07, "loss": 0.144, "step": 9850 }, { "epoch": 0.81, "learning_rate": 1.4842105263157895e-07, "loss": 0.1351, "step": 9875 }, { "epoch": 0.81, "learning_rate": 1.2210526315789474e-07, "loss": 0.1487, "step": 9900 }, { "epoch": 0.82, "learning_rate": 9.578947368421054e-08, "loss": 0.1336, "step": 9925 }, { "epoch": 0.82, "learning_rate": 6.947368421052633e-08, "loss": 0.1362, "step": 9950 }, { "epoch": 0.82, "learning_rate": 4.315789473684211e-08, "loss": 0.1421, "step": 9975 }, { "epoch": 0.82, "learning_rate": 1.6842105263157897e-08, "loss": 0.1397, "step": 10000 }, { "epoch": 0.82, "step": 10000, "total_flos": 1.632967868976988e+20, "train_loss": 0.18710677490234376, "train_runtime": 35654.5907, "train_samples_per_second": 4.488, "train_steps_per_second": 0.28 } ], "logging_steps": 25, "max_steps": 10000, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2000, "total_flos": 1.632967868976988e+20, "train_batch_size": 16, "trial_name": null, "trial_params": null }