| { | |
| "best_metric": 1.1605136394500732, | |
| "best_model_checkpoint": "rm-ckpt-reward-p100-w0.3-s0/checkpoint-2200", | |
| "epoch": 1.1584544114550432, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 1.395, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3157, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3105, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2898, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001, | |
| "loss": 1.263, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2683, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2433, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2361, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_val_accuracy": 0.5835, | |
| "eval_val_loss": 1.2417031526565552, | |
| "eval_val_runtime": 655.2015, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2347, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2328, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2319, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2296, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2067, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2101, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2065, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2207, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2141, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2122, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_val_accuracy": 0.5943333333333334, | |
| "eval_val_loss": 1.2143710851669312, | |
| "eval_val_runtime": 655.5732, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2178, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2065, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2077, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2015, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2121, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1873, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2211, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2024, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2018, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1915, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_val_accuracy": 0.5968333333333333, | |
| "eval_val_loss": 1.2014297246932983, | |
| "eval_val_runtime": 654.9118, | |
| "eval_val_samples_per_second": 1.527, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001, | |
| "loss": 1.187, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1846, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001, | |
| "loss": 1.191, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1995, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2025, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1969, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1895, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1942, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1896, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2049, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_val_accuracy": 0.6015, | |
| "eval_val_loss": 1.1935878992080688, | |
| "eval_val_runtime": 655.3426, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1909, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2016, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1918, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1982, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1955, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1949, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1957, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1812, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1801, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0001, | |
| "loss": 1.184, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_val_accuracy": 0.6025, | |
| "eval_val_loss": 1.1882715225219727, | |
| "eval_val_runtime": 655.2879, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1634, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1614, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1824, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1846, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1846, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1908, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1865, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1951, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1854, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1856, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_val_accuracy": 0.6013333333333334, | |
| "eval_val_loss": 1.1858690977096558, | |
| "eval_val_runtime": 655.6111, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1898, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1962, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001, | |
| "loss": 1.173, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1999, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1783, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2053, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1898, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1911, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1715, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1666, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_val_accuracy": 0.6033333333333334, | |
| "eval_val_loss": 1.1816191673278809, | |
| "eval_val_runtime": 655.5284, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1884, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1837, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001, | |
| "loss": 1.185, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001, | |
| "loss": 1.179, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1717, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1772, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001, | |
| "loss": 1.176, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1839, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1889, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1765, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_val_accuracy": 0.5996666666666667, | |
| "eval_val_loss": 1.1803770065307617, | |
| "eval_val_runtime": 655.2163, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001, | |
| "loss": 1.18, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1701, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1694, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1675, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1853, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1614, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1632, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001, | |
| "loss": 1.149, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001, | |
| "loss": 1.153, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1696, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_val_accuracy": 0.6045, | |
| "eval_val_loss": 1.1773730516433716, | |
| "eval_val_runtime": 655.5445, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001, | |
| "loss": 1.179, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1925, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1754, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1714, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1722, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1838, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1705, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1678, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1726, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1631, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_val_accuracy": 0.6073333333333334, | |
| "eval_val_loss": 1.176171898841858, | |
| "eval_val_runtime": 655.3242, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001, | |
| "loss": 1.177, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1549, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1683, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001, | |
| "loss": 1.179, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1537, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001, | |
| "loss": 1.169, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1563, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1817, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1691, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1774, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_val_accuracy": 0.601, | |
| "eval_val_loss": 1.1745272874832153, | |
| "eval_val_runtime": 655.3598, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1875, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1617, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1688, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1738, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1661, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1713, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1595, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1895, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1865, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001, | |
| "loss": 1.167, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_val_accuracy": 0.6008333333333333, | |
| "eval_val_loss": 1.175210952758789, | |
| "eval_val_runtime": 655.623, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1532, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1664, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1719, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1479, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1581, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1579, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1705, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1685, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1624, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1813, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_val_accuracy": 0.6023333333333334, | |
| "eval_val_loss": 1.171212911605835, | |
| "eval_val_runtime": 655.8777, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1509, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1757, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1719, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1568, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1693, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1435, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1641, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1682, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1813, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1587, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_val_accuracy": 0.6063333333333334, | |
| "eval_val_loss": 1.1695449352264404, | |
| "eval_val_runtime": 655.6474, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1598, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1478, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1585, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1727, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1478, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1603, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001, | |
| "loss": 1.151, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1555, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1376, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1554, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_val_accuracy": 0.6056666666666666, | |
| "eval_val_loss": 1.1676816940307617, | |
| "eval_val_runtime": 655.7108, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1529, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1417, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1714, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1585, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1295, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1492, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0001, | |
| "loss": 1.164, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001, | |
| "loss": 1.168, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1568, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1639, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_val_accuracy": 0.6061666666666666, | |
| "eval_val_loss": 1.1664668321609497, | |
| "eval_val_runtime": 655.8117, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1666, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1527, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1557, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0001, | |
| "loss": 1.176, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1579, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1684, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001, | |
| "loss": 1.168, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1403, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1596, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1885, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_val_accuracy": 0.6055, | |
| "eval_val_loss": 1.1667187213897705, | |
| "eval_val_runtime": 655.8869, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1581, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1547, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1583, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1635, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1299, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1604, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1744, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1523, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1849, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1535, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_val_accuracy": 0.6076666666666666, | |
| "eval_val_loss": 1.1651777029037476, | |
| "eval_val_runtime": 655.5772, | |
| "eval_val_samples_per_second": 1.525, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1561, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1553, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1584, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1412, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1713, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1739, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1547, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1463, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1689, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1522, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_val_accuracy": 0.6046666666666666, | |
| "eval_val_loss": 1.1651347875595093, | |
| "eval_val_runtime": 655.1953, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1688, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1549, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1678, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1601, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1533, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1606, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1555, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1551, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1485, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1631, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_val_accuracy": 0.6056666666666666, | |
| "eval_val_loss": 1.1633808612823486, | |
| "eval_val_runtime": 655.153, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1526, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1618, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1616, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1541, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001, | |
| "loss": 1.157, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1453, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1257, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1464, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1619, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1535, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_val_accuracy": 0.607, | |
| "eval_val_loss": 1.1625254154205322, | |
| "eval_val_runtime": 655.4059, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1495, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1381, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1469, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001, | |
| "loss": 1.166, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1664, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1795, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1437, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001, | |
| "loss": 1.169, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1412, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1438, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_val_accuracy": 0.6048333333333333, | |
| "eval_val_loss": 1.1605136394500732, | |
| "eval_val_runtime": 655.4932, | |
| "eval_val_samples_per_second": 1.526, | |
| "eval_val_steps_per_second": 0.191, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3798, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |