| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 50, | |
| "global_step": 1524, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5105, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2713, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2324, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.237317442893982, | |
| "eval_runtime": 19.2113, | |
| "eval_samples_per_second": 25.662, | |
| "eval_steps_per_second": 1.614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2385, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2294, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2065, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2171, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2114, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.2198712825775146, | |
| "eval_runtime": 19.1971, | |
| "eval_samples_per_second": 25.681, | |
| "eval_steps_per_second": 1.615, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1593, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1865, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1765, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2079, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1831, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.2110768556594849, | |
| "eval_runtime": 19.4082, | |
| "eval_samples_per_second": 25.402, | |
| "eval_steps_per_second": 1.597, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2075, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2124, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2023, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1721, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2027, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.2048192024230957, | |
| "eval_runtime": 19.3037, | |
| "eval_samples_per_second": 25.539, | |
| "eval_steps_per_second": 1.606, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1674, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1882, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2099, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1988, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1827, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2000844478607178, | |
| "eval_runtime": 19.2851, | |
| "eval_samples_per_second": 25.564, | |
| "eval_steps_per_second": 1.607, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1452, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3e-05, | |
| "loss": 1.185, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1979, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2155, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1696, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.1973345279693604, | |
| "eval_runtime": 18.7078, | |
| "eval_samples_per_second": 26.353, | |
| "eval_steps_per_second": 1.657, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1426, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1691, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1991, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1992, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2186, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.193804383277893, | |
| "eval_runtime": 18.8972, | |
| "eval_samples_per_second": 26.088, | |
| "eval_steps_per_second": 1.64, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1691, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1595, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1494, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1985, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1795, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 1.1919257640838623, | |
| "eval_runtime": 19.3777, | |
| "eval_samples_per_second": 25.442, | |
| "eval_steps_per_second": 1.6, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1254, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1772, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1956, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1959, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2167, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.188421607017517, | |
| "eval_runtime": 18.7028, | |
| "eval_samples_per_second": 26.36, | |
| "eval_steps_per_second": 1.658, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1625, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1979, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1705, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1998, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1992, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.1840450763702393, | |
| "eval_runtime": 19.5434, | |
| "eval_samples_per_second": 25.226, | |
| "eval_steps_per_second": 1.586, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1842, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1598, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1538, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1506, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2032, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.1824493408203125, | |
| "eval_runtime": 18.4972, | |
| "eval_samples_per_second": 26.653, | |
| "eval_steps_per_second": 1.676, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1795, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1604, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1548, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1876, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1841, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.1797986030578613, | |
| "eval_runtime": 19.5627, | |
| "eval_samples_per_second": 25.201, | |
| "eval_steps_per_second": 1.585, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1579, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1858, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1994, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1712, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3e-05, | |
| "loss": 1.166, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.1789214611053467, | |
| "eval_runtime": 19.1568, | |
| "eval_samples_per_second": 25.735, | |
| "eval_steps_per_second": 1.618, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1426, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1291, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1825, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1214, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1641, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 1.1761133670806885, | |
| "eval_runtime": 18.1966, | |
| "eval_samples_per_second": 27.093, | |
| "eval_steps_per_second": 1.704, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1069, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1267, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1472, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3e-05, | |
| "loss": 1.2204, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1859, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 1.1751502752304077, | |
| "eval_runtime": 18.7143, | |
| "eval_samples_per_second": 26.343, | |
| "eval_steps_per_second": 1.656, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1314, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3e-05, | |
| "loss": 1.12, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1007, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0822, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3e-05, | |
| "loss": 1.132, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 1.1736373901367188, | |
| "eval_runtime": 19.2149, | |
| "eval_samples_per_second": 25.657, | |
| "eval_steps_per_second": 1.613, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1076, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1007, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1215, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0956, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1461, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.1723910570144653, | |
| "eval_runtime": 18.6093, | |
| "eval_samples_per_second": 26.492, | |
| "eval_steps_per_second": 1.666, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0818, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0959, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0948, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1246, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0965, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.172638177871704, | |
| "eval_runtime": 18.6729, | |
| "eval_samples_per_second": 26.402, | |
| "eval_steps_per_second": 1.66, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3e-05, | |
| "loss": 1.114, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1152, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0885, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1221, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1064, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.172351598739624, | |
| "eval_runtime": 19.5348, | |
| "eval_samples_per_second": 25.237, | |
| "eval_steps_per_second": 1.587, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0518, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0938, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1184, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3e-05, | |
| "loss": 1.09, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3e-05, | |
| "loss": 1.123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.1728639602661133, | |
| "eval_runtime": 18.8741, | |
| "eval_samples_per_second": 26.12, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1059, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1061, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1147, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1322, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1079, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.1694797277450562, | |
| "eval_runtime": 18.842, | |
| "eval_samples_per_second": 26.165, | |
| "eval_steps_per_second": 1.645, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0826, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1194, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1398, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3e-05, | |
| "loss": 1.11, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3e-05, | |
| "loss": 1.12, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.1707435846328735, | |
| "eval_runtime": 19.0362, | |
| "eval_samples_per_second": 25.898, | |
| "eval_steps_per_second": 1.628, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0891, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1216, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1122, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1065, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1288, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.1693464517593384, | |
| "eval_runtime": 19.1181, | |
| "eval_samples_per_second": 25.787, | |
| "eval_steps_per_second": 1.622, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1145, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0812, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1291, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1114, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3e-05, | |
| "loss": 1.133, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.1675716638565063, | |
| "eval_runtime": 19.1116, | |
| "eval_samples_per_second": 25.796, | |
| "eval_steps_per_second": 1.622, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0918, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1009, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1279, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1314, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1647, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.1693305969238281, | |
| "eval_runtime": 18.9258, | |
| "eval_samples_per_second": 26.049, | |
| "eval_steps_per_second": 1.638, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0633, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0961, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1106, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1233, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1269, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 1.1658315658569336, | |
| "eval_runtime": 18.972, | |
| "eval_samples_per_second": 25.986, | |
| "eval_steps_per_second": 1.634, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0683, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1079, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1367, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1077, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1332, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.1656816005706787, | |
| "eval_runtime": 19.0244, | |
| "eval_samples_per_second": 25.914, | |
| "eval_steps_per_second": 1.629, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0921, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0669, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1185, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3e-05, | |
| "loss": 1.108, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1276, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 1.1681002378463745, | |
| "eval_runtime": 18.4913, | |
| "eval_samples_per_second": 26.661, | |
| "eval_steps_per_second": 1.676, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0666, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1286, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1286, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0967, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1361, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.1633367538452148, | |
| "eval_runtime": 18.9278, | |
| "eval_samples_per_second": 26.046, | |
| "eval_steps_per_second": 1.638, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0907, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1137, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 3e-05, | |
| "loss": 1.125, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1047, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1205, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.1639732122421265, | |
| "eval_runtime": 19.1908, | |
| "eval_samples_per_second": 25.689, | |
| "eval_steps_per_second": 1.615, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0902, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 3e-05, | |
| "loss": 1.0794, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 1524, | |
| "total_flos": 2.2001611985471406e+18, | |
| "train_loss": 1.1488912840840697, | |
| "train_runtime": 10306.9039, | |
| "train_samples_per_second": 9.463, | |
| "train_steps_per_second": 0.148 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1524, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 2.2001611985471406e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |