| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.988950276243094, | |
| "eval_steps": 100, | |
| "global_step": 9000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.4737423991155337e-05, | |
| "loss": 1.4587, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 1.3197085857391357, | |
| "eval_runtime": 65.3939, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.4461028192371477e-05, | |
| "loss": 1.2795, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.2743616104125977, | |
| "eval_runtime": 65.3955, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.418463239358762e-05, | |
| "loss": 1.2566, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.256579875946045, | |
| "eval_runtime": 65.3852, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.390823659480376e-05, | |
| "loss": 1.2463, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.2438602447509766, | |
| "eval_runtime": 65.3739, | |
| "eval_samples_per_second": 13.996, | |
| "eval_steps_per_second": 0.352, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.3631840796019903e-05, | |
| "loss": 1.2276, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.2349315881729126, | |
| "eval_runtime": 65.3806, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.3355444997236043e-05, | |
| "loss": 1.2233, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.2274835109710693, | |
| "eval_runtime": 65.3699, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.3079049198452184e-05, | |
| "loss": 1.2182, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.2212377786636353, | |
| "eval_runtime": 65.3863, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.2802653399668325e-05, | |
| "loss": 1.2184, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.2167881727218628, | |
| "eval_runtime": 65.4277, | |
| "eval_samples_per_second": 13.985, | |
| "eval_steps_per_second": 0.352, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.252625760088447e-05, | |
| "loss": 1.2163, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.2119972705841064, | |
| "eval_runtime": 65.3982, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.224986180210061e-05, | |
| "loss": 1.1956, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.2085155248641968, | |
| "eval_runtime": 65.4054, | |
| "eval_samples_per_second": 13.99, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.197346600331675e-05, | |
| "loss": 1.2108, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.2050749063491821, | |
| "eval_runtime": 65.3891, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.1697070204532894e-05, | |
| "loss": 1.1973, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.2018028497695923, | |
| "eval_runtime": 65.3989, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.1420674405749035e-05, | |
| "loss": 1.2038, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.198926329612732, | |
| "eval_runtime": 65.3902, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.1144278606965175e-05, | |
| "loss": 1.1999, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.1960697174072266, | |
| "eval_runtime": 65.3767, | |
| "eval_samples_per_second": 13.996, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.0867882808181316e-05, | |
| "loss": 1.1862, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.1933324337005615, | |
| "eval_runtime": 65.3845, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.059148700939746e-05, | |
| "loss": 1.1896, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.1911386251449585, | |
| "eval_runtime": 65.3997, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.0315091210613597e-05, | |
| "loss": 1.1895, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.188926100730896, | |
| "eval_runtime": 65.3962, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.003869541182974e-05, | |
| "loss": 1.1881, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.186944842338562, | |
| "eval_runtime": 65.374, | |
| "eval_samples_per_second": 13.996, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9762299613045882e-05, | |
| "loss": 1.1874, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.1846946477890015, | |
| "eval_runtime": 65.3986, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.9485903814262023e-05, | |
| "loss": 1.1905, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.1831568479537964, | |
| "eval_runtime": 65.3641, | |
| "eval_samples_per_second": 13.999, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.9209508015478167e-05, | |
| "loss": 1.1872, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.1817291975021362, | |
| "eval_runtime": 65.4068, | |
| "eval_samples_per_second": 13.989, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.8933112216694307e-05, | |
| "loss": 1.1773, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.17881178855896, | |
| "eval_runtime": 65.3689, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.865671641791045e-05, | |
| "loss": 1.1754, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.177442193031311, | |
| "eval_runtime": 65.3786, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.838032061912659e-05, | |
| "loss": 1.1784, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.1754305362701416, | |
| "eval_runtime": 65.4015, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.8103924820342733e-05, | |
| "loss": 1.1763, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.1741561889648438, | |
| "eval_runtime": 65.3967, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.7827529021558873e-05, | |
| "loss": 1.1705, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.172415852546692, | |
| "eval_runtime": 65.3819, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.7551133222775014e-05, | |
| "loss": 1.1726, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.170956015586853, | |
| "eval_runtime": 65.4953, | |
| "eval_samples_per_second": 13.97, | |
| "eval_steps_per_second": 0.351, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.7274737423991155e-05, | |
| "loss": 1.1542, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.169766902923584, | |
| "eval_runtime": 65.4615, | |
| "eval_samples_per_second": 13.978, | |
| "eval_steps_per_second": 0.351, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.69983416252073e-05, | |
| "loss": 1.1733, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.168212652206421, | |
| "eval_runtime": 65.4725, | |
| "eval_samples_per_second": 13.975, | |
| "eval_steps_per_second": 0.351, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.672194582642344e-05, | |
| "loss": 1.1596, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.1670770645141602, | |
| "eval_runtime": 65.4866, | |
| "eval_samples_per_second": 13.972, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.644555002763958e-05, | |
| "loss": 1.1604, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.166330337524414, | |
| "eval_runtime": 65.4697, | |
| "eval_samples_per_second": 13.976, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.6169154228855724e-05, | |
| "loss": 1.1554, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.1642917394638062, | |
| "eval_runtime": 65.458, | |
| "eval_samples_per_second": 13.978, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.5892758430071865e-05, | |
| "loss": 1.1534, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.1629236936569214, | |
| "eval_runtime": 65.4858, | |
| "eval_samples_per_second": 13.972, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5616362631288005e-05, | |
| "loss": 1.1627, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.1618852615356445, | |
| "eval_runtime": 65.4438, | |
| "eval_samples_per_second": 13.981, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.5339966832504146e-05, | |
| "loss": 1.1575, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.1608364582061768, | |
| "eval_runtime": 65.4065, | |
| "eval_samples_per_second": 13.989, | |
| "eval_steps_per_second": 0.352, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.5063571033720288e-05, | |
| "loss": 1.1648, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.159523844718933, | |
| "eval_runtime": 65.4364, | |
| "eval_samples_per_second": 13.983, | |
| "eval_steps_per_second": 0.351, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.4787175234936429e-05, | |
| "loss": 1.1577, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.1583499908447266, | |
| "eval_runtime": 65.4227, | |
| "eval_samples_per_second": 13.986, | |
| "eval_steps_per_second": 0.352, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.4510779436152571e-05, | |
| "loss": 1.16, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.1572628021240234, | |
| "eval_runtime": 65.429, | |
| "eval_samples_per_second": 13.985, | |
| "eval_steps_per_second": 0.352, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 1.4234383637368712e-05, | |
| "loss": 1.1514, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.156549096107483, | |
| "eval_runtime": 65.3706, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.3957987838584854e-05, | |
| "loss": 1.1613, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.1555191278457642, | |
| "eval_runtime": 65.3524, | |
| "eval_samples_per_second": 14.001, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.3681592039800995e-05, | |
| "loss": 1.1546, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.1544185876846313, | |
| "eval_runtime": 65.3797, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.3405196241017137e-05, | |
| "loss": 1.1491, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1530828475952148, | |
| "eval_runtime": 65.3838, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.312880044223328e-05, | |
| "loss": 1.1517, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.152304768562317, | |
| "eval_runtime": 65.3976, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.285240464344942e-05, | |
| "loss": 1.1519, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.1511619091033936, | |
| "eval_runtime": 65.3815, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.2576008844665563e-05, | |
| "loss": 1.1455, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.1500450372695923, | |
| "eval_runtime": 65.3586, | |
| "eval_samples_per_second": 14.0, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.2299613045881703e-05, | |
| "loss": 1.1257, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.149997591972351, | |
| "eval_runtime": 65.3761, | |
| "eval_samples_per_second": 13.996, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 1.2023217247097844e-05, | |
| "loss": 1.1252, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.149656891822815, | |
| "eval_runtime": 65.396, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.1746821448313986e-05, | |
| "loss": 1.1324, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.1489354372024536, | |
| "eval_runtime": 65.4189, | |
| "eval_samples_per_second": 13.987, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.1470425649530129e-05, | |
| "loss": 1.1194, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 1.1480780839920044, | |
| "eval_runtime": 65.3723, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.119402985074627e-05, | |
| "loss": 1.1201, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.1470924615859985, | |
| "eval_runtime": 65.3931, | |
| "eval_samples_per_second": 13.992, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.0917634051962412e-05, | |
| "loss": 1.1206, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 1.1463979482650757, | |
| "eval_runtime": 65.3812, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.0641238253178552e-05, | |
| "loss": 1.1237, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.1460208892822266, | |
| "eval_runtime": 65.4045, | |
| "eval_samples_per_second": 13.99, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.0364842454394693e-05, | |
| "loss": 1.1252, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 1.1448407173156738, | |
| "eval_runtime": 65.3974, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.0088446655610835e-05, | |
| "loss": 1.1097, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.144822597503662, | |
| "eval_runtime": 65.4129, | |
| "eval_samples_per_second": 13.988, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.812050856826976e-06, | |
| "loss": 1.1136, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_loss": 1.1438499689102173, | |
| "eval_runtime": 65.3802, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 9.535655058043118e-06, | |
| "loss": 1.1188, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.1431740522384644, | |
| "eval_runtime": 65.408, | |
| "eval_samples_per_second": 13.989, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 1.1229, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.1426993608474731, | |
| "eval_runtime": 65.4152, | |
| "eval_samples_per_second": 13.988, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 8.9828634604754e-06, | |
| "loss": 1.1158, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_loss": 1.142805814743042, | |
| "eval_runtime": 65.389, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 8.706467661691544e-06, | |
| "loss": 1.1123, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.141711950302124, | |
| "eval_runtime": 65.4062, | |
| "eval_samples_per_second": 13.99, | |
| "eval_steps_per_second": 0.352, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 8.430071862907685e-06, | |
| "loss": 1.1088, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.1413805484771729, | |
| "eval_runtime": 65.3833, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 8.153676064123827e-06, | |
| "loss": 1.1166, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.1401617527008057, | |
| "eval_runtime": 65.3721, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 7.877280265339968e-06, | |
| "loss": 1.1058, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 1.139762282371521, | |
| "eval_runtime": 65.366, | |
| "eval_samples_per_second": 13.998, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 7.600884466556109e-06, | |
| "loss": 1.1117, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.139173984527588, | |
| "eval_runtime": 65.3916, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 7.3244886677722505e-06, | |
| "loss": 1.1094, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.138359546661377, | |
| "eval_runtime": 65.3904, | |
| "eval_samples_per_second": 13.993, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 7.048092868988391e-06, | |
| "loss": 1.1086, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.1380010843276978, | |
| "eval_runtime": 65.4015, | |
| "eval_samples_per_second": 13.991, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 6.771697070204533e-06, | |
| "loss": 1.1123, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.137791395187378, | |
| "eval_runtime": 65.3778, | |
| "eval_samples_per_second": 13.996, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.495301271420674e-06, | |
| "loss": 1.1192, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.137495994567871, | |
| "eval_runtime": 65.4289, | |
| "eval_samples_per_second": 13.985, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 6.2189054726368165e-06, | |
| "loss": 1.1047, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.1372565031051636, | |
| "eval_runtime": 65.3657, | |
| "eval_samples_per_second": 13.998, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.942509673852958e-06, | |
| "loss": 1.1084, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.136530876159668, | |
| "eval_runtime": 65.37, | |
| "eval_samples_per_second": 13.997, | |
| "eval_steps_per_second": 0.352, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 5.666113875069099e-06, | |
| "loss": 1.1137, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.1357197761535645, | |
| "eval_runtime": 65.3617, | |
| "eval_samples_per_second": 13.999, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.38971807628524e-06, | |
| "loss": 1.1139, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.1352890729904175, | |
| "eval_runtime": 65.3665, | |
| "eval_samples_per_second": 13.998, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.1133222775013826e-06, | |
| "loss": 1.1122, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.1347852945327759, | |
| "eval_runtime": 65.3678, | |
| "eval_samples_per_second": 13.998, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.836926478717524e-06, | |
| "loss": 1.1148, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 1.134663462638855, | |
| "eval_runtime": 65.381, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.560530679933666e-06, | |
| "loss": 1.116, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.134074330329895, | |
| "eval_runtime": 65.3847, | |
| "eval_samples_per_second": 13.994, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.284134881149806e-06, | |
| "loss": 1.105, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 1.1337759494781494, | |
| "eval_runtime": 65.3676, | |
| "eval_samples_per_second": 13.998, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.007739082365948e-06, | |
| "loss": 1.1155, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.1333887577056885, | |
| "eval_runtime": 65.3814, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.7313432835820893e-06, | |
| "loss": 1.1082, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.1329772472381592, | |
| "eval_runtime": 65.3817, | |
| "eval_samples_per_second": 13.995, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.4549474847982316e-06, | |
| "loss": 1.1145, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 1.1328340768814087, | |
| "eval_runtime": 65.4303, | |
| "eval_samples_per_second": 13.984, | |
| "eval_steps_per_second": 0.352, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.1785516860143727e-06, | |
| "loss": 1.1078, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.1321594715118408, | |
| "eval_runtime": 65.5896, | |
| "eval_samples_per_second": 13.95, | |
| "eval_steps_per_second": 0.351, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.902155887230514e-06, | |
| "loss": 1.1041, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.1319067478179932, | |
| "eval_runtime": 65.4493, | |
| "eval_samples_per_second": 13.98, | |
| "eval_steps_per_second": 0.351, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.6257600884466557e-06, | |
| "loss": 1.0935, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.1322442293167114, | |
| "eval_runtime": 65.3072, | |
| "eval_samples_per_second": 14.011, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.349364289662797e-06, | |
| "loss": 1.0906, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 1.1326180696487427, | |
| "eval_runtime": 65.2969, | |
| "eval_samples_per_second": 14.013, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.0729684908789387e-06, | |
| "loss": 1.1016, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 1.132248878479004, | |
| "eval_runtime": 65.2925, | |
| "eval_samples_per_second": 14.014, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.7965726920950804e-06, | |
| "loss": 1.0907, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.1321300268173218, | |
| "eval_runtime": 65.2955, | |
| "eval_samples_per_second": 14.013, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.5201768933112217e-06, | |
| "loss": 1.0908, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.1320557594299316, | |
| "eval_runtime": 65.2825, | |
| "eval_samples_per_second": 14.016, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.2437810945273632e-06, | |
| "loss": 1.0997, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.131882667541504, | |
| "eval_runtime": 65.2854, | |
| "eval_samples_per_second": 14.015, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.673852957435047e-07, | |
| "loss": 1.0856, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.1319279670715332, | |
| "eval_runtime": 65.279, | |
| "eval_samples_per_second": 14.017, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 6.909894969596462e-07, | |
| "loss": 1.0898, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 1.1317994594573975, | |
| "eval_runtime": 65.2805, | |
| "eval_samples_per_second": 14.016, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 4.145936981757878e-07, | |
| "loss": 1.0944, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.1316641569137573, | |
| "eval_runtime": 65.3051, | |
| "eval_samples_per_second": 14.011, | |
| "eval_steps_per_second": 0.352, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.3819789939192925e-07, | |
| "loss": 1.0875, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.1316481828689575, | |
| "eval_runtime": 65.2846, | |
| "eval_samples_per_second": 14.016, | |
| "eval_steps_per_second": 0.352, | |
| "step": 9000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 9050, | |
| "num_train_epochs": 2, | |
| "save_steps": 1000, | |
| "total_flos": 7.910691746781069e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |