| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 12525, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.800399201596807e-05, | |
| "loss": 0.3028, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.600798403193613e-05, | |
| "loss": 0.2468, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.40119760479042e-05, | |
| "loss": 0.2372, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.201596806387226e-05, | |
| "loss": 0.2205, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0019960079840326e-05, | |
| "loss": 0.2164, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.802395209580839e-05, | |
| "loss": 0.2057, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.6027944111776455e-05, | |
| "loss": 0.2063, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.4031936127744515e-05, | |
| "loss": 0.2132, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.2035928143712576e-05, | |
| "loss": 0.1854, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.003992015968064e-05, | |
| "loss": 0.1965, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 2.8043912175648708e-05, | |
| "loss": 0.2027, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.604790419161677e-05, | |
| "loss": 0.2023, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.4051896207584833e-05, | |
| "loss": 0.1888, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.2055888223552897e-05, | |
| "loss": 0.1855, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.0059880239520957e-05, | |
| "loss": 0.1887, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.806387225548902e-05, | |
| "loss": 0.1855, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.6067864271457086e-05, | |
| "loss": 0.1828, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.407185628742515e-05, | |
| "loss": 0.1744, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.2075848303393214e-05, | |
| "loss": 0.1745, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.0079840319361278e-05, | |
| "loss": 0.1922, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 8.083832335329342e-06, | |
| "loss": 0.1827, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 6.0878243512974054e-06, | |
| "loss": 0.1682, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.091816367265469e-06, | |
| "loss": 0.1826, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.095808383233533e-06, | |
| "loss": 0.1874, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.98003992015968e-08, | |
| "loss": 0.1663, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 12525, | |
| "total_flos": 581706992910336.0, | |
| "train_loss": 0.1998214961525923, | |
| "train_runtime": 7855.9485, | |
| "train_samples_per_second": 6.377, | |
| "train_steps_per_second": 1.594 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 12525, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 581706992910336.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |