{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9912235415591121, "eval_steps": 500, "global_step": 15, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07, "learning_rate": 1.9781476007338058e-05, "loss": 0.9148, "step": 1 }, { "epoch": 0.33, "learning_rate": 1.5000000000000002e-05, "loss": 0.9129, "step": 5 }, { "epoch": 0.66, "learning_rate": 5.000000000000003e-06, "loss": 0.906, "step": 10 }, { "epoch": 0.99, "learning_rate": 0.0, "loss": 0.8999, "step": 15 }, { "epoch": 0.99, "eval_loss": 0.8835160732269287, "eval_runtime": 42.1009, "eval_samples_per_second": 47.505, "eval_steps_per_second": 0.76, "step": 15 }, { "epoch": 0.99, "step": 15, "total_flos": 1.2602014135484416e+16, "train_loss": 0.9063981016476949, "train_runtime": 3868.736, "train_samples_per_second": 16.017, "train_steps_per_second": 0.004 } ], "logging_steps": 5, "max_steps": 15, "num_train_epochs": 1, "save_steps": 500, "total_flos": 1.2602014135484416e+16, "trial_name": null, "trial_params": null }