{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9997758637251448, "global_step": 7806, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.13, "learning_rate": 5e-05, "loss": 1.5943, "step": 500 }, { "epoch": 0.26, "learning_rate": 5e-05, "loss": 1.3222, "step": 1000 }, { "epoch": 0.38, "learning_rate": 5e-05, "loss": 1.2248, "step": 1500 }, { "epoch": 0.51, "learning_rate": 5e-05, "loss": 1.1644, "step": 2000 }, { "epoch": 0.64, "learning_rate": 5e-05, "loss": 1.1237, "step": 2500 }, { "epoch": 0.77, "learning_rate": 5e-05, "loss": 1.0812, "step": 3000 }, { "epoch": 0.9, "learning_rate": 5e-05, "loss": 1.0478, "step": 3500 }, { "epoch": 1.02, "learning_rate": 5e-05, "loss": 1.0206, "step": 4000 }, { "epoch": 1.15, "learning_rate": 5e-05, "loss": 0.9776, "step": 4500 }, { "epoch": 1.28, "learning_rate": 5e-05, "loss": 0.9567, "step": 5000 }, { "epoch": 1.41, "learning_rate": 5e-05, "loss": 0.9352, "step": 5500 }, { "epoch": 1.54, "learning_rate": 5e-05, "loss": 0.9128, "step": 6000 }, { "epoch": 1.67, "learning_rate": 5e-05, "loss": 0.9002, "step": 6500 }, { "epoch": 1.79, "learning_rate": 5e-05, "loss": 0.8833, "step": 7000 }, { "epoch": 1.92, "learning_rate": 5e-05, "loss": 0.866, "step": 7500 }, { "epoch": 2.0, "step": 7806, "total_flos": 586555202732032.0, "train_loss": 1.0591433517999476, "train_runtime": 246981.8418, "train_samples_per_second": 12.139, "train_steps_per_second": 0.032 } ], "max_steps": 7806, "num_train_epochs": 2, "total_flos": 586555202732032.0, "trial_name": null, "trial_params": null }