{ "best_metric": 2.627840757369995, "best_model_checkpoint": "output/coldplay/checkpoint-48", "epoch": 1.0, "global_step": 48, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1, "learning_rate": 0.00013355940688336427, "loss": 3.2771, "step": 5 }, { "epoch": 0.21, "learning_rate": 0.00012302403914397873, "loss": 2.8643, "step": 10 }, { "epoch": 0.31, "learning_rate": 0.00010671211798514472, "loss": 2.6223, "step": 15 }, { "epoch": 0.42, "learning_rate": 8.635498649403293e-05, "loss": 2.9051, "step": 20 }, { "epoch": 0.52, "learning_rate": 6.411334533481218e-05, "loss": 2.8302, "step": 25 }, { "epoch": 0.62, "learning_rate": 4.2347916539754844e-05, "loss": 2.8412, "step": 30 }, { "epoch": 0.73, "learning_rate": 2.3368877084135277e-05, "loss": 2.7828, "step": 35 }, { "epoch": 0.83, "learning_rate": 9.190657300387505e-06, "loss": 2.6878, "step": 40 }, { "epoch": 0.94, "learning_rate": 1.3181297643383925e-06, "loss": 2.57, "step": 45 }, { "epoch": 1.0, "eval_loss": 2.627840757369995, "eval_runtime": 3.4104, "eval_samples_per_second": 21.405, "eval_steps_per_second": 2.932, "step": 48 } ], "max_steps": 48, "num_train_epochs": 1, "total_flos": 50037424128000.0, "trial_name": null, "trial_params": null }