{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.006, "eval_steps": 1000, "global_step": 15, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 6.666666666666667e-05, "loss": 2.3598, "step": 1 }, { "epoch": 0.0, "learning_rate": 0.00013333333333333334, "loss": 2.1113, "step": 2 }, { "epoch": 0.0, "learning_rate": 0.0002, "loss": 2.0722, "step": 3 }, { "epoch": 0.0, "learning_rate": 0.00019863945578231293, "loss": 2.1798, "step": 4 }, { "epoch": 0.0, "learning_rate": 0.00019727891156462587, "loss": 1.9333, "step": 5 }, { "epoch": 0.0, "learning_rate": 0.0001959183673469388, "loss": 2.4093, "step": 6 }, { "epoch": 0.0, "learning_rate": 0.0001945578231292517, "loss": 2.6837, "step": 7 }, { "epoch": 0.0, "learning_rate": 0.00019319727891156462, "loss": 1.5956, "step": 8 }, { "epoch": 0.0, "learning_rate": 0.00019183673469387756, "loss": 2.02, "step": 9 }, { "epoch": 0.0, "learning_rate": 0.00019047619047619048, "loss": 2.0534, "step": 10 }, { "epoch": 0.0, "learning_rate": 0.00018911564625850343, "loss": 1.804, "step": 11 }, { "epoch": 0.0, "learning_rate": 0.00018775510204081634, "loss": 2.0297, "step": 12 }, { "epoch": 0.01, "learning_rate": 0.00018639455782312926, "loss": 1.8164, "step": 13 }, { "epoch": 0.01, "learning_rate": 0.0001850340136054422, "loss": 1.8929, "step": 14 }, { "epoch": 0.01, "learning_rate": 0.00018367346938775512, "loss": 1.7967, "step": 15 } ], "logging_steps": 1, "max_steps": 150, "num_train_epochs": 1, "save_steps": 5, "total_flos": 1808974570045440.0, "trial_name": null, "trial_params": null }