{ "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": 2.0719, "step": 3 }, { "epoch": 0.0, "learning_rate": 0.00019793814432989693, "loss": 2.1789, "step": 4 }, { "epoch": 0.0, "learning_rate": 0.00019587628865979381, "loss": 1.9318, "step": 5 }, { "epoch": 0.0, "learning_rate": 0.00019381443298969073, "loss": 2.4083, "step": 6 }, { "epoch": 0.0, "learning_rate": 0.00019175257731958765, "loss": 2.6823, "step": 7 }, { "epoch": 0.0, "learning_rate": 0.00018969072164948454, "loss": 1.5946, "step": 8 }, { "epoch": 0.0, "learning_rate": 0.00018762886597938145, "loss": 2.0224, "step": 9 }, { "epoch": 0.0, "learning_rate": 0.00018556701030927837, "loss": 2.0527, "step": 10 }, { "epoch": 0.0, "learning_rate": 0.00018350515463917526, "loss": 1.8021, "step": 11 }, { "epoch": 0.0, "learning_rate": 0.00018144329896907217, "loss": 2.0241, "step": 12 }, { "epoch": 0.01, "learning_rate": 0.0001793814432989691, "loss": 1.8196, "step": 13 }, { "epoch": 0.01, "learning_rate": 0.00017731958762886598, "loss": 1.8936, "step": 14 }, { "epoch": 0.01, "learning_rate": 0.0001752577319587629, "loss": 1.797, "step": 15 } ], "logging_steps": 1, "max_steps": 100, "num_train_epochs": 1, "save_steps": 5, "total_flos": 1808974570045440.0, "trial_name": null, "trial_params": null }