{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0014344526845781992, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0, "learning_rate": 0.00019396926207859084, "loss": 0.0, "step": 20 }, { "epoch": 0.0, "learning_rate": 0.00015000000000000001, "loss": 0.0, "step": 40 }, { "epoch": 0.0, "learning_rate": 8.263518223330697e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.0, "learning_rate": 2.339555568810221e-05, "loss": 0.0, "step": 80 }, { "epoch": 0.0, "learning_rate": 0.0, "loss": 0.0, "step": 100 }, { "epoch": 0.0, "step": 100, "total_flos": 1.768131718545408e+16, "train_loss": 0.0, "train_runtime": 501.823, "train_samples_per_second": 0.399, "train_steps_per_second": 0.199 } ], "logging_steps": 20, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "total_flos": 1.768131718545408e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }