{ "best_metric": null, "best_model_checkpoint": null, "epoch": 6.25, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0684, "eval_samples_per_second": 2901.651, "eval_steps_per_second": 15.912, "step": 80 }, { "epoch": 2.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.085, "eval_samples_per_second": 2857.108, "eval_steps_per_second": 15.668, "step": 160 }, { "epoch": 3.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0741, "eval_samples_per_second": 2886.267, "eval_steps_per_second": 15.828, "step": 240 }, { "epoch": 4.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0619, "eval_samples_per_second": 2919.396, "eval_steps_per_second": 16.01, "step": 320 }, { "epoch": 5.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0935, "eval_samples_per_second": 2834.951, "eval_steps_per_second": 15.547, "step": 400 }, { "epoch": 6.0, "eval_accuracy": 0.0064516129032258064, "eval_loss": NaN, "eval_runtime": 1.0912, "eval_samples_per_second": 2841.003, "eval_steps_per_second": 15.58, "step": 480 }, { "epoch": 6.25, "learning_rate": 2.1428571428571427e-06, "loss": 0.0, "step": 500 } ], "logging_steps": 500, "max_steps": 560, "num_input_tokens_seen": 0, "num_train_epochs": 7, "save_steps": 500, "total_flos": 591309336775836.0, "train_batch_size": 192, "trial_name": null, "trial_params": { "alpha": 0.8888205059702218, "num_train_epochs": 7, "temperature": 15 } }