{ "best_metric": 0.695776641368866, "best_model_checkpoint": "output/checkpoint-100", "epoch": 0.08018442417560388, "eval_steps": 50, "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": 1.3333333333333332e-06, "loss": 0.6133, "step": 1 }, { "epoch": 0.04, "learning_rate": 5.9999999999999995e-05, "loss": 0.61, "step": 50 }, { "epoch": 0.04, "eval_accuracy": 0.6895522388059702, "eval_loss": 0.6718239784240723, "eval_runtime": 61.4305, "eval_samples_per_second": 5.453, "eval_steps_per_second": 1.367, "step": 50 }, { "epoch": 0.08, "learning_rate": 0.00012666666666666666, "loss": 0.6233, "step": 100 }, { "epoch": 0.08, "eval_accuracy": 0.6835820895522388, "eval_loss": 0.695776641368866, "eval_runtime": 61.5801, "eval_samples_per_second": 5.44, "eval_steps_per_second": 1.364, "step": 100 } ], "logging_steps": 50, "max_steps": 1247, "num_train_epochs": 1, "save_steps": 100, "total_flos": 3.729294230224896e+16, "trial_name": null, "trial_params": null }