{ "best_metric": 0.20286166667938232, "best_model_checkpoint": "model1/checkpoint-205", "epoch": 5.0, "global_step": 1025, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.931129476584022, "eval_loss": 0.20286166667938232, "eval_runtime": 7.2605, "eval_samples_per_second": 149.99, "eval_steps_per_second": 9.503, "step": 205 }, { "epoch": 2.0, "eval_accuracy": 0.9357208448117539, "eval_loss": 0.22182105481624603, "eval_runtime": 7.6337, "eval_samples_per_second": 142.657, "eval_steps_per_second": 9.039, "step": 410 }, { "epoch": 2.44, "learning_rate": 1.024390243902439e-05, "loss": 0.1905, "step": 500 }, { "epoch": 3.0, "eval_accuracy": 0.9357208448117539, "eval_loss": 0.2710420787334442, "eval_runtime": 7.705, "eval_samples_per_second": 141.337, "eval_steps_per_second": 8.955, "step": 615 }, { "epoch": 4.0, "eval_accuracy": 0.9366391184573003, "eval_loss": 0.29000386595726013, "eval_runtime": 7.7216, "eval_samples_per_second": 141.034, "eval_steps_per_second": 8.936, "step": 820 }, { "epoch": 4.88, "learning_rate": 4.878048780487805e-07, "loss": 0.0358, "step": 1000 }, { "epoch": 5.0, "eval_accuracy": 0.9366391184573003, "eval_loss": 0.30663052201271057, "eval_runtime": 7.6339, "eval_samples_per_second": 142.652, "eval_steps_per_second": 9.039, "step": 1025 } ], "max_steps": 1025, "num_train_epochs": 5, "total_flos": 939897589526400.0, "trial_name": null, "trial_params": null }