{ "best_metric": NaN, "best_model_checkpoint": "/tmp/model/checkpoint-5", "epoch": 1.0, "eval_steps": 500, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2, "learning_rate": 2.5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.4, "learning_rate": 5e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.6, "learning_rate": 4.615384615384616e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.8, "learning_rate": 4.230769230769231e-05, "loss": 0.0, "step": 4 }, { "epoch": 1.0, "learning_rate": 3.846153846153846e-05, "loss": 0.0, "step": 5 }, { "epoch": 1.0, "eval_accuracy": 0.2, "eval_f1_macro": 0.06666666666666668, "eval_f1_micro": 0.20000000000000004, "eval_f1_weighted": 0.06666666666666668, "eval_loss": NaN, "eval_precision_macro": 0.04, "eval_precision_micro": 0.2, "eval_precision_weighted": 0.04, "eval_recall_macro": 0.2, "eval_recall_micro": 0.2, "eval_recall_weighted": 0.2, "eval_runtime": 1.4358, "eval_samples_per_second": 6.965, "eval_steps_per_second": 0.696, "step": 5 } ], "logging_steps": 1, "max_steps": 15, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 849638208061440.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }