{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "global_step": 2625, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.57, "learning_rate": 4.047619047619048e-05, "loss": 0.3398, "step": 500 }, { "epoch": 1.0, "eval_accuracy": 0.9404197400772744, "eval_f1": 0.7127468581687613, "eval_loss": 0.16514258086681366, "eval_precision": 0.6821305841924399, "eval_recall": 0.7462406015037594, "eval_runtime": 8.3315, "eval_samples_per_second": 96.741, "eval_steps_per_second": 12.123, "step": 875 }, { "epoch": 1.14, "learning_rate": 3.095238095238095e-05, "loss": 0.1895, "step": 1000 }, { "epoch": 1.71, "learning_rate": 2.1428571428571428e-05, "loss": 0.1346, "step": 1500 }, { "epoch": 2.0, "eval_accuracy": 0.9471812434141201, "eval_f1": 0.7536488279522335, "eval_loss": 0.15585720539093018, "eval_precision": 0.7117794486215538, "eval_recall": 0.8007518796992481, "eval_runtime": 8.3949, "eval_samples_per_second": 96.011, "eval_steps_per_second": 12.031, "step": 1750 }, { "epoch": 2.29, "learning_rate": 1.1904761904761905e-05, "loss": 0.1163, "step": 2000 }, { "epoch": 2.86, "learning_rate": 2.3809523809523808e-06, "loss": 0.0711, "step": 2500 }, { "epoch": 3.0, "eval_accuracy": 0.9476642079381805, "eval_f1": 0.7592425608656447, "eval_loss": 0.17694610357284546, "eval_precision": 0.729636048526863, "eval_recall": 0.7913533834586466, "eval_runtime": 8.2863, "eval_samples_per_second": 97.268, "eval_steps_per_second": 12.189, "step": 2625 } ], "max_steps": 2625, "num_train_epochs": 3, "total_flos": 697494389101650.0, "trial_name": null, "trial_params": null }