{ "best_metric": 0.8848263254113345, "best_model_checkpoint": "distilbert-hate_speech18\\run-3\\checkpoint-960", "epoch": 4.0, "eval_steps": 500, "global_step": 960, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 2.741556032723218e-06, "loss": 0.3969, "step": 240 }, { "epoch": 1.0, "eval_accuracy": 0.8606032906764168, "eval_loss": 0.38725385069847107, "eval_runtime": 13.634, "eval_samples_per_second": 160.481, "eval_steps_per_second": 5.061, "step": 240 }, { "epoch": 2.0, "learning_rate": 2.0561670245424133e-06, "loss": 0.3833, "step": 480 }, { "epoch": 2.0, "eval_accuracy": 0.8816270566727605, "eval_loss": 0.3825770616531372, "eval_runtime": 13.6065, "eval_samples_per_second": 160.806, "eval_steps_per_second": 5.071, "step": 480 }, { "epoch": 3.0, "learning_rate": 1.370778016361609e-06, "loss": 0.3791, "step": 720 }, { "epoch": 3.0, "eval_accuracy": 0.8834552102376599, "eval_loss": 0.38152310252189636, "eval_runtime": 13.6038, "eval_samples_per_second": 160.837, "eval_steps_per_second": 5.072, "step": 720 }, { "epoch": 4.0, "learning_rate": 6.853890081808044e-07, "loss": 0.3767, "step": 960 }, { "epoch": 4.0, "eval_accuracy": 0.8848263254113345, "eval_loss": 0.37997502088546753, "eval_runtime": 13.589, "eval_samples_per_second": 161.012, "eval_steps_per_second": 5.078, "step": 960 } ], "logging_steps": 500, "max_steps": 1200, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "total_flos": 651630374965248.0, "trial_name": null, "trial_params": { "alpha": 0.3534065692399305, "learning_rate": 3.4269450409040222e-06, "num_train_epochs": 5, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "temperature": 11 } }