{ "best_metric": 0.7221644120707597, "best_model_checkpoint": "berttiny-hateXplain-parentpretrained\\run-3\\checkpoint-484", "epoch": 4.0, "eval_steps": 500, "global_step": 484, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 3.432859087215925e-05, "loss": 0.6101, "step": 121 }, { "epoch": 1.0, "eval_accuracy": 0.6696149843912591, "eval_loss": 0.5727917551994324, "eval_runtime": 5.4304, "eval_samples_per_second": 353.931, "eval_steps_per_second": 2.946, "step": 121 }, { "epoch": 2.0, "learning_rate": 2.288572724810617e-05, "loss": 0.5466, "step": 242 }, { "epoch": 2.0, "eval_accuracy": 0.7096774193548387, "eval_loss": 0.5379418134689331, "eval_runtime": 5.3325, "eval_samples_per_second": 360.429, "eval_steps_per_second": 3.0, "step": 242 }, { "epoch": 3.0, "learning_rate": 1.1442863624053085e-05, "loss": 0.5163, "step": 363 }, { "epoch": 3.0, "eval_accuracy": 0.7185223725286161, "eval_loss": 0.5288857817649841, "eval_runtime": 5.421, "eval_samples_per_second": 354.547, "eval_steps_per_second": 2.951, "step": 363 }, { "epoch": 4.0, "learning_rate": 0.0, "loss": 0.5044, "step": 484 }, { "epoch": 4.0, "eval_accuracy": 0.7221644120707597, "eval_loss": 0.5248228907585144, "eval_runtime": 5.5066, "eval_samples_per_second": 349.037, "eval_steps_per_second": 2.906, "step": 484 } ], "logging_steps": 500, "max_steps": 484, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 10998668340780.0, "trial_name": null, "trial_params": { "alpha": 0.9476011981470215, "learning_rate": 4.577145449621234e-05, "num_train_epochs": 4, "temperature": 6 } }