{ "best_metric": 0.879798903107861, "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-43\\checkpoint-1916", "epoch": 4.0, "eval_steps": 500, "global_step": 1916, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "learning_rate": 5.34554568566064e-05, "loss": 0.483, "step": 479 }, { "epoch": 1.0, "eval_accuracy": 0.8596892138939671, "eval_loss": 0.47507455945014954, "eval_runtime": 10.9084, "eval_samples_per_second": 200.58, "eval_steps_per_second": 1.65, "step": 479 }, { "epoch": 2.0, "learning_rate": 3.56369712377376e-05, "loss": 0.4592, "step": 958 }, { "epoch": 2.0, "eval_accuracy": 0.8779707495429616, "eval_loss": 0.4689006209373474, "eval_runtime": 10.9282, "eval_samples_per_second": 200.215, "eval_steps_per_second": 1.647, "step": 958 }, { "epoch": 3.0, "learning_rate": 1.78184856188688e-05, "loss": 0.4483, "step": 1437 }, { "epoch": 3.0, "eval_accuracy": 0.8784277879341865, "eval_loss": 0.4681478440761566, "eval_runtime": 10.9709, "eval_samples_per_second": 199.438, "eval_steps_per_second": 1.641, "step": 1437 }, { "epoch": 4.0, "learning_rate": 0.0, "loss": 0.4428, "step": 1916 }, { "epoch": 4.0, "eval_accuracy": 0.879798903107861, "eval_loss": 0.46910566091537476, "eval_runtime": 10.8704, "eval_samples_per_second": 201.28, "eval_steps_per_second": 1.656, "step": 1916 } ], "logging_steps": 500, "max_steps": 1916, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 4969223449632.0, "trial_name": null, "trial_params": { "learning_rate": 7.12739424754752e-05, "num_train_epochs": 4, "per_device_train_batch_size": 16, "seed": 34 } }