| {"adam_epsilon": 1e-08, "best_model_dir": "temp/outputs/best_model", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 1, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 300, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 300, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 140, "model_name": "temp/lm/outputs/best_model", "model_type": "bert", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 3, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_recent_only": true, "save_steps": 300, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.1, "warmup_steps": 268, "weight_decay": 0, "skip_special_tokens": true, "model_class": "LanguageModelingModel", "classification_report": false, "labels_list": ["NOT_TOXIC", "TOXIC"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false} |