| {"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "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": 3, "encoding": null, "eval_batch_size": 16, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "bert-base-cased", "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 30, "optimizer": "AdamW", "output_dir": "bert-ner-model_new", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 10, "quantized_model": false, "reprocess_input_data": true, "save_best_model": "bert-ner-model_new", "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 96, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": false, "labels_list": ["O", "B-TA", "I-TA", "B-PRO", "I-PRO", "B-TEM", "I-TEM", "B-COM", "I-COM", "B-PAR", "I-PAR", "B-CIT", "I-CIT", "B-MOU", "I-MOU", "B-HAM", "I-HAM", "B-AWA", "I-AWA", "B-VIS", "I-VIS", "B-FES", "I-FES", "B-ISL", "I-ISL", "B-TOW", "I-TOW", "B-VIL", "I-VIL", "B-CHU", "I-CHU", "B-PAG", "I-PAG", "B-BEA", "I-BEA", "B-WAR", "I-WAR", "B-WAT", "I-WAT", "B-SA", "I-SA", "B-SER", "I-SER", "B-STR", "I-STR", "B-NUN", "I-NUN", "B-PAL", "I-PAL", "B-VOL", "I-VOL", "B-HIL", "I-HIL", "B-MAR", "I-MAR", "B-VAL", "I-VAL", "B-PROD", "I-PROD", "B-DIS", "I-DIS", "B-FOO", "I-FOO", "B-DISH", "I-DISH", "B-DRI", "I-DRI"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []} |