| {"adam_epsilon": 1e-08, "best_model_dir": "outputs/de_model_ds/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": true, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 30, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 64, "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": 3e-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": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 200, "optimizer": "AdamW", "output_dir": "outputs/de_model_ds", "overwrite_output_dir": true, "process_count": 254, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "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_steps": -1, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_type": null, "tokenizer_name": null, "train_batch_size": 64, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": "sl-tagging", "warmup_ratio": 0.06, "warmup_steps": 66468, "weight_decay": 0.01, "model_class": "NERModel", "classification_report": true, "labels_list": ["O", "B-PROBLEM", "I-PROBLEM", "E-PROBLEM", "S-PROBLEM", "B-TREATMENT", "I-TREATMENT", "E-TREATMENT", "S-TREATMENT", "B-TEST", "I-TEST", "E-TEST", "S-TEST"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []} |