model_args.json

{"classification_report": false, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "do_lower_case": 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": 8, "evaluate_during_training": false, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": false, "fp16": false, "fp16_opt_level": "O1", "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 1, "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 1, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_steps": 2000, "save_optimizer_and_scheduler": true, "silent": false, "tensorboard_dir": null, "train_batch_size": 8, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1296, "weight_decay": 0, "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "None", "discriminator_config": {}, "discriminator_loss_weight": 50, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": true, "mlm_probability": 0.15, "sliding_window": false, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "tokenizer_name": "distilbert-base-german-cased", "vocab_size": null, "model_name": "distilbert-base-german-cased-derstandard/", "model_type": "distilbert"}