model_args.json

{
  "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": 8,
  "evaluate_during_training": false,
  "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": 5e-05,
  "local_rank": -1,
  "logging_steps": 50,
  "loss_type": null,
  "loss_args": {},
  "manual_seed": null,
  "max_grad_norm": 1.0,
  "max_seq_length": 128,
  "model_name": "model/",
  "model_type": "bart",
  "multiprocessing_chunksize": -1,
  "n_gpu": 1,
  "no_cache": false,
  "no_save": false,
  "not_saved_args": [],
  "num_train_epochs": 10,
  "optimizer": "AdamW",
  "output_dir": "outputs/",
  "overwrite_output_dir": true,
  "polynomial_decay_schedule_lr_end": 1e-07,
  "polynomial_decay_schedule_power": 1.0,
  "process_count": 6,
  "quantized_model": false,
  "reprocess_input_data": true,
  "save_best_model": true,
  "save_eval_checkpoints": true,
  "save_model_every_epoch": true,
  "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_name": null,
  "tokenizer_type": null,
  "train_batch_size": 8,
  "train_custom_parameters_only": false,
  "use_cached_eval_features": false,
  "use_early_stopping": false,
  "use_hf_datasets": false,
  "use_multiprocessing": false,
  "use_multiprocessing_for_evaluation": false,
  "wandb_kwargs": {},
  "wandb_project": "Paraphrasing with BART",
  "warmup_ratio": 0.06,
  "warmup_steps": 5609,
  "weight_decay": 0.0,
  "model_class": "Seq2SeqModel",
  "base_marian_model_name": "model/",
  "dataset_class": null,
  "dataset_cache_dir": null,
  "do_sample": false,
  "early_stopping": true,
  "evaluate_generated_text": false,
  "faiss_d": 768,
  "faiss_m": 128,
  "include_title_in_knowledge_dataset": true,
  "length_penalty": 2.0,
  "max_length": 128,
  "max_steps": -1,
  "num_beams": 4,
  "num_return_sequences": 1,
  "rag_embed_batch_size": 16,
  "repetition_penalty": 1.0,
  "save_knowledge_dataset": true,
  "save_knowledge_dataset_with_checkpoints": false,
  "split_text_character": " ",
  "split_text_n": 100,
  "src_lang": "en_XX",
  "tgt_lang": "ro_RO",
  "top_k": 100,
  "top_p": 0.95,
  "use_multiprocessed_decoding": false
}