| {"_name_or_path": "lmqg_output/optimized/bart_large_squad/model_byrqch/epoch_2", "activation_dropout": 0.1, "activation_function": "gelu", "add_bias_logits": false, "add_final_layer_norm": false, "architectures": ["BartForConditionalGeneration"], "attention_dropout": 0.1, "bos_token_id": 0, "classif_dropout": 0.1, "classifier_dropout": 0.0, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "dropout": 0.1, "early_stopping": true, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 2, "forced_eos_token_id": 2, "gradient_checkpointing": false, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "init_std": 0.02, "is_encoder_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "max_position_embeddings": 1024, "model_type": "bart", "no_repeat_ngram_size": 3, "normalize_before": false, "num_beams": 4, "num_hidden_layers": 12, "pad_token_id": 1, "scale_embedding": false, "task_specific_params": {"summarization": {"length_penalty": 1.0, "max_length": 128, "min_length": 12, "num_beams": 4}, "summarization_cnn": {"length_penalty": 2.0, "max_length": 142, "min_length": 56, "num_beams": 4}, "summarization_xsum": {"length_penalty": 1.0, "max_length": 62, "min_length": 11, "num_beams": 6}}, "transformers_version": "4.8.2", "use_cache": true, "vocab_size": 50266, "add_prefix": false} |