| { | |
| "_name_or_path": "lmqg_output/trimmed_qa/mbart-large-cc25-trimmed-es-esquad-qa/best_model", | |
| "_num_labels": 3, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_bias_logits": false, | |
| "add_final_layer_norm": true, | |
| "add_prefix": false, | |
| "architectures": [ | |
| "MBartForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classif_dropout": 0.0, | |
| "classifier_dropout": 0.0, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "dropout": 0.1, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 2, | |
| "forced_eos_token_id": 2, | |
| "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_length": 1024, | |
| "max_position_embeddings": 1024, | |
| "model_type": "mbart", | |
| "normalize_before": true, | |
| "normalize_embedding": true, | |
| "num_beams": 5, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 1, | |
| "scale_embedding": true, | |
| "static_position_embeddings": false, | |
| "task_specific_params": { | |
| "translation_en_to_ro": { | |
| "decoder_start_token_id": 250020 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "use_cache": true, | |
| "vocab_size": 87106, | |
| "vocabtrimmer": { | |
| "mining_config": { | |
| "dataset": "vocabtrimmer/mc4_validation", | |
| "dataset_column": "text", | |
| "dataset_name": "es", | |
| "dataset_split": "validation", | |
| "language": "es", | |
| "min_frequency": 2, | |
| "target_vocab_size": null | |
| }, | |
| "stats": { | |
| "compression_rate_embedding": 34.8382374703532, | |
| "compression_rate_full": 72.6886100564091, | |
| "parameter_size_embedding/raw": 512055296, | |
| "parameter_size_embedding/trimmed": 178391040, | |
| "parameter_size_full/raw": 610851840, | |
| "parameter_size_full/trimmed": 444019712, | |
| "vocab_size/raw": 250027, | |
| "vocab_size/trimmed": 87105 | |
| } | |
| } | |
| } | |