| { | |
| "_name_or_path": "bert-base-cased", | |
| "architectures": [ | |
| "BertForTokenClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "ADJ", | |
| "1": "ADP", | |
| "2": "ADV", | |
| "3": "AUX", | |
| "4": "CCONJ", | |
| "5": "DET", | |
| "6": "INTJ", | |
| "7": "NOUN", | |
| "8": "NUM", | |
| "9": "PART", | |
| "10": "PRON", | |
| "11": "PROPN", | |
| "12": "PUNCT", | |
| "13": "SCONJ", | |
| "14": "SYM", | |
| "15": "VERB", | |
| "16": "X" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "ADJ": 0, | |
| "ADP": 1, | |
| "ADV": 2, | |
| "AUX": 3, | |
| "CCONJ": 4, | |
| "DET": 5, | |
| "INTJ": 6, | |
| "NOUN": 7, | |
| "NUM": 8, | |
| "PART": 9, | |
| "PRON": 10, | |
| "PROPN": 11, | |
| "PUNCT": 12, | |
| "SCONJ": 13, | |
| "SYM": 14, | |
| "VERB": 15, | |
| "X": 16 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "test_args": { | |
| "Y": "labels", | |
| "dataset": "wietsedv/udpos28", | |
| "model": "bert-base-cased", | |
| "setting": "udpos", | |
| "subset": "en", | |
| "subword_alignment": "all", | |
| "task": "POS", | |
| "train_args": { | |
| "batch_size": 4, | |
| "epochs": 3, | |
| "learning_rate": 2e-05, | |
| "warmup_ratio": 0.1, | |
| "weight_decay": 0.01 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.18.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 28996 | |
| } | |