| { | |
| "_name_or_path": "bert-base-cased", | |
| "architectures": [ | |
| "BertCRF" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bias_0": null, | |
| "classifier_dropout": null, | |
| "freeze": false, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-PER", | |
| "2": "I-PER", | |
| "3": "B-ORG", | |
| "4": "I-ORG", | |
| "5": "B-LOC", | |
| "6": "I-LOC", | |
| "7": "B-MISC", | |
| "8": "I-MISC" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "B-LOC": 5, | |
| "B-MISC": 7, | |
| "B-ORG": 3, | |
| "B-PER": 1, | |
| "I-LOC": 6, | |
| "I-MISC": 8, | |
| "I-ORG": 4, | |
| "I-PER": 2, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pooler": "last", | |
| "position_embedding_type": "absolute", | |
| "subword_alignment": "first", | |
| "test_args": { | |
| "CRF": true, | |
| "Y": "ner_tags", | |
| "dataset": "conll2003", | |
| "lowC": false, | |
| "model": "bert-base-cased", | |
| "name": "2epochslowestloss", | |
| "setting": "conll2003", | |
| "subword_alignment": "first", | |
| "task": "ner", | |
| "train_args": { | |
| "batch_size": 2, | |
| "classifier_lr": 0.001, | |
| "epochs": 2.0, | |
| "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, | |
| "weight_0": 0.01 | |
| } | |