| { | |
| "_name_or_path": "roberta_mistfull_64batch_10epochs752", | |
| "architectures": [ | |
| "RobertaForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "eos_token_id": 2, | |
| "finetuning_task": "text-classification", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "0", | |
| "1": "1", | |
| "2": "10", | |
| "3": "11", | |
| "4": "12", | |
| "5": "13", | |
| "6": "14", | |
| "7": "15", | |
| "8": "16", | |
| "9": "17", | |
| "10": "18", | |
| "11": "19", | |
| "12": "2", | |
| "13": "20", | |
| "14": "21", | |
| "15": "22", | |
| "16": "23", | |
| "17": "24", | |
| "18": "25", | |
| "19": "26", | |
| "20": "27", | |
| "21": "3", | |
| "22": "4", | |
| "23": "5", | |
| "24": "6", | |
| "25": "7", | |
| "26": "8", | |
| "27": "9" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "label2id": { | |
| "0": 0, | |
| "1": 1, | |
| "10": 2, | |
| "11": 3, | |
| "12": 4, | |
| "13": 5, | |
| "14": 6, | |
| "15": 7, | |
| "16": 8, | |
| "17": 9, | |
| "18": 10, | |
| "19": 11, | |
| "2": 12, | |
| "20": 13, | |
| "21": 14, | |
| "22": 15, | |
| "23": 16, | |
| "24": 17, | |
| "25": 18, | |
| "26": 19, | |
| "27": 20, | |
| "3": 21, | |
| "4": 22, | |
| "5": 23, | |
| "6": 24, | |
| "7": 25, | |
| "8": 26, | |
| "9": 27 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 514, | |
| "model_type": "roberta", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "problem_type": "multi_label_classification", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.45.0.dev0", | |
| "type_vocab_size": 1, | |
| "use_cache": true, | |
| "vocab_size": 50265 | |
| } | |