{ "_name_or_path": "/content/content/results/best_model", "architectures": [ "BertForSequenceClassification" ], "attention_dropout": 0.1398512537120637, "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "dropout": 0.16756117436991105, "eval_batch_size": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "train_batch_size": 32, "transformers_version": "4.41.2", "type_vocab_size": 2, "use_cache": true, "vocab_size": 31102, "id2label": { "0": "Does NOT contain CTA", "1": "Contains CTA" }, "label2id": { "Does NOT contain CTA": 0, "Contains CTA": 1 } }