{ "_name_or_path": "checkpoints/pretraining_checkpoints/translation_dataset/small_bert/", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 512, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 2048, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 8, "num_hidden_layers": 4, "pad_token_id": 0, "position_embedding_type": "absolute", "transformers_version": "4.6.0.dev0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }