{ "_name_or_path": "./naacl_ablation_results/s_distilbert_t_bert_data_wikitext-dataset_seed_42_mlm_True_ce_0.2_mlm_0.2_cos_0.2_causal-ce_0.2_causal-cos_0.2_nm_multiple_single_multilayer_layer_6_crossway_False_int-prop_0.3_consec-token_True_masked-token_False_max-int-token_-1_eff-bs_240/", "activation": "gelu", "architectures": [ "DistilBertForMaskedLM" ], "attention_dropout": 0.1, "dim": 768, "dropout": 0.1, "hidden_dim": 3072, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "output_hidden_states": true, "pad_token_id": 0, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": true, "tie_weights_": true, "torch_dtype": "float32", "transformers_version": "4.18.0", "vocab_size": 30522 }