{ "_name_or_path": "/work/yuxiang1234/CLIP-dissect/fine-tuning/ast-esc50/ckpt-old/checkpoint-5000", "architectures": [ "ASTForAudioClassification" ], "attention_probs_dropout_prob": 0.0, "frequency_stride": 10, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8", "9": "LABEL_9", "10": "LABEL_10", "11": "LABEL_11", "12": "LABEL_12", "13": "LABEL_13", "14": "LABEL_14", "15": "LABEL_15", "16": "LABEL_16", "17": "LABEL_17", "18": "LABEL_18", "19": "LABEL_19", "20": "LABEL_20", "21": "LABEL_21", "22": "LABEL_22", "23": "LABEL_23", "24": "LABEL_24", "25": "LABEL_25", "26": "LABEL_26", "27": "LABEL_27", "28": "LABEL_28", "29": "LABEL_29", "30": "LABEL_30", "31": "LABEL_31", "32": "LABEL_32", "33": "LABEL_33", "34": "LABEL_34", "35": "LABEL_35", "36": "LABEL_36", "37": "LABEL_37", "38": "LABEL_38", "39": "LABEL_39", "40": "LABEL_40", "41": "LABEL_41", "42": "LABEL_42", "43": "LABEL_43", "44": "LABEL_44", "45": "LABEL_45", "46": "LABEL_46", "47": "LABEL_47", "48": "LABEL_48", "49": "LABEL_49" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_10": 10, "LABEL_11": 11, "LABEL_12": 12, "LABEL_13": 13, "LABEL_14": 14, "LABEL_15": 15, "LABEL_16": 16, "LABEL_17": 17, "LABEL_18": 18, "LABEL_19": 19, "LABEL_2": 2, "LABEL_20": 20, "LABEL_21": 21, "LABEL_22": 22, "LABEL_23": 23, "LABEL_24": 24, "LABEL_25": 25, "LABEL_26": 26, "LABEL_27": 27, "LABEL_28": 28, "LABEL_29": 29, "LABEL_3": 3, "LABEL_30": 30, "LABEL_31": 31, "LABEL_32": 32, "LABEL_33": 33, "LABEL_34": 34, "LABEL_35": 35, "LABEL_36": 36, "LABEL_37": 37, "LABEL_38": 38, "LABEL_39": 39, "LABEL_4": 4, "LABEL_40": 40, "LABEL_41": 41, "LABEL_42": 42, "LABEL_43": 43, "LABEL_44": 44, "LABEL_45": 45, "LABEL_46": 46, "LABEL_47": 47, "LABEL_48": 48, "LABEL_49": 49, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8, "LABEL_9": 9 }, "layer_norm_eps": 1e-12, "max_length": 1024, "model_type": "audio-spectrogram-transformer", "num_attention_heads": 12, "num_hidden_layers": 12, "num_mel_bins": 128, "patch_size": 16, "problem_type": "single_label_classification", "qkv_bias": true, "time_stride": 10, "torch_dtype": "float32", "transformers_version": "4.34.0" }