Training in progress, epoch 0

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
+  "activation_dropout": 0.8,
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_dropout": 0.8,
+  "attention_probs_dropout_prob": 0.0,
+  "final_dropout": 0.8,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.8,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "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": "4.32.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,13 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "ASTFeatureExtractor",
+  "feature_size": 1,
+  "max_length": 1024,
+  "mean": -4.2677393,
+  "num_mel_bins": 128,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000,
+  "std": 4.5689974
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e4d7c23a004c525b29b93c67f3b4f7265e90601eff9e3bc0db70f8d8199996
+size 344860025

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687c617ad8f69b5465e984cff0e888bfb571126db388d986adc305b4ce4b03b7
+size 4091