End of training

README.md

@@ -1,3 +1,72 @@
 ---
-license: mit
+license: bsd-3-clause
+base_model: MIT/ast-finetuned-audioset-10-10-0.450
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ast-finetuned-audioset-10-10-0.450_ESC50
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# ast-finetuned-audioset-10-10-0.450_ESC50
+
+This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.450](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.450) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2887
+- Accuracy: 0.9275
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.7745        | 0.99  | 66   | 2.3340          | 0.605    |
+| 0.7521        | 1.99  | 133  | 0.8978          | 0.8875   |
+| 0.2307        | 3.0   | 200  | 0.5545          | 0.8975   |
+| 0.0903        | 4.0   | 267  | 0.4063          | 0.925    |
+| 0.03          | 4.99  | 333  | 0.3488          | 0.92     |
+| 0.0123        | 5.99  | 400  | 0.2987          | 0.925    |
+| 0.0101        | 7.0   | 467  | 0.2887          | 0.9275   |
+| 0.0067        | 8.0   | 534  | 0.2808          | 0.9275   |
+| 0.0055        | 8.99  | 600  | 0.2784          | 0.9275   |
+| 0.0051        | 9.89  | 660  | 0.2778          | 0.9275   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,129 @@
+{
+  "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.450",
+  "architectures": [
+    "ASTForAudioClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "frequency_stride": 10,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "dog",
+    "1": "rooster",
+    "2": "pig",
+    "3": "cow",
+    "4": "frog",
+    "5": "cat",
+    "6": "hen",
+    "7": "insects",
+    "8": "sheep",
+    "9": "crow",
+    "10": "rain",
+    "11": "sea_waves",
+    "12": "crackling_fire",
+    "13": "crickets",
+    "14": "chirping_birds",
+    "15": "water_drops",
+    "16": "wind",
+    "17": "pouring_water",
+    "18": "toilet_flush",
+    "19": "thunderstorm",
+    "20": "crying_baby",
+    "21": "sneezing",
+    "22": "clapping",
+    "23": "breathing",
+    "24": "coughing",
+    "25": "footsteps",
+    "26": "laughing",
+    "27": "brushing_teeth",
+    "28": "snoring",
+    "29": "drinking_sipping",
+    "30": "door_wood_knock",
+    "31": "mouse_click",
+    "32": "keyboard_typing",
+    "33": "door_wood_creaks",
+    "34": "can_opening",
+    "35": "washing_machine",
+    "36": "vacuum_cleaner",
+    "37": "clock_alarm",
+    "38": "clock_tick",
+    "39": "glass_breaking",
+    "40": "helicopter",
+    "41": "chainsaw",
+    "42": "siren",
+    "43": "car_horn",
+    "44": "engine",
+    "45": "train",
+    "46": "church_bells",
+    "47": "airplane",
+    "48": "fireworks",
+    "49": "hand_saw"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "airplane": 47,
+    "breathing": 23,
+    "brushing_teeth": 27,
+    "can_opening": 34,
+    "car_horn": 43,
+    "cat": 5,
+    "chainsaw": 41,
+    "chirping_birds": 14,
+    "church_bells": 46,
+    "clapping": 22,
+    "clock_alarm": 37,
+    "clock_tick": 38,
+    "coughing": 24,
+    "cow": 3,
+    "crackling_fire": 12,
+    "crickets": 13,
+    "crow": 9,
+    "crying_baby": 20,
+    "dog": 0,
+    "door_wood_creaks": 33,
+    "door_wood_knock": 30,
+    "drinking_sipping": 29,
+    "engine": 44,
+    "fireworks": 48,
+    "footsteps": 25,
+    "frog": 4,
+    "glass_breaking": 39,
+    "hand_saw": 49,
+    "helicopter": 40,
+    "hen": 6,
+    "insects": 7,
+    "keyboard_typing": 32,
+    "laughing": 26,
+    "mouse_click": 31,
+    "pig": 2,
+    "pouring_water": 17,
+    "rain": 10,
+    "rooster": 1,
+    "sea_waves": 11,
+    "sheep": 8,
+    "siren": 42,
+    "sneezing": 21,
+    "snoring": 28,
+    "thunderstorm": 19,
+    "toilet_flush": 18,
+    "train": 45,
+    "vacuum_cleaner": 36,
+    "washing_machine": 35,
+    "water_drops": 15,
+    "wind": 16
+  },
+  "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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc01752ed54f1d27ff2ae6cfb51c873eaa63453381ce9df6f046087f9df692c
+size 344937696

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
+}

runs/Apr16_06-20-57_d86b394b49b0/events.out.tfevents.1713248458.d86b394b49b0.1349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48041ea72bff316e7fd5c593392a49eda4ca0ce365fbf8b9046070cd88b49e4
+size 6952

runs/Apr16_06-22-04_d86b394b49b0/events.out.tfevents.1713248534.d86b394b49b0.1349.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9384e7361977904104ca66f2fbd3cf524cdc209de39f1678afde7b5d60e2e64f
+size 34653

runs/Apr16_06-26-39_d86b394b49b0/events.out.tfevents.1713248800.d86b394b49b0.3419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a53198bbc8fc2c18ba873fd4387b18b3179c018726150d3006e449066303e982
+size 24408

runs/Apr16_06-26-39_d86b394b49b0/events.out.tfevents.1713255041.d86b394b49b0.3419.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52500a6fe8b402d120cd70bd6780ab333b90db9279dd612273f74bdbe491a1f4
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aebfd73f38d521ee28efc1bd8e87b47326d041ee82c2def6d38159cbda60b71
+size 5048