Abhinay45 commited on
Commit
0faaf25
1 Parent(s): c3e0548

End of training

Browse files
Files changed (5) hide show
  1. README.md +54 -0
  2. config.json +49 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +13 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bsd-3-clause
3
+ base_model: MIT/ast-finetuned-audioset-10-10-0.4593
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ model-index:
9
+ - name: ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/soundofai/huggingface-audio-course/runs/4estu7od)
17
+ # ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan
18
+
19
+ This model is a fine-tuned version of [MIT/ast-finetuned-audioset-10-10-0.4593](https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593) on the GTZAN dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 20
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.41.0.dev0
52
+ - Pytorch 2.2.1+cu121
53
+ - Datasets 2.19.0
54
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MIT/ast-finetuned-audioset-10-10-0.4593",
3
+ "architectures": [
4
+ "ASTForAudioClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "frequency_stride": 10,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "blues",
13
+ "1": "classical",
14
+ "2": "country",
15
+ "3": "disco",
16
+ "4": "hiphop",
17
+ "5": "jazz",
18
+ "6": "metal",
19
+ "7": "pop",
20
+ "8": "reggae",
21
+ "9": "rock"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "blues": "0",
27
+ "classical": "1",
28
+ "country": "2",
29
+ "disco": "3",
30
+ "hiphop": "4",
31
+ "jazz": "5",
32
+ "metal": "6",
33
+ "pop": "7",
34
+ "reggae": "8",
35
+ "rock": "9"
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "max_length": 1024,
39
+ "model_type": "audio-spectrogram-transformer",
40
+ "num_attention_heads": 12,
41
+ "num_hidden_layers": 12,
42
+ "num_mel_bins": 128,
43
+ "patch_size": 16,
44
+ "problem_type": "single_label_classification",
45
+ "qkv_bias": true,
46
+ "time_stride": 10,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.41.0.dev0"
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d192d5ce8aec9e3e5f64e175dd1ce228def4f35f76f35598c4fd4833b49403
3
+ size 344814656
preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "ASTFeatureExtractor",
4
+ "feature_size": 1,
5
+ "max_length": 1024,
6
+ "mean": -4.2677393,
7
+ "num_mel_bins": 128,
8
+ "padding_side": "right",
9
+ "padding_value": 0.0,
10
+ "return_attention_mask": false,
11
+ "sampling_rate": 16000,
12
+ "std": 4.5689974
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4998a63c4315fc2679afa0e33e4332c772314aed2f698b51dd2aafaa9db3fd8b
3
+ size 5176