saketag73 commited on
Commit
d7a46cd
1 Parent(s): fa62a18

End of training

Browse files
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-finetuned-gtzan
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.8
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # distilhubert-finetuned-gtzan
29
+
30
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.7861
33
+ - Accuracy: 0.8
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 5e-05
53
+ - train_batch_size: 16
54
+ - eval_batch_size: 16
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - num_epochs: 15
60
+ - mixed_precision_training: Native AMP
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 1.9073 | 1.0 | 113 | 1.8699 | 0.4 |
67
+ | 1.3144 | 2.0 | 226 | 1.2309 | 0.625 |
68
+ | 0.8747 | 3.0 | 339 | 0.9318 | 0.74 |
69
+ | 0.6776 | 4.0 | 452 | 0.8368 | 0.735 |
70
+ | 0.383 | 5.0 | 565 | 0.6930 | 0.745 |
71
+ | 0.3383 | 6.0 | 678 | 0.8012 | 0.755 |
72
+ | 0.2922 | 7.0 | 791 | 0.6724 | 0.78 |
73
+ | 0.1086 | 8.0 | 904 | 0.7984 | 0.755 |
74
+ | 0.0409 | 9.0 | 1017 | 0.7385 | 0.805 |
75
+ | 0.0507 | 10.0 | 1130 | 0.6669 | 0.805 |
76
+ | 0.0424 | 11.0 | 1243 | 0.7698 | 0.815 |
77
+ | 0.0078 | 12.0 | 1356 | 0.7985 | 0.81 |
78
+ | 0.0068 | 13.0 | 1469 | 0.7679 | 0.81 |
79
+ | 0.0063 | 14.0 | 1582 | 0.8139 | 0.795 |
80
+ | 0.0065 | 15.0 | 1695 | 0.7861 | 0.8 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.38.2
86
+ - Pytorch 2.2.1+cu121
87
+ - Datasets 2.19.0
88
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.2,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.2,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.2,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.2,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.2,
50
+ "hidden_size": 768,
51
+ "id2label": {
52
+ "0": "blues",
53
+ "1": "classical",
54
+ "2": "country",
55
+ "3": "disco",
56
+ "4": "hiphop",
57
+ "5": "jazz",
58
+ "6": "metal",
59
+ "7": "pop",
60
+ "8": "reggae",
61
+ "9": "rock"
62
+ },
63
+ "initializer_range": 0.02,
64
+ "intermediate_size": 3072,
65
+ "label2id": {
66
+ "blues": "0",
67
+ "classical": "1",
68
+ "country": "2",
69
+ "disco": "3",
70
+ "hiphop": "4",
71
+ "jazz": "5",
72
+ "metal": "6",
73
+ "pop": "7",
74
+ "reggae": "8",
75
+ "rock": "9"
76
+ },
77
+ "layer_norm_eps": 1e-05,
78
+ "layerdrop": 0.0,
79
+ "mask_feature_length": 10,
80
+ "mask_feature_min_masks": 0,
81
+ "mask_feature_prob": 0.0,
82
+ "mask_time_length": 10,
83
+ "mask_time_min_masks": 2,
84
+ "mask_time_prob": 0.05,
85
+ "model_type": "hubert",
86
+ "num_attention_heads": 12,
87
+ "num_conv_pos_embedding_groups": 16,
88
+ "num_conv_pos_embeddings": 128,
89
+ "num_feat_extract_layers": 7,
90
+ "num_hidden_layers": 2,
91
+ "pad_token_id": 0,
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.38.2",
94
+ "use_weighted_layer_sum": false,
95
+ "vocab_size": 32
96
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bd849908a8fad753dbf7bff2a0aff6ad40e1a64b3d9b177ada74adc8b7d251
3
+ size 94771728
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
runs/Apr21_11-00-55_47a38f36bf3c/events.out.tfevents.1713697259.47a38f36bf3c.941.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8108f6495bb10e48abf0c25ffb614e567a79ab861493d2282e662c08b423cfa1
3
+ size 82459
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b1083926797f9f9c3d7220f580859ec35b5635fb050c80a997b7970e5dbea41
3
+ size 4984