danielgh commited on
Commit
f3c23b2
1 Parent(s): 84f7466

End of training

Browse files
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ config: all
20
+ split: train
21
+ args: all
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.86
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # distilhubert-finetuned-gtzan
32
+
33
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.5720
36
+ - Accuracy: 0.86
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 8
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_ratio: 0.1
62
+ - num_epochs: 10
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.8941 | 1.0 | 113 | 1.8243 | 0.56 |
70
+ | 1.1572 | 2.0 | 226 | 1.1978 | 0.7 |
71
+ | 1.035 | 3.0 | 339 | 0.9851 | 0.72 |
72
+ | 0.6312 | 4.0 | 452 | 0.8181 | 0.77 |
73
+ | 0.5429 | 5.0 | 565 | 0.6398 | 0.83 |
74
+ | 0.3732 | 6.0 | 678 | 0.5851 | 0.83 |
75
+ | 0.2133 | 7.0 | 791 | 0.5662 | 0.85 |
76
+ | 0.1017 | 8.0 | 904 | 0.6408 | 0.81 |
77
+ | 0.1394 | 9.0 | 1017 | 0.5693 | 0.85 |
78
+ | 0.0788 | 10.0 | 1130 | 0.5720 | 0.86 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.38.2
84
+ - Pytorch 2.2.1+cu121
85
+ - Datasets 2.18.0
86
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
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": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.1,
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 sha256:4711cdc3d667d562ba72bdff82cc2e2540f37abecbb61563e4536a622d04f9c2
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/Mar31_20-45-25_5bd5e296c9cd/events.out.tfevents.1711917938.5bd5e296c9cd.350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5553893f26cc06e9f94f49d4f9d9ac567d06074d2fe306bbe3cf4590b5c8cf
3
+ size 56948
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44558d2af0f6c3705c9351c9d2e8537780059f2cf200a88977df3e94fa8a1db9
3
+ size 4920