Hugging Face's logo

vapari
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
vapari commited on
Commit
1ebfc03
•
1 Parent(s): a0fe08c

End of training

Browse files
Files changed (2) hide show
  1. README.md +99 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: ntu-spml/distilhubert
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - marsyas/gtzan
9
+ metrics:
10
+ - accuracy
11
+ model-index:
12
+ - name: distilhubert-finetuned-gtzan
13
+ results:
14
+ - task:
15
+ name: Audio Classification
16
+ type: audio-classification
17
+ dataset:
18
+ name: GTZAN
19
+ type: marsyas/gtzan
20
+ config: all
21
+ split: train
22
+ args: all
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.8333333333333334
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # distilhubert-finetuned-gtzan
33
+
34
+ This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.7729
37
+ - Accuracy: 0.8333
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 10
58
+ - eval_batch_size: 10
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 2
61
+ - total_train_batch_size: 20
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 20
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
+ | 2.188 | 1.0 | 35 | 2.1681 | 0.2692 |
73
+ | 1.887 | 2.0 | 70 | 1.8252 | 0.5769 |
74
+ | 1.5321 | 3.0 | 105 | 1.4375 | 0.5385 |
75
+ | 1.0946 | 4.0 | 140 | 1.2295 | 0.6282 |
76
+ | 0.9091 | 5.0 | 175 | 1.0390 | 0.6923 |
77
+ | 0.6839 | 6.0 | 210 | 0.9047 | 0.7821 |
78
+ | 0.5769 | 7.0 | 245 | 0.8309 | 0.7308 |
79
+ | 0.4118 | 8.0 | 280 | 0.9522 | 0.6538 |
80
+ | 0.3767 | 9.0 | 315 | 0.8164 | 0.7308 |
81
+ | 0.2247 | 10.0 | 350 | 0.6987 | 0.8205 |
82
+ | 0.1392 | 11.0 | 385 | 0.7565 | 0.7692 |
83
+ | 0.0886 | 12.0 | 420 | 0.7082 | 0.8205 |
84
+ | 0.0583 | 13.0 | 455 | 0.7529 | 0.8205 |
85
+ | 0.0383 | 14.0 | 490 | 0.7678 | 0.7949 |
86
+ | 0.0345 | 15.0 | 525 | 0.7480 | 0.8333 |
87
+ | 0.0269 | 16.0 | 560 | 0.7542 | 0.8333 |
88
+ | 0.0246 | 17.0 | 595 | 0.7550 | 0.8205 |
89
+ | 0.0233 | 18.0 | 630 | 0.7725 | 0.8333 |
90
+ | 0.0225 | 19.0 | 665 | 0.7701 | 0.8333 |
91
+ | 0.0225 | 20.0 | 700 | 0.7729 | 0.8333 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.45.1
97
+ - Pytorch 2.4.1+cu121
98
+ - Datasets 3.0.1
99
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d4813ed3952e99f71f869e5705aa82ae6bdf608a120de698e3a0e9f2b779a1b
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c9103f5743f413cbe3e73566611dfe793f811c02814264519dd4e68a7aafd2
3
  size 94771728