Hugging Face's logo

AdonaiHS
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
AdonaiHS commited on
Commit
8c9aa23
•
1 Parent(s): 83689eb

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -21
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.85
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.9971
36
- - Accuracy: 0.85
37
 
38
  ## Model description
39
 
@@ -53,33 +53,22 @@ More information needed
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
- - training_steps: 3000
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.2793 | 0.88 | 100 | 2.1792 | 0.41 |
69
- | 1.992 | 1.77 | 200 | 1.6741 | 0.56 |
70
- | 1.4928 | 2.65 | 300 | 1.2795 | 0.56 |
71
- | 1.1156 | 3.54 | 400 | 0.9983 | 0.69 |
72
- | 0.9162 | 4.42 | 500 | 0.8222 | 0.73 |
73
- | 0.6785 | 5.31 | 600 | 0.8422 | 0.78 |
74
- | 0.4695 | 6.19 | 700 | 0.7034 | 0.8 |
75
- | 0.3362 | 7.08 | 800 | 0.9594 | 0.72 |
76
- | 0.2051 | 7.96 | 900 | 0.6157 | 0.84 |
77
- | 0.1242 | 8.85 | 1000 | 0.6059 | 0.86 |
78
- | 0.0678 | 9.73 | 1100 | 0.7626 | 0.86 |
79
- | 0.0479 | 10.62 | 1200 | 0.7886 | 0.84 |
80
- | 0.0216 | 11.5 | 1300 | 0.8302 | 0.85 |
81
- | 0.0202 | 12.39 | 1400 | 0.8921 | 0.86 |
82
- | 0.0155 | 13.27 | 1500 | 0.9971 | 0.85 |
83
 
84
 
85
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.58
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 1.7506
36
+ - Accuracy: 0.58
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
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
+ - training_steps: 100
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.2637 | 0.44 | 25 | 2.1478 | 0.39 |
69
+ | 2.0908 | 0.88 | 50 | 1.9407 | 0.51 |
70
+ | 1.8916 | 1.32 | 75 | 1.7992 | 0.55 |
71
+ | 1.798 | 1.75 | 100 | 1.7506 | 0.58 |
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b4c1596e96c5204045574c049f6080c867205413071850e95df85ba5dd1e1a
3
  size 94782534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc42d76faaf6e61c5a66060e5175d055184b3150ab785ad60371f9599fffe24
3
  size 94782534
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:504f30d1f315d40b94affa7506d01418a7e4c8da08b48c4f101d17e0120f767b
3
  size 4079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3287f431371faa7864d06e6661dca59b91bf1c47ebaf25150f7cf474b596e08
3
  size 4079