Hugging Face's logo

jkorstad
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
PyTorch
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jkorstad commited on
Commit
2d6288c
·
verified ·
1 Parent(s): 2f78080

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9
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: 0.6062
36
- - Accuracy: 0.9
37
 
38
  ## Model description
39
 
@@ -52,7 +52,7 @@ More information needed
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
@@ -60,31 +60,32 @@ The following hyperparameters were used during training:
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
  - num_epochs: 15
 
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.0776 | 1.0 | 113 | 1.9082 | 0.48 |
69
- | 1.3768 | 2.0 | 226 | 1.3052 | 0.63 |
70
- | 1.0741 | 3.0 | 339 | 0.9721 | 0.79 |
71
- | 0.778 | 4.0 | 452 | 0.8452 | 0.76 |
72
- | 0.6383 | 5.0 | 565 | 0.5935 | 0.85 |
73
- | 0.3313 | 6.0 | 678 | 0.5947 | 0.81 |
74
- | 0.3514 | 7.0 | 791 | 0.6064 | 0.8 |
75
- | 0.0922 | 8.0 | 904 | 0.5759 | 0.81 |
76
- | 0.1757 | 9.0 | 1017 | 0.4683 | 0.88 |
77
- | 0.0496 | 10.0 | 1130 | 0.5958 | 0.86 |
78
- | 0.0141 | 11.0 | 1243 | 0.5512 | 0.87 |
79
- | 0.0345 | 12.0 | 1356 | 0.6297 | 0.86 |
80
- | 0.0079 | 13.0 | 1469 | 0.6009 | 0.89 |
81
- | 0.0072 | 14.0 | 1582 | 0.6069 | 0.9 |
82
- | 0.007 | 15.0 | 1695 | 0.6062 | 0.9 |
83
 
84
 
85
  ### Framework versions
86
 
87
- - Transformers 4.35.0.dev0
88
- - Pytorch 2.0.1+cu118
89
- - Datasets 2.14.5
90
- - Tokenizers 0.14.0
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.81
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: 0.6504
36
+ - Accuracy: 0.81
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 2e-05
56
  - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
 
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
  - num_epochs: 15
63
+ - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.2428 | 1.0 | 113 | 2.1981 | 0.35 |
70
+ | 1.7527 | 2.0 | 226 | 1.7611 | 0.55 |
71
+ | 1.6002 | 3.0 | 339 | 1.4516 | 0.65 |
72
+ | 1.2101 | 4.0 | 452 | 1.2245 | 0.7 |
73
+ | 1.1006 | 5.0 | 565 | 1.0758 | 0.73 |
74
+ | 0.9583 | 6.0 | 678 | 0.9477 | 0.76 |
75
+ | 0.8705 | 7.0 | 791 | 0.8907 | 0.77 |
76
+ | 0.6892 | 8.0 | 904 | 0.8438 | 0.75 |
77
+ | 0.6141 | 9.0 | 1017 | 0.7574 | 0.79 |
78
+ | 0.5614 | 10.0 | 1130 | 0.7300 | 0.81 |
79
+ | 0.5347 | 11.0 | 1243 | 0.6830 | 0.8 |
80
+ | 0.5106 | 12.0 | 1356 | 0.7286 | 0.81 |
81
+ | 0.4662 | 13.0 | 1469 | 0.6701 | 0.8 |
82
+ | 0.6223 | 14.0 | 1582 | 0.6728 | 0.8 |
83
+ | 0.3604 | 15.0 | 1695 | 0.6504 | 0.81 |
84
 
85
 
86
  ### Framework versions
87
 
88
+ - Transformers 4.40.0
89
+ - Pytorch 2.2.1+cu121
90
+ - Datasets 2.19.0
91
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c29bcb3b5d35ac8d5099c98e9e68cc6569c82699e7eacdebe802ad58c7b57adc
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9045f06b3c0152a57e1d02a649b2b78e65a39581931a1cca5d64860c9d1f06
3
  size 94771728