Hugging Face's logo

1aurent
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1aurent commited on
Commit
66192a9
•
1 Parent(s): 6b53e06

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -14
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.83
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: 0.9268
36
- - Accuracy: 0.83
37
 
38
  ## Model description
39
 
@@ -62,22 +62,21 @@ The following hyperparameters were used during training:
62
  - lr_scheduler_type: cosine
63
  - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 10
65
- - label_smoothing_factor: 0.1
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 1.956 | 0.99 | 56 | 1.8086 | 0.5 |
72
- | 1.4192 | 2.0 | 113 | 1.3941 | 0.67 |
73
- | 1.1689 | 2.99 | 169 | 1.0402 | 0.76 |
74
- | 0.9796 | 4.0 | 226 | 0.9111 | 0.79 |
75
- | 0.7421 | 4.99 | 282 | 0.9137 | 0.85 |
76
- | 0.6455 | 6.0 | 339 | 0.9775 | 0.83 |
77
- | 0.6572 | 6.99 | 395 | 0.9103 | 0.83 |
78
- | 0.5707 | 8.0 | 452 | 0.9437 | 0.83 |
79
- | 0.5765 | 8.99 | 508 | 0.9216 | 0.84 |
80
- | 0.519 | 9.91 | 560 | 0.9268 | 0.83 |
81
 
82
 
83
  ### Framework versions
 
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
 
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: 0.5287
36
+ - Accuracy: 0.85
37
 
38
  ## Model description
39
 
 
62
  - lr_scheduler_type: cosine
63
  - lr_scheduler_warmup_ratio: 0.1
64
  - num_epochs: 10
 
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.0055 | 0.99 | 56 | 1.7312 | 0.58 |
71
+ | 1.2943 | 2.0 | 113 | 1.1415 | 0.63 |
72
+ | 0.9066 | 2.99 | 169 | 0.8956 | 0.71 |
73
+ | 0.8174 | 4.0 | 226 | 0.8152 | 0.75 |
74
+ | 0.5274 | 4.99 | 282 | 0.6256 | 0.81 |
75
+ | 0.3878 | 6.0 | 339 | 0.7913 | 0.77 |
76
+ | 0.2518 | 6.99 | 395 | 0.5656 | 0.85 |
77
+ | 0.1841 | 8.0 | 452 | 0.5490 | 0.84 |
78
+ | 0.0929 | 8.99 | 508 | 0.5192 | 0.87 |
79
+ | 0.105 | 9.91 | 560 | 0.5287 | 0.85 |
80
 
81
 
82
  ### Framework versions