Hugging Face's logo

atuaans
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Model card Files Metrics Community
atuaans commited on
Commit
2b38410
·
verified ·
1 Parent(s): 259878e

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -20
  2. model.safetensors +1 -1
  3. runs/Mar03_05-10-00_8d5bb58652ed/events.out.tfevents.1740978603.8d5bb58652ed.381.1 +2 -2
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.84
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.7633
37
- - Accuracy: 0.84
38
 
39
  ## Model description
40
 
@@ -60,33 +60,28 @@ The following hyperparameters were used during training:
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 15
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0856 | 1.0 | 113 | 1.9958 | 0.55 |
71
- | 1.3505 | 2.0 | 226 | 1.3490 | 0.66 |
72
- | 1.1144 | 3.0 | 339 | 1.1364 | 0.71 |
73
- | 0.6962 | 4.0 | 452 | 0.8410 | 0.74 |
74
- | 0.5305 | 5.0 | 565 | 0.6694 | 0.82 |
75
- | 0.4263 | 6.0 | 678 | 0.5555 | 0.85 |
76
- | 0.2089 | 7.0 | 791 | 0.5021 | 0.85 |
77
- | 0.0563 | 8.0 | 904 | 0.6863 | 0.84 |
78
- | 0.0457 | 9.0 | 1017 | 0.5442 | 0.89 |
79
- | 0.0251 | 10.0 | 1130 | 0.6050 | 0.87 |
80
- | 0.0127 | 11.0 | 1243 | 0.6369 | 0.86 |
81
- | 0.0095 | 12.0 | 1356 | 0.7710 | 0.87 |
82
- | 0.0083 | 13.0 | 1469 | 0.7371 | 0.86 |
83
- | 0.0082 | 14.0 | 1582 | 0.7961 | 0.86 |
84
- | 0.008 | 15.0 | 1695 | 0.7633 | 0.84 |
85
 
86
 
87
  ### Framework versions
88
 
89
- - Transformers 4.49.0
90
  - Pytorch 2.5.1+cu124
91
  - Datasets 3.3.2
92
  - Tokenizers 0.21.0
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.87
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
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: 0.6047
37
+ - Accuracy: 0.87
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 10
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.353 | 1.0 | 113 | 1.4739 | 0.62 |
71
+ | 0.8942 | 2.0 | 226 | 1.0342 | 0.7 |
72
+ | 0.8116 | 3.0 | 339 | 0.9046 | 0.74 |
73
+ | 0.509 | 4.0 | 452 | 0.8493 | 0.75 |
74
+ | 0.3621 | 5.0 | 565 | 0.5743 | 0.83 |
75
+ | 0.1877 | 6.0 | 678 | 0.5558 | 0.83 |
76
+ | 0.1237 | 7.0 | 791 | 0.6280 | 0.81 |
77
+ | 0.0465 | 8.0 | 904 | 0.6802 | 0.83 |
78
+ | 0.0388 | 9.0 | 1017 | 0.5849 | 0.87 |
79
+ | 0.0362 | 10.0 | 1130 | 0.6047 | 0.87 |
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.48.3
85
  - Pytorch 2.5.1+cu124
86
  - Datasets 3.3.2
87
  - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d24250abc5a586fca90f5f74266cffdabb858b0f9383d87ca1c7a2c56e1c970
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28fedb23e2d9f235ee5e4a4e22f6a823cf0372d843d53e103905373783a3739
3
  size 94771728
runs/Mar03_05-10-00_8d5bb58652ed/events.out.tfevents.1740978603.8d5bb58652ed.381.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562d38fae4d2bed7caf8cfb0466f6df4f330b69c0f8d9ed044b1b35b52573681
3
- size 56770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a051b2d743ee51c82d9f293659d594a350419445e58d5570e5628950d93fc63
3
+ size 57447