Hugging Face's logo

arroyadr
/
wav2vec2-base-finetuned-gtzan

Audio Classification
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
arroyadr commited on
Commit
30317b5
•
1 Parent(s): 7b4eb62

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -13
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5989
36
  - Accuracy: 0.85
37
 
38
  ## Model description
@@ -52,29 +52,30 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 3e-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
- - num_epochs: 10
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 2.0398 | 1.0 | 113 | 1.9342 | 0.37 |
69
- | 1.5814 | 2.0 | 226 | 1.6164 | 0.59 |
70
- | 1.082 | 3.0 | 339 | 1.3515 | 0.62 |
71
- | 1.1223 | 4.0 | 452 | 1.0876 | 0.71 |
72
- | 0.6871 | 5.0 | 565 | 0.9143 | 0.8 |
73
- | 0.5697 | 6.0 | 678 | 0.9288 | 0.78 |
74
- | 0.6816 | 7.0 | 791 | 0.6928 | 0.83 |
75
- | 0.2974 | 8.0 | 904 | 0.6669 | 0.82 |
76
- | 0.4022 | 9.0 | 1017 | 0.5819 | 0.86 |
77
- | 0.223 | 10.0 | 1130 | 0.5989 | 0.85 |
 
78
 
79
 
80
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6459
36
  - Accuracy: 0.85
37
 
38
  ## Model description
 
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
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
+ - num_epochs: 11
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 2.0912 | 1.0 | 113 | 1.9840 | 0.33 |
69
+ | 1.7391 | 2.0 | 226 | 1.6205 | 0.57 |
70
+ | 1.3242 | 3.0 | 339 | 1.3338 | 0.61 |
71
+ | 1.1953 | 4.0 | 452 | 1.1904 | 0.68 |
72
+ | 0.8983 | 5.0 | 565 | 1.0357 | 0.75 |
73
+ | 0.8686 | 6.0 | 678 | 0.9569 | 0.78 |
74
+ | 0.84 | 7.0 | 791 | 0.7681 | 0.8 |
75
+ | 0.5776 | 8.0 | 904 | 0.6968 | 0.84 |
76
+ | 0.5186 | 9.0 | 1017 | 0.6541 | 0.86 |
77
+ | 0.3765 | 10.0 | 1130 | 0.6743 | 0.85 |
78
+ | 0.3671 | 11.0 | 1243 | 0.6459 | 0.85 |
79
 
80
 
81
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d50c6859714bda13dedfa25b78d5b549a3b7e7b31a2a3d494b4f860efe5cebf7
3
  size 378358633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939753ebb49ce9fe3174b4520f37b8c114ee5a0f48e117a7ada6a9d410068bbb
3
  size 378358633