Hugging Face's logo

NathanClonts
/
wav2vec2-base-finetuned-gtzan

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
NathanClonts commited on
Commit
339885d
•
1 Parent(s): 94f1d7a

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.84
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 [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: 0.6933
36
- - Accuracy: 0.84
37
 
38
  ## Model description
39
 
@@ -53,33 +53,36 @@ More information needed
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
  - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 16
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 12
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | 2.1735 | 0.99 | 56 | 2.1378 | 0.24 |
72
- | 1.7104 | 2.0 | 113 | 1.7187 | 0.52 |
73
- | 1.3864 | 2.99 | 169 | 1.5629 | 0.53 |
74
- | 1.1797 | 4.0 | 226 | 1.4349 | 0.62 |
75
- | 1.0675 | 4.99 | 282 | 1.0705 | 0.74 |
76
- | 0.9568 | 6.0 | 339 | 1.0412 | 0.74 |
77
- | 0.7465 | 6.99 | 395 | 0.8219 | 0.84 |
78
- | 0.6917 | 8.0 | 452 | 0.8743 | 0.78 |
79
- | 0.4634 | 8.99 | 508 | 0.8266 | 0.81 |
80
- | 0.4757 | 10.0 | 565 | 0.7233 | 0.86 |
81
- | 0.4341 | 10.99 | 621 | 0.8024 | 0.81 |
82
- | 0.3802 | 11.89 | 672 | 0.6933 | 0.84 |
 
 
 
83
 
84
 
85
  ### Framework versions
 
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 [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: 0.7472
36
+ - Accuracy: 0.81
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 3e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 8
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 15
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
70
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
71
+ | 2.2042 | 1.0 | 112 | 0.27 | 2.1274 |
72
+ | 1.7875 | 2.0 | 225 | 0.51 | 1.6840 |
73
+ | 1.4927 | 3.0 | 337 | 0.57 | 1.3809 |
74
+ | 1.2344 | 4.0 | 450 | 0.64 | 1.2021 |
75
+ | 1.2579 | 5.0 | 562 | 0.62 | 1.1646 |
76
+ | 0.9661 | 6.0 | 675 | 0.65 | 1.0412 |
77
+ | 1.0119 | 7.0 | 787 | 0.74 | 0.8671 |
78
+ | 0.8629 | 8.0 | 900 | 0.66 | 0.9364 |
79
+ | 0.607 | 9.0 | 1012 | 0.75 | 0.8867 |
80
+ | 0.5699 | 10.0 | 1125 | 0.78 | 0.7432 |
81
+ | 0.5128 | 11.0 | 1237 | 0.76 | 0.8212 |
82
+ | 0.4203 | 12.0 | 1350 | 0.77 | 0.8128 |
83
+ | 0.348 | 13.0 | 1462 | 0.81 | 0.7472 |
84
+ | 0.3869 | 14.0 | 1575 | 0.8 | 0.7456 |
85
+ | 0.2129 | 14.93 | 1680 | 0.79 | 0.7243 |
86
 
87
 
88
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5caf0f981efa0ec26183a4482245da3167ed710bd127eedbb5ef123ab34fc385
3
  size 378310592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6657dfd19a7f8abe7fa5f9795edf87dbad8964605f70f6818c10e54b10f5008
3
  size 378310592