Hugging Face's logo

steimel64
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
steimel64 commited on
Commit
59352e2
•
1 Parent(s): fccebce

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.795
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: 0.7653
36
- - Accuracy: 0.795
37
 
38
  ## Model description
39
 
@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 12
57
  - eval_batch_size: 12
58
  - seed: 42
59
- - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_ratio: 0.1
62
  - num_epochs: 20
@@ -66,26 +66,26 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 2.2686 | 1.0 | 67 | 2.2487 | 0.31 |
70
- | 1.9958 | 2.0 | 134 | 1.9025 | 0.575 |
71
- | 1.648 | 3.0 | 201 | 1.5536 | 0.615 |
72
- | 1.3416 | 4.0 | 268 | 1.3325 | 0.64 |
73
- | 1.3047 | 5.0 | 335 | 1.1516 | 0.72 |
74
- | 0.9143 | 6.0 | 402 | 1.1127 | 0.7 |
75
- | 0.8579 | 7.0 | 469 | 0.9662 | 0.76 |
76
- | 0.6832 | 8.0 | 536 | 0.9027 | 0.765 |
77
- | 0.6911 | 9.0 | 603 | 0.8941 | 0.745 |
78
- | 0.4231 | 10.0 | 670 | 0.7967 | 0.755 |
79
- | 0.408 | 11.0 | 737 | 0.7842 | 0.795 |
80
- | 0.3304 | 12.0 | 804 | 0.7397 | 0.775 |
81
- | 0.2291 | 13.0 | 871 | 0.7237 | 0.79 |
82
- | 0.2075 | 14.0 | 938 | 0.7330 | 0.785 |
83
- | 0.2427 | 15.0 | 1005 | 0.7522 | 0.8 |
84
- | 0.1248 | 16.0 | 1072 | 0.7514 | 0.795 |
85
- | 0.0969 | 17.0 | 1139 | 0.7590 | 0.795 |
86
- | 0.0976 | 18.0 | 1206 | 0.7689 | 0.79 |
87
- | 0.0943 | 19.0 | 1273 | 0.7650 | 0.795 |
88
- | 0.0852 | 20.0 | 1340 | 0.7653 | 0.795 |
89
 
90
 
91
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.68
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: 1.0287
36
+ - Accuracy: 0.68
37
 
38
  ## Model description
39
 
 
56
  - train_batch_size: 12
57
  - eval_batch_size: 12
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: 20
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.2707 | 1.0 | 67 | 2.2547 | 0.24 |
70
+ | 1.9726 | 2.0 | 134 | 1.9286 | 0.47 |
71
+ | 1.7201 | 3.0 | 201 | 1.6220 | 0.555 |
72
+ | 1.4034 | 4.0 | 268 | 1.4356 | 0.62 |
73
+ | 1.2869 | 5.0 | 335 | 1.3000 | 0.625 |
74
+ | 1.1802 | 6.0 | 402 | 1.2106 | 0.6 |
75
+ | 0.9141 | 7.0 | 469 | 1.0985 | 0.645 |
76
+ | 0.7732 | 8.0 | 536 | 1.0355 | 0.65 |
77
+ | 0.774 | 9.0 | 603 | 1.0320 | 0.66 |
78
+ | 0.4535 | 10.0 | 670 | 0.9950 | 0.66 |
79
+ | 0.423 | 11.0 | 737 | 1.0255 | 0.655 |
80
+ | 0.3026 | 12.0 | 804 | 0.9779 | 0.675 |
81
+ | 0.3175 | 13.0 | 871 | 0.9669 | 0.66 |
82
+ | 0.2618 | 14.0 | 938 | 0.9921 | 0.655 |
83
+ | 0.2809 | 15.0 | 1005 | 1.0084 | 0.695 |
84
+ | 0.1598 | 16.0 | 1072 | 1.0141 | 0.69 |
85
+ | 0.1342 | 17.0 | 1139 | 1.0378 | 0.68 |
86
+ | 0.1156 | 18.0 | 1206 | 1.0149 | 0.675 |
87
+ | 0.1109 | 19.0 | 1273 | 1.0374 | 0.68 |
88
+ | 0.1004 | 20.0 | 1340 | 1.0287 | 0.68 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afa500baf3e69500981bb2f55bd06ed26afb1f4cdbc089427dbabd17e8417370
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2801460a3af5c10c71653bd9993b517facf049ead0e10afe703f25dd02873b7f
3
  size 94771728