Hugging Face's logo

danielgh
/
distilhubert-finetuned-gtzan

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
danielgh commited on
Commit
5360e29
•
1 Parent(s): f3c23b2

End of training

Browse files
Files changed (5) hide show
  1. README.md +26 -16
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Apr01_22-15-21_c2a2a1940cbb/events.out.tfevents.1712009725.c2a2a1940cbb.287.0 +3 -0
  5. training_args.bin +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.86
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: 0.5720
36
- - Accuracy: 0.86
37
 
38
  ## Model description
39
 
@@ -59,28 +59,38 @@ The following hyperparameters were used during training:
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
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 1.8941 | 1.0 | 113 | 1.8243 | 0.56 |
70
- | 1.1572 | 2.0 | 226 | 1.1978 | 0.7 |
71
- | 1.035 | 3.0 | 339 | 0.9851 | 0.72 |
72
- | 0.6312 | 4.0 | 452 | 0.8181 | 0.77 |
73
- | 0.5429 | 5.0 | 565 | 0.6398 | 0.83 |
74
- | 0.3732 | 6.0 | 678 | 0.5851 | 0.83 |
75
- | 0.2133 | 7.0 | 791 | 0.5662 | 0.85 |
76
- | 0.1017 | 8.0 | 904 | 0.6408 | 0.81 |
77
- | 0.1394 | 9.0 | 1017 | 0.5693 | 0.85 |
78
- | 0.0788 | 10.0 | 1130 | 0.5720 | 0.86 |
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
- - Transformers 4.38.2
84
- - Pytorch 2.2.1+cu121
85
  - Datasets 2.18.0
86
  - Tokenizers 0.15.2
 
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
 
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: 0.9399
36
+ - Accuracy: 0.83
37
 
38
  ## Model description
39
 
 
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
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 2.1679 | 1.0 | 113 | 2.0910 | 0.38 |
70
+ | 1.4665 | 2.0 | 226 | 1.4798 | 0.53 |
71
+ | 1.2128 | 3.0 | 339 | 1.1715 | 0.64 |
72
+ | 0.7499 | 4.0 | 452 | 0.9591 | 0.68 |
73
+ | 0.6869 | 5.0 | 565 | 0.8078 | 0.76 |
74
+ | 0.3399 | 6.0 | 678 | 0.7513 | 0.81 |
75
+ | 0.3071 | 7.0 | 791 | 0.6606 | 0.84 |
76
+ | 0.0791 | 8.0 | 904 | 0.6416 | 0.84 |
77
+ | 0.1047 | 9.0 | 1017 | 0.7613 | 0.82 |
78
+ | 0.0784 | 10.0 | 1130 | 0.8558 | 0.82 |
79
+ | 0.0097 | 11.0 | 1243 | 0.9087 | 0.82 |
80
+ | 0.0071 | 12.0 | 1356 | 0.9155 | 0.83 |
81
+ | 0.0052 | 13.0 | 1469 | 0.9210 | 0.85 |
82
+ | 0.0044 | 14.0 | 1582 | 0.9543 | 0.84 |
83
+ | 0.0035 | 15.0 | 1695 | 0.9726 | 0.85 |
84
+ | 0.0032 | 16.0 | 1808 | 0.9183 | 0.84 |
85
+ | 0.0029 | 17.0 | 1921 | 0.9181 | 0.83 |
86
+ | 0.0027 | 18.0 | 2034 | 0.9575 | 0.84 |
87
+ | 0.0027 | 19.0 | 2147 | 0.9427 | 0.83 |
88
+ | 0.0026 | 20.0 | 2260 | 0.9399 | 0.83 |
89
 
90
 
91
  ### Framework versions
92
 
93
+ - Transformers 4.39.2
94
+ - Pytorch 2.2.2+cu121
95
  - Datasets 2.18.0
96
  - Tokenizers 0.15.2
config.json CHANGED
@@ -90,7 +90,7 @@
90
  "num_hidden_layers": 2,
91
  "pad_token_id": 0,
92
  "torch_dtype": "float32",
93
- "transformers_version": "4.38.2",
94
  "use_weighted_layer_sum": false,
95
  "vocab_size": 32
96
  }
 
90
  "num_hidden_layers": 2,
91
  "pad_token_id": 0,
92
  "torch_dtype": "float32",
93
+ "transformers_version": "4.39.2",
94
  "use_weighted_layer_sum": false,
95
  "vocab_size": 32
96
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4711cdc3d667d562ba72bdff82cc2e2540f37abecbb61563e4536a622d04f9c2
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb20019c08e9d32588fd05c6b8fc507cb491d669d5830d82eb0f63e51c4f9b8
3
  size 94771728
runs/Apr01_22-15-21_c2a2a1940cbb/events.out.tfevents.1712009725.c2a2a1940cbb.287.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e985933d7b92a5b2baab0c285a9c72edaecd50a30ab5a1a7d067ba41c82c0c
3
+ size 107910
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44558d2af0f6c3705c9351c9d2e8537780059f2cf200a88977df3e94fa8a1db9
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c93d4b99396ad81af65d995efe5f896644310b30bf23ffbf90ed36bbde870fb1
3
+ size 4984