Hugging Face's logo

mitro99
/
distilhubert-finetuned-gtzan_batch4_grad16_cosinelr

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mitro99 commited on
Commit
4a52217
•
1 Parent(s): d76b50c

End of training

Browse files
Files changed (5) hide show
  1. README.md +98 -0
  2. model.safetensors +1 -1
  3. runs/Jan12_11-59-28_DESKTOP-BM47F3J/events.out.tfevents.1705082371.DESKTOP-BM47F3J.3100.1 +2 -2
  4. runs/Jan12_13-23-19_DESKTOP-BM47F3J/events.out.tfevents.1705087404.DESKTOP-BM47F3J.38520.0 +3 -0
  5. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: ntu-spml/distilhubert
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - marsyas/gtzan
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: distilhubert-finetuned-gtzan
12
+ results:
13
+ - task:
14
+ name: Audio Classification
15
+ type: audio-classification
16
+ dataset:
17
+ name: GTZAN
18
+ type: marsyas/gtzan
19
+ config: all
20
+ split: train
21
+ args: all
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.85
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # distilhubert-finetuned-gtzan
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
+ - Accuracy: 0.85
36
+ - Loss: 0.7531
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 4
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 16
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: cosine
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 20
65
+ - mixed_precision_training: Native AMP
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
70
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
71
+ | 2.2849 | 1.0 | 14 | 0.17 | 2.2588 |
72
+ | 2.1931 | 1.99 | 28 | 0.47 | 2.0874 |
73
+ | 1.9194 | 2.99 | 42 | 0.58 | 1.8044 |
74
+ | 1.6351 | 3.98 | 56 | 0.61 | 1.5806 |
75
+ | 1.4473 | 4.98 | 70 | 0.71 | 1.3886 |
76
+ | 1.3131 | 5.97 | 84 | 0.7 | 1.2738 |
77
+ | 1.2141 | 6.97 | 98 | 0.72 | 1.1616 |
78
+ | 1.0657 | 7.96 | 112 | 0.74 | 1.1272 |
79
+ | 0.96 | 8.96 | 126 | 0.75 | 1.0251 |
80
+ | 0.8387 | 9.96 | 140 | 0.8 | 0.9364 |
81
+ | 0.8653 | 10.95 | 154 | 0.79 | 0.8858 |
82
+ | 0.7653 | 11.95 | 168 | 0.8 | 0.8233 |
83
+ | 0.7329 | 12.94 | 182 | 0.83 | 0.7982 |
84
+ | 0.675 | 13.94 | 196 | 0.81 | 0.8189 |
85
+ | 0.6174 | 14.93 | 210 | 0.82 | 0.8236 |
86
+ | 0.5714 | 16.0 | 225 | 0.82 | 0.7755 |
87
+ | 0.598 | 17.0 | 239 | 0.81 | 0.7511 |
88
+ | 0.5794 | 17.99 | 253 | 0.84 | 0.7553 |
89
+ | 0.589 | 18.99 | 267 | 0.85 | 0.7533 |
90
+ | 0.5717 | 19.91 | 280 | 0.85 | 0.7531 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.36.2
96
+ - Pytorch 2.1.1+cu121
97
+ - Datasets 2.16.1
98
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12be8f28e95a43cc201650a192773addce5ac4e1f662d514c5834a6c030c9e41
3
  size 94771728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031593efe77658b4f8ffe13605aadb9ffa278b38d183bcc3f87ae7a3b91a9220
3
  size 94771728
runs/Jan12_11-59-28_DESKTOP-BM47F3J/events.out.tfevents.1705082371.DESKTOP-BM47F3J.3100.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc60d467c4c73349613f9dbd601bee593996eb793ed48ada40f101ec3f164856
3
- size 11571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851b30d98dc2213d9267facccc56c556eb538e7668fa51eddef8904e446fe626
3
+ size 21124
runs/Jan12_13-23-19_DESKTOP-BM47F3J/events.out.tfevents.1705087404.DESKTOP-BM47F3J.38520.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5ebc6e36cf99a7b7db3b7e495bec7f47d07590b4794ec460619646f8b25310
3
+ size 6001
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92dc3fdfea875bccb9d1c63054c789931a36b4b94c7e3c3e8f271a553f25997c
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce0ed23fe7550cca8e8c43a85720905e24f1e1207b9fd646aa24c05f30dee26
3
  size 4792