Commit
•
234b3a4
1
Parent(s):
bd15563
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: default
|
20 |
+
split: train
|
21 |
+
args: default
|
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
|
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 |
+
- Loss: 0.5280
|
36 |
+
- Accuracy: 0.86
|
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: 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 |
+
| 2.0395 | 1.0 | 113 | 1.8776 | 0.45 |
|
69 |
+
| 1.3755 | 2.0 | 226 | 1.3103 | 0.61 |
|
70 |
+
| 1.0674 | 3.0 | 339 | 0.9634 | 0.79 |
|
71 |
+
| 0.8273 | 4.0 | 452 | 0.8435 | 0.77 |
|
72 |
+
| 0.6761 | 5.0 | 565 | 0.6378 | 0.81 |
|
73 |
+
| 0.4143 | 6.0 | 678 | 0.5439 | 0.84 |
|
74 |
+
| 0.4146 | 7.0 | 791 | 0.5217 | 0.84 |
|
75 |
+
| 0.1978 | 8.0 | 904 | 0.5172 | 0.85 |
|
76 |
+
| 0.2495 | 9.0 | 1017 | 0.5295 | 0.84 |
|
77 |
+
| 0.1658 | 10.0 | 1130 | 0.5280 | 0.86 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.32.0.dev0
|
83 |
+
- Pytorch 2.0.1+cu118
|
84 |
+
- Datasets 2.14.4
|
85 |
+
- Tokenizers 0.13.3
|