update model card README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: ntu-spml/distilhubert
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -8,32 +7,19 @@ datasets:
|
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
11 |
-
- name: distilhubert-finetuned-
|
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-
|
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:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,43 +39,33 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 5e-05
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
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:
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
|
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.19 | 11.0 | 2475 | 0.9976 | 0.84 |
|
79 |
-
| 0.0013 | 12.0 | 2700 | 0.9684 | 0.83 |
|
80 |
-
| 0.0011 | 13.0 | 2925 | 0.9241 | 0.85 |
|
81 |
-
| 0.001 | 14.0 | 3150 | 0.9540 | 0.86 |
|
82 |
-
| 0.0008 | 15.0 | 3375 | 1.0849 | 0.85 |
|
83 |
-
| 0.0007 | 16.0 | 3600 | 0.9005 | 0.85 |
|
84 |
-
| 0.0007 | 17.0 | 3825 | 0.9798 | 0.84 |
|
85 |
-
| 0.0007 | 18.0 | 4050 | 1.0058 | 0.84 |
|
86 |
-
| 0.0005 | 19.0 | 4275 | 1.0524 | 0.85 |
|
87 |
-
| 0.0006 | 20.0 | 4500 | 1.0442 | 0.85 |
|
88 |
|
89 |
|
90 |
### Framework versions
|
91 |
|
92 |
-
- Transformers 4.
|
93 |
- Pytorch 2.0.1+cu117
|
94 |
- Datasets 2.13.1
|
95 |
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
+
- name: distilhubert-finetuned-gtzan
|
11 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
+
# distilhubert-finetuned-gtzan
|
18 |
|
19 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6231
|
22 |
+
- Accuracy: 0.83
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 10
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| 1.7262 | 1.0 | 113 | 1.8018 | 0.41 |
|
55 |
+
| 1.1879 | 2.0 | 226 | 1.2414 | 0.64 |
|
56 |
+
| 1.0662 | 3.0 | 339 | 0.9183 | 0.76 |
|
57 |
+
| 0.6538 | 4.0 | 452 | 0.6994 | 0.83 |
|
58 |
+
| 0.4435 | 5.0 | 565 | 0.6452 | 0.82 |
|
59 |
+
| 0.2902 | 6.0 | 678 | 0.5580 | 0.85 |
|
60 |
+
| 0.1912 | 7.0 | 791 | 0.6249 | 0.82 |
|
61 |
+
| 0.2514 | 8.0 | 904 | 0.6166 | 0.83 |
|
62 |
+
| 0.1347 | 9.0 | 1017 | 0.6010 | 0.84 |
|
63 |
+
| 0.2313 | 10.0 | 1130 | 0.6231 | 0.83 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
+
- Transformers 4.30.2
|
69 |
- Pytorch 2.0.1+cu117
|
70 |
- Datasets 2.13.1
|
71 |
- Tokenizers 0.13.3
|