Commit
•
230cff3
1
Parent(s):
c5c7bd5
End of training
Browse files- README.md +96 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-gtzanVD
|
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: 0.9839786381842457
|
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-gtzanVD
|
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: 0.1334
|
36 |
+
- Accuracy: 0.9840
|
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: 20
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
69 |
+
| 0.3554 | 1.0 | 842 | 0.1898 | 0.9439 |
|
70 |
+
| 0.1136 | 2.0 | 1684 | 0.1657 | 0.9626 |
|
71 |
+
| 0.1571 | 3.0 | 2526 | 0.1132 | 0.9693 |
|
72 |
+
| 0.0004 | 4.0 | 3368 | 0.1235 | 0.9786 |
|
73 |
+
| 0.0011 | 5.0 | 4210 | 0.1555 | 0.9680 |
|
74 |
+
| 0.0001 | 6.0 | 5052 | 0.3138 | 0.9493 |
|
75 |
+
| 0.0001 | 7.0 | 5894 | 0.1825 | 0.9680 |
|
76 |
+
| 0.0001 | 8.0 | 6736 | 0.1982 | 0.9706 |
|
77 |
+
| 0.0001 | 9.0 | 7578 | 0.1690 | 0.9693 |
|
78 |
+
| 0.3166 | 10.0 | 8420 | 0.1487 | 0.9733 |
|
79 |
+
| 0.0 | 11.0 | 9262 | 0.2615 | 0.9680 |
|
80 |
+
| 0.0 | 12.0 | 10104 | 0.1536 | 0.9800 |
|
81 |
+
| 0.0001 | 13.0 | 10946 | 0.5478 | 0.9399 |
|
82 |
+
| 0.0 | 14.0 | 11788 | 0.1334 | 0.9840 |
|
83 |
+
| 0.0 | 15.0 | 12630 | 0.1270 | 0.9746 |
|
84 |
+
| 0.0 | 16.0 | 13472 | 0.1053 | 0.9840 |
|
85 |
+
| 0.0 | 17.0 | 14314 | 0.1181 | 0.9813 |
|
86 |
+
| 0.0 | 18.0 | 15156 | 0.1165 | 0.9826 |
|
87 |
+
| 0.0 | 19.0 | 15998 | 0.1191 | 0.9826 |
|
88 |
+
| 0.0 | 20.0 | 16840 | 0.1188 | 0.9826 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.39.3
|
94 |
+
- Pytorch 2.2.2+cu121
|
95 |
+
- Datasets 2.18.0
|
96 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94763496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75c73eb8e5021c0f92324f64bdf25bdd588d4b371e20ec71529d3e337c0ea5d8
|
3 |
size 94763496
|