End of training
Browse files- README.md +127 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-audio-course-finetuned-gtzan-v5
|
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: 0.87
|
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-audio-course-finetuned-gtzan-v5
|
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: 0.9236
|
36 |
+
- Accuracy: 0.87
|
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: 0.0001
|
56 |
+
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 16
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.7
|
64 |
+
- num_epochs: 50
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 2.2989 | 0.99 | 56 | 2.2882 | 0.11 |
|
71 |
+
| 2.2716 | 2.0 | 113 | 2.2469 | 0.31 |
|
72 |
+
| 2.1919 | 2.99 | 169 | 2.1317 | 0.4 |
|
73 |
+
| 2.0117 | 4.0 | 226 | 1.9244 | 0.53 |
|
74 |
+
| 1.7966 | 4.99 | 282 | 1.7315 | 0.65 |
|
75 |
+
| 1.6379 | 6.0 | 339 | 1.5920 | 0.59 |
|
76 |
+
| 1.4496 | 6.99 | 395 | 1.3539 | 0.71 |
|
77 |
+
| 1.3264 | 8.0 | 452 | 1.1879 | 0.7 |
|
78 |
+
| 1.0601 | 8.99 | 508 | 1.1342 | 0.7 |
|
79 |
+
| 0.9737 | 10.0 | 565 | 0.9209 | 0.79 |
|
80 |
+
| 0.7915 | 10.99 | 621 | 0.8768 | 0.74 |
|
81 |
+
| 0.6432 | 12.0 | 678 | 0.8060 | 0.8 |
|
82 |
+
| 0.5217 | 12.99 | 734 | 0.6562 | 0.85 |
|
83 |
+
| 0.3335 | 14.0 | 791 | 0.7744 | 0.76 |
|
84 |
+
| 0.2866 | 14.99 | 847 | 0.6969 | 0.82 |
|
85 |
+
| 0.1425 | 16.0 | 904 | 0.6378 | 0.82 |
|
86 |
+
| 0.1278 | 16.99 | 960 | 0.6972 | 0.82 |
|
87 |
+
| 0.0706 | 18.0 | 1017 | 0.7328 | 0.84 |
|
88 |
+
| 0.0301 | 18.99 | 1073 | 0.9245 | 0.76 |
|
89 |
+
| 0.0379 | 20.0 | 1130 | 0.8437 | 0.85 |
|
90 |
+
| 0.0147 | 20.99 | 1186 | 0.7489 | 0.83 |
|
91 |
+
| 0.0067 | 22.0 | 1243 | 0.8975 | 0.83 |
|
92 |
+
| 0.0049 | 22.99 | 1299 | 1.1788 | 0.81 |
|
93 |
+
| 0.0038 | 24.0 | 1356 | 1.1146 | 0.81 |
|
94 |
+
| 0.0028 | 24.99 | 1412 | 1.0270 | 0.85 |
|
95 |
+
| 0.0027 | 26.0 | 1469 | 1.0634 | 0.83 |
|
96 |
+
| 0.0024 | 26.99 | 1525 | 1.0220 | 0.84 |
|
97 |
+
| 0.0023 | 28.0 | 1582 | 1.0282 | 0.83 |
|
98 |
+
| 0.0487 | 28.99 | 1638 | 1.0735 | 0.82 |
|
99 |
+
| 0.0458 | 30.0 | 1695 | 1.1198 | 0.82 |
|
100 |
+
| 0.2453 | 30.99 | 1751 | 1.1154 | 0.81 |
|
101 |
+
| 0.0552 | 32.0 | 1808 | 1.1630 | 0.79 |
|
102 |
+
| 0.1202 | 32.99 | 1864 | 1.2746 | 0.81 |
|
103 |
+
| 0.2709 | 34.0 | 1921 | 1.3797 | 0.79 |
|
104 |
+
| 0.275 | 34.99 | 1977 | 1.5372 | 0.75 |
|
105 |
+
| 0.1268 | 36.0 | 2034 | 0.8140 | 0.86 |
|
106 |
+
| 0.1582 | 36.99 | 2090 | 1.4153 | 0.77 |
|
107 |
+
| 0.0054 | 38.0 | 2147 | 1.3796 | 0.79 |
|
108 |
+
| 0.0299 | 38.99 | 2203 | 1.3653 | 0.78 |
|
109 |
+
| 0.0199 | 40.0 | 2260 | 0.9987 | 0.87 |
|
110 |
+
| 0.0021 | 40.99 | 2316 | 1.0689 | 0.84 |
|
111 |
+
| 0.0007 | 42.0 | 2373 | 1.0383 | 0.85 |
|
112 |
+
| 0.0006 | 42.99 | 2429 | 1.0493 | 0.84 |
|
113 |
+
| 0.0006 | 44.0 | 2486 | 1.0744 | 0.85 |
|
114 |
+
| 0.0005 | 44.99 | 2542 | 0.9151 | 0.86 |
|
115 |
+
| 0.0004 | 46.0 | 2599 | 0.8946 | 0.87 |
|
116 |
+
| 0.01 | 46.99 | 2655 | 0.8960 | 0.88 |
|
117 |
+
| 0.0073 | 48.0 | 2712 | 0.9485 | 0.87 |
|
118 |
+
| 0.0004 | 48.99 | 2768 | 0.9247 | 0.87 |
|
119 |
+
| 0.0004 | 49.56 | 2800 | 0.9236 | 0.87 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.32.1
|
125 |
+
- Pytorch 2.0.1+cu117
|
126 |
+
- Datasets 2.14.4
|
127 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94783376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:747b1a06dea76b94b9d0681824093195d2a3e897ba1ff754f3c6c16c1cabecc2
|
3 |
size 94783376
|